rhg: add resolve_file_args to path_utils.rs

Extracted logic for resolving `FILE ...` arguments from cat.rs into a new
function in path_utils.rs. I plan to use this for rhg annotate.

I tried to reuse hg::utils::files::canonical_path instead, but that didn't work.
For example it reports a InsideDotHg error for any path containing "..".

rust/rhg/src/commands/cat.rs

@@ -1,116 +1,78
 use crate::error::CommandError;
+use crate::utils::path_utils::resolve_file_args;
 use clap::Arg;
 use format_bytes::format_bytes;
 use hg::operations::cat;
-use hg::utils::hg_path::HgPathBuf;
 use std::ffi::OsString;
-use std::os::unix::prelude::OsStrExt;
 
 pub const HELP_TEXT: &str = "
 Output the current or given revision of files
 ";
 
 pub fn args() -> clap::Command {
     clap::command!("cat")
         .arg(
             Arg::new("rev")
                 .help("search the repository as it is in REV")
                 .short('r')
                 .long("rev")
                 .value_name("REV"),
         )
         .arg(
             clap::Arg::new("files")
                 .required(true)
                 .num_args(1..)
                 .value_name("FILE")
                 .value_parser(clap::value_parser!(std::ffi::OsString))
                 .help("Files to output"),
         )
         .about(HELP_TEXT)
 }
 
 #[logging_timer::time("trace")]
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     let cat_enabled = invocation.config.get_bool(b"rhg", b"cat")?;
     if !cat_enabled {
         return Err(CommandError::unsupported(
             "cat is disabled in rhg (enable it with 'rhg.cat = true' \
             or enable fallback with 'rhg.on-unsupported = fallback')",
         ));
     }
 
-    let rev = invocation.subcommand_args.get_one::<String>("rev");
-    let file_args =
-        match invocation.subcommand_args.get_many::<OsString>("files") {
-            Some(files) => files
-                .filter(|s| !s.is_empty())
-                .map(|s| s.as_os_str())
-                .collect(),
-            None => vec![],
-        };
-
     let repo = invocation.repo?;
-    let cwd = hg::utils::current_dir()?;
-    let working_directory = repo.working_directory_path();
-    let working_directory = cwd.join(working_directory); // Make it absolute
-
-    let mut files = vec![];
-    for file in file_args {
-        if file.as_bytes().starts_with(b"set:") {
-            let message = "fileset";
-            return Err(CommandError::unsupported(message));
-        }
 
-        let normalized = cwd.join(file);
-        // TODO: actually normalize `..` path segments etc?
-        let dotted = normalized.components().any(|c| c.as_os_str() == "..");
-        if file.as_bytes() == b"." || dotted {
-            let message = "`..` or `.` path segment";
-            return Err(CommandError::unsupported(message));
-        }
-        let relative_path = working_directory
-            .strip_prefix(&cwd)
-            .unwrap_or(&working_directory);
-        let stripped = normalized
-            .strip_prefix(&working_directory)
-            .map_err(|_| {
-                CommandError::abort(format!(
-                    "abort: {} not under root '{}'\n(consider using '--cwd {}')",
-                    String::from_utf8_lossy(file.as_bytes()),
-                    working_directory.display(),
-                    relative_path.display(),
-                ))
-            })?;
-        let hg_file = HgPathBuf::try_from(stripped.to_path_buf())
-            .map_err(|e| CommandError::abort(e.to_string()))?;
-        files.push(hg_file);
-    }
+    let rev = invocation.subcommand_args.get_one::<String>("rev");
+    let files = match invocation.subcommand_args.get_many::<OsString>("files")
+    {
+        None => vec![],
+        Some(files) => resolve_file_args(repo, files)?,
+    };
+
     let files = files.iter().map(|file| file.as_ref()).collect();
     // TODO probably move this to a util function like `repo.default_rev` or
     // something when it's used somewhere else
     let rev = match rev {
         Some(r) => r.to_string(),
         None => format!("{:x}", repo.dirstate_parents()?.p1),
     };
 
     let output = cat(repo, &rev, files)?;
     for (_file, contents) in output.results {
         invocation.ui.write_stdout(&contents)?;
     }
     if !output.missing.is_empty() {
         let short = format!("{:x}", output.node.short()).into_bytes();
         for path in &output.missing {
             invocation.ui.write_stderr(&format_bytes!(
                 b"{}: no such file in rev {}\n",
                 path.as_bytes(),
                 short
             ))?;
         }
     }
     if output.found_any {
         Ok(())
     } else {
         Err(CommandError::Unsuccessful)
     }
 }

