rust-status: refactor options into a `StatusOptions` struct

Differential Revision: https://phab.mercurial-scm.org/D8086

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

@@ -1,335 +1,321 b''
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
 use crate::{
     dirstate::SIZE_FROM_OTHER_PARENT,
     matchers::Matcher,
     utils::{
         files::HgMetadata,
         hg_path::{
             hg_path_to_path_buf, os_string_to_hg_path_buf, HgPath, HgPathBuf,
         },
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState,
 };
 use rayon::prelude::*;
 use std::collections::HashSet;
 use std::fs::{read_dir, DirEntry};
 use std::path::Path;
 
 /// Marker enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
 }
 
 type IoResult<T> = std::io::Result<T>;
 
 /// Dates and times that are outside the 31-bit signed range are compared
 /// modulo 2^31. This should prevent hg from behaving badly with very large
 /// files or corrupt dates while still having a high probability of detecting
 /// changes. (issue2608)
 /// TODO I haven't found a way of having `b` be `Into<i32>`, since `From<u64>`
 /// is not defined for `i32`, and there is no `As` trait. This forces the
 /// caller to cast `b` as `i32`.
 fn mod_compare(a: i32, b: i32) -> bool {
     a & i32::max_value() != b & i32::max_value()
 }
 
 /// Return a sorted list containing information about the entries
 /// in the directory.
 ///
 /// * `skip_dot_hg` - Return an empty vec if `path` contains a `.hg` directory
 fn list_directory(
     path: impl AsRef<Path>,
     skip_dot_hg: bool,
 ) -> std::io::Result<Vec<(HgPathBuf, DirEntry)>> {
     let mut results = vec![];
     let entries = read_dir(path.as_ref())?;
 
     for entry in entries {
         let entry = entry?;
         let filename = os_string_to_hg_path_buf(entry.file_name())?;
         let file_type = entry.file_type()?;
         if skip_dot_hg && filename.as_bytes() == b".hg" && file_type.is_dir() {
             return Ok(vec![]);
         } else {
             results.push((HgPathBuf::from(filename), entry))
         }
     }
 
     results.sort_unstable_by_key(|e| e.0.clone());
     Ok(results)
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
-    check_exec: bool,
-    list_clean: bool,
-    last_normal_time: i64,
+    options: StatusOptions,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
-                (mode ^ st_mode as i32) & 0o100 != 0o000 && check_exec;
+                (mode ^ st_mode as i32) & 0o100 != 0o000 && options.check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
             let other_parent = size == SIZE_FROM_OTHER_PARENT;
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
                 Dispatch::Modified
             } else if mod_compare(mtime, st_mtime as i32) {
                 Dispatch::Unsure
-            } else if st_mtime == last_normal_time {
+            } else if st_mtime == options.last_normal_time {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
-            } else if list_clean {
+            } else if options.list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::Unknown
             }
         }
         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,
     }
 }
 
 /// Get stat data about the files explicitly specified by match.
 /// TODO subrepos
 fn walk_explicit<'a>(
     files: &'a HashSet<&HgPath>,
     dmap: &'a DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
-    check_exec: bool,
-    list_clean: bool,
-    last_normal_time: i64,
+    options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&'a HgPath, Dispatch)>> {
     files.par_iter().filter_map(move |filename| {
         // TODO normalization
         let normalized = filename.as_ref();
 
         let buf = match hg_path_to_path_buf(normalized) {
             Ok(x) => x,
             Err(e) => return Some(Err(e.into())),
         };
         let target = root_dir.as_ref().join(buf);
         let st = target.symlink_metadata();
         match st {
             Ok(meta) => {
                 let file_type = meta.file_type();
                 if file_type.is_file() || file_type.is_symlink() {
                     if let Some(entry) = dmap.get(normalized) {
                         return Some(Ok((
                             normalized,
                             dispatch_found(
                                 &normalized,
                                 *entry,
                                 HgMetadata::from_metadata(meta),
                                 &dmap.copy_map,
-                                check_exec,
-                                list_clean,
-                                last_normal_time,
+                                options,
                             ),
                         )));
                     }
                 } else {
                     if dmap.contains_key(normalized) {
                         return Some(Ok((normalized, Dispatch::Removed)));
                     }
                 }
             }
             Err(_) => {
                 if let Some(entry) = dmap.get(normalized) {
                     return Some(Ok((
                         normalized,
                         dispatch_missing(entry.state),
                     )));
                 }
             }
         };
         None
     })
 }
 
