Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
32817870a5 | ||
|
|
b93e41efc5 | ||
|
|
082ef8522a | ||
|
|
2e95655244 | ||
|
|
942cb9f583 | ||
|
|
8470662c54 | ||
|
|
a091c2f34f | ||
|
|
bca0fe34bc | ||
|
|
6df757006a | ||
|
|
6f70eca78e | ||
|
|
0d8a474442 | ||
|
|
8be0f04b61 | ||
|
|
d5165b36a2 | ||
|
|
a76f36bdff | ||
|
|
e9009dd47c | ||
|
|
d0b49d3c8c | ||
|
|
25f578161d | ||
|
|
ea56818a80 | ||
|
|
39ab4aae48 | ||
|
|
6cba77d3cb | ||
|
|
26375885ed | ||
|
|
544d0913e8 | ||
|
|
714b3048dc | ||
|
|
bef39f75cf | ||
|
|
0a1fa95eb4 | ||
|
|
242a28bb8f | ||
|
|
bd17d506f8 | ||
|
|
1cd6a26be3 | ||
|
|
fe75998cea | ||
|
|
9d55ffb9f6 | ||
|
|
2275004f79 | ||
|
|
914ff2b5ae | ||
|
|
01677f2670 | ||
|
|
3f9d36607a | ||
|
|
f1399aa661 | ||
|
|
a3d9d05777 | ||
|
|
bf625bf8d9 | ||
|
|
e0f0c7e0b7 | ||
|
|
a6a925667a | ||
|
|
e259016a00 | ||
|
|
471f57b8e1 | ||
|
|
3ade754ea2 | ||
|
|
661ae3cf7a | ||
|
|
f803bf3cd7 | ||
|
|
084740ad95 | ||
|
|
65eed0cc72 | ||
|
|
1e0e284d5f | ||
|
|
f0fbd0775c | ||
|
|
d25a573e8f | ||
|
|
eafe1307b8 | ||
|
|
056ae0463f | ||
|
|
b2b0fe7b99 | ||
|
|
d13042b550 | ||
|
|
cb67d97b0f | ||
|
|
0323fdc44d | ||
|
|
2b2a49c679 | ||
|
|
ed129f7c71 | ||
|
|
b90b7e4b9c |
No files matched your search
@@ -0,0 +1,59 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
pull_request:
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
rust:
|
||||
runs-on: ubuntu-24.04
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install native dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y \
|
||||
pkg-config \
|
||||
libfuse3-dev \
|
||||
libgtk-4-dev \
|
||||
libadwaita-1-dev \
|
||||
libwebkitgtk-6.0-dev \
|
||||
libsecret-1-dev \
|
||||
libdbus-1-dev
|
||||
|
||||
- name: Install minimum supported Rust
|
||||
uses: actions-rust-lang/setup-rust-toolchain@v1
|
||||
with:
|
||||
toolchain: '1.96'
|
||||
components: rustfmt, clippy
|
||||
|
||||
- uses: swatinem/rust-cache@v2
|
||||
|
||||
- name: Formatting
|
||||
run: cargo fmt --all -- --check
|
||||
|
||||
- name: Lints
|
||||
run: cargo clippy --workspace --all-targets -- -D warnings
|
||||
|
||||
- name: Unit tests
|
||||
run: cargo test --workspace --locked
|
||||
|
||||
- name: Account-free filesystem acceptance
|
||||
run: scripts/fuse-acceptance.sh --offline-only
|
||||
|
||||
- name: Acceptance runner safety guard
|
||||
run: |
|
||||
if scripts/fuse-acceptance.sh /tmp >acceptance.out 2>&1; then
|
||||
echo "runner unexpectedly accepted a non-FUSE path"
|
||||
exit 1
|
||||
fi
|
||||
grep -q "refusing primary non-FUSE path" acceptance.out
|
||||
|
||||
# Real Proton credentials and /dev/fuse deliberately do not run on pull
|
||||
# requests. Follow docs/TESTING.md on a dedicated test-account runner.
|
||||
@@ -26,6 +26,7 @@ jobs:
|
||||
libfuse3-dev \
|
||||
libgtk-4-dev \
|
||||
libadwaita-1-dev \
|
||||
libwebkitgtk-6.0-dev \
|
||||
libsecret-1-dev \
|
||||
libdbus-1-dev \
|
||||
desktop-file-utils \
|
||||
@@ -34,11 +35,29 @@ jobs:
|
||||
- name: Set up Rust
|
||||
uses: actions-rust-lang/setup-rust-toolchain@v1
|
||||
with:
|
||||
toolchain: stable
|
||||
toolchain: '1.96'
|
||||
components: rustfmt, clippy
|
||||
|
||||
- name: Cache Cargo target
|
||||
uses: swatinem/rust-cache@v2
|
||||
|
||||
- name: Verify tag and manifest versions
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
shell: bash
|
||||
run: |
|
||||
tag_version="${GITHUB_REF_NAME#v}"
|
||||
manifest_version="$(sed -n 's/^version = "\([^"]*\)"/\1/p' Cargo.toml | head -n1)"
|
||||
pkgbuild_version="$(sed -n 's/^pkgver=//p' packaging/PKGBUILD | head -n1)"
|
||||
test "$tag_version" = "$manifest_version"
|
||||
test "$tag_version" = "$pkgbuild_version"
|
||||
|
||||
- name: Release quality gates
|
||||
run: |
|
||||
cargo fmt --all -- --check
|
||||
cargo clippy --workspace --all-targets -- -D warnings
|
||||
cargo test --workspace --locked
|
||||
scripts/fuse-acceptance.sh --offline-only
|
||||
|
||||
- name: Build release binaries
|
||||
run: |
|
||||
cargo build --release --locked
|
||||
@@ -75,6 +94,8 @@ jobs:
|
||||
mkdir -p deb/usr/share/applications
|
||||
mkdir -p deb/usr/share/icons/hicolor/scalable/apps
|
||||
mkdir -p deb/usr/share/licenses/proton-drive-linux
|
||||
mkdir -p deb/usr/lib/systemd/user
|
||||
mkdir -p deb/etc/xdg/autostart
|
||||
|
||||
# Copy binaries
|
||||
cp target/release/pdfs deb/usr/bin/
|
||||
@@ -84,7 +105,9 @@ jobs:
|
||||
|
||||
# Copy desktop integration files
|
||||
cp packaging/io.narl.proton-drive-linux.desktop deb/usr/share/applications/
|
||||
cp packaging/io.narl.proton-drive-linux-tray.desktop deb/etc/xdg/autostart/
|
||||
cp packaging/io.narl.proton-drive-linux.svg deb/usr/share/icons/hicolor/scalable/apps/
|
||||
cp packaging/proton-drive.service deb/usr/lib/systemd/user/
|
||||
cp LICENSE deb/usr/share/licenses/proton-drive-linux/
|
||||
|
||||
# Calculate Installed-Size in KB for the control file
|
||||
@@ -98,7 +121,7 @@ jobs:
|
||||
Priority: optional
|
||||
Architecture: amd64
|
||||
Maintainer: Nils Pukropp <contact@narl.io>
|
||||
Depends: fuse3, libgtk-4-1 (>= 4.12.0), libadwaita-1-0 (>= 1.5.0), libsecret-1-0
|
||||
Depends: fuse3, libgtk-4-1 (>= 4.12.0), libadwaita-1-0 (>= 1.5.0), libsecret-1-0, libwebkitgtk-6.0-4
|
||||
Installed-Size: ${INSTALLED_SIZE}
|
||||
Description: Proton Drive client for Linux
|
||||
Proton Drive client for Linux featuring:
|
||||
@@ -120,8 +143,10 @@ jobs:
|
||||
|
||||
# Build RPM package
|
||||
rpmbuild -bb \
|
||||
--nodeps \
|
||||
--define "_topdir $PWD/rpmbuild" \
|
||||
--define "_sourcedir $PWD" \
|
||||
--define "git_dir $PWD" \
|
||||
--define "version ${RPM_VERSION}" \
|
||||
--define "_dbpath $PWD/rpmbuild/db" \
|
||||
packaging/proton-drive-linux.spec
|
||||
|
||||
@@ -3,15 +3,15 @@ resolver = "2"
|
||||
members = ["crates/pdfs-core", "crates/pdfs-fuse", "crates/pdfs-cli", "crates/pdfs-gui"]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.6.1"
|
||||
version = "1.1.1"
|
||||
edition = "2024"
|
||||
license = "MIT"
|
||||
authors = ["Nils Pukropp <contact@narl.io>"]
|
||||
rust-version = "1.96"
|
||||
|
||||
[workspace.dependencies]
|
||||
proton-sdk = { version = "0.1.10" }
|
||||
proton-drive-rs = { version = "0.1.10" }
|
||||
proton-sdk = { version = "0.2.2" }
|
||||
proton-drive-rs = { version = "0.2.2" }
|
||||
|
||||
# Internal crates.
|
||||
pdfs-core = { path = "crates/pdfs-core" }
|
||||
|
||||
@@ -6,11 +6,129 @@ A fast, unofficial Proton Drive client for Linux. This client features an advanc
|
||||
|
||||
- **Files-on-Demand (FUSE)**: Mount your Proton Drive as a virtual filesystem where files are downloaded only when opened, utilizing smart block-level caching and disk-backed writes.
|
||||
- **Command-Line Interface (CLI)**: Manage your drive, authenticate, and monitor sync status directly from the terminal.
|
||||
- **Non-Blocking GTK4 Desktop App**: Browse files, manage pins, and configure options through a modern, native GUI with a fully non-blocking asynchronous main loop.
|
||||
- **Non-Blocking GTK4 Desktop App**: Browse files, manage pins, configure options, and monitor active transfers through a modern, native GUI with a fully non-blocking asynchronous main loop.
|
||||
- **Shared Links & Invites**: Browse files shared with you by other users, and view/manage your own public shared links directly in the GUI.
|
||||
- **Local Backup (Computers)**: Sync and back up local directories (like Downloads, Documents, Pictures, etc.) directly to your Proton Drive account.
|
||||
- **System Tray Integration**: Background indicator for status monitoring, quick actions, and fast sync controls.
|
||||
- **Fuzzy Search Launcher Prompt (HUD)**: A Google Drive-style search launcher (`pdfs-prompt`) for finding and opening files or folders instantly, ideal for binding to a system-wide hotkey.
|
||||
- **Unified Search Launcher (HUD)**: A resident Google Drive-style launcher (`pdfs-prompt`) that searches Proton Drive and local files together, ranks the best matches, tolerates abbreviations and typos, and is ideal for a system-wide hotkey.
|
||||
- **Secure Credential Storage**: Integrates with the system Secret Service (GNOME Keyring, KWallet, etc.) with smart in-memory credential caching to avoid UI thread blockages.
|
||||
- **Proton Photos Support**: Access your Proton Photos timeline, view thumbnails, and download backed-up media natively (available in the GUI as a navigation tab and via the CLI).
|
||||
- **Human Verification (CAPTCHA) Recovery**: Detects sign-in gates (VPN/new IP challenges) and launches an embedded `WebKitWebView` dialog to safely complete the challenge, transparently retrying authentication with the earned token.
|
||||
- **Selective Sync (`.pdfsignore`)**: Keep build trees, dependency directories, and editor leftovers out of synced folders using gitignore-style rules.
|
||||
- **Data-Safe Offline Writes**: Durable scratch/staging files and a transactional pending queue preserve acknowledged writes across network failures and restarts.
|
||||
|
||||
## Quick Search and Media Opening
|
||||
|
||||
`pdfs-prompt` searches Drive metadata and the local home-directory index in one request. Results are ranked together rather than split by source. Matching is case-insensitive and supports exact names, prefixes, parent paths, multiple terms, punctuation-separated words, ordered abbreviations, common typos, and adjacent transpositions.
|
||||
|
||||
The prompt stays resident after its first launch, so invoking the shortcut again reuses and resets the existing window. Drive folders open from the mount. Audio and video results also open through FUSE, allowing media players to seek and request ranges without downloading the entire file first; ordinary Drive files are materialized into the local cache before opening.
|
||||
|
||||
## Selective Sync (`.pdfsignore`)
|
||||
|
||||
Two-way synced folders skip paths matched by ignore rules, so syncing a project
|
||||
directory does not upload `node_modules/`, `target/`, or `.git/`.
|
||||
|
||||
Rules come from two places, and both apply:
|
||||
|
||||
1. **Per folder** — a `.pdfsignore` file at the root of the synced folder
|
||||
(`.protonignore` also works). Gitignore syntax, including negation:
|
||||
|
||||
```gitignore
|
||||
# everything build-related
|
||||
build/
|
||||
*.log
|
||||
|
||||
# ...except this one
|
||||
!important.log
|
||||
```
|
||||
|
||||
2. **Globally** — an `ignore_patterns` list in `config.json`, applied to every
|
||||
synced folder. When unset, sensible defaults apply: `.git/`, `.hg/`, `.svn/`,
|
||||
`node_modules/`, `target/`, `.venv/`, `__pycache__/`, `*~`, `*.swp`, `*.tmp`,
|
||||
`.DS_Store`, and `Thumbs.db`.
|
||||
|
||||
```json
|
||||
{
|
||||
"ignore_patterns": ["node_modules/", "target/", "*.iso"]
|
||||
}
|
||||
```
|
||||
|
||||
Set it to `[]` to opt out of the defaults entirely.
|
||||
|
||||
Rules are re-read at the start of every sync pass, so edits take effect on the
|
||||
next pass without restarting the daemon.
|
||||
|
||||
**Ignoring is never destructive.** If a rule starts matching a file that was
|
||||
already synced, its copy on Drive is left untouched — the file simply stops
|
||||
being tracked. Removing the rule later picks the existing remote file back up
|
||||
rather than re-uploading it.
|
||||
|
||||
## Diagnostics & Maintenance
|
||||
|
||||
When something looks wrong, `pdfs diagnose` checks the installation and prints a
|
||||
report. It runs without a daemon on purpose — the state worth diagnosing is
|
||||
usually the state where the daemon will not start:
|
||||
|
||||
```console
|
||||
$ pdfs diagnose
|
||||
Paths
|
||||
[ok ] state dir: /home/you/.local/state/proton-drive-linux
|
||||
[ok ] database: /home/you/.local/state/proton-drive-linux/cache.db (170.3 MiB)
|
||||
|
||||
Account
|
||||
[ok ] keyring session: you@proton.me
|
||||
|
||||
Daemon
|
||||
[ok ] daemon responding
|
||||
[ok ] mounted at: /home/you/ProtonDrive
|
||||
[ok ] queued writes: none
|
||||
|
||||
No problems found.
|
||||
```
|
||||
|
||||
It exits non-zero if any check fails, so it works in a health-check script.
|
||||
|
||||
For the local metadata database and content cache:
|
||||
|
||||
| Command | What it does |
|
||||
|---|---|
|
||||
| `pdfs cache inspect` | Database size, reclaimable space, per-table row counts, cache usage against budget |
|
||||
| `pdfs cache inspect --deep` | Also runs SQLite's integrity check — reads every page, so it is slow on a large database |
|
||||
| `pdfs cache vacuum` | Checkpoints the write-ahead log and compacts the database |
|
||||
| `pdfs cache clear` | Deletes cached file content, keeping pinned files |
|
||||
|
||||
`vacuum` takes a write lock for its duration and needs room for a second copy of
|
||||
the database while it runs, so it is a deliberate operation rather than
|
||||
something the daemon does on a timer.
|
||||
|
||||
Before a release, run the real-kernel acceptance suite against a dedicated test
|
||||
account and mount. See [`docs/TESTING.md`](docs/TESTING.md); it includes optional
|
||||
two-mount convergence checks and confines destructive operations to a fresh
|
||||
test directory.
|
||||
|
||||
## Scripting (`--json`)
|
||||
|
||||
Query commands accept a global `--json` flag and emit machine-readable output:
|
||||
|
||||
```console
|
||||
$ pdfs --json sync list | jq '.items[] | select(.state != "idle") | .local_path'
|
||||
$ pdfs --json cache inspect | jq '.db_reclaimable_bytes'
|
||||
$ pdfs --json status | jq -r '.mount.mountpoint'
|
||||
```
|
||||
|
||||
Supported on `status`, `ls`, `pins`, `sync list`, `devices list`, `transfers`,
|
||||
`activity`, and `cache inspect`. Commands that perform an action keep their
|
||||
human output — a script that needs to know whether one worked has the exit code.
|
||||
|
||||
Two things worth relying on:
|
||||
|
||||
- **The payload is unwrapped.** Output is `{"items": […]}`, not the daemon's
|
||||
internal `{"SyncFolders": {"items": […]}}`, so scripts never name an internal
|
||||
variant.
|
||||
- **Errors still fail.** A daemon-side error prints its JSON body (with a
|
||||
machine-readable `kind`) on stdout *and* exits non-zero, so `set -e` and
|
||||
`if pdfs …` behave as expected rather than treating a failed lookup as
|
||||
success.
|
||||
|
||||
## Performance & Caching
|
||||
|
||||
@@ -20,6 +138,19 @@ The client includes several optimizations designed for high efficiency, a low me
|
||||
- **Disk-Backed Writes**: Large file writes are staged on disk in temporary scratch files (rather than fully buffered in RAM) and track modified byte intervals. Only the unedited remote segments are fetched at commit time, keeping memory usage minimal.
|
||||
- **Non-Blocking GTK4 Loop**: To prevent UI freezes, all synchronous D-Bus credential checks, control socket requests, and cache usage calculations are offloaded to background worker threads or fetched asynchronously.
|
||||
- **Flicker-Free UI Rendering**: The GTK4 application performs differential rendering of the pins list, only modifying list rows when the list content changes, preserving the user's scroll position and widget focus.
|
||||
- **Durable Staging**: Scratch metadata and staged writes are synced and atomically published before an upload is acknowledged locally. Rapid revisions supersede pending work transactionally.
|
||||
|
||||
## Filesystem Safety
|
||||
|
||||
Version 1.0 strengthens the boundaries around local-only data and destructive reconciliation:
|
||||
|
||||
- Truncate composes with queued revisions, preserving the authoritative prefix and correct zero-filled growth.
|
||||
- Combined move-and-rename operations are queued durably and tolerate partially completed remote state.
|
||||
- Session tombstones prevent successfully unlinked entries from reappearing through eventually consistent listings.
|
||||
- Names are valid UTF-8 and no longer than Linux's 255-byte component limit.
|
||||
- Incomplete mirror scans are non-destructive, and total-wipe protection covers every non-empty baseline.
|
||||
- Failed conflict preservation, local deletion, or staging publication does not settle a new baseline or discard the only local copy.
|
||||
- State, cache, and config directories must be real, current-user-owned `0700` directories; control sockets are `0600`.
|
||||
|
||||
|
||||
## Screenshots
|
||||
@@ -32,11 +163,16 @@ The client includes several optimizations designed for high efficiency, a low me
|
||||
<td align="center" width="50%"><img src="images/files.png" alt="Files Browser" width="100%"><br><sub><b>Files Browser</b></sub></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center" width="50%"><img src="images/photos.png" alt="Photos Timeline" width="100%"><br><sub><b>Photos Timeline</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/prompt.png" alt="Search Launcher Prompt" width="100%"><br><sub><b>Search Launcher Prompt</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/shared.png" alt="Shared Links" width="100%"><br><sub><b>Shared Links</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/shared_with_me.png" alt="Shared with me" width="100%"><br><sub><b>Shared with me</b></sub></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center" colspan="2"><img src="images/settings.png" alt="Settings" width="50%"><br><sub><b>Settings</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/computers.png" alt="Local Backups (Computers)" width="100%"><br><sub><b>Local Backups (Computers)</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/photos.png" alt="Photos Timeline" width="100%"><br><sub><b>Photos Timeline</b></sub></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center" width="50%"><img src="images/prompt.png" alt="Search Launcher Prompt" width="100%"><br><sub><b>Search Launcher Prompt</b></sub></td>
|
||||
<td align="center" width="50%"><img src="images/settings.png" alt="Settings" width="100%"><br><sub><b>Settings</b></sub></td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
@@ -54,13 +190,30 @@ sudo apt-get install -y \
|
||||
libfuse3-dev \
|
||||
libgtk-4-dev \
|
||||
libadwaita-1-dev \
|
||||
libwebkitgtk-6.0-dev \
|
||||
libsecret-1-dev \
|
||||
libdbus-1-dev
|
||||
```
|
||||
|
||||
### Arch Linux
|
||||
```bash
|
||||
sudo pacman -S --needed pkgconf fuse3 gtk4 libadwaita libsecret dbus
|
||||
sudo pacman -S --needed pkgconf fuse3 gtk4 libadwaita libsecret dbus webkitgtk-6.0
|
||||
```
|
||||
|
||||
### Fedora (44+)
|
||||
```bash
|
||||
sudo dnf install -y \
|
||||
pkgconf-pkg-config fuse3-devel gtk4-devel libadwaita-devel \
|
||||
webkitgtk6.0-devel libsecret-devel dbus-devel glib2-devel cargo rust
|
||||
```
|
||||
|
||||
Runtime extras (pick your desktop):
|
||||
```bash
|
||||
# GNOME — keyring + tray (AppIndicator)
|
||||
sudo dnf install -y gnome-keyring gnome-shell-extension-appindicator xdg-utils
|
||||
|
||||
# KDE Plasma — KWallet (Secret Service); tray works via built-in SNI
|
||||
sudo dnf install -y kwallet xdg-utils
|
||||
```
|
||||
|
||||
---
|
||||
@@ -101,6 +254,20 @@ A local `PKGBUILD` is available under the `packaging/` directory. You can build
|
||||
cd packaging && makepkg -fi
|
||||
```
|
||||
|
||||
### 3. Fedora (local RPM)
|
||||
A local `.spec` is available under `packaging/`. From the repository root:
|
||||
```bash
|
||||
sudo dnf install -y rpm-build
|
||||
rpmbuild -bb packaging/proton-drive-linux.spec \
|
||||
--define "git_dir $PWD" \
|
||||
--define "_rpmdir $PWD/packaging/out" \
|
||||
--define "_builddir $PWD/packaging/build" \
|
||||
--define "_sourcedir $PWD" \
|
||||
--define "_specdir $PWD/packaging" \
|
||||
--define "_srcrpmdir $PWD/packaging/out"
|
||||
sudo dnf install packaging/out/x86_64/proton-drive-linux-*.rpm
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Automated Releases (CI/CD)
|
||||
@@ -111,15 +278,18 @@ This project has a GitHub Actions CI workflow configured under `.github/workflow
|
||||
1. **Triggers**:
|
||||
- Pushing a git tag matching `v*` (e.g. `git tag v0.1.0 && git push origin v0.1.0`).
|
||||
- Manual runs via the **Actions** tab in GitHub (**workflow_dispatch**).
|
||||
2. **Build Process**:
|
||||
2. **Quality Gates and Build Process**:
|
||||
- For tagged builds, verifies that the tag, workspace version, and `packaging/PKGBUILD` version agree.
|
||||
- Runs `cargo fmt`, Clippy with warnings denied, the locked workspace test suite, and the account-free FUSE acceptance contract.
|
||||
- Spawns an Ubuntu runner and installs GTK4, Libadwaita, FUSE3, and Secret Service packages.
|
||||
- Sets up the Rust compiler and caches build targets to speed up runs.
|
||||
- Compiles the workspace members in release mode.
|
||||
3. **Artifact Packaging**:
|
||||
- Generates a `.tar.gz` containing the raw binaries (`pdfs`, `pdfs-app`, `pdfs-tray`, `pdfs-prompt`).
|
||||
- Packs them into a Debian package (`.deb`).
|
||||
- Packs them into Debian (`.deb`) and Fedora (`.rpm`) packages.
|
||||
- Includes the systemd user service and tray autostart entry in the Debian package.
|
||||
4. **Publishing**:
|
||||
- Creates a GitHub Release matching the pushed tag and uploads the `.deb` and `.tar.gz` packages as release assets.
|
||||
- Creates a GitHub Release matching the pushed tag and uploads the `.deb`, `.rpm`, and `.tar.gz` packages as release assets.
|
||||
- For manual runs, compiles and exposes the packages as workflow run artifacts for testing.
|
||||
|
||||
---
|
||||
|
||||
@@ -21,3 +21,4 @@ sha2.workspace = true
|
||||
rusqlite.workspace = true
|
||||
keyring.workspace = true
|
||||
parking_lot.workspace = true
|
||||
libc.workspace = true
|
||||
@@ -8,6 +8,7 @@
|
||||
|
||||
use keyring::Entry;
|
||||
use proton_drive_rs::{KeySalt, ProtonDriveClient};
|
||||
use proton_sdk::api::{HumanVerification, HumanVerificationCredential};
|
||||
use proton_sdk::config::ProtonClientConfiguration;
|
||||
use proton_sdk::session::{PasswordMode, ProtonApiSession, ResumeParameters};
|
||||
use serde::{Deserialize, Serialize};
|
||||
@@ -84,14 +85,68 @@ fn keyring_entry() -> Result<Entry> {
|
||||
/// Run an interactive SRP + (optional) 2FA login and persist the session.
|
||||
///
|
||||
/// `get_totp` is only invoked when the account requires a second factor, so
|
||||
/// callers can defer prompting until it is actually needed.
|
||||
/// callers can defer prompting until it is actually needed. It may be called
|
||||
/// more than once — [`login_interactive`] re-runs the whole login after human
|
||||
/// verification, and a 2FA account needs a fresh code on that second attempt.
|
||||
///
|
||||
/// A gated login fails with [`Error::HumanVerificationRequired`]; a front-end
|
||||
/// that can present the challenge should use [`login_interactive`] instead.
|
||||
pub async fn login(
|
||||
username: &str,
|
||||
password: &str,
|
||||
get_totp: impl FnOnce() -> Result<String>,
|
||||
get_totp: impl Fn() -> Result<String>,
|
||||
) -> Result<()> {
|
||||
let mut session =
|
||||
ProtonApiSession::begin(client_config(), username, password.as_bytes()).await?;
|
||||
login_verified(username, password, None, get_totp).await
|
||||
}
|
||||
|
||||
/// [`login`], able to answer a human-verification gate rather than fail on it.
|
||||
///
|
||||
/// `get_hv` is invoked only when the API actually gates the login, mirroring how
|
||||
/// `get_totp` is only invoked for accounts with a second factor: neither costs a
|
||||
/// prompt the user did not need. It receives the challenge and returns the token
|
||||
/// the user earned by solving it.
|
||||
///
|
||||
/// The retry lives here rather than in the front-ends because the recovery is
|
||||
/// not a UI concern: the gated attempt burned its SRP handshake, so the login
|
||||
/// has to start over with the credential attached, and every front-end would
|
||||
/// otherwise have to know that. Gating the *retry* is not handled — a second
|
||||
/// challenge in a row means the token was rejected, and looping on it would trap
|
||||
/// the user in a CAPTCHA that never clears.
|
||||
pub async fn login_interactive(
|
||||
username: &str,
|
||||
password: &str,
|
||||
get_totp: impl Fn() -> Result<String>,
|
||||
get_hv: impl FnOnce(HumanVerification) -> Result<HumanVerificationCredential>,
|
||||
) -> Result<()> {
|
||||
match login_verified(username, password, None, &get_totp).await {
|
||||
Err(Error::HumanVerificationRequired(hv)) => {
|
||||
let credential = get_hv(*hv)?;
|
||||
login_verified(username, password, Some(&credential), &get_totp).await
|
||||
}
|
||||
other => other,
|
||||
}
|
||||
}
|
||||
|
||||
/// [`login`], replaying a human-verification token the user has already earned.
|
||||
///
|
||||
/// A gated login fails with [`Error::HumanVerificationRequired`] carrying the
|
||||
/// challenge. The front-end presents it, collects the solved token, and calls
|
||||
/// this. The login starts over from the SRP handshake rather than resuming: the
|
||||
/// gated attempt never got a session, and its `srp_session` is spent.
|
||||
pub async fn login_verified(
|
||||
username: &str,
|
||||
password: &str,
|
||||
verification: Option<&HumanVerificationCredential>,
|
||||
get_totp: impl Fn() -> Result<String>,
|
||||
) -> Result<()> {
|
||||
let mut session = ProtonApiSession::begin_verified(
|
||||
client_config(),
|
||||
username,
|
||||
password.as_bytes(),
|
||||
verification,
|
||||
)
|
||||
.await
|
||||
.map_err(classify_verification_gate)?;
|
||||
|
||||
if session.is_waiting_for_second_factor() {
|
||||
let code = get_totp()?;
|
||||
@@ -110,6 +165,23 @@ pub async fn login(
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Lift a human-verification gate out of the generic API error into the typed
|
||||
/// variant a front-end can act on.
|
||||
///
|
||||
/// Only a gate that names a solvable method is converted. A `9001` with no
|
||||
/// `Details`, or one offering only `email`/`sms`, stays a plain API error:
|
||||
/// promoting it would send the UI to open a verification page it cannot
|
||||
/// complete, which reads to the user as a hang rather than a refusal.
|
||||
fn classify_verification_gate(e: proton_sdk::error::ProtonError) -> Error {
|
||||
let proton_sdk::error::ProtonError::Api(api) = &e else {
|
||||
return e.into();
|
||||
};
|
||||
match api.human_verification() {
|
||||
Some(hv) if hv.supports_captcha() => Error::HumanVerificationRequired(Box::new(hv)),
|
||||
_ => e.into(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Persist the session's current tokens, mailbox password and key salts.
|
||||
pub async fn save(
|
||||
session: &ProtonApiSession,
|
||||
|
||||
@@ -150,13 +150,23 @@ pub struct StagedWrite {
|
||||
pub based_on: Option<Baseline>,
|
||||
}
|
||||
|
||||
/// The identity of a remote revision, as far as we can observe it: a file whose
|
||||
/// size and mtime both still match the ones a queued change was made against has
|
||||
/// not been rewritten by anyone else in the meantime.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq)]
|
||||
/// The identity of a remote revision, as far as we can observe it.
|
||||
///
|
||||
/// `revision_id` is the authoritative identity when present: the server assigns a
|
||||
/// fresh id to every sealed revision, so an unchanged id proves no one rewrote
|
||||
/// the file — even when the server re-stamped its `mtime` on the *same* revision,
|
||||
/// which is the drift that used to cut spurious conflict copies (B16/B25).
|
||||
/// `mtime`/`size` remain the fallback for a baseline recorded before the id was
|
||||
/// observable, or a node read through a surface that does not carry it.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
pub struct Baseline {
|
||||
pub mtime: i64,
|
||||
pub size: u64,
|
||||
#[serde(default)]
|
||||
pub hash: Option<String>,
|
||||
/// Server revision id this change was made against (`None` if unknown).
|
||||
#[serde(default)]
|
||||
pub revision_id: Option<String>,
|
||||
}
|
||||
|
||||
/// Content cache rooted at a directory, with a sibling pin-registry file.
|
||||
@@ -239,7 +249,9 @@ impl ContentCache {
|
||||
let recovery_dir = content_dir.join("recovery");
|
||||
std::fs::create_dir_all(&recovery_dir)?;
|
||||
Self::rescue_scratch(&scratch_dir, &recovery_dir);
|
||||
let _ = std::fs::remove_dir_all(&scratch_dir);
|
||||
// A failed rescue may leave the only durable copy here. Never clear the
|
||||
// directory wholesale; discard only blobs that carry no fsync marker.
|
||||
Self::discard_unmarked_scratch(&scratch_dir);
|
||||
std::fs::create_dir_all(&scratch_dir)?;
|
||||
// Staging, by contrast, is deliberately preserved across runs.
|
||||
let staging_dir = content_dir.join("staging");
|
||||
@@ -431,7 +443,12 @@ impl ContentCache {
|
||||
// 64-char hex key with no `.`, so this appends rather than replaces.
|
||||
// `store_thumbnail` cannot use the same idiom — see the note there.
|
||||
let tmp = blob.with_extension("tmp");
|
||||
std::fs::write(&tmp, bytes)?;
|
||||
{
|
||||
let mut f = std::fs::File::create(&tmp)?;
|
||||
use std::io::Write;
|
||||
f.write_all(bytes)?;
|
||||
f.sync_all()?;
|
||||
}
|
||||
std::fs::rename(&tmp, &blob)?;
|
||||
let meta = serde_json::to_vec(&Meta { mtime, size })?;
|
||||
std::fs::write(self.meta_path(uid), meta)?;
|
||||
@@ -464,6 +481,9 @@ impl ContentCache {
|
||||
if std::fs::hard_link(src, &tmp).is_err() {
|
||||
std::fs::copy(src, &tmp)?;
|
||||
}
|
||||
if let Ok(f) = std::fs::File::open(&tmp) {
|
||||
let _ = f.sync_all();
|
||||
}
|
||||
let bytes = std::fs::metadata(&tmp)?.len();
|
||||
std::fs::rename(&tmp, &blob)?;
|
||||
let meta = serde_json::to_vec(&Meta { mtime, size })?;
|
||||
@@ -526,7 +546,12 @@ impl ContentCache {
|
||||
let tmp = self
|
||||
.block_dir
|
||||
.join(format!("{}.b{idx}.tmp", Self::key(uid)));
|
||||
std::fs::write(&tmp, bytes)?;
|
||||
{
|
||||
let mut f = std::fs::File::create(&tmp)?;
|
||||
use std::io::Write;
|
||||
f.write_all(bytes)?;
|
||||
f.sync_all()?;
|
||||
}
|
||||
std::fs::rename(&tmp, &blob)?;
|
||||
std::fs::write(
|
||||
self.block_meta(uid, idx),
|
||||
@@ -654,18 +679,24 @@ impl ContentCache {
|
||||
pub fn create_scratch(&self) -> Result<(std::fs::File, PathBuf)> {
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
static N: AtomicU64 = AtomicU64::new(0);
|
||||
let path = self.scratch_dir.join(format!(
|
||||
"w-{}-{}",
|
||||
std::process::id(),
|
||||
N.fetch_add(1, Ordering::Relaxed)
|
||||
));
|
||||
let file = std::fs::OpenOptions::new()
|
||||
.create(true)
|
||||
.truncate(true)
|
||||
.read(true)
|
||||
.write(true)
|
||||
.open(&path)?;
|
||||
Ok((file, path))
|
||||
loop {
|
||||
let path = self.scratch_dir.join(format!(
|
||||
"w-{}-{}-{}",
|
||||
std::process::id(),
|
||||
now_millis(),
|
||||
N.fetch_add(1, Ordering::Relaxed)
|
||||
));
|
||||
match std::fs::OpenOptions::new()
|
||||
.create_new(true)
|
||||
.read(true)
|
||||
.write(true)
|
||||
.open(&path)
|
||||
{
|
||||
Ok(file) => return Ok((file, path)),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => continue,
|
||||
Err(e) => return Err(e.into()),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// The sidecar path for a scratch file, holding the [`StagedWrite`] that
|
||||
@@ -694,16 +725,23 @@ impl ContentCache {
|
||||
/// have synced `scratch` first: a sidecar promising bytes that never reached
|
||||
/// the disk is worse than no sidecar.
|
||||
pub fn mark_scratch_durable(&self, scratch: &Path, meta: &StagedWrite) -> Result<()> {
|
||||
use std::io::Write as _;
|
||||
|
||||
let side = Self::scratch_sidecar(scratch);
|
||||
let tmp = side.with_extension("json.tmp");
|
||||
std::fs::write(&tmp, serde_json::to_vec(meta)?)?;
|
||||
let mut file = std::fs::OpenOptions::new()
|
||||
.write(true)
|
||||
.create(true)
|
||||
.truncate(true)
|
||||
.open(&tmp)?;
|
||||
file.write_all(&serde_json::to_vec(meta)?)?;
|
||||
file.sync_all()?;
|
||||
drop(file);
|
||||
std::fs::rename(&tmp, &side)?;
|
||||
// The rename is what publishes the sidecar; fsync the directory so the
|
||||
// rename itself survives, not just the bytes it points at.
|
||||
if let Some(dir) = side.parent()
|
||||
&& let Ok(d) = std::fs::File::open(dir)
|
||||
{
|
||||
let _ = d.sync_all();
|
||||
if let Some(dir) = side.parent() {
|
||||
std::fs::File::open(dir)?.sync_all()?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -733,14 +771,40 @@ impl ContentCache {
|
||||
continue;
|
||||
}
|
||||
let side = Self::scratch_sidecar(&blob);
|
||||
// Parsed, not merely present: an unreadable sidecar cannot drive a
|
||||
// recovery, so the blob is rubbish like any other leftover.
|
||||
if std::fs::read(&side)
|
||||
if !side.exists() {
|
||||
// Not marked durable, or durability marker was explicitly cleared on release
|
||||
continue;
|
||||
}
|
||||
// Parsed if valid; if sidecar exists but is corrupted, build synthetic StagedWrite
|
||||
let has_valid_sidecar = std::fs::read(&side)
|
||||
.ok()
|
||||
.and_then(|b| serde_json::from_slice::<StagedWrite>(&b).ok())
|
||||
.is_none()
|
||||
{
|
||||
continue;
|
||||
.is_some();
|
||||
if !has_valid_sidecar {
|
||||
if let Ok(meta) = std::fs::metadata(&blob)
|
||||
&& meta.len() > 0
|
||||
{
|
||||
let blob_name = blob
|
||||
.file_name()
|
||||
.map(|n| n.to_string_lossy().to_string())
|
||||
.unwrap_or_default();
|
||||
let synthetic = StagedWrite {
|
||||
uid: format!("recovered~{blob_name}"),
|
||||
len: meta.len(),
|
||||
base_size: meta.len(),
|
||||
base_mtime: 0,
|
||||
authored: vec![(0, meta.len())],
|
||||
complete: true,
|
||||
based_on: None,
|
||||
};
|
||||
if let Ok(data) = serde_json::to_vec(&synthetic) {
|
||||
let _ = std::fs::write(&side, data);
|
||||
} else {
|
||||
continue;
|
||||
}
|
||||
} else {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
let Some(name) = blob.file_name() else {
|
||||
continue;
|
||||
@@ -755,9 +819,53 @@ impl ContentCache {
|
||||
}
|
||||
}
|
||||
|
||||
fn discard_unmarked_scratch(scratch_dir: &Path) {
|
||||
let Ok(entries) = std::fs::read_dir(scratch_dir) else {
|
||||
return;
|
||||
};
|
||||
for entry in entries.flatten() {
|
||||
let blob = entry.path();
|
||||
if blob.extension().is_some_and(|e| e == "json") {
|
||||
continue;
|
||||
}
|
||||
if !Self::scratch_sidecar(&blob).exists() {
|
||||
let _ = std::fs::remove_file(blob);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Emergency eviction of unpinned blobs when local disk runs out of space (ENOSPC).
|
||||
pub fn emergency_evict(&self) {
|
||||
let pinned: HashSet<String> = self
|
||||
.db
|
||||
.pinned_uids()
|
||||
.unwrap_or_default()
|
||||
.iter()
|
||||
.map(|uid| Self::key_str(uid))
|
||||
.collect();
|
||||
let content_dir = self.content_dir.clone();
|
||||
// Force pool enforcement ignoring current cap check to free disk space immediately
|
||||
let Ok(list) = self.db.cache_eviction_candidates(KIND_BLOB, 10) else {
|
||||
return;
|
||||
};
|
||||
for (key, bytes) in list {
|
||||
if pinned.contains(&key) {
|
||||
continue;
|
||||
}
|
||||
let p = content_dir.join(&key);
|
||||
let m = content_dir.join(format!("{key}.meta"));
|
||||
let _ = std::fs::remove_file(&p);
|
||||
let _ = std::fs::remove_file(&m);
|
||||
let _ = self.db.cache_remove(&key);
|
||||
self.blob_bytes.fetch_sub(bytes, Ordering::Relaxed);
|
||||
break; // Evict one item at a time until space is freed
|
||||
}
|
||||
}
|
||||
|
||||
/// Writes rescued from an unclean shutdown, as `(blob, meta)` pairs for the
|
||||
/// daemon to hand to the upload queue. A blob whose sidecar did not survive
|
||||
/// the rescue is deleted here — nothing can address it.
|
||||
/// is not actionable automatically, but is retained for manual recovery:
|
||||
/// unexplained bytes are never evidence that user data is disposable.
|
||||
pub fn recovered_writes(&self) -> Vec<(PathBuf, StagedWrite)> {
|
||||
let Ok(entries) = std::fs::read_dir(&self.recovery_dir) else {
|
||||
return Vec::new();
|
||||
@@ -768,14 +876,11 @@ impl ContentCache {
|
||||
if blob.extension().is_some_and(|e| e == "json") {
|
||||
continue;
|
||||
}
|
||||
match std::fs::read(Self::scratch_sidecar(&blob))
|
||||
if let Some(meta) = std::fs::read(Self::scratch_sidecar(&blob))
|
||||
.ok()
|
||||
.and_then(|b| serde_json::from_slice::<StagedWrite>(&b).ok())
|
||||
{
|
||||
Some(meta) => out.push((blob, meta)),
|
||||
None => {
|
||||
let _ = std::fs::remove_file(&blob);
|
||||
}
|
||||
out.push((blob, meta));
|
||||
}
|
||||
}
|
||||
out
|
||||
@@ -803,6 +908,8 @@ impl ContentCache {
|
||||
/// failure here means we could not save the bytes at all, so it is reported
|
||||
/// rather than swallowed.
|
||||
pub fn stage_write(&self, meta: &StagedWrite, scratch: &Path) -> Result<PathBuf> {
|
||||
use std::io::Write as _;
|
||||
|
||||
static N: AtomicU64 = AtomicU64::new(0);
|
||||
// The uid goes in the name so a staged file can be tied back to its node
|
||||
// without a database; `/` in a uid would otherwise open a path.
|
||||
@@ -813,18 +920,32 @@ impl ContentCache {
|
||||
now_millis(),
|
||||
N.fetch_add(1, Ordering::Relaxed)
|
||||
));
|
||||
if let Err(e) = std::fs::rename(scratch, &path) {
|
||||
// Cross-device: rename cannot move it, so copy and drop the original.
|
||||
let _ = e;
|
||||
let copied = if let Err(e) = std::fs::rename(scratch, &path) {
|
||||
if e.kind() != std::io::ErrorKind::CrossesDevices {
|
||||
return Err(e.into());
|
||||
}
|
||||
std::fs::copy(scratch, &path)?;
|
||||
let _ = std::fs::remove_file(scratch);
|
||||
}
|
||||
true
|
||||
} else {
|
||||
false
|
||||
};
|
||||
std::fs::File::open(&path)?.sync_all()?;
|
||||
// Sidecar last: a staged file without one is still recoverable bytes,
|
||||
// while a sidecar without a file would describe nothing.
|
||||
std::fs::write(
|
||||
path.with_extension("json"),
|
||||
serde_json::to_vec_pretty(meta)?,
|
||||
)?;
|
||||
let side = path.with_extension("json");
|
||||
let side_tmp = path.with_extension("json.tmp");
|
||||
let mut side_file = std::fs::OpenOptions::new()
|
||||
.write(true)
|
||||
.create_new(true)
|
||||
.open(&side_tmp)?;
|
||||
side_file.write_all(&serde_json::to_vec_pretty(meta)?)?;
|
||||
side_file.sync_all()?;
|
||||
drop(side_file);
|
||||
std::fs::rename(&side_tmp, &side)?;
|
||||
std::fs::File::open(&self.staging_dir)?.sync_all()?;
|
||||
if copied {
|
||||
std::fs::remove_file(scratch)?;
|
||||
}
|
||||
Ok(path)
|
||||
}
|
||||
|
||||
@@ -1759,6 +1880,8 @@ mod tests {
|
||||
based_on: Some(Baseline {
|
||||
mtime: 100,
|
||||
size: 40,
|
||||
hash: None,
|
||||
revision_id: None,
|
||||
}),
|
||||
};
|
||||
let staged = c.stage_write(&meta, &scratch).unwrap();
|
||||
@@ -1836,6 +1959,51 @@ mod tests {
|
||||
assert!(c2.recovered_writes().is_empty(), "recovery does not repeat");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn recovery_keeps_an_orphan_blob_when_its_sidecar_is_missing() {
|
||||
let (c, dir) = cache();
|
||||
let orphan = dir.path().join("content/recovery/orphaned-user-bytes");
|
||||
std::fs::write(&orphan, b"retain me").unwrap();
|
||||
|
||||
assert!(c.recovered_writes().is_empty());
|
||||
assert_eq!(
|
||||
std::fs::read(&orphan).unwrap(),
|
||||
b"retain me",
|
||||
"metadata loss must not trigger deletion of unexplained content"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_scratch_rescue_does_not_delete_the_durable_source() {
|
||||
use std::io::Write as _;
|
||||
let dir = TempDir::new();
|
||||
let db = Arc::new(Db::open_in_memory().unwrap());
|
||||
let content = dir.path().join("content");
|
||||
let pins = dir.path().join("pins.json");
|
||||
let c = ContentCache::open(content.clone(), pins.clone(), 0, db.clone()).unwrap();
|
||||
let (mut file, scratch) = c.create_scratch().unwrap();
|
||||
file.write_all(b"durable source").unwrap();
|
||||
file.sync_all().unwrap();
|
||||
let meta = StagedWrite {
|
||||
uid: uid("rescue").to_string(),
|
||||
len: 14,
|
||||
base_size: 0,
|
||||
base_mtime: 0,
|
||||
authored: vec![(0, 14)],
|
||||
complete: true,
|
||||
based_on: None,
|
||||
};
|
||||
c.mark_scratch_durable(&scratch, &meta).unwrap();
|
||||
let blocking_destination = content.join("recovery").join(scratch.file_name().unwrap());
|
||||
std::fs::create_dir(&blocking_destination).unwrap();
|
||||
drop(file);
|
||||
drop(c);
|
||||
|
||||
let _c2 = ContentCache::open(content, pins, 0, db).unwrap();
|
||||
assert_eq!(std::fs::read(&scratch).unwrap(), b"durable source");
|
||||
assert!(ContentCache::scratch_sidecar(&scratch).exists());
|
||||
}
|
||||
|
||||
/// Releasing a write hands the bytes to staging, so the sidecar an earlier
|
||||
/// `fsync` left must not offer recovery a second, stale copy of it.
|
||||
#[test]
|
||||
|
||||
@@ -6,6 +6,7 @@ use directories::ProjectDirs;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::error::{Error, Result};
|
||||
use crate::syncignore::DEFAULT_IGNORE_PATTERNS;
|
||||
|
||||
/// Proton requires `external-drive-{name}@{semver}-{channel}` (channel ∈
|
||||
/// stable/beta/alpha); a malformed value trips the 422 anti-abuse path.
|
||||
@@ -19,6 +20,59 @@ pub const KEYRING_SERVICE: &str = "proton-drive-linux";
|
||||
/// blobs back under this; pinned files are exempt. See [`crate::cache`].
|
||||
pub const DEFAULT_CACHE_BUDGET_BYTES: u64 = 5 * 1024 * 1024 * 1024;
|
||||
|
||||
/// Environment override for [`AppConfig::resolved_conflict_sweep`]. Exists so a
|
||||
/// support case can disable the sweep without editing the config file or
|
||||
/// reinstalling — it wins over the stored setting.
|
||||
pub const CONFLICT_SWEEP_ENV: &str = "PDFS_CONFLICT_SWEEP";
|
||||
|
||||
/// What the background conflict sweep (`pdfs-fuse`'s `pdfs-conflict-sweep`
|
||||
/// thread) is allowed to do about a `(sync-conflict …)` copy it believes is a
|
||||
/// redundant duplicate.
|
||||
///
|
||||
/// Defaults to [`SweepMode::Report`]: the sweep's whole reason to exist is that
|
||||
/// the *previous* revision-identity check was wrong (B69), so the replacement is
|
||||
/// not trusted with deletion until it has a release cycle of field evidence
|
||||
/// behind it. See `docs/BUGS.md` B71.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Default)]
|
||||
#[serde(rename_all = "lowercase")]
|
||||
pub enum SweepMode {
|
||||
/// Do not run the sweep at all — the thread is never spawned.
|
||||
Off,
|
||||
/// Run, and log what it *would* remove, but never trash anything. Divergent
|
||||
/// and orphaned copies are still surfaced to the activity feed as usual.
|
||||
#[default]
|
||||
Report,
|
||||
/// Trash copies proven identical to their live sibling.
|
||||
Enforce,
|
||||
}
|
||||
|
||||
impl SweepMode {
|
||||
/// Parse an operator-supplied value ([`CONFLICT_SWEEP_ENV`] or a CLI flag).
|
||||
/// `None` for anything unrecognised, so a typo falls back to the stored
|
||||
/// setting rather than silently picking a mode the operator did not ask for.
|
||||
pub fn parse(value: &str) -> Option<Self> {
|
||||
match value.trim().to_ascii_lowercase().as_str() {
|
||||
"off" | "no" | "false" | "0" | "disabled" => Some(Self::Off),
|
||||
"report" | "dry-run" | "dryrun" | "observe" => Some(Self::Report),
|
||||
"enforce" | "on" | "yes" | "true" | "1" => Some(Self::Enforce),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether this mode is allowed to trash a duplicate.
|
||||
pub fn is_enforcing(self) -> bool {
|
||||
matches!(self, Self::Enforce)
|
||||
}
|
||||
}
|
||||
|
||||
/// Precedence for [`AppConfig::resolved_conflict_sweep`], split out from the
|
||||
/// environment read so it can be unit-tested without mutating process state.
|
||||
fn resolve_sweep_mode(env: Option<&str>, stored: Option<SweepMode>) -> SweepMode {
|
||||
env.and_then(SweepMode::parse)
|
||||
.or(stored)
|
||||
.unwrap_or_default()
|
||||
}
|
||||
|
||||
/// Configuration structure allowing the user to customize client identification headers.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone)]
|
||||
pub struct AppConfig {
|
||||
@@ -34,6 +88,24 @@ pub struct AppConfig {
|
||||
/// path here. Defaulted for configs predating the field.
|
||||
#[serde(default)]
|
||||
pub mountpoint: Option<String>,
|
||||
/// Ignore patterns (gitignore syntax) applied to every mirror sync folder,
|
||||
/// on top of each folder's own `.pdfsignore`. `None` means "use
|
||||
/// [`DEFAULT_IGNORE_PATTERNS`]"; an explicit empty list disables the
|
||||
/// defaults. Defaulted for configs predating the field.
|
||||
#[serde(default)]
|
||||
pub ignore_patterns: Option<Vec<String>>,
|
||||
/// Device uid this machine has been *adopted* into, overriding the hostname
|
||||
/// heuristic in `ensure_device`. Lives here rather than in `cache.db` so it
|
||||
/// survives a fresh install — on a new machine the DB is empty by
|
||||
/// definition, which is exactly when the pin matters. `None` means "resolve
|
||||
/// by hostname". Defaulted for configs predating the field.
|
||||
#[serde(default)]
|
||||
pub device_uid: Option<String>,
|
||||
/// What the background conflict sweep may do. `None` means "use
|
||||
/// [`SweepMode::default`]" (report-only). Defaulted for configs predating
|
||||
/// the field, and overridable at runtime via [`CONFLICT_SWEEP_ENV`].
|
||||
#[serde(default)]
|
||||
pub conflict_sweep: Option<SweepMode>,
|
||||
}
|
||||
|
||||
impl Default for AppConfig {
|
||||
@@ -43,6 +115,9 @@ impl Default for AppConfig {
|
||||
user_agent: USER_AGENT.to_string(),
|
||||
cache_budget: None,
|
||||
mountpoint: None,
|
||||
ignore_patterns: None,
|
||||
device_uid: None,
|
||||
conflict_sweep: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -53,6 +128,34 @@ impl AppConfig {
|
||||
pub fn resolved_cache_budget(&self) -> u64 {
|
||||
self.cache_budget.unwrap_or(DEFAULT_CACHE_BUDGET_BYTES)
|
||||
}
|
||||
|
||||
/// The effective conflict-sweep mode: the [`CONFLICT_SWEEP_ENV`] override if
|
||||
/// it parses, then the user's stored choice, then [`SweepMode::default`].
|
||||
///
|
||||
/// The environment wins so a support case can stop a destructive background
|
||||
/// loop without editing config or reinstalling (`docs/BUGS.md` B71). An
|
||||
/// unparseable value is ignored rather than treated as "off", so a typo
|
||||
/// cannot silently change behaviour in either direction.
|
||||
pub fn resolved_conflict_sweep(&self) -> SweepMode {
|
||||
resolve_sweep_mode(
|
||||
std::env::var(CONFLICT_SWEEP_ENV).ok().as_deref(),
|
||||
self.conflict_sweep,
|
||||
)
|
||||
}
|
||||
|
||||
/// The effective global sync ignore patterns: the user's explicit list, or
|
||||
/// [`DEFAULT_IGNORE_PATTERNS`] when unset. An explicit empty list is
|
||||
/// honoured as "no global patterns", which is why this is not a
|
||||
/// `unwrap_or_default`.
|
||||
pub fn resolved_ignore_patterns(&self) -> Vec<String> {
|
||||
match &self.ignore_patterns {
|
||||
Some(patterns) => patterns.clone(),
|
||||
None => DEFAULT_IGNORE_PATTERNS
|
||||
.iter()
|
||||
.map(|s| (*s).to_string())
|
||||
.collect(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Resolved XDG locations for state, cache, and the default mountpoint.
|
||||
@@ -75,11 +178,21 @@ impl AppDirs {
|
||||
/// Load config from disk, creating default if missing.
|
||||
pub fn load_config(&self) -> AppConfig {
|
||||
let path = self.config_path();
|
||||
if path.exists()
|
||||
&& let Ok(content) = std::fs::read_to_string(&path)
|
||||
&& let Ok(config) = serde_json::from_str::<AppConfig>(&content)
|
||||
{
|
||||
return config;
|
||||
if path.exists() {
|
||||
match std::fs::read_to_string(&path)
|
||||
.map_err(Error::from)
|
||||
.and_then(|content| {
|
||||
serde_json::from_str::<AppConfig>(&content).map_err(Error::from)
|
||||
}) {
|
||||
Ok(config) => return config,
|
||||
Err(e) => {
|
||||
// Preserve the original bytes for diagnosis/recovery. In
|
||||
// particular, never replace a truncated config with defaults
|
||||
// and silently lose mount, device, or ignore settings.
|
||||
tracing::error!(path = %path.display(), error = %e, "config is unreadable; using in-memory defaults without overwriting it");
|
||||
return AppConfig::default();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let default_config = AppConfig::default();
|
||||
@@ -95,10 +208,26 @@ impl AppDirs {
|
||||
/// cache budget or mountpoint; the daemon re-reads the file on its next mount.
|
||||
pub fn save_config(&self, config: &AppConfig) -> Result<()> {
|
||||
let path = self.config_path();
|
||||
if let Some(parent) = path.parent() {
|
||||
std::fs::create_dir_all(parent)?;
|
||||
}
|
||||
std::fs::write(&path, serde_json::to_string_pretty(config)?)?;
|
||||
let parent = path
|
||||
.parent()
|
||||
.ok_or_else(|| Error::Other("configuration path has no parent".into()))?;
|
||||
std::fs::create_dir_all(parent)?;
|
||||
let nonce = std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.map(|duration| duration.as_nanos())
|
||||
.unwrap_or(0);
|
||||
let tmp = path.with_extension(format!("json.tmp-{}-{nonce}", std::process::id()));
|
||||
use std::os::unix::fs::OpenOptionsExt as _;
|
||||
let mut file = std::fs::OpenOptions::new()
|
||||
.write(true)
|
||||
.create_new(true)
|
||||
.mode(0o600)
|
||||
.open(&tmp)?;
|
||||
use std::io::Write as _;
|
||||
file.write_all(&serde_json::to_vec_pretty(config)?)?;
|
||||
file.sync_all()?;
|
||||
std::fs::rename(&tmp, &path)?;
|
||||
std::fs::File::open(parent)?.sync_all()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -181,24 +310,41 @@ impl AppDirs {
|
||||
pub fn ensure(&self) -> Result<()> {
|
||||
for dir in [self.state_dir(), self.cache_dir()] {
|
||||
std::fs::create_dir_all(&dir)?;
|
||||
restrict_dir(&dir);
|
||||
restrict_dir(&dir)?;
|
||||
}
|
||||
let config_dir = self.dirs.config_dir().to_path_buf();
|
||||
if std::fs::create_dir_all(&config_dir).is_ok() {
|
||||
restrict_dir(&config_dir);
|
||||
}
|
||||
std::fs::create_dir_all(&config_dir)?;
|
||||
restrict_dir(&config_dir)?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Make `dir` owner-only (`0700`). Best effort: a mode we cannot set (an
|
||||
/// exotic filesystem, a directory we do not own) is not worth refusing to
|
||||
/// start over, and the caller has no better answer than continuing.
|
||||
fn restrict_dir(dir: &Path) {
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
if let Err(e) = std::fs::set_permissions(dir, std::fs::Permissions::from_mode(0o700)) {
|
||||
tracing::warn!(path = %dir.display(), error = %e, "could not restrict directory to 0700");
|
||||
/// Make `dir` owner-only (`0700`). These directories contain decrypted bytes,
|
||||
/// plaintext names, and an authenticated control socket, so failure is fatal.
|
||||
fn restrict_dir(dir: &Path) -> Result<()> {
|
||||
use std::os::unix::fs::{MetadataExt as _, PermissionsExt};
|
||||
let before = std::fs::symlink_metadata(dir)?;
|
||||
if before.file_type().is_symlink() || !before.is_dir() {
|
||||
return Err(Error::Other(format!(
|
||||
"sensitive path is not a real directory: {}",
|
||||
dir.display()
|
||||
)));
|
||||
}
|
||||
if before.uid() != unsafe { libc::geteuid() } {
|
||||
return Err(Error::Other(format!(
|
||||
"sensitive directory is not owned by the current user: {}",
|
||||
dir.display()
|
||||
)));
|
||||
}
|
||||
std::fs::set_permissions(dir, std::fs::Permissions::from_mode(0o700))?;
|
||||
let after = std::fs::symlink_metadata(dir)?;
|
||||
if after.permissions().mode() & 0o777 != 0o700 {
|
||||
return Err(Error::Other(format!(
|
||||
"sensitive directory did not become owner-only: {}",
|
||||
dir.display()
|
||||
)));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Make a just-bound Unix socket owner-only (`0600`).
|
||||
@@ -233,29 +379,57 @@ mod tests {
|
||||
/// and the control socket that commands the daemon's session.
|
||||
#[test]
|
||||
fn restrict_dir_makes_a_directory_owner_only() {
|
||||
let dir = std::env::temp_dir().join(format!("pdfs-cfg-{}", std::process::id()));
|
||||
let dir = std::env::temp_dir().join(format!(
|
||||
"pdfs-cfg-{}-{:?}",
|
||||
std::process::id(),
|
||||
std::thread::current().id()
|
||||
));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
// Start deliberately world-readable, as `create_dir_all` under a typical
|
||||
// umask would leave it.
|
||||
std::fs::set_permissions(&dir, std::fs::Permissions::from_mode(0o755)).unwrap();
|
||||
|
||||
restrict_dir(&dir);
|
||||
restrict_dir(&dir).unwrap();
|
||||
|
||||
assert_eq!(mode_of(&dir), 0o700, "group and other must have no access");
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn restrict_dir_refuses_a_symlink() {
|
||||
let root = std::env::temp_dir().join(format!(
|
||||
"pdfs-cfg-link-{}-{:?}",
|
||||
std::process::id(),
|
||||
std::thread::current().id()
|
||||
));
|
||||
let target = root.join("target");
|
||||
let link = root.join("state");
|
||||
std::fs::create_dir_all(&target).unwrap();
|
||||
std::os::unix::fs::symlink(&target, &link).unwrap();
|
||||
|
||||
assert!(restrict_dir(&link).is_err());
|
||||
|
||||
let _ = std::fs::remove_dir_all(&root);
|
||||
}
|
||||
|
||||
/// Connecting to the control socket confers the daemon's authenticated
|
||||
/// session with no credential, so it is an authority boundary rather than
|
||||
/// merely private data.
|
||||
#[test]
|
||||
fn restrict_socket_makes_a_socket_owner_only() {
|
||||
let dir = std::env::temp_dir().join(format!("pdfs-sock-{}", std::process::id()));
|
||||
let dir = std::env::temp_dir().join(format!(
|
||||
"pdfs-sock-{}-{:?}",
|
||||
std::process::id(),
|
||||
std::thread::current().id()
|
||||
));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
let sock = dir.join("control.sock");
|
||||
let listener = std::os::unix::net::UnixListener::bind(&sock).unwrap();
|
||||
// chmod semantics are identical for a socket path and a regular file;
|
||||
// use a file so this regression also runs in sandboxes that prohibit
|
||||
// creating Unix sockets.
|
||||
let listener = std::fs::File::create(&sock).unwrap();
|
||||
|
||||
restrict_socket(&sock).unwrap();
|
||||
|
||||
@@ -271,6 +445,9 @@ mod tests {
|
||||
user_agent: "test-agent/1.0".to_string(),
|
||||
cache_budget: Some(1234),
|
||||
mountpoint: Some("/tmp/x".to_string()),
|
||||
ignore_patterns: Some(vec!["build/".to_string()]),
|
||||
device_uid: Some("dev-uid".to_string()),
|
||||
conflict_sweep: Some(SweepMode::Enforce),
|
||||
};
|
||||
let json = serde_json::to_string(&config).unwrap();
|
||||
let decoded: AppConfig = serde_json::from_str(&json).unwrap();
|
||||
@@ -284,4 +461,86 @@ mod tests {
|
||||
assert_eq!(default_config.app_version, APP_VERSION);
|
||||
assert_eq!(default_config.user_agent, USER_AGENT);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sweep_mode_defaults_to_report_only() {
|
||||
// The sweep trashes user files, so an installed config that has never
|
||||
// heard of the setting must not get the enforcing behaviour.
|
||||
assert_eq!(SweepMode::default(), SweepMode::Report);
|
||||
assert!(!SweepMode::default().is_enforcing());
|
||||
assert_eq!(resolve_sweep_mode(None, None), SweepMode::Report);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sweep_mode_parses_operator_spellings() {
|
||||
for s in ["off", "OFF", " no ", "false", "0", "disabled"] {
|
||||
assert_eq!(SweepMode::parse(s), Some(SweepMode::Off), "{s}");
|
||||
}
|
||||
for s in ["report", "dry-run", "dryrun", "observe"] {
|
||||
assert_eq!(SweepMode::parse(s), Some(SweepMode::Report), "{s}");
|
||||
}
|
||||
for s in ["enforce", "on", "yes", "true", "1"] {
|
||||
assert_eq!(SweepMode::parse(s), Some(SweepMode::Enforce), "{s}");
|
||||
}
|
||||
// A typo must not resolve to anything, so it falls through to the config.
|
||||
assert_eq!(SweepMode::parse("offf"), None);
|
||||
assert_eq!(SweepMode::parse(""), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sweep_mode_env_overrides_config_but_a_typo_does_not() {
|
||||
let stored = Some(SweepMode::Enforce);
|
||||
// The point of the override: kill a destructive loop without editing config.
|
||||
assert_eq!(resolve_sweep_mode(Some("off"), stored), SweepMode::Off);
|
||||
// Unrecognised value falls back to the stored choice rather than guessing.
|
||||
assert_eq!(resolve_sweep_mode(Some("nope"), stored), SweepMode::Enforce);
|
||||
assert_eq!(resolve_sweep_mode(None, stored), SweepMode::Enforce);
|
||||
// No env, no stored value: report-only.
|
||||
assert_eq!(resolve_sweep_mode(Some("nope"), None), SweepMode::Report);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_config_predating_conflict_sweep_still_loads() {
|
||||
let json = r#"{"app_version":"v","user_agent":"u"}"#;
|
||||
let decoded: AppConfig = serde_json::from_str(json).unwrap();
|
||||
assert!(decoded.conflict_sweep.is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sweep_mode_round_trips_through_the_config_file() {
|
||||
let config = AppConfig {
|
||||
conflict_sweep: Some(SweepMode::Enforce),
|
||||
..Default::default()
|
||||
};
|
||||
let json = serde_json::to_string(&config).unwrap();
|
||||
assert!(json.contains(r#""conflict_sweep":"enforce""#), "{json}");
|
||||
let decoded: AppConfig = serde_json::from_str(&json).unwrap();
|
||||
assert_eq!(decoded.conflict_sweep, Some(SweepMode::Enforce));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_config_predating_ignore_patterns_still_loads() {
|
||||
// Every installed config on disk looks like this; the field must not be
|
||||
// required or the daemon would fall back to a default config on upgrade.
|
||||
let json = r#"{"app_version":"v","user_agent":"u"}"#;
|
||||
let decoded: AppConfig = serde_json::from_str(json).unwrap();
|
||||
assert!(decoded.ignore_patterns.is_none());
|
||||
assert_eq!(
|
||||
decoded.resolved_ignore_patterns().len(),
|
||||
DEFAULT_IGNORE_PATTERNS.len(),
|
||||
"an absent list means the defaults apply"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_explicit_empty_ignore_list_disables_the_defaults() {
|
||||
let config = AppConfig {
|
||||
ignore_patterns: Some(Vec::new()),
|
||||
..AppConfig::default()
|
||||
};
|
||||
assert!(
|
||||
config.resolved_ignore_patterns().is_empty(),
|
||||
"opting out must be expressible, so this cannot be unwrap_or_default"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -101,6 +101,19 @@ pub enum Request {
|
||||
/// Independent of [`Request::Search`] so a front-end can fire both at once and
|
||||
/// render whichever lands first. Replies with [`Response::LocalResults`].
|
||||
SearchLocal { query: String, limit: usize },
|
||||
/// Search both the Drive metadata index and the local-file index in one
|
||||
/// round-trip. This is the preferred prompt API; the two legacy search
|
||||
/// requests remain available for older clients. `limit` applies to each
|
||||
/// source independently. `filters` is applied before limiting, so selecting
|
||||
/// (for example) images cannot hide valid matches below an unfiltered top
|
||||
/// `limit`. Older clients omit it and therefore search both sources and all
|
||||
/// kinds. Replies with [`Response::SearchResultsV2`].
|
||||
SearchV2 {
|
||||
query: String,
|
||||
limit: usize,
|
||||
#[serde(default)]
|
||||
filters: SearchFilters,
|
||||
},
|
||||
/// Rename a file or folder. `path` is mountpoint-relative; `new_name` is a
|
||||
/// single path component (no separators). Replies with [`Response::Ok`].
|
||||
Rename { path: String, new_name: String },
|
||||
@@ -136,6 +149,22 @@ pub enum Request {
|
||||
/// persist it to config so the next mount keeps it. Replies with
|
||||
/// [`Response::Ok`].
|
||||
SetCacheBudget { bytes: u64 },
|
||||
/// Report on the health of the metadata database and content cache: sizes,
|
||||
/// row counts, and — when `deep` — SQLite's own integrity check. Replies
|
||||
/// with [`Response::CacheReport`].
|
||||
///
|
||||
/// `deep` reads every page of the database, so it is opt-in: worth it when
|
||||
/// diagnosing a suspected corruption, wasteful as a routine status call.
|
||||
CacheInspect {
|
||||
#[serde(default)]
|
||||
deep: bool,
|
||||
},
|
||||
/// Checkpoint the write-ahead log and compact the database, replying with
|
||||
/// [`Response::Ok`] reporting the bytes reclaimed.
|
||||
///
|
||||
/// Takes a write lock for the duration and needs room for a second copy of
|
||||
/// the database, which is why it is user-invoked rather than periodic.
|
||||
CacheVacuum,
|
||||
/// Snapshot what the daemon is working on: in-flight transfers (active
|
||||
/// uploads/downloads) and the longer jobs around them (scans, folder
|
||||
/// skeletons, the local index, sync passes). Replies with
|
||||
@@ -172,6 +201,11 @@ pub enum Request {
|
||||
RenameDevice { uid: String, name: String },
|
||||
/// Delete (deregister) a device by its uid. Replies with [`Response::Ok`].
|
||||
DeleteDevice { uid: String },
|
||||
/// Adopt an existing device as this machine's, pinning its uid in
|
||||
/// `config.json` so a hostname change or reinstall re-attaches to it instead
|
||||
/// of registering a duplicate (features.md 5.1). `uid: None` clears the pin.
|
||||
/// Replies with [`Response::Ok`].
|
||||
AdoptDevice { uid: Option<String> },
|
||||
|
||||
// ---- device folder sync (devices.md) ----------------------------------
|
||||
/// Add a local folder to this machine's device, uploading its tree and
|
||||
@@ -188,6 +222,13 @@ pub enum Request {
|
||||
/// Force a reconcile pass: one folder by id, or all when `id` is `None`.
|
||||
/// Replies with [`Response::Ok`].
|
||||
SyncNow { id: Option<i64> },
|
||||
/// List the folders under this machine's device that can be synced here,
|
||||
/// each with a proposed local path (features.md 5.2). Replies with
|
||||
/// [`Response::RestorableFolders`].
|
||||
ListRestorableFolders,
|
||||
/// Attach the given remote device folders to local paths and sync them down.
|
||||
/// Replies with [`Response::Ok`].
|
||||
RestoreSyncFolders { items: Vec<RestoreItem> },
|
||||
|
||||
// ---- sharing a node ---------------------------------------------------
|
||||
/// Invite `emails` (Proton and/or external addresses, auto-detected) to the
|
||||
@@ -243,6 +284,16 @@ pub enum Request {
|
||||
/// [`Response::Entries`] (each entry carries its `uid`; `path` is empty since
|
||||
/// the item lives outside the mount tree).
|
||||
ListSharedWithMe,
|
||||
/// List the children of a folder shared with me, addressed by `uid`. Replies
|
||||
/// with [`Response::Entries`]; like [`Request::ListSharedWithMe`] the entries
|
||||
/// carry a `uid` and an empty `path`, since the subtree lives outside the
|
||||
/// mount. Lets a front-end browse into a shared folder.
|
||||
ListSharedFolder { uid: String },
|
||||
/// Download a file shared with me into the content cache, addressed by `uid`.
|
||||
/// Replies with [`Response::FilePath`] so the front-end can open it with the
|
||||
/// default app. The by-uid twin of [`Request::OpenFile`], which can only
|
||||
/// address nodes inside the mount.
|
||||
OpenSharedFile { uid: String },
|
||||
/// Leave a shared node by its `uid`, giving up my access. Replies with
|
||||
/// [`Response::Ok`].
|
||||
LeaveShared { uid: String },
|
||||
@@ -269,6 +320,11 @@ pub enum Request {
|
||||
/// Remove a saved bookmark by its `token`. Replies with [`Response::Ok`].
|
||||
DeleteBookmark { token: String },
|
||||
|
||||
// ---- account ----------------------------------------------------------
|
||||
/// Total account storage usage (used/total, all Proton products, not just
|
||||
/// Drive). Replies with [`Response::AccountQuota`].
|
||||
AccountQuota,
|
||||
|
||||
// ---- activity ---------------------------------------------------------
|
||||
/// Fetch the daemon's recent activity log, newest first, capped at `limit`
|
||||
/// entries. Replies with [`Response::Activity`]. The log is persisted, so it
|
||||
@@ -324,6 +380,11 @@ pub struct DeviceInfo {
|
||||
/// front-end must not offer that as casually as removing another computer.
|
||||
#[serde(default)]
|
||||
pub this_device: bool,
|
||||
/// Whether this device is the one *explicitly adopted* in `config.json`
|
||||
/// ([`Request::AdoptDevice`]), as opposed to one matched by hostname. Only
|
||||
/// an adopted device survives a hostname change or a reinstall.
|
||||
#[serde(default)]
|
||||
pub adopted: bool,
|
||||
}
|
||||
|
||||
/// One synced local folder on this machine's device (in [`Response::SyncFolders`]).
|
||||
@@ -353,6 +414,36 @@ pub struct SyncFolderInfo {
|
||||
pub progress: Option<SyncProgress>,
|
||||
}
|
||||
|
||||
/// A folder under this machine's device offered for restore (in
|
||||
/// [`Response::RestorableFolders`]).
|
||||
#[derive(Serialize, Deserialize, Debug, Clone)]
|
||||
pub struct RestorableFolder {
|
||||
/// Uid of the remote folder — the handle for [`RestoreItem`].
|
||||
pub remote_uid: String,
|
||||
/// Its remote name.
|
||||
pub name: String,
|
||||
/// Where the daemon *proposes* to put it: the path the profile recorded when
|
||||
/// that path makes sense on this machine, else `~/<name>`. A front-end shows
|
||||
/// this as an editable default, never applies it silently.
|
||||
pub local_path: String,
|
||||
/// Proposed mode, from the profile; `mirror` when unknown.
|
||||
pub mode: String,
|
||||
/// Already synced on this machine, so restoring it again would be a no-op.
|
||||
/// Listed anyway so the picker shows the whole device.
|
||||
#[serde(default)]
|
||||
pub already_synced: bool,
|
||||
}
|
||||
|
||||
/// One folder to restore, in [`Request::RestoreSyncFolders`].
|
||||
#[derive(Serialize, Deserialize, Debug, Clone)]
|
||||
pub struct RestoreItem {
|
||||
pub remote_uid: String,
|
||||
/// Absolute local path to sync it to; created if missing.
|
||||
pub local_path: String,
|
||||
/// `mirror` or `ondemand`.
|
||||
pub mode: String,
|
||||
}
|
||||
|
||||
/// Which stage a running sync pass is in, in a [`SyncProgress`].
