rust-status: fix issue6456 for the Rust implementation also

This implementation is being used by a few people now, so we need it fixed, even
though a big rewrite will be coming quite soon.

Differential Revision: https://phab.mercurial-scm.org/D10217

rust/hg-core/src/dirstate/status.rs

@@ -1,988 +1,994 b''
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
 #[cfg(feature = "dirstate-tree")]
 use crate::dirstate::dirstate_tree::iter::StatusShortcut;
 #[cfg(not(feature = "dirstate-tree"))]
 use crate::utils::path_auditor::PathAuditor;
 use crate::{
     dirstate::SIZE_FROM_OTHER_PARENT,
     filepatterns::PatternFileWarning,
     matchers::{get_ignore_function, Matcher, VisitChildrenSet},
     utils::{
         files::{find_dirs, HgMetadata},
         hg_path::{
             hg_path_to_path_buf, os_string_to_hg_path_buf, HgPath, HgPathBuf,
             HgPathError,
         },
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState, FastHashMap,
     PatternError,
 };
 use lazy_static::lazy_static;
 use micro_timer::timed;
 use rayon::prelude::*;
 use std::{
     borrow::Cow,
     collections::HashSet,
     fmt,
     fs::{read_dir, DirEntry},
     io::ErrorKind,
     ops::Deref,
     path::{Path, PathBuf},
 };
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug, Copy, Clone)]
 pub enum BadType {
     CharacterDevice,
     BlockDevice,
     FIFO,
     Socket,
     Directory,
     Unknown,
 }
 
 impl fmt::Display for BadType {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         f.write_str(match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         })
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// Enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 #[derive(Debug, Copy, Clone)]
 pub enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
     Ignored,
     /// Empty dispatch, the file is not worth listing
     None,
     /// Was explicitly matched but cannot be found/accessed
     Bad(BadMatch),
     Directory {
         /// True if the directory used to be a file in the dmap so we can say
         /// that it's been removed.
         was_file: bool,
     },
 }
 
 type IoResult<T> = std::io::Result<T>;
 
 /// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait, 'static>`, so add
 /// an explicit lifetime here to not fight `'static` bounds "out of nowhere".
 type IgnoreFnType<'a> = Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>;
 
 /// We have a good mix of owned (from directory traversal) and borrowed (from
 /// the dirstate/explicit) paths, this comes up a lot.
 pub type HgPathCow<'a> = Cow<'a, HgPath>;
 
 /// A path with its computed ``Dispatch`` information
 type DispatchedPath<'a> = (HgPathCow<'a>, Dispatch);
 
 /// The conversion from `HgPath` to a real fs path failed.
 /// `22` is the error code for "Invalid argument"
 const INVALID_PATH_DISPATCH: Dispatch = Dispatch::Bad(BadMatch::OsError(22));
 
 /// Dates and times that are outside the 31-bit signed range are compared
 /// modulo 2^31. This should prevent hg from behaving badly with very large
 /// files or corrupt dates while still having a high probability of detecting
 /// changes. (issue2608)
 /// TODO I haven't found a way of having `b` be `Into<i32>`, since `From<u64>`
 /// is not defined for `i32`, and there is no `As` trait. This forces the
 /// caller to cast `b` as `i32`.
 fn mod_compare(a: i32, b: i32) -> bool {
     a & i32::max_value() != b & i32::max_value()
 }
 
 /// Return a sorted list containing information about the entries
 /// in the directory.
 ///
 /// * `skip_dot_hg` - Return an empty vec if `path` contains a `.hg` directory
 fn list_directory(
     path: impl AsRef<Path>,
     skip_dot_hg: bool,
 ) -> std::io::Result<Vec<(HgPathBuf, DirEntry)>> {
     let mut results = vec![];
     let entries = read_dir(path.as_ref())?;
 
     for entry in entries {
         let entry = entry?;
         let filename = os_string_to_hg_path_buf(entry.file_name())?;
         let file_type = entry.file_type()?;
         if skip_dot_hg && filename.as_bytes() == b".hg" && file_type.is_dir() {
             return Ok(vec![]);
         } else {
             results.push((filename, entry))
         }
     }
 
     results.sort_unstable_by_key(|e| e.0.clone());
     Ok(results)
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
     options: StatusOptions,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
                 (mode ^ st_mode as i32) & 0o100 != 0o000 && options.check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
             let other_parent = size == SIZE_FROM_OTHER_PARENT;
 