+#[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,
+}
+
 /// Stat all entries in the `DirstateMap` and mark them for dispatch into
 /// the relevant collections.
 fn stat_dmap_entries(
     dmap: &DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
-    check_exec: bool,
-    list_clean: bool,
-    last_normal_time: i64,
+    options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&HgPath, Dispatch)>> {
     dmap.par_iter().map(move |(filename, entry)| {
         let filename: &HgPath = filename;
         let filename_as_path = hg_path_to_path_buf(filename)?;
         let meta = root_dir.as_ref().join(filename_as_path).symlink_metadata();
 
         match meta {
             Ok(ref m)
                 if !(m.file_type().is_file()
                     || m.file_type().is_symlink()) =>
             {
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Ok(m) => Ok((
                 filename,
                 dispatch_found(
                     filename,
                     *entry,
                     HgMetadata::from_metadata(m),
                     &dmap.copy_map,
-                    check_exec,
-                    list_clean,
-                    last_normal_time,
+                    options,
                 ),
             )),
             Err(ref e)
                 if e.kind() == std::io::ErrorKind::NotFound
                     || e.raw_os_error() == Some(20) =>
             {
                 // Rust does not yet have an `ErrorKind` for
                 // `NotADirectory` (errno 20)
                 // It happens if the dirstate contains `foo/bar` and
                 // foo is not a directory
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Err(e) => Err(e),
         }
     })
 }
 
 pub struct StatusResult<'a> {
     pub modified: Vec<&'a HgPath>,
     pub added: Vec<&'a HgPath>,
     pub removed: Vec<&'a HgPath>,
     pub deleted: Vec<&'a HgPath>,
     pub clean: Vec<&'a HgPath>,
     /* TODO ignored
      * TODO unknown */
 }
 
 fn build_response<'a>(
     results: impl IntoIterator<Item = IoResult<(&'a HgPath, Dispatch)>>,
 ) -> IoResult<(Vec<&'a HgPath>, StatusResult<'a>)> {
     let mut lookup = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
 
     for res in results.into_iter() {
         let (filename, dispatch) = res?;
         match dispatch {
             Dispatch::Unknown => {}
             Dispatch::Unsure => lookup.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
         }
     }
 
     Ok((
         lookup,
         StatusResult {
             modified,
             added,
             removed,
             deleted,
             clean,
         },
     ))
 }
 
 pub fn status<'a: 'c, 'b: 'c, 'c>(
     dmap: &'a DirstateMap,
     matcher: &'b impl Matcher,
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
-    list_clean: bool,
-    last_normal_time: i64,
-    check_exec: bool,
+    options: StatusOptions,
 ) -> IoResult<(Vec<&'c HgPath>, StatusResult<'c>)> {
     let files = matcher.file_set();
     let mut results = vec![];
     if let Some(files) = files {
-        results.par_extend(walk_explicit(
-            &files,
-            &dmap,
-            root_dir,
-            check_exec,
-            list_clean,
-            last_normal_time,
-        ));
+        results.par_extend(walk_explicit(&files, &dmap, root_dir, options));
     }
 
     if !matcher.is_exact() {
-        let stat_results = stat_dmap_entries(
-            &dmap,
-            root_dir,
-            check_exec,
-            list_clean,
-            last_normal_time,
-        );
+        let stat_results = stat_dmap_entries(&dmap, root_dir, options);
         results.par_extend(stat_results);
     }
 
     build_response(results)
 }

rust/hg-core/src/lib.rs

@@ -1,184 +1,184 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 mod ancestors;
 pub mod dagops;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 mod dirstate;
 pub mod discovery;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     dirstate_map::DirstateMap,
     parsers::{pack_dirstate, parse_dirstate, PARENT_SIZE},
-    status::{status, StatusResult},
+    status::{status, StatusOptions, StatusResult},
     CopyMap, CopyMapIter, DirstateEntry, DirstateParents, EntryState,
     StateMap, StateMapIter,
 };
 mod filepatterns;
 pub mod matchers;
 pub mod revlog;
 pub use revlog::*;
 #[cfg(feature = "with-re2")]
 pub mod re2;
 pub mod utils;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
     parse_pattern_syntax, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use twox_hash::RandomXxHashBuilder64;
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum DirstateParseError {
     TooLittleData,
     Overflow,
     CorruptedEntry(String),
     Damaged,
 }
 
