rust-status: check for '.hg' regardless of file type (issue6300)

'.hg' would show up in `hg status` if were a symlink.

Differential Revision: https://phab.mercurial-scm.org/D8461

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

@@ -1,910 +1,913 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.
 
 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,
         },
         path_auditor::PathAuditor,
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState, FastHashMap,
     PatternError,
 };
 use lazy_static::lazy_static;
 use micro_timer::timed;
 use rayon::prelude::*;
 use std::{
     borrow::Cow,
     collections::HashSet,
     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 ToString for BadType {
     fn to_string(&self) -> String {
         match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         }
         .to_string()
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// Marker 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)]
 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>;
 
 /// 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((HgPathBuf::from(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
             } else if mod_compare(mtime, st_mtime as i32) {
                 Dispatch::Unsure
             } else if 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,
     }
 }
 
 lazy_static! {
     static ref DEFAULT_WORK: HashSet<&'static HgPath> = {
         let mut h = HashSet::new();
         h.insert(HgPath::new(b""));
         h
     };
 }
 
 /// Get stat data about the files explicitly specified by match.
 /// TODO subrepos
 #[timed]
 fn walk_explicit<'a>(
     files: Option<&'a HashSet<&HgPath>>,
     dmap: &'a DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send + 'a,
     options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&'a HgPath, Dispatch)>> {
     files
         .unwrap_or(&DEFAULT_WORK)
         .par_iter()
         .map(move |filename| {
             // TODO normalization
             let normalized = filename.as_ref();
 
             let buf = match hg_path_to_path_buf(normalized) {
                 Ok(x) => x,
                 Err(e) => return Some(Err(e.into())),
             };
             let target = root_dir.as_ref().join(buf);
             let st = target.symlink_metadata();
             let in_dmap = 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(Ok((
                                 normalized,
                                 dispatch_found(
                                     &normalized,
                                     *entry,
                                     HgMetadata::from_metadata(meta),
                                     &dmap.copy_map,
                                     options,
                                 ),
                             )));
                         }
                         Some(Ok((normalized, Dispatch::Unknown)))
                     } else {
                         if file_type.is_dir() {
                             Some(Ok((
                                 normalized,
                                 Dispatch::Directory {
                                     was_file: in_dmap.is_some(),
                                 },
                             )))
                         } else {
                             Some(Ok((
                                 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(Ok((
                             normalized,
                             dispatch_missing(entry.state),
                         )));
                     }
                 }
             };
             None
         })
         .flatten()
 }
 
 #[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,
 }
 
 /// 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<'a>(
     scope: &rayon::Scope<'a>,
     files_sender: &'a crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'a,
     dmap: &'a DirstateMap,
     old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
     ignore_fn: &'a IgnoreFnType,
     dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     filename: HgPathBuf,
     dir_entry: DirEntry,
 ) -> IoResult<()> {
     let file_type = dir_entry.file_type()?;
     let entry_option = dmap.get(&filename);
 
