rust: do a clippy pass

This is the result of running `cargo clippy` on hg-core/hg-cpython and fixing
the lints that do not require too much code churn (and would warrant a separate
commit/complete refactor) and only come from our code (a lot of warnings in
hg-cpython come from `rust-cpython`).

Most of those were good lints, two of them was the linter not being smart
enough (or compiler to get up to `clippy`'s level depending on how you see it).

Maybe in the future we could have `clippy` be part of the CI.

Differential Revision: https://phab.mercurial-scm.org/D8635

rust/hg-core/src/ancestors.rs

@@ -1,787 +1,787
 // 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.
 
 //! Rust versions of generic DAG ancestors algorithms for Mercurial
 
 use super::{Graph, GraphError, Revision, NULL_REVISION};
 use crate::dagops;
 use std::cmp::max;
 use std::collections::{BinaryHeap, HashSet};
 
 /// Iterator over the ancestors of a given list of revisions
 /// This is a generic type, defined and implemented for any Graph, so that
 /// it's easy to
 ///
 /// - unit test in pure Rust
 /// - bind to main Mercurial code, potentially in several ways and have these
 ///   bindings evolve over time
 pub struct AncestorsIterator<G: Graph> {
     graph: G,
     visit: BinaryHeap<Revision>,
     seen: HashSet<Revision>,
     stoprev: Revision,
 }
 
 /// Lazy ancestors set, backed by AncestorsIterator
 pub struct LazyAncestors<G: Graph + Clone> {
     graph: G,
     containsiter: AncestorsIterator<G>,
     initrevs: Vec<Revision>,
     stoprev: Revision,
     inclusive: bool,
 }
 
 pub struct MissingAncestors<G: Graph> {
     graph: G,
     bases: HashSet<Revision>,
     max_base: Revision,
 }
 
 impl<G: Graph> AncestorsIterator<G> {
     /// Constructor.
     ///
     /// if `inclusive` is true, then the init revisions are emitted in
     /// particular, otherwise iteration starts from their parents.
     pub fn new(
         graph: G,
         initrevs: impl IntoIterator<Item = Revision>,
         stoprev: Revision,
         inclusive: bool,
     ) -> Result<Self, GraphError> {
         let filtered_initrevs = initrevs.into_iter().filter(|&r| r >= stoprev);
         if inclusive {
             let visit: BinaryHeap<Revision> = filtered_initrevs.collect();
-            let seen = visit.iter().map(|&x| x).collect();
+            let seen = visit.iter().cloned().collect();
             return Ok(AncestorsIterator {
-                visit: visit,
-                seen: seen,
-                stoprev: stoprev,
-                graph: graph,
+                visit,
+                seen,
+                stoprev,
+                graph,
             });
         }
         let mut this = AncestorsIterator {
             visit: BinaryHeap::new(),
             seen: HashSet::new(),
-            stoprev: stoprev,
-            graph: graph,
+            stoprev,
+            graph,
         };
         this.seen.insert(NULL_REVISION);
         for rev in filtered_initrevs {
             for parent in this.graph.parents(rev)?.iter().cloned() {
                 this.conditionally_push_rev(parent);
             }
         }
         Ok(this)
     }
 
     #[inline]
     fn conditionally_push_rev(&mut self, rev: Revision) {
         if self.stoprev <= rev && self.seen.insert(rev) {
             self.visit.push(rev);
         }
     }
 
     /// Consumes partially the iterator to tell if the given target
     /// revision
     /// is in the ancestors it emits.
     /// This is meant for iterators actually dedicated to that kind of
     /// purpose
     pub fn contains(&mut self, target: Revision) -> Result<bool, GraphError> {
         if self.seen.contains(&target) && target != NULL_REVISION {
             return Ok(true);
         }
         for item in self {
             let rev = item?;
             if rev == target {
                 return Ok(true);
             }
             if rev < target {
                 return Ok(false);
             }
         }
         Ok(false)
     }
 
     pub fn peek(&self) -> Option<Revision> {
-        self.visit.peek().map(|&r| r)
+        self.visit.peek().cloned()
     }
 
     /// Tell if the iterator is about an empty set
     ///
     /// The result does not depend whether the iterator has been consumed
     /// or not.
     /// This is mostly meant for iterators backing a lazy ancestors set
     pub fn is_empty(&self) -> bool {
         if self.visit.len() > 0 {
             return false;
         }
         if self.seen.len() > 1 {
             return false;
         }
         // at this point, the seen set is at most a singleton.
         // If not `self.inclusive`, it's still possible that it has only
         // the null revision
         self.seen.is_empty() || self.seen.contains(&NULL_REVISION)
     }
 }
 
 /// Main implementation for the iterator
 ///
 /// The algorithm is the same as in `_lazyancestorsiter()` from `ancestors.py`
 /// with a few non crucial differences:
 ///
 /// - there's no filtering of invalid parent revisions. Actually, it should be
 ///   consistent and more efficient to filter them from the end caller.
 /// - we don't have the optimization for adjacent revisions (i.e., the case
 ///   where `p1 == rev - 1`), because it amounts to update the first element of
 ///   the heap without sifting, which Rust's BinaryHeap doesn't let us do.
 /// - we save a few pushes by comparing with `stoprev` before pushing
 impl<G: Graph> Iterator for AncestorsIterator<G> {
     type Item = Result<Revision, GraphError>;
 
     fn next(&mut self) -> Option<Self::Item> {
         let current = match self.visit.peek() {
             None => {
                 return None;
             }
             Some(c) => *c,
         };
         let [p1, p2] = match self.graph.parents(current) {
             Ok(ps) => ps,
             Err(e) => return Some(Err(e)),
         };
         if p1 < self.stoprev || !self.seen.insert(p1) {
             self.visit.pop();
         } else {
             *(self.visit.peek_mut().unwrap()) = p1;
         };
 
         self.conditionally_push_rev(p2);
         Some(Ok(current))
     }
 }
 
 impl<G: Graph + Clone> LazyAncestors<G> {
     pub fn new(
         graph: G,
         initrevs: impl IntoIterator<Item = Revision>,
         stoprev: Revision,
         inclusive: bool,
     ) -> Result<Self, GraphError> {
         let v: Vec<Revision> = initrevs.into_iter().collect();
         Ok(LazyAncestors {
             graph: graph.clone(),
             containsiter: AncestorsIterator::new(
                 graph,
                 v.iter().cloned(),
                 stoprev,
                 inclusive,
             )?,
             initrevs: v,
-            stoprev: stoprev,
-            inclusive: inclusive,
+            stoprev,
+            inclusive,
         })
     }
 
     pub fn contains(&mut self, rev: Revision) -> Result<bool, GraphError> {
         self.containsiter.contains(rev)
     }
 
     pub fn is_empty(&self) -> bool {
         self.containsiter.is_empty()
     }
 
     pub fn iter(&self) -> AncestorsIterator<G> {
         // the arguments being the same as for self.containsiter, we know
         // for sure that AncestorsIterator constructor can't fail
         AncestorsIterator::new(
             self.graph.clone(),
             self.initrevs.iter().cloned(),
             self.stoprev,
             self.inclusive,
         )
         .unwrap()
     }
 }
 
 impl<G: Graph> MissingAncestors<G> {
     pub fn new(graph: G, bases: impl IntoIterator<Item = Revision>) -> Self {
         let mut created = MissingAncestors {
-            graph: graph,
+            graph,
             bases: HashSet::new(),
             max_base: NULL_REVISION,
         };
         created.add_bases(bases);
         created
     }
 
     pub fn has_bases(&self) -> bool {
         !self.bases.is_empty()
     }
 
     /// Return a reference to current bases.
     ///
     /// This is useful in unit tests, but also setdiscovery.py does
     /// read the bases attribute of a ancestor.missingancestors instance.
     pub fn get_bases<'a>(&'a self) -> &'a HashSet<Revision> {
         &self.bases
     }
 
     /// Computes the relative heads of current bases.
     ///
     /// The object is still usable after this.
     pub fn bases_heads(&self) -> Result<HashSet<Revision>, GraphError> {
         dagops::heads(&self.graph, self.bases.iter())
     }
 
     /// Consumes the object and returns the relative heads of its bases.
     pub fn into_bases_heads(
         mut self,
     ) -> Result<HashSet<Revision>, GraphError> {
         dagops::retain_heads(&self.graph, &mut self.bases)?;
         Ok(self.bases)
     }
 
     /// Add some revisions to `self.bases`
     ///
     /// Takes care of keeping `self.max_base` up to date.
     pub fn add_bases(
         &mut self,
         new_bases: impl IntoIterator<Item = Revision>,
     ) {
         let mut max_base = self.max_base;
         self.bases.extend(
             new_bases
                 .into_iter()
                 .filter(|&rev| rev != NULL_REVISION)
                 .map(|r| {
                     if r > max_base {
                         max_base = r;
                     }
                     r
                 }),
         );
         self.max_base = max_base;
     }
 
     /// Remove all ancestors of self.bases from the revs set (in place)
     pub fn remove_ancestors_from(
         &mut self,
         revs: &mut HashSet<Revision>,
     ) -> Result<(), GraphError> {
         revs.retain(|r| !self.bases.contains(r));
         // the null revision is always an ancestor. Logically speaking
         // it's debatable in case bases is empty, but the Python
         // implementation always adds NULL_REVISION to bases, making it
         // unconditionnally true.
         revs.remove(&NULL_REVISION);
         if revs.is_empty() {
             return Ok(());
         }
         // anything in revs > start is definitely not an ancestor of bases
         // revs <= start need to be investigated
         if self.max_base == NULL_REVISION {
             return Ok(());
         }
 
         // whatever happens, we'll keep at least keepcount of them
         // knowing this gives us a earlier stop condition than
         // going all the way to the root
         let keepcount = revs.iter().filter(|r| **r > self.max_base).count();
 
         let mut curr = self.max_base;
         while curr != NULL_REVISION && revs.len() > keepcount {
             if self.bases.contains(&curr) {
                 revs.remove(&curr);
                 self.add_parents(curr)?;
             }
             curr -= 1;
         }
         Ok(())
     }
 
     /// Add the parents of `rev` to `self.bases`
     ///
     /// This has no effect on `self.max_base`
     #[inline]
     fn add_parents(&mut self, rev: Revision) -> Result<(), GraphError> {
         if rev == NULL_REVISION {
             return Ok(());
         }
         for p in self.graph.parents(rev)?.iter().cloned() {
             // No need to bother the set with inserting NULL_REVISION over and
             // over
             if p != NULL_REVISION {
                 self.bases.insert(p);
             }
         }
         Ok(())
     }
 
     /// Return all the ancestors of revs that are not ancestors of self.bases
     ///
     /// This may include elements from revs.
     ///
     /// Equivalent to the revset (::revs - ::self.bases). Revs are returned in
     /// revision number order, which is a topological order.
     pub fn missing_ancestors(
         &mut self,
         revs: impl IntoIterator<Item = Revision>,
     ) -> Result<Vec<Revision>, GraphError> {
         // just for convenience and comparison with Python version
         let bases_visit = &mut self.bases;
         let mut revs: HashSet<Revision> = revs
             .into_iter()
             .filter(|r| !bases_visit.contains(r))
             .collect();
         let revs_visit = &mut revs;
         let mut both_visit: HashSet<Revision> =
             revs_visit.intersection(&bases_visit).cloned().collect();
         if revs_visit.is_empty() {
             return Ok(Vec::new());
         }
         let max_revs = revs_visit.iter().cloned().max().unwrap();
         let start = max(self.max_base, max_revs);
 
         // TODO heuristics for with_capacity()?
         let mut missing: Vec<Revision> = Vec::new();
         for curr in (0..=start).rev() {
             if revs_visit.is_empty() {
                 break;
             }
             if both_visit.remove(&curr) {
                 // curr's parents might have made it into revs_visit through
                 // another path
                 for p in self.graph.parents(curr)?.iter().cloned() {
                     if p == NULL_REVISION {
                         continue;
                     }
                     revs_visit.remove(&p);
                     bases_visit.insert(p);
                     both_visit.insert(p);
                 }
             } else if revs_visit.remove(&curr) {
                 missing.push(curr);
                 for p in self.graph.parents(curr)?.iter().cloned() {
                     if p == NULL_REVISION {
                         continue;
                     }
                     if bases_visit.contains(&p) {
                         // p is already known to be an ancestor of revs_visit
                         revs_visit.remove(&p);
                         both_visit.insert(p);
                     } else if both_visit.contains(&p) {
                         // p should have been in bases_visit
                         revs_visit.remove(&p);
                         bases_visit.insert(p);
                     } else {
                         // visit later
                         revs_visit.insert(p);
                     }
                 }
             } else if bases_visit.contains(&curr) {
                 for p in self.graph.parents(curr)?.iter().cloned() {
                     if p == NULL_REVISION {
                         continue;
                     }
                     if revs_visit.remove(&p) || both_visit.contains(&p) {
                         // p is an ancestor of bases_visit, and is implicitly
                         // in revs_visit, which means p is ::revs & ::bases.
                         bases_visit.insert(p);
                         both_visit.insert(p);
                     } else {
                         bases_visit.insert(p);
                     }
                 }
             }
         }
         missing.reverse();
         Ok(missing)
     }
 }
 
 #[cfg(test)]
 mod tests {
 
     use super::*;
     use crate::testing::{SampleGraph, VecGraph};
     use std::iter::FromIterator;
 
     fn list_ancestors<G: Graph>(
         graph: G,
         initrevs: Vec<Revision>,
         stoprev: Revision,
         inclusive: bool,
     ) -> Vec<Revision> {
         AncestorsIterator::new(graph, initrevs, stoprev, inclusive)
             .unwrap()
             .map(|res| res.unwrap())
             .collect()
     }
 
     #[test]
     /// Same tests as test-ancestor.py, without membership
     /// (see also test-ancestor.py.out)
     fn test_list_ancestor() {
         assert_eq!(list_ancestors(SampleGraph, vec![], 0, false), vec![]);
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 0, false),
             vec![8, 7, 4, 3, 2, 1, 0]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![1, 3], 0, false),
             vec![1, 0]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 0, true),
             vec![13, 11, 8, 7, 4, 3, 2, 1, 0]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 6, false),
             vec![8, 7]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 6, true),
             vec![13, 11, 8, 7]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 11, true),
             vec![13, 11]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![11, 13], 12, true),
             vec![13]
         );
         assert_eq!(
             list_ancestors(SampleGraph, vec![10, 1], 0, true),
             vec![10, 5, 4, 2, 1, 0]
         );
     }
 
     #[test]
     /// Corner case that's not directly in test-ancestors.py, but
     /// that happens quite often, as demonstrated by running the whole
     /// suite.
     /// For instance, run tests/test-obsolete-checkheads.t
     fn test_nullrev_input() {
         let mut iter =
             AncestorsIterator::new(SampleGraph, vec![-1], 0, false).unwrap();
         assert_eq!(iter.next(), None)
     }
 
     #[test]
     fn test_contains() {
         let mut lazy =
             AncestorsIterator::new(SampleGraph, vec![10, 1], 0, true).unwrap();
         assert!(lazy.contains(1).unwrap());
         assert!(!lazy.contains(3).unwrap());
 
         let mut lazy =
             AncestorsIterator::new(SampleGraph, vec![0], 0, false).unwrap();
         assert!(!lazy.contains(NULL_REVISION).unwrap());
     }
 
     #[test]
     fn test_peek() {
         let mut iter =
             AncestorsIterator::new(SampleGraph, vec![10], 0, true).unwrap();
         // peek() gives us the next value
         assert_eq!(iter.peek(), Some(10));
         // but it's not been consumed
         assert_eq!(iter.next(), Some(Ok(10)));
         // and iteration resumes normally
         assert_eq!(iter.next(), Some(Ok(5)));
 
         // let's drain the iterator to test peek() at the end
         while iter.next().is_some() {}
         assert_eq!(iter.peek(), None);
     }
 
     #[test]
     fn test_empty() {
         let mut iter =
             AncestorsIterator::new(SampleGraph, vec![10], 0, true).unwrap();
         assert!(!iter.is_empty());
         while iter.next().is_some() {}
         assert!(!iter.is_empty());
 
         let iter =
             AncestorsIterator::new(SampleGraph, vec![], 0, true).unwrap();
         assert!(iter.is_empty());
 
         // case where iter.seen == {NULL_REVISION}
         let iter =
             AncestorsIterator::new(SampleGraph, vec![0], 0, false).unwrap();
         assert!(iter.is_empty());
     }
 
     /// A corrupted Graph, supporting error handling tests
     #[derive(Clone, Debug)]
     struct Corrupted;
 
     impl Graph for Corrupted {
         fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
             match rev {
                 1 => Ok([0, -1]),
                 r => Err(GraphError::ParentOutOfRange(r)),
             }
         }
     }
 
     #[test]
     fn test_initrev_out_of_range() {
         // inclusive=false looks up initrev's parents right away
         match AncestorsIterator::new(SampleGraph, vec![25], 0, false) {
             Ok(_) => panic!("Should have been ParentOutOfRange"),
             Err(e) => assert_eq!(e, GraphError::ParentOutOfRange(25)),
         }
     }
 
     #[test]
     fn test_next_out_of_range() {
         // inclusive=false looks up initrev's parents right away
         let mut iter =
             AncestorsIterator::new(Corrupted, vec![1], 0, false).unwrap();
         assert_eq!(iter.next(), Some(Err(GraphError::ParentOutOfRange(0))));
     }
 
     #[test]
     fn test_lazy_iter_contains() {
         let mut lazy =
             LazyAncestors::new(SampleGraph, vec![11, 13], 0, false).unwrap();
 
         let revs: Vec<Revision> = lazy.iter().map(|r| r.unwrap()).collect();
         // compare with iterator tests on the same initial revisions
         assert_eq!(revs, vec![8, 7, 4, 3, 2, 1, 0]);
 
         // contains() results are correct, unaffected by the fact that
         // we consumed entirely an iterator out of lazy
         assert_eq!(lazy.contains(2), Ok(true));
         assert_eq!(lazy.contains(9), Ok(false));
     }
 
     #[test]
     fn test_lazy_contains_iter() {
         let mut lazy =
             LazyAncestors::new(SampleGraph, vec![11, 13], 0, false).unwrap(); // reminder: [8, 7, 4, 3, 2, 1, 0]
 
         assert_eq!(lazy.contains(2), Ok(true));
         assert_eq!(lazy.contains(6), Ok(false));
 
         // after consumption of 2 by the inner iterator, results stay
         // consistent
         assert_eq!(lazy.contains(2), Ok(true));
         assert_eq!(lazy.contains(5), Ok(false));
 
         // iter() still gives us a fresh iterator
         let revs: Vec<Revision> = lazy.iter().map(|r| r.unwrap()).collect();
         assert_eq!(revs, vec![8, 7, 4, 3, 2, 1, 0]);
     }
 
     #[test]
     /// Test constructor, add/get bases and heads
     fn test_missing_bases() -> Result<(), GraphError> {
         let mut missing_ancestors =
             MissingAncestors::new(SampleGraph, [5, 3, 1, 3].iter().cloned());
         let mut as_vec: Vec<Revision> =
             missing_ancestors.get_bases().iter().cloned().collect();
         as_vec.sort();
         assert_eq!(as_vec, [1, 3, 5]);
         assert_eq!(missing_ancestors.max_base, 5);
 
         missing_ancestors.add_bases([3, 7, 8].iter().cloned());
         as_vec = missing_ancestors.get_bases().iter().cloned().collect();
         as_vec.sort();
         assert_eq!(as_vec, [1, 3, 5, 7, 8]);
         assert_eq!(missing_ancestors.max_base, 8);
 
         as_vec = missing_ancestors.bases_heads()?.iter().cloned().collect();
         as_vec.sort();
         assert_eq!(as_vec, [3, 5, 7, 8]);
         Ok(())
     }
 
     fn assert_missing_remove(
         bases: &[Revision],
         revs: &[Revision],
         expected: &[Revision],
     ) {
         let mut missing_ancestors =
             MissingAncestors::new(SampleGraph, bases.iter().cloned());
         let mut revset: HashSet<Revision> = revs.iter().cloned().collect();
         missing_ancestors
             .remove_ancestors_from(&mut revset)
             .unwrap();
         let mut as_vec: Vec<Revision> = revset.into_iter().collect();
         as_vec.sort();
         assert_eq!(as_vec.as_slice(), expected);
     }
 