 impl From<std::io::Error> for DirstateParseError {
     fn from(e: std::io::Error) -> Self {
         DirstateParseError::CorruptedEntry(e.to_string())
     }
 }
 
 impl ToString for DirstateParseError {
     fn to_string(&self) -> String {
         use crate::DirstateParseError::*;
         match self {
             TooLittleData => "Too little data for dirstate.".to_string(),
             Overflow => "Overflow in dirstate.".to_string(),
             CorruptedEntry(e) => format!("Corrupted entry: {:?}.", e),
             Damaged => "Dirstate appears to be damaged.".to_string(),
         }
     }
 }
 
 #[derive(Debug, PartialEq)]
 pub enum DirstatePackError {
     CorruptedEntry(String),
     CorruptedParent,
     BadSize(usize, usize),
 }
 
 impl From<std::io::Error> for DirstatePackError {
     fn from(e: std::io::Error) -> Self {
         DirstatePackError::CorruptedEntry(e.to_string())
     }
 }
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     InvalidPath(HgPathError),
 }
 
 impl ToString for DirstateMapError {
     fn to_string(&self) -> String {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 "expected a value, found none".to_string()
             }
             DirstateMapError::EmptyPath => "Overflow in dirstate.".to_string(),
             DirstateMapError::InvalidPath(e) => e.to_string(),
         }
     }
 }
 
 pub enum DirstateError {
     Parse(DirstateParseError),
     Pack(DirstatePackError),
     Map(DirstateMapError),
     IO(std::io::Error),
 }
 
 impl From<DirstateParseError> for DirstateError {
     fn from(e: DirstateParseError) -> Self {
         DirstateError::Parse(e)
     }
 }
 
 impl From<DirstatePackError> for DirstateError {
     fn from(e: DirstatePackError) -> Self {
         DirstateError::Pack(e)
     }
 }
 
 #[derive(Debug)]
 pub enum PatternError {
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
     /// This is temporary, see `re2/mod.rs`.
     /// This will cause a fallback to Python.
     Re2NotInstalled,
 }
 
 impl ToString for PatternError {
     fn to_string(&self) -> String {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 format!("Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 format!(
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 format!("matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(e) => e.to_string(),
             PatternError::Path(e) => e.to_string(),
             PatternError::NonRegexPattern(pattern) => {
                 format!("'{:?}' cannot be turned into a regex", pattern)
             }
             PatternError::Re2NotInstalled => {
                 "Re2 is not installed, cannot use regex functionality."
                     .to_string()
             }
         }
     }
 }
 
 impl From<DirstateMapError> for DirstateError {
     fn from(e: DirstateMapError) -> Self {
         DirstateError::Map(e)
     }
 }
 
 impl From<std::io::Error> for DirstateError {
     fn from(e: std::io::Error) -> Self {
         DirstateError::IO(e)
     }
 }
 
 impl From<std::io::Error> for PatternError {
     fn from(e: std::io::Error) -> Self {
         PatternError::IO(e)
     }
 }
 
 impl From<HgPathError> for PatternError {
     fn from(e: HgPathError) -> Self {
         PatternError::Path(e)
     }
 }

rust/hg-core/src/matchers.rs

@@ -1,888 +1,892 b''
 // matchers.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.
 
 //! Structs and types for matching files and directories.
 
 #[cfg(feature = "with-re2")]
 use crate::re2::Re2;
 use crate::{
     dirstate::dirs_multiset::DirsChildrenMultiset,
     filepatterns::{
         build_single_regex, filter_subincludes, get_patterns_from_file,
         PatternFileWarning, PatternResult, SubInclude,
     },
     utils::{
         files::find_dirs,
         hg_path::{HgPath, HgPathBuf},
         Escaped,
     },
     DirsMultiset, DirstateMapError, FastHashMap, IgnorePattern, PatternError,
     PatternSyntax,
 };
 
 use std::collections::HashSet;
 use std::fmt::{Display, Error, Formatter};
 use std::iter::FromIterator;
 use std::ops::Deref;
 use std::path::Path;
 