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum SyncPhase {
|
||||
@@ -482,6 +573,11 @@ pub enum ActivityKind {
|
||||
Share,
|
||||
PublicLink,
|
||||
Unshare,
|
||||
/// A `(sync-conflict …)` copy that needs the user's attention: it diverges
|
||||
/// from the live file (or has no sibling), so the auto-sweep left it in place
|
||||
/// rather than removing it. An auto-*removed* identical copy is logged as a
|
||||
/// [`ActivityKind::Trash`] instead, since that is what happened to it.
|
||||
Conflict,
|
||||
}
|
||||
|
||||
/// One line in the daemon's activity log (in [`Response::Activity`]). Newest
|
||||
@@ -587,6 +683,15 @@ pub struct SearchHit {
|
||||
pub pinned: bool,
|
||||
/// Node uid in `volume~link` form.
|
||||
pub uid: String,
|
||||
/// Absolute path through the most specific active on-demand mount, when the
|
||||
/// node is covered by one. Clients should prefer this for folders and
|
||||
/// streamable media, and fall back to `mountpoint/path` when absent.
|
||||
#[serde(default)]
|
||||
pub mounted_path: Option<String>,
|
||||
/// Relevance assigned by the daemon. Higher scores sort first. Legacy
|
||||
/// daemons omit it, in which case clients retain the daemon's result order.
|
||||
#[serde(default)]
|
||||
pub score: i64,
|
||||
}
|
||||
|
||||
/// One hit in a [`Request::SearchLocal`] result: a file on this machine, outside
|
||||
@@ -601,6 +706,107 @@ pub struct LocalHit {
|
||||
pub size: u64,
|
||||
/// Modification time, epoch seconds.
|
||||
pub modified: i64,
|
||||
/// Relevance assigned by the daemon. Higher scores sort first. Legacy
|
||||
/// daemons omit it, in which case clients retain the daemon's result order.
|
||||
#[serde(default)]
|
||||
pub score: i64,
|
||||
}
|
||||
|
||||
/// A searchable corpus in [`Request::SearchV2`]. Kept explicit on the wire so
|
||||
/// future sources can be added without multiplying request variants.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, Hash)]
|
||||
pub enum SearchSource {
|
||||
Drive,
|
||||
Local,
|
||||
}
|
||||
|
||||
/// Coarse result kind used by the prompt's facets. Classification belongs in
|
||||
/// core/the daemon and must happen before the per-source limit is applied.
|
||||
#[derive(Serialize, Deserialize, Debug, Default, Clone, Copy, PartialEq, Eq, Hash)]
|
||||
pub enum SearchKind {
|
||||
#[default]
|
||||
All,
|
||||
Folders,
|
||||
Documents,
|
||||
Images,
|
||||
Media,
|
||||
}
|
||||
|
||||
impl SearchKind {
|
||||
/// Classify a result before the caller applies its final limit. This stays
|
||||
/// beside the wire enum so every front end and both search corpora agree.
|
||||
pub fn accepts(self, name: &str, is_dir: bool) -> bool {
|
||||
if self == Self::All {
|
||||
return true;
|
||||
}
|
||||
if self == Self::Folders {
|
||||
return is_dir;
|
||||
}
|
||||
if is_dir {
|
||||
return false;
|
||||
}
|
||||
let extension = std::path::Path::new(name)
|
||||
.extension()
|
||||
.and_then(|value| value.to_str())
|
||||
.unwrap_or_default()
|
||||
.to_ascii_lowercase();
|
||||
match self {
|
||||
Self::Documents => matches!(
|
||||
extension.as_str(),
|
||||
"pdf"
|
||||
| "doc"
|
||||
| "docx"
|
||||
| "odt"
|
||||
| "rtf"
|
||||
| "txt"
|
||||
| "md"
|
||||
| "xls"
|
||||
| "xlsx"
|
||||
| "ods"
|
||||
| "csv"
|
||||
| "ppt"
|
||||
| "pptx"
|
||||
| "odp"
|
||||
| "epub"
|
||||
),
|
||||
Self::Images => matches!(
|
||||
extension.as_str(),
|
||||
"png" | "jpg" | "jpeg" | "webp" | "gif" | "bmp" | "svg" | "avif" | "heic" | "tiff"
|
||||
),
|
||||
Self::Media => {
|
||||
PhotoKind::classify(Some(name), None) == PhotoKind::Video
|
||||
|| matches!(
|
||||
extension.as_str(),
|
||||
"mp3" | "flac" | "wav" | "ogg" | "opus" | "m4a" | "aac"
|
||||
)
|
||||
}
|
||||
Self::All | Self::Folders => unreachable!(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Optional constraints for a unified search. The default deliberately means
|
||||
/// the original SearchV2 behaviour, preserving old JSON requests.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
pub struct SearchFilters {
|
||||
/// Sources to query. An explicit empty list searches neither source.
|
||||
#[serde(default = "default_search_sources")]
|
||||
pub sources: Vec<SearchSource>,
|
||||
#[serde(default)]
|
||||
pub kind: SearchKind,
|
||||
}
|
||||
|
||||
impl Default for SearchFilters {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
sources: default_search_sources(),
|
||||
kind: SearchKind::All,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn default_search_sources() -> Vec<SearchSource> {
|
||||
vec![SearchSource::Drive, SearchSource::Local]
|
||||
}
|
||||
|
||||
/// What kind of media a timeline entry is, so the Photos page can split into
|
||||
@@ -817,6 +1023,28 @@ pub enum Response {
|
||||
},
|
||||
/// A human-readable success message.
|
||||
Ok { message: String },
|
||||
/// Health report for the metadata database and content cache (reply to
|
||||
/// [`Request::CacheInspect`]).
|
||||
CacheReport {
|
||||
/// Schema version the database file is at.
|
||||
schema_version: i64,
|
||||
/// Bytes the database file accounts for.
|
||||
db_bytes: u64,
|
||||
/// Bytes a vacuum could hand back.
|
||||
db_reclaimable_bytes: u64,
|
||||
/// Row counts per table, in display order.
|
||||
tables: Vec<(String, i64)>,
|
||||
/// Bytes of cached content blobs, blocks, and thumbnails.
|
||||
cache_used: u64,
|
||||
/// Configured soft byte cap (`0` = unlimited).
|
||||
cache_budget: u64,
|
||||
/// Problems SQLite reported. Empty means sound; absent when the caller
|
||||
/// did not ask for a deep check.
|
||||
integrity_problems: Vec<String>,
|
||||
/// Whether the integrity check actually ran, so an empty problem list
|
||||
/// is not mistaken for a clean bill of health it never gave.
|
||||
integrity_checked: bool,
|
||||
},
|
||||
/// The pin registry.
|
||||
Pins { pins: Vec<Pin> },
|
||||
/// A directory listing (reply to [`Request::ListDir`]) or a trash listing
|
||||
@@ -847,6 +1075,14 @@ pub enum Response {
|
||||
/// is true while a scan of the machine is still running, so a front-end can
|
||||
/// say "still indexing" instead of "no matches" on a cold first launch.
|
||||
LocalResults { hits: Vec<LocalHit>, indexing: bool },
|
||||
/// Drive and local-file search results returned together (reply to
|
||||
/// [`Request::SearchV2`]). `local_indexing` distinguishes a genuinely empty
|
||||
/// local result set from one observed while the initial scan is running.
|
||||
SearchResultsV2 {
|
||||
drive_hits: Vec<SearchHit>,
|
||||
local_hits: Vec<LocalHit>,
|
||||
local_indexing: bool,
|
||||
},
|
||||
/// A snapshot of what the daemon is working on (reply to
|
||||
/// [`Request::GetQueueStatus`]): `items` are byte-moving transfers, `jobs`
|
||||
/// the longer non-transfer work around them (scans, folder skeletons, the
|
||||
@@ -860,6 +1096,8 @@ pub enum Response {
|
||||
Devices { items: Vec<DeviceInfo> },
|
||||
/// This device's synced folders (reply to [`Request::ListSyncFolders`]).
|
||||
SyncFolders { items: Vec<SyncFolderInfo> },
|
||||
/// Folders offered for restore (reply to [`Request::ListRestorableFolders`]).
|
||||
RestorableFolders { items: Vec<RestorableFolder> },
|
||||
/// A node's share: members + pending invitations, and its public link if any
|
||||
/// (reply to [`Request::ListShare`]).
|
||||
Share {
|
||||
@@ -873,6 +1111,11 @@ pub enum Response {
|
||||
Invitations { items: Vec<InvitationInfo> },
|
||||
/// Saved public links (reply to [`Request::ListBookmarks`]).
|
||||
Bookmarks { items: Vec<BookmarkInfo> },
|
||||
/// Account storage usage in bytes (reply to [`Request::AccountQuota`]).
|
||||
/// `max_space` is the total; `used_space` what is consumed. `max_space == 0`
|
||||
/// means the total is unknown, which a front-end shows as a plain used figure
|
||||
/// rather than a full bar.
|
||||
AccountQuota { max_space: i64, used_space: i64 },
|
||||
/// Nodes I have shared with others (reply to [`Request::ListSharedByMe`]).
|
||||
SharedByMe { items: Vec<SharedItem> },
|
||||
/// The daemon's recent activity, newest first (reply to
|
||||
@@ -997,6 +1240,58 @@ mod tests {
|
||||
assert_eq!(PhotoKind::classify(Some("x.jpg"), Some("video/mp4")), Photo);
|
||||
}
|
||||
|
||||
/// Keep every extension accepted by the shared classifier covered. Drive
|
||||
/// activation uses this classification before it knows whether opening a
|
||||
/// file should stream through FUSE or materialise a complete cache entry;
|
||||
/// silently dropping one of these formats would therefore regress large
|
||||
/// videos back to the expensive whole-file path.
|
||||
#[test]
|
||||
fn photo_kind_recognises_every_supported_video_extension() {
|
||||
for ext in VIDEO_EXTS {
|
||||
let lower = format!("movie.{ext}");
|
||||
let upper = format!("MOVIE.{}", ext.to_ascii_uppercase());
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some(&lower), None),
|
||||
PhotoKind::Video,
|
||||
"lower-case .{ext}"
|
||||
);
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some(&upper), None),
|
||||
PhotoKind::Video,
|
||||
"upper-case .{ext}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn photo_kind_uses_video_mime_only_when_extension_is_not_authoritative() {
|
||||
use PhotoKind::*;
|
||||
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some("extensionless"), Some("video/mp4; codecs=avc1")),
|
||||
Video
|
||||
);
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some("clip.unknown"), Some("video/x-matroska")),
|
||||
Video
|
||||
);
|
||||
// Audio is not a video and must not accidentally take the video
|
||||
// streaming policy merely because both are time-based media.
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some("recording"), Some("audio/flac")),
|
||||
Photo
|
||||
);
|
||||
// A known still/raw suffix remains authoritative over server metadata.
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some("poster.AVIF"), Some("video/mp4")),
|
||||
Photo
|
||||
);
|
||||
assert_eq!(
|
||||
PhotoKind::classify(Some("negative.NEF"), Some("video/mp4")),
|
||||
Raw
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn photo_kind_i64_round_trips() {
|
||||
for k in [PhotoKind::Photo, PhotoKind::Video, PhotoKind::Raw] {
|
||||
@@ -1060,6 +1355,150 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unified_search_request_and_response_roundtrip() {
|
||||
let request = Request::SearchV2 {
|
||||
query: "quarterly report".into(),
|
||||
limit: 37,
|
||||
filters: SearchFilters::default(),
|
||||
};
|
||||
let line = serde_json::to_string(&request).unwrap();
|
||||
assert_eq!(
|
||||
line,
|
||||
r#"{"SearchV2":{"query":"quarterly report","limit":37,"filters":{"sources":["Drive","Local"],"kind":"All"}}}"#
|
||||
);
|
||||
let decoded: Request = serde_json::from_str(&line).unwrap();
|
||||
assert_eq!(line, serde_json::to_string(&decoded).unwrap());
|
||||
|
||||
let response = Response::SearchResultsV2 {
|
||||
drive_hits: vec![SearchHit {
|
||||
name: "report.pdf".into(),
|
||||
path: "Work/report.pdf".into(),
|
||||
is_dir: false,
|
||||
size: 12,
|
||||
modified: 123,
|
||||
pinned: true,
|
||||
uid: "vol~link".into(),
|
||||
mounted_path: Some("/home/me/Videos/report.pdf".into()),
|
||||
score: 985,
|
||||
}],
|
||||
local_hits: vec![LocalHit {
|
||||
name: "notes.txt".into(),
|
||||
path: "/home/me/notes.txt".into(),
|
||||
is_dir: false,
|
||||
size: 7,
|
||||
modified: 456,
|
||||
score: 720,
|
||||
}],
|
||||
local_indexing: true,
|
||||
};
|
||||
let line = serde_json::to_string(&response).unwrap();
|
||||
assert!(!line.contains('\n'));
|
||||
let decoded: Response = serde_json::from_str(&line).unwrap();
|
||||
match decoded {
|
||||
Response::SearchResultsV2 {
|
||||
drive_hits,
|
||||
local_hits,
|
||||
local_indexing,
|
||||
} => {
|
||||
assert_eq!(drive_hits.len(), 1);
|
||||
assert_eq!(drive_hits[0].uid, "vol~link");
|
||||
assert_eq!(drive_hits[0].score, 985);
|
||||
assert_eq!(local_hits.len(), 1);
|
||||
assert_eq!(local_hits[0].path, "/home/me/notes.txt");
|
||||
assert_eq!(local_hits[0].score, 720);
|
||||
assert!(local_indexing);
|
||||
}
|
||||
other => panic!("expected unified search results, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_v2_legacy_wire_form_gets_compatible_defaults() {
|
||||
let decoded: Request =
|
||||
serde_json::from_str(r#"{"SearchV2":{"query":"old client","limit":20}}"#).unwrap();
|
||||
match decoded {
|
||||
Request::SearchV2 {
|
||||
query,
|
||||
limit,
|
||||
filters,
|
||||
} => {
|
||||
assert_eq!(query, "old client");
|
||||
assert_eq!(limit, 20);
|
||||
assert_eq!(filters, SearchFilters::default());
|
||||
}
|
||||
other => panic!("expected SearchV2, got {other:?}"),
|
||||
}
|
||||
|
||||
// New daemons add scores, but old-daemon replies remain readable and
|
||||
// signal that their existing order should be retained with score 0.
|
||||
let decoded: Response = serde_json::from_str(
|
||||
r#"{"SearchResultsV2":{"drive_hits":[{"name":"a","path":"a","is_dir":false,"size":1,"modified":2,"pinned":false,"uid":"v~a"}],"local_hits":[{"name":"b","path":"/b","is_dir":false,"size":3,"modified":4}],"local_indexing":false}}"#,
|
||||
)
|
||||
.unwrap();
|
||||
match decoded {
|
||||
Response::SearchResultsV2 {
|
||||
drive_hits,
|
||||
local_hits,
|
||||
..
|
||||
} => {
|
||||
assert_eq!(drive_hits[0].score, 0);
|
||||
assert_eq!(local_hits[0].score, 0);
|
||||
}
|
||||
other => panic!("expected SearchResultsV2, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_v2_filters_roundtrip() {
|
||||
let request = Request::SearchV2 {
|
||||
query: "holiday".into(),
|
||||
limit: 50,
|
||||
filters: SearchFilters {
|
||||
sources: vec![SearchSource::Drive],
|
||||
kind: SearchKind::Images,
|
||||
},
|
||||
};
|
||||
let line = serde_json::to_string(&request).unwrap();
|
||||
let decoded: Request = serde_json::from_str(&line).unwrap();
|
||||
assert!(matches!(
|
||||
decoded,
|
||||
Request::SearchV2 {
|
||||
filters: SearchFilters { sources, kind: SearchKind::Images },
|
||||
..
|
||||
} if sources == vec![SearchSource::Drive]
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_kind_classifies_before_results_are_limited() {
|
||||
assert!(SearchKind::Folders.accepts("movie.mp4", true));
|
||||
assert!(!SearchKind::Folders.accepts("movie.mp4", false));
|
||||
assert!(SearchKind::Documents.accepts("REPORT.PDF", false));
|
||||
assert!(SearchKind::Images.accepts("scan.HEIC", false));
|
||||
assert!(SearchKind::Media.accepts("film.mkv", false));
|
||||
assert!(SearchKind::Media.accepts("recording.flac", false));
|
||||
assert!(!SearchKind::Media.accepts("poster.jpg", false));
|
||||
assert!(SearchKind::All.accepts("anything", true));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_search_wire_forms_still_decode() {
|
||||
let drive: Request =
|
||||
serde_json::from_str(r#"{"Search":{"query":"old","limit":20}}"#).unwrap();
|
||||
assert!(matches!(
|
||||
drive,
|
||||
Request::Search { query, limit } if query == "old" && limit == 20
|
||||
));
|
||||
|
||||
let local: Request =
|
||||
serde_json::from_str(r#"{"SearchLocal":{"query":"old","limit":10}}"#).unwrap();
|
||||
assert!(matches!(
|
||||
local,
|
||||
Request::SearchLocal { query, limit } if query == "old" && limit == 10
|
||||
));
|
||||
}
|
||||
|
||||
/// The trash requests carry uids rather than paths; they must survive the same
|
||||
/// line-delimited round-trip, since a mangled uid would restore or destroy the
|
||||
/// wrong node.
|
||||
@@ -1123,6 +1562,18 @@ mod tests {
|
||||
mode: "ondemand".into(),
|
||||
},
|
||||
Request::SyncNow { id: Some(3) },
|
||||
Request::AdoptDevice {
|
||||
uid: Some("dev-1".into()),
|
||||
},
|
||||
Request::AdoptDevice { uid: None },
|
||||
Request::ListRestorableFolders,
|
||||
Request::RestoreSyncFolders {
|
||||
items: vec![RestoreItem {
|
||||
remote_uid: "vol~link".into(),
|
||||
local_path: "/home/me/Docs".into(),
|
||||
mode: "mirror".into(),
|
||||
}],
|
||||
},
|
||||
Request::ShareNode {
|
||||
path: "a/b".into(),
|
||||
emails: vec!["x@proton.me".into(), "y@example.com".into()],
|
||||
@@ -1154,6 +1605,12 @@ mod tests {
|
||||
Request::ListSharedByMe,
|
||||
Request::ListActivity { limit: 100 },
|
||||
Request::ListSharedWithMe,
|
||||
Request::ListSharedFolder {
|
||||
uid: "vol~link".into(),
|
||||
},
|
||||
Request::OpenSharedFile {
|
||||
uid: "vol~link".into(),
|
||||
},
|
||||
Request::LeaveShared {
|
||||
uid: "vol~link".into(),
|
||||
},
|
||||
@@ -1168,6 +1625,7 @@ mod tests {
|
||||
Request::DeleteBookmark {
|
||||
token: "tok".into(),
|
||||
},
|
||||
Request::AccountQuota,
|
||||
];
|
||||
for req in reqs {
|
||||
let line = serde_json::to_string(&req).unwrap();
|
||||
|
||||
@@ -7,6 +7,7 @@ use super::Db;
|
||||
use crate::Result;
|
||||
use crate::localindex::LocalEntry;
|
||||
|
||||
use super::nodes::candidate_trigrams;
|
||||
use super::utils::{TRIGRAM_MIN, like_escape};
|
||||
|
||||
/// One hit from [`Db::search_local`]: an indexed file on the machine itself, not
|
||||
@@ -147,6 +148,58 @@ impl Db {
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Bounded candidates for the fuzzy scorer, including matches in the full
|
||||
/// local path. ORed trigrams admit misspellings while the FTS index prevents
|
||||
/// this from becoming an unbounded filesystem-table scan.
|
||||
pub fn search_local_candidates(&self, query: &str, limit: usize) -> Result<Vec<LocalFileHit>> {
|
||||
let query = query.trim();
|
||||
if query.is_empty() || limit == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let conn = self.conn.lock();
|
||||
let terms = candidate_trigrams(query);
|
||||
let lane_limit = limit.div_ceil(2);
|
||||
let mut rows: Vec<LocalFileHit> = if terms.is_empty() {
|
||||
let pat = format!("%{}%", like_escape(query));
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT path, name, is_dir, size, mtime FROM local_files
|
||||
WHERE name LIKE ?1 ESCAPE '\\' OR path LIKE ?1 ESCAPE '\\'
|
||||
ORDER BY mtime DESC LIMIT ?2",
|
||||
)?;
|
||||
stmt.query_map(params![pat, limit as i64], local_hit)?
|
||||
.collect::<std::result::Result<_, _>>()?
|
||||
} else {
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT f.path, f.name, f.is_dir, f.size, f.mtime
|
||||
FROM local_fts x JOIN local_files f ON f.id = x.rowid
|
||||
WHERE local_fts MATCH ?1
|
||||
ORDER BY x.rank LIMIT ?2",
|
||||
)?;
|
||||
stmt.query_map(params![terms.join(" OR "), lane_limit as i64], local_hit)?
|
||||
.collect::<std::result::Result<_, _>>()?
|
||||
};
|
||||
if !terms.is_empty()
|
||||
&& let Some(first) = query.chars().next()
|
||||
{
|
||||
let prefix = format!("{}%", like_escape(&first.to_string()));
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT path, name, is_dir, size, mtime FROM local_files
|
||||
WHERE name COLLATE NOCASE LIKE ?1 ESCAPE '\\'
|
||||
ORDER BY name COLLATE NOCASE LIMIT ?2",
|
||||
)?;
|
||||
let fallback = stmt
|
||||
.query_map(params![prefix, lane_limit as i64], local_hit)?
|
||||
.collect::<std::result::Result<Vec<_>, _>>()?;
|
||||
for hit in fallback {
|
||||
if !rows.iter().any(|existing| existing.path == hit.path) {
|
||||
rows.push(hit);
|
||||
}
|
||||
}
|
||||
rows.truncate(limit);
|
||||
}
|
||||
Ok(rows)
|
||||
}
|
||||
}
|
||||
|
||||
/// Row → [`LocalFileHit`]. Every local-search query selects the same
|
||||
|
||||
@@ -0,0 +1,335 @@
|
||||
//! Database health reporting and repair (features.md 4.3).
|
||||
//!
|
||||
//! Everything here exists for the case where something has already gone wrong:
|
||||
//! a crash mid-write, a full disk, a cache that has grown out of proportion to
|
||||
//! what it holds. The daemon never calls these on its own — they are what
|
||||
//! `pdfs cache inspect`, `pdfs cache vacuum`, and `pdfs diagnose` are built on,
|
||||
//! so a user with a suspect install can get an answer without being told to
|
||||
//! delete their state directory and re-sync from scratch.
|
||||
|
||||
use rusqlite::OptionalExtension;
|
||||
|
||||
use super::Db;
|
||||
use crate::Result;
|
||||
|
||||
/// A point-in-time picture of the database's size and contents.
|
||||
///
|
||||
/// Sizes are computed from SQLite's own page accounting rather than by stat'ing
|
||||
/// the file, so they stay right when the file is sparse or a checkpoint is
|
||||
/// pending.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct DbStats {
|
||||
/// Schema version the file is currently at.
|
||||
pub schema_version: i64,
|
||||
/// Total pages allocated to the database.
|
||||
pub page_count: i64,
|
||||
/// Pages allocated but unused — what a `VACUUM` would reclaim.
|
||||
pub free_pages: i64,
|
||||
/// Bytes per page.
|
||||
pub page_size: i64,
|
||||
/// Row counts for the tables worth reporting, in display order.
|
||||
pub tables: Vec<(String, i64)>,
|
||||
}
|
||||
|
||||
impl DbStats {
|
||||
/// Bytes the database file accounts for.
|
||||
pub fn total_bytes(&self) -> u64 {
|
||||
(self.page_count * self.page_size).max(0) as u64
|
||||
}
|
||||
|
||||
/// Bytes a `VACUUM` could hand back to the filesystem.
|
||||
pub fn reclaimable_bytes(&self) -> u64 {
|
||||
(self.free_pages * self.page_size).max(0) as u64
|
||||
}
|
||||
}
|
||||
|
||||
/// What a maintenance run reclaimed.
|
||||
///
|
||||
/// Deliberately does not carry an orphaned-row count: the content cache already
|
||||
/// rebuilds its index from what is actually on disk every time it opens (see
|
||||
/// [`crate::cache::ContentCache`]'s `reconcile`), so a second pruning pass here
|
||||
/// would be a duplicate of that logic with a worse view of the truth.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
|
||||
pub struct VacuumOutcome {
|
||||
/// Database bytes before the run.
|
||||
pub before_bytes: u64,
|
||||
/// Database bytes after it.
|
||||
pub after_bytes: u64,
|
||||
/// WAL frames written back into the database by the checkpoint.
|
||||
pub wal_frames_checkpointed: i64,
|
||||
}
|
||||
|
||||
impl VacuumOutcome {
|
||||
/// Bytes handed back to the filesystem. Saturating: a database can legitimately
|
||||
/// grow across a vacuum (a checkpoint folds WAL frames in), and reporting that
|
||||
/// as a huge positive number via wraparound would be worse than reporting zero.
|
||||
pub fn freed_bytes(&self) -> u64 {
|
||||
self.before_bytes.saturating_sub(self.after_bytes)
|
||||
}
|
||||
}
|
||||
|
||||
/// The tables `inspect` reports on, in the order a reader wants them.
|
||||
const REPORTED_TABLES: &[&str] = &[
|
||||
"nodes",
|
||||
"cache_entries",
|
||||
"pins",
|
||||
"photos",
|
||||
"trash",
|
||||
"device",
|
||||
"sync_folder",
|
||||
"sync_entry",
|
||||
"pending_op",
|
||||
"activity",
|
||||
"local_files",
|
||||
];
|
||||
|
||||
impl Db {
|
||||
/// SQLite's own consistency check.
|
||||
///
|
||||
/// Returns an empty vector when the database is sound; otherwise each entry
|
||||
/// is one problem SQLite found. Read-only and safe against a live daemon,
|
||||
/// though it reads every page, so it is not free on a large file.
|
||||
pub fn integrity_check(&self) -> Result<Vec<String>> {
|
||||
let conn = self.conn.lock();
|
||||
let mut stmt = conn.prepare("PRAGMA integrity_check")?;
|
||||
let rows = stmt.query_map([], |r| r.get::<_, String>(0))?;
|
||||
let mut problems = Vec::new();
|
||||
for row in rows {
|
||||
let row = row?;
|
||||
// A sound database reports the single line "ok"; anything else is a
|
||||
// finding.
|
||||
if row != "ok" {
|
||||
problems.push(row);
|
||||
}
|
||||
}
|
||||
Ok(problems)
|
||||
}
|
||||
|
||||
/// Size and row-count snapshot for `pdfs cache inspect`.
|
||||
pub fn stats(&self) -> Result<DbStats> {
|
||||
let conn = self.conn.lock();
|
||||
let page_count: i64 = conn.query_row("PRAGMA page_count", [], |r| r.get(0))?;
|
||||
let free_pages: i64 = conn.query_row("PRAGMA freelist_count", [], |r| r.get(0))?;
|
||||
let page_size: i64 = conn.query_row("PRAGMA page_size", [], |r| r.get(0))?;
|
||||
// The schema version lives in the `sync_state` key/value table, not in
|
||||
// `PRAGMA user_version` — see `migrations`.
|
||||
let schema_version: i64 = conn
|
||||
.query_row(
|
||||
"SELECT value FROM sync_state WHERE key = 'schema_version'",
|
||||
[],
|
||||
|r| r.get::<_, String>(0),
|
||||
)
|
||||
.optional()?
|
||||
.and_then(|v| v.parse().ok())
|
||||
.unwrap_or(0);
|
||||
|
||||
let mut tables = Vec::new();
|
||||
for name in REPORTED_TABLES {
|
||||
// A table listed here may not exist yet on an older schema, and a
|
||||
// report is not worth failing over a missing one.
|
||||
let exists: Option<String> = conn
|
||||
.query_row(
|
||||
"SELECT name FROM sqlite_master WHERE type='table' AND name=?1",
|
||||
[name],
|
||||
|r| r.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
if exists.is_none() {
|
||||
continue;
|
||||
}
|
||||
let count: i64 =
|
||||
conn.query_row(&format!("SELECT count(*) FROM \"{name}\""), [], |r| {
|
||||
r.get(0)
|
||||
})?;
|
||||
tables.push(((*name).to_string(), count));
|
||||
}
|
||||
|
||||
Ok(DbStats {
|
||||
schema_version,
|
||||
page_count,
|
||||
free_pages,
|
||||
page_size,
|
||||
tables,
|
||||
})
|
||||
}
|
||||
|
||||
/// Fold the WAL back into the database and compact the file.
|
||||
///
|
||||
/// `VACUUM` rewrites the whole database into a fresh file, so it needs room
|
||||
/// for a second copy and takes a write lock for the duration. That makes it
|
||||
/// a deliberate, user-invoked operation rather than something the daemon
|
||||
/// does on a timer.
|
||||
///
|
||||
/// The checkpoint runs *after* the vacuum. Checkpointing only beforehand
|
||||
/// folds a log that the vacuum is about to rewrite anyway, and leaves the
|
||||
/// rewrite itself sitting in the WAL: measured on a live install, a 170 MiB
|
||||
/// database vacuumed to 136 MiB while its WAL grew 67 MiB → 143 MiB,
|
||||
/// erasing the reclaim in net disk terms and reporting `0 frames`
|
||||
/// checkpointed because it ran when there was nothing to fold.
|
||||
///
|
||||
/// Ordering it afterwards is strictly better but is *not* a proven fix for
|
||||
/// that inflation. The live case inflates because the daemon's other
|
||||
/// connections hold read transactions, and a `TRUNCATE` checkpoint waits on
|
||||
/// readers — so under a busy daemon this can still return having moved
|
||||
/// little. `journal_size_limit` remains the backstop that caps the file.
|
||||
/// Confirming the fix needs a measurement against a live daemon, not a
|
||||
/// single-connection test, which folds the WAL on its own either way.
|
||||
pub fn vacuum(&self) -> Result<VacuumOutcome> {
|
||||
let before = self.stats()?.total_bytes();
|
||||
|
||||
{
|
||||
let conn = self.conn.lock();
|
||||
conn.execute_batch("VACUUM")?;
|
||||
}
|
||||
|
||||
let wal_frames_checkpointed = self.checkpoint_wal()?;
|
||||
|
||||
let after = self.stats()?.total_bytes();
|
||||
Ok(VacuumOutcome {
|
||||
before_bytes: before,
|
||||
after_bytes: after,
|
||||
wal_frames_checkpointed,
|
||||
})
|
||||
}
|
||||
|
||||
/// Checkpoint the WAL and truncate it, returning the number of frames
|
||||
/// written back into the database.
|
||||
///
|
||||
/// `TRUNCATE` blocks on readers rather than giving up part-way, which is
|
||||
/// what makes the result meaningful: a `PASSIVE` checkpoint against a busy
|
||||
/// daemon can legitimately move nothing and report success.
|
||||
pub fn checkpoint_wal(&self) -> Result<i64> {
|
||||
let conn = self.conn.lock();
|
||||
// Columns are (busy, log frames, frames checkpointed).
|
||||
let frames: i64 = conn.query_row("PRAGMA wal_checkpoint(TRUNCATE)", [], |r| r.get(2))?;
|
||||
Ok(frames.max(0))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn a_fresh_database_passes_its_integrity_check() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
assert!(db.integrity_check().unwrap().is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn stats_report_the_schema_and_the_known_tables() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let stats = db.stats().unwrap();
|
||||
|
||||
assert!(stats.schema_version > 0, "migrations set a user_version");
|
||||
assert!(stats.page_size > 0);
|
||||
assert!(
|
||||
stats.tables.iter().any(|(name, _)| name == "nodes"),
|
||||
"the nodes table should be reported; got {:?}",
|
||||
stats.tables
|
||||
);
|
||||
// A fresh database has no rows in any of them.
|
||||
assert!(stats.tables.iter().all(|(_, count)| *count == 0));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn total_and_reclaimable_bytes_derive_from_the_page_counts() {
|
||||
let stats = DbStats {
|
||||
schema_version: 1,
|
||||
page_count: 10,
|
||||
free_pages: 4,
|
||||
page_size: 4096,
|
||||
tables: Vec::new(),
|
||||
};
|
||||
assert_eq!(stats.total_bytes(), 40960);
|
||||
assert_eq!(stats.reclaimable_bytes(), 16384);
|
||||
}
|
||||
|
||||
/// A vacuum that leaves the file larger (a checkpoint folded WAL frames in)
|
||||
/// must report nothing freed, not an underflowed enormous number.
|
||||
#[test]
|
||||
fn freed_bytes_does_not_underflow_when_the_file_grew() {
|
||||
let outcome = VacuumOutcome {
|
||||
before_bytes: 100,
|
||||
after_bytes: 400,
|
||||
..VacuumOutcome::default()
|
||||
};
|
||||
assert_eq!(outcome.freed_bytes(), 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn freed_bytes_reports_the_difference_when_the_file_shrank() {
|
||||
let outcome = VacuumOutcome {
|
||||
before_bytes: 4096,
|
||||
after_bytes: 1024,
|
||||
..VacuumOutcome::default()
|
||||
};
|
||||
assert_eq!(outcome.freed_bytes(), 3072);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn vacuuming_a_fresh_database_leaves_it_sound() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
db.vacuum().unwrap();
|
||||
assert!(db.integrity_check().unwrap().is_empty());
|
||||
}
|
||||
|
||||
/// A unique temp directory removed on drop; avoids a dev-dependency, as in
|
||||
/// [`crate::cache`]'s tests. Needed here because an in-memory database has
|
||||
/// no WAL file to measure.
|
||||
struct TempDir(std::path::PathBuf);
|
||||
impl TempDir {
|
||||
fn new() -> Self {
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
static N: AtomicU64 = AtomicU64::new(0);
|
||||
let p = std::env::temp_dir().join(format!(
|
||||
"pdfs-maint-{}-{}",
|
||||
std::process::id(),
|
||||
N.fetch_add(1, Ordering::Relaxed)
|
||||
));
|
||||
std::fs::create_dir_all(&p).unwrap();
|
||||
TempDir(p)
|
||||
}
|
||||
}
|
||||
impl Drop for TempDir {
|
||||
fn drop(&mut self) {
|
||||
let _ = std::fs::remove_dir_all(&self.0);
|
||||
}
|
||||
}
|
||||
|
||||
/// A file-backed vacuum reclaims space and leaves the file sound.
|
||||
///
|
||||
/// Note what this does *not* pin: the WAL-inflation behaviour that motivated
|
||||
/// the checkpoint ordering in [`Db::vacuum`]. Measured here, both orderings
|
||||
/// report `frames=0` and leave a 0-byte WAL, because a single-connection
|
||||
/// test lets SQLite fold the log itself. The live case inflated only because
|
||||
/// the daemon holds concurrent readers that block a checkpoint, and
|
||||
/// reproducing that needs a second connection parked in a read transaction.
|
||||
/// An assertion on frame count or WAL size here would pass under both
|
||||
/// orderings and so would be decoration — see the note in `vacuum`.
|
||||
#[test]
|
||||
fn a_file_backed_vacuum_reclaims_space_and_stays_sound() {
|
||||
let dir = TempDir::new();
|
||||
let path = dir.0.join("cache.db");
|
||||
let db = Db::open(&path).unwrap();
|
||||
|
||||
for i in 0..2000 {
|
||||
db.set_state_str(&format!("k{i}"), &"v".repeat(256))
|
||||
.unwrap();
|
||||
}
|
||||
let full = db.stats().unwrap().total_bytes();
|
||||
for i in 0..2000 {
|
||||
db.set_state_str(&format!("k{i}"), "").unwrap();
|
||||
}
|
||||
|
||||
let outcome = db.vacuum().unwrap();
|
||||
|
||||
assert!(
|
||||
outcome.after_bytes < full,
|
||||
"vacuum did not reclaim: {} → {} (peak {full})",
|
||||
outcome.before_bytes,
|
||||
outcome.after_bytes
|
||||
);
|
||||
assert!(db.integrity_check().unwrap().is_empty());
|
||||
}
|
||||
}
|
||||
@@ -9,7 +9,7 @@ use super::Db;
|
||||
use crate::Result;
|
||||
|
||||
/// Current schema version. Bump on every forward migration added below.
|
||||
pub(super) const SCHEMA_VERSION: i64 = 14;
|
||||
pub(super) const SCHEMA_VERSION: i64 = 16;
|
||||
|
||||
impl Db {
|
||||
pub(super) fn migrate(&self) -> Result<()> {
|
||||
@@ -31,7 +31,12 @@ impl Db {
|
||||
.and_then(|v| v.parse().ok())
|
||||
.unwrap_or(0);
|
||||
|
||||
if current >= SCHEMA_VERSION {
|
||||
if current > SCHEMA_VERSION {
|
||||
return Err(crate::Error::Other(format!(
|
||||
"database schema {current} is newer than this build supports ({SCHEMA_VERSION}); refusing to open it to avoid corrupting user data"
|
||||
)));
|
||||
}
|
||||
if current == SCHEMA_VERSION {
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
@@ -78,6 +83,12 @@ impl Db {
|
||||
if current < 14 {
|
||||
tx.execute_batch(MIGRATION_V14)?;
|
||||
}
|
||||
if current < 15 {
|
||||
tx.execute_batch(MIGRATION_V15)?;
|
||||
}
|
||||
if current < 16 {
|
||||
tx.execute_batch(MIGRATION_V16)?;
|
||||
}
|
||||
tx.execute(
|
||||
"INSERT INTO sync_state (key, value) VALUES ('schema_version', ?1)
|
||||
ON CONFLICT(key) DO UPDATE SET value = excluded.value",
|
||||
@@ -340,3 +351,63 @@ ALTER TABLE photos ADD COLUMN kind INTEGER NOT NULL DEFAULT 0;
|
||||
const MIGRATION_V14: &str = "
|
||||
CREATE INDEX cache_entries_lru ON cache_entries(kind, last_accessed);
|
||||
";
|
||||
|
||||
/// Schema v15: key the search index by rowid so a row can be replaced without
|
||||
/// scanning the whole index (B12).
|
||||
///
|
||||
/// v3 built `nodes_fts` with the node's `uid` as an `UNINDEXED` column and
|
||||
/// `upsert_nodes` refreshed a row with `DELETE FROM nodes_fts WHERE uid = ?`.
|
||||
/// `UNINDEXED` means exactly what it says — the column is retrievable but not
|
||||
/// searchable — so that predicate could only ever be a full scan of the index
|
||||
/// (`EXPLAIN QUERY PLAN`: `SCAN nodes_fts VIRTUAL TABLE`). Every node written
|
||||
/// scanned every node indexed: measured at 6.5 ms per node against a 17k-node
|
||||
/// index, about half the cost of a cold listing, and *growing with the size of
|
||||
/// the account* rather than the size of the listing.
|
||||
///
|
||||
/// FTS5 deletes by `rowid` efficiently, and `nodes` is an ordinary rowid table
|
||||
/// (`uid` is its `TEXT PRIMARY KEY`, not `WITHOUT ROWID`), so its rowid is a
|
||||
/// stable per-node key that `ON CONFLICT DO UPDATE` preserves. Rebuild the index
|
||||
/// keyed by it and drop the `uid` column: searches now join on `rowid`, which is
|
||||
/// also a cheaper join than the old one on a TEXT uid.
|
||||
const MIGRATION_V15: &str = "
|
||||
DROP TABLE IF EXISTS nodes_fts;
|
||||
CREATE VIRTUAL TABLE nodes_fts USING fts5(
|
||||
name, tokenize='trigram'
|
||||
);
|
||||
INSERT INTO nodes_fts (rowid, name)
|
||||
SELECT rowid, name FROM nodes WHERE trashed = 0;
|
||||
";
|
||||
|
||||
/// Schema v16: fuzzy search needs a bounded candidate set that includes parent
|
||||
/// paths. Keeping the path in the trigram indexes lets SQLite narrow both name
|
||||
/// and path candidates without walking either base table for every keystroke.
|
||||
/// Node paths are initially backfilled below and subsequently maintained by the
|
||||
/// node write path (including descendants after a folder move/rename).
|
||||
const MIGRATION_V16: &str = "
|
||||
DROP TABLE IF EXISTS nodes_fts;
|
||||
CREATE VIRTUAL TABLE nodes_fts USING fts5(
|
||||
name, path, tokenize='trigram'
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_nodes_name_nocase ON nodes(name COLLATE NOCASE);
|
||||
INSERT INTO nodes_fts (rowid, name, path)
|
||||
WITH RECURSIVE paths(rowid, uid, path) AS (
|
||||
SELECT n.rowid, n.uid, '' FROM nodes n
|
||||
WHERE n.parent_uid IS NULL
|
||||
OR NOT EXISTS (SELECT 1 FROM nodes p WHERE p.uid = n.parent_uid)
|
||||
UNION ALL
|
||||
SELECT n.rowid, n.uid,
|
||||
CASE WHEN paths.path = '' THEN n.name ELSE paths.path || '/' || n.name END
|
||||
FROM nodes n JOIN paths ON n.parent_uid = paths.uid
|
||||
)
|
||||
SELECT n.rowid, n.name, paths.path
|
||||
FROM nodes n JOIN paths ON paths.rowid = n.rowid
|
||||
WHERE n.trashed = 0;
|
||||
|
||||
DROP TABLE IF EXISTS local_fts;
|
||||
CREATE VIRTUAL TABLE local_fts USING fts5(
|
||||
name, path, content='local_files', content_rowid='id', tokenize='trigram'
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_local_files_name_nocase
|
||||
ON local_files(name COLLATE NOCASE);
|
||||
INSERT INTO local_fts(local_fts) VALUES('rebuild');
|
||||
";
|
||||
@@ -25,6 +25,7 @@ mod activity;
|
||||
mod cache;
|
||||
mod devices;
|
||||
mod local;
|
||||
mod maintenance;
|
||||
mod migrations;
|
||||
mod nodes;
|
||||
mod ops;
|
||||
@@ -38,9 +39,10 @@ mod utils;
|
||||
pub use cache::CacheEntryInput;
|
||||
pub use devices::StoredDevice;
|
||||
pub use local::LocalFileHit;
|
||||
pub use maintenance::{DbStats, VacuumOutcome};
|
||||
pub use nodes::{SearchHit, StoredNode};
|
||||
pub use ops::{
|
||||
AttachedBlob, LOCAL_VOLUME, OP_CREATE, OP_MKDIR, OP_RENAME, OP_REVISION, OP_TRASH,
|
||||
AttachedBlob, LOCAL_VOLUME, OP_CREATE, OP_MKDIR, OP_RENAME, OP_REVISION, OP_TRASH, PARK_UNTIL,
|
||||
PendingCounts, PendingOp, op_supersedes,
|
||||
};
|
||||
pub use photos::{StoredPhoto, THUMB_HAVE, THUMB_NONE, THUMB_UNKNOWN};
|
||||
|
||||
@@ -70,12 +70,53 @@ impl Db {
|
||||
// FTS5 has no UPSERT, so refresh the row by delete-then-insert.
|
||||
// Trashed nodes are kept out of the index entirely so they never
|
||||
// surface in search results.
|
||||
tx.execute("DELETE FROM nodes_fts WHERE uid = ?1", params![uid])?;
|
||||
if !node.trashed {
|
||||
tx.execute(
|
||||
"INSERT INTO nodes_fts (uid, name) VALUES (?1, ?2)",
|
||||
params![uid, node.name],
|
||||
//
|
||||
// Keyed by the node's rowid, never by its uid: the uid is not an
|
||||
// indexed FTS column, so deleting by it scans the entire index once
|
||||
// per node written (B12). The rowid is stable across the upsert
|
||||
// above — `ON CONFLICT DO UPDATE` keeps the existing row — so it is
|
||||
// the same key before and after.
|
||||
let rowid: i64 = tx.query_row(
|
||||
"SELECT rowid FROM nodes WHERE uid = ?1",
|
||||
params![uid],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
// A folder rename/move changes every descendant's searchable path.
|
||||
// Refresh the affected subtree, while retaining efficient rowid
|
||||
// deletes for the overwhelmingly common one-file case.
|
||||
let mut affected = vec![rowid];
|
||||
if node.is_folder() {
|
||||
let mut stmt = tx.prepare(
|
||||
"WITH RECURSIVE descendants(rowid, uid) AS (
|
||||
SELECT rowid, uid FROM nodes WHERE parent_uid = ?1
|
||||
UNION ALL
|
||||
SELECT n.rowid, n.uid FROM nodes n
|
||||
JOIN descendants d ON n.parent_uid = d.uid
|
||||
) SELECT rowid FROM descendants",
|
||||
)?;
|
||||
for descendant in stmt.query_map(params![uid], |row| row.get(0))? {
|
||||
affected.push(descendant?);
|
||||
}
|
||||
}
|
||||
for affected_rowid in affected {
|
||||
tx.execute(
|
||||
"DELETE FROM nodes_fts WHERE rowid = ?1",
|
||||
params![affected_rowid],
|
||||
)?;
|
||||
let indexed: Option<(String, String)> = tx
|
||||
.query_row(
|
||||
"SELECT name, uid FROM nodes WHERE rowid = ?1 AND trashed = 0",
|
||||
params![affected_rowid],
|
||||
|row| Ok((row.get(0)?, row.get(1)?)),
|
||||
)
|
||||
.optional()?;
|
||||
if let Some((name, indexed_uid)) = indexed {
|
||||
let path = path_of(&tx, &indexed_uid)?;
|
||||
tx.execute(
|
||||
"INSERT INTO nodes_fts (rowid, name, path) VALUES (?1, ?2, ?3)",
|
||||
params![affected_rowid, name, path],
|
||||
)?;
|
||||
}
|
||||
}
|
||||
}
|
||||
tx.commit()?;
|
||||
@@ -88,12 +129,71 @@ impl Db {
|
||||
let uid = uid.to_string();
|
||||
let mut conn = self.conn.lock();
|
||||
let tx = conn.transaction()?;
|
||||
// Read the rowid before dropping the node: it is the search index's key
|
||||
// (B12), and it is gone once the row is. A node with no row leaves
|
||||
// nothing to unindex — the index is keyed off `nodes`, so it cannot
|
||||
// hold an entry the table never had.
|
||||
let rowid: Option<i64> = tx
|
||||
.query_row(
|
||||
"SELECT rowid FROM nodes WHERE uid = ?1",
|
||||
params![uid],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
tx.execute("DELETE FROM nodes WHERE uid = ?1", params![uid])?;
|
||||
tx.execute("DELETE FROM nodes_fts WHERE uid = ?1", params![uid])?;
|
||||
if let Some(rowid) = rowid {
|
||||
tx.execute("DELETE FROM nodes_fts WHERE rowid = ?1", params![rowid])?;
|
||||
}
|
||||
tx.commit()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Check if a folder node has any non-trashed children in the database.
|
||||
pub fn has_children(&self, parent_uid: &NodeUid) -> Result<bool> {
|
||||
let uid_str = parent_uid.to_string();
|
||||
let conn = self.conn.lock();
|
||||
let count: i64 = conn.query_row(
|
||||
"SELECT COUNT(*) FROM nodes WHERE parent_uid = ?1 AND trashed = 0",
|
||||
params![uid_str],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
Ok(count > 0)
|
||||
}
|
||||
|
||||
/// Resolve `uid` relative to an ancestor node.
|
||||
///
|
||||
/// This is used when a remote subtree has its own local sync mount: the
|
||||
/// sync folder stores the ancestor UID, while search results identify the
|
||||
/// selected descendant. Returning `None` for an unrelated or incomplete
|
||||
/// chain keeps callers from accidentally joining a Drive-wide path onto the
|
||||
/// wrong mountpoint. The ancestor itself resolves to the empty path.
|
||||
pub fn path_relative_to(&self, ancestor_uid: &str, uid: &str) -> Result<Option<String>> {
|
||||
let conn = self.conn.lock();
|
||||
let mut stmt = conn.prepare(
|
||||
"WITH RECURSIVE anc(uid, parent_uid, name, depth) AS (
|
||||
SELECT uid, parent_uid, name, 0 FROM nodes WHERE uid = ?1
|
||||
UNION ALL
|
||||
SELECT n.uid, n.parent_uid, n.name, anc.depth + 1
|
||||
FROM nodes n JOIN anc ON n.uid = anc.parent_uid
|
||||
WHERE anc.depth < 1024
|
||||
)
|
||||
SELECT uid, name FROM anc ORDER BY depth",
|
||||
)?;
|
||||
let rows = stmt.query_map(params![uid], |row| {
|
||||
Ok((row.get::<_, String>(0)?, row.get::<_, String>(1)?))
|
||||
})?;
|
||||
let mut parts = Vec::new();
|
||||
for row in rows {
|
||||
let (current_uid, name) = row?;
|
||||
if current_uid == ancestor_uid {
|
||||
parts.reverse();
|
||||
return Ok(Some(parts.join("/")));
|
||||
}
|
||||
parts.push(name);
|
||||
}
|
||||
Ok(None)
|
||||
}
|
||||
|
||||
/// Full-text search over node names, newest schema's trigram index giving
|
||||
/// substring (not just prefix) matches. Returns up to `limit` non-trashed
|
||||
/// hits, each with its mountpoint-relative path resolved. Queries shorter
|
||||
@@ -123,7 +223,7 @@ impl Db {
|
||||
.join(" AND ");
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT n.node_json, n.uid
|
||||
FROM nodes_fts f JOIN nodes n ON n.uid = f.uid
|
||||
FROM nodes_fts f JOIN nodes n ON n.rowid = f.rowid
|
||||
WHERE f.name MATCH ?1 AND n.trashed = 0 AND n.node_json IS NOT NULL
|
||||
ORDER BY f.rank LIMIT ?2",
|
||||
)?;
|
||||
@@ -139,6 +239,68 @@ impl Db {
|
||||
Ok(hits)
|
||||
}
|
||||
|
||||
/// Return a bounded, deliberately broad candidate pool for fuzzy ranking.
|
||||
/// Unlike [`search`](Self::search), trigram terms are ORed across both the
|
||||
/// basename and parent path, so a typo can still share enough trigrams to
|
||||
/// enter the pool. Final relevance ordering belongs to the caller.
|
||||
pub fn search_candidates(&self, query: &str, limit: usize) -> Result<Vec<SearchHit>> {
|
||||
let query = query.trim();
|
||||
if query.is_empty() || limit == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let conn = self.conn.lock();
|
||||
let terms = candidate_trigrams(query);
|
||||
let lane_limit = limit.div_ceil(2);
|
||||
let mut rows: Vec<(String, String)> = if terms.is_empty() {
|
||||
let pat = format!("%{}%", like_escape(query));
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT node_json, uid FROM nodes
|
||||
WHERE name LIKE ?1 ESCAPE '\\' AND trashed = 0 AND node_json IS NOT NULL
|
||||
ORDER BY name LIMIT ?2",
|
||||
)?;
|
||||
collect_pairs(stmt.query_map(params![pat, limit as i64], pair)?)?
|
||||
} else {
|
||||
let expression = terms.join(" OR ");
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT n.node_json, n.uid
|
||||
FROM nodes_fts f JOIN nodes n ON n.rowid = f.rowid
|
||||
WHERE nodes_fts MATCH ?1 AND n.trashed = 0 AND n.node_json IS NOT NULL
|
||||
ORDER BY f.rank LIMIT ?2",
|
||||
)?;
|
||||
collect_pairs(stmt.query_map(params![expression, lane_limit as i64], pair)?)?
|
||||
};
|
||||
// A short substitution can destroy every trigram (`vedio` vs `video`).
|
||||
// Feed the scorer an additional indexed same-initial lane so it can
|
||||
// recover those candidates without scanning the full node table.
|
||||
if !terms.is_empty()
|
||||
&& let Some(first) = query.chars().next()
|
||||
{
|
||||
let prefix = format!("{}%", like_escape(&first.to_string()));
|
||||
let mut stmt = conn.prepare(
|
||||
"SELECT node_json, uid FROM nodes
|
||||
WHERE name COLLATE NOCASE LIKE ?1 ESCAPE '\\'
|
||||
AND trashed = 0 AND node_json IS NOT NULL
|
||||
ORDER BY name COLLATE NOCASE LIMIT ?2",
|
||||
)?;
|
||||
let fallback =
|
||||
collect_pairs(stmt.query_map(params![prefix, lane_limit as i64], pair)?)?;
|
||||
for row in fallback {
|
||||
if !rows.iter().any(|(_, uid)| uid == &row.1) {
|
||||
rows.push(row);
|
||||
}
|
||||
}
|
||||
rows.truncate(limit);
|
||||
}
|
||||
rows.into_iter()
|
||||
.map(|(json, uid)| {
|
||||
Ok(SearchHit {
|
||||
node: serde_json::from_str(&json)?,
|
||||
path: path_of(&conn, &uid)?,
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Mark (or unmark) a folder's child listing as complete. A listed folder
|
||||
/// rehydrates its `children` map on mount even when empty; an unlisted one
|
||||
/// re-enumerates from the remote on next access.
|
||||
@@ -225,6 +387,23 @@ impl Db {
|
||||
// in sync on every store/read/evict, so it is authoritative for eviction.
|
||||
}
|
||||
|
||||
/// Unique quoted character trigrams suitable for an FTS5 OR expression.
|
||||
pub(super) fn candidate_trigrams(query: &str) -> Vec<String> {
|
||||
let chars: Vec<char> = query.to_lowercase().chars().collect();
|
||||
let mut terms = Vec::new();
|
||||
for window in chars.windows(TRIGRAM_MIN) {
|
||||
if window.iter().all(|c| c.is_whitespace()) {
|
||||
continue;
|
||||
}
|
||||
let raw: String = window.iter().collect();
|
||||
let quoted = format!("\"{}\"", raw.replace('"', "\"\""));
|
||||
if !terms.contains("ed) {
|
||||
terms.push(quoted);
|
||||
}
|
||||
}
|
||||
terms
|
||||
}
|
||||
|
||||
/// Effective plaintext size of a node for the indexed `size` column: the
|
||||
/// claimed size when known, else the on-storage size; folders are 0.
|
||||
pub(super) fn node_size(node: &Node) -> i64 {
|
||||
|
||||
@@ -63,6 +63,16 @@ pub fn op_supersedes(kind: &str) -> bool {
|
||||
/// drain replaces it with the uid the server assigns.
|
||||
pub const LOCAL_VOLUME: &str = "local";
|
||||
|
||||
/// A `next_attempt_at` far enough in the future that [`Db::next_due_op`] never
|
||||
/// selects the op (ms since epoch, ≈ year 2223). Used to *park* a queued create
|
||||
/// for a transient file — a browser's in-flight `*.crdownload`/`*.part`, an
|
||||
/// editor's `*.swp` — so its bytes never upload while it wears that name. A
|
||||
/// rename to the finished name un-parks it (see [`Db::set_create_hold`]), which
|
||||
/// is the only moment the completed file is meant to reach Drive. Without the
|
||||
/// park, every partial and every abandoned temp would upload and, on a
|
||||
/// stall+resume, fork a `(sync-conflict)` copy (docs/BUGS.md B70).
|
||||
pub const PARK_UNTIL: i64 = 8_000_000_000_000;
|
||||
|
||||
/// A mutation that has been accepted locally but not yet performed against the
|
||||
/// API — the durable half of the write-back queue (offline.md Phase 3).
|
||||
///
|
||||
@@ -118,9 +128,10 @@ pub struct AttachedBlob {
|
||||
|
||||
impl Db {
|
||||
pub fn enqueue_op(&self, op: &PendingOp) -> Result<(i64, Option<String>)> {
|
||||
let conn = self.conn.lock();
|
||||
let mut conn = self.conn.lock();
|
||||
let tx = conn.transaction()?;
|
||||
let superseded: Option<String> = if op_supersedes(&op.kind) {
|
||||
let blob: Option<String> = conn
|
||||
let blob: Option<String> = tx
|
||||
.query_row(
|
||||
"SELECT blob_path FROM pending_op WHERE uid = ?1 AND kind = ?2",
|
||||
params![op.uid, op.kind],
|
||||
@@ -128,7 +139,7 @@ impl Db {
|
||||
)
|
||||
.optional()?
|
||||
.flatten();
|
||||
conn.execute(
|
||||
tx.execute(
|
||||
"DELETE FROM pending_op WHERE uid = ?1 AND kind = ?2",
|
||||
params![op.uid, op.kind],
|
||||
)?;
|
||||
@@ -136,10 +147,10 @@ impl Db {
|
||||
} else {
|
||||
None
|
||||
};
|
||||
conn.execute(
|
||||
tx.execute(
|
||||
"INSERT INTO pending_op
|
||||
(kind, uid, parent_uid, name, blob_path, meta_json, created_at)
|
||||
VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7)",
|
||||
(kind, uid, parent_uid, name, blob_path, meta_json, created_at, next_attempt_at)
|
||||
VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7, ?8)",
|
||||
params![
|
||||
op.kind,
|
||||
op.uid,
|
||||
@@ -147,10 +158,13 @@ impl Db {
|
||||
op.name,
|
||||
op.blob_path,
|
||||
op.meta_json,
|
||||
op.created_at
|
||||
op.created_at,
|
||||
op.next_attempt_at
|
||||
],
|
||||
)?;
|
||||
Ok((conn.last_insert_rowid(), superseded))
|
||||
let id = tx.last_insert_rowid();
|
||||
tx.commit()?;
|
||||
Ok((id, superseded))
|
||||
}
|
||||
|
||||
/// Point a queued create at the bytes that were just written to it, returning
|
||||
@@ -179,11 +193,18 @@ impl Db {
|
||||
let Some((id, superseded)) = existing else {
|
||||
return Ok(None);
|
||||
};
|
||||
// Clearing the backoff lets the fresh bytes be tried promptly — except
|
||||
// when the create is *parked* (a transient file, next_attempt_at at the
|
||||
// PARK_UNTIL sentinel). Attaching a new revision to a still-growing
|
||||
// download must not wake it; only the finalize rename does. So preserve a
|
||||
// park and reset an ordinary backoff.
|
||||
conn.execute(
|
||||
"UPDATE pending_op
|
||||
SET blob_path = ?2, meta_json = ?3, attempts = 0, next_attempt_at = 0
|
||||
SET blob_path = ?2, meta_json = ?3, attempts = 0,
|
||||
next_attempt_at = CASE WHEN next_attempt_at >= ?4
|
||||
THEN next_attempt_at ELSE 0 END
|
||||
WHERE id = ?1",
|
||||
params![id, blob_path, meta_json],
|
||||
params![id, blob_path, meta_json, PARK_UNTIL],
|
||||
)?;
|
||||
Ok(Some(AttachedBlob { id, superseded }))
|
||||
}
|
||||
@@ -229,6 +250,52 @@ impl Db {
|
||||
Ok(n > 0)
|
||||
}
|
||||
|
||||
/// Park or un-park a queued create/mkdir for `uid`, returning whether a row
|
||||
/// was touched.
|
||||
///
|
||||
/// Parking sets `next_attempt_at` to [`PARK_UNTIL`] so [`Db::next_due_op`]
|
||||
/// skips it indefinitely; un-parking sets it due now. Used to keep a
|
||||
/// transient file's bytes off Drive until it is renamed to its finished name
|
||||
/// (docs/BUGS.md B70). Un-parking a create that was never parked is harmless:
|
||||
/// it just makes the create due immediately, which for a normal local node it
|
||||
/// already is.
|
||||
pub fn set_create_hold(&self, uid: &str, held: bool) -> Result<bool> {
|
||||
let conn = self.conn.lock();
|
||||
let n = conn.execute(
|
||||
"UPDATE pending_op SET next_attempt_at = ?2
|
||||
WHERE uid = ?1 AND kind IN (?3, ?4)",
|
||||
params![uid, if held { PARK_UNTIL } else { 0 }, OP_CREATE, OP_MKDIR],
|
||||
)?;
|
||||
Ok(n > 0)
|
||||
}
|
||||
|
||||
/// Check if a queued create or mkdir op exists for `uid`.
|
||||
pub fn has_create_op(&self, uid: &str) -> Result<bool> {
|
||||
let conn = self.conn.lock();
|
||||
let count: i64 = conn.query_row(
|
||||
"SELECT COUNT(*) FROM pending_op WHERE uid = ?1 AND kind IN (?2, ?3)",
|
||||
params![uid, OP_CREATE, OP_MKDIR],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
Ok(count > 0)
|
||||
}
|
||||
|
||||
/// Check whether *any* op of any kind is queued against `uid`.
|
||||
///
|
||||
/// Used as a safety interlock by callers that are about to remove a node
|
||||
/// they only know about from a stale snapshot: a queued op means the user's
|
||||
/// bytes are still owed an upload, and dropping it would discard the staged
|
||||
/// blob that holds them (`docs/BUGS.md` B71).
|
||||
pub fn has_any_op(&self, uid: &str) -> Result<bool> {
|
||||
let conn = self.conn.lock();
|
||||
let count: i64 = conn.query_row(
|
||||
"SELECT COUNT(*) FROM pending_op WHERE uid = ?1",
|
||||
params![uid],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
Ok(count > 0)
|
||||
}
|
||||
|
||||
/// Drop every op targeting a node **or anything queued beneath it**,
|
||||
/// returning the staged blobs they held so the caller can delete them.
|
||||
///
|
||||
@@ -347,6 +414,28 @@ impl Db {
|
||||
Ok(op)
|
||||
}
|
||||
|
||||
/// The earliest `next_attempt_at` among all queued ops, or `None` if the
|
||||
/// queue is empty. Used by the drain loop to sleep exactly until the next
|
||||
/// debounced or backed-off op becomes eligible rather than waiting the full
|
||||
/// idle-poll interval.
|
||||
pub fn earliest_due_at(&self) -> Result<Option<i64>> {
|
||||
let conn = self.conn.lock();
|
||||
let ts: Option<i64> = conn
|
||||
.query_row(
|
||||
&format!(
|
||||
"SELECT MIN(next_attempt_at) FROM pending_op \
|
||||
WHERE parent_uid IS NULL OR substr(parent_uid, 1, {n}) <> '{v}~'",
|
||||
v = LOCAL_VOLUME,
|
||||
n = LOCAL_VOLUME.len() + 1,
|
||||
),
|
||||
[],
|
||||
|r| r.get(0),
|
||||
)
|
||||
.optional()?
|
||||
.flatten();
|
||||
Ok(ts)
|
||||
}
|
||||
|
||||
/// Every queued op, oldest first. For status read-outs and the CLI — the
|
||||
/// drain wants [`next_due_op`](Self::next_due_op) instead.
|
||||
pub fn pending_ops(&self) -> Result<Vec<PendingOp>> {
|
||||
|
||||
@@ -5,6 +5,7 @@ use crate::control::{ActivityEntry, ActivityKind};
|
||||
use crate::localindex::LocalEntry;
|
||||
use proton_drive_rs::proton_sdk::ids::NodeUid;
|
||||
use proton_drive_rs::{Node, NodeKind};
|
||||
use serde_json::json;
|
||||
|
||||
/// `Db::open` applies the pragmas that `open_in_memory` skips, so the WAL
|
||||
/// settings can only be checked against a real file.
|
||||
@@ -542,6 +543,95 @@ fn search_short_query_like_fallback() {
|
||||
assert_eq!(hits[0].node.name, "ab.txt");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fuzzy_candidates_include_typo_and_parent_path_matches() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
db.upsert_node(&folder("root", None, "My Files")).unwrap();
|
||||
db.upsert_node(&folder("projects", Some("root"), "Projects"))
|
||||
.unwrap();
|
||||
db.upsert_node(&file("report", "projects", "quarterly-report.pdf", 1))
|
||||
.unwrap();
|
||||
db.upsert_node(&file("video", "projects", "video.mp4", 1))
|
||||
.unwrap();
|
||||
|
||||
let typo = db.search_candidates("quartrly", 20).unwrap();
|
||||
assert!(
|
||||
typo.iter()
|
||||
.any(|hit| hit.node.name == "quarterly-report.pdf")
|
||||
);
|
||||
assert!(
|
||||
db.search_candidates("vedio", 20)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.any(|hit| hit.node.name == "video.mp4")
|
||||
);
|
||||
|
||||
let path = db.search_candidates("projects", 20).unwrap();
|
||||
assert!(
|
||||
path.iter()
|
||||
.any(|hit| hit.node.name == "quarterly-report.pdf")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn renaming_parent_refreshes_descendant_search_paths() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
db.upsert_node(&folder("root", None, "My Files")).unwrap();
|
||||
db.upsert_node(&folder("folder", Some("root"), "zzbeforezz"))
|
||||
.unwrap();
|
||||
db.upsert_node(&file("child", "folder", "plain.txt", 1))
|
||||
.unwrap();
|
||||
assert!(
|
||||
db.search_candidates("zzbeforezz", 20)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.any(|h| h.node.name == "plain.txt")
|
||||
);
|
||||
|
||||
db.upsert_node(&folder("folder", Some("root"), "yyafteryy"))
|
||||
.unwrap();
|
||||
assert!(
|
||||
!db.search_candidates("zzbeforezz", 20)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.any(|h| h.node.name == "plain.txt")
|
||||
);
|
||||
assert!(
|
||||
db.search_candidates("yyafteryy", 20)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.any(|h| h.node.name == "plain.txt")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn local_fuzzy_candidates_include_typo_and_parent_path() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let generation = db.local_begin_scan().unwrap();
|
||||
db.local_upsert_batch(
|
||||
generation,
|
||||
&[
|
||||
local(
|
||||
"/home/u/Projects/quarterly-report.pdf",
|
||||
"quarterly-report.pdf",
|
||||
false,
|
||||
),
|
||||
local("/home/u/Videos/video.mp4", "video.mp4", false),
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
db.local_finish_scan(generation, 1).unwrap();
|
||||
|
||||
assert_eq!(db.search_local_candidates("quartrly", 20).unwrap().len(), 1);
|
||||
assert_eq!(db.search_local_candidates("projects", 20).unwrap().len(), 1);
|
||||
assert!(
|
||||
db.search_local_candidates("vedio", 20)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.any(|hit| hit.name == "video.mp4")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_drops_fts_row_on_delete_and_trash() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
@@ -564,6 +654,78 @@ fn search_drops_fts_row_on_delete_and_trash() {
|
||||
assert_eq!(db.search("unique", 10).unwrap().len(), 0);
|
||||
}
|
||||
|
||||
/// Renaming re-indexes the node, which is the case delete-by-rowid has to get
|
||||
/// right: the *old* name must leave the index. A stale row here would be
|
||||
/// invisible in every other test — the new name is findable either way.
|
||||
#[test]
|
||||
fn renaming_a_node_replaces_the_name_in_the_search_index() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
db.upsert_node(&folder("root", None, "My Files")).unwrap();
|
||||
db.upsert_node(&file("f1", "root", "beforename.txt", 1))
|
||||
.unwrap();
|
||||
assert_eq!(db.search("beforename", 10).unwrap().len(), 1);
|
||||
|
||||
db.upsert_node(&file("f1", "root", "aftername.txt", 1))
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
db.search("aftername", 10).unwrap().len(),
|
||||
1,
|
||||
"the new name must be searchable"
|
||||
);
|
||||
assert_eq!(
|
||||
db.search("beforename", 10).unwrap().len(),
|
||||
0,
|
||||
"the old name must have left the index, not merely been added alongside"
|
||||
);
|
||||
}
|
||||
|
||||
/// B12: the cost of writing a listing must not scale with how much is already
|
||||
/// indexed. The old `DELETE FROM nodes_fts WHERE uid = ?` scanned the whole
|
||||
/// index once per node written, so a large account paid more to write the *same*
|
||||
/// folder — measured at 6.5 ms per node against a 17k-node index on the live DB.
|
||||
///
|
||||
/// Written as a ratio between two index sizes rather than an absolute time, so
|
||||
/// it fails on the scaling regression and not on a slow machine.
|
||||
#[test]
|
||||
fn writing_nodes_does_not_scale_with_the_size_of_the_index() {
|
||||
use std::time::Instant;
|
||||
|
||||
/// Fill `db` with `n` indexed nodes, then time re-writing a fixed batch.
