rust-status: only involve ignore mechanism when needed

This prevents unnecessary fallbacks to Python, improving performance for
`hg update` for instance.

On Mozilla-Central a noop update goes from 1.6s down to 700ms.

Differential Revision: https://phab.mercurial-scm.org/D8315

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

@@ -1,895 +1,911 b''
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
 use crate::{
     dirstate::SIZE_FROM_OTHER_PARENT,
     filepatterns::PatternFileWarning,
     matchers::{get_ignore_function, Matcher, VisitChildrenSet},
     utils::{
         files::{find_dirs, HgMetadata},
         hg_path::{
             hg_path_to_path_buf, os_string_to_hg_path_buf, HgPath, HgPathBuf,
             HgPathError,
         },
         path_auditor::PathAuditor,
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState, FastHashMap,
     PatternError,
 };
 use lazy_static::lazy_static;
 use micro_timer::timed;
 use rayon::prelude::*;
 use std::{
     borrow::Cow,
     collections::HashSet,
     fs::{read_dir, DirEntry},
     io::ErrorKind,
     ops::Deref,
-    path::Path,
+    path::{Path, PathBuf},
 };
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug, Copy, Clone)]
 pub enum BadType {
     CharacterDevice,
     BlockDevice,
     FIFO,
     Socket,
     Directory,
     Unknown,
 }
 
 impl ToString for BadType {
     fn to_string(&self) -> String {
         match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         }
         .to_string()
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// Marker enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 #[derive(Debug, Copy, Clone)]
 enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
     Ignored,
     /// Empty dispatch, the file is not worth listing
     None,
     /// Was explicitly matched but cannot be found/accessed
     Bad(BadMatch),
     Directory {
         /// True if the directory used to be a file in the dmap so we can say
         /// that it's been removed.
         was_file: bool,
     },
 }
 
 type IoResult<T> = std::io::Result<T>;
+/// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait, 'static>`, so add
+/// an explicit lifetime here to not fight `'static` bounds "out of nowhere".
+type IgnoreFnType<'a> = Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>;
 
 /// Dates and times that are outside the 31-bit signed range are compared
 /// modulo 2^31. This should prevent hg from behaving badly with very large
 /// files or corrupt dates while still having a high probability of detecting
 /// changes. (issue2608)
 /// TODO I haven't found a way of having `b` be `Into<i32>`, since `From<u64>`
 /// is not defined for `i32`, and there is no `As` trait. This forces the
 /// caller to cast `b` as `i32`.
 fn mod_compare(a: i32, b: i32) -> bool {
     a & i32::max_value() != b & i32::max_value()
 }
 
 /// Return a sorted list containing information about the entries
 /// in the directory.
 ///
 /// * `skip_dot_hg` - Return an empty vec if `path` contains a `.hg` directory
 fn list_directory(
     path: impl AsRef<Path>,
     skip_dot_hg: bool,
 ) -> std::io::Result<Vec<(HgPathBuf, DirEntry)>> {
     let mut results = vec![];
     let entries = read_dir(path.as_ref())?;
 
     for entry in entries {
         let entry = entry?;
         let filename = os_string_to_hg_path_buf(entry.file_name())?;
         let file_type = entry.file_type()?;
         if skip_dot_hg && filename.as_bytes() == b".hg" && file_type.is_dir() {
             return Ok(vec![]);
         } else {
             results.push((HgPathBuf::from(filename), entry))
         }
     }
 
     results.sort_unstable_by_key(|e| e.0.clone());
     Ok(results)
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
     options: StatusOptions,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
                 (mode ^ st_mode as i32) & 0o100 != 0o000 && options.check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
             let other_parent = size == SIZE_FROM_OTHER_PARENT;
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
                 Dispatch::Modified
             } else if mod_compare(mtime, st_mtime as i32) {
                 Dispatch::Unsure
             } else if st_mtime == options.last_normal_time {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
             } else if options.list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::None
             }
         }
         EntryState::Merged => Dispatch::Modified,
         EntryState::Added => Dispatch::Added,
         EntryState::Removed => Dispatch::Removed,
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// The file corresponding to this Dirstate entry is missing.
 fn dispatch_missing(state: EntryState) -> Dispatch {
     match state {
         // File was removed from the filesystem during commands
         EntryState::Normal | EntryState::Merged | EntryState::Added => {
             Dispatch::Deleted
         }
         // File was removed, everything is normal
         EntryState::Removed => Dispatch::Removed,
         // File is unknown to Mercurial, everything is normal
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 lazy_static! {
     static ref DEFAULT_WORK: HashSet<&'static HgPath> = {
         let mut h = HashSet::new();
         h.insert(HgPath::new(b""));
         h
     };
 }
 
 /// Get stat data about the files explicitly specified by match.
 /// TODO subrepos
 #[timed]
 fn walk_explicit<'a>(
     files: Option<&'a HashSet<&HgPath>>,
     dmap: &'a DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send + 'a,
     options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&'a HgPath, Dispatch)>> {
     files
         .unwrap_or(&DEFAULT_WORK)
         .par_iter()
         .map(move |filename| {
             // TODO normalization
             let normalized = filename.as_ref();
 
             let buf = match hg_path_to_path_buf(normalized) {
                 Ok(x) => x,
                 Err(e) => return Some(Err(e.into())),
             };
             let target = root_dir.as_ref().join(buf);
             let st = target.symlink_metadata();
             let in_dmap = dmap.get(normalized);
             match st {
                 Ok(meta) => {
                     let file_type = meta.file_type();
                     return if file_type.is_file() || file_type.is_symlink() {
                         if let Some(entry) = in_dmap {
                             return Some(Ok((
                                 normalized,
                                 dispatch_found(
                                     &normalized,
                                     *entry,
                                     HgMetadata::from_metadata(meta),
                                     &dmap.copy_map,
                                     options,
                                 ),
                             )));
                         }
                         Some(Ok((normalized, Dispatch::Unknown)))
                     } else {
                         if file_type.is_dir() {
                             Some(Ok((
                                 normalized,
                                 Dispatch::Directory {
                                     was_file: in_dmap.is_some(),
                                 },
                             )))
                         } else {
                             Some(Ok((
                                 normalized,
                                 Dispatch::Bad(BadMatch::BadType(
                                     // TODO do more than unknown
                                     // Support for all `BadType` variant
                                     // varies greatly between platforms.
                                     // So far, no tests check the type and
                                     // this should be good enough for most
                                     // users.
                                     BadType::Unknown,
                                 )),
                             )))
                         }
                     };
                 }
                 Err(_) => {
                     if let Some(entry) = in_dmap {
                         return Some(Ok((
                             normalized,
                             dispatch_missing(entry.state),
                         )));
                     }
                 }
             };
             None
         })
         .flatten()
 }
 
 #[derive(Debug, Copy, Clone)]
 pub struct StatusOptions {
     /// Remember the most recent modification timeslot for status, to make
     /// sure we won't miss future size-preserving file content modifications
     /// that happen within the same timeslot.
     pub last_normal_time: i64,
     /// Whether we are on a filesystem with UNIX-like exec flags
     pub check_exec: bool,
     pub list_clean: bool,
     pub list_unknown: bool,
     pub list_ignored: bool,
 }
 
 /// Dispatch a single entry (file, folder, symlink...) found during `traverse`.
 /// If the entry is a folder that needs to be traversed, it will be handled
 /// in a separate thread.
 