+    if filename.as_bytes() == b".hg" {
+        // Could be a directory or a symlink
+        return Ok(());
+    }
+
     if file_type.is_dir() {
         handle_traversed_dir(
             scope,
             files_sender,
             matcher,
             root_dir,
             dmap,
             old_results,
             ignore_fn,
             dir_ignore_fn,
             options,
             entry_option,
             filename,
         );
     } else if file_type.is_file() || file_type.is_symlink() {
         if let Some(entry) = entry_option {
             if matcher.matches_everything() || matcher.matches(&filename) {
                 let metadata = dir_entry.metadata()?;
                 files_sender
                     .send(Ok((
                         filename.to_owned(),
                         dispatch_found(
                             &filename,
                             *entry,
                             HgMetadata::from_metadata(metadata),
                             &dmap.copy_map,
                             options,
                         ),
                     )))
                     .unwrap();
             }
         } else if (matcher.matches_everything() || matcher.matches(&filename))
             && !ignore_fn(&filename)
         {
             if (options.list_ignored || matcher.exact_match(&filename))
                 && dir_ignore_fn(&filename)
             {
                 if options.list_ignored {
                     files_sender
                         .send(Ok((filename.to_owned(), Dispatch::Ignored)))
                         .unwrap();
                 }
             } else {
                 files_sender
                     .send(Ok((filename.to_owned(), Dispatch::Unknown)))
                     .unwrap();
             }
         } else if ignore_fn(&filename) && options.list_ignored {
             files_sender
                 .send(Ok((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 matcher.matches_everything() || matcher.matches(&filename) {
             files_sender
                 .send(Ok((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<'a>(
     scope: &rayon::Scope<'a>,
     files_sender: &'a crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'a,
     dmap: &'a DirstateMap,
     old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
     ignore_fn: &'a IgnoreFnType,
     dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     entry_option: Option<&'a DirstateEntry>,
     directory: HgPathBuf,
 ) {
     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 matcher.matches_everything() || matcher.matches(&directory) {
                 files_sender
                     .send(Ok((
                         directory.to_owned(),
                         dispatch_missing(entry.state),
                     )))
                     .unwrap();
             }
         }
         // Do we need to traverse it?
         if !ignore_fn(&directory) || options.list_ignored {
             traverse_dir(
                 files_sender,
                 matcher,
                 root_dir,
                 dmap,
                 directory,
                 &old_results,
                 ignore_fn,
                 dir_ignore_fn,
                 options,
             )
             .unwrap_or_else(|e| files_sender.send(Err(e)).unwrap())
         }
     });
 }
 
 /// Decides whether the directory needs to be listed, and if so handles the
 /// entries in a separate thread.
 fn traverse_dir<'a>(
     files_sender: &crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     dmap: &'a DirstateMap,
     directory: impl AsRef<HgPath>,
     old_results: &FastHashMap<Cow<'a, HgPath>, Dispatch>,
     ignore_fn: &IgnoreFnType,
     dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
 ) -> IoResult<()> {
     let directory = directory.as_ref();
-    if directory.as_bytes() == b".hg" {
-        return Ok(());
-    }
+
     let visit_entries = match matcher.visit_children_set(directory) {
         VisitChildrenSet::Empty => return Ok(()),
         VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
         VisitChildrenSet::Set(set) => Some(set),
     };
     let buf = hg_path_to_path_buf(directory)?;
     let dir_path = root_dir.as_ref().join(buf);
 
     let skip_dot_hg = !directory.as_bytes().is_empty();
     let entries = match list_directory(dir_path, skip_dot_hg) {
         Err(e) => match e.kind() {
             ErrorKind::NotFound | ErrorKind::PermissionDenied => {
                 files_sender
                     .send(Ok((
                         directory.to_owned(),
                         Dispatch::Bad(BadMatch::OsError(
                             // Unwrapping here is OK because the error always
                             // is a real os error
                             e.raw_os_error().unwrap(),
                         )),
                     )))
                     .unwrap();
                 return Ok(());
             }
             _ => return Err(e),
         },
         Ok(entries) => entries,
     };
 
     rayon::scope(|scope| -> IoResult<()> {
         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()) {
                 handle_traversed_entry(
                     scope,
                     files_sender,
                     matcher,
                     root_dir,
                     dmap,
                     old_results,
                     ignore_fn,
                     dir_ignore_fn,
                     options,
                     filename,
                     dir_entry,
                 )?;
             }
         }
         Ok(())
     })
 }
 
 /// 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]
 fn traverse<'a>(
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     dmap: &'a DirstateMap,
     path: impl AsRef<HgPath>,
     old_results: &FastHashMap<Cow<'a, HgPath>, Dispatch>,
     ignore_fn: &IgnoreFnType,
     dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) -> IoResult<()> {
     let root_dir = root_dir.as_ref();
 
     // The traversal is done in parallel, so use a channel to gather entries.
     // `crossbeam::Sender` is `Send`, while `mpsc::Sender` is not.
     let (files_transmitter, files_receiver) = crossbeam::channel::unbounded();
 
     traverse_dir(
         &files_transmitter,
         matcher,
         root_dir,
         &dmap,
         path,
         &old_results,
         &ignore_fn,
         &dir_ignore_fn,
         options,
     )?;
 
     // Disconnect the channel so the receiver stops waiting
     drop(files_transmitter);
 
