matchers: fix the bug in rust PatternMatcher that made it cut off early

This brings the rust output in line with the Python output.

rust/hg-core/src/matchers.rs

@@ -1,2434 +1,2431 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.
 
 use format_bytes::format_bytes;
 use once_cell::sync::OnceCell;
 
 use crate::{
     dirstate::dirs_multiset::DirsChildrenMultiset,
     filepatterns::{
         build_single_regex, filter_subincludes, get_patterns_from_file,
         PatternFileWarning, PatternResult,
     },
     utils::{
-        files::find_dirs,
+        files::{dir_ancestors, find_dirs},
         hg_path::{HgPath, HgPathBuf, HgPathError},
         Escaped,
     },
     DirsMultiset, FastHashMap, IgnorePattern, PatternError, PatternSyntax,
 };
 
 use crate::dirstate::status::IgnoreFnType;
 use crate::filepatterns::normalize_path_bytes;
 use std::collections::HashSet;
 use std::fmt::{Display, Error, Formatter};
 use std::path::{Path, PathBuf};
 use std::{borrow::ToOwned, collections::BTreeSet};
 
 #[derive(Debug, PartialEq)]
 pub enum VisitChildrenSet {
     /// Don't visit anything
     Empty,
     /// Visit this directory and probably its children
     This,
     /// Only visit the children (both files and directories) if they
     /// are mentioned in this set. (empty set corresponds to [Empty])
     /// TODO Should we implement a `NonEmptyHashSet`?
     Set(HashSet<HgPathBuf>),
     /// Visit this directory and all subdirectories
     /// (you can stop asking about the children set)
     Recursive,
 }
 
 pub trait Matcher: core::fmt::Debug {
     /// Explicitly listed files
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>>;
     /// Returns whether `filename` is in `file_set`
     fn exact_match(&self, filename: &HgPath) -> bool;
     /// Returns whether `filename` is matched by this matcher
     fn matches(&self, filename: &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: &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<HgPathBuf>> {
         None
     }
     fn exact_match(&self, _filename: &HgPath) -> bool {
         false
     }
     fn matches(&self, _filename: &HgPath) -> bool {
         true
     }
     fn visit_children_set(&self, _directory: &HgPath) -> VisitChildrenSet {
         VisitChildrenSet::Recursive
     }
     fn matches_everything(&self) -> bool {
         true
     }
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 /// Matches nothing.
 #[derive(Debug)]
 pub struct NeverMatcher;
 
 impl Matcher for NeverMatcher {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         None
     }
     fn exact_match(&self, _filename: &HgPath) -> bool {
         false
     }
     fn matches(&self, _filename: &HgPath) -> bool {
         false
     }
     fn visit_children_set(&self, _directory: &HgPath) -> VisitChildrenSet {
         VisitChildrenSet::Empty
     }
     fn matches_everything(&self) -> bool {
         false
     }
     fn is_exact(&self) -> bool {
         true
     }
 }
 
 /// Matches the input files exactly. They are interpreted as paths, not
 /// patterns.
 ///
 ///```
 /// use hg::{ matchers::{Matcher, FileMatcher}, utils::hg_path::{HgPath, HgPathBuf} };
 ///
 /// let files = vec![HgPathBuf::from_bytes(b"a.txt"), HgPathBuf::from_bytes(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 {
     files: HashSet<HgPathBuf>,
     dirs: DirsMultiset,
     sorted_visitchildrenset_candidates: OnceCell<BTreeSet<HgPathBuf>>,
 }
 
 impl FileMatcher {
     pub fn new(files: Vec<HgPathBuf>) -> Result<Self, HgPathError> {
         let dirs = DirsMultiset::from_manifest(&files)?;
         Ok(Self {
             files: HashSet::from_iter(files),
             dirs,
             sorted_visitchildrenset_candidates: OnceCell::new(),
         })
     }
     fn inner_matches(&self, filename: &HgPath) -> bool {
         self.files.contains(filename.as_ref())
     }
 }
 
 impl Matcher for FileMatcher {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         Some(&self.files)
     }
     fn exact_match(&self, filename: &HgPath) -> bool {
         self.inner_matches(filename)
     }
     fn matches(&self, filename: &HgPath) -> bool {
         self.inner_matches(filename)
     }
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         if self.files.is_empty() || !self.dirs.contains(directory) {
             return VisitChildrenSet::Empty;
         }
 
         let compute_candidates = || -> BTreeSet<HgPathBuf> {
             let mut candidates: BTreeSet<HgPathBuf> =
                 self.dirs.iter().cloned().collect();
             candidates.extend(self.files.iter().cloned());
             candidates.remove(HgPath::new(b""));
             candidates
         };
         let candidates =
             if directory.as_ref().is_empty() {
                 compute_candidates()
             } else {
                 let sorted_candidates = self
                     .sorted_visitchildrenset_candidates
                     .get_or_init(compute_candidates);
                 let directory_bytes = directory.as_ref().as_bytes();
                 let start: HgPathBuf =
                     format_bytes!(b"{}/", directory_bytes).into();
                 let start_len = start.len();
                 // `0` sorts after `/`
                 let end = format_bytes!(b"{}0", directory_bytes).into();
                 BTreeSet::from_iter(sorted_candidates.range(start..end).map(
                     |c| HgPathBuf::from_bytes(&c.as_bytes()[start_len..]),
                 ))
             };
 
         // `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
                 .into_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 a set of (kind, pat, source) against a 'root' directory.
 /// (Currently the 'root' directory is effectively always empty)
 /// ```
 /// use hg::{
 ///     matchers::{PatternMatcher, Matcher},
 ///     IgnorePattern,
 ///     PatternSyntax,
 ///     utils::hg_path::{HgPath, HgPathBuf}
 /// };
 /// use std::collections::HashSet;
 /// use std::path::Path;
 /// ///
 /// let ignore_patterns : Vec<IgnorePattern> =
 ///     vec![IgnorePattern::new(PatternSyntax::Regexp, br".*\.c$", Path::new("")),
 ///          IgnorePattern::new(PatternSyntax::Path, b"foo/a", Path::new("")),
 ///          IgnorePattern::new(PatternSyntax::RelPath, b"b", Path::new("")),
 ///          IgnorePattern::new(PatternSyntax::Glob, b"*.h", Path::new("")),
 ///     ];
 /// let matcher = PatternMatcher::new(ignore_patterns).unwrap();
 /// ///
 /// assert_eq!(matcher.matches(HgPath::new(b"main.c")), true); // matches re:.*\.c$
 /// assert_eq!(matcher.matches(HgPath::new(b"b.txt")), false);
 /// assert_eq!(matcher.matches(HgPath::new(b"foo/a")), true); // matches path:foo/a
 /// assert_eq!(matcher.matches(HgPath::new(b"a")), false); // does not match path:b, since 'root' is 'foo'
 /// assert_eq!(matcher.matches(HgPath::new(b"b")), true); // matches relpath:b, since 'root' is 'foo'
 /// assert_eq!(matcher.matches(HgPath::new(b"lib.h")), true); // matches glob:*.h
 /// assert_eq!(matcher.file_set().unwrap(),
 ///            &HashSet::from([HgPathBuf::from_bytes(b""), HgPathBuf::from_bytes(b"foo/a"),
 ///                            HgPathBuf::from_bytes(b""), HgPathBuf::from_bytes(b"b")]));
 /// assert_eq!(matcher.exact_match(HgPath::new(b"foo/a")), true);
 /// assert_eq!(matcher.exact_match(HgPath::new(b"b")), true);
 /// assert_eq!(matcher.exact_match(HgPath::new(b"lib.h")), false); // exact matches are for (rel)path kinds
 /// ```
 pub struct PatternMatcher<'a> {
     patterns: Vec<u8>,
     match_fn: IgnoreFnType<'a>,
     /// Whether all the patterns match a prefix (i.e. recursively)
     prefix: bool,
     files: HashSet<HgPathBuf>,
     dirs: DirsMultiset,
 }
 
 impl core::fmt::Debug for PatternMatcher<'_> {
     fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
         f.debug_struct("PatternMatcher")
             .field("patterns", &String::from_utf8_lossy(&self.patterns))
             .field("prefix", &self.prefix)
             .field("files", &self.files)
             .field("dirs", &self.dirs)
             .finish()
     }
 }
 
 impl<'a> PatternMatcher<'a> {
     pub fn new(ignore_patterns: Vec<IgnorePattern>) -> PatternResult<Self> {
         let (files, _) = roots_and_dirs(&ignore_patterns);
         let dirs = DirsMultiset::from_manifest(&files)?;
         let files: HashSet<HgPathBuf> = HashSet::from_iter(files);
 
         let prefix = ignore_patterns.iter().all(|k| {
             matches!(k.syntax, PatternSyntax::Path | PatternSyntax::RelPath)
         });
         let (patterns, match_fn) = build_match(ignore_patterns, b"$")?;
 
         Ok(Self {
             patterns,
             match_fn,
             prefix,
             files,
             dirs,
         })
     }
 }
 
 impl<'a> Matcher for PatternMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         Some(&self.files)
     }
 
     fn exact_match(&self, filename: &HgPath) -> bool {
         self.files.contains(filename)
     }
 
     fn matches(&self, filename: &HgPath) -> bool {
         if self.files.contains(filename) {
             return true;
         }
         (self.match_fn)(filename)
     }
 
