rust: Remove EntryState::Unknown

This enum variant represented the `state == '?'` case, which was used
to represent the absence of a dirstate entry/item (and therefore of that
entry’s state).

Now that previous refactors have removed this use in the Python/Rust
FFI APIs, the remaining uses can be removed by replacing `EntryState`
by `Option<EntryState>` where appropriate, using `None` to represent
the absence of an entry.

Differential Revision: https://phab.mercurial-scm.org/D11465

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

@@ -1,481 +1,470 b''
 // dirstate_map.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::parsers::Timestamp;
 use crate::{
     dirstate::EntryState,
     dirstate::MTIME_UNSET,
     dirstate::SIZE_FROM_OTHER_PARENT,
     dirstate::SIZE_NON_NORMAL,
     dirstate::V1_RANGEMASK,
     pack_dirstate, parse_dirstate,
     utils::hg_path::{HgPath, HgPathBuf},
     CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateParents,
     StateMap,
 };
 use micro_timer::timed;
 use std::collections::HashSet;
 use std::iter::FromIterator;
 use std::ops::Deref;
 
 #[derive(Default)]
 pub struct DirstateMap {
     state_map: StateMap,
     pub copy_map: CopyMap,
     pub dirs: Option<DirsMultiset>,
     pub all_dirs: Option<DirsMultiset>,
     non_normal_set: Option<HashSet<HgPathBuf>>,
     other_parent_set: Option<HashSet<HgPathBuf>>,
 }
 
 /// Should only really be used in python interface code, for clarity
 impl Deref for DirstateMap {
     type Target = StateMap;
 
     fn deref(&self) -> &Self::Target {
         &self.state_map
     }
 }
 
 impl FromIterator<(HgPathBuf, DirstateEntry)> for DirstateMap {
     fn from_iter<I: IntoIterator<Item = (HgPathBuf, DirstateEntry)>>(
         iter: I,
     ) -> Self {
         Self {
             state_map: iter.into_iter().collect(),
             ..Self::default()
         }
     }
 }
 
 impl DirstateMap {
     pub fn new() -> Self {
         Self::default()
     }
 
     pub fn clear(&mut self) {
         self.state_map = StateMap::default();
         self.copy_map.clear();
         self.non_normal_set = None;
         self.other_parent_set = None;
     }
 
     pub fn set_v1_inner(&mut self, filename: &HgPath, entry: DirstateEntry) {
         self.state_map.insert(filename.to_owned(), entry);
     }
 
     /// Add a tracked file to the dirstate
     pub fn add_file(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
         // XXX once the dust settle this should probably become an enum
         added: bool,
         merged: bool,
         from_p2: bool,
         possibly_dirty: bool,
     ) -> Result<(), DirstateError> {
         let state;
         let size;
         let mtime;
         if added {
             assert!(!possibly_dirty);
             assert!(!from_p2);
             state = EntryState::Added;
             size = SIZE_NON_NORMAL;
             mtime = MTIME_UNSET;
         } else if merged {
             assert!(!possibly_dirty);
             assert!(!from_p2);
             state = EntryState::Merged;
             size = SIZE_FROM_OTHER_PARENT;
             mtime = MTIME_UNSET;
         } else if from_p2 {
             assert!(!possibly_dirty);
             state = EntryState::Normal;
             size = SIZE_FROM_OTHER_PARENT;
             mtime = MTIME_UNSET;
         } else if possibly_dirty {
             state = EntryState::Normal;
             size = SIZE_NON_NORMAL;
             mtime = MTIME_UNSET;
         } else {
             state = EntryState::Normal;
             size = entry.size() & V1_RANGEMASK;
             mtime = entry.mtime() & V1_RANGEMASK;
         }
         let mode = entry.mode();
         let entry = DirstateEntry::from_v1_data(state, mode, size, mtime);
 
-        let old_state = match self.get(filename) {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
-        if old_state == EntryState::Unknown || old_state == EntryState::Removed
-        {
+        let old_state = self.get(filename).map(|e| e.state());
+        if old_state.is_none() || old_state == Some(EntryState::Removed) {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.add_path(filename)?;
             }
         }
-        if old_state == EntryState::Unknown {
+        if old_state.is_none() {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename)?;
             }
         }
         self.state_map.insert(filename.to_owned(), entry.to_owned());
 
         if entry.is_non_normal() {
             self.get_non_normal_other_parent_entries()
                 .0
                 .insert(filename.to_owned());
         }
 
         if entry.is_from_other_parent() {
             self.get_non_normal_other_parent_entries()
                 .1
                 .insert(filename.to_owned());
         }
         Ok(())
     }
 
     /// Mark a file as removed in the dirstate.
     ///
     /// The `size` parameter is used to store sentinel values that indicate
     /// the file's previous state.  In the future, we should refactor this
     /// to be more explicit about what that state is.
     pub fn remove_file(
         &mut self,
         filename: &HgPath,
         in_merge: bool,
     ) -> Result<(), DirstateError> {
         let old_entry_opt = self.get(filename);
-        let old_state = match old_entry_opt {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
+        let old_state = old_entry_opt.map(|e| e.state());
         let mut size = 0;
         if in_merge {
             // XXX we should not be able to have 'm' state and 'FROM_P2' if not
             // during a merge. So I (marmoute) am not sure we need the
             // conditionnal at all. Adding double checking this with assert
             // would be nice.
             if let Some(old_entry) = old_entry_opt {
                 // backup the previous state
                 if old_entry.state() == EntryState::Merged {
                     size = SIZE_NON_NORMAL;
                 } else if old_entry.state() == EntryState::Normal
                     && old_entry.size() == SIZE_FROM_OTHER_PARENT
                 {
                     // other parent
                     size = SIZE_FROM_OTHER_PARENT;
                     self.get_non_normal_other_parent_entries()
                         .1
                         .insert(filename.to_owned());
                 }
             }
         }
-        if old_state != EntryState::Unknown && old_state != EntryState::Removed
-        {
+        if old_state.is_some() && old_state != Some(EntryState::Removed) {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.delete_path(filename)?;
             }
         }
-        if old_state == EntryState::Unknown {
+        if old_state.is_none() {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename)?;
             }
         }
         if size == 0 {
             self.copy_map.remove(filename);
         }
 
         self.state_map
             .insert(filename.to_owned(), DirstateEntry::new_removed(size));
         self.get_non_normal_other_parent_entries()
             .0
             .insert(filename.to_owned());
         Ok(())
     }
 
     /// Remove a file from the dirstate.
     /// Returns `true` if the file was previously recorded.
     pub fn drop_file(
         &mut self,
         filename: &HgPath,
     ) -> Result<bool, DirstateError> {
-        let old_state = match self.get(filename) {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
+        let old_state = self.get(filename).map(|e| e.state());
         let exists = self.state_map.remove(filename).is_some();
 
         if exists {
-            if old_state != EntryState::Removed {
+            if old_state != Some(EntryState::Removed) {
                 if let Some(ref mut dirs) = self.dirs {
                     dirs.delete_path(filename)?;
                 }
             }
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.delete_path(filename)?;
             }
         }
         self.get_non_normal_other_parent_entries()
             .0
             .remove(filename);
 
         Ok(exists)
     }
 
     pub fn clear_ambiguous_times(
         &mut self,
         filenames: Vec<HgPathBuf>,
         now: i32,
     ) {
         for filename in filenames {
             if let Some(entry) = self.state_map.get_mut(&filename) {
                 if entry.clear_ambiguous_mtime(now) {
                     self.get_non_normal_other_parent_entries()
                         .0
                         .insert(filename.to_owned());
                 }
             }
         }
     }
 
     pub fn non_normal_entries_remove(
         &mut self,
         key: impl AsRef<HgPath>,
     ) -> bool {
         self.get_non_normal_other_parent_entries()
             .0
             .remove(key.as_ref())
     }
 
     pub fn non_normal_entries_add(&mut self, key: impl AsRef<HgPath>) {
         self.get_non_normal_other_parent_entries()
             .0
             .insert(key.as_ref().into());
     }
 
     pub fn non_normal_entries_union(
         &mut self,
         other: HashSet<HgPathBuf>,
     ) -> Vec<HgPathBuf> {
         self.get_non_normal_other_parent_entries()
             .0
             .union(&other)
             .map(ToOwned::to_owned)
             .collect()
     }
 
     pub fn get_non_normal_other_parent_entries(
         &mut self,
     ) -> (&mut HashSet<HgPathBuf>, &mut HashSet<HgPathBuf>) {
         self.set_non_normal_other_parent_entries(false);
         (
             self.non_normal_set.as_mut().unwrap(),
             self.other_parent_set.as_mut().unwrap(),
         )
     }
 
     /// Useful to get immutable references to those sets in contexts where
     /// you only have an immutable reference to the `DirstateMap`, like when
     /// sharing references with Python.
     ///
     /// TODO, get rid of this along with the other "setter/getter" stuff when
     /// a nice typestate plan is defined.
     ///
     /// # Panics
     ///
     /// Will panic if either set is `None`.
     pub fn get_non_normal_other_parent_entries_panic(
         &self,
     ) -> (&HashSet<HgPathBuf>, &HashSet<HgPathBuf>) {
         (
             self.non_normal_set.as_ref().unwrap(),
             self.other_parent_set.as_ref().unwrap(),
         )
     }
 
     pub fn set_non_normal_other_parent_entries(&mut self, force: bool) {
         if !force
             && self.non_normal_set.is_some()
             && self.other_parent_set.is_some()
         {
             return;
         }
         let mut non_normal = HashSet::new();
         let mut other_parent = HashSet::new();
 
         for (filename, entry) in self.state_map.iter() {
             if entry.is_non_normal() {
                 non_normal.insert(filename.to_owned());
             }
             if entry.is_from_other_parent() {
                 other_parent.insert(filename.to_owned());
             }
         }
         self.non_normal_set = Some(non_normal);
         self.other_parent_set = Some(other_parent);
     }
 