     // TODO don't collect. Find a way of replicating the behavior of
     // `itertools::process_results`, but for `rayon::ParallelIterator`
     let new_results: IoResult<Vec<(Cow<'a, HgPath>, Dispatch)>> =
         files_receiver
             .into_iter()
             .map(|item| {
                 let (f, d) = item?;
                 Ok((Cow::Owned(f), d))
             })
             .collect();
 
     results.par_extend(new_results?);
 
     Ok(())
 }
 
 /// Stat all entries in the `DirstateMap` and mark them for dispatch.
 fn stat_dmap_entries(
     dmap: &DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
     options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&HgPath, Dispatch)>> {
     dmap.par_iter().map(move |(filename, entry)| {
         let filename: &HgPath = filename;
         let filename_as_path = hg_path_to_path_buf(filename)?;
         let meta = root_dir.as_ref().join(filename_as_path).symlink_metadata();
 
         match meta {
             Ok(ref m)
                 if !(m.file_type().is_file()
                     || m.file_type().is_symlink()) =>
             {
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Ok(m) => Ok((
                 filename,
                 dispatch_found(
                     filename,
                     *entry,
                     HgMetadata::from_metadata(m),
                     &dmap.copy_map,
                     options,
                 ),
             )),
             Err(ref 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
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Err(e) => Err(e),
         }
     })
 }
 
 /// This takes a mutable reference to the results to account for the `extend`
 /// in timings
 #[timed]
 fn extend_from_dmap<'a>(
     dmap: &'a DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) {
     results.par_extend(
         stat_dmap_entries(dmap, root_dir, options)
             .flatten()
             .map(|(filename, dispatch)| (Cow::Borrowed(filename), dispatch)),
     );
 }
 
 #[derive(Debug)]
 pub struct DirstateStatus<'a> {
     pub modified: Vec<Cow<'a, HgPath>>,
     pub added: Vec<Cow<'a, HgPath>>,
     pub removed: Vec<Cow<'a, HgPath>>,
     pub deleted: Vec<Cow<'a, HgPath>>,
     pub clean: Vec<Cow<'a, HgPath>>,
     pub ignored: Vec<Cow<'a, HgPath>>,
     pub unknown: Vec<Cow<'a, HgPath>>,
     pub bad: Vec<(Cow<'a, HgPath>, BadMatch)>,
 }
 
 #[timed]
 fn build_response<'a>(
     results: impl IntoIterator<Item = (Cow<'a, HgPath>, Dispatch)>,
 ) -> (Vec<Cow<'a, HgPath>>, 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,
         },
     )
 }
 
 #[derive(Debug)]
 pub enum StatusError {
     IO(std::io::Error),
     Path(HgPathError),
     Pattern(PatternError),
 }
 
 pub type StatusResult<T> = Result<T, StatusError>;
 
 impl From<PatternError> for StatusError {
     fn from(e: PatternError) -> Self {
         StatusError::Pattern(e)
     }
 }
 impl From<HgPathError> for StatusError {
     fn from(e: HgPathError) -> Self {
         StatusError::Path(e)
     }
 }
 impl From<std::io::Error> for StatusError {
     fn from(e: std::io::Error) -> Self {
         StatusError::IO(e)
     }
 }
 
 impl ToString for StatusError {
     fn to_string(&self) -> String {
         match self {
             StatusError::IO(e) => e.to_string(),
             StatusError::Path(e) => e.to_string(),
             StatusError::Pattern(e) => e.to_string(),
         }
     }
 }
 
 /// This takes a mutable reference to the results to account for the `extend`
 /// in timings
 #[timed]
 fn handle_unknowns<'a>(
     dmap: &'a DirstateMap,
     matcher: &(impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) -> IoResult<()> {
     let to_visit: Vec<(&HgPath, &DirstateEntry)> = if results.is_empty()
         && matcher.matches_everything()
     {
         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();
         dmap.iter()
             .filter_map(move |(f, e)| {
                 if !old_results.contains_key(f.deref()) && matcher.matches(f) {
                     Some((f.deref(), e))
                 } else {
                     None
                 }
             })
             .collect()
     };
 