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         if self.prefix && self.files.contains(directory) {
             return VisitChildrenSet::Recursive;
         }
-        let path_or_parents_in_set = find_dirs(directory)
+        let path_or_parents_in_set = dir_ancestors(directory)
             .any(|parent_dir| self.files.contains(parent_dir));
         if self.dirs.contains(directory) || path_or_parents_in_set {
             VisitChildrenSet::This
         } else {
             VisitChildrenSet::Empty
         }
     }
 
     fn matches_everything(&self) -> bool {
         false
     }
 
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 /// Matches files that are included in the ignore rules.
 /// ```
 /// 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);
 /// ///
 /// let ignore_patterns =
 /// vec![IgnorePattern::new(PatternSyntax::RootFiles, b"dir/subdir", Path::new(""))];
 /// let matcher = IncludeMatcher::new(ignore_patterns).unwrap();
 /// ///
 /// assert!(!matcher.matches(HgPath::new(b"file")));
 /// assert!(!matcher.matches(HgPath::new(b"dir/file")));
 /// assert!(matcher.matches(HgPath::new(b"dir/subdir/file")));
 /// assert!(!matcher.matches(HgPath::new(b"dir/subdir/subsubdir/file")));
 /// ```
 pub struct IncludeMatcher<'a> {
     patterns: Vec<u8>,
     match_fn: IgnoreFnType<'a>,
     /// Whether all the patterns match a prefix (i.e. recursively)
     prefix: bool,
     roots: HashSet<HgPathBuf>,
     dirs: HashSet<HgPathBuf>,
     parents: HashSet<HgPathBuf>,
 }
 
 impl core::fmt::Debug for IncludeMatcher<'_> {
     fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
         f.debug_struct("IncludeMatcher")
             .field("patterns", &String::from_utf8_lossy(&self.patterns))
             .field("prefix", &self.prefix)
             .field("roots", &self.roots)
             .field("dirs", &self.dirs)
             .field("parents", &self.parents)
             .finish()
     }
 }
 
 impl<'a> Matcher for IncludeMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         None
     }
 
     fn exact_match(&self, _filename: &HgPath) -> bool {
         false
     }
 
     fn matches(&self, filename: &HgPath) -> bool {
         (self.match_fn)(filename)
     }
 
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         let dir = directory;
         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(dir.as_ref()) {
             let multiset = self.get_all_parents_children();
             if let Some(children) = multiset.get(dir) {
                 return VisitChildrenSet::Set(
                     children.iter().map(HgPathBuf::from).collect(),
                 );
             }
         }
         VisitChildrenSet::Empty
     }
 
     fn matches_everything(&self) -> bool {
         false
     }
 
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 /// The union of multiple matchers. Will match if any of the matchers match.
 #[derive(Debug)]
 pub struct UnionMatcher {
     matchers: Vec<Box<dyn Matcher + Sync>>,
 }
 
 impl Matcher for UnionMatcher {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         None
     }
 
     fn exact_match(&self, _filename: &HgPath) -> bool {
         false
     }
 
     fn matches(&self, filename: &HgPath) -> bool {
         self.matchers.iter().any(|m| m.matches(filename))
     }
 
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         let mut result = HashSet::new();
         let mut this = false;
         for matcher in self.matchers.iter() {
             let visit = matcher.visit_children_set(directory);
             match visit {
                 VisitChildrenSet::Empty => continue,
                 VisitChildrenSet::This => {
                     this = true;
                     // Don't break, we might have an 'all' in here.
                     continue;
                 }
                 VisitChildrenSet::Set(set) => {
                     result.extend(set);
                 }
                 VisitChildrenSet::Recursive => {
                     return visit;
                 }
             }
         }
         if this {
             return VisitChildrenSet::This;
         }
         if result.is_empty() {
             VisitChildrenSet::Empty
         } else {
             VisitChildrenSet::Set(result)
         }
     }
 
     fn matches_everything(&self) -> bool {
         // TODO Maybe if all are AlwaysMatcher?
         false
     }
 
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 impl UnionMatcher {
     pub fn new(matchers: Vec<Box<dyn Matcher + Sync>>) -> Self {
         Self { matchers }
     }
 }
 
 #[derive(Debug)]
 pub struct IntersectionMatcher {
     m1: Box<dyn Matcher + Sync>,
     m2: Box<dyn Matcher + Sync>,
     files: Option<HashSet<HgPathBuf>>,
 }
 
 impl Matcher for IntersectionMatcher {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         self.files.as_ref()
     }
 
     fn exact_match(&self, filename: &HgPath) -> bool {
         self.files.as_ref().map_or(false, |f| f.contains(filename))
     }
 
     fn matches(&self, filename: &HgPath) -> bool {
         self.m1.matches(filename) && self.m2.matches(filename)
     }
 
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         let m1_set = self.m1.visit_children_set(directory);
         if m1_set == VisitChildrenSet::Empty {
             return VisitChildrenSet::Empty;
         }
         let m2_set = self.m2.visit_children_set(directory);
         if m2_set == VisitChildrenSet::Empty {
             return VisitChildrenSet::Empty;
         }
 
         if m1_set == VisitChildrenSet::Recursive {
             return m2_set;
         } else if m2_set == VisitChildrenSet::Recursive {
             return m1_set;
         }
 
         match (&m1_set, &m2_set) {
             (VisitChildrenSet::Recursive, _) => m2_set,
             (_, VisitChildrenSet::Recursive) => m1_set,
             (VisitChildrenSet::This, _) | (_, VisitChildrenSet::This) => {
                 VisitChildrenSet::This
             }
             (VisitChildrenSet::Set(m1), VisitChildrenSet::Set(m2)) => {
                 let set: HashSet<_> = m1.intersection(m2).cloned().collect();
                 if set.is_empty() {
                     VisitChildrenSet::Empty
                 } else {
                     VisitChildrenSet::Set(set)
                 }
             }
             _ => unreachable!(),
         }
     }
 
     fn matches_everything(&self) -> bool {
         self.m1.matches_everything() && self.m2.matches_everything()
     }
 
     fn is_exact(&self) -> bool {
         self.m1.is_exact() || self.m2.is_exact()
     }
 }
 
 impl IntersectionMatcher {
     pub fn new(
         mut m1: Box<dyn Matcher + Sync>,
         mut m2: Box<dyn Matcher + Sync>,
     ) -> Self {
         let files = if m1.is_exact() || m2.is_exact() {
             if !m1.is_exact() {
                 std::mem::swap(&mut m1, &mut m2);
             }
             m1.file_set().map(|m1_files| {
                 m1_files.iter().cloned().filter(|f| m2.matches(f)).collect()
             })
         } else {
             // without exact input file sets, we can't do an exact
             // intersection, so we must over-approximate by
             // unioning instead
             m1.file_set().map(|m1_files| match m2.file_set() {
                 Some(m2_files) => m1_files.union(m2_files).cloned().collect(),
                 None => m1_files.iter().cloned().collect(),
             })
         };
         Self { m1, m2, files }
     }
 }
 
 #[derive(Debug)]
 pub struct DifferenceMatcher {
     base: Box<dyn Matcher + Sync>,
     excluded: Box<dyn Matcher + Sync>,
     files: Option<HashSet<HgPathBuf>>,
 }
 
 impl Matcher for DifferenceMatcher {
     fn file_set(&self) -> Option<&HashSet<HgPathBuf>> {
         self.files.as_ref()
     }
 
     fn exact_match(&self, filename: &HgPath) -> bool {
         self.files.as_ref().map_or(false, |f| f.contains(filename))
     }
 
     fn matches(&self, filename: &HgPath) -> bool {
         self.base.matches(filename) && !self.excluded.matches(filename)
     }
 
     fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
         let excluded_set = self.excluded.visit_children_set(directory);
         if excluded_set == VisitChildrenSet::Recursive {
             return VisitChildrenSet::Empty;
         }
         let base_set = self.base.visit_children_set(directory);
         // Possible values for base: 'recursive', 'this', set(...), set()
         // Possible values for excluded:          'this', set(...), set()
         // If excluded has nothing under here that we care about, return base,
         // even if it's 'recursive'.
         if excluded_set == VisitChildrenSet::Empty {
             return base_set;
         }
         match base_set {
             VisitChildrenSet::This | VisitChildrenSet::Recursive => {
                 // Never return 'recursive' here if excluded_set is any kind of
                 // non-empty (either 'this' or set(foo)), since excluded might
                 // return set() for a subdirectory.
                 VisitChildrenSet::This
             }
             set => {
                 // Possible values for base:         set(...), set()
                 // Possible values for excluded: 'this', set(...)
                 // We ignore excluded set results. They're possibly incorrect:
                 //  base = path:dir/subdir
                 //  excluded=rootfilesin:dir,
                 //  visit_children_set(''):
                 //   base returns {'dir'}, excluded returns {'dir'}, if we
                 //   subtracted we'd return set(), which is *not* correct, we
                 //   still need to visit 'dir'!
                 set
             }
         }
     }
 
     fn matches_everything(&self) -> bool {
         false
     }
 
     fn is_exact(&self) -> bool {
         self.base.is_exact()
     }
 }
 
 impl DifferenceMatcher {
     pub fn new(
         base: Box<dyn Matcher + Sync>,
         excluded: Box<dyn Matcher + Sync>,
     ) -> Self {
         let base_is_exact = base.is_exact();
         let base_files = base.file_set().map(ToOwned::to_owned);
         let mut new = Self {
             base,
             excluded,
             files: None,
         };
         if base_is_exact {
             new.files = base_files.map(|files| {
                 files.iter().cloned().filter(|f| new.matches(f)).collect()
             });
         }
         new
     }
 }
 