|
||||
fn cost_against_index_of(n: usize) -> std::time::Duration {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
db.upsert_node(&folder("root", None, "My Files")).unwrap();
|
||||
let filler: Vec<_> = (0..n)
|
||||
.map(|i| file(&format!("bg{i}"), "root", &format!("background{i}.txt"), 1))
|
||||
.collect();
|
||||
db.upsert_nodes(&filler).unwrap();
|
||||
|
||||
// The batch under test is identical in both runs; only the amount of
|
||||
// already-indexed data around it differs.
|
||||
let batch: Vec<_> = (0..200)
|
||||
.map(|i| file(&format!("m{i}"), "root", &format!("measured{i}.txt"), 1))
|
||||
.collect();
|
||||
db.upsert_nodes(&batch).unwrap();
|
||||
|
||||
let t = Instant::now();
|
||||
db.upsert_nodes(&batch).unwrap();
|
||||
t.elapsed()
|
||||
}
|
||||
|
||||
let small = cost_against_index_of(200);
|
||||
let large = cost_against_index_of(5000);
|
||||
|
||||
// Calibration, measured while writing this: over the same 25× growth in
|
||||
// index size, the old full-scan path cost 6.4× more (46 ms → 294 ms) while
|
||||
// the rowid path costs 1.04× (39 ms → 41 ms). 3× sits well clear of both.
|
||||
println!("B12: 200-node write — against 200 indexed {small:?}, against 5000 {large:?}");
|
||||
assert!(
|
||||
large < small * 3,
|
||||
"writing a listing got dramatically more expensive as the index grew, \
|
||||
which is the B12 full-scan regression; small={small:?} large={large:?}"
|
||||
);
|
||||
}
|
||||
|
||||
fn activity(target: &str, kind: ActivityKind, ok: bool) -> ActivityEntry {
|
||||
ActivityEntry {
|
||||
time: 1700,
|
||||
@@ -622,6 +784,41 @@ fn opens_and_migrates() {
|
||||
assert_eq!(version, SCHEMA_VERSION.to_string());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn refuses_a_schema_newer_than_the_running_build() {
|
||||
let path = std::env::temp_dir().join(format!(
|
||||
"pdfs-db-future-{}-{}.db",
|
||||
std::process::id(),
|
||||
std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_nanos()
|
||||
));
|
||||
let conn = rusqlite::Connection::open(&path).unwrap();
|
||||
conn.execute_batch(
|
||||
"CREATE TABLE sync_state (key TEXT PRIMARY KEY, value TEXT);
|
||||
INSERT INTO sync_state VALUES ('schema_version', '9999');",
|
||||
)
|
||||
.unwrap();
|
||||
drop(conn);
|
||||
|
||||
let err = Db::open(&path)
|
||||
.err()
|
||||
.expect("future schema must fail closed");
|
||||
assert!(err.to_string().contains("newer than this build supports"));
|
||||
let conn = rusqlite::Connection::open(&path).unwrap();
|
||||
let version: String = conn
|
||||
.query_row(
|
||||
"SELECT value FROM sync_state WHERE key = 'schema_version'",
|
||||
[],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(version, "9999", "failed open must not rewrite the database");
|
||||
drop(conn);
|
||||
let _ = std::fs::remove_file(path);
|
||||
}
|
||||
|
||||
/// A queued write whose baseline is restamped must keep everything else.
|
||||
///
|
||||
/// The restamp happens after our *own* upload seals a new revision under a
|
||||
@@ -705,6 +902,39 @@ fn a_second_write_supersedes_the_first_pending_op() {
|
||||
assert_eq!(db.pending_op_counts().unwrap().uploads, 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_superseding_insert_keeps_the_old_pending_op() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let op = |blob: &str| PendingOp {
|
||||
id: 0,
|
||||
kind: OP_REVISION.to_string(),
|
||||
uid: uid("atomic").to_string(),
|
||||
parent_uid: None,
|
||||
name: None,
|
||||
blob_path: Some(blob.to_string()),
|
||||
meta_json: Some("{}".to_string()),
|
||||
created_at: 1,
|
||||
attempts: 0,
|
||||
last_error: None,
|
||||
next_attempt_at: 0,
|
||||
};
|
||||
db.enqueue_op(&op("/staging/original")).unwrap();
|
||||
db.with_conn(|conn| {
|
||||
conn.execute_batch(
|
||||
"CREATE TRIGGER reject_replacement BEFORE INSERT ON pending_op
|
||||
WHEN NEW.blob_path = '/staging/replacement'
|
||||
BEGIN SELECT RAISE(ABORT, 'injected insert failure'); END;",
|
||||
)?;
|
||||
Ok(())
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert!(db.enqueue_op(&op("/staging/replacement")).is_err());
|
||||
let ops = db.pending_ops().unwrap();
|
||||
assert_eq!(ops.len(), 1);
|
||||
assert_eq!(ops[0].blob_path.as_deref(), Some("/staging/original"));
|
||||
}
|
||||
|
||||
/// Deleting a folder that was created offline must take the ops queued
|
||||
/// underneath it with it: they name a placeholder parent that will now never
|
||||
/// become real, so nothing could ever drain them and nothing is left to
|
||||
@@ -1020,6 +1250,96 @@ fn pending_mode_is_queued_until_the_mode_is_reached() {
|
||||
assert_eq!(folder.pending_mode, None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn node_path_resolves_relative_to_a_sync_root_uid() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let root = node_from(serde_json::Value::Null, "root", "My Files", json!("Folder"));
|
||||
let videos = node_from(json!(uid("root")), "videos", "Videos", json!("Folder"));
|
||||
let anime = node_from(json!(uid("videos")), "anime", "anime", json!("Folder"));
|
||||
let show = node_from(json!(uid("anime")), "show", "Oshi no Ko", json!("Folder"));
|
||||
let episode = node_from(
|
||||
json!(uid("show")),
|
||||
"episode",
|
||||
"episode 01.mkv",
|
||||
json!({"File": {
|
||||
"media_type": "video/x-matroska",
|
||||
"total_size_on_storage": 42,
|
||||
"claimed_size": 42,
|
||||
"claimed_modification_time": null
|
||||
}}),
|
||||
);
|
||||
db.upsert_nodes(&[root, videos, anime, show, episode])
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
db.path_relative_to(&uid("videos").to_string(), &uid("episode").to_string())
|
||||
.unwrap()
|
||||
.as_deref(),
|
||||
Some("anime/Oshi no Ko/episode 01.mkv")
|
||||
);
|
||||
assert_eq!(
|
||||
db.path_relative_to(&uid("videos").to_string(), &uid("videos").to_string())
|
||||
.unwrap()
|
||||
.as_deref(),
|
||||
Some("")
|
||||
);
|
||||
assert_eq!(
|
||||
db.path_relative_to(&uid("anime").to_string(), &uid("episode").to_string())
|
||||
.unwrap()
|
||||
.as_deref(),
|
||||
Some("Oshi no Ko/episode 01.mkv")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn node_path_rejects_unrelated_missing_and_broken_ancestor_chains() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let root = node_from(serde_json::Value::Null, "root", "My Files", json!("Folder"));
|
||||
let videos = node_from(json!(uid("root")), "videos", "Videos", json!("Folder"));
|
||||
let episode = node_from(
|
||||
json!(uid("videos")),
|
||||
"episode",
|
||||
"episode.mkv",
|
||||
json!({"File": {
|
||||
"media_type": "video/x-matroska",
|
||||
"total_size_on_storage": 42,
|
||||
"claimed_size": 42,
|
||||
"claimed_modification_time": null
|
||||
}}),
|
||||
);
|
||||
let unrelated = node_from(
|
||||
json!(uid("root")),
|
||||
"documents",
|
||||
"Documents",
|
||||
json!("Folder"),
|
||||
);
|
||||
let orphan = node_from(
|
||||
json!(uid("missing-parent")),
|
||||
"orphan",
|
||||
"orphan.mkv",
|
||||
json!({"File": {
|
||||
"media_type": "video/x-matroska",
|
||||
"total_size_on_storage": 42,
|
||||
"claimed_size": 42,
|
||||
"claimed_modification_time": null
|
||||
}}),
|
||||
);
|
||||
db.upsert_nodes(&[root, videos, episode, unrelated, orphan])
|
||||
.unwrap();
|
||||
|
||||
for (ancestor, descendant) in [
|
||||
("documents", "episode"),
|
||||
("videos", "missing-node"),
|
||||
("videos", "orphan"),
|
||||
] {
|
||||
assert_eq!(
|
||||
db.path_relative_to(&uid(ancestor).to_string(), &uid(descendant).to_string())
|
||||
.unwrap(),
|
||||
None
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cache_index_touch_access_and_lru_order() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
@@ -1295,6 +1615,58 @@ fn next_due_op_skips_ops_blocked_on_a_local_parent() {
|
||||
assert_eq!(db.next_due_op(10).unwrap().unwrap().uid, "vol~link3");
|
||||
}
|
||||
|
||||
/// B70: a transient file's create is parked so its bytes never upload while it
|
||||
/// wears that name, the park survives a write attaching its blob, and the
|
||||
/// finalize rename (un-park) is what finally makes the completed file due.
|
||||
#[test]
|
||||
fn a_parked_transient_create_stays_off_the_drain_until_finalized() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let node = uid("dl").to_string();
|
||||
let parent = uid("root").to_string();
|
||||
db.enqueue_op(&PendingOp {
|
||||
id: 0,
|
||||
kind: OP_CREATE.to_string(),
|
||||
uid: node.clone(),
|
||||
parent_uid: Some(parent),
|
||||
name: Some("movie.mkv.part".to_string()),
|
||||
blob_path: None,
|
||||
meta_json: None,
|
||||
created_at: 1,
|
||||
attempts: 0,
|
||||
last_error: None,
|
||||
next_attempt_at: PARK_UNTIL,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// Parked: never selected, however far the clock advances.
|
||||
assert!(
|
||||
db.next_due_op(PARK_UNTIL - 1).unwrap().is_none(),
|
||||
"a parked create is never due"
|
||||
);
|
||||
|
||||
// A write attaches its blob to the create but must not wake it.
|
||||
let attached = db
|
||||
.attach_blob_to_create(&node, "/staging/blob1", "{}")
|
||||
.unwrap();
|
||||
assert!(attached.is_some(), "the blob attached to the create");
|
||||
assert!(
|
||||
db.next_due_op(PARK_UNTIL - 1).unwrap().is_none(),
|
||||
"still parked after a write attaches"
|
||||
);
|
||||
|
||||
// Finalize: un-park, and the completed file is due to upload with its bytes.
|
||||
assert!(
|
||||
db.set_create_hold(&node, false).unwrap(),
|
||||
"a create row was un-parked"
|
||||
);
|
||||
let due = db
|
||||
.next_due_op(1_000)
|
||||
.unwrap()
|
||||
.expect("the un-parked create is due");
|
||||
assert_eq!(due.uid, node);
|
||||
assert_eq!(due.blob_path.as_deref(), Some("/staging/blob1"));
|
||||
}
|
||||
|
||||
/// Backoff still gates: nothing is returned before an op is due.
|
||||
#[test]
|
||||
fn next_due_op_respects_backoff() {
|
||||
@@ -1450,3 +1822,93 @@ fn db_contention_under_fuse_worker_load() {
|
||||
serial / total as u32
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_db_has_children_and_trashed_filtering() {
|
||||
use proton_drive_rs::proton_sdk::ids::{LinkId, VolumeId};
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let parent_uid = NodeUid::new(VolumeId::from("vol"), LinkId::from("parent"));
|
||||
let child_uid = NodeUid::new(VolumeId::from("vol"), LinkId::from("child"));
|
||||
|
||||
assert!(
|
||||
!db.has_children(&parent_uid).unwrap(),
|
||||
"no children initially"
|
||||
);
|
||||
|
||||
let parent_node = Node {
|
||||
uid: parent_uid.clone(),
|
||||
parent_uid: None,
|
||||
name: "parent".into(),
|
||||
kind: NodeKind::Folder,
|
||||
creation_time: 100,
|
||||
modification_time: 100,
|
||||
trashed: false,
|
||||
is_shared: false,
|
||||
is_shared_publicly: false,
|
||||
signature_email: None,
|
||||
verification: Default::default(),
|
||||
};
|
||||
db.upsert_node(&parent_node).unwrap();
|
||||
|
||||
let mut child_node = Node {
|
||||
uid: child_uid.clone(),
|
||||
parent_uid: Some(parent_uid.clone()),
|
||||
name: "child.txt".into(),
|
||||
kind: NodeKind::File {
|
||||
media_type: "text/plain".into(),
|
||||
total_size_on_storage: 10,
|
||||
active_revision_state: None,
|
||||
active_revision_id: None,
|
||||
content_sha1: None,
|
||||
claimed_size: Some(10),
|
||||
claimed_modification_time: None,
|
||||
},
|
||||
creation_time: 100,
|
||||
modification_time: 100,
|
||||
trashed: false,
|
||||
is_shared: false,
|
||||
is_shared_publicly: false,
|
||||
signature_email: None,
|
||||
verification: Default::default(),
|
||||
};
|
||||
db.upsert_node(&child_node).unwrap();
|
||||
|
||||
assert!(db.has_children(&parent_uid).unwrap(), "child node present");
|
||||
|
||||
// Trashing child removes it from active children
|
||||
child_node.trashed = true;
|
||||
db.upsert_node(&child_node).unwrap();
|
||||
|
||||
assert!(
|
||||
!db.has_children(&parent_uid).unwrap(),
|
||||
"trashed child ignored"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_db_has_create_op() {
|
||||
let db = Db::open_in_memory().unwrap();
|
||||
let local_uid = "local~testnode12345678901234567890";
|
||||
|
||||
assert!(!db.has_create_op(local_uid).unwrap(), "no op initially");
|
||||
|
||||
let op = ops::PendingOp {
|
||||
id: 0,
|
||||
kind: ops::OP_CREATE.to_string(),
|
||||
uid: local_uid.to_string(),
|
||||
parent_uid: Some("vol~parent".to_string()),
|
||||
name: Some("test.txt".to_string()),
|
||||
blob_path: None,
|
||||
meta_json: None,
|
||||
created_at: 1000,
|
||||
attempts: 0,
|
||||
last_error: None,
|
||||
next_attempt_at: 0,
|
||||
};
|
||||
db.enqueue_op(&op).unwrap();
|
||||
|
||||
assert!(db.has_create_op(local_uid).unwrap(), "create op present");
|
||||
|
||||
db.delete_ops_for_uid(local_uid).unwrap();
|
||||
assert!(!db.has_create_op(local_uid).unwrap(), "op deleted");
|
||||
}
|
||||
@@ -1,5 +1,6 @@
|
||||
//! Crate-wide error type.
|
||||
|
||||
use proton_sdk::api::HumanVerification;
|
||||
use thiserror::Error;
|
||||
|
||||
use crate::control::ErrorKind;
|
||||
@@ -31,6 +32,15 @@ pub enum Error {
|
||||
#[error("saved session can no longer unlock your keys — run `pdfs login` again")]
|
||||
ReloginRequired,
|
||||
|
||||
/// The login was gated behind human verification. Not a failure the user can
|
||||
/// fix by retrying: the challenge has to be solved and the login restarted
|
||||
/// with the resulting token (see [`auth::login_verified`](crate::auth::login_verified)).
|
||||
///
|
||||
/// Carries the challenge rather than just a message so a front-end can
|
||||
/// present it; a front-end that cannot (no webview) still has prose to show.
|
||||
#[error("sign-in needs human verification — complete the CAPTCHA to continue")]
|
||||
HumanVerificationRequired(Box<HumanVerification>),
|
||||
|
||||
#[error("{0}")]
|
||||
Other(String),
|
||||
}
|
||||
@@ -154,7 +164,9 @@ impl From<serde_json::Error> for CoreError {
|
||||
impl From<Error> for CoreError {
|
||||
fn from(e: Error) -> Self {
|
||||
let kind = match &e {
|
||||
Error::NotLoggedIn | Error::ReloginRequired => ErrorKind::Denied,
|
||||
Error::NotLoggedIn | Error::ReloginRequired | Error::HumanVerificationRequired(_) => {
|
||||
ErrorKind::Denied
|
||||
}
|
||||
Error::Proton(proton_sdk::ProtonError::Api(api)) => api_kind(api.code),
|
||||
// A `ProtonError` that never reached the API is a transport failure.
|
||||
Error::Proton(_) => ErrorKind::Offline,
|
||||
|
||||
@@ -9,8 +9,11 @@ pub mod control;
|
||||
pub mod db;
|
||||
pub mod error;
|
||||
pub mod localindex;
|
||||
pub mod profile;
|
||||
pub mod search;
|
||||
pub mod service;
|
||||
pub mod shell;
|
||||
pub mod syncignore;
|
||||
|
||||
pub use error::{CoreError, CoreResult, Error, Result};
|
||||
|
||||
|
||||
@@ -0,0 +1,171 @@
|
||||
//! The machine profile that travels with a device (features.md 5.3).
|
||||
//!
|
||||
//! Sync folder mappings, pins, and the settings that shape them live in
|
||||
//! `cache.db` and `config.json` — both on the local disk. When that disk dies,
|
||||
//! the remote data survives but the *arrangement* of it does not: which folders
|
||||
//! were synced, where they lived locally, which were on-demand, what was pinned.
|
||||
//!
|
||||
//! So the daemon mirrors that arrangement into a `profile.json` in its device's
|
||||
//! root folder on Drive. It goes up the normal upload path, which means it is
|
||||
//! end-to-end encrypted with the account keys like any other file — 5.3's
|
||||
//! "encrypt with the user's Proton keys" is satisfied by *not* special-casing
|
||||
//! it. It lives under the device rather than the Drive root because it describes
|
||||
//! that device; adopting the device is what makes it relevant.
|
||||
//!
|
||||
//! This module is pure data. The upload/download and the restore flow live in
|
||||
//! `pdfs-fuse`, next to the client that performs them.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
/// File name of the profile inside the device root folder.
|
||||
pub const PROFILE_FILE_NAME: &str = "profile.json";
|
||||
|
||||
/// Format version of the profile document.
|
||||
///
|
||||
/// Bumped only for changes a *reader* cannot survive. Adding fields does not
|
||||
/// qualify — unknown fields are ignored on the way in, so an older client reads
|
||||
/// a newer profile's common subset. A newer `version` than this is refused
|
||||
/// outright rather than half-applied: a restore that silently drops folders it
|
||||
/// did not understand is worse than one that tells you to upgrade.
|
||||
pub const PROFILE_VERSION: u32 = 1;
|
||||
|
||||
/// One synced folder, as it was arranged on the machine that wrote the profile.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
pub struct ProfileFolder {
|
||||
/// Uid of the folder's remote root, under the device root. The stable
|
||||
/// identity — the local path may not exist on the restoring machine, but
|
||||
/// this does.
|
||||
pub remote_uid: String,
|
||||
/// Absolute local path it was synced to. A *suggestion* on restore: another
|
||||
/// machine may have a different username, home, or mount layout.
|
||||
pub local_path: String,
|
||||
/// `mirror` or `ondemand`.
|
||||
pub mode: String,
|
||||
}
|
||||
|
||||
/// One pinned node (P5 pins), as `pins` stores it.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
pub struct ProfilePin {
|
||||
pub uid: String,
|
||||
/// Mountpoint-relative path, kept for display: a pin whose node has been
|
||||
/// deleted should still be nameable in a restore summary.
|
||||
pub path: String,
|
||||
pub recursive: bool,
|
||||
}
|
||||
|
||||
/// The full arrangement of one machine.
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
pub struct Profile {
|
||||
pub version: u32,
|
||||
/// The device this profile describes.
|
||||
pub device_uid: String,
|
||||
/// Hostname of the machine that wrote it, so a restore prompt can say
|
||||
/// *"restore settings from laptop-xyz?"* rather than quoting a uid.
|
||||
pub hostname: String,
|
||||
/// When it was written, epoch seconds.
|
||||
pub saved_at: i64,
|
||||
#[serde(default)]
|
||||
pub folders: Vec<ProfileFolder>,
|
||||
#[serde(default)]
|
||||
pub pins: Vec<ProfilePin>,
|
||||
/// Global sync ignore patterns. Safe to restore as-is.
|
||||
#[serde(default)]
|
||||
pub ignore_patterns: Option<Vec<String>>,
|
||||
/// Machine-shaped settings. Carried, but never applied without asking: a
|
||||
/// laptop's 5 GB cache budget and `~/ProtonDrive` mountpoint are not
|
||||
/// obviously right on the next machine.
|
||||
#[serde(default)]
|
||||
pub cache_budget: Option<u64>,
|
||||
#[serde(default)]
|
||||
pub mountpoint: Option<String>,
|
||||
}
|
||||
|
||||
impl Profile {
|
||||
/// Parse a profile document, refusing one written by a newer client.
|
||||
pub fn parse(bytes: &[u8]) -> Result<Self, String> {
|
||||
let profile: Profile =
|
||||
serde_json::from_slice(bytes).map_err(|e| format!("malformed profile.json: {e}"))?;
|
||||
if profile.version > PROFILE_VERSION {
|
||||
return Err(format!(
|
||||
"profile.json was written by a newer client (version {}, this client understands {PROFILE_VERSION}); upgrade to restore it",
|
||||
profile.version
|
||||
));
|
||||
}
|
||||
Ok(profile)
|
||||
}
|
||||
|
||||
/// Serialize for upload. Pretty-printed: it is a small file a user may well
|
||||
/// open in the web UI to see what their machine had.
|
||||
pub fn to_bytes(&self) -> Result<Vec<u8>, String> {
|
||||
serde_json::to_vec_pretty(self).map_err(|e| format!("serialize profile: {e}"))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn sample() -> Profile {
|
||||
Profile {
|
||||
version: PROFILE_VERSION,
|
||||
device_uid: "dev-1".to_string(),
|
||||
hostname: "laptop-xyz".to_string(),
|
||||
saved_at: 1_700_000_000,
|
||||
folders: vec![ProfileFolder {
|
||||
remote_uid: "vol~link".to_string(),
|
||||
local_path: "/home/nils/Documents".to_string(),
|
||||
mode: "mirror".to_string(),
|
||||
}],
|
||||
pins: vec![ProfilePin {
|
||||
uid: "vol~pin".to_string(),
|
||||
path: "Photos/2024".to_string(),
|
||||
recursive: true,
|
||||
}],
|
||||
ignore_patterns: Some(vec!["target/".to_string()]),
|
||||
cache_budget: Some(5_000_000_000),
|
||||
mountpoint: Some("/home/nils/ProtonDrive".to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_trips() {
|
||||
let p = sample();
|
||||
assert_eq!(Profile::parse(&p.to_bytes().unwrap()).unwrap(), p);
|
||||
}
|
||||
|
||||
/// A field added by a later client must not break this one's restore: the
|
||||
/// common subset is still usable, which is the whole reason `version` is
|
||||
/// reserved for breaking changes only.
|
||||
#[test]
|
||||
fn unknown_fields_are_ignored() {
|
||||
let json = br#"{
|
||||
"version": 1,
|
||||
"device_uid": "dev-1",
|
||||
"hostname": "laptop-xyz",
|
||||
"saved_at": 1,
|
||||
"folders": [],
|
||||
"something_from_the_future": {"a": 1}
|
||||
}"#;
|
||||
let p = Profile::parse(json).unwrap();
|
||||
assert_eq!(p.device_uid, "dev-1");
|
||||
assert!(p.folders.is_empty());
|
||||
}
|
||||
|
||||
/// Missing optional sections read as empty rather than failing: a profile
|
||||
/// written before pins existed is still a valid folder mapping.
|
||||
#[test]
|
||||
fn absent_sections_default() {
|
||||
let json = br#"{"version":1,"device_uid":"d","hostname":"h","saved_at":0}"#;
|
||||
let p = Profile::parse(json).unwrap();
|
||||
assert!(p.pins.is_empty());
|
||||
assert!(p.ignore_patterns.is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn future_version_is_refused() {
|
||||
let mut p = sample();
|
||||
p.version = PROFILE_VERSION + 1;
|
||||
let err = Profile::parse(&p.to_bytes().unwrap()).unwrap_err();
|
||||
assert!(err.contains("newer client"), "{err}");
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,214 @@
|
||||
//! Shared, deterministic search-result relevance scoring.
|
||||
//!
|
||||
//! The scorer deliberately operates on a small candidate set rather than
|
||||
//! replacing an index. Callers should use SQLite (or another index) to find
|
||||
//! candidates, then use this module to put local and remote results on the
|
||||
//! same relevance scale.
|
||||
|
||||
/// Scores a candidate against a user query.
|
||||
///
|
||||
/// Every query term must match either `basename` or `parent_path`. Basename
|
||||
/// matches are weighted twice as strongly as path matches. The returned score
|
||||
/// is stable and only meaningful when compared with scores produced by this
|
||||
/// function.
|
||||
#[must_use]
|
||||
pub fn relevance_score(query: &str, basename: &str, parent_path: &str) -> Option<i64> {
|
||||
let query = normalize(query);
|
||||
if query.is_empty() {
|
||||
return Some(0);
|
||||
}
|
||||
|
||||
let name = normalize(basename);
|
||||
let path = normalize(parent_path);
|
||||
let query_terms: Vec<_> = query.split_whitespace().collect();
|
||||
let name_words: Vec<_> = name.split_whitespace().collect();
|
||||
let path_words: Vec<_> = path.split_whitespace().collect();
|
||||
|
||||
let mut total = 0_i64;
|
||||
for term in query_terms {
|
||||
let name_score = field_term_score(term, &name, &name_words).map(|score| score * 2);
|
||||
let path_score = field_term_score(term, &path, &path_words);
|
||||
total += name_score.into_iter().chain(path_score).max()?;
|
||||
}
|
||||
|
||||
// Whole-field bonuses make ordering intuitive without changing whether a
|
||||
// candidate matches. They dominate small differences between term scores.
|
||||
if name == query {
|
||||
total += 20_000;
|
||||
} else if name.starts_with(&query) {
|
||||
total += 10_000;
|
||||
} else if name.contains(&query) {
|
||||
total += 4_000;
|
||||
}
|
||||
|
||||
Some(total)
|
||||
}
|
||||
|
||||
fn normalize(value: &str) -> String {
|
||||
let mut normalized = String::with_capacity(value.len());
|
||||
let mut last_was_space = true;
|
||||
|
||||
for character in value.chars().flat_map(char::to_lowercase) {
|
||||
if character.is_alphanumeric() {
|
||||
normalized.push(character);
|
||||
last_was_space = false;
|
||||
} else if !last_was_space {
|
||||
normalized.push(' ');
|
||||
last_was_space = true;
|
||||
}
|
||||
}
|
||||
|
||||
if last_was_space {
|
||||
normalized.pop();
|
||||
}
|
||||
normalized
|
||||
}
|
||||
|
||||
fn field_term_score(term: &str, field: &str, words: &[&str]) -> Option<i64> {
|
||||
if field == term {
|
||||
return Some(10_000);
|
||||
}
|
||||
if field.starts_with(term) {
|
||||
return Some(8_500);
|
||||
}
|
||||
if words.contains(&term) {
|
||||
return Some(8_000);
|
||||
}
|
||||
if words.iter().any(|word| word.starts_with(term)) {
|
||||
return Some(7_000);
|
||||
}
|
||||
if field.contains(term) {
|
||||
return Some(6_000);
|
||||
}
|
||||
|
||||
// Subsequence matching supports useful abbreviations such as "qtrrpt".
|
||||
let subsequence = std::iter::once(field)
|
||||
.chain(words.iter().copied())
|
||||
.filter_map(|word| subsequence_gap(term, word))
|
||||
.min();
|
||||
if let Some(gap) = subsequence {
|
||||
return Some(4_500 - i64::try_from(gap.min(500)).unwrap_or(500));
|
||||
}
|
||||
|
||||
// Typo matching is deliberately restricted to substantial terms to avoid
|
||||
// noisy matches for one- and two-letter searches.
|
||||
if term.chars().count() >= 4
|
||||
&& words
|
||||
.iter()
|
||||
.any(|word| bounded_damerau_levenshtein(term, word, typo_limit(term)))
|
||||
{
|
||||
return Some(3_500);
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
fn subsequence_gap(needle: &str, haystack: &str) -> Option<usize> {
|
||||
let needle_length = needle.chars().count();
|
||||
let mut needle = needle.chars();
|
||||
let mut wanted = needle.next()?;
|
||||
let mut first = None;
|
||||
|
||||
for (index, character) in haystack.chars().enumerate() {
|
||||
if character == wanted {
|
||||
first.get_or_insert(index);
|
||||
match needle.next() {
|
||||
Some(next) => wanted = next,
|
||||
None => return Some(index + 1 - first.unwrap_or(index) - needle_length),
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn typo_limit(term: &str) -> usize {
|
||||
usize::from(term.chars().count() >= 5) + 1
|
||||
}
|
||||
|
||||
/// A bounded optimal-string-alignment distance check. This treats a single
|
||||
/// adjacent transposition (for example, `vidoe`) as one edit.
|
||||
fn bounded_damerau_levenshtein(left: &str, right: &str, limit: usize) -> bool {
|
||||
let left: Vec<_> = left.chars().collect();
|
||||
let right: Vec<_> = right.chars().collect();
|
||||
if left.len().abs_diff(right.len()) > limit || left.len().max(right.len()) > 64 {
|
||||
return false;
|
||||
}
|
||||
|
||||
let mut distances = vec![vec![0_usize; right.len() + 1]; left.len() + 1];
|
||||
for (index, row) in distances.iter_mut().enumerate() {
|
||||
row[0] = index;
|
||||
}
|
||||
for (index, distance) in distances[0].iter_mut().enumerate() {
|
||||
*distance = index;
|
||||
}
|
||||
|
||||
for i in 1..=left.len() {
|
||||
for j in 1..=right.len() {
|
||||
let cost = usize::from(left[i - 1] != right[j - 1]);
|
||||
distances[i][j] = (distances[i - 1][j] + 1)
|
||||
.min(distances[i][j - 1] + 1)
|
||||
.min(distances[i - 1][j - 1] + cost);
|
||||
if i > 1 && j > 1 && left[i - 1] == right[j - 2] && left[i - 2] == right[j - 1] {
|
||||
distances[i][j] = distances[i][j].min(distances[i - 2][j - 2] + 1);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
distances[left.len()][right.len()] <= limit
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::relevance_score;
|
||||
|
||||
#[test]
|
||||
fn exact_name_beats_prefix_and_substring() {
|
||||
let exact = relevance_score("report", "report", "work").unwrap();
|
||||
let prefix = relevance_score("report", "report final", "work").unwrap();
|
||||
let substring = relevance_score("report", "annual report", "work").unwrap();
|
||||
assert!(exact > prefix);
|
||||
assert!(prefix > substring);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn basename_is_weighted_above_parent_path() {
|
||||
let name = relevance_score("budget", "budget notes", "archive").unwrap();
|
||||
let path = relevance_score("budget", "notes", "work/budget").unwrap();
|
||||
assert!(name > path);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn matches_typos_and_adjacent_transpositions() {
|
||||
assert!(relevance_score("vedio", "video.mp4", "media").is_some());
|
||||
assert!(relevance_score("vidoe", "video.mp4", "media").is_some());
|
||||
assert!(relevance_score("presentaton", "presentation.pdf", "work").is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn separators_form_searchable_word_boundaries() {
|
||||
assert!(relevance_score("final draft", "Final_Draft-v2.pdf", "work").is_some());
|
||||
assert!(relevance_score("quarter report", "quarterly-report.pdf", "work").is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unicode_case_folding_preserves_accented_matches() {
|
||||
assert!(relevance_score("CAFÉ", "Café Photos", "Trips").is_some());
|
||||
assert!(relevance_score("ångström", "ÅNGSTRÖM notes", "Research").is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn matches_terms_across_name_and_path() {
|
||||
assert!(relevance_score("tax invoice", "invoice-1042.pdf", "archive/tax/2025").is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ordered_subsequence_supports_abbreviations() {
|
||||
assert!(relevance_score("qtrrpt", "quarter-report.pdf", "finance").is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unrelated_candidates_and_short_typos() {
|
||||
assert_eq!(relevance_score("video", "holiday.jpg", "photos"), None);
|
||||
assert_eq!(relevance_score("xy", "xz.txt", "misc"), None);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,347 @@
|
||||
//! Selective-sync ignore rules for mirror folders (features.md 1.1).
|
||||
//!
|
||||
//! A mirror folder otherwise uploads every path beneath its root, which for a
|
||||
//! project directory means `node_modules/`, `.git/`, and `target/` — quota
|
||||
//! spent on files nobody wants on Drive, and enough API traffic to invite rate
|
||||
//! limiting.
|
||||
//!
|
||||
//! Rules come from two places, unioned:
|
||||
//!
|
||||
//! * `.pdfsignore` (or `.protonignore`) at the root of the synced folder,
|
||||
//! gitignore syntax.
|
||||
//! * A global pattern list from the config, applied to every synced folder.
|
||||
//!
|
||||
//! Both are read fresh at the start of each reconcile pass, so editing the file
|
||||
//! takes effect on the next pass without restarting the daemon.
|
||||
//!
|
||||
//! # Ignoring is not deleting
|
||||
//!
|
||||
//! A path that becomes ignored after it was already synced keeps its remote
|
||||
//! copy and its baseline row. The sync engine drops ignored paths from
|
||||
//! classification entirely rather than treating them as locally deleted —
|
||||
//! see the union filter in `pdfs-fuse`'s `do_reconcile`. Editing a text file
|
||||
//! must never trash data on Drive.
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use ignore::gitignore::{Gitignore, GitignoreBuilder};
|
||||
|
||||
/// Patterns applied to every synced folder when the config does not override
|
||||
/// them. Version-control metadata, dependency and build trees, editor
|
||||
/// leftovers, and OS turds — none of which belong on Drive, all of which are
|
||||
/// large or rewritten constantly.
|
||||
pub const DEFAULT_IGNORE_PATTERNS: &[&str] = &[
|
||||
".git/",
|
||||
".hg/",
|
||||
".svn/",
|
||||
"node_modules/",
|
||||
"target/",
|
||||
".venv/",
|
||||
"__pycache__/",
|
||||
"*~",
|
||||
"*.swp",
|
||||
"*.tmp",
|
||||
".DS_Store",
|
||||
"Thumbs.db",
|
||||
];
|
||||
|
||||
/// Suffixes of files that are, by convention, incomplete or throwaway while they
|
||||
/// wear the name: a download in flight, an editor's swap or backup, an atomic
|
||||
/// write's scratch copy. On an on-demand mount these should never seal a remote
|
||||
/// revision — the app renames the finished file to its real name, and only that
|
||||
/// belongs on Drive. See [`is_transient_name`] and docs/BUGS.md B70.
|
||||
const TRANSIENT_SUFFIXES: &[&str] = &[
|
||||
".crdownload", // Chromium/Brave/Edge
|
||||
".part", // Firefox, wget, aria2c
|
||||
".partial", // some downloaders / older IE
|
||||
".download", // Safari / macOS
|
||||
".tmp", // generic scratch
|
||||
".temp", // generic scratch
|
||||
".swp", // vim swap
|
||||
".swx", // vim swap (secondary)
|
||||
];
|
||||
|
||||
/// Whether `name` is a transient scratch/in-flight file whose bytes should not
|
||||
/// be uploaded on an on-demand mount until it is renamed to its finished name.
|
||||
///
|
||||
/// Recognises browser download temps, editor swap/backup files, and lock files.
|
||||
/// Case-insensitive on the suffix so `FOO.CRDOWNLOAD` counts too. This is the
|
||||
/// on-demand-write counterpart to [`DEFAULT_IGNORE_PATTERNS`] (which only covers
|
||||
/// mirror-folder reconcile); keep the two conceptually in step.
|
||||
pub fn is_transient_name(name: &str) -> bool {
|
||||
let lower = name.to_ascii_lowercase();
|
||||
if TRANSIENT_SUFFIXES.iter().any(|s| lower.ends_with(s)) {
|
||||
return true;
|
||||
}
|
||||
// Emacs/gedit/kate backup copies.
|
||||
if name.ends_with('~') {
|
||||
return true;
|
||||
}
|
||||
// LibreOffice lock files (`.~lock.<doc>#`) and MS Office temps (`~$doc`).
|
||||
if name.starts_with(".~lock.") || name.starts_with("~$") {
|
||||
return true;
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
/// Filenames accepted as a folder's ignore file, in precedence order.
|
||||
const IGNORE_FILE_NAMES: &[&str] = &[".pdfsignore", ".protonignore"];
|
||||
|
||||
/// Compiled ignore rules for one synced folder.
|
||||
pub struct IgnoreRules {
|
||||
matcher: Option<Gitignore>,
|
||||
}
|
||||
|
||||
impl IgnoreRules {
|
||||
/// Build the rules for a folder rooted at `root`: `globals` first, then any
|
||||
/// ignore file found at the root, so a folder-local rule can negate a
|
||||
/// global one with `!pattern`.
|
||||
///
|
||||
/// Malformed patterns are skipped individually rather than failing the
|
||||
/// load — a typo in `.pdfsignore` must not take the folder's sync down.
|
||||
pub fn load(root: &Path, globals: &[String]) -> Self {
|
||||
let mut builder = GitignoreBuilder::new(root);
|
||||
let mut any = false;
|
||||
|
||||
for pattern in globals {
|
||||
if builder.add_line(None, pattern).is_ok() {
|
||||
any = true;
|
||||
}
|
||||
}
|
||||
|
||||
for name in IGNORE_FILE_NAMES {
|
||||
let path = root.join(name);
|
||||
if !path.is_file() {
|
||||
continue;
|
||||
}
|
||||
// `add` returns the first parse error but still takes the lines it
|
||||
// could read, so a bad line costs that line and nothing more.
|
||||
let _ = builder.add(&path);
|
||||
any = true;
|
||||
break;
|
||||
}
|
||||
|
||||
if !any {
|
||||
return Self { matcher: None };
|
||||
}
|
||||
Self {
|
||||
matcher: builder.build().ok(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Rules matching nothing, for callers with no folder context.
|
||||
pub fn empty() -> Self {
|
||||
Self { matcher: None }
|
||||
}
|
||||
|
||||
/// Whether any rule is loaded. When false, [`is_ignored`](Self::is_ignored)
|
||||
/// is always false and callers can skip filtering entirely.
|
||||
pub fn is_empty(&self) -> bool {
|
||||
self.matcher.is_none()
|
||||
}
|
||||
|
||||
/// Whether `rel` — a `/`-joined path relative to the folder root — is
|
||||
/// ignored.
|
||||
///
|
||||
/// A path under an ignored directory is ignored too. `Gitignore` matches
|
||||
/// one path against one rule set and does not walk parents itself, so each
|
||||
/// ancestor is tested as a directory. This is what makes filtering the
|
||||
/// classification union sound: the engine can ask about any path in
|
||||
/// isolation, in any order, without having walked its parents first.
|
||||
pub fn is_ignored(&self, rel: &str, is_dir: bool) -> bool {
|
||||
let Some(matcher) = &self.matcher else {
|
||||
return false;
|
||||
};
|
||||
if rel.is_empty() {
|
||||
return false;
|
||||
}
|
||||
|
||||
let mut prefix = String::new();
|
||||
let mut parts = rel.split('/').peekable();
|
||||
while let Some(part) = parts.next() {
|
||||
if !prefix.is_empty() {
|
||||
prefix.push('/');
|
||||
}
|
||||
prefix.push_str(part);
|
||||
let last = parts.peek().is_none();
|
||||
// Every ancestor is a directory; only the final component's kind
|
||||
// is the caller's to say.
|
||||
let as_dir = if last { is_dir } else { true };
|
||||
if matcher.matched(&prefix, as_dir).is_ignore() {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for IgnoreRules {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.debug_struct("IgnoreRules")
|
||||
.field("active", &!self.is_empty())
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// A unique temp directory removed on drop; avoids a dev-dependency, as in
|
||||
/// [`crate::cache`]'s tests.
|
||||
struct TempDir(std::path::PathBuf);
|
||||
impl TempDir {
|
||||
fn new() -> Self {
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
static N: AtomicU64 = AtomicU64::new(0);
|
||||
let p = std::env::temp_dir().join(format!(
|
||||
"pdfs-ignore-{}-{}",
|
||||
std::process::id(),
|
||||
N.fetch_add(1, Ordering::Relaxed)
|
||||
));
|
||||
std::fs::create_dir_all(&p).unwrap();
|
||||
TempDir(p)
|
||||
}
|
||||
fn path(&self) -> &Path {
|
||||
&self.0
|
||||
}
|
||||
}
|
||||
impl Drop for TempDir {
|
||||
fn drop(&mut self) {
|
||||
let _ = std::fs::remove_dir_all(&self.0);
|
||||
}
|
||||
}
|
||||
|
||||
fn globals() -> Vec<String> {
|
||||
DEFAULT_IGNORE_PATTERNS
|
||||
.iter()
|
||||
.map(|s| (*s).to_string())
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn write(root: &Path, name: &str, body: &str) {
|
||||
std::fs::write(root.join(name), body).unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_rules_at_all_ignores_nothing() {
|
||||
let dir = TempDir::new();
|
||||
let rules = IgnoreRules::load(dir.path(), &[]);
|
||||
assert!(rules.is_empty());
|
||||
assert!(!rules.is_ignored("anything", false));
|
||||
assert!(!rules.is_ignored("deep/nested/path.rs", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn global_defaults_match_without_an_ignore_file() {
|
||||
let dir = TempDir::new();
|
||||
let rules = IgnoreRules::load(dir.path(), &globals());
|
||||
assert!(rules.is_ignored("node_modules", true));
|
||||
assert!(rules.is_ignored("target", true));
|
||||
assert!(rules.is_ignored("notes.txt~", false));
|
||||
assert!(!rules.is_ignored("src/main.rs", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_path_under_an_ignored_directory_is_ignored() {
|
||||
let dir = TempDir::new();
|
||||
let rules = IgnoreRules::load(dir.path(), &globals());
|
||||
// The engine asks about deep paths in isolation, so each must answer
|
||||
// correctly without its parents having been tested first.
|
||||
assert!(rules.is_ignored("node_modules/left-pad/index.js", false));
|
||||
assert!(rules.is_ignored("node_modules/left-pad", true));
|
||||
assert!(rules.is_ignored("target/debug/build/x/out", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_folder_ignore_file_adds_to_the_globals() {
|
||||
let dir = TempDir::new();
|
||||
write(dir.path(), ".pdfsignore", "secrets/\n*.log\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &globals());
|
||||
assert!(rules.is_ignored("secrets/key.pem", false));
|
||||
assert!(rules.is_ignored("run.log", false));
|
||||
// Globals still apply alongside the file.
|
||||
assert!(rules.is_ignored("node_modules", true));
|
||||
assert!(!rules.is_ignored("run.txt", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_folder_rule_can_negate_a_global_one() {
|
||||
let dir = TempDir::new();
|
||||
write(dir.path(), ".pdfsignore", "!keep.tmp\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &globals());
|
||||
assert!(rules.is_ignored("scratch.tmp", false));
|
||||
assert!(!rules.is_ignored("keep.tmp", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn protonignore_is_accepted_as_an_alias() {
|
||||
let dir = TempDir::new();
|
||||
write(dir.path(), ".protonignore", "build/\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &[]);
|
||||
assert!(rules.is_ignored("build/out.o", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn pdfsignore_wins_when_both_files_exist() {
|
||||
let dir = TempDir::new();
|
||||
write(dir.path(), ".pdfsignore", "from-pdfs/\n");
|
||||
write(dir.path(), ".protonignore", "from-proton/\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &[]);
|
||||
assert!(rules.is_ignored("from-pdfs/x", false));
|
||||
assert!(!rules.is_ignored("from-proton/x", false));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_malformed_pattern_does_not_take_the_rest_down() {
|
||||
let dir = TempDir::new();
|
||||
// An unclosed character class is not a valid glob.
|
||||
write(dir.path(), ".pdfsignore", "[unclosed\nvalid/\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &globals());
|
||||
assert!(rules.is_ignored("valid/x", false));
|
||||
assert!(rules.is_ignored("node_modules", true));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_root_itself_is_never_ignored() {
|
||||
let dir = TempDir::new();
|
||||
write(dir.path(), ".pdfsignore", "*\n");
|
||||
let rules = IgnoreRules::load(dir.path(), &[]);
|
||||
// A blanket rule must not classify the folder root, or the pass would
|
||||
// have nothing to reconcile against.
|
||||
assert!(!rules.is_ignored("", true));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn transient_download_and_editor_names_are_recognised() {
|
||||
for name in [
|
||||
"Unconfirmed 540477.crdownload",
|
||||
"movie.mkv.part",
|
||||
"big.iso.partial",
|
||||
"photo.jpg.download",
|
||||
"export.xml.tmp",
|
||||
"notes.TEMP",
|
||||
".notes.txt.swp",
|
||||
"doc.txt~",
|
||||
".~lock.report.odt#",
|
||||
"~$budget.xlsx",
|
||||
"FOO.CRDOWNLOAD",
|
||||
] {
|
||||
assert!(is_transient_name(name), "{name} should be transient");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn finished_names_are_not_transient() {
|
||||
for name in [
|
||||
"teamspeak.tar.gz",
|
||||
"nils.zip",
|
||||
"report.xml",
|
||||
"archive.partly.zip", // ".partly" is not ".part"
|
||||
"template.dotx",
|
||||
"readme",
|
||||
] {
|
||||
assert!(!is_transient_name(name), "{name} should not be transient");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,398 @@
|
||||
//! Remote-event invalidation and local-index background workers.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// Drop `uid` from one mount's tree and tell that mount's kernel session the
|
||||
/// entry is gone. Shared by the trash and delete paths, which differ only in
|
||||
/// which event carried them.
|
||||
///
|
||||
/// Returns whether this mount actually held the node, so the caller can evict
|
||||
/// its content blob once if *any* mount did.
|
||||
fn forget_and_notify(st: &mut State, notifier: Option<&Notifier>, uid: &NodeUid) -> bool {
|
||||
// Capture the inode before `forget` clears the uid mapping.
|
||||
let child = st.by_uid.get(uid).copied();
|
||||
let Some((parent, name)) = st.forget(uid) else {
|
||||
return false;
|
||||
};
|
||||
if let Some(notifier) = notifier {
|
||||
match child {
|
||||
Some(child) => {
|
||||
let _ = notifier.delete(INodeNo(parent), INodeNo(child), OsStr::new(&name));
|
||||
}
|
||||
None => {
|
||||
let _ = notifier.inval_entry(INodeNo(parent), OsStr::new(&name));
|
||||
}
|
||||
}
|
||||
}
|
||||
true
|
||||
}
|
||||
|
||||
/// Apply one remote event to the local cache and notify the kernel so it drops
|
||||
/// any stale cached metadata/data for the affected inodes.
|
||||
///
|
||||
/// The cache is authoritative-by-absence: dropping a directory's `children`
|
||||
/// entry forces the next `lookup`/`readdir` to re-enumerate from the remote, so
|
||||
/// most events only need to invalidate listings rather than re-fetch eagerly.
|
||||
///
|
||||
/// Applied to **every** mounted inode space, not just the primary one. This task
|
||||
/// is per-daemon while node state is per-mount, and a `DriveEvent` names a uid,
|
||||
/// not a mount — so a file trashed from another device has to be withdrawn from
|
||||
/// whichever of our sessions is showing it, which for anything under a sync
|
||||
/// folder is a [`Core::fork_state`] fork rather than `core.state`. Reaching for
|
||||
/// the primary state alone left forks serving a deleted file indefinitely, the
|
||||
/// read-side twin of `docs/BUGS.md` B74. Inode numbers are per-mount, so each
|
||||
/// mount must be notified through its **own** channel; that pairing is what
|
||||
/// [`Core::for_each_mount`] exists to preserve.
|
||||
fn apply_event(core: &Core, event: &DriveEvent, dirty: &mut DirtyParents) {
|
||||
match event {
|
||||
DriveEvent::NodeUpdated {
|
||||
node_uid,
|
||||
parent_node_uid,
|
||||
is_trashed,
|
||||
..
|
||||
} => {
|
||||
// A node we owe an upload for is *ahead* of the remote, not behind
|
||||
// it: this event is almost always the echo of our own empty-file
|
||||
// create, and re-fetching would replace the size and mtime of the
|
||||
// write we just accepted with the stale revision's — making a file
|
||||
// that was copied in seconds ago read as empty until its upload
|
||||
// lands (offline.md Phase 3).
|
||||
//
|
||||
// A write that has already drained is the same story one step later:
|
||||
// the drain brought the tree level with the revision it sealed, so
|
||||
// the feed's report of that revision has nothing to add, and acting
|
||||
// on it evicts the very bytes we uploaded. Claimed unconditionally,
|
||||
// even for a trash, so an echo we no longer care about does not
|
||||
// linger to suppress a later foreign change.
|
||||
let echo = core.take_self_change(node_uid);
|
||||
let ours = !*is_trashed && (echo || core.pending.lock().contains_key(node_uid));
|
||||
if ours {
|
||||
debug!(uid = %node_uid, "ignoring remote event for a node with a queued write");
|
||||
}
|
||||
let mut had_node = false;
|
||||
core.for_each_mount(|st, notifier| {
|
||||
if *is_trashed {
|
||||
// Trashing makes a node vanish from its parent listing.
|
||||
had_node |= forget_and_notify(st, notifier, node_uid);
|
||||
} else if !ours && let Some(&ino) = st.by_uid.get(node_uid) {
|
||||
// Known node changed: drop its cached attrs/data (and
|
||||
// listing if it is a directory) so the next access
|
||||
// re-fetches. Its content blob may now be stale too.
|
||||
had_node = true;
|
||||
st.invalidate_listing(ino);
|
||||
if let Some(notifier) = notifier {
|
||||
let _ = notifier.inval_inode(INodeNo(ino), 0, 0);
|
||||
}
|
||||
}
|
||||
});
|
||||
// Once, not once per mount: the content cache is per-daemon.
|
||||
if had_node {
|
||||
core.cache.evict(node_uid);
|
||||
}
|
||||
// A create, rename or move-in shows up as a change to the parent
|
||||
// listing too, which is recorded for the end of the batch rather
|
||||
// than acted on here — see [`DirtyParents`].
|
||||
if let Some(parent_uid) = parent_node_uid {
|
||||
match ours {
|
||||
true => dirty
|
||||
.ours
|
||||
.entry(parent_uid.clone())
|
||||
.or_default()
|
||||
.insert(node_uid.clone()),
|
||||
false => dirty.foreign.insert(parent_uid.clone()),
|
||||
};
|
||||
}
|
||||
}
|
||||
DriveEvent::NodeDeleted { node_uid, .. } => {
|
||||
core.cache.evict(node_uid);
|
||||
core.for_each_mount(|st, notifier| {
|
||||
forget_and_notify(st, notifier, node_uid);
|
||||
});
|
||||
}
|
||||
// Continuity or scope was lost: our cached listings may be arbitrarily
|
||||
// stale, so drop every listing and tell the kernel to forget all
|
||||
// metadata. Inodes stay stable; dirs simply re-enumerate on next access.
|
||||
DriveEvent::ContinuityLost { .. } | DriveEvent::ScopeAccessLost { .. } => {
|
||||
warn!("event continuity lost; dropping all cached listings, resyncing lazily");
|
||||
core.for_each_mount(|st, notifier| {
|
||||
let dirs: Vec<u64> = st.children.keys().copied().collect();
|
||||
for &ino in &dirs {
|
||||
st.invalidate_listing(ino);
|
||||
if let Some(notifier) = notifier {
|
||||
let _ = notifier.inval_inode(INodeNo(ino), 0, 0);
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
// No substantive local change; the cursor advance is handled by the
|
||||
// caller persisting the event id.
|
||||
DriveEvent::CursorAdvanced { .. } | DriveEvent::SharedWithMeUpdated { .. } => {}
|
||||
}
|
||||
}
|
||||
|
||||
/// The folders one batch of events changed, collected so the listings are
|
||||
/// dropped once at the end of the batch rather than once per event.
|
||||
///
|
||||
/// Both halves of that matter. A burst of uploads produces one event per file
|
||||
/// all naming the *same* folder, and dropping the listing per event made every
|
||||
/// interleaved lookup re-enumerate that folder from the API — quadratic in its
|
||||
/// size, and slow enough to stall a busy mount. Splitting foreign changes from
|
||||
/// our own then removes the re-enumeration entirely for the common case: a file
|
||||
/// this daemon created is already in the tree under the right parent, so there
|
||||
/// is nothing for a re-enumeration to discover.
|
||||
///
|
||||
/// Neither is a weakening. The state after the batch is what it always was.
|
||||
#[derive(Default)]
|
||||
struct DirtyParents {
|
||||
/// Folders changed by someone else. Their listings must go: an event names
|
||||
/// no name, so a rename inside a folder is indistinguishable from a write to
|
||||
/// a file in it, and only re-enumerating can tell us which happened.
|
||||
foreign: HashSet<NodeUid>,
|
||||
/// Folders changed by this daemon, and the children the changes were about.
|
||||
/// Checked per mount — a mount that already lists every one of those
|
||||
/// children under that parent keeps its listing.
|
||||
ours: HashMap<NodeUid, HashSet<NodeUid>>,
|
||||
}
|
||||
|
||||
/// Whether this mount's cached listing of `parent_uid` already accounts for
|
||||
/// `child_uid`, so a change we made to that child leaves nothing to re-read.
|
||||
///
|
||||
/// "Nothing cached" counts as current: an absent listing is re-enumerated on the
|
||||
/// next `readdir` regardless, so there is nothing to drop.
|
||||
fn listing_accounts_for(st: &State, parent_uid: &NodeUid, child_uid: &NodeUid) -> bool {
|
||||
let Some(&parent) = st.by_uid.get(parent_uid) else {
|
||||
return true;
|
||||
};
|
||||
let Some(children) = st.children.get(&parent) else {
|
||||
return true;
|
||||
};
|
||||
let Some(&child) = st.by_uid.get(child_uid) else {
|
||||
return false;
|
||||
};
|
||||
children.contains(&child) && st.entries.get(&child).is_some_and(|e| e.parent == parent)
|
||||
}
|
||||
|
||||
/// Drop the cached listing of every folder a batch of events changed, in every
|
||||
/// mount that holds one, so the next `readdir`/`lookup` re-enumerates it.
|
||||
///
|
||||
/// Runs strictly after the whole batch is applied: doing it per event would
|
||||
/// leave a window where a concurrent `readdir` re-populates a listing that a
|
||||
/// later event in the same batch then has to drop again.
|
||||
fn flush_dirty_parents(core: &Core, dirty: &DirtyParents) {
|
||||
if dirty.foreign.is_empty() && dirty.ours.is_empty() {
|
||||
return;
|
||||
}
|
||||
core.for_each_mount(|st, notifier| {
|
||||
let drop_listing = |st: &mut State, parent_uid: &NodeUid| {
|
||||
let Some(&parent) = st.by_uid.get(parent_uid) else {
|
||||
return;
|
||||
};
|
||||
st.invalidate_listing(parent);
|
||||
if let Some(notifier) = notifier {
|
||||
let _ = notifier.inval_inode(INodeNo(parent), 0, 0);
|
||||
}
|
||||
};
|
||||
for parent_uid in &dirty.foreign {
|
||||
drop_listing(st, parent_uid);
|
||||
}
|
||||
for (parent_uid, children) in &dirty.ours {
|
||||
if dirty.foreign.contains(parent_uid) {
|
||||
continue;
|
||||
}
|
||||
// One child this mount has not placed is enough: the listing it is
|
||||
// serving is missing something the user just made.
|
||||
if children
|
||||
.iter()
|
||||
.all(|child| listing_accounts_for(st, parent_uid, child))
|
||||
{
|
||||
continue;
|
||||
}
|
||||
drop_listing(st, parent_uid);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Poll the remote event cursor forever, applying each batch to the shared
|
||||
/// state. Resumes from the cursor persisted in the DB so changes made while
|
||||
/// unmounted are applied; only a first-ever mount seeds from the server head.
|
||||
/// The cursor is persisted after every batch. Runs as a Tokio task; returns
|
||||
/// only on fatal error.
|
||||
///
|
||||
/// Takes the whole `Core` rather than the primary mount's pieces: an event has
|
||||
/// to be applied to every mounted inode space, and the registry that enumerates
|
||||
/// them lives on the `Core` (see [`apply_event`]).
|
||||
pub(super) async fn run_event_sync(
|
||||
client: ProtonDriveClient,
|
||||
scope: DriveEventScopeId,
|
||||
core: Core,
|
||||
) {
|
||||
let db = core.db.clone();
|
||||
let mut cursor: Option<DriveEventId> = match db.get_event_cursor() {
|
||||
// Resume: pick up exactly where the last run left off.
|
||||
Ok(Some(saved)) => Some(DriveEventId::from(saved)),
|
||||
// First mount: a `None` cursor yields a single `CursorAdvanced` at the
|
||||
// server head; persist it so the next restart resumes instead of
|
||||
// reseeding (which would skip everything that changed offline).
|
||||
// Seeding needs the network, and this task also runs on mounts that
|
||||
// started offline (offline.md Phase 1) — so retry rather than giving up,
|
||||
// which used to disable live sync for the life of the daemon.
|
||||
Ok(None) => {
|
||||
let mut delay = ONLINE_PROBE_MIN;
|
||||
loop {
|
||||
match client.enumerate_events(&scope, None).await {
|
||||
Ok(events) => {
|
||||
let head = events.last().map(|e| e.id().clone());
|
||||
let Some(c) = &head else {
|
||||
break None;
|
||||
};
|
||||
if let Err(e) = db.set_event_cursor(c.as_str()) {
|
||||
warn!(error = %e, ?delay, "persist seed cursor failed; retrying");
|
||||
tokio::time::sleep(delay).await;
|
||||
delay = (delay * 2).min(ONLINE_PROBE_MAX);
|
||||
continue;
|
||||
}
|
||||
break Some(c.clone());
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(error = %e, ?delay, "seed event cursor failed; retrying");
|
||||
tokio::time::sleep(delay).await;
|
||||
delay = (delay * 2).min(ONLINE_PROBE_MAX);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
error!(error = %e, "read persisted cursor failed; live sync disabled");
|
||||
return;
|
||||
}
|
||||
};
|
||||
info!(?cursor, "event sync started");
|
||||
|
||||
loop {
|
||||
tokio::time::sleep(POLL_INTERVAL).await;
|
||||
let events = match client.enumerate_events(&scope, cursor.as_ref()).await {
|
||||
Ok(events) => events,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "event poll failed; retrying after interval");
|
||||
continue;
|
||||
}
|
||||
};
|
||||
if events.is_empty() {
|
||||
continue;
|
||||
}
|
||||
debug!(count = events.len(), "applying remote events");
|
||||
// Folders whose listing this batch invalidates, applied once at the end
|
||||
// rather than per event — see [`DirtyParents`]. Every `break` below falls
|
||||
// through to that flush, so an interrupted batch still publishes what it
|
||||
// did apply.
|
||||
let mut dirty = DirtyParents::default();
|
||||
for event in &events {
|
||||
// Converge the SDK's own caches (folder keys, entity cache) on the
|
||||
// server before applying the event to our tree. Without this, a node
|
||||
// re-keyed/moved by another client keeps a stale key in the SDK for
|
||||
// the life of the daemon (SDK plan #9). `apply_event` only touches
|
||||
// our FUSE state, so nothing else does this.
|
||||
if let Err(e) = client.invalidate_caches_for_event(event).await {
|
||||
warn!(error = %e, "sdk cache invalidation for event failed; retaining cursor for retry");
|
||||
break;
|
||||
}
|
||||
apply_event(&core, event, &mut dirty);
|
||||
let applied = event.id().clone();
|
||||
if let Err(e) = db.set_event_cursor(applied.as_str()) {
|
||||
warn!(error = %e, "persist event cursor failed; retaining prior cursor for retry");
|
||||
break;
|
||||
}
|
||||
// Advance only after this exact event is durably acknowledged. If a
|
||||
// later event fails, polling resumes from here and replays nothing
|
||||
// that was not already made visible locally.
|
||||
cursor = Some(applied);
|
||||
}
|
||||
flush_dirty_parents(&core, &dirty);
|
||||
}
|
||||
}
|
||||
|
||||
/// Keep the local-file index fresh for the launcher prompt's "This computer"
|
||||
/// results. Rebuilds the index whenever it is older than [`LOCAL_INDEX_TTL`],
|
||||
/// then sleeps; runs on its own thread for the life of the daemon.
|
||||
///
|
||||
/// The walk is the one part of the daemon that touches the wider filesystem, so
|
||||
/// it is deliberately kept off every hot path: it never runs on a FUSE or
|
||||
/// control-socket thread, and it excludes the mountpoint (walking it would fault
|
||||
/// every remote node in through FUSE, defeating on-demand hydration).
|
||||
pub(super) fn run_local_index(
|
||||
db: Arc<Db>,
|
||||
indexing: Arc<AtomicBool>,
|
||||
transfers: Arc<TransferRegistry>,
|
||||
mountpoint: PathBuf,
|
||||
) {
|
||||
loop {
|
||||
let age = db.local_indexed_at().ok().flatten();
|
||||
let stale =
|
||||
age.is_none_or(|at| now_secs().saturating_sub(at) >= LOCAL_INDEX_TTL.as_secs() as i64);
|
||||
if stale {
|
||||
scan_local_once(&db, &indexing, &transfers, &mountpoint);
|
||||
}
|
||||
std::thread::sleep(LOCAL_INDEX_CHECK);
|
||||
}
|
||||
}
|
||||
|
||||
/// Walk `$HOME` once and replace the local-file index with what it finds.
|
||||
/// Batches stream straight into SQLite, so peak memory is one batch — not the
|
||||
/// whole home directory.
|
||||
///
|
||||
/// Reports itself as a job: the first scan after a fresh install walks the whole
|
||||
/// home directory, and `indexing` alone only tells the launcher prompt to say
|
||||
/// "still indexing" — nothing else showed that the daemon was busy.
|
||||
fn scan_local_once(
|
||||
db: &Db,
|
||||
indexing: &AtomicBool,
|
||||
transfers: &Arc<TransferRegistry>,
|
||||
mountpoint: &Path,
|
||||
) {
|
||||
let dirs = match AppDirs::new() {
|
||||
Ok(d) => d,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "local index: cannot resolve app dirs");
|
||||
return;
|
||||
}
|
||||
};
|
||||
let Some(home) = dirs.home_dir() else {
|
||||
warn!("local index: cannot resolve home directory");
|
||||
return;
|
||||
};
|
||||
let generation = match db.local_begin_scan() {
|
||||
Ok(g) => g,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "local index: cannot open scan generation");
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
let excludes = localindex::default_excludes(mountpoint, &dirs.state_dir(), &dirs.cache_dir());
|
||||
indexing.store(true, Ordering::Relaxed);
|
||||
let started = Instant::now();
|
||||
|
||||
// The walk has no idea how many files it will find, so the job counts what it
|
||||
// has seen and stays indeterminate.
|
||||
let job = transfers.begin_job("Indexing this computer");
|
||||
job.detail("Scanning your files");
|
||||
let walked = localindex::scan(&[home], &excludes, |batch| {
|
||||
if let Err(e) = db.local_upsert_batch(generation, &batch) {
|
||||
warn!(error = %e, "local index: batch write failed");
|
||||
}
|
||||
});
|
||||
|
||||
// Prune what this scan did not see and rebuild the FTS index over the rest,
|
||||
// even if some batches failed — a partial index still beats none.
|
||||
job.detail("Building the search index");
|
||||
match db.local_finish_scan(generation, now_secs()) {
|
||||
Ok(indexed) => info!(
|
||||
walked,
|
||||
indexed,
|
||||
elapsed_ms = started.elapsed().as_millis() as u64,
|
||||
"local index rebuilt"
|
||||
),
|
||||
Err(e) => warn!(error = %e, "local index: finish failed"),
|
||||
}
|
||||
indexing.store(false, Ordering::Relaxed);
|
||||
}
|
||||
@@ -12,8 +12,8 @@
|
||||
use std::io::{BufRead, BufReader, Write as _};
|
||||
use std::os::unix::net::{UnixListener, UnixStream};
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::atomic::Ordering;
|
||||
use std::time::Instant;
|
||||
use std::sync::atomic::{AtomicUsize, Ordering};
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use pdfs_core::config::AppDirs;
|
||||
use pdfs_core::control::{
|
||||
@@ -27,6 +27,67 @@ use tracing::{info, warn};
|
||||
use super::transfers::CountingReader;
|
||||
use super::{Core, count_noun, human_bytes, human_duration, parse_uid};
|
||||
|
||||
const MAX_CONTROL_REQUEST_BYTES: u64 = 1024 * 1024;
|
||||
const CONTROL_READ_TIMEOUT: Duration = Duration::from_secs(10);
|
||||
const MAX_CONTROL_HANDLERS: usize = 64;
|
||||
static ACTIVE_CONTROL_HANDLERS: AtomicUsize = AtomicUsize::new(0);
|
||||
|
||||
struct ControlHandlerPermit;
|
||||
|
||||
impl ControlHandlerPermit {
|
||||
fn acquire() -> Option<Self> {
|
||||
ACTIVE_CONTROL_HANDLERS
|
||||
.fetch_update(Ordering::AcqRel, Ordering::Acquire, |active| {
|
||||
(active < MAX_CONTROL_HANDLERS).then_some(active + 1)
|
||||
})
|
||||
.ok()
|
||||
.map(|_| Self)
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for ControlHandlerPermit {
|
||||
fn drop(&mut self) {
|
||||
ACTIVE_CONTROL_HANDLERS.fetch_sub(1, Ordering::AcqRel);
|
||||
}
|
||||
}
|
||||
|
||||
fn read_request_line(reader: &mut impl BufRead) -> std::io::Result<Option<String>> {
|
||||
let mut bytes = Vec::new();
|
||||
loop {
|
||||
let available = reader.fill_buf()?;
|
||||
if available.is_empty() {
|
||||
break;
|
||||
}
|
||||
let take = available
|
||||
.iter()
|
||||
.position(|byte| *byte == b'\n')
|
||||
.map_or(available.len(), |index| index + 1);
|
||||
if bytes.len().saturating_add(take) > MAX_CONTROL_REQUEST_BYTES as usize {
|
||||
return Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidData,
|
||||
"control request exceeds size limit",
|
||||
));
|
||||
}
|
||||
bytes.extend_from_slice(&available[..take]);
|
||||
reader.consume(take);
|
||||
if bytes.ends_with(b"\n") {
|
||||
break;
|
||||
}
|
||||
}
|
||||
if bytes.is_empty() {
|
||||
return Ok(None);
|
||||
}
|
||||
if bytes.len() as u64 > MAX_CONTROL_REQUEST_BYTES || !bytes.ends_with(b"\n") {
|
||||
return Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidData,
|
||||
"control request exceeds limit or is not newline terminated",
|
||||
));
|
||||
}
|
||||
String::from_utf8(bytes)
|
||||
.map(Some)
|
||||
.map_err(|e| std::io::Error::new(std::io::ErrorKind::InvalidData, e))
|
||||
}
|
||||
|
||||
/// Turn a CLI-supplied path into a mountpoint-relative path. An absolute path
|
||||
/// must live under `mountpoint`; a relative path is taken as already relative to
|
||||
/// the mount root.
|
||||
@@ -44,6 +105,10 @@ fn rel_to_mount(mountpoint: &Path, path: &str) -> CoreResult<PathBuf> {
|
||||
/// Handle one control-socket connection: read a single JSON request line,
|
||||
/// dispatch it against `core`, and write back a JSON response line.
|
||||
fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: UnixStream) {
|
||||
if let Err(e) = stream.set_read_timeout(Some(CONTROL_READ_TIMEOUT)) {
|
||||
warn!(error = %e, "control: could not set request timeout");
|
||||
return;
|
||||
}
|
||||
let mut reader = BufReader::new(match stream.try_clone() {
|
||||
Ok(s) => s,
|
||||
Err(e) => {
|
||||
@@ -51,10 +116,14 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
return;
|
||||
}
|
||||
});
|
||||
let mut line = String::new();
|
||||
if reader.read_line(&mut line).is_err() || line.trim().is_empty() {
|
||||
return;
|
||||
}
|
||||
let line = match read_request_line(&mut reader) {
|
||||
Ok(Some(line)) if !line.trim().is_empty() => line,
|
||||
Ok(_) => return,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "control: rejected request");
|
||||
return;
|
||||
}
|
||||
};
|
||||
let response = match serde_json::from_str::<CtlRequest>(line.trim()) {
|
||||
Ok(CtlRequest::Status) => {
|
||||
let pins = core.cache.list_pins();
|
||||
@@ -73,18 +142,24 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
}
|
||||
Ok(CtlRequest::Pin { path }) => match rel_to_mount(mountpoint, &path) {
|
||||
Ok(rel) => match core.pin(&rel) {
|
||||
Ok(name) => CtlResponse::Ok {
|
||||
message: format!("pinned {name}"),
|
||||
},
|
||||
Ok(name) => {
|
||||
core.touch_profile();
|
||||
CtlResponse::Ok {
|
||||
message: format!("pinned {name}"),
|
||||
}
|
||||
}
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::Unpin { path }) => match rel_to_mount(mountpoint, &path) {
|
||||
Ok(rel) => match core.unpin(&rel) {
|
||||
Ok(name) => CtlResponse::Ok {
|
||||
message: format!("unpinned {name}"),
|
||||
},
|
||||
Ok(name) => {
|
||||
core.touch_profile();
|
||||
CtlResponse::Ok {
|
||||
message: format!("unpinned {name}"),
|
||||
}
|
||||
}
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
@@ -235,6 +310,18 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::SearchV2 {
|
||||
query,
|
||||
limit,
|
||||
filters,
|
||||
}) => match core.search_v2(&query, limit, &filters) {
|
||||
Ok((drive_hits, local_hits)) => CtlResponse::SearchResultsV2 {
|
||||
drive_hits,
|
||||
local_hits,
|
||||
local_indexing: core.indexing.load(Ordering::Relaxed),
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::Rename { path, new_name }) => match rel_to_mount(mountpoint, &path) {
|
||||
Ok(rel) => match core.rename(&rel, &new_name) {
|
||||
Ok(name) => {
|
||||
@@ -404,6 +491,45 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
),
|
||||
}
|
||||
}
|
||||
Ok(CtlRequest::CacheInspect { deep }) => match core.db.stats() {
|
||||
Ok(stats) => {
|
||||
// The deep check reads every page, so it runs only on request;
|
||||
// `integrity_checked` tells the caller which answer it is
|
||||
// holding, since "no problems found" and "never looked" are
|
||||
// both an empty list.