     // We walked all dirs under the roots that weren't ignored, and
     // everything that matched was stat'ed and is already in results.
     // The rest must thus be ignored or under a symlink.
     let path_auditor = PathAuditor::new(root_dir);
 
     // TODO don't collect. Find a way of replicating the behavior of
     // `itertools::process_results`, but for `rayon::ParallelIterator`
     let new_results: IoResult<Vec<_>> = to_visit
         .into_par_iter()
         .filter_map(|(filename, entry)| -> Option<IoResult<_>> {
             // 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(e) => return Some(Err(e.into())),
                 };
                 Some(Ok((
                     Cow::Borrowed(filename),
                     match root_dir.as_ref().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,
                                 &dmap.copy_map,
                                 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(Ok((
                     Cow::Borrowed(filename),
                     dispatch_missing(entry.state),
                 )))
             }
         })
         .collect();
 
     results.par_extend(new_results?);
 
     Ok(())
 }
 
 /// 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: 'c, 'b: 'c, 'c>(
     dmap: &'a DirstateMap,
     matcher: &'b (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'c,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<Cow<'c, HgPath>>, DirstateStatus<'c>),
     Vec<PatternFileWarning>,
 )> {
     // Needs to outlive `dir_ignore_fn` since it's captured.
     let mut ignore_fn: IgnoreFnType;
 
     // Only involve real ignore mechanism if we're listing unknowns or ignored.
     let (dir_ignore_fn, warnings): (IgnoreFnType, _) = if options.list_ignored
         || options.list_unknown
     {
         let (ignore, warnings) = get_ignore_function(ignore_files, root_dir)?;
 
         ignore_fn = ignore;
         let dir_ignore_fn = Box::new(|dir: &_| {
             // Is the path or one of its ancestors ignored?
             if ignore_fn(dir) {
                 true
             } else {
                 for p in find_dirs(dir) {
                     if ignore_fn(p) {
                         return true;
                     }
                 }
                 false
             }
         });
         (dir_ignore_fn, warnings)
     } else {
         ignore_fn = Box::new(|&_| true);
         (Box::new(|&_| true), vec![])
     };
 
     let files = matcher.file_set();
 
     // Step 1: check the files explicitly mentioned by the user
     let explicit = walk_explicit(files, &dmap, root_dir, options);
 
     // Collect results into a `Vec` because we do very few lookups in most
     // cases.
     let (work, mut results): (Vec<_>, Vec<_>) = explicit
         .filter_map(Result::ok)
         .map(|(filename, dispatch)| (Cow::Borrowed(filename), dispatch))
         .partition(|(_, dispatch)| match dispatch {
             Dispatch::Directory { .. } => true,
             _ => false,
         });
 
     if !work.is_empty() {
         // Hashmaps are quite a bit slower to build than vecs, so only build it
         // if needed.
         let old_results = results.iter().cloned().collect();
 
         // Step 2: recursively check the working directory for changes if
         // needed
         for (dir, dispatch) in work {
             match dispatch {
                 Dispatch::Directory { was_file } => {
                     if was_file {
                         results.push((dir.to_owned(), Dispatch::Removed));
                     }
                     if options.list_ignored
                         || options.list_unknown && !dir_ignore_fn(&dir)
                     {
                         traverse(
                             matcher,
                             root_dir,
                             &dmap,
                             &dir,
                             &old_results,
                             &ignore_fn,
                             &dir_ignore_fn,
                             options,
                             &mut results,
                         )?;
                     }
                 }
                 _ => unreachable!("There can only be directories in `work`"),
             }
         }
     }
 
     if !matcher.is_exact() {
         // Step 3: Check the remaining files from the dmap.
         // If a dmap file is not in results yet, it was either
         // a) not matched b) ignored, c) missing, or d) under a
         // symlink directory.
 
         if options.list_unknown {
             handle_unknowns(dmap, matcher, root_dir, options, &mut results)?;
         } else {
             // We may not have walked the full directory tree above, so stat
             // and check everything we missed.
             extend_from_dmap(&dmap, root_dir, options, &mut results);
         }
     }
 