     #[test]
     fn test_missing_remove() {
         assert_missing_remove(
             &[1, 2, 3, 4, 7],
             Vec::from_iter(1..10).as_slice(),
             &[5, 6, 8, 9],
         );
         assert_missing_remove(&[10], &[11, 12, 13, 14], &[11, 12, 13, 14]);
         assert_missing_remove(&[7], &[1, 2, 3, 4, 5], &[3, 5]);
     }
 
     fn assert_missing_ancestors(
         bases: &[Revision],
         revs: &[Revision],
         expected: &[Revision],
     ) {
         let mut missing_ancestors =
             MissingAncestors::new(SampleGraph, bases.iter().cloned());
         let missing = missing_ancestors
             .missing_ancestors(revs.iter().cloned())
             .unwrap();
         assert_eq!(missing.as_slice(), expected);
     }
 
     #[test]
     fn test_missing_ancestors() {
         // examples taken from test-ancestors.py by having it run
         // on the same graph (both naive and fast Python algs)
         assert_missing_ancestors(&[10], &[11], &[3, 7, 11]);
         assert_missing_ancestors(&[11], &[10], &[5, 10]);
         assert_missing_ancestors(&[7], &[9, 11], &[3, 6, 9, 11]);
     }
 
     /// An interesting case found by a random generator similar to
     /// the one in test-ancestor.py. An early version of Rust MissingAncestors
     /// failed this, yet none of the integration tests of the whole suite
     /// catched it.
     #[test]
     fn test_remove_ancestors_from_case1() {
         let graph: VecGraph = vec![
             [NULL_REVISION, NULL_REVISION],
             [0, NULL_REVISION],
             [1, 0],
             [2, 1],
             [3, NULL_REVISION],
             [4, NULL_REVISION],
             [5, 1],
             [2, NULL_REVISION],
             [7, NULL_REVISION],
             [8, NULL_REVISION],
             [9, NULL_REVISION],
             [10, 1],
             [3, NULL_REVISION],
             [12, NULL_REVISION],
             [13, NULL_REVISION],
             [14, NULL_REVISION],
             [4, NULL_REVISION],
             [16, NULL_REVISION],
             [17, NULL_REVISION],
             [18, NULL_REVISION],
             [19, 11],
             [20, NULL_REVISION],
             [21, NULL_REVISION],
             [22, NULL_REVISION],
             [23, NULL_REVISION],
             [2, NULL_REVISION],
             [3, NULL_REVISION],
             [26, 24],
             [27, NULL_REVISION],
             [28, NULL_REVISION],
             [12, NULL_REVISION],
             [1, NULL_REVISION],
             [1, 9],
             [32, NULL_REVISION],
             [33, NULL_REVISION],
             [34, 31],
             [35, NULL_REVISION],
             [36, 26],
             [37, NULL_REVISION],
             [38, NULL_REVISION],
             [39, NULL_REVISION],
             [40, NULL_REVISION],
             [41, NULL_REVISION],
             [42, 26],
             [0, NULL_REVISION],
             [44, NULL_REVISION],
             [45, 4],
             [40, NULL_REVISION],
             [47, NULL_REVISION],
             [36, 0],
             [49, NULL_REVISION],
             [NULL_REVISION, NULL_REVISION],
             [51, NULL_REVISION],
             [52, NULL_REVISION],
             [53, NULL_REVISION],
             [14, NULL_REVISION],
             [55, NULL_REVISION],
             [15, NULL_REVISION],
             [23, NULL_REVISION],
             [58, NULL_REVISION],
             [59, NULL_REVISION],
             [2, NULL_REVISION],
             [61, 59],
             [62, NULL_REVISION],
             [63, NULL_REVISION],
             [NULL_REVISION, NULL_REVISION],
             [65, NULL_REVISION],
             [66, NULL_REVISION],
             [67, NULL_REVISION],
             [68, NULL_REVISION],
             [37, 28],
             [69, 25],
             [71, NULL_REVISION],
             [72, NULL_REVISION],
             [50, 2],
             [74, NULL_REVISION],
             [12, NULL_REVISION],
             [18, NULL_REVISION],
             [77, NULL_REVISION],
             [78, NULL_REVISION],
             [79, NULL_REVISION],
             [43, 33],
             [81, NULL_REVISION],
             [82, NULL_REVISION],
             [83, NULL_REVISION],
             [84, 45],
             [85, NULL_REVISION],
             [86, NULL_REVISION],
             [NULL_REVISION, NULL_REVISION],
             [88, NULL_REVISION],
             [NULL_REVISION, NULL_REVISION],
             [76, 83],
             [44, NULL_REVISION],
             [92, NULL_REVISION],
             [93, NULL_REVISION],
             [9, NULL_REVISION],
             [95, 67],
             [96, NULL_REVISION],
             [97, NULL_REVISION],
             [NULL_REVISION, NULL_REVISION],
         ];
         let problem_rev = 28 as Revision;
         let problem_base = 70 as Revision;
         // making the problem obvious: problem_rev is a parent of problem_base
         assert_eq!(graph.parents(problem_base).unwrap()[1], problem_rev);
 
         let mut missing_ancestors: MissingAncestors<VecGraph> =
             MissingAncestors::new(
                 graph,
                 [60, 26, 70, 3, 96, 19, 98, 49, 97, 47, 1, 6]
                     .iter()
                     .cloned(),
             );
         assert!(missing_ancestors.bases.contains(&problem_base));
 
         let mut revs: HashSet<Revision> =
             [4, 12, 41, 28, 68, 38, 1, 30, 56, 44]
                 .iter()
                 .cloned()
                 .collect();
         missing_ancestors.remove_ancestors_from(&mut revs).unwrap();
         assert!(!revs.contains(&problem_rev));
     }
 }

rust/hg-core/src/dagops.rs

@@ -1,275 +1,276
 // dagops.rs
 //
 // Copyright 2019 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.
 
 //! Miscellaneous DAG operations
 //!
 //! # Terminology
 //! - By *relative heads* of a collection of revision numbers (`Revision`), we
 //!   mean those revisions that have no children among the collection.
 //! - Similarly *relative roots* of a collection of `Revision`, we mean those
 //!   whose parents, if any, don't belong to the collection.
 use super::{Graph, GraphError, Revision, NULL_REVISION};
 use crate::ancestors::AncestorsIterator;
 use std::collections::{BTreeSet, HashSet};
 
-fn remove_parents(
+fn remove_parents<S: std::hash::BuildHasher>(
     graph: &impl Graph,
     rev: Revision,
-    set: &mut HashSet<Revision>,
+    set: &mut HashSet<Revision, S>,
 ) -> Result<(), GraphError> {
     for parent in graph.parents(rev)?.iter() {
         if *parent != NULL_REVISION {
             set.remove(parent);
         }
     }
     Ok(())
 }
 
 /// Relative heads out of some revisions, passed as an iterator.
 ///
 /// These heads are defined as those revisions that have no children
 /// among those emitted by the iterator.
 ///
 /// # Performance notes
 /// Internally, this clones the iterator, and builds a `HashSet` out of it.
 ///
 /// This function takes an `Iterator` instead of `impl IntoIterator` to
 /// guarantee that cloning the iterator doesn't result in cloning the full
 /// construct it comes from.
 pub fn heads<'a>(
     graph: &impl Graph,
     iter_revs: impl Clone + Iterator<Item = &'a Revision>,
 ) -> Result<HashSet<Revision>, GraphError> {
     let mut heads: HashSet<Revision> = iter_revs.clone().cloned().collect();
     heads.remove(&NULL_REVISION);
     for rev in iter_revs {
         if *rev != NULL_REVISION {
             remove_parents(graph, *rev, &mut heads)?;
         }
     }
     Ok(heads)
 }
 
 /// Retain in `revs` only its relative heads.
 ///
 /// This is an in-place operation, so that control of the incoming
 /// set is left to the caller.
 /// - a direct Python binding would probably need to build its own `HashSet`
 ///   from an incoming iterable, even if its sole purpose is to extract the
 ///   heads.
 /// - a Rust caller can decide whether cloning beforehand is appropriate
 ///
 /// # Performance notes
 /// Internally, this function will store a full copy of `revs` in a `Vec`.
-pub fn retain_heads(
+pub fn retain_heads<S: std::hash::BuildHasher>(
     graph: &impl Graph,
-    revs: &mut HashSet<Revision>,
+    revs: &mut HashSet<Revision, S>,
 ) -> Result<(), GraphError> {
     revs.remove(&NULL_REVISION);
     // we need to construct an iterable copy of revs to avoid itering while
     // mutating
     let as_vec: Vec<Revision> = revs.iter().cloned().collect();
     for rev in as_vec {
         if rev != NULL_REVISION {
             remove_parents(graph, rev, revs)?;
         }
     }
     Ok(())
 }
 
 /// Roots of `revs`, passed as a `HashSet`
 ///
 /// They are returned in arbitrary order
-pub fn roots<G: Graph>(
+pub fn roots<G: Graph, S: std::hash::BuildHasher>(
     graph: &G,
-    revs: &HashSet<Revision>,
+    revs: &HashSet<Revision, S>,
 ) -> Result<Vec<Revision>, GraphError> {
     let mut roots: Vec<Revision> = Vec::new();
     for rev in revs {
         if graph
             .parents(*rev)?
             .iter()
             .filter(|p| **p != NULL_REVISION)
             .all(|p| !revs.contains(p))
         {
             roots.push(*rev);
         }
     }
     Ok(roots)
 }
 
 /// Compute the topological range between two collections of revisions
 ///
 /// This is equivalent to the revset `<roots>::<heads>`.
 ///
 /// Currently, the given `Graph` has to implement `Clone`, which means
 /// actually cloning just a reference-counted Python pointer if
 /// it's passed over through `rust-cpython`. This is due to the internal
 /// use of `AncestorsIterator`
 ///
 /// # Algorithmic details
 ///
 /// This is a two-pass swipe inspired from what `reachableroots2` from
 /// `mercurial.cext.parsers` does to obtain the same results.
 ///
 /// - first, we climb up the DAG from `heads` in topological order, keeping
 ///   them in the vector `heads_ancestors` vector, and adding any element of
 ///   `roots` we find among them to the resulting range.
 /// - Then, we iterate on that recorded vector so that a revision is always
 ///   emitted after its parents and add all revisions whose parents are already
 ///   in the range to the results.
 ///
 /// # Performance notes
 ///
 /// The main difference with the C implementation is that
 /// the latter uses a flat array with bit flags, instead of complex structures
 /// like `HashSet`, making it faster in most scenarios. In theory, it's
 /// possible that the present implementation could be more memory efficient
 /// for very large repositories with many branches.
 pub fn range(
     graph: &(impl Graph + Clone),
     roots: impl IntoIterator<Item = Revision>,
     heads: impl IntoIterator<Item = Revision>,
 ) -> Result<BTreeSet<Revision>, GraphError> {
     let mut range = BTreeSet::new();
     let roots: HashSet<Revision> = roots.into_iter().collect();
     let min_root: Revision = match roots.iter().cloned().min() {
         None => {
             return Ok(range);
         }
         Some(r) => r,
     };
 
     // Internally, AncestorsIterator currently maintains a `HashSet`
     // of all seen revision, which is also what we record, albeit in an ordered
     // way. There's room for improvement on this duplication.
     let ait = AncestorsIterator::new(graph.clone(), heads, min_root, true)?;
     let mut heads_ancestors: Vec<Revision> = Vec::new();
     for revres in ait {
         let rev = revres?;
         if roots.contains(&rev) {
             range.insert(rev);
         }
         heads_ancestors.push(rev);
     }
 
     for rev in heads_ancestors.into_iter().rev() {
         for parent in graph.parents(rev)?.iter() {
             if *parent != NULL_REVISION && range.contains(parent) {
                 range.insert(rev);
             }
         }
     }
     Ok(range)
 }
 
 #[cfg(test)]
 mod tests {
 
     use super::*;
     use crate::testing::SampleGraph;
 
     /// Apply `retain_heads()` to the given slice and return as a sorted `Vec`
     fn retain_heads_sorted(
         graph: &impl Graph,
         revs: &[Revision],
     ) -> Result<Vec<Revision>, GraphError> {
         let mut revs: HashSet<Revision> = revs.iter().cloned().collect();
         retain_heads(graph, &mut revs)?;
         let mut as_vec: Vec<Revision> = revs.iter().cloned().collect();
         as_vec.sort();
         Ok(as_vec)
     }
 
     #[test]
     fn test_retain_heads() -> Result<(), GraphError> {
         assert_eq!(retain_heads_sorted(&SampleGraph, &[4, 5, 6])?, vec![5, 6]);
         assert_eq!(
             retain_heads_sorted(&SampleGraph, &[4, 1, 6, 12, 0])?,
             vec![1, 6, 12]
         );
         assert_eq!(
             retain_heads_sorted(&SampleGraph, &[1, 2, 3, 4, 5, 6, 7, 8, 9])?,
             vec![3, 5, 8, 9]
         );
         Ok(())
     }
 
     /// Apply `heads()` to the given slice and return as a sorted `Vec`
     fn heads_sorted(
         graph: &impl Graph,
         revs: &[Revision],
     ) -> Result<Vec<Revision>, GraphError> {
         let heads = heads(graph, revs.iter())?;
         let mut as_vec: Vec<Revision> = heads.iter().cloned().collect();
         as_vec.sort();
         Ok(as_vec)
     }
 
     #[test]
     fn test_heads() -> Result<(), GraphError> {
         assert_eq!(heads_sorted(&SampleGraph, &[4, 5, 6])?, vec![5, 6]);
         assert_eq!(
             heads_sorted(&SampleGraph, &[4, 1, 6, 12, 0])?,
             vec![1, 6, 12]
         );
         assert_eq!(
             heads_sorted(&SampleGraph, &[1, 2, 3, 4, 5, 6, 7, 8, 9])?,
             vec![3, 5, 8, 9]
         );
         Ok(())
     }
 
     /// Apply `roots()` and sort the result for easier comparison
     fn roots_sorted(
         graph: &impl Graph,
         revs: &[Revision],
     ) -> Result<Vec<Revision>, GraphError> {
-        let mut as_vec = roots(graph, &revs.iter().cloned().collect())?;
+        let set: HashSet<_> = revs.iter().cloned().collect();
+        let mut as_vec = roots(graph, &set)?;
         as_vec.sort();
         Ok(as_vec)
     }
 
     #[test]
     fn test_roots() -> Result<(), GraphError> {
         assert_eq!(roots_sorted(&SampleGraph, &[4, 5, 6])?, vec![4]);
         assert_eq!(
             roots_sorted(&SampleGraph, &[4, 1, 6, 12, 0])?,
             vec![0, 4, 12]
         );
         assert_eq!(
             roots_sorted(&SampleGraph, &[1, 2, 3, 4, 5, 6, 7, 8, 9])?,
             vec![1, 8]
         );
         Ok(())
     }
 
     /// Apply `range()` and convert the result into a Vec for easier comparison
     fn range_vec(
         graph: impl Graph + Clone,
         roots: &[Revision],
         heads: &[Revision],
     ) -> Result<Vec<Revision>, GraphError> {
         range(&graph, roots.iter().cloned(), heads.iter().cloned())
             .map(|bs| bs.into_iter().collect())
     }
 
     #[test]
     fn test_range() -> Result<(), GraphError> {
         assert_eq!(range_vec(SampleGraph, &[0], &[4])?, vec![0, 1, 2, 4]);
         assert_eq!(range_vec(SampleGraph, &[0], &[8])?, vec![]);
         assert_eq!(
             range_vec(SampleGraph, &[5, 6], &[10, 11, 13])?,
             vec![5, 10]
         );
         assert_eq!(
             range_vec(SampleGraph, &[5, 6], &[10, 12])?,
             vec![5, 6, 9, 10, 12]
         );
         Ok(())
     }
 }

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

@@ -1,418 +1,422
 // dirs_multiset.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.
 
 //! A multiset of directory names.
 //!
 //! Used to counts the references to directories in a manifest or dirstate.
 use crate::{
     dirstate::EntryState,
     utils::{
         files,
         hg_path::{HgPath, HgPathBuf, HgPathError},
     },
     DirstateEntry, DirstateMapError, FastHashMap,
 };
 use std::collections::{hash_map, hash_map::Entry, HashMap, HashSet};
 
 // could be encapsulated if we care API stability more seriously
 pub type DirsMultisetIter<'a> = hash_map::Keys<'a, HgPathBuf, u32>;
 
 #[derive(PartialEq, Debug)]
 pub struct DirsMultiset {
     inner: FastHashMap<HgPathBuf, u32>,
 }
 
 impl DirsMultiset {
     /// Initializes the multiset from a dirstate.
     ///
     /// If `skip_state` is provided, skips dirstate entries with equal state.
     pub fn from_dirstate(
         dirstate: &FastHashMap<HgPathBuf, DirstateEntry>,
         skip_state: Option<EntryState>,
     ) -> Result<Self, DirstateMapError> {
         let mut multiset = DirsMultiset {
             inner: FastHashMap::default(),
         };
 
         for (filename, DirstateEntry { state, .. }) in dirstate {
             // This `if` is optimized out of the loop
             if let Some(skip) = skip_state {
                 if skip != *state {
                     multiset.add_path(filename)?;
                 }
             } else {
                 multiset.add_path(filename)?;
             }
         }
 
         Ok(multiset)
     }
 
     /// Initializes the multiset from a manifest.
     pub fn from_manifest(
         manifest: &[impl AsRef<HgPath>],
     ) -> Result<Self, DirstateMapError> {
         let mut multiset = DirsMultiset {
             inner: FastHashMap::default(),
         };
 
         for filename in manifest {
             multiset.add_path(filename.as_ref())?;
         }
 
         Ok(multiset)
     }
 
     /// Increases the count of deepest directory contained in the path.
     ///
     /// If the directory is not yet in the map, adds its parents.
     pub fn add_path(
         &mut self,
         path: impl AsRef<HgPath>,
     ) -> Result<(), DirstateMapError> {
         for subpath in files::find_dirs(path.as_ref()) {
             if subpath.as_bytes().last() == Some(&b'/') {
                 // TODO Remove this once PathAuditor is certified
                 // as the only entrypoint for path data
                 let second_slash_index = subpath.len() - 1;
 
                 return Err(DirstateMapError::InvalidPath(
                     HgPathError::ConsecutiveSlashes {
                         bytes: path.as_ref().as_bytes().to_owned(),
                         second_slash_index,
                     },
                 ));
             }
             if let Some(val) = self.inner.get_mut(subpath) {
                 *val += 1;
                 break;
             }
             self.inner.insert(subpath.to_owned(), 1);
         }
         Ok(())
     }
 
     /// Decreases the count of deepest directory contained in the path.
     ///
     /// If it is the only reference, decreases all parents until one is
     /// removed.
     /// If the directory is not in the map, something horrible has happened.
     pub fn delete_path(
         &mut self,
         path: impl AsRef<HgPath>,
     ) -> Result<(), DirstateMapError> {
         for subpath in files::find_dirs(path.as_ref()) {
             match self.inner.entry(subpath.to_owned()) {
                 Entry::Occupied(mut entry) => {
-                    let val = entry.get().clone();
+                    let val = *entry.get();
                     if val > 1 {
                         entry.insert(val - 1);
                         break;
                     }
                     entry.remove();
                 }
                 Entry::Vacant(_) => {
                     return Err(DirstateMapError::PathNotFound(
                         path.as_ref().to_owned(),
                     ))
                 }
             };
         }
 
         Ok(())
     }
 
     pub fn contains(&self, key: impl AsRef<HgPath>) -> bool {
         self.inner.contains_key(key.as_ref())
     }
 
     pub fn iter(&self) -> DirsMultisetIter {
         self.inner.keys()
     }
 
     pub fn len(&self) -> usize {
         self.inner.len()
     }
+
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
 }
 