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
-                Dispatch::Modified
+                if metadata.is_symlink() && size_changed {
+                    // issue6456: Size returned may be longer due to encryption
+                    // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
+                    Dispatch::Unsure
+                } else {
+                    Dispatch::Modified
+                }
             } else if mod_compare(mtime, st_mtime as i32)
                 || st_mtime == options.last_normal_time
             {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
             } else if options.list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::None
             }
         }
         EntryState::Merged => Dispatch::Modified,
         EntryState::Added => Dispatch::Added,
         EntryState::Removed => Dispatch::Removed,
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// The file corresponding to this Dirstate entry is missing.
 fn dispatch_missing(state: EntryState) -> Dispatch {
     match state {
         // File was removed from the filesystem during commands
         EntryState::Normal | EntryState::Merged | EntryState::Added => {
             Dispatch::Deleted
         }
         // File was removed, everything is normal
         EntryState::Removed => Dispatch::Removed,
         // File is unknown to Mercurial, everything is normal
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 fn dispatch_os_error(e: &std::io::Error) -> Dispatch {
     Dispatch::Bad(BadMatch::OsError(
         e.raw_os_error().expect("expected real OS error"),
     ))
 }
 
 lazy_static! {
     static ref DEFAULT_WORK: HashSet<&'static HgPath> = {
         let mut h = HashSet::new();
         h.insert(HgPath::new(b""));
         h
     };
 }
 
 #[derive(Debug, Copy, Clone)]
 pub struct StatusOptions {
     /// Remember the most recent modification timeslot for status, to make
     /// sure we won't miss future size-preserving file content modifications
     /// that happen within the same timeslot.
     pub last_normal_time: i64,
     /// Whether we are on a filesystem with UNIX-like exec flags
     pub check_exec: bool,
     pub list_clean: bool,
     pub list_unknown: bool,
     pub list_ignored: bool,
     /// Whether to collect traversed dirs for applying a callback later.
     /// Used by `hg purge` for example.
     pub collect_traversed_dirs: bool,
 }
 
 #[derive(Debug)]
 pub struct DirstateStatus<'a> {
     pub modified: Vec<HgPathCow<'a>>,
     pub added: Vec<HgPathCow<'a>>,
     pub removed: Vec<HgPathCow<'a>>,
     pub deleted: Vec<HgPathCow<'a>>,
     pub clean: Vec<HgPathCow<'a>>,
     pub ignored: Vec<HgPathCow<'a>>,
     pub unknown: Vec<HgPathCow<'a>>,
     pub bad: Vec<(HgPathCow<'a>, BadMatch)>,
     /// Only filled if `collect_traversed_dirs` is `true`
     pub traversed: Vec<HgPathBuf>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum StatusError {
     /// Generic IO error
     IO(std::io::Error),
     /// An invalid path that cannot be represented in Mercurial was found
     Path(HgPathError),
     /// An invalid "ignore" pattern was found
     Pattern(PatternError),
 }
 
 pub type StatusResult<T> = Result<T, StatusError>;
 
 impl fmt::Display for StatusError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             StatusError::IO(error) => error.fmt(f),
             StatusError::Path(error) => error.fmt(f),
             StatusError::Pattern(error) => error.fmt(f),
         }
     }
 }
 
 /// Gives information about which files are changed in the working directory
 /// and how, compared to the revision we're based on
 pub struct Status<'a, M: Matcher + Sync> {
     dmap: &'a DirstateMap,
     pub(crate) matcher: &'a M,
     root_dir: PathBuf,
     pub(crate) options: StatusOptions,
     ignore_fn: IgnoreFnType<'a>,
 }
 
 impl<'a, M> Status<'a, M>
 where
     M: Matcher + Sync,
 {
     pub fn new(
         dmap: &'a DirstateMap,
         matcher: &'a M,
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> StatusResult<(Self, Vec<PatternFileWarning>)> {
         // Needs to outlive `dir_ignore_fn` since it's captured.
 
         let (ignore_fn, warnings): (IgnoreFnType, _) =
             if options.list_ignored || options.list_unknown {
                 get_ignore_function(ignore_files, &root_dir)?
             } else {
                 (Box::new(|&_| true), vec![])
             };
 
         Ok((
             Self {
                 dmap,
                 matcher,
                 root_dir,
                 options,
                 ignore_fn,
             },
             warnings,
         ))
     }
 
     /// Is the path ignored?
     pub fn is_ignored(&self, path: impl AsRef<HgPath>) -> bool {
         (self.ignore_fn)(path.as_ref())
     }
 