     Ok((build_response(results), warnings))
 }

tests/test-status.t

@@ -1,674 +1,682 b''
   $ hg init repo1
   $ cd repo1
   $ mkdir a b a/1 b/1 b/2
   $ touch in_root a/in_a b/in_b a/1/in_a_1 b/1/in_b_1 b/2/in_b_2
 
 hg status in repo root:
 
   $ hg status
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
 hg status . in repo root:
 
   $ hg status .
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ hg status --cwd a
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a .
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a ..
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd b
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b .
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   $ hg status --cwd b ..
   ? ../a/1/in_a_1
   ? ../a/in_a
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   ? ../in_root
 
   $ hg status --cwd a/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a/1 .
   ? in_a_1
   $ hg status --cwd a/1 ..
   ? in_a_1
   ? ../in_a
 
   $ hg status --cwd b/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/1 .
   ? in_b_1
   $ hg status --cwd b/1 ..
   ? in_b_1
   ? ../2/in_b_2
   ? ../in_b
 
   $ hg status --cwd b/2
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/2 .
   ? in_b_2
   $ hg status --cwd b/2 ..
   ? ../1/in_b_1
   ? in_b_2
   ? ../in_b
 
 combining patterns with root and patterns without a root works
 
   $ hg st a/in_a re:.*b$
   ? a/in_a
   ? b/in_b
 
 tweaking defaults works
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
   $ HGPLAINEXCEPT=tweakdefaults hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root (glob)
 
 relative paths can be requested
 
   $ hg status --cwd a --config ui.relative-paths=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd a . --config ui.relative-paths=legacy
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a . --config ui.relative-paths=no
   ? a/1/in_a_1
   ? a/in_a
 
 commands.status.relative overrides ui.relative-paths
 
   $ cat >> $HGRCPATH <<EOF
   > [ui]
   > relative-paths = False
   > [commands]
   > status.relative = True
   > EOF
   $ hg status --cwd a
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
 
 if relative paths are explicitly off, tweakdefaults doesn't change it
   $ cat >> $HGRCPATH <<EOF
   > [commands]
   > status.relative = False
   > EOF
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ cd ..
 
   $ hg init repo2
   $ cd repo2
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg ci -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch modified added unknown ignored
   $ hg add added
   $ hg remove removed
   $ rm deleted
 
 hg status:
 
   $ hg status
   A added
   R removed
   ! deleted
   ? unknown
 
 hg status modified added removed deleted unknown never-existed ignored:
 
   $ hg status modified added removed deleted unknown never-existed ignored
   never-existed: * (glob)
   A added
   R removed
   ! deleted
   ? unknown
 
   $ hg copy modified copied
 
 hg status -C:
 
   $ hg status -C
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
 
 hg status -A:
 
   $ hg status -A
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
   I ignored
   C .hgignore
   C modified
 
   $ hg status -A -T '{status} {path} {node|shortest}\n'
   A added ffff
   A copied ffff
   R removed ffff
   ! deleted ffff
   ? unknown ffff
   I ignored ffff
   C .hgignore ffff
   C modified ffff
 
   $ hg status -A -Tjson
   [
    {
     "itemtype": "file",
     "path": "added",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "copied",
     "source": "modified",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "removed",
     "status": "R"
    },
    {
     "itemtype": "file",
     "path": "deleted",
     "status": "!"
    },
    {
     "itemtype": "file",
     "path": "unknown",
     "status": "?"
    },
    {
     "itemtype": "file",
     "path": "ignored",
     "status": "I"
    },
    {
     "itemtype": "file",
     "path": ".hgignore",
     "status": "C"
    },
    {
     "itemtype": "file",
     "path": "modified",
     "status": "C"
    }
   ]
 
   $ hg status -A -Tpickle > pickle
   >>> from __future__ import print_function
   >>> from mercurial import util
   >>> pickle = util.pickle
   >>> data = sorted((x[b'status'].decode(), x[b'path'].decode()) for x in pickle.load(open("pickle", r"rb")))
   >>> for s, p in data: print("%s %s" % (s, p))
   ! deleted
   ? pickle
   ? unknown
   A added
   A copied
   C .hgignore
   C modified
   I ignored
   R removed
   $ rm pickle
 
   $ echo "^ignoreddir$" > .hgignore
   $ mkdir ignoreddir
   $ touch ignoreddir/file
 