 /// This is basically a reimplementation of `DirsMultiset` that stores the
 /// children instead of just a count of them, plus a small optional
 /// optimization to avoid some directories we don't need.
 #[derive(PartialEq, Debug)]
 pub struct DirsChildrenMultiset<'a> {
     inner: FastHashMap<&'a HgPath, HashSet<&'a HgPath>>,
     only_include: Option<HashSet<&'a HgPath>>,
 }
 
 impl<'a> DirsChildrenMultiset<'a> {
     pub fn new(
         paths: impl Iterator<Item = &'a HgPathBuf>,
         only_include: Option<&'a HashSet<impl AsRef<HgPath> + 'a>>,
     ) -> Self {
         let mut new = Self {
             inner: HashMap::default(),
             only_include: only_include
-                .map(|s| s.iter().map(|p| p.as_ref()).collect()),
+                .map(|s| s.iter().map(AsRef::as_ref).collect()),
         };
 
         for path in paths {
             new.add_path(path)
         }
 
         new
     }
     fn add_path(&mut self, path: &'a (impl AsRef<HgPath> + 'a)) {
         if path.as_ref().is_empty() {
             return;
         }
         for (directory, basename) in files::find_dirs_with_base(path.as_ref())
         {
             if !self.is_dir_included(directory) {
                 continue;
             }
             self.inner
                 .entry(directory)
                 .and_modify(|e| {
                     e.insert(basename);
                 })
                 .or_insert_with(|| {
                     let mut set = HashSet::new();
                     set.insert(basename);
                     set
                 });
         }
     }
     fn is_dir_included(&self, dir: impl AsRef<HgPath>) -> bool {
         match &self.only_include {
             None => false,
             Some(i) => i.contains(dir.as_ref()),
         }
     }
 
     pub fn get(
         &self,
         path: impl AsRef<HgPath>,
     ) -> Option<&HashSet<&'a HgPath>> {
         self.inner.get(path.as_ref())
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn test_delete_path_path_not_found() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
         let path = HgPathBuf::from_bytes(b"doesnotexist/");
         assert_eq!(
             Err(DirstateMapError::PathNotFound(path.to_owned())),
             map.delete_path(&path)
         );
     }
 
     #[test]
     fn test_delete_path_empty_path() {
         let mut map =
             DirsMultiset::from_manifest(&vec![HgPathBuf::new()]).unwrap();
         let path = HgPath::new(b"");
         assert_eq!(Ok(()), map.delete_path(path));
         assert_eq!(
             Err(DirstateMapError::PathNotFound(path.to_owned())),
             map.delete_path(path)
         );
     }
 
     #[test]
     fn test_delete_path_successful() {
         let mut map = DirsMultiset {
             inner: [("", 5), ("a", 3), ("a/b", 2), ("a/c", 1)]
                 .iter()
                 .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
                 .collect(),
         };
 
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/b/")));
         eprintln!("{:?}", map);
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/b/")));
         eprintln!("{:?}", map);
         assert_eq!(
             Err(DirstateMapError::PathNotFound(HgPathBuf::from_bytes(
                 b"a/b/"
             ))),
             map.delete_path(HgPath::new(b"a/b/"))
         );
 
         assert_eq!(2, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/c")).unwrap());
         eprintln!("{:?}", map);
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/")));
         eprintln!("{:?}", map);
 
         assert_eq!(Ok(()), map.delete_path(HgPath::new(b"a/c/")));
         assert_eq!(
             Err(DirstateMapError::PathNotFound(HgPathBuf::from_bytes(
                 b"a/c/"
             ))),
             map.delete_path(HgPath::new(b"a/c/"))
         );
     }
 
     #[test]
     fn test_add_path_empty_path() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
         let path = HgPath::new(b"");
         map.add_path(path).unwrap();
 
         assert_eq!(1, map.len());
     }
 
     #[test]
     fn test_add_path_successful() {
         let manifest: Vec<HgPathBuf> = vec![];
         let mut map = DirsMultiset::from_manifest(&manifest).unwrap();
 
         map.add_path(HgPath::new(b"a/")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"")).unwrap());
         assert_eq!(2, map.len());
 
         // Non directory should be ignored
         map.add_path(HgPath::new(b"a")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, map.len());
 
         // Non directory will still add its base
         map.add_path(HgPath::new(b"a/b")).unwrap();
         assert_eq!(2, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, map.len());
 
         // Duplicate path works
         map.add_path(HgPath::new(b"a/")).unwrap();
         assert_eq!(3, *map.inner.get(HgPath::new(b"a")).unwrap());
 
         // Nested dir adds to its base
         map.add_path(HgPath::new(b"a/b/")).unwrap();
         assert_eq!(4, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/b")).unwrap());
 
         // but not its base's base, because it already existed
         map.add_path(HgPath::new(b"a/b/c/")).unwrap();
         assert_eq!(4, *map.inner.get(HgPath::new(b"a")).unwrap());
         assert_eq!(2, *map.inner.get(HgPath::new(b"a/b")).unwrap());
 
         map.add_path(HgPath::new(b"a/c/")).unwrap();
         assert_eq!(1, *map.inner.get(HgPath::new(b"a/c")).unwrap());
 
         let expected = DirsMultiset {
             inner: [("", 2), ("a", 5), ("a/b", 2), ("a/b/c", 1), ("a/c", 1)]
                 .iter()
                 .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
                 .collect(),
         };
         assert_eq!(map, expected);
     }
 
     #[test]
     fn test_dirsmultiset_new_empty() {
         let manifest: Vec<HgPathBuf> = vec![];
         let new = DirsMultiset::from_manifest(&manifest).unwrap();
         let expected = DirsMultiset {
             inner: FastHashMap::default(),
         };
         assert_eq!(expected, new);
 
         let new = DirsMultiset::from_dirstate(&FastHashMap::default(), None)
             .unwrap();
         let expected = DirsMultiset {
             inner: FastHashMap::default(),
         };
         assert_eq!(expected, new);
     }
 
     #[test]
     fn test_dirsmultiset_new_no_skip() {
         let input_vec: Vec<HgPathBuf> = ["a/", "b/", "a/c", "a/d/"]
             .iter()
             .map(|e| HgPathBuf::from_bytes(e.as_bytes()))
             .collect();
         let expected_inner = [("", 2), ("a", 3), ("b", 1), ("a/d", 1)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new = DirsMultiset::from_manifest(&input_vec).unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
 
         let input_map = ["a/", "b/", "a/c", "a/d/"]
             .iter()
             .map(|f| {
                 (
                     HgPathBuf::from_bytes(f.as_bytes()),
                     DirstateEntry {
                         state: EntryState::Normal,
                         mode: 0,
                         mtime: 0,
                         size: 0,
                     },
                 )
             })
             .collect();
         let expected_inner = [("", 2), ("a", 3), ("b", 1), ("a/d", 1)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new = DirsMultiset::from_dirstate(&input_map, None).unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
     }
 
     #[test]
     fn test_dirsmultiset_new_skip() {
         let input_map = [
             ("a/", EntryState::Normal),
             ("a/b/", EntryState::Normal),
             ("a/c", EntryState::Removed),
             ("a/d/", EntryState::Merged),
         ]
         .iter()
         .map(|(f, state)| {
             (
                 HgPathBuf::from_bytes(f.as_bytes()),
                 DirstateEntry {
                     state: *state,
                     mode: 0,
                     mtime: 0,
                     size: 0,
                 },
             )
         })
         .collect();
 
         // "a" incremented with "a/c" and "a/d/"
         let expected_inner = [("", 1), ("a", 2), ("a/d", 1)]
             .iter()
             .map(|(k, v)| (HgPathBuf::from_bytes(k.as_bytes()), *v))
             .collect();
 
         let new =
             DirsMultiset::from_dirstate(&input_map, Some(EntryState::Normal))
                 .unwrap();
         let expected = DirsMultiset {
             inner: expected_inner,
         };
         assert_eq!(expected, new);
     }
 }

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

@@ -1,497 +1,497
 // 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::{
     dirstate::{parsers::PARENT_SIZE, EntryState, SIZE_FROM_OTHER_PARENT},
     pack_dirstate, parse_dirstate,
     utils::{
         files::normalize_case,
         hg_path::{HgPath, HgPathBuf},
     },
     CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateMapError,
     DirstateParents, DirstateParseError, FastHashMap, StateMap,
 };
 use core::borrow::Borrow;
 use std::collections::HashSet;
 use std::convert::TryInto;
 use std::iter::FromIterator;
 use std::ops::Deref;
 use std::time::Duration;
 
 pub type FileFoldMap = FastHashMap<HgPathBuf, HgPathBuf>;
 
 const NULL_ID: [u8; 20] = [0; 20];
 const MTIME_UNSET: i32 = -1;
 
 #[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: Option<HashSet<HgPathBuf>>,
     other_parent_set: Option<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 = None;
         self.other_parent_set = None;
         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,
     ) -> Result<(), DirstateMapError> {
         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.get_non_normal_other_parent_entries()
                 .0
                 .insert(filename.to_owned());
         }
 
         if entry.size == SIZE_FROM_OTHER_PARENT {
             self.get_non_normal_other_parent_entries()
                 .1
                 .insert(filename.to_owned());
         }
         Ok(())
     }
 
     /// 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.get_non_normal_other_parent_entries()
             .0
             .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.get_non_normal_other_parent_entries()
             .0
             .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.get_non_normal_other_parent_entries()
                     .0
                     .insert(filename.to_owned());
             }
         }
     }
 
     pub fn non_normal_entries_remove(
         &mut self,
         key: impl AsRef<HgPath>,
     ) -> bool {
         self.get_non_normal_other_parent_entries()
             .0
             .remove(key.as_ref())
     }
     pub fn non_normal_entries_union(
         &mut self,
         other: HashSet<HgPathBuf>,
     ) -> Vec<HgPathBuf> {
         self.get_non_normal_other_parent_entries()
             .0
             .union(&other)
-            .map(|e| e.to_owned())
+            .map(ToOwned::to_owned)
             .collect()
     }
 
     pub fn get_non_normal_other_parent_entries(
         &mut self,
     ) -> (&mut HashSet<HgPathBuf>, &mut HashSet<HgPathBuf>) {
         self.set_non_normal_other_parent_entries(false);
         (
             self.non_normal_set.as_mut().unwrap(),
             self.other_parent_set.as_mut().unwrap(),
         )
     }
 
     /// Useful to get immutable references to those sets in contexts where
     /// you only have an immutable reference to the `DirstateMap`, like when
     /// sharing references with Python.
     ///
     /// TODO, get rid of this along with the other "setter/getter" stuff when
     /// a nice typestate plan is defined.
     ///
     /// # Panics
     ///
     /// Will panic if either set is `None`.
     pub fn get_non_normal_other_parent_entries_panic(
         &self,
     ) -> (&HashSet<HgPathBuf>, &HashSet<HgPathBuf>) {
         (
             self.non_normal_set.as_ref().unwrap(),
             self.other_parent_set.as_ref().unwrap(),
         )
     }
 
     pub fn set_non_normal_other_parent_entries(&mut self, force: bool) {
         if !force
             && self.non_normal_set.is_some()
             && self.other_parent_set.is_some()
         {
             return;
         }
         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_FROM_OTHER_PARENT
             {
                 other_parent.insert(filename.to_owned());
             }
         }
         self.non_normal_set = Some(non_normal);
         self.other_parent_set = Some(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) -> Result<(), DirstateMapError> {
         if self.all_dirs.is_none() {
             self.all_dirs =
                 Some(DirsMultiset::from_dirstate(&self.state_map, None)?);
         }
         Ok(())
     }
 
     pub fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         if self.dirs.is_none() {
             self.dirs = Some(DirsMultiset::from_dirstate(
                 &self.state_map,
                 Some(EntryState::Removed),
             )?);
         }
         Ok(())
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.set_dirs()?;
         Ok(self.dirs.as_ref().unwrap().contains(directory))
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         self.set_all_dirs()?;
         Ok(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;
 
         self.set_non_normal_other_parent_entries(true);
         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::default();
         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!(map.has_dir(HgPath::new(b"nope")).unwrap(), false);
         assert!(map.all_dirs.is_some());
         assert!(map.dirs.is_none());
 
         assert_eq!(map.has_tracked_dir(HgPath::new(b"nope")).unwrap(), false);
         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,
             },
         )
         .unwrap();
 
         assert_eq!(1, map.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().0.len());
         assert_eq!(0, map.get_non_normal_other_parent_entries().1.len());
     }
 
     #[test]
     fn test_non_normal_other_parent_entries() {
         let mut 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 mut 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"));
         let entries = map.get_non_normal_other_parent_entries();
 
         assert_eq!(
             (&mut non_normal, &mut other_parent),
             (entries.0, entries.1)
         );
     }
 }

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

@@ -1,435 +1,435
 // 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;
 use crate::{
     dirstate::{CopyMap, EntryState, StateMap},
     DirstateEntry, DirstatePackError, DirstateParents, DirstateParseError,
 };
 use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
 use micro_timer::timed;
 use std::convert::{TryFrom, TryInto};
 use std::io::Cursor;
 use std::time::Duration;
 
 /// Parents are stored in the dirstate as byte hashes.
 pub const PARENT_SIZE: usize = 20;
 /// Dirstate entries have a static part of 8 + 32 + 32 + 32 + 32 bits.
 const MIN_ENTRY_SIZE: usize = 17;
 
 // TODO parse/pack: is mutate-on-loop better for performance?
 
 #[timed]
 pub fn parse_dirstate(
     state_map: &mut StateMap,
     copy_map: &mut CopyMap,
     contents: &[u8],
 ) -> Result<DirstateParents, DirstateParseError> {
     if contents.len() < PARENT_SIZE * 2 {
         return Err(DirstateParseError::TooLittleData);
     }
 
     let mut curr_pos = PARENT_SIZE * 2;
     let parents = DirstateParents {
         p1: contents[..PARENT_SIZE].try_into().unwrap(),
         p2: contents[PARENT_SIZE..curr_pos].try_into().unwrap(),
     };
 
     while curr_pos < contents.len() {
         if curr_pos + MIN_ENTRY_SIZE > contents.len() {
             return Err(DirstateParseError::Overflow);
         }
         let entry_bytes = &contents[curr_pos..];
 
         let mut cursor = Cursor::new(entry_bytes);
         let state = EntryState::try_from(cursor.read_u8()?)?;
         let mode = cursor.read_i32::<BigEndian>()?;
         let size = cursor.read_i32::<BigEndian>()?;
         let mtime = cursor.read_i32::<BigEndian>()?;
         let path_len = cursor.read_i32::<BigEndian>()? as usize;
 
         if path_len > contents.len() - curr_pos {
             return Err(DirstateParseError::Overflow);
         }
 
         // Slice instead of allocating a Vec needed for `read_exact`
         let path = &entry_bytes[MIN_ENTRY_SIZE..MIN_ENTRY_SIZE + (path_len)];
 
         let (path, copy) = match memchr::memchr(0, path) {
             None => (path, None),
             Some(i) => (&path[..i], Some(&path[(i + 1)..])),
         };
 
         if let Some(copy_path) = copy {
             copy_map.insert(
                 HgPath::new(path).to_owned(),
                 HgPath::new(copy_path).to_owned(),
             );
         };
         state_map.insert(
             HgPath::new(path).to_owned(),
             DirstateEntry {
                 state,
                 mode,
                 size,
                 mtime,
             },
         );
         curr_pos = curr_pos + MIN_ENTRY_SIZE + (path_len);
     }
 
     Ok(parents)
 }
 
 /// `now` is the duration in seconds since the Unix epoch
 pub fn pack_dirstate(
     state_map: &mut StateMap,
     copy_map: &CopyMap,
     parents: DirstateParents,
     now: Duration,
 ) -> Result<Vec<u8>, DirstatePackError> {
     // TODO move away from i32 before 2038.
     let now: i32 = now.as_secs().try_into().expect("time overflow");
 
     let expected_size: usize = state_map
         .iter()
         .map(|(filename, _)| {
             let mut length = MIN_ENTRY_SIZE + filename.len();
             if let Some(copy) = copy_map.get(filename) {
                 length += copy.len() + 1;
             }
             length
         })
         .sum();
     let expected_size = expected_size + PARENT_SIZE * 2;
 
     let mut packed = Vec::with_capacity(expected_size);
     let mut new_state_map = vec![];
 
     packed.extend(&parents.p1);
     packed.extend(&parents.p2);
 
     for (filename, entry) in state_map.iter() {
         let new_filename = filename.to_owned();
         let mut new_mtime: i32 = entry.mtime;
         if entry.state == EntryState::Normal && entry.mtime == now {
             // The file was last modified "simultaneously" with the current
             // write to dirstate (i.e. within the same second for file-
             // systems with a granularity of 1 sec). This commonly happens
             // for at least a couple of files on 'update'.
             // The user could change the file without changing its size
             // within the same second. Invalidate the file's mtime in
             // dirstate, forcing future 'status' calls to compare the
             // contents of the file if the size is the same. This prevents
             // mistakenly treating such files as clean.
             new_mtime = -1;
             new_state_map.push((
                 filename.to_owned(),
                 DirstateEntry {
                     mtime: new_mtime,
                     ..*entry
                 },
             ));
         }
         let mut new_filename = new_filename.into_vec();
         if let Some(copy) = copy_map.get(filename) {
-            new_filename.push('\0' as u8);
+            new_filename.push(b'\0');
             new_filename.extend(copy.bytes());
         }
 
         packed.write_u8(entry.state.into())?;
         packed.write_i32::<BigEndian>(entry.mode)?;
         packed.write_i32::<BigEndian>(entry.size)?;
         packed.write_i32::<BigEndian>(new_mtime)?;
         packed.write_i32::<BigEndian>(new_filename.len() as i32)?;
         packed.extend(new_filename)
     }
 
     if packed.len() != expected_size {
         return Err(DirstatePackError::BadSize(expected_size, packed.len()));
     }
 
     state_map.extend(new_state_map);
 
     Ok(packed)
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::{utils::hg_path::HgPathBuf, FastHashMap};
 
     #[test]
     fn test_pack_dirstate_empty() {
         let mut state_map: StateMap = FastHashMap::default();
         let copymap = FastHashMap::default();
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = b"1234567891011121314100000000000000000000".to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
 
         assert!(state_map.is_empty())
     }
     #[test]
     fn test_pack_dirstate_one_entry() {
         let expected_state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut state_map = expected_state_map.clone();
 
         let copymap = FastHashMap::default();
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = [
             49, 50, 51, 52, 53, 54, 55, 56, 57, 49, 48, 49, 49, 49, 50, 49,
             51, 49, 52, 49, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
             48, 48, 48, 48, 48, 48, 48, 48, 110, 0, 0, 1, 164, 0, 0, 0, 0, 47,
             41, 58, 244, 0, 0, 0, 2, 102, 49,
         ]
         .to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
 
         assert_eq!(expected_state_map, state_map);
     }
     #[test]
     fn test_pack_dirstate_one_entry_with_copy() {
         let expected_state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut state_map = expected_state_map.clone();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let expected = [
             49, 50, 51, 52, 53, 54, 55, 56, 57, 49, 48, 49, 49, 49, 50, 49,
             51, 49, 52, 49, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
             48, 48, 48, 48, 48, 48, 48, 48, 110, 0, 0, 1, 164, 0, 0, 0, 0, 47,
             41, 58, 244, 0, 0, 0, 11, 102, 49, 0, 99, 111, 112, 121, 110, 97,
             109, 101,
         ]
         .to_vec();
 
         assert_eq!(
             expected,
             pack_dirstate(&mut state_map, &copymap, parents, now).unwrap()
         );
         assert_eq!(expected_state_map, state_map);
     }
 
     #[test]
     fn test_parse_pack_one_entry_with_copy() {
         let mut state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 791231220,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let mut new_state_map: StateMap = FastHashMap::default();
         let mut new_copy_map: CopyMap = FastHashMap::default();
         let new_parents = parse_dirstate(
             &mut new_state_map,
             &mut new_copy_map,
             result.as_slice(),
         )
         .unwrap();
         assert_eq!(
             (parents, state_map, copymap),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 
     #[test]
     fn test_parse_pack_multiple_entries_with_copy() {
         let mut state_map: StateMap = [
             (
                 HgPathBuf::from_bytes(b"f1"),
                 DirstateEntry {
                     state: EntryState::Normal,
                     mode: 0o644,
                     size: 0,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f2"),
                 DirstateEntry {
                     state: EntryState::Merged,
                     mode: 0o777,
                     size: 1000,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f3"),
                 DirstateEntry {
                     state: EntryState::Removed,
                     mode: 0o644,
                     size: 234553,
                     mtime: 791231220,
                 },
             ),
             (
                 HgPathBuf::from_bytes(b"f4\xF6"),
                 DirstateEntry {
                     state: EntryState::Added,
                     mode: 0o644,
                     size: -1,
                     mtime: -1,
                 },
             ),
         ]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         copymap.insert(
             HgPathBuf::from_bytes(b"f4\xF6"),
             HgPathBuf::from_bytes(b"copyname2"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let mut new_state_map: StateMap = FastHashMap::default();
         let mut new_copy_map: CopyMap = FastHashMap::default();
         let new_parents = parse_dirstate(
             &mut new_state_map,
             &mut new_copy_map,
             result.as_slice(),
         )
         .unwrap();
         assert_eq!(
             (parents, state_map, copymap),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 
     #[test]
     /// https://www.mercurial-scm.org/repo/hg/rev/af3f26b6bba4
     fn test_parse_pack_one_entry_with_copy_and_time_conflict() {
         let mut state_map: StateMap = [(
             HgPathBuf::from_bytes(b"f1"),
             DirstateEntry {
                 state: EntryState::Normal,
                 mode: 0o644,
                 size: 0,
                 mtime: 15000000,
             },
         )]
         .iter()
         .cloned()
         .collect();
         let mut copymap = FastHashMap::default();
         copymap.insert(
             HgPathBuf::from_bytes(b"f1"),
             HgPathBuf::from_bytes(b"copyname"),
         );
         let parents = DirstateParents {
             p1: *b"12345678910111213141",
             p2: *b"00000000000000000000",
         };
         let now = Duration::new(15000000, 0);
         let result =
             pack_dirstate(&mut state_map, &copymap, parents.clone(), now)
                 .unwrap();
 
         let mut new_state_map: StateMap = FastHashMap::default();
         let mut new_copy_map: CopyMap = FastHashMap::default();
         let new_parents = parse_dirstate(
             &mut new_state_map,
             &mut new_copy_map,
             result.as_slice(),
         )
         .unwrap();
 
         assert_eq!(
             (
                 parents,
                 [(
                     HgPathBuf::from_bytes(b"f1"),
                     DirstateEntry {
                         state: EntryState::Normal,
                         mode: 0o644,
                         size: 0,
                         mtime: -1
                     }
                 )]
                 .iter()
                 .cloned()
                 .collect::<StateMap>(),
                 copymap,
             ),
             (new_parents, new_state_map, new_copy_map)
         )
     }
 }