 fn handle_traversed_entry<'a>(
     scope: &rayon::Scope<'a>,
     files_sender: &'a crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'a,
     dmap: &'a DirstateMap,
     old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
-    ignore_fn: &'a (impl for<'r> Fn(&'r HgPath) -> bool + Sync),
-    dir_ignore_fn: &'a (impl for<'r> Fn(&'r HgPath) -> bool + Sync),
+    ignore_fn: &'a IgnoreFnType,
+    dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     filename: HgPathBuf,
     dir_entry: DirEntry,
 ) -> IoResult<()> {
     let file_type = dir_entry.file_type()?;
     let entry_option = dmap.get(&filename);
 
     if file_type.is_dir() {
         handle_traversed_dir(
             scope,
             files_sender,
             matcher,
             root_dir,
             dmap,
             old_results,
             ignore_fn,
             dir_ignore_fn,
             options,
             entry_option,
             filename,
         );
     } else if file_type.is_file() || file_type.is_symlink() {
         if let Some(entry) = entry_option {
             if matcher.matches_everything() || matcher.matches(&filename) {
                 let metadata = dir_entry.metadata()?;
                 files_sender
                     .send(Ok((
                         filename.to_owned(),
                         dispatch_found(
                             &filename,
                             *entry,
                             HgMetadata::from_metadata(metadata),
                             &dmap.copy_map,
                             options,
                         ),
                     )))
                     .unwrap();
             }
         } else if (matcher.matches_everything() || matcher.matches(&filename))
             && !ignore_fn(&filename)
         {
             if (options.list_ignored || matcher.exact_match(&filename))
                 && dir_ignore_fn(&filename)
             {
                 if options.list_ignored {
                     files_sender
                         .send(Ok((filename.to_owned(), Dispatch::Ignored)))
                         .unwrap();
                 }
             } else {
                 files_sender
                     .send(Ok((filename.to_owned(), Dispatch::Unknown)))
                     .unwrap();
             }
         } else if ignore_fn(&filename) && options.list_ignored {
             files_sender
                 .send(Ok((filename.to_owned(), Dispatch::Ignored)))
                 .unwrap();
         }
     } else if let Some(entry) = entry_option {
         // Used to be a file or a folder, now something else.
         if matcher.matches_everything() || matcher.matches(&filename) {
             files_sender
                 .send(Ok((filename.to_owned(), dispatch_missing(entry.state))))
                 .unwrap();
         }
     }
 
     Ok(())
 }
 
 /// A directory was found in the filesystem and needs to be traversed
 fn handle_traversed_dir<'a>(
     scope: &rayon::Scope<'a>,
     files_sender: &'a crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'a,
     dmap: &'a DirstateMap,
     old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
-    ignore_fn: &'a (impl for<'r> Fn(&'r HgPath) -> bool + Sync),
-    dir_ignore_fn: &'a (impl for<'r> Fn(&'r HgPath) -> bool + Sync),
+    ignore_fn: &'a IgnoreFnType,
+    dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     entry_option: Option<&'a DirstateEntry>,
     directory: HgPathBuf,
 ) {
     scope.spawn(move |_| {
         // Nested `if` until `rust-lang/rust#53668` is stable
         if let Some(entry) = entry_option {
             // Used to be a file, is now a folder
             if matcher.matches_everything() || matcher.matches(&directory) {
                 files_sender
                     .send(Ok((
                         directory.to_owned(),
                         dispatch_missing(entry.state),
                     )))
                     .unwrap();
             }
         }
         // Do we need to traverse it?
         if !ignore_fn(&directory) || options.list_ignored {
             traverse_dir(
                 files_sender,
                 matcher,
                 root_dir,
                 dmap,
                 directory,
                 &old_results,
                 ignore_fn,
                 dir_ignore_fn,
                 options,
             )
             .unwrap_or_else(|e| files_sender.send(Err(e)).unwrap())
         }
     });
 }
 
 /// Decides whether the directory needs to be listed, and if so handles the
 /// entries in a separate thread.
 fn traverse_dir<'a>(
     files_sender: &crossbeam::Sender<IoResult<(HgPathBuf, Dispatch)>>,
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     dmap: &'a DirstateMap,
     directory: impl AsRef<HgPath>,
     old_results: &FastHashMap<Cow<'a, HgPath>, Dispatch>,
-    ignore_fn: &(impl for<'r> Fn(&'r HgPath) -> bool + Sync),
-    dir_ignore_fn: &(impl for<'r> Fn(&'r HgPath) -> bool + Sync),
+    ignore_fn: &IgnoreFnType,
+    dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
 ) -> IoResult<()> {
     let directory = directory.as_ref();
     if directory.as_bytes() == b".hg" {
         return Ok(());
     }
     let visit_entries = match matcher.visit_children_set(directory) {
         VisitChildrenSet::Empty => return Ok(()),
         VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
         VisitChildrenSet::Set(set) => Some(set),
     };
     let buf = hg_path_to_path_buf(directory)?;
     let dir_path = root_dir.as_ref().join(buf);
 
     let skip_dot_hg = !directory.as_bytes().is_empty();
     let entries = match list_directory(dir_path, skip_dot_hg) {
         Err(e) => match e.kind() {
             ErrorKind::NotFound | ErrorKind::PermissionDenied => {
                 files_sender
                     .send(Ok((
                         directory.to_owned(),
                         Dispatch::Bad(BadMatch::OsError(
                             // Unwrapping here is OK because the error always
                             // is a real os error
                             e.raw_os_error().unwrap(),
                         )),
                     )))
                     .unwrap();
                 return Ok(());
             }
             _ => return Err(e),
         },
         Ok(entries) => entries,
     };
 
     rayon::scope(|scope| -> IoResult<()> {
         for (filename, dir_entry) in entries {
             if let Some(ref set) = visit_entries {
                 if !set.contains(filename.deref()) {
                     continue;
                 }
             }
             // TODO normalize
             let filename = if directory.is_empty() {
                 filename.to_owned()
             } else {
                 directory.join(&filename)
             };
 
             if !old_results.contains_key(filename.deref()) {
                 handle_traversed_entry(
                     scope,
                     files_sender,
                     matcher,
                     root_dir,
                     dmap,
                     old_results,
                     ignore_fn,
                     dir_ignore_fn,
                     options,
                     filename,
                     dir_entry,
                 )?;
             }
         }
         Ok(())
     })
 }
 
 /// Walk the working directory recursively to look for changes compared to the
 /// current `DirstateMap`.
 ///
 /// This takes a mutable reference to the results to account for the `extend`
 /// in timings
 #[timed]
 fn traverse<'a>(
     matcher: &'a (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     dmap: &'a DirstateMap,
     path: impl AsRef<HgPath>,
     old_results: &FastHashMap<Cow<'a, HgPath>, Dispatch>,
-    ignore_fn: &(impl for<'r> Fn(&'r HgPath) -> bool + Sync),
-    dir_ignore_fn: &(impl for<'r> Fn(&'r HgPath) -> bool + Sync),
+    ignore_fn: &IgnoreFnType,
+    dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) -> IoResult<()> {
     let root_dir = root_dir.as_ref();
 