     /// Both of these setters and their uses appear to be the simplest way to
     /// emulate a Python lazy property, but it is ugly and unidiomatic.
     /// TODO One day, rewriting this struct using the typestate might be a
     /// good idea.
     pub fn set_all_dirs(&mut self) -> Result<(), DirstateError> {
         if self.all_dirs.is_none() {
             self.all_dirs = Some(DirsMultiset::from_dirstate(
                 self.state_map.iter().map(|(k, v)| Ok((k, *v))),
                 false,
             )?);
         }
         Ok(())
     }
 
     pub fn set_dirs(&mut self) -> Result<(), DirstateError> {
         if self.dirs.is_none() {
             self.dirs = Some(DirsMultiset::from_dirstate(
                 self.state_map.iter().map(|(k, v)| Ok((k, *v))),
                 true,
             )?);
         }
         Ok(())
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         self.set_dirs()?;
         Ok(self.dirs.as_ref().unwrap().contains(directory))
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         self.set_all_dirs()?;
         Ok(self.all_dirs.as_ref().unwrap().contains(directory))
     }
 
     #[timed]
     pub fn read(
         &mut self,
         file_contents: &[u8],
     ) -> Result<Option<DirstateParents>, DirstateError> {
         if file_contents.is_empty() {
             return Ok(None);
         }
 
         let (parents, entries, copies) = parse_dirstate(file_contents)?;
         self.state_map.extend(
             entries
                 .into_iter()
                 .map(|(path, entry)| (path.to_owned(), entry)),
         );
         self.copy_map.extend(
             copies
                 .into_iter()
                 .map(|(path, copy)| (path.to_owned(), copy.to_owned())),
         );
         Ok(Some(parents.clone()))
     }
 
     pub fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         let packed =
             pack_dirstate(&mut self.state_map, &self.copy_map, parents, now)?;
 
         self.set_non_normal_other_parent_entries(true);
         Ok(packed)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn test_dirs_multiset() {
         let mut map = DirstateMap::new();
         assert!(map.dirs.is_none());
         assert!(map.all_dirs.is_none());
 
         assert_eq!(map.has_dir(HgPath::new(b"nope")).unwrap(), false);
         assert!(map.all_dirs.is_some());
         assert!(map.dirs.is_none());
 
         assert_eq!(map.has_tracked_dir(HgPath::new(b"nope")).unwrap(), false);
         assert!(map.dirs.is_some());
     }
 
     #[test]
     fn test_add_file() {
         let mut map = DirstateMap::new();
 
         assert_eq!(0, map.len());
 
         map.add_file(
             HgPath::new(b"meh"),
             DirstateEntry::from_v1_data(EntryState::Normal, 1337, 1337, 1337),
             false,
             false,
             false,
             false,
         )
         .unwrap();
 
         assert_eq!(1, map.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().0.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().1.len());
     }
 
     #[test]
     fn test_non_normal_other_parent_entries() {
         let mut map: DirstateMap = [
             (b"f1", (EntryState::Removed, 1337, 1337, 1337)),
             (b"f2", (EntryState::Normal, 1337, 1337, -1)),
             (b"f3", (EntryState::Normal, 1337, 1337, 1337)),
             (b"f4", (EntryState::Normal, 1337, -2, 1337)),
             (b"f5", (EntryState::Added, 1337, 1337, 1337)),
             (b"f6", (EntryState::Added, 1337, 1337, -1)),
             (b"f7", (EntryState::Merged, 1337, 1337, -1)),
             (b"f8", (EntryState::Merged, 1337, 1337, 1337)),
             (b"f9", (EntryState::Merged, 1337, -2, 1337)),
             (b"fa", (EntryState::Added, 1337, -2, 1337)),
             (b"fb", (EntryState::Removed, 1337, -2, 1337)),
         ]
         .iter()
         .map(|(fname, (state, mode, size, mtime))| {
             (
                 HgPathBuf::from_bytes(fname.as_ref()),
                 DirstateEntry::from_v1_data(*state, *mode, *size, *mtime),
             )
         })
         .collect();
 
         let mut non_normal = [
             b"f1", b"f2", b"f5", b"f6", b"f7", b"f8", b"f9", b"fa", b"fb",
         ]
         .iter()
         .map(|x| HgPathBuf::from_bytes(x.as_ref()))
         .collect();
 
         let mut other_parent = HashSet::new();
         other_parent.insert(HgPathBuf::from_bytes(b"f4"));
         let entries = map.get_non_normal_other_parent_entries();
 
         assert_eq!(
             (&mut non_normal, &mut other_parent),
             (entries.0, entries.1)
         );
     }
 }

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

@@ -1,193 +1,190 b''
 use crate::errors::HgError;
 use std::convert::TryFrom;
 
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum EntryState {
     Normal,
     Added,
     Removed,
     Merged,
-    Unknown,
 }
 
 /// The C implementation uses all signed types. This will be an issue
 /// either when 4GB+ source files are commonplace or in 2038, whichever
 /// comes first.
 #[derive(Debug, PartialEq, Copy, Clone)]
 pub struct DirstateEntry {
     state: EntryState,
     mode: i32,
     size: i32,
     mtime: i32,
 }
 
 pub const V1_RANGEMASK: i32 = 0x7FFFFFFF;
 
 pub const MTIME_UNSET: i32 = -1;
 
 /// A `DirstateEntry` with a size of `-2` means that it was merged from the
 /// other parent. This allows revert to pick the right status back during a
 /// merge.
 pub const SIZE_FROM_OTHER_PARENT: i32 = -2;
 /// A special value used for internal representation of special case in
 /// dirstate v1 format.
 pub const SIZE_NON_NORMAL: i32 = -1;
 
 impl DirstateEntry {
     pub fn from_v1_data(
         state: EntryState,
         mode: i32,
         size: i32,
         mtime: i32,
     ) -> Self {
         Self {
             state,
             mode,
             size,
             mtime,
         }
     }
 
     /// Creates a new entry in "removed" state.
     ///
     /// `size` is expected to be zero, `SIZE_NON_NORMAL`, or
     /// `SIZE_FROM_OTHER_PARENT`
     pub fn new_removed(size: i32) -> Self {
         Self {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         }
     }
 
     /// TODO: refactor `DirstateMap::add_file` to not take a `DirstateEntry`
     /// parameter and remove this constructor
     pub fn new_for_add_file(mode: i32, size: i32, mtime: i32) -> Self {
         Self {
             // XXX Arbitrary default value since the value is determined later
             state: EntryState::Normal,
             mode,
             size,
             mtime,
         }
     }
 
     pub fn state(&self) -> EntryState {
         self.state
     }
 
     pub fn mode(&self) -> i32 {
         self.mode
     }
 
     pub fn size(&self) -> i32 {
         self.size
     }
 
     pub fn mtime(&self) -> i32 {
         self.mtime
     }
 
     /// Returns `(state, mode, size, mtime)` for the puprose of serialization
     /// in the dirstate-v1 format.
     ///
     /// This includes marker values such as `mtime == -1`. In the future we may
     /// want to not represent these cases that way in memory, but serialization
     /// will need to keep the same format.
     pub fn v1_data(&self) -> (u8, i32, i32, i32) {
         (self.state.into(), self.mode, self.size, self.mtime)
     }
 
     pub fn is_non_normal(&self) -> bool {
         self.state != EntryState::Normal || self.mtime == MTIME_UNSET
     }
 
     pub fn is_from_other_parent(&self) -> bool {
         self.state == EntryState::Normal && self.size == SIZE_FROM_OTHER_PARENT
     }
 
     // TODO: other platforms
     #[cfg(unix)]
     pub fn mode_changed(
         &self,
         filesystem_metadata: &std::fs::Metadata,
     ) -> bool {
         use std::os::unix::fs::MetadataExt;
         const EXEC_BIT_MASK: u32 = 0o100;
         let dirstate_exec_bit = (self.mode as u32) & EXEC_BIT_MASK;
         let fs_exec_bit = filesystem_metadata.mode() & EXEC_BIT_MASK;
         dirstate_exec_bit != fs_exec_bit
     }
 
     /// Returns a `(state, mode, size, mtime)` tuple as for
     /// `DirstateMapMethods::debug_iter`.
     pub fn debug_tuple(&self) -> (u8, i32, i32, i32) {
         (self.state.into(), self.mode, self.size, self.mtime)
     }
 
     pub fn mtime_is_ambiguous(&self, now: i32) -> bool {
         self.state == EntryState::Normal && self.mtime == now
     }
 
     pub fn clear_ambiguous_mtime(&mut self, now: i32) -> bool {
         let ambiguous = self.mtime_is_ambiguous(now);
         if ambiguous {
             // The file was last modified "simultaneously" with the current
             // write to dirstate (i.e. within the same second for file-
             // systems with a granularity of 1 sec). This commonly happens
             // for at least a couple of files on 'update'.
             // The user could change the file without changing its size
             // within the same second. Invalidate the file's mtime in
             // dirstate, forcing future 'status' calls to compare the
             // contents of the file if the size is the same. This prevents
             // mistakenly treating such files as clean.
             self.clear_mtime()
         }
         ambiguous
     }
 
     pub fn clear_mtime(&mut self) {
         self.mtime = -1;
     }
 }
 
 impl EntryState {
     pub fn is_tracked(self) -> bool {
         use EntryState::*;
         match self {
             Normal | Added | Merged => true,
-            Removed | Unknown => false,
+            Removed => false,
         }
     }
 }
 
 impl TryFrom<u8> for EntryState {
     type Error = HgError;
 
     fn try_from(value: u8) -> Result<Self, Self::Error> {
         match value {
             b'n' => Ok(EntryState::Normal),
             b'a' => Ok(EntryState::Added),
             b'r' => Ok(EntryState::Removed),
             b'm' => Ok(EntryState::Merged),
-            b'?' => Ok(EntryState::Unknown),
             _ => Err(HgError::CorruptedRepository(format!(
                 "Incorrect dirstate entry state {}",
                 value
             ))),
         }
     }
 }
 
 impl Into<u8> for EntryState {
     fn into(self) -> u8 {
         match self {
             EntryState::Normal => b'n',
             EntryState::Added => b'a',
             EntryState::Removed => b'r',
             EntryState::Merged => b'm',
-            EntryState::Unknown => b'?',
         }
     }
 }

