rust: Move "lookup" a.k.a. "unsure" paths into `DirstateStatus` struct

Instead of having `status()` returning a tuple of those paths and
`DirstateStatus`.

Differential Revision: https://phab.mercurial-scm.org/D10494

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

@@ -1,913 +1,912 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::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())
             {
                 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)>,
+    /// Either clean or modified, but we can’t tell from filesystem metadata
+    /// alone. The file contents need to be read and compared with that in
+    /// the parent.
+    pub unsure: Vec<HgPathCow<'a>>,
     /// 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: ?Sized + 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: ?Sized + 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
     #[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
     #[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![];
+) -> DirstateStatus<'a> {
+    let mut unsure = 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::Unsure => unsure.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,
-        },
-    )
+    DirstateStatus {
+        modified,
+        added,
+        removed,
+        deleted,
+        clean,
+        ignored,
+        unknown,
+        bad,
+        unsure,
+        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 (dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
-) -> StatusResult<(
-    (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
-    Vec<PatternFileWarning>,
-)> {
+) -> StatusResult<(DirstateStatus<'a>, Vec<PatternFileWarning>)> {
     let (status, warnings) =
         Status::new(dmap, matcher, root_dir, ignore_files, options)?;
 
     Ok((status.run()?, warnings))
 }

rust/hg-core/src/dirstate_tree/dirstate_map.rs

@@ -1,658 +1,652 b''
 use bytes_cast::BytesCast;
 use std::path::PathBuf;
 use std::{collections::BTreeMap, convert::TryInto};
 
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::clear_ambiguous_mtime;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::parse_dirstate_parents;
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::revlog::node::NULL_NODE;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateMapError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
-use crate::HgPathCow;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub struct DirstateMap {
     parents: Option<DirstateParents>,
     dirty_parents: bool,
     root: ChildNodes,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     nodes_with_entry_count: usize,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     nodes_with_copy_source_count: usize,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `BTreeMap` would waste time always re-comparing the same
 /// string prefix.
 type ChildNodes = BTreeMap<WithBasename<HgPathBuf>, Node>;
 
 /// Represents a file or a directory
 #[derive(Default)]
 struct Node {
     /// `None` for directories
     entry: Option<DirstateEntry>,
 
     copy_source: Option<HgPathBuf>,
 
     children: ChildNodes,
 
     /// How many (non-inclusive) descendants of this node are tracked files
     tracked_descendants_count: usize,
 }
 
 impl Node {
     /// Whether this node has a `DirstateEntry` with `.state.is_tracked()`
     fn is_tracked_file(&self) -> bool {
         if let Some(entry) = &self.entry {
             entry.state.is_tracked()
         } else {
             false
         }
     }
 }
 
 /// `(full_path, entry, copy_source)`
 type NodeDataMut<'a> = (
     &'a WithBasename<HgPathBuf>,
     &'a mut Option<DirstateEntry>,
     &'a mut Option<HgPathBuf>,
 );
 
 impl DirstateMap {
     pub fn new() -> Self {
         Self {
             parents: None,
             dirty_parents: false,
             root: ChildNodes::new(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
         }
     }
 
     fn get_node(&self, path: &HgPath) -> Option<&Node> {
         let mut children = &self.root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get(component)?;
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
     ) -> Option<&'tree mut Node> {
         Self::each_and_get(root, path, |_| {})
     }
 
     /// Call `each` for each ancestor node of the one at `path` (not including
     /// that node itself), starting from nearest the root.
     ///
     /// Panics (possibly after some calls to `each`) if there is no node at
     /// `path`.
     fn for_each_ancestor_node<'tree>(
         &mut self,
         path: &HgPath,
         each: impl FnMut(&mut Node),
     ) {
         let parent = path.parent();
         if !parent.is_empty() {
             Self::each_and_get(&mut self.root, parent, each)
                 .expect("missing dirstate node");
         }
     }
 
     /// Common implementation detail of `get_node_mut` and
     /// `for_each_ancestor_node`
     fn each_and_get<'tree>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
         mut each: impl FnMut(&mut Node),
     ) -> Option<&'tree mut Node> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get_mut(component)?;
             each(child);
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &mut child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     fn get_or_insert_node<'tree>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
     ) -> &'tree mut Node {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
             // TODO: can we avoid double lookup in all cases without allocating
             // an owned key in cases where the map already contains that key?
             let child_node =
                 if child_nodes.contains_key(ancestor_path.base_name()) {
                     child_nodes.get_mut(ancestor_path.base_name()).unwrap()
                 } else {
                     // This is always a vacant entry, using `.entry()` lets us
                     // return a `&mut Node` of the newly-inserted node without
                     // yet another lookup. `BTreeMap::insert` doesn’t do this.
                     child_nodes.entry(ancestor_path.to_owned()).or_default()
                 };
             if let Some(next) = inclusive_ancestor_paths.next() {
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return child_node;
             }
         }
     }
 