     // The traversal is done in parallel, so use a channel to gather entries.
     // `crossbeam::Sender` is `Send`, while `mpsc::Sender` is not.
     let (files_transmitter, files_receiver) = crossbeam::channel::unbounded();
 
     traverse_dir(
         &files_transmitter,
         matcher,
         root_dir,
         &dmap,
         path,
         &old_results,
         &ignore_fn,
         &dir_ignore_fn,
         options,
     )?;
 
     // Disconnect the channel so the receiver stops waiting
     drop(files_transmitter);
 
     // TODO don't collect. Find a way of replicating the behavior of
     // `itertools::process_results`, but for `rayon::ParallelIterator`
     let new_results: IoResult<Vec<(Cow<'a, HgPath>, Dispatch)>> =
         files_receiver
             .into_iter()
             .map(|item| {
                 let (f, d) = item?;
                 Ok((Cow::Owned(f), d))
             })
             .collect();
 
     results.par_extend(new_results?);
 
     Ok(())
 }
 
 /// Stat all entries in the `DirstateMap` and mark them for dispatch.
 fn stat_dmap_entries(
     dmap: &DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
     options: StatusOptions,
 ) -> impl ParallelIterator<Item = IoResult<(&HgPath, Dispatch)>> {
     dmap.par_iter().map(move |(filename, entry)| {
         let filename: &HgPath = filename;
         let filename_as_path = hg_path_to_path_buf(filename)?;
         let meta = root_dir.as_ref().join(filename_as_path).symlink_metadata();
 
         match meta {
             Ok(ref m)
                 if !(m.file_type().is_file()
                     || m.file_type().is_symlink()) =>
             {
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Ok(m) => Ok((
                 filename,
                 dispatch_found(
                     filename,
                     *entry,
                     HgMetadata::from_metadata(m),
                     &dmap.copy_map,
                     options,
                 ),
             )),
             Err(ref e)
                 if e.kind() == ErrorKind::NotFound
                     || e.raw_os_error() == Some(20) =>
             {
                 // Rust does not yet have an `ErrorKind` for
                 // `NotADirectory` (errno 20)
                 // It happens if the dirstate contains `foo/bar` and
                 // foo is not a directory
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Err(e) => Err(e),
         }
     })
 }
 
 /// This takes a mutable reference to the results to account for the `extend`
 /// in timings
 #[timed]
 fn extend_from_dmap<'a>(
     dmap: &'a DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) {
     results.par_extend(
         stat_dmap_entries(dmap, root_dir, options)
             .flatten()
             .map(|(filename, dispatch)| (Cow::Borrowed(filename), dispatch)),
     );
 }
 
 #[derive(Debug)]
 pub struct DirstateStatus<'a> {
     pub modified: Vec<Cow<'a, HgPath>>,
     pub added: Vec<Cow<'a, HgPath>>,
     pub removed: Vec<Cow<'a, HgPath>>,
     pub deleted: Vec<Cow<'a, HgPath>>,
     pub clean: Vec<Cow<'a, HgPath>>,
     pub ignored: Vec<Cow<'a, HgPath>>,
     pub unknown: Vec<Cow<'a, HgPath>>,
     pub bad: Vec<(Cow<'a, HgPath>, BadMatch)>,
 }
 
 #[timed]
 fn build_response<'a>(
     results: impl IntoIterator<Item = (Cow<'a, HgPath>, Dispatch)>,
 ) -> (Vec<Cow<'a, HgPath>>, DirstateStatus<'a>) {
     let mut lookup = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
     let mut ignored = vec![];
     let mut unknown = vec![];
     let mut bad = vec![];
 
     for (filename, dispatch) in results.into_iter() {
         match dispatch {
             Dispatch::Unknown => unknown.push(filename),
             Dispatch::Unsure => lookup.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
             Dispatch::Ignored => ignored.push(filename),
             Dispatch::None => {}
             Dispatch::Bad(reason) => bad.push((filename, reason)),
             Dispatch::Directory { .. } => {}
         }
     }
 
     (
         lookup,
         DirstateStatus {
             modified,
             added,
             removed,
             deleted,
             clean,
             ignored,
             unknown,
             bad,
         },
     )
 }
 
 #[derive(Debug)]
 pub enum StatusError {
     IO(std::io::Error),
     Path(HgPathError),
     Pattern(PatternError),
 }
 
 pub type StatusResult<T> = Result<T, StatusError>;
 
 impl From<PatternError> for StatusError {
     fn from(e: PatternError) -> Self {
         StatusError::Pattern(e)
     }
 }
 impl From<HgPathError> for StatusError {
     fn from(e: HgPathError) -> Self {
         StatusError::Path(e)
     }
 }
 impl From<std::io::Error> for StatusError {
     fn from(e: std::io::Error) -> Self {
         StatusError::IO(e)
     }
 }
 
 impl ToString for StatusError {
     fn to_string(&self) -> String {
         match self {
             StatusError::IO(e) => e.to_string(),
             StatusError::Path(e) => e.to_string(),
             StatusError::Pattern(e) => e.to_string(),
         }
     }
 }
 
 /// This takes a mutable reference to the results to account for the `extend`
 /// in timings
 #[timed]
 fn handle_unknowns<'a>(
     dmap: &'a DirstateMap,
     matcher: &(impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
 ) -> IoResult<()> {
     let to_visit: Vec<(&HgPath, &DirstateEntry)> = if results.is_empty()
         && matcher.matches_everything()
     {
         dmap.iter().map(|(f, e)| (f.deref(), e)).collect()
     } else {
         // Only convert to a hashmap if needed.
         let old_results: FastHashMap<_, _> = results.iter().cloned().collect();
         dmap.iter()
             .filter_map(move |(f, e)| {
                 if !old_results.contains_key(f.deref()) && matcher.matches(f) {
                     Some((f.deref(), e))
                 } else {
                     None
                 }
             })
             .collect()
     };
 
     // We walked all dirs under the roots that weren't ignored, and
     // everything that matched was stat'ed and is already in results.
     // The rest must thus be ignored or under a symlink.
     let path_auditor = PathAuditor::new(root_dir);
 
     // TODO don't collect. Find a way of replicating the behavior of
     // `itertools::process_results`, but for `rayon::ParallelIterator`
     let new_results: IoResult<Vec<_>> = to_visit
         .into_par_iter()
         .filter_map(|(filename, entry)| -> Option<IoResult<_>> {
             // Report ignored items in the dmap as long as they are not
             // under a symlink directory.
             if path_auditor.check(filename) {
                 // TODO normalize for case-insensitive filesystems
                 let buf = match hg_path_to_path_buf(filename) {
                     Ok(x) => x,
                     Err(e) => return Some(Err(e.into())),
                 };
                 Some(Ok((
                     Cow::Borrowed(filename),
                     match root_dir.as_ref().join(&buf).symlink_metadata() {
                         // File was just ignored, no links, and exists
                         Ok(meta) => {
                             let metadata = HgMetadata::from_metadata(meta);
                             dispatch_found(
                                 filename,
                                 *entry,
                                 metadata,
                                 &dmap.copy_map,
                                 options,
                             )
                         }
                         // File doesn't exist
                         Err(_) => dispatch_missing(entry.state),
                     },
                 )))
             } else {
                 // It's either missing or under a symlink directory which
                 // we, in this case, report as missing.
                 Some(Ok((
                     Cow::Borrowed(filename),
                     dispatch_missing(entry.state),
                 )))
             }
         })
         .collect();
 
     results.par_extend(new_results?);
 