 /// Wraps [`regex::bytes::Regex`] to improve performance in multithreaded
 /// contexts.
 ///
 /// The `status` algorithm makes heavy use of threads, and calling `is_match`
 /// from many threads at once is prone to contention, probably within the
 /// scratch space needed as the regex DFA is built lazily.
 ///
 /// We are in the process of raising the issue upstream, but for now
 /// the workaround used here is to store the `Regex` in a lazily populated
 /// thread-local variable, sharing the initial read-only compilation, but
 /// not the lazy dfa scratch space mentioned above.
 ///
 /// This reduces the contention observed with 16+ threads, but does not
 /// completely remove it. Hopefully this can be addressed upstream.
 struct RegexMatcher {
     /// Compiled at the start of the status algorithm, used as a base for
     /// cloning in each thread-local `self.local`, thus sharing the expensive
     /// first compilation.
     base: regex::bytes::Regex,
     /// Thread-local variable that holds the `Regex` that is actually queried
     /// from each thread.
     local: thread_local::ThreadLocal<regex::bytes::Regex>,
 }
 
 impl RegexMatcher {
     /// Returns whether the path matches the stored `Regex`.
     pub fn is_match(&self, path: &HgPath) -> bool {
         self.local
             .get_or(|| self.base.clone())
             .is_match(path.as_bytes())
     }
 }
 
 /// Return a `RegexBuilder` from a bytes pattern
 ///
 /// This works around the fact that even if it works on byte haysacks,
 /// [`regex::bytes::Regex`] still uses UTF-8 patterns.
 pub fn re_bytes_builder(pattern: &[u8]) -> regex::bytes::RegexBuilder {
     use std::io::Write;
 
     // The `regex` crate adds `.*` to the start and end of expressions if there
     // are no anchors, so add the start anchor.
     let mut escaped_bytes = vec![b'^', b'(', b'?', b':'];
     for byte in pattern {
         if *byte > 127 {
             write!(escaped_bytes, "\\x{:x}", *byte).unwrap();
         } else {
             escaped_bytes.push(*byte);
         }
     }
     escaped_bytes.push(b')');
 
     // Avoid the cost of UTF8 checking
     //
     // # Safety
     // This is safe because we escaped all non-ASCII bytes.
     let pattern_string = unsafe { String::from_utf8_unchecked(escaped_bytes) };
     regex::bytes::RegexBuilder::new(&pattern_string)
 }
 
 /// 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 (the `regex` crate), for instance anything with
 /// back-references.
 #[logging_timer::time("trace")]
 fn re_matcher(pattern: &[u8]) -> PatternResult<RegexMatcher> {
     let re = re_bytes_builder(pattern)
         .unicode(false)
         // Big repos with big `.hgignore` will hit the default limit and
         // incur a significant performance hit. One repo's `hg status` hit
         // multiple *minutes*.
         .dfa_size_limit(50 * (1 << 20))
         .build()
         .map_err(|e| PatternError::UnsupportedSyntax(e.to_string()))?;
 
     Ok(RegexMatcher {
         base: re,
         local: Default::default(),
     })
 }
 
 /// 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: &[IgnorePattern],
     glob_suffix: &[u8],
 ) -> PatternResult<(Vec<u8>, IgnoreFnType<'a>)> {
     let mut regexps = vec![];
     let mut exact_set = HashSet::new();
 
     for pattern in ignore_patterns {
         if let Some(re) = build_single_regex(pattern, glob_suffix)? {
             regexps.push(re);
         } else {
             let exact = normalize_path_bytes(&pattern.pattern);
             exact_set.insert(HgPathBuf::from_bytes(&exact));
         }
     }
 
     let full_regex = regexps.join(&b'|');
 
     // An empty pattern would cause the regex engine to incorrectly match the
     // (empty) root directory
     let func = if !(regexps.is_empty()) {
         let matcher = re_matcher(&full_regex)?;
         let func = move |filename: &HgPath| {
             exact_set.contains(filename) || matcher.is_match(filename)
         };
         Box::new(func) as IgnoreFnType
     } else {
         let func = move |filename: &HgPath| exact_set.contains(filename);
         Box::new(func) as IgnoreFnType
     };
 
     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 = HgPathBuf::new();
                 for p in pattern.split(|c| *c == b'/') {
                     if p.iter()
                         .any(|c| matches!(*c, b'[' | b'{' | b'*' | b'?'))
                     {
                         break;
                     }
                     root.push(HgPathBuf::from_bytes(p).as_ref());
                 }
                 roots.push(root);
             }
             PatternSyntax::Path
             | PatternSyntax::RelPath
             | PatternSyntax::FilePath => {
                 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)?
             .iter()
             .map(ToOwned::to_owned),
     );
     parents.extend(
         DirsMultiset::from_manifest(&roots)?
             .iter()
             .map(ToOwned::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>(
     ignore_patterns: Vec<IgnorePattern>,
     glob_suffix: &[u8],
 ) -> PatternResult<(Vec<u8>, IgnoreFnType<'a>)> {
     let mut match_funcs: Vec<IgnoreFnType<'a>> = vec![];
     // For debugging and printing
     let mut patterns = vec![];
 
     let (subincludes, ignore_patterns) = filter_subincludes(ignore_patterns)?;
 
     if !subincludes.is_empty() {
         // Build prefix-based matcher functions for subincludes
         let mut submatchers = FastHashMap::default();
         let mut prefixes = vec![];
 
         for sub_include in subincludes {
             let matcher = IncludeMatcher::new(sub_include.included_patterns)?;
             let match_fn =
                 Box::new(move |path: &HgPath| matcher.matches(path));
             prefixes.push(sub_include.prefix.clone());
             submatchers.insert(sub_include.prefix.clone(), match_fn);
         }
 
         let match_subinclude = move |filename: &HgPath| {
             for prefix in prefixes.iter() {
                 if let Some(rel) = filename.relative_to(prefix) {
                     if (submatchers[prefix])(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().rposition(|a| *a == b'/');
                 let dir = if let Some(i) = i { &path[..i] } else { b"." };
                 dirs.contains(dir)
             };
             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, glob_suffix)?;
             patterns = new_re;
             match_funcs.push(match_func)
         }
     }
 
     Ok(if match_funcs.len() == 1 {
         (patterns, match_funcs.remove(0))
     } else {
         (
             patterns,
             Box::new(move |f: &HgPath| -> bool {
                 match_funcs.iter().any(|match_func| match_func(f))
             }),
         )
     })
 }
 
 /// 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_matcher<'a>(
     mut all_pattern_files: Vec<PathBuf>,
     root_dir: &Path,
     inspect_pattern_bytes: &mut impl FnMut(&Path, &[u8]),
 ) -> PatternResult<(IncludeMatcher<'a>, Vec<PatternFileWarning>)> {
     let mut all_patterns = vec![];
     let mut all_warnings = vec![];
 
     // Sort to make the ordering of calls to `inspect_pattern_bytes`
     // deterministic even if the ordering of `all_pattern_files` is not (such
     // as when a iteration order of a Python dict or Rust HashMap is involved).
     // Sort by "string" representation instead of the default by component
     // (with a Rust-specific definition of a component)
     all_pattern_files
         .sort_unstable_by(|a, b| a.as_os_str().cmp(b.as_os_str()));
 
     for pattern_file in &all_pattern_files {
         let (patterns, warnings) = get_patterns_from_file(
             pattern_file,
             root_dir,
             inspect_pattern_bytes,
         )?;
 
         all_patterns.extend(patterns.to_owned());
         all_warnings.extend(warnings);
     }
     let matcher = IncludeMatcher::new(all_patterns)?;
     Ok((matcher, 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: Vec<PathBuf>,
     root_dir: &Path,
     inspect_pattern_bytes: &mut impl FnMut(&Path, &[u8]),
 ) -> PatternResult<(IgnoreFnType<'a>, Vec<PatternFileWarning>)> {
     let res =
         get_ignore_matcher(all_pattern_files, root_dir, inspect_pattern_bytes);
     res.map(|(matcher, all_warnings)| {
         let res: IgnoreFnType<'a> =
             Box::new(move |path: &HgPath| matcher.matches(path));
 
         (res, all_warnings)
     })
 }
 
 impl<'a> IncludeMatcher<'a> {
     pub fn new(ignore_patterns: Vec<IgnorePattern>) -> PatternResult<Self> {
         let RootsDirsAndParents {
             roots,
             dirs,
             parents,
         } = roots_dirs_and_parents(&ignore_patterns)?;
         let prefix = ignore_patterns.iter().all(|k| {
             matches!(k.syntax, PatternSyntax::Path | PatternSyntax::RelPath)
         });
         let (patterns, match_fn) = build_match(ignore_patterns, b"(?:/|$)")?;
 