     /// The meaning of `new_copy_source` is:
     ///
     /// * `Some(Some(x))`: set `Node::copy_source` to `Some(x)`
     /// * `Some(None)`: set `Node::copy_source` to `None`
     /// * `None`: leave `Node::copy_source` unchanged
     fn add_file_node(
         &mut self,
         path: &HgPath,
         new_entry: DirstateEntry,
         new_copy_source: Option<Option<HgPathBuf>>,
     ) {
         let node = Self::get_or_insert_node(&mut self.root, path);
         if node.entry.is_none() {
             self.nodes_with_entry_count += 1
         }
         if let Some(source) = &new_copy_source {
             if node.copy_source.is_none() && source.is_some() {
                 self.nodes_with_copy_source_count += 1
             }
             if node.copy_source.is_some() && source.is_none() {
                 self.nodes_with_copy_source_count -= 1
             }
         }
         let tracked_count_increment =
             match (node.is_tracked_file(), new_entry.state.is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         node.entry = Some(new_entry);
         if let Some(source) = new_copy_source {
             node.copy_source = source
         }
         // Borrow of `self.root` through `node` ends here
 
         match tracked_count_increment {
             1 => self.for_each_ancestor_node(path, |node| {
                 node.tracked_descendants_count += 1
             }),
             // We can’t use `+= -1` because the counter is unsigned
             -1 => self.for_each_ancestor_node(path, |node| {
                 node.tracked_descendants_count -= 1
             }),
             _ => {}
         }
     }
 
     fn iter_nodes<'a>(
         &'a self,
     ) -> impl Iterator<Item = (&'a WithBasename<HgPathBuf>, &'a Node)> + 'a
     {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.iter();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let new_iter = child_node.children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((key, child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((key, child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some((key, child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     /// Mutable iterator for the `(entry, copy source)` of each node.
     ///
     /// It would not be safe to yield mutable references to nodes themeselves
     /// with `-> impl Iterator<Item = &mut Node>` since child nodes are
     /// reachable from their ancestor nodes, potentially creating multiple
     /// `&mut` references to a given node.
     fn iter_node_data_mut<'a>(
         &'a mut self,
     ) -> impl Iterator<Item = NodeDataMut<'a>> + 'a {
         // Explict stack for pseudo-recursion, see `iter_nodes` above.
         let mut stack = Vec::new();
         let mut iter = self.root.iter_mut();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let data =
                     (key, &mut child_node.entry, &mut child_node.copy_source);
                 let new_iter = child_node.children.iter_mut();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((data, old_iter));
             }
             // Found the end of a `children.values_mut()` iterator.
             if let Some((data, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(data)
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 }
 
 impl super::dispatch::DirstateMapMethods for DirstateMap {
     fn clear(&mut self) {
         self.set_parents(&DirstateParents {
             p1: NULL_NODE,
             p2: NULL_NODE,
         });
         self.root.clear();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         self.add_file_node(filename, entry, None);
         Ok(())
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         let entry = DirstateEntry {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         };
         self.add_file_node(filename, entry, None);
         Ok(())
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = Self::get_node_mut(&mut self.root, filename) {
             let was_tracked = node.is_tracked_file();
             let had_entry = node.entry.is_some();
             let had_copy_source = node.copy_source.is_some();
 
             // TODO: this leaves in the tree a "non-file" node. Should we
             // remove the node instead, together with ancestor nodes for
             // directories that become empty?
             node.entry = None;
             node.copy_source = None;
 
             if had_entry {
                 self.nodes_with_entry_count -= 1
             }
             if had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
             if was_tracked {
                 self.for_each_ancestor_node(filename, |node| {
                     node.tracked_descendants_count -= 1
                 })
             }
             Ok(had_entry)
         } else {
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32) {
         for filename in filenames {
             if let Some(node) = Self::get_node_mut(&mut self.root, &filename) {
                 if let Some(entry) = node.entry.as_mut() {
                     clear_ambiguous_mtime(entry, now);
                 }
             }
         }
     }
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool {
         self.get_node(key)
             .and_then(|node| node.entry.as_ref())
             .map_or(false, DirstateEntry::is_non_normal)
     }
 
     fn non_normal_entries_remove(&mut self, _key: &HgPath) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| {
                     entry.is_non_normal() || entry.is_from_other_parent()
                 })
                 .map(|_| path.full_path())
         }))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, _force: bool) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" and "from other parent" sets that need to be recomputed
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_non_normal())
                 .map(|_| path.full_path())
         }))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_from_other_parent())
                 .map(|_| path.full_path())
         }))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none() && node.tracked_descendants_count > 0)
         } else {
             Ok(false)
         }
     }
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none())
         } else {
             Ok(false)
         }
     }
 
     fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError> {
         if self.parents.is_none() {
             let parents = if !file_contents.is_empty() {
                 parse_dirstate_parents(file_contents)?.clone()
             } else {
                 DirstateParents {
                     p1: NULL_NODE,
                     p2: NULL_NODE,
                 }
             };
             self.parents = Some(parents);
         }
         Ok(self.parents.as_ref().unwrap())
     }
 
     fn set_parents(&mut self, parents: &DirstateParents) {
         self.parents = Some(parents.clone());
         self.dirty_parents = true;
     }
 
     fn read<'a>(
         &mut self,
         file_contents: &'a [u8],
     ) -> Result<Option<&'a DirstateParents>, DirstateError> {
         if file_contents.is_empty() {
             return Ok(None);
         }
 
         let parents = parse_dirstate_entries(
             file_contents,
             |path, entry, copy_source| {
                 self.add_file_node(
                     path,
                     *entry,
                     Some(copy_source.map(HgPath::to_owned)),
                 )
             },
         )?;
 
         if !self.dirty_parents {
             self.set_parents(parents);
         }
 
         Ok(Some(parents))
     }
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for (path, node) in self.iter_nodes() {
             if node.entry.is_some() {
                 size += packed_entry_size(
                     path.full_path(),
                     node.copy_source.as_ref(),
                 )
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         let now: i32 = now.0.try_into().expect("time overflow");
         for (path, opt_entry, copy_source) in self.iter_node_data_mut() {
             if let Some(entry) = opt_entry {
                 clear_ambiguous_mtime(entry, now);
                 pack_entry(
                     path.full_path(),
                     entry,
                     copy_source.as_ref(),
                     &mut packed,
                 );
             }
         }
         self.dirty_parents = false;
         Ok(packed)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `all_dirs` that
         // needs to be recomputed
         Ok(())
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `dirs` that needs
         // to be recomputed
         Ok(())
     }
 
     fn status<'a>(
         &'a self,
         _matcher: &'a (dyn Matcher + Sync),
         _root_dir: PathBuf,
         _ignore_files: Vec<PathBuf>,
         _options: StatusOptions,
-    ) -> Result<
-        (
-            (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
-            Vec<PatternFileWarning>,
-        ),
-        StatusError,
-    > {
+    ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
+    {
         todo!()
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.copy_source
                 .as_ref()
                 .map(|copy_source| (path.full_path(), copy_source))
         }))
     }
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool {
         if let Some(node) = self.get_node(key) {
             node.copy_source.is_some()
         } else {
             false
         }
     }
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPathBuf> {
         self.get_node(key)?.copy_source.as_ref()
     }
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf> {
         let count = &mut self.nodes_with_copy_source_count;
         Self::get_node_mut(&mut self.root, key).and_then(|node| {
             if node.copy_source.is_some() {
                 *count -= 1
             }
             node.copy_source.take()
         })
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf> {
         let node = Self::get_or_insert_node(&mut self.root, &key);
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         node.copy_source.replace(value)
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count
     }
 
     fn contains_key(&self, key: &HgPath) -> bool {
         self.get(key).is_some()
     }
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry> {
         self.get_node(key)?.entry.as_ref()
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry.as_ref().map(|entry| (path.full_path(), entry))
         }))
     }
 }

rust/hg-core/src/dirstate_tree/dispatch.rs

@@ -1,326 +1,314 b''
 use std::path::PathBuf;
 
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateMap;
 use crate::DirstateMapError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
-use crate::HgPathCow;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub trait DirstateMapMethods {
     fn clear(&mut self);
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError>;
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError>;
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError>;
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32);
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool;
 
     fn non_normal_entries_remove(&mut self, key: &HgPath);
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + '_>;
 
     fn set_non_normal_other_parent_entries(&mut self, force: bool);
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_>;
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_>;
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_>;
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError>;
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError>;
 
     fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError>;
 
     fn set_parents(&mut self, parents: &DirstateParents);
 
     fn read<'a>(
         &mut self,
         file_contents: &'a [u8],
     ) -> Result<Option<&'a DirstateParents>, DirstateError>;
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError>;
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError>;
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError>;
 
     fn status<'a>(
         &'a self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
-    ) -> Result<
-        (
-            (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
-            Vec<PatternFileWarning>,
-        ),
-        StatusError,
-    >;
+    ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>;
 
     fn copy_map_len(&self) -> usize;
 