     Ok(())
 }
 
 /// Get the status of files in the working directory.
 ///
 /// This is the current entry-point for `hg-core` and is realistically unusable
 /// outside of a Python context because its arguments need to provide a lot of
 /// information that will not be necessary in the future.
 #[timed]
 pub fn status<'a: 'c, 'b: 'c, 'c>(
     dmap: &'a DirstateMap,
     matcher: &'b (impl Matcher + Sync),
     root_dir: impl AsRef<Path> + Sync + Send + Copy + 'c,
-    ignore_files: &[impl AsRef<Path> + 'c],
+    ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<Cow<'c, HgPath>>, DirstateStatus<'c>),
     Vec<PatternFileWarning>,
 )> {
-    let (ignore_fn, warnings) = get_ignore_function(&ignore_files, root_dir)?;
+    // Needs to outlive `dir_ignore_fn` since it's captured.
+    let mut ignore_fn: IgnoreFnType;
+
+    // Only involve real ignore mechanism if we're listing unknowns or ignored.
+    let (dir_ignore_fn, warnings): (IgnoreFnType, _) = if options.list_ignored
+        || options.list_unknown
+    {
+        let (ignore, warnings) = get_ignore_function(ignore_files, root_dir)?;
 
-    // Is the path or one of its ancestors ignored?
-    let dir_ignore_fn = |dir: &_| {
-        if ignore_fn(dir) {
-            true
-        } else {
-            for p in find_dirs(dir) {
-                if ignore_fn(p) {
-                    return true;
+        ignore_fn = ignore;
+        let dir_ignore_fn = Box::new(|dir: &_| {
+            // Is the path or one of its ancestors ignored?
+            if ignore_fn(dir) {
+                true
+            } else {
+                for p in find_dirs(dir) {
+                    if ignore_fn(p) {
+                        return true;
+                    }
                 }
+                false
             }
-            false
-        }
+        });
+        (dir_ignore_fn, warnings)
+    } else {
+        ignore_fn = Box::new(|&_| true);
+        (Box::new(|&_| true), vec![])
     };
 
     let files = matcher.file_set();
 
     // Step 1: check the files explicitly mentioned by the user
     let explicit = walk_explicit(files, &dmap, root_dir, options);
 
     // Collect results into a `Vec` because we do very few lookups in most
     // cases.
     let (work, mut results): (Vec<_>, Vec<_>) = explicit
         .filter_map(Result::ok)
         .map(|(filename, dispatch)| (Cow::Borrowed(filename), dispatch))
         .partition(|(_, dispatch)| match dispatch {
             Dispatch::Directory { .. } => true,
             _ => false,
         });
 
     if !work.is_empty() {
         // Hashmaps are quite a bit slower to build than vecs, so only build it
         // if needed.
         let old_results = results.iter().cloned().collect();
 
         // Step 2: recursively check the working directory for changes if
         // needed
         for (dir, dispatch) in work {
             match dispatch {
                 Dispatch::Directory { was_file } => {
                     if was_file {
                         results.push((dir.to_owned(), Dispatch::Removed));
                     }
                     if options.list_ignored
                         || options.list_unknown && !dir_ignore_fn(&dir)
                     {
                         traverse(
                             matcher,
                             root_dir,
                             &dmap,
                             &dir,
                             &old_results,
                             &ignore_fn,
                             &dir_ignore_fn,
                             options,
                             &mut results,
                         )?;
                     }
                 }
                 _ => unreachable!("There can only be directories in `work`"),
             }
         }
     }
 
     if !matcher.is_exact() {
         // Step 3: Check the remaining files from the dmap.
         // If a dmap file is not in results yet, it was either
         // a) not matched b) ignored, c) missing, or d) under a
         // symlink directory.
 
         if options.list_unknown {
             handle_unknowns(dmap, matcher, root_dir, options, &mut results)?;
         } else {
             // We may not have walked the full directory tree above, so stat
             // and check everything we missed.
             extend_from_dmap(&dmap, root_dir, options, &mut results);
         }
     }
 
     Ok((build_response(results), warnings))
 }

rust/hg-core/src/matchers.rs

@@ -1,923 +1,926 b''
 // matchers.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Structs and types for matching files and directories.
 
 #[cfg(feature = "with-re2")]
 use crate::re2::Re2;
 use crate::{
     dirstate::dirs_multiset::DirsChildrenMultiset,
     filepatterns::{
         build_single_regex, filter_subincludes, get_patterns_from_file,
         PatternFileWarning, PatternResult, SubInclude,
     },
     utils::{
         files::find_dirs,
         hg_path::{HgPath, HgPathBuf},
         Escaped,
     },
     DirsMultiset, DirstateMapError, FastHashMap, IgnorePattern, PatternError,
     PatternSyntax,
 };
 
-use micro_timer::timed;
+use std::borrow::ToOwned;
 use std::collections::HashSet;
 use std::fmt::{Display, Error, Formatter};
 use std::iter::FromIterator;
 use std::ops::Deref;
-use std::path::Path;
+use std::path::{Path, PathBuf};
 
 #[derive(Debug, PartialEq)]
 pub enum VisitChildrenSet<'a> {
     /// Don't visit anything
     Empty,
     /// Only visit this directory
     This,
     /// Visit this directory and these subdirectories
     /// TODO Should we implement a `NonEmptyHashSet`?
     Set(HashSet<&'a HgPath>),
     /// Visit this directory and all subdirectories
     Recursive,
 }
 
 pub trait Matcher {
     /// Explicitly listed files
     fn file_set(&self) -> Option<&HashSet<&HgPath>>;
     /// Returns whether `filename` is in `file_set`
     fn exact_match(&self, filename: impl AsRef<HgPath>) -> bool;
     /// Returns whether `filename` is matched by this matcher
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool;
     /// Decides whether a directory should be visited based on whether it
     /// has potential matches in it or one of its subdirectories, and
     /// potentially lists which subdirectories of that directory should be
     /// visited. This is based on the match's primary, included, and excluded
     /// patterns.
     ///
     /// # Example
     ///
     /// Assume matchers `['path:foo/bar', 'rootfilesin:qux']`, we would
     /// return the following values (assuming the implementation of
     /// visit_children_set is capable of recognizing this; some implementations
     /// are not).
     ///
     /// ```text
     /// ```ignore
     /// '' -> {'foo', 'qux'}
     /// 'baz' -> set()
     /// 'foo' -> {'bar'}
     /// // Ideally this would be `Recursive`, but since the prefix nature of
     /// // matchers is applied to the entire matcher, we have to downgrade this
     /// // to `This` due to the (yet to be implemented in Rust) non-prefix
     /// // `RootFilesIn'-kind matcher being mixed in.
     /// 'foo/bar' -> 'this'
     /// 'qux' -> 'this'
     /// ```
     /// # Important
     ///
     /// Most matchers do not know if they're representing files or
     /// directories. They see `['path:dir/f']` and don't know whether `f` is a
     /// file or a directory, so `visit_children_set('dir')` for most matchers
     /// will return `HashSet{ HgPath { "f" } }`, but if the matcher knows it's
     /// a file (like the yet to be implemented in Rust `ExactMatcher` does),
     /// it may return `VisitChildrenSet::This`.
     /// Do not rely on the return being a `HashSet` indicating that there are
     /// no files in this dir to investigate (or equivalently that if there are
     /// files to investigate in 'dir' that it will always return
     /// `VisitChildrenSet::This`).
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet;
     /// Matcher will match everything and `files_set()` will be empty:
     /// optimization might be possible.
     fn matches_everything(&self) -> bool;
     /// Matcher will match exactly the files in `files_set()`: optimization
     /// might be possible.
     fn is_exact(&self) -> bool;
 }
 