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

@@ -1,947 +1,944 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_tree::on_disk::DirstateV2ParseError;
 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".
 pub 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 {
     match entry.state() {
         EntryState::Normal => {
             let mode = entry.mode();
             let size = entry.size();
             let mtime = entry.mtime();
 
             let HgMetadata {
                 st_mode,
                 st_size,
                 st_mtime,
                 ..
             } = metadata;
 
             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, Default)]
 pub struct DirstateStatus<'a> {
     /// Tracked files whose contents have changed since the parent revision
     pub modified: Vec<HgPathCow<'a>>,
 
     /// Newly-tracked files that were not present in the parent
     pub added: Vec<HgPathCow<'a>>,
 
     /// Previously-tracked files that have been (re)moved with an hg command
     pub removed: Vec<HgPathCow<'a>>,
 
     /// (Still) tracked files that are missing, (re)moved with an non-hg
     /// command
     pub deleted: Vec<HgPathCow<'a>>,
 
     /// Tracked files that are up to date with the parent.
     /// Only pupulated if `StatusOptions::list_clean` is true.
     pub clean: Vec<HgPathCow<'a>>,
 
     /// Files in the working directory that are ignored with `.hgignore`.
     /// Only pupulated if `StatusOptions::list_ignored` is true.
     pub ignored: Vec<HgPathCow<'a>>,
 
     /// Files in the working directory that are neither tracked nor ignored.
     /// Only pupulated if `StatusOptions::list_unknown` is true.
     pub unknown: Vec<HgPathCow<'a>>,
 
     /// Was explicitly matched but cannot be found/accessed
     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<HgPathCow<'a>>,
 
     /// Whether `status()` made changed to the `DirstateMap` that should be
     /// written back to disk
     pub dirty: bool,
 }
 
 #[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),
     /// Corrupted dirstate
     DirstateV2ParseError(DirstateV2ParseError),
 }
 
 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),
             StatusError::DirstateV2ParseError(_) => {
                 f.write_str("dirstate-v2 parse error")
             }
         }
     }
 }
 
 /// 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, &mut |_| {})?
             } 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 {
                 if self.matcher.matches(&filename) {
                     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<HgPathCow<'a>>,
 ) -> 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 => 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 { .. } => {}
         }
     }
 
     DirstateStatus {
         modified,
         added,
         removed,
         deleted,
         clean,
         ignored,
         unknown,
         bad,
         unsure,
         traversed,
         dirty: false,
     }
 }
 
 /// 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<(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

@@ -1,1315 +1,1309 b''
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::convert::TryInto;
 use std::path::PathBuf;
 
 use super::on_disk;
 use super::on_disk::DirstateV2ParseError;
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::Timestamp;
 use crate::dirstate::MTIME_UNSET;
 use crate::dirstate::SIZE_FROM_OTHER_PARENT;
 use crate::dirstate::SIZE_NON_NORMAL;
 use crate::dirstate::V1_RANGEMASK;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::FastHashMap;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 /// Append to an existing data file if the amount of unreachable data (not used
 /// anymore) is less than this fraction of the total amount of existing data.
 const ACCEPTABLE_UNREACHABLE_BYTES_RATIO: f32 = 0.5;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     pub(super) on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     pub(super) nodes_with_entry_count: u32,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     pub(super) nodes_with_copy_source_count: u32,
 
     /// See on_disk::Header
     pub(super) ignore_patterns_hash: on_disk::IgnorePatternsHash,
 
     /// How many bytes of `on_disk` are not used anymore
     pub(super) unreachable_bytes: u32,
 }
 
 /// 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 `HashMap` would waste time always re-hashing the same
 /// string prefix.
 pub(super) type NodeKey<'on_disk> = WithBasename<Cow<'on_disk, HgPath>>;
 
 /// Similar to `&'tree Cow<'on_disk, HgPath>`, but can also be returned
 /// for on-disk nodes that don’t actually have a `Cow` to borrow.
 pub(super) enum BorrowedPath<'tree, 'on_disk> {
     InMemory(&'tree HgPathBuf),
     OnDisk(&'on_disk HgPath),
 }
 
 pub(super) enum ChildNodes<'on_disk> {
     InMemory(FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum ChildNodesRef<'tree, 'on_disk> {
     InMemory(&'tree FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum NodeRef<'tree, 'on_disk> {
     InMemory(&'tree NodeKey<'on_disk>, &'tree Node<'on_disk>),
     OnDisk(&'on_disk on_disk::Node),
 }
 
 impl<'tree, 'on_disk> BorrowedPath<'tree, 'on_disk> {
     pub fn detach_from_tree(&self) -> Cow<'on_disk, HgPath> {
         match *self {
             BorrowedPath::InMemory(in_memory) => Cow::Owned(in_memory.clone()),
             BorrowedPath::OnDisk(on_disk) => Cow::Borrowed(on_disk),
         }
     }
 }
 
 impl<'tree, 'on_disk> std::ops::Deref for BorrowedPath<'tree, 'on_disk> {
     type Target = HgPath;
 
     fn deref(&self) -> &HgPath {
         match *self {
             BorrowedPath::InMemory(in_memory) => in_memory,
             BorrowedPath::OnDisk(on_disk) => on_disk,
         }
     }
 }
 
 impl Default for ChildNodes<'_> {
     fn default() -> Self {
         ChildNodes::InMemory(Default::default())
     }
 }
 
 impl<'on_disk> ChildNodes<'on_disk> {
     pub(super) fn as_ref<'tree>(
         &'tree self,
     ) -> ChildNodesRef<'tree, 'on_disk> {
         match self {
             ChildNodes::InMemory(nodes) => ChildNodesRef::InMemory(nodes),
             ChildNodes::OnDisk(nodes) => ChildNodesRef::OnDisk(nodes),
         }
     }
 
     pub(super) fn is_empty(&self) -> bool {
         match self {
             ChildNodes::InMemory(nodes) => nodes.is_empty(),
             ChildNodes::OnDisk(nodes) => nodes.is_empty(),
         }
     }
 
     fn make_mut(
         &mut self,
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
     ) -> Result<
         &mut FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>,
         DirstateV2ParseError,
     > {
         match self {
             ChildNodes::InMemory(nodes) => Ok(nodes),
             ChildNodes::OnDisk(nodes) => {
                 *unreachable_bytes +=
                     std::mem::size_of_val::<[on_disk::Node]>(nodes) as u32;
                 let nodes = nodes
                     .iter()
                     .map(|node| {
                         Ok((
                             node.path(on_disk)?,
                             node.to_in_memory_node(on_disk)?,
                         ))
                     })
                     .collect::<Result<_, _>>()?;
                 *self = ChildNodes::InMemory(nodes);
                 match self {
                     ChildNodes::InMemory(nodes) => Ok(nodes),
                     ChildNodes::OnDisk(_) => unreachable!(),
                 }
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> ChildNodesRef<'tree, 'on_disk> {
     pub(super) fn get(
         &self,
         base_name: &HgPath,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         match self {
             ChildNodesRef::InMemory(nodes) => Ok(nodes
                 .get_key_value(base_name)
                 .map(|(k, v)| NodeRef::InMemory(k, v))),
             ChildNodesRef::OnDisk(nodes) => {
                 let mut parse_result = Ok(());
                 let search_result = nodes.binary_search_by(|node| {
                     match node.base_name(on_disk) {
                         Ok(node_base_name) => node_base_name.cmp(base_name),
                         Err(e) => {
                             parse_result = Err(e);
                             // Dummy comparison result, `search_result` won’t
                             // be used since `parse_result` is an error
                             std::cmp::Ordering::Equal
                         }
                     }
                 });
                 parse_result.map(|()| {
                     search_result.ok().map(|i| NodeRef::OnDisk(&nodes[i]))
                 })
             }
         }
     }
 
     /// Iterate in undefined order
     pub(super) fn iter(
         &self,
     ) -> impl Iterator<Item = NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => itertools::Either::Left(
                 nodes.iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => {
                 itertools::Either::Right(nodes.iter().map(NodeRef::OnDisk))
             }
         }
     }
 