         Ok(Self {
             patterns,
             match_fn,
             prefix,
             roots,
             dirs,
             parents,
         })
     }
 
     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))
     }
 
     pub fn debug_get_patterns(&self) -> &[u8] {
         self.patterns.as_ref()
     }
 }
 
 impl<'a> Display for IncludeMatcher<'a> {
     fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error> {
         // XXX What about exact matches?
         // I'm not sure it's worth it to clone the HashSet and keep it
         // around just in case someone wants to display the matcher, plus
         // it's going to be unreadable after a few entries, but we need to
         // inform in this display that exact matches are being used and are
         // (on purpose) missing from the `includes`.
         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::collections::BTreeMap;
     use std::collections::BTreeSet;
     use std::fmt::Debug;
     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
             }
         );
     }
 
     #[test]
     fn test_filematcher_visit_children_set() {
         // Visitchildrenset
         let files = vec![HgPathBuf::from_bytes(b"dir/subdir/foo.txt")];
         let matcher = FileMatcher::new(files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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![
             HgPathBuf::from_bytes(b"rootfile.txt"),
             HgPathBuf::from_bytes(b"a/file1.txt"),
             HgPathBuf::from_bytes(b"a/b/file2.txt"),
             // No file in a/b/c
             HgPathBuf::from_bytes(b"a/b/c/d/file4.txt"),
         ];
         let matcher = FileMatcher::new(files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"a"));
         set.insert(HgPathBuf::from_bytes(b"rootfile.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"b"));
         set.insert(HgPathBuf::from_bytes(b"file1.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"c"));
         set.insert(HgPathBuf::from_bytes(b"file2.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"d"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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
         );
     }
 
     #[test]
     fn test_patternmatcher() {
         // VisitdirPrefix
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Path,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Recursive
         );
         // OPT: This should probably be Recursive if its parent is?
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetPrefix
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Path,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Recursive
         );
         // OPT: This should probably be Recursive if its parent is?
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitdirRootfilesin
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RootFiles,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         // FIXME: These should probably be This.
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetRootfilesin
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RootFiles,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         // FIXME: These should probably be {'dir'}, {'subdir'} and This,
         // respectively, or at least This for all three.
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
 
         // VisitdirGlob
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Glob,
             b"dir/z*",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         // FIXME: This probably should be This
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         // OPT: these should probably be False.
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
 
         // VisitchildrensetGlob
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Glob,
             b"dir/z*",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         // FIXME: This probably should be This
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Empty
         );
         // OPT: these should probably be Empty
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
 
         // VisitdirFilepath
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::FilePath,
             b"dir/z",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetFilepath
         let m = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::FilePath,
             b"dir/z",
             Path::new(""),
         )])
         .unwrap();
         assert_eq!(
             m.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             m.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
     }
 
     #[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(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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(HgPathBuf::from_bytes(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
         );
 
         // VisitchildrensetFilePath
         let matcher = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::FilePath,
             b"dir/z",
             Path::new(""),
         )])
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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
         );
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"z"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
         // OPT: these should probably be set().
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
 
         // Test multiple patterns
         let matcher = IncludeMatcher::new(vec![
             IgnorePattern::new(PatternSyntax::RelPath, b"foo", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g*", Path::new("")),
         ])
         .unwrap();
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
 
         // Test multiple patterns
         let matcher = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Glob,
             b"**/*.exe",
             Path::new(""),
         )])
         .unwrap();
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::This
         );
     }
 
     #[test]
     fn test_unionmatcher() {
         // Path + Rootfiles
         let m1 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RelPath,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         let m2 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RootFiles,
             b"dir",
             Path::new(""),
         )])
         .unwrap();
         let matcher = UnionMatcher::new(vec![Box::new(m1), Box::new(m2)]);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Recursive
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // OPT: These next two could be 'all' instead of 'this'.
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
 
         // Path + unrelated Path
         let m1 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RelPath,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         let m2 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RelPath,
             b"folder",
             Path::new(""),
         )])
         .unwrap();
         let matcher = UnionMatcher::new(vec![Box::new(m1), Box::new(m2)]);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"folder"));
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Recursive
         );
         // OPT: These next two could be 'all' instead of 'this'.
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
 
         // Path + subpath
         let m1 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RelPath,
             b"dir/subdir/x",
             Path::new(""),
         )])
         .unwrap();
         let m2 = IncludeMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RelPath,
             b"dir/subdir",
             Path::new(""),
         )])
         .unwrap();
         let matcher = UnionMatcher::new(vec![Box::new(m1), Box::new(m2)]);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Recursive
         );
         // OPT: this should probably be 'all' not 'this'.
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::This
         );
     }
 
     #[test]
     fn test_intersectionmatcher() {
         // Include path + Include rootfiles
         let m1 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let m2 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RootFiles,
                 b"dir",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let matcher = IntersectionMatcher::new(m1, m2);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
 
         // Non intersecting paths
         let m1 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let m2 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"folder",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let matcher = IntersectionMatcher::new(m1, m2);
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
 
         // Nested paths
         let m1 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir/x",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let m2 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let matcher = IntersectionMatcher::new(m1, m2);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"x"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::Empty
         );
         // OPT: this should probably be 'all' not 'this'.
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
 
         // Diverging paths
         let m1 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir/x",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let m2 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir/z",
                 Path::new(""),
             )])
             .unwrap(),
         );
         let matcher = IntersectionMatcher::new(m1, m2);
 
         // OPT: these next two could probably be Empty as well.
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         // OPT: these next two could probably be Empty as well.
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
     }
 
     #[test]
     fn test_differencematcher() {
         // Two alwaysmatchers should function like a nevermatcher
         let m1 = AlwaysMatcher;
         let m2 = AlwaysMatcher;
         let matcher = DifferenceMatcher::new(Box::new(m1), Box::new(m2));
 
         for case in &[
             &b""[..],
             b"dir",
             b"dir/subdir",
             b"dir/subdir/z",
             b"dir/foo",
             b"dir/subdir/x",
             b"folder",
         ] {
             assert_eq!(
                 matcher.visit_children_set(HgPath::new(case)),
                 VisitChildrenSet::Empty
             );
         }
 
         // One always and one never should behave the same as an always
         let m1 = AlwaysMatcher;
         let m2 = NeverMatcher;
         let matcher = DifferenceMatcher::new(Box::new(m1), Box::new(m2));
 
         for case in &[
             &b""[..],
             b"dir",
             b"dir/subdir",
             b"dir/subdir/z",
             b"dir/foo",
             b"dir/subdir/x",
             b"folder",
         ] {
             assert_eq!(
                 matcher.visit_children_set(HgPath::new(case)),
                 VisitChildrenSet::Recursive
             );
         }
 
         // Two include matchers
         let m1 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new("/repo"),
             )])
             .unwrap(),
         );
         let m2 = Box::new(
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RootFiles,
                 b"dir",
                 Path::new("/repo"),
             )])
             .unwrap(),
         );
 
         let matcher = DifferenceMatcher::new(m1, m2);
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPathBuf::from_bytes(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
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/foo")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/z")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
     }
 
     mod invariants {
         pub mod visit_children_set {
 
             use crate::{
                 matchers::{tests::Tree, Matcher, VisitChildrenSet},
                 utils::hg_path::HgPath,
             };
 
             #[allow(dead_code)]
             #[derive(Debug)]
             struct Error<'a, M> {
                 matcher: &'a M,
                 path: &'a HgPath,
                 matching: &'a Tree,
                 visit_children_set: &'a VisitChildrenSet,
             }
 
             fn holds(matching: &Tree, vcs: &VisitChildrenSet) -> bool {
                 match vcs {
                     VisitChildrenSet::Empty => matching.is_empty(),
                     VisitChildrenSet::This => {
                         // `This` does not come with any obligations.
                         true
                     }
                     VisitChildrenSet::Recursive => {
                         // `Recursive` does not come with any correctness
                         // obligations.
                         // It instructs the caller to stop calling
                         // `visit_children_set` for all
                         // descendants, so may have negative performance
                         // implications, but we're not testing against that
                         // here.
                         true
                     }
                     VisitChildrenSet::Set(allowed_children) => {
                         // `allowed_children` does not distinguish between
                         // files and directories: if it's not included, it
                         // must not be matched.
                         for k in matching.dirs.keys() {
                             if !(allowed_children.contains(k)) {
                                 return false;
                             }
                         }
                         for k in matching.files.iter() {
                             if !(allowed_children.contains(k)) {
                                 return false;
                             }
                         }
                         true
                     }
                 }
             }
 
             pub fn check<M: Matcher + std::fmt::Debug>(
                 matcher: &M,
                 path: &HgPath,
                 matching: &Tree,
                 visit_children_set: &VisitChildrenSet,
             ) {
                 if !holds(matching, visit_children_set) {
                     panic!(
                         "{:#?}",
                         Error {
                             matcher,
                             path,
                             visit_children_set,
                             matching
                         }
                     )
                 }
             }
         }
     }
 