 /// Matches everything.
 ///```
 /// use hg::{ matchers::{Matcher, AlwaysMatcher}, utils::hg_path::HgPath };
 ///
 /// let matcher = AlwaysMatcher;
 ///
 /// assert_eq!(matcher.matches(HgPath::new(b"whatever")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"b.txt")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"main.c")), true);
 /// assert_eq!(matcher.matches(HgPath::new(br"re:.*\.c$")), true);
 /// ```
 #[derive(Debug)]
 pub struct AlwaysMatcher;
 
 impl Matcher for AlwaysMatcher {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         None
     }
     fn exact_match(&self, _filename: impl AsRef<HgPath>) -> bool {
         false
     }
     fn matches(&self, _filename: impl AsRef<HgPath>) -> bool {
         true
     }
     fn visit_children_set(
         &self,
         _directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         VisitChildrenSet::Recursive
     }
     fn matches_everything(&self) -> bool {
         true
     }
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 /// Matches the input files exactly. They are interpreted as paths, not
 /// patterns.
 ///
 ///```
 /// use hg::{ matchers::{Matcher, FileMatcher}, utils::hg_path::HgPath };
 ///
 /// let files = [HgPath::new(b"a.txt"), HgPath::new(br"re:.*\.c$")];
 /// let matcher = FileMatcher::new(&files).unwrap();
 ///
 /// assert_eq!(matcher.matches(HgPath::new(b"a.txt")), true);
 /// assert_eq!(matcher.matches(HgPath::new(b"b.txt")), false);
 /// assert_eq!(matcher.matches(HgPath::new(b"main.c")), false);
 /// assert_eq!(matcher.matches(HgPath::new(br"re:.*\.c$")), true);
 /// ```
 #[derive(Debug)]
 pub struct FileMatcher<'a> {
     files: HashSet<&'a HgPath>,
     dirs: DirsMultiset,
 }
 
 impl<'a> FileMatcher<'a> {
     pub fn new(
         files: &'a [impl AsRef<HgPath>],
     ) -> Result<Self, DirstateMapError> {
         Ok(Self {
             files: HashSet::from_iter(files.iter().map(|f| f.as_ref())),
             dirs: DirsMultiset::from_manifest(files)?,
         })
     }
     fn inner_matches(&self, filename: impl AsRef<HgPath>) -> bool {
         self.files.contains(filename.as_ref())
     }
 }
 
 impl<'a> Matcher for FileMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         Some(&self.files)
     }
     fn exact_match(&self, filename: impl AsRef<HgPath>) -> bool {
         self.inner_matches(filename)
     }
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool {
         self.inner_matches(filename)
     }
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         if self.files.is_empty() || !self.dirs.contains(&directory) {
             return VisitChildrenSet::Empty;
         }
         let dirs_as_set = self.dirs.iter().map(|k| k.deref()).collect();
 
         let mut candidates: HashSet<&HgPath> =
             self.files.union(&dirs_as_set).map(|k| *k).collect();
         candidates.remove(HgPath::new(b""));
 
         if !directory.as_ref().is_empty() {
             let directory = [directory.as_ref().as_bytes(), b"/"].concat();
             candidates = candidates
                 .iter()
                 .filter_map(|c| {
                     if c.as_bytes().starts_with(&directory) {
                         Some(HgPath::new(&c.as_bytes()[directory.len()..]))
                     } else {
                         None
                     }
                 })
                 .collect();
         }
 
         // `self.dirs` includes all of the directories, recursively, so if
         // we're attempting to match 'foo/bar/baz.txt', it'll have '', 'foo',
         // 'foo/bar' in it. Thus we can safely ignore a candidate that has a
         // '/' in it, indicating it's for a subdir-of-a-subdir; the immediate
         // subdir will be in there without a slash.
         VisitChildrenSet::Set(
             candidates
                 .iter()
                 .filter_map(|c| {
                     if c.bytes().all(|b| *b != b'/') {
                         Some(*c)
                     } else {
                         None
                     }
                 })
                 .collect(),
         )
     }
     fn matches_everything(&self) -> bool {
         false
     }
     fn is_exact(&self) -> bool {
         true
     }
 }
 
 /// Matches files that are included in the ignore rules.
 #[cfg_attr(
     feature = "with-re2",
     doc = r##"
 ```
 use hg::{
     matchers::{IncludeMatcher, Matcher},
     IgnorePattern,
     PatternSyntax,
     utils::hg_path::HgPath
 };
 use std::path::Path;
 ///
 let ignore_patterns =
 vec![IgnorePattern::new(PatternSyntax::RootGlob, b"this*", Path::new(""))];
 let (matcher, _) = IncludeMatcher::new(ignore_patterns, "").unwrap();
 ///
 assert_eq!(matcher.matches(HgPath::new(b"testing")), false);
 assert_eq!(matcher.matches(HgPath::new(b"this should work")), true);
 assert_eq!(matcher.matches(HgPath::new(b"this also")), true);
 assert_eq!(matcher.matches(HgPath::new(b"but not this")), false);
 ```
 "##
 )]
 pub struct IncludeMatcher<'a> {
     patterns: Vec<u8>,
     match_fn: Box<dyn for<'r> Fn(&'r HgPath) -> bool + 'a + Sync>,
     /// Whether all the patterns match a prefix (i.e. recursively)
     prefix: bool,
     roots: HashSet<HgPathBuf>,
     dirs: HashSet<HgPathBuf>,
     parents: HashSet<HgPathBuf>,
 }
 
 impl<'a> Matcher for IncludeMatcher<'a> {
     fn file_set(&self) -> Option<&HashSet<&HgPath>> {
         None
     }
 
     fn exact_match(&self, _filename: impl AsRef<HgPath>) -> bool {
         false
     }
 
     fn matches(&self, filename: impl AsRef<HgPath>) -> bool {
         (self.match_fn)(filename.as_ref())
     }
 
     fn visit_children_set(
         &self,
         directory: impl AsRef<HgPath>,
     ) -> VisitChildrenSet {
         let dir = directory.as_ref();
         if self.prefix && self.roots.contains(dir) {
             return VisitChildrenSet::Recursive;
         }
         if self.roots.contains(HgPath::new(b""))
             || self.roots.contains(dir)
             || self.dirs.contains(dir)
             || find_dirs(dir).any(|parent_dir| self.roots.contains(parent_dir))
         {
             return VisitChildrenSet::This;
         }
 
         if self.parents.contains(directory.as_ref()) {
             let multiset = self.get_all_parents_children();
             if let Some(children) = multiset.get(dir) {
                 return VisitChildrenSet::Set(children.to_owned());
             }
         }
         VisitChildrenSet::Empty
     }
 
     fn matches_everything(&self) -> bool {
         false
     }
 
     fn is_exact(&self) -> bool {
         false
     }
 }
 
 #[cfg(feature = "with-re2")]
 /// Returns a function that matches an `HgPath` against the given regex
 /// pattern.
 ///
 /// This can fail when the pattern is invalid or not supported by the
 /// underlying engine `Re2`, for instance anything with back-references.
 fn re_matcher(
     pattern: &[u8],
 ) -> PatternResult<impl Fn(&HgPath) -> bool + Sync> {
     let regex = Re2::new(pattern);
     let regex = regex.map_err(|e| PatternError::UnsupportedSyntax(e))?;
     Ok(move |path: &HgPath| regex.is_match(path.as_bytes()))
 }
 