rust/rhg/src/utils/path_utils.rs

@@ -1,55 +1,96
 // path utils module
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use hg::errors::HgError;
 use hg::repo::Repo;
 use hg::utils::current_dir;
 use hg::utils::files::{get_bytes_from_path, relativize_path};
 use hg::utils::hg_path::HgPath;
 use hg::utils::hg_path::HgPathBuf;
 use std::borrow::Cow;
+use std::ffi::OsString;
+
+use crate::error::CommandError;
 
 pub struct RelativizePaths {
     repo_root: HgPathBuf,
     cwd: HgPathBuf,
     outside_repo: bool,
 }
 
 impl RelativizePaths {
     pub fn new(repo: &Repo) -> Result<Self, HgError> {
         let cwd = current_dir()?;
         let repo_root = repo.working_directory_path();
         let repo_root = cwd.join(repo_root); // Make it absolute
         let repo_root_hgpath =
             HgPathBuf::from(get_bytes_from_path(&repo_root));
 
         if let Ok(cwd_relative_to_repo) = cwd.strip_prefix(&repo_root) {
             // The current directory is inside the repo, so we can work with
             // relative paths
             Ok(Self {
                 repo_root: repo_root_hgpath,
                 cwd: HgPathBuf::from(get_bytes_from_path(
                     cwd_relative_to_repo,
                 )),
                 outside_repo: false,
             })
         } else {
             Ok(Self {
                 repo_root: repo_root_hgpath,
                 cwd: HgPathBuf::from(get_bytes_from_path(cwd)),
                 outside_repo: true,
             })
         }
     }
 
     pub fn relativize<'a>(&self, path: &'a HgPath) -> Cow<'a, [u8]> {
         if self.outside_repo {
             let joined = self.repo_root.join(path);
             Cow::Owned(relativize_path(&joined, &self.cwd).into_owned())
         } else {
             relativize_path(path, &self.cwd)
         }
     }
 }
+
+/// Resolves `FILE ...` arguments to a list of paths in the repository.
+pub fn resolve_file_args<'a>(
+    repo: &Repo,
+    file_args: impl Iterator<Item = &'a OsString>,
+) -> Result<Vec<HgPathBuf>, CommandError> {
+    let cwd = hg::utils::current_dir()?;
+    let root = cwd.join(repo.working_directory_path());
+    let mut result = Vec::new();
+    for pattern in file_args {
+        // TODO: Support all the formats in `hg help patterns`.
+        if pattern.as_encoded_bytes().contains(&b':') {
+            return Err(CommandError::unsupported(
+                "rhg does not support file patterns",
+            ));
+        }
+        // TODO: use hg::utils::files::canonical_path (currently doesn't work).
+        let path = cwd.join(pattern);
+        let dotted = path.components().any(|c| c.as_os_str() == "..");
+        if pattern.as_encoded_bytes() == b"." || dotted {
+            let message = "`..` or `.` path segment";
+            return Err(CommandError::unsupported(message));
+        }
+        let relative_path = root.strip_prefix(&cwd).unwrap_or(&root);
+        let stripped = path.strip_prefix(&root).map_err(|_| {
+            CommandError::abort(format!(
+                "abort: {} not under root '{}'\n(consider using '--cwd {}')",
+                String::from_utf8_lossy(pattern.as_encoded_bytes()),
+                root.display(),
+                relative_path.display(),
+            ))
+        })?;
+        let hg_file = HgPathBuf::try_from(stripped.to_path_buf())
+            .map_err(|e| CommandError::abort(e.to_string()))?;
+        result.push(hg_file);
+    }
+    Ok(result)
+}

tests/test-rhg.t

@@ -1,458 +1,458
 #require rhg
 
   $ NO_FALLBACK="env RHG_ON_UNSUPPORTED=abort"
 
 Unimplemented command
   $ $NO_FALLBACK rhg unimplemented-command
   unsupported feature: error: unrecognized subcommand 'unimplemented-command'
   
   Usage: rhg [OPTIONS] <COMMAND>
   
   For more information, try '--help'.
   