     #[derive(Debug, Clone)]
     pub struct Tree {
         files: BTreeSet<HgPathBuf>,
         dirs: BTreeMap<HgPathBuf, Tree>,
     }
 
     impl Tree {
         fn len(&self) -> usize {
             let mut n = 0;
             n += self.files.len();
             for d in self.dirs.values() {
                 n += d.len();
             }
             n
         }
 
         fn is_empty(&self) -> bool {
             self.files.is_empty() && self.dirs.is_empty()
         }
 
         fn filter_and_check<M: Matcher + Debug>(
             &self,
             m: &M,
             path: &HgPath,
         ) -> Self {
             let files: BTreeSet<HgPathBuf> = self
                 .files
                 .iter()
                 .filter(|v| m.matches(&path.join(v)))
                 .map(|f| f.to_owned())
                 .collect();
             let dirs: BTreeMap<HgPathBuf, Tree> = self
                 .dirs
                 .iter()
                 .filter_map(|(k, v)| {
                     let path = path.join(k);
                     let v = v.filter_and_check(m, &path);
                     if v.is_empty() {
                         None
                     } else {
                         Some((k.to_owned(), v))
                     }
                 })
                 .collect();
             let matching = Self { files, dirs };
             let vcs = m.visit_children_set(path);
             invariants::visit_children_set::check(m, path, &matching, &vcs);
             matching
         }
 
         fn check_matcher<M: Matcher + Debug>(
             &self,
             m: &M,
             expect_count: usize,
         ) {
             let res = self.filter_and_check(m, &HgPathBuf::new());
             if expect_count != res.len() {
                 eprintln!(
                     "warning: expected {} matches, got {} for {:#?}",
                     expect_count,
                     res.len(),
                     m
                 );
             }
         }
     }
 
     fn mkdir(children: &[(&[u8], &Tree)]) -> Tree {
         let p = HgPathBuf::from_bytes;
         let names = [
             p(b"a"),
             p(b"b.txt"),
             p(b"file.txt"),
             p(b"c.c"),
             p(b"c.h"),
             p(b"dir1"),
             p(b"dir2"),
             p(b"subdir"),
         ];
         let files: BTreeSet<HgPathBuf> = BTreeSet::from(names);
         let dirs = children
             .iter()
             .map(|(name, t)| (p(name), (*t).clone()))
             .collect();
         Tree { files, dirs }
     }
 
     fn make_example_tree() -> Tree {
         let leaf = mkdir(&[]);
         let abc = mkdir(&[(b"d", &leaf)]);
         let ab = mkdir(&[(b"c", &abc)]);
         let a = mkdir(&[(b"b", &ab)]);
         let dir = mkdir(&[(b"subdir", &leaf), (b"subdir.c", &leaf)]);
         mkdir(&[(b"dir", &dir), (b"dir1", &dir), (b"dir2", &dir), (b"a", &a)])
     }
 
     #[test]
     fn test_pattern_matcher_visit_children_set() {
         let tree = make_example_tree();
-        let _pattern_dir1_glob_c =
+        let pattern_dir1_glob_c =
             PatternMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::Glob,
                 b"dir1/*.c",
                 Path::new(""),
             )])
             .unwrap();
         let pattern_dir1 = || {
             PatternMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::Path,
                 b"dir1",
                 Path::new(""),
             )])
             .unwrap()
         };
         let pattern_dir1_a = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::Glob,
             b"dir1/a",
             Path::new(""),
         )])
         .unwrap();
         let pattern_relglob_c = || {
             PatternMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"*.c",
                 Path::new(""),
             )])
             .unwrap()
         };
-        //        // TODO: re-enable this test when the corresponding bug is
-        // fixed        if false {
-        //            tree.check_matcher(&pattern_dir1_glob_c);
-        //        }
         let files = vec![HgPathBuf::from_bytes(b"dir/subdir/b.txt")];
         let file_dir_subdir_b = FileMatcher::new(files).unwrap();
 
         let files = vec![
             HgPathBuf::from_bytes(b"file.txt"),
             HgPathBuf::from_bytes(b"a/file.txt"),
             HgPathBuf::from_bytes(b"a/b/file.txt"),
             // No file in a/b/c
             HgPathBuf::from_bytes(b"a/b/c/d/file.txt"),
         ];
         let file_abcdfile = FileMatcher::new(files).unwrap();
         let _rootfilesin_dir = PatternMatcher::new(vec![IgnorePattern::new(
             PatternSyntax::RootFiles,
             b"dir",
             Path::new(""),
         )])
         .unwrap();
 
         let pattern_filepath_dir_subdir =
             PatternMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::FilePath,
                 b"dir/subdir",
                 Path::new(""),
             )])
             .unwrap();
 
         let include_dir_subdir =
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )])
             .unwrap();
 
         let more_includematchers = [
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::Glob,
                 b"dir/s*",
                 Path::new(""),
             )])
             .unwrap(),
             // Test multiple patterns
             IncludeMatcher::new(vec![
                 IgnorePattern::new(
                     PatternSyntax::RelPath,
                     b"dir",
                     Path::new(""),
                 ),
                 IgnorePattern::new(PatternSyntax::Glob, b"s*", Path::new("")),
             ])
             .unwrap(),
             // Test multiple patterns
             IncludeMatcher::new(vec![IgnorePattern::new(
                 PatternSyntax::Glob,
                 b"**/*.c",
                 Path::new(""),
             )])
             .unwrap(),
         ];
 
         tree.check_matcher(&pattern_dir1(), 25);
         tree.check_matcher(&pattern_dir1_a, 1);
+        tree.check_matcher(&pattern_dir1_glob_c, 2);
         tree.check_matcher(&pattern_relglob_c(), 14);
         tree.check_matcher(&AlwaysMatcher, 112);
         tree.check_matcher(&NeverMatcher, 0);
         tree.check_matcher(
             &IntersectionMatcher::new(
                 Box::new(pattern_relglob_c()),
                 Box::new(pattern_dir1()),
             ),
             3,
         );
         tree.check_matcher(
             &UnionMatcher::new(vec![
                 Box::new(pattern_relglob_c()),
                 Box::new(pattern_dir1()),
             ]),
             36,
         );
         tree.check_matcher(
             &DifferenceMatcher::new(
                 Box::new(pattern_relglob_c()),
                 Box::new(pattern_dir1()),
             ),
             11,
         );
         tree.check_matcher(&file_dir_subdir_b, 1);
         tree.check_matcher(&file_abcdfile, 4);
         //        // TODO: re-enable this test when the corresponding bug is
         // fixed
         //
         //        if false {
         //            tree.check_matcher(&rootfilesin_dir, 6);
         //        }
         tree.check_matcher(&pattern_filepath_dir_subdir, 1);
         tree.check_matcher(&include_dir_subdir, 9);
         tree.check_matcher(&more_includematchers[0], 17);
         tree.check_matcher(&more_includematchers[1], 25);
         tree.check_matcher(&more_includematchers[2], 35);
     }
 }

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

@@ -1,436 +1,440 b''
 // files.rs
 //
 // Copyright 2019
 // Raphaël Gomès <[e-mail]>,
 // Yuya Nishihara <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Functions for fiddling with files.
 
 use crate::utils::{
     hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
     path_auditor::PathAuditor,
     replace_slice,
 };
 use lazy_static::lazy_static;
 use same_file::is_same_file;
 use std::borrow::{Cow, ToOwned};
 use std::ffi::{OsStr, OsString};
 use std::iter::FusedIterator;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 pub fn get_os_str_from_bytes(bytes: &[u8]) -> &OsStr {
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(bytes);
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     // Perhaps, the return type would have to be Result<PathBuf>.
     os_str
 }
 
 pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
     Path::new(get_os_str_from_bytes(bytes))
 }
 
 // TODO: need to convert from WTF8 to MBCS bytes on Windows.
 // that's why Vec<u8> is returned.
 #[cfg(unix)]
 pub fn get_bytes_from_path(path: impl AsRef<Path>) -> Vec<u8> {
     get_bytes_from_os_str(path.as_ref())
 }
 
 #[cfg(unix)]
 pub fn get_bytes_from_os_str(str: impl AsRef<OsStr>) -> Vec<u8> {
     use std::os::unix::ffi::OsStrExt;
     str.as_ref().as_bytes().to_vec()
 }
 
