rust-status: update rust-cpython bridge to account for the changes in core

Differential Revision: https://phab.mercurial-scm.org/D7930

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

@@ -1,756 +1,770
 // 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 rayon::prelude::*;
 use std::collections::VecDeque;
 use std::{
     borrow::Cow,
     collections::HashSet,
     fs::{read_dir, DirEntry},
     io::ErrorKind,
     ops::Deref,
     path::Path,
 };
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug)]
 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)]
 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)]
 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>;
 
 /// 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
 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 file found during `traverse`.
 /// If `file` is a folder that needs to be traversed, it will be pushed into
 /// `work`.
 fn traverse_worker<'a>(
     work: &mut VecDeque<HgPathBuf>,
     matcher: &impl Matcher,
     dmap: &DirstateMap,
     filename: impl AsRef<HgPath>,
     dir_entry: &DirEntry,
     ignore_fn: &impl for<'r> Fn(&'r HgPath) -> bool,
     dir_ignore_fn: &impl for<'r> Fn(&'r HgPath) -> bool,
     options: StatusOptions,
 ) -> Option<IoResult<(Cow<'a, HgPath>, Dispatch)>> {
     let file_type = match dir_entry.file_type() {
         Ok(x) => x,
         Err(e) => return Some(Err(e.into())),
     };
     let filename = filename.as_ref();
     let entry_option = dmap.get(filename);
 
     if file_type.is_dir() {
         // Do we need to traverse it?
         if !ignore_fn(&filename) || options.list_ignored {
             work.push_front(filename.to_owned());
         }
         // 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(&filename) {
                 return Some(Ok((
                     Cow::Owned(filename.to_owned()),
                     dispatch_missing(entry.state),
                 )));
             }
         }
     } 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 = match dir_entry.metadata() {
                     Ok(x) => x,
                     Err(e) => return Some(Err(e.into())),
                 };
                 return Some(Ok((
                     Cow::Owned(filename.to_owned()),
                     dispatch_found(
                         &filename,
                         *entry,
                         HgMetadata::from_metadata(metadata),
                         &dmap.copy_map,
                         options,
                     ),
                 )));
             }
         } 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 {
                     return Some(Ok((
                         Cow::Owned(filename.to_owned()),
                         Dispatch::Ignored,
                     )));
                 }
             } else {
                 return Some(Ok((
                     Cow::Owned(filename.to_owned()),
                     Dispatch::Unknown,
                 )));
             }
         }
     } 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) {
             return Some(Ok((
                 Cow::Owned(filename.to_owned()),
                 dispatch_missing(entry.state),
             )));
         }
     }
     None
 }
 
 /// Walk the working directory recursively to look for changes compared to the
 /// current `DirstateMap`.
 fn traverse<'a>(
     matcher: &(impl Matcher + Sync),
     root_dir: impl AsRef<Path>,
     dmap: &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),
     options: StatusOptions,
 ) -> IoResult<FastHashMap<Cow<'a, HgPath>, Dispatch>> {
     let root_dir = root_dir.as_ref();
     let mut new_results = FastHashMap::default();
 
     let mut work = VecDeque::new();
     work.push_front(path.as_ref().to_owned());
 
     while let Some(ref directory) = work.pop_front() {
         if directory.as_bytes() == b".hg" {
             continue;
         }
         let visit_entries = match matcher.visit_children_set(directory) {
             VisitChildrenSet::Empty => continue,
             VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
             VisitChildrenSet::Set(set) => Some(set),
         };
         let buf = hg_path_to_path_buf(directory)?;
         let dir_path = root_dir.join(buf);
 
         let skip_dot_hg = !directory.as_bytes().is_empty();
         let entries = match list_directory(dir_path, skip_dot_hg) {
             Err(e) => match e.kind() {
                 ErrorKind::NotFound | ErrorKind::PermissionDenied => {
                     new_results.insert(
                         Cow::Owned(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(),
                         )),
                     );
                     continue;
                 }
                 _ => return Err(e),
             },
             Ok(entries) => entries,
         };
 