   [252]
   $ rhg unimplemented-command --config rhg.on-unsupported=abort-silent
   [252]
 
 Finding root
   $ $NO_FALLBACK rhg root
   abort: no repository found in '$TESTTMP' (.hg not found)!
   [255]
 
   $ hg init repository
   $ cd repository
   $ $NO_FALLBACK rhg root
   $TESTTMP/repository
 
 Reading and setting configuration
   $ echo "[ui]" >> $HGRCPATH
   $ echo "username = user1" >> $HGRCPATH
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "sparse =" >> $HGRCPATH
   $ $NO_FALLBACK rhg config ui.username
   user1
   $ echo "[ui]" >> .hg/hgrc
   $ echo "username = user2" >> .hg/hgrc
   $ $NO_FALLBACK rhg config ui.username
   user2
   $ $NO_FALLBACK rhg --config ui.username=user3 config ui.username
   user3
 
 Unwritable file descriptor
   $ $NO_FALLBACK rhg root > /dev/full
   abort: No space left on device (os error 28)
   [255]
 
 Deleted repository
   $ rm -rf `pwd`
   $ $NO_FALLBACK rhg root
   abort: error getting current working directory: $ENOENT$
   [255]
 
 Listing tracked files
   $ cd $TESTTMP
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3; do
   >   echo $i >> file$i
   >   hg add file$i
   > done
   > hg commit -m "commit $i" -q
 
 Listing tracked files from root
   $ $NO_FALLBACK rhg files
   file1
   file2
   file3
 
 Listing tracked files from subdirectory
   $ mkdir -p path/to/directory
   $ cd path/to/directory
   $ $NO_FALLBACK rhg files
   ../../../file1
   ../../../file2
   ../../../file3
 
   $ $NO_FALLBACK rhg files --config ui.relative-paths=legacy
   ../../../file1
   ../../../file2
   ../../../file3
 
   $ $NO_FALLBACK rhg files --config ui.relative-paths=false
   file1
   file2
   file3
 
   $ $NO_FALLBACK rhg files --config ui.relative-paths=true
   ../../../file1
   ../../../file2
   ../../../file3
 
 Listing tracked files through broken pipe
   $ $NO_FALLBACK rhg files | head -n 1
   ../../../file1
 
 Status with --rev and --change
   $ cd $TESTTMP/repository
   $ $NO_FALLBACK rhg status --change null
   $ $NO_FALLBACK rhg status --change 0
   A file1
   A file2
   A file3
   $ $NO_FALLBACK rhg status --rev null --rev 0
   A file1
   A file2
   A file3
 
 Status with --change --copies
   $ hg copy file2 file2copy
   $ hg rename file3 file3rename
   $ hg commit -m "commit 4" -q
   $ $NO_FALLBACK rhg status --change . --copies
   A file2copy
     file2
   A file3rename
     file3
   R file3
 
 Debuging data in inline index
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ for i in 1 2 3 4 5 6; do
   >   echo $i >> file-$i
   >   hg add file-$i
   >   hg commit -m "Commit $i" -q
   > done
   $ $NO_FALLBACK rhg debugdata -c 2
   8d0267cb034247ebfa5ee58ce59e22e57a492297
   test
   0 0
   file-3
   
   Commit 3 (no-eol)
   $ $NO_FALLBACK rhg debugdata -m 2
   file-1\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   file-2\x005d9299349fc01ddd25d0070d149b124d8f10411e (esc)
   file-3\x002661d26c649684b482d10f91960cc3db683c38b4 (esc)
 
 Debuging with full node id
   $ $NO_FALLBACK rhg debugdata -c `hg log -r 0 -T '{node}'`
   d1d1c679d3053e8926061b6f45ca52009f011e3f
   test
   0 0
   file-1
   
   Commit 1 (no-eol)
 
 Specifying revisions by changeset ID
   $ hg log -T '{node}\n'
   c6ad58c44207b6ff8a4fbbca7045a5edaa7e908b
   d654274993d0149eecc3cc03214f598320211900
   f646af7e96481d3a5470b695cf30ad8e3ab6c575
   cf8b83f14ead62b374b6e91a0e9303b85dfd9ed7
   91c6f6e73e39318534dc415ea4e8a09c99cd74d6
   6ae9681c6d30389694d8701faf24b583cf3ccafe
   $ $NO_FALLBACK rhg files -r cf8b83
   file-1
   file-2
   file-3
   $ $NO_FALLBACK rhg cat -r cf8b83 file-2
   2
   $ $NO_FALLBACK rhg cat --rev cf8b83 file-2
   2
   $ $NO_FALLBACK rhg cat -r c file-2
   abort: ambiguous revision identifier: c
   [255]
   $ $NO_FALLBACK rhg cat -r d file-2
   2
   $ $NO_FALLBACK rhg cat -r 0000 file-2
   file-2: no such file in rev 000000000000
   [1]
 