     /// Iterate in parallel in undefined order
     pub(super) fn par_iter(
         &self,
     ) -> impl rayon::iter::ParallelIterator<Item = NodeRef<'tree, 'on_disk>>
     {
         use rayon::prelude::*;
         match self {
             ChildNodesRef::InMemory(nodes) => rayon::iter::Either::Left(
                 nodes.par_iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => rayon::iter::Either::Right(
                 nodes.par_iter().map(NodeRef::OnDisk),
             ),
         }
     }
 
     pub(super) fn sorted(&self) -> Vec<NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => {
                 let mut vec: Vec<_> = nodes
                     .iter()
                     .map(|(k, v)| NodeRef::InMemory(k, v))
                     .collect();
                 fn sort_key<'a>(node: &'a NodeRef) -> &'a HgPath {
                     match node {
                         NodeRef::InMemory(path, _node) => path.base_name(),
                         NodeRef::OnDisk(_) => unreachable!(),
                     }
                 }
                 // `sort_unstable_by_key` doesn’t allow keys borrowing from the
                 // value: https://github.com/rust-lang/rust/issues/34162
                 vec.sort_unstable_by(|a, b| sort_key(a).cmp(sort_key(b)));
                 vec
             }
             ChildNodesRef::OnDisk(nodes) => {
                 // Nodes on disk are already sorted
                 nodes.iter().map(NodeRef::OnDisk).collect()
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> NodeRef<'tree, 'on_disk> {
     pub(super) fn full_path(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.full_path()),
             NodeRef::OnDisk(node) => node.full_path(on_disk),
         }
     }
 
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn full_path_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<BorrowedPath<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => match path.full_path() {
                 Cow::Borrowed(on_disk) => Ok(BorrowedPath::OnDisk(on_disk)),
                 Cow::Owned(in_memory) => Ok(BorrowedPath::InMemory(in_memory)),
             },
             NodeRef::OnDisk(node) => {
                 Ok(BorrowedPath::OnDisk(node.full_path(on_disk)?))
             }
         }
     }
 
     pub(super) fn base_name(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.base_name()),
             NodeRef::OnDisk(node) => node.base_name(on_disk),
         }
     }
 
     pub(super) fn children(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<ChildNodesRef<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(node.children.as_ref()),
             NodeRef::OnDisk(node) => {
                 Ok(ChildNodesRef::OnDisk(node.children(on_disk)?))
             }
         }
     }
 
     pub(super) fn has_copy_source(&self) -> bool {
         match self {
             NodeRef::InMemory(_path, node) => node.copy_source.is_some(),
             NodeRef::OnDisk(node) => node.has_copy_source(),
         }
     }
 
     pub(super) fn copy_source(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<&'tree HgPath>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.copy_source.as_ref().map(|s| &**s))
             }
             NodeRef::OnDisk(node) => node.copy_source(on_disk),
         }
     }
 
     pub(super) fn entry(
         &self,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().copied())
             }
             NodeRef::OnDisk(node) => node.entry(),
         }
     }
 
     pub(super) fn state(
         &self,
     ) -> Result<Option<EntryState>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().map(|entry| entry.state()))
             }
             NodeRef::OnDisk(node) => node.state(),
         }
     }
 
     pub(super) fn cached_directory_mtime(
         &self,
     ) -> Option<&'tree on_disk::Timestamp> {
         match self {
             NodeRef::InMemory(_path, node) => match &node.data {
                 NodeData::CachedDirectory { mtime } => Some(mtime),
                 _ => None,
             },
             NodeRef::OnDisk(node) => node.cached_directory_mtime(),
         }
     }
 
     pub(super) fn descendants_with_entry_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => {
                 node.descendants_with_entry_count
             }
             NodeRef::OnDisk(node) => node.descendants_with_entry_count.get(),
         }
     }
 
     pub(super) fn tracked_descendants_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => node.tracked_descendants_count,
             NodeRef::OnDisk(node) => node.tracked_descendants_count.get(),
         }
     }
 }
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     pub(super) data: NodeData,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node have an entry.
     pub(super) descendants_with_entry_count: u32,
 
     /// How many (non-inclusive) descendants of this node have an entry whose
     /// state is "tracked".
     pub(super) tracked_descendants_count: u32,
 }
 
 pub(super) enum NodeData {
     Entry(DirstateEntry),
     CachedDirectory { mtime: on_disk::Timestamp },
     None,
 }
 
 impl Default for NodeData {
     fn default() -> Self {
         NodeData::None
     }
 }
 
 impl NodeData {
     fn has_entry(&self) -> bool {
         match self {
             NodeData::Entry(_) => true,
             _ => false,
         }
     }
 
     fn as_entry(&self) -> Option<&DirstateEntry> {
         match self {
             NodeData::Entry(entry) => Some(entry),
             _ => None,
         }
     }
 }
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub(super) fn empty(on_disk: &'on_disk [u8]) -> Self {
         Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
             ignore_patterns_hash: [0; on_disk::IGNORE_PATTERNS_HASH_LEN],
             unreachable_bytes: 0,
         }
     }
 
     #[timed]
     pub fn new_v2(
         on_disk: &'on_disk [u8],
         data_size: usize,
         metadata: &[u8],
     ) -> Result<Self, DirstateError> {
         if let Some(data) = on_disk.get(..data_size) {
             Ok(on_disk::read(data, metadata)?)
         } else {
             Err(DirstateV2ParseError.into())
         }
     }
 
     #[timed]
     pub fn new_v1(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self::empty(on_disk);
         if map.on_disk.is_empty() {
             return Ok((map, None));
         }
 
         let parents = parse_dirstate_entries(
             map.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state().is_tracked();
                 let node = Self::get_or_insert_node(
                     map.on_disk,
                     &mut map.unreachable_bytes,
                     &mut map.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                         ancestor.descendants_with_entry_count += 1
                     },
                 )?;
                 assert!(
                     !node.data.has_entry(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.data = NodeData::Entry(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 map.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     map.nodes_with_copy_source_count += 1
                 }
                 Ok(())
             },
         )?;
         let parents = Some(parents.clone());
 
         Ok((map, parents))
     }
 
     /// Assuming dirstate-v2 format, returns whether the next write should
     /// append to the existing data file that contains `self.on_disk` (true),
     /// or create a new data file from scratch (false).
     pub(super) fn write_should_append(&self) -> bool {
         let ratio = self.unreachable_bytes as f32 / self.on_disk.len() as f32;
         ratio < ACCEPTABLE_UNREACHABLE_BYTES_RATIO
     }
 
     fn get_node<'tree>(
         &'tree self,
         path: &HgPath,
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         let mut children = self.root.as_ref();
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children.get(component, self.on_disk)? {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = child.children(self.on_disk)?;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     /// 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>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Result<Option<&'tree mut Node<'on_disk>>, DirstateV2ParseError> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children
                 .make_mut(on_disk, unreachable_bytes)?
                 .get_mut(component)
             {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = &mut child.children;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     pub(super) fn get_or_insert<'tree, 'path>(
         &'tree mut self,
         path: &HgPath,
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |_| {},
         )
     }
 
     fn get_or_insert_node<'tree, 'path>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         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 allocating an owned key in cases where the
             // map already contains that key, without introducing double
             // lookup?
             let child_node = child_nodes
                 .make_mut(on_disk, unreachable_bytes)?
                 .entry(to_cow(ancestor_path))
                 .or_default();
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return Ok(child_node);
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
-        old_state: EntryState,
+        old_state: Option<EntryState>,
         new_entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
-        let had_entry = old_state != EntryState::Unknown;
+        let had_entry = old_state.is_some();
+        let was_tracked = old_state.map_or(false, |s| s.is_tracked());
         let tracked_count_increment =
-            match (old_state.is_tracked(), new_entry.state().is_tracked()) {
+            match (was_tracked, new_entry.state().is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 if !had_entry {
                     ancestor.descendants_with_entry_count += 1;
                 }
 
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         )?;
         if !had_entry {
             self.nodes_with_entry_count += 1
         }
         node.data = NodeData::Entry(new_entry);
         Ok(())
     }
 
     fn iter_nodes<'tree>(
         &'tree self,
     ) -> impl Iterator<
         Item = Result<NodeRef<'tree, 'on_disk>, DirstateV2ParseError>,
     > + 'tree {
         // 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.as_ref().iter();
         std::iter::from_fn(move || {
             while let Some(child_node) = iter.next() {
                 let children = match child_node.children(self.on_disk) {
                     Ok(children) => children,
                     Err(error) => return Some(Err(error)),
                 };
                 // Pseudo-recursion
                 let new_iter = children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(Ok(child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     fn clear_known_ambiguous_mtimes(
         &mut self,
         paths: &[impl AsRef<HgPath>],
     ) -> Result<(), DirstateV2ParseError> {
         for path in paths {
             if let Some(node) = Self::get_node_mut(
                 self.on_disk,
                 &mut self.unreachable_bytes,
                 &mut self.root,
                 path.as_ref(),
             )? {
                 if let NodeData::Entry(entry) = &mut node.data {
                     entry.clear_mtime();
                 }
             }
         }
         Ok(())
     }
 
     /// Return a faillilble iterator of full paths of nodes that have an
     /// `entry` for which the given `predicate` returns true.
     ///
     /// Fallibility means that each iterator item is a `Result`, which may
     /// indicate a parse error of the on-disk dirstate-v2 format. Such errors
     /// should only happen if Mercurial is buggy or a repository is corrupted.
     fn filter_full_paths<'tree>(
         &'tree self,
         predicate: impl Fn(&DirstateEntry) -> bool + 'tree,
     ) -> impl Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + 'tree
     {
         filter_map_results(self.iter_nodes(), move |node| {
             if let Some(entry) = node.entry()? {
                 if predicate(&entry) {
                     return Ok(Some(node.full_path(self.on_disk)?));
                 }
             }
             Ok(None)
         })
     }
 
     fn count_dropped_path(unreachable_bytes: &mut u32, path: &Cow<HgPath>) {
         if let Cow::Borrowed(path) = path {
             *unreachable_bytes += path.len() as u32
         }
     }
 }
 
