rust: introduce SIZE_FROM_OTHER_PARENT constant

This will clarify what `-2` meant in the codebase.
This change also merged imports in affected files for cleanup.

Differential Revision: https://phab.mercurial-scm.org/D7301

rust/hg-core/src/dirstate.rs

@@ -1,77 +1,82 b''
 // dirstate module
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::{utils::hg_path::HgPathBuf, DirstateParseError};
 use std::collections::hash_map;
 use std::collections::HashMap;
 use std::convert::TryFrom;
 
 pub mod dirs_multiset;
 pub mod dirstate_map;
 pub mod parsers;
 pub mod status;
 
 #[derive(Debug, PartialEq, Clone)]
 pub struct DirstateParents {
     pub p1: [u8; 20],
     pub p2: [u8; 20],
 }
 
 /// The C implementation uses all signed types. This will be an issue
 /// either when 4GB+ source files are commonplace or in 2038, whichever
 /// comes first.
 #[derive(Debug, PartialEq, Copy, Clone)]
 pub struct DirstateEntry {
     pub state: EntryState,
     pub mode: i32,
     pub mtime: i32,
     pub size: i32,
 }
 
+/// A `DirstateEntry` with a size of `-2` means that it was merged from the
+/// other parent. This allows revert to pick the right status back during a
+/// merge.
+pub const SIZE_FROM_OTHER_PARENT: i32 = -2;
+
 pub type StateMap = HashMap<HgPathBuf, DirstateEntry>;
 pub type StateMapIter<'a> = hash_map::Iter<'a, HgPathBuf, DirstateEntry>;
 pub type CopyMap = HashMap<HgPathBuf, HgPathBuf>;
 pub type CopyMapIter<'a> = hash_map::Iter<'a, HgPathBuf, HgPathBuf>;
 
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum EntryState {
     Normal,
     Added,
     Removed,
     Merged,
     Unknown,
 }
 
 impl TryFrom<u8> for EntryState {
     type Error = DirstateParseError;
 
     fn try_from(value: u8) -> Result<Self, Self::Error> {
         match value {
             b'n' => Ok(EntryState::Normal),
             b'a' => Ok(EntryState::Added),
             b'r' => Ok(EntryState::Removed),
             b'm' => Ok(EntryState::Merged),
             b'?' => Ok(EntryState::Unknown),
             _ => Err(DirstateParseError::CorruptedEntry(format!(
                 "Incorrect entry state {}",
                 value
             ))),
         }
     }
 }
 
 impl Into<u8> for EntryState {
     fn into(self) -> u8 {
         match self {
             EntryState::Normal => b'n',
             EntryState::Added => b'a',
             EntryState::Removed => b'r',
             EntryState::Merged => b'm',
             EntryState::Unknown => b'?',
         }
     }
 }

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

@@ -1,424 +1,426 b''
 // dirstate_map.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
-use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::{
-    dirstate::{parsers::PARENT_SIZE, EntryState},
+    dirstate::{parsers::PARENT_SIZE, EntryState, SIZE_FROM_OTHER_PARENT},
     pack_dirstate, parse_dirstate,
-    utils::files::normalize_case,
+    utils::{
+        files::normalize_case,
+        hg_path::{HgPath, HgPathBuf},
+    },
     CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateMapError,
     DirstateParents, DirstateParseError, StateMap,
 };
 use core::borrow::Borrow;
 use std::collections::{HashMap, HashSet};
 use std::convert::TryInto;
 use std::iter::FromIterator;
 use std::ops::Deref;
 use std::time::Duration;
 
 pub type FileFoldMap = HashMap<HgPathBuf, HgPathBuf>;
 
 const NULL_ID: [u8; 20] = [0; 20];
 const MTIME_UNSET: i32 = -1;
-const SIZE_DIRTY: i32 = -2;
 