 #[cfg(unix)]
 pub fn get_bytes_from_os_string(str: OsString) -> Vec<u8> {
     use std::os::unix::ffi::OsStringExt;
     str.into_vec()
 }
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub struct Ancestors<'a> {
     next: Option<&'a HgPath>,
 }
 
 impl<'a> Iterator for Ancestors<'a> {
     type Item = &'a HgPath;
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some(s) if s.is_empty() => None,
             Some(s) => {
                 let p = s.bytes().rposition(|c| *c == b'/').unwrap_or(0);
                 Some(HgPath::new(&s.as_bytes()[..p]))
             }
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for Ancestors<'a> {}
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub(crate) struct AncestorsWithBase<'a> {
     next: Option<(&'a HgPath, &'a HgPath)>,
 }
 
 impl<'a> Iterator for AncestorsWithBase<'a> {
     type Item = (&'a HgPath, &'a HgPath);
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some((s, _)) if s.is_empty() => None,
             Some((s, _)) => Some(s.split_filename()),
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for AncestorsWithBase<'a> {}
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub fn find_dirs(path: &HgPath) -> Ancestors {
     let mut dirs = Ancestors { next: Some(path) };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
+pub fn dir_ancestors(path: &HgPath) -> Ancestors {
+    Ancestors { next: Some(path) }
+}
+
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub(crate) fn find_dirs_with_base(path: &HgPath) -> AncestorsWithBase {
     let mut dirs = AncestorsWithBase {
         next: Some((path, HgPath::new(b""))),
     };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// TODO more than ASCII?
 pub fn normalize_case(path: &HgPath) -> HgPathBuf {
     #[cfg(windows)] // NTFS compares via upper()
     return path.to_ascii_uppercase();
     #[cfg(unix)]
     path.to_ascii_lowercase()
 }
 
 lazy_static! {
     static ref IGNORED_CHARS: Vec<Vec<u8>> = {
         [
             0x200c, 0x200d, 0x200e, 0x200f, 0x202a, 0x202b, 0x202c, 0x202d,
             0x202e, 0x206a, 0x206b, 0x206c, 0x206d, 0x206e, 0x206f, 0xfeff,
         ]
         .iter()
         .map(|code| {
             std::char::from_u32(*code)
                 .unwrap()
                 .encode_utf8(&mut [0; 3])
                 .bytes()
                 .collect()
         })
         .collect()
     };
 }
 
 fn hfs_ignore_clean(bytes: &[u8]) -> Vec<u8> {
     let mut buf = bytes.to_owned();
     let needs_escaping = bytes.iter().any(|b| *b == b'\xe2' || *b == b'\xef');
     if needs_escaping {
         for forbidden in IGNORED_CHARS.iter() {
             replace_slice(&mut buf, forbidden, &[])
         }
         buf
     } else {
         buf
     }
 }
 
 pub fn lower_clean(bytes: &[u8]) -> Vec<u8> {
     hfs_ignore_clean(&bytes.to_ascii_lowercase())
 }
 
 /// Returns the canonical path of `name`, given `cwd` and `root`
 pub fn canonical_path(
     root: impl AsRef<Path>,
     cwd: impl AsRef<Path>,
     name: impl AsRef<Path>,
 ) -> Result<PathBuf, HgPathError> {
     // TODO add missing normalization for other platforms
     let root = root.as_ref();
     let cwd = cwd.as_ref();
     let name = name.as_ref();
 
     let name = if !name.is_absolute() {
         root.join(cwd).join(name)
     } else {
         name.to_owned()
     };
     let auditor = PathAuditor::new(root);
     if name != root && name.starts_with(root) {
         let name = name.strip_prefix(root).unwrap();
         auditor.audit_path(path_to_hg_path_buf(name)?)?;
         Ok(name.to_owned())
     } else if name == root {
         Ok("".into())
     } else {
         // Determine whether `name' is in the hierarchy at or beneath `root',
         // by iterating name=name.parent() until it returns `None` (can't
         // check name == '/', because that doesn't work on windows).
         let mut name = name.deref();
         let original_name = name.to_owned();
         loop {
             let same = is_same_file(name, root).unwrap_or(false);
             if same {
                 if name == original_name {
                     // `name` was actually the same as root (maybe a symlink)
                     return Ok("".into());
                 }
                 // `name` is a symlink to root, so `original_name` is under
                 // root
                 let rel_path = original_name.strip_prefix(name).unwrap();
                 auditor.audit_path(path_to_hg_path_buf(rel_path)?)?;
                 return Ok(rel_path.to_owned());
             }
             name = match name.parent() {
                 None => break,
                 Some(p) => p,
             };
         }
         // TODO hint to the user about using --cwd
         // Bubble up the responsibility to Python for now
         Err(HgPathError::NotUnderRoot {
             path: original_name,
             root: root.to_owned(),
         })
     }
 }
 
 /// Returns the representation of the path relative to the current working
 /// directory for display purposes.
 ///
 /// `cwd` is a `HgPath`, so it is considered relative to the root directory
 /// of the repository.
 ///
 /// # Examples
 ///
 /// ```
 /// use hg::utils::hg_path::HgPath;
 /// use hg::utils::files::relativize_path;
 /// use std::borrow::Cow;
 ///
 /// let file = HgPath::new(b"nested/file");
 /// let cwd = HgPath::new(b"");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"nested/file"));
 ///
 /// let cwd = HgPath::new(b"nested");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"file"));
 ///
 /// let cwd = HgPath::new(b"other");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"../nested/file"));
 /// ```
 pub fn relativize_path(path: &HgPath, cwd: impl AsRef<HgPath>) -> Cow<[u8]> {
     if cwd.as_ref().is_empty() {
         Cow::Borrowed(path.as_bytes())
     } else {
         // This is not all accurate as to how large `res` will actually be, but
         // profiling `rhg files` on a large-ish repo shows it’s better than
         // starting from a zero-capacity `Vec` and letting `extend` reallocate
         // repeatedly.
         let guesstimate = path.as_bytes().len();
 
         let mut res: Vec<u8> = Vec::with_capacity(guesstimate);
         let mut path_iter = path.as_bytes().split(|b| *b == b'/').peekable();
         let mut cwd_iter =
             cwd.as_ref().as_bytes().split(|b| *b == b'/').peekable();
         loop {
             match (path_iter.peek(), cwd_iter.peek()) {
                 (Some(a), Some(b)) if a == b => (),
                 _ => break,
             }
             path_iter.next();
             cwd_iter.next();
         }
         let mut need_sep = false;
         for _ in cwd_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(b"..");
         }
         for c in path_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(c);
         }
         Cow::Owned(res)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
         let mut dirs = super::find_dirs(HgPath::new(b"foo/bar/baz"));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo/bar")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn find_dirs_empty() {
         // looks weird, but mercurial.pathutil.finddirs(b"") yields b""
         let mut dirs = super::find_dirs(HgPath::new(b""));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_some() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b"foo/bar/baz"));
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo/bar"), HgPath::new(b"baz")))
         );
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo"), HgPath::new(b"bar")))
         );
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b"foo"))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_empty() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b""));
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b""))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_canonical_path() {
         let root = Path::new("/repo");
         let cwd = Path::new("/dir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/dir/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("repo/filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo/subdir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("subdir/filename"))
         );
     }
 
     #[test]
     fn test_canonical_path_not_rooted() {
         use std::fs::create_dir;
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let beneath_repo = base_dir_path.join("a");
         let root = base_dir_path.join("a/b");
         let out_of_repo = base_dir_path.join("c");
         let under_repo_symlink = out_of_repo.join("d");
 
         create_dir(&beneath_repo).unwrap();
         create_dir(&root).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
 
         assert_eq!(
             canonical_path(&root, Path::new(""), out_of_repo),
             Ok(PathBuf::from(""))
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &beneath_repo),
             Err(HgPathError::NotUnderRoot {
                 path: beneath_repo,
                 root: root.to_owned()
             })
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), under_repo_symlink),
             Ok(PathBuf::from("d"))
         );
     }
 }

tests/test-status.t

@@ -1,1053 +1,1053 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
   $ cat >> $HGRCPATH << EOF
   > [format]
   > use-dirstate-v2=1
   > [storage]
   > dirstate-v2.slow-path=allow
   > EOF
 #endif
 
   $ hg init repo1
   $ cd repo1
   $ mkdir a b a/1 b/1 b/2
   $ touch in_root a/in_a b/in_b a/1/in_a_1 b/1/in_b_1 b/2/in_b_2
 
 hg status in repo root:
 
   $ hg status
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
 hg status . in repo root:
 
   $ hg status .
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ hg status --cwd a
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a .
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a ..
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd b
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b .
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   $ hg status --cwd b ..
   ? ../a/1/in_a_1
   ? ../a/in_a
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   ? ../in_root
 
   $ hg status --cwd a/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a/1 .
   ? in_a_1
   $ hg status --cwd a/1 ..
   ? in_a_1
   ? ../in_a
 
   $ hg status --cwd b/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/1 .
   ? in_b_1
   $ hg status --cwd b/1 ..
   ? in_b_1
   ? ../2/in_b_2
   ? ../in_b
 
   $ hg status --cwd b/2
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/2 .
   ? in_b_2
   $ hg status --cwd b/2 ..
   ? ../1/in_b_1
   ? in_b_2
   ? ../in_b
 
 combining patterns with root and patterns without a root works
 
   $ hg st a/in_a re:.*b$
   ? a/in_a
   ? b/in_b
 
 tweaking defaults works
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
   $ HGPLAINEXCEPT=tweakdefaults hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root (glob)
 
 relative paths can be requested
 
   $ hg status --cwd a --config ui.relative-paths=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd a . --config ui.relative-paths=legacy
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a . --config ui.relative-paths=no
   ? a/1/in_a_1
   ? a/in_a
 
 commands.status.relative overrides ui.relative-paths
 
   $ cat >> $HGRCPATH <<EOF
   > [ui]
   > relative-paths = False
   > [commands]
   > status.relative = True
   > EOF
   $ hg status --cwd a
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
 
 if relative paths are explicitly off, tweakdefaults doesn't change it
   $ cat >> $HGRCPATH <<EOF
   > [commands]
   > status.relative = False
   > EOF
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ cd ..
 