     fn copy_map_iter(&self) -> CopyMapIter<'_>;
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool;
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPathBuf>;
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf>;
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf>;
 
     fn len(&self) -> usize;
 
     fn contains_key(&self, key: &HgPath) -> bool;
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry>;
 
     fn iter(&self) -> StateMapIter<'_>;
 }
 
 impl DirstateMapMethods for DirstateMap {
     fn clear(&mut self) {
         self.clear()
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         self.add_file(filename, old_state, entry)
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         self.remove_file(filename, old_state, size)
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         self.drop_file(filename, old_state)
     }
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32) {
         self.clear_ambiguous_times(filenames, now)
     }
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool {
         let (non_normal, _other_parent) =
             self.get_non_normal_other_parent_entries();
         non_normal.contains(key)
     }
 
     fn non_normal_entries_remove(&mut self, key: &HgPath) {
         self.non_normal_entries_remove(key)
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + '_> {
         let (non_normal, other_parent) =
             self.get_non_normal_other_parent_entries();
         Box::new(non_normal.union(other_parent))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, force: bool) {
         self.set_non_normal_other_parent_entries(force)
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         let (non_normal, _other_parent) =
             self.get_non_normal_other_parent_entries();
         Box::new(non_normal.iter())
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         let (non_normal, _other_parent) =
             self.get_non_normal_other_parent_entries_panic();
         Box::new(non_normal.iter())
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         let (_non_normal, other_parent) =
             self.get_non_normal_other_parent_entries();
         Box::new(other_parent.iter())
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.has_tracked_dir(directory)
     }
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.has_dir(directory)
     }
 
     fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError> {
         self.parents(file_contents)
     }
 
     fn set_parents(&mut self, parents: &DirstateParents) {
         self.set_parents(parents)
     }
 
     fn read<'a>(
         &mut self,
         file_contents: &'a [u8],
     ) -> Result<Option<&'a DirstateParents>, DirstateError> {
         self.read(file_contents)
     }
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         self.pack(parents, now)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         self.set_all_dirs()
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         self.set_dirs()
     }
 
     fn status<'a>(
         &'a self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
-    ) -> Result<
-        (
-            (Vec<HgPathCow<'a>>, DirstateStatus<'a>),
-            Vec<PatternFileWarning>,
-        ),
-        StatusError,
-    > {
+    ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
+    {
         crate::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.copy_map.len()
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(self.copy_map.iter())
     }
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool {
         self.copy_map.contains_key(key)
     }
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPathBuf> {
         self.copy_map.get(key)
     }
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf> {
         self.copy_map.remove(key)
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf> {
         self.copy_map.insert(key, value)
     }
 
     fn len(&self) -> usize {
         (&**self).len()
     }
 
     fn contains_key(&self, key: &HgPath) -> bool {
         (&**self).contains_key(key)
     }
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry> {
         (&**self).get(key)
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new((&**self).iter())
     }
 }

rust/hg-core/src/operations/dirstate_status.rs

@@ -1,73 +1,68 b''
 // dirstate_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.
 
-use crate::dirstate::status::{build_response, Dispatch, HgPathCow, Status};
+use crate::dirstate::status::{build_response, Dispatch, Status};
 use crate::matchers::Matcher;
 use crate::{DirstateStatus, StatusError};
 
-/// A tuple of the paths that need to be checked in the filelog because it's
-/// ambiguous whether they've changed, and the rest of the already dispatched
-/// files.
-pub type LookupAndStatus<'a> = (Vec<HgPathCow<'a>>, DirstateStatus<'a>);
-
 impl<'a, M: ?Sized + Matcher + Sync> Status<'a, M> {
-    pub(crate) fn run(&self) -> Result<LookupAndStatus<'a>, StatusError> {
+    pub(crate) fn run(&self) -> Result<DirstateStatus<'a>, StatusError> {
         let (traversed_sender, traversed_receiver) =
             crossbeam_channel::unbounded();
 
         // Step 1: check the files explicitly mentioned by the user
         let (work, mut results) = self.walk_explicit(traversed_sender.clone());
 
         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 self.options.list_ignored
                             || self.options.list_unknown
                                 && !self.dir_ignore(&dir)
                         {
                             self.traverse(
                                 &dir,
                                 &old_results,
                                 &mut results,
                                 traversed_sender.clone(),
                             );
                         }
                     }
                     _ => {
                         unreachable!("There can only be directories in `work`")
                     }
                 }
             }
         }
 
         if !self.matcher.is_exact() {
             if self.options.list_unknown {
                 self.handle_unknowns(&mut results);
             } else {
                 // TODO this is incorrect, see issue6335
                 // This requires a fix in both Python and Rust that can happen
                 // with other pending changes to `status`.
                 self.extend_from_dmap(&mut results);
             }
         }
 
         drop(traversed_sender);
         let traversed = traversed_receiver.into_iter().collect();
 
         Ok(build_response(results, traversed))
     }
 }

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

@@ -1,303 +1,302 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.
 
