feat: option to prevent cross-filesystem traversal

.devcontainer/devcontainer.json

@@ -1,6 +1,9 @@
 {
   "name": "parallel-disk-usage (Rust only)",
   "image": "mcr.microsoft.com/devcontainers/rust:1",
+  "remoteEnv": {
+    "TEST_SKIP": "cross_device_excludes_mount"
+  },
   "customizations": {
     "vscode": {
       "extensions": [

.devcontainer/full/devcontainer.json

@@ -1,6 +1,9 @@
 {
   "name": "parallel-disk-usage (full)",
   "image": "mcr.microsoft.com/devcontainers/rust:1",
+  "remoteEnv": {
+    "TEST_SKIP": "cross_device_excludes_mount"
+  },
   "features": {
     "ghcr.io/devcontainers/features/node:1": {
       "version": "lts",

.github/workflows/deploy.yaml

@@ -29,6 +29,12 @@ jobs:
           curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > $installer
           bash $installer --default-toolchain $(cat rust-toolchain) -y
 
+      - name: Install external test dependencies
+        if: runner.os == 'Linux'
+        run: |
+          sudo apt update
+          sudo apt install -y squashfs-tools squashfuse fuse3
+
       - name: Test (dev)
         shell: bash
         env:

.github/workflows/test.yaml

@@ -42,6 +42,12 @@ jobs:
           curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > $installer
           bash $installer --default-toolchain $(cat rust-toolchain) -y
 
+      - name: Install external test dependencies
+        if: runner.os == 'Linux'
+        run: |
+          sudo apt update
+          sudo apt install -y squashfs-tools squashfuse fuse3
+
       - name: Test (dev)
         shell: bash
         env:

CONTRIBUTING.md

@@ -351,6 +351,16 @@ rustup toolchain install "$(< rust-toolchain)"
 rustup component add --toolchain "$(< rust-toolchain)" rustfmt clippy
 ```
 
+## Optional External Dependencies
+
+Some integration tests require external (non-Cargo) tools that are **not** managed by `Cargo.toml`. These tests panic when the tools are absent; CI installs them to get full coverage.
+
+- `squashfs-tools` (provides `mksquashfs`) — cross-device (`--one-file-system`) FUSE test
+- `squashfuse` (provides `squashfuse`) — cross-device (`--one-file-system`) FUSE test
+- `fuse3` (provides `fusermount3`, `/dev/fuse`) — cross-device (`--one-file-system`) FUSE test
+
+Tests that need these tools will panic with a diagnostic message if they are missing. The panic message includes the specific `TEST_SKIP` variable to skip the test via `./test.sh`.
+
 ## Automated Checks
 
 Before submitting, ensure:

Cargo.toml

@@ -91,3 +91,4 @@ maplit = "1.0.2"
 normalize-path = "0.2.1"
 pretty_assertions = "1.4.1"
 rand = "0.10.0"
+which = "8.0.2"

README.md

@@ -61,7 +61,6 @@ The benchmark was generated by [a GitHub Workflow](https://github.com/KSXGitHub/
 
 * Ignorant of reflinks (from COW filesystems such as BTRFS and ZFS).
 * Does not follow symbolic links.
-* Does not differentiate filesystems: Mounted folders are counted as normal folders.
 * The runtime is optimized at the expense of binary size.
 
 ## Usage

USAGE.md

@@ -39,6 +39,13 @@ How to display the numbers of bytes.
 
 Detect and subtract the sizes of hardlinks from their parent directory totals.
 
+<a id="option-x" name="option-x"></a><a id="one-file-system" name="one-file-system"></a>
+### `--one-file-system`
+
+* _Aliases:_ `-x`.
+
+Skip directories on different filesystems.
+
 <a id="top-down" name="top-down"></a>
 ### `--top-down`
 

exports/completion.bash

@@ -23,7 +23,7 @@ _pdu() {
 
     case "${cmd}" in
         pdu)
-            opts="-b -H -q -d -w -m -s -p -h -V --json-input --json-output --bytes-format --detect-links --dedupe-links --deduplicate-hardlinks --top-down --align-right --quantity --depth --max-depth --width --total-width --column-width --min-ratio --no-sort --no-errors --silent-errors --progress --threads --omit-json-shared-details --omit-json-shared-summary --help --version [FILES]..."
+            opts="-b -H -x -q -d -w -m -s -p -h -V --json-input --json-output --bytes-format --detect-links --dedupe-links --deduplicate-hardlinks --one-file-system --top-down --align-right --quantity --depth --max-depth --width --total-width --column-width --min-ratio --no-sort --no-errors --silent-errors --progress --threads --omit-json-shared-details --omit-json-shared-summary --help --version [FILES]..."
             if [[ ${cur} == -* || ${COMP_CWORD} -eq 1 ]] ; then
                 COMPREPLY=( $(compgen -W "${opts}" -- "${cur}") )
                 return 0

exports/completion.elv

@@ -38,6 +38,8 @@ set edit:completion:arg-completer[pdu] = {|@words|
             cand --deduplicate-hardlinks 'Detect and subtract the sizes of hardlinks from their parent directory totals'
             cand --detect-links 'Detect and subtract the sizes of hardlinks from their parent directory totals'
             cand --dedupe-links 'Detect and subtract the sizes of hardlinks from their parent directory totals'
+            cand -x 'Skip directories on different filesystems'
+            cand --one-file-system 'Skip directories on different filesystems'
             cand --top-down 'Print the tree top-down instead of bottom-up'
             cand --align-right 'Set the root of the bars to the right'
             cand --no-sort 'Do not sort the branches in the tree'

exports/completion.fish

@@ -12,6 +12,7 @@ complete -c pdu -l threads -d 'Set the maximum number of threads to spawn. Could
 complete -c pdu -l json-input -d 'Read JSON data from stdin'
 complete -c pdu -l json-output -d 'Print JSON data instead of an ASCII chart'
 complete -c pdu -s H -l deduplicate-hardlinks -l detect-links -l dedupe-links -d 'Detect and subtract the sizes of hardlinks from their parent directory totals'
+complete -c pdu -s x -l one-file-system -d 'Skip directories on different filesystems'
 complete -c pdu -l top-down -d 'Print the tree top-down instead of bottom-up'
 complete -c pdu -l align-right -d 'Set the root of the bars to the right'
 complete -c pdu -l no-sort -d 'Do not sort the branches in the tree'

exports/completion.ps1

@@ -41,6 +41,8 @@ Register-ArgumentCompleter -Native -CommandName 'pdu' -ScriptBlock {
             [CompletionResult]::new('--deduplicate-hardlinks', '--deduplicate-hardlinks', [CompletionResultType]::ParameterName, 'Detect and subtract the sizes of hardlinks from their parent directory totals')
             [CompletionResult]::new('--detect-links', '--detect-links', [CompletionResultType]::ParameterName, 'Detect and subtract the sizes of hardlinks from their parent directory totals')
             [CompletionResult]::new('--dedupe-links', '--dedupe-links', [CompletionResultType]::ParameterName, 'Detect and subtract the sizes of hardlinks from their parent directory totals')
+            [CompletionResult]::new('-x', '-x', [CompletionResultType]::ParameterName, 'Skip directories on different filesystems')
+            [CompletionResult]::new('--one-file-system', '--one-file-system', [CompletionResultType]::ParameterName, 'Skip directories on different filesystems')
             [CompletionResult]::new('--top-down', '--top-down', [CompletionResultType]::ParameterName, 'Print the tree top-down instead of bottom-up')
             [CompletionResult]::new('--align-right', '--align-right', [CompletionResultType]::ParameterName, 'Set the root of the bars to the right')
             [CompletionResult]::new('--no-sort', '--no-sort', [CompletionResultType]::ParameterName, 'Do not sort the branches in the tree')

exports/completion.zsh

@@ -37,12 +37,14 @@ block-count\:"Count numbers of blocks"))' \
 '-m+[Minimal size proportion required to appear]:MIN_RATIO:_default' \