 /// Like `Iterator::filter_map`, but over a fallible iterator of `Result`s.
 ///
 /// The callback is only called for incoming `Ok` values. Errors are passed
 /// through as-is. In order to let it use the `?` operator the callback is
 /// expected to return a `Result` of `Option`, instead of an `Option` of
 /// `Result`.
 fn filter_map_results<'a, I, F, A, B, E>(
     iter: I,
     f: F,
 ) -> impl Iterator<Item = Result<B, E>> + 'a
 where
     I: Iterator<Item = Result<A, E>> + 'a,
     F: Fn(A) -> Result<Option<B>, E> + 'a,
 {
     iter.filter_map(move |result| match result {
         Ok(node) => f(node).transpose(),
         Err(e) => Some(Err(e)),
     })
 }
 
 impl<'on_disk> super::dispatch::DirstateMapMethods for DirstateMap<'on_disk> {
     fn clear(&mut self) {
         self.root = Default::default();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn set_v1(&mut self, filename: &HgPath, entry: DirstateEntry) {
         let node =
             self.get_or_insert(&filename).expect("no parse error in v1");
         node.data = NodeData::Entry(entry);
         node.children = ChildNodes::default();
         node.copy_source = None;
         node.descendants_with_entry_count = 0;
         node.tracked_descendants_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
         added: bool,
         merged: bool,
         from_p2: bool,
         possibly_dirty: bool,
     ) -> Result<(), DirstateError> {
         let state;
         let size;
         let mtime;
         if added {
             assert!(!possibly_dirty);
             assert!(!from_p2);
             state = EntryState::Added;
             size = SIZE_NON_NORMAL;
             mtime = MTIME_UNSET;
         } else if merged {
             assert!(!possibly_dirty);
             assert!(!from_p2);
             state = EntryState::Merged;
             size = SIZE_FROM_OTHER_PARENT;
             mtime = MTIME_UNSET;
         } else if from_p2 {
             assert!(!possibly_dirty);
             state = EntryState::Normal;
             size = SIZE_FROM_OTHER_PARENT;
             mtime = MTIME_UNSET;
         } else if possibly_dirty {
             state = EntryState::Normal;
             size = SIZE_NON_NORMAL;
             mtime = MTIME_UNSET;
         } else {
             state = EntryState::Normal;
             size = entry.size() & V1_RANGEMASK;
             mtime = entry.mtime() & V1_RANGEMASK;
         }
         let mode = entry.mode();
         let entry = DirstateEntry::from_v1_data(state, mode, size, mtime);
 
-        let old_state = match self.get(filename)? {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
+        let old_state = self.get(filename)?.map(|e| e.state());
 
         Ok(self.add_or_remove_file(filename, old_state, entry)?)
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         in_merge: bool,
     ) -> Result<(), DirstateError> {
         let old_entry_opt = self.get(filename)?;
-        let old_state = match old_entry_opt {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
+        let old_state = old_entry_opt.map(|e| e.state());
         let mut size = 0;
         if in_merge {
             // XXX we should not be able to have 'm' state and 'FROM_P2' if not
             // during a merge. So I (marmoute) am not sure we need the
             // conditionnal at all. Adding double checking this with assert
             // would be nice.
             if let Some(old_entry) = old_entry_opt {
                 // backup the previous state
                 if old_entry.state() == EntryState::Merged {
                     size = SIZE_NON_NORMAL;
                 } else if old_entry.state() == EntryState::Normal
                     && old_entry.size() == SIZE_FROM_OTHER_PARENT
                 {
                     // other parent
                     size = SIZE_FROM_OTHER_PARENT;
                 }
             }
         }
         if size == 0 {
             self.copy_map_remove(filename)?;
         }
         let entry = DirstateEntry::new_removed(size);
         Ok(self.add_or_remove_file(filename, old_state, entry)?)
     }
 
     fn drop_file(&mut self, filename: &HgPath) -> Result<bool, DirstateError> {
-        let old_state = match self.get(filename)? {
-            Some(e) => e.state(),
-            None => EntryState::Unknown,
-        };
+        let was_tracked = self
+            .get(filename)?
+            .map_or(false, |e| e.state().is_tracked());
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
             had_copy_source: bool,
         }
 
         /// If this returns `Ok(Some((dropped, removed)))`, then
         ///
         /// * `dropped` is about the leaf node that was at `filename`
         /// * `removed` is whether this particular level of recursion just
         ///   removed a node in `nodes`.
         fn recur<'on_disk>(
             on_disk: &'on_disk [u8],
             unreachable_bytes: &mut u32,
             nodes: &mut ChildNodes<'on_disk>,
             path: &HgPath,
         ) -> Result<Option<(Dropped, bool)>, DirstateV2ParseError> {
             let (first_path_component, rest_of_path) =
                 path.split_first_component();
             let nodes = nodes.make_mut(on_disk, unreachable_bytes)?;
             let node = if let Some(node) = nodes.get_mut(first_path_component)
             {
                 node
             } else {
                 return Ok(None);
             };
             let dropped;
             if let Some(rest) = rest_of_path {
                 if let Some((d, removed)) = recur(
                     on_disk,
                     unreachable_bytes,
                     &mut node.children,
                     rest,
                 )? {
                     dropped = d;
                     if dropped.had_entry {
                         node.descendants_with_entry_count -= 1;
                     }
                     if dropped.was_tracked {
                         node.tracked_descendants_count -= 1;
                     }
 
                     // Directory caches must be invalidated when removing a
                     // child node
                     if removed {
                         if let NodeData::CachedDirectory { .. } = &node.data {
                             node.data = NodeData::None
                         }
                     }
                 } else {
                     return Ok(None);
                 }
             } else {
                 let had_entry = node.data.has_entry();
                 if had_entry {
                     node.data = NodeData::None
                 }
                 if let Some(source) = &node.copy_source {
                     DirstateMap::count_dropped_path(unreachable_bytes, source)
                 }
                 dropped = Dropped {
                     was_tracked: node
                         .data
                         .as_entry()
                         .map_or(false, |entry| entry.state().is_tracked()),
                     had_entry,
                     had_copy_source: node.copy_source.take().is_some(),
                 };
             }
             // After recursion, for both leaf (rest_of_path is None) nodes and
             // parent nodes, remove a node if it just became empty.
             let remove = !node.data.has_entry()
                 && node.copy_source.is_none()
                 && node.children.is_empty();
             if remove {
                 let (key, _) =
                     nodes.remove_entry(first_path_component).unwrap();
                 DirstateMap::count_dropped_path(
                     unreachable_bytes,
                     key.full_path(),
                 )
             }
             Ok(Some((dropped, remove)))
         }
 
         if let Some((dropped, _removed)) = recur(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             filename,
         )? {
             if dropped.had_entry {
                 self.nodes_with_entry_count -= 1
             }
             if dropped.had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
             Ok(dropped.had_entry)
         } else {
-            debug_assert!(!old_state.is_tracked());
+            debug_assert!(!was_tracked);
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(
         &mut self,
         filenames: Vec<HgPathBuf>,
         now: i32,
     ) -> Result<(), DirstateV2ParseError> {
         for filename in filenames {
             if let Some(node) = Self::get_node_mut(
                 self.on_disk,
                 &mut self.unreachable_bytes,
                 &mut self.root,
                 &filename,
             )? {
                 if let NodeData::Entry(entry) = &mut node.data {
                     entry.clear_ambiguous_mtime(now);
                 }
             }
         }
         Ok(())
     }
 
     fn non_normal_entries_contains(
         &mut self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.entry()?.map_or(false, |entry| entry.is_non_normal())
         } else {
             false
         })
     }
 
     fn non_normal_entries_remove(&mut self, key: &HgPath) -> bool {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date.
         if let Ok(Some(v)) = self.get(key) {
             return v.is_non_normal();
         }
         false
     }
 
     fn non_normal_entries_add(&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 = Result<&HgPath, DirstateV2ParseError>> + '_>
     {
         Box::new(self.filter_full_paths(|entry| {
             entry.is_non_normal() || entry.is_from_other_parent()
         }))
     }
 
     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 = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<
         dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         Box::new(self.filter_full_paths(|entry| entry.is_non_normal()))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<
         dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         Box::new(self.filter_full_paths(|entry| entry.is_from_other_parent()))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         if let Some(node) = self.get_node(directory)? {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             let state = node.state()?;
             Ok(state.is_none() && node.tracked_descendants_count() > 0)
         } else {
             Ok(false)
         }
     }
 
     fn has_dir(&mut self, directory: &HgPath) -> Result<bool, DirstateError> {
         if let Some(node) = self.get_node(directory)? {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             let state = node.state()?;
             Ok(state.is_none() && node.descendants_with_entry_count() > 0)
         } else {
             Ok(false)
         }
     }
 