 Test templater support:
 
   $ hg status -AT "[{status}]\t{if(source, '{source} -> ')}{path}\n"
   [M]	.hgignore
   [A]	added
   [A]	modified -> copied
   [R]	removed
   [!]	deleted
   [?]	ignored
   [?]	unknown
   [I]	ignoreddir/file
   [C]	modified
   $ hg status -AT default
   M .hgignore
   A added
   A copied
     modified
   R removed
   ! deleted
   ? ignored
   ? unknown
   I ignoreddir/file
   C modified
   $ hg status -T compact
   abort: "status" not in template map
   [255]
 
 hg status ignoreddir/file:
 
   $ hg status ignoreddir/file
 
 hg status -i ignoreddir/file:
 
   $ hg status -i ignoreddir/file
   I ignoreddir/file
   $ cd ..
 
 Check 'status -q' and some combinations
 
   $ hg init repo3
   $ cd repo3
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg commit -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch added unknown ignored
   $ hg add added
   $ echo "test" >> modified
   $ hg remove removed
   $ rm deleted
   $ hg copy modified copied
 
 Specify working directory revision explicitly, that should be the same as
 "hg status"
 
   $ hg status --change "wdir()"
   M modified
   A added
   A copied
   R removed
   ! deleted
   ? unknown
 
 Run status with 2 different flags.
 Check if result is the same or different.
 If result is not as expected, raise error
 
   $ assert() {
   >     hg status $1 > ../a
   >     hg status $2 > ../b
   >     if diff ../a ../b > /dev/null; then
   >         out=0
   >     else
   >         out=1
   >     fi
   >     if [ $3 -eq 0 ]; then
   >         df="same"
   >     else
   >         df="different"
   >     fi
   >     if [ $out -ne $3 ]; then
   >         echo "Error on $1 and $2, should be $df."
   >     fi
   > }
 
 Assert flag1 flag2 [0-same | 1-different]
 
   $ assert "-q" "-mard"      0
   $ assert "-A" "-marduicC"  0
   $ assert "-qA" "-mardcC"   0
   $ assert "-qAui" "-A"      0
   $ assert "-qAu" "-marducC" 0
   $ assert "-qAi" "-mardicC" 0
   $ assert "-qu" "-u"        0
   $ assert "-q" "-u"         1
   $ assert "-m" "-a"         1
   $ assert "-r" "-d"         1
   $ cd ..
 
   $ hg init repo4
   $ cd repo4
   $ touch modified removed deleted
   $ hg ci -q -A -m 'initial checkin'
   $ touch added unknown
   $ hg add added
   $ hg remove removed
   $ rm deleted
   $ echo x > modified
   $ hg copy modified copied
   $ hg ci -m 'test checkin' -d "1000001 0"
   $ rm *
   $ touch unrelated
   $ hg ci -q -A -m 'unrelated checkin' -d "1000002 0"
 
 hg status --change 1:
 
   $ hg status --change 1
   M modified
   A added
   A copied
   R removed
 
 hg status --change 1 unrelated:
 
   $ hg status --change 1 unrelated
 
 hg status -C --change 1 added modified copied removed deleted:
 
   $ hg status -C --change 1 added modified copied removed deleted
   M modified
   A added
   A copied
     modified
   R removed
 
 hg status -A --change 1 and revset:
 
   $ hg status -A --change '1|1'
   M modified
   A added
   A copied
     modified
   R removed
   C deleted
 
   $ cd ..
 
 hg status with --rev and reverted changes:
 
   $ hg init reverted-changes-repo
   $ cd reverted-changes-repo
   $ echo a > file
   $ hg add file
   $ hg ci -m a
   $ echo b > file
   $ hg ci -m b
 
 reverted file should appear clean
 
   $ hg revert -r 0 .
   reverting file
   $ hg status -A --rev 0
   C file
 
 #if execbit
 reverted file with changed flag should appear modified
 
   $ chmod +x file
   $ hg status -A --rev 0
   M file
 
   $ hg revert -r 0 .
   reverting file
 
 reverted and committed file with changed flag should appear modified
 
   $ hg co -C .
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ chmod +x file
   $ hg ci -m 'change flag'
   $ hg status -A --rev 1 --rev 2
   M file
   $ hg diff -r 1 -r 2
 