 #[derive(Default)]
 pub struct DirstateMap {
     state_map: StateMap,
     pub copy_map: CopyMap,
     file_fold_map: Option<FileFoldMap>,
     pub dirs: Option<DirsMultiset>,
     pub all_dirs: Option<DirsMultiset>,
     non_normal_set: HashSet<HgPathBuf>,
     other_parent_set: HashSet<HgPathBuf>,
     parents: Option<DirstateParents>,
     dirty_parents: bool,
 }
 
 /// Should only really be used in python interface code, for clarity
 impl Deref for DirstateMap {
     type Target = StateMap;
 
     fn deref(&self) -> &Self::Target {
         &self.state_map
     }
 }
 
 impl FromIterator<(HgPathBuf, DirstateEntry)> for DirstateMap {
     fn from_iter<I: IntoIterator<Item = (HgPathBuf, DirstateEntry)>>(
         iter: I,
     ) -> Self {
         Self {
             state_map: iter.into_iter().collect(),
             ..Self::default()
         }
     }
 }
 
 impl DirstateMap {
     pub fn new() -> Self {
         Self::default()
     }
 
     pub fn clear(&mut self) {
         self.state_map.clear();
         self.copy_map.clear();
         self.file_fold_map = None;
         self.non_normal_set.clear();
         self.other_parent_set.clear();
         self.set_parents(&DirstateParents {
             p1: NULL_ID,
             p2: NULL_ID,
         })
     }
 
     /// Add a tracked file to the dirstate
     pub fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) {
         if old_state == EntryState::Unknown || old_state == EntryState::Removed
         {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.add_path(filename)
             }
         }
         if old_state == EntryState::Unknown {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename)
             }
         }
         self.state_map.insert(filename.to_owned(), entry.to_owned());
 
         if entry.state != EntryState::Normal || entry.mtime == MTIME_UNSET {
             self.non_normal_set.insert(filename.to_owned());
         }
 
-        if entry.size == SIZE_DIRTY {
+        if entry.size == SIZE_FROM_OTHER_PARENT {
             self.other_parent_set.insert(filename.to_owned());
         }
     }
 
     /// Mark a file as removed in the dirstate.
     ///
     /// The `size` parameter is used to store sentinel values that indicate
     /// the file's previous state.  In the future, we should refactor this
     /// to be more explicit about what that state is.
     pub fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         if old_state != EntryState::Unknown && old_state != EntryState::Removed
         {
             if let Some(ref mut dirs) = self.dirs {
                 dirs.delete_path(filename)?;
             }
         }
         if old_state == EntryState::Unknown {
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.add_path(filename);
             }
         }
 
         if let Some(ref mut file_fold_map) = self.file_fold_map {
             file_fold_map.remove(&normalize_case(filename));
         }
         self.state_map.insert(
             filename.to_owned(),
             DirstateEntry {
                 state: EntryState::Removed,
                 mode: 0,
                 size,
                 mtime: 0,
             },
         );
         self.non_normal_set.insert(filename.to_owned());
         Ok(())
     }
 
     /// Remove a file from the dirstate.
     /// Returns `true` if the file was previously recorded.
     pub fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         let exists = self.state_map.remove(filename).is_some();
 
         if exists {
             if old_state != EntryState::Removed {
                 if let Some(ref mut dirs) = self.dirs {
                     dirs.delete_path(filename)?;
                 }
             }
             if let Some(ref mut all_dirs) = self.all_dirs {
                 all_dirs.delete_path(filename)?;
             }
         }
         if let Some(ref mut file_fold_map) = self.file_fold_map {
             file_fold_map.remove(&normalize_case(filename));
         }
         self.non_normal_set.remove(filename);
 