 #[derive(Debug, PartialEq)]
 pub enum VisitChildrenSet<'a> {
     /// Don't visit anything
     Empty,
     /// Only visit this directory
     This,
     /// Visit this directory and these subdirectories
     /// TODO Should we implement a `NonEmptyHashSet`?
     Set(HashSet<&'a HgPath>),
     /// Visit this directory and all subdirectories
     Recursive,
 }
 
 pub trait Matcher {
     /// Explicitly listed files
     fn file_set(&self) -> Option<&HashSet<&HgPath>>;
     /// Returns whether `filename` is in `file_set`
     fn exact_match(&self, filename: impl AsRef<HgPath>) -> bool;
     /// Returns whether `filename` is matched by this matcher
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool;
     /// Decides whether a directory should be visited based on whether it
     /// has potential matches in it or one of its subdirectories, and
     /// potentially lists which subdirectories of that directory should be
     /// visited. This is based on the match's primary, included, and excluded
     /// patterns.
     ///
     /// # Example
     ///
     /// Assume matchers `['path:foo/bar', 'rootfilesin:qux']`, we would
     /// return the following values (assuming the implementation of
     /// visit_children_set is capable of recognizing this; some implementations
     /// are not).
     ///
     /// ```text
     /// ```ignore
     /// '' -> {'foo', 'qux'}
     /// 'baz' -> set()
     /// 'foo' -> {'bar'}
     /// // Ideally this would be `Recursive`, but since the prefix nature of
     /// // matchers is applied to the entire matcher, we have to downgrade this
     /// // to `This` due to the (yet to be implemented in Rust) non-prefix
     /// // `RootFilesIn'-kind matcher being mixed in.
     /// 'foo/bar' -> 'this'
     /// 'qux' -> 'this'
     /// ```
     /// # Important
     ///
     /// Most matchers do not know if they're representing files or
     /// directories. They see `['path:dir/f']` and don't know whether `f` is a
     /// file or a directory, so `visit_children_set('dir')` for most matchers
     /// will return `HashSet{ HgPath { "f" } }`, but if the matcher knows it's
     /// a file (like the yet to be implemented in Rust `ExactMatcher` does),
     /// it may return `VisitChildrenSet::This`.
     /// Do not rely on the return being a `HashSet` indicating that there are
     /// no files in this dir to investigate (or equivalently that if there are
     /// files to investigate in 'dir' that it will always return
     /// `VisitChildrenSet::This`).
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet;
     /// Matcher will match everything and `files_set()` will be empty:
     /// optimization might be possible.
     fn matches_everything(&self) -> bool;
     /// Matcher will match exactly the files in `files_set()`: optimization
     /// might be possible.
     fn is_exact(&self) -> bool;
 }
 
 /// Matches everything.
 ///```
 /// use hg::{ matchers::{Matcher, AlwaysMatcher}, utils::hg_path::HgPath };
 ///
 /// let matcher = AlwaysMatcher;
 ///
 /// assert_eq!(matcher.matches(HgPath::new(b"whatever")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"b.txt")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"main.c")), true);
 /// assert_eq!(matcher.matches(HgPath::new(br"re:.*\.c$")), true);
 /// ```
 #[derive(Debug)]
 pub struct AlwaysMatcher;
 
 impl Matcher for AlwaysMatcher {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         None
     }
     fn exact_match(&self, _filename: impl AsRef<HgPath>) -> bool {
         false
     }
     fn matches(&self, _filename: impl AsRef<HgPath>) -> bool {
         true
     }
     fn visit_children_set(
         &self,
         _directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         VisitChildrenSet::Recursive
     }
     fn matches_everything(&self) -> bool {
         true
     }
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 /// Matches the input files exactly. They are interpreted as paths, not
 /// patterns.
 ///
 ///```
 /// use hg::{ matchers::{Matcher, FileMatcher}, utils::hg_path::HgPath };
 ///
 /// let files = [HgPath::new(b"a.txt"), HgPath::new(br"re:.*\.c$")];
 /// let matcher = FileMatcher::new(&files).unwrap();
 ///
 /// assert_eq!(matcher.matches(HgPath::new(b"a.txt")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"b.txt")), false);
 /// assert_eq!(matcher.matches(HgPath::new(b"main.c")), false);
 /// assert_eq!(matcher.matches(HgPath::new(br"re:.*\.c$")), true);
 /// ```
 #[derive(Debug)]
 pub struct FileMatcher<'a> {
     files: HashSet<&'a HgPath>,
     dirs: DirsMultiset,
 }
 