 //! Bindings for the `hg::status` module provided by the
 //! `hg-core` crate. From Python, this will be seen as
 //! `rustext.dirstate.status`.
 
 use crate::{dirstate::DirstateMap, exceptions::FallbackError};
 use cpython::exc::OSError;
 use cpython::{
     exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
     PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::{
     matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
     parse_pattern_syntax,
     utils::{
         files::{get_bytes_from_path, get_path_from_bytes},
         hg_path::{HgPath, HgPathBuf},
     },
     BadMatch, DirstateStatus, IgnorePattern, PatternFileWarning, StatusError,
     StatusOptions,
 };
-use std::borrow::{Borrow, Cow};
+use std::borrow::Borrow;
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list(
     py: Python,
     collection: &[impl AsRef<HgPath>],
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for path in collection.iter() {
         list.append(
             py,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 fn collect_bad_matches(
     py: Python,
     collection: &[(impl AsRef<HgPath>, BadMatch)],
 ) -> PyResult<PyList> {
     let list = PyList::new(py, &[]);
 
     let os = py.import("os")?;
     let get_error_message = |code: i32| -> PyResult<_> {
         os.call(
             py,
             "strerror",
             PyTuple::new(py, &[code.to_py_object(py).into_object()]),
             None,
         )
     };
 
     for (path, bad_match) in collection.iter() {
         let message = match bad_match {
             BadMatch::OsError(code) => get_error_message(*code)?,
             BadMatch::BadType(bad_type) => format!(
                 "unsupported file type (type is {})",
                 bad_type.to_string()
             )
             .to_py_object(py)
             .into_object(),
         };
         list.append(
             py,
             (PyBytes::new(py, path.as_ref().as_bytes()), message)
                 .to_py_object(py)
                 .into_object(),
         )
     }
 
     Ok(list)
 }
 
 fn handle_fallback(py: Python, err: StatusError) -> PyErr {
     match err {
         StatusError::Pattern(e) => {
             let as_string = e.to_string();
             log::trace!("Rust status fallback: `{}`", &as_string);
 
             PyErr::new::<FallbackError, _>(py, &as_string)
         }
         StatusError::IO(e) => PyErr::new::<OSError, _>(py, e.to_string()),
         e => PyErr::new::<ValueError, _>(py, e.to_string()),
     }
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
     ignore_files: PyList,
     check_exec: bool,
     last_normal_time: i64,
     list_clean: bool,
     list_ignored: bool,
     list_unknown: bool,
     collect_traversed_dirs: bool,
 ) -> PyResult<PyTuple> {
     let bytes = root_dir.extract::<PyBytes>(py)?;
     let root_dir = get_path_from_bytes(bytes.data(py));
 
     let dmap: DirstateMap = dmap.to_py_object(py);
     let dmap = dmap.get_inner(py);
 
     let ignore_files: PyResult<Vec<_>> = ignore_files
         .iter(py)
         .map(|b| {
             let file = b.extract::<PyBytes>(py)?;
             Ok(get_path_from_bytes(file.data(py)).to_owned())
         })
         .collect();
     let ignore_files = ignore_files?;
 
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => {
             let matcher = AlwaysMatcher;
-            let ((lookup, status_res), warnings) = dmap
+            let (status_res, warnings) = dmap
                 .status(
                     &matcher,
                     root_dir.to_path_buf(),
                     ignore_files,
                     StatusOptions {
                         check_exec,
                         last_normal_time,
                         list_clean,
                         list_ignored,
                         list_unknown,
                         collect_traversed_dirs,
                     },
                 )
                 .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, lookup, status_res, warnings)
+            build_response(py, status_res, warnings)
         }
         "exactmatcher" => {
             let files = matcher.call_method(
                 py,
                 "files",
                 PyTuple::new(py, &[]),
                 None,
             )?;
             let files: PyList = files.cast_into(py)?;
             let files: PyResult<Vec<HgPathBuf>> = files
                 .iter(py)
                 .map(|f| {
                     Ok(HgPathBuf::from_bytes(
                         f.extract::<PyBytes>(py)?.data(py),
                     ))
                 })
                 .collect();
 