|
||||
let (integrity_problems, integrity_checked) = if deep {
|
||||
match core.db.integrity_check() {
|
||||
Ok(problems) => (problems, true),
|
||||
Err(e) => (vec![format!("integrity check failed: {e:?}")], true),
|
||||
}
|
||||
} else {
|
||||
(Vec::new(), false)
|
||||
};
|
||||
CtlResponse::CacheReport {
|
||||
schema_version: stats.schema_version,
|
||||
db_bytes: stats.total_bytes(),
|
||||
db_reclaimable_bytes: stats.reclaimable_bytes(),
|
||||
tables: stats.tables,
|
||||
cache_used: core.cache.usage(),
|
||||
cache_budget: core.cache.budget(),
|
||||
integrity_problems,
|
||||
integrity_checked,
|
||||
}
|
||||
}
|
||||
Err(e) => CtlResponse::error(CoreError::internal(format!("read db stats: {e:?}"))),
|
||||
},
|
||||
Ok(CtlRequest::CacheVacuum) => match core.db.vacuum() {
|
||||
Ok(outcome) => CtlResponse::Ok {
|
||||
message: format!(
|
||||
"vacuumed: {:.1} MiB freed ({:.1} MiB → {:.1} MiB), {} WAL frame(s) checkpointed",
|
||||
outcome.freed_bytes() as f64 / 1_048_576.0,
|
||||
outcome.before_bytes as f64 / 1_048_576.0,
|
||||
outcome.after_bytes as f64 / 1_048_576.0,
|
||||
outcome.wal_frames_checkpointed,
|
||||
),
|
||||
},
|
||||
Err(e) => CtlResponse::error(CoreError::internal(format!("vacuum: {e:?}"))),
|
||||
},
|
||||
Ok(CtlRequest::GetQueueStatus) => CtlResponse::Transfers {
|
||||
items: core.transfers.snapshot(),
|
||||
jobs: core.jobs_snapshot(),
|
||||
@@ -417,9 +543,12 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
cfg.cache_budget = Some(bytes);
|
||||
dirs.save_config(&cfg)
|
||||
}) {
|
||||
Ok(Ok(())) => CtlResponse::Ok {
|
||||
message: format!("cache budget set to {bytes} bytes"),
|
||||
},
|
||||
Ok(Ok(())) => {
|
||||
core.touch_profile();
|
||||
CtlResponse::Ok {
|
||||
message: format!("cache budget set to {bytes} bytes"),
|
||||
}
|
||||
}
|
||||
Ok(Err(e)) => CtlResponse::error(CoreError::internal(format!(
|
||||
"budget applied but config write failed: {e}"
|
||||
))),
|
||||
@@ -444,6 +573,10 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::AdoptDevice { uid }) => match core.adopt_device(uid.as_deref()) {
|
||||
Ok(message) => CtlResponse::Ok { message },
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::AddSyncFolder { local_path }) => {
|
||||
// Registering the device and uploading a folder tree far outlasts the
|
||||
// socket read timeout, so ack immediately and work on a background
|
||||
@@ -455,6 +588,7 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
let started = Instant::now();
|
||||
match core.add_sync_folder(&path) {
|
||||
Ok(folder) => {
|
||||
core.touch_profile();
|
||||
let name = Path::new(&folder.local_path)
|
||||
.file_name()
|
||||
.and_then(|n| n.to_str())
|
||||
@@ -483,15 +617,19 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
},
|
||||
Ok(CtlRequest::RemoveSyncFolder { id, delete_remote }) => {
|
||||
match core.remove_sync_folder(id, delete_remote) {
|
||||
Ok(()) => CtlResponse::Ok {
|
||||
message: "removed synced folder".to_string(),
|
||||
},
|
||||
Ok(()) => {
|
||||
core.touch_profile();
|
||||
CtlResponse::Ok {
|
||||
message: "removed synced folder".to_string(),
|
||||
}
|
||||
}
|
||||
Err(e) => CtlResponse::error(e),
|
||||
}
|
||||
}
|
||||
Ok(CtlRequest::SetSyncFolderMode { id, mode }) => {
|
||||
match core.request_sync_folder_mode(id, &mode) {
|
||||
Ok(message) => {
|
||||
core.touch_profile();
|
||||
core.log_activity(ActivityKind::Upload, &message, "", true);
|
||||
CtlResponse::Ok { message }
|
||||
}
|
||||
@@ -507,6 +645,28 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
},
|
||||
}
|
||||
}
|
||||
Ok(CtlRequest::ListRestorableFolders) => match core.list_restorable_folders() {
|
||||
Ok(items) => CtlResponse::RestorableFolders { items },
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::RestoreSyncFolders { items }) => {
|
||||
// Like AddSyncFolder: each restored folder downloads a whole tree,
|
||||
// which outlasts the socket timeout. Ack, then work.
|
||||
let core = core.clone();
|
||||
std::thread::spawn(move || match core.restore_sync_folders(&items) {
|
||||
Ok(message) => {
|
||||
core.touch_profile();
|
||||
core.log_activity(ActivityKind::Download, &message, "", true);
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(error = %e, "restore failed");
|
||||
core.log_activity(ActivityKind::Download, "restore folders", &e, false);
|
||||
}
|
||||
});
|
||||
CtlResponse::Ok {
|
||||
message: "restoring folders".to_string(),
|
||||
}
|
||||
}
|
||||
Ok(CtlRequest::ShareNode {
|
||||
path,
|
||||
emails,
|
||||
@@ -601,6 +761,23 @@ fn handle_control_conn(core: &Core, username: &str, mountpoint: &Path, stream: U
|
||||
Ok(entries) => CtlResponse::Entries { entries },
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::AccountQuota) => match core.account_quota() {
|
||||
Ok((max_space, used_space)) => CtlResponse::AccountQuota {
|
||||
max_space,
|
||||
used_space,
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::ListSharedFolder { uid }) => match core.list_shared_folder(&uid) {
|
||||
Ok(entries) => CtlResponse::Entries { entries },
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::OpenSharedFile { uid }) => match core.open_shared_file(&uid) {
|
||||
Ok(p) => CtlResponse::FilePath {
|
||||
path: p.display().to_string(),
|
||||
},
|
||||
Err(e) => CtlResponse::error(e),
|
||||
},
|
||||
Ok(CtlRequest::LeaveShared { uid }) => match core.leave_shared(&uid) {
|
||||
Ok(()) => {
|
||||
core.log_activity(ActivityKind::Unshare, "shared item", "left", true);
|
||||
@@ -684,12 +861,22 @@ pub(crate) fn run_control_socket(
|
||||
for conn in listener.incoming() {
|
||||
match conn {
|
||||
Ok(stream) => {
|
||||
let Some(permit) = ControlHandlerPermit::acquire() else {
|
||||
warn!(
|
||||
limit = MAX_CONTROL_HANDLERS,
|
||||
"control: rejecting connection at handler limit"
|
||||
);
|
||||
continue;
|
||||
};
|
||||
let core = core.clone();
|
||||
let username = username.clone();
|
||||
let mountpoint = mountpoint.clone();
|
||||
if let Err(e) = std::thread::Builder::new()
|
||||
.name("pdfs-control".into())
|
||||
.spawn(move || handle_control_conn(&core, &username, &mountpoint, stream))
|
||||
.spawn(move || {
|
||||
let _permit = permit;
|
||||
handle_control_conn(&core, &username, &mountpoint, stream);
|
||||
})
|
||||
{
|
||||
warn!(error = %e, "control: spawn handler failed");
|
||||
}
|
||||
@@ -700,3 +887,38 @@ pub(crate) fn run_control_socket(
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod request_limit_tests {
|
||||
use super::*;
|
||||
use std::io::Cursor;
|
||||
|
||||
#[test]
|
||||
fn accepts_one_bounded_newline_terminated_request() {
|
||||
let mut input = Cursor::new(b"{\"Status\":null}\n".to_vec());
|
||||
assert_eq!(
|
||||
read_request_line(&mut input).unwrap().as_deref(),
|
||||
Some("{\"Status\":null}\n")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_a_request_without_a_terminating_newline() {
|
||||
let mut input = Cursor::new(b"{\"Status\":null}".to_vec());
|
||||
assert_eq!(
|
||||
read_request_line(&mut input).unwrap_err().kind(),
|
||||
std::io::ErrorKind::InvalidData
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_a_request_larger_than_the_limit() {
|
||||
let mut bytes = vec![b'x'; MAX_CONTROL_REQUEST_BYTES as usize + 1];
|
||||
bytes.push(b'\n');
|
||||
let mut input = Cursor::new(bytes);
|
||||
assert_eq!(
|
||||
read_request_line(&mut input).unwrap_err().kind(),
|
||||
std::io::ErrorKind::InvalidData
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -20,14 +20,40 @@ use pdfs_core::db::{StoredDevice, StoredSyncFolder};
|
||||
use pdfs_core::{CoreError, CoreResult};
|
||||
use proton_drive_rs::proton_sdk::ids::{DeviceUid, NodeUid};
|
||||
use proton_drive_rs::{DeviceType, Node};
|
||||
use std::sync::OnceLock;
|
||||
use tracing::{info, warn};
|
||||
|
||||
use super::sync::{self, base_name};
|
||||
use super::{
|
||||
BackgroundSession, Core, ProtonFs, State, SwitchBlocked, clear_stale_mount, device_type_str,
|
||||
dir_is_empty, evict_dir_contents, now_secs, parse_uid, sync_folder_info, this_hostname,
|
||||
dir_is_empty, evict_dir_contents, fuse_connection_id, is_stale_mount, now_secs, parse_uid,
|
||||
sync_folder_info, this_hostname, umount_session_unblocked,
|
||||
};
|
||||
|
||||
/// The device uid this machine has been adopted into, from `config.json`.
|
||||
///
|
||||
/// Read fresh each time rather than cached on [`Core`]: adoption rewrites the
|
||||
/// config from the control socket, and the next `ensure_device` must see it
|
||||
/// without a daemon restart.
|
||||
pub(crate) fn adopted_device_uid() -> Option<String> {
|
||||
let uid = pdfs_core::config::AppDirs::new()
|
||||
.ok()?
|
||||
.load_config()
|
||||
.device_uid?;
|
||||
let uid = uid.trim().to_string();
|
||||
(!uid.is_empty()).then_some(uid)
|
||||
}
|
||||
|
||||
/// Pin (or, with `None`, unpin) the adopted device uid in `config.json`.
|
||||
pub(crate) fn set_adopted_device_uid(uid: Option<&str>) -> CoreResult<()> {
|
||||
let dirs = pdfs_core::config::AppDirs::new()
|
||||
.map_err(|e| CoreError::internal(format!("config dirs: {e}")))?;
|
||||
let mut cfg = dirs.load_config();
|
||||
cfg.device_uid = uid.map(|u| u.to_string());
|
||||
dirs.save_config(&cfg)
|
||||
.map_err(|e| CoreError::internal(format!("write config: {e}")))
|
||||
}
|
||||
|
||||
impl Core {
|
||||
// ---- devices ----------------------------------------------------------
|
||||
|
||||
@@ -42,12 +68,14 @@ impl Core {
|
||||
// No cached device row yet means this machine syncs nothing, so none of
|
||||
// the listed devices is ours.
|
||||
let this_uid = self.db.device_get().ok().flatten().map(|d| d.uid);
|
||||
let pinned = adopted_device_uid();
|
||||
Ok(devices
|
||||
.into_iter()
|
||||
.map(|d| {
|
||||
let uid = d.uid.to_string();
|
||||
DeviceInfo {
|
||||
this_device: this_uid.as_deref() == Some(uid.as_str()),
|
||||
adopted: pinned.as_deref() == Some(uid.as_str()),
|
||||
uid,
|
||||
name: d.name.unwrap_or_else(|_| "(unnamed device)".to_string()),
|
||||
device_type: device_type_str(d.device_type).to_string(),
|
||||
@@ -78,21 +106,97 @@ impl Core {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Adopt an existing device as *this* machine's, pinning it in `config.json`
|
||||
/// so hostname changes and reinstalls stop registering duplicates
|
||||
/// (features.md 5.1). `None` clears the pin and returns to hostname matching.
|
||||
///
|
||||
/// Refuses a uid that is not in the account: the whole point of the pin is
|
||||
/// that it is authoritative, so accepting a bad one would defer the failure
|
||||
/// to the next `ensure_device` with no obvious cause.
|
||||
pub(crate) fn adopt_device(&self, uid: Option<&str>) -> CoreResult<String> {
|
||||
let Some(uid) = uid else {
|
||||
set_adopted_device_uid(None)?;
|
||||
return Ok("adoption cleared; device now resolved by hostname".to_string());
|
||||
};
|
||||
let remote = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_devices())
|
||||
.map_err(|e| CoreError::from_api(&e, "enumerate devices"))?;
|
||||
let dev = remote
|
||||
.into_iter()
|
||||
.find(|d| d.uid.to_string() == uid)
|
||||
.ok_or_else(|| CoreError::not_found(format!("no device {uid} in this account")))?;
|
||||
|
||||
let name = dev
|
||||
.name
|
||||
.as_deref()
|
||||
.ok()
|
||||
.map(|n| n.to_string())
|
||||
.unwrap_or_else(this_hostname);
|
||||
set_adopted_device_uid(Some(uid))?;
|
||||
// Write the row through too, so callers that read the cached device
|
||||
// (and `ListSyncFolders`' "this device" flag) agree immediately rather
|
||||
// than after the next `ensure_device`.
|
||||
self.db
|
||||
.device_set(&StoredDevice {
|
||||
uid: uid.to_string(),
|
||||
share_id: dev.share_id.to_string(),
|
||||
root_uid: dev.root_folder_uid.to_string(),
|
||||
name: name.clone(),
|
||||
created: dev.creation_time,
|
||||
})
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?;
|
||||
info!(uid, name, "adopted device");
|
||||
Ok(format!("adopted device {name}"))
|
||||
}
|
||||
|
||||
// ---- device folder sync (devices.md, Phase 1) -------------------------
|
||||
|
||||
/// Auto-register (or recover) this machine as a Proton Drive Device, caching
|
||||
/// it so restarts reuse the same device. Recovery matches an existing remote
|
||||
/// Linux device by name before creating a new one, so a lost local record
|
||||
/// doesn't orphan the device's root folder.
|
||||
///
|
||||
/// Resolution order: the *adopted* uid pinned in `config.json`, then the
|
||||
/// cached DB row (validated remotely), then a hostname match, then create.
|
||||
/// The pin exists because the hostname heuristic silently registers a second
|
||||
/// device after a rename or reinstall, orphaning the first one's folders
|
||||
/// (features.md 5.1).
|
||||
pub(crate) fn ensure_device(&self) -> CoreResult<StoredDevice> {
|
||||
let name = this_hostname();
|
||||
// Enumerate the remote devices once: used both to validate any cached
|
||||
// record and to recover an existing device by name.
|
||||
// Enumerate the remote devices once: used to validate the pin, validate
|
||||
// any cached record, and recover an existing device by name.
|
||||
let remote = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_devices())
|
||||
.map_err(|e| CoreError::from_api(&e, "enumerate devices"))?;
|
||||
|
||||
// An adopted uid is an explicit instruction, so it outranks everything
|
||||
// and it fails loudly: falling back to the heuristic here would create
|
||||
// the duplicate device the user adopted specifically to avoid.
|
||||
if let Some(pin) = adopted_device_uid() {
|
||||
let d = remote
|
||||
.iter()
|
||||
.find(|d| d.uid.to_string() == pin)
|
||||
.ok_or_else(|| {
|
||||
CoreError::not_found(format!(
|
||||
"adopted device {pin} not found in this account; \
|
||||
run `pdfs devices adopt --clear` to return to hostname matching"
|
||||
))
|
||||
})?;
|
||||
let dev = StoredDevice {
|
||||
uid: d.uid.to_string(),
|
||||
share_id: d.share_id.to_string(),
|
||||
root_uid: d.root_folder_uid.to_string(),
|
||||
name: d.name.as_deref().ok().unwrap_or(&name).to_string(),
|
||||
created: d.creation_time,
|
||||
};
|
||||
self.db
|
||||
.device_set(&dev)
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?;
|
||||
return Ok(dev);
|
||||
}
|
||||
|
||||
// A cached device is only trustworthy if it still exists remotely. A
|
||||
// device deleted from another client (or the web UI) leaves a stale row
|
||||
// whose root folder is gone, so creating folders under it fails with
|
||||
@@ -345,8 +449,8 @@ impl Core {
|
||||
// folder the daemon no longer tracks, and nothing would ever unmount it.
|
||||
// Tear it down first — including before trashing the remote tree it
|
||||
// serves, which would otherwise leave it answering for deleted nodes.
|
||||
if let Some(session) = self.mounts.lock().remove(&id) {
|
||||
if let Err(e) = session.umount_and_join() {
|
||||
if let Some((session, conn)) = self.mounts.lock().remove(&id) {
|
||||
if let Err(e) = umount_session_unblocked(session, conn) {
|
||||
warn!(id, error = %e, "unmount on-demand folder failed");
|
||||
} else {
|
||||
info!(id, path = %folder.local_path, "unmounted on-demand folder");
|
||||
@@ -390,10 +494,22 @@ impl Core {
|
||||
by_uid: HashMap::new(),
|
||||
children: HashMap::new(),
|
||||
next_ino: 2,
|
||||
active_writes: HashMap::new(),
|
||||
handles: HashMap::new(),
|
||||
next_fh: 1,
|
||||
db: self.db.clone(),
|
||||
}));
|
||||
// A fresh inode space needs a fresh notification channel: this fork's
|
||||
// session is the only one that knows these inodes, so it must be the one
|
||||
// notified about them. Filled in by `spawn_ondemand_mount`.
|
||||
fork.notifier = Arc::new(OnceLock::new());
|
||||
// Size upgrades are keyed by inode, which is per-fork too.
|
||||
fork.size_upgrades = Arc::new(Mutex::new(HashMap::new()));
|
||||
// The daemon's single drain thread belongs to the primary mount, but it
|
||||
// drains ops for nodes that live *here*. Publishing this inode space is
|
||||
// what lets it find them; without it a queued create's node keeps its
|
||||
// `local~` uid after the upload lands and reads it as empty (B74).
|
||||
fork.register_state();
|
||||
fork
|
||||
}
|
||||
|
||||
@@ -572,27 +688,25 @@ impl Core {
|
||||
// fails, since eviction may already have deleted part of the tree.
|
||||
// Recovery is the user's explicit switch back to `mirror`, whose arm
|
||||
// clears the baseline and re-downloads.
|
||||
self.db
|
||||
.sync_folder_set_mode(id, "ondemand")
|
||||
.map_err(|e| SwitchBlocked::Failed(format!("db: {e:?}")))?;
|
||||
|
||||
// Reclaim the disk: empty the local dir (keep it as the mountpoint).
|
||||
if let Err(e) = evict_dir_contents(&local) {
|
||||
let _ = self.db.sync_folder_set_state(id, "error", now_secs());
|
||||
return Err(SwitchBlocked::Failed(format!(
|
||||
"evict {}: {e}",
|
||||
local.display()
|
||||
)));
|
||||
if let Err(e) = self.db.sync_folder_set_mode(id, "ondemand") {
|
||||
return Err(SwitchBlocked::Failed(format!("db: {e:?}")));
|
||||
}
|
||||
|
||||
let session = match self.spawn_ondemand_mount(&local, root) {
|
||||
Ok(session) => session,
|
||||
Err(e) => {
|
||||
let _ = self.db.sync_folder_set_state(id, "error", now_secs());
|
||||
return Err(SwitchBlocked::Failed(e.to_string()));
|
||||
}
|
||||
};
|
||||
self.mounts.lock().insert(id, session);
|
||||
// Reclaim the disk before mounting. Once FUSE covers `local`, a
|
||||
// directory walk addresses the remote namespace, so evicting at
|
||||
// that point sends unlink/rmdir requests to Drive and leaves the
|
||||
// underlying mirror hidden and untouched.
|
||||
if let Err(e) = evict_dir_contents(&local) {
|
||||
warn!(id, path = %local.display(), error = %e, "evict local dir contents failed");
|
||||
}
|
||||
let session = self.spawn_ondemand_mount(&local, root).map_err(|e| {
|
||||
SwitchBlocked::Failed(format!(
|
||||
"mount ondemand failed after local cache eviction; switch back to mirror to restore it: {e}"
|
||||
))
|
||||
})?;
|
||||
self.mounts
|
||||
.lock()
|
||||
.insert(id, (session, fuse_connection_id(&local)));
|
||||
let _ = self.sync_tx.send(sync::SyncMsg::Rewatch);
|
||||
self.db.sync_folder_set_state(id, "idle", now_secs()).ok();
|
||||
info!(id, path = %local.display(), "mounted sync folder on-demand");
|
||||
@@ -600,8 +714,8 @@ impl Core {
|
||||
}
|
||||
_ => {
|
||||
// ondemand→mirror: tear down the secondary mount first.
|
||||
if let Some(session) = self.mounts.lock().remove(&id)
|
||||
&& let Err(e) = session.umount_and_join()
|
||||
if let Some((session, conn)) = self.mounts.lock().remove(&id)
|
||||
&& let Err(e) = umount_session_unblocked(session, conn)
|
||||
{
|
||||
warn!(id, error = %e, "unmount on-demand folder failed");
|
||||
}
|
||||
@@ -639,10 +753,15 @@ impl Core {
|
||||
MountOption::Subtype("protondrive".to_string()),
|
||||
MountOption::DefaultPermissions,
|
||||
];
|
||||
let fs = ProtonFs::new(self.fork_state(), root);
|
||||
Session::new(fs, local, &config)
|
||||
let core = self.fork_state();
|
||||
let fs = ProtonFs::new(core.clone(), root);
|
||||
let session = Session::new(fs, local, &config)
|
||||
.and_then(|s| s.spawn())
|
||||
.map_err(|e| CoreError::internal(format!("mount {}: {e}", local.display())))
|
||||
.map_err(|e| CoreError::internal(format!("mount {}: {e}", local.display())))?;
|
||||
// Hand this fork its own session's notification channel, so a background
|
||||
// size upgrade can drop the kernel's cached attrs for these inodes.
|
||||
let _ = core.notifier.set(session.notifier());
|
||||
Ok(session)
|
||||
}
|
||||
|
||||
/// Re-establish FUSE mounts for folders left in `ondemand` mode across a daemon
|
||||
@@ -664,6 +783,17 @@ impl Core {
|
||||
continue;
|
||||
}
|
||||
let local = PathBuf::from(&folder.local_path);
|
||||
// A daemon killed before it could unmount (systemd's stop timeout,
|
||||
// say) leaves this path attached to a dead FUSE connection: it still
|
||||
// exists, but every stat on it fails with ENOTCONN — so `is_dir()`
|
||||
// reads it as *missing* and the folder gets parked in `error` on
|
||||
// every subsequent start, with no way back but a manual
|
||||
// `fusermount -u`. Detach the corpse first; the directory
|
||||
// underneath then restores normally.
|
||||
if is_stale_mount(&local) {
|
||||
warn!(id = folder.id, path = %local.display(), "restore on-demand: clearing stale mount");
|
||||
clear_stale_mount(&local);
|
||||
}
|
||||
if !local.is_dir() {
|
||||
warn!(id = folder.id, path = %local.display(), "restore on-demand: local path missing");
|
||||
let _ = self
|
||||
@@ -725,7 +855,9 @@ impl Core {
|
||||
};
|
||||
match self.spawn_ondemand_mount(&local, root) {
|
||||
Ok(session) => {
|
||||
self.mounts.lock().insert(folder.id, session);
|
||||
self.mounts
|
||||
.lock()
|
||||
.insert(folder.id, (session, fuse_connection_id(&local)));
|
||||
let _ = self.db.sync_folder_set_state(folder.id, "idle", now_secs());
|
||||
info!(id = folder.id, path = %local.display(), "remounted on-demand folder");
|
||||
}
|
||||
|
||||
@@ -23,6 +23,7 @@
|
||||
use std::fs::File;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::atomic::Ordering;
|
||||
use std::time::Duration;
|
||||
|
||||
use pdfs_core::cache::{Baseline, StagedWrite};
|
||||
use pdfs_core::control::{ActivityKind, TransferDirection};
|
||||
@@ -35,8 +36,8 @@ use super::state::Intervals;
|
||||
use super::transfers::CountingReader;
|
||||
use super::{
|
||||
Core, DRAIN_BACKOFF_MAX, DRAIN_BACKOFF_MIN, DRAIN_IDLE_POLL, ROOT_INO, conflict_name,
|
||||
is_already_exists, is_gone, is_local_uid_str, media_type_for, node_size, now_millis, now_secs,
|
||||
parse_node_uid,
|
||||
is_already_exists, is_gone, is_local_uid_str, media_type_for, node_revision_id, node_size,
|
||||
now_millis, now_secs, parse_node_uid,
|
||||
};
|
||||
|
||||
impl Core {
|
||||
@@ -62,23 +63,30 @@ impl Core {
|
||||
let due = self.db.next_due_op(now).unwrap_or_default();
|
||||
|
||||
let Some(op) = due.filter(|_| self.online.load(Ordering::Relaxed)) else {
|
||||
self.wait_for_drain_work();
|
||||
self.recover_fsynced_writes();
|
||||
// A debounced or backed-off op may be waiting: sleep only
|
||||
// until it becomes due rather than the full idle-poll.
|
||||
self.wait_for_drain_work_or_due();
|
||||
continue;
|
||||
};
|
||||
if let Err(e) = self.drain_op(&op) {
|
||||
let attempts = op.attempts + 1;
|
||||
let err_str = e.to_string();
|
||||
// Never infer that user data is disposable from an error string
|
||||
// or an arbitrary retry count. The staged blob and this row are
|
||||
// the only durable description of an accepted write. Even a
|
||||
// permission/quota error can become recoverable after the user
|
||||
// changes account state, and deleting the row here made the blob
|
||||
// unreachable after five ordinary network failures.
|
||||
let backoff = DRAIN_BACKOFF_MIN
|
||||
.saturating_mul(1u32 << attempts.min(6))
|
||||
.min(DRAIN_BACKOFF_MAX);
|
||||
warn!(uid = %op.uid, attempts, error = %e, "pending upload failed; will retry");
|
||||
warn!(uid = %op.uid, attempts, error = %err_str, "pending upload failed; will retry");
|
||||
if let Err(e) = self.db.record_op_failure(
|
||||
op.id,
|
||||
&e.to_string(),
|
||||
&err_str,
|
||||
now_millis() + backoff.as_millis() as i64,
|
||||
) {
|
||||
// The backoff is the only thing keeping a failing op from
|
||||
// being picked again immediately, so without it the loop
|
||||
// would spin on this op as fast as the API can refuse it.
|
||||
error!(uid = %op.uid, error = %e, "recording a drain failure failed");
|
||||
self.wait_for_drain_work();
|
||||
}
|
||||
@@ -97,6 +105,25 @@ impl Core {
|
||||
*woken = false;
|
||||
}
|
||||
|
||||
/// Like [`wait_for_drain_work`](Self::wait_for_drain_work), but first
|
||||
/// checks whether a debounced or backed-off op is due before the idle-poll
|
||||
/// ceiling. A 2-second debounce must not sleep 30 seconds.
|
||||
fn wait_for_drain_work_or_due(&self) {
|
||||
let timeout = match self.db.earliest_due_at() {
|
||||
Ok(Some(ts)) => {
|
||||
let remaining = (ts - now_millis()).max(0) as u64;
|
||||
Duration::from_millis(remaining).min(DRAIN_IDLE_POLL)
|
||||
}
|
||||
_ => DRAIN_IDLE_POLL,
|
||||
};
|
||||
let (lock, cv) = &*self.drain_wake;
|
||||
let mut woken = lock.lock();
|
||||
if !*woken {
|
||||
cv.wait_for(&mut woken, timeout);
|
||||
}
|
||||
*woken = false;
|
||||
}
|
||||
|
||||
/// Perform one queued op and retire it.
|
||||
pub(crate) fn drain_op(&self, op: &PendingOp) -> Result<(), Box<dyn std::error::Error>> {
|
||||
match op.kind.as_str() {
|
||||
@@ -202,6 +229,7 @@ impl Core {
|
||||
}
|
||||
}
|
||||
self.db.delete_op(op.id)?;
|
||||
self.note_self_change(&uid);
|
||||
info!(%uid, name = %landed, "pending rename landed");
|
||||
Ok(())
|
||||
}
|
||||
@@ -225,6 +253,7 @@ impl Core {
|
||||
Err(e) => return Err(e.into()),
|
||||
}
|
||||
self.db.delete_op(op.id)?;
|
||||
self.own_sealed_revs.lock().remove(&uid);
|
||||
self.invalidate_trash();
|
||||
self.log_activity(ActivityKind::Trash, &name, "trashed", true);
|
||||
info!(%uid, name, "pending trash landed");
|
||||
@@ -235,18 +264,19 @@ impl Core {
|
||||
/// it away from the one the user asked for. Best effort: the event sync
|
||||
/// would correct the tree anyway, but not before the user has looked at it.
|
||||
pub(crate) fn adopt_drained_name(&self, uid: &NodeUid, name: &str) {
|
||||
let mut st = self.state.lock();
|
||||
let Some(&ino) = st.by_uid.get(uid) else {
|
||||
return;
|
||||
};
|
||||
let Some(entry) = st.entries.get_mut(&ino) else {
|
||||
return;
|
||||
};
|
||||
entry.node.name = name.to_string();
|
||||
let node = entry.node.clone();
|
||||
if let Err(e) = st.db.upsert_node(&node) {
|
||||
warn!(%uid, error = %e, "db upsert_node failed after a conflict rename");
|
||||
}
|
||||
self.for_each_state(|st| {
|
||||
let Some(&ino) = st.by_uid.get(uid) else {
|
||||
return;
|
||||
};
|
||||
let Some(entry) = st.entries.get_mut(&ino) else {
|
||||
return;
|
||||
};
|
||||
entry.node.name = name.to_string();
|
||||
let node = entry.node.clone();
|
||||
if let Err(e) = st.db.upsert_node(&node) {
|
||||
warn!(%uid, error = %e, "db upsert_node failed after a conflict rename");
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Make a node that so far exists only on this machine real, and adopt the
|
||||
@@ -315,6 +345,9 @@ impl Core {
|
||||
// sync, whereas a surviving op would create the file a second time.
|
||||
self.db.delete_op(op.id)?;
|
||||
self.adopt_real_uid(&local, &real)?;
|
||||
// The feed will report this create back to us; the tree already has it
|
||||
// under its real uid, so that event is ours to ignore (`Core::self_changes`).
|
||||
self.note_self_change(&real);
|
||||
if let Some(blob) = op.blob_path.as_deref() {
|
||||
self.cache.discard_staged(Path::new(blob));
|
||||
}
|
||||
@@ -391,6 +424,14 @@ impl Core {
|
||||
///
|
||||
/// The inode is deliberately kept, so anything already holding the file open
|
||||
/// keeps working across the drain.
|
||||
///
|
||||
/// Applied to **every** live inode space, not just this Core's. A node
|
||||
/// created inside an on-demand sync folder lives in that fork's `state`,
|
||||
/// while the drain that lands its create belongs to the primary mount — so
|
||||
/// reaching for `self.state` here found nothing and left the fork's entry on
|
||||
/// its `local~` uid, which reads as an empty file for as long as the daemon
|
||||
/// runs (`docs/BUGS.md` B74). A uid is unique across mounts, so at most one
|
||||
/// of them matches and the others are no-ops.
|
||||
pub(crate) fn adopt_real_uid(
|
||||
&self,
|
||||
local: &NodeUid,
|
||||
@@ -403,8 +444,10 @@ impl Core {
|
||||
self.db
|
||||
.remap_local_uid(&local.to_string(), &real.to_string())?;
|
||||
|
||||
let mut st = self.state.lock();
|
||||
if let Some(ino) = st.by_uid.remove(local) {
|
||||
self.for_each_state(|st| {
|
||||
let Some(ino) = st.by_uid.remove(local) else {
|
||||
return;
|
||||
};
|
||||
st.by_uid.insert(real.clone(), ino);
|
||||
if let Some(e) = st.entries.get_mut(&ino) {
|
||||
e.uid = real.clone();
|
||||
@@ -432,8 +475,7 @@ impl Core {
|
||||
kids.push(ino);
|
||||
}
|
||||
}
|
||||
}
|
||||
drop(st);
|
||||
});
|
||||
// Write the real node through, now that nothing points at the old uid.
|
||||
if let Err(e) = self.db.upsert_node(&node) {
|
||||
warn!(%real, error = %e, "db upsert_node failed after remap");
|
||||
@@ -467,7 +509,7 @@ impl Core {
|
||||
uid: &NodeUid,
|
||||
meta: &StagedWrite,
|
||||
) -> Result<Option<String>, Box<dyn std::error::Error>> {
|
||||
let Some(base) = meta.based_on else {
|
||||
let Some(ref base) = meta.based_on else {
|
||||
return Ok(None);
|
||||
};
|
||||
let Some(node) = self.fetch_node_remote(uid)? else {
|
||||
@@ -476,15 +518,23 @@ impl Core {
|
||||
if node.trashed {
|
||||
return Ok(Some("the file was trashed remotely".into()));
|
||||
}
|
||||
let (mtime, size) = (node.modification_time, node_size(&node));
|
||||
if mtime != base.mtime || size != base.size {
|
||||
return Ok(Some(format!(
|
||||
"the remote revision changed under the queued write \
|
||||
(expected {} bytes at mtime {}, found {size} at {mtime})",
|
||||
base.size, base.mtime
|
||||
)));
|
||||
let Some(reason) = revision_changed(base, &node) else {
|
||||
return Ok(None);
|
||||
};
|
||||
// The remote moved on from the baseline — normally a conflict. But if it
|
||||
// sits at a revision *this daemon* sealed, no other device changed the
|
||||
// file: it is a single-writer stall→resume (a browser that closed and
|
||||
// reopened its download fd; B70 layer B). Chain onto it — supersede
|
||||
// instead of forking — so the finished bytes win the name rather than
|
||||
// being exiled to a `(sync-conflict)` copy.
|
||||
let remote_rev = node_revision_id(&node);
|
||||
let own_rev = self.own_sealed_revs.lock().get(uid).cloned();
|
||||
if is_own_self_supersede(meta.complete, remote_rev.as_deref(), own_rev.as_deref()) {
|
||||
debug!(%uid, ?remote_rev,
|
||||
"queued write chains onto our own sealed revision; not a conflict");
|
||||
return Ok(None);
|
||||
}
|
||||
Ok(None)
|
||||
Ok(Some(reason))
|
||||
}
|
||||
|
||||
/// Land a queued write that can no longer be applied to its own node as a
|
||||
@@ -568,11 +618,11 @@ impl Core {
|
||||
self.cache.evict(uid);
|
||||
self.evict_reader(uid);
|
||||
// The conflict copy is a node the tree has never seen.
|
||||
let mut st = self.state.lock();
|
||||
if let Some(&ino) = st.by_uid.get(&parent) {
|
||||
st.invalidate_listing(ino);
|
||||
}
|
||||
drop(st);
|
||||
self.for_each_state(|st| {
|
||||
if let Some(&ino) = st.by_uid.get(&parent) {
|
||||
st.invalidate_listing(ino);
|
||||
}
|
||||
});
|
||||
self.log_activity(
|
||||
ActivityKind::Upload,
|
||||
&name,
|
||||
@@ -626,13 +676,25 @@ impl Core {
|
||||
|
||||
/// A node's parent uid and name, as the tree currently has them.
|
||||
pub(crate) fn node_place(&self, uid: &NodeUid) -> Option<(NodeUid, String)> {
|
||||
{
|
||||
let st = self.state.lock();
|
||||
// Across every mount: the drain runs on the primary Core, but a node
|
||||
// written inside a sync folder is interned in that fork's inode space,
|
||||
// so asking `self.state` alone always missed it and fell through to the
|
||||
// DB. That still gave the right answer — the fallback below exists for
|
||||
// exactly this shape of miss — but it went to disk for something already
|
||||
// in memory, and only *because* of the fallback was it not a bug.
|
||||
let mut found = None;
|
||||
self.for_each_state(|st| {
|
||||
if found.is_some() {
|
||||
return;
|
||||
}
|
||||
if let Some(entry) = st.by_uid.get(uid).and_then(|ino| st.entries.get(ino))
|
||||
&& let Some(parent) = entry.node.parent_uid.clone()
|
||||
{
|
||||
return Some((parent, entry.node.name.clone()));
|
||||
found = Some((parent, entry.node.name.clone()));
|
||||
}
|
||||
});
|
||||
if found.is_some() {
|
||||
return found;
|
||||
}
|
||||
// The in-memory tree only holds what has been walked to since the daemon
|
||||
// started, and the drain routinely runs before anything has walked to
|
||||
@@ -727,7 +789,14 @@ impl Core {
|
||||
// an orphaned file (harmless), whereas the reverse would leave a queued
|
||||
// op pointing at nothing.
|
||||
self.db.delete_op(op.id)?;
|
||||
self.pending.lock().remove(&uid);
|
||||
{
|
||||
let mut p = self.pending.lock();
|
||||
if let Some(op_in_mem) = p.get(&uid)
|
||||
&& op_in_mem.path == blob
|
||||
{
|
||||
p.remove(&uid);
|
||||
}
|
||||
}
|
||||
|
||||
// The staged blob now matches the sealed revision, so a pinned file keeps
|
||||
// it as its cached content rather than re-downloading what we just sent.
|
||||
@@ -780,22 +849,60 @@ impl Core {
|
||||
return;
|
||||
}
|
||||
};
|
||||
// This function's whole job is to bring the tree level with the revision
|
||||
// we just sealed, so the feed's report of that revision has nothing left
|
||||
// to tell us. Claimed here rather than at the upload call so it is only
|
||||
// recorded when the node was actually re-read (`Core::self_changes`).
|
||||
self.note_self_change(uid);
|
||||
// Rebase any *open* write handles targeting this node. A handle opened
|
||||
// before this upload carries a stale base — its `base_mtime`/`base_size`
|
||||
// name the revision we just replaced. Without this update,
|
||||
// `remote_baseline` will build a `based_on` from those stale values, the
|
||||
// drain will compare them against the revision we sealed, and the write
|
||||
// will be diverted into a conflict copy of itself.
|
||||
//
|
||||
// This is the open-handle counterpart of `rebaseline_pending`, which
|
||||
// covers the same gap for *queued* ops.
|
||||
{
|
||||
let sealed_mtime = node.modification_time;
|
||||
let sealed_size = node_size(&node);
|
||||
let sealed_rev = node_revision_id(&node);
|
||||
// Remember it as ours, so a queued write that opened over an earlier
|
||||
// revision recognises this as a self-supersede rather than a foreign
|
||||
// change and does not fork (B70 layer B; consulted in
|
||||
// `revision_conflict`).
|
||||
if let Some(rev) = sealed_rev.clone() {
|
||||
self.own_sealed_revs.lock().insert(uid.clone(), rev);
|
||||
}
|
||||
self.for_each_state(|st| {
|
||||
for aw in st.active_writes.values_mut() {
|
||||
if aw.uid == *uid {
|
||||
aw.base_mtime = sealed_mtime;
|
||||
aw.base_size = sealed_size;
|
||||
aw.base_revision_id = sealed_rev.clone();
|
||||
debug!(%uid, mtime = sealed_mtime, size = sealed_size,
|
||||
"rebased open write handle onto the revision just uploaded");
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
// Ordered so that a write queued *during* the fetch above is still
|
||||
// caught: it took its baseline from the node's optimistic stamp, and
|
||||
// this overwrites it with the revision the server actually holds.
|
||||
if self.rebaseline_pending(uid, &node) {
|
||||
return;
|
||||
}
|
||||
let mut st = self.state.lock();
|
||||
let Some(parent) = st
|
||||
.by_uid
|
||||
.get(uid)
|
||||
.and_then(|ino| st.entries.get(ino))
|
||||
.map(|e| e.parent)
|
||||
else {
|
||||
return;
|
||||
};
|
||||
st.intern(parent, node);
|
||||
self.for_each_state(|st| {
|
||||
let Some(parent) = st
|
||||
.by_uid
|
||||
.get(uid)
|
||||
.and_then(|ino| st.entries.get(ino))
|
||||
.map(|e| e.parent)
|
||||
else {
|
||||
return;
|
||||
};
|
||||
st.intern(parent, node.clone());
|
||||
});
|
||||
}
|
||||
|
||||
/// Point a still-queued write at the revision this upload just sealed, and
|
||||
@@ -818,12 +925,14 @@ impl Core {
|
||||
let base = Baseline {
|
||||
mtime: sealed.modification_time,
|
||||
size: node_size(sealed),
|
||||
hash: None,
|
||||
revision_id: node_revision_id(sealed),
|
||||
};
|
||||
let mut pending = self.pending.lock();
|
||||
let Some(p) = pending.get_mut(uid) else {
|
||||
return false;
|
||||
};
|
||||
p.meta.based_on = Some(base);
|
||||
p.meta.based_on = Some(base.clone());
|
||||
match serde_json::to_string(&p.meta) {
|
||||
Ok(json) => {
|
||||
if let Err(e) = self.db.update_op_meta(&uid.to_string(), OP_REVISION, &json) {
|
||||
@@ -839,3 +948,153 @@ impl Core {
|
||||
true
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether the remote `node` moved on from the revision a queued write was
|
||||
/// `base`d on — the reason string when it did, `None` when the write can still be
|
||||
/// applied. Pure so it is testable without a live remote (the trashed/gone checks
|
||||
/// stay in [`Core::revision_conflict`], which does the fetch).
|
||||
///
|
||||
/// The revision id is the authoritative identity: it advances iff a *new* revision
|
||||
/// was sealed. When both sides carry one, it alone decides — the server re-stamps
|
||||
/// the *same* revision's mtime, and reading that drift as a change is exactly what
|
||||
/// diverted a write into a conflict copy of its own base (B16/B25). Only when
|
||||
/// there is no id to compare (an old sidecar, or a surface that omits it) does it
|
||||
/// fall back to the observable `(mtime, size)` tuple.
|
||||
fn revision_changed(base: &Baseline, node: &Node) -> Option<String> {
|
||||
if let (Some(base_rev), Some(remote_rev)) = (&base.revision_id, node_revision_id(node)) {
|
||||
return (*base_rev != remote_rev).then(|| {
|
||||
format!(
|
||||
"the remote revision changed under the queued write \
|
||||
(based on revision {base_rev}, remote now at {remote_rev})"
|
||||
)
|
||||
});
|
||||
}
|
||||
let (mtime, size) = (node.modification_time, node_size(node));
|
||||
(mtime != base.mtime || size != base.size).then(|| {
|
||||
format!(
|
||||
"the remote revision changed under the queued write \
|
||||
(expected {} bytes at mtime {}, found {size} at {mtime})",
|
||||
base.size, base.mtime
|
||||
)
|
||||
})
|
||||
}
|
||||
|
||||
/// Whether a queued write that found the remote moved on ([`revision_changed`]
|
||||
/// fired) is nonetheless a single-writer self-supersede rather than a foreign
|
||||
/// conflict — the remote sits at a revision this daemon sealed itself, so
|
||||
/// chaining onto it is safe and forking would be wrong (B70 layer B).
|
||||
///
|
||||
/// `remote_rev` is the id the remote currently holds, `own_rev` this node's
|
||||
/// latest own-sealed id. Requires a `complete` blob: an incomplete one's gaps
|
||||
/// still refer to the stale base, so it must take the non-destructive
|
||||
/// conflict-copy path instead of overwriting. A `None` remote id never matches
|
||||
/// (there is nothing to prove it was ours), so absence falls through to a fork.
|
||||
fn is_own_self_supersede(complete: bool, remote_rev: Option<&str>, own_rev: Option<&str>) -> bool {
|
||||
complete && remote_rev.is_some() && remote_rev == own_rev
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use proton_drive_rs::NodeKind;
|
||||
use proton_drive_rs::proton_sdk::ids::{LinkId, VolumeId};
|
||||
|
||||
fn file_node(mtime: i64, size: i64, rev: Option<&str>) -> Node {
|
||||
Node {
|
||||
uid: NodeUid::new(VolumeId::from("v"), LinkId::from("l")),
|
||||
parent_uid: None,
|
||||
kind: NodeKind::File {
|
||||
media_type: "text/plain".into(),
|
||||
total_size_on_storage: size,
|
||||
active_revision_state: None,
|
||||
active_revision_id: rev.map(String::from),
|
||||
claimed_size: Some(size),
|
||||
claimed_modification_time: None,
|
||||
content_sha1: None,
|
||||
},
|
||||
name: "f.txt".into(),
|
||||
creation_time: 0,
|
||||
modification_time: mtime,
|
||||
trashed: false,
|
||||
is_shared: false,
|
||||
is_shared_publicly: false,
|
||||
signature_email: None,
|
||||
verification: Default::default(),
|
||||
}
|
||||
}
|
||||
|
||||
fn baseline(mtime: i64, size: u64, rev: Option<&str>) -> Baseline {
|
||||
Baseline {
|
||||
mtime,
|
||||
size,
|
||||
hash: None,
|
||||
revision_id: rev.map(String::from),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn same_revision_id_is_not_a_conflict_despite_mtime_drift() {
|
||||
// The exact shape of the reported bug: same revision, server re-stamped
|
||||
// its mtime (1784897777 -> 1784897780), same size. Must NOT conflict.
|
||||
let base = baseline(1_784_897_777, 87_438, Some("rev-A"));
|
||||
let remote = file_node(1_784_897_780, 87_438, Some("rev-A"));
|
||||
assert_eq!(revision_changed(&base, &remote), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_new_revision_id_is_a_conflict_even_at_the_same_size() {
|
||||
// A same-size edit by another device advances the revision id: this is a
|
||||
// real conflict the id catches where (mtime, size) alone could miss it.
|
||||
let base = baseline(100, 40, Some("rev-A"));
|
||||
let remote = file_node(100, 40, Some("rev-B"));
|
||||
assert!(revision_changed(&base, &remote).is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn without_ids_it_falls_back_to_mtime_and_size() {
|
||||
// Old sidecar (no revision id): the (mtime, size) tuple still governs.
|
||||
let base = baseline(100, 40, None);
|
||||
assert_eq!(revision_changed(&base, &file_node(100, 40, None)), None);
|
||||
assert!(revision_changed(&base, &file_node(101, 40, None)).is_some());
|
||||
assert!(revision_changed(&base, &file_node(100, 41, None)).is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_complete_write_over_our_own_sealed_revision_chains_not_forks() {
|
||||
// B70 layer B: the partial we sealed ourselves (rev-mine) is what the
|
||||
// remote holds; the resume rewrote the whole file. Not a foreign change.
|
||||
assert!(is_own_self_supersede(
|
||||
true,
|
||||
Some("rev-mine"),
|
||||
Some("rev-mine")
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_move_to_a_revision_we_did_not_seal_still_forks() {
|
||||
// Another device wrote rev-theirs; we only ever sealed rev-mine. Fork.
|
||||
assert!(!is_own_self_supersede(
|
||||
true,
|
||||
Some("rev-theirs"),
|
||||
Some("rev-mine")
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_incomplete_blob_never_self_supersedes() {
|
||||
// Its gaps still refer to the stale base; overwriting would mix
|
||||
// revisions, so it must take the conflict-copy path even over our seal.
|
||||
assert!(!is_own_self_supersede(
|
||||
false,
|
||||
Some("rev-mine"),
|
||||
Some("rev-mine")
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_missing_remote_id_never_self_supersedes() {
|
||||
// No id to prove the revision was ours: fall through to a fork rather
|
||||
// than matching None==None.
|
||||
assert!(!is_own_self_supersede(true, None, None));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,422 @@
|
||||
//! Mount lifecycle and background-service orchestration.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// Why a [`mount`] call returned. Lets the daemon decide whether to exit (clean
|
||||
/// shutdown) or remount (the mount went away under it).
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum MountOutcome {
|
||||
/// The daemon was asked to stop (SIGTERM/SIGINT) and we lazily unmounted
|
||||
/// ourselves. The caller should exit cleanly.
|
||||
Shutdown,
|
||||
/// The kernel mount ended on its own (e.g. an external `fusermount -u`).
|
||||
/// The caller may want to remount.
|
||||
Unmounted,
|
||||
}
|
||||
|
||||
/// Whether `path` is a mountpoint whose FUSE connection is dead — the state a
|
||||
/// daemon killed before it could unmount leaves behind.
|
||||
///
|
||||
/// The kernel answers every operation on such a path with `ENOTCONN`, which the
|
||||
/// ordinary existence checks (`is_dir`, `exists`) report as plain `false`: the
|
||||
/// path looks *absent* rather than broken. Callers that would otherwise treat
|
||||
/// that as "nothing to mount here" use this to tell the two apart.
|
||||
pub(crate) fn is_stale_mount(path: &Path) -> bool {
|
||||
matches!(
|
||||
std::fs::metadata(path).map_err(|e| e.raw_os_error()),
|
||||
Err(Some(libc::ENOTCONN))
|
||||
)
|
||||
}
|
||||
|
||||
/// A secondary (on-demand sync folder) FUSE session, paired with its FUSE
|
||||
/// connection id so teardown can abort a mid-transfer connection rather than
|
||||
/// block on it. See [`Core::mounts`] and [`umount_session_unblocked`].
|
||||
pub(super) type SecondaryMount = (BackgroundSession, Option<u32>);
|
||||
|
||||
/// The kernel's id for the FUSE connection backing the mount at `mountpoint` —
|
||||
/// the directory name under `/sys/fs/fuse/connections`, which is the minor
|
||||
/// number of the mountpoint's device. Must be read *while still mounted*; after
|
||||
/// unmount the path resolves to the underlying directory on another device.
|
||||
/// `None` when the path can't be stat'd.
|
||||
pub(super) fn fuse_connection_id(mountpoint: &Path) -> Option<u32> {
|
||||
use std::os::unix::fs::MetadataExt;
|
||||
let dev = std::fs::metadata(mountpoint).ok()?.dev();
|
||||
Some(libc::minor(dev))
|
||||
}
|
||||
|
||||
/// Force the kernel to abort FUSE connection `id`, erroring every in-flight
|
||||
/// request.
|
||||
///
|
||||
/// On a stop signal we unmount lazily (`MNT_DETACH`) so the call succeeds even
|
||||
/// mid-transfer — but detach only removes the mountpoint; it does *not* end the
|
||||
/// connection while a request is still in flight. fuser's session loop then
|
||||
/// blocks on `/dev/fuse` waiting for a next request that never comes, so `join`
|
||||
/// hangs — long enough during a transfer that systemd's stop timeout SIGKILLs
|
||||
/// the daemon mid-unmount, stranding the on-demand mounts as dead endpoints.
|
||||
/// Writing the connection's `abort` file makes the pending reads fail with
|
||||
/// `ENODEV`, so the loop returns and `join` completes at once. Best-effort:
|
||||
/// there is nothing more to do on the shutdown path if it fails.
|
||||
pub(super) fn abort_fuse_connection(id: u32) {
|
||||
let path = format!("/sys/fs/fuse/connections/{id}/abort");
|
||||
if std::fs::write(&path, b"1").is_ok() {
|
||||
info!(id, "aborted FUSE connection to unblock unmount");
|
||||
}
|
||||
}
|
||||
|
||||
/// Unmount a background session that may be mid-transfer without wedging: abort
|
||||
/// its connection first (so the session loop exits promptly), then lazily
|
||||
/// unmount and join. `conn` is the id captured at mount time; `None` skips the
|
||||
/// abort and just unmounts (a healthy idle mount joins on its own `Destroy`).
|
||||
pub(super) fn umount_session_unblocked(
|
||||
session: BackgroundSession,
|
||||
conn: Option<u32>,
|
||||
) -> std::io::Result<()> {
|
||||
if let Some(id) = conn {
|
||||
abort_fuse_connection(id);
|
||||
}
|
||||
session.umount_and_join()
|
||||
}
|
||||
|
||||
/// Best-effort teardown of a stale mount left behind by a crashed daemon. A
|
||||
/// previous run that died without unmounting leaves the kernel mount in place,
|
||||
/// so the fresh `Session::new` below would fail with EBUSY ("Device or resource
|
||||
/// busy"). `fusermount3 -u -z` is the lazy (detach) unmount, which succeeds even
|
||||
/// when the old mount is still busy. Swallow all output/errors: if there is no
|
||||
/// stale mount this is simply a no-op.
|
||||
pub(super) fn clear_stale_mount(mountpoint: &Path) {
|
||||
for bin in ["fusermount3", "fusermount"] {
|
||||
let ok = std::process::Command::new(bin)
|
||||
.arg("-u")
|
||||
.arg("-z")
|
||||
.arg(mountpoint)
|
||||
.stdout(std::process::Stdio::null())
|
||||
.stderr(std::process::Stdio::null())
|
||||
.status()
|
||||
.map(|s| s.success())
|
||||
.unwrap_or(false);
|
||||
if ok {
|
||||
info!(mountpoint = %mountpoint.display(), "cleared stale mount before remount");
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `sync_state` key holding the uid of the My Files root, so a later run can
|
||||
/// recover it from `nodes` without the API (offline.md Phase 1).
|
||||
const ROOT_UID_KEY: &str = "root_uid";
|
||||
|
||||
/// The My Files root, and whether we got it from the API (`true`) or from the
|
||||
/// cache because the API was unreachable (`false`).
|
||||
///
|
||||
/// A successful fetch also records the root's uid, which is what makes the
|
||||
/// fallback possible on a later run: `nodes` is keyed by uid, so without this we
|
||||
/// would have the root's row on disk and no way to tell which one it is.
|
||||
///
|
||||
/// Failing to fetch is only fatal on a genuinely cold start — no cached root
|
||||
/// means an empty tree, and mounting that would show the user an empty Drive
|
||||
/// rather than an honest error.
|
||||
fn fetch_or_recall_root(
|
||||
client: &ProtonDriveClient,
|
||||
rt: &tokio::runtime::Handle,
|
||||
db: &Db,
|
||||
) -> std::io::Result<(Node, bool)> {
|
||||
let err = match rt.block_on(client.get_my_files_folder()) {
|
||||
Ok(root) => {
|
||||
if let Err(e) = db.set_state_str(ROOT_UID_KEY, &root.uid.to_string()) {
|
||||
warn!(error = %e, "persist root uid failed");
|
||||
}
|
||||
return Ok((root, true));
|
||||
}
|
||||
Err(e) => e,
|
||||
};
|
||||
let cached = db
|
||||
.state_str(ROOT_UID_KEY)
|
||||
.ok()
|
||||
.flatten()
|
||||
.and_then(|uid| db.node_by_uid(&uid).ok().flatten());
|
||||
match cached {
|
||||
Some(root) => {
|
||||
warn!(error = %err, "fetch My Files root failed; mounting from cache (offline)");
|
||||
Ok((root, false))
|
||||
}
|
||||
None => Err(std::io::Error::other(format!("fetch My Files root: {err}"))),
|
||||
}
|
||||
}
|
||||
|
||||
/// Per-mount settings resolved from [`pdfs_core::config::AppConfig`] by the
|
||||
/// caller, so `mount` itself never reads config or the environment.
|
||||
pub struct MountOptions {
|
||||
/// Proton account the session belongs to, for display and per-user paths.
|
||||
pub username: String,
|
||||
/// What the background conflict sweep may do. See `docs/BUGS.md` B71.
|
||||
pub sweep_mode: SweepMode,
|
||||
}
|
||||
|
||||
/// Mount the filesystem at `mountpoint` and block until it is unmounted or the
|
||||
/// daemon is asked to stop.
|
||||
///
|
||||
/// Resolves the My Files root up front — from the API, or from the cached tree
|
||||
/// when the API is unreachable (`fetch_or_recall_root`) — then spawns the
|
||||
/// Phase 2 event-sync task, the
|
||||
/// Phase 4 control socket, and runs the FUSE session on its own thread while
|
||||
/// this thread waits for either a stop signal (SIGTERM/SIGINT) or the kernel
|
||||
/// mount ending on its own. On a stop signal we lazily unmount ourselves
|
||||
/// (`umount_and_join`, the MNT_DETACH path that succeeds even while downloads
|
||||
/// are in flight), so `systemctl --user stop` is always a clean teardown.
|
||||
/// `rt` must be a handle to a *running* multi-threaded runtime.
|
||||
pub fn mount(
|
||||
client: ProtonDriveClient,
|
||||
rt: tokio::runtime::Handle,
|
||||
mountpoint: &Path,
|
||||
cache: ContentCache,
|
||||
control_socket: &Path,
|
||||
db: Arc<Db>,
|
||||
options: MountOptions,
|
||||
) -> std::io::Result<MountOutcome> {
|
||||
let MountOptions {
|
||||
username,
|
||||
sweep_mode,
|
||||
} = options;
|
||||
let (root, online) = fetch_or_recall_root(&client, &rt, &db)?;
|
||||
let scope = root.tree_event_scope_id();
|
||||
|
||||
// The folder-sync engine (devices.md Phase 2) runs on its own thread and is
|
||||
// nudged over this channel; the sender lives in Core so control-socket
|
||||
// handlers can trigger reconciles.
|
||||
let (sync_tx, sync_rx) = std::sync::mpsc::channel::<sync::SyncMsg>();
|
||||
|
||||
let core = Core {
|
||||
client: client.clone(),
|
||||
rt: rt.clone(),
|
||||
state: Arc::new(Mutex::new(State {
|
||||
entries: HashMap::new(),
|
||||
by_uid: HashMap::new(),
|
||||
children: HashMap::new(),
|
||||
next_ino: 2,
|
||||
active_writes: HashMap::new(),
|
||||
handles: HashMap::new(),
|
||||
next_fh: 1,
|
||||
db: db.clone(),
|
||||
})),
|
||||
cache: Arc::new(cache),
|
||||
readers: Arc::new(Mutex::new(HashMap::new())),
|
||||
stream_ring: Arc::new(Mutex::new(StreamRing::default())),
|
||||
workers: Arc::new(Workers::new(FUSE_WORKERS)?),
|
||||
db,
|
||||
online: Arc::new(AtomicBool::new(online)),
|
||||
pending: Arc::new(Mutex::new(HashMap::new())),
|
||||
hidden: Arc::new(Mutex::new(HashSet::new())),
|
||||
drain_wake: Arc::new((Mutex::new(false), Condvar::new())),
|
||||
timeline_refreshing: Arc::new(AtomicBool::new(false)),
|
||||
trash_refreshing: Arc::new(AtomicBool::new(false)),
|
||||
trash_progress: Arc::new(tokio::sync::Notify::new()),
|
||||
conflict_notified: Arc::new(Mutex::new(HashSet::new())),
|
||||
sweep_mode,
|
||||
own_sealed_revs: Arc::new(Mutex::new(HashMap::new())),
|
||||
self_changes: Arc::new(Mutex::new(HashMap::new())),
|
||||
thumb_gen: Arc::new(Mutex::new(HashSet::new())),
|
||||
no_thumbnail: Arc::new(Mutex::new(HashMap::new())),
|
||||
size_upgrades: Arc::new(Mutex::new(HashMap::new())),
|
||||
notifier: Arc::new(OnceLock::new()),
|
||||
transfers: TransferRegistry::new(),
|
||||
indexing: Arc::new(AtomicBool::new(false)),
|
||||
sync_progress: Arc::new(Mutex::new(HashMap::new())),
|
||||
sync_tx,
|
||||
mounts: Arc::new(Mutex::new(HashMap::new())),
|
||||
sync_locks: Arc::new(Mutex::new(HashMap::new())),
|
||||
states: Arc::new(StateRegistry::default()),
|
||||
};
|
||||
// Before anything can queue work against it: the drain thread below reaches
|
||||
// every mount's inode space through this registry, not through `core.state`.
|
||||
core.register_state();
|
||||
|
||||
// Writes queued by a previous run (or left behind by a crash) are still owed
|
||||
// an upload, and reads must be served from their staged blobs until they land.
|
||||
core.hydrate_pending();
|
||||
// Then the writes that were fsynced but never closed, which the cache moved
|
||||
// aside at open. After `hydrate_pending`, so a recovered partial write can
|
||||
// see an already-queued write to the same node.
|
||||
core.recover_fsynced_writes();
|
||||
{
|
||||
let core = core.clone();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-drain".into())
|
||||
.spawn(move || core.run_pending_drain())?;
|
||||
}
|
||||
|
||||
// Start the folder-sync engine. It watches every mirror folder, polls the
|
||||
// remotes, and reconciles on its own thread — never in front of a FUSE call.
|
||||
sync::spawn(core.clone(), sync_rx);
|
||||
|
||||
// Reconcile leftover `(sync-conflict …)` copies: drop the ones that turned
|
||||
// out identical to the live file, surface the ones that genuinely diverge.
|
||||
// Its own thread — it enumerates and trashes, and must never block a FUSE call.
|
||||
// `Off` skips the thread entirely rather than starting an idle one, so the
|
||||
// setting is verifiable from the outside (`ls /proc/<pid>/task/*/comm`).
|
||||
if sweep_mode == SweepMode::Off {
|
||||
info!("conflict sweep disabled by configuration");
|
||||
} else {
|
||||
info!(mode = ?sweep_mode, "conflict sweep enabled");
|
||||
let core = core.clone();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-conflict-sweep".into())
|
||||
.spawn(move || core.run_conflict_sweep_loop())?;
|
||||
}
|
||||
|
||||
// Mounted from the cache: watch for the network coming back so the mount can
|
||||
// stop being read-only-ish without the user restarting the daemon.
|
||||
if !online {
|
||||
let core = core.clone();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-online-probe".into())
|
||||
.spawn(move || core.run_online_probe())?;
|
||||
}
|
||||
|
||||
// Re-establish on-demand mounts left over from a previous run (devices.md
|
||||
// Phase 4). On its own thread: each remount fetches a remote node, and we
|
||||
// must not block the main mount below on the network.
|
||||
{
|
||||
let core = core.clone();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-restore-ondemand".into())
|
||||
.spawn(move || core.restore_ondemand_mounts())?;
|
||||
}
|
||||
|
||||
// Keep the launcher prompt's "This computer" index fresh. Its own thread:
|
||||
// the walk is I/O-heavy and must never sit in front of a FUSE callback.
|
||||
{
|
||||
let db = core.db.clone();
|
||||
let indexing = core.indexing.clone();
|
||||
let transfers = core.transfers.clone();
|
||||
let mountpoint = mountpoint.to_path_buf();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-localindex".into())
|
||||
.spawn(move || run_local_index(db, indexing, transfers, mountpoint))?;
|
||||
}
|
||||
|
||||
let mut config = Config::default();
|
||||
config.mount_options = vec![
|
||||
MountOption::FSName("protondrive".to_string()),
|
||||
MountOption::Subtype("protondrive".to_string()),
|
||||
MountOption::DefaultPermissions,
|
||||
];
|
||||
|
||||
// A crashed previous run can leave the kernel mount in place, which makes
|
||||
// the fresh mount below fail with EBUSY. Lazily detach any leftover first.
|
||||
clear_stale_mount(mountpoint);
|
||||
info!(mountpoint = %mountpoint.display(), "mounting Proton Drive");
|
||||
|
||||
// Bind the control socket before the FUSE session takes over the thread. A
|
||||
// stale socket file from a previous run would block the bind, so clear it.
|
||||
let _ = std::fs::remove_file(control_socket);
|
||||
let old_umask = unsafe { libc::umask(0o77) };
|
||||
let listener_res = UnixListener::bind(control_socket);
|
||||
unsafe { libc::umask(old_umask) };
|
||||
let listener = listener_res?;
|
||||
// Owner-only before anything can connect: a peer on this socket commands the
|
||||
// daemon's authenticated session without a credential of its own (B6).
|
||||
if let Err(e) = pdfs_core::config::restrict_socket(control_socket) {
|
||||
error!(error = %e, "cannot restrict control socket permissions; refusing to serve");
|
||||
let _ = std::fs::remove_file(control_socket);
|
||||
return Err(std::io::Error::other(format!(
|
||||
"control socket permissions: {e}"
|
||||
)));
|
||||
}
|
||||
{
|
||||
let core = core.clone();
|
||||
let username = username.clone();
|
||||
let mountpoint = mountpoint.to_path_buf();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-control".into())
|
||||
.spawn(move || run_control_socket(core, username, mountpoint, listener))?;
|
||||
}
|
||||
|
||||
let fs = ProtonFs::new(core.clone(), root);
|
||||
// Warm the in-memory maps from the DB so a cold start serves previously
|
||||
// seen metadata without re-hitting the API (plan.md P1).
|
||||
core.hydrate();
|
||||
|
||||
// Build the session explicitly (not `mount2`) so we can grab a `Notifier`
|
||||
// for the event task. `spawn` runs the session loop on its own background
|
||||
// thread; we then wait here for either a stop signal or the mount ending.
|
||||
let bg = Session::new(fs, mountpoint, &config)?.spawn()?;
|
||||
// The connection id, captured now while the mount is live, so a stop signal
|
||||
// mid-transfer can abort it rather than block `join` (see `abort_fuse_connection`).
|
||||
let main_conn = fuse_connection_id(mountpoint);
|
||||
let notifier = bg.notifier();
|
||||
// Same channel, kept on the `Core` so background work (a size upgrade, say)
|
||||
// can invalidate kernel-cached metadata without threading a handle through.
|
||||
let _ = core.notifier.set(notifier.clone());
|
||||
rt.spawn(run_event_sync(client, scope, core.clone()));
|
||||
|
||||
// Stop signals (SIGTERM from `systemctl --user stop`, SIGINT from Ctrl-C)
|
||||
// are delivered onto the async runtime; bridge them onto a sync channel so
|
||||
// the loop below can react without blocking a worker thread. A bounded
|
||||
// channel of 1 is enough — we only need to know that *a* stop arrived.
|
||||
let (sig_tx, sig_rx) = std::sync::mpsc::sync_channel::<()>(1);
|
||||
rt.spawn(async move {
|
||||
let mut sigterm =
|
||||
match tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate()) {
|
||||
Ok(s) => s,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "install SIGTERM handler failed");
|
||||
return;
|
||||
}
|
||||
};
|
||||
let mut sigint =
|
||||
match tokio::signal::unix::signal(tokio::signal::unix::SignalKind::interrupt()) {
|
||||
Ok(s) => s,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "install SIGINT handler failed");
|
||||
return;
|
||||
}
|
||||
};
|
||||
tokio::select! {
|
||||
_ = sigterm.recv() => info!("received SIGTERM"),
|
||||
_ = sigint.recv() => info!("received SIGINT"),
|
||||
}
|
||||
let _ = sig_tx.try_send(());
|
||||
});
|
||||
|
||||
// Wait for whichever happens first: a stop signal (→ we unmount ourselves
|
||||
// via the lazy MNT_DETACH path, clean even mid-download), or the kernel
|
||||
// mount ending on its own (→ the session thread finishes). Poll instead of
|
||||
// blocking on `join` so we can also notice the signal.
|
||||
let outcome = loop {
|
||||
match sig_rx.recv_timeout(Duration::from_millis(500)) {
|
||||
Ok(()) => {
|
||||
info!("stop requested; unmounting");
|
||||
if let Err(e) = umount_session_unblocked(bg, main_conn) {
|
||||
warn!(error = %e, "umount_and_join failed");
|
||||
}
|
||||
break MountOutcome::Shutdown;
|
||||
}
|
||||
Err(std::sync::mpsc::RecvTimeoutError::Timeout) => {
|
||||
if bg.guard.is_finished() {
|
||||
info!("mount ended externally");
|
||||
if let Err(e) = bg.join() {
|
||||
warn!(error = %e, "session join failed");
|
||||
}
|
||||
break MountOutcome::Unmounted;
|
||||
}
|
||||
}
|
||||
Err(std::sync::mpsc::RecvTimeoutError::Disconnected) => {
|
||||
// Signal task gone (failed to install); fall back to join.
|
||||
let _ = bg.join();
|
||||
break MountOutcome::Unmounted;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// Unmount every on-demand sync folder too, or the kernel mounts linger as
|
||||
// stale and the next start fails with EBUSY (devices.md Phase 3).
|
||||
let secondaries: Vec<_> = core.mounts.lock().drain().collect();
|
||||
for (id, (session, conn)) in secondaries {
|
||||
if let Err(e) = umount_session_unblocked(session, conn) {
|
||||
warn!(id, error = %e, "unmount on-demand folder failed");
|
||||
}
|
||||
}
|
||||
|
||||
let _ = std::fs::remove_file(control_socket);
|
||||
Ok(outcome)
|
||||
}
|
||||
@@ -18,10 +18,78 @@ use proton_drive_rs::{NodeKind, ThumbnailType};
|
||||
use tracing::{info, warn};
|
||||
|
||||
use super::{
|
||||
Core, PHOTOS_AVAILABLE, PHOTOS_SYNCED_MS, THUMB_GEN_CONCURRENCY, TIMELINE_ENRICH_CHUNK,
|
||||
TIMELINE_TTL, ThumbAttempt, node_size, now_ms, parse_uid, ratio_of, scale_thumbnail,
|
||||
Core, PHOTOS_AVAILABLE, PHOTOS_SYNCED_MS, TIMELINE_ENRICH_CHUNK, TIMELINE_TTL, node_size,
|
||||
now_ms, parse_uid,
|
||||
};
|
||||
|
||||
/// Longest edge, in px, of a thumbnail generated locally for a photo the server
|
||||
/// has none for. Matches the server's own thumbnail scale closely enough that a
|
||||
/// tile can't tell them apart.
|
||||
const THUMB_EDGE: u32 = 512;
|
||||
/// JPEG quality of a locally generated thumbnail.
|
||||
const THUMB_QUALITY: u8 = 82;
|
||||
/// How many photos may be downloaded at once to generate their missing
|
||||
/// thumbnails. Bounded: a screenful of 20 MB digicam JPEGs would otherwise
|
||||
/// saturate the link and starve the rest of the daemon.
|
||||
const THUMB_GEN_CONCURRENCY: usize = 4;
|
||||
|
||||
/// The aspect ratio (w/h) of an encoded image, read from its header alone — no
|
||||
/// pixels are decoded. `None` when the format is unknown or the header is torn.
|
||||
fn ratio_of(bytes: &[u8]) -> Option<f64> {
|
||||
let (width, height) = image::ImageReader::new(std::io::Cursor::new(bytes))
|
||||
.with_guessed_format()
|
||||
.ok()?
|
||||
.into_dimensions()
|
||||
.ok()?;
|
||||
(height > 0).then(|| f64::from(width) / f64::from(height))
|
||||
}
|
||||
|
||||
/// A thumbnail the daemon made itself, and the aspect ratio of the photo it was
|
||||
/// made from (free at that point — the full image had to be decoded anyway).