 impl<'a> FileMatcher<'a> {
     pub fn new(
         files: &'a [impl AsRef<HgPath>],
     ) -> Result<Self, DirstateMapError> {
         Ok(Self {
             files: HashSet::from_iter(files.iter().map(|f| f.as_ref())),
             dirs: DirsMultiset::from_manifest(files)?,
         })
     }
     fn inner_matches(&self, filename: impl AsRef<HgPath>) -> bool {
         self.files.contains(filename.as_ref())
     }
 }
 
 impl<'a> Matcher for FileMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         Some(&self.files)
     }
     fn exact_match(&self, filename: impl AsRef<HgPath>) -> bool {
         self.inner_matches(filename)
     }
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool {
         self.inner_matches(filename)
     }
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         if self.files.is_empty() || !self.dirs.contains(&directory) {
             return VisitChildrenSet::Empty;
         }
         let dirs_as_set = self.dirs.iter().map(|k| k.deref()).collect();
 
         let mut candidates: HashSet<&HgPath> =
             self.files.union(&dirs_as_set).map(|k| *k).collect();
         candidates.remove(HgPath::new(b""));
 
         if !directory.as_ref().is_empty() {
             let directory = [directory.as_ref().as_bytes(), b"/"].concat();
             candidates = candidates
                 .iter()
                 .filter_map(|c| {
                     if c.as_bytes().starts_with(&directory) {
                         Some(HgPath::new(&c.as_bytes()[directory.len()..]))
                     } else {
                         None
                     }
                 })
                 .collect();
         }
 
         // `self.dirs` includes all of the directories, recursively, so if
         // we're attempting to match 'foo/bar/baz.txt', it'll have '', 'foo',
         // 'foo/bar' in it. Thus we can safely ignore a candidate that has a
         // '/' in it, indicating it's for a subdir-of-a-subdir; the immediate
         // subdir will be in there without a slash.
         VisitChildrenSet::Set(
             candidates
                 .iter()
                 .filter_map(|c| {
                     if c.bytes().all(|b| *b != b'/') {
                         Some(*c)
                     } else {
                         None
                     }
                 })
                 .collect(),
         )
     }
     fn matches_everything(&self) -> bool {
         false
     }
     fn is_exact(&self) -> bool {
         true
     }
 }
 
 /// Matches files that are included in the ignore rules.
 #[cfg_attr(
     feature = "with-re2",
     doc = r##"
 ```
 use hg::{
     matchers::{IncludeMatcher, Matcher},
     IgnorePattern,
     PatternSyntax,
     utils::hg_path::HgPath
 };
 use std::path::Path;
 ///
 let ignore_patterns =
 vec![IgnorePattern::new(PatternSyntax::RootGlob, b"this*", Path::new(""))];
 let (matcher, _) = IncludeMatcher::new(ignore_patterns, "").unwrap();
 ///
 assert_eq!(matcher.matches(HgPath::new(b"testing")), false);
 assert_eq!(matcher.matches(HgPath::new(b"this should work")), true);
 assert_eq!(matcher.matches(HgPath::new(b"this also")), true);
 assert_eq!(matcher.matches(HgPath::new(b"but not this")), false);
 ```
 "##
 )]
 pub struct IncludeMatcher<'a> {
     patterns: Vec<u8>,
     match_fn: Box<dyn for<'r> Fn(&'r HgPath) -> bool + 'a + Sync>,
     /// Whether all the patterns match a prefix (i.e. recursively)
     prefix: bool,
     roots: HashSet<HgPathBuf>,
     dirs: HashSet<HgPathBuf>,
     parents: HashSet<HgPathBuf>,
 }
 
 impl<'a> Matcher for IncludeMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         None
     }
 
     fn exact_match(&self, _filename: impl AsRef<HgPath>) -> bool {
         false
     }
 
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool {
         (self.match_fn)(filename.as_ref())
     }
 