             let files = files?;
             let matcher = FileMatcher::new(files.as_ref())
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
-            let ((lookup, status_res), warnings) = dmap
+            let (status_res, warnings) = dmap
                 .status(
                     &matcher,
                     root_dir.to_path_buf(),
                     ignore_files,
                     StatusOptions {
                         check_exec,
                         last_normal_time,
                         list_clean,
                         list_ignored,
                         list_unknown,
                         collect_traversed_dirs,
                     },
                 )
                 .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, lookup, status_res, warnings)
+            build_response(py, status_res, warnings)
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
             // redundant with those we will parse later on, as they include
             // those passed from the command line.
             let ignore_patterns: PyResult<Vec<_>> = matcher
                 .getattr(py, "_kindpats")?
                 .iter(py)?
                 .map(|k| {
                     let k = k?;
                     let syntax = parse_pattern_syntax(
                         &[
                             k.get_item(py, 0)?
                                 .extract::<PyBytes>(py)?
                                 .data(py),
                             &b":"[..],
                         ]
                         .concat(),
                     )
                     .map_err(|e| {
                         handle_fallback(py, StatusError::Pattern(e))
                     })?;
                     let pattern = k.get_item(py, 1)?.extract::<PyBytes>(py)?;
                     let pattern = pattern.data(py);
                     let source = k.get_item(py, 2)?.extract::<PyBytes>(py)?;
                     let source = get_path_from_bytes(source.data(py));
                     let new = IgnorePattern::new(syntax, pattern, source);
                     Ok(new)
                 })
                 .collect();
 
             let ignore_patterns = ignore_patterns?;
             let mut all_warnings = vec![];
 
             let (matcher, warnings) =
                 IncludeMatcher::new(ignore_patterns, &root_dir)
                     .map_err(|e| handle_fallback(py, e.into()))?;
             all_warnings.extend(warnings);
 
-            let ((lookup, status_res), warnings) = dmap
+            let (status_res, warnings) = dmap
                 .status(
                     &matcher,
                     root_dir.to_path_buf(),
                     ignore_files,
                     StatusOptions {
                         check_exec,
                         last_normal_time,
                         list_clean,
                         list_ignored,
                         list_unknown,
                         collect_traversed_dirs,
                     },
                 )
                 .map_err(|e| handle_fallback(py, e))?;
 
             all_warnings.extend(warnings);
 
-            build_response(py, lookup, status_res, all_warnings)
+            build_response(py, status_res, all_warnings)
         }
         e => Err(PyErr::new::<ValueError, _>(
             py,
             format!("Unsupported matcher {}", e),
         )),
     }
 }
 
 fn build_response(
     py: Python,
-    lookup: Vec<Cow<HgPath>>,
     status_res: DirstateStatus,
     warnings: Vec<PatternFileWarning>,
 ) -> PyResult<PyTuple> {
     let modified = collect_pybytes_list(py, status_res.modified.as_ref());
     let added = collect_pybytes_list(py, status_res.added.as_ref());
     let removed = collect_pybytes_list(py, status_res.removed.as_ref());
     let deleted = collect_pybytes_list(py, status_res.deleted.as_ref());
     let clean = collect_pybytes_list(py, status_res.clean.as_ref());
     let ignored = collect_pybytes_list(py, status_res.ignored.as_ref());
     let unknown = collect_pybytes_list(py, status_res.unknown.as_ref());
-    let lookup = collect_pybytes_list(py, lookup.as_ref());
+    let unsure = collect_pybytes_list(py, status_res.unsure.as_ref());
     let bad = collect_bad_matches(py, status_res.bad.as_ref())?;
     let traversed = collect_pybytes_list(py, status_res.traversed.as_ref());
     let py_warnings = PyList::new(py, &[]);
     for warning in warnings.iter() {
         // We use duck-typing on the Python side for dispatch, good enough for
         // now.
         match warning {
             PatternFileWarning::InvalidSyntax(file, syn) => {
                 py_warnings.append(
                     py,
                     (
                         PyBytes::new(py, &get_bytes_from_path(&file)),
                         PyBytes::new(py, syn),
                     )
                         .to_py_object(py)
                         .into_object(),
                 );
             }
             PatternFileWarning::NoSuchFile(file) => py_warnings.append(
                 py,
                 PyBytes::new(py, &get_bytes_from_path(&file)).into_object(),
             ),
         }
     }
 
     Ok(PyTuple::new(
         py,
         &[
-            lookup.into_object(),
+            unsure.into_object(),
             modified.into_object(),
             added.into_object(),
             removed.into_object(),
             deleted.into_object(),
             clean.into_object(),
             ignored.into_object(),
             unknown.into_object(),
             py_warnings.into_object(),
             bad.into_object(),
             traversed.into_object(),
         ][..],
     ))
 }

rust/rhg/src/commands/status.rs

@@ -1,315 +1,315 b''
 // status.rs
 //
 // Copyright 2020, Georges Racinet <[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.
 