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

@@ -1,956 +1,953
 // 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, 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.push((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 {
+            } else if mod_compare(mtime, st_mtime as i32)
+                || 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,
     traversed_sender: crossbeam::Sender<HgPathBuf>,
 ) -> impl ParallelIterator<Item = IoResult<(&'a HgPath, Dispatch)>> {
     files
         .unwrap_or(&DEFAULT_WORK)
         .par_iter()
-        .map(move |filename| {
+        .map(move |&filename| {
             // TODO normalization
-            let normalized = filename.as_ref();
+            let normalized = filename;
 
             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() {
+                        if options.collect_traversed_dirs {
+                            traversed_sender
+                                .send(normalized.to_owned())
+                                .expect("receiver should outlive sender");
+                        }
+                        Some(Ok((
+                            normalized,
+                            Dispatch::Directory {
+                                was_file: in_dmap.is_some(),
+                            },
+                        )))
                     } else {
-                        if file_type.is_dir() {
-                            if options.collect_traversed_dirs {
-                                traversed_sender
-                                    .send(normalized.to_owned())
-                                    .expect("receiver should outlive sender");
-                            }
-                            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,
-                                )),
-                            )))
-                        }
+                        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,
     /// Whether to collect traversed dirs for applying a callback later.
     /// Used by `hg purge` for example.
     pub collect_traversed_dirs: 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 IgnoreFnType,
     dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     filename: HgPathBuf,
     dir_entry: DirEntry,
     traversed_sender: crossbeam::Sender<HgPathBuf>,
 ) -> IoResult<()> {
     let file_type = dir_entry.file_type()?;
     let entry_option = dmap.get(&filename);
 
     if filename.as_bytes() == b".hg" {
         // Could be a directory or a symlink
         return Ok(());
     }
 
     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,
             traversed_sender,
         );
     } 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 {
-                if options.list_unknown {
-                    files_sender
-                        .send(Ok((filename.to_owned(), Dispatch::Unknown)))
-                        .unwrap();
-                }
+            } else if options.list_unknown {
+                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 IgnoreFnType,
     dir_ignore_fn: &'a IgnoreFnType,
     options: StatusOptions,
     entry_option: Option<&'a DirstateEntry>,
     directory: HgPathBuf,
     traversed_sender: crossbeam::Sender<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,
                 traversed_sender,
             )
             .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: &IgnoreFnType,
     dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
     traversed_sender: crossbeam::Sender<HgPathBuf>,
 ) -> IoResult<()> {
     let directory = directory.as_ref();
 
     if options.collect_traversed_dirs {
         traversed_sender
             .send(directory.to_owned())
             .expect("receiver should outlive sender");
     }
 
     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,
                     traversed_sender.clone(),
                 )?;
             }
         }
         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: &IgnoreFnType,
     dir_ignore_fn: &IgnoreFnType,
     options: StatusOptions,
     results: &mut Vec<(Cow<'a, HgPath>, Dispatch)>,
     traversed_sender: crossbeam::Sender<HgPathBuf>,
 ) -> IoResult<()> {
     let root_dir = root_dir.as_ref();
 
     // The traversal is done in parallel, so use a channel to gather entries.
     // `crossbeam::Sender` is `Sync`, 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,
         traversed_sender,
     )?;
 
     // 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)>,
     /// Only filled if `collect_traversed_dirs` is `true`
     pub traversed: Vec<HgPathBuf>,
 }
 
 #[timed]
 fn build_response<'a>(
     results: impl IntoIterator<Item = (Cow<'a, HgPath>, Dispatch)>,
     traversed: Vec<HgPathBuf>,
 ) -> (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,
             traversed,
         },
     )
 }
 
 #[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: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(
     (Vec<Cow<'c, HgPath>>, DirstateStatus<'c>),
     Vec<PatternFileWarning>,
 )> {
     // Needs to outlive `dir_ignore_fn` since it's captured.
     let 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)?;
 
         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
             }
         });
         (dir_ignore_fn, warnings)
     } else {
         ignore_fn = Box::new(|&_| true);
         (Box::new(|&_| true), vec![])
     };
 
     let files = matcher.file_set();
 
     // `crossbeam::Sender` is `Sync`, while `mpsc::Sender` is not.
     let (traversed_sender, traversed_recv) = crossbeam::channel::unbounded();
 
     // Step 1: check the files explicitly mentioned by the user
     let explicit = walk_explicit(
         files,
         &dmap,
         root_dir,
         options,
         traversed_sender.clone(),
     );
 
     // 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,
                             traversed_sender.clone(),
                         )?;
                     }
                 }
                 _ => 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);
         }
     }
 
     // Close the channel
     drop(traversed_sender);
     let traversed_dirs = traversed_recv.into_iter().collect();
 
     Ok((build_response(results, traversed_dirs), warnings))
 }

rust/hg-core/src/discovery.rs

@@ -1,695 +1,695
 // discovery.rs
 //
 // Copyright 2019 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.
 
 //! Discovery operations
 //!
 //! This is a Rust counterpart to the `partialdiscovery` class of
 //! `mercurial.setdiscovery`
 
 use super::{Graph, GraphError, Revision, NULL_REVISION};
 use crate::{ancestors::MissingAncestors, dagops, FastHashMap};
 use rand::seq::SliceRandom;
 use rand::{thread_rng, RngCore, SeedableRng};
 use std::cmp::{max, min};
 use std::collections::{HashSet, VecDeque};
 
 type Rng = rand_pcg::Pcg32;
 type Seed = [u8; 16];
 
 pub struct PartialDiscovery<G: Graph + Clone> {
     target_heads: Option<Vec<Revision>>,
     graph: G, // plays the role of self._repo
     common: MissingAncestors<G>,
     undecided: Option<HashSet<Revision>>,
     children_cache: Option<FastHashMap<Revision, Vec<Revision>>>,
     missing: HashSet<Revision>,
     rng: Rng,
     respect_size: bool,
     randomize: bool,
 }
 
 pub struct DiscoveryStats {
     pub undecided: Option<usize>,
 }
 
 /// Update an existing sample to match the expected size
 ///
 /// The sample is updated with revisions exponentially distant from each
 /// element of `heads`.
 ///
 /// If a target size is specified, the sampling will stop once this size is
 /// reached. Otherwise sampling will happen until roots of the <revs> set are
 /// reached.
 ///
 /// - `revs`: set of revs we want to discover (if None, `assume` the whole dag
 ///   represented by `parentfn`
 /// - `heads`: set of DAG head revs
 /// - `sample`: a sample to update
 /// - `parentfn`: a callable to resolve parents for a revision
 /// - `quicksamplesize`: optional target size of the sample
 fn update_sample<I>(
     revs: Option<&HashSet<Revision>>,
     heads: impl IntoIterator<Item = Revision>,
     sample: &mut HashSet<Revision>,
     parentsfn: impl Fn(Revision) -> Result<I, GraphError>,
     quicksamplesize: Option<usize>,
 ) -> Result<(), GraphError>
 where
     I: Iterator<Item = Revision>,
 {
     let mut distances: FastHashMap<Revision, u32> = FastHashMap::default();
     let mut visit: VecDeque<Revision> = heads.into_iter().collect();
     let mut factor: u32 = 1;
     let mut seen: HashSet<Revision> = HashSet::new();
     while let Some(current) = visit.pop_front() {
         if !seen.insert(current) {
             continue;
         }
 
         let d = *distances.entry(current).or_insert(1);
         if d > factor {
             factor *= 2;
         }
         if d == factor {
             sample.insert(current);
             if let Some(sz) = quicksamplesize {
                 if sample.len() >= sz {
                     return Ok(());
                 }
             }
         }
         for p in parentsfn(current)? {
             if let Some(revs) = revs {
                 if !revs.contains(&p) {
                     continue;
                 }
             }
             distances.entry(p).or_insert(d + 1);
             visit.push_back(p);
         }
     }
     Ok(())
 }
 
 struct ParentsIterator {
     parents: [Revision; 2],
     cur: usize,
 }
 
 impl ParentsIterator {
     fn graph_parents(
         graph: &impl Graph,
         r: Revision,
     ) -> Result<ParentsIterator, GraphError> {
         Ok(ParentsIterator {
             parents: graph.parents(r)?,
             cur: 0,
         })
     }
 }
 
 impl Iterator for ParentsIterator {
     type Item = Revision;
 
     fn next(&mut self) -> Option<Revision> {
         if self.cur > 1 {
             return None;
         }
         let rev = self.parents[self.cur];
         self.cur += 1;
         if rev == NULL_REVISION {
             return self.next();
         }
         Some(rev)
     }
 }
 
 impl<G: Graph + Clone> PartialDiscovery<G> {
     /// Create a PartialDiscovery object, with the intent
     /// of comparing our `::<target_heads>` revset to the contents of another
     /// repo.
     ///
     /// For now `target_heads` is passed as a vector, and will be used
     /// at the first call to `ensure_undecided()`.
     ///
     /// If we want to make the signature more flexible,
     /// we'll have to make it a type argument of `PartialDiscovery` or a trait
     /// object since we'll keep it in the meanwhile
     ///
     /// The `respect_size` boolean controls how the sampling methods
     /// will interpret the size argument requested by the caller. If it's
     /// `false`, they are allowed to produce a sample whose size is more
     /// appropriate to the situation (typically bigger).
     ///
     /// The `randomize` boolean affects sampling, and specifically how
     /// limiting or last-minute expanding is been done:
     ///
     /// If `true`, both will perform random picking from `self.undecided`.
     /// This is currently the best for actual discoveries.
     ///
     /// If `false`, a reproductible picking strategy is performed. This is
     /// useful for integration tests.
     pub fn new(
         graph: G,
         target_heads: Vec<Revision>,
         respect_size: bool,
         randomize: bool,
     ) -> Self {
         let mut seed = [0; 16];
         if randomize {
             thread_rng().fill_bytes(&mut seed);
         }
         Self::new_with_seed(graph, target_heads, seed, respect_size, randomize)
     }
 
     pub fn new_with_seed(
         graph: G,
         target_heads: Vec<Revision>,
         seed: Seed,
         respect_size: bool,
         randomize: bool,
     ) -> Self {
         PartialDiscovery {
             undecided: None,
             children_cache: None,
             target_heads: Some(target_heads),
             graph: graph.clone(),
             common: MissingAncestors::new(graph, vec![]),
             missing: HashSet::new(),
             rng: Rng::from_seed(seed),
-            respect_size: respect_size,
-            randomize: randomize,
+            respect_size,
+            randomize,
         }
     }
 
     /// Extract at most `size` random elements from sample and return them
     /// as a vector
     fn limit_sample(
         &mut self,
         mut sample: Vec<Revision>,
         size: usize,
     ) -> Vec<Revision> {
         if !self.randomize {
             sample.sort();
             sample.truncate(size);
             return sample;
         }
         let sample_len = sample.len();
         if sample_len <= size {
             return sample;
         }
         let rng = &mut self.rng;
         let dropped_size = sample_len - size;
         let limited_slice = if size < dropped_size {
             sample.partial_shuffle(rng, size).0
         } else {
             sample.partial_shuffle(rng, dropped_size).1
         };
         limited_slice.to_owned()
     }
 
     /// Register revisions known as being common
     pub fn add_common_revisions(
         &mut self,
         common: impl IntoIterator<Item = Revision>,
     ) -> Result<(), GraphError> {
         let before_len = self.common.get_bases().len();
         self.common.add_bases(common);
         if self.common.get_bases().len() == before_len {
             return Ok(());
         }
         if let Some(ref mut undecided) = self.undecided {
             self.common.remove_ancestors_from(undecided)?;
         }
         Ok(())
     }
 
     /// Register revisions known as being missing
     ///
     /// # Performance note
     ///
     /// Except in the most trivial case, the first call of this method has
     /// the side effect of computing `self.undecided` set for the first time,
     /// and the related caches it might need for efficiency of its internal
     /// computation. This is typically faster if more information is
     /// available in `self.common`. Therefore, for good performance, the
     /// caller should avoid calling this too early.
     pub fn add_missing_revisions(
         &mut self,
         missing: impl IntoIterator<Item = Revision>,
     ) -> Result<(), GraphError> {
         let mut tovisit: VecDeque<Revision> = missing.into_iter().collect();
         if tovisit.is_empty() {
             return Ok(());
         }
         self.ensure_children_cache()?;
         self.ensure_undecided()?; // for safety of possible future refactors
         let children = self.children_cache.as_ref().unwrap();
         let mut seen: HashSet<Revision> = HashSet::new();
         let undecided_mut = self.undecided.as_mut().unwrap();
         while let Some(rev) = tovisit.pop_front() {
             if !self.missing.insert(rev) {
                 // either it's known to be missing from a previous
                 // invocation, and there's no need to iterate on its
                 // children (we now they are all missing)
                 // or it's from a previous iteration of this loop
                 // and its children have already been queued
                 continue;
             }
             undecided_mut.remove(&rev);
             match children.get(&rev) {
                 None => {
                     continue;
                 }
                 Some(this_children) => {
                     for child in this_children.iter().cloned() {
                         if seen.insert(child) {
                             tovisit.push_back(child);
                         }
                     }
                 }
             }
         }
         Ok(())
     }
 
     /// Do we have any information about the peer?
     pub fn has_info(&self) -> bool {
         self.common.has_bases()
     }
 
     /// Did we acquire full knowledge of our Revisions that the peer has?
     pub fn is_complete(&self) -> bool {
-        self.undecided.as_ref().map_or(false, |s| s.is_empty())
+        self.undecided.as_ref().map_or(false, HashSet::is_empty)
     }
 
     /// Return the heads of the currently known common set of revisions.
     ///
     /// If the discovery process is not complete (see `is_complete()`), the
     /// caller must be aware that this is an intermediate state.
     ///
     /// On the other hand, if it is complete, then this is currently
     /// the only way to retrieve the end results of the discovery process.
     ///
     /// We may introduce in the future an `into_common_heads` call that
     /// would be more appropriate for normal Rust callers, dropping `self`
     /// if it is complete.
     pub fn common_heads(&self) -> Result<HashSet<Revision>, GraphError> {
         self.common.bases_heads()
     }
 
     /// Force first computation of `self.undecided`
     ///
     /// After this, `self.undecided.as_ref()` and `.as_mut()` can be
     /// unwrapped to get workable immutable or mutable references without
     /// any panic.
     ///
     /// This is an imperative call instead of an access with added lazyness
     /// to reduce easily the scope of mutable borrow for the caller,
     /// compared to undecided(&'a mut self) -> &'a… that would keep it
     /// as long as the resulting immutable one.
     fn ensure_undecided(&mut self) -> Result<(), GraphError> {
         if self.undecided.is_some() {
             return Ok(());
         }
         let tgt = self.target_heads.take().unwrap();
         self.undecided =
             Some(self.common.missing_ancestors(tgt)?.into_iter().collect());
         Ok(())
     }
 
     fn ensure_children_cache(&mut self) -> Result<(), GraphError> {
         if self.children_cache.is_some() {
             return Ok(());
         }
         self.ensure_undecided()?;
 
         let mut children: FastHashMap<Revision, Vec<Revision>> =
             FastHashMap::default();
         for &rev in self.undecided.as_ref().unwrap() {
             for p in ParentsIterator::graph_parents(&self.graph, rev)? {
-                children.entry(p).or_insert_with(|| Vec::new()).push(rev);
+                children.entry(p).or_insert_with(Vec::new).push(rev);
             }
         }
         self.children_cache = Some(children);
         Ok(())
     }
 
     /// Provide statistics about the current state of the discovery process
     pub fn stats(&self) -> DiscoveryStats {
         DiscoveryStats {
-            undecided: self.undecided.as_ref().map(|s| s.len()),
+            undecided: self.undecided.as_ref().map(HashSet::len),
         }
     }
 
     pub fn take_quick_sample(
         &mut self,
         headrevs: impl IntoIterator<Item = Revision>,
         size: usize,
     ) -> Result<Vec<Revision>, GraphError> {
         self.ensure_undecided()?;
         let mut sample = {
             let undecided = self.undecided.as_ref().unwrap();
             if undecided.len() <= size {
                 return Ok(undecided.iter().cloned().collect());
             }
             dagops::heads(&self.graph, undecided.iter())?
         };
         if sample.len() >= size {
             return Ok(self.limit_sample(sample.into_iter().collect(), size));
         }
         update_sample(
             None,
             headrevs,
             &mut sample,
             |r| ParentsIterator::graph_parents(&self.graph, r),
             Some(size),
         )?;
         Ok(sample.into_iter().collect())
     }
 
     /// Extract a sample from `self.undecided`, going from its heads and roots.
     ///
     /// The `size` parameter is used to avoid useless computations if
     /// it turns out to be bigger than the whole set of undecided Revisions.
     ///
     /// The sample is taken by using `update_sample` from the heads, then
     /// from the roots, working on the reverse DAG,
     /// expressed by `self.children_cache`.
     ///
     /// No effort is being made to complete or limit the sample to `size`
     /// but this method returns another interesting size that it derives
     /// from its knowledge of the structure of the various sets, leaving
     /// to the caller the decision to use it or not.
     fn bidirectional_sample(
         &mut self,
         size: usize,
     ) -> Result<(HashSet<Revision>, usize), GraphError> {
         self.ensure_undecided()?;
         {
             // we don't want to compute children_cache before this
             // but doing it after extracting self.undecided takes a mutable
             // ref to self while a shareable one is still active.
             let undecided = self.undecided.as_ref().unwrap();
             if undecided.len() <= size {
                 return Ok((undecided.clone(), size));
             }
         }
 
         self.ensure_children_cache()?;
         let revs = self.undecided.as_ref().unwrap();
         let mut sample: HashSet<Revision> = revs.clone();
 
         // it's possible that leveraging the children cache would be more
         // efficient here
         dagops::retain_heads(&self.graph, &mut sample)?;
         let revsheads = sample.clone(); // was again heads(revs) in python
 
         // update from heads
         update_sample(
             Some(revs),
             revsheads.iter().cloned(),
             &mut sample,
             |r| ParentsIterator::graph_parents(&self.graph, r),
             None,
         )?;
 
         // update from roots
         let revroots: HashSet<Revision> =
             dagops::roots(&self.graph, revs)?.into_iter().collect();
         let prescribed_size = max(size, min(revroots.len(), revsheads.len()));
 
         let children = self.children_cache.as_ref().unwrap();
         let empty_vec: Vec<Revision> = Vec::new();
         update_sample(
             Some(revs),
             revroots,
             &mut sample,
             |r| Ok(children.get(&r).unwrap_or(&empty_vec).iter().cloned()),
             None,
         )?;
         Ok((sample, prescribed_size))
     }
 