     /// Is the path or one of its ancestors ignored?
     pub fn dir_ignore(&self, dir: impl AsRef<HgPath>) -> bool {
         // Only involve ignore mechanism if we're listing unknowns or ignored.
         if self.options.list_ignored || self.options.list_unknown {
             if self.is_ignored(&dir) {
                 true
             } else {
                 for p in find_dirs(dir.as_ref()) {
                     if self.is_ignored(p) {
                         return true;
                     }
                 }
                 false
             }
         } else {
             true
         }
     }
 
     /// Get stat data about the files explicitly specified by the matcher.
     /// Returns a tuple of the directories that need to be traversed and the
     /// files with their corresponding `Dispatch`.
     /// TODO subrepos
     #[timed]
     pub fn walk_explicit(
         &self,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) -> (Vec<DispatchedPath<'a>>, Vec<DispatchedPath<'a>>) {
         self.matcher
             .file_set()
             .unwrap_or(&DEFAULT_WORK)
             .par_iter()
             .flat_map(|&filename| -> Option<_> {
                 // TODO normalization
                 let normalized = filename;
 
                 let buf = match hg_path_to_path_buf(normalized) {
                     Ok(x) => x,
                     Err(_) => {
                         return Some((
                             Cow::Borrowed(normalized),
                             INVALID_PATH_DISPATCH,
                         ))
                     }
                 };
                 let target = self.root_dir.join(buf);
                 let st = target.symlink_metadata();
                 let in_dmap = self.dmap.get(normalized);
                 match st {
                     Ok(meta) => {
                         let file_type = meta.file_type();
                         return if file_type.is_file() || file_type.is_symlink()
                         {
                             if let Some(entry) = in_dmap {
                                 return Some((
                                     Cow::Borrowed(normalized),
                                     dispatch_found(
                                         &normalized,
                                         *entry,
                                         HgMetadata::from_metadata(meta),
                                         &self.dmap.copy_map,
                                         self.options,
                                     ),
                                 ));
                             }
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Unknown,
                             ))
                         } else if file_type.is_dir() {
                             if self.options.collect_traversed_dirs {
                                 traversed_sender
                                     .send(normalized.to_owned())
                                     .expect("receiver should outlive sender");
                             }
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Directory {
                                     was_file: in_dmap.is_some(),
                                 },
                             ))
                         } else {
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Bad(BadMatch::BadType(
                                     // TODO do more than unknown
                                     // Support for all `BadType` variant
                                     // varies greatly between platforms.
                                     // So far, no tests check the type and
                                     // this should be good enough for most
                                     // users.
                                     BadType::Unknown,
                                 )),
                             ))
                         };
                     }
                     Err(_) => {
                         if let Some(entry) = in_dmap {
                             return Some((
                                 Cow::Borrowed(normalized),
                                 dispatch_missing(entry.state),
                             ));
                         }
                     }
                 };
                 None
             })
             .partition(|(_, dispatch)| match dispatch {
                 Dispatch::Directory { .. } => true,
                 _ => false,
             })
     }
 
     /// Walk the working directory recursively to look for changes compared to
     /// the current `DirstateMap`.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[timed]
     pub fn traverse(
         &self,
         path: impl AsRef<HgPath>,
         old_results: &FastHashMap<HgPathCow<'a>, Dispatch>,
         results: &mut Vec<DispatchedPath<'a>>,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) {
         // The traversal is done in parallel, so use a channel to gather
         // entries. `crossbeam_channel::Sender` is `Sync`, while `mpsc::Sender`
         // is not.
         let (files_transmitter, files_receiver) =
             crossbeam_channel::unbounded();
 
         self.traverse_dir(
             &files_transmitter,
             path,
             &old_results,
             traversed_sender,
         );
 
         // Disconnect the channel so the receiver stops waiting
         drop(files_transmitter);
 
         let new_results = files_receiver
             .into_iter()
             .par_bridge()
             .map(|(f, d)| (Cow::Owned(f), d));
 
         results.par_extend(new_results);
     }
 
     /// Dispatch a single entry (file, folder, symlink...) found during
     /// `traverse`. If the entry is a folder that needs to be traversed, it
     /// will be handled in a separate thread.
     fn handle_traversed_entry<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         filename: HgPathBuf,
         dir_entry: DirEntry,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) -> IoResult<()>
     where
         'a: 'b,
     {
         let file_type = dir_entry.file_type()?;
         let entry_option = self.dmap.get(&filename);
 
         if filename.as_bytes() == b".hg" {
             // Could be a directory or a symlink
             return Ok(());
         }
 