     #[timed]
     fn pack_v1(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         let now: i32 = now.0.try_into().expect("time overflow");
         let mut ambiguous_mtimes = Vec::new();
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 size += packed_entry_size(
                     node.full_path(self.on_disk)?,
                     node.copy_source(self.on_disk)?,
                 );
                 if entry.mtime_is_ambiguous(now) {
                     ambiguous_mtimes.push(
                         node.full_path_borrowed(self.on_disk)?
                             .detach_from_tree(),
                     )
                 }
             }
         }
         self.clear_known_ambiguous_mtimes(&ambiguous_mtimes)?;
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 pack_entry(
                     node.full_path(self.on_disk)?,
                     &entry,
                     node.copy_source(self.on_disk)?,
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     /// Returns new data and metadata together with whether that data should be
     /// appended to the existing data file whose content is at
     /// `self.on_disk` (true), instead of written to a new data file
     /// (false).
     #[timed]
     fn pack_v2(
         &mut self,
         now: Timestamp,
         can_append: bool,
     ) -> Result<(Vec<u8>, Vec<u8>, bool), DirstateError> {
         // TODO: how do we want to handle this in 2038?
         let now: i32 = now.0.try_into().expect("time overflow");
         let mut paths = Vec::new();
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 if entry.mtime_is_ambiguous(now) {
                     paths.push(
                         node.full_path_borrowed(self.on_disk)?
                             .detach_from_tree(),
                     )
                 }
             }
         }
         // Borrow of `self` ends here since we collect cloned paths
 
         self.clear_known_ambiguous_mtimes(&paths)?;
 
         on_disk::write(self, can_append)
     }
 
     fn status<'a>(
         &'a mut self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
     {
         super::status::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count as usize
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             Ok(if let Some(source) = node.copy_source(self.on_disk)? {
                 Some((node.full_path(self.on_disk)?, source))
             } else {
                 None
             })
         }))
     }
 
     fn copy_map_contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.has_copy_source()
         } else {
             false
         })
     }
 
     fn copy_map_get(
         &self,
         key: &HgPath,
     ) -> Result<Option<&HgPath>, DirstateV2ParseError> {
         if let Some(node) = self.get_node(key)? {
             if let Some(source) = node.copy_source(self.on_disk)? {
                 return Ok(Some(source));
             }
         }
         Ok(None)
     }
 
     fn copy_map_remove(
         &mut self,
         key: &HgPath,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let count = &mut self.nodes_with_copy_source_count;
         let unreachable_bytes = &mut self.unreachable_bytes;
         Ok(Self::get_node_mut(
             self.on_disk,
             unreachable_bytes,
             &mut self.root,
             key,
         )?
         .and_then(|node| {
             if let Some(source) = &node.copy_source {
                 *count -= 1;
                 Self::count_dropped_path(unreachable_bytes, source);
             }
             node.copy_source.take().map(Cow::into_owned)
         }))
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             &key,
             WithBasename::to_cow_owned,
             |_ancestor| {},
         )?;
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count as usize
     }
 
     fn contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(self.get(key)?.is_some())
     }
 
     fn get(
         &self,
         key: &HgPath,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.entry()?
         } else {
             None
         })
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             Ok(if let Some(entry) = node.entry()? {
                 Some((node.full_path(self.on_disk)?, entry))
             } else {
                 None
             })
         }))
     }
 
     fn iter_tracked_dirs(
         &mut self,
     ) -> Result<
         Box<
             dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>>
                 + Send
                 + '_,
         >,
         DirstateError,
     > {
         let on_disk = self.on_disk;
         Ok(Box::new(filter_map_results(
             self.iter_nodes(),
             move |node| {
                 Ok(if node.tracked_descendants_count() > 0 {
                     Some(node.full_path(on_disk)?)
                 } else {
                     None
                 })
             },
         )))
     }
 
     fn debug_iter(
         &self,
         all: bool,
     ) -> Box<
         dyn Iterator<
                 Item = Result<
                     (&HgPath, (u8, i32, i32, i32)),
                     DirstateV2ParseError,
                 >,
             > + Send
             + '_,
     > {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             let debug_tuple = if let Some(entry) = node.entry()? {
                 entry.debug_tuple()
             } else if !all {
                 return Ok(None);
             } else if let Some(mtime) = node.cached_directory_mtime() {
                 (b' ', 0, -1, mtime.seconds() as i32)
             } else {
                 (b' ', 0, -1, -1)
             };
             Ok(Some((node.full_path(self.on_disk)?, debug_tuple)))
         }))
     }
 }

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

@@ -1,756 +1,753 b''
 use crate::dirstate::status::IgnoreFnType;
 use crate::dirstate_tree::dirstate_map::BorrowedPath;
 use crate::dirstate_tree::dirstate_map::ChildNodesRef;
 use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::dirstate_map::NodeData;
 use crate::dirstate_tree::dirstate_map::NodeRef;
 use crate::dirstate_tree::on_disk::DirstateV2ParseError;
 use crate::dirstate_tree::on_disk::Timestamp;
 use crate::matchers::get_ignore_function;
 use crate::matchers::Matcher;
 use crate::utils::files::get_bytes_from_os_string;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::BadMatch;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::HgPathBuf;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
 use micro_timer::timed;
 use rayon::prelude::*;
 use sha1::{Digest, Sha1};
 use std::borrow::Cow;
 use std::io;
 use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Mutex;
 use std::time::SystemTime;
 
 /// Returns the status of the working directory compared to its parent
 /// changeset.
 ///
 /// This algorithm is based on traversing the filesystem tree (`fs` in function
 /// and variable names) and dirstate tree at the same time. The core of this
 /// traversal is the recursive `traverse_fs_directory_and_dirstate` function
 /// and its use of `itertools::merge_join_by`. When reaching a path that only
 /// exists in one of the two trees, depending on information requested by
 /// `options` we may need to traverse the remaining subtree.
 #[timed]
 pub fn status<'tree, 'on_disk: 'tree>(
     dmap: &'tree mut DirstateMap<'on_disk>,
     matcher: &(dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> Result<(DirstateStatus<'on_disk>, Vec<PatternFileWarning>), StatusError> {
     let (ignore_fn, warnings, patterns_changed): (IgnoreFnType, _, _) =
         if options.list_ignored || options.list_unknown {
             let mut hasher = Sha1::new();
             let (ignore_fn, warnings) = get_ignore_function(
                 ignore_files,
                 &root_dir,
                 &mut |pattern_bytes| hasher.update(pattern_bytes),
             )?;
             let new_hash = *hasher.finalize().as_ref();
             let changed = new_hash != dmap.ignore_patterns_hash;
             dmap.ignore_patterns_hash = new_hash;
             (ignore_fn, warnings, Some(changed))
         } else {
             (Box::new(|&_| true), vec![], None)
         };
 
     let common = StatusCommon {
         dmap,
         options,
         matcher,
         ignore_fn,
         outcome: Default::default(),
         ignore_patterns_have_changed: patterns_changed,
         new_cachable_directories: Default::default(),
         outated_cached_directories: Default::default(),
         filesystem_time_at_status_start: filesystem_now(&root_dir).ok(),
     };
     let is_at_repo_root = true;
     let hg_path = &BorrowedPath::OnDisk(HgPath::new(""));
     let has_ignored_ancestor = false;
     let root_cached_mtime = None;
     let root_dir_metadata = None;
     // If the path we have for the repository root is a symlink, do follow it.
     // (As opposed to symlinks within the working directory which are not
     // followed, using `std::fs::symlink_metadata`.)
     common.traverse_fs_directory_and_dirstate(
         has_ignored_ancestor,
         dmap.root.as_ref(),
         hg_path,
         &root_dir,
         root_dir_metadata,
         root_cached_mtime,
         is_at_repo_root,
     )?;
     let mut outcome = common.outcome.into_inner().unwrap();
     let new_cachable = common.new_cachable_directories.into_inner().unwrap();
     let outdated = common.outated_cached_directories.into_inner().unwrap();
 
     outcome.dirty = common.ignore_patterns_have_changed == Some(true)
         || !outdated.is_empty()
         || !new_cachable.is_empty();
 
     // Remove outdated mtimes before adding new mtimes, in case a given
     // directory is both
     for path in &outdated {
         let node = dmap.get_or_insert(path)?;
         if let NodeData::CachedDirectory { .. } = &node.data {
             node.data = NodeData::None
         }
     }
     for (path, mtime) in &new_cachable {
         let node = dmap.get_or_insert(path)?;
         match &node.data {
             NodeData::Entry(_) => {} // Don’t overwrite an entry
             NodeData::CachedDirectory { .. } | NodeData::None => {
                 node.data = NodeData::CachedDirectory { mtime: *mtime }
             }
         }
     }
 
     Ok((outcome, warnings))
 }
 
 /// Bag of random things needed by various parts of the algorithm. Reduces the
 /// number of parameters passed to functions.
 struct StatusCommon<'a, 'tree, 'on_disk: 'tree> {
     dmap: &'tree DirstateMap<'on_disk>,
     options: StatusOptions,
     matcher: &'a (dyn Matcher + Sync),
     ignore_fn: IgnoreFnType<'a>,
     outcome: Mutex<DirstateStatus<'on_disk>>,
     new_cachable_directories: Mutex<Vec<(Cow<'on_disk, HgPath>, Timestamp)>>,
     outated_cached_directories: Mutex<Vec<Cow<'on_disk, HgPath>>>,
 
     /// Whether ignore files like `.hgignore` have changed since the previous
     /// time a `status()` call wrote their hash to the dirstate. `None` means
     /// we don’t know as this run doesn’t list either ignored or uknown files
     /// and therefore isn’t reading `.hgignore`.
     ignore_patterns_have_changed: Option<bool>,
 
     /// The current time at the start of the `status()` algorithm, as measured
     /// and possibly truncated by the filesystem.
     filesystem_time_at_status_start: Option<SystemTime>,
 }
 
 impl<'a, 'tree, 'on_disk> StatusCommon<'a, 'tree, 'on_disk> {
     fn read_dir(
         &self,
         hg_path: &HgPath,
         fs_path: &Path,
         is_at_repo_root: bool,
     ) -> Result<Vec<DirEntry>, ()> {
         DirEntry::read_dir(fs_path, is_at_repo_root)
             .map_err(|error| self.io_error(error, hg_path))
     }
 
     fn io_error(&self, error: std::io::Error, hg_path: &HgPath) {
         let errno = error.raw_os_error().expect("expected real OS error");
         self.outcome
             .lock()
             .unwrap()
             .bad
             .push((hg_path.to_owned().into(), BadMatch::OsError(errno)))
     }
 
     fn check_for_outdated_directory_cache(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if self.ignore_patterns_have_changed == Some(true)
             && dirstate_node.cached_directory_mtime().is_some()
         {
             self.outated_cached_directories.lock().unwrap().push(
                 dirstate_node
                     .full_path_borrowed(self.dmap.on_disk)?
                     .detach_from_tree(),
             )
         }
         Ok(())
     }
 