 '--min-ratio=[Minimal size proportion required to appear]:MIN_RATIO:_default' \
 '--threads=[Set the maximum number of threads to spawn. Could be either "auto", "max", or a positive integer]:THREADS:_default' \
-'(-q --quantity -H --deduplicate-hardlinks)--json-input[Read JSON data from stdin]' \
+'(-q --quantity -H --deduplicate-hardlinks -x --one-file-system)--json-input[Read JSON data from stdin]' \
 '--json-output[Print JSON data instead of an ASCII chart]' \
 '-H[Detect and subtract the sizes of hardlinks from their parent directory totals]' \
 '--deduplicate-hardlinks[Detect and subtract the sizes of hardlinks from their parent directory totals]' \
 '--detect-links[Detect and subtract the sizes of hardlinks from their parent directory totals]' \
 '--dedupe-links[Detect and subtract the sizes of hardlinks from their parent directory totals]' \
+'-x[Skip directories on different filesystems]' \
+'--one-file-system[Skip directories on different filesystems]' \
 '--top-down[Print the tree top-down instead of bottom-up]' \
 '--align-right[Set the root of the bars to the right]' \
 '--no-sort[Do not sort the branches in the tree]' \

exports/long.help

@@ -31,6 +31,9 @@ Options:
 
           [aliases: --detect-links, --dedupe-links]
 
+  -x, --one-file-system
+          Skip directories on different filesystems
+
       --top-down
           Print the tree top-down instead of bottom-up
 

exports/short.help

@@ -14,6 +14,8 @@ Options:
           How to display the numbers of bytes [default: metric] [possible values: plain, metric, binary]
   -H, --deduplicate-hardlinks
           Detect and subtract the sizes of hardlinks from their parent directory totals [aliases: --detect-links, --dedupe-links]
+  -x, --one-file-system
+          Skip directories on different filesystems
       --top-down
           Print the tree top-down instead of bottom-up
       --align-right

src/app.rs

@@ -5,6 +5,7 @@ pub use sub::Sub;
 use crate::{
     args::{Args, Quantity, Threads},
     bytes_format::BytesFormat,
+    device::DeviceBoundary,
     get_size::{GetApparentSize, GetSize},
     hardlink,
     json_data::{JsonData, JsonDataBody, JsonShared, JsonTree},
@@ -133,6 +134,13 @@ impl App {
                 .pipe(Err);
         }
 
+        #[cfg(not(unix))]
+        if self.args.one_file_system {
+            return crate::runtime_error::UnsupportedFeature::OneFileSystem
+                .pipe(RuntimeError::UnsupportedFeature)
+                .pipe(Err);
+        }
+
         let threads = match self.args.threads {
             Threads::Auto => {
                 let disks = Disks::new_with_refreshed_list();
@@ -283,6 +291,7 @@ impl App {
                     progress: $progress,
                     #[cfg(unix)] deduplicate_hardlinks: $hardlinks,
                     #[cfg(not(unix))] deduplicate_hardlinks: _,
+                    one_file_system,
                     files,
                     json_output,
                     bytes_format,
@@ -299,6 +308,7 @@ impl App {
                     bar_alignment: BarAlignment::from_align_right(align_right),
                     size_getter: <$size_getter as GetSizeUtils>::INSTANCE,
                     hardlinks_handler: <$size_getter as CreateHardlinksHandler<{ cfg!(unix) && $hardlinks }, $progress>>::create_hardlinks_handler(),
+                    device_boundary: DeviceBoundary::from_one_file_system(one_file_system),
                     reporter: <$size_getter as CreateReporter<$progress>>::create_reporter(report_error),
                     bytes_format: <$size_getter as GetSizeUtils>::formatter(bytes_format),
                     files,

src/app/sub.rs

@@ -1,6 +1,7 @@
 use crate::{
     args::{Depth, Fraction},
     data_tree::DataTree,
+    device::DeviceBoundary,
     fs_tree_builder::FsTreeBuilder,
     get_size::GetSize,
     hardlink::{DeduplicateSharedSize, HardlinkIgnorant, RecordHardlinks},
@@ -43,6 +44,8 @@ where
     pub size_getter: SizeGetter,
     /// Handle to detect, record, and deduplicate hardlinks.
     pub hardlinks_handler: HardlinksHandler,
+    /// Whether to cross device boundary into a different filesystem.
+    pub device_boundary: DeviceBoundary,
     /// Reports measurement progress.
     pub reporter: Report,
     /// Minimal size proportion required to appear.
@@ -71,6 +74,7 @@ where
             max_depth,
             size_getter,
             hardlinks_handler,
+            device_boundary,
             reporter,
             min_ratio,
             no_sort,
@@ -86,6 +90,7 @@ where
                     root,
                     size_getter,
                     hardlinks_recorder: &hardlinks_handler,
+                    device_boundary,
                     max_depth,
                 }
                 .into()

src/args.rs

@@ -94,7 +94,7 @@ pub struct Args {
     /// Read JSON data from stdin.
     #[clap(
         long,
-        conflicts_with_all = ["quantity", "deduplicate_hardlinks"]
+        conflicts_with_all = ["quantity", "deduplicate_hardlinks", "one_file_system"]
     )]
     pub json_input: bool,
 
@@ -112,6 +112,11 @@ pub struct Args {
     #[cfg_attr(not(unix), clap(hide = true))]
     pub deduplicate_hardlinks: bool,
 
+    /// Skip directories on different filesystems.
+    #[clap(long, short = 'x')]
+    #[cfg_attr(not(unix), clap(hide = true))]
+    pub one_file_system: bool,
+
     /// Print the tree top-down instead of bottom-up.
     #[clap(long)]
     pub top_down: bool,

src/device.rs

@@ -0,0 +1,17 @@
+/// Whether to cross device boundary into a different filesystem.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum DeviceBoundary {
+    Cross,
+    Stay,
+}
+
+impl DeviceBoundary {
+    /// Derive device boundary from `--one-file-system`.
+    #[cfg(feature = "cli")]
+    pub(crate) fn from_one_file_system(one_file_system: bool) -> Self {
+        match one_file_system {
+            false => DeviceBoundary::Cross,
+            true => DeviceBoundary::Stay,
+        }
+    }
+}