         if file_type.is_dir() {
             self.handle_traversed_dir(
                 scope,
                 files_sender,
                 old_results,
                 entry_option,
                 filename,
                 traversed_sender,
             );
         } else if file_type.is_file() || file_type.is_symlink() {
             if let Some(entry) = entry_option {
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&filename)
                 {
                     let metadata = dir_entry.metadata()?;
                     files_sender
                         .send((
                             filename.to_owned(),
                             dispatch_found(
                                 &filename,
                                 *entry,
                                 HgMetadata::from_metadata(metadata),
                                 &self.dmap.copy_map,
                                 self.options,
                             ),
                         ))
                         .unwrap();
                 }
             } else if (self.matcher.matches_everything()
                 || self.matcher.matches(&filename))
                 && !self.is_ignored(&filename)
             {
                 if (self.options.list_ignored
                     || self.matcher.exact_match(&filename))
                     && self.dir_ignore(&filename)
                 {
                     if self.options.list_ignored {
                         files_sender
                             .send((filename.to_owned(), Dispatch::Ignored))
                             .unwrap();
                     }
                 } else if self.options.list_unknown {
                     files_sender
                         .send((filename.to_owned(), Dispatch::Unknown))
                         .unwrap();
                 }
             } else if self.is_ignored(&filename) && self.options.list_ignored {
                 files_sender
                     .send((filename.to_owned(), Dispatch::Ignored))
                     .unwrap();
             }
         } else if let Some(entry) = entry_option {
             // Used to be a file or a folder, now something else.
             if self.matcher.matches_everything()
                 || self.matcher.matches(&filename)
             {
                 files_sender
                     .send((filename.to_owned(), dispatch_missing(entry.state)))
                     .unwrap();
             }
         }
 
         Ok(())
     }
 
     /// A directory was found in the filesystem and needs to be traversed
     fn handle_traversed_dir<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         entry_option: Option<&'a DirstateEntry>,
         directory: HgPathBuf,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) where
         'a: 'b,
     {
         scope.spawn(move |_| {
             // Nested `if` until `rust-lang/rust#53668` is stable
             if let Some(entry) = entry_option {
                 // Used to be a file, is now a folder
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&directory)
                 {
                     files_sender
                         .send((
                             directory.to_owned(),
                             dispatch_missing(entry.state),
                         ))
                         .unwrap();
                 }
             }
             // Do we need to traverse it?
             if !self.is_ignored(&directory) || self.options.list_ignored {
                 self.traverse_dir(
                     files_sender,
                     directory,
                     &old_results,
                     traversed_sender,
                 )
             }
         });
     }
 
     /// Decides whether the directory needs to be listed, and if so handles the
     /// entries in a separate thread.
     fn traverse_dir(
         &self,
         files_sender: &crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         directory: impl AsRef<HgPath>,
         old_results: &FastHashMap<Cow<HgPath>, Dispatch>,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) {
         let directory = directory.as_ref();
 
         if self.options.collect_traversed_dirs {
             traversed_sender
                 .send(directory.to_owned())
                 .expect("receiver should outlive sender");
         }
 
         let visit_entries = match self.matcher.visit_children_set(directory) {
             VisitChildrenSet::Empty => return,
             VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
             VisitChildrenSet::Set(set) => Some(set),
         };
         let buf = match hg_path_to_path_buf(directory) {
             Ok(b) => b,
             Err(_) => {
                 files_sender
                     .send((directory.to_owned(), INVALID_PATH_DISPATCH))
                     .expect("receiver should outlive sender");
                 return;
             }
         };
         let dir_path = self.root_dir.join(buf);
 
         let skip_dot_hg = !directory.as_bytes().is_empty();
         let entries = match list_directory(dir_path, skip_dot_hg) {
             Err(e) => {
                 files_sender
                     .send((directory.to_owned(), dispatch_os_error(&e)))
                     .expect("receiver should outlive sender");
                 return;
             }
             Ok(entries) => entries,
         };
 
         rayon::scope(|scope| {
             for (filename, dir_entry) in entries {
                 if let Some(ref set) = visit_entries {
                     if !set.contains(filename.deref()) {
                         continue;
                     }
                 }
                 // TODO normalize
                 let filename = if directory.is_empty() {
                     filename.to_owned()
                 } else {
                     directory.join(&filename)
                 };
 
                 if !old_results.contains_key(filename.deref()) {
                     match self.handle_traversed_entry(
                         scope,
                         files_sender,
                         old_results,
                         filename,
                         dir_entry,
                         traversed_sender.clone(),
                     ) {
                         Err(e) => {
                             files_sender
                                 .send((
                                     directory.to_owned(),
                                     dispatch_os_error(&e),
                                 ))
                                 .expect("receiver should outlive sender");
                         }
                         Ok(_) => {}
                     }
                 }
             }
         })
     }
 