 #endif
 
   $ cd ..
 
 hg status of binary file starting with '\1\n', a separator for metadata:
 
   $ hg init repo5
   $ cd repo5
   >>> open("010a", r"wb").write(b"\1\nfoo") and None
   $ hg ci -q -A -m 'initial checkin'
   $ hg status -A
   C 010a
 
   >>> open("010a", r"wb").write(b"\1\nbar") and None
   $ hg status -A
   M 010a
   $ hg ci -q -m 'modify 010a'
   $ hg status -A --rev 0:1
   M 010a
 
   $ touch empty
   $ hg ci -q -A -m 'add another file'
   $ hg status -A --rev 1:2 010a
   C 010a
 
   $ cd ..
 
 test "hg status" with "directory pattern" which matches against files
 only known on target revision.
 
   $ hg init repo6
   $ cd repo6
 
   $ echo a > a.txt
   $ hg add a.txt
   $ hg commit -m '#0'
   $ mkdir -p 1/2/3/4/5
   $ echo b > 1/2/3/4/5/b.txt
   $ hg add 1/2/3/4/5/b.txt
   $ hg commit -m '#1'
 
   $ hg update -C 0 > /dev/null
   $ hg status -A
   C a.txt
 
 the directory matching against specified pattern should be removed,
 because directory existence prevents 'dirstate.walk()' from showing
 warning message about such pattern.
 
   $ test ! -d 1
   $ hg status -A --rev 1 1/2/3/4/5/b.txt
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3/4/5
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1
   R 1/2/3/4/5/b.txt
 
   $ hg status --config ui.formatdebug=True --rev 1 1
   status = [
       {
           'itemtype': 'file',
           'path': '1/2/3/4/5/b.txt',
           'status': 'R'
       },
   ]
 
 #if windows
   $ hg --config ui.slash=false status -A --rev 1 1
   R 1\2\3\4\5\b.txt
 #endif
 
   $ cd ..
 
 Status after move overwriting a file (issue4458)
 =================================================
 
 
   $ hg init issue4458
   $ cd issue4458
   $ echo a > a
   $ echo b > b
   $ hg commit -Am base
   adding a
   adding b
 
 
 with --force
 
   $ hg mv b --force a
   $ hg st --copies
   M a
     b
   R b
   $ hg revert --all
   reverting a
   undeleting b
   $ rm *.orig
 
 without force
 
   $ hg rm a
   $ hg st --copies
   R a
   $ hg mv b a
   $ hg st --copies
   M a
     b
   R b
 
 using ui.statuscopies setting
   $ hg st --config ui.statuscopies=true
   M a
     b
   R b
   $ hg st --config ui.statuscopies=false
   M a
   R b
   $ hg st --config ui.tweakdefaults=yes
   M a
     b
   R b
 
 using log status template (issue5155)
   $ hg log -Tstatus -r 'wdir()' -C
   changeset:   2147483647:ffffffffffff
   parent:      0:8c55c58b4c0e
   user:        test
   date:        * (glob)
   files:
   M a
     b
   R b
   
   $ hg log -GTstatus -r 'wdir()' -C
   o  changeset:   2147483647:ffffffffffff
   |  parent:      0:8c55c58b4c0e
   ~  user:        test
      date:        * (glob)
      files:
      M a
        b
      R b
   
 
 Other "bug" highlight, the revision status does not report the copy information.
 This is buggy behavior.
 
   $ hg commit -m 'blah'
   $ hg st --copies --change .
   M a
   R b
 
 using log status template, the copy information is displayed correctly.
   $ hg log -Tstatus -r. -C
   changeset:   1:6685fde43d21
   tag:         tip
   user:        test
   date:        * (glob)
   summary:     blah
   files:
   M a
     b
   R b
   
 
   $ cd ..
+
+Make sure .hg doesn't show up even as a symlink
+
+  $ hg init repo0
+  $ mkdir symlink-repo0
+  $ cd symlink-repo0
+  $ ln -s ../repo0/.hg
+  $ hg status