     /// Fill up sample up to the wished size with random undecided Revisions.
     ///
     /// This is intended to be used as a last resort completion if the
     /// regular sampling algorithm returns too few elements.
     fn random_complete_sample(
         &mut self,
         sample: &mut Vec<Revision>,
         size: usize,
     ) {
         let sample_len = sample.len();
         if size <= sample_len {
             return;
         }
         let take_from: Vec<Revision> = self
             .undecided
             .as_ref()
             .unwrap()
             .iter()
             .filter(|&r| !sample.contains(r))
             .cloned()
             .collect();
         sample.extend(self.limit_sample(take_from, size - sample_len));
     }
 
     pub fn take_full_sample(
         &mut self,
         size: usize,
     ) -> Result<Vec<Revision>, GraphError> {
         let (sample_set, prescribed_size) = self.bidirectional_sample(size)?;
         let size = if self.respect_size {
             size
         } else {
             prescribed_size
         };
         let mut sample =
             self.limit_sample(sample_set.into_iter().collect(), size);
         self.random_complete_sample(&mut sample, size);
         Ok(sample)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::testing::SampleGraph;
 
     /// A PartialDiscovery as for pushing all the heads of `SampleGraph`
     ///
     /// To avoid actual randomness in these tests, we give it a fixed
     /// random seed, but by default we'll test the random version.
     fn full_disco() -> PartialDiscovery<SampleGraph> {
         PartialDiscovery::new_with_seed(
             SampleGraph,
             vec![10, 11, 12, 13],
             [0; 16],
             true,
             true,
         )
     }
 
     /// A PartialDiscovery as for pushing the 12 head of `SampleGraph`
     ///
     /// To avoid actual randomness in tests, we give it a fixed random seed.
     fn disco12() -> PartialDiscovery<SampleGraph> {
         PartialDiscovery::new_with_seed(
             SampleGraph,
             vec![12],
             [0; 16],
             true,
             true,
         )
     }
 
     fn sorted_undecided(
         disco: &PartialDiscovery<SampleGraph>,
     ) -> Vec<Revision> {
         let mut as_vec: Vec<Revision> =
             disco.undecided.as_ref().unwrap().iter().cloned().collect();
         as_vec.sort();
         as_vec
     }
 
     fn sorted_missing(disco: &PartialDiscovery<SampleGraph>) -> Vec<Revision> {
         let mut as_vec: Vec<Revision> =
             disco.missing.iter().cloned().collect();
         as_vec.sort();
         as_vec
     }
 
     fn sorted_common_heads(
         disco: &PartialDiscovery<SampleGraph>,
     ) -> Result<Vec<Revision>, GraphError> {
         let mut as_vec: Vec<Revision> =
             disco.common_heads()?.iter().cloned().collect();
         as_vec.sort();
         Ok(as_vec)
     }
 
     #[test]
     fn test_add_common_get_undecided() -> Result<(), GraphError> {
         let mut disco = full_disco();
         assert_eq!(disco.undecided, None);
         assert!(!disco.has_info());
         assert_eq!(disco.stats().undecided, None);
 
         disco.add_common_revisions(vec![11, 12])?;
         assert!(disco.has_info());
         assert!(!disco.is_complete());
         assert!(disco.missing.is_empty());
 
         // add_common_revisions did not trigger a premature computation
         // of `undecided`, let's check that and ask for them
         assert_eq!(disco.undecided, None);
         disco.ensure_undecided()?;
         assert_eq!(sorted_undecided(&disco), vec![5, 8, 10, 13]);
         assert_eq!(disco.stats().undecided, Some(4));
         Ok(())
     }
 
     /// in this test, we pretend that our peer misses exactly (8+10)::
     /// and we're comparing all our repo to it (as in a bare push)
     #[test]
     fn test_discovery() -> Result<(), GraphError> {
         let mut disco = full_disco();
         disco.add_common_revisions(vec![11, 12])?;
         disco.add_missing_revisions(vec![8, 10])?;
         assert_eq!(sorted_undecided(&disco), vec![5]);
         assert_eq!(sorted_missing(&disco), vec![8, 10, 13]);
         assert!(!disco.is_complete());
 
         disco.add_common_revisions(vec![5])?;
         assert_eq!(sorted_undecided(&disco), vec![]);
         assert_eq!(sorted_missing(&disco), vec![8, 10, 13]);
         assert!(disco.is_complete());
         assert_eq!(sorted_common_heads(&disco)?, vec![5, 11, 12]);
         Ok(())
     }
 
     #[test]
     fn test_add_missing_early_continue() -> Result<(), GraphError> {
         eprintln!("test_add_missing_early_stop");
         let mut disco = full_disco();
         disco.add_common_revisions(vec![13, 3, 4])?;
         disco.ensure_children_cache()?;
         // 12 is grand-child of 6 through 9
         // passing them in this order maximizes the chances of the
         // early continue to do the wrong thing
         disco.add_missing_revisions(vec![6, 9, 12])?;
         assert_eq!(sorted_undecided(&disco), vec![5, 7, 10, 11]);
         assert_eq!(sorted_missing(&disco), vec![6, 9, 12]);
         assert!(!disco.is_complete());
         Ok(())
     }
 
     #[test]
     fn test_limit_sample_no_need_to() {
         let sample = vec![1, 2, 3, 4];
         assert_eq!(full_disco().limit_sample(sample, 10), vec![1, 2, 3, 4]);
     }
 
     #[test]
     fn test_limit_sample_less_than_half() {
         assert_eq!(full_disco().limit_sample((1..6).collect(), 2), vec![2, 5]);
     }
 
     #[test]
     fn test_limit_sample_more_than_half() {
         assert_eq!(full_disco().limit_sample((1..4).collect(), 2), vec![1, 2]);
     }
 
     #[test]
     fn test_limit_sample_no_random() {
         let mut disco = full_disco();
         disco.randomize = false;
         assert_eq!(
             disco.limit_sample(vec![1, 8, 13, 5, 7, 3], 4),
             vec![1, 3, 5, 7]
         );
     }
 
     #[test]
     fn test_quick_sample_enough_undecided_heads() -> Result<(), GraphError> {
         let mut disco = full_disco();
         disco.undecided = Some((1..=13).collect());
 
         let mut sample_vec = disco.take_quick_sample(vec![], 4)?;
         sample_vec.sort();
         assert_eq!(sample_vec, vec![10, 11, 12, 13]);
         Ok(())
     }
 
     #[test]
     fn test_quick_sample_climbing_from_12() -> Result<(), GraphError> {
         let mut disco = disco12();
         disco.ensure_undecided()?;
 
         let mut sample_vec = disco.take_quick_sample(vec![12], 4)?;
         sample_vec.sort();
         // r12's only parent is r9, whose unique grand-parent through the
         // diamond shape is r4. This ends there because the distance from r4
         // to the root is only 3.
         assert_eq!(sample_vec, vec![4, 9, 12]);
         Ok(())
     }
 
     #[test]
     fn test_children_cache() -> Result<(), GraphError> {
         let mut disco = full_disco();
         disco.ensure_children_cache()?;
 
         let cache = disco.children_cache.unwrap();
         assert_eq!(cache.get(&2).cloned(), Some(vec![4]));
         assert_eq!(cache.get(&10).cloned(), None);
 
         let mut children_4 = cache.get(&4).cloned().unwrap();
         children_4.sort();
         assert_eq!(children_4, vec![5, 6, 7]);
 
         let mut children_7 = cache.get(&7).cloned().unwrap();
         children_7.sort();
         assert_eq!(children_7, vec![9, 11]);
 
         Ok(())
     }
 
     #[test]
     fn test_complete_sample() {
         let mut disco = full_disco();
         let undecided: HashSet<Revision> =
             [4, 7, 9, 2, 3].iter().cloned().collect();
         disco.undecided = Some(undecided);
 
         let mut sample = vec![0];
         disco.random_complete_sample(&mut sample, 3);
         assert_eq!(sample.len(), 3);
 
         let mut sample = vec![2, 4, 7];
         disco.random_complete_sample(&mut sample, 1);
         assert_eq!(sample.len(), 3);
     }
 
     #[test]
     fn test_bidirectional_sample() -> Result<(), GraphError> {
         let mut disco = full_disco();
         disco.undecided = Some((0..=13).into_iter().collect());
 
         let (sample_set, size) = disco.bidirectional_sample(7)?;
         assert_eq!(size, 7);
         let mut sample: Vec<Revision> = sample_set.into_iter().collect();
         sample.sort();
         // our DAG is a bit too small for the results to be really interesting
         // at least it shows that
         // - we went both ways
         // - we didn't take all Revisions (6 is not in the sample)
         assert_eq!(sample, vec![0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13]);
         Ok(())
     }
 }

rust/hg-core/src/filepatterns.rs

@@ -1,669 +1,670
 // filepatterns.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.
 
 //! Handling of Mercurial-specific patterns.
 
 use crate::{
     utils::{
         files::{canonical_path, get_bytes_from_path, get_path_from_bytes},
         hg_path::{path_to_hg_path_buf, HgPathBuf, HgPathError},
         SliceExt,
     },
     FastHashMap, PatternError,
 };
 use lazy_static::lazy_static;
 use regex::bytes::{NoExpand, Regex};
 use std::fs::File;
 use std::io::Read;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 use std::vec::Vec;
 
 lazy_static! {
     static ref RE_ESCAPE: Vec<Vec<u8>> = {
         let mut v: Vec<Vec<u8>> = (0..=255).map(|byte| vec![byte]).collect();
         let to_escape = b"()[]{}?*+-|^$\\.&~# \t\n\r\x0b\x0c";
         for byte in to_escape {
             v[*byte as usize].insert(0, b'\\');
         }
         v
     };
 }
 
 /// These are matched in order
 const GLOB_REPLACEMENTS: &[(&[u8], &[u8])] =
     &[(b"*/", b"(?:.*/)?"), (b"*", b".*"), (b"", b"[^/]*")];
 
 /// Appended to the regexp of globs
 const GLOB_SUFFIX: &[u8; 7] = b"(?:/|$)";
 
 #[derive(Debug, Copy, Clone, PartialEq, Eq)]
 pub enum PatternSyntax {
     /// A regular expression
     Regexp,
     /// Glob that matches at the front of the path
     RootGlob,
     /// Glob that matches at any suffix of the path (still anchored at
     /// slashes)
     Glob,
     /// a path relative to repository root, which is matched recursively
     Path,
     /// A path relative to cwd
     RelPath,
     /// an unrooted glob (*.rs matches Rust files in all dirs)
     RelGlob,
     /// A regexp that needn't match the start of a name
     RelRegexp,
     /// A path relative to repository root, which is matched non-recursively
     /// (will not match subdirectories)
     RootFiles,
     /// A file of patterns to read and include
     Include,
     /// A file of patterns to match against files under the same directory
     SubInclude,
 }
 
 /// Transforms a glob pattern into a regex
 fn glob_to_re(pat: &[u8]) -> Vec<u8> {
     let mut input = pat;
     let mut res: Vec<u8> = vec![];
     let mut group_depth = 0;
 
     while let Some((c, rest)) = input.split_first() {
         input = rest;
 
         match c {
             b'*' => {
                 for (source, repl) in GLOB_REPLACEMENTS {
                     if let Some(rest) = input.drop_prefix(source) {
                         input = rest;
                         res.extend(*repl);
                         break;
                     }
                 }
             }
             b'?' => res.extend(b"."),
             b'[' => {
                 match input.iter().skip(1).position(|b| *b == b']') {
                     None => res.extend(b"\\["),
                     Some(end) => {
                         // Account for the one we skipped
                         let end = end + 1;
 
                         res.extend(b"[");
 
                         for (i, b) in input[..end].iter().enumerate() {
                             if *b == b'!' && i == 0 {
                                 res.extend(b"^")
                             } else if *b == b'^' && i == 0 {
                                 res.extend(b"\\^")
                             } else if *b == b'\\' {
                                 res.extend(b"\\\\")
                             } else {
                                 res.push(*b)
                             }
                         }
                         res.extend(b"]");
                         input = &input[end + 1..];
                     }
                 }
             }
             b'{' => {
                 group_depth += 1;
                 res.extend(b"(?:")
             }
             b'}' if group_depth > 0 => {
                 group_depth -= 1;
                 res.extend(b")");
             }
             b',' if group_depth > 0 => res.extend(b"|"),
             b'\\' => {
                 let c = {
                     if let Some((c, rest)) = input.split_first() {
                         input = rest;
                         c
                     } else {
                         c
                     }
                 };
                 res.extend(&RE_ESCAPE[*c as usize])
             }
             _ => res.extend(&RE_ESCAPE[*c as usize]),
         }
     }
     res
 }
 
 fn escape_pattern(pattern: &[u8]) -> Vec<u8> {
     pattern
         .iter()
         .flat_map(|c| RE_ESCAPE[*c as usize].clone())
         .collect()
 }
 
 pub fn parse_pattern_syntax(
     kind: &[u8],
 ) -> Result<PatternSyntax, PatternError> {
     match kind {
         b"re:" => Ok(PatternSyntax::Regexp),
         b"path:" => Ok(PatternSyntax::Path),
         b"relpath:" => Ok(PatternSyntax::RelPath),
         b"rootfilesin:" => Ok(PatternSyntax::RootFiles),
         b"relglob:" => Ok(PatternSyntax::RelGlob),
         b"relre:" => Ok(PatternSyntax::RelRegexp),
         b"glob:" => Ok(PatternSyntax::Glob),
         b"rootglob:" => Ok(PatternSyntax::RootGlob),
         b"include:" => Ok(PatternSyntax::Include),
         b"subinclude:" => Ok(PatternSyntax::SubInclude),
         _ => Err(PatternError::UnsupportedSyntax(
             String::from_utf8_lossy(kind).to_string(),
         )),
     }
 }
 
 /// Builds the regex that corresponds to the given pattern.
 /// If within a `syntax: regexp` context, returns the pattern,
 /// otherwise, returns the corresponding regex.
 fn _build_single_regex(entry: &IgnorePattern) -> Vec<u8> {
     let IgnorePattern {
         syntax, pattern, ..
     } = entry;
     if pattern.is_empty() {
         return vec![];
     }
     match syntax {
         PatternSyntax::Regexp => pattern.to_owned(),
         PatternSyntax::RelRegexp => {
             // The `regex` crate accepts `**` while `re2` and Python's `re`
             // do not. Checking for `*` correctly triggers the same error all
             // engines.
             if pattern[0] == b'^'
                 || pattern[0] == b'*'
                 || pattern.starts_with(b".*")
             {
                 return pattern.to_owned();
             }
             [&b".*"[..], pattern].concat()
         }
         PatternSyntax::Path | PatternSyntax::RelPath => {
             if pattern == b"." {
                 return vec![];
             }
             [escape_pattern(pattern).as_slice(), b"(?:/|$)"].concat()
         }
         PatternSyntax::RootFiles => {
             let mut res = if pattern == b"." {
                 vec![]
             } else {
                 // Pattern is a directory name.
                 [escape_pattern(pattern).as_slice(), b"/"].concat()
             };
 
             // Anything after the pattern must be a non-directory.
             res.extend(b"[^/]+$");
             res
         }
         PatternSyntax::RelGlob => {
             let glob_re = glob_to_re(pattern);
             if let Some(rest) = glob_re.drop_prefix(b"[^/]*") {
                 [b".*", rest, GLOB_SUFFIX].concat()
             } else {
                 [b"(?:.*/)?", glob_re.as_slice(), GLOB_SUFFIX].concat()
             }
         }
         PatternSyntax::Glob | PatternSyntax::RootGlob => {
             [glob_to_re(pattern).as_slice(), GLOB_SUFFIX].concat()
         }
         PatternSyntax::Include | PatternSyntax::SubInclude => unreachable!(),
     }
 }
 
 const GLOB_SPECIAL_CHARACTERS: [u8; 7] =
     [b'*', b'?', b'[', b']', b'{', b'}', b'\\'];
 
 /// TODO support other platforms
 #[cfg(unix)]
 pub fn normalize_path_bytes(bytes: &[u8]) -> Vec<u8> {
     if bytes.is_empty() {
         return b".".to_vec();
     }
     let sep = b'/';
 
     let mut initial_slashes = bytes.iter().take_while(|b| **b == sep).count();
     if initial_slashes > 2 {
         // POSIX allows one or two initial slashes, but treats three or more
         // as single slash.
         initial_slashes = 1;
     }
     let components = bytes
         .split(|b| *b == sep)
         .filter(|c| !(c.is_empty() || c == b"."))
         .fold(vec![], |mut acc, component| {
             if component != b".."
                 || (initial_slashes == 0 && acc.is_empty())
                 || (!acc.is_empty() && acc[acc.len() - 1] == b"..")
             {
                 acc.push(component)
             } else if !acc.is_empty() {
                 acc.pop();
             }
             acc
         });
     let mut new_bytes = components.join(&sep);
 
     if initial_slashes > 0 {
         let mut buf: Vec<_> = (0..initial_slashes).map(|_| sep).collect();
         buf.extend(new_bytes);
         new_bytes = buf;
     }
     if new_bytes.is_empty() {
         b".".to_vec()
     } else {
         new_bytes
     }
 }
 
 /// Wrapper function to `_build_single_regex` that short-circuits 'exact' globs
 /// that don't need to be transformed into a regex.
 pub fn build_single_regex(
     entry: &IgnorePattern,
 ) -> Result<Option<Vec<u8>>, PatternError> {
     let IgnorePattern {
         pattern, syntax, ..
     } = entry;
     let pattern = match syntax {
         PatternSyntax::RootGlob
         | PatternSyntax::Path
         | PatternSyntax::RelGlob
         | PatternSyntax::RootFiles => normalize_path_bytes(&pattern),
         PatternSyntax::Include | PatternSyntax::SubInclude => {
             return Err(PatternError::NonRegexPattern(entry.clone()))
         }
         _ => pattern.to_owned(),
     };
     if *syntax == PatternSyntax::RootGlob
         && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
     {
         Ok(None)
     } else {
         let mut entry = entry.clone();
         entry.pattern = pattern;
         Ok(Some(_build_single_regex(&entry)))
     }
 }
 
 lazy_static! {
     static ref SYNTAXES: FastHashMap<&'static [u8], &'static [u8]> = {
         let mut m = FastHashMap::default();
 
         m.insert(b"re".as_ref(), b"relre:".as_ref());
         m.insert(b"regexp".as_ref(), b"relre:".as_ref());
         m.insert(b"glob".as_ref(), b"relglob:".as_ref());
         m.insert(b"rootglob".as_ref(), b"rootglob:".as_ref());
         m.insert(b"include".as_ref(), b"include:".as_ref());
         m.insert(b"subinclude".as_ref(), b"subinclude:".as_ref());
         m
     };
 }
 
 #[derive(Debug)]
 pub enum PatternFileWarning {
     /// (file path, syntax bytes)
     InvalidSyntax(PathBuf, Vec<u8>),
     /// File path
     NoSuchFile(PathBuf),
 }
 
 pub fn parse_pattern_file_contents<P: AsRef<Path>>(
     lines: &[u8],
     file_path: P,
     warn: bool,
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     let comment_regex = Regex::new(r"((?:^|[^\\])(?:\\\\)*)#.*").unwrap();
+
+    #[allow(clippy::trivial_regex)]
     let comment_escape_regex = Regex::new(r"\\#").unwrap();
     let mut inputs: Vec<IgnorePattern> = vec![];
     let mut warnings: Vec<PatternFileWarning> = vec![];
 
     let mut current_syntax = b"relre:".as_ref();
 
     for (line_number, mut line) in lines.split(|c| *c == b'\n').enumerate() {
         let line_number = line_number + 1;
 
         let line_buf;
         if line.contains(&b'#') {
             if let Some(cap) = comment_regex.captures(line) {
                 line = &line[..cap.get(1).unwrap().end()]
             }
             line_buf = comment_escape_regex.replace_all(line, NoExpand(b"#"));
             line = &line_buf;
         }
 
         let mut line = line.trim_end();
 
         if line.is_empty() {
             continue;
         }
 
         if let Some(syntax) = line.drop_prefix(b"syntax:") {
             let syntax = syntax.trim();
 
             if let Some(rel_syntax) = SYNTAXES.get(syntax) {
                 current_syntax = rel_syntax;
             } else if warn {
                 warnings.push(PatternFileWarning::InvalidSyntax(
                     file_path.as_ref().to_owned(),
                     syntax.to_owned(),
                 ));
             }
             continue;
         }
 
         let mut line_syntax: &[u8] = &current_syntax;
 
         for (s, rels) in SYNTAXES.iter() {
             if let Some(rest) = line.drop_prefix(rels) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
             if let Some(rest) = line.drop_prefix(&[s, &b":"[..]].concat()) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
         }
 
         inputs.push(IgnorePattern::new(
             parse_pattern_syntax(&line_syntax).map_err(|e| match e {
                 PatternError::UnsupportedSyntax(syntax) => {
                     PatternError::UnsupportedSyntaxInFile(
                         syntax,
                         file_path.as_ref().to_string_lossy().into(),
                         line_number,
                     )
                 }
                 _ => e,
             })?,
             &line,
             &file_path,
         ));
     }
     Ok((inputs, warnings))
 }
 
 pub fn read_pattern_file<P: AsRef<Path>>(
     file_path: P,
     warn: bool,
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     let mut f = match File::open(file_path.as_ref()) {
         Ok(f) => Ok(f),
         Err(e) => match e.kind() {
             std::io::ErrorKind::NotFound => {
                 return Ok((
                     vec![],
                     vec![PatternFileWarning::NoSuchFile(
                         file_path.as_ref().to_owned(),
                     )],
                 ))
             }
             _ => Err(e),
         },
     }?;
     let mut contents = Vec::new();
 
     f.read_to_end(&mut contents)?;
 