   $ hg init repo2
   $ cd repo2
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg ci -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch modified added unknown ignored
   $ hg add added
   $ hg remove removed
   $ rm deleted
 
 hg status:
 
   $ hg status
   A added
   R removed
   ! deleted
   ? unknown
 
 hg status -n:
   $ env RHG_ON_UNSUPPORTED=abort hg status -n
   added
   removed
   deleted
   unknown
 
 hg status modified added removed deleted unknown never-existed ignored:
 
   $ hg status modified added removed deleted unknown never-existed ignored
   never-existed: * (glob)
   A added
   R removed
   ! deleted
   ? unknown
 
   $ hg copy modified copied
 
 hg status -C:
 
   $ hg status -C
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
 
 hg status -0:
 
   $ hg status -0 --config rhg.on-unsupported=abort
   A added\x00A copied\x00R removed\x00! deleted\x00? unknown\x00 (no-eol) (esc)
 
 hg status -A:
 
   $ hg status -A
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
   I ignored
   C .hgignore
   C modified
 
   $ hg status -A -T '{status} {path} {node|shortest}\n'
   A added ffff
   A copied ffff
   R removed ffff
   ! deleted ffff
   ? unknown ffff
   I ignored ffff
   C .hgignore ffff
   C modified ffff
 
   $ hg status -A -Tjson
   [
    {
     "itemtype": "file",
     "path": "added",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "copied",
     "source": "modified",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "removed",
     "status": "R"
    },
    {
     "itemtype": "file",
     "path": "deleted",
     "status": "!"
    },
    {
     "itemtype": "file",
     "path": "unknown",
     "status": "?"
    },
    {
     "itemtype": "file",
     "path": "ignored",
     "status": "I"
    },
    {
     "itemtype": "file",
     "path": ".hgignore",
     "status": "C"
    },
    {
     "itemtype": "file",
     "path": "modified",
     "status": "C"
    }
   ]
 
   $ hg status -A -Tpickle > pickle
   >>> import pickle
   >>> from mercurial import util
   >>> data = sorted((x[b'status'].decode(), x[b'path'].decode()) for x in pickle.load(open("pickle", r"rb")))
   >>> for s, p in data: print("%s %s" % (s, p))
   ! deleted
   ? pickle
   ? unknown
   A added
   A copied
   C .hgignore
   C modified
   I ignored
   R removed
   $ rm pickle
 
   $ echo "^ignoreddir$" > .hgignore
   $ mkdir ignoreddir
   $ touch ignoreddir/file
 
 Test templater support:
 
   $ hg status -AT "[{status}]\t{if(source, '{source} -> ')}{path}\n"
   [M]	.hgignore
   [A]	added
   [A]	modified -> copied
   [R]	removed
   [!]	deleted
   [?]	ignored
   [?]	unknown
   [I]	ignoreddir/file
   [C]	modified
   $ hg status -AT default
   M .hgignore
   A added
   A copied
     modified
   R removed
   ! deleted
   ? ignored
   ? unknown
   I ignoreddir/file
   C modified
   $ hg status -T compact
   abort: "status" not in template map
   [255]
 
 hg status ignoreddir/file:
 
   $ hg status ignoreddir/file
 
 hg status -i ignoreddir/file:
 
   $ hg status -i ignoreddir/file
   I ignoreddir/file
   $ cd ..
 
 Check 'status -q' and some combinations
 
   $ hg init repo3
   $ cd repo3
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg commit -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch added unknown ignored
   $ hg add added
   $ echo "test" >> modified
   $ hg remove removed
   $ rm deleted
   $ hg copy modified copied
 
 Specify working directory revision explicitly, that should be the same as
 "hg status"
 
   $ hg status --change "wdir()"
   M modified
   A added
   A copied
   R removed
   ! deleted
   ? unknown
 
 Run status with 2 different flags.
 Check if result is the same or different.
 If result is not as expected, raise error
 
   $ assert() {
   >     hg status $1 > ../a
   >     hg status $2 > ../b
   >     if diff ../a ../b > /dev/null; then
   >         out=0
   >     else
   >         out=1
   >     fi
   >     if [ $3 -eq 0 ]; then
   >         df="same"
   >     else
   >         df="different"
   >     fi
   >     if [ $out -ne $3 ]; then
   >         echo "Error on $1 and $2, should be $df."
   >     fi
   > }
 
 Assert flag1 flag2 [0-same | 1-different]
 
   $ assert "-q" "-mard"      0
   $ assert "-A" "-marduicC"  0
   $ assert "-qA" "-mardcC"   0
   $ assert "-qAui" "-A"      0
   $ assert "-qAu" "-marducC" 0
   $ assert "-qAi" "-mardicC" 0
   $ assert "-qu" "-u"        0
   $ assert "-q" "-u"         1
   $ assert "-m" "-a"         1
   $ assert "-r" "-d"         1
   $ cd ..
 
   $ hg init repo4
   $ cd repo4
   $ touch modified removed deleted
   $ hg ci -q -A -m 'initial checkin'
   $ touch added unknown
   $ hg add added
   $ hg remove removed
   $ rm deleted
   $ echo x > modified
   $ hg copy modified copied
   $ hg ci -m 'test checkin' -d "1000001 0"
   $ rm *
   $ touch unrelated
   $ hg ci -q -A -m 'unrelated checkin' -d "1000002 0"
 
 hg status --change 1:
 
   $ hg status --change 1
   M modified
   A added
   A copied
   R removed
 
 hg status --change 1 unrelated:
 
   $ hg status --change 1 unrelated
 
 hg status -C --change 1 added modified copied removed deleted:
 
   $ hg status -C --change 1 added modified copied removed deleted
   M modified
   A added
   A copied
     modified
   R removed
 
 hg status -A --change 1 and revset:
 
   $ hg status -A --change '1|1'
   M modified
   A added
   A copied
     modified
   R removed
   C deleted
 
   $ cd ..
 
 hg status with --rev and reverted changes:
 
   $ hg init reverted-changes-repo
   $ cd reverted-changes-repo
   $ echo a > file
   $ hg add file
   $ hg ci -m a
   $ echo b > file
   $ hg ci -m b
 
 reverted file should appear clean
 
   $ hg revert -r 0 .
   reverting file
   $ hg status -A --rev 0
   C file
 
 #if execbit
 reverted file with changed flag should appear modified
 
   $ chmod +x file
   $ hg status -A --rev 0
   M file
 
   $ hg revert -r 0 .
   reverting file
 
 reverted and committed file with changed flag should appear modified
 
   $ hg co -C .
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ chmod +x file
   $ hg ci -m 'change flag'
   $ hg status -A --rev 1 --rev 2
   M file
   $ hg diff -r 1 -r 2
 
 #endif
 
   $ cd ..
 
 hg status of binary file starting with '\1\n', a separator for metadata:
 
   $ hg init repo5
   $ cd repo5
   >>> open("010a", r"wb").write(b"\1\nfoo") and None
   $ hg ci -q -A -m 'initial checkin'
   $ hg status -A
   C 010a
 
   >>> open("010a", r"wb").write(b"\1\nbar") and None
   $ hg status -A
   M 010a
   $ hg ci -q -m 'modify 010a'
   $ hg status -A --rev 0:1
   M 010a
 
   $ touch empty
   $ hg ci -q -A -m 'add another file'
   $ hg status -A --rev 1:2 010a
   C 010a
 
   $ cd ..
 
 test "hg status" with "directory pattern" which matches against files
 only known on target revision.
 
   $ hg init repo6
   $ cd repo6
 
   $ echo a > a.txt
   $ hg add a.txt
   $ hg commit -m '#0'
   $ mkdir -p 1/2/3/4/5
   $ echo b > 1/2/3/4/5/b.txt
   $ hg add 1/2/3/4/5/b.txt
   $ hg commit -m '#1'
 
   $ hg update -C 0 > /dev/null
   $ hg status -A
   C a.txt
 
 the directory matching against specified pattern should be removed,
 because directory existence prevents 'dirstate.walk()' from showing
 warning message about such pattern.
 
   $ test ! -d 1
   $ hg status -A --rev 1 1/2/3/4/5/b.txt
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3/4/5
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1
   R 1/2/3/4/5/b.txt
 
   $ hg status --config ui.formatdebug=True --rev 1 1
   status = [
       {
           'itemtype': 'file',
           'path': '1/2/3/4/5/b.txt',
           'status': 'R'
       },
   ]
 
 #if windows
   $ hg --config ui.slash=false status -A --rev 1 1
   R 1\2\3\4\5\b.txt
 #endif
 
   $ cd ..
 