     /// If this returns true, we can get accurate results by only using
     /// `symlink_metadata` for child nodes that exist in the dirstate and don’t
     /// need to call `read_dir`.
     fn can_skip_fs_readdir(
         &self,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<&Timestamp>,
     ) -> bool {
         if !self.options.list_unknown && !self.options.list_ignored {
             // All states that we care about listing have corresponding
             // dirstate entries.
             // This happens for example with `hg status -mard`.
             return true;
         }
         if !self.options.list_ignored
             && self.ignore_patterns_have_changed == Some(false)
         {
             if let Some(cached_mtime) = cached_directory_mtime {
                 // The dirstate contains a cached mtime for this directory, set
                 // by a previous run of the `status` algorithm which found this
                 // directory eligible for `read_dir` caching.
                 if let Some(meta) = directory_metadata {
                     if let Ok(current_mtime) = meta.modified() {
                         if current_mtime == cached_mtime.into() {
                             // The mtime of that directory has not changed
                             // since then, which means that the results of
                             // `read_dir` should also be unchanged.
                             return true;
                         }
                     }
                 }
             }
         }
         false
     }
 
     /// Returns whether all child entries of the filesystem directory have a
     /// corresponding dirstate node or are ignored.
     fn traverse_fs_directory_and_dirstate(
         &self,
         has_ignored_ancestor: bool,
         dirstate_nodes: ChildNodesRef<'tree, 'on_disk>,
         directory_hg_path: &BorrowedPath<'tree, 'on_disk>,
         directory_fs_path: &Path,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<&Timestamp>,
         is_at_repo_root: bool,
     ) -> Result<bool, DirstateV2ParseError> {
         if self.can_skip_fs_readdir(directory_metadata, cached_directory_mtime)
         {
             dirstate_nodes
                 .par_iter()
                 .map(|dirstate_node| {
                     let fs_path = directory_fs_path.join(get_path_from_bytes(
                         dirstate_node.base_name(self.dmap.on_disk)?.as_bytes(),
                     ));
                     match std::fs::symlink_metadata(&fs_path) {
                         Ok(fs_metadata) => self.traverse_fs_and_dirstate(
                             &fs_path,
                             &fs_metadata,
                             dirstate_node,
                             has_ignored_ancestor,
                         ),
                         Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
                             self.traverse_dirstate_only(dirstate_node)
                         }
                         Err(error) => {
                             let hg_path =
                                 dirstate_node.full_path(self.dmap.on_disk)?;
                             Ok(self.io_error(error, hg_path))
                         }
                     }
                 })
                 .collect::<Result<_, _>>()?;
 
             // We don’t know, so conservatively say this isn’t the case
             let children_all_have_dirstate_node_or_are_ignored = false;
 
             return Ok(children_all_have_dirstate_node_or_are_ignored);
         }
 
         let mut fs_entries = if let Ok(entries) = self.read_dir(
             directory_hg_path,
             directory_fs_path,
             is_at_repo_root,
         ) {
             entries
         } else {
             // Treat an unreadable directory (typically because of insufficient
             // permissions) like an empty directory. `self.read_dir` has
             // already called `self.io_error` so a warning will be emitted.
             Vec::new()
         };
 
         // `merge_join_by` requires both its input iterators to be sorted:
 
         let dirstate_nodes = dirstate_nodes.sorted();
         // `sort_unstable_by_key` doesn’t allow keys borrowing from the value:
         // https://github.com/rust-lang/rust/issues/34162
         fs_entries.sort_unstable_by(|e1, e2| e1.base_name.cmp(&e2.base_name));
 
         // Propagate here any error that would happen inside the comparison
         // callback below
         for dirstate_node in &dirstate_nodes {
             dirstate_node.base_name(self.dmap.on_disk)?;
         }
         itertools::merge_join_by(
             dirstate_nodes,
             &fs_entries,
             |dirstate_node, fs_entry| {
                 // This `unwrap` never panics because we already propagated
                 // those errors above
                 dirstate_node
                     .base_name(self.dmap.on_disk)
                     .unwrap()
                     .cmp(&fs_entry.base_name)
             },
         )
         .par_bridge()
         .map(|pair| {
             use itertools::EitherOrBoth::*;
             let has_dirstate_node_or_is_ignored;
             match pair {
                 Both(dirstate_node, fs_entry) => {
                     self.traverse_fs_and_dirstate(
                         &fs_entry.full_path,
                         &fs_entry.metadata,
                         dirstate_node,
                         has_ignored_ancestor,
                     )?;
                     has_dirstate_node_or_is_ignored = true
                 }
                 Left(dirstate_node) => {
                     self.traverse_dirstate_only(dirstate_node)?;
                     has_dirstate_node_or_is_ignored = true;
                 }
                 Right(fs_entry) => {
                     has_dirstate_node_or_is_ignored = self.traverse_fs_only(
                         has_ignored_ancestor,
                         directory_hg_path,
                         fs_entry,
                     )
                 }
             }
             Ok(has_dirstate_node_or_is_ignored)
         })
         .try_reduce(|| true, |a, b| Ok(a && b))
     }
 
     fn traverse_fs_and_dirstate(
         &self,
         fs_path: &Path,
         fs_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
         has_ignored_ancestor: bool,
     ) -> Result<(), DirstateV2ParseError> {
         self.check_for_outdated_directory_cache(&dirstate_node)?;
         let hg_path = &dirstate_node.full_path_borrowed(self.dmap.on_disk)?;
         let file_type = fs_metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if !file_or_symlink {
             // If we previously had a file here, it was removed (with
             // `hg rm` or similar) or deleted before it could be
             // replaced by a directory or something else.
             self.mark_removed_or_deleted_if_file(
                 &hg_path,
                 dirstate_node.state()?,
             );
         }
         if file_type.is_dir() {
             if self.options.collect_traversed_dirs {
                 self.outcome
                     .lock()
                     .unwrap()
                     .traversed
                     .push(hg_path.detach_from_tree())
             }
             let is_ignored = has_ignored_ancestor || (self.ignore_fn)(hg_path);
             let is_at_repo_root = false;
             let children_all_have_dirstate_node_or_are_ignored = self
                 .traverse_fs_directory_and_dirstate(
                     is_ignored,
                     dirstate_node.children(self.dmap.on_disk)?,
                     hg_path,
                     fs_path,
                     Some(fs_metadata),
                     dirstate_node.cached_directory_mtime(),
                     is_at_repo_root,
                 )?;
             self.maybe_save_directory_mtime(
                 children_all_have_dirstate_node_or_are_ignored,
                 fs_metadata,
                 dirstate_node,
             )?
         } else {
             if file_or_symlink && self.matcher.matches(hg_path) {
                 if let Some(state) = dirstate_node.state()? {
                     match state {
                         EntryState::Added => self
                             .outcome
                             .lock()
                             .unwrap()
                             .added
                             .push(hg_path.detach_from_tree()),
                         EntryState::Removed => self
                             .outcome
                             .lock()
                             .unwrap()
                             .removed
                             .push(hg_path.detach_from_tree()),
                         EntryState::Merged => self
                             .outcome
                             .lock()
                             .unwrap()
                             .modified
                             .push(hg_path.detach_from_tree()),
                         EntryState::Normal => self
                             .handle_normal_file(&dirstate_node, fs_metadata)?,
-                        // This variant is not used in DirstateMap
-                        // nodes
-                        EntryState::Unknown => unreachable!(),
                     }
                 } else {
                     // `node.entry.is_none()` indicates a "directory"
                     // node, but the filesystem has a file
                     self.mark_unknown_or_ignored(
                         has_ignored_ancestor,
                         hg_path,
                     );
                 }
             }
 
             for child_node in dirstate_node.children(self.dmap.on_disk)?.iter()
             {
                 self.traverse_dirstate_only(child_node)?
             }
         }
         Ok(())
     }
 
     fn maybe_save_directory_mtime(
         &self,
         children_all_have_dirstate_node_or_are_ignored: bool,
         directory_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if children_all_have_dirstate_node_or_are_ignored {
             // All filesystem directory entries from `read_dir` have a
             // corresponding node in the dirstate, so we can reconstitute the
             // names of those entries without calling `read_dir` again.
             if let (Some(status_start), Ok(directory_mtime)) = (
                 &self.filesystem_time_at_status_start,
                 directory_metadata.modified(),
             ) {
                 // Although the Rust standard library’s `SystemTime` type
                 // has nanosecond precision, the times reported for a
                 // directory’s (or file’s) modified time may have lower
                 // resolution based on the filesystem (for example ext3
                 // only stores integer seconds), kernel (see
                 // https://stackoverflow.com/a/14393315/1162888), etc.
                 if &directory_mtime >= status_start {
                     // The directory was modified too recently, don’t cache its
                     // `read_dir` results.
                     //
                     // A timeline like this is possible:
                     //
                     // 1. A change to this directory (direct child was
                     //    added or removed) cause its mtime to be set
                     //    (possibly truncated) to `directory_mtime`
                     // 2. This `status` algorithm calls `read_dir`
                     // 3. An other change is made to the same directory is
                     //    made so that calling `read_dir` agin would give
                     //    different results, but soon enough after 1. that
                     //    the mtime stays the same
                     //
                     // On a system where the time resolution poor, this
                     // scenario is not unlikely if all three steps are caused
                     // by the same script.
                 } else {
                     // We’ve observed (through `status_start`) that time has
                     // “progressed” since `directory_mtime`, so any further
                     // change to this directory is extremely likely to cause a
                     // different mtime.
                     //
                     // Having the same mtime again is not entirely impossible
                     // since the system clock is not monotonous. It could jump
                     // backward to some point before `directory_mtime`, then a
                     // directory change could potentially happen during exactly
                     // the wrong tick.
                     //
                     // We deem this scenario (unlike the previous one) to be
                     // unlikely enough in practice.
                     let timestamp = directory_mtime.into();
                     let cached = dirstate_node.cached_directory_mtime();
                     if cached != Some(&timestamp) {
                         let hg_path = dirstate_node
                             .full_path_borrowed(self.dmap.on_disk)?
                             .detach_from_tree();
                         self.new_cachable_directories
                             .lock()
                             .unwrap()
                             .push((hg_path, timestamp))
                     }
                 }
             }
         }
         Ok(())
     }
 