     Ok(parse_pattern_file_contents(&contents, file_path, warn)?)
 }
 
 /// Represents an entry in an "ignore" file.
 #[derive(Debug, Eq, PartialEq, Clone)]
 pub struct IgnorePattern {
     pub syntax: PatternSyntax,
     pub pattern: Vec<u8>,
     pub source: PathBuf,
 }
 
 impl IgnorePattern {
     pub fn new(
         syntax: PatternSyntax,
         pattern: &[u8],
         source: impl AsRef<Path>,
     ) -> Self {
         Self {
             syntax,
             pattern: pattern.to_owned(),
             source: source.as_ref().to_owned(),
         }
     }
 }
 
 pub type PatternResult<T> = Result<T, PatternError>;
 
 /// Wrapper for `read_pattern_file` that also recursively expands `include:`
 /// patterns.
 ///
 /// `subinclude:` is not treated as a special pattern here: unraveling them
 /// needs to occur in the "ignore" phase.
 pub fn get_patterns_from_file(
     pattern_file: impl AsRef<Path>,
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(Vec<IgnorePattern>, Vec<PatternFileWarning>)> {
     let (patterns, mut warnings) = read_pattern_file(&pattern_file, true)?;
     let patterns = patterns
         .into_iter()
         .flat_map(|entry| -> PatternResult<_> {
             let IgnorePattern {
-                syntax,
-                pattern,
-                source: _,
+                syntax, pattern, ..
             } = &entry;
             Ok(match syntax {
                 PatternSyntax::Include => {
                     let inner_include =
                         root_dir.as_ref().join(get_path_from_bytes(&pattern));
                     let (inner_pats, inner_warnings) = get_patterns_from_file(
                         &inner_include,
                         root_dir.as_ref(),
                     )?;
                     warnings.extend(inner_warnings);
                     inner_pats
                 }
                 _ => vec![entry],
             })
         })
         .flatten()
         .collect();
 
     Ok((patterns, warnings))
 }
 
 /// Holds all the information needed to handle a `subinclude:` pattern.
 pub struct SubInclude {
     /// Will be used for repository (hg) paths that start with this prefix.
     /// It is relative to the current working directory, so comparing against
     /// repository paths is painless.
     pub prefix: HgPathBuf,
     /// The file itself, containing the patterns
     pub path: PathBuf,
     /// Folder in the filesystem where this it applies
     pub root: PathBuf,
 }
 
 impl SubInclude {
     pub fn new(
         root_dir: impl AsRef<Path>,
         pattern: &[u8],
         source: impl AsRef<Path>,
     ) -> Result<SubInclude, HgPathError> {
         let normalized_source =
             normalize_path_bytes(&get_bytes_from_path(source));
 
         let source_root = get_path_from_bytes(&normalized_source);
-        let source_root = source_root.parent().unwrap_or(source_root.deref());
+        let source_root =
+            source_root.parent().unwrap_or_else(|| source_root.deref());
 
         let path = source_root.join(get_path_from_bytes(pattern));
-        let new_root = path.parent().unwrap_or(path.deref());
+        let new_root = path.parent().unwrap_or_else(|| path.deref());
 
         let prefix = canonical_path(&root_dir, &root_dir, new_root)?;
 
         Ok(Self {
             prefix: path_to_hg_path_buf(prefix).and_then(|mut p| {
                 if !p.is_empty() {
                     p.push(b'/');
                 }
                 Ok(p)
             })?,
             path: path.to_owned(),
             root: new_root.to_owned(),
         })
     }
 }
 
 /// Separate and pre-process subincludes from other patterns for the "ignore"
 /// phase.
 pub fn filter_subincludes(
     ignore_patterns: &[IgnorePattern],
     root_dir: impl AsRef<Path>,
 ) -> Result<(Vec<SubInclude>, Vec<&IgnorePattern>), HgPathError> {
     let mut subincludes = vec![];
     let mut others = vec![];
 
     for ignore_pattern in ignore_patterns.iter() {
         let IgnorePattern {
             syntax,
             pattern,
             source,
         } = ignore_pattern;
         if *syntax == PatternSyntax::SubInclude {
             subincludes.push(SubInclude::new(&root_dir, pattern, &source)?);
         } else {
             others.push(ignore_pattern)
         }
     }
     Ok((subincludes, others))
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn escape_pattern_test() {
         let untouched =
             br#"!"%',/0123456789:;<=>@ABCDEFGHIJKLMNOPQRSTUVWXYZ_`abcdefghijklmnopqrstuvwxyz"#;
         assert_eq!(escape_pattern(untouched), untouched.to_vec());
         // All escape codes
         assert_eq!(
             escape_pattern(br#"()[]{}?*+-|^$\\.&~# \t\n\r\v\f"#),
             br#"\(\)\[\]\{\}\?\*\+\-\|\^\$\\\\\.\&\~\#\ \\t\\n\\r\\v\\f"#
                 .to_vec()
         );
     }
 
     #[test]
     fn glob_test() {
         assert_eq!(glob_to_re(br#"?"#), br#"."#);
         assert_eq!(glob_to_re(br#"*"#), br#"[^/]*"#);
         assert_eq!(glob_to_re(br#"**"#), br#".*"#);
         assert_eq!(glob_to_re(br#"**/a"#), br#"(?:.*/)?a"#);
         assert_eq!(glob_to_re(br#"a/**/b"#), br#"a/(?:.*/)?b"#);
         assert_eq!(glob_to_re(br#"[a*?!^][^b][!c]"#), br#"[a*?!^][\^b][^c]"#);
         assert_eq!(glob_to_re(br#"{a,b}"#), br#"(?:a|b)"#);
         assert_eq!(glob_to_re(br#".\*\?"#), br#"\.\*\?"#);
     }
 
     #[test]
     fn test_parse_pattern_file_contents() {
         let lines = b"syntax: glob\n*.elc";
 
         assert_eq!(
             parse_pattern_file_contents(lines, Path::new("file_path"), false)
                 .unwrap()
                 .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"*.elc",
                 Path::new("file_path")
             )],
         );
 
         let lines = b"syntax: include\nsyntax: glob";
 
         assert_eq!(
             parse_pattern_file_contents(lines, Path::new("file_path"), false)
                 .unwrap()
                 .0,
             vec![]
         );
         let lines = b"glob:**.o";
         assert_eq!(
             parse_pattern_file_contents(lines, Path::new("file_path"), false)
                 .unwrap()
                 .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"**.o",
                 Path::new("file_path")
             )]
         );
     }
 
     #[test]
     fn test_build_single_regex() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"rust/target/",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()),
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::Regexp,
                 br"rust/target/\d+",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"rust/target/\d+".to_vec()),
         );
     }
 
     #[test]
     fn test_build_single_regex_shortcut() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"whatever",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"*.o",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"[^/]*\.o(?:/|$)".to_vec()),
         );
     }
 }

rust/hg-core/src/matchers.rs

@@ -1,937 +1,937
 // matchers.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Structs and types for matching files and directories.
 
 use 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 crate::filepatterns::normalize_path_bytes;
 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, PathBuf};
 
 use micro_timer::timed;
 
 #[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())),
+            files: HashSet::from_iter(files.iter().map(AsRef::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 dirs_as_set = self.dirs.iter().map(Deref::deref).collect();
 
         let mut candidates: HashSet<&HgPath> =
-            self.files.union(&dirs_as_set).map(|k| *k).collect();
+            self.files.union(&dirs_as_set).cloned().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.
 /// ```
 /// 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
     }
 }
 
 /// 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.
 #[timed]
 fn re_matcher(
     pattern: &[u8],
 ) -> PatternResult<impl Fn(&HgPath) -> bool + Sync> {
     use std::io::Write;
 
     // The `regex` crate adds `.*` to the start and end of expressions if there
     // are no anchors, so add the start anchor.
     let mut escaped_bytes = vec![b'^', b'(', b'?', b':'];
     for byte in pattern {
         if *byte > 127 {
             write!(escaped_bytes, "\\x{:x}", *byte).unwrap();
         } else {
             escaped_bytes.push(*byte);
         }
     }
     escaped_bytes.push(b')');
 
     // Avoid the cost of UTF8 checking
     //
     // # Safety
     // This is safe because we escaped all non-ASCII bytes.
     let pattern_string = unsafe { String::from_utf8_unchecked(escaped_bytes) };
     let re = regex::bytes::RegexBuilder::new(&pattern_string)
         .unicode(false)
         // Big repos with big `.hgignore` will hit the default limit and
         // incur a significant performance hit. One repo's `hg status` hit
         // multiple *minutes*.
         .dfa_size_limit(50 * (1 << 20))
         .build()
         .map_err(|e| PatternError::UnsupportedSyntax(e.to_string()))?;
 
     Ok(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 mut regexps = vec![];
     let mut exact_set = HashSet::new();
 
     for pattern in ignore_patterns {
         if let Some(re) = build_single_regex(pattern)? {
             regexps.push(re);
         } else {
             let exact = normalize_path_bytes(&pattern.pattern);
             exact_set.insert(HgPathBuf::from_bytes(&exact));
         }
     }
 
     let full_regex = regexps.join(&b'|');
 
     // An empty pattern would cause the regex engine to incorrectly match the
     // (empty) root directory
     let func = if !(regexps.is_empty()) {
         let matcher = re_matcher(&full_regex)?;
         let func = move |filename: &HgPath| {
             exact_set.contains(filename) || matcher(filename)
         };
         Box::new(func) as Box<dyn Fn(&HgPath) -> bool + Sync>
     } else {
         let func = move |filename: &HgPath| exact_set.contains(filename);
         Box::new(func) as Box<dyn Fn(&HgPath) -> bool + Sync>
     };
 
     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()),
+            .map(ToOwned::to_owned),
     );
     parents.extend(
         DirsMultiset::from_manifest(&roots)
             .map_err(|e| match e {
                 DirstateMapError::InvalidPath(e) => e,
                 _ => unreachable!(),
             })?
             .iter()
-            .map(|k| k.to_owned()),
+            .map(ToOwned::to_owned),
     );
 
     Ok(RootsDirsAndParents {
         roots: HashSet::from_iter(roots),
         dirs: HashSet::from_iter(dirs),
         parents,
     })
 }
 
 /// Returns a function that checks whether a given file (in the general sense)
 /// should be matched.
 fn build_match<'a, '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(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) {
+                    if (submatchers[prefix])(rel) {
                         return true;
                     }
                 }
             }
             false
         };
 
         match_funcs.push(Box::new(match_subinclude));
     }
 
     if !ignore_patterns.is_empty() {
         // Either do dumb matching if all patterns are rootfiles, or match
         // with a regex.
         if ignore_patterns
             .iter()
             .all(|k| k.syntax == PatternSyntax::RootFiles)
         {
             let dirs: HashSet<_> = ignore_patterns
                 .iter()
                 .map(|k| k.pattern.to_owned())
                 .collect();
             let mut dirs_vec: Vec<_> = dirs.iter().cloned().collect();
 
             let match_func = move |path: &HgPath| -> bool {
                 let path = path.as_bytes();
                 let i = path.iter().rfind(|a| **a == b'/');
                 let dir = if let Some(i) = i {
                     &path[..*i as usize]
                 } else {
                     b"."
                 };
                 dirs.contains(dir.deref())
             };
             match_funcs.push(Box::new(match_func));
 
             patterns.extend(b"rootfilesin: ");
             dirs_vec.sort();
             patterns.extend(dirs_vec.escaped_bytes());
         } else {
             let (new_re, match_func) = build_regex_match(&ignore_patterns)?;
             patterns = new_re;
             match_funcs.push(match_func)
         }
     }
 
     Ok(if match_funcs.len() == 1 {
         (patterns, match_funcs.remove(0), all_warnings)
     } else {
         (
             patterns,
             Box::new(move |f: &HgPath| -> bool {
                 match_funcs.iter().any(|match_func| match_func(f))
             }),
             all_warnings,
         )
     })
 }
 
 /// Parses all "ignore" files with their recursive includes and returns a
 /// function that checks whether a given file (in the general sense) should be
 /// ignored.
 pub fn get_ignore_function<'a>(
     all_pattern_files: Vec<PathBuf>,
     root_dir: impl AsRef<Path>,
 ) -> PatternResult<(
     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.to_owned());
         all_warnings.extend(warnings);
     }
     let (matcher, warnings) = IncludeMatcher::new(all_patterns, root_dir)?;
     all_warnings.extend(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> {
         // XXX What about exact matches?
         // I'm not sure it's worth it to clone the HashSet and keep it
         // around just in case someone wants to display the matcher, plus
         // it's going to be unreadable after a few entries, but we need to
         // inform in this display that exact matches are being used and are
         // (on purpose) missing from the `includes`.
         write!(
             f,
             "IncludeMatcher(includes='{}')",
             String::from_utf8_lossy(&self.patterns.escaped_bytes())
         )
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
     use std::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
         );
     }
 
     #[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-core/src/revlog.rs

@@ -1,56 +1,61
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 //! Mercurial concepts for handling revision history
 
 pub mod node;
 pub mod nodemap;
 pub use node::{Node, NodeError, NodePrefix, NodePrefixRef};
 
 /// Mercurial revision numbers
 ///
 /// As noted in revlog.c, revision numbers are actually encoded in
 /// 4 bytes, and are liberally converted to ints, whence the i32
 pub type Revision = i32;
 
 /// Marker expressing the absence of a parent
 ///
 /// Independently of the actual representation, `NULL_REVISION` is guaranteed
 /// to be smaller than all existing revisions.
 pub const NULL_REVISION: Revision = -1;
 
 /// Same as `mercurial.node.wdirrev`
 ///
 /// This is also equal to `i32::max_value()`, but it's better to spell
 /// it out explicitely, same as in `mercurial.node`
+#[allow(clippy::unreadable_literal)]
 pub const WORKING_DIRECTORY_REVISION: Revision = 0x7fffffff;
 
 /// The simplest expression of what we need of Mercurial DAGs.
 pub trait Graph {
     /// Return the two parents of the given `Revision`.
     ///
     /// Each of the parents can be independently `NULL_REVISION`
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError>;
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
     WorkingDirectoryUnsupported,
 }
 
 /// The Mercurial Revlog Index
 ///
 /// This is currently limited to the minimal interface that is needed for
 /// the [`nodemap`](nodemap/index.html) module
 pub trait RevlogIndex {
     /// Total number of Revisions referenced in this index
     fn len(&self) -> usize;
 
+    fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
     /// Return a reference to the Node or `None` if rev is out of bounds
     ///
     /// `NULL_REVISION` is not considered to be out of bounds.
     fn node(&self, rev: Revision) -> Option<&Node>;
 }

rust/hg-core/src/revlog/node.rs

@@ -1,429 +1,433
 // Copyright 2019-2020 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.
 
 //! Definitions and utilities for Revision nodes
 //!
 //! In Mercurial code base, it is customary to call "a node" the binary SHA
 //! of a revision.
 
 use hex::{self, FromHex, FromHexError};
 
 /// The length in bytes of a `Node`
 ///
 /// This constant is meant to ease refactors of this module, and
 /// are private so that calling code does not expect all nodes have
 /// the same size, should we support several formats concurrently in
 /// the future.
 const NODE_BYTES_LENGTH: usize = 20;
 
 /// The length in bytes of a `Node`
 ///
 /// see also `NODES_BYTES_LENGTH` about it being private.
 const NODE_NYBBLES_LENGTH: usize = 2 * NODE_BYTES_LENGTH;
 
 /// Private alias for readability and to ease future change
 type NodeData = [u8; NODE_BYTES_LENGTH];
 
 /// Binary revision SHA
 ///
 /// ## Future changes of hash size
 ///
 /// To accomodate future changes of hash size, Rust callers
 /// should use the conversion methods at the boundaries (FFI, actual
 /// computation of hashes and I/O) only, and only if required.
 ///
 /// All other callers outside of unit tests should just handle `Node` values
 /// and never make any assumption on the actual length, using [`nybbles_len`]
 /// if they need a loop boundary.
 ///
 /// All methods that create a `Node` either take a type that enforces
 /// the size or fail immediately at runtime with [`ExactLengthRequired`].
 ///
 /// [`nybbles_len`]: #method.nybbles_len
 /// [`ExactLengthRequired`]: struct.NodeError#variant.ExactLengthRequired
 #[derive(Clone, Debug, PartialEq)]
 #[repr(transparent)]
 pub struct Node {
     data: NodeData,
 }
 
 /// The node value for NULL_REVISION
 pub const NULL_NODE: Node = Node {
     data: [0; NODE_BYTES_LENGTH],
 };
 
 impl From<NodeData> for Node {
     fn from(data: NodeData) -> Node {
         Node { data }
     }
 }
 
 #[derive(Debug, PartialEq)]
 pub enum NodeError {
     ExactLengthRequired(usize, String),
     PrefixTooLong(String),
     HexError(FromHexError, String),
 }
 
 /// Low level utility function, also for prefixes
 fn get_nybble(s: &[u8], i: usize) -> u8 {
     if i % 2 == 0 {
         s[i / 2] >> 4
     } else {
         s[i / 2] & 0x0f
     }
 }
 
 impl Node {
     /// Retrieve the `i`th half-byte of the binary data.
     ///
     /// This is also the `i`th hexadecimal digit in numeric form,
     /// also called a [nybble](https://en.wikipedia.org/wiki/Nibble).
     pub fn get_nybble(&self, i: usize) -> u8 {
         get_nybble(&self.data, i)
     }
 
     /// Length of the data, in nybbles
     pub fn nybbles_len(&self) -> usize {
         // public exposure as an instance method only, so that we can
         // easily support several sizes of hashes if needed in the future.
         NODE_NYBBLES_LENGTH
     }
 
     /// Convert from hexadecimal string representation
     ///
     /// Exact length is required.
     ///
     /// To be used in FFI and I/O only, in order to facilitate future
     /// changes of hash format.
     pub fn from_hex(hex: &str) -> Result<Node, NodeError> {
         Ok(NodeData::from_hex(hex)
             .map_err(|e| NodeError::from((e, hex)))?
             .into())
     }
 
     /// Convert to hexadecimal string representation
     ///
     /// To be used in FFI and I/O only, in order to facilitate future
     /// changes of hash format.
     pub fn encode_hex(&self) -> String {
         hex::encode(self.data)
     }
 
     /// Provide access to binary data
     ///
     /// This is needed by FFI layers, for instance to return expected
     /// binary values to Python.
     pub fn as_bytes(&self) -> &[u8] {
         &self.data
     }
 }
 
 impl<T: AsRef<str>> From<(FromHexError, T)> for NodeError {
     fn from(err_offender: (FromHexError, T)) -> Self {
         let (err, offender) = err_offender;
         match err {
             FromHexError::InvalidStringLength => {
                 NodeError::ExactLengthRequired(
                     NODE_NYBBLES_LENGTH,
                     offender.as_ref().to_owned(),
                 )
             }
             _ => NodeError::HexError(err, offender.as_ref().to_owned()),
         }
     }
 }
 