 Cat files
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg init repository
   $ cd repository
   $ echo "original content" > original
   $ hg add original
   $ hg commit -m "add original" original
 Without `--rev`
   $ $NO_FALLBACK rhg cat original
   original content
 With `--rev`
   $ $NO_FALLBACK rhg cat -r 0 original
   original content
 Cat copied file should not display copy metadata
   $ hg copy original copy_of_original
   $ hg commit -m "add copy of original"
   $ $NO_FALLBACK rhg cat original
   original content
   $ $NO_FALLBACK rhg cat -r 1 copy_of_original
   original content
 
 
 Fallback to Python
   $ $NO_FALLBACK rhg cat original --exclude="*.rs"
   unsupported feature: error: unexpected argument '--exclude' found
   
     tip: to pass '--exclude' as a value, use '-- --exclude'
   
   Usage: rhg cat <FILE>...
   
   For more information, try '--help'.
   
   [252]
   $ rhg cat original --exclude="*.rs"
   original content
 
 Check that `fallback-immediately` overrides `$NO_FALLBACK`
   $ $NO_FALLBACK rhg cat original --exclude="*.rs" --config rhg.fallback-immediately=1
   original content
 
   $ (unset RHG_FALLBACK_EXECUTABLE; rhg cat original --exclude="*.rs")
   abort: 'rhg.on-unsupported=fallback' without 'rhg.fallback-executable' set.
   [255]
 
   $ (unset RHG_FALLBACK_EXECUTABLE; rhg cat original)
   original content
 
   $ rhg cat original --exclude="*.rs" --config rhg.fallback-executable=false
   [1]
 
   $ rhg cat original --exclude="*.rs" --config rhg.fallback-executable=hg-non-existent
   abort: invalid fallback 'hg-non-existent': cannot find binary path
   [253]
 
   $ rhg cat original --exclude="*.rs" --config rhg.fallback-executable=rhg
   Blocking recursive fallback. The 'rhg.fallback-executable = rhg' config points to `rhg` itself.
   unsupported feature: error: unexpected argument '--exclude' found
   
     tip: to pass '--exclude' as a value, use '-- --exclude'
   
   Usage: rhg cat <FILE>...
   
   For more information, try '--help'.
   
   [252]
 
 Fallback with shell path segments
   $ $NO_FALLBACK rhg cat .
   unsupported feature: `..` or `.` path segment
   [252]
   $ $NO_FALLBACK rhg cat ..
   unsupported feature: `..` or `.` path segment
   [252]
   $ $NO_FALLBACK rhg cat ../..
   unsupported feature: `..` or `.` path segment
   [252]
 
 Fallback with filesets
   $ $NO_FALLBACK rhg cat "set:c or b"
-  unsupported feature: fileset
+  unsupported feature: rhg does not support file patterns
   [252]
 
 Fallback with generic hooks
   $ $NO_FALLBACK rhg cat original --config hooks.pre-cat=something
   unsupported feature: pre-cat hook defined
   [252]
 
   $ $NO_FALLBACK rhg cat original --config hooks.post-cat=something
   unsupported feature: post-cat hook defined
   [252]
 
   $ $NO_FALLBACK rhg cat original --config hooks.fail-cat=something
   unsupported feature: fail-cat hook defined
   [252]
 
 Fallback with [defaults]
   $ $NO_FALLBACK rhg cat original --config "defaults.cat=-r null"
   unsupported feature: `defaults` config set
   [252]
 
 
 Requirements
   $ $NO_FALLBACK rhg debugrequirements
   dotencode
   fncache
   generaldelta
   persistent-nodemap
   revlog-compression-zstd (zstd !)
   revlogv1
   share-safe
   sparserevlog
   store
 
   $ echo indoor-pool >> .hg/requires
   $ $NO_FALLBACK rhg files
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ $NO_FALLBACK rhg cat -r 1 copy_of_original
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ $NO_FALLBACK rhg debugrequirements
   unsupported feature: repository requires feature unknown to this Mercurial: indoor-pool
   [252]
 
   $ echo -e '\xFF' >> .hg/requires
   $ $NO_FALLBACK rhg debugrequirements
   abort: parse error in 'requires' file
   [255]
 
 Persistent nodemap
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg --config format.use-persistent-nodemap=no init repository
   $ cd repository
   $ $NO_FALLBACK rhg debugrequirements | grep nodemap
   [1]
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   $ $NO_FALLBACK rhg files -r c3ae8dec9fad
   of
 