 Status after move overwriting a file (issue4458)
 =================================================
 
 
   $ hg init issue4458
   $ cd issue4458
   $ echo a > a
   $ echo b > b
   $ hg commit -Am base
   adding a
   adding b
 
 
 with --force
 
   $ hg mv b --force a
   $ hg st --copies
   M a
     b
   R b
   $ hg revert --all
   reverting a
   undeleting b
   $ rm *.orig
 
 without force
 
   $ hg rm a
   $ hg st --copies
   R a
   $ hg mv b a
   $ hg st --copies
   M a
     b
   R b
 
 using ui.statuscopies setting
   $ hg st --config ui.statuscopies=true
   M a
     b
   R b
   $ hg st --config ui.statuscopies=true --no-copies
   M a
   R b
   $ hg st --config ui.statuscopies=false
   M a
   R b
   $ hg st --config ui.statuscopies=false --copies
   M a
     b
   R b
   $ hg st --config ui.tweakdefaults=yes
   M a
     b
   R b
 
 using log status template (issue5155)
   $ hg log -Tstatus -r 'wdir()' -C
   changeset:   2147483647:ffffffffffff
   parent:      0:8c55c58b4c0e
   user:        test
   date:        * (glob)
   files:
   M a
     b
   R b
   
   $ hg log -GTstatus -r 'wdir()' -C
   o  changeset:   2147483647:ffffffffffff
   |  parent:      0:8c55c58b4c0e
   ~  user:        test
      date:        * (glob)
      files:
      M a
        b
      R b
   
 
 Other "bug" highlight, the revision status does not report the copy information.
 This is buggy behavior.
 
   $ hg commit -m 'blah'
   $ hg st --copies --change .
   M a
   R b
 
 using log status template, the copy information is displayed correctly.
   $ hg log -Tstatus -r. -C
   changeset:   1:6685fde43d21
   tag:         tip
   user:        test
   date:        * (glob)
   summary:     blah
   files:
   M a
     b
   R b
   
 
   $ cd ..
 
 Make sure .hg doesn't show up even as a symlink
 
   $ hg init repo0
   $ mkdir symlink-repo0
   $ cd symlink-repo0
   $ ln -s ../repo0/.hg
   $ hg status
 
 If the size hasn’t changed but mtime has, status needs to read the contents
 of the file to check whether it has changed
 
   $ echo 1 > a
   $ echo 1 > b
   $ touch -t 200102030000 a b
   $ hg commit -Aqm '#0'
   $ echo 2 > a
   $ touch -t 200102040000 a b
   $ hg status
   M a
 
 Asking specifically for the status of a deleted/removed file
 
   $ rm a
   $ rm b
   $ hg status a
   ! a
   $ hg rm a
   $ hg rm b
   $ hg status a
   R a
   $ hg commit -qm '#1'
   $ hg status a
   a: $ENOENT$
 
 Check using include flag with pattern when status does not need to traverse
 the working directory (issue6483)
 
   $ cd ..
   $ hg init issue6483
   $ cd issue6483
   $ touch a.py b.rs
   $ hg add a.py b.rs
   $ hg st -aI "*.py"
   A a.py
 
 Also check exclude pattern
 
   $ hg st -aX "*.rs"
   A a.py
 
 issue6335
 When a directory containing a tracked file gets symlinked, as of 5.8
 `hg st` only gives the correct answer about clean (or deleted) files
 if also listing unknowns.
 The tree-based dirstate and status algorithm fix this:
 
 #if symlink no-dirstate-v1 rust
 
   $ cd ..
   $ hg init issue6335
   $ cd issue6335
   $ mkdir foo
   $ touch foo/a
   $ hg ci -Ama
   adding foo/a
   $ mv foo bar
   $ ln -s bar foo
   $ hg status
   ! foo/a
   ? bar/a
   ? foo
 
   $ hg status -c  # incorrect output without the Rust implementation
   $ hg status -cu
   ? bar/a
   ? foo
   $ hg status -d  # incorrect output without the Rust implementation
   ! foo/a
   $ hg status -du
   ! foo/a
   ? bar/a
   ? foo
 
 #endif
 
 
 Create a repo with files in each possible status
 
   $ cd ..
   $ hg init repo7
   $ cd repo7
   $ mkdir subdir
   $ touch clean modified deleted removed
   $ touch subdir/clean subdir/modified subdir/deleted subdir/removed
   $ echo ignored > .hgignore
   $ hg ci -Aqm '#0'
   $ echo 1 > modified
   $ echo 1 > subdir/modified
   $ rm deleted
   $ rm subdir/deleted
   $ hg rm removed
   $ hg rm subdir/removed
   $ touch unknown ignored
   $ touch subdir/unknown subdir/ignored
 
 Check the output
 
   $ hg status
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
 
   $ hg status -mard
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
 
   $ hg status -A
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
   I ignored
   I subdir/ignored
   C .hgignore
   C clean
   C subdir/clean
 
+Test various matchers interatction with dirstate code:
+
   $ hg status path:subdir
   M subdir/modified
   R subdir/removed
   ! subdir/deleted
   ? subdir/unknown
 
-FIXME: it's a bug in rhg that the status below is empty:
-
   $ hg status 'glob:subdir/*'
-  M subdir/modified (no-rhg !)
-  R subdir/removed (no-rhg !)
-  ! subdir/deleted (no-rhg !)
-  ? subdir/unknown (no-rhg !)
+  M subdir/modified
+  R subdir/removed
+  ! subdir/deleted
+  ? subdir/unknown
 
 FIXME: it's a bug (both in rhg and in Python) that the status below is wrong,
 in rhg it's empty, in Python it's missing the unknown file:
 
   $ hg status rootfilesin:subdir
   M subdir/modified (no-rhg !)
   R subdir/removed (no-rhg !)
   ! subdir/deleted (no-rhg !)
 
 Note: `hg status some-name` creates a patternmatcher which is not supported
 yet by the Rust implementation of status, but includematcher is supported.
 --include is used below for that reason
 
 #if unix-permissions
 
 Not having permission to read a directory that contains tracked files makes
 status emit a warning then behave as if the directory was empty or removed
 entirely:
 
   $ chmod 0 subdir
   $ hg status --include subdir
   subdir: $EACCES$
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   $ chmod 755 subdir
 
 #endif
 
 Remove a directory that contains tracked files
 
   $ rm -r subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
 
 … and replace it by a file
 
   $ touch subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   ? subdir
 
 Replaced a deleted or removed file with a directory
 
   $ mkdir deleted removed
   $ touch deleted/1 removed/1
   $ hg status --include deleted --include removed
   R removed
   ! deleted
   ? deleted/1
   ? removed/1
   $ hg add removed/1
   $ hg status --include deleted --include removed
   A removed/1
   R removed
   ! deleted
   ? deleted/1
 
 Deeply nested files in an ignored directory are still listed on request
 
   $ echo ignored-dir >> .hgignore
   $ mkdir ignored-dir
   $ mkdir ignored-dir/subdir
   $ touch ignored-dir/subdir/1
   $ hg status --ignored
   I ignored
   I ignored-dir/subdir/1
 
 Check using include flag while listing ignored composes correctly (issue6514)
 
   $ cd ..
   $ hg init issue6514
   $ cd issue6514
   $ mkdir ignored-folder
   $ touch A.hs B.hs C.hs ignored-folder/other.txt ignored-folder/ctest.hs
   $ cat >.hgignore <<EOF
   > A.hs
   > B.hs
   > ignored-folder/
   > EOF
   $ hg st -i -I 're:.*\.hs$'
   I A.hs
   I B.hs
   I ignored-folder/ctest.hs
 
 #if rust dirstate-v2
 
 Check read_dir caching
 
   $ cd ..
   $ hg init repo8
   $ cd repo8
   $ mkdir subdir
   $ touch subdir/a subdir/b
   $ hg ci -Aqm '#0'
 
 The cached mtime is initially unset
 
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 It is still not set when there are unknown files
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 Now the directory is eligible for caching, so its mtime is saved in the dirstate
 
   $ rm subdir/unknown
   $ sleep 0.1 # ensure the kernel’s internal clock for mtimes has ticked
   $ hg status
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
 This time the command should be ever so slightly faster since it does not need `read_dir("subdir")`
 
   $ hg status
 
 Creating a new file changes the directory’s mtime, invalidating the cache
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
 
   $ rm subdir/unknown
   $ hg status
 
 Removing a node from the dirstate resets the cache for its parent directory
 
   $ hg forget subdir/a
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
   $ hg ci -qm '#1'
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
   $ hg status
   ? subdir/a
 
 Changing the hgignore rules makes us recompute the status (and rewrite the dirstate).
 
   $ rm subdir/a
   $ mkdir another-subdir
   $ touch another-subdir/something-else
 
   $ cat > "$TESTTMP"/extra-hgignore <<EOF
   > something-else
   > EOF
 
   $ hg status --config ui.ignore.global="$TESTTMP"/extra-hgignore
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
   $ hg status
   ? another-subdir/something-else
 
 One invocation of status is enough to populate the cache even if it's invalidated
 in the same run.
 
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
 #endif
 
 
 Test copy source formatting.
   $ cd ..
   $ hg init copy-source-repo
   $ cd copy-source-repo
   $ mkdir -p foo/bar
   $ cd foo/bar
   $ touch file
   $ hg addremove
   adding foo/bar/file
   $ hg commit -m 'add file'
   $ hg mv file copy
 
 Copy source respects relative path setting.
   $ hg st --config ui.statuscopies=true --config commands.status.relative=true
   A copy
     file
   R file
 
 Copy source is not shown when --no-status is passed.
   $ hg st --config ui.statuscopies=true --no-status
   foo/bar/copy
   foo/bar/file