     /// A file with `EntryState::Normal` in the dirstate was found in the
     /// filesystem
     fn handle_normal_file(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
         fs_metadata: &std::fs::Metadata,
     ) -> Result<(), DirstateV2ParseError> {
         // Keep the low 31 bits
         fn truncate_u64(value: u64) -> i32 {
             (value & 0x7FFF_FFFF) as i32
         }
         fn truncate_i64(value: i64) -> i32 {
             (value & 0x7FFF_FFFF) as i32
         }
 
         let entry = dirstate_node
             .entry()?
             .expect("handle_normal_file called with entry-less node");
         let hg_path = &dirstate_node.full_path_borrowed(self.dmap.on_disk)?;
         let mode_changed =
             || self.options.check_exec && entry.mode_changed(fs_metadata);
         let size = entry.size();
         let size_changed = size != truncate_u64(fs_metadata.len());
         if size >= 0 && size_changed && fs_metadata.file_type().is_symlink() {
             // issue6456: Size returned may be longer due to encryption
             // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
             self.outcome
                 .lock()
                 .unwrap()
                 .unsure
                 .push(hg_path.detach_from_tree())
         } else if dirstate_node.has_copy_source()
             || entry.is_from_other_parent()
             || (size >= 0 && (size_changed || mode_changed()))
         {
             self.outcome
                 .lock()
                 .unwrap()
                 .modified
                 .push(hg_path.detach_from_tree())
         } else {
             let mtime = mtime_seconds(fs_metadata);
             if truncate_i64(mtime) != entry.mtime()
                 || mtime == self.options.last_normal_time
             {
                 self.outcome
                     .lock()
                     .unwrap()
                     .unsure
                     .push(hg_path.detach_from_tree())
             } else if self.options.list_clean {
                 self.outcome
                     .lock()
                     .unwrap()
                     .clean
                     .push(hg_path.detach_from_tree())
             }
         }
         Ok(())
     }
 
     /// A node in the dirstate tree has no corresponding filesystem entry
     fn traverse_dirstate_only(
         &self,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         self.check_for_outdated_directory_cache(&dirstate_node)?;
         self.mark_removed_or_deleted_if_file(
             &dirstate_node.full_path_borrowed(self.dmap.on_disk)?,
             dirstate_node.state()?,
         );
         dirstate_node
             .children(self.dmap.on_disk)?
             .par_iter()
             .map(|child_node| self.traverse_dirstate_only(child_node))
             .collect()
     }
 
     /// A node in the dirstate tree has no corresponding *file* on the
     /// filesystem
     ///
     /// Does nothing on a "directory" node
     fn mark_removed_or_deleted_if_file(
         &self,
         hg_path: &BorrowedPath<'tree, 'on_disk>,
         dirstate_node_state: Option<EntryState>,
     ) {
         if let Some(state) = dirstate_node_state {
             if self.matcher.matches(hg_path) {
                 if let EntryState::Removed = state {
                     self.outcome
                         .lock()
                         .unwrap()
                         .removed
                         .push(hg_path.detach_from_tree())
                 } else {
                     self.outcome
                         .lock()
                         .unwrap()
                         .deleted
                         .push(hg_path.detach_from_tree())
                 }
             }
         }
     }
 
     /// Something in the filesystem has no corresponding dirstate node
     ///
     /// Returns whether that path is ignored
     fn traverse_fs_only(
         &self,
         has_ignored_ancestor: bool,
         directory_hg_path: &HgPath,
         fs_entry: &DirEntry,
     ) -> bool {
         let hg_path = directory_hg_path.join(&fs_entry.base_name);
         let file_type = fs_entry.metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if file_type.is_dir() {
             let is_ignored =
                 has_ignored_ancestor || (self.ignore_fn)(&hg_path);
             let traverse_children = if is_ignored {
                 // Descendants of an ignored directory are all ignored
                 self.options.list_ignored
             } else {
                 // Descendants of an unknown directory may be either unknown or
                 // ignored
                 self.options.list_unknown || self.options.list_ignored
             };
             if traverse_children {
                 let is_at_repo_root = false;
                 if let Ok(children_fs_entries) = self.read_dir(
                     &hg_path,
                     &fs_entry.full_path,
                     is_at_repo_root,
                 ) {
                     children_fs_entries.par_iter().for_each(|child_fs_entry| {
                         self.traverse_fs_only(
                             is_ignored,
                             &hg_path,
                             child_fs_entry,
                         );
                     })
                 }
             }
             if self.options.collect_traversed_dirs {
                 self.outcome.lock().unwrap().traversed.push(hg_path.into())
             }
             is_ignored
         } else {
             if file_or_symlink {
                 if self.matcher.matches(&hg_path) {
                     self.mark_unknown_or_ignored(
                         has_ignored_ancestor,
                         &BorrowedPath::InMemory(&hg_path),
                     )
                 } else {
                     // We haven’t computed whether this path is ignored. It
                     // might not be, and a future run of status might have a
                     // different matcher that matches it. So treat it as not
                     // ignored. That is, inhibit readdir caching of the parent
                     // directory.
                     false
                 }
             } else {
                 // This is neither a directory, a plain file, or a symlink.
                 // Treat it like an ignored file.
                 true
             }
         }
     }
 
     /// Returns whether that path is ignored
     fn mark_unknown_or_ignored(
         &self,
         has_ignored_ancestor: bool,
         hg_path: &BorrowedPath<'_, 'on_disk>,
     ) -> bool {
         let is_ignored = has_ignored_ancestor || (self.ignore_fn)(&hg_path);
         if is_ignored {
             if self.options.list_ignored {
                 self.outcome
                     .lock()
                     .unwrap()
                     .ignored
                     .push(hg_path.detach_from_tree())
             }
         } else {
             if self.options.list_unknown {
                 self.outcome
                     .lock()
                     .unwrap()
                     .unknown
                     .push(hg_path.detach_from_tree())
             }
         }
         is_ignored
     }
 }
 
 #[cfg(unix)] // TODO
 fn mtime_seconds(metadata: &std::fs::Metadata) -> i64 {
     // Going through `Metadata::modified()` would be portable, but would take
     // care to construct a `SystemTime` value with sub-second precision just
     // for us to throw that away here.
     use std::os::unix::fs::MetadataExt;
     metadata.mtime()
 }
 
 struct DirEntry {
     base_name: HgPathBuf,
     full_path: PathBuf,
     metadata: std::fs::Metadata,
 }
 
 impl DirEntry {
     /// Returns **unsorted** entries in the given directory, with name and
     /// metadata.
     ///
     /// If a `.hg` sub-directory is encountered:
     ///
     /// * At the repository root, ignore that sub-directory
     /// * Elsewhere, we’re listing the content of a sub-repo. Return an empty
     ///   list instead.
     fn read_dir(path: &Path, is_at_repo_root: bool) -> io::Result<Vec<Self>> {
         let mut results = Vec::new();
         for entry in path.read_dir()? {
             let entry = entry?;
             let metadata = entry.metadata()?;
             let name = get_bytes_from_os_string(entry.file_name());
             // FIXME don't do this when cached
             if name == b".hg" {
                 if is_at_repo_root {
                     // Skip the repo’s own .hg (might be a symlink)
                     continue;
                 } else if metadata.is_dir() {
                     // A .hg sub-directory at another location means a subrepo,
                     // skip it entirely.
                     return Ok(Vec::new());
                 }
             }
             results.push(DirEntry {
                 base_name: name.into(),
                 full_path: entry.path(),
                 metadata,
             })
         }
         Ok(results)
     }
 }
 
 /// Return the `mtime` of a temporary file newly-created in the `.hg` directory
 /// of the give repository.
 ///
 /// This is similar to `SystemTime::now()`, with the result truncated to the
 /// same time resolution as other files’ modification times. Using `.hg`
 /// instead of the system’s default temporary directory (such as `/tmp`) makes
 /// it more likely the temporary file is in the same disk partition as contents
 /// of the working directory, which can matter since different filesystems may
 /// store timestamps with different resolutions.
 ///
 /// This may fail, typically if we lack write permissions. In that case we
 /// should continue the `status()` algoritm anyway and consider the current
 /// date/time to be unknown.
 fn filesystem_now(repo_root: &Path) -> Result<SystemTime, io::Error> {
     tempfile::tempfile_in(repo_root.join(".hg"))?
         .metadata()?
         .modified()
 }