|
||||
struct GeneratedThumb {
|
||||
bytes: Vec<u8>,
|
||||
ratio: f64,
|
||||
}
|
||||
|
||||
/// How one attempt at generating a missing thumbnail ended. The distinction that
|
||||
/// matters is *permanent* versus *transient*: only bytes we cannot decode prove
|
||||
/// the photo will never have a thumbnail, and only that verdict is persisted.
|
||||
enum ThumbAttempt {
|
||||
Made(GeneratedThumb),
|
||||
/// Decoded nothing — a format this build has no decoder for. Permanent.
|
||||
Undecodable,
|
||||
/// The photo couldn't be downloaded. Transient: try again next time.
|
||||
Unavailable,
|
||||
}
|
||||
|
||||
/// Scale a full-size photo down to a thumbnail: at most [`THUMB_EDGE`] on its
|
||||
/// longest side, JPEG, aspect ratio preserved. `None` when the bytes aren't an
|
||||
/// image this build can decode — the caller then writes the photo off as
|
||||
/// un-thumbnailable.
|
||||
///
|
||||
/// CPU-bound (a 20 MP JPEG is real work), so callers run it on the blocking pool.
|
||||
fn scale_thumbnail(bytes: &[u8]) -> Option<GeneratedThumb> {
|
||||
let image = image::ImageReader::new(std::io::Cursor::new(bytes))
|
||||
.with_guessed_format()
|
||||
.ok()?
|
||||
.decode()
|
||||
.ok()?;
|
||||
let (width, height) = (image.width(), image.height());
|
||||
if width == 0 || height == 0 {
|
||||
return None;
|
||||
}
|
||||
let ratio = f64::from(width) / f64::from(height);
|
||||
|
||||
// `thumbnail` fits the image *inside* the box, so the longest edge lands on
|
||||
// THUMB_EDGE and the ratio is untouched.
|
||||
let thumb = image.thumbnail(THUMB_EDGE, THUMB_EDGE).to_rgb8();
|
||||
let mut bytes = Vec::new();
|
||||
image::codecs::jpeg::JpegEncoder::new_with_quality(&mut bytes, THUMB_QUALITY)
|
||||
.encode_image(&thumb)
|
||||
.ok()?;
|
||||
Some(GeneratedThumb { bytes, ratio })
|
||||
}
|
||||
|
||||
impl Core {
|
||||
pub(crate) fn photos_timeline(
|
||||
&self,
|
||||
@@ -361,3 +429,60 @@ impl Core {
|
||||
Ok(self.cache.content_path(uid))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod thumb_tests {
|
||||
use super::{THUMB_EDGE, ratio_of, scale_thumbnail};
|
||||
|
||||
/// A `width`×`height` JPEG, standing in for a camera photo the server never
|
||||
/// generated a thumbnail for.
|
||||
fn jpeg(width: u32, height: u32) -> Vec<u8> {
|
||||
let image = image::RgbImage::from_fn(width, height, |x, y| {
|
||||
image::Rgb([(x % 256) as u8, (y % 256) as u8, 128])
|
||||
});
|
||||
let mut bytes = Vec::new();
|
||||
image::codecs::jpeg::JpegEncoder::new(&mut bytes)
|
||||
.encode_image(&image)
|
||||
.unwrap();
|
||||
bytes
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn scaling_fits_the_long_edge_and_keeps_the_aspect_ratio() {
|
||||
let photo = jpeg(4000, 3000);
|
||||
let thumb = scale_thumbnail(&photo).expect("a JPEG scales");
|
||||
|
||||
let (width, height) = image::ImageReader::new(std::io::Cursor::new(&thumb.bytes))
|
||||
.with_guessed_format()
|
||||
.unwrap()
|
||||
.into_dimensions()
|
||||
.unwrap();
|
||||
assert_eq!(width, THUMB_EDGE, "the long edge lands on the target");
|
||||
assert_eq!(height, THUMB_EDGE * 3 / 4, "and nothing is cropped");
|
||||
assert!((thumb.ratio - 4.0 / 3.0).abs() < 1e-6);
|
||||
assert!(
|
||||
thumb.bytes.len() < photo.len(),
|
||||
"a thumbnail that isn't smaller than its photo is no thumbnail"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_portrait_photo_fits_its_long_edge_too() {
|
||||
let thumb = scale_thumbnail(&jpeg(1000, 2000)).expect("a JPEG scales");
|
||||
assert!(thumb.ratio < 1.0, "portrait stays portrait");
|
||||
assert_eq!(ratio_of(&thumb.bytes).map(|r| r < 1.0), Some(true));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn undecodable_bytes_are_not_a_thumbnail() {
|
||||
// What a photo in a format this build has no decoder for looks like: the
|
||||
// caller writes it off as un-thumbnailable rather than retrying forever.
|
||||
assert!(scale_thumbnail(b"not an image at all").is_none());
|
||||
assert!(ratio_of(b"not an image at all").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ratio_is_read_from_the_header_alone() {
|
||||
assert_eq!(ratio_of(&jpeg(300, 200)), Some(1.5));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,394 @@
|
||||
//! Reading and writing this machine's `profile.json` in its device root, and
|
||||
//! the restore that rebuilds a machine from one (features.md 5.2 and 5.3).
|
||||
//!
|
||||
//! The document itself is defined in [`pdfs_core::profile`]; this is the half
|
||||
//! that talks to Drive. Saving is best-effort and never blocks a user action:
|
||||
//! the profile is a convenience for a *future* machine, so failing to write it
|
||||
//! must not fail the folder add that triggered it.
|
||||
|
||||
use std::io::Cursor;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::OnceLock;
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
|
||||
use pdfs_core::control::RestorableFolder;
|
||||
use pdfs_core::profile::{PROFILE_FILE_NAME, PROFILE_VERSION, Profile, ProfileFolder, ProfilePin};
|
||||
use pdfs_core::{CoreError, CoreResult};
|
||||
use proton_drive_rs::proton_sdk::ids::NodeUid;
|
||||
use tracing::{info, warn};
|
||||
|
||||
use super::sync;
|
||||
use super::{Core, now_secs, parse_uid, this_hostname};
|
||||
|
||||
/// Coalescing flags for background profile saves.
|
||||
///
|
||||
/// A single burst of user actions (adding three folders, pinning a tree) should
|
||||
/// cost one upload, not one per action. `SAVING` admits one worker at a time and
|
||||
/// `DIRTY` records that something changed while it was busy, so the worker takes
|
||||
/// exactly one more lap afterwards.
|
||||
///
|
||||
/// Process-global rather than a [`Core`] field because on-demand mounts fork
|
||||
/// their own `Core` (`Core::fork_state`) and all of them describe the same
|
||||
/// machine — there is one profile per daemon, so there is one flag pair.
|
||||
static SAVE_STATE: OnceLock<(AtomicBool, AtomicBool)> = OnceLock::new();
|
||||
|
||||
fn save_state() -> &'static (AtomicBool, AtomicBool) {
|
||||
SAVE_STATE.get_or_init(|| (AtomicBool::new(false), AtomicBool::new(false)))
|
||||
}
|
||||
|
||||
impl Core {
|
||||
/// Note that the arrangement this machine's profile describes has changed,
|
||||
/// and upload a fresh profile in the background.
|
||||
///
|
||||
/// Fire-and-forget by design: callers are mutation paths (add/remove a sync
|
||||
/// folder, switch a mode, pin a node, save settings) whose success does not
|
||||
/// depend on the backup succeeding.
|
||||
pub(crate) fn touch_profile(&self) {
|
||||
let (saving, dirty) = save_state();
|
||||
dirty.store(true, Ordering::SeqCst);
|
||||
// Someone is already uploading; they will see DIRTY and take another lap.
|
||||
if saving.swap(true, Ordering::SeqCst) {
|
||||
return;
|
||||
}
|
||||
let core = self.clone();
|
||||
std::thread::spawn(move || {
|
||||
let (saving, dirty) = save_state();
|
||||
while dirty.swap(false, Ordering::SeqCst) {
|
||||
if let Err(e) = core.save_profile() {
|
||||
warn!(error = %e.message, "profile backup failed");
|
||||
break;
|
||||
}
|
||||
}
|
||||
saving.store(false, Ordering::SeqCst);
|
||||
});
|
||||
}
|
||||
|
||||
/// Serialize this machine's arrangement and upload it to `profile.json` in
|
||||
/// the device root, replacing any existing one.
|
||||
///
|
||||
/// Does nothing when no device is registered: a machine that has never
|
||||
/// synced a folder has nothing to describe, and registering a device just to
|
||||
/// hold an empty profile would put a stray computer in the user's Drive.
|
||||
pub(crate) fn save_profile(&self) -> CoreResult<()> {
|
||||
let Some(device) = self
|
||||
.db
|
||||
.device_get()
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?
|
||||
else {
|
||||
return Ok(());
|
||||
};
|
||||
let root_uid = parse_uid(&device.root_uid).ok_or_else(|| {
|
||||
CoreError::internal(format!("bad device root uid: {}", device.root_uid))
|
||||
})?;
|
||||
|
||||
let profile = self.build_profile(&device.uid)?;
|
||||
let bytes = profile.to_bytes().map_err(CoreError::internal)?;
|
||||
let len = bytes.len() as i64;
|
||||
|
||||
// Replace the existing document rather than adding a second file of the
|
||||
// same name: the profile is a single mutable record, and a device root
|
||||
// with `profile.json` and `profile (1).json` in it teaches the restore
|
||||
// nothing about which to trust.
|
||||
let existing = self.find_device_child_file(&root_uid, PROFILE_FILE_NAME)?;
|
||||
match existing {
|
||||
Some(uid) => self
|
||||
.rt
|
||||
.block_on(self.client.upload_new_revision_from(
|
||||
&uid,
|
||||
Cursor::new(bytes),
|
||||
len,
|
||||
Vec::new(),
|
||||
Some(now_secs()),
|
||||
))
|
||||
.map(|_| ())
|
||||
.map_err(|e| CoreError::from_api(&e, "upload profile revision"))?,
|
||||
None => {
|
||||
self.rt
|
||||
.block_on(self.client.upload_file_replacing_draft_from(
|
||||
&root_uid,
|
||||
PROFILE_FILE_NAME,
|
||||
"application/json",
|
||||
Cursor::new(bytes),
|
||||
len,
|
||||
Vec::new(),
|
||||
Some(now_secs()),
|
||||
false,
|
||||
))
|
||||
.map_err(|e| CoreError::from_api(&e, "upload profile"))?;
|
||||
}
|
||||
}
|
||||
info!(folders = profile.folders.len(), "profile backed up");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Snapshot the local arrangement into a [`Profile`].
|
||||
fn build_profile(&self, device_uid: &str) -> CoreResult<Profile> {
|
||||
let folders = self
|
||||
.db
|
||||
.sync_folder_list()
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?
|
||||
.into_iter()
|
||||
.map(|f| ProfileFolder {
|
||||
remote_uid: f.remote_uid,
|
||||
local_path: f.local_path,
|
||||
// A queued switch is where the user asked the folder to be, so
|
||||
// that is what the next machine should set up.
|
||||
mode: f.pending_mode.unwrap_or(f.mode),
|
||||
})
|
||||
.collect();
|
||||
let pins = self
|
||||
.db
|
||||
.pin_list()
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?
|
||||
.into_iter()
|
||||
.map(|(uid, path, recursive)| ProfilePin {
|
||||
uid,
|
||||
path,
|
||||
recursive,
|
||||
})
|
||||
.collect();
|
||||
let cfg = pdfs_core::config::AppDirs::new()
|
||||
.map(|d| d.load_config())
|
||||
.unwrap_or_default();
|
||||
Ok(Profile {
|
||||
version: PROFILE_VERSION,
|
||||
device_uid: device_uid.to_string(),
|
||||
hostname: this_hostname(),
|
||||
saved_at: now_secs(),
|
||||
folders,
|
||||
pins,
|
||||
ignore_patterns: cfg.ignore_patterns,
|
||||
cache_budget: cfg.cache_budget,
|
||||
mountpoint: cfg.mountpoint,
|
||||
})
|
||||
}
|
||||
|
||||
/// An untrashed *file* named `name` directly under the device root.
|
||||
///
|
||||
/// The sibling of `find_device_child_folder`; kept separate because a folder
|
||||
/// named `profile.json` must not be mistaken for the profile.
|
||||
fn find_device_child_file(
|
||||
&self,
|
||||
root_uid: &NodeUid,
|
||||
name: &str,
|
||||
) -> CoreResult<Option<NodeUid>> {
|
||||
let uids = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_folder_children_node_uids(root_uid))
|
||||
.map_err(|e| CoreError::from_api(&e, "list device root"))?;
|
||||
if uids.is_empty() {
|
||||
return Ok(None);
|
||||
}
|
||||
let nodes = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_nodes(&uids))
|
||||
.map_err(|e| CoreError::from_api(&e, "resolve device root children"))?;
|
||||
Ok(nodes
|
||||
.into_iter()
|
||||
.find(|n| !n.is_folder() && !n.trashed && n.name == name)
|
||||
.map(|n| n.uid))
|
||||
}
|
||||
|
||||
/// Download and parse the profile in the device root, if there is one.
|
||||
fn load_profile(&self, root_uid: &NodeUid) -> CoreResult<Option<Profile>> {
|
||||
let Some(uid) = self.find_device_child_file(root_uid, PROFILE_FILE_NAME)? else {
|
||||
return Ok(None);
|
||||
};
|
||||
let mut buf: Vec<u8> = Vec::new();
|
||||
self.rt
|
||||
.block_on(self.client.download_file_to(&uid, &mut buf))
|
||||
.map_err(|e| CoreError::from_api(&e, "download profile"))?;
|
||||
Profile::parse(&buf).map(Some).map_err(CoreError::invalid)
|
||||
}
|
||||
|
||||
// ---- restore (features.md 5.2) ----------------------------------------
|
||||
|
||||
/// The folders under this machine's device that could be synced here, each
|
||||
/// carrying a proposed local path.
|
||||
///
|
||||
/// The proposal comes from the profile when one exists and its path is
|
||||
/// usable on this machine, and from `~/<name>` otherwise — a restored
|
||||
/// `/home/other-user/Documents` would be wrong on a machine where that user
|
||||
/// does not exist, and silently creating it would be worse.
|
||||
pub(crate) fn list_restorable_folders(&self) -> CoreResult<Vec<RestorableFolder>> {
|
||||
let device = self.ensure_device()?;
|
||||
let root_uid = parse_uid(&device.root_uid).ok_or_else(|| {
|
||||
CoreError::internal(format!("bad device root uid: {}", device.root_uid))
|
||||
})?;
|
||||
|
||||
let profile = match self.load_profile(&root_uid) {
|
||||
Ok(p) => p,
|
||||
// A missing or unreadable profile is not fatal: the remote tree
|
||||
// alone is enough to offer a restore, just with plainer defaults.
|
||||
Err(e) => {
|
||||
warn!(error = %e.message, "could not read profile; proposing defaults");
|
||||
None
|
||||
}
|
||||
};
|
||||
|
||||
let uids = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_folder_children_node_uids(&root_uid))
|
||||
.map_err(|e| CoreError::from_api(&e, "list device root"))?;
|
||||
let nodes = if uids.is_empty() {
|
||||
Vec::new()
|
||||
} else {
|
||||
self.rt
|
||||
.block_on(self.client.enumerate_nodes(&uids))
|
||||
.map_err(|e| CoreError::from_api(&e, "resolve device root children"))?
|
||||
};
|
||||
|
||||
// Folders already synced here are not restorable — they are already
|
||||
// restored — but they are still listed, flagged, so the picker can show
|
||||
// the whole device rather than a confusing subset.
|
||||
let existing: Vec<String> = self
|
||||
.db
|
||||
.sync_folder_list()
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?
|
||||
.into_iter()
|
||||
.map(|f| f.remote_uid)
|
||||
.collect();
|
||||
|
||||
Ok(nodes
|
||||
.into_iter()
|
||||
.filter(|n| n.is_folder() && !n.trashed)
|
||||
.map(|n| {
|
||||
let uid = n.uid.to_string();
|
||||
let saved = profile
|
||||
.as_ref()
|
||||
.and_then(|p| p.folders.iter().find(|f| f.remote_uid == uid));
|
||||
let proposed = saved
|
||||
.map(|f| PathBuf::from(&f.local_path))
|
||||
.filter(|p| path_is_usable_here(p))
|
||||
.unwrap_or_else(|| default_local_path(&n.name));
|
||||
RestorableFolder {
|
||||
already_synced: existing.iter().any(|e| e == &uid),
|
||||
remote_uid: uid,
|
||||
name: n.name,
|
||||
local_path: proposed.to_string_lossy().to_string(),
|
||||
mode: saved
|
||||
.map(|f| f.mode.clone())
|
||||
.unwrap_or_else(|| "mirror".into()),
|
||||
}
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
/// Attach remote device folders to local paths and let the sync engine fill
|
||||
/// them in.
|
||||
///
|
||||
/// The download is not written here: a new sync-folder row starts with an
|
||||
/// empty baseline, and an empty baseline against an empty local directory
|
||||
/// and a populated remote already classifies as "download everything". The
|
||||
/// restore is therefore just bookkeeping plus a `Reconcile`, and it reuses
|
||||
/// the engine's conflict handling for the case where the local directory
|
||||
/// turns out not to be empty after all.
|
||||
pub(crate) fn restore_sync_folders(
|
||||
&self,
|
||||
items: &[pdfs_core::control::RestoreItem],
|
||||
) -> CoreResult<String> {
|
||||
if items.is_empty() {
|
||||
return Err(CoreError::invalid("nothing to restore"));
|
||||
}
|
||||
let device = self.ensure_device()?;
|
||||
let existing = self
|
||||
.db
|
||||
.sync_folder_list()
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?;
|
||||
|
||||
let mut restored = 0usize;
|
||||
let mut skipped: Vec<String> = Vec::new();
|
||||
for item in items {
|
||||
let local = PathBuf::from(&item.local_path);
|
||||
if !local.is_absolute() {
|
||||
skipped.push(format!("{}: local path must be absolute", item.local_path));
|
||||
continue;
|
||||
}
|
||||
if existing.iter().any(|f| f.remote_uid == item.remote_uid) {
|
||||
skipped.push(format!("{}: already synced", item.local_path));
|
||||
continue;
|
||||
}
|
||||
if existing
|
||||
.iter()
|
||||
.any(|f| Path::new(&f.local_path) == local.as_path())
|
||||
{
|
||||
skipped.push(format!("{}: path already in use", item.local_path));
|
||||
continue;
|
||||
}
|
||||
if let Err(e) = std::fs::create_dir_all(&local) {
|
||||
skipped.push(format!("{}: {e}", item.local_path));
|
||||
continue;
|
||||
}
|
||||
let mode = match item.mode.as_str() {
|
||||
"mirror" | "ondemand" => item.mode.as_str(),
|
||||
other => {
|
||||
skipped.push(format!("{}: unknown mode {other}", item.local_path));
|
||||
continue;
|
||||
}
|
||||
};
|
||||
let id = self
|
||||
.db
|
||||
.sync_folder_add(&local.to_string_lossy(), &item.remote_uid, &device.share_id)
|
||||
.map_err(|e| CoreError::internal(format!("db: {e:?}")))?;
|
||||
// `ondemand` is applied through the normal request path, which
|
||||
// mounts the FUSE session and handles the folder being busy — the
|
||||
// restore does not get its own copy of that logic.
|
||||
if mode == "ondemand" {
|
||||
let _ = self.request_sync_folder_mode(id, "ondemand");
|
||||
}
|
||||
let _ = self.sync_tx.send(sync::SyncMsg::Reconcile(id));
|
||||
restored += 1;
|
||||
}
|
||||
let _ = self.sync_tx.send(sync::SyncMsg::Rewatch);
|
||||
|
||||
let mut message = format!("restored {restored} folder(s)");
|
||||
if !skipped.is_empty() {
|
||||
message.push_str(&format!("; skipped: {}", skipped.join(", ")));
|
||||
}
|
||||
info!(restored, skipped = skipped.len(), "restore complete");
|
||||
Ok(message)
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether a path recorded on another machine can be reused verbatim here.
|
||||
///
|
||||
/// Requires the *parent* to exist: `~/Documents` on a machine with the same
|
||||
/// username is a fine proposal even though the directory itself is gone (the
|
||||
/// restore creates it), but `/home/someone-else/Documents` is not.
|
||||
fn path_is_usable_here(path: &Path) -> bool {
|
||||
path.is_absolute() && path.parent().is_some_and(|p| p.is_dir())
|
||||
}
|
||||
|
||||
/// `~/<name>`, or `/<name>` if the home directory cannot be determined.
|
||||
fn default_local_path(name: &str) -> PathBuf {
|
||||
match pdfs_core::config::AppDirs::new()
|
||||
.ok()
|
||||
.and_then(|d| d.home_dir())
|
||||
{
|
||||
Some(home) => home.join(name),
|
||||
None => PathBuf::from("/").join(name),
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn foreign_home_is_not_reused() {
|
||||
assert!(!path_is_usable_here(Path::new(
|
||||
"/home/definitely-not-a-user-here/Documents"
|
||||
)));
|
||||
assert!(!path_is_usable_here(Path::new("relative/path")));
|
||||
}
|
||||
|
||||
/// A path whose parent exists but which does not itself is exactly the
|
||||
/// restore case — the directory is about to be created.
|
||||
#[test]
|
||||
fn missing_leaf_under_existing_parent_is_reused() {
|
||||
let dir = std::env::temp_dir().join("pdfs-restore-probe");
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
assert!(path_is_usable_here(&dir.join("Documents")));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,645 @@
|
||||
//! Revision-reader cache and streamed range-read subsystem.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// A read of an unpinned video at least this large streams *without* persisting
|
||||
/// its blocks to the on-disk cache. Playing a 2 GB film would otherwise pour it
|
||||
/// through the block LRU and evict everything else the user actually wants kept —
|
||||
/// and it re-streams cheaply enough on a rewatch that keeping it was never worth
|
||||
/// that. Pinned videos (kept offline on purpose) and anything smaller cache as
|
||||
/// usual.
|
||||
pub(super) const STREAM_BYPASS_MIN: u64 = 256 * 1024 * 1024;
|
||||
|
||||
/// How many bytes of streamed blocks the in-memory ring keeps. Bypassing the
|
||||
/// on-disk cache must not mean re-fetching: the kernel asks for a streamed file
|
||||
/// in reads far smaller than [`BLOCK_SIZE`], so without a ring every 128 KiB the
|
||||
/// player consumes would download and decrypt a whole 4 MiB block again. Sized
|
||||
/// for a handful of blocks per concurrently-streamed file.
|
||||
const STREAM_RING_BYTES: u64 = 128 * 1024 * 1024;
|
||||
|
||||
/// Blocks fetched *past* the one a sequential streaming read needed, warmed into
|
||||
/// the ring in the background so the player's next read is already in memory
|
||||
/// instead of waiting a round-trip. Kept small so it cannot crowd out the
|
||||
/// in-flight block governor.
|
||||
const STREAM_READAHEAD: u64 = 4;
|
||||
|
||||
/// How many [`RevisionReader`]s stay open at once.
|
||||
///
|
||||
/// A reader holds its revision's content key and block table — a few KB even for
|
||||
/// a large file, so this is bounded for tidiness and staleness rather than
|
||||
/// memory. Evicted least-recently-used; a dropped reader costs one re-open
|
||||
/// (two API calls and a node-key unlock) the next time that file is read.
|
||||
const MAX_OPEN_READERS: usize = 64;
|
||||
|
||||
/// An open reader plus the node metadata it was opened against.
|
||||
///
|
||||
/// The SDK pins a reader to the revision that was active at `open_revision`, so
|
||||
/// a reader is only reusable while the node still reports the same
|
||||
/// `(mtime, size)` — the same validity pair the content cache uses (a new
|
||||
/// revision bumps mtime). On a mismatch the reader is dropped and reopened.
|
||||
pub(super) struct CachedReader {
|
||||
reader: Arc<RevisionReader>,
|
||||
mtime: i64,
|
||||
size: u64,
|
||||
/// For LRU eviction.
|
||||
last_used: Instant,
|
||||
}
|
||||
|
||||
/// What the `readers` map holds for a node: an open reader, or the fact that
|
||||
/// someone is already opening one.
|
||||
///
|
||||
/// The `Pending` arm is what makes the map single-flight rather than merely a
|
||||
/// cache. Opening resolves link details, ancestor keys, an S2K node-key unlock
|
||||
/// and the block table — five round-trips — and read-ahead on a cold file puts
|
||||
/// several workers into the open at the same moment, so without this each
|
||||
/// racer would redo all of it and discard every result but one.
|
||||
pub(super) enum ReaderSlot {
|
||||
Ready(CachedReader),
|
||||
Pending(PendingOpen),
|
||||
}
|
||||
|
||||
/// An `open_revision` in flight. Racers clone `rx` and await the leader's result
|
||||
/// instead of opening their own.
|
||||
pub(super) struct PendingOpen {
|
||||
/// Identifies this attempt so the leader can tell "my slot is still there"
|
||||
/// from "someone evicted or replaced it while I was on the network", and
|
||||
/// only publish its reader in the first case.
|
||||
id: u64,
|
||||
/// What the leader is opening against. A racer wanting a different revision
|
||||
/// must not join this open — it would get a reader for the wrong bytes.
|
||||
mtime: i64,
|
||||
size: u64,
|
||||
rx: tokio::sync::watch::Receiver<Option<Result<Arc<RevisionReader>, Errno>>>,
|
||||
}
|
||||
|
||||
/// Distinguishes `PendingOpen`s. Only uniqueness matters, so a plain counter
|
||||
/// does; ids are never compared for order.
|
||||
static NEXT_OPEN_ID: AtomicU64 = AtomicU64::new(0);
|
||||
|
||||
/// Drive client, a Tokio handle to bridge the synchronous FUSE/socket threads
|
||||
/// to the async SDK, the inode bookkeeping, and the on-disk content cache.
|
||||
///
|
||||
/// Cheaply cloneable (every field is a handle/`Arc`), so the control-socket task
|
||||
/// gets its own copy while the FUSE session keeps another.
|
||||
/// In-memory LRU of blocks belonging to a file streaming past the on-disk cache
|
||||
/// (see [`STREAM_BYPASS_MIN`]). Bypassing the disk stops one film evicting the
|
||||
/// block LRU; it must not also mean the same 4 MiB block is downloaded once per
|
||||
/// 128 KiB the player reads out of it.
|
||||
///
|
||||
/// Validated by the same `(mtime, size)` pair the on-disk caches use: a node
|
||||
/// whose tag no longer matches has its blocks dropped rather than served, so a
|
||||
/// new revision can never be stitched together from the old one.
|
||||
#[derive(Default)]
|
||||
pub(super) struct StreamRing {
|
||||
blocks: HashMap<(NodeUid, u64), Arc<Vec<u8>>>,
|
||||
/// Keys oldest-first, for eviction.
|
||||
order: VecDeque<(NodeUid, u64)>,
|
||||
/// Per-node validity tag, `(mtime, size)`.
|
||||
tags: HashMap<NodeUid, (i64, u64)>,
|
||||
bytes: u64,
|
||||
}
|
||||
|
||||
impl StreamRing {
|
||||
fn get(&mut self, uid: &NodeUid, mtime: i64, size: u64, idx: u64) -> Option<Arc<Vec<u8>>> {
|
||||
if self.tags.get(uid) != Some(&(mtime, size)) {
|
||||
return None;
|
||||
}
|
||||
self.blocks.get(&(uid.clone(), idx)).cloned()
|
||||
}
|
||||
|
||||
fn insert(&mut self, uid: &NodeUid, mtime: i64, size: u64, idx: u64, bytes: Arc<Vec<u8>>) {
|
||||
if self.tags.get(uid) != Some(&(mtime, size)) {
|
||||
// Revision changed under us (or first sight): anything held for this
|
||||
// node describes the old one.
|
||||
self.drop_node(uid);
|
||||
self.tags.insert(uid.clone(), (mtime, size));
|
||||
}
|
||||
let key = (uid.clone(), idx);
|
||||
if self.blocks.contains_key(&key) {
|
||||
return;
|
||||
}
|
||||
self.bytes += bytes.len() as u64;
|
||||
self.blocks.insert(key.clone(), bytes);
|
||||
self.order.push_back(key);
|
||||
while self.bytes > STREAM_RING_BYTES {
|
||||
let Some(victim) = self.order.pop_front() else {
|
||||
break;
|
||||
};
|
||||
if let Some(dropped) = self.blocks.remove(&victim) {
|
||||
self.bytes -= dropped.len() as u64;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn drop_node(&mut self, uid: &NodeUid) {
|
||||
self.order.retain(|(u, _)| u != uid);
|
||||
let mut freed = 0u64;
|
||||
self.blocks.retain(|(u, _), bytes| {
|
||||
if u == uid {
|
||||
freed += bytes.len() as u64;
|
||||
false
|
||||
} else {
|
||||
true
|
||||
}
|
||||
});
|
||||
self.bytes -= freed;
|
||||
self.tags.remove(uid);
|
||||
}
|
||||
}
|
||||
|
||||
impl Core {
|
||||
/// An open [`RevisionReader`] for `uid`, reusing the cached one when it is
|
||||
/// still valid for `(mtime, fsize)` and opening a fresh one otherwise.
|
||||
///
|
||||
/// Opening resolves the file's link details, ancestor keys, node key (an S2K
|
||||
/// unlock) and block table. Doing that once per file rather than once per
|
||||
/// block is the whole point: a cold 100 MB read is 25 block misses, which
|
||||
/// used to mean 25 full resolutions (50 API calls, 25 unlocks) and now means
|
||||
/// one.
|
||||
///
|
||||
/// Racing reads of one cold file open it **once**: the first caller claims
|
||||
/// the slot and the rest await its result. That matters now that `read` is
|
||||
/// served off the dispatch loop, because read-ahead on a first touch issues
|
||||
/// several parallel reads of the same file as a matter of course.
|
||||
async fn revision_reader(
|
||||
&self,
|
||||
uid: &NodeUid,
|
||||
mtime: i64,
|
||||
fsize: u64,
|
||||
) -> Result<Arc<RevisionReader>, Errno> {
|
||||
loop {
|
||||
// Decide under the lock, act outside it — network I/O must never run
|
||||
// under a std `Mutex`, and an await must never hold one.
|
||||
enum Act {
|
||||
Hit(Arc<RevisionReader>),
|
||||
Join(tokio::sync::watch::Receiver<Option<Result<Arc<RevisionReader>, Errno>>>),
|
||||
Lead(
|
||||
u64,
|
||||
tokio::sync::watch::Sender<Option<Result<Arc<RevisionReader>, Errno>>>,
|
||||
),
|
||||
}
|
||||
let act = {
|
||||
let mut readers = self.readers.lock();
|
||||
match readers.get_mut(uid) {
|
||||
Some(ReaderSlot::Ready(entry))
|
||||
if entry.mtime == mtime && entry.size == fsize =>
|
||||
{
|
||||
entry.last_used = Instant::now();
|
||||
Act::Hit(entry.reader.clone())
|
||||
}
|
||||
Some(ReaderSlot::Pending(p)) if p.mtime == mtime && p.size == fsize => {
|
||||
Act::Join(p.rx.clone())
|
||||
}
|
||||
// Either nothing here, or something for a revision we no
|
||||
// longer want (a stale reader, or an open for one). Ours
|
||||
// replaces it: the newer `(mtime, size)` is the truth.
|
||||
_ => {
|
||||
let id = NEXT_OPEN_ID.fetch_add(1, Ordering::Relaxed);
|
||||
let (tx, rx) = tokio::sync::watch::channel(None);
|
||||
readers.insert(
|
||||
uid.clone(),
|
||||
ReaderSlot::Pending(PendingOpen {
|
||||
id,
|
||||
mtime,
|
||||
size: fsize,
|
||||
rx,
|
||||
}),
|
||||
);
|
||||
Act::Lead(id, tx)
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
match act {
|
||||
Act::Hit(reader) => return Ok(reader),
|
||||
Act::Join(mut rx) => {
|
||||
// `changed()` errors only if the leader dropped its sender
|
||||
// without publishing — it panicked. Retry from the top
|
||||
// rather than fail: the slot it left is gone, so this pass
|
||||
// leads its own open.
|
||||
loop {
|
||||
if let Some(result) = rx.borrow_and_update().clone() {
|
||||
return result;
|
||||
}
|
||||
if rx.changed().await.is_err() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
Act::Lead(id, tx) => {
|
||||
debug!(%uid, mtime, fsize, "opening revision");
|
||||
let result = match self.client.open_revision(uid).await {
|
||||
Ok(reader) => Ok(Arc::new(reader)),
|
||||
Err(e) => {
|
||||
warn!(%uid, error = %e, "open_revision failed");
|
||||
Err(Errno::EIO)
|
||||
}
|
||||
};
|
||||
{
|
||||
let mut readers = self.readers.lock();
|
||||
// Publish only into the slot we claimed. If it is gone
|
||||
// or belongs to a later attempt, an eviction or a newer
|
||||
// revision overtook us: our reader still answers the
|
||||
// callers waiting on it, but it must not be cached.
|
||||
let ours = matches!(
|
||||
readers.get(uid),
|
||||
Some(ReaderSlot::Pending(p)) if p.id == id
|
||||
);
|
||||
if ours {
|
||||
match &result {
|
||||
Ok(reader) => {
|
||||
readers.insert(
|
||||
uid.clone(),
|
||||
ReaderSlot::Ready(CachedReader {
|
||||
reader: reader.clone(),
|
||||
mtime,
|
||||
size: fsize,
|
||||
last_used: Instant::now(),
|
||||
}),
|
||||
);
|
||||
}
|
||||
// Never cache a failure: the next read retries.
|
||||
Err(_) => {
|
||||
readers.remove(uid);
|
||||
}
|
||||
}
|
||||
}
|
||||
Self::trim_readers(&mut readers);
|
||||
}
|
||||
// After the map is updated, so a racer that wakes and
|
||||
// re-enters finds the finished slot rather than racing us.
|
||||
let _ = tx.send(Some(result.clone()));
|
||||
return result;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Bound the reader map: drop least-recently-used entries until it is back
|
||||
/// at [`MAX_OPEN_READERS`]. Only `Ready` slots are eviction candidates — a
|
||||
/// `Pending` has callers waiting on it and no reader to drop yet.
|
||||
fn trim_readers(readers: &mut HashMap<NodeUid, ReaderSlot>) {
|
||||
while readers.len() > MAX_OPEN_READERS {
|
||||
let victim = readers
|
||||
.iter()
|
||||
.filter_map(|(uid, slot)| match slot {
|
||||
ReaderSlot::Ready(entry) => Some((uid, entry.last_used)),
|
||||
ReaderSlot::Pending(_) => None,
|
||||
})
|
||||
.min_by_key(|(_, last_used)| *last_used)
|
||||
.map(|(uid, _)| uid.clone());
|
||||
let Some(victim) = victim else {
|
||||
break; // every slot is an open in flight; nothing to drop
|
||||
};
|
||||
readers.remove(&victim);
|
||||
}
|
||||
}
|
||||
|
||||
/// Drop any open reader for `uid`, so the next read reopens against the
|
||||
/// current revision. Called wherever cached content is evicted.
|
||||
///
|
||||
/// Drops an in-flight open too: its leader finds the slot gone and declines
|
||||
/// to cache what it opened, which is what we want — the eviction says that
|
||||
/// revision is no longer the truth.
|
||||
pub(super) fn evict_reader(&self, uid: &NodeUid) {
|
||||
self.readers.lock().remove(uid);
|
||||
}
|
||||
|
||||
/// Serve bytes `[offset, offset + len)` of `uid`'s active revision, hitting
|
||||
/// the on-disk caches before the network: a whole-file blob (pinned files)
|
||||
/// first, then the block cache — fetching only the [`BLOCK_SIZE`]-aligned
|
||||
/// blocks that overlap the request and caching each. `mtime`/`fsize` validate
|
||||
/// both caches. Network I/O runs without any lock held.
|
||||
pub(super) fn read_range(
|
||||
&self,
|
||||
uid: &NodeUid,
|
||||
mtime: i64,
|
||||
fsize: u64,
|
||||
offset: u64,
|
||||
len: u64,
|
||||
cache_blocks: bool,
|
||||
) -> Result<Vec<u8>, Errno> {
|
||||
// A queued write has not reached the remote yet, so the remote's current
|
||||
// revision is stale and the staged blob is the truth. Serve from it until
|
||||
// the drain worker lands the upload (offline.md Phase 3).
|
||||
if let Some(pending) = self.pending.lock().get(uid).cloned() {
|
||||
return self.read_pending(&pending, offset, len);
|
||||
}
|
||||
// A node created offline and never written has no blob and no remote: it
|
||||
// is an empty file, and asking the API about a `local~` uid would only
|
||||
// earn a 404 (offline.md Phase 3b).
|
||||
if is_local_uid(uid) {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
self.read_range_remote(uid, mtime, fsize, offset, len, cache_blocks)
|
||||
}
|
||||
|
||||
/// Serve a read from a staged blob, falling back to the remote base for any
|
||||
/// range the write did not author (an incomplete [`StagedWrite`] holds zeros
|
||||
/// there, which must never be handed out as content).
|
||||
fn read_pending(
|
||||
&self,
|
||||
pending: &PendingRevision,
|
||||
offset: u64,
|
||||
len: u64,
|
||||
) -> Result<Vec<u8>, Errno> {
|
||||
let m = &pending.meta;
|
||||
if offset >= m.len || len == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let uid = parse_node_uid(&m.uid).ok_or(Errno::EIO)?;
|
||||
let file = File::open(&pending.path).map_err(|e| {
|
||||
error!(%uid, path = %pending.path.display(), error = %e, "open staged blob failed");
|
||||
Errno::EIO
|
||||
})?;
|
||||
let mut written = Intervals::default();
|
||||
for &(s, e) in &m.authored {
|
||||
written.add(s, e);
|
||||
}
|
||||
// Same merge as `serve_open_read`, but resolving gaps against the remote
|
||||
// rather than through `read_range` — going through `read_range` would find
|
||||
// this very pending op and recurse.
|
||||
let end = offset.saturating_add(len).min(m.len);
|
||||
let mut out = Vec::with_capacity((end - offset) as usize);
|
||||
for (s, e, authored) in written.segments(offset, end) {
|
||||
if authored {
|
||||
let mut buf = vec![0u8; (e - s) as usize];
|
||||
file.read_exact_at(&mut buf, s).map_err(|err| {
|
||||
warn!(%uid, error = %err, "staged blob read failed");
|
||||
Errno::EIO
|
||||
})?;
|
||||
out.extend_from_slice(&buf);
|
||||
continue;
|
||||
}
|
||||
let bend = e.min(m.base_size);
|
||||
if s < bend {
|
||||
out.extend_from_slice(&self.read_range_remote(
|
||||
&uid,
|
||||
m.base_mtime,
|
||||
m.base_size,
|
||||
s,
|
||||
bend - s,
|
||||
true,
|
||||
)?);
|
||||
}
|
||||
// Past the base: a hole the write extended over.
|
||||
out.resize(out.len() + e.saturating_sub(s.max(m.base_size)) as usize, 0);
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Warm the [`STREAM_READAHEAD`] blocks after `last` into the ring, in the
|
||||
/// background, so a player reading forward finds its next block already in
|
||||
/// memory rather than paying a fetch + decrypt round-trip at each boundary.
|
||||
///
|
||||
/// Fire-and-forget: a failure here is not an error, it only means the read
|
||||
/// that needs those bytes will fetch them itself.
|
||||
fn stream_readahead(&self, uid: &NodeUid, mtime: i64, fsize: u64, last: u64) {
|
||||
let last_block = (fsize.saturating_sub(1)) / BLOCK_SIZE;
|
||||
let wanted: Vec<u64> = ((last + 1)..=(last + STREAM_READAHEAD).min(last_block))
|
||||
.filter(|&bidx| {
|
||||
self.stream_ring
|
||||
.lock()
|
||||
.get(uid, mtime, fsize, bidx)
|
||||
.is_none()
|
||||
})
|
||||
.collect();
|
||||
if wanted.is_empty() {
|
||||
return;
|
||||
}
|
||||
let core = self.clone();
|
||||
let uid = uid.clone();
|
||||
self.rt.spawn(async move {
|
||||
let Ok(reader) = core.revision_reader(&uid, mtime, fsize).await else {
|
||||
return;
|
||||
};
|
||||
// Concurrently, for the same reason the demand path fetches its
|
||||
// misses concurrently: serially awaited blocks cost the sum of their
|
||||
// round-trips, and the player catches up with the readahead before it
|
||||
// finishes. The SDK's in-flight block governor bounds the fan-out.
|
||||
let mut set = tokio::task::JoinSet::new();
|
||||
for bidx in wanted {
|
||||
let reader = reader.clone();
|
||||
let bstart = bidx * BLOCK_SIZE;
|
||||
let blen = BLOCK_SIZE.min(fsize - bstart);
|
||||
set.spawn(async move { (bidx, reader.read_at(bstart, blen).await) });
|
||||
}
|
||||
while let Some(joined) = set.join_next().await {
|
||||
let Ok((bidx, read)) = joined else { continue };
|
||||
match read {
|
||||
Ok(bytes) => {
|
||||
core.stream_ring
|
||||
.lock()
|
||||
.insert(&uid, mtime, fsize, bidx, Arc::new(bytes))
|
||||
}
|
||||
Err(e) => debug!(%uid, bidx, error = %e, "stream readahead failed"),
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Read from the content cache, else the remote. The base-content path, with
|
||||
/// no awareness of queued writes — callers wanting the file's *current*
|
||||
/// content want [`Core::read_range`]. Gap-filling a staged blob is the one
|
||||
/// caller that genuinely means "the base", since that is what its zeroed
|
||||
/// ranges have to be filled from.
|
||||
fn read_range_remote(
|
||||
&self,
|
||||
uid: &NodeUid,
|
||||
mtime: i64,
|
||||
fsize: u64,
|
||||
offset: u64,
|
||||
len: u64,
|
||||
cache_blocks: bool,
|
||||
) -> Result<Vec<u8>, Errno> {
|
||||
if let Some(bytes) = self.cache.read_range(uid, mtime, fsize, offset, len) {
|
||||
return Ok(bytes);
|
||||
}
|
||||
if offset >= fsize || len == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let end = offset.saturating_add(len).min(fsize);
|
||||
let mut out = Vec::with_capacity((end - offset) as usize);
|
||||
let first = offset / BLOCK_SIZE;
|
||||
let last = (end - 1) / BLOCK_SIZE;
|
||||
|
||||
// Collect the blocks overlapping the request, serving any already cached
|
||||
// and fetching the rest concurrently. A multi-block read (e.g. a media
|
||||
// player buffering, or a large sequential read split into one FUSE call)
|
||||
// would otherwise stall on each block round-trip in turn; downloading the
|
||||
// misses in parallel saturates the connection and bounds latency at the
|
||||
// slowest single block instead of their sum.
|
||||
let mut blocks: Vec<Option<Arc<Vec<u8>>>> = Vec::with_capacity((last - first + 1) as usize);
|
||||
let mut misses: Vec<u64> = Vec::new();
|
||||
for bidx in first..=last {
|
||||
// A streaming read keeps its blocks only in memory, so the ring is
|
||||
// the only cache it has — check it before the disk (which will not
|
||||
// hold them) and before the network (which would refetch the same
|
||||
// 4 MiB block for every 128 KiB the player consumes).
|
||||
let hit = if cache_blocks {
|
||||
self.cache
|
||||
.cached_block(uid, mtime, fsize, bidx)
|
||||
.map(Arc::new)
|
||||
} else {
|
||||
self.stream_ring.lock().get(uid, mtime, fsize, bidx)
|
||||
};
|
||||
match hit {
|
||||
Some(b) => blocks.push(Some(b)),
|
||||
None => {
|
||||
blocks.push(None);
|
||||
misses.push(bidx);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if !misses.is_empty() {
|
||||
let fetched = self.rt.block_on(async {
|
||||
// Resolve the file's keys and block table once, then read every
|
||||
// missing block through the shared reader. Previously each block
|
||||
// called `download_range`, which redid that resolution per block.
|
||||
let reader = self.revision_reader(uid, mtime, fsize).await?;
|
||||
|
||||
let mut set = tokio::task::JoinSet::new();
|
||||
for &bidx in &misses {
|
||||
let reader = reader.clone();
|
||||
let uid = uid.clone();
|
||||
let bstart = bidx * BLOCK_SIZE;
|
||||
let blen = BLOCK_SIZE.min(fsize - bstart);
|
||||
set.spawn(async move {
|
||||
reader
|
||||
.read_at(bstart, blen)
|
||||
.await
|
||||
.map(|bytes| (bidx, bytes))
|
||||
.map_err(|e| {
|
||||
warn!(%uid, bstart, blen, error = %e, "block read failed");
|
||||
Errno::EIO
|
||||
})
|
||||
});
|
||||
}
|
||||
let mut out = Vec::with_capacity(misses.len());
|
||||
while let Some(joined) = set.join_next().await {
|
||||
// A join error means the task panicked; surface it as EIO.
|
||||
out.push(joined.map_err(|_| Errno::EIO)??);
|
||||
}
|
||||
Ok::<_, Errno>(out)
|
||||
})?;
|
||||
for (bidx, bytes) in fetched {
|
||||
// A streaming read (large unpinned video) skips the on-disk cache
|
||||
// so it can't evict the rest of it; it keeps the block in the
|
||||
// in-memory ring instead, which is bounded and dies with the read.
|
||||
let bytes = Arc::new(bytes);
|
||||
if cache_blocks {
|
||||
let _ = self.cache.store_block(uid, mtime, fsize, bidx, &bytes);
|
||||
} else {
|
||||
self.stream_ring
|
||||
.lock()
|
||||
.insert(uid, mtime, fsize, bidx, bytes.clone());
|
||||
}
|
||||
blocks[(bidx - first) as usize] = Some(bytes);
|
||||
}
|
||||
if !cache_blocks {
|
||||
self.stream_readahead(uid, mtime, fsize, last);
|
||||
}
|
||||
}
|
||||
|
||||
for (i, block) in blocks.into_iter().enumerate() {
|
||||
let bidx = first + i as u64;
|
||||
let bstart = bidx * BLOCK_SIZE;
|
||||
// Every slot is populated: cache hits up front, misses by the fetch above.
|
||||
let block = block.expect("block fetched or cached");
|
||||
let s = (offset.max(bstart) - bstart) as usize;
|
||||
let e = (end.min(bstart + block.len() as u64) - bstart) as usize;
|
||||
if s < e {
|
||||
out.extend_from_slice(&block[s..e]);
|
||||
}
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Serve a read against an open write handle: stitch authored ranges (from
|
||||
/// the scratch file) and untouched ranges (from the remote base via the
|
||||
/// block cache) in order, zero-filling any region past the base.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
pub(super) fn serve_open_read(
|
||||
&self,
|
||||
file: &Arc<File>,
|
||||
len: u64,
|
||||
uid: &NodeUid,
|
||||
base_mtime: i64,
|
||||
base_size: u64,
|
||||
written: &Intervals,
|
||||
offset: u64,
|
||||
size: u64,
|
||||
) -> Result<Vec<u8>, Errno> {
|
||||
if offset >= len || size == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let end = offset.saturating_add(size).min(len);
|
||||
let mut out = Vec::with_capacity((end - offset) as usize);
|
||||
for (s, e, authored) in written.segments(offset, end) {
|
||||
if authored {
|
||||
let mut buf = vec![0u8; (e - s) as usize];
|
||||
file.read_exact_at(&mut buf, s).map_err(|err| {
|
||||
warn!(%uid, error = %err, "scratch read failed");
|
||||
Errno::EIO
|
||||
})?;
|
||||
out.extend_from_slice(&buf);
|
||||
} else {
|
||||
let bend = e.min(base_size);
|
||||
if s < bend {
|
||||
out.extend_from_slice(&self.read_range(
|
||||
uid,
|
||||
base_mtime,
|
||||
base_size,
|
||||
s,
|
||||
bend - s,
|
||||
true,
|
||||
)?);
|
||||
}
|
||||
// Anything past the base is a hole: zero-fill.
|
||||
let zeros = e.saturating_sub(s.max(base_size));
|
||||
out.resize(out.len() + zeros as usize, 0);
|
||||
}
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Fill every unauthored range of a scratch/staged file that overlaps its
|
||||
/// base with the base's bytes, so the file becomes the complete new content.
|
||||
///
|
||||
/// This is the step a partial overwrite cannot skip: only the authored bytes
|
||||
/// were ever written to disk, and a revision upload sends the whole file.
|
||||
/// The gaps come from the *remote base* (through the block cache, so a small
|
||||
/// edit of a large file does not pull all of it), which is exactly why this
|
||||
/// can fail with no network — see `StagedWrite`.
|
||||
pub(super) fn fill_gaps(
|
||||
&self,
|
||||
uid: &NodeUid,
|
||||
file: &File,
|
||||
len: u64,
|
||||
base_mtime: i64,
|
||||
base_size: u64,
|
||||
written: &Intervals,
|
||||
) -> Result<(), Errno> {
|
||||
file.set_len(len).map_err(|e| {
|
||||
error!(%uid, error = %e, "resize scratch file failed");
|
||||
Errno::EIO
|
||||
})?;
|
||||
for (s, e, authored) in written.segments(0, len) {
|
||||
if authored {
|
||||
continue;
|
||||
}
|
||||
let bend = e.min(base_size);
|
||||
if s >= bend {
|
||||
continue; // wholly past the base: already zero-filled on disk
|
||||
}
|
||||
let bytes = self.read_range_remote(uid, base_mtime, base_size, s, bend - s, true)?;
|
||||
file.write_all_at(&bytes, s).map_err(|err| {
|
||||
error!(%uid, error = %err, "scratch gap-fill write failed");
|
||||
Errno::EIO
|
||||
})?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@@ -15,7 +15,34 @@ use pdfs_core::{CoreError, CoreResult};
|
||||
use proton_drive_rs::proton_sdk::ids::NodeUid;
|
||||
use proton_drive_rs::{MemberRole, NodeKind};
|
||||
|
||||
use super::{Core, ROOT_INO, parse_uid, public_link_info, role_from_str, role_to_str};
|
||||
use proton_drive_rs::Node;
|
||||
|
||||
use super::{Core, ROOT_INO, node_size, parse_uid, public_link_info, role_from_str, role_to_str};
|
||||
|
||||
/// A node from a *shared* listing as a [`DirEntry`]. Shared nodes live outside
|
||||
/// the mount, so the entry is uid-addressed: `path` is empty, and the local-state
|
||||
/// flags (`pinned`, `cached`) are false — they describe my own tree, not this one.
|
||||
fn shared_entry(n: Node) -> DirEntry {
|
||||
let is_dir = n.is_folder();
|
||||
let size = match &n.kind {
|
||||
NodeKind::File {
|
||||
claimed_size,
|
||||
total_size_on_storage,
|
||||
..
|
||||
} => claimed_size.unwrap_or(*total_size_on_storage).max(0) as u64,
|
||||
NodeKind::Folder => 0,
|
||||
};
|
||||
DirEntry {
|
||||
name: n.name,
|
||||
is_dir,
|
||||
size,
|
||||
modified: n.modification_time,
|
||||
pinned: false,
|
||||
cached: false,
|
||||
uid: n.uid.to_string(),
|
||||
path: String::new(),
|
||||
}
|
||||
}
|
||||
|
||||
impl Core {
|
||||
// ---- sharing a node ---------------------------------------------------
|
||||
@@ -232,30 +259,62 @@ impl Core {
|
||||
.rt
|
||||
.block_on(self.client.enumerate_nodes(&uids))
|
||||
.map_err(|e| CoreError::from_api(&e, "enumerate nodes"))?;
|
||||
Ok(nodes
|
||||
.into_iter()
|
||||
.map(|n| {
|
||||
let is_dir = n.is_folder();
|
||||
let size = match &n.kind {
|
||||
NodeKind::File {
|
||||
claimed_size,
|
||||
total_size_on_storage,
|
||||
..
|
||||
} => claimed_size.unwrap_or(*total_size_on_storage).max(0) as u64,
|
||||
NodeKind::Folder => 0,
|
||||
};
|
||||
DirEntry {
|
||||
name: n.name,
|
||||
is_dir,
|
||||
size,
|
||||
modified: 0,
|
||||
pinned: false,
|
||||
cached: false,
|
||||
uid: n.uid.to_string(),
|
||||
path: String::new(),
|
||||
}
|
||||
})
|
||||
.collect())
|
||||
Ok(nodes.into_iter().map(shared_entry).collect())
|
||||
}
|
||||
|
||||
/// List the children of a folder shared with me, addressed by uid.
|
||||
///
|
||||
/// A shared subtree has no path in this account's mount — the FUSE tree only
|
||||
/// spans my own volume — so browsing into one is uid-addressed the whole way
|
||||
/// down, each listing handing the front-end the uids it descends with next.
|
||||
pub(crate) fn list_shared_folder(&self, uid: &str) -> CoreResult<Vec<DirEntry>> {
|
||||
let uid =
|
||||
parse_uid(uid).ok_or_else(|| CoreError::invalid(format!("invalid uid: {uid}")))?;
|
||||
let child_uids = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_folder_children_node_uids(&uid))
|
||||
.map_err(|e| CoreError::from_api(&e, "enumerate shared children"))?;
|
||||
if child_uids.is_empty() {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let nodes = self
|
||||
.rt
|
||||
.block_on(self.client.enumerate_nodes(&child_uids))
|
||||
.map_err(|e| CoreError::from_api(&e, "enumerate nodes"))?;
|
||||
Ok(nodes.into_iter().map(shared_entry).collect())
|
||||
}
|
||||
|
||||
/// Download a file shared with me into the content cache, returning its
|
||||
/// on-disk path (served from cache when a fresh blob already exists).
|
||||
///
|
||||
/// The by-uid twin of [`Core::open_file`]: same cache and same tracked
|
||||
/// download, but the node is fetched from the server rather than resolved
|
||||
/// through the inode tree, which does not cover other people's volumes.
|
||||
///
|
||||
/// [`Core::open_file`]: super::Core::open_file
|
||||
pub(crate) fn open_shared_file(&self, uid: &str) -> CoreResult<std::path::PathBuf> {
|
||||
let uid =
|
||||
parse_uid(uid).ok_or_else(|| CoreError::invalid(format!("invalid uid: {uid}")))?;
|
||||
let node = self
|
||||
.rt
|
||||
.block_on(self.client.get_node(&uid))
|
||||
.map_err(|e| CoreError::from_api(&e, "get shared node"))?
|
||||
.ok_or_else(|| CoreError::not_found("shared node not found"))?;
|
||||
if !node.is_file() {
|
||||
return Err(CoreError::invalid("not a regular file"));
|
||||
}
|
||||
let size = node_size(&node);
|
||||
let mtime = node.modification_time;
|
||||
if let Some(p) = self.cache.cached_content_path(&uid, mtime, size) {
|
||||
return Ok(p);
|
||||
}
|
||||
let bytes = self
|
||||
.download_file_tracked(&uid, &node.name, size)
|
||||
.map_err(|e| CoreError::from_api(&e, "download"))?;
|
||||
self.cache
|
||||
.store(&uid, mtime, size, &bytes)
|
||||
.map_err(|e| CoreError::internal(format!("cache store: {e}")))?;
|
||||
Ok(self.cache.content_path(&uid))
|
||||
}
|
||||
|
||||
/// Leave a shared node by its uid.
|
||||
@@ -333,6 +392,19 @@ impl Core {
|
||||
.map_err(|e| CoreError::from_api(&e, "delete bookmark"))
|
||||
}
|
||||
|
||||
// ---- account ----------------------------------------------------------
|
||||
|
||||
/// Total account storage usage `(max_space, used_space)` in bytes, across all
|
||||
/// Proton products (not Drive-only). A remote round-trip; nothing here is
|
||||
/// cached.
|
||||
pub(crate) fn account_quota(&self) -> CoreResult<(i64, i64)> {
|
||||
let q = self
|
||||
.rt
|
||||
.block_on(self.client.quota())
|
||||
.map_err(|e| CoreError::from_api(&e, "account quota"))?;
|
||||
Ok((q.max_space, q.used_space))
|
||||
}
|
||||
|
||||
// ---- shared by me -----------------------------------------------------
|
||||
|
||||
/// List the nodes I have shared with others, each with a summary of its share
|
||||
@@ -394,15 +466,33 @@ impl Core {
|
||||
/// been seen through the mount (e.g. shared but not browsed to this session) —
|
||||
/// the caller then leaves the path empty.
|
||||
pub(crate) fn rel_path_for_uid(&self, uid: &NodeUid) -> Option<String> {
|
||||
let st = self.state.lock();
|
||||
let mut ino = *st.by_uid.get(uid)?;
|
||||
let mut parts = Vec::new();
|
||||
while ino != ROOT_INO {
|
||||
let entry = st.entries.get(&ino)?;
|
||||
parts.push(entry.node.name.clone());
|
||||
ino = entry.parent;
|
||||
}
|
||||
parts.reverse();
|
||||
Some(parts.join("/"))
|
||||
// Searched across every mount: a node browsed through a sync folder is
|
||||
// interned in that fork's inode space, so the primary state alone had no
|
||||
// entry for it and the caller silently showed an empty path
|
||||
// (`docs/BUGS.md` B74). The path is relative to whichever mount holds
|
||||
// it, which is the one the user reached it through.
|
||||
let mut path = None;
|
||||
self.for_each_state(|st| {
|
||||
if path.is_some() {
|
||||
return;
|
||||
}
|
||||
path = walk_to_root(st, uid);
|
||||
});
|
||||
path
|
||||
}
|
||||
}
|
||||
|
||||
/// Walk one inode space from `uid` up to its root, building the path. `None` if
|
||||
/// that mount has never interned the node, or if the chain breaks partway —
|
||||
/// a broken chain is a missing path, never a partial one.
|
||||
fn walk_to_root(st: &super::State, uid: &NodeUid) -> Option<String> {
|
||||
let mut ino = *st.by_uid.get(uid)?;
|
||||
let mut parts = Vec::new();
|
||||
while ino != ROOT_INO {
|
||||
let entry = st.entries.get(&ino)?;
|
||||
parts.push(entry.node.name.clone());
|
||||
ino = entry.parent;
|
||||
}
|
||||
parts.reverse();
|
||||
Some(parts.join("/"))
|
||||
}
|
||||
@@ -18,6 +18,9 @@ pub(crate) struct Entry {
|
||||
pub(crate) uid: NodeUid,
|
||||
pub(crate) parent: u64,
|
||||
pub(crate) node: Node,
|
||||
pub(crate) lookup_count: u64,
|
||||
pub(crate) open_count: u32,
|
||||
pub(crate) unlinked: bool,
|
||||
}
|
||||
|
||||
/// A set of non-overlapping `[start, end)` byte ranges, kept sorted and merged.
|
||||
@@ -103,8 +106,16 @@ pub(crate) struct WriteHandle {
|
||||
pub(crate) base_size: u64,
|
||||
/// Modification time of the remote base at open, validating its block cache.
|
||||
pub(crate) base_mtime: i64,
|
||||
/// Server revision id of the remote base at open, if it had one. This is the
|
||||
/// stable identity the drain conflict-checks against: `base_mtime` alone
|
||||
/// drifts when the server re-stamps the *same* revision, which reads as a
|
||||
/// spurious conflict (see B16/B25). `None` for a file with no sealed remote
|
||||
/// revision, or one read through a surface that does not carry the id.
|
||||
pub(crate) base_revision_id: Option<String>,
|
||||
/// Whether anything diverged from the remote and needs an upload.
|
||||
pub(crate) dirty: bool,
|
||||
/// Number of file handles currently sharing this scratch state.
|
||||
pub(crate) open_count: usize,
|
||||
}
|
||||
|
||||
/// A released write whose upload has not happened yet (offline.md Phase 3).
|
||||
@@ -131,9 +142,11 @@ pub(crate) struct State {
|
||||
/// key means the directory has been enumerated.
|
||||
pub(crate) children: HashMap<u64, Vec<u64>>,
|
||||
pub(crate) next_ino: u64,
|
||||
/// Open write handles keyed by file handle id. Read-only opens use fh 0 and
|
||||
/// Shared write state keyed by inode. Concurrent writers share the scratch file.
|
||||
pub(crate) active_writes: HashMap<u64, WriteHandle>,
|
||||
/// Maps file handle id (fh) to inode (ino). Read-only opens use fh 0 and
|
||||
/// have no entry here.
|
||||
pub(crate) handles: HashMap<u64, WriteHandle>,
|
||||
pub(crate) handles: HashMap<u64, u64>,
|
||||
pub(crate) next_fh: u64,
|
||||
/// Unified SQLite metadata cache. Every map mutation below writes through to
|
||||
/// it inside the `State` lock so the DB stays the authoritative copy across
|
||||
@@ -169,11 +182,26 @@ impl State {
|
||||
uid: node.uid.clone(),
|
||||
parent,
|
||||
node,
|
||||
lookup_count: 1,
|
||||
open_count: 0,
|
||||
unlinked: false,
|
||||
},
|
||||
);
|
||||
ino
|
||||
}
|
||||
|
||||
/// Decrement lookup count for an inode and prune if lookup_count == 0 && open_count == 0 && unlinked.
|
||||
pub(crate) fn forget_lookup(&mut self, ino: u64, nlookup: u64) -> Option<(u64, String)> {
|
||||
if let Some(entry) = self.entries.get_mut(&ino) {
|
||||
entry.lookup_count = entry.lookup_count.saturating_sub(nlookup);
|
||||
if entry.lookup_count == 0 && entry.open_count == 0 && entry.unlinked {
|
||||
let uid = entry.uid.clone();
|
||||
return self.forget(&uid);
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Allocate (or reuse) a stable inode for a node that came *from* the
|
||||
/// database, which is why nothing is written back.
|
||||
pub(crate) fn intern_from_db(&mut self, parent: u64, node: Node) -> u64 {
|
||||
@@ -195,6 +223,59 @@ impl State {
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Check if a directory inode has any child nodes in memory or in the database.
|
||||
pub(crate) fn has_children(&self, parent: u64) -> bool {
|
||||
// A resident listing is authoritative even when empty. Falling through
|
||||
// from `Some([])` to SQLite lets an obsolete child row contradict the
|
||||
// listing `ensure_children` just established, so readdir says empty but
|
||||
// rmdir returns ENOTEMPTY forever.
|
||||
if let Some(kids) = self.children.get(&parent) {
|
||||
return !kids.is_empty();
|
||||
}
|
||||
if let Some(entry) = self.entries.get(&parent)
|
||||
&& let Ok(has_kids) = self.db.has_children(&entry.uid)
|
||||
{
|
||||
return has_kids;
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
/// Check if `ancestor_ino` is `target_ino` or an ancestor of `target_ino` (for rename cycle prevention).
|
||||
pub(crate) fn is_ancestor_of(&self, ancestor_ino: u64, mut target_ino: u64) -> bool {
|
||||
if ancestor_ino == target_ino {
|
||||
return true;
|
||||
}
|
||||
let mut visited = std::collections::HashSet::new();
|
||||
visited.insert(target_ino);
|
||||
while let Some(entry) = self.entries.get(&target_ino) {
|
||||
let parent = entry.parent;
|
||||
if parent == ancestor_ino {
|
||||
return true;
|
||||
}
|
||||
if parent == 0 || !visited.insert(parent) {
|
||||
break;
|
||||
}
|
||||
target_ino = parent;
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
/// Forget a node or, if open handles exist (open_count > 0), mark it unlinked
|
||||
/// and remove it from parent children so lookups fail while open reads succeed.
|
||||
pub(crate) fn forget_or_unlink(&mut self, uid: &NodeUid) -> Option<(u64, String)> {
|
||||
if let Some(&ino) = self.by_uid.get(uid)
|
||||
&& let Some(entry) = self.entries.get_mut(&ino)
|
||||
&& entry.open_count > 0
|
||||
{
|
||||
entry.unlinked = true;
|
||||
if let Some(kids) = self.children.get_mut(&entry.parent) {
|
||||
kids.retain(|&k| k != ino);
|
||||
}
|
||||
return Some((entry.parent, entry.node.name.clone()));
|
||||
}
|
||||
self.forget(uid)
|
||||
}
|
||||
|
||||
/// Forget a node entirely: drop its inode, its uid mapping, its own cached
|
||||
/// listing, its slot in its parent's listing, and its DB row. Returns
|
||||
/// `(parent_ino, name)` when the node was known, so the caller can notify
|
||||
@@ -363,6 +444,8 @@ mod tests {
|
||||
media_type: "text/plain".into(),
|
||||
total_size_on_storage: 0,
|
||||
active_revision_state: None,
|
||||
active_revision_id: None,
|
||||
content_sha1: None,
|
||||
claimed_size: Some(0),
|
||||
claimed_modification_time: None,
|
||||
}
|
||||
@@ -410,6 +493,7 @@ mod tests {
|
||||
by_uid: HashMap::new(),
|
||||
children: HashMap::new(),
|
||||
next_ino: 1,
|
||||
active_writes: HashMap::new(),
|
||||
handles: HashMap::new(),
|
||||
next_fh: 1,
|
||||
db: Arc::new(db),
|
||||
@@ -492,4 +576,52 @@ mod tests {
|
||||
with no way to notice anything else changed"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_is_ancestor_of_hierarchy() {
|
||||
let (mut st, _dir) = state();
|
||||
let root = st.intern(0, node("root_id", "none", "root", true));
|
||||
let p1 = st.intern(root, node("p1_id", "root_id", "p1", true));
|
||||
let p2 = st.intern(p1, node("p2_id", "p1_id", "p2", true));
|
||||
let child = st.intern(p2, node("child_id", "p2_id", "child", true));
|
||||
|
||||
assert!(st.is_ancestor_of(root, root), "self is ancestor");
|
||||
assert!(st.is_ancestor_of(root, p1), "root is ancestor of p1");
|
||||
assert!(
|
||||
st.is_ancestor_of(root, child),
|
||||
"root is ancestor of deep child"
|
||||
);
|
||||
assert!(st.is_ancestor_of(p1, child), "p1 is ancestor of deep child");
|
||||
assert!(
|
||||
!st.is_ancestor_of(child, root),
|
||||
"child is not ancestor of root"
|
||||
);
|
||||
assert!(!st.is_ancestor_of(child, p1), "child is not ancestor of p1");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_state_has_children_mem_and_db() {
|
||||
let (mut st, _dir) = state();
|
||||
let folder = st.intern_mem(0, node("dir_uid", "none", "dir", true));
|
||||
assert!(!st.has_children(folder), "initially empty");
|
||||
|
||||
// Memory-only children (using intern_mem so DB is not populated yet)
|
||||
let f1 = st.intern_mem(folder, node("file1_uid", "dir_uid", "file1.txt", false));
|
||||
st.children.insert(folder, vec![f1]);
|
||||
assert!(st.has_children(folder), "has child in memory");
|
||||
|
||||
st.children.insert(folder, vec![]);
|
||||
assert!(!st.has_children(folder), "cleared memory children");
|
||||
|
||||
// DB children
|
||||
st.db
|
||||
.upsert_node(&node("file2_uid", "dir_uid", "file2.txt", false))
|
||||
.unwrap();
|
||||
assert!(
|
||||
!st.has_children(folder),
|
||||
"a resident empty listing overrides stale DB children"
|
||||
);
|
||||
st.children.remove(&folder);
|
||||
assert!(st.has_children(folder), "has child in db");
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,461 @@
|
||||
//! Background conflict sweep.
|
||||
//!
|
||||
//! A `(sync-conflict <ts>)` copy is only ever a fallback: the drain and the sync
|
||||
//! engine cut one when they cannot prove a queued write is safe to apply, so the
|
||||
//! user never loses bytes. Most of those copies turn out to be byte-identical to
|
||||
//! the live file — a spurious conflict from a re-stamped revision (B16/B25) or a
|
||||
//! first-sync of an already-identical file. This sweep reconciles them after the
|
||||
//! fact:
|
||||
//!
|
||||
//! - **Identical** to the live sibling (same size *and* same content SHA-1): the
|
||||
//! copy is redundant, so it is trashed and logged as a [`ActivityKind::Trash`].
|
||||
//! - **Divergent** (different bytes) or **orphaned** (no live sibling): left in
|
||||
//! place and surfaced once as an [`ActivityKind::Conflict`], because only the
|
||||
//! user can decide which version wins.
|
||||
//!
|
||||
//! Identity is proved without downloading anything: the SHA-1 comes from the
|
||||
//! revision's decrypted extended attributes, which enumeration already reads. A
|
||||
//! copy whose sibling has no recorded SHA-1 is treated as divergent — the sweep
|
||||
//! never removes a file it cannot prove is a duplicate.