         Ok(exists)
     }
 
     pub fn clear_ambiguous_times(
         &mut self,
         filenames: Vec<HgPathBuf>,
         now: i32,
     ) {
         for filename in filenames {
             let mut changed = false;
             self.state_map
                 .entry(filename.to_owned())
                 .and_modify(|entry| {
                     if entry.state == EntryState::Normal && entry.mtime == now
                     {
                         changed = true;
                         *entry = DirstateEntry {
                             mtime: MTIME_UNSET,
                             ..*entry
                         };
                     }
                 });
             if changed {
                 self.non_normal_set.insert(filename.to_owned());
             }
         }
     }
 
     pub fn non_normal_other_parent_entries(
         &self,
     ) -> (HashSet<HgPathBuf>, HashSet<HgPathBuf>) {
         let mut non_normal = HashSet::new();
         let mut other_parent = HashSet::new();
 
         for (
             filename,
             DirstateEntry {
                 state, size, mtime, ..
             },
         ) in self.state_map.iter()
         {
             if *state != EntryState::Normal || *mtime == MTIME_UNSET {
                 non_normal.insert(filename.to_owned());
             }
-            if *state == EntryState::Normal && *size == SIZE_DIRTY {
+            if *state == EntryState::Normal && *size == SIZE_FROM_OTHER_PARENT
+            {
                 other_parent.insert(filename.to_owned());
             }
         }
 
         (non_normal, other_parent)
     }
 
     /// Both of these setters and their uses appear to be the simplest way to
     /// emulate a Python lazy property, but it is ugly and unidiomatic.
     /// TODO One day, rewriting this struct using the typestate might be a
     /// good idea.
     pub fn set_all_dirs(&mut self) {
         if self.all_dirs.is_none() {
             self.all_dirs =
                 Some(DirsMultiset::from_dirstate(&self.state_map, None));
         }
     }
 
     pub fn set_dirs(&mut self) {
         if self.dirs.is_none() {
             self.dirs = Some(DirsMultiset::from_dirstate(
                 &self.state_map,
                 Some(EntryState::Removed),
             ));
         }
     }
 
     pub fn has_tracked_dir(&mut self, directory: &HgPath) -> bool {
         self.set_dirs();
         self.dirs.as_ref().unwrap().contains(directory)
     }
 
     pub fn has_dir(&mut self, directory: &HgPath) -> bool {
         self.set_all_dirs();
         self.all_dirs.as_ref().unwrap().contains(directory)
     }
 
     pub fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError> {
         if let Some(ref parents) = self.parents {
             return Ok(parents);
         }
         let parents;
         if file_contents.len() == PARENT_SIZE * 2 {
             parents = DirstateParents {
                 p1: file_contents[..PARENT_SIZE].try_into().unwrap(),
                 p2: file_contents[PARENT_SIZE..PARENT_SIZE * 2]
                     .try_into()
                     .unwrap(),
             };
         } else if file_contents.is_empty() {
             parents = DirstateParents {
                 p1: NULL_ID,
                 p2: NULL_ID,
             };
         } else {
             return Err(DirstateError::Parse(DirstateParseError::Damaged));
         }
 
         self.parents = Some(parents);
         Ok(self.parents.as_ref().unwrap())
     }
 
     pub fn set_parents(&mut self, parents: &DirstateParents) {
         self.parents = Some(parents.clone());
         self.dirty_parents = true;
     }
 
     pub fn read(
         &mut self,
         file_contents: &[u8],
     ) -> Result<Option<DirstateParents>, DirstateError> {
         if file_contents.is_empty() {
             return Ok(None);
         }
 
         let parents = parse_dirstate(
             &mut self.state_map,
             &mut self.copy_map,
             file_contents,
         )?;
 
         if !self.dirty_parents {
             self.set_parents(&parents);
         }
 
         Ok(Some(parents))
     }
 
     pub fn pack(
         &mut self,
         parents: DirstateParents,
         now: Duration,
     ) -> Result<Vec<u8>, DirstateError> {
         let packed =
             pack_dirstate(&mut self.state_map, &self.copy_map, parents, now)?;
 
         self.dirty_parents = false;
 
         let result = self.non_normal_other_parent_entries();
         self.non_normal_set = result.0;
         self.other_parent_set = result.1;
         Ok(packed)
     }
 