 /// The beginning of a binary revision SHA.
 ///
 /// Since it can potentially come from an hexadecimal representation with
 /// odd length, it needs to carry around whether the last 4 bits are relevant
 /// or not.
 #[derive(Debug, PartialEq)]
 pub struct NodePrefix {
     buf: Vec<u8>,
     is_odd: bool,
 }
 
 impl NodePrefix {
     /// Convert from hexadecimal string representation
     ///
     /// Similarly to `hex::decode`, can be used with Unicode string types
     /// (`String`, `&str`) as well as bytes.
     ///
     /// To be used in FFI and I/O only, in order to facilitate future
     /// changes of hash format.
     pub fn from_hex(hex: impl AsRef<[u8]>) -> Result<Self, NodeError> {
         let hex = hex.as_ref();
         let len = hex.len();
         if len > NODE_NYBBLES_LENGTH {
             return Err(NodeError::PrefixTooLong(
                 String::from_utf8_lossy(hex).to_owned().to_string(),
             ));
         }
 
         let is_odd = len % 2 == 1;
         let even_part = if is_odd { &hex[..len - 1] } else { hex };
         let mut buf: Vec<u8> = Vec::from_hex(&even_part)
             .map_err(|e| (e, String::from_utf8_lossy(hex)))?;
 
         if is_odd {
             let latest_char = char::from(hex[len - 1]);
             let latest_nybble = latest_char.to_digit(16).ok_or_else(|| {
                 (
                     FromHexError::InvalidHexCharacter {
                         c: latest_char,
                         index: len - 1,
                     },
                     String::from_utf8_lossy(hex),
                 )
             })? as u8;
             buf.push(latest_nybble << 4);
         }
         Ok(NodePrefix { buf, is_odd })
     }
 
     pub fn borrow(&self) -> NodePrefixRef {
         NodePrefixRef {
             buf: &self.buf,
             is_odd: self.is_odd,
         }
     }
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub struct NodePrefixRef<'a> {
     buf: &'a [u8],
     is_odd: bool,
 }
 
 impl<'a> NodePrefixRef<'a> {
     pub fn len(&self) -> usize {
         if self.is_odd {
             self.buf.len() * 2 - 1
         } else {
             self.buf.len() * 2
         }
     }
 
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
     pub fn is_prefix_of(&self, node: &Node) -> bool {
         if self.is_odd {
             let buf = self.buf;
             let last_pos = buf.len() - 1;
             node.data.starts_with(buf.split_at(last_pos).0)
                 && node.data[last_pos] >> 4 == buf[last_pos] >> 4
         } else {
             node.data.starts_with(self.buf)
         }
     }
 
     /// Retrieve the `i`th half-byte from the prefix.
     ///
     /// This is also the `i`th hexadecimal digit in numeric form,
     /// also called a [nybble](https://en.wikipedia.org/wiki/Nibble).
     pub fn get_nybble(&self, i: usize) -> u8 {
         assert!(i < self.len());
         get_nybble(self.buf, i)
     }
 
     /// Return the index first nybble that's different from `node`
     ///
     /// If the return value is `None` that means that `self` is
     /// a prefix of `node`, but the current method is a bit slower
     /// than `is_prefix_of`.
     ///
     /// Returned index is as in `get_nybble`, i.e., starting at 0.
     pub fn first_different_nybble(&self, node: &Node) -> Option<usize> {
         let buf = self.buf;
         let until = if self.is_odd {
             buf.len() - 1
         } else {
             buf.len()
         };
-        for i in 0..until {
-            if buf[i] != node.data[i] {
-                if buf[i] & 0xf0 == node.data[i] & 0xf0 {
-                    return Some(2 * i + 1);
+        for (i, item) in buf.iter().enumerate().take(until) {
+            if *item != node.data[i] {
+                return if *item & 0xf0 == node.data[i] & 0xf0 {
+                    Some(2 * i + 1)
                 } else {
-                    return Some(2 * i);
-                }
+                    Some(2 * i)
+                };
             }
         }
         if self.is_odd && buf[until] & 0xf0 != node.data[until] & 0xf0 {
             Some(until * 2)
         } else {
             None
         }
     }
 }
 
 /// A shortcut for full `Node` references
 impl<'a> From<&'a Node> for NodePrefixRef<'a> {
     fn from(node: &'a Node) -> Self {
         NodePrefixRef {
             buf: &node.data,
             is_odd: false,
         }
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     fn sample_node() -> Node {
         let mut data = [0; NODE_BYTES_LENGTH];
         data.copy_from_slice(&[
             0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba,
             0x98, 0x76, 0x54, 0x32, 0x10, 0xde, 0xad, 0xbe, 0xef,
         ]);
         data.into()
     }
 
     /// Pad an hexadecimal string to reach `NODE_NYBBLES_LENGTH`
     ///
     /// The padding is made with zeros
     pub fn hex_pad_right(hex: &str) -> String {
         let mut res = hex.to_string();
         while res.len() < NODE_NYBBLES_LENGTH {
             res.push('0');
         }
         res
     }
 
     fn sample_node_hex() -> String {
         hex_pad_right("0123456789abcdeffedcba9876543210deadbeef")
     }
 
     #[test]
     fn test_node_from_hex() {
         assert_eq!(Node::from_hex(&sample_node_hex()), Ok(sample_node()));
 
         let mut short = hex_pad_right("0123");
         short.pop();
         short.pop();
         assert_eq!(
             Node::from_hex(&short),
             Err(NodeError::ExactLengthRequired(NODE_NYBBLES_LENGTH, short)),
         );
 
         let not_hex = hex_pad_right("012... oops");
         assert_eq!(
             Node::from_hex(&not_hex),
             Err(NodeError::HexError(
                 FromHexError::InvalidHexCharacter { c: '.', index: 3 },
                 not_hex,
             )),
         );
     }
 
     #[test]
     fn test_node_encode_hex() {
         assert_eq!(sample_node().encode_hex(), sample_node_hex());
     }
 
     #[test]
     fn test_prefix_from_hex() -> Result<(), NodeError> {
         assert_eq!(
             NodePrefix::from_hex("0e1")?,
             NodePrefix {
                 buf: vec![14, 16],
                 is_odd: true
             }
         );
         assert_eq!(
             NodePrefix::from_hex("0e1a")?,
             NodePrefix {
                 buf: vec![14, 26],
                 is_odd: false
             }
         );
 
         // checking limit case
         let node_as_vec = sample_node().data.iter().cloned().collect();
         assert_eq!(
             NodePrefix::from_hex(sample_node_hex())?,
             NodePrefix {
                 buf: node_as_vec,
                 is_odd: false
             }
         );
 
         Ok(())
     }
 
     #[test]
     fn test_prefix_from_hex_errors() {
         assert_eq!(
             NodePrefix::from_hex("testgr"),
             Err(NodeError::HexError(
                 FromHexError::InvalidHexCharacter { c: 't', index: 0 },
                 "testgr".to_string()
             ))
         );
         let mut long = NULL_NODE.encode_hex();
         long.push('c');
         match NodePrefix::from_hex(&long)
             .expect_err("should be refused as too long")
         {
             NodeError::PrefixTooLong(s) => assert_eq!(s, long),
             err => panic!(format!("Should have been TooLong, got {:?}", err)),
         }
     }
 
     #[test]
     fn test_is_prefix_of() -> Result<(), NodeError> {
         let mut node_data = [0; NODE_BYTES_LENGTH];
         node_data[0] = 0x12;
         node_data[1] = 0xca;
         let node = Node::from(node_data);
         assert!(NodePrefix::from_hex("12")?.borrow().is_prefix_of(&node));
         assert!(!NodePrefix::from_hex("1a")?.borrow().is_prefix_of(&node));
         assert!(NodePrefix::from_hex("12c")?.borrow().is_prefix_of(&node));
         assert!(!NodePrefix::from_hex("12d")?.borrow().is_prefix_of(&node));
         Ok(())
     }
 
     #[test]
     fn test_get_nybble() -> Result<(), NodeError> {
         let prefix = NodePrefix::from_hex("dead6789cafe")?;
         assert_eq!(prefix.borrow().get_nybble(0), 13);
         assert_eq!(prefix.borrow().get_nybble(7), 9);
         Ok(())
     }
 
     #[test]
     fn test_first_different_nybble_even_prefix() {
         let prefix = NodePrefix::from_hex("12ca").unwrap();
         let prefref = prefix.borrow();
         let mut node = Node::from([0; NODE_BYTES_LENGTH]);
         assert_eq!(prefref.first_different_nybble(&node), Some(0));
         node.data[0] = 0x13;
         assert_eq!(prefref.first_different_nybble(&node), Some(1));
         node.data[0] = 0x12;
         assert_eq!(prefref.first_different_nybble(&node), Some(2));
         node.data[1] = 0xca;
         // now it is a prefix
         assert_eq!(prefref.first_different_nybble(&node), None);
     }
 
     #[test]
     fn test_first_different_nybble_odd_prefix() {
         let prefix = NodePrefix::from_hex("12c").unwrap();
         let prefref = prefix.borrow();
         let mut node = Node::from([0; NODE_BYTES_LENGTH]);
         assert_eq!(prefref.first_different_nybble(&node), Some(0));
         node.data[0] = 0x13;
         assert_eq!(prefref.first_different_nybble(&node), Some(1));
         node.data[0] = 0x12;
         assert_eq!(prefref.first_different_nybble(&node), Some(2));
         node.data[1] = 0xca;
         // now it is a prefix
         assert_eq!(prefref.first_different_nybble(&node), None);
     }
 }
 
 #[cfg(test)]
 pub use tests::hex_pad_right;

rust/hg-core/src/revlog/nodemap.rs

@@ -1,1122 +1,1118
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 //! Indexing facilities for fast retrieval of `Revision` from `Node`
 //!
 //! This provides a variation on the 16-ary radix tree that is
 //! provided as "nodetree" in revlog.c, ready for append-only persistence
 //! on disk.
 //!
 //! Following existing implicit conventions, the "nodemap" terminology
 //! is used in a more abstract context.
 
 use super::{
     node::NULL_NODE, Node, NodeError, NodePrefix, NodePrefixRef, Revision,
     RevlogIndex, NULL_REVISION,
 };
 
 use std::cmp::max;
 use std::fmt;
 use std::mem;
 use std::ops::Deref;
 use std::ops::Index;
 use std::slice;
 
 #[derive(Debug, PartialEq)]
 pub enum NodeMapError {
     MultipleResults,
     InvalidNodePrefix(NodeError),
     /// A `Revision` stored in the nodemap could not be found in the index
     RevisionNotInIndex(Revision),
 }
 
 impl From<NodeError> for NodeMapError {
     fn from(err: NodeError) -> Self {
         NodeMapError::InvalidNodePrefix(err)
     }
 }
 
 /// Mapping system from Mercurial nodes to revision numbers.
 ///
 /// ## `RevlogIndex` and `NodeMap`
 ///
 /// One way to think about their relationship is that
 /// the `NodeMap` is a prefix-oriented reverse index of the `Node` information
 /// carried by a [`RevlogIndex`].
 ///
 /// Many of the methods in this trait take a `RevlogIndex` argument
 /// which is used for validation of their results. This index must naturally
 /// be the one the `NodeMap` is about, and it must be consistent.
 ///
 /// Notably, the `NodeMap` must not store
 /// information about more `Revision` values than there are in the index.
 /// In these methods, an encountered `Revision` is not in the index, a
 /// [`RevisionNotInIndex`] error is returned.
 ///
 /// In insert operations, the rule is thus that the `NodeMap` must always
 /// be updated after the `RevlogIndex`
 /// be updated first, and the `NodeMap` second.
 ///
 /// [`RevisionNotInIndex`]: enum.NodeMapError.html#variant.RevisionNotInIndex
 /// [`RevlogIndex`]: ../trait.RevlogIndex.html
 pub trait NodeMap {
     /// Find the unique `Revision` having the given `Node`
     ///
     /// If no Revision matches the given `Node`, `Ok(None)` is returned.
     fn find_node(
         &self,
         index: &impl RevlogIndex,
         node: &Node,
     ) -> Result<Option<Revision>, NodeMapError> {
         self.find_bin(index, node.into())
     }
 
     /// Find the unique Revision whose `Node` starts with a given binary prefix
     ///
     /// If no Revision matches the given prefix, `Ok(None)` is returned.
     ///
     /// If several Revisions match the given prefix, a [`MultipleResults`]
     /// error is returned.
     fn find_bin<'a>(
         &self,
         idx: &impl RevlogIndex,
         prefix: NodePrefixRef<'a>,
     ) -> Result<Option<Revision>, NodeMapError>;
 
     /// Find the unique Revision whose `Node` hexadecimal string representation
     /// starts with a given prefix
     ///
     /// If no Revision matches the given prefix, `Ok(None)` is returned.
     ///
     /// If several Revisions match the given prefix, a [`MultipleResults`]
     /// error is returned.
     fn find_hex(
         &self,
         idx: &impl RevlogIndex,
         prefix: &str,
     ) -> Result<Option<Revision>, NodeMapError> {
         self.find_bin(idx, NodePrefix::from_hex(prefix)?.borrow())
     }
 
     /// Give the size of the shortest node prefix that determines
     /// the revision uniquely.
     ///
     /// From a binary node prefix, if it is matched in the node map, this
     /// returns the number of hexadecimal digits that would had sufficed
     /// to find the revision uniquely.
     ///
     /// Returns `None` if no `Revision` could be found for the prefix.
     ///
     /// If several Revisions match the given prefix, a [`MultipleResults`]
     /// error is returned.
     fn unique_prefix_len_bin<'a>(
         &self,
         idx: &impl RevlogIndex,
         node_prefix: NodePrefixRef<'a>,
     ) -> Result<Option<usize>, NodeMapError>;
 
     /// Same as `unique_prefix_len_bin`, with the hexadecimal representation
     /// of the prefix as input.
     fn unique_prefix_len_hex(
         &self,
         idx: &impl RevlogIndex,
         prefix: &str,
     ) -> Result<Option<usize>, NodeMapError> {
         self.unique_prefix_len_bin(idx, NodePrefix::from_hex(prefix)?.borrow())
     }
 
     /// Same as `unique_prefix_len_bin`, with a full `Node` as input
     fn unique_prefix_len_node(
         &self,
         idx: &impl RevlogIndex,
         node: &Node,
     ) -> Result<Option<usize>, NodeMapError> {
         self.unique_prefix_len_bin(idx, node.into())
     }
 }
 
 pub trait MutableNodeMap: NodeMap {
     fn insert<I: RevlogIndex>(
         &mut self,
         index: &I,
         node: &Node,
         rev: Revision,
     ) -> Result<(), NodeMapError>;
 }
 
 /// Low level NodeTree [`Blocks`] elements
 ///
 /// These are exactly as for instance on persistent storage.
 type RawElement = i32;
 
 /// High level representation of values in NodeTree
 /// [`Blocks`](struct.Block.html)
 ///
 /// This is the high level representation that most algorithms should
 /// use.
 #[derive(Clone, Debug, Eq, PartialEq)]
 enum Element {
     Rev(Revision),
     Block(usize),
     None,
 }
 
 impl From<RawElement> for Element {
     /// Conversion from low level representation, after endianness conversion.
     ///
     /// See [`Block`](struct.Block.html) for explanation about the encoding.
     fn from(raw: RawElement) -> Element {
         if raw >= 0 {
             Element::Block(raw as usize)
         } else if raw == -1 {
             Element::None
         } else {
             Element::Rev(-raw - 2)
         }
     }
 }
 
 impl From<Element> for RawElement {
     fn from(element: Element) -> RawElement {
         match element {
             Element::None => 0,
             Element::Block(i) => i as RawElement,
             Element::Rev(rev) => -rev - 2,
         }
     }
 }
 
 /// A logical block of the `NodeTree`, packed with a fixed size.
 ///
 /// These are always used in container types implementing `Index<Block>`,
 /// such as `&Block`
 ///
 /// As an array of integers, its ith element encodes that the
 /// ith potential edge from the block, representing the ith hexadecimal digit
 /// (nybble) `i` is either:
 ///
 /// - absent (value -1)
 /// - another `Block` in the same indexable container (value ≥ 0)
 ///  - a `Revision` leaf (value ≤ -2)
 ///
 /// Endianness has to be fixed for consistency on shared storage across
 /// different architectures.
 ///
 /// A key difference with the C `nodetree` is that we need to be
 /// able to represent the [`Block`] at index 0, hence -1 is the empty marker
 /// rather than 0 and the `Revision` range upper limit of -2 instead of -1.
 ///
 /// Another related difference is that `NULL_REVISION` (-1) is not
 /// represented at all, because we want an immutable empty nodetree
 /// to be valid.
 
 #[derive(Copy, Clone)]
 pub struct Block([u8; BLOCK_SIZE]);
 
 /// Not derivable for arrays of length >32 until const generics are stable
 impl PartialEq for Block {
     fn eq(&self, other: &Self) -> bool {
-        &self.0[..] == &other.0[..]
+        self.0[..] == other.0[..]
     }
 }
 
 pub const BLOCK_SIZE: usize = 64;
 
 impl Block {
     fn new() -> Self {
         // -1 in 2's complement to create an absent node
         let byte: u8 = 255;
         Block([byte; BLOCK_SIZE])
     }
 
     fn get(&self, nybble: u8) -> Element {
         let index = nybble as usize * mem::size_of::<RawElement>();
         Element::from(RawElement::from_be_bytes([
             self.0[index],
             self.0[index + 1],
             self.0[index + 2],
             self.0[index + 3],
         ]))
     }
 
     fn set(&mut self, nybble: u8, element: Element) {
         let values = RawElement::to_be_bytes(element.into());
         let index = nybble as usize * mem::size_of::<RawElement>();
         self.0[index] = values[0];
         self.0[index + 1] = values[1];
         self.0[index + 2] = values[2];
         self.0[index + 3] = values[3];
     }
 }
 
 impl fmt::Debug for Block {
     /// sparse representation for testing and debugging purposes
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         f.debug_map()
             .entries((0..16).filter_map(|i| match self.get(i) {
                 Element::None => None,
                 element => Some((i, element)),
             }))
             .finish()
     }
 }
 
 /// A mutable 16-radix tree with the root block logically at the end
 ///
 /// Because of the append only nature of our node trees, we need to
 /// keep the original untouched and store new blocks separately.
 ///
 /// The mutable root `Block` is kept apart so that we don't have to rebump
 /// it on each insertion.
 pub struct NodeTree {
     readonly: Box<dyn Deref<Target = [Block]> + Send>,
     growable: Vec<Block>,
     root: Block,
     masked_inner_blocks: usize,
 }
 
 impl Index<usize> for NodeTree {
     type Output = Block;
 
     fn index(&self, i: usize) -> &Block {
         let ro_len = self.readonly.len();
         if i < ro_len {
             &self.readonly[i]
         } else if i == ro_len + self.growable.len() {
             &self.root
         } else {
             &self.growable[i - ro_len]
         }
     }
 }
 
 /// Return `None` unless the `Node` for `rev` has given prefix in `index`.
 fn has_prefix_or_none(
     idx: &impl RevlogIndex,
     prefix: NodePrefixRef,
     rev: Revision,
 ) -> Result<Option<Revision>, NodeMapError> {
     idx.node(rev)
         .ok_or_else(|| NodeMapError::RevisionNotInIndex(rev))
         .map(|node| {
             if prefix.is_prefix_of(node) {
                 Some(rev)
             } else {
                 None
             }
         })
 }
 
 /// validate that the candidate's node starts indeed with given prefix,
 /// and treat ambiguities related to `NULL_REVISION`.
 ///
 /// From the data in the NodeTree, one can only conclude that some
 /// revision is the only one for a *subprefix* of the one being looked up.
 fn validate_candidate(
     idx: &impl RevlogIndex,
     prefix: NodePrefixRef,
     candidate: (Option<Revision>, usize),
 ) -> Result<(Option<Revision>, usize), NodeMapError> {
     let (rev, steps) = candidate;
     if let Some(nz_nybble) = prefix.first_different_nybble(&NULL_NODE) {
         rev.map_or(Ok((None, steps)), |r| {
             has_prefix_or_none(idx, prefix, r)
                 .map(|opt| (opt, max(steps, nz_nybble + 1)))
         })
     } else {
         // the prefix is only made of zeros; NULL_REVISION always matches it
         // and any other *valid* result is an ambiguity
         match rev {
             None => Ok((Some(NULL_REVISION), steps + 1)),
             Some(r) => match has_prefix_or_none(idx, prefix, r)? {
                 None => Ok((Some(NULL_REVISION), steps + 1)),
                 _ => Err(NodeMapError::MultipleResults),
             },
         }
     }
 }
 
 impl NodeTree {
     /// Initiate a NodeTree from an immutable slice-like of `Block`
     ///
     /// We keep `readonly` and clone its root block if it isn't empty.
     fn new(readonly: Box<dyn Deref<Target = [Block]> + Send>) -> Self {
-        let root = readonly
-            .last()
-            .map(|b| b.clone())
-            .unwrap_or_else(|| Block::new());
+        let root = readonly.last().cloned().unwrap_or_else(Block::new);
         NodeTree {
-            readonly: readonly,
+            readonly,
             growable: Vec::new(),
-            root: root,
+            root,
             masked_inner_blocks: 0,
         }
     }
 