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::time::Duration;
|
||||
|
||||
use pdfs_core::config::SweepMode;
|
||||
use pdfs_core::control::ActivityKind;
|
||||
use proton_drive_rs::proton_sdk::ids::NodeUid;
|
||||
use tracing::{debug, info, warn};
|
||||
|
||||
use super::{Core, node_content_sha1, node_revision_id, node_size};
|
||||
|
||||
/// Time between sweeps. Conflicts are rare and non-urgent; a slow cadence keeps
|
||||
/// the sweep off the hot path while still cleaning up within a few minutes.
|
||||
const CONFLICT_SWEEP_INTERVAL: Duration = Duration::from_secs(300);
|
||||
|
||||
/// Delay before the first sweep, so it does not compete with the burst of work a
|
||||
/// fresh mount does at startup (hydrate, recover, initial enumeration).
|
||||
const CONFLICT_SWEEP_WARMUP: Duration = Duration::from_secs(30);
|
||||
|
||||
/// Strip a ` (sync-conflict <stamp>)` (optionally `-<n>`) marker from `name`,
|
||||
/// returning the original file name it was a copy of. `None` when `name` is not a
|
||||
/// conflict copy. Inverse of the `conflict_name` / `conflict_path_with_suffix`
|
||||
/// formats, so the two halves of the product agree on what a conflict is.
|
||||
pub(crate) fn conflict_base_name(name: &str) -> Option<String> {
|
||||
const MARKER: &str = " (sync-conflict ";
|
||||
let start = name.find(MARKER)?;
|
||||
let after = start + MARKER.len();
|
||||
let close_rel = name[after..].find(')')?;
|
||||
let close = after + close_rel;
|
||||
let inner = &name[after..close];
|
||||
// The token is `<digits>` or `<digits>-<digits>`; reject anything else so a
|
||||
// file that merely happens to contain the phrase is not mistaken for a copy.
|
||||
let mut parts = inner.splitn(2, '-');
|
||||
let stamp = parts.next().unwrap_or_default();
|
||||
let suffix = parts.next();
|
||||
let is_digits = |s: &str| !s.is_empty() && s.bytes().all(|b| b.is_ascii_digit());
|
||||
if !is_digits(stamp) || suffix.is_some_and(|s| !is_digits(s)) {
|
||||
return None;
|
||||
}
|
||||
let mut base = String::with_capacity(start + name.len() - close);
|
||||
base.push_str(&name[..start]);
|
||||
base.push_str(&name[close + 1..]);
|
||||
Some(base)
|
||||
}
|
||||
|
||||
impl Core {
|
||||
/// Sweep for stale conflict copies forever, on its own thread. See the module
|
||||
/// docs for the identical/divergent policy.
|
||||
pub(crate) fn run_conflict_sweep_loop(&self) {
|
||||
std::thread::sleep(CONFLICT_SWEEP_WARMUP);
|
||||
loop {
|
||||
self.sweep_conflicts_once();
|
||||
std::thread::sleep(CONFLICT_SWEEP_INTERVAL);
|
||||
}
|
||||
}
|
||||
|
||||
/// One sweep pass over every node the daemon currently knows.
|
||||
fn sweep_conflicts_once(&self) {
|
||||
let stored = match self.db.load_all() {
|
||||
Ok(s) => s,
|
||||
Err(e) => {
|
||||
warn!(error = ?e, "conflict sweep: load nodes failed");
|
||||
return;
|
||||
}
|
||||
};
|
||||
let nodes: Vec<_> = stored.into_iter().map(|s| s.node).collect();
|
||||
|
||||
// Index live (non-trashed) files by (parent, name) for sibling lookup.
|
||||
let mut by_parent_name: HashMap<(String, &str), &_> = HashMap::new();
|
||||
for node in &nodes {
|
||||
if node.trashed || node.is_folder() {
|
||||
continue;
|
||||
}
|
||||
let parent = node
|
||||
.parent_uid
|
||||
.as_ref()
|
||||
.map(|u| u.to_string())
|
||||
.unwrap_or_default();
|
||||
by_parent_name.insert((parent, node.name.as_str()), node);
|
||||
}
|
||||
|
||||
let online = self.online.load(std::sync::atomic::Ordering::Relaxed);
|
||||
for node in &nodes {
|
||||
if node.trashed || node.is_folder() {
|
||||
continue;
|
||||
}
|
||||
let Some(base) = conflict_base_name(&node.name) else {
|
||||
continue;
|
||||
};
|
||||
let parent = node
|
||||
.parent_uid
|
||||
.as_ref()
|
||||
.map(|u| u.to_string())
|
||||
.unwrap_or_default();
|
||||
let sibling = by_parent_name.get(&(parent, base.as_str())).copied();
|
||||
|
||||
match decide(node, sibling, &base, self.sweep_mode) {
|
||||
SweepAction::Remove => {
|
||||
// Only while online — the remote trash is the point. Offline,
|
||||
// it waits for a later pass.
|
||||
if online {
|
||||
self.remove_conflict_copy(node, &base);
|
||||
}
|
||||
}
|
||||
SweepAction::Flag(detail) => self.flag_conflict(&node.uid, &node.name, detail),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Trash a conflict copy proven identical to its live sibling, and unhook it
|
||||
/// locally — the same sequence the interactive unlink path uses after a trash.
|
||||
///
|
||||
/// `snapshot` is the node as the pass saw it, which by now is stale: the pass
|
||||
/// enumerated every node up front and has been doing network I/O since. Before
|
||||
/// touching anything remote this re-reads the node and refuses to act unless
|
||||
/// it is *still* the same revision, still untrashed, still unwritten and still
|
||||
/// unopened. Without that, a user edit landing inside the window is destroyed
|
||||
/// — `discard_queued_ops` below drops the queued write *and its staged blob*,
|
||||
/// which may hold the only copy of those bytes (`docs/BUGS.md` B71).
|
||||
fn remove_conflict_copy(&self, snapshot: &proton_drive_rs::Node, base: &str) {
|
||||
let uid = &snapshot.uid;
|
||||
let name = snapshot.name.as_str();
|
||||
if !self.duplicate_still_removable(snapshot) {
|
||||
return;
|
||||
}
|
||||
match self
|
||||
.rt
|
||||
.block_on(self.client.trash_nodes(std::slice::from_ref(uid)))
|
||||
{
|
||||
Ok(()) => {}
|
||||
Err(e) if super::is_gone(&e) => {}
|
||||
Err(e) => {
|
||||
warn!(%uid, name, error = %e, "conflict sweep: trashing duplicate failed");
|
||||
return;
|
||||
}
|
||||
}
|
||||
// Every mount, not just the primary: a conflict copy inside a sync
|
||||
// folder lives in that fork's inode space, and leaving it hooked up
|
||||
// there keeps a node we have just trashed remotely visible and
|
||||
// readable there (`docs/BUGS.md` B74).
|
||||
self.for_each_state(|st| {
|
||||
st.forget_or_unlink(uid);
|
||||
});
|
||||
self.discard_queued_ops(uid);
|
||||
self.cache.evict(uid);
|
||||
self.evict_reader(uid);
|
||||
if let Err(e) = self.db.delete_node(uid) {
|
||||
warn!(%uid, error = ?e, "conflict sweep: db delete after trash failed");
|
||||
}
|
||||
self.invalidate_trash();
|
||||
self.conflict_notified.lock().remove(uid);
|
||||
self.log_activity(
|
||||
ActivityKind::Trash,
|
||||
name,
|
||||
format!("auto-removed duplicate of {base}"),
|
||||
true,
|
||||
);
|
||||
info!(%uid, name, base, "conflict sweep: removed identical conflict copy");
|
||||
}
|
||||
|
||||
/// Re-check, immediately before the destructive call, everything the pass
|
||||
/// decided from its stale snapshot. Any doubt means "leave it alone": a
|
||||
/// conflict copy that survives to the next pass costs nothing, a wrongly
|
||||
/// removed one costs the user data.
|
||||
fn duplicate_still_removable(&self, snapshot: &proton_drive_rs::Node) -> bool {
|
||||
let uid = &snapshot.uid;
|
||||
let name = snapshot.name.as_str();
|
||||
|
||||
// A queued op means bytes are still owed an upload. `discard_queued_ops`
|
||||
// would throw those away along with the staged blob holding them.
|
||||
match self.db.has_any_op(&uid.to_string()) {
|
||||
Ok(false) => {}
|
||||
Ok(true) => {
|
||||
debug!(%uid, name, "conflict sweep: skipping duplicate with queued ops");
|
||||
return false;
|
||||
}
|
||||
// Cannot prove the queue is empty — assume it is not.
|
||||
Err(e) => {
|
||||
warn!(%uid, name, error = ?e, "conflict sweep: op check failed; skipping");
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Someone is writing to it, or holds it open. Trashing now would pull the
|
||||
// node out from under a live handle.
|
||||
if self.is_busy(uid) {
|
||||
debug!(%uid, name, "conflict sweep: skipping duplicate that is open or being written");
|
||||
return false;
|
||||
}
|
||||
|
||||
// Finally, the node itself must not have moved on since the snapshot.
|
||||
match self.db.node_by_uid(&uid.to_string()) {
|
||||
Ok(Some(fresh)) => {
|
||||
if fresh.trashed {
|
||||
return false;
|
||||
}
|
||||
if fresh.name != snapshot.name || fresh.parent_uid != snapshot.parent_uid {
|
||||
debug!(%uid, name, "conflict sweep: duplicate was renamed or moved; skipping");
|
||||
return false;
|
||||
}
|
||||
if node_revision_id(&fresh) != node_revision_id(snapshot)
|
||||
|| node_size(&fresh) != node_size(snapshot)
|
||||
|| node_content_sha1(&fresh) != node_content_sha1(snapshot)
|
||||
{
|
||||
debug!(%uid, name, "conflict sweep: duplicate changed since the pass began");
|
||||
return false;
|
||||
}
|
||||
true
|
||||
}
|
||||
// Already gone locally, or unreadable — either way, not ours to remove.
|
||||
Ok(None) => false,
|
||||
Err(e) => {
|
||||
warn!(%uid, name, error = ?e, "conflict sweep: re-read failed; skipping");
|
||||
false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether a node has a write in flight or a file handle open against it.
|
||||
/// Read-only opens use fh 0 and are not tracked, so this is specifically the
|
||||
/// writer/holder check.
|
||||
/// Asked across **every** mount. The sweep runs on the primary Core but
|
||||
/// trashes nodes anywhere in the tree, and a file open inside a sync folder
|
||||
/// is tracked in that fork's `State` — so consulting `self.state` alone
|
||||
/// answered "idle" for every such file and let the sweep delete one with a
|
||||
/// writer attached (`docs/BUGS.md` B74). Busy anywhere means busy.
|
||||
fn is_busy(&self, uid: &NodeUid) -> bool {
|
||||
let mut busy = false;
|
||||
self.for_each_state(|st| {
|
||||
let Some(&ino) = st.by_uid.get(uid) else {
|
||||
return;
|
||||
};
|
||||
busy |=
|
||||
st.active_writes.contains_key(&ino) || st.handles.values().any(|&held| held == ino);
|
||||
});
|
||||
busy
|
||||
}
|
||||
|
||||
/// Surface a conflict copy that needs the user's attention, at most once per
|
||||
/// daemon run so the activity feed is not spammed each pass.
|
||||
fn flag_conflict(&self, uid: &NodeUid, name: &str, detail: String) {
|
||||
if !self.conflict_notified.lock().insert(uid.clone()) {
|
||||
return;
|
||||
}
|
||||
debug!(%uid, name, detail, "conflict sweep: flagged divergent conflict copy");
|
||||
self.log_activity(ActivityKind::Conflict, name, detail, false);
|
||||
}
|
||||
}
|
||||
|
||||
/// What the sweep concluded about one `(sync-conflict …)` copy.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
enum SweepAction {
|
||||
/// Provably redundant: trash it, subject to the runtime interlocks in
|
||||
/// [`Core::duplicate_still_removable`].
|
||||
Remove,
|
||||
/// Only the user can resolve this one; surface it with this detail.
|
||||
Flag(String),
|
||||
}
|
||||
|
||||
/// Decide what to do about conflict copy `node` given its live sibling (if any)
|
||||
/// and the configured `mode`.
|
||||
///
|
||||
/// Pure, so the policy that governs deletion is testable without a mount, a
|
||||
/// runtime, or an account — the same split used for `revision_changed` and
|
||||
/// `is_own_self_supersede`. Everything that can fail or race lives in the caller.
|
||||
fn decide(
|
||||
node: &proton_drive_rs::Node,
|
||||
sibling: Option<&proton_drive_rs::Node>,
|
||||
base: &str,
|
||||
mode: SweepMode,
|
||||
) -> SweepAction {
|
||||
match sibling {
|
||||
Some(sib) if is_identical(node, sib) => {
|
||||
if mode.is_enforcing() {
|
||||
SweepAction::Remove
|
||||
} else {
|
||||
// Report-only: say what would happen, remove nothing. The point is
|
||||
// to accumulate field evidence that the identity check is right
|
||||
// before it is trusted with deletion (docs/BUGS.md B71).
|
||||
SweepAction::Flag(format!(
|
||||
"identical to {base}; would be removed (sweep is report-only)"
|
||||
))
|
||||
}
|
||||
}
|
||||
Some(_) => SweepAction::Flag(format!("differs from {base}")),
|
||||
None => SweepAction::Flag(format!("no original {base} to reconcile against")),
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether two file nodes provably hold the same bytes: equal size and equal,
|
||||
/// present content SHA-1. A missing digest on either side is not proof, so the
|
||||
/// sweep treats it as divergent rather than risk removing a real difference.
|
||||
fn is_identical(a: &proton_drive_rs::Node, b: &proton_drive_rs::Node) -> bool {
|
||||
if node_size(a) != node_size(b) {
|
||||
return false;
|
||||
}
|
||||
match (node_content_sha1(a), node_content_sha1(b)) {
|
||||
(Some(x), Some(y)) => x == y,
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use proton_drive_rs::NodeKind;
|
||||
use proton_drive_rs::proton_sdk::ids::{LinkId, VolumeId};
|
||||
|
||||
/// A file node with the two fields the sweep's identity check reads.
|
||||
fn file(name: &str, size: i64, sha1: Option<&str>) -> proton_drive_rs::Node {
|
||||
proton_drive_rs::Node {
|
||||
uid: NodeUid::new(VolumeId::from("v"), LinkId::from(name)),
|
||||
parent_uid: None,
|
||||
kind: NodeKind::File {
|
||||
media_type: "text/plain".into(),
|
||||
total_size_on_storage: size,
|
||||
active_revision_state: None,
|
||||
active_revision_id: Some("rev".into()),
|
||||
claimed_size: Some(size),
|
||||
claimed_modification_time: None,
|
||||
content_sha1: sha1.map(String::from),
|
||||
},
|
||||
name: name.into(),
|
||||
creation_time: 0,
|
||||
modification_time: 0,
|
||||
trashed: false,
|
||||
is_shared: false,
|
||||
is_shared_publicly: false,
|
||||
signature_email: None,
|
||||
verification: Default::default(),
|
||||
}
|
||||
}
|
||||
|
||||
/// The only input shape that may ever produce a removal: same size, same
|
||||
/// present digest, live sibling, enforcing mode.
|
||||
#[test]
|
||||
fn removes_only_a_provably_identical_copy_when_enforcing() {
|
||||
let copy = file("f (sync-conflict 1).txt", 100, Some("aaa"));
|
||||
let live = file("f.txt", 100, Some("aaa"));
|
||||
assert_eq!(
|
||||
decide(©, Some(&live), "f.txt", SweepMode::Enforce),
|
||||
SweepAction::Remove
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn report_only_never_removes_but_still_says_what_it_would_do() {
|
||||
let copy = file("f (sync-conflict 1).txt", 100, Some("aaa"));
|
||||
let live = file("f.txt", 100, Some("aaa"));
|
||||
// Same inputs as the removal case above; only the mode differs.
|
||||
let SweepAction::Flag(detail) = decide(©, Some(&live), "f.txt", SweepMode::Report)
|
||||
else {
|
||||
panic!("report mode must never remove");
|
||||
};
|
||||
assert!(detail.contains("would be removed"), "{detail}");
|
||||
assert!(detail.contains("report-only"), "{detail}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_differing_size_is_a_real_conflict() {
|
||||
let copy = file("f (sync-conflict 1).txt", 101, Some("aaa"));
|
||||
let live = file("f.txt", 100, Some("aaa"));
|
||||
assert_eq!(
|
||||
decide(©, Some(&live), "f.txt", SweepMode::Enforce),
|
||||
SweepAction::Flag("differs from f.txt".into())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_missing_digest_is_never_proof_of_identity() {
|
||||
// Equal sizes are not enough: two different 100-byte files are common.
|
||||
// A copy the sweep cannot fingerprint must survive, in either direction.
|
||||
for (a, b) in [(None, Some("aaa")), (Some("aaa"), None), (None, None)] {
|
||||
let copy = file("f (sync-conflict 1).txt", 100, a);
|
||||
let live = file("f.txt", 100, b);
|
||||
assert_eq!(
|
||||
decide(©, Some(&live), "f.txt", SweepMode::Enforce),
|
||||
SweepAction::Flag("differs from f.txt".into()),
|
||||
"{a:?} vs {b:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_differing_digest_at_equal_size_is_a_real_conflict() {
|
||||
let copy = file("f (sync-conflict 1).txt", 100, Some("aaa"));
|
||||
let live = file("f.txt", 100, Some("bbb"));
|
||||
assert_eq!(
|
||||
decide(©, Some(&live), "f.txt", SweepMode::Enforce),
|
||||
SweepAction::Flag("differs from f.txt".into())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_orphaned_copy_is_surfaced_not_removed() {
|
||||
// No live original left to reconcile against — the copy may be the only
|
||||
// surviving version of the file, so it is never the sweep's to remove.
|
||||
let copy = file("f (sync-conflict 1).txt", 100, Some("aaa"));
|
||||
assert_eq!(
|
||||
decide(©, None, "f.txt", SweepMode::Enforce),
|
||||
SweepAction::Flag("no original f.txt to reconcile against".into())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn identity_needs_both_size_and_digest_to_match() {
|
||||
let a = file("a", 100, Some("aaa"));
|
||||
assert!(is_identical(&a, &file("b", 100, Some("aaa"))));
|
||||
assert!(!is_identical(&a, &file("b", 101, Some("aaa"))));
|
||||
assert!(!is_identical(&a, &file("b", 100, Some("bbb"))));
|
||||
assert!(!is_identical(&a, &file("b", 100, None)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_conflict_names_and_leaves_others_alone() {
|
||||
assert_eq!(
|
||||
conflict_base_name("test_export (sync-conflict 1784898786).xml").as_deref(),
|
||||
Some("test_export.xml")
|
||||
);
|
||||
assert_eq!(
|
||||
conflict_base_name("README (sync-conflict 42)").as_deref(),
|
||||
Some("README")
|
||||
);
|
||||
// The sync engine's de-duplicated suffix form.
|
||||
assert_eq!(
|
||||
conflict_base_name("notes (sync-conflict 1700-3).txt").as_deref(),
|
||||
Some("notes.txt")
|
||||
);
|
||||
// Not a conflict copy.
|
||||
assert_eq!(conflict_base_name("report.xml"), None);
|
||||
// Looks close but the token is not a stamp.
|
||||
assert_eq!(conflict_base_name("x (sync-conflict abc).txt"), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_dotted_stem_keeps_its_inner_dots() {
|
||||
assert_eq!(
|
||||
conflict_base_name("archive.tar (sync-conflict 7).gz").as_deref(),
|
||||
Some("archive.tar.gz")
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,251 @@
|
||||
//! Filesystem watcher, polling, and debounce control plane.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// How long the watcher must go quiet before a burst counts as finished.
|
||||
///
|
||||
/// Measured from the *last* event, not the first: applications do not write a
|
||||
/// file once. An editor saves by writing a temp file and renaming it over the
|
||||
/// target; an export or a database dump writes continuously for as long as it
|
||||
/// takes. Settling a fixed interval after the first event walks the tree while
|
||||
/// the file is still growing, and uploads a torn snapshot as a real revision —
|
||||
/// corrected on the next pass, but only after spending the encrypt-and-upload
|
||||
/// on a file that was never in that state.
|
||||
const DEBOUNCE: Duration = Duration::from_secs(2);
|
||||
/// Ceiling on the settle wait, so a directory under sustained change still
|
||||
/// syncs. Without it, copying a large tree in — events arriving forever —
|
||||
/// would postpone the reconcile for as long as the copy ran.
|
||||
const MAX_SETTLE: Duration = Duration::from_secs(30);
|
||||
/// How often to re-walk remotes so changes made on other clients are pulled in.
|
||||
const POLL_INTERVAL: Duration = Duration::from_secs(120);
|
||||
/// How many uploads/downloads/folder-creations a reconcile runs at once. The
|
||||
/// per-item work is a network round-trip, so a folder with thousands of files is
|
||||
/// unusable done one-at-a-time; this bounds concurrency like the bulk-upload
|
||||
/// engine does.
|
||||
pub(super) const SYNC_CONCURRENCY: usize = 8;
|
||||
|
||||
/// A message to the sync engine's control thread.
|
||||
pub(crate) enum SyncMsg {
|
||||
/// Reconcile one folder by id (a local change, or a targeted `SyncNow`).
|
||||
Reconcile(i64),
|
||||
/// Reconcile every mirror folder (periodic poll, or startup).
|
||||
ReconcileAll,
|
||||
/// Re-read the folder set and adjust the filesystem watches (after add/remove).
|
||||
Rewatch,
|
||||
}
|
||||
|
||||
/// Start the sync engine: a control thread that owns the filesystem watcher and
|
||||
/// serialises reconcile passes, plus a periodic poll thread. The engine receives
|
||||
/// on `rx`; senders live in [`Core::sync_tx`].
|
||||
pub(crate) fn spawn(core: Core, rx: Receiver<SyncMsg>) {
|
||||
if let Err(e) = std::thread::Builder::new()
|
||||
.name("pdfs-sync".into())
|
||||
.spawn(move || engine_loop(core, rx))
|
||||
{
|
||||
warn!(error = %e, "failed to start sync engine");
|
||||
}
|
||||
}
|
||||
|
||||
/// The engine control loop. Single-threaded so reconcile passes never overlap.
|
||||
fn engine_loop(core: Core, rx: Receiver<SyncMsg>) {
|
||||
// Paths the watcher currently covers, mapped to their folder id, so an event
|
||||
// path can be resolved back to the folder it belongs to.
|
||||
let watched: Mutex<Vec<(PathBuf, i64)>> = Mutex::new(Vec::new());
|
||||
|
||||
let tx_events = core.sync_tx.clone();
|
||||
let mut watcher =
|
||||
match notify::recommended_watcher(move |res: notify::Result<notify::Event>| {
|
||||
let Ok(event) = res else { return };
|
||||
// Ignore pure metadata/access noise; content changes are what matter.
|
||||
if matches!(event.kind, notify::EventKind::Access(_)) {
|
||||
return;
|
||||
}
|
||||
let _ = tx_events.send(SyncMsg::ReconcileAll);
|
||||
}) {
|
||||
Ok(w) => w,
|
||||
Err(e) => {
|
||||
warn!(error = %e, "filesystem watcher unavailable; sync is poll-only");
|
||||
// Still run the loop so polling and explicit SyncNow work.
|
||||
poll_only_loop(&core, rx);
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
// Periodic remote poll.
|
||||
{
|
||||
let tx = core.sync_tx.clone();
|
||||
std::thread::Builder::new()
|
||||
.name("pdfs-sync-poll".into())
|
||||
.spawn(move || {
|
||||
loop {
|
||||
std::thread::sleep(POLL_INTERVAL);
|
||||
if tx.send(SyncMsg::ReconcileAll).is_err() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
})
|
||||
.ok();
|
||||
}
|
||||
|
||||
rewatch(&core, &mut watcher, &watched);
|
||||
reconcile_all(&core);
|
||||
|
||||
while let Ok(msg) = rx.recv() {
|
||||
let mut ids: HashSet<i64> = HashSet::new();
|
||||
let mut all = false;
|
||||
let mut do_rewatch = false;
|
||||
classify(msg, &mut ids, &mut all, &mut do_rewatch);
|
||||
settle(&rx, &mut ids, &mut all, &mut do_rewatch);
|
||||
|
||||
if do_rewatch {
|
||||
rewatch(&core, &mut watcher, &watched);
|
||||
}
|
||||
if all {
|
||||
reconcile_all(&core);
|
||||
} else {
|
||||
for id in ids {
|
||||
if let Ok(Some(folder)) = core.db.sync_folder_get(id) {
|
||||
core.reconcile_folder(&folder);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Fallback loop when no filesystem watcher could be created: poll + SyncNow only.
|
||||
fn poll_only_loop(core: &Core, rx: Receiver<SyncMsg>) {
|
||||
{
|
||||
let tx = core.sync_tx.clone();
|
||||
std::thread::spawn(move || {
|
||||
loop {
|
||||
std::thread::sleep(POLL_INTERVAL);
|
||||
if tx.send(SyncMsg::ReconcileAll).is_err() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
reconcile_all(core);
|
||||
while let Ok(msg) = rx.recv() {
|
||||
let mut ids: HashSet<i64> = HashSet::new();
|
||||
let mut all = false;
|
||||
let mut do_rewatch = false;
|
||||
classify(msg, &mut ids, &mut all, &mut do_rewatch);
|
||||
settle(&rx, &mut ids, &mut all, &mut do_rewatch);
|
||||
if all {
|
||||
reconcile_all(core);
|
||||
} else {
|
||||
for id in ids {
|
||||
if let Ok(Some(folder)) = core.db.sync_folder_get(id) {
|
||||
core.reconcile_folder(&folder);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Absorb the rest of an event burst, returning once the watcher has been quiet
|
||||
/// for `quiet` or `cap` has elapsed since the first event — whichever comes
|
||||
/// first. The caller has already classified the event that opened the burst.
|
||||
///
|
||||
/// Split out with its timings as parameters so the settling behaviour can be
|
||||
/// tested in milliseconds rather than in the tens of seconds the real constants
|
||||
/// describe.
|
||||
pub(super) fn settle_with(
|
||||
rx: &Receiver<SyncMsg>,
|
||||
ids: &mut HashSet<i64>,
|
||||
all: &mut bool,
|
||||
do_rewatch: &mut bool,
|
||||
quiet: Duration,
|
||||
cap: Duration,
|
||||
) {
|
||||
let deadline = Instant::now() + cap;
|
||||
loop {
|
||||
let now = Instant::now();
|
||||
if now >= deadline {
|
||||
break;
|
||||
}
|
||||
// Never wait past the cap, however quiet the watcher goes.
|
||||
let wait = quiet.min(deadline - now);
|
||||
match rx.recv_timeout(wait) {
|
||||
// Another event: the burst is still going, so the quiet window
|
||||
// starts again from here.
|
||||
Ok(m) => classify(m, ids, all, do_rewatch),
|
||||
// Quiet for a full window: whatever was being written has stopped.
|
||||
Err(RecvTimeoutError::Timeout) => break,
|
||||
// Every sender is gone; the caller's loop is about to end anyway.
|
||||
Err(RecvTimeoutError::Disconnected) => break,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// [`settle_with`] at the real timings.
|
||||
fn settle(rx: &Receiver<SyncMsg>, ids: &mut HashSet<i64>, all: &mut bool, do_rewatch: &mut bool) {
|
||||
settle_with(rx, ids, all, do_rewatch, DEBOUNCE, MAX_SETTLE);
|
||||
}
|
||||
|
||||
pub(super) fn classify(msg: SyncMsg, ids: &mut HashSet<i64>, all: &mut bool, rewatch: &mut bool) {
|
||||
match msg {
|
||||
SyncMsg::Reconcile(id) => {
|
||||
ids.insert(id);
|
||||
}
|
||||
SyncMsg::ReconcileAll => *all = true,
|
||||
SyncMsg::Rewatch => *rewatch = true,
|
||||
}
|
||||
}
|
||||
|
||||
/// Reconcile every mirror folder in turn.
|
||||
fn reconcile_all(core: &Core) {
|
||||
let folders = match core.db.sync_folder_list() {
|
||||
Ok(f) => f,
|
||||
Err(e) => {
|
||||
warn!(error = ?e, "sync: cannot list folders");
|
||||
return;
|
||||
}
|
||||
};
|
||||
for folder in folders {
|
||||
core.reconcile_folder(&folder);
|
||||
}
|
||||
}
|
||||
|
||||
/// Bring the filesystem watches in line with the current mirror-folder set:
|
||||
/// watch newly-added folders, drop removed ones.
|
||||
fn rewatch(
|
||||
core: &Core,
|
||||
watcher: &mut notify::RecommendedWatcher,
|
||||
watched: &Mutex<Vec<(PathBuf, i64)>>,
|
||||
) {
|
||||
let want: Vec<(PathBuf, i64)> = match core.db.sync_folder_list() {
|
||||
Ok(f) => f
|
||||
.into_iter()
|
||||
.filter(|f| f.mode == "mirror")
|
||||
.map(|f| (PathBuf::from(f.local_path), f.id))
|
||||
.collect(),
|
||||
Err(e) => {
|
||||
warn!(error = ?e, "sync: cannot list folders to watch");
|
||||
return;
|
||||
}
|
||||
};
|
||||
let mut have = watched.lock();
|
||||
// Drop watches no longer wanted.
|
||||
have.retain(|(path, _)| {
|
||||
if want.iter().any(|(p, _)| p == path) {
|
||||
true
|
||||
} else {
|
||||
let _ = watcher.unwatch(path);
|
||||
false
|
||||
}
|
||||
});
|
||||
// Add newly wanted watches.
|
||||
for (path, id) in &want {
|
||||
if have.iter().any(|(p, _)| p == path) {
|
||||
continue;
|
||||
}
|
||||
match watcher.watch(path, RecursiveMode::Recursive) {
|
||||
Ok(()) => have.push((path.clone(), *id)),
|
||||
Err(e) => warn!(path = %path.display(), error = %e, "sync: watch failed"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ---- reconcile ------------------------------------------------------------
|
||||
@@ -0,0 +1,81 @@
|
||||
//! Local open-for-write detection used to defer torn uploads.
|
||||
|
||||
use super::*;
|
||||
|
||||
// ---- open-for-write detection ---------------------------------------------
|
||||
|
||||
/// Scan `/proc/*/fd` once and return the set of **canonical** paths under
|
||||
/// `root` that any process currently holds open for writing (`O_WRONLY` or
|
||||
/// `O_RDWR`). The scan is best-effort: unreadable `/proc/*/fd` directories
|
||||
/// (other users' processes, or kernel threads) are silently skipped.
|
||||
///
|
||||
/// Cost: one `readdir` of `/proc`, then for every process one `readdir` of its
|
||||
/// `/proc/<pid>/fd/`, and one `readlink` + one `open` of `/proc/<pid>/fdinfo/<n>`
|
||||
/// per open fd that resolves under `root`. For a typical desktop with a few
|
||||
/// hundred processes and a handful of files inside the sync root, this
|
||||
/// completes in low single-digit milliseconds.
|
||||
pub(super) fn open_for_write_set(root: &Path) -> HashSet<PathBuf> {
|
||||
let mut result = HashSet::new();
|
||||
let Ok(root_canonical) = std::fs::canonicalize(root) else {
|
||||
return result;
|
||||
};
|
||||
let Ok(proc_entries) = std::fs::read_dir("/proc") else {
|
||||
return result;
|
||||
};
|
||||
for proc_entry in proc_entries.filter_map(|e| e.ok()) {
|
||||
let pid_name = proc_entry.file_name();
|
||||
// Skip non-numeric entries (kernel threads, /proc/self, etc.)
|
||||
if !pid_name
|
||||
.to_str()
|
||||
.is_some_and(|s| s.bytes().all(|b| b.is_ascii_digit()))
|
||||
{
|
||||
continue;
|
||||
}
|
||||
let fd_dir = PathBuf::from("/proc").join(&pid_name).join("fd");
|
||||
let Ok(fds) = std::fs::read_dir(&fd_dir) else {
|
||||
continue;
|
||||
};
|
||||
for fd_entry in fds.filter_map(|e| e.ok()) {
|
||||
// readlink on /proc/<pid>/fd/<n> gives the target path.
|
||||
let link = fd_dir.join(fd_entry.file_name());
|
||||
let Ok(target) = std::fs::read_link(&link) else {
|
||||
continue;
|
||||
};
|
||||
// Quick prefix check before the more expensive fdinfo read.
|
||||
if !target.starts_with(&root_canonical) {
|
||||
continue;
|
||||
}
|
||||
// Read the fd's flags from /proc/<pid>/fdinfo/<n> to determine
|
||||
// the access mode. The first line is "pos:\t<offset>", the second
|
||||
// is "flags:\t<octal>". We only need the low two bits of flags:
|
||||
// 0 = O_RDONLY, 1 = O_WRONLY, 2 = O_RDWR
|
||||
let fdinfo_path = PathBuf::from("/proc")
|
||||
.join(&pid_name)
|
||||
.join("fdinfo")
|
||||
.join(fd_entry.file_name());
|
||||
if let Ok(contents) = std::fs::read_to_string(&fdinfo_path)
|
||||
&& is_write_mode(&contents)
|
||||
{
|
||||
result.insert(target);
|
||||
}
|
||||
}
|
||||
}
|
||||
result
|
||||
}
|
||||
|
||||
/// Parse the `flags:` line out of a `/proc/<pid>/fdinfo/<n>` file and return
|
||||
/// true if the low two bits indicate write access (`O_WRONLY = 1` or
|
||||
/// `O_RDWR = 2`).
|
||||
pub(super) fn is_write_mode(fdinfo: &str) -> bool {
|
||||
for line in fdinfo.lines() {
|
||||
if let Some(rest) = line.strip_prefix("flags:\t") {
|
||||
if let Ok(flags) = u32::from_str_radix(rest.trim_start_matches('0'), 8) {
|
||||
let access = flags & 0o3; // O_ACCMODE
|
||||
return access == 1 || access == 2; // O_WRONLY or O_RDWR
|
||||
}
|
||||
// An empty octal string ("0" stripped to "") means flags == 0 == O_RDONLY.
|
||||
return false;
|
||||
}
|
||||
}
|
||||
false
|
||||
}
|
||||
@@ -0,0 +1,164 @@
|
||||
//! Reconciliation snapshots, queued operations, and pass outcomes.
|
||||
|
||||
use super::*;
|
||||
|
||||
pub(super) struct LocalItem {
|
||||
pub(super) is_dir: bool,
|
||||
pub(super) mtime: i64,
|
||||
pub(super) size: i64,
|
||||
/// True when another process holds this file open for writing (detected via
|
||||
/// `/proc/*/fd`). An open-for-write file is kept in the map — so it is not
|
||||
/// misread as a deletion — but treated as unchanged for upload purposes,
|
||||
/// deferring the upload until the writer closes the file.
|
||||
pub(super) open_for_write: bool,
|
||||
}
|
||||
|
||||
/// One item found while walking a remote tree.
|
||||
pub(super) struct RemoteItem {
|
||||
pub(super) uid: NodeUid,
|
||||
pub(super) is_dir: bool,
|
||||
pub(super) mtime: i64,
|
||||
pub(super) size: i64,
|
||||
}
|
||||
|
||||
/// The result of a reconcile pass: what it moved, how many paths were kept as
|
||||
/// conflict copies, and how many failed to apply (and so still need another
|
||||
/// pass). The counts drive both the folder's state and its activity summary.
|
||||
#[derive(Default)]
|
||||
pub(super) struct Outcome {
|
||||
pub(super) uploaded: usize,
|
||||
pub(super) downloaded: usize,
|
||||
pub(super) created: usize,
|
||||
pub(super) deleted: usize,
|
||||
pub(super) conflicts: usize,
|
||||
pub(super) errors: usize,
|
||||
/// Files skipped because another process held them open for writing.
|
||||
pub(super) deferred: usize,
|
||||
}
|
||||
|
||||
impl Outcome {
|
||||
/// Fold in one applied op.
|
||||
pub(super) fn record(&mut self, applied: &Applied) {
|
||||
match applied {
|
||||
Applied::Dir(..) => self.created += 1,
|
||||
Applied::Uploaded => self.uploaded += 1,
|
||||
Applied::Downloaded => self.downloaded += 1,
|
||||
Applied::Conflict => self.conflicts += 1,
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether the pass moved nothing at all — the common case on a poll of an
|
||||
/// unchanged folder, which should not add a line to the activity feed.
|
||||
pub(super) fn is_empty(&self) -> bool {
|
||||
self.uploaded == 0
|
||||
&& self.downloaded == 0
|
||||
&& self.created == 0
|
||||
&& self.deleted == 0
|
||||
&& self.conflicts == 0
|
||||
&& self.errors == 0
|
||||
&& self.deferred == 0
|
||||
}
|
||||
|
||||
/// A human summary of the pass: "3 uploaded, 1 downloaded, 2 failed".
|
||||
pub(super) fn summary(&self) -> String {
|
||||
let mut parts = Vec::new();
|
||||
for (n, label) in [
|
||||
(self.uploaded, "uploaded"),
|
||||
(self.downloaded, "downloaded"),
|
||||
(self.created, "folder(s) created"),
|
||||
(self.deleted, "deleted"),
|
||||
(self.conflicts, "conflicted"),
|
||||
(self.deferred, "deferred (open for write)"),
|
||||
(self.errors, "failed"),
|
||||
] {
|
||||
if n > 0 {
|
||||
parts.push(format!("{n} {label}"));
|
||||
}
|
||||
}
|
||||
parts.join(", ")
|
||||
}
|
||||
}
|
||||
|
||||
/// A network operation queued during classification and run concurrently in a
|
||||
/// per-depth batch. Parent uids are resolved up front (the parent folder is one
|
||||
/// depth shallower and already created), so tasks share nothing mutable.
|
||||
pub(super) enum Pending {
|
||||
/// Create a new remote folder under `parent`.
|
||||
CreateDir { rel: String, parent: NodeUid },
|
||||
/// Upload a brand-new local file into `parent`.
|
||||
UploadNew { rel: String, parent: NodeUid },
|
||||
/// Upload a changed local file as a new revision of `uid`.
|
||||
UploadRevision { rel: String, uid: NodeUid },
|
||||
/// Download remote `uid` to the local path, stamping `mtime`. `size` is the
|
||||
/// remote's reported size, used as the transfer's expected total.
|
||||
Download {
|
||||
rel: String,
|
||||
uid: NodeUid,
|
||||
mtime: i64,
|
||||
size: i64,
|
||||
},
|
||||
/// Both sides changed: set the local copy aside, then download remote `uid`.
|
||||
Conflict {
|
||||
rel: String,
|
||||
uid: NodeUid,
|
||||
mtime: i64,
|
||||
size: i64,
|
||||
},
|
||||
/// Both sides changed during a [`push pass`](Core::push_pass): upload the local
|
||||
/// copy into `parent` under a conflict name, leaving the remote file as it is.
|
||||
PushConflict { rel: String, parent: NodeUid },
|
||||
}
|
||||
|
||||
impl Pending {
|
||||
/// The path this op acts on, relative to the folder root.
|
||||
pub(super) fn rel(&self) -> &str {
|
||||
match self {
|
||||
Pending::CreateDir { rel, .. }
|
||||
| Pending::UploadNew { rel, .. }
|
||||
| Pending::UploadRevision { rel, .. }
|
||||
| Pending::Download { rel, .. }
|
||||
| Pending::Conflict { rel, .. }
|
||||
| Pending::PushConflict { rel, .. } => rel,
|
||||
}
|
||||
}
|
||||
|
||||
/// How this op reads in the activity feed.
|
||||
pub(super) fn kind(&self) -> ActivityKind {
|
||||
match self {
|
||||
Pending::CreateDir { .. } => ActivityKind::CreateFolder,
|
||||
Pending::UploadNew { .. }
|
||||
| Pending::UploadRevision { .. }
|
||||
| Pending::PushConflict { .. } => ActivityKind::Upload,
|
||||
Pending::Download { .. } | Pending::Conflict { .. } => ActivityKind::Download,
|
||||
}
|
||||
}
|
||||
|
||||
/// The activity line's detail, which distinguishes ops that share a kind.
|
||||
pub(super) fn detail(&self) -> &'static str {
|
||||
match self {
|
||||
Pending::CreateDir { .. } => "on Drive",
|
||||
Pending::UploadNew { .. } => "new file",
|
||||
Pending::UploadRevision { .. } => "new version",
|
||||
Pending::Download { .. } => "from Drive",
|
||||
Pending::Conflict { .. } => "local changes kept as a conflict copy",
|
||||
Pending::PushConflict { .. } => "local changes uploaded as a conflict copy",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Why a full reconcile pass stopped without a result.
|
||||
pub(super) enum PassAbort {
|
||||
/// An on-demand switch was queued while the pass was running. Everything left
|
||||
/// to do is work on a local copy about to be evicted, so the pass gives up its
|
||||
/// remaining work to a [`push pass`](Core::push_pass) instead. Not a failure —
|
||||
/// nothing is left half-applied, because each step is applied whole.
|
||||
Interrupted,
|
||||
/// The pass could not establish its diff (a walk or the baseline load failed).
|
||||
Failed(String),
|
||||
}
|
||||
|
||||
impl From<String> for PassAbort {
|
||||
fn from(e: String) -> Self {
|
||||
PassAbort::Failed(e)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,402 @@
|
||||
//! Pure reconciliation ordering, safety guards, signatures, and path rules.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// The paths a reconcile pass will classify: the union of the local, remote,
|
||||
/// and baseline states, minus anything the ignore rules exclude, shallowest
|
||||
/// first so a parent folder is created before its children are placed in it.
|
||||
///
|
||||
/// The ignore filter belongs *here*, on the union, rather than on the local walk
|
||||
/// alone — filtering the walk alone would be actively destructive. A file synced
|
||||
/// before it became ignored is absent from `local` but present in `remote` and
|
||||
/// `baseline`, which is precisely the "local deleted, remote untouched" shape
|
||||
/// `do_reconcile` responds to by trashing the remote copy. Adding a line to
|
||||
/// `.pdfsignore` must never delete anything from Drive.
|
||||
///
|
||||
/// Ignored baseline rows are deliberately left in the database rather than
|
||||
/// removed: with the row intact, un-ignoring the path later re-adopts the
|
||||
/// existing remote file instead of reading as a brand-new local one.
|
||||
pub(super) fn classification_order<L, R, B>(
|
||||
local: &HashMap<String, L>,
|
||||
remote: &HashMap<String, R>,
|
||||
baseline: &HashMap<String, B>,
|
||||
rules: &IgnoreRules,
|
||||
) -> Vec<String>
|
||||
where
|
||||
L: HasKind,
|
||||
R: HasKind,
|
||||
{
|
||||
let mut paths: HashSet<String> = HashSet::new();
|
||||
paths.extend(local.keys().cloned());
|
||||
paths.extend(remote.keys().cloned());
|
||||
paths.extend(baseline.keys().cloned());
|
||||
let mut order: Vec<String> = paths.into_iter().collect();
|
||||
if !rules.is_empty() {
|
||||
order.retain(|rel| {
|
||||
// A baseline-only path has no kind recorded, so it is tested as
|
||||
// both; see `filter_baseline` for why erring towards "ignored" is
|
||||
// the safe direction here.
|
||||
let kind = local
|
||||
.get(rel)
|
||||
.map(HasKind::is_dir)
|
||||
.or_else(|| remote.get(rel).map(HasKind::is_dir));
|
||||
match kind {
|
||||
Some(is_dir) => !rules.is_ignored(rel, is_dir),
|
||||
None => !rules.is_ignored(rel, false) && !rules.is_ignored(rel, true),
|
||||
}
|
||||
});
|
||||
}
|
||||
order.sort_by_key(|p| p.matches('/').count());
|
||||
order
|
||||
}
|
||||
|
||||
/// Lets [`classification_order`] ask either walk's item whether it is a
|
||||
/// directory without knowing which walk it came from.
|
||||
pub(super) trait HasKind {
|
||||
fn is_dir(&self) -> bool;
|
||||
}
|
||||
|
||||
impl HasKind for LocalItem {
|
||||
fn is_dir(&self) -> bool {
|
||||
self.is_dir
|
||||
}
|
||||
}
|
||||
|
||||
impl HasKind for RemoteItem {
|
||||
fn is_dir(&self) -> bool {
|
||||
self.is_dir
|
||||
}
|
||||
}
|
||||
|
||||
/// The baseline minus its ignored paths, for [`guard_local_wipe`].
|
||||
///
|
||||
/// The guard asks "did every synced path vanish locally?", and an ignored path
|
||||
/// is absent from the local walk by rule rather than by loss. Left in, a rule
|
||||
/// covering the whole tree would trip the guard on every pass and wedge that
|
||||
/// folder's sync for good.
|
||||
///
|
||||
/// A baseline row does not record whether it was a file or a folder, so a path
|
||||
/// counts as ignored if it matches as either. Erring towards "ignored" only ever
|
||||
/// shrinks the set the guard checks, which weakens a safety net rather than
|
||||
/// causing a deletion — the wrong direction to be wrong in is the other one.
|
||||
pub(super) fn filter_baseline<'a, B>(
|
||||
baseline: &'a HashMap<String, B>,
|
||||
rules: &IgnoreRules,
|
||||
) -> HashMap<String, &'a B> {
|
||||
baseline
|
||||
.iter()
|
||||
.filter(|(rel, _)| !rules.is_ignored(rel, false) && !rules.is_ignored(rel, true))
|
||||
.map(|(rel, entry)| (rel.clone(), entry))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Refuse to run a pass whose local side has vanished in its entirety.
|
||||
///
|
||||
/// When every baseline path is absent locally, the likely cause is an unavailable
|
||||
/// mount or unreadable folder rather than a deliberate whole-tree deletion.
|
||||
/// One surviving path is enough to clear the guard.
|
||||
pub(super) fn guard_local_wipe<B, L>(
|
||||
baseline: &HashMap<String, B>,
|
||||
local: &HashMap<String, L>,
|
||||
) -> Result<(), String> {
|
||||
if !baseline.is_empty() && baseline.keys().all(|rel| !local.contains_key(rel)) {
|
||||
return Err(format!(
|
||||
"every one of the {} synced paths is missing locally; refusing to trash \
|
||||
them on Drive. Check that the folder is mounted and readable.",
|
||||
baseline.len()
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// The size the baseline recorded for `rel`, if its remote signature's mtime
|
||||
/// still matches `mtime`.
|
||||
pub(super) fn unchanged_remote_size(
|
||||
baseline: &HashMap<String, StoredSyncEntry>,
|
||||
rel: &str,
|
||||
mtime: i64,
|
||||
) -> Option<i64> {
|
||||
match baseline.get(rel).and_then(remote_sig) {
|
||||
Some((recorded, size)) if recorded == mtime => Some(size),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Join a child `name` onto a walk's `prefix`, giving a rel path.
|
||||
pub(super) fn join_rel(prefix: &str, name: &str) -> String {
|
||||
if prefix.is_empty() {
|
||||
name.to_string()
|
||||
} else {
|
||||
format!("{prefix}/{name}")
|
||||
}
|
||||
}
|
||||
|
||||
/// The stored remote signature of a baseline row, if it has one.
|
||||
pub(super) fn remote_sig(e: &StoredSyncEntry) -> Option<(i64, i64)> {
|
||||
match (&e.remote_rev, &e.remote_hash) {
|
||||
(Some(m), Some(s)) => Some((m.parse().ok()?, s.parse().ok()?)),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// The parent of a `/`-joined relative path (`""` for a top-level entry).
|
||||
pub(super) fn parent_rel(rel: &str) -> &str {
|
||||
match rel.rfind('/') {
|
||||
Some(i) => &rel[..i],
|
||||
None => "",
|
||||
}
|
||||
}
|
||||
|
||||
/// The final component of a `/`-joined relative path.
|
||||
pub(crate) fn base_name(rel: &str) -> &str {
|
||||
match rel.rfind('/') {
|
||||
Some(i) => &rel[i + 1..],
|
||||
None => rel,
|
||||
}
|
||||
}
|
||||
|
||||
/// Turn a `/`-joined relative path into an OS path (`/` is already the separator
|
||||
/// on Linux, this keeps the intent explicit).
|
||||
pub(super) fn rel_to_path(rel: &str) -> PathBuf {
|
||||
rel.split('/').collect()
|
||||
}
|
||||
|
||||
/// The name for a conflict copy of `path`, e.g. `notes (sync-conflict 1700000000).txt`.
|
||||
#[cfg(test)]
|
||||
pub(super) fn conflict_path(path: &Path, stamp: i64) -> PathBuf {
|
||||
conflict_path_with_suffix(path, stamp, 0)
|
||||
}
|
||||
|
||||
/// As [`conflict_path`], with a deterministic suffix used when that name already
|
||||
/// exists. This keeps conflict preservation from ever replacing an older copy.
|
||||
pub(super) fn conflict_path_with_suffix(path: &Path, stamp: i64, suffix: u32) -> PathBuf {
|
||||
let stem = path.file_stem().and_then(|s| s.to_str()).unwrap_or("file");
|
||||
let ext = path.extension().and_then(|s| s.to_str());
|
||||
let suffix = if suffix == 0 {
|
||||
String::new()
|
||||
} else {
|
||||
format!("-{suffix}")
|
||||
};
|
||||
let name = match ext {
|
||||
Some(ext) => format!("{stem} (sync-conflict {stamp}{suffix}).{ext}"),
|
||||
None => format!("{stem} (sync-conflict {stamp}{suffix})"),
|
||||
};
|
||||
match path.parent() {
|
||||
Some(dir) => dir.join(name),
|
||||
None => PathBuf::from(name),
|
||||
}
|
||||
}
|
||||
|
||||
/// A pure decision for one file-shaped path. Transfer identities and filesystem
|
||||
/// effects are attached by the executor after this classification.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub(super) enum FilePlan {
|
||||
Unchanged,
|
||||
Deferred,
|
||||
UploadNew,
|
||||
UploadRevision,
|
||||
Download,
|
||||
Conflict,
|
||||
DeleteLocal,
|
||||
DeleteRemote,
|
||||
ForgetBaseline,
|
||||
/// First sync of a file that already exists on both sides with identical
|
||||
/// content: record the baseline without transferring anything. Without this,
|
||||
/// a folder synced for the first time cuts a `(sync-conflict)` copy of every
|
||||
/// pre-existing file, because a missing baseline makes both sides read as
|
||||
/// "changed" (see the mass first-sync conflict storm in docs/BUGS.md).
|
||||
AdoptBaseline,
|
||||
}
|
||||
|
||||
pub(super) fn plan_file(
|
||||
local: Option<&LocalItem>,
|
||||
remote: Option<&RemoteItem>,
|
||||
baseline: Option<&StoredSyncEntry>,
|
||||
) -> FilePlan {
|
||||
if local.is_some_and(|item| item.open_for_write) {
|
||||
return FilePlan::Deferred;
|
||||
}
|
||||
|
||||
let local_changed = local.is_some_and(|item| {
|
||||
baseline.is_none_or(|base| base.local_mtime != item.mtime || base.local_size != item.size)
|
||||
});
|
||||
let remote_changed = remote.is_some_and(|item| {
|
||||
baseline.is_none_or(|base| remote_sig(base) != Some((item.mtime, item.size)))
|
||||
});
|
||||
|
||||
match (local, remote) {
|
||||
(Some(l), Some(r)) => match (local_changed, remote_changed) {
|
||||
(false, false) => FilePlan::Unchanged,
|
||||
(true, false) => FilePlan::UploadRevision,
|
||||
(false, true) => FilePlan::Download,
|
||||
// With a baseline, both-changed is a genuine concurrent edit and must
|
||||
// be preserved as a conflict. Without one, "both changed" only means
|
||||
// this is the first sync and there was nothing to compare to: adopt
|
||||
// the baseline when the sizes already match rather than conflict-copy
|
||||
// an already-identical file. Divergent sizes stay a real conflict.
|
||||
(true, true) if baseline.is_none() && l.size == r.size => FilePlan::AdoptBaseline,
|
||||
(true, true) => FilePlan::Conflict,
|
||||
},
|
||||
(Some(_), None) if baseline.is_none() || local_changed => FilePlan::UploadNew,
|
||||
(Some(_), None) => FilePlan::DeleteLocal,
|
||||
(None, Some(_)) if baseline.is_none() || remote_changed => FilePlan::Download,
|
||||
(None, Some(_)) => FilePlan::DeleteRemote,
|
||||
(None, None) => FilePlan::ForgetBaseline,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod file_plan_tests {
|
||||
use super::*;
|
||||
use proton_drive_rs::proton_sdk::ids::{LinkId, VolumeId};
|
||||
|
||||
fn local(mtime: i64, size: i64) -> LocalItem {
|
||||
LocalItem {
|
||||
is_dir: false,
|
||||
mtime,
|
||||
size,
|
||||
open_for_write: false,
|
||||
}
|
||||
}
|
||||
|
||||
fn remote(mtime: i64, size: i64) -> RemoteItem {
|
||||
RemoteItem {
|
||||
uid: NodeUid::new(VolumeId::from("v"), LinkId::from("l")),
|
||||
is_dir: false,
|
||||
mtime,
|
||||
size,
|
||||
}
|
||||
}
|
||||
|
||||
fn baseline(
|
||||
local_mtime: i64,
|
||||
local_size: i64,
|
||||
remote_mtime: i64,
|
||||
remote_size: i64,
|
||||
) -> StoredSyncEntry {
|
||||
StoredSyncEntry {
|
||||
rel_path: "file".into(),
|
||||
remote_uid: Some("v~l".into()),
|
||||
local_mtime,
|
||||
local_size,
|
||||
remote_rev: Some(remote_mtime.to_string()),
|
||||
remote_hash: Some(remote_size.to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn file_plan_covers_every_presence_and_change_shape() {
|
||||
let same_local = local(10, 20);
|
||||
let changed_local = local(11, 20);
|
||||
let same_remote = remote(30, 40);
|
||||
let changed_remote = remote(31, 40);
|
||||
let base = baseline(10, 20, 30, 40);
|
||||
let cases = [
|
||||
(None, None, None, FilePlan::ForgetBaseline),
|
||||
(None, None, Some(&base), FilePlan::ForgetBaseline),
|
||||
(Some(&same_local), None, None, FilePlan::UploadNew),
|
||||
(Some(&same_local), None, Some(&base), FilePlan::DeleteLocal),
|
||||
(Some(&changed_local), None, Some(&base), FilePlan::UploadNew),
|
||||
(None, Some(&same_remote), None, FilePlan::Download),
|
||||
(
|
||||
None,
|
||||
Some(&same_remote),
|
||||
Some(&base),
|
||||
FilePlan::DeleteRemote,
|
||||
),
|
||||
(None, Some(&changed_remote), Some(&base), FilePlan::Download),
|
||||
(
|
||||
Some(&same_local),
|
||||
Some(&same_remote),
|
||||
None,
|
||||
FilePlan::Conflict,
|
||||
),
|
||||
(
|
||||
Some(&same_local),
|
||||
Some(&same_remote),
|
||||
Some(&base),
|
||||
FilePlan::Unchanged,
|
||||
),
|
||||
(
|
||||
Some(&changed_local),
|
||||
Some(&same_remote),
|
||||
Some(&base),
|
||||
FilePlan::UploadRevision,
|
||||
),
|
||||
(
|
||||
Some(&same_local),
|
||||
Some(&changed_remote),
|
||||
Some(&base),
|
||||
FilePlan::Download,
|
||||
),
|
||||
(
|
||||
Some(&changed_local),
|
||||
Some(&changed_remote),
|
||||
Some(&base),
|
||||
FilePlan::Conflict,
|
||||
),
|
||||
];
|
||||
|
||||
for (local, remote, baseline, expected) in cases {
|
||||
assert_eq!(plan_file(local, remote, baseline), expected);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_open_writer_overrides_every_other_file_decision() {
|
||||
let mut local = local(11, 20);
|
||||
local.open_for_write = true;
|
||||
let remote = remote(31, 40);
|
||||
let base = baseline(10, 20, 30, 40);
|
||||
|
||||
for (remote, baseline) in [
|
||||
(None, None),
|
||||
(None, Some(&base)),
|
||||
(Some(&remote), None),
|
||||
(Some(&remote), Some(&base)),
|
||||
] {
|
||||
assert_eq!(
|
||||
plan_file(Some(&local), remote, baseline),
|
||||
FilePlan::Deferred
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn first_sync_of_an_identical_file_adopts_the_baseline_not_a_conflict() {
|
||||
// No baseline yet (first sync). Same size on both sides is a pre-existing
|
||||
// identical file, not a concurrent edit: adopt it rather than cut a
|
||||
// conflict copy of every file in the folder.
|
||||
let local = local(10, 40);
|
||||
let remote = remote(30, 40);
|
||||
assert_eq!(
|
||||
plan_file(Some(&local), Some(&remote), None),
|
||||
FilePlan::AdoptBaseline
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn first_sync_of_differing_sizes_is_still_a_conflict() {
|
||||
// No baseline and the sizes disagree: a genuine both-sides divergence,
|
||||
// preserved non-destructively as a conflict.
|
||||
let local = local(10, 20);
|
||||
let remote = remote(30, 40);
|
||||
assert_eq!(
|
||||
plan_file(Some(&local), Some(&remote), None),
|
||||
FilePlan::Conflict
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_missing_remote_signature_is_treated_as_changed() {
|
||||
let local = local(10, 20);
|
||||
let remote = remote(30, 40);
|
||||
let mut base = baseline(10, 20, 30, 40);
|
||||
base.remote_hash = None;
|
||||
|
||||
assert_eq!(
|
||||
plan_file(Some(&local), Some(&remote), Some(&base)),
|
||||
FilePlan::Download
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,298 @@
|
||||
//! Bulk local-to-Drive upload workflow.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// How many files the bulk uploader ships at once. Overlaps the per-file network
|
||||
/// round-trips without letting an unbounded number of block buffers pile up.
|
||||
const UPLOAD_CONCURRENCY: usize = 4;
|
||||
|
||||
/// One file queued for bulk upload, resolved during the directory walk so the
|
||||
/// concurrent phase carries everything it needs (no shared state, no `block_on`).
|
||||
struct UploadTask {
|
||||
/// Inode of the (already-created) remote parent folder, for interning the
|
||||
/// uploaded node afterwards.
|
||||
parent_ino: u64,
|
||||
parent_uid: NodeUid,
|
||||
name: String,
|
||||
/// Local filesystem path to stream from.
|
||||
path: PathBuf,
|
||||
size: u64,
|
||||
}
|
||||
|
||||
/// Tally of a completed [`Core::upload_paths`] batch, for the daemon log.
|
||||
#[derive(Default)]
|
||||
pub(super) struct UploadStats {
|
||||
pub(super) uploaded: usize,
|
||||
pub(super) failed: usize,
|
||||
/// Total plaintext bytes of the files that uploaded successfully.
|
||||
pub(super) bytes: u64,
|
||||
/// Folders created (or reused) to mirror the local tree.
|
||||
pub(super) folders: usize,
|
||||
}
|
||||
|
||||
/// Upload every [`UploadTask`] with at most `limit` in flight at once, each
|
||||
/// streamed straight from disk and ticking its own transfer-registry guard.
|
||||
/// Returns, per file, either `(parent_ino, new_uid)` for the caller to intern or
|
||||
/// `(name, error)` to log — one failure never sinks the batch.
|
||||
///
|
||||
/// `job` counts files finished (either way: a failure is still one file the batch
|
||||
/// no longer waits on), so a front-end can show "12 of 40" over the per-file bars.
|
||||
async fn run_uploads(
|
||||
core: Core,
|
||||
tasks: Vec<UploadTask>,
|
||||
limit: usize,
|
||||
job: Arc<JobGuard>,
|
||||
) -> Vec<Result<(u64, NodeUid, u64), (String, String)>> {
|
||||
let sem = Arc::new(tokio::sync::Semaphore::new(limit));
|
||||
let mut set = tokio::task::JoinSet::new();
|
||||
for t in tasks {
|
||||
let core = core.clone();
|
||||
let sem = sem.clone();
|
||||
set.spawn(async move {
|
||||
let _permit = sem.acquire_owned().await.expect("semaphore not closed");
|
||||
let file = match std::fs::File::open(&t.path) {
|
||||
Ok(f) => f,
|
||||
Err(e) => return Err((t.name, format!("open {}: {e}", t.path.display()))),
|
||||
};
|
||||
let mtime = std::fs::metadata(&t.path)
|
||||
.and_then(|m| m.modified())
|
||||
.ok()
|
||||
.and_then(|mt| mt.duration_since(std::time::UNIX_EPOCH).ok())
|
||||
.map(|d| d.as_secs() as i64);
|
||||
let guard = core
|
||||
.transfers
|
||||
.begin(&t.name, "", TransferDirection::Upload, t.size);
|
||||
let reader = OwnedCountingReader::new(file, guard);
|
||||
match core
|
||||
.client
|
||||
.upload_file_from(
|
||||
&t.parent_uid,
|
||||
&t.name,
|
||||
media_type_for(&t.name),
|
||||
reader,
|
||||
t.size as i64,
|
||||
Vec::new(),
|
||||
mtime,
|
||||
false,
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(uid) => Ok((t.parent_ino, uid, t.size)),
|
||||
Err(e) => Err((t.name, format!("upload: {e}"))),
|
||||
}
|
||||
});
|
||||
}
|
||||
let mut out = Vec::new();
|
||||
while let Some(joined) = set.join_next().await {
|
||||
job.step();
|
||||
match joined {
|
||||
Ok(result) => out.push(result),
|
||||
Err(e) => warn!(error = %e, "upload task panicked"),
|
||||
}
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
impl Core {
|
||||
/// Bulk-upload local files and directory trees under `sources` into the
|
||||
/// mountpoint-relative `parent_rel` folder. Directories are recreated (or
|
||||
/// merged into an existing same-named folder) and walked; the resulting flat
|
||||
/// set of files is uploaded with bounded concurrency, each ticking the
|
||||
/// transfer registry so a front-end sees live progress. Runs on a background
|
||||
/// thread — a large tree far outlasts the control socket's read timeout — so
|
||||
/// it reports only a summary for the log. Individual failures are counted and
|
||||
/// logged rather than aborting the whole batch.
|
||||
pub(super) fn upload_paths(
|
||||
&self,
|
||||
parent_rel: &Path,
|
||||
sources: &[PathBuf],
|
||||
) -> CoreResult<UploadStats> {
|
||||
let (pino, parent_uid) = self.resolve(parent_rel)?;
|
||||
self.ensure_children(pino)
|
||||
.map_err(|e| self.errno_error(e, "enumerate"))?;
|
||||
|
||||
// Phase 1 (sequential): build the remote folder skeleton and collect the
|
||||
// flat list of files to upload. Folders must exist before their children,
|
||||
// so this can't be parallelised. On a deep tree this is a folder-creation
|
||||
// round-trip per directory before a single byte moves — long enough that
|
||||
// it needs a job of its own, or the daemon looks idle for minutes.
|
||||
let mut tasks = Vec::new();
|
||||
let mut folders = 0usize;
|
||||
{
|
||||
let job = self.transfers.begin_job("Preparing upload");
|
||||
for src in sources {
|
||||
if let Err(e) =
|
||||
self.collect_uploads(pino, &parent_uid, src, &mut tasks, &mut folders, &job)
|
||||
{
|
||||
warn!(source = %src.display(), error = %e, "skipping source");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Phase 2 (concurrent): upload the files, up to UPLOAD_CONCURRENCY at once.
|
||||
// Each file reports its own bytes; this job is the batch's "N of M files",
|
||||
// which is the number a user actually waits on.
|
||||
let job = Arc::new(self.transfers.begin_job(match tasks.len() {
|
||||
1 => "Uploading 1 file".to_string(),
|
||||
n => format!("Uploading {n} files"),
|
||||
}));
|
||||
job.set_total(tasks.len() as u64);
|
||||
let outcomes = self.rt.block_on(run_uploads(
|
||||
self.clone(),
|
||||
tasks,
|
||||
UPLOAD_CONCURRENCY,
|
||||
job.clone(),
|
||||
));
|
||||
drop(job);
|
||||
|
||||
// Phase 3 (sequential): intern each uploaded node so it shows up in the
|
||||
// listing without a re-enumeration. fetch_node uses `block_on`, so it must
|
||||
// run here rather than inside the async batch — and it is a round-trip per
|
||||
// file, so it too gets a job rather than a silent tail.
|
||||
let mut stats = UploadStats {
|
||||
folders,
|
||||
..UploadStats::default()
|
||||
};
|
||||
let job = self.transfers.begin_job("Finishing upload");
|
||||
job.set_total(outcomes.len() as u64);
|
||||
for outcome in outcomes {
|
||||
job.step();
|
||||
match outcome {
|
||||
Ok((parent_ino, uid, size)) => {
|
||||
stats.uploaded += 1;
|
||||
stats.bytes += size;
|
||||
match self.fetch_node(&uid) {
|
||||
Ok(node) => {
|
||||
let mut st = self.state.lock();
|
||||
let ino = st.intern(parent_ino, node);
|
||||
if let Some(kids) = st.children.get_mut(&parent_ino)
|
||||
&& !kids.contains(&ino)
|
||||
{
|
||||
kids.push(ino);
|
||||
}
|
||||
}
|
||||
// Uploaded fine but the metadata refresh failed; it will
|
||||
// appear on the next directory enumeration regardless.
|
||||
Err(e) => warn!(%uid, error = ?e, "uploaded node metadata refresh failed"),
|
||||
}
|
||||
}
|
||||
Err((name, msg)) => {
|
||||
stats.failed += 1;
|
||||
warn!(name, error = %msg, "file upload failed");
|
||||
}
|
||||
}
|
||||
}
|
||||
info!(
|
||||
uploaded = stats.uploaded,
|
||||
failed = stats.failed,
|
||||
"bulk upload finished"
|
||||
);
|
||||
Ok(stats)
|
||||
}
|
||||
|
||||
/// Resolve a remote child folder named `name` under `pino`, creating it if it
|
||||
/// doesn't exist, and return its `(inode, uid)`. Reusing an existing same-named
|
||||
/// folder makes re-uploading a directory merge into it rather than fail on a
|
||||
/// duplicate name.
|
||||
fn ensure_remote_folder(
|
||||
&self,
|
||||
pino: u64,
|
||||
parent_uid: &NodeUid,
|
||||
name: &str,
|
||||
) -> CoreResult<(u64, NodeUid)> {
|
||||
if name.is_empty() || name.contains('/') {
|
||||
return Err(CoreError::invalid(format!("invalid folder name: {name:?}")));
|
||||
}
|
||||
self.ensure_children(pino)
|
||||
.map_err(|e| self.errno_error(e, "enumerate"))?;
|
||||
{
|
||||
let st = self.state.lock();
|
||||
if let Some(kids) = st.children.get(&pino) {
|
||||
for &ino in kids {
|
||||
if let Some(e) = st.entries.get(&ino)
|
||||
&& e.node.is_folder()
|
||||
&& e.node.name == name
|
||||
{
|
||||
return Ok((ino, e.uid.clone()));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
let new_uid = self
|
||||
.rt
|
||||
.block_on(
|
||||
self.client
|
||||
.create_folder(parent_uid, name, Some(now_secs())),
|
||||
)
|
||||
.map_err(|e| CoreError::from_api(&e, &format!("create folder {name}")))?;
|
||||
let node = self
|
||||
.fetch_node(&new_uid)
|
||||
.map_err(|e| self.errno_error(e, "fetch node"))?;
|
||||
let mut st = self.state.lock();
|
||||
let ino = st.intern(pino, node);
|
||||
if let Some(kids) = st.children.get_mut(&pino)
|
||||
&& !kids.contains(&ino)
|
||||
{
|
||||
kids.push(ino);
|
||||
}
|
||||
Ok((ino, new_uid))
|
||||
}
|
||||
|
||||
/// Walk one local source path, appending its files to `tasks`. A file becomes
|
||||
/// one task; a directory is recreated remotely and recursed into (children
|
||||
/// sorted for a stable order). Symlinks and other special files are skipped.
|
||||
///
|
||||
/// `job` narrates the walk with the folder currently being mirrored. It stays
|
||||
/// indeterminate: nothing knows the size of the tree until the walk has ended.
|
||||
fn collect_uploads(
|
||||
&self,
|
||||
pino: u64,
|
||||
parent_uid: &NodeUid,
|
||||
src: &Path,
|
||||
tasks: &mut Vec<UploadTask>,
|
||||
folders: &mut usize,
|
||||
job: &JobGuard,
|
||||
) -> CoreResult<()> {
|
||||
let meta = std::fs::symlink_metadata(src)
|
||||
.map_err(|e| CoreError::internal(format!("stat {}: {e}", src.display())))?;
|
||||
let name = src
|
||||
.file_name()
|
||||
.and_then(|n| n.to_str())
|
||||
.ok_or_else(|| CoreError::invalid(format!("unusable name: {}", src.display())))?
|
||||
.to_string();
|
||||
|
||||
if meta.is_dir() {
|
||||
job.detail(&name);
|
||||
let (child_ino, child_uid) = self.ensure_remote_folder(pino, parent_uid, &name)?;
|
||||
*folders += 1;
|
||||
let mut entries: Vec<PathBuf> = std::fs::read_dir(src)
|
||||
.map_err(|e| CoreError::internal(format!("read dir {}: {e}", src.display())))?
|
||||
.filter_map(|e| e.ok())
|
||||
.map(|e| e.path())
|
||||
.collect();
|
||||
entries.sort();
|
||||
for entry in entries {
|
||||
if let Err(e) =
|
||||
self.collect_uploads(child_ino, &child_uid, &entry, tasks, folders, job)
|
||||
{
|
||||
warn!(source = %entry.display(), error = %e, "skipping entry");
|
||||
}
|
||||
}
|
||||
// Deeper folders have retitled the job by now; put this one back so the
|
||||
// line tracks the walk's position rather than its deepest leaf.
|
||||
job.detail(&name);
|
||||
} else if meta.is_file() {
|
||||
if name.contains('/') {
|
||||
return Err(CoreError::invalid(format!("invalid file name: {name:?}")));
|
||||
}
|
||||
tasks.push(UploadTask {
|
||||
parent_ino: pino,
|
||||
parent_uid: parent_uid.clone(),
|
||||
name,
|
||||
path: src.to_path_buf(),
|
||||
size: meta.len(),
|
||||
});
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@@ -30,3 +30,4 @@ gtk4 = { version = "0.9", features = ["v4_12"] }
|
||||
adw = { package = "libadwaita", version = "0.7", features = ["v1_5"] }
|
||||
async-channel = "2"
|
||||
exif = { version = "0.6", package = "kamadak-exif" }
|
||||
webkit6 = "0.4"
|
||||
@@ -0,0 +1,89 @@
|
||||
//! Shared Drive-result activation policy for the GTK browser and quick prompt.
|
||||
//!
|
||||
//! Media should be handed to its mounted path so players can issue range reads
|
||||
//! through FUSE. Other files retain the materialize-then-open behaviour because
|
||||
//! many desktop applications expect a stable ordinary file.