 #[cfg(not(feature = "with-re2"))]
 /// 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.
 fn re_matcher(
     pattern: &[u8],
 ) -> PatternResult<impl Fn(&HgPath) -> bool + Sync> {
     use std::io::Write;
 
     let mut escaped_bytes = vec![];
     for byte in pattern {
         if *byte > 127 {
             write!(escaped_bytes, "\\x{:x}", *byte).unwrap();
         } else {
             escaped_bytes.push(*byte);
         }
     }
 
     // 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) };
     let re = regex::bytes::RegexBuilder::new(&pattern_string)
         .unicode(false)
         .build()
         .map_err(|e| PatternError::UnsupportedSyntax(e.to_string()))?;
 
     Ok(move |path: &HgPath| re.is_match(path.as_bytes()))
 }
 
 /// Returns the regex pattern and a function that matches an `HgPath` against
 /// said regex formed by the given ignore patterns.
 fn build_regex_match<'a>(
     ignore_patterns: &'a [&'a IgnorePattern],
 ) -> PatternResult<(Vec<u8>, Box<dyn Fn(&HgPath) -> bool + Sync>)> {
     let regexps: Result<Vec<_>, PatternError> = ignore_patterns
         .into_iter()
         .map(|k| build_single_regex(*k))
         .collect();
     let regexps = regexps?;
     let full_regex = regexps.join(&b'|');
 
     let matcher = re_matcher(&full_regex)?;
     let func = Box::new(move |filename: &HgPath| matcher(filename));
 
     Ok((full_regex, func))
 }
 
 /// Returns roots and directories corresponding to each pattern.
 ///
 /// This calculates the roots and directories exactly matching the patterns and
 /// returns a tuple of (roots, dirs). It does not return other directories
 /// which may also need to be considered, like the parent directories.
 fn roots_and_dirs(
     ignore_patterns: &[IgnorePattern],
 ) -> (Vec<HgPathBuf>, Vec<HgPathBuf>) {
     let mut roots = Vec::new();
     let mut dirs = Vec::new();
 
     for ignore_pattern in ignore_patterns {
         let IgnorePattern {
             syntax, pattern, ..
         } = ignore_pattern;
         match syntax {
             PatternSyntax::RootGlob | PatternSyntax::Glob => {
                 let mut root = vec![];
 
                 for p in pattern.split(|c| *c == b'/') {
                     if p.iter().any(|c| match *c {
                         b'[' | b'{' | b'*' | b'?' => true,
                         _ => false,
                     }) {
                         break;
                     }
                     root.push(HgPathBuf::from_bytes(p));
                 }
                 let buf =
                     root.iter().fold(HgPathBuf::new(), |acc, r| acc.join(r));
                 roots.push(buf);
             }
             PatternSyntax::Path | PatternSyntax::RelPath => {
                 let pat = HgPath::new(if pattern == b"." {
                     &[] as &[u8]
                 } else {
                     pattern
                 });
                 roots.push(pat.to_owned());
             }
             PatternSyntax::RootFiles => {
                 let pat = if pattern == b"." {
                     &[] as &[u8]
                 } else {
                     pattern
                 };
                 dirs.push(HgPathBuf::from_bytes(pat));
             }
             _ => {
                 roots.push(HgPathBuf::new());
             }
         }
     }
     (roots, dirs)
 }
 
 /// Paths extracted from patterns
 #[derive(Debug, PartialEq)]
 struct RootsDirsAndParents {
     /// Directories to match recursively
     pub roots: HashSet<HgPathBuf>,
     /// Directories to match non-recursively
     pub dirs: HashSet<HgPathBuf>,
     /// Implicitly required directories to go to items in either roots or dirs
     pub parents: HashSet<HgPathBuf>,
 }
 
 /// Extract roots, dirs and parents from patterns.
 fn roots_dirs_and_parents(
     ignore_patterns: &[IgnorePattern],
 ) -> PatternResult<RootsDirsAndParents> {
     let (roots, dirs) = roots_and_dirs(ignore_patterns);
 
     let mut parents = HashSet::new();
 
     parents.extend(
         DirsMultiset::from_manifest(&dirs)
             .map_err(|e| match e {
                 DirstateMapError::InvalidPath(e) => e,
                 _ => unreachable!(),
             })?
             .iter()
             .map(|k| k.to_owned()),
     );
     parents.extend(
         DirsMultiset::from_manifest(&roots)
             .map_err(|e| match e {
                 DirstateMapError::InvalidPath(e) => e,
                 _ => unreachable!(),
             })?
             .iter()
             .map(|k| k.to_owned()),
     );
 
     Ok(RootsDirsAndParents {
         roots: HashSet::from_iter(roots),
         dirs: HashSet::from_iter(dirs),
         parents,
     })
 }
 
 /// Returns a function that checks whether a given file (in the general sense)
 /// should be matched.
 fn build_match<'a, 'b>(
     ignore_patterns: &'a [IgnorePattern],
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(
     Vec<u8>,
     Box<dyn Fn(&HgPath) -> bool + 'b + Sync>,
     Vec<PatternFileWarning>,
 )> {
     let mut match_funcs: Vec<Box<dyn Fn(&HgPath) -> bool + Sync>> = vec![];
     // For debugging and printing
     let mut patterns = vec![];
     let mut all_warnings = vec![];
 
     let (subincludes, ignore_patterns) =
         filter_subincludes(ignore_patterns, root_dir)?;
 
     if !subincludes.is_empty() {
         // Build prefix-based matcher functions for subincludes
         let mut submatchers = FastHashMap::default();
         let mut prefixes = vec![];
 
         for SubInclude { prefix, root, path } in subincludes.into_iter() {
-            let (match_fn, warnings) = get_ignore_function(&[path], root)?;
+            let (match_fn, warnings) =
+                get_ignore_function(vec![path.to_path_buf()], root)?;
             all_warnings.extend(warnings);
             prefixes.push(prefix.to_owned());
             submatchers.insert(prefix.to_owned(), match_fn);
         }
 
         let match_subinclude = move |filename: &HgPath| {
             for prefix in prefixes.iter() {
                 if let Some(rel) = filename.relative_to(prefix) {
                     if (submatchers.get(prefix).unwrap())(rel) {
                         return true;
                     }
                 }
             }
             false
         };
 
         match_funcs.push(Box::new(match_subinclude));
     }
 
     if !ignore_patterns.is_empty() {
         // Either do dumb matching if all patterns are rootfiles, or match
         // with a regex.
         if ignore_patterns
             .iter()
             .all(|k| k.syntax == PatternSyntax::RootFiles)
         {
             let dirs: HashSet<_> = ignore_patterns
                 .iter()
                 .map(|k| k.pattern.to_owned())
                 .collect();
             let mut dirs_vec: Vec<_> = dirs.iter().cloned().collect();
 
             let match_func = move |path: &HgPath| -> bool {
                 let path = path.as_bytes();
                 let i = path.iter().rfind(|a| **a == b'/');
                 let dir = if let Some(i) = i {
                     &path[..*i as usize]
                 } else {
                     b"."
                 };
                 dirs.contains(dir.deref())
             };
             match_funcs.push(Box::new(match_func));
 
             patterns.extend(b"rootfilesin: ");
             dirs_vec.sort();
             patterns.extend(dirs_vec.escaped_bytes());
         } else {
             let (new_re, match_func) = build_regex_match(&ignore_patterns)?;
             patterns = new_re;
             match_funcs.push(match_func)
         }
     }
 