     /// Add the files in the dirstate to the results.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[cfg(feature = "dirstate-tree")]
     #[timed]
     pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
         results.par_extend(
             self.dmap
                 .fs_iter(self.root_dir.clone())
                 .par_bridge()
                 .filter(|(path, _)| self.matcher.matches(path))
                 .map(move |(filename, shortcut)| {
                     let entry = match shortcut {
                         StatusShortcut::Entry(e) => e,
                         StatusShortcut::Dispatch(d) => {
                             return (Cow::Owned(filename), d)
                         }
                     };
                     let filename_as_path = match hg_path_to_path_buf(&filename)
                     {
                         Ok(f) => f,
                         Err(_) => {
                             return (
                                 Cow::Owned(filename),
                                 INVALID_PATH_DISPATCH,
                             )
                         }
                     };
                     let meta = self
                         .root_dir
                         .join(filename_as_path)
                         .symlink_metadata();
 
                     match meta {
                         Ok(m)
                             if !(m.file_type().is_file()
                                 || m.file_type().is_symlink()) =>
                         {
                             (
                                 Cow::Owned(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Ok(m) => {
                             let dispatch = dispatch_found(
                                 &filename,
                                 entry,
                                 HgMetadata::from_metadata(m),
                                 &self.dmap.copy_map,
                                 self.options,
                             );
                             (Cow::Owned(filename), dispatch)
                         }
                         Err(e)
                             if e.kind() == ErrorKind::NotFound
                                 || e.raw_os_error() == Some(20) =>
                         {
                             // Rust does not yet have an `ErrorKind` for
                             // `NotADirectory` (errno 20)
                             // It happens if the dirstate contains `foo/bar`
                             // and foo is not a
                             // directory
                             (
                                 Cow::Owned(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Err(e) => {
                             (Cow::Owned(filename), dispatch_os_error(&e))
                         }
                     }
                 }),
         );
     }
 
     /// Add the files in the dirstate to the results.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[cfg(not(feature = "dirstate-tree"))]
     #[timed]
     pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
         results.par_extend(
             self.dmap
                 .par_iter()
                 .filter(|(path, _)| self.matcher.matches(path))
                 .map(move |(filename, entry)| {
                     let filename: &HgPath = filename;
                     let filename_as_path = match hg_path_to_path_buf(filename)
                     {
                         Ok(f) => f,
                         Err(_) => {
                             return (
                                 Cow::Borrowed(filename),
                                 INVALID_PATH_DISPATCH,
                             )
                         }
                     };
                     let meta = self
                         .root_dir
                         .join(filename_as_path)
                         .symlink_metadata();
                     match meta {
                         Ok(m)
                             if !(m.file_type().is_file()
                                 || m.file_type().is_symlink()) =>
                         {
                             (
                                 Cow::Borrowed(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Ok(m) => (
                             Cow::Borrowed(filename),
                             dispatch_found(
                                 filename,
                                 *entry,
                                 HgMetadata::from_metadata(m),
                                 &self.dmap.copy_map,
                                 self.options,
                             ),
                         ),
                         Err(e)
                             if e.kind() == ErrorKind::NotFound
                                 || e.raw_os_error() == Some(20) =>
                         {
                             // Rust does not yet have an `ErrorKind` for
                             // `NotADirectory` (errno 20)
                             // It happens if the dirstate contains `foo/bar`
                             // and foo is not a
                             // directory
                             (
                                 Cow::Borrowed(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Err(e) => {
                             (Cow::Borrowed(filename), dispatch_os_error(&e))
                         }
                     }
                 }),
         );
     }
 