   $ cd $TESTTMP
   $ rm -rf repository
   $ hg --config format.use-persistent-nodemap=True init repository
   $ cd repository
   $ $NO_FALLBACK rhg debugrequirements | grep nodemap
   persistent-nodemap
   $ hg debugbuilddag .+5000 --overwritten-file --config "storage.revlog.nodemap.mode=warn"
   $ hg id -r tip
   c3ae8dec9fad tip
   $ ls .hg/store/00changelog*
   .hg/store/00changelog-*.nd (glob)
   .hg/store/00changelog.d
   .hg/store/00changelog.i
   .hg/store/00changelog.n
 
 Rhg status on a sparse repo with nodemap (this specific combination used to crash in 6.5.2)
 
   $ hg debugsparse -X excluded-dir
   $ $NO_FALLBACK rhg status
 
 Specifying revisions by changeset ID
   $ $NO_FALLBACK rhg files -r c3ae8dec9fad
   of
   $ $NO_FALLBACK rhg cat -r c3ae8dec9fad of
   r5000
 
 Crate a shared repository
 
   $ echo "[extensions]"      >> $HGRCPATH
   $ echo "share = "          >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo1
   $ echo a > repo1/a
   $ hg -R repo1 commit -A -m'init'
   adding a
 
   $ hg share repo1 repo2
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ $NO_FALLBACK rhg files -R repo2
   repo2/a
   $ $NO_FALLBACK rhg -R repo2 cat -r 0 repo2/a
   a
 
 Same with relative sharing
 
   $ hg share repo2 repo3 --relative
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ $NO_FALLBACK rhg files -R repo3
   repo3/a
   $ $NO_FALLBACK rhg -R repo3 cat -r 0 repo3/a
   a
 
 Same with share-safe
 
   $ echo "[format]"         >> $HGRCPATH
   $ echo "use-share-safe = True" >> $HGRCPATH
 
   $ cd $TESTTMP
   $ hg init repo4
   $ cd repo4
   $ echo a > a
   $ hg commit -A -m'init'
   adding a
 
   $ cd ..
   $ hg share repo4 repo5
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 And check that basic rhg commands work with sharing
 
   $ cd repo5
   $ $NO_FALLBACK rhg files
   a
   $ $NO_FALLBACK rhg cat -r 0 a
   a
 
 The blackbox extension is supported
 
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "blackbox =" >> $HGRCPATH
   $ echo "[blackbox]" >> $HGRCPATH
   $ echo "maxsize = 1" >> $HGRCPATH
   $ $NO_FALLBACK rhg files > /dev/null
   $ cat .hg/blackbox.log
   ????-??-?? ??:??:??.??? * @d3873e73d99ef67873dac33fbcc66268d5d2b6f4 (*)> (rust) files exited 0 after * seconds (glob)
   $ cat .hg/blackbox.log.1
   ????-??-?? ??:??:??.??? * @d3873e73d99ef67873dac33fbcc66268d5d2b6f4 (*)> (rust) files (glob)
 
 Subrepos are not supported
 
   $ touch .hgsub
   $ $NO_FALLBACK rhg files
   unsupported feature: subrepos (.hgsub is present)
   [252]
   $ rhg files
   a
   $ rm .hgsub
 
 The `:required` extension suboptions are correctly ignored
 
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "blackbox:required = yes" >> $HGRCPATH
   $ rhg files
   a
   $ echo "*:required = yes" >> $HGRCPATH
   $ rhg files
   a
 
 Check that we expand both user and environment in ignore includes (HOME is TESTTMP)
 
   $ echo "specificprefix" > ~/ignore.expected-extension
   $ touch specificprefix
   $ $NO_FALLBACK rhg st
   ? specificprefix
   $ $NO_FALLBACK RHG_EXT_TEST=expected-extension rhg st --config 'ui.ignore=~/ignore.${RHG_EXT_TEST}'
 
 We can ignore all extensions at once
 
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "thisextensionbetternotexist=" >> $HGRCPATH
   $ echo "thisextensionbetternotexisteither=" >> $HGRCPATH
   $ $NO_FALLBACK rhg files
   unsupported feature: extensions: thisextensionbetternotexist, thisextensionbetternotexisteither (consider adding them to 'rhg.ignored-extensions' config)
   [252]
 
   $ echo "[rhg]" >> $HGRCPATH
   $ echo "ignored-extensions=*" >> $HGRCPATH
   $ $NO_FALLBACK rhg files
   a