     Ok(if match_funcs.len() == 1 {
         (patterns, match_funcs.remove(0), all_warnings)
     } else {
         (
             patterns,
             Box::new(move |f: &HgPath| -> bool {
                 match_funcs.iter().any(|match_func| match_func(f))
             }),
             all_warnings,
         )
     })
 }
 
 /// Parses all "ignore" files with their recursive includes and returns a
 /// function that checks whether a given file (in the general sense) should be
 /// ignored.
-#[timed]
 pub fn get_ignore_function<'a>(
-    all_pattern_files: &[impl AsRef<Path>],
+    all_pattern_files: Vec<PathBuf>,
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(
-    impl for<'r> Fn(&'r HgPath) -> bool + Sync,
+    Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>,
     Vec<PatternFileWarning>,
 )> {
     let mut all_patterns = vec![];
     let mut all_warnings = vec![];
 
     for pattern_file in all_pattern_files.into_iter() {
         let (patterns, warnings) =
             get_patterns_from_file(pattern_file, &root_dir)?;
 
-        all_patterns.extend(patterns);
+        all_patterns.extend(patterns.to_owned());
         all_warnings.extend(warnings);
     }
     let (matcher, warnings) = IncludeMatcher::new(all_patterns, root_dir)?;
     all_warnings.extend(warnings);
-    Ok((move |path: &HgPath| matcher.matches(path), all_warnings))
+    Ok((
+        Box::new(move |path: &HgPath| matcher.matches(path)),
+        all_warnings,
+    ))
 }
 
 impl<'a> IncludeMatcher<'a> {
     pub fn new(
         ignore_patterns: Vec<IgnorePattern>,
         root_dir: impl AsRef<Path>,
     ) -> PatternResult<(Self, Vec<PatternFileWarning>)> {
         let (patterns, match_fn, warnings) =
             build_match(&ignore_patterns, root_dir)?;
         let RootsDirsAndParents {
             roots,
             dirs,
             parents,
         } = roots_dirs_and_parents(&ignore_patterns)?;
 
         let prefix = ignore_patterns.iter().any(|k| match k.syntax {
             PatternSyntax::Path | PatternSyntax::RelPath => true,
             _ => false,
         });
 
         Ok((
             Self {
                 patterns,
                 match_fn,
                 prefix,
                 roots,
                 dirs,
                 parents,
             },
             warnings,
         ))
     }
 
     fn get_all_parents_children(&self) -> DirsChildrenMultiset {
         // TODO cache
         let thing = self
             .dirs
             .iter()
             .chain(self.roots.iter())
             .chain(self.parents.iter());
         DirsChildrenMultiset::new(thing, Some(&self.parents))
     }
 }
 
 impl<'a> Display for IncludeMatcher<'a> {
     fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error> {
         write!(
             f,
             "IncludeMatcher(includes='{}')",
             String::from_utf8_lossy(&self.patterns.escaped_bytes())
         )
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
     use std::path::Path;
 
     #[test]
     fn test_roots_and_dirs() {
         let pats = vec![
             IgnorePattern::new(PatternSyntax::Glob, b"g/h/*", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g/h", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g*", Path::new("")),
         ];
         let (roots, dirs) = roots_and_dirs(&pats);
 
         assert_eq!(
             roots,
             vec!(
                 HgPathBuf::from_bytes(b"g/h"),
                 HgPathBuf::from_bytes(b"g/h"),
                 HgPathBuf::new()
             ),
         );
         assert_eq!(dirs, vec!());
     }
 
     #[test]
     fn test_roots_dirs_and_parents() {
         let pats = vec![
             IgnorePattern::new(PatternSyntax::Glob, b"g/h/*", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g/h", Path::new("")),
             IgnorePattern::new(PatternSyntax::Glob, b"g*", Path::new("")),
         ];
 
         let mut roots = HashSet::new();
         roots.insert(HgPathBuf::from_bytes(b"g/h"));
         roots.insert(HgPathBuf::new());
 
         let dirs = HashSet::new();
 
         let mut parents = HashSet::new();
         parents.insert(HgPathBuf::new());
         parents.insert(HgPathBuf::from_bytes(b"g"));
 
         assert_eq!(
             roots_dirs_and_parents(&pats).unwrap(),
             RootsDirsAndParents {
                 roots,
                 dirs,
                 parents
             }
         );
     }
 
     #[test]
     fn test_filematcher_visit_children_set() {
         // Visitchildrenset
         let files = vec![HgPath::new(b"dir/subdir/foo.txt")];
         let matcher = FileMatcher::new(&files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"foo.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/foo.txt")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
     }
 
     #[test]
     fn test_filematcher_visit_children_set_files_and_dirs() {
         let files = vec![
             HgPath::new(b"rootfile.txt"),
             HgPath::new(b"a/file1.txt"),
             HgPath::new(b"a/b/file2.txt"),
             // No file in a/b/c
             HgPath::new(b"a/b/c/d/file4.txt"),
         ];
         let matcher = FileMatcher::new(&files).unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"a"));
         set.insert(HgPath::new(b"rootfile.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"b"));
         set.insert(HgPath::new(b"file1.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"c"));
         set.insert(HgPath::new(b"file2.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"d"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c")),
             VisitChildrenSet::Set(set)
         );
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"file4.txt"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c/d")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"a/b/c/d/e")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
     }
 
     #[cfg(feature = "with-re2")]
     #[test]
     fn test_includematcher() {
         // VisitchildrensetPrefix
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::RelPath,
                 b"dir/subdir",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::Recursive
         );
         // OPT: This should probably be 'all' if its parent is?
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetRootfilesin
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::RootFiles,
                 b"dir/subdir",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"subdir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::Set(set)
         );
 
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
 
         // VisitchildrensetGlob
         let (matcher, _) = IncludeMatcher::new(
             vec![IgnorePattern::new(
                 PatternSyntax::Glob,
                 b"dir/z*",
                 Path::new(""),
             )],
             "",
         )
         .unwrap();
 
         let mut set = HashSet::new();
         set.insert(HgPath::new(b"dir"));
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"")),
             VisitChildrenSet::Set(set)
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"folder")),
             VisitChildrenSet::Empty
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir")),
             VisitChildrenSet::This
         );
         // OPT: these should probably be set().
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir")),
             VisitChildrenSet::This
         );
         assert_eq!(
             matcher.visit_children_set(HgPath::new(b"dir/subdir/x")),
             VisitChildrenSet::This
         );
     }
 }