         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()) {
                 if let Some((res, dispatch)) = traverse_worker(
                     &mut work,
                     matcher,
                     &dmap,
                     &filename,
                     &dir_entry,
                     &ignore_fn,
                     &dir_ignore_fn,
                     options,
                 )
                 .transpose()?
                 {
                     new_results.insert(res, dispatch);
                 }
             }
         }
     }
 
     new_results.extend(old_results.into_iter());
 
     Ok(new_results)
 }
 
 /// 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),
         }
     })
 }
 
 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)>,
 }
 
 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,
         },
     )
 }
 
 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(),
         }
     }
 }
 
 /// 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.
 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],
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<Cow<'c, HgPath>>, DirstateStatus<'c>),
     Vec<PatternFileWarning>,
 )> {
     let (ignore_fn, 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;
                 }
             }
             false
         }
     };
 
     let files = matcher.file_set();
 
     // Step 1: check the files explicitly mentioned by the user
     let explicit = walk_explicit(files, &dmap, root_dir, options);
     let (work, mut results): (Vec<_>, FastHashMap<_, _>) = explicit
         .filter_map(Result::ok)
         .map(|(filename, dispatch)| (Cow::Borrowed(filename), dispatch))
         .partition(|(_, dispatch)| match dispatch {
             Dispatch::Directory { .. } => true,
             _ => false,
         });
 
     // 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.insert(dir.to_owned(), Dispatch::Removed);
                 }
                 if options.list_ignored
                     || options.list_unknown && !dir_ignore_fn(&dir)
                 {
                     results = traverse(
                         matcher,
                         root_dir,
                         &dmap,
                         &dir,
                         results,
                         &ignore_fn,
                         &dir_ignore_fn,
                         options,
                     )?;
                 }
             }
             _ => 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 {
             let to_visit: Box<dyn Iterator<Item = (&HgPath, &DirstateEntry)>> =
                 if results.is_empty() && matcher.matches_everything() {
                     Box::new(dmap.iter().map(|(f, e)| (f.deref(), e)))
                 } else {
                     Box::new(dmap.iter().filter_map(|(f, e)| {
                         if !results.contains_key(f.deref())
                             && matcher.matches(f)
                         {
                             Some((f.deref(), e))
                         } else {
                             None
                         }
                     }))
                 };
             let mut to_visit: Vec<_> = to_visit.collect();
             to_visit.sort_by(|a, b| a.0.cmp(&b.0));
 
             // 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 mut path_auditor = PathAuditor::new(root_dir);
 
             for (ref filename, entry) in to_visit {
                 // 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 = hg_path_to_path_buf(filename)?;
                     results.insert(
                         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.
                     results.insert(
                         Cow::Borrowed(filename),
                         dispatch_missing(entry.state),
                     );
                 }
             }
         } else {
             // We may not have walked the full directory tree above, so stat
             // and check everything we missed.
             let stat_results = stat_dmap_entries(&dmap, root_dir, options);
             results.par_extend(stat_results.flatten().map(
                 |(filename, dispatch)| (Cow::Borrowed(filename), dispatch),
             ));
         }
     }
 
     let results = results.into_iter().filter_map(|(filename, dispatch)| {
         match dispatch {
             Dispatch::Bad(_) => return Some((filename, dispatch)),
             _ => {}
         };
         // TODO do this in //, not at the end
         if !dmap.contains_key(filename.deref()) {
             if (options.list_ignored || matcher.exact_match(&filename))
                 && dir_ignore_fn(&filename)
             {
                 if options.list_ignored {
                     return Some((filename.to_owned(), Dispatch::Ignored));
                 }
             } else {
                 if !ignore_fn(&filename) {
                     return Some((filename.to_owned(), Dispatch::Unknown));
                 }
             }
             return None;
         }
         Some((filename, dispatch))
     });
 