 use crate::error::CommandError;
 use crate::ui::Ui;
 use clap::{Arg, SubCommand};
 use hg;
 use hg::errors::IoResultExt;
 use hg::matchers::AlwaysMatcher;
 use hg::operations::cat;
 use hg::repo::Repo;
 use hg::revlog::node::Node;
 use hg::utils::hg_path::{hg_path_to_os_string, HgPath};
 use hg::{DirstateMap, StatusError};
 use hg::{HgPathCow, StatusOptions};
 use log::{info, warn};
 use std::convert::TryInto;
 use std::fs;
 use std::io::BufReader;
 use std::io::Read;
 
 pub const HELP_TEXT: &str = "
 Show changed files in the working directory
 
 This is a pure Rust version of `hg status`.
 
 Some options might be missing, check the list below.
 ";
 
 pub fn args() -> clap::App<'static, 'static> {
     SubCommand::with_name("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::with_name("all")
                 .help("show status of all files")
                 .short("-A")
                 .long("--all"),
         )
         .arg(
             Arg::with_name("modified")
                 .help("show only modified files")
                 .short("-m")
                 .long("--modified"),
         )
         .arg(
             Arg::with_name("added")
                 .help("show only added files")
                 .short("-a")
                 .long("--added"),
         )
         .arg(
             Arg::with_name("removed")
                 .help("show only removed files")
                 .short("-r")
                 .long("--removed"),
         )
         .arg(
             Arg::with_name("clean")
                 .help("show only clean files")
                 .short("-c")
                 .long("--clean"),
         )
         .arg(
             Arg::with_name("deleted")
                 .help("show only deleted files")
                 .short("-d")
                 .long("--deleted"),
         )
         .arg(
             Arg::with_name("unknown")
                 .help("show only unknown (not tracked) files")
                 .short("-u")
                 .long("--unknown"),
         )
         .arg(
             Arg::with_name("ignored")
                 .help("show only ignored files")
                 .short("-i")
                 .long("--ignored"),
         )
 }
 
 /// Pure data type allowing the caller to specify file states to display
 #[derive(Copy, Clone, Debug)]
 pub struct DisplayStates {
     pub modified: bool,
     pub added: bool,
     pub removed: bool,
     pub clean: bool,
     pub deleted: bool,
     pub unknown: bool,
     pub ignored: bool,
 }
 
 pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: false,
     deleted: true,
     unknown: true,
     ignored: false,
 };
 
 pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: true,
     deleted: true,
     unknown: true,
     ignored: true,
 };
 
 impl DisplayStates {
     pub fn is_empty(&self) -> bool {
         !(self.modified
             || self.added
             || self.removed
             || self.clean
             || self.deleted
             || self.unknown
             || self.ignored)
     }
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     let status_enabled_default = false;
     let status_enabled = invocation.config.get_option(b"rhg", b"status")?;
     if !status_enabled.unwrap_or(status_enabled_default) {
         return Err(CommandError::unsupported(
             "status is experimental in rhg (enable it with 'rhg.status = true' \
             or enable fallback with 'rhg.on-unsupported = fallback')"
         ));
     }
 
     let ui = invocation.ui;
     let args = invocation.subcommand_args;
     let display_states = if args.is_present("all") {
         // TODO when implementing `--quiet`: it excludes clean files
         // from `--all`
         ALL_DISPLAY_STATES
     } else {
         let requested = DisplayStates {
             modified: args.is_present("modified"),
             added: args.is_present("added"),
             removed: args.is_present("removed"),
             clean: args.is_present("clean"),
             deleted: args.is_present("deleted"),
             unknown: args.is_present("unknown"),
             ignored: args.is_present("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
 
     let repo = invocation.repo?;
     let mut dmap = DirstateMap::new();
     let dirstate_data = repo.hg_vfs().mmap_open("dirstate")?;
     let parents = dmap.read(&dirstate_data)?;
     let options = StatusOptions {
         // TODO should be provided by the dirstate parsing and
         // hence be stored on dmap. Using a value that assumes we aren't
         // below the time resolution granularity of the FS and the
         // dirstate.
         last_normal_time: 0,
         // we're currently supporting file systems with exec flags only
         // anyway
         check_exec: true,
         list_clean: display_states.clean,
         list_unknown: display_states.unknown,
         list_ignored: display_states.ignored,
         collect_traversed_dirs: false,
     };
     let ignore_file = repo.working_directory_vfs().join(".hgignore"); // TODO hardcoded
-    let ((lookup, ds_status), pattern_warnings) = hg::status(
+    let (ds_status, pattern_warnings) = hg::status(
         &dmap,
         &AlwaysMatcher,
         repo.working_directory_path().to_owned(),
         vec![ignore_file],
         options,
     )?;
     if !pattern_warnings.is_empty() {
         warn!("Pattern warnings: {:?}", &pattern_warnings);
     }
 