     /// Checks all files that are in the dirstate but were not found during the
     /// working directory traversal. This means that the rest must
     /// be either ignored, under a symlink or under a new nested repo.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[cfg(not(feature = "dirstate-tree"))]
     #[timed]
     pub fn handle_unknowns(&self, results: &mut Vec<DispatchedPath<'a>>) {
         let to_visit: Vec<(&HgPath, &DirstateEntry)> =
             if results.is_empty() && self.matcher.matches_everything() {
                 self.dmap.iter().map(|(f, e)| (f.deref(), e)).collect()
             } else {
                 // Only convert to a hashmap if needed.
                 let old_results: FastHashMap<_, _> =
                     results.iter().cloned().collect();
                 self.dmap
                     .iter()
                     .filter_map(move |(f, e)| {
                         if !old_results.contains_key(f.deref())
                             && self.matcher.matches(f)
                         {
                             Some((f.deref(), e))
                         } else {
                             None
                         }
                     })
                     .collect()
             };
 
         let path_auditor = PathAuditor::new(&self.root_dir);
 
         let new_results = to_visit.into_par_iter().filter_map(
             |(filename, entry)| -> Option<_> {
                 // Report ignored items in the dmap as long as they are not
                 // under a symlink directory.
                 if path_auditor.check(filename) {
                     // TODO normalize for case-insensitive filesystems
                     let buf = match hg_path_to_path_buf(filename) {
                         Ok(x) => x,
                         Err(_) => {
                             return Some((
                                 Cow::Owned(filename.to_owned()),
                                 INVALID_PATH_DISPATCH,
                             ));
                         }
                     };
                     Some((
                         Cow::Owned(filename.to_owned()),
                         match self.root_dir.join(&buf).symlink_metadata() {
                             // File was just ignored, no links, and exists
                             Ok(meta) => {
                                 let metadata = HgMetadata::from_metadata(meta);
                                 dispatch_found(
                                     filename,
                                     *entry,
                                     metadata,
                                     &self.dmap.copy_map,
                                     self.options,
                                 )
                             }
                             // File doesn't exist
                             Err(_) => dispatch_missing(entry.state),
                         },
                     ))
                 } else {
                     // It's either missing or under a symlink directory which
                     // we, in this case, report as missing.
                     Some((
                         Cow::Owned(filename.to_owned()),
                         dispatch_missing(entry.state),
                     ))
                 }
             },
         );
 
         results.par_extend(new_results);
     }
 }
 
 #[timed]
 pub fn build_response<'a>(
     results: impl IntoIterator<Item = DispatchedPath<'a>>,
     traversed: Vec<HgPathBuf>,
 ) -> (Vec<HgPathCow<'a>>, DirstateStatus<'a>) {
     let mut lookup = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
     let mut ignored = vec![];
     let mut unknown = vec![];
     let mut bad = vec![];
 
     for (filename, dispatch) in results.into_iter() {
         match dispatch {
             Dispatch::Unknown => unknown.push(filename),
             Dispatch::Unsure => lookup.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
             Dispatch::Ignored => ignored.push(filename),
             Dispatch::None => {}
             Dispatch::Bad(reason) => bad.push((filename, reason)),
             Dispatch::Directory { .. } => {}
         }
     }
 
     (
         lookup,
         DirstateStatus {
             modified,
             added,
             removed,
             deleted,
             clean,
             ignored,
             unknown,
             bad,
             traversed,
         },
     )
 }
 
 /// Get the status of files in the working directory.
 ///
 /// This is the current entry-point for `hg-core` and is realistically unusable
 /// outside of a Python context because its arguments need to provide a lot of
 /// information that will not be necessary in the future.
 #[timed]
 pub fn status<'a>(
     dmap: &'a DirstateMap,
     matcher: &'a (impl Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
     Vec<PatternFileWarning>,
 )> {
     let (status, warnings) =
         Status::new(dmap, matcher, root_dir, ignore_files, options)?;
 
     Ok((status.run()?, warnings))
 }

rust/hg-core/src/utils/files.rs

@@ -1,451 +1,457 b''
 // files.rs
 //
 // Copyright 2019
 // Raphaël Gomès <[e-mail]>,
 // Yuya Nishihara <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Functions for fiddling with files.
 
 use crate::utils::{
     hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
     path_auditor::PathAuditor,
     replace_slice,
 };
 use lazy_static::lazy_static;
 use same_file::is_same_file;
 use std::borrow::{Cow, ToOwned};
 use std::ffi::OsStr;
 use std::fs::Metadata;
 use std::iter::FusedIterator;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 pub fn get_os_str_from_bytes(bytes: &[u8]) -> &OsStr {
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(bytes);
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     // Perhaps, the return type would have to be Result<PathBuf>.
     os_str
 }
 
 pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
     Path::new(get_os_str_from_bytes(bytes))
 }
 
 // TODO: need to convert from WTF8 to MBCS bytes on Windows.
 // that's why Vec<u8> is returned.
 #[cfg(unix)]
 pub fn get_bytes_from_path(path: impl AsRef<Path>) -> Vec<u8> {
     get_bytes_from_os_str(path.as_ref())
 }
 