     Ok((build_response(results), warnings))
 }

rust/hg-cpython/src/dirstate.rs

@@ -1,133 +1,144
 // dirstate.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::dirstate` module provided by the
 //! `hg-core` package.
 //!
 //! From Python, this will be seen as `mercurial.rustext.dirstate`
 mod copymap;
 mod dirs_multiset;
 mod dirstate_map;
 mod non_normal_entries;
 mod status;
-use crate::dirstate::{
-    dirs_multiset::Dirs, dirstate_map::DirstateMap, status::status_wrapper,
+use crate::{
+    dirstate::{
+        dirs_multiset::Dirs, dirstate_map::DirstateMap, status::status_wrapper,
+    },
+    exceptions,
 };
 use cpython::{
-    exc, PyBytes, PyDict, PyErr, PyModule, PyObject, PyResult, PySequence,
-    Python,
+    exc, PyBytes, PyDict, PyErr, PyList, PyModule, PyObject, PyResult,
+    PySequence, Python,
 };
 use hg::{
     utils::hg_path::HgPathBuf, DirstateEntry, DirstateParseError, EntryState,
     StateMap,
 };
 use libc::{c_char, c_int};
 use std::convert::TryFrom;
 
 // C code uses a custom `dirstate_tuple` type, checks in multiple instances
 // for this type, and raises a Python `Exception` if the check does not pass.
 // Because this type differs only in name from the regular Python tuple, it
 // would be a good idea in the near future to remove it entirely to allow
 // for a pure Python tuple of the same effective structure to be used,
 // rendering this type and the capsule below useless.
 py_capsule_fn!(
     from mercurial.cext.parsers import make_dirstate_tuple_CAPI
         as make_dirstate_tuple_capi
         signature (
             state: c_char,
             mode: c_int,
             size: c_int,
             mtime: c_int,
         ) -> *mut RawPyObject
 );
 
 pub fn make_dirstate_tuple(
     py: Python,
     entry: &DirstateEntry,
 ) -> PyResult<PyObject> {
     // might be silly to retrieve capsule function in hot loop
     let make = make_dirstate_tuple_capi::retrieve(py)?;
 
     let &DirstateEntry {
         state,
         mode,
         size,
         mtime,
     } = entry;
     // Explicitly go through u8 first, then cast to platform-specific `c_char`
     // because Into<u8> has a specific implementation while `as c_char` would
     // just do a naive enum cast.
     let state_code: u8 = state.into();
 
     let maybe_obj = unsafe {
         let ptr = make(state_code as c_char, mode, size, mtime);
         PyObject::from_owned_ptr_opt(py, ptr)
     };
     maybe_obj.ok_or_else(|| PyErr::fetch(py))
 }
 
 pub fn extract_dirstate(py: Python, dmap: &PyDict) -> Result<StateMap, PyErr> {
     dmap.items(py)
         .iter()
         .map(|(filename, stats)| {
             let stats = stats.extract::<PySequence>(py)?;
             let state = stats.get_item(py, 0)?.extract::<PyBytes>(py)?;
             let state = EntryState::try_from(state.data(py)[0]).map_err(
                 |e: DirstateParseError| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 },
             )?;
             let mode = stats.get_item(py, 1)?.extract(py)?;
             let size = stats.get_item(py, 2)?.extract(py)?;
             let mtime = stats.get_item(py, 3)?.extract(py)?;
             let filename = filename.extract::<PyBytes>(py)?;
             let filename = filename.data(py);
             Ok((
                 HgPathBuf::from(filename.to_owned()),
                 DirstateEntry {
                     state,
                     mode,
                     size,
                     mtime,
                 },
             ))
         })
         .collect()
 }
 
 /// Create the module, with `__package__` given from parent
 pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
     let dotted_name = &format!("{}.dirstate", package);
     let m = PyModule::new(py, dotted_name)?;
 
     m.add(py, "__package__", package)?;
     m.add(py, "__doc__", "Dirstate - Rust implementation")?;
 
+    m.add(
+        py,
+        "FallbackError",
+        py.get_type::<exceptions::FallbackError>(),
+    )?;
     m.add_class::<Dirs>(py)?;
     m.add_class::<DirstateMap>(py)?;
     m.add(
         py,
         "status",
         py_fn!(
             py,
             status_wrapper(
                 dmap: DirstateMap,
                 root_dir: PyObject,
                 matcher: PyObject,
-                list_clean: bool,
+                ignorefiles: PyList,
+                check_exec: bool,
                 last_normal_time: i64,
-                check_exec: bool
+                list_clean: bool,
+                list_ignored: bool,
+                list_unknown: bool
             )
         ),
     )?;
 
     let sys = PyModule::import(py, "sys")?;
     let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
     sys_modules.set_item(py, dotted_name, &m)?;
 