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         let dir = directory.as_ref();
         if self.prefix && self.roots.contains(dir) {
             return VisitChildrenSet::Recursive;
         }
         if self.roots.contains(HgPath::new(b""))
             || self.roots.contains(dir)
             || self.dirs.contains(dir)
             || find_dirs(dir).any(|parent_dir| self.roots.contains(parent_dir))
         {
             return VisitChildrenSet::This;
         }
 
         if self.parents.contains(directory.as_ref()) {
             let multiset = self.get_all_parents_children();
             if let Some(children) = multiset.get(dir) {
                 return VisitChildrenSet::Set(children.to_owned());
             }
         }
         VisitChildrenSet::Empty
     }
 
     fn matches_everything(&self) -> bool {
         false
     }
 
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 #[cfg(feature = "with-re2")]
 /// Returns a function that matches an `HgPath` against the given regex
 /// pattern.
 ///
 /// This can fail when the pattern is invalid or not supported by the
 /// underlying engine `Re2`, for instance anything with back-references.
 fn re_matcher(
     pattern: &[u8],
 ) -> PatternResult<impl Fn(&HgPath) -> bool + Sync> {
     let regex = Re2::new(pattern);
     let regex = regex.map_err(|e| PatternError::UnsupportedSyntax(e))?;
     Ok(move |path: &HgPath| regex.is_match(path.as_bytes()))
 }
 
 #[cfg(not(feature = "with-re2"))]
 fn re_matcher(_: &[u8]) -> PatternResult<Box<dyn Fn(&HgPath) -> bool + Sync>> {
     Err(PatternError::Re2NotInstalled)
 }
 
 /// Returns the regex pattern and a function that matches an `HgPath` against
 /// said regex formed by the given ignore patterns.
 fn build_regex_match<'a>(
     ignore_patterns: &'a [&'a IgnorePattern],
 ) -> PatternResult<(Vec<u8>, Box<dyn Fn(&HgPath) -> bool + Sync>)> {
     let regexps: Result<Vec<_>, PatternError> = ignore_patterns
         .into_iter()
         .map(|k| build_single_regex(*k))
         .collect();
     let regexps = regexps?;
     let full_regex = regexps.join(&b'|');
 
     let matcher = re_matcher(&full_regex)?;
     let func = Box::new(move |filename: &HgPath| matcher(filename));
 
     Ok((full_regex, func))
 }
 
 /// Returns roots and directories corresponding to each pattern.
 ///
 /// This calculates the roots and directories exactly matching the patterns and
 /// returns a tuple of (roots, dirs). It does not return other directories
 /// which may also need to be considered, like the parent directories.
 fn roots_and_dirs(
     ignore_patterns: &[IgnorePattern],
 ) -> (Vec<HgPathBuf>, Vec<HgPathBuf>) {
     let mut roots = Vec::new();
     let mut dirs = Vec::new();
 
     for ignore_pattern in ignore_patterns {
         let IgnorePattern {
             syntax, pattern, ..
         } = ignore_pattern;
         match syntax {
             PatternSyntax::RootGlob | PatternSyntax::Glob => {
                 let mut root = vec![];
 
                 for p in pattern.split(|c| *c == b'/') {
                     if p.iter().any(|c| match *c {
                         b'[' | b'{' | b'*' | b'?' => true,
                         _ => false,
                     }) {
                         break;
                     }
                     root.push(HgPathBuf::from_bytes(p));
                 }
                 let buf =
                     root.iter().fold(HgPathBuf::new(), |acc, r| acc.join(r));
                 roots.push(buf);
             }
             PatternSyntax::Path | PatternSyntax::RelPath => {
                 let pat = HgPath::new(if pattern == b"." {
                     &[] as &[u8]
                 } else {
                     pattern
                 });
                 roots.push(pat.to_owned());
             }
             PatternSyntax::RootFiles => {
                 let pat = if pattern == b"." {
                     &[] as &[u8]
                 } else {
                     pattern
                 };
                 dirs.push(HgPathBuf::from_bytes(pat));
             }
             _ => {
                 roots.push(HgPathBuf::new());
             }
         }
     }
     (roots, dirs)
 }
 
 /// Paths extracted from patterns
 #[derive(Debug, PartialEq)]
 struct RootsDirsAndParents {
     /// Directories to match recursively
     pub roots: HashSet<HgPathBuf>,
     /// Directories to match non-recursively
     pub dirs: HashSet<HgPathBuf>,
     /// Implicitly required directories to go to items in either roots or dirs
     pub parents: HashSet<HgPathBuf>,
 }
 