|
||||
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use pdfs_core::control::PhotoKind;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub(crate) enum DriveActivation {
|
||||
Folder,
|
||||
MountedMedia,
|
||||
Materialize,
|
||||
}
|
||||
|
||||
pub(crate) fn drive_activation(name: &str, is_dir: bool) -> DriveActivation {
|
||||
if is_dir {
|
||||
DriveActivation::Folder
|
||||
} else if is_streamable_media(name) {
|
||||
DriveActivation::MountedMedia
|
||||
} else {
|
||||
DriveActivation::Materialize
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn mounted_path(mountpoint: &Path, relative_path: &str) -> PathBuf {
|
||||
mountpoint.join(relative_path)
|
||||
}
|
||||
|
||||
fn is_streamable_media(name: &str) -> bool {
|
||||
if PhotoKind::classify(Some(name), None) == PhotoKind::Video {
|
||||
return true;
|
||||
}
|
||||
|
||||
let extension = Path::new(name)
|
||||
.extension()
|
||||
.and_then(|value| value.to_str())
|
||||
.unwrap_or_default();
|
||||
|
||||
matches!(
|
||||
extension.to_ascii_lowercase().as_str(),
|
||||
"mp3" | "flac" | "wav" | "ogg" | "opus" | "m4a" | "aac"
|
||||
)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn folders_use_the_mount_regardless_of_extension() {
|
||||
assert_eq!(
|
||||
drive_activation("recordings.mp4", true),
|
||||
DriveActivation::Folder
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn media_extensions_use_fuse_path_case_insensitively() {
|
||||
for name in ["movie.MKV", "voice.opus", "song.FLAC", "clip.m4v"] {
|
||||
assert_eq!(
|
||||
drive_activation(name, false),
|
||||
DriveActivation::MountedMedia,
|
||||
"{name}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ordinary_files_are_materialized() {
|
||||
for name in ["report.pdf", "notes.txt", "archive.zip", "no-extension"] {
|
||||
assert_eq!(
|
||||
drive_activation(name, false),
|
||||
DriveActivation::Materialize,
|
||||
"{name}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mounted_paths_preserve_relative_components() {
|
||||
assert_eq!(
|
||||
mounted_path(Path::new("/mnt/drive"), "Videos/a movie.mkv"),
|
||||
Path::new("/mnt/drive/Videos/a movie.mkv")
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1,3 +1,5 @@
|
||||
#[path = "../activation.rs"]
|
||||
pub(crate) mod activation;
|
||||
pub(crate) mod pages;
|
||||
pub(crate) mod widgets;
|
||||
|
||||
@@ -11,6 +13,7 @@ use pages::shared::*;
|
||||
use pages::shared_by_me::*;
|
||||
use pages::status::*;
|
||||
use pages::trash::*;
|
||||
use pages::verify::*;
|
||||
use widgets::details::*;
|
||||
use widgets::share_dialog::*;
|
||||
|
||||
@@ -40,9 +43,10 @@ use pdfs_core::config::AppDirs;
|
||||
|
||||
use pdfs_core::control::{
|
||||
ActivityEntry, ActivityKind, BookmarkInfo, DeviceInfo, DirEntry, ErrorKind, InvitationInfo,
|
||||
JobItem, PhotoItem, PhotoKind, PublicLinkInfo, RefreshScope, Request, Response, SearchHit,
|
||||
ShareEntry, ShareEntryKind, SharedItem, SyncFolderInfo, SyncPhase, SyncProgress,
|
||||
TransferDirection, TransferItem, pending_summary, send,
|
||||
JobItem, PhotoItem, PhotoKind, PublicLinkInfo, RefreshScope, Request, Response,
|
||||
RestorableFolder, RestoreItem, SearchHit, ShareEntry, ShareEntryKind, SharedItem,
|
||||
SyncFolderInfo, SyncPhase, SyncProgress, TransferDirection, TransferItem, pending_summary,
|
||||
send,
|
||||
};
|
||||
|
||||
use pdfs_core::service;
|
||||
@@ -398,6 +402,11 @@ fn build_window(app: &adw::Application) {
|
||||
transfers_inflight: Cell::new(false),
|
||||
cache_bar: main_widgets.cache_bar.clone(),
|
||||
cache_label: main_widgets.cache_label.clone(),
|
||||
quota_group: main_widgets.quota_group.clone(),
|
||||
quota_bar: main_widgets.quota_bar.clone(),
|
||||
quota_label: main_widgets.quota_label.clone(),
|
||||
quota_inflight: Cell::new(false),
|
||||
quota_checked_at: Cell::new(None),
|
||||
autostart_row: main_widgets.autostart_row.clone(),
|
||||
budget_row: main_widgets.budget_row.clone(),
|
||||
mountpoint_row: main_widgets.mountpoint_row.clone(),
|
||||
@@ -477,6 +486,7 @@ fn build_window(app: &adw::Application) {
|
||||
with_me_group: shared_widgets.shared_with_me.clone(),
|
||||
invitations_group: shared_widgets.invitations.clone(),
|
||||
bookmarks_group: shared_widgets.bookmarks.clone(),
|
||||
nav: RefCell::new(Vec::new()),
|
||||
rows: RefCell::new(Vec::new()),
|
||||
inflight: Cell::new(false),
|
||||
loaded_at: Cell::new(None),
|
||||
@@ -498,6 +508,8 @@ fn build_window(app: &adw::Application) {
|
||||
rows: RefCell::new(Vec::new()),
|
||||
sync_group: devices_widgets.sync_group.clone(),
|
||||
sync_rows: RefCell::new(Vec::new()),
|
||||
rename_this: devices_widgets.rename_this.clone(),
|
||||
this_device: RefCell::new(None),
|
||||
inflight: Cell::new(false),
|
||||
loaded_at: Cell::new(None),
|
||||
},
|
||||
@@ -534,7 +546,12 @@ fn build_window(app: &adw::Application) {
|
||||
wire_trash(&ui, &trash_widgets.list, &trash_widgets.empty);
|
||||
wire_shared(&ui, &shared_widgets.retry, &shared_widgets.add_bookmark);
|
||||
wire_shared_by_me(&ui, &shared_by_me_widgets.retry);
|
||||
wire_devices(&ui, &devices_widgets.retry, &devices_widgets.add_folder);
|
||||
wire_devices(
|
||||
&ui,
|
||||
&devices_widgets.retry,
|
||||
&devices_widgets.add_folder,
|
||||
&devices_widgets.restore,
|
||||
);
|
||||
wire_activity(&ui, &activity_widgets.retry);
|
||||
wire_refresh(
|
||||
&ui,
|
||||
|
||||
@@ -281,6 +281,7 @@ pub(crate) fn activity_verb(kind: ActivityKind) -> &'static str {
|
||||
ActivityKind::Share => "Shared",
|
||||
ActivityKind::PublicLink => "Linked",
|
||||
ActivityKind::Unshare => "Unshared",
|
||||
ActivityKind::Conflict => "Conflict",
|
||||
}
|
||||
}
|
||||
|
||||
@@ -299,6 +300,7 @@ pub(crate) fn activity_icon(kind: ActivityKind) -> &'static str {
|
||||
ActivityKind::Restore => "edit-undo-symbolic",
|
||||
ActivityKind::Share | ActivityKind::PublicLink => "emblem-shared-symbolic",
|
||||
ActivityKind::Unshare => "action-unavailable-symbolic",
|
||||
ActivityKind::Conflict => "dialog-warning-symbolic",
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
use crate::activation::{DriveActivation, drive_activation, mounted_path};
|
||||
use crate::*;
|
||||
|
||||
pub(crate) struct BrowserState {
|
||||
@@ -493,9 +494,9 @@ pub(crate) fn show_context_menu(ui: &Rc<Ui>, entry: &DirEntry, anchor: >k4::Bo
|
||||
popover.set_parent(anchor);
|
||||
popover.connect_closed(|p| p.unparent());
|
||||
|
||||
// Videos lead with Play (stream from the mount, no download); the plain Open
|
||||
// Media leads with Play (stream from the mount, no download); the plain Open
|
||||
// below still downloads a local copy for anyone who wants one.
|
||||
if is_video_entry(entry) {
|
||||
if is_streamable_media_entry(entry) {
|
||||
let play = menu_item("Play (stream)", "media-playback-start-symbolic");
|
||||
let ui_play = ui.clone();
|
||||
let entry_play = entry.clone();
|
||||
@@ -514,8 +515,8 @@ pub(crate) fn show_context_menu(ui: &Rc<Ui>, entry: &DirEntry, anchor: >k4::Bo
|
||||
open.connect_clicked(move |_| {
|
||||
pop.popdown();
|
||||
// Open always means "download a local copy and hand off", even for a
|
||||
// video — `activate_entry` would otherwise stream it.
|
||||
if is_video_entry(&entry_open) {
|
||||
// media file — `activate_entry` would otherwise stream it.
|
||||
if is_streamable_media_entry(&entry_open) {
|
||||
download_and_open(&ui_open, &entry_open);
|
||||
} else {
|
||||
activate_entry(&ui_open, &entry_open);
|
||||
@@ -610,14 +611,12 @@ pub(crate) fn entry_at(model: Option<&impl IsA<gio::ListModel>>, pos: u32) -> Op
|
||||
Some(entry)
|
||||
}
|
||||
|
||||
/// Whether an entry's name marks it as a video, reusing the same classifier the
|
||||
/// Photos page splits on — so the file browser and the gallery agree on what a
|
||||
/// video is.
|
||||
pub(crate) fn is_video_entry(entry: &DirEntry) -> bool {
|
||||
!entry.is_dir && PhotoKind::classify(Some(&entry.name), None) == PhotoKind::Video
|
||||
/// Whether an entry can be opened through FUSE instead of fully materialized.
|
||||
pub(crate) fn is_streamable_media_entry(entry: &DirEntry) -> bool {
|
||||
drive_activation(&entry.name, entry.is_dir) == DriveActivation::MountedMedia
|
||||
}
|
||||
|
||||
/// Stream a video straight from the mount, no download. Drive folders *are* part
|
||||
/// Stream media straight from the mount, no download. Drive folders *are* part
|
||||
/// of the FUSE mount, so a player pointed at `<mountpoint>/<rel>` reads the file
|
||||
/// through [`Core::read_range_remote`] — 4 MB blocks fetched on demand as it
|
||||
/// seeks and buffers — instead of waiting for the whole file to land like
|
||||
@@ -626,11 +625,11 @@ pub(crate) fn is_video_entry(entry: &DirEntry) -> bool {
|
||||
pub(crate) fn stream_entry(ui: &Rc<Ui>, entry: &DirEntry) {
|
||||
let rel = entry_rel(ui, entry);
|
||||
let mountpoint = ui.dirs.resolved_mountpoint(&ui.dirs.load_config());
|
||||
let abs = mountpoint.join(&rel);
|
||||
let abs = mounted_path(&mountpoint, &rel);
|
||||
let Some(path) = abs.to_str() else {
|
||||
toast_error(
|
||||
ui,
|
||||
"Couldn't play video",
|
||||
"Couldn't play media",
|
||||
"The file path isn't valid UTF-8.",
|
||||
);
|
||||
return;
|
||||
@@ -639,7 +638,7 @@ pub(crate) fn stream_entry(ui: &Rc<Ui>, entry: &DirEntry) {
|
||||
play_external(path);
|
||||
}
|
||||
|
||||
/// Open an entry the Nautilus way: folders descend, videos stream from the mount,
|
||||
/// Open an entry the Nautilus way: folders descend, media streams from the mount,
|
||||
/// other files download-and-open.
|
||||
pub(crate) fn activate_entry(ui: &Rc<Ui>, entry: &DirEntry) {
|
||||
let rel = entry_rel(ui, entry);
|
||||
@@ -651,8 +650,8 @@ pub(crate) fn activate_entry(ui: &Rc<Ui>, entry: &DirEntry) {
|
||||
}
|
||||
*ui.browser.path.borrow_mut() = rel;
|
||||
load_browser(ui);
|
||||
} else if is_video_entry(entry) {
|
||||
// A video streams rather than downloads: that is exactly the "play it,
|
||||
} else if drive_activation(&entry.name, entry.is_dir) == DriveActivation::MountedMedia {
|
||||
// Media streams rather than downloads: that is exactly the "play it,
|
||||
// don't fetch the whole thing" behaviour this is for.
|
||||
stream_entry(ui, entry);
|
||||
} else {
|
||||
|
||||
@@ -10,6 +10,13 @@ pub(crate) struct DevicesState {
|
||||
pub(crate) rows: RefCell<Vec<gtk4::Widget>>,
|
||||
pub(crate) sync_group: adw::PreferencesGroup,
|
||||
pub(crate) sync_rows: RefCell<Vec<gtk4::Widget>>,
|
||||
/// "Rename" action in the "This computer" header. Insensitive until the
|
||||
/// device list identifies this machine's own device.
|
||||
pub(crate) rename_this: gtk4::Button,
|
||||
/// This machine's own device `(uid, name)`, from the last device list. The
|
||||
/// current device is filtered out of the "Other computers" rows, so this is
|
||||
/// where its rename target lives. `None` until identified.
|
||||
pub(crate) this_device: RefCell<Option<(String, String)>>,
|
||||
pub(crate) inflight: Cell<bool>,
|
||||
pub(crate) loaded_at: Cell<Option<Instant>>,
|
||||
}
|
||||
@@ -20,11 +27,16 @@ pub(crate) struct DevicesWidgets {
|
||||
pub(crate) status: adw::StatusPage,
|
||||
/// "This computer" — the local folders synced to this machine's device.
|
||||
pub(crate) sync_group: adw::PreferencesGroup,
|
||||
/// "Rename" in the "This computer" header — renames this machine's device.
|
||||
pub(crate) rename_this: gtk4::Button,
|
||||
/// "Other computers" — the account's *other* registered devices. This
|
||||
/// machine's own device is deliberately not among them; see
|
||||
/// [`repaint_devices`].
|
||||
pub(crate) group: adw::PreferencesGroup,
|
||||
pub(crate) add_folder: gtk4::Button,
|
||||
/// "Restore Folders" — re-attach this device's remote folders to local
|
||||
/// directories after adopting it on a new machine.
|
||||
pub(crate) restore: gtk4::Button,
|
||||
pub(crate) retry: gtk4::Button,
|
||||
pub(crate) refresh: gtk4::Button,
|
||||
}
|
||||
@@ -47,11 +59,18 @@ pub(crate) fn build_devices_page() -> (gtk4::Widget, DevicesWidgets) {
|
||||
.valign(gtk4::Align::Center)
|
||||
.build();
|
||||
add_folder.add_css_class("flat");
|
||||
let restore = gtk4::Button::builder()
|
||||
.label("Restore Folders")
|
||||
.tooltip_text("Sync this computer's Drive folders back to local directories")
|
||||
.valign(gtk4::Align::Center)
|
||||
.build();
|
||||
restore.add_css_class("flat");
|
||||
let refresh = refresh_button();
|
||||
|
||||
let header = gtk4::Box::new(gtk4::Orientation::Horizontal, 8);
|
||||
header.append(&titles);
|
||||
header.append(&refresh);
|
||||
header.append(&restore);
|
||||
header.append(&add_folder);
|
||||
|
||||
// The description spells out what the per-row On-demand switch does to the
|
||||
@@ -65,6 +84,17 @@ pub(crate) fn build_devices_page() -> (gtk4::Widget, DevicesWidgets) {
|
||||
them as you open them.",
|
||||
)
|
||||
.build();
|
||||
// Rename control for *this* machine's device, in the section header. The
|
||||
// current device is filtered out of "Other computers", so this is the only
|
||||
// place it can be renamed; insensitive until the device list identifies it.
|
||||
let rename_this = gtk4::Button::builder()
|
||||
.icon_name("document-edit-symbolic")
|
||||
.tooltip_text("Rename this computer")
|
||||
.valign(gtk4::Align::Center)
|
||||
.sensitive(false)
|
||||
.build();
|
||||
rename_this.add_css_class("flat");
|
||||
sync_group.set_header_suffix(Some(&rename_this));
|
||||
let group = adw::PreferencesGroup::builder()
|
||||
.title("Other computers")
|
||||
.description("Other devices backing up to this account.")
|
||||
@@ -113,8 +143,10 @@ pub(crate) fn build_devices_page() -> (gtk4::Widget, DevicesWidgets) {
|
||||
content,
|
||||
status,
|
||||
sync_group,
|
||||
rename_this,
|
||||
group,
|
||||
add_folder,
|
||||
restore,
|
||||
retry,
|
||||
refresh,
|
||||
},
|
||||
@@ -122,7 +154,12 @@ pub(crate) fn build_devices_page() -> (gtk4::Widget, DevicesWidgets) {
|
||||
}
|
||||
|
||||
/// Install the Devices page's retry button and the "Add Folder" action.
|
||||
pub(crate) fn wire_devices(ui: &Rc<Ui>, retry: >k4::Button, add_folder: >k4::Button) {
|
||||
pub(crate) fn wire_devices(
|
||||
ui: &Rc<Ui>,
|
||||
retry: >k4::Button,
|
||||
add_folder: >k4::Button,
|
||||
restore: >k4::Button,
|
||||
) {
|
||||
let ui_retry = ui.clone();
|
||||
retry.connect_clicked(move |_| {
|
||||
service::restart();
|
||||
@@ -130,6 +167,14 @@ pub(crate) fn wire_devices(ui: &Rc<Ui>, retry: >k4::Button, add_folder: >k4:
|
||||
});
|
||||
let ui_add = ui.clone();
|
||||
add_folder.connect_clicked(move |_| prompt_add_sync_folder(&ui_add));
|
||||
let ui_restore = ui.clone();
|
||||
restore.connect_clicked(move |_| prompt_restore_folders(&ui_restore));
|
||||
let ui_ren = ui.clone();
|
||||
ui.devices.rename_this.connect_clicked(move |_| {
|
||||
if let Some((uid, name)) = ui_ren.devices.this_device.borrow().clone() {
|
||||
prompt_rename_device(&ui_ren, &uid, &name);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Show a status page in place of the Devices list.
|
||||
@@ -264,6 +309,22 @@ pub(crate) fn repaint_devices(ui: &Rc<Ui>, devices: &[DeviceInfo]) {
|
||||
for row in ui.devices.rows.borrow_mut().drain(..) {
|
||||
ui.devices.group.remove(&row);
|
||||
}
|
||||
// Identify this machine's own device so the "This computer" header's Rename
|
||||
// action has a target. It never appears in the rows below, so this is the
|
||||
// only place its name/uid is captured.
|
||||
match devices.iter().find(|d| d.this_device) {
|
||||
Some(me) => {
|
||||
*ui.devices.this_device.borrow_mut() = Some((me.uid.clone(), me.name.clone()));
|
||||
ui.devices.rename_this.set_sensitive(true);
|
||||
ui.devices
|
||||
.rename_this
|
||||
.set_tooltip_text(Some(&format!("Rename this computer ({})", me.name)));
|
||||
}
|
||||
None => {
|
||||
*ui.devices.this_device.borrow_mut() = None;
|
||||
ui.devices.rename_this.set_sensitive(false);
|
||||
}
|
||||
}
|
||||
let others: Vec<&DeviceInfo> = devices.iter().filter(|d| !d.this_device).collect();
|
||||
if others.is_empty() {
|
||||
let row = adw::ActionRow::builder()
|
||||
@@ -294,6 +355,21 @@ pub(crate) fn repaint_devices(ui: &Rc<Ui>, devices: &[DeviceInfo]) {
|
||||
.valign(gtk4::Align::Center)
|
||||
.build();
|
||||
rename.add_css_class("flat");
|
||||
// Adoption is how a reinstalled or renamed machine re-attaches to the
|
||||
// device it used to be, instead of registering a duplicate. It only
|
||||
// makes sense on *another* device's row, which is the only place this
|
||||
// loop paints.
|
||||
let adopt = gtk4::Button::builder()
|
||||
.icon_name("insert-object-symbolic")
|
||||
.tooltip_text("Use this computer's identity for this machine")
|
||||
.valign(gtk4::Align::Center)
|
||||
.build();
|
||||
adopt.add_css_class("flat");
|
||||
let ui_ad = ui.clone();
|
||||
let uid_ad = dev.uid.clone();
|
||||
let name_ad = dev.name.clone();
|
||||
adopt.connect_clicked(move |_| prompt_adopt_device(&ui_ad, &uid_ad, &name_ad));
|
||||
row.add_suffix(&adopt);
|
||||
let ui_ren = ui.clone();
|
||||
let uid_ren = dev.uid.clone();
|
||||
let name_ren = dev.name.clone();
|
||||
@@ -533,6 +609,110 @@ pub(crate) fn prompt_add_sync_folder(ui: &Rc<Ui>) {
|
||||
});
|
||||
}
|
||||
|
||||
/// Ask the daemon what this machine's device holds, then show a picker mapping
|
||||
/// each remote folder onto a local directory.
|
||||
///
|
||||
/// The daemon's paths are proposals — from the device's `profile.json` when it
|
||||
/// makes sense here, else `~/<name>` — so every one of them is editable and
|
||||
/// nothing is restored without being ticked.
|
||||
pub(crate) fn prompt_restore_folders(ui: &Rc<Ui>) {
|
||||
ui.busy_begin();
|
||||
let rx = spawn_request(ui.dirs.control_socket(), Request::ListRestorableFolders);
|
||||
let ui = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let result = rx.recv().await;
|
||||
ui.busy_end();
|
||||
match result {
|
||||
Ok(Ok(Response::RestorableFolders { items })) => show_restore_picker(&ui, items),
|
||||
Ok(Ok(Response::Error { message, kind })) => {
|
||||
toast_failure(&ui, "Couldn't list folders to restore", &message, kind)
|
||||
}
|
||||
_ => toast_error(
|
||||
&ui,
|
||||
"Couldn't list folders to restore",
|
||||
"The mount service didn't respond.",
|
||||
),
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// The restore picker itself: one editable row per restorable folder.
|
||||
fn show_restore_picker(ui: &Rc<Ui>, items: Vec<RestorableFolder>) {
|
||||
let win = ui_window(ui);
|
||||
let candidates: Vec<RestorableFolder> =
|
||||
items.into_iter().filter(|f| !f.already_synced).collect();
|
||||
if candidates.is_empty() {
|
||||
toast(
|
||||
ui,
|
||||
"Nothing to restore — this computer's folders are all synced here.",
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
let group = adw::PreferencesGroup::builder()
|
||||
.description(
|
||||
"Tick the folders to sync to this machine, and adjust where each one should live.",
|
||||
)
|
||||
.build();
|
||||
// Held so the response handler can read back what the user ticked and typed.
|
||||
let mut controls: Vec<(String, String, gtk4::CheckButton, adw::EntryRow)> = Vec::new();
|
||||
for f in candidates {
|
||||
let check = gtk4::CheckButton::builder()
|
||||
.active(true)
|
||||
.valign(gtk4::Align::Center)
|
||||
.build();
|
||||
let row = adw::EntryRow::builder().title(&f.name).build();
|
||||
row.set_text(&f.local_path);
|
||||
row.add_prefix(&check);
|
||||
group.add(&row);
|
||||
controls.push((f.remote_uid, f.mode, check, row));
|
||||
}
|
||||
|
||||
let scroll = gtk4::ScrolledWindow::builder()
|
||||
.propagate_natural_height(true)
|
||||
.max_content_height(420)
|
||||
.child(&group)
|
||||
.build();
|
||||
let dialog = adw::AlertDialog::builder()
|
||||
.heading("Restore folders")
|
||||
.body("These folders are backed up under this computer in Proton Drive.")
|
||||
.extra_child(&scroll)
|
||||
.build();
|
||||
dialog.add_response("cancel", "Cancel");
|
||||
dialog.add_response("restore", "Restore");
|
||||
dialog.set_response_appearance("restore", adw::ResponseAppearance::Suggested);
|
||||
dialog.set_default_response(Some("restore"));
|
||||
dialog.set_close_response("cancel");
|
||||
|
||||
let ui = ui.clone();
|
||||
dialog.connect_response(None, move |_, resp| {
|
||||
if resp != "restore" {
|
||||
return;
|
||||
}
|
||||
let items: Vec<RestoreItem> = controls
|
||||
.iter()
|
||||
.filter(|(_, _, check, _)| check.is_active())
|
||||
.map(|(uid, mode, _, row)| RestoreItem {
|
||||
remote_uid: uid.clone(),
|
||||
local_path: row.text().to_string(),
|
||||
mode: mode.clone(),
|
||||
})
|
||||
.collect();
|
||||
if items.is_empty() {
|
||||
return;
|
||||
}
|
||||
// The daemon acks before the downloads finish, like AddSyncFolder — the
|
||||
// rows appear as the periodic refresh picks them up.
|
||||
run_devices_mutation(
|
||||
&ui,
|
||||
Request::RestoreSyncFolders { items },
|
||||
"Restoring folders…",
|
||||
"Couldn't restore folders",
|
||||
);
|
||||
});
|
||||
dialog.present(win.as_ref());
|
||||
}
|
||||
|
||||
/// Flip a synced folder between `mirror` and `ondemand`. Reloads after so the
|
||||
/// row's subtitle and switch reflect the daemon's real state (the request may be
|
||||
/// rejected, e.g. switching to on-demand while a folder is mid-sync).
|
||||
@@ -698,6 +878,46 @@ pub(crate) fn prompt_remove_device(ui: &Rc<Ui>, uid: &str, name: &str) {
|
||||
dialog.present(win.as_ref());
|
||||
}
|
||||
|
||||
/// Confirm, then adopt another device as this machine's identity.
|
||||
///
|
||||
/// Worth a confirmation rather than a plain click: adoption re-points this
|
||||
/// machine's syncing at another computer's device folder, and the folders
|
||||
/// already synced here keep pointing at the old one until they are removed. The
|
||||
/// dialog says so, because the alternative is a user discovering it by watching
|
||||
/// their folders diverge.
|
||||
pub(crate) fn prompt_adopt_device(ui: &Rc<Ui>, uid: &str, name: &str) {
|
||||
let win = ui_window(ui);
|
||||
let dialog = adw::AlertDialog::builder()
|
||||
.heading("Use this computer's identity")
|
||||
.body(format!(
|
||||
"Treat this machine as “{name}”?\n\nNew synced folders are created under that \
|
||||
computer in Proton Drive, and this machine keeps that identity even if its hostname \
|
||||
changes. Folders already synced here are not moved.\n\nUse “Restore folders” \
|
||||
afterwards to bring back what “{name}” was syncing."
|
||||
))
|
||||
.build();
|
||||
dialog.add_response("cancel", "Cancel");
|
||||
dialog.add_response("adopt", "Use identity");
|
||||
dialog.set_response_appearance("adopt", adw::ResponseAppearance::Suggested);
|
||||
dialog.set_default_response(Some("cancel"));
|
||||
dialog.set_close_response("cancel");
|
||||
let ui = ui.clone();
|
||||
let uid = uid.to_string();
|
||||
dialog.connect_response(None, move |_, resp| {
|
||||
if resp == "adopt" {
|
||||
run_devices_mutation(
|
||||
&ui,
|
||||
Request::AdoptDevice {
|
||||
uid: Some(uid.clone()),
|
||||
},
|
||||
"Identity adopted",
|
||||
"Couldn't adopt that computer",
|
||||
);
|
||||
}
|
||||
});
|
||||
dialog.present(win.as_ref());
|
||||
}
|
||||
|
||||
/// Run a mutation raised from the Devices page and reload the page on success.
|
||||
pub(crate) fn run_devices_mutation(
|
||||
ui: &Rc<Ui>,
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
use crate::*;
|
||||
use pdfs_core::proton_sdk::api::HumanVerificationCredential;
|
||||
|
||||
pub(crate) struct LoginState {
|
||||
// Login page.
|
||||
@@ -104,18 +105,35 @@ pub(crate) fn wire_login(ui: &Rc<Ui>) {
|
||||
|
||||
ui.login.login_button.set_sensitive(false);
|
||||
ui.login.login_status.set_text("Signing in…");
|
||||
let (rx, totp_req_rx) = spawn_login(username, password);
|
||||
let (rx, totp_req_rx, hv_req_rx) = spawn_login(username, password);
|
||||
|
||||
// Surface the 2FA dialog only if the SDK actually asks for a code (i.e.
|
||||
// the account has 2FA enabled). The worker blocks until the dialog feeds
|
||||
// back a code (or is cancelled, dropping the sender).
|
||||
//
|
||||
// Loops rather than awaiting once: a login gated behind a CAPTCHA is
|
||||
// restarted after verification, so a 2FA account is asked for a second,
|
||||
// unexpired code on the retry.
|
||||
let ui_2fa = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
if let Ok(code_tx) = totp_req_rx.recv().await {
|
||||
while let Ok(code_tx) = totp_req_rx.recv().await {
|
||||
prompt_2fa(&ui_2fa, code_tx);
|
||||
}
|
||||
});
|
||||
|
||||
// Same shape for human verification: only fires when the API gates the
|
||||
// sign-in, and the worker is blocked on the token until it does.
|
||||
let ui_hv = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
if let Ok((url, token_tx)) = hv_req_rx.recv().await {
|
||||
ui_hv
|
||||
.login
|
||||
.login_status
|
||||
.set_text("Complete the verification to continue…");
|
||||
prompt_human_verification(&ui_hv, &url, token_tx);
|
||||
}
|
||||
});
|
||||
|
||||
let ui = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let result = rx
|
||||
@@ -155,9 +173,13 @@ pub(crate) fn spawn_login(
|
||||
) -> (
|
||||
async_channel::Receiver<Result<(), String>>,
|
||||
async_channel::Receiver<std::sync::mpsc::Sender<String>>,
|
||||
async_channel::Receiver<(String, std::sync::mpsc::Sender<String>)>,
|
||||
) {
|
||||
let (tx, rx) = async_channel::bounded(1);
|
||||
let (totp_req_tx, totp_req_rx) = async_channel::bounded(1);
|
||||
// Two, not one: a CAPTCHA-gated login restarts, so a 2FA account is asked
|
||||
// for a code on each attempt and a single slot would deadlock the worker.
|
||||
let (totp_req_tx, totp_req_rx) = async_channel::bounded(2);
|
||||
let (hv_req_tx, hv_req_rx) = async_channel::bounded(1);
|
||||
std::thread::spawn(move || {
|
||||
let rt = match tokio::runtime::Builder::new_current_thread()
|
||||
.enable_all()
|
||||
@@ -170,24 +192,42 @@ pub(crate) fn spawn_login(
|
||||
}
|
||||
};
|
||||
let result = rt.block_on(async move {
|
||||
auth::login(&username, &password, || {
|
||||
// 2FA required: hand a one-shot sender to the UI and block until
|
||||
// the dialog supplies the code. A dropped sender (cancelled
|
||||
// dialog) surfaces as a cancelled login.
|
||||
let (code_tx, code_rx) = std::sync::mpsc::channel::<String>();
|
||||
totp_req_tx
|
||||
.send_blocking(code_tx)
|
||||
.map_err(|_| pdfs_core::Error::Other("two-factor prompt closed".into()))?;
|
||||
code_rx
|
||||
.recv()
|
||||
.map_err(|_| pdfs_core::Error::Other("two-factor entry cancelled".into()))
|
||||
})
|
||||
auth::login_interactive(
|
||||
&username,
|
||||
&password,
|
||||
|| {
|
||||
// 2FA required: hand a one-shot sender to the UI and block
|
||||
// until the dialog supplies the code. A dropped sender
|
||||
// (cancelled dialog) surfaces as a cancelled login.
|
||||
let (code_tx, code_rx) = std::sync::mpsc::channel::<String>();
|
||||
totp_req_tx
|
||||
.send_blocking(code_tx)
|
||||
.map_err(|_| pdfs_core::Error::Other("two-factor prompt closed".into()))?;
|
||||
code_rx
|
||||
.recv()
|
||||
.map_err(|_| pdfs_core::Error::Other("two-factor entry cancelled".into()))
|
||||
},
|
||||
|hv| {
|
||||
// Gated: hand the UI the page to show, block on the token the
|
||||
// user earns by solving it.
|
||||
let (token_tx, token_rx) = std::sync::mpsc::channel::<String>();
|
||||
hv_req_tx
|
||||
.send_blocking((hv.verification_url(), token_tx))
|
||||
.map_err(|_| {
|
||||
pdfs_core::Error::Other("verification prompt closed".into())
|
||||
})?;
|
||||
let token = token_rx
|
||||
.recv()
|
||||
.map_err(|_| pdfs_core::Error::Other("verification cancelled".into()))?;
|
||||
Ok(HumanVerificationCredential::captcha(token))
|
||||
},
|
||||
)
|
||||
.await
|
||||
.map_err(|e| e.to_string())
|
||||
});
|
||||
let _ = tx.send_blocking(result);
|
||||
});
|
||||
(rx, totp_req_rx)
|
||||
(rx, totp_req_rx, hv_req_rx)
|
||||
}
|
||||
|
||||
/// Show the lazy two-factor dialog and feed the entered code back to the waiting
|
||||
|
||||
@@ -8,3 +8,4 @@ pub(crate) mod shared;
|
||||
pub(crate) mod shared_by_me;
|
||||
pub(crate) mod status;
|
||||
pub(crate) mod trash;
|
||||
pub(crate) mod verify;
|
||||
@@ -10,6 +10,10 @@ pub(crate) struct SharedState {
|
||||
pub(crate) with_me_group: adw::PreferencesGroup,
|
||||
pub(crate) invitations_group: adw::PreferencesGroup,
|
||||
pub(crate) bookmarks_group: adw::PreferencesGroup,
|
||||
/// Where in a shared folder the page currently is, as `(uid, name)` from the
|
||||
/// top level down. Empty = the top level. Shared subtrees have no path in the
|
||||
/// mount, so descending is uid-addressed and the stack *is* the breadcrumb.
|
||||
pub(crate) nav: RefCell<Vec<(String, String)>>,
|
||||
pub(crate) rows: RefCell<Vec<(adw::PreferencesGroup, gtk4::Widget)>>,
|
||||
/// Guards the Shared page's load so overlapping navigations don't stack.
|
||||
pub(crate) inflight: Cell<bool>,
|
||||
@@ -139,10 +143,19 @@ pub(crate) fn shared_status(ui: &Rc<Ui>, icon: &str, title: &str, description: &
|
||||
|
||||
/// Fetch the three Shared sections (shared-with-me, invitations, bookmarks) in
|
||||
/// parallel and repaint the page once all three land.
|
||||
///
|
||||
/// Inside a shared folder ([`SharedState::nav`] non-empty) only that folder's
|
||||
/// children are fetched: invitations and bookmarks belong to the top level, and
|
||||
/// carrying them down a subtree would read as if they lived there.
|
||||
pub(crate) fn load_shared(ui: &Rc<Ui>) {
|
||||
if ui.shared.inflight.get() {
|
||||
return;
|
||||
}
|
||||
let current = ui.shared.nav.borrow().last().cloned();
|
||||
if let Some((uid, _)) = current {
|
||||
load_shared_folder(ui, uid);
|
||||
return;
|
||||
}
|
||||
ui.shared.inflight.set(true);
|
||||
shared_status(
|
||||
ui,
|
||||
@@ -192,6 +205,163 @@ pub(crate) fn load_shared(ui: &Rc<Ui>) {
|
||||
});
|
||||
}
|
||||
|
||||
/// List one shared folder's children and repaint the page as that folder's view.
|
||||
/// The uid comes from the row that was activated (or from the nav stack on a
|
||||
/// reload) — a shared subtree is reachable no other way.
|
||||
fn load_shared_folder(ui: &Rc<Ui>, uid: String) {
|
||||
ui.shared.inflight.set(true);
|
||||
shared_status(
|
||||
ui,
|
||||
"folder-symbolic",
|
||||
"Loading…",
|
||||
"Reading this shared folder.",
|
||||
false,
|
||||
);
|
||||
ui.busy_begin();
|
||||
let rx = spawn_request(ui.dirs.control_socket(), Request::ListSharedFolder { uid });
|
||||
let ui = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let result = rx.recv().await;
|
||||
ui.busy_end();
|
||||
ui.shared.inflight.set(false);
|
||||
match result {
|
||||
Ok(Ok(Response::Entries { entries })) => {
|
||||
repaint_shared_folder(&ui, &entries);
|
||||
ui.shared.loaded_at.set(Some(Instant::now()));
|
||||
}
|
||||
Ok(Ok(Response::Error { message, kind })) => {
|
||||
// The folder is gone or access was revoked: fall back to the top
|
||||
// level rather than stranding the page on a dead uid.
|
||||
ui.shared.nav.borrow_mut().pop();
|
||||
toast_failure(&ui, "Couldn't open shared folder", &message, kind);
|
||||
load_shared(&ui);
|
||||
}
|
||||
_ => {
|
||||
ui.shared.loaded_at.set(None);
|
||||
shared_unreachable(&ui);
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Paint the contents of the shared folder at the top of the nav stack: a row to
|
||||
/// go back up, then the children. Invitations and bookmarks are hidden here —
|
||||
/// they are top-level things, not contents of this folder.
|
||||
fn repaint_shared_folder(ui: &Rc<Ui>, entries: &[DirEntry]) {
|
||||
for (group, row) in ui.shared.rows.borrow_mut().drain(..) {
|
||||
group.remove(&row);
|
||||
}
|
||||
ui.shared.content.set_visible_child_name("list");
|
||||
ui.shared.invitations_group.set_visible(false);
|
||||
ui.shared.bookmarks_group.set_visible(false);
|
||||
|
||||
let nav = ui.shared.nav.borrow().clone();
|
||||
let title = nav
|
||||
.iter()
|
||||
.map(|(_, name)| name.as_str())
|
||||
.collect::<Vec<_>>()
|
||||
.join(" / ");
|
||||
ui.shared.with_me_group.set_title(&title);
|
||||
|
||||
let mut rows: Vec<(adw::PreferencesGroup, gtk4::Widget)> = Vec::new();
|
||||
let up = adw::ActionRow::builder()
|
||||
.title("Back")
|
||||
.activatable(true)
|
||||
.build();
|
||||
up.add_prefix(>k4::Image::from_icon_name("go-up-symbolic"));
|
||||
let ui_up = ui.clone();
|
||||
up.connect_activated(move |_| {
|
||||
ui_up.shared.nav.borrow_mut().pop();
|
||||
load_shared(&ui_up);
|
||||
});
|
||||
ui.shared.with_me_group.add(&up);
|
||||
rows.push((ui.shared.with_me_group.clone(), up.upcast()));
|
||||
|
||||
if entries.is_empty() {
|
||||
let row = dim_row("This folder is empty.");
|
||||
ui.shared.with_me_group.add(&row);
|
||||
rows.push((ui.shared.with_me_group.clone(), row.upcast()));
|
||||
} else {
|
||||
for entry in entries {
|
||||
let row = shared_entry_row(ui, entry);
|
||||
ui.shared.with_me_group.add(&row);
|
||||
rows.push((ui.shared.with_me_group.clone(), row.upcast()));
|
||||
}
|
||||
}
|
||||
*ui.shared.rows.borrow_mut() = rows;
|
||||
}
|
||||
|
||||
/// A row for one node shared with me: folders descend into, files download and
|
||||
/// open with the user's default application.
|
||||
fn shared_entry_row(ui: &Rc<Ui>, entry: &DirEntry) -> adw::ActionRow {
|
||||
let row = adw::ActionRow::builder()
|
||||
.title(&entry.name)
|
||||
.activatable(true)
|
||||
.build();
|
||||
if !entry.is_dir {
|
||||
row.set_subtitle(&human_bytes(entry.size));
|
||||
}
|
||||
row.add_prefix(>k4::Image::from_icon_name(if entry.is_dir {
|
||||
"folder-symbolic"
|
||||
} else {
|
||||
"text-x-generic-symbolic"
|
||||
}));
|
||||
let ui_act = ui.clone();
|
||||
let uid = entry.uid.clone();
|
||||
let name = entry.name.clone();
|
||||
let is_dir = entry.is_dir;
|
||||
row.connect_activated(move |_| {
|
||||
if is_dir {
|
||||
ui_act
|
||||
.shared
|
||||
.nav
|
||||
.borrow_mut()
|
||||
.push((uid.clone(), name.clone()));
|
||||
load_shared(&ui_act);
|
||||
} else {
|
||||
open_shared_file(&ui_act, &uid, &name);
|
||||
}
|
||||
});
|
||||
row
|
||||
}
|
||||
|
||||
/// Download a file shared with me into the daemon's cache and hand it to the
|
||||
/// user's default application — the shared-item twin of the browser's
|
||||
/// download-and-open, addressed by uid because the file lives outside the mount.
|
||||
fn open_shared_file(ui: &Rc<Ui>, uid: &str, name: &str) {
|
||||
// Ignore a repeat activation of a file already downloading, so an impatient
|
||||
// double-click doesn't kick off a second round-trip.
|
||||
if !ui.opening.borrow_mut().insert(uid.to_string()) {
|
||||
return;
|
||||
}
|
||||
ui.busy_begin();
|
||||
toast(ui, &format!("Downloading “{name}”…"));
|
||||
let rx = spawn_request(
|
||||
ui.dirs.control_socket(),
|
||||
Request::OpenSharedFile {
|
||||
uid: uid.to_string(),
|
||||
},
|
||||
);
|
||||
let ui = ui.clone();
|
||||
let uid = uid.to_string();
|
||||
glib::spawn_future_local(async move {
|
||||
let result = rx.recv().await;
|
||||
ui.busy_end();
|
||||
ui.opening.borrow_mut().remove(&uid);
|
||||
match result {
|
||||
Ok(Ok(Response::FilePath { path })) => open_path(&path),
|
||||
Ok(Ok(Response::Error { message, kind })) => {
|
||||
toast_failure(&ui, "Couldn't open file", &message, kind)
|
||||
}
|
||||
_ => toast_error(
|
||||
&ui,
|
||||
"Couldn't open file",
|
||||
"The mount service didn't respond.",
|
||||
),
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// The daemon didn't answer the Shared page. Same still-starting vs. down split
|
||||
/// as the other pages.
|
||||
pub(crate) fn shared_unreachable(ui: &Rc<Ui>) {
|
||||
@@ -233,6 +403,9 @@ pub(crate) fn repaint_shared(
|
||||
group.remove(&row);
|
||||
}
|
||||
ui.shared.content.set_visible_child_name("list");
|
||||
ui.shared.invitations_group.set_visible(true);
|
||||
ui.shared.bookmarks_group.set_visible(true);
|
||||
ui.shared.with_me_group.set_title("Shared with me");
|
||||
let mut rows: Vec<(adw::PreferencesGroup, gtk4::Widget)> = Vec::new();
|
||||
|
||||
// Shared with me: name + Leave.
|
||||
@@ -242,12 +415,7 @@ pub(crate) fn repaint_shared(
|
||||
rows.push((ui.shared.with_me_group.clone(), row.upcast()));
|
||||
} else {
|
||||
for entry in shared {
|
||||
let row = adw::ActionRow::builder().title(&entry.name).build();
|
||||
row.add_prefix(>k4::Image::from_icon_name(if entry.is_dir {
|
||||
"folder-symbolic"
|
||||
} else {
|
||||
"text-x-generic-symbolic"
|
||||
}));
|
||||
let row = shared_entry_row(ui, entry);
|
||||
let leave = gtk4::Button::builder()
|
||||
.label("Leave")
|
||||
.valign(gtk4::Align::Center)
|
||||
|
||||
@@ -17,6 +17,14 @@ pub(crate) struct StatusState {
|
||||
pub(crate) mount_row: adw::ActionRow,
|
||||
pub(crate) cache_bar: gtk4::ProgressBar,
|
||||
pub(crate) cache_label: gtk4::Label,
|
||||
/// Account-quota group + its bar/label. Hidden until the first reading.
|
||||
pub(crate) quota_group: adw::PreferencesGroup,
|
||||
pub(crate) quota_bar: gtk4::ProgressBar,
|
||||
pub(crate) quota_label: gtk4::Label,
|
||||
/// One `AccountQuota` in flight at a time, and when it last succeeded — quota
|
||||
/// barely moves, so [`refresh_quota`] refetches on a long TTL, not every tick.
|
||||
pub(crate) quota_inflight: Cell<bool>,
|
||||
pub(crate) quota_checked_at: Cell<Option<Instant>>,
|
||||
/// "Start on login" toggle. [`Self::settings_suppress`] guards programmatic
|
||||
/// sets so reflecting the systemd state doesn't fire the toggle handler.
|
||||
pub(crate) autostart_row: adw::SwitchRow,
|
||||
@@ -78,6 +86,10 @@ pub(crate) struct MainWidgets {
|
||||
pub(crate) mount_row: adw::ActionRow,
|
||||
/// Live upload/download progress, populated by the refresh loop.
|
||||
pub(crate) transfers_group: adw::PreferencesGroup,
|
||||
/// Account-quota group; hidden until `refresh_quota` gets a reading.
|
||||
pub(crate) quota_group: adw::PreferencesGroup,
|
||||
pub(crate) quota_bar: gtk4::ProgressBar,
|
||||
pub(crate) quota_label: gtk4::Label,
|
||||
pub(crate) cache_bar: gtk4::ProgressBar,
|
||||
pub(crate) cache_label: gtk4::Label,
|
||||
pub(crate) pins_group: adw::PreferencesGroup,
|
||||
@@ -111,6 +123,29 @@ pub(crate) fn build_main_page() -> (gtk4::Widget, MainWidgets) {
|
||||
account_row.add_suffix(&logout_button);
|
||||
account_group.add(&account_row);
|
||||
|
||||
// Account storage: the Proton account quota (used of total), distinct from
|
||||
// the local content cache below. A progress bar + "X of Y used" line, painted
|
||||
// by `refresh_quota`. Hidden until the first successful read so a cold start
|
||||
// (or an account the API can't report) shows nothing rather than an empty bar.
|
||||
let quota_group = adw::PreferencesGroup::builder()
|
||||
.title("Account storage")
|
||||
.description("Your Proton storage across all products.")
|
||||
.visible(false)
|
||||
.build();
|
||||
let quota_box = gtk4::Box::new(gtk4::Orientation::Vertical, 6);
|
||||
quota_box.set_margin_top(6);
|
||||
quota_box.set_margin_bottom(6);
|
||||
let quota_bar = gtk4::ProgressBar::new();
|
||||
let quota_label = gtk4::Label::builder().halign(gtk4::Align::Start).build();
|
||||
quota_label.add_css_class("dim-label");
|
||||
quota_box.append("a_bar);
|
||||
quota_box.append("a_label);
|
||||
let quota_row = adw::PreferencesRow::builder()
|
||||
.activatable(false)
|
||||
.child("a_box)
|
||||
.build();
|
||||
quota_group.add("a_row);
|
||||
|
||||
// Mount group: a read-only status line. The mount is managed automatically
|
||||
// by the systemd user service; there is no toggle to fiddle with.
|
||||
let mount_group = adw::PreferencesGroup::builder().title("Drive").build();
|
||||
@@ -219,6 +254,7 @@ pub(crate) fn build_main_page() -> (gtk4::Widget, MainWidgets) {
|
||||
inner.set_margin_start(12);
|
||||
inner.set_margin_end(12);
|
||||
inner.append(&account_group);
|
||||
inner.append("a_group);
|
||||
inner.append(&mount_group);
|
||||
inner.append(&transfers_group);
|
||||
inner.append(&storage_group);
|
||||
@@ -238,6 +274,9 @@ pub(crate) fn build_main_page() -> (gtk4::Widget, MainWidgets) {
|
||||
account_row,
|
||||
mount_row,
|
||||
transfers_group,
|
||||
quota_group,
|
||||
quota_bar,
|
||||
quota_label,
|
||||
cache_bar,
|
||||
cache_label,
|
||||
pins_group,
|
||||
@@ -463,12 +502,65 @@ pub(crate) fn refresh(ui: &Rc<Ui>) {
|
||||
// Both of these pages show work as it happens, so they follow the tick while
|
||||
// they are on screen. Every other page loads on navigation only.
|
||||
match ui.stack.visible_child_name().as_deref() {
|
||||
Some("main") => refresh_quota(ui),
|
||||
Some("devices") => refresh_sync_folders(ui),
|
||||
Some("activity") => refresh_activity(ui),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
/// How long a quota reading stays fresh. Account storage barely moves, so the
|
||||
/// Settings tick refetches it only this often rather than every 2s.
|
||||
const QUOTA_TTL: Duration = Duration::from_secs(60);
|
||||
|
||||
/// Fetch the account quota (if the last reading is stale) and paint the Account
|
||||
/// storage group. Runs only while Settings is on screen. The group stays hidden
|
||||
/// until a reading lands, so an account the API can't report — or a still-starting
|
||||
/// daemon — shows nothing rather than an empty bar. A failed fetch leaves the last
|
||||
/// good reading in place.
|
||||
pub(crate) fn refresh_quota(ui: &Rc<Ui>) {
|
||||
if ui.status.quota_inflight.get() {
|
||||
return;
|
||||
}
|
||||
if let Some(at) = ui.status.quota_checked_at.get()
|
||||
&& at.elapsed() < QUOTA_TTL
|
||||
{
|
||||
return;
|
||||
}
|
||||
ui.status.quota_inflight.set(true);
|
||||
let rx = spawn_request(ui.dirs.control_socket(), Request::AccountQuota);
|
||||
let ui = ui.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let result = rx.recv().await;
|
||||
ui.status.quota_inflight.set(false);
|
||||
if let Ok(Ok(Response::AccountQuota {
|
||||
max_space,
|
||||
used_space,
|
||||
})) = result
|
||||
{
|
||||
ui.status.quota_checked_at.set(Some(Instant::now()));
|
||||
let used = used_space.max(0) as u64;
|
||||
if max_space > 0 {
|
||||
let total = max_space as u64;
|
||||
let fraction = (used as f64 / total as f64).min(1.0);
|
||||
ui.status.quota_bar.set_fraction(fraction);
|
||||
let pct = (fraction * 100.0).round() as u64;
|
||||
ui.status.quota_label.set_text(&format!(
|
||||
"{} of {} used ({pct}%)",
|
||||
human_bytes(used),
|
||||
human_bytes(total)
|
||||
));
|
||||
} else {
|
||||
ui.status.quota_bar.set_fraction(0.0);
|
||||
ui.status
|
||||
.quota_label
|
||||
.set_text(&format!("{} used", human_bytes(used)));
|
||||
}
|
||||
ui.status.quota_group.set_visible(true);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Record the mount state seen by the last status poll: gate every control that
|
||||
/// needs a live daemon, and notify the desktop when the state actually flips.
|
||||
///
|
||||
|
||||
@@ -0,0 +1,166 @@
|
||||
//! The human-verification (CAPTCHA) dialog.
|
||||
//!
|
||||
//! Proton gates logins it does not recognise — a new IP, a VPN exit — behind a
|
||||
//! CAPTCHA. The API answers the login with a challenge instead of a session, and
|
||||
//! expects the client to present Proton's hosted verification page, collect the
|
||||
//! token the user earns by solving it, and retry the login carrying that token.
|
||||
//!
|
||||
//! The page is hosted in a `WebKitWebView` rather than handed to the system
|
||||
//! browser because it reports completion by posting a message to its host, not
|
||||
//! by redirecting: a browser has nowhere to post it back to.
|
||||
|
||||
use crate::*;
|
||||
use webkit6::prelude::*;
|
||||
|
||||
/// Bridge the verification page's `postMessage` to a handler this side can read.
|
||||
///
|
||||
/// The page targets its embedding host (`window.parent`), which in a webview is
|
||||
/// the page itself — so nothing arrives unless the message is forwarded
|
||||
/// explicitly. Injecting at document start guarantees the listener is installed
|
||||
/// before the page can post anything.
|
||||
const BRIDGE: &str = r#"
|
||||
window.addEventListener('message', function (event) {
|
||||
try {
|
||||
window.webkit.messageHandlers.hv.postMessage(JSON.stringify(event.data));
|
||||
} catch (e) {}
|
||||
});
|
||||
"#;
|
||||
|
||||
/// Present the challenge and hand the solved token back through `token_tx`.
|
||||
///
|
||||
/// Closing the dialog without solving drops the sender, which the waiting login
|
||||
/// worker reads as a cancelled sign-in — the same contract as the 2FA prompt.
|
||||
pub(crate) fn prompt_human_verification(
|
||||
ui: &Rc<Ui>,
|
||||
url: &str,
|
||||
token_tx: std::sync::mpsc::Sender<String>,
|
||||
) {
|
||||
let content = webkit6::UserContentManager::new();
|
||||
content.add_script(&webkit6::UserScript::new(
|
||||
BRIDGE,
|
||||
webkit6::UserContentInjectedFrames::AllFrames,
|
||||
webkit6::UserScriptInjectionTime::Start,
|
||||
&[],
|
||||
&[],
|
||||
));
|
||||
// Registration is what makes `messageHandlers.hv` exist in the page; without
|
||||
// it the bridge above throws on every message.
|
||||
content.register_script_message_handler("hv", None);
|
||||
|
||||
let webview = webkit6::WebView::builder()
|
||||
.user_content_manager(&content)
|
||||
.vexpand(true)
|
||||
.hexpand(true)
|
||||
.build();
|
||||
|
||||
let dialog = adw::Dialog::builder()
|
||||
.title("Verification")
|
||||
.content_width(420)
|
||||
.content_height(560)
|
||||
.build();
|
||||
|
||||
let header = adw::HeaderBar::new();
|
||||
let body = gtk4::Box::new(gtk4::Orientation::Vertical, 0);
|
||||
body.append(&header);
|
||||
body.append(&webview);
|
||||
dialog.set_child(Some(&body));
|
||||
|
||||
// Taken on the first success *or* on close, so the token is sent at most
|
||||
// once and a cancelled dialog always drops the sender.
|
||||
let token_tx = Rc::new(RefCell::new(Some(token_tx)));
|
||||
|
||||
let tx = token_tx.clone();
|
||||
let dlg_weak = dialog.downgrade();
|
||||
content.connect_script_message_received(Some("hv"), move |_, value| {
|
||||
let Some(token) = extract_token(&value.to_str()) else {
|
||||
// Every `postMessage` on the page reaches here, most of them the
|
||||
// verification app's own chatter. Anything that is not a completion
|
||||
// is simply not ours.
|
||||
return;
|
||||
};
|
||||
if let Some(tx) = tx.borrow_mut().take() {
|
||||
let _ = tx.send(token);
|
||||
}
|
||||
if let Some(dlg) = dlg_weak.upgrade() {
|
||||
dlg.close();
|
||||
}
|
||||
});
|
||||
|
||||
// Covers the close button, Escape, and the user giving up.
|
||||
dialog.connect_closed(move |_| {
|
||||
token_tx.borrow_mut().take();
|
||||
});
|
||||
|
||||
webview.load_uri(url);
|
||||
|
||||
let parent = ui.login.login_button.root().and_downcast::<gtk4::Window>();
|
||||
// Returns immediately; the login worker stays blocked on the channel until
|
||||
// the handler above sends, or the dialog closes and drops the sender.
|
||||
dialog.present(parent.as_ref());
|
||||
}
|
||||
|
||||
/// Pull the verification token out of a message posted by the verification page.
|
||||
///
|
||||
/// Returns `None` for anything that is not a completion message. The page posts
|
||||
/// a good deal besides — resize requests, readiness pings — and treating an
|
||||
/// unrecognised shape as success would hand the API an empty token and fail the
|
||||
/// login with a confusing error.
|
||||
fn extract_token(raw: &str) -> Option<String> {
|
||||
let mut value: serde_json::Value = serde_json::from_str(raw).ok()?;
|
||||
// If the message was stringified twice (e.g. raw is a double-quoted JSON string),
|
||||
// parse the inner string.
|
||||
if let Some(inner) = value.as_str()
|
||||
&& let Ok(parsed) = serde_json::from_str(inner)
|
||||
{
|
||||
value = parsed;
|
||||
}
|
||||
// The payload is nested under `payload` and the message names itself in
|
||||
// `type`; both spellings of the success type have shipped.
|
||||
let kind = value.get("type")?.as_str()?;
|
||||
if !matches!(
|
||||
kind,
|
||||
"HUMAN_VERIFICATION_SUCCESS" | "human_verification_success"
|
||||
) {
|
||||
return None;
|
||||
}
|
||||
let payload = value.get("payload")?;
|
||||
let token = payload.get("token")?.as_str()?;
|
||||
if token.is_empty() {
|
||||
return None;
|
||||
}
|
||||
Some(token.to_owned())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::extract_token;
|
||||
|
||||
#[test]
|
||||
fn a_completion_message_yields_its_token() {
|
||||
let raw =
|
||||
r#"{"type":"HUMAN_VERIFICATION_SUCCESS","payload":{"token":"tok-1","type":"captcha"}}"#;
|
||||
assert_eq!(extract_token(raw).as_deref(), Some("tok-1"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_double_serialized_completion_message_yields_its_token() {
|
||||
let raw = r#""{\"type\":\"HUMAN_VERIFICATION_SUCCESS\",\"payload\":{\"token\":\"tok-1\",\"type\":\"captcha\"}}""#;
|
||||
assert_eq!(extract_token(raw).as_deref(), Some("tok-1"));
|
||||
}
|
||||
|
||||
/// The page posts plenty that is not a completion; none of it may be
|
||||
/// mistaken for one, or the login retries with a garbage token.
|
||||
#[test]
|
||||
fn unrelated_messages_are_ignored() {
|
||||
for raw in [
|
||||
r#"{"type":"resize","payload":{"height":400}}"#,
|
||||
r#"{"type":"HUMAN_VERIFICATION_SUCCESS"}"#,
|
||||
r#"{"payload":{"token":"tok"}}"#,
|
||||
r#"{"type":"HUMAN_VERIFICATION_SUCCESS","payload":{"token":""}}"#,
|
||||
"not json at all",
|
||||
"",
|
||||
] {
|
||||
assert!(extract_token(raw).is_none(), "accepted: {raw}");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,11 +1,11 @@
|
||||
//! `pdfs-prompt` — the launcher: one search field over both Proton Drive and the
|
||||
//! files on this machine, styled after Google Drive's search overlay.
|
||||
//!
|
||||
//! Bind it to a system shortcut (e.g. in Hyprland) for a quick HUD search. It is
|
||||
//! a short-lived process: it must draw *now*, so nothing here blocks the main
|
||||
//! loop. Every daemon round-trip runs on a worker thread and lands back through
|
||||
//! an async channel; the two searches (Drive and local) are fired in parallel and
|
||||
//! each section renders as its own reply arrives.
|
||||
//! Bind it to a system shortcut (e.g. in Hyprland) for a quick HUD search. The
|
||||
//! application is single-instance and keeps its window alive between summons,
|
||||
//! so repeat activations only reset and present the existing widget tree. Every
|
||||
//! daemon round-trip runs on a worker thread and lands back through an async
|
||||
//! channel. Drive and local lookup share one request so a result set paints once.
|
||||
|
||||
use std::cell::{Cell, RefCell};
|
||||
use std::path::{Path, PathBuf};
|
||||
@@ -17,7 +17,12 @@ use adw::prelude::*;
|
||||
use gtk4::{gio, glib};
|
||||
|
||||
use pdfs_core::config::AppDirs;
|
||||
use pdfs_core::control::{LocalHit, Request, Response, SearchHit, send};
|
||||
use pdfs_core::control::{
|
||||
LocalHit, Request, Response, SearchFilters, SearchHit, SearchKind, SearchSource, send,
|
||||
};
|
||||
|
||||
mod activation;
|
||||
use activation::{DriveActivation, drive_activation, mounted_path};
|
||||
|
||||
const APP_ID: &str = "io.narl.proton-drive-linux-prompt";
|
||||
|
||||
@@ -60,6 +65,16 @@ impl Filter {
|
||||
Filter::Media => !is_dir && is_media(name),
|
||||
}
|
||||
}
|
||||
|
||||
fn search_kind(self) -> SearchKind {
|
||||
match self {
|
||||
Self::All => SearchKind::All,
|
||||
Self::Folders => SearchKind::Folders,
|
||||
Self::Documents => SearchKind::Documents,
|
||||
Self::Images => SearchKind::Images,
|
||||
Self::Media => SearchKind::Media,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn extension(name: &str) -> String {
|
||||
@@ -174,6 +189,13 @@ impl Hit {
|
||||
matches!(self, Hit::Drive(h) if h.pinned)
|
||||
}
|
||||
|
||||
fn score(&self) -> i64 {
|
||||
match self {
|
||||
Self::Drive(hit) => hit.score,
|
||||
Self::Local(hit) => hit.score,
|
||||
}
|
||||
}
|
||||
|
||||
/// Stable identity used to preserve the keyboard cursor across re-renders.
|
||||
/// The bool keeps a Drive and a local hit at the same path distinct.
|
||||
fn key(&self) -> (bool, String) {
|
||||
@@ -184,6 +206,15 @@ impl Hit {
|
||||
}
|
||||
}
|
||||
|
||||
fn rank_hits(hits: &mut [Hit]) {
|
||||
hits.sort_by(|a, b| {
|
||||
b.score()
|
||||
.cmp(&a.score())
|
||||
.then_with(|| a.name().cmp(b.name()))
|
||||
.then_with(|| a.key().cmp(&b.key()))
|
||||
});
|
||||
}
|
||||
|
||||
/// Everything the window needs to render and act, in one place so the many
|
||||
/// callbacks below capture a single `Rc` instead of a dozen clones each.
|
||||
struct Ui {
|
||||
@@ -195,6 +226,7 @@ struct Ui {
|
||||
stack: gtk4::Stack,
|
||||
scroller: gtk4::ScrolledWindow,
|
||||
results: gtk4::Box,
|
||||
search_section: Section,
|
||||
drive_section: Section,
|
||||
local_section: Section,
|
||||
placeholder: adw::StatusPage,
|
||||
@@ -217,8 +249,7 @@ struct Ui {
|
||||
/// Monotonic query id. A reply whose id is stale (the user typed again while
|
||||
/// it was in flight) is dropped instead of overwriting fresher results.
|
||||
query_id: Cell<u64>,
|
||||
/// In-flight searches for the current query id, so the spinner stops only
|
||||
/// once both sections have answered.
|
||||
/// In-flight requests for the current query id.
|
||||
pending: Cell<u8>,
|
||||
/// True once a Drive open is running: the window is about to close, so
|
||||
/// further input is ignored.
|
||||
@@ -229,6 +260,10 @@ struct Ui {
|
||||
/// against the selected row once the fresh results settle, rather than being
|
||||
/// dropped — so a plain "type, Enter" always opens something.
|
||||
open_pending: Cell<bool>,
|
||||
/// Prevent lifecycle-driven entry resets from also scheduling the normal
|
||||
/// debounced empty-query request; activation performs one explicit daemon
|
||||
/// bootstrap instead.
|
||||
suppress_entry_change: Cell<bool>,
|
||||
/// The window, so a deferred open (above) can reach it from `render`.
|
||||
window: RefCell<Option<adw::ApplicationWindow>>,
|
||||
}
|
||||
@@ -301,17 +336,33 @@ fn main() -> glib::ExitCode {
|
||||
.init();
|
||||
|
||||
let app = adw::Application::builder().application_id(APP_ID).build();
|
||||
// GtkApplication normally remains active while it owns a window, including
|
||||
// when that window is hidden. Hold it explicitly as well: residency is a
|
||||
// product requirement here, not an incidental window-lifetime side effect.
|
||||
let _resident = app.hold();
|
||||
app.connect_startup(|_| load_css());
|
||||
app.connect_activate(build_window);
|
||||
let prompt: Rc<RefCell<Option<Rc<Ui>>>> = Rc::new(RefCell::new(None));
|
||||
app.connect_activate(move |app| {
|
||||
let ui = if let Some(ui) = prompt.borrow().clone() {
|
||||
ui
|
||||
} else {
|
||||
let Some(ui) = build_window(app) else {
|
||||
return;
|
||||
};
|
||||
*prompt.borrow_mut() = Some(ui.clone());
|
||||
ui
|
||||
};
|
||||
ui.activate();
|
||||
});
|
||||
app.run()
|
||||
}
|
||||
|
||||
fn build_window(app: &adw::Application) {
|
||||
fn build_window(app: &adw::Application) -> Option<Rc<Ui>> {
|
||||
let dirs = match AppDirs::new() {
|
||||
Ok(d) => d,
|
||||
Err(e) => {
|
||||
tracing::error!("cannot resolve app dirs: {e}");
|
||||
return;
|
||||
return None;
|
||||
}
|
||||
};
|
||||
|
||||
@@ -362,8 +413,10 @@ fn build_window(app: &adw::Application) {
|
||||
let results = gtk4::Box::new(gtk4::Orientation::Vertical, 0);
|
||||
results.add_css_class("results");
|
||||
|
||||
let search_section = Section::new("Best matches", "system-search-symbolic");
|
||||
let drive_section = Section::new("Proton Drive", "folder-remote-symbolic");
|
||||
let local_section = Section::new("This computer", "drive-harddisk-symbolic");
|
||||
search_section.attach(&results);
|
||||
drive_section.attach(&results);
|
||||
local_section.attach(&results);
|
||||
|
||||
@@ -430,6 +483,7 @@ fn build_window(app: &adw::Application) {
|
||||
stack,
|
||||
scroller,
|
||||
results,
|
||||
search_section,
|
||||
drive_section,
|
||||
local_section,
|
||||
placeholder,
|
||||
@@ -446,6 +500,7 @@ fn build_window(app: &adw::Application) {
|
||||
opening: Cell::new(false),
|
||||
indexing: Cell::new(false),
|
||||
open_pending: Cell::new(false),
|
||||
suppress_entry_change: Cell::new(false),
|
||||
window: RefCell::new(None),
|
||||
});
|
||||
*ui.window.borrow_mut() = Some(window.clone());
|
||||
@@ -477,15 +532,17 @@ fn build_window(app: &adw::Application) {
|
||||
(&ui.local_section.list, true),
|
||||
] {
|
||||
let ui_row = ui.clone();
|
||||
let window_row = window.clone();
|
||||
list.connect_row_activated(move |_, row| {
|
||||
let offset = if is_local { ui_row.drive_count() } else { 0 };
|
||||
ui_row.open(offset + row.index() as usize, &window_row);
|
||||
ui_row.open(offset + row.index() as usize);
|
||||
});
|
||||
}
|
||||
let ui_row = ui.clone();
|
||||
ui.search_section
|
||||
.list
|
||||
.connect_row_activated(move |_, row| ui_row.open(row.index() as usize));
|
||||
|
||||
let ui_key = ui.clone();
|
||||
let window_key = window.clone();
|
||||
let keys = gtk4::EventControllerKey::new();
|
||||
keys.connect_key_pressed(move |_, key, _, state| {
|
||||
if ui_key.opening.get() {
|
||||
@@ -496,7 +553,7 @@ fn build_window(app: &adw::Application) {
|
||||
// Spotlight-style: first Escape clears a non-empty query, a
|
||||
// second (or an already-empty box) dismisses the launcher.
|
||||
if ui_key.entry.text().is_empty() {
|
||||
window_key.close();
|
||||
ui_key.dismiss();
|
||||
} else {
|
||||
ui_key.entry.set_text("");
|
||||
}
|
||||
@@ -515,12 +572,10 @@ fn build_window(app: &adw::Application) {
|
||||
ui_key.cycle_filter(back);
|
||||
glib::Propagation::Stop
|
||||
}
|
||||
gtk4::gdk::Key::Return | gtk4::gdk::Key::KP_Enter => {
|
||||
// Fall back to the top row when nothing is explicitly selected
|
||||
// (e.g. results haven't rendered yet); `open` guards the rest.
|
||||
ui_key.open(ui_key.cursor.get().unwrap_or(0), &window_key);
|
||||
glib::Propagation::Stop
|
||||
}
|
||||
// Return is deliberately absent: `GtkText` binds it to `activate`
|
||||
// and consumes it, so a bubble-phase controller on the window never
|
||||
// sees it while the entry has focus (which is always, here). It is
|
||||
// handled on the entry's `activate` signal instead — see below.
|
||||
_ => glib::Propagation::Proceed,
|
||||
}
|
||||
});
|
||||
@@ -528,9 +583,47 @@ fn build_window(app: &adw::Application) {
|
||||
// pointer has moved focus into it.
|
||||
window.add_controller(keys);
|
||||
|
||||
// Enter opens the row under the cursor. This lives on the entry rather than
|
||||
// with the other keys on the window because `GtkText` claims Return for its
|
||||
// own `activate` binding, so a bubble-phase controller upstream of the
|
||||
// focused entry is never reached. Enter with focus in the list is covered by
|
||||
// `row_activated` above.
|
||||
let ui_activate = ui.clone();
|
||||
entry.connect_activate(move |_| {
|
||||
if ui_activate.opening.get() {
|
||||
return;
|
||||
}
|
||||
// Fall back to the top row when nothing is explicitly selected (e.g.
|
||||
// results haven't rendered yet); `open` guards the rest.
|
||||
ui_activate.open(ui_activate.cursor.get().unwrap_or(0));
|
||||
});
|
||||
|
||||
// Some GTK/input-method combinations consume the physical Return binding in
|
||||
// GtkText without emitting Entry::activate. Capture only Return ahead of the
|
||||
// text widget and leave every other key to normal GTK/IME handling. Stopping
|
||||
// propagation also prevents the activate signal above from opening twice;
|
||||
// that signal remains the programmatic/accessibility activation path.
|
||||
let ui_return = ui.clone();
|
||||
let return_key = gtk4::EventControllerKey::new();
|
||||
return_key.set_propagation_phase(gtk4::PropagationPhase::Capture);
|
||||
return_key.connect_key_pressed(move |_, key, _, _| {
|
||||
if matches!(key, gtk4::gdk::Key::Return | gtk4::gdk::Key::KP_Enter) {
|
||||
if !ui_return.opening.get() {
|
||||
ui_return.open(ui_return.cursor.get().unwrap_or(0));
|
||||
}
|
||||
glib::Propagation::Stop
|
||||
} else {
|
||||
glib::Propagation::Proceed
|
||||
}
|
||||
});
|
||||
entry.add_controller(return_key);
|
||||
|
||||
let debounce: Rc<RefCell<Option<glib::SourceId>>> = Rc::new(RefCell::new(None));
|
||||
let ui_changed = ui.clone();
|
||||
entry.connect_changed(move |entry| {
|
||||
if ui_changed.suppress_entry_change.get() {
|
||||
return;
|
||||
}
|
||||
// A fresh keystroke supersedes any Enter that was waiting on results:
|
||||
// the user is still refining the query, not asking to open yet.
|
||||
ui_changed.open_pending.set(false);
|
||||
@@ -550,22 +643,59 @@ fn build_window(app: &adw::Application) {
|
||||
let ui_retry = ui.clone();
|
||||
retry.connect_clicked(move |_| ui_retry.connect());
|
||||
|
||||
// A launcher is modal by convention: losing focus dismisses it.
|
||||
window.connect_is_active_notify(|w| {
|
||||
if !w.is_active() {
|
||||
w.close();
|
||||
}
|
||||
// Keep the widget tree alive when the compositor asks the window to close.
|
||||
// This also avoids running GTK's destruction path while async replies still
|
||||
// hold references to prompt widgets.
|
||||
let ui_close = ui.clone();
|
||||
window.connect_close_request(move |_| {
|
||||
ui_close.dismiss();
|
||||
glib::Propagation::Stop
|
||||
});
|
||||
let entry_map = entry.clone();
|
||||
window.connect_map(move |_| {
|
||||
entry_map.grab_focus();
|
||||
});
|
||||
|
||||
ui.connect();
|
||||
window.present();
|
||||
Some(ui)
|
||||
}
|
||||
|
||||
impl Ui {
|
||||
/// Reset and present the resident prompt in response to GApplication
|
||||
/// activation. A second invocation while a file is materialising merely
|
||||
/// raises the progress window; it must not make the in-flight open mutable.
|
||||
fn activate(self: &Rc<Self>) {
|
||||
let Some(window) = self.window.borrow().clone() else {
|
||||
return;
|
||||
};
|
||||
if !self.opening.get() {
|
||||
// Supersede replies from the previous showing before clearing the
|
||||
// query. The daemon work may finish, but it can no longer repaint
|
||||
// the newly activated prompt with stale rows.