     pub fn build_file_fold_map(&mut self) -> &FileFoldMap {
         if let Some(ref file_fold_map) = self.file_fold_map {
             return file_fold_map;
         }
         let mut new_file_fold_map = FileFoldMap::new();
         for (filename, DirstateEntry { state, .. }) in self.state_map.borrow()
         {
             if *state == EntryState::Removed {
                 new_file_fold_map
                     .insert(normalize_case(filename), filename.to_owned());
             }
         }
         self.file_fold_map = Some(new_file_fold_map);
         self.file_fold_map.as_ref().unwrap()
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn test_dirs_multiset() {
         let mut map = DirstateMap::new();
         assert!(map.dirs.is_none());
         assert!(map.all_dirs.is_none());
 
         assert_eq!(false, map.has_dir(HgPath::new(b"nope")));
         assert!(map.all_dirs.is_some());
         assert!(map.dirs.is_none());
 
         assert_eq!(false, map.has_tracked_dir(HgPath::new(b"nope")));
         assert!(map.dirs.is_some());
     }
 
     #[test]
     fn test_add_file() {
         let mut map = DirstateMap::new();
 
         assert_eq!(0, map.len());
 
         map.add_file(
             HgPath::new(b"meh"),
             EntryState::Normal,
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 1337,
                 mtime: 1337,
                 size: 1337,
             },
         );
 
         assert_eq!(1, map.len());
         assert_eq!(0, map.non_normal_set.len());
         assert_eq!(0, map.other_parent_set.len());
     }
 
     #[test]
     fn test_non_normal_other_parent_entries() {
         let map: DirstateMap = [
             (b"f1", (EntryState::Removed, 1337, 1337, 1337)),
             (b"f2", (EntryState::Normal, 1337, 1337, -1)),
             (b"f3", (EntryState::Normal, 1337, 1337, 1337)),
             (b"f4", (EntryState::Normal, 1337, -2, 1337)),
             (b"f5", (EntryState::Added, 1337, 1337, 1337)),
             (b"f6", (EntryState::Added, 1337, 1337, -1)),
             (b"f7", (EntryState::Merged, 1337, 1337, -1)),
             (b"f8", (EntryState::Merged, 1337, 1337, 1337)),
             (b"f9", (EntryState::Merged, 1337, -2, 1337)),
             (b"fa", (EntryState::Added, 1337, -2, 1337)),
             (b"fb", (EntryState::Removed, 1337, -2, 1337)),
         ]
         .iter()
         .map(|(fname, (state, mode, size, mtime))| {
             (
                 HgPathBuf::from_bytes(fname.as_ref()),
                 DirstateEntry {
                     state: *state,
                     mode: *mode,
                     size: *size,
                     mtime: *mtime,
                 },
             )
         })
         .collect();
 
         let non_normal = [
             b"f1", b"f2", b"f5", b"f6", b"f7", b"f8", b"f9", b"fa", b"fb",
         ]
         .iter()
         .map(|x| HgPathBuf::from_bytes(x.as_ref()))
         .collect();
 
         let mut other_parent = HashSet::new();
         other_parent.insert(HgPathBuf::from_bytes(b"f4"));
 
         assert_eq!(
             (non_normal, other_parent),
             map.non_normal_other_parent_entries()
         );
     }
 }

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

@@ -1,223 +1,228 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::utils::files::HgMetadata;
-use crate::utils::hg_path::{hg_path_to_path_buf, HgPath};
-use crate::{CopyMap, DirstateEntry, DirstateMap, EntryState};
+use crate::{
+    dirstate::SIZE_FROM_OTHER_PARENT,
+    utils::{
+        files::HgMetadata,
+        hg_path::{hg_path_to_path_buf, HgPath},
+    },
+    CopyMap, DirstateEntry, DirstateMap, EntryState,
+};
 use rayon::prelude::*;
 use std::path::Path;
 