 /// Extract roots, dirs and parents from patterns.
 fn roots_dirs_and_parents(
     ignore_patterns: &[IgnorePattern],
 ) -> PatternResult<RootsDirsAndParents> {
     let (roots, dirs) = roots_and_dirs(ignore_patterns);
 
     let mut parents = HashSet::new();
 
     parents.extend(
         DirsMultiset::from_manifest(&dirs)
             .map_err(|e| match e {
                 DirstateMapError::InvalidPath(e) => e,
                 _ => unreachable!(),
             })?
             .iter()
             .map(|k| k.to_owned()),
     );
     parents.extend(
         DirsMultiset::from_manifest(&roots)
             .map_err(|e| match e {
                 DirstateMapError::InvalidPath(e) => e,
                 _ => unreachable!(),
             })?
             .iter()
             .map(|k| k.to_owned()),
     );
 
     Ok(RootsDirsAndParents {
         roots: HashSet::from_iter(roots),
         dirs: HashSet::from_iter(dirs),
         parents,
     })
 }
 
 /// Returns a function that checks whether a given file (in the general sense)
 /// should be matched.
 fn build_match<'a, 'b>(
     ignore_patterns: &'a [IgnorePattern],
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(
     Vec<u8>,
     Box<dyn Fn(&HgPath) -> bool + 'b + Sync>,
     Vec<PatternFileWarning>,
 )> {
     let mut match_funcs: Vec<Box<dyn Fn(&HgPath) -> bool + Sync>> = vec![];
     // For debugging and printing
     let mut patterns = vec![];
     let mut all_warnings = vec![];
 
     let (subincludes, ignore_patterns) =
         filter_subincludes(ignore_patterns, root_dir)?;
 
     if !subincludes.is_empty() {
         // Build prefix-based matcher functions for subincludes
         let mut submatchers = FastHashMap::default();
         let mut prefixes = vec![];
 
         for SubInclude { prefix, root, path } in subincludes.into_iter() {
             let (match_fn, warnings) = get_ignore_function(&[path], root)?;
             all_warnings.extend(warnings);
             prefixes.push(prefix.to_owned());
             submatchers.insert(prefix.to_owned(), match_fn);
         }
 
         let match_subinclude = move |filename: &HgPath| {
             for prefix in prefixes.iter() {
                 if let Some(rel) = filename.relative_to(prefix) {
                     if (submatchers.get(prefix).unwrap())(rel) {
                         return true;
                     }
                 }
             }
             false
         };
 
         match_funcs.push(Box::new(match_subinclude));
     }
 
     if !ignore_patterns.is_empty() {
         // Either do dumb matching if all patterns are rootfiles, or match
         // with a regex.
         if ignore_patterns
             .iter()
             .all(|k| k.syntax == PatternSyntax::RootFiles)
         {
             let dirs: HashSet<_> = ignore_patterns
                 .iter()
                 .map(|k| k.pattern.to_owned())
                 .collect();
             let mut dirs_vec: Vec<_> = dirs.iter().cloned().collect();
 
             let match_func = move |path: &HgPath| -> bool {
                 let path = path.as_bytes();
                 let i = path.iter().rfind(|a| **a == b'/');
                 let dir = if let Some(i) = i {
                     &path[..*i as usize]
                 } else {
                     b"."
                 };
                 dirs.contains(dir.deref())
             };
             match_funcs.push(Box::new(match_func));
 
             patterns.extend(b"rootfilesin: ");
             dirs_vec.sort();
             patterns.extend(dirs_vec.escaped_bytes());
         } else {
             let (new_re, match_func) = build_regex_match(&ignore_patterns)?;
             patterns = new_re;
             match_funcs.push(match_func)
         }
     }
 
     Ok(if match_funcs.len() == 1 {
         (patterns, match_funcs.remove(0), all_warnings)
     } else {
         (
             patterns,
             Box::new(move |f: &HgPath| -> bool {
                 match_funcs.iter().any(|match_func| match_func(f))
             }),
             all_warnings,
         )
     })
 }
 
 /// Parses all "ignore" files with their recursive includes and returns a
 /// function that checks whether a given file (in the general sense) should be
 /// ignored.
 pub fn get_ignore_function<'a>(
     all_pattern_files: &[impl AsRef<Path>],
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(
     impl for<'r> Fn(&'r HgPath) -> bool + Sync,
     Vec<PatternFileWarning>,
 )> {
     let mut all_patterns = vec![];
     let mut all_warnings = vec![];
 
     for pattern_file in all_pattern_files.into_iter() {
         let (patterns, warnings) =
             get_patterns_from_file(pattern_file, &root_dir)?;
 