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

@@ -1,297 +1,297 b''
 // status.rs
 //
 // Copyright 2019, Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::status` module provided by the
 //! `hg-core` crate. From Python, this will be seen as
 //! `rustext.dirstate.status`.
 
 use crate::{dirstate::DirstateMap, exceptions::FallbackError};
 use cpython::{
     exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
     PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::{
     matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
     parse_pattern_syntax, status,
     utils::{
         files::{get_bytes_from_path, get_path_from_bytes},
         hg_path::{HgPath, HgPathBuf},
     },
     BadMatch, DirstateStatus, IgnorePattern, PatternFileWarning, StatusError,
     StatusOptions,
 };
 use std::borrow::{Borrow, Cow};
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list(
     py: Python,
     collection: &[impl AsRef<HgPath>],
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for path in collection.iter() {
         list.append(
             py,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 fn collect_bad_matches(
     py: Python,
     collection: &[(impl AsRef<HgPath>, BadMatch)],
 ) -> PyResult<PyList> {
     let list = PyList::new(py, &[]);
 
     let os = py.import("os")?;
     let get_error_message = |code: i32| -> PyResult<_> {
         os.call(
             py,
             "strerror",
             PyTuple::new(py, &[code.to_py_object(py).into_object()]),
             None,
         )
     };
 
     for (path, bad_match) in collection.iter() {
         let message = match bad_match {
             BadMatch::OsError(code) => get_error_message(*code)?,
             BadMatch::BadType(bad_type) => format!(
                 "unsupported file type (type is {})",
                 bad_type.to_string()
             )
             .to_py_object(py)
             .into_object(),
         };
         list.append(
             py,
             (PyBytes::new(py, path.as_ref().as_bytes()), message)
                 .to_py_object(py)
                 .into_object(),
         )
     }
 
     Ok(list)
 }
 
 fn handle_fallback(py: Python, err: StatusError) -> PyErr {
     match err {
         StatusError::Pattern(e) => {
             let as_string = e.to_string();
             log::trace!("Rust status fallback: `{}`", &as_string);
 
             PyErr::new::<FallbackError, _>(py, &as_string)
         }
         e => PyErr::new::<ValueError, _>(py, e.to_string()),
     }
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
     ignore_files: PyList,
     check_exec: bool,
     last_normal_time: i64,
     list_clean: bool,
     list_ignored: bool,
     list_unknown: bool,
 ) -> PyResult<PyTuple> {
     let bytes = root_dir.extract::<PyBytes>(py)?;
     let root_dir = get_path_from_bytes(bytes.data(py));
 
     let dmap: DirstateMap = dmap.to_py_object(py);
     let dmap = dmap.get_inner(py);
 
     let ignore_files: PyResult<Vec<_>> = ignore_files
         .iter(py)
         .map(|b| {
             let file = b.extract::<PyBytes>(py)?;
             Ok(get_path_from_bytes(file.data(py)).to_owned())
         })
         .collect();
     let ignore_files = ignore_files?;
 
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => {
             let matcher = AlwaysMatcher;
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 &root_dir,
-                &ignore_files,
+                ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
             build_response(py, lookup, status_res, warnings)
         }
         "exactmatcher" => {
             let files = matcher.call_method(
                 py,
                 "files",
                 PyTuple::new(py, &[]),
                 None,
             )?;
             let files: PyList = files.cast_into(py)?;
             let files: PyResult<Vec<HgPathBuf>> = files
                 .iter(py)
                 .map(|f| {
                     Ok(HgPathBuf::from_bytes(
                         f.extract::<PyBytes>(py)?.data(py),
                     ))
                 })
                 .collect();
 
             let files = files?;
             let matcher = FileMatcher::new(&files)
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 &root_dir,
-                &ignore_files,
+                ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
             build_response(py, lookup, status_res, warnings)
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
             // redundant with those we will parse later on, as they include
             // those passed from the command line.
             let ignore_patterns: PyResult<Vec<_>> = matcher
                 .getattr(py, "_kindpats")?
                 .iter(py)?
                 .map(|k| {
                     let k = k?;
                     let syntax = parse_pattern_syntax(
                         &[
                             k.get_item(py, 0)?
                                 .extract::<PyBytes>(py)?
                                 .data(py),
                             &b":"[..],
                         ]
                         .concat(),
                     )
                     .map_err(|e| {
                         handle_fallback(py, StatusError::Pattern(e))
                     })?;
                     let pattern = k.get_item(py, 1)?.extract::<PyBytes>(py)?;
                     let pattern = pattern.data(py);
                     let source = k.get_item(py, 2)?.extract::<PyBytes>(py)?;
                     let source = get_path_from_bytes(source.data(py));
                     let new = IgnorePattern::new(syntax, pattern, source);
                     Ok(new)
                 })
                 .collect();
 
             let ignore_patterns = ignore_patterns?;
             let mut all_warnings = vec![];
 
             let (matcher, warnings) =
                 IncludeMatcher::new(ignore_patterns, &root_dir)
                     .map_err(|e| handle_fallback(py, e.into()))?;
             all_warnings.extend(warnings);
 
             let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 &root_dir,
-                &ignore_files,
+                ignore_files,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                 },
             )
             .map_err(|e| handle_fallback(py, e))?;
 
             all_warnings.extend(warnings);
 
             build_response(py, lookup, status_res, all_warnings)
         }
         e => {
             return Err(PyErr::new::<ValueError, _>(
                 py,
                 format!("Unsupported matcher {}", e),
             ));
         }
     }
 }
 
 fn build_response(
     py: Python,
     lookup: Vec<Cow<HgPath>>,
     status_res: DirstateStatus,
     warnings: Vec<PatternFileWarning>,
 ) -> PyResult<PyTuple> {
     let modified = collect_pybytes_list(py, status_res.modified.as_ref());
     let added = collect_pybytes_list(py, status_res.added.as_ref());
     let removed = collect_pybytes_list(py, status_res.removed.as_ref());
     let deleted = collect_pybytes_list(py, status_res.deleted.as_ref());
     let clean = collect_pybytes_list(py, status_res.clean.as_ref());
     let ignored = collect_pybytes_list(py, status_res.ignored.as_ref());
     let unknown = collect_pybytes_list(py, status_res.unknown.as_ref());
     let lookup = collect_pybytes_list(py, lookup.as_ref());
     let bad = collect_bad_matches(py, status_res.bad.as_ref())?;
     let py_warnings = PyList::new(py, &[]);
     for warning in warnings.iter() {
         // We use duck-typing on the Python side for dispatch, good enough for
         // now.
         match warning {
             PatternFileWarning::InvalidSyntax(file, syn) => {
                 py_warnings.append(
                     py,
                     (
                         PyBytes::new(py, &get_bytes_from_path(&file)),
                         PyBytes::new(py, syn),
                     )
                         .to_py_object(py)
                         .into_object(),
                 );
             }
             PatternFileWarning::NoSuchFile(file) => py_warnings.append(
                 py,
                 PyBytes::new(py, &get_bytes_from_path(&file)).into_object(),
             ),
         }
     }
 
     Ok(PyTuple::new(
         py,
         &[
             lookup.into_object(),
             modified.into_object(),
             added.into_object(),
             removed.into_object(),
             deleted.into_object(),
             clean.into_object(),
             ignored.into_object(),
             unknown.into_object(),
             py_warnings.into_object(),
             bad.into_object(),
         ][..],
     ))
 }