 /// Marker enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
 }
 
 /// 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()
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
     check_exec: bool,
     list_clean: bool,
     last_normal_time: i64,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
                 (mode ^ st_mode as i32) & 0o100 != 0o000 && check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
-            let other_parent = size == -2;
+            let other_parent = size == SIZE_FROM_OTHER_PARENT;
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
                 Dispatch::Modified
             } else if mod_compare(mtime, st_mtime as i32) {
                 Dispatch::Unsure
             } else if st_mtime == last_normal_time {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
             } else if list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::Unknown
             }
         }
         EntryState::Merged => Dispatch::Modified,
         EntryState::Added => Dispatch::Added,
         EntryState::Removed => Dispatch::Removed,
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// The file corresponding to this Dirstate entry is missing.
 fn dispatch_missing(state: EntryState) -> Dispatch {
     match state {
         // File was removed from the filesystem during commands
         EntryState::Normal | EntryState::Merged | EntryState::Added => {
             Dispatch::Deleted
         }
         // File was removed, everything is normal
         EntryState::Removed => Dispatch::Removed,
         // File is unknown to Mercurial, everything is normal
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// Stat all entries in the `DirstateMap` and mark them for dispatch into
 /// the relevant collections.
 fn stat_dmap_entries(
     dmap: &DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send,
     check_exec: bool,
     list_clean: bool,
     last_normal_time: i64,
 ) -> impl ParallelIterator<Item = std::io::Result<(&HgPath, Dispatch)>> {
     dmap.par_iter().map(move |(filename, entry)| {
         let filename: &HgPath = filename;
         let filename_as_path = hg_path_to_path_buf(filename)?;
         let meta = root_dir.as_ref().join(filename_as_path).symlink_metadata();
 
         match meta {
             Ok(ref m)
                 if !(m.file_type().is_file()
                     || m.file_type().is_symlink()) =>
             {
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Ok(m) => Ok((
                 filename,
                 dispatch_found(
                     filename,
                     *entry,
                     HgMetadata::from_metadata(m),
                     &dmap.copy_map,
                     check_exec,
                     list_clean,
                     last_normal_time,
                 ),
             )),
             Err(ref e)
                 if e.kind() == std::io::ErrorKind::NotFound
                     || e.raw_os_error() == Some(20) =>
             {
                 // Rust does not yet have an `ErrorKind` for
                 // `NotADirectory` (errno 20)
                 // It happens if the dirstate contains `foo/bar` and
                 // foo is not a directory
                 Ok((filename, dispatch_missing(entry.state)))
             }
             Err(e) => Err(e),
         }
     })
 }
 
 pub struct StatusResult<'a> {
     pub modified: Vec<&'a HgPath>,
     pub added: Vec<&'a HgPath>,
     pub removed: Vec<&'a HgPath>,
     pub deleted: Vec<&'a HgPath>,
     pub clean: Vec<&'a HgPath>,
     // TODO ignored
     // TODO unknown
 }
 
 fn build_response(
     results: Vec<(&HgPath, Dispatch)>,
 ) -> (Vec<&HgPath>, StatusResult) {
     let mut lookup = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
 
     for (filename, dispatch) in results.into_iter() {
         match dispatch {
             Dispatch::Unknown => {}
             Dispatch::Unsure => lookup.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
         }
     }
 
     (
         lookup,
         StatusResult {
             modified,
             added,
             removed,
             deleted,
             clean,
         },
     )
 }
 
 pub fn status(
     dmap: &DirstateMap,
     root_dir: impl AsRef<Path> + Sync + Send + Copy,
     list_clean: bool,
     last_normal_time: i64,
     check_exec: bool,
 ) -> std::io::Result<(Vec<&HgPath>, StatusResult)> {
     let results: std::io::Result<_> = stat_dmap_entries(
         &dmap,
         root_dir,
         check_exec,
         list_clean,
         last_normal_time,
     )
     .collect();
 
     Ok(build_response(results?))
 }