 #[cfg(unix)]
 pub fn get_bytes_from_os_str(str: impl AsRef<OsStr>) -> Vec<u8> {
     use std::os::unix::ffi::OsStrExt;
     str.as_ref().as_bytes().to_vec()
 }
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub struct Ancestors<'a> {
     next: Option<&'a HgPath>,
 }
 
 impl<'a> Iterator for Ancestors<'a> {
     type Item = &'a HgPath;
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some(s) if s.is_empty() => None,
             Some(s) => {
                 let p = s.bytes().rposition(|c| *c == b'/').unwrap_or(0);
                 Some(HgPath::new(&s.as_bytes()[..p]))
             }
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for Ancestors<'a> {}
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub(crate) struct AncestorsWithBase<'a> {
     next: Option<(&'a HgPath, &'a HgPath)>,
 }
 
 impl<'a> Iterator for AncestorsWithBase<'a> {
     type Item = (&'a HgPath, &'a HgPath);
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some((s, _)) if s.is_empty() => None,
             Some((s, _)) => Some(s.split_filename()),
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for AncestorsWithBase<'a> {}
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub fn find_dirs(path: &HgPath) -> Ancestors {
     let mut dirs = Ancestors { next: Some(path) };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub(crate) fn find_dirs_with_base(path: &HgPath) -> AncestorsWithBase {
     let mut dirs = AncestorsWithBase {
         next: Some((path, HgPath::new(b""))),
     };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// TODO more than ASCII?
 pub fn normalize_case(path: &HgPath) -> HgPathBuf {
     #[cfg(windows)] // NTFS compares via upper()
     return path.to_ascii_uppercase();
     #[cfg(unix)]
     path.to_ascii_lowercase()
 }
 
 lazy_static! {
     static ref IGNORED_CHARS: Vec<Vec<u8>> = {
         [
             0x200c, 0x200d, 0x200e, 0x200f, 0x202a, 0x202b, 0x202c, 0x202d,
             0x202e, 0x206a, 0x206b, 0x206c, 0x206d, 0x206e, 0x206f, 0xfeff,
         ]
         .iter()
         .map(|code| {
             std::char::from_u32(*code)
                 .unwrap()
                 .encode_utf8(&mut [0; 3])
                 .bytes()
                 .collect()
         })
         .collect()
     };
 }
 
 fn hfs_ignore_clean(bytes: &[u8]) -> Vec<u8> {
     let mut buf = bytes.to_owned();
     let needs_escaping = bytes.iter().any(|b| *b == b'\xe2' || *b == b'\xef');
     if needs_escaping {
         for forbidden in IGNORED_CHARS.iter() {
             replace_slice(&mut buf, forbidden, &[])
         }
         buf
     } else {
         buf
     }
 }
 
 pub fn lower_clean(bytes: &[u8]) -> Vec<u8> {
     hfs_ignore_clean(&bytes.to_ascii_lowercase())
 }
 
 #[derive(Eq, PartialEq, Ord, PartialOrd, Copy, Clone)]
 pub struct HgMetadata {
     pub st_dev: u64,
     pub st_mode: u32,
     pub st_nlink: u64,
     pub st_size: u64,
     pub st_mtime: i64,
     pub st_ctime: i64,
 }
 
 // TODO support other plaforms
 #[cfg(unix)]
 impl HgMetadata {
     pub fn from_metadata(metadata: Metadata) -> Self {
         use std::os::unix::fs::MetadataExt;
         Self {
             st_dev: metadata.dev(),
             st_mode: metadata.mode(),
             st_nlink: metadata.nlink(),
             st_size: metadata.size(),
             st_mtime: metadata.mtime(),
             st_ctime: metadata.ctime(),
         }
     }
+
+    pub fn is_symlink(&self) -> bool {
+        // This is way too manual, but `HgMetadata` will go away in the
+        // near-future dirstate rewrite anyway.
+        self.st_mode & 0170000 == 0120000
+    }
 }
 