     if !ds_status.bad.is_empty() {
         warn!("Bad matches {:?}", &(ds_status.bad))
     }
-    if !lookup.is_empty() {
+    if !ds_status.unsure.is_empty() {
         info!(
             "Files to be rechecked by retrieval from filelog: {:?}",
-            &lookup
+            &ds_status.unsure
         );
     }
     // TODO check ordering to match `hg status` output.
     // (this is as in `hg help status`)
     if display_states.modified {
         display_status_paths(ui, &(ds_status.modified), b"M")?;
     }
-    if !lookup.is_empty() {
+    if !ds_status.unsure.is_empty() {
         let p1: Node = parents
             .expect(
                 "Dirstate with no parents should not list any file to
                  be rechecked for modifications",
             )
             .p1
             .into();
         let p1_hex = format!("{:x}", p1);
         let mut rechecked_modified: Vec<HgPathCow> = Vec::new();
         let mut rechecked_clean: Vec<HgPathCow> = Vec::new();
-        for to_check in lookup {
+        for to_check in ds_status.unsure {
             if cat_file_is_modified(repo, &to_check, &p1_hex)? {
                 rechecked_modified.push(to_check);
             } else {
                 rechecked_clean.push(to_check);
             }
         }
         if display_states.modified {
             display_status_paths(ui, &rechecked_modified, b"M")?;
         }
         if display_states.clean {
             display_status_paths(ui, &rechecked_clean, b"C")?;
         }
     }
     if display_states.added {
         display_status_paths(ui, &(ds_status.added), b"A")?;
     }
     if display_states.clean {
         display_status_paths(ui, &(ds_status.clean), b"C")?;
     }
     if display_states.removed {
         display_status_paths(ui, &(ds_status.removed), b"R")?;
     }
     if display_states.deleted {
         display_status_paths(ui, &(ds_status.deleted), b"!")?;
     }
     if display_states.unknown {
         display_status_paths(ui, &(ds_status.unknown), b"?")?;
     }
     if display_states.ignored {
         display_status_paths(ui, &(ds_status.ignored), b"I")?;
     }
     Ok(())
 }
 
 // Probably more elegant to use a Deref or Borrow trait rather than
 // harcode HgPathBuf, but probably not really useful at this point
 fn display_status_paths(
     ui: &Ui,
     paths: &[HgPathCow],
     status_prefix: &[u8],
 ) -> Result<(), CommandError> {
     for path in paths {
         // Same TODO as in commands::root
         let bytes: &[u8] = path.as_bytes();
         // TODO optim, probably lots of unneeded copies here, especially
         // if out stream is buffered
         ui.write_stdout(&[status_prefix, b" ", bytes, b"\n"].concat())?;
     }
     Ok(())
 }
 
 /// Check if a file is modified by comparing actual repo store and file system.
 ///
 /// This meant to be used for those that the dirstate cannot resolve, due
 /// to time resolution limits.
 ///
 /// TODO: detect permission bits and similar metadata modifications
 fn cat_file_is_modified(
     repo: &Repo,
     hg_path: &HgPath,
     rev: &str,
 ) -> Result<bool, CommandError> {
     // TODO CatRev expects &[HgPathBuf], something like
     // &[impl Deref<HgPath>] would be nicer and should avoid the copy
     let path_bufs = [hg_path.into()];
     // TODO IIUC CatRev returns a simple Vec<u8> for all files
     //      being able to tell them apart as (path, bytes) would be nicer
     //      and OPTIM would allow manifest resolution just once.
     let output = cat(repo, rev, &path_bufs).map_err(|e| (e, rev))?;
 
     let fs_path = repo
         .working_directory_vfs()
         .join(hg_path_to_os_string(hg_path).expect("HgPath conversion"));
     let hg_data_len: u64 = match output.concatenated.len().try_into() {
         Ok(v) => v,
         Err(_) => {
             // conversion of data length to u64 failed,
             // good luck for any file to have this content
             return Ok(true);
         }
     };
     let fobj = fs::File::open(&fs_path).when_reading_file(&fs_path)?;
     if fobj.metadata().map_err(|e| StatusError::from(e))?.len() != hg_data_len
     {
         return Ok(true);
     }
     for (fs_byte, hg_byte) in
         BufReader::new(fobj).bytes().zip(output.concatenated)
     {
         if fs_byte.map_err(|e| StatusError::from(e))? != hg_byte {
             return Ok(true);
         }
     }
     Ok(false)
 }