         all_patterns.extend(patterns);
         all_warnings.extend(warnings);
     }
     let (matcher, warnings) = IncludeMatcher::new(all_patterns, root_dir)?;
     all_warnings.extend(warnings);
     Ok((move |path: &HgPath| matcher.matches(path), all_warnings))
 }
 
 impl<'a> IncludeMatcher<'a> {
     pub fn new(
         ignore_patterns: Vec<IgnorePattern>,
         root_dir: impl AsRef<Path>,
     ) -> PatternResult<(Self, Vec<PatternFileWarning>)> {
         let (patterns, match_fn, warnings) =
             build_match(&ignore_patterns, root_dir)?;
         let RootsDirsAndParents {
             roots,
             dirs,
             parents,
         } = roots_dirs_and_parents(&ignore_patterns)?;
 
         let prefix = ignore_patterns.iter().any(|k| match k.syntax {
             PatternSyntax::Path | PatternSyntax::RelPath => true,
             _ => false,
         });
 
         Ok((
             Self {
                 patterns,
                 match_fn,
                 prefix,
                 roots,
                 dirs,
                 parents,
             },
             warnings,
         ))
     }
 
     fn get_all_parents_children(&self) -> DirsChildrenMultiset {
         // TODO cache
         let thing = self
             .dirs
             .iter()
             .chain(self.roots.iter())
             .chain(self.parents.iter());
         DirsChildrenMultiset::new(thing, Some(&self.parents))
     }
 }
 
 impl<'a> Display for IncludeMatcher<'a> {
     fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error> {
         write!(
             f,
             "IncludeMatcher(includes='{}')",
             String::from_utf8_lossy(&self.patterns.escaped_bytes())
         )
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
     use std::path::Path;
 
     #[test]
     fn test_roots_and_dirs() {
         let pats = vec![
             IgnorePattern::new(PatternSyntax::Glob, b"g/h/*", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g/h", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g*", Path::new("")),
         ];
         let (roots, dirs) = roots_and_dirs(&pats);
 
         assert_eq!(
             roots,
             vec!(
                 HgPathBuf::from_bytes(b"g/h"),
                 HgPathBuf::from_bytes(b"g/h"),
                 HgPathBuf::new()
             ),
         );
         assert_eq!(dirs, vec!());
     }
 
     #[test]
     fn test_roots_dirs_and_parents() {
         let pats = vec![
             IgnorePattern::new(PatternSyntax::Glob, b"g/h/*", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g/h", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g*", Path::new("")),
         ];
 
         let mut roots = HashSet::new();
         roots.insert(HgPathBuf::from_bytes(b"g/h"));
         roots.insert(HgPathBuf::new());
 
         let dirs = HashSet::new();
 
         let mut parents = HashSet::new();
         parents.insert(HgPathBuf::new());
         parents.insert(HgPathBuf::from_bytes(b"g"));
 
         assert_eq!(
             roots_dirs_and_parents(&pats).unwrap(),
-            RootsDirsAndParents {roots, dirs, parents}
+            RootsDirsAndParents {
+                roots,
+                dirs,
+                parents
+            }
         );
     }
 
     #[test]
     fn test_filematcher_visit_children_set() {
         // Visitchildrenset
         let files = vec![HgPath::new(b"dir/subdir/foo.txt")];
         let matcher = FileMatcher::new(&files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"foo.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/foo.txt")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
     }
 
     #[test]
     fn test_filematcher_visit_children_set_files_and_dirs() {
         let files = vec![
             HgPath::new(b"rootfile.txt"),
             HgPath::new(b"a/file1.txt"),
             HgPath::new(b"a/b/file2.txt"),
             // No file in a/b/c
             HgPath::new(b"a/b/c/d/file4.txt"),
         ];
         let matcher = FileMatcher::new(&files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"a"));
         set.insert(HgPath::new(b"rootfile.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"b"));
         set.insert(HgPath::new(b"file1.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"c"));
         set.insert(HgPath::new(b"file2.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"d"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"file4.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c/d")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c/d/e")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
     }
 
     #[cfg(feature = "with-re2")]
     #[test]
     fn test_includematcher() {
         // VisitchildrensetPrefix
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Recursive
         );
         // OPT: This should probably be 'all' if its parent is?
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetRootfilesin
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::RootFiles,
                 b"dir/subdir",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetGlob
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::Glob,
                 b"dir/z*",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         // OPT: these should probably be set().
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
     }
 }