 /// Returns the canonical path of `name`, given `cwd` and `root`
 pub fn canonical_path(
     root: impl AsRef<Path>,
     cwd: impl AsRef<Path>,
     name: impl AsRef<Path>,
 ) -> Result<PathBuf, HgPathError> {
     // TODO add missing normalization for other platforms
     let root = root.as_ref();
     let cwd = cwd.as_ref();
     let name = name.as_ref();
 
     let name = if !name.is_absolute() {
         root.join(&cwd).join(&name)
     } else {
         name.to_owned()
     };
     let auditor = PathAuditor::new(&root);
     if name != root && name.starts_with(&root) {
         let name = name.strip_prefix(&root).unwrap();
         auditor.audit_path(path_to_hg_path_buf(name)?)?;
         Ok(name.to_owned())
     } else if name == root {
         Ok("".into())
     } else {
         // Determine whether `name' is in the hierarchy at or beneath `root',
         // by iterating name=name.parent() until it returns `None` (can't
         // check name == '/', because that doesn't work on windows).
         let mut name = name.deref();
         let original_name = name.to_owned();
         loop {
             let same = is_same_file(&name, &root).unwrap_or(false);
             if same {
                 if name == original_name {
                     // `name` was actually the same as root (maybe a symlink)
                     return Ok("".into());
                 }
                 // `name` is a symlink to root, so `original_name` is under
                 // root
                 let rel_path = original_name.strip_prefix(&name).unwrap();
                 auditor.audit_path(path_to_hg_path_buf(&rel_path)?)?;
                 return Ok(rel_path.to_owned());
             }
             name = match name.parent() {
                 None => break,
                 Some(p) => p,
             };
         }
         // TODO hint to the user about using --cwd
         // Bubble up the responsibility to Python for now
         Err(HgPathError::NotUnderRoot {
             path: original_name.to_owned(),
             root: root.to_owned(),
         })
     }
 }
 
 /// Returns the representation of the path relative to the current working
 /// directory for display purposes.
 ///
 /// `cwd` is a `HgPath`, so it is considered relative to the root directory
 /// of the repository.
 ///
 /// # Examples
 ///
 /// ```
 /// use hg::utils::hg_path::HgPath;
 /// use hg::utils::files::relativize_path;
 /// use std::borrow::Cow;
 ///
 /// let file = HgPath::new(b"nested/file");
 /// let cwd = HgPath::new(b"");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"nested/file"));
 ///
 /// let cwd = HgPath::new(b"nested");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"file"));
 ///
 /// let cwd = HgPath::new(b"other");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"../nested/file"));
 /// ```
 pub fn relativize_path(path: &HgPath, cwd: impl AsRef<HgPath>) -> Cow<[u8]> {
     if cwd.as_ref().is_empty() {
         Cow::Borrowed(path.as_bytes())
     } else {
         let mut res: Vec<u8> = Vec::new();
         let mut path_iter = path.as_bytes().split(|b| *b == b'/').peekable();
         let mut cwd_iter =
             cwd.as_ref().as_bytes().split(|b| *b == b'/').peekable();
         loop {
             match (path_iter.peek(), cwd_iter.peek()) {
                 (Some(a), Some(b)) if a == b => (),
                 _ => break,
             }
             path_iter.next();
             cwd_iter.next();
         }
         let mut need_sep = false;
         for _ in cwd_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(b"..");
         }
         for c in path_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(c);
         }
         Cow::Owned(res)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
         let mut dirs = super::find_dirs(HgPath::new(b"foo/bar/baz"));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo/bar")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn find_dirs_empty() {
         // looks weird, but mercurial.pathutil.finddirs(b"") yields b""
         let mut dirs = super::find_dirs(HgPath::new(b""));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_some() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b"foo/bar/baz"));
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo/bar"), HgPath::new(b"baz")))
         );
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo"), HgPath::new(b"bar")))
         );
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b"foo"))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_empty() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b""));
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b""))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_canonical_path() {
         let root = Path::new("/repo");
         let cwd = Path::new("/dir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/dir/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("repo/filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo/subdir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("subdir/filename"))
         );
     }
 
     #[test]
     fn test_canonical_path_not_rooted() {
         use std::fs::create_dir;
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let beneath_repo = base_dir_path.join("a");
         let root = base_dir_path.join("a/b");
         let out_of_repo = base_dir_path.join("c");
         let under_repo_symlink = out_of_repo.join("d");
 
         create_dir(&beneath_repo).unwrap();
         create_dir(&root).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
 
         assert_eq!(
             canonical_path(&root, Path::new(""), out_of_repo),
             Ok(PathBuf::from(""))
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &beneath_repo),
             Err(HgPathError::NotUnderRoot {
                 path: beneath_repo.to_owned(),
                 root: root.to_owned()
             })
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &under_repo_symlink),
             Ok(PathBuf::from("d"))
         );
     }
 }