|
||||
self.query_id.set(self.query_id.get() + 1);
|
||||
self.pending.set(0);
|
||||
self.open_pending.set(false);
|
||||
self.spinner.stop();
|
||||
self.spinner.set_visible(false);
|
||||
self.suppress_entry_change.set(true);
|
||||
self.entry.set_text("");
|
||||
self.suppress_entry_change.set(false);
|
||||
self.set_filter(Filter::All);
|
||||
self.connect();
|
||||
}
|
||||
window.present();
|
||||
self.entry.grab_focus();
|
||||
}
|
||||
|
||||
/// Dismiss without destroying the application window. GTK continues to
|
||||
/// associate the hidden window with the single application instance, so a
|
||||
/// later desktop shortcut invocation is a cheap `activate` round-trip.
|
||||
fn dismiss(&self) {
|
||||
self.open_pending.set(false);
|
||||
if let Some(window) = self.window.borrow().as_ref() {
|
||||
window.set_visible(false);
|
||||
}
|
||||
}
|
||||
|
||||
/// Ask the daemon for status and, if it answers, load the suggested (pinned)
|
||||
/// files. Runs off-thread: a dead daemon must not freeze the first frame.
|
||||
fn connect(self: &Rc<Self>) {
|
||||
@@ -626,6 +756,8 @@ impl Ui {
|
||||
modified: 0,
|
||||
pinned: true,
|
||||
uid: pin.uid,
|
||||
mounted_path: None,
|
||||
score: 0,
|
||||
})
|
||||
.collect(),
|
||||
_ => Vec::new(),
|
||||
@@ -636,32 +768,41 @@ impl Ui {
|
||||
});
|
||||
}
|
||||
|
||||
/// Fire both searches for `query` in parallel. An empty query falls back to
|
||||
/// the suggestions view.
|
||||
/// Search Drive and local metadata in one daemon round-trip. An empty query
|
||||
/// falls back to the suggestions view.
|
||||
fn search(self: &Rc<Self>, query: &str) {
|
||||
if query.is_empty() {
|
||||
self.load_suggestions();
|
||||
return;
|
||||
}
|
||||
|
||||
let id = self.begin_query(2);
|
||||
|
||||
let drive = spawn_request(
|
||||
let id = self.begin_query(1);
|
||||
let search = spawn_request(
|
||||
self.socket.clone(),
|
||||
Request::Search {
|
||||
Request::SearchV2 {
|
||||
query: query.to_string(),
|
||||
limit: SEARCH_LIMIT,
|
||||
filters: SearchFilters {
|
||||
sources: vec![SearchSource::Drive, SearchSource::Local],
|
||||
kind: self.filter.get().search_kind(),
|
||||
},
|
||||
},
|
||||
);
|
||||
let ui = self.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let reply = drive.recv().await;
|
||||
let reply = search.recv().await;
|
||||
if !ui.finish_query(id) {
|
||||
return;
|
||||
}
|
||||
match reply {
|
||||
Ok(Ok(Response::SearchResults { hits })) => {
|
||||
*ui.drive_hits.borrow_mut() = hits;
|
||||
Ok(Ok(Response::SearchResultsV2 {
|
||||
drive_hits,
|
||||
local_hits,
|
||||
local_indexing,
|
||||
})) => {
|
||||
*ui.drive_hits.borrow_mut() = drive_hits;
|
||||
*ui.local_hits.borrow_mut() = local_hits;
|
||||
ui.indexing.set(local_indexing);
|
||||
ui.render();
|
||||
}
|
||||
// Transport failure: the daemon is gone. Don't paint "No
|
||||
@@ -669,32 +810,6 @@ impl Ui {
|
||||
Ok(Err(_)) | Err(_) => ui.go_offline(),
|
||||
_ => {
|
||||
ui.drive_hits.borrow_mut().clear();
|
||||
ui.render();
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
let local = spawn_request(
|
||||
self.socket.clone(),
|
||||
Request::SearchLocal {
|
||||
query: query.to_string(),
|
||||
limit: SEARCH_LIMIT,
|
||||
},
|
||||
);
|
||||
let ui = self.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let reply = local.recv().await;
|
||||
if !ui.finish_query(id) {
|
||||
return;
|
||||
}
|
||||
match reply {
|
||||
Ok(Ok(Response::LocalResults { hits, indexing })) => {
|
||||
ui.indexing.set(indexing);
|
||||
*ui.local_hits.borrow_mut() = hits;
|
||||
ui.render();
|
||||
}
|
||||
Ok(Err(_)) | Err(_) => ui.go_offline(),
|
||||
_ => {
|
||||
ui.local_hits.borrow_mut().clear();
|
||||
ui.render();
|
||||
}
|
||||
@@ -737,7 +852,12 @@ impl Ui {
|
||||
for (chip_filter, chip) in self.chips.borrow().iter() {
|
||||
chip.set_active(*chip_filter == filter);
|
||||
}
|
||||
self.render();
|
||||
let query = self.entry.text().trim().to_string();
|
||||
if query.is_empty() {
|
||||
self.render();
|
||||
} else {
|
||||
self.search(&query);
|
||||
}
|
||||
}
|
||||
|
||||
fn cycle_filter(self: &Rc<Self>, backwards: bool) {
|
||||
@@ -762,9 +882,8 @@ impl Ui {
|
||||
.count()
|
||||
}
|
||||
|
||||
/// Rebuild both sections from the last replies under the active chip, then
|
||||
/// restore the cursor to the top. Every state change funnels through here, so
|
||||
/// the list, the placeholder, and the footer can never disagree.
|
||||
/// Rebuild suggestions or the globally-ranked search section, preserving the
|
||||
/// selected identity when a result survives the update.
|
||||
fn render(self: &Rc<Self>) {
|
||||
let filter = self.filter.get();
|
||||
|
||||
@@ -794,17 +913,24 @@ impl Ui {
|
||||
|
||||
let query = self.entry.text().trim().to_string();
|
||||
let searching = !query.is_empty();
|
||||
let drive_title = if searching {
|
||||
"Proton Drive"
|
||||
} else {
|
||||
"Pinned in Proton Drive"
|
||||
};
|
||||
self.drive_section.set_rows(&drive, Some(drive_title));
|
||||
self.local_section.set_rows(&local, None);
|
||||
|
||||
let total = drive.len() + local.len();
|
||||
let mut visible = drive;
|
||||
visible.extend(local);
|
||||
if searching {
|
||||
rank_hits(&mut visible);
|
||||
self.search_section.set_rows(&visible, Some("Best matches"));
|
||||
self.drive_section.set_rows(&[], None);
|
||||
self.local_section.set_rows(&[], None);
|
||||
} else {
|
||||
self.search_section.set_rows(&[], None);
|
||||
let drive_count = visible
|
||||
.iter()
|
||||
.take_while(|hit| matches!(hit, Hit::Drive(_)))
|
||||
.count();
|
||||
self.drive_section
|
||||
.set_rows(&visible[..drive_count], Some("Pinned in Proton Drive"));
|
||||
self.local_section.set_rows(&visible[drive_count..], None);
|
||||
}
|
||||
|
||||
// Find where the previously-selected row landed in the rebuilt list.
|
||||
let restored = selected_key.and_then(|key| visible.iter().position(|hit| hit.key() == key));
|
||||
@@ -840,8 +966,8 @@ impl Ui {
|
||||
// so it lands on the final list, not a half-populated one.
|
||||
if self.open_pending.get() && self.pending.get() == 0 {
|
||||
self.open_pending.set(false);
|
||||
if let (Some(index), Some(window)) = (self.cursor.get(), self.window.borrow().clone()) {
|
||||
self.open(index, &window);
|
||||
if let Some(index) = self.cursor.get() {
|
||||
self.open(index);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -878,6 +1004,19 @@ impl Ui {
|
||||
/// section owns it, clear the other section's selection, and scroll it into
|
||||
/// view. Focus stays in the entry so typing never breaks.
|
||||
fn select(self: &Rc<Self>, index: usize) {
|
||||
if !self.rendered_query.borrow().is_empty() {
|
||||
self.drive_section.list.unselect_all();
|
||||
self.local_section.list.unselect_all();
|
||||
let Some(row) = self.search_section.list.row_at_index(index as i32) else {
|
||||
return;
|
||||
};
|
||||
self.search_section.list.select_row(Some(&row));
|
||||
self.cursor.set(Some(index));
|
||||
self.scroll_into_view(&row);
|
||||
return;
|
||||
}
|
||||
|
||||
self.search_section.list.unselect_all();
|
||||
let drive_count = self.drive_count();
|
||||
let (list, other, local_index) = if index < drive_count {
|
||||
(
|
||||
@@ -924,7 +1063,7 @@ impl Ui {
|
||||
/// straight to the desktop; a Drive hit must first be hydrated into the cache
|
||||
/// by the daemon (`OpenFile`), which can take a moment — the window stays up,
|
||||
/// with the spinner running, until the path comes back.
|
||||
fn open(self: &Rc<Self>, index: usize, window: &adw::ApplicationWindow) {
|
||||
fn open(self: &Rc<Self>, index: usize) {
|
||||
if self.opening.get() {
|
||||
return;
|
||||
}
|
||||
@@ -943,15 +1082,36 @@ impl Ui {
|
||||
match hit {
|
||||
Hit::Local(local) => {
|
||||
xdg_open(Path::new(&local.path));
|
||||
window.close();
|
||||
}
|
||||
// A Drive folder exists in the mount — open it in the file manager
|
||||
// rather than downloading anything.
|
||||
Hit::Drive(drive) if drive.is_dir => {
|
||||
xdg_open(&self.mountpoint.borrow().join(&drive.path));
|
||||
window.close();
|
||||
self.dismiss();
|
||||
}
|
||||
Hit::Drive(drive) => {
|
||||
// Empty-query rows come from ListPins, whose `recursive` flag is
|
||||
// pin policy rather than reliable node kind metadata. Every pin
|
||||
// already has a mounted path, so activate that path directly;
|
||||
// this handles non-recursively pinned folders without mistaking
|
||||
// them for files and sending an invalid OpenFile request.
|
||||
if self.rendered_query.borrow().is_empty() {
|
||||
let path = drive.mounted_path.as_deref().map_or_else(
|
||||
|| mounted_path(&self.mountpoint.borrow(), &drive.path),
|
||||
PathBuf::from,
|
||||
);
|
||||
xdg_open(&path);
|
||||
self.dismiss();
|
||||
return;
|
||||
}
|
||||
match drive_activation(&drive.name, drive.is_dir) {
|
||||
DriveActivation::Folder | DriveActivation::MountedMedia => {
|
||||
let path = drive.mounted_path.as_deref().map_or_else(
|
||||
|| mounted_path(&self.mountpoint.borrow(), &drive.path),
|
||||
PathBuf::from,
|
||||
);
|
||||
xdg_open(&path);
|
||||
self.dismiss();
|
||||
return;
|
||||
}
|
||||
DriveActivation::Materialize => {}
|
||||
}
|
||||
|
||||
self.opening.set(true);
|
||||
self.spinner.set_visible(true);
|
||||
self.spinner.start();
|
||||
@@ -964,7 +1124,6 @@ impl Ui {
|
||||
},
|
||||
);
|
||||
let ui = self.clone();
|
||||
let window = window.clone();
|
||||
glib::spawn_future_local(async move {
|
||||
let reply = rx.recv().await;
|
||||
ui.spinner.stop();
|
||||
@@ -973,7 +1132,7 @@ impl Ui {
|
||||
match reply {
|
||||
Ok(Ok(Response::FilePath { path })) => {
|
||||
xdg_open(Path::new(&path));
|
||||
window.close();
|
||||
ui.dismiss();
|
||||
}
|
||||
Ok(Ok(Response::Error { message, .. })) => {
|
||||
ui.hint.set_label(&format!("Could not open: {message}"));
|
||||
@@ -1274,3 +1433,37 @@ fn load_css() {
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn ranked_hits_merge_sources_on_one_score_scale() {
|
||||
let mut hits = vec![
|
||||
Hit::Drive(SearchHit {
|
||||
name: "alpha.pdf".into(),
|
||||
path: "Drive/alpha.pdf".into(),
|
||||
is_dir: false,
|
||||
size: 1,
|
||||
modified: 1,
|
||||
pinned: false,
|
||||
uid: "v~a".into(),
|
||||
mounted_path: None,
|
||||
score: 100,
|
||||
}),
|
||||
Hit::Local(LocalHit {
|
||||
name: "better.pdf".into(),
|
||||
path: "/home/me/better.pdf".into(),
|
||||
is_dir: false,
|
||||
size: 1,
|
||||
modified: 1,
|
||||
score: 300,
|
||||
}),
|
||||
];
|
||||
|
||||
rank_hits(&mut hits);
|
||||
assert!(matches!(&hits[0], Hit::Local(hit) if hit.name == "better.pdf"));
|
||||
assert!(matches!(&hits[1], Hit::Drive(hit) if hit.name == "alpha.pdf"));
|
||||
}
|
||||
}
|
||||
@@ -30,10 +30,10 @@ graph TD
|
||||
|
||||
| Crate | Primary Role | Key Components | State Management |
|
||||
|---|---|---|---|
|
||||
| [`pdfs-core`](file:///home/narl/dev/private/proton-drive-linux/crates/pdfs-core) | Core Infrastructure & Services | Cache Bookkeeping, Database migrations/schemas, IPC protocol payloads. | Holds the unified SQLite DB (`Db`) connection and the on-disk cache metadata (`ContentCache`). |
|
||||
| [`pdfs-fuse`](file:///home/narl/dev/private/proton-drive-linux/crates/pdfs-fuse) | VFS Layer & Reconciliation | FUSE callbacks, background upload queue (`drain`), two-way sync runner. | Manages in-memory inode maps (`State`), active descriptors (`WriteHandle`), and background task threads. |
|
||||
| [`pdfs-cli`](file:///home/narl/dev/private/proton-drive-linux/crates/pdfs-cli) | Command Line Interface | Command routing, daemon launcher, IPC client wrapper. | Stateless; communicates with daemon over IPC control socket. |
|
||||
| [`pdfs-gui`](file:///home/narl/dev/private/proton-drive-linux/crates/pdfs-gui) | Graphical Interface | GTK Page timelines (Files, Photos, Shares, Status). | Stateless; polls daemon for status and lists timelines via IPC socket. |
|
||||
| [`pdfs-core`](../crates/pdfs-core) | Core Infrastructure & Services | Cache bookkeeping, database migrations/schemas, IPC protocol payloads, and shared search relevance scoring. | Holds the unified SQLite DB (`Db`) connection and the on-disk cache metadata (`ContentCache`). |
|
||||
| [`pdfs-fuse`](../crates/pdfs-fuse) | VFS Layer & Reconciliation | FUSE callbacks, background upload queue (`drain`), two-way sync runner. | Manages in-memory inode maps (`State`), active descriptors (`WriteHandle`), and background task threads. |
|
||||
| [`pdfs-cli`](../crates/pdfs-cli) | Command Line Interface | Command routing, daemon launcher, IPC client wrapper. | Stateless; communicates with daemon over IPC control socket. |
|
||||
| [`pdfs-gui`](../crates/pdfs-gui) | Graphical Interface | GTK pages, tray, and the resident quick-search prompt. | Keeps UI state only; all durable state and Drive access remain behind the IPC socket. |
|
||||
|
||||
---
|
||||
|
||||
@@ -127,9 +127,9 @@ Because Proton Drive does not support partial byte writes, modified files must b
|
||||
1. **Staging writes (`WriteHandle`):** Writes are stored locally in a `scratch` file. The daemon tracks modified regions using `Intervals` (which holds ranges of edited bytes).
|
||||
2. **Close/Release (`queue_revision`):** When the application closes the file descriptor, the daemon:
|
||||
- Fetches any untouched gaps from the remote base file to compile the full file.
|
||||
- Moves the scratch file to `staging` under a `{uid}-{millis}-{counter}` name, so a staged blob can be tied back to its node without consulting the database.
|
||||
- Queues a pending database operation (`PendingOp`).
|
||||
3. **Async Drain Thread (`run_pending_drain`):** The background drain worker picks up the database operations queue, handles revisions uploads, resolves conflicts, and cleans up staging files.
|
||||
- Durably publishes the scratch data and authored-range sidecar into `staging` under a `{uid}-{millis}-{counter}` name. Temporary data and metadata are synced before atomic rename, and their directory is synced before the source is removed.
|
||||
- Transactionally queues or supersedes a pending database operation (`PendingOp`), so insertion failure cannot erase the previously acknowledged upload. For `OP_REVISION` ops, execution is debounced by 2 seconds (`DRAIN_REVISION_DEBOUNCE = 2s`) to give rapid follow-up writes (e.g. `aria2c` preallocation followed by writing) time to supersede the staged blob before network transmission.
|
||||
3. **Async Drain Thread (`run_pending_drain`):** The background drain worker picks up the database operations queue, handles revision uploads, resolves conflicts, and cleans up staging files. Upon landing a revision upload (`refresh_after_upload`), it rebaselines both still-queued ops (`rebaseline_pending`) and open write handles targeting the same node to prevent false self-conflict copies on subsequent writes.
|
||||
|
||||
```mermaid
|
||||
sequenceDiagram
|
||||
@@ -170,7 +170,7 @@ sequenceDiagram
|
||||
The sync engine handles offline-capable, bidirectional synchronization between the local disk and Proton Drive for directories marked in `mirror` mode.
|
||||
|
||||
### Lifecycle of a Sync Pass
|
||||
1. **Walk Local:** Walks the local directory tree recursively, scanning sizes and modification times.
|
||||
1. **Walk Local:** Walks the local directory tree recursively, scanning sizes and modification times while carrying a completeness result. A `readdir`, metadata, permission, or transient I/O failure makes the pass non-destructive instead of turning omitted paths into deletions.
|
||||
2. **Walk Remote:** Walks the remote database representation. If remote file modification times are updated, it calls the API to decrypt their sizes.
|
||||
3. **Load Baseline:** Loads the `sync_entry` database table, which contains the snapshot of both sides during the *last successful sync*.
|
||||
4. **Permutation Diffing:** The loop compares the three states (`local`, `remote`, `baseline`) to classify items:
|
||||
@@ -192,7 +192,7 @@ graph TD
|
||||
```
|
||||
|
||||
5. **Depth-Ascending Batching:** Folders are processed first to ensure hierarchies exist before files are placed. Work is executed concurrently up to a set limit.
|
||||
6. **Post-Sync Settle:** On success, baseline entries are upserted, timestamps updated, and any pending mode switches (e.g. going on-demand) are evaluated.
|
||||
6. **Safety Gate and Settle:** Destructive plans are rejected when the scan is incomplete. Total-wipe protection applies to every non-empty baseline, including a single-entry folder. On success, baseline entries are upserted, timestamps updated, and any pending mode switches (e.g. going on-demand) are evaluated. Failed local deletion or conflict preservation retains the previous baseline and prevents remote content from overwriting the local source.
|
||||
|
||||
---
|
||||
|
||||
@@ -202,11 +202,18 @@ The CLI and GUI front-ends do not access database files or make network calls di
|
||||
|
||||
* **Transport:** IPC over Unix Stream Socket.
|
||||
* **Framing:** Line-delimited JSON payloads.
|
||||
* **Resource limits:** Requests are limited to 1 MiB, must end with a newline, and must arrive within 10 seconds. At most 64 connection handlers are active at once.
|
||||
* **Control Protocol:**
|
||||
* Client sends a single JSON line (`Request`).
|
||||
* Daemon parses, handles the request, and replies with a single JSON line (`Response`).
|
||||
* Timeout durations are separated: **2 seconds** for writes (avoids hangs on defunct sockets) and **120 seconds** for reads (accommodates heavy transfers).
|
||||
|
||||
### Unified Search
|
||||
|
||||
`SearchV2` is the shared search boundary for the resident prompt. One request carries the query, result limit, requested sources (`Drive`, `Local`), and content kind. The daemon queries Drive metadata and the local home-directory index, then applies [`pdfs_core::search::relevance_score`](../crates/pdfs-core/src/search.rs) to both result sets. Exact and prefix matches rank above substring, abbreviation, and bounded typo matches; all query terms must match either the basename or parent path. Returning scores on one scale lets the GUI merge both sources into a deterministic **Best matches** list.
|
||||
|
||||
The prompt is a single-instance GTK application. It retains and hides its window between activations, resets its query state when summoned, and ignores stale asynchronous replies. Folder and streamable audio/video results open through the FUSE mount so applications can issue range reads; ordinary Drive files use the daemon's materialize-then-open path.
|
||||
|
||||
---
|
||||
|
||||
## 7. Subsystem Interaction & Thread Map
|
||||
@@ -215,9 +222,10 @@ The background daemon relies on the following thread topology:
|
||||
|
||||
1. **Main Thread / Dispatch Loop:** Blocks on `fuser::Session` loop. Reads kernel FUSE events and hands off network-bound VFS work to the FUSE workers pool.
|
||||
2. **FUSE Workers Pool (11 threads, two lanes):** Bounded thread pool handling network operations. Split into 3 threads reserved for metadata (`lookup`, `readdir`) and 8 general threads that serve transfers (block reads) and fall back to metadata when no transfer is waiting. Reserved threads never accept a transfer — that is what keeps a directory listing from queuing behind saturated downloads (audit A6).
|
||||
3. **IPC listener Thread:** Listens on Unix socket connections, spawning a lightweight task per connection to serve front-end status/configuration requests.
|
||||
3. **IPC listener Thread:** Listens on the Unix socket and admits at most 64 concurrent, timeout-bound handlers for front-end status/configuration requests.
|
||||
4. **Sync Engine Loop Thread:** Serializes sync runs. Wakes on debounced local inotify filesystem changes, remote polling intervals, or manual user requests.
|
||||
5. **Drain Queue Worker Thread:** Processes staged writes (`PendingOp`) sequentially, uploading revisions and retrying with exponential backoff on failures.
|
||||
6. **Conflict Sweep Thread (`pdfs-conflict-sweep`, optional):** Reconciles leftover `(sync-conflict …)` copies — 30 s warmup, then one pass every 5 minutes. A copy proven identical to its live sibling (equal size **and** equal `content_sha1`) is redundant; anything it cannot prove identical is surfaced to the activity feed and left alone. Governed by `AppConfig.conflict_sweep` / `PDFS_CONFLICT_SWEEP` (`SweepMode`): **report-only by default**, `off` skips the thread entirely, and only `enforce` lets it trash. Because it deletes, the enforcing path re-verifies revision id, size, digest, name, parent, queued ops and open handles immediately before acting rather than trusting its own pass-start snapshot. See `docs/BUGS.md` B69 and B71.
|
||||
|
||||
---
|
||||
|
||||
@@ -261,13 +269,13 @@ Two exposures this client does **not** currently mitigate, stated plainly rather
|
||||
- **Swap.** Content keys, session keys, and decrypted buffers live in ordinary heap memory. Nothing calls `mlock(2)`, so under memory pressure they may be paged out. Raising `LimitMEMLOCK` in the systemd unit would *not* change this — there is no locking to permit. The effective mitigation is encrypted swap (dm-crypt / `systemd-cryptsetup`), which is standard on a LUKS install.
|
||||
- **Kernel page cache.** Plaintext returned through FUSE is cached by the kernel like any other file data, and is likewise swappable. Defeating this would mean `direct_io` on every read, forfeiting the readahead and caching that make the mount usable. The trade is taken deliberately in favour of performance.
|
||||
|
||||
### 8.5 File modes: currently inherited, not enforced
|
||||
### 8.5 Enforced ownership and file modes
|
||||
|
||||
**The daemon does not set restrictive permissions on anything it creates.** Cache and state directories come from `create_dir_all`, and `control.sock` from a plain `UnixListener::bind` — all subject to the process umask, which on a typical desktop yields `0755` directories and a `0755` socket.
|
||||
On every start, `AppDirs::ensure` verifies that the state, cache, and configuration paths are real directories owned by the effective user, rejects symlink substitution or the wrong owner, and enforces mode `0700`. Both Unix sockets are changed to `0600` immediately after binding; failure is fatal rather than falling back to an unguarded daemon.
|
||||
|
||||
What protects them today is the mode of the XDG parents (`~/.cache`, `~/.local/state`), which are conventionally `0700` — but that is a property of the user's system, not something this client establishes or verifies. On a machine where the home directory is group- or world-traversable, the consequences differ by artifact:
|
||||
These checks protect the artifacts even when the surrounding home or XDG parent is traversable:
|
||||
|
||||
| Artifact | Exposure if the parent is traversable |
|
||||
| Artifact | Why access is restricted |
|
||||
|---|---|
|
||||
| `content/` | Another local user can read cached plaintext file content |
|
||||
| `cache.db` | Another local user can read the full decrypted name/structure index |
|
||||
@@ -275,12 +283,71 @@ What protects them today is the mode of the XDG parents (`~/.cache`, `~/.local/s
|
||||
|
||||
The socket is the sharpest of the three, because it is an authority boundary rather than a data one — connecting to it confers the daemon's authenticated session without any credential.
|
||||
|
||||
**Fixed (bugs.md B6):** `AppDirs::ensure` now sets `0700` on the state, cache, and config directories on every start — not only at creation, so a directory that already exists with a permissive mode is tightened — and `config::restrict_socket` sets `0600` on both sockets immediately after `bind`. The directories are restricted *before* the socket is bound, which closes the window between `bind` and `chmod`. A control socket whose mode cannot be set takes the daemon down rather than serving unguarded.
|
||||
Configuration publication follows the same fail-closed model: a restricted temporary file is written and synced, atomically renamed, and followed by a directory sync. A malformed existing configuration is reported and preserved rather than overwritten with defaults.
|
||||
|
||||
See [RECOVERY.md](RECOVERY.md) for what a lost machine means for the plaintext described in this section, and what to revoke.
|
||||
|
||||
### 8.6 Implications for deployment
|
||||
|
||||
- Treat the cache and state directories as being as sensitive as the Drive contents themselves.
|
||||
- Multi-user machines warrant checking `~/.cache` and `~/.local/state` are `0700` until §8.5 is addressed.
|
||||
- Restored or manually copied profiles must remain owned by the user. The daemon refuses to start against wrong-owner or symlinked sensitive directories.
|
||||
- Purging the cache (`pdfs` settings, or `PurgeCache` over IPC) removes content but **not** `cache.db`, and deliberately never removes undrained `staging/` or `recovery/` blobs.
|
||||
|
||||
---
|
||||
|
||||
## 9. Human Verification (CAPTCHA) Flow
|
||||
|
||||
When logging in from an unfamiliar IP address or VPN, the Proton API may gate the sign-in with a human verification challenge (CAPTCHA). This client handles this asynchronously and interactively.
|
||||
|
||||
### 9.1 Sequence of Verification and Re-Authentication
|
||||
|
||||
```mermaid
|
||||
sequenceDiagram
|
||||
autonumber
|
||||
actor User as User (GUI)
|
||||
participant Core as pdfs-core (Auth)
|
||||
participant UI as pdfs-gui (Login Page)
|
||||
participant Web as WebKitWebView Dialog
|
||||
participant API as Proton API Server
|
||||
|
||||
User->>UI: Enter credentials & click Sign In
|
||||
UI->>Core: login_interactive()
|
||||
Core->>API: auth/v4 (Initial SRP Handshake)
|
||||
API-->>Core: HTTP 422 (Error 9001: CAPTCHA Challenge URL)
|
||||
Core->>UI: Error::HumanVerificationRequired(hv)
|
||||
UI->>UI: Block login thread, dispatch to GTK main loop
|
||||
UI->>Web: Create dialog & load verification URL
|
||||
Note over User, Web: User completes CAPTCHA in embedded WebView
|
||||
Web->>UI: window.postMessage(HUMAN_VERIFICATION_SUCCESS)
|
||||
UI->>UI: Extract token (with double-serialization safety)
|
||||
UI->>UI: Close dialog & send token to blocked login thread
|
||||
UI->>Core: login_verified(with verification token)
|
||||
Core->>API: auth/v4 (SRP retry with x-pm-human-verification-token)
|
||||
API-->>Core: Returns session tokens
|
||||
Core-->>UI: Login Successful
|
||||
```
|
||||
|
||||
### 9.2 Key Technical Design Decisions
|
||||
|
||||
1. **Weak Reference UI Binding:** To prevent memory leaks and strong reference cycles between the parent dialog, the child `WebKitWebView`, the script message manager, and the connection callback, the dialog is downgraded to a `WeakRef` inside the callback:
|
||||
```rust
|
||||
let dlg_weak = dialog.downgrade();
|
||||
content.connect_script_message_received(Some("hv"), move |_, value| {
|
||||
// ...
|
||||
if let Some(dlg) = dlg_weak.upgrade() {
|
||||
dlg.close();
|
||||
}
|
||||
});
|
||||
```
|
||||
2. **Double-Serialization Tolerance:** The JavaScript message listener forwards event data as a JSON string to the native handler. Since the underlying page may post either JS objects or pre-serialized JSON strings, the Rust side performs dual-phase parsing:
|
||||
```rust
|
||||
let mut value = serde_json::from_str(raw).ok()?;
|
||||
if let Some(inner) = value.as_str() {
|
||||
if let Ok(parsed) = serde_json::from_str(inner) {
|
||||
value = parsed;
|
||||
}
|
||||
}
|
||||
```
|
||||
This ensures compatibility with all versions of Proton's client verification scripts.
|
||||
3. **SRP Handshake Reset:** Because a gated login burns the SRP handshake on the API side, the client cannot simply resume the previous request. Instead, `auth::login_interactive` restarts the SRP process from scratch with the verification credentials attached, keeping the complex handshake details isolated from the front-end.
|
||||
4. **CLI Fallback:** Since the CLI has no native web browser engine, hitting the CAPTCHA gate fails immediately with a user-friendly message directing the user to sign in once via the GUI (`pdfs-app`) to persist the authenticated session keys to the system keyring.
|
||||
@@ -0,0 +1,149 @@
|
||||
# Development and Verification Status for 1.0
|
||||
|
||||
This document summarizes the work still pending after the 1.0.0 release branch and records the most important recently completed changes. [`BUGS.md`](BUGS.md) is the authoritative issue ledger; [`TESTING.md`](TESTING.md) defines the acceptance commands.
|
||||
|
||||
---
|
||||
|
||||
## 1. Core Feature Roadmap (Horizon Tasks)
|
||||
Consolidated from the historical feature roadmap; current bug status lives in [`BUGS.md`](BUGS.md).
|
||||
|
||||
* **Local Cache & Metadata Encryption at Rest (Priority 5 / Horizon 1)**: Encrypt the SQLite database `cache.db` on disk using SQLCipher (`rusqlite` feature `bundled-sqlcipher`), and encrypt raw content cache blocks (`content/blocks/` and `content/scratch/`) using a fast symmetric scheme like AES-GCM or ChaCha20-Poly1305. The encryption key should be derived from the OS Keyring.
|
||||
* **Active Bandwidth Throttling & Traffic Shaping (Horizon 1)**: Add speed governors for daemon uploads and downloads. Support configuration variables `max_upload_rate_kbps` and `max_download_rate_kbps` in `config.json` that can be dynamically adjusted over the Unix control socket.
|
||||
* **Interactive & Policy-Based Conflict Resolution (Horizon 1)**: Implement configurable conflict resolution policies (`rename-local`, `rename-remote`, `prefer-local`, `prefer-remote`, `interactive`). Add a "Conflicts" tab to the GUI to notify the user, block sync, and launch external visual diff tools (like Meld or KDiff3).
|
||||
* **Multi-Account / Multi-Profile Support (Horizon 3)**: Enable running multiple profiles concurrently. Support separate configuration namespaces (e.g. `profiles/<profile_name>/`), independent SQLite databases, distinct mount paths (e.g. `~/ProtonDrive/Personal` and `~/ProtonDrive/Work`), and multiple daemon processes.
|
||||
* **Custom FUSE Mount Options (Horizon 1)**: Expose custom mounting parameters in configuration (e.g. `ro` for read-only, `direct_io` to bypass kernel caching, `allow_other`). Auto-generate systemd user mount units upon sync folder configuration.
|
||||
* **Symbolic Link & Hard Link Virtualization (Horizon 2)**: Add symbolic link virtualization inside the metadata store (`NodeType::Symlink`) by intercepting `readlink(2)` and `symlink(2)`. Targets should sync remotely as small encrypted metadata placeholder files on Drive (`proton-vfs-symlink: <target>`).
|
||||
* **Desktop File Manager Integration (Horizon 2)**: Develop shell extension plugins for popular Linux file managers (Nautilus Python plugin, Dolphin Service Menus, Thunar custom actions) to offer context-menu shortcuts ("Pin", "Unpin", "Copy Share Link", "View Version History") and file overlay sync badges.
|
||||
* **Integrated Photo Gallery Enhancements (Horizon 2)**: Extract and display Exif metadata (camera model, exposure, coordinates) from photos locally, support creating and editing Proton Photo Albums, build a date-based timeline scrollbar, and create an auto-upload Pictures folder pipeline.
|
||||
* **Random-Access Media Streaming seek support (Horizon 2)**: Intercept out-of-order sparse reads (player seeks) in `pdfs-fuse` and prioritize downloading blocks around the seek offset, aborting/postponing sequential pre-fetches.
|
||||
* **Dynamic Sync Dashboard & Queue Visualization (Horizon 2)**: GUI real-time transfer list (progress bars, speed, ETA), sync history feed, storage usage breakdown, and global pause/resume sync controls.
|
||||
* **Interactive Terminal UI (TUI) Mode (Horizon 3)**: Implement `pdfs tui` using the `ratatui` crate to show transfer speed, sync status, active transfer queue with progress bars, and scrolling daemon logs.
|
||||
* **Shutdown Safety & Write Queue Visibility (Horizon 1 / P4)**: Register systemd inhibitor locks in `pdfs-fuse` when there are outstanding staging writes to prevent shutdown or sleep, pop up warnings when exiting the GUI, and build a blocking `pdfs sync flush` command.
|
||||
* **Block-Level Deduplication (Horizon 3)**: Transition to a Content-Addressable block cache where cached blocks are stored on disk by their SHA-256 hash. Map logical ranges in the database: `(node_uid, block_idx) -> block_hash` to avoid storing or downloading identical blocks.
|
||||
* **Pre-emptive Sync Debouncing & File System Events (Horizon 3)**: Group filesystem write events on paths and delay sync queue insertion until a quiet period has elapsed (e.g. 5 seconds of inactivity) to prevent thrashing the Proton API.
|
||||
* **File Version History (Horizon 2)**: Expose past file revisions and version history inside the GUI browser tabs.
|
||||
|
||||
---
|
||||
|
||||
## 2. Performance, Correctness & Robustness Items
|
||||
Consolidated from the performance and media-streaming audit notes.
|
||||
|
||||
* **B6. Debounce the LRU access touch**: Keep last-touch times in memory and flush them in batches (debounce window of 30-60 seconds) to avoid performing a SQLite `UPDATE` to the `cache_entries` table on every cache hit.
|
||||
* **E12. Client in-flight cap shape**: Address the lock discrepancy between `MAX_CONCURRENT_BLOCK_DOWNLOADS = 10` (per-file) and `DEFAULT_MAX_INFLIGHT_BLOCKS = 12` (global client-wide). Either raise the global cap, lower the per-file window, or dynamically calculate the window to prevent single files from starving concurrent transfers.
|
||||
* **Pipeline `enumerate_nodes_detail` (P2.8 / 8)**: Introduce pipelined node enumeration to speed up directory listings.
|
||||
* **Local ancestor-chain walk (P3.4 / 4)**: Optimize recursive path lookups where full batching is impossible.
|
||||
* **Name Search for Photos/Videos**: Add search by photo/video name (deferred from Phase 3 gallery implementation).
|
||||
* **Sequential-Read Prefetch for Media Streaming**: Implement sequential read prefetch for media files to avoid stalls when buffering.
|
||||
* **Minor sweep items (Phase F)**:
|
||||
* **F1. `StreamRing.tags` Leak**: Clean up tag entries in `StreamRing.tags` when blocks are evicted. Currently, it only shrinks on `drop_node` (revision mismatch), leading to tag accumulation.
|
||||
* **F2. Non-saturating bytes subtraction**: Use `saturating_sub` in `lib.rs:382` (`self.bytes -= dropped.len()`) to prevent release mode panics/wrapping if accounting drifts.
|
||||
* **F3. Short block yields a short read / EOF**: Address the kernel EOF interpretation on short block reads. Either pad the block or fail loudly rather than silently serving short data.
|
||||
* **F4. `stream_readahead` check-then-spawn race**: Prevent duplicate concurrent readahead tasks for the same block. Check-then-spawn is currently racey.
|
||||
* **F5. `refresh_blocks` permit lock (SDK)**: Ensure URL refreshing (`refresh_blocks`) does not hold an in-flight block permit, preventing expired URLs from pinning client permits.
|
||||
* **F7. Document temporary cache file safety**: Add explanatory comment to `cache.rs:362` explaining why `with_extension("tmp")` is safe there but not in `store_thumbnail`.
|
||||
|
||||
---
|
||||
|
||||
## 3. Open & Unverified Bugs
|
||||
Derived from: [`BUGS.md`](BUGS.md)
|
||||
|
||||
* **B2. Unattributed Trash Origin**: Investigate why deleted/moved files are occasionally sent to trash instead of vanishing on older rename operations.
|
||||
* **B10. GLib Critical Warning on HUD Close**: Assertion failure `g_list_store_remove: assertion '!g_sequence_iter_is_end (it)' failed` when prompt window closes during active launch (`xdg-open`). Needs investigation under `G_DEBUG=fatal-criticals`.
|
||||
* **B15. Empty-but-listed folders and duplicate UIDs**: Investigate folder-identity issues (e.g. duplicate remote folders like `Music` with different UIDs) and how folders obtain `listed = 1` in the database without matching child rows.
|
||||
* **B8 (CAPTCHA sign-in bridge)**: Verify a real gated sign-in using Webkit CAPTCHA completion.
|
||||
* **Draft Revision Upload loop**: Verify SDK-side deletion and retry logic when a conflicting draft revision exists under the same client UID.
|
||||
* **Optimistic Size Loss on Restart**: Verify that pending uploads retain their optimistic sizes across a daemon restart.
|
||||
* **B48 — stale listing after unlink**: Session tombstones and authoritative empty listings are implemented; run focused live verification against eventually consistent remote enumeration.
|
||||
* **B49–B55 — data-safety fixes**: Conflict preservation, orphan/staging durability, transactional supersession, one-entry wipe protection, and incomplete-scan handling have regression coverage but still require the fault, power-loss, and live mode-matrix cases recorded in `BUGS.md`.
|
||||
* **B56–B60 — fail-closed state and IPC fixes**: Future schemas, event cursor advancement, socket limits, private-directory validation, and atomic config saves are implemented. Malformed-schema, database-full, connection-flood, wrong-owner, and concurrent/faulted-save verification remains.
|
||||
* **B61 — credential rotation persistence**: Surface and retry keyring persistence failures so a rotated single-use refresh token cannot be lost on restart.
|
||||
* **B62–B65 — release assurance**: Clean-install package verification, complete version/protocol identity, recovery sign-off, advisory/license policy, SBOM, provenance, checksums, and signatures remain.
|
||||
* **B66–B68 — lifecycle and recovery**: Add queue flush/shutdown protection, explicit device adoption during fresh-state restore, and move profile backup below a writable remote folder.
|
||||
|
||||
---
|
||||
|
||||
## 4. Testing, Verification & Disaster Recovery Drills
|
||||
Derived from: [`TESTING.md`](TESTING.md) and [`RECOVERY.md`](RECOVERY.md)
|
||||
|
||||
* **IPC Memory and Performance Stress Tests (Phase 3)**: Verify memory allocations do not balloon when sending large `UploadPhoto` JSON payloads. Test control socket timeout behaviors under long-running block operations.
|
||||
* **Fault Injection and Resiliency Tests (Phase 4)**:
|
||||
* **Network degradation**: Verify that interrupted uploads leave readable staging buffers and result in clean backoff retries.
|
||||
* **Disk full (ENOSPC)**: Verify that write staging and gap-filling report correct errors to FUSE and preserve staged work.
|
||||
* **Concurrent reader starvation**: Test that parallel sequential reads do not freeze directory lookups or metadata handlers.
|
||||
* **Disaster Recovery Drill (P5 / Phase 5)**: Execute a complete manual disaster recovery test:
|
||||
1. Register a device.
|
||||
2. Sync a folder and upload data.
|
||||
3. Wipe the local state directory and SQLite cache.
|
||||
4. Restart the daemon.
|
||||
5. Run `pdfs sync restore` and assert the recovered filesystem matches the source byte-for-byte.
|
||||
* **Managed live mode matrix**: Before release, run `scripts/fuse-acceptance.sh --managed-live <empty-a> <empty-b>` with `PDFS_ACCEPTANCE_ONLY` unset. It validates on-demand/on-demand, on-demand/mirror, mirror/on-demand, and mirror/mirror transitions.
|
||||
* **Crash-consistency matrix**: Inject failure after scratch/sidecar sync, each staging rename, directory sync, pending-op insert/commit, and source deletion; prove that a complete discoverable copy and either the old or new queue record always survives.
|
||||
|
||||
---
|
||||
|
||||
## 5. Fixed & Resolved Bugs
|
||||
Derived from: [`BUGS.md`](BUGS.md)
|
||||
|
||||
### Completely Fixed & Verified
|
||||
* **B1 — FUSE rename loses the file (data loss)**: In `rename`, the node's database row was deleted while only updating the in-memory state, causing the file to vanish on next listing sync. Fixed by correctly calling `st.invalidate_listing(newparent)` to refresh SQLite cache states.
|
||||
* **B4 — `invalidate_listing` silently skipped non-resident folders**: Folders not loaded in memory were being skipped during listing invalidation, leaving stale cache flags in the DB. Fixed by removing the residency check guard.
|
||||
* **B5 — `ls -l` costs a network round trip per file (thumbnail xattr probes)**: File listings triggered blocking network checks for thumbnails on unsupported files. Fixed by caching negative thumbnail results and restricting xattr advertisement to supported image/media files.
|
||||
* **B6 — Daemon sets no file modes: `control.sock` is an unguarded authority**: The Unix control socket was created without restricting file permissions, exposing daemon controls to other local users. Fixed by applying proper creation permission masks.
|
||||
* **B7 — renamed directory reads as missing until the entry TTL expires**: Kernel cache maps remained stale after a FUSE directory re-anchor. Fixed by proactively sending entry invalidation notifications to the kernel.
|
||||
* **B9 — Enter did not open the selected result in the launcher**: Hooked up keyboard execution (Enter key) in `pdfs-prompt` search HUD to launch the selected item using `xdg-open`.
|
||||
* **B11 — a file moved while its create is still queued reads as empty**: Reconciling a local rename on a file that had not finished uploading yet uploaded empty blocks. Fixed by carrying over and staging the correct logical file size.
|
||||
* **B12 — cold enumeration is slow per entry, and goes superlinear past ~500**: S2K decryption and thumbnail resolution loops were serial. Fixed by parallelizing key derivations and caching metadata.
|
||||
* **B13 — `rename` over an existing destination fails instead of replacing it**: Fixed POSIX rename target overwrite behavior to replace existing destinations.
|
||||
* **B14 — provisional (ciphertext) sizes make rsync read short and abort the file**: Adjusted size reporting to align logical and ciphertext sizing, preventing premature EOF.
|
||||
* **B45 — truncate over a queued rewrite**: Path-based and handle-based truncate now compose over the complete pending blob; shrink, growth, and sparse I/O are live-verified.
|
||||
* **B46 — combined cross-directory move and rename**: The desired end state is durably queued and reconciles partially completed remote operations; replacement and combined cases are live-verified.
|
||||
* **B47 — overlong/invalid names**: All name-taking callbacks share a validator for `NAME_MAX`, reserved components, and UTF-8; managed-live verification passed.
|
||||
|
||||
### Implemented in 1.0 (Further Fault Verification Pending)
|
||||
|
||||
* **Unified search and resident prompt**: `SearchV2` combines Drive and local lookup with shared relevance scoring and content/source filters. The prompt reuses its window and opens streamable media through FUSE.
|
||||
* **Durable write publication**: Scratch sidecars and staged blobs use synced temporary files, atomic renames, and directory synchronization; orphan rescue retains its source on failure.
|
||||
* **Transactional pending operations**: Superseding a queued operation cannot delete the old durable record unless the replacement commits.
|
||||
* **Safer mirror reconciliation**: Conflict-copy failure aborts publication, incomplete scans are non-destructive, and total-wipe protection includes one-entry baselines.
|
||||
* **Bounded IPC**: Control requests are limited to 1 MiB and 10 seconds, with at most 64 active handlers.
|
||||
* **Private local state**: Sensitive directories require correct ownership, real-directory identity, and `0700`; sockets use `0600`; config saves are atomic and malformed input is preserved.
|
||||
* **Release gates**: Tag/workspace/package versions are checked and formatting, lint, tests, and offline FUSE acceptance run before packaging.
|
||||
|
||||
### Code Fixed / Implemented (Pending Verification)
|
||||
* **B8 — no way to complete a CAPTCHA, so a gated sign-in is unrecoverable**: Implemented a Webkit-based bridge to prompt the user to resolve interactive CAPTCHAs during gated logins. (Needs verification on a real gate request).
|
||||
|
||||
### Closed / Not a Bug
|
||||
* **B3 — Activity log timestamps written in seconds, read as milliseconds**: Closed as investigator error (timestamps are consistent).
|
||||
|
||||
---
|
||||
|
||||
## 6. Recently Implemented Features
|
||||
|
||||
### Open-for-Write Deferral for Mirror Sync (Implemented)
|
||||
**File**: [`sync.rs`](../crates/pdfs-fuse/src/sync.rs)
|
||||
|
||||
The mirror folder sync engine now defers uploading any file that is currently held open for writing by another process, matching the guarantee the FUSE mount path already provides (where uploads are deferred until `close(fd)`).
|
||||
|
||||
**Problem**: Previously, the mirror sync path relied solely on a 2-second trailing-edge debounce (with a 30-second ceiling) to avoid uploading files mid-write. This was insufficient for slow continuous writers (e.g., database dumps, large exports, or editors that keep files open for extended periods), which could have their incomplete state uploaded as a real revision.
|
||||
|
||||
**Solution**: Before each reconcile pass, the sync engine scans `/proc/*/fd` once to build a set of canonical paths within the sync root that any process holds open for writing (`O_WRONLY` or `O_RDWR`). Files in this set are:
|
||||
|
||||
- **Kept in the local walk** — so they are not misclassified as deletions
|
||||
- **Treated as unchanged** — so no upload is queued for them
|
||||
- **Counted as `deferred`** — so the activity summary reports them (e.g., "3 uploaded, 1 deferred (open for write)")
|
||||
- **Picked up on the next pass** — after the writer has closed the file
|
||||
|
||||
**How it works**:
|
||||
1. `open_for_write_set(root)` reads `/proc/*/fd` → `readlink` for each fd → prefix-checks against the sync root → reads `/proc/<pid>/fdinfo/<n>` to check the `flags:` line's low two bits (O_ACCMODE)
|
||||
2. `walk_local` sets `LocalItem.open_for_write = true` for matching files
|
||||
3. Both `do_reconcile` and `push_pass` skip upload classification for flagged files
|
||||
4. `Outcome.deferred` tracks the count for the activity summary
|
||||
|
||||
**Performance**: The `/proc` scan completes in low single-digit milliseconds on a typical desktop. Only fds whose `readlink` target falls under the sync root incur the `fdinfo` read.
|
||||
|
||||
**Tests added**: 8 unit tests covering `is_write_mode` parsing of various fdinfo flag combinations, and `Outcome` summary formatting with deferred counts.
|
||||
|
||||
| Sync Path | Open-for-write protection | Mechanism |
|
||||
|---|---|---|
|
||||
| FUSE mount | ✅ Perfect | Upload deferred until `close(fd)` |
|
||||
| Mirror folders | ✅ Perfect | `/proc/*/fd` scan per reconcile pass |
|
||||
@@ -0,0 +1,181 @@
|
||||
# Testing
|
||||
|
||||
The normal Rust suite exercises the metadata database, sync planner, offline
|
||||
queue, write staging, cache, and FUSE handler state without requiring a Proton
|
||||
account:
|
||||
|
||||
```console
|
||||
cargo test --workspace
|
||||
cargo clippy --workspace --all-targets -- -D warnings
|
||||
```
|
||||
|
||||
## Filesystem API and live FUSE acceptance suite
|
||||
|
||||
The account-free suite exercises the filesystem syscall contract against a
|
||||
temporary local directory. This validates the runner and covers creation/open
|
||||
flags, positioned and vectored I/O, truncation and sparse files, `mmap`,
|
||||
`sendfile`, `copy_file_range`, durability barriers, namespace/error semantics,
|
||||
`renameat2` flags, open-file lifetime, names and enumeration, readdir stability
|
||||
under concurrent mutation, metadata updates, extended attributes, allocation and
|
||||
punched holes, refusal semantics for unimplemented operations, concurrent I/O,
|
||||
and real application workloads. It never reads application state or contacts
|
||||
Proton:
|
||||
|
||||
```console
|
||||
scripts/fuse-acceptance.sh --offline-only
|
||||
```
|
||||
|
||||
Kernel/FUSE behavior and remote convergence need a real mount. Live testing is
|
||||
explicitly opt-in and always runs the account-free contract first. It runs
|
||||
destructive POSIX operations only below a fresh `pdfs-acceptance-*` directory.
|
||||
It refuses paths that are not FUSE mounts and removes its directory on success,
|
||||
failure, or interruption.
|
||||
|
||||
Use a dedicated test account without irreplaceable data:
|
||||
|
||||
```console
|
||||
scripts/fuse-acceptance.sh --live /mnt/on-demand-testmount
|
||||
```
|
||||
|
||||
### The mount is diffed against an ordinary filesystem
|
||||
|
||||
The local reference run is not only a self-test of the runner. Every case
|
||||
records the facts it established, and a live run is compared against those
|
||||
recordings, so a case fails when the mount *differs* from an ordinary
|
||||
filesystem — not only when it raises. The report names the exact key:
|
||||
|
||||
```
|
||||
[DIVERGENCE] live FUSE /mnt/testmount does not match the reference filesystem:
|
||||
! creation and open flags.truncated.size: live=6 reference=0
|
||||
```
|
||||
|
||||
Facts are recorded in one of two ways, chosen in the test body:
|
||||
|
||||
- **compared** — a claim about filesystem semantics. The mount must agree.
|
||||
- **noted** — context that legitimately differs: inode numbers, block counts,
|
||||
reported mode bits, and which optional syscalls exist at all. Reported under
|
||||
`[capabilities]`, never a failure.
|
||||
|
||||
Because the choice is made at each call site, the set of accepted divergences
|
||||
is visible in the test that accepts it. There is no separate allowlist to drift
|
||||
out of date. When adding a case, prefer `record`; reach for `note` only when an
|
||||
ordinary filesystem can do something a network filesystem genuinely cannot.
|
||||
|
||||
### Operations the filesystem does not implement
|
||||
|
||||
`git`, `rsync`, `cp -a`, `tar`, `df` and most installers probe for symlinks,
|
||||
hard links, FIFOs, device nodes, `statfs`, file locks, `copy_file_range`,
|
||||
`O_DIRECT` and `SEEK_HOLE` whether or not a filesystem offers them. The suite
|
||||
asserts that each either works or is *refused cleanly* — a recognised errno,
|
||||
never `EIO` and never a hang. A refusal that is merely unimplemented is fine;
|
||||
one that is dirty breaks software that never asked for the feature.
|
||||
|
||||
### Regressions from the bug ledger
|
||||
|
||||
Cases named `regression B<n>` reproduce a bug from `docs/BUGS.md` so it stays
|
||||
fixed. B69 (identical rewrite must not fork a `(sync-conflict …)` copy), B70 (an
|
||||
in-flight `.crdownload` must not be sealed as a revision) and B74 (a file
|
||||
renamed after close must keep its content) need a real mount and a reachable
|
||||
daemon; they are skipped, not failed, without one.
|
||||
|
||||
B74 is currently **failing** — it is a live data-loss defect, not a regression
|
||||
guard, and it was found by exactly this mechanism: the B70 case failed, and
|
||||
narrowing it produced a smaller reproduction that has its own case now. Expect a
|
||||
red run against a real mount until it is fixed.
|
||||
|
||||
A regression case asserts against the *remote* outcome, so it must wait for the
|
||||
queue to drain before reading. Reading straight back through the mount proves
|
||||
nothing: the local attribute and content caches will happily return the bytes
|
||||
that were just written even when nothing reached Drive, which is precisely how
|
||||
B74 stayed invisible.
|
||||
|
||||
### Timeouts, reports, and hung mounts
|
||||
|
||||
A wedged FUSE operation cannot be interrupted from Python, so each case runs
|
||||
under a soft alarm (`--timeout`, default 180s) that reports the case and lets
|
||||
cleanup run, backed by a hard stop that dumps every thread's stack and exits.
|
||||
That backstop is the only way to learn *where* a mount hung. A timeout ends the
|
||||
run: later cases against a wedged mount produce noise, not information.
|
||||
|
||||
```console
|
||||
scripts/fuse-acceptance.sh --live /mnt/testmount \
|
||||
--timeout 300 --report-junit results.xml --budget 30
|
||||
```
|
||||
|
||||
`--report-json` also writes every recorded observation, which is what to attach
|
||||
to a bug report. `--budget SECONDS` flags cases that pass but got slower —
|
||||
B5 was a 186 ms-per-call regression that a pass/fail suite could not see.
|
||||
`--list` prints every case and which targets it runs against, and `--fail-fast`
|
||||
stops at the first failure.
|
||||
|
||||
`--journal-check` fails the run if `proton-drive.service` logged any error while
|
||||
it ran. A suite can pass every assertion while the daemon logs failures behind
|
||||
it; that has happened, and it was caught only by reading the journal by hand.
|
||||
|
||||
Abandoned `pdfs-acceptance-*` roots from a crashed run are removed at startup,
|
||||
but only if they match the exact generated name and are over an hour old
|
||||
(`PDFS_ACCEPTANCE_REAP_AGE`), so a concurrent run is never disturbed.
|
||||
|
||||
### Automated mode matrix
|
||||
|
||||
The managed live runner accepts two existing, empty, unmounted directories. It
|
||||
registers both as new sync folders, waits for initial synchronization, then
|
||||
tests all four pairs in order: on-demand/on-demand, on-demand/mirror,
|
||||
mirror/on-demand, and mirror/mirror. Every transition must become idle, and an
|
||||
on-demand folder must actually appear as a mount before its contract runs.
|
||||
|
||||
```console
|
||||
mkdir -p /mnt/pdfs-test-a /mnt/pdfs-test-b
|
||||
scripts/fuse-acceptance.sh --managed-live /mnt/pdfs-test-a /mnt/pdfs-test-b
|
||||
```
|
||||
|
||||
This creates remote folders and permanently deletes those test remotes during
|
||||
cleanup. It refuses non-empty paths, existing mounts, and paths already present
|
||||
in `pdfs sync list`. Use `PDFS_ACCEPTANCE_SYNC_TIMEOUT` to extend transition
|
||||
timeouts and `PDFS_ACCEPTANCE_PDFS` to select a non-installed CLI binary, for
|
||||
example `target/debug/pdfs`.
|
||||
|
||||
### Durability drill
|
||||
|
||||
`--durability` restarts `proton-drive.service` in the middle of the suite and
|
||||
re-verifies the bytes written before it. `staging/` and `recovery/` can hold the
|
||||
only copy of a file whose upload has not finished, so this is the case that
|
||||
proves the queue is persistent rather than in-memory. It is opt-in because it
|
||||
interrupts a running daemon; `PDFS_ACCEPTANCE_UNIT` selects a different unit.
|
||||
|
||||
### Selecting cases
|
||||
|
||||
During development, `PDFS_ACCEPTANCE_ONLY` runs tests whose descriptive name
|
||||
contains the supplied text (for example `PDFS_ACCEPTANCE_ONLY=namespace`). A
|
||||
release acceptance run must leave it unset so the complete contract executes.
|
||||
|
||||
Passing more paths runs the same filesystem suite independently against each.
|
||||
The first path must be the FUSE mount under test; later paths may be another
|
||||
FUSE mount or a normal local mirror filesystem:
|
||||
|
||||
```console
|
||||
PDFS_ACCEPTANCE_SYNC_TIMEOUT=180 \
|
||||
scripts/fuse-acceptance.sh --live /mnt/on-demand-testmount /mnt/testmount
|
||||
```
|
||||
|
||||
If two paths really are views of the **same remote folder**, enable an
|
||||
additional byte-for-byte convergence check explicitly:
|
||||
|
||||
```console
|
||||
PDFS_ACCEPTANCE_CONVERGENCE=1 \
|
||||
scripts/fuse-acceptance.sh --live /mnt/first-view /mnt/second-view
|
||||
```
|
||||
|
||||
Do not enable that flag merely because two sync folders belong to the same
|
||||
account. Their configured remote UIDs must be identical.
|
||||
|
||||
Normally the live suite applies the same API contract independently to each
|
||||
supplied mount. In convergence mode it exercises the primary once and verifies
|
||||
that the resulting bytes appear through every secondary view. A pass is
|
||||
strong evidence for those paths, not a blanket data-loss guarantee. Before a
|
||||
release, also run the recovery drills in `docs/RECOVERY.md` and inspect
|
||||
`docs/BUGS.md` for live-verification items.
|
||||
|
||||
The runner accepts already-mounted paths instead of starting a daemon. This
|
||||
keeps authentication and keyring setup explicit and prevents it from silently
|
||||
reusing or replacing the normal application state directory.
|
||||
|
After Width: | Height: | Size: 91 KiB |
|
Before Width: | Height: | Size: 190 KiB After Width: | Height: | Size: 46 KiB |
|
Before Width: | Height: | Size: 190 KiB After Width: | Height: | Size: 170 KiB |
|
Before Width: | Height: | Size: 239 KiB After Width: | Height: | Size: 108 KiB |
|
After Width: | Height: | Size: 41 KiB |
|
After Width: | Height: | Size: 52 KiB |
@@ -9,13 +9,13 @@
|
||||
# Build + install: cd packaging && makepkg -fi
|
||||
|
||||
pkgname=proton-drive-linux
|
||||
pkgver=0.5.0
|
||||
pkgver=1.1.1
|
||||
pkgrel=1
|
||||
pkgdesc="Proton Drive client for Linux: FUSE files-on-demand mount, CLI, GTK4 app + tray"
|
||||
arch=('x86_64')
|
||||
url="https://github.com/narl/proton-drive-linux"
|
||||
license=('MIT')
|
||||
depends=('fuse3' 'gtk4' 'libadwaita')
|
||||
depends=('fuse3' 'gtk4' 'libadwaita' 'webkitgtk-6.0')
|
||||
makedepends=('cargo' 'git')
|
||||
provides=('pdfs')
|
||||
# Files-on-demand mount + keyring need these at runtime.
|
||||
|
||||
@@ -1,45 +1,82 @@
|
||||
# Local in-tree RPM (mirrors packaging/PKGBUILD).
|
||||
# From the repository root:
|
||||
# rpmbuild -bb packaging/proton-drive-linux.spec --define "git_dir $PWD" ...
|
||||
# %build needs network so cargo can fetch crates.io (same trade-off as the Arch PKGBUILD).
|
||||
|
||||
%global debug_package %{nil}
|
||||
# Match Arch PKGBUILD `!lto` — LTO has broken some GTK/Rust links in practice.
|
||||
%global _lto_cflags %{nil}
|
||||
|
||||
%{!?version: %global version 0.4.0}
|
||||
|
||||
Name: proton-drive-linux
|
||||
Version: %{version}
|
||||
Release: 1%{?dist}
|
||||
Summary: Proton Drive client for Linux (unofficial)
|
||||
|
||||
Summary: Proton Drive client for Linux (FUSE, CLI, GTK4 app + tray)
|
||||
License: MIT
|
||||
URL: https://github.com/narl/proton-drive-linux
|
||||
ExclusiveArch: x86_64
|
||||
|
||||
# Disable debuginfo package generation since we package pre-built release binaries
|
||||
%global debug_package %{nil}
|
||||
# Disable binary strip/post-processing checks to avoid issues with pre-compiled binaries
|
||||
%global __os_install_post %{nil}
|
||||
BuildRequires: cargo
|
||||
BuildRequires: rust
|
||||
BuildRequires: pkgconf-pkg-config
|
||||
BuildRequires: fuse3-devel
|
||||
BuildRequires: gtk4-devel
|
||||
BuildRequires: libadwaita-devel
|
||||
BuildRequires: libsecret-devel
|
||||
BuildRequires: dbus-devel
|
||||
BuildRequires: glib2-devel
|
||||
BuildRequires: webkitgtk6.0-devel
|
||||
|
||||
Requires: fuse3
|
||||
Requires: gtk4 >= 4.12.0
|
||||
Requires: libadwaita >= 1.5.0
|
||||
Requires: gtk4
|
||||
Requires: libadwaita
|
||||
Requires: libsecret
|
||||
Requires: dbus
|
||||
Requires: webkitgtk6.0
|
||||
Requires: xdg-utils
|
||||
|
||||
# DE-specific; do not Require a single desktop environment.
|
||||
Recommends: gnome-keyring
|
||||
Recommends: gnome-shell-extension-appindicator
|
||||
Recommends: kwallet
|
||||
|
||||
Provides: pdfs = %{version}-%{release}
|
||||
|
||||
%description
|
||||
A fast, unofficial Proton Drive client for Linux. This client features an advanced files-on-demand FUSE virtual mount with block-level caching, a command-line interface (CLI), and a fully non-blocking GTK4 desktop application with system tray integration.
|
||||
Unofficial Proton Drive client featuring a FUSE files-on-demand mount,
|
||||
CLI, GTK4/Libadwaita GUI, system tray, and search launcher.
|
||||
|
||||
%prep
|
||||
# In-tree build: no Source tarball. Pass --define "git_dir /path/to/checkout".
|
||||
test -n "%{?git_dir}" || (echo 'Pass --define "git_dir $PWD" from the repo root' >&2; exit 1)
|
||||
test -f %{git_dir}/Cargo.toml
|
||||
cp -a %{git_dir}/LICENSE .
|
||||
%build
|
||||
cd %{git_dir}
|
||||
cargo build --release --locked \
|
||||
--bin pdfs \
|
||||
--bin pdfs-tray \
|
||||
--bin pdfs-app \
|
||||
--bin pdfs-prompt
|
||||
|
||||
%install
|
||||
mkdir -p %{buildroot}%{_bindir}
|
||||
mkdir -p %{buildroot}%{_datadir}/applications
|
||||
mkdir -p %{buildroot}%{_sysconfdir}/xdg/autostart
|
||||
mkdir -p %{buildroot}%{_datadir}/icons/hicolor/scalable/apps
|
||||
mkdir -p %{buildroot}%{_usr}/lib/systemd/user
|
||||
mkdir -p %{buildroot}%{_datadir}/licenses/proton-drive-linux
|
||||
rel=%{git_dir}/target/release
|
||||
install -D -m0755 "$rel/pdfs" %{buildroot}%{_bindir}/pdfs
|
||||
install -D -m0755 "$rel/pdfs-tray" %{buildroot}%{_bindir}/pdfs-tray
|
||||
install -D -m0755 "$rel/pdfs-app" %{buildroot}%{_bindir}/pdfs-app
|
||||
install -D -m0755 "$rel/pdfs-prompt" %{buildroot}%{_bindir}/pdfs-prompt
|
||||
|
||||
cp %{_sourcedir}/target/release/pdfs %{buildroot}%{_bindir}/
|
||||
cp %{_sourcedir}/target/release/pdfs-tray %{buildroot}%{_bindir}/
|
||||
cp %{_sourcedir}/target/release/pdfs-app %{buildroot}%{_bindir}/
|
||||
cp %{_sourcedir}/target/release/pdfs-prompt %{buildroot}%{_bindir}/
|
||||
|
||||
cp %{_sourcedir}/packaging/io.narl.proton-drive-linux.desktop %{buildroot}%{_datadir}/applications/
|
||||
cp %{_sourcedir}/packaging/io.narl.proton-drive-linux-tray.desktop %{buildroot}%{_sysconfdir}/xdg/autostart/
|
||||
cp %{_sourcedir}/packaging/io.narl.proton-drive-linux.svg %{buildroot}%{_datadir}/icons/hicolor/scalable/apps/
|
||||
cp %{_sourcedir}/packaging/proton-drive.service %{buildroot}%{_usr}/lib/systemd/user/
|
||||
cp %{_sourcedir}/LICENSE %{buildroot}%{_datadir}/licenses/proton-drive-linux/
|
||||
install -D -m0644 %{git_dir}/packaging/io.narl.proton-drive-linux.desktop \
|
||||
%{buildroot}%{_datadir}/applications/io.narl.proton-drive-linux.desktop
|
||||
install -D -m0644 %{git_dir}/packaging/io.narl.proton-drive-linux-tray.desktop \
|
||||
%{buildroot}%{_sysconfdir}/xdg/autostart/io.narl.proton-drive-linux-tray.desktop
|
||||
install -D -m0644 %{git_dir}/packaging/io.narl.proton-drive-linux.svg \
|
||||
%{buildroot}%{_datadir}/icons/hicolor/scalable/apps/io.narl.proton-drive-linux.svg
|
||||
install -D -m0644 %{git_dir}/packaging/proton-drive.service \
|
||||
%{buildroot}/usr/lib/systemd/user/proton-drive.service
|
||||
|
||||
%files
|
||||
%license LICENSE
|
||||
%{_bindir}/pdfs
|
||||
%{_bindir}/pdfs-tray
|
||||
%{_bindir}/pdfs-app
|
||||
@@ -47,5 +84,8 @@ cp %{_sourcedir}/LICENSE %{buildroot}%{_datadir}/licenses/proton-drive-linux/
|
||||
%{_datadir}/applications/io.narl.proton-drive-linux.desktop
|
||||
%{_sysconfdir}/xdg/autostart/io.narl.proton-drive-linux-tray.desktop
|
||||
%{_datadir}/icons/hicolor/scalable/apps/io.narl.proton-drive-linux.svg
|
||||
%{_usr}/lib/systemd/user/proton-drive.service
|
||||
%{_datadir}/licenses/proton-drive-linux/LICENSE
|
||||
/usr/lib/systemd/user/proton-drive.service
|
||||
|
||||
%changelog
|
||||
* Sun Jul 19 2026 Local Packager - 0.4.0-1
|
||||
- Initial Fedora local package (in-tree cargo build).
|
||||
@@ -0,0 +1,82 @@
|
||||
#!/usr/bin/env bash
|
||||
# Filesystem syscall contract, with optional tests against mounted Drive views.
|
||||
set -Eeuo pipefail
|
||||
|
||||
usage() {
|
||||
cat >&2 <<'EOF'
|
||||
usage: scripts/fuse-acceptance.sh [--offline-only] [OPTION ...]
|
||||
scripts/fuse-acceptance.sh --live MOUNTPOINT [MOUNTPOINT ...] [OPTION ...]
|
||||
scripts/fuse-acceptance.sh --managed-live EMPTY_DIR EMPTY_DIR [OPTION ...]
|
||||
scripts/fuse-acceptance.sh MOUNTPOINT [MOUNTPOINT ...] # compatibility
|
||||
|
||||
The local reference suite always runs first and requires no account; the mount
|
||||
is then diffed against its recorded behaviour. --live runs the same contract on
|
||||
each mount. Set PDFS_ACCEPTANCE_CONVERGENCE=1 only when all live mountpoints
|
||||
show the same remote folder.
|
||||
|
||||
Options are forwarded to the Python runner. The useful ones:
|
||||
--list print every case and the targets it runs against
|
||||
--timeout SECONDS per-case limit (default 180); a hung case dumps stacks
|
||||
--fail-fast stop at the first failure instead of continuing
|
||||
--report-json PATH machine-readable results and recorded observations
|
||||
--report-junit PATH JUnit XML for CI
|
||||
--budget SECONDS report any case slower than this
|
||||
--journal-check fail if the daemon logs errors during the run
|
||||
--durability restart the daemon mid-suite and re-verify bytes
|
||||
EOF
|
||||
exit 2
|
||||
}
|
||||
|
||||
command -v python3 >/dev/null || { echo "python3 is required" >&2; exit 2; }
|
||||
script_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
runner=(python3 -u "$script_dir/fuse-acceptance.py")
|
||||
|
||||
mountpoints=()
|
||||
passthrough=()
|
||||
# Paths come first and options after them, so the first dash-prefixed argument
|
||||
# ends the path list and everything from there is forwarded untouched.
|
||||
collect_paths() {
|
||||
while (( $# > 0 )) && [[ "$1" != -* ]]; do
|
||||
mountpoints+=("$1")
|
||||
shift
|
||||
done
|
||||
passthrough=("$@")
|
||||
}
|
||||
|
||||
case "${1:-}" in
|
||||
-h|--help) usage ;;
|
||||
--offline-only|"")
|
||||
shift || true
|
||||
exec "${runner[@]}" "$@"
|
||||
;;
|
||||
--live)
|
||||
shift
|
||||
collect_paths "$@"
|
||||
(( ${#mountpoints[@]} > 0 )) || usage
|
||||
;;
|
||||
--managed-live)
|
||||
shift
|
||||
(( $# >= 2 )) || usage
|
||||
first="$1"; second="$2"; shift 2
|
||||
exec "${runner[@]}" --managed-live "$first" "$second" "$@"
|
||||
;;
|
||||
--*)
|
||||
# Bare options with no mode: an offline run with those options.
|
||||
exec "${runner[@]}" "$@"
|
||||
;;
|
||||
*)
|
||||
collect_paths "$@"
|
||||
;;
|
||||
esac
|
||||
|
||||
command -v findmnt >/dev/null || { echo "findmnt is required for --live" >&2; exit 2; }
|
||||
for mountpoint in "${mountpoints[@]}"; do
|
||||
[[ -d "$mountpoint" ]] || { echo "not a directory: $mountpoint" >&2; exit 2; }
|
||||
done
|
||||
fstype="$(findmnt -T "${mountpoints[0]}" -n -o FSTYPE | head -n 1)"
|
||||
[[ "$fstype" == fuse* ]] || {
|
||||
echo "refusing primary non-FUSE path ${mountpoints[0]} (type: ${fstype:-unknown})" >&2
|
||||
exit 2
|
||||
}
|
||||
|
||||
exec "${runner[@]}" --live "${mountpoints[@]}" "${passthrough[@]}"
|
||||