     Ok(m)
 }

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

@@ -1,129 +1,294
 // 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;
-use cpython::exc::ValueError;
+use crate::{dirstate::DirstateMap, exceptions::FallbackError};
 use cpython::{
-    ObjectProtocol, PyBytes, PyErr, PyList, PyObject, PyResult, PyTuple,
-    Python, PythonObject, ToPyObject,
+    exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
+    PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
-use hg::utils::hg_path::HgPathBuf;
 use hg::{
-    matchers::{AlwaysMatcher, FileMatcher},
-    status,
-    utils::{files::get_path_from_bytes, hg_path::HgPath},
-    DirstateStatus,
+    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;
+use std::borrow::{Borrow, Cow};
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
-fn collect_pybytes_list<P: AsRef<HgPath>>(
+fn collect_pybytes_list(
     py: Python,
-    collection: &[P],
+    collection: &[impl AsRef<HgPath>],
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
-    for (i, path) in collection.iter().enumerate() {
-        list.insert(
+    for path in collection.iter() {
+        list.append(
             py,
-            i,
             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) => {
+            PyErr::new::<FallbackError, _>(py, e.to_string())
+        }
+        e => PyErr::new::<ValueError, _>(py, e.to_string()),
+    }
+}
+
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
-    list_clean: bool,
+    ignore_files: PyList,
+    check_exec: bool,
     last_normal_time: i64,
-    check_exec: bool,
-) -> PyResult<(PyList, PyList, PyList, PyList, PyList, PyList, PyList)> {
+    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) = status(
+            let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 &root_dir,
-                list_clean,
-                last_normal_time,
-                check_exec,
+                &ignore_files,
+                StatusOptions {
+                    check_exec,
+                    last_normal_time,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                },
             )
-            .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
-            build_response(lookup, status_res, py)
+            .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) = status(
+            let ((lookup, status_res), warnings) = status(
                 &dmap,
                 &matcher,
                 &root_dir,
-                list_clean,
-                last_normal_time,
-                check_exec,
+                &ignore_files,
+                StatusOptions {
+                    check_exec,
+                    last_normal_time,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                },
             )
-            .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
-            build_response(lookup, status_res, py)
+            .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,
+                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(
-    lookup: Vec<&HgPath>,
+    py: Python,
+    lookup: Vec<Cow<HgPath>>,
     status_res: DirstateStatus,
-    py: Python,
-) -> PyResult<(PyList, PyList, PyList, PyList, PyList, PyList, PyList)> {
+    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 unknown = PyList::new(py, &[]);
+    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((lookup, modified, added, removed, deleted, unknown, clean))
+    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(),
+        ][..],
+    ))
 }

rust/hg-cpython/src/exceptions.rs

@@ -1,42 +1,44
 // ancestors.rs
 //
 // Copyright 2018 Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for Rust errors
 //!
 //! [`GraphError`] exposes `hg::GraphError` as a subclass of `ValueError`
 //! but some variants of `hg::GraphError` can be converted directly to other
 //! existing Python exceptions if appropriate.
 //!
 //! [`GraphError`]: struct.GraphError.html
 use cpython::{
     exc::{RuntimeError, ValueError},
     py_exception, PyErr, Python,
 };
 use hg;
 
 py_exception!(rustext, GraphError, ValueError);
 
 impl GraphError {
     pub fn pynew(py: Python, inner: hg::GraphError) -> PyErr {
         match inner {
             hg::GraphError::ParentOutOfRange(r) => {
                 GraphError::new(py, ("ParentOutOfRange", r))
             }
             hg::GraphError::WorkingDirectoryUnsupported => {
                 match py
                     .import("mercurial.error")
                     .and_then(|m| m.get(py, "WdirUnsupported"))
                 {
                     Err(e) => e,
                     Ok(cls) => PyErr::from_instance(py, cls),
                 }
             }
         }
     }
 }
 
 py_exception!(rustext, HgPathPyError, RuntimeError);
+py_exception!(rustext, FallbackError, RuntimeError);
+py_exception!(shared_ref, AlreadyBorrowed, RuntimeError);