     /// Create from an opaque bunch of bytes
     ///
     /// The created `NodeTreeBytes` from `buffer`,
     /// of which exactly `amount` bytes are used.
     ///
     /// - `buffer` could be derived from `PyBuffer` and `Mmap` objects.
     /// - `offset` allows for the final file format to include fixed data
     ///   (generation number, behavioural flags)
     /// - `amount` is expressed in bytes, and is not automatically derived from
     ///   `bytes`, so that a caller that manages them atomically can perform
     ///   temporary disk serializations and still rollback easily if needed.
     ///   First use-case for this would be to support Mercurial shell hooks.
     ///
     /// panics if `buffer` is smaller than `amount`
     pub fn load_bytes(
         bytes: Box<dyn Deref<Target = [u8]> + Send>,
         amount: usize,
     ) -> Self {
         NodeTree::new(Box::new(NodeTreeBytes::new(bytes, amount)))
     }
 
     /// Retrieve added `Block` and the original immutable data
     pub fn into_readonly_and_added(
         self,
     ) -> (Box<dyn Deref<Target = [Block]> + Send>, Vec<Block>) {
         let mut vec = self.growable;
         let readonly = self.readonly;
         if readonly.last() != Some(&self.root) {
             vec.push(self.root);
         }
         (readonly, vec)
     }
 
     /// Retrieve added `Blocks` as bytes, ready to be written to persistent
     /// storage
     pub fn into_readonly_and_added_bytes(
         self,
     ) -> (Box<dyn Deref<Target = [Block]> + Send>, Vec<u8>) {
         let (readonly, vec) = self.into_readonly_and_added();
         // Prevent running `v`'s destructor so we are in complete control
         // of the allocation.
         let vec = mem::ManuallyDrop::new(vec);
 
         // Transmute the `Vec<Block>` to a `Vec<u8>`. Blocks are contiguous
         // bytes, so this is perfectly safe.
         let bytes = unsafe {
             // Assert that `Block` hasn't been changed and has no padding
             let _: [u8; 4 * BLOCK_SIZE] =
                 std::mem::transmute([Block::new(); 4]);
 
             // /!\ Any use of `vec` after this is use-after-free.
             // TODO: use `into_raw_parts` once stabilized
             Vec::from_raw_parts(
                 vec.as_ptr() as *mut u8,
                 vec.len() * BLOCK_SIZE,
                 vec.capacity() * BLOCK_SIZE,
             )
         };
         (readonly, bytes)
     }
 
     /// Total number of blocks
     fn len(&self) -> usize {
         self.readonly.len() + self.growable.len() + 1
     }
 
     /// Implemented for completeness
     ///
     /// A `NodeTree` always has at least the mutable root block.
     #[allow(dead_code)]
     fn is_empty(&self) -> bool {
         false
     }
 
     /// Main working method for `NodeTree` searches
     ///
     /// The first returned value is the result of analysing `NodeTree` data
     /// *alone*: whereas `None` guarantees that the given prefix is absent
     /// from the `NodeTree` data (but still could match `NULL_NODE`), with
     /// `Some(rev)`, it is to be understood that `rev` is the unique `Revision`
     /// that could match the prefix. Actually, all that can be inferred from
     /// the `NodeTree` data is that `rev` is the revision with the longest
     /// common node prefix with the given prefix.
     ///
     /// The second returned value is the size of the smallest subprefix
     /// of `prefix` that would give the same result, i.e. not the
     /// `MultipleResults` error variant (again, using only the data of the
     /// `NodeTree`).
     fn lookup(
         &self,
         prefix: NodePrefixRef,
     ) -> Result<(Option<Revision>, usize), NodeMapError> {
         for (i, visit_item) in self.visit(prefix).enumerate() {
             if let Some(opt) = visit_item.final_revision() {
                 return Ok((opt, i + 1));
             }
         }
         Err(NodeMapError::MultipleResults)
     }
 
     fn visit<'n, 'p>(
         &'n self,
         prefix: NodePrefixRef<'p>,
     ) -> NodeTreeVisitor<'n, 'p> {
         NodeTreeVisitor {
             nt: self,
-            prefix: prefix,
+            prefix,
             visit: self.len() - 1,
             nybble_idx: 0,
             done: false,
         }
     }
     /// Return a mutable reference for `Block` at index `idx`.
     ///
     /// If `idx` lies in the immutable area, then the reference is to
     /// a newly appended copy.
     ///
     /// Returns (new_idx, glen, mut_ref) where
     ///
     /// - `new_idx` is the index of the mutable `Block`
     /// - `mut_ref` is a mutable reference to the mutable Block.
     /// - `glen` is the new length of `self.growable`
     ///
     /// Note: the caller wouldn't be allowed to query `self.growable.len()`
     /// itself because of the mutable borrow taken with the returned `Block`
     fn mutable_block(&mut self, idx: usize) -> (usize, &mut Block, usize) {
         let ro_blocks = &self.readonly;
         let ro_len = ro_blocks.len();
         let glen = self.growable.len();
         if idx < ro_len {
             self.masked_inner_blocks += 1;
-            // TODO OPTIM I think this makes two copies
-            self.growable.push(ro_blocks[idx].clone());
+            self.growable.push(ro_blocks[idx]);
             (glen + ro_len, &mut self.growable[glen], glen + 1)
         } else if glen + ro_len == idx {
             (idx, &mut self.root, glen)
         } else {
             (idx, &mut self.growable[idx - ro_len], glen)
         }
     }
 
     /// Main insertion method
     ///
     /// This will dive in the node tree to find the deepest `Block` for
     /// `node`, split it as much as needed and record `node` in there.
     /// The method then backtracks, updating references in all the visited
     /// blocks from the root.
     ///
     /// All the mutated `Block` are copied first to the growable part if
     /// needed. That happens for those in the immutable part except the root.
     pub fn insert<I: RevlogIndex>(
         &mut self,
         index: &I,
         node: &Node,
         rev: Revision,
     ) -> Result<(), NodeMapError> {
         let ro_len = &self.readonly.len();
 
         let mut visit_steps: Vec<_> = self.visit(node.into()).collect();
         let read_nybbles = visit_steps.len();
         // visit_steps cannot be empty, since we always visit the root block
         let deepest = visit_steps.pop().unwrap();
 
         let (mut block_idx, mut block, mut glen) =
             self.mutable_block(deepest.block_idx);
 
         if let Element::Rev(old_rev) = deepest.element {
             let old_node = index
                 .node(old_rev)
                 .ok_or_else(|| NodeMapError::RevisionNotInIndex(old_rev))?;
             if old_node == node {
                 return Ok(()); // avoid creating lots of useless blocks
             }
 
             // Looping over the tail of nybbles in both nodes, creating
             // new blocks until we find the difference
             let mut new_block_idx = ro_len + glen;
             let mut nybble = deepest.nybble;
             for nybble_pos in read_nybbles..node.nybbles_len() {
                 block.set(nybble, Element::Block(new_block_idx));
 
                 let new_nybble = node.get_nybble(nybble_pos);
                 let old_nybble = old_node.get_nybble(nybble_pos);
 
                 if old_nybble == new_nybble {
                     self.growable.push(Block::new());
                     block = &mut self.growable[glen];
                     glen += 1;
                     new_block_idx += 1;
                     nybble = new_nybble;
                 } else {
                     let mut new_block = Block::new();
                     new_block.set(old_nybble, Element::Rev(old_rev));
                     new_block.set(new_nybble, Element::Rev(rev));
                     self.growable.push(new_block);
                     break;
                 }
             }
         } else {
             // Free slot in the deepest block: no splitting has to be done
             block.set(deepest.nybble, Element::Rev(rev));
         }
 
         // Backtrack over visit steps to update references
         while let Some(visited) = visit_steps.pop() {
             let to_write = Element::Block(block_idx);
             if visit_steps.is_empty() {
                 self.root.set(visited.nybble, to_write);
                 break;
             }
             let (new_idx, block, _) = self.mutable_block(visited.block_idx);
             if block.get(visited.nybble) == to_write {
                 break;
             }
             block.set(visited.nybble, to_write);
             block_idx = new_idx;
         }
         Ok(())
     }
 
     /// Make the whole `NodeTree` logically empty, without touching the
     /// immutable part.
     pub fn invalidate_all(&mut self) {
         self.root = Block::new();
         self.growable = Vec::new();
         self.masked_inner_blocks = self.readonly.len();
     }
 
     /// Return the number of blocks in the readonly part that are currently
     /// masked in the mutable part.
     ///
     /// The `NodeTree` structure has no efficient way to know how many blocks
     /// are already unreachable in the readonly part.
     ///
     /// After a call to `invalidate_all()`, the returned number can be actually
     /// bigger than the whole readonly part, a conventional way to mean that
     /// all the readonly blocks have been masked. This is what is really
     /// useful to the caller and does not require to know how many were
     /// actually unreachable to begin with.
     pub fn masked_readonly_blocks(&self) -> usize {
         if let Some(readonly_root) = self.readonly.last() {
             if readonly_root == &self.root {
                 return 0;
             }
         } else {
             return 0;
         }
         self.masked_inner_blocks + 1
     }
 }
 
 pub struct NodeTreeBytes {
     buffer: Box<dyn Deref<Target = [u8]> + Send>,
     len_in_blocks: usize,
 }
 
 impl NodeTreeBytes {
     fn new(
         buffer: Box<dyn Deref<Target = [u8]> + Send>,
         amount: usize,
     ) -> Self {
         assert!(buffer.len() >= amount);
         let len_in_blocks = amount / BLOCK_SIZE;
         NodeTreeBytes {
             buffer,
             len_in_blocks,
         }
     }
 }
 
 impl Deref for NodeTreeBytes {
     type Target = [Block];
 
     fn deref(&self) -> &[Block] {
         unsafe {
             slice::from_raw_parts(
                 (&self.buffer).as_ptr() as *const Block,
                 self.len_in_blocks,
             )
         }
     }
 }
 
 struct NodeTreeVisitor<'n, 'p> {
     nt: &'n NodeTree,
     prefix: NodePrefixRef<'p>,
     visit: usize,
     nybble_idx: usize,
     done: bool,
 }
 
 #[derive(Debug, PartialEq, Clone)]
 struct NodeTreeVisitItem {
     block_idx: usize,
     nybble: u8,
     element: Element,
 }
 
 impl<'n, 'p> Iterator for NodeTreeVisitor<'n, 'p> {
     type Item = NodeTreeVisitItem;
 
     fn next(&mut self) -> Option<Self::Item> {
         if self.done || self.nybble_idx >= self.prefix.len() {
             return None;
         }
 
         let nybble = self.prefix.get_nybble(self.nybble_idx);
         self.nybble_idx += 1;
 
         let visit = self.visit;
         let element = self.nt[visit].get(nybble);
         if let Element::Block(idx) = element {
             self.visit = idx;
         } else {
             self.done = true;
         }
 
         Some(NodeTreeVisitItem {
             block_idx: visit,
-            nybble: nybble,
-            element: element,
+            nybble,
+            element,
         })
     }
 }
 
 impl NodeTreeVisitItem {
     // Return `Some(opt)` if this item is final, with `opt` being the
     // `Revision` that it may represent.
     //
     // If the item is not terminal, return `None`
     fn final_revision(&self) -> Option<Option<Revision>> {
         match self.element {
             Element::Block(_) => None,
             Element::Rev(r) => Some(Some(r)),
             Element::None => Some(None),
         }
     }
 }
 
 impl From<Vec<Block>> for NodeTree {
     fn from(vec: Vec<Block>) -> Self {
         Self::new(Box::new(vec))
     }
 }
 
 impl fmt::Debug for NodeTree {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let readonly: &[Block] = &*self.readonly;
         write!(
             f,
             "readonly: {:?}, growable: {:?}, root: {:?}",
             readonly, self.growable, self.root
         )
     }
 }
 
 impl Default for NodeTree {
     /// Create a fully mutable empty NodeTree
     fn default() -> Self {
         NodeTree::new(Box::new(Vec::new()))
     }
 }
 
 impl NodeMap for NodeTree {
     fn find_bin<'a>(
         &self,
         idx: &impl RevlogIndex,
         prefix: NodePrefixRef<'a>,
     ) -> Result<Option<Revision>, NodeMapError> {
         validate_candidate(idx, prefix.clone(), self.lookup(prefix)?)
             .map(|(opt, _shortest)| opt)
     }
 
     fn unique_prefix_len_bin<'a>(
         &self,
         idx: &impl RevlogIndex,
         prefix: NodePrefixRef<'a>,
     ) -> Result<Option<usize>, NodeMapError> {
         validate_candidate(idx, prefix.clone(), self.lookup(prefix)?)
             .map(|(opt, shortest)| opt.map(|_rev| shortest))
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::NodeMapError::*;
     use super::*;
     use crate::revlog::node::{hex_pad_right, Node};
     use std::collections::HashMap;
 
     /// Creates a `Block` using a syntax close to the `Debug` output
     macro_rules! block {
         {$($nybble:tt : $variant:ident($val:tt)),*} => (
             {
                 let mut block = Block::new();
                 $(block.set($nybble, Element::$variant($val)));*;
                 block
             }
         )
     }
 
     #[test]
     fn test_block_debug() {
         let mut block = Block::new();
         block.set(1, Element::Rev(3));
         block.set(10, Element::Block(0));
         assert_eq!(format!("{:?}", block), "{1: Rev(3), 10: Block(0)}");
     }
 
     #[test]
     fn test_block_macro() {
         let block = block! {5: Block(2)};
         assert_eq!(format!("{:?}", block), "{5: Block(2)}");
 
         let block = block! {13: Rev(15), 5: Block(2)};
         assert_eq!(format!("{:?}", block), "{5: Block(2), 13: Rev(15)}");
     }
 
     #[test]
     fn test_raw_block() {
         let mut raw = [255u8; 64];
 
         let mut counter = 0;
         for val in [0, 15, -2, -1, -3].iter() {
             for byte in RawElement::to_be_bytes(*val).iter() {
                 raw[counter] = *byte;
                 counter += 1;
             }
         }
         let block = Block(raw);
         assert_eq!(block.get(0), Element::Block(0));
         assert_eq!(block.get(1), Element::Block(15));
         assert_eq!(block.get(3), Element::None);
         assert_eq!(block.get(2), Element::Rev(0));
         assert_eq!(block.get(4), Element::Rev(1));
     }
 
     type TestIndex = HashMap<Revision, Node>;
 
     impl RevlogIndex for TestIndex {
         fn node(&self, rev: Revision) -> Option<&Node> {
             self.get(&rev)
         }
 
         fn len(&self) -> usize {
             self.len()
         }
     }
 
     /// Pad hexadecimal Node prefix with zeros on the right
     ///
     /// This avoids having to repeatedly write very long hexadecimal
     /// strings for test data, and brings actual hash size independency.
     #[cfg(test)]
     fn pad_node(hex: &str) -> Node {
         Node::from_hex(&hex_pad_right(hex)).unwrap()
     }
 
     /// Pad hexadecimal Node prefix with zeros on the right, then insert
     fn pad_insert(idx: &mut TestIndex, rev: Revision, hex: &str) {
         idx.insert(rev, pad_node(hex));
     }
 
     fn sample_nodetree() -> NodeTree {
         NodeTree::from(vec![
             block![0: Rev(9)],
             block![0: Rev(0), 1: Rev(9)],
             block![0: Block(1), 1:Rev(1)],
         ])
     }
 
     #[test]
     fn test_nt_debug() {
         let nt = sample_nodetree();
         assert_eq!(
             format!("{:?}", nt),
             "readonly: \
              [{0: Rev(9)}, {0: Rev(0), 1: Rev(9)}, {0: Block(1), 1: Rev(1)}], \
              growable: [], \
              root: {0: Block(1), 1: Rev(1)}",
         );
     }
 
     #[test]
     fn test_immutable_find_simplest() -> Result<(), NodeMapError> {
         let mut idx: TestIndex = HashMap::new();
         pad_insert(&mut idx, 1, "1234deadcafe");
 
         let nt = NodeTree::from(vec![block! {1: Rev(1)}]);
         assert_eq!(nt.find_hex(&idx, "1")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "12")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "1234de")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "1a")?, None);
         assert_eq!(nt.find_hex(&idx, "ab")?, None);
 
         // and with full binary Nodes
         assert_eq!(nt.find_node(&idx, idx.get(&1).unwrap())?, Some(1));
         let unknown = Node::from_hex(&hex_pad_right("3d")).unwrap();
         assert_eq!(nt.find_node(&idx, &unknown)?, None);
         Ok(())
     }
 
     #[test]
     fn test_immutable_find_one_jump() {
         let mut idx = TestIndex::new();
         pad_insert(&mut idx, 9, "012");
         pad_insert(&mut idx, 0, "00a");
 
         let nt = sample_nodetree();
 
         assert_eq!(nt.find_hex(&idx, "0"), Err(MultipleResults));
         assert_eq!(nt.find_hex(&idx, "01"), Ok(Some(9)));
         assert_eq!(nt.find_hex(&idx, "00"), Err(MultipleResults));
         assert_eq!(nt.find_hex(&idx, "00a"), Ok(Some(0)));
         assert_eq!(nt.unique_prefix_len_hex(&idx, "00a"), Ok(Some(3)));
         assert_eq!(nt.find_hex(&idx, "000"), Ok(Some(NULL_REVISION)));
     }
 
     #[test]
     fn test_mutated_find() -> Result<(), NodeMapError> {
         let mut idx = TestIndex::new();
         pad_insert(&mut idx, 9, "012");
         pad_insert(&mut idx, 0, "00a");
         pad_insert(&mut idx, 2, "cafe");
         pad_insert(&mut idx, 3, "15");
         pad_insert(&mut idx, 1, "10");
 
         let nt = NodeTree {
             readonly: sample_nodetree().readonly,
             growable: vec![block![0: Rev(1), 5: Rev(3)]],
             root: block![0: Block(1), 1:Block(3), 12: Rev(2)],
             masked_inner_blocks: 1,
         };
         assert_eq!(nt.find_hex(&idx, "10")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "c")?, Some(2));
         assert_eq!(nt.unique_prefix_len_hex(&idx, "c")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "00"), Err(MultipleResults));
         assert_eq!(nt.find_hex(&idx, "000")?, Some(NULL_REVISION));
         assert_eq!(nt.unique_prefix_len_hex(&idx, "000")?, Some(3));
         assert_eq!(nt.find_hex(&idx, "01")?, Some(9));
         assert_eq!(nt.masked_readonly_blocks(), 2);
         Ok(())
     }
 
     struct TestNtIndex {
         index: TestIndex,
         nt: NodeTree,
     }
 
     impl TestNtIndex {
         fn new() -> Self {
             TestNtIndex {
                 index: HashMap::new(),
                 nt: NodeTree::default(),
             }
         }
 
         fn insert(
             &mut self,
             rev: Revision,
             hex: &str,
         ) -> Result<(), NodeMapError> {
             let node = pad_node(hex);
             self.index.insert(rev, node.clone());
             self.nt.insert(&self.index, &node, rev)?;
             Ok(())
         }
 
         fn find_hex(
             &self,
             prefix: &str,
         ) -> Result<Option<Revision>, NodeMapError> {
             self.nt.find_hex(&self.index, prefix)
         }
 
         fn unique_prefix_len_hex(
             &self,
             prefix: &str,
         ) -> Result<Option<usize>, NodeMapError> {
             self.nt.unique_prefix_len_hex(&self.index, prefix)
         }
 
         /// Drain `added` and restart a new one
         fn commit(self) -> Self {
             let mut as_vec: Vec<Block> =
                 self.nt.readonly.iter().map(|block| block.clone()).collect();
             as_vec.extend(self.nt.growable);
             as_vec.push(self.nt.root);
 
             Self {
                 index: self.index,
                 nt: NodeTree::from(as_vec).into(),
             }
         }
     }
 
     #[test]
     fn test_insert_full_mutable() -> Result<(), NodeMapError> {
         let mut idx = TestNtIndex::new();
         idx.insert(0, "1234")?;
         assert_eq!(idx.find_hex("1")?, Some(0));
         assert_eq!(idx.find_hex("12")?, Some(0));
 
         // let's trigger a simple split
         idx.insert(1, "1a34")?;
         assert_eq!(idx.nt.growable.len(), 1);
         assert_eq!(idx.find_hex("12")?, Some(0));
         assert_eq!(idx.find_hex("1a")?, Some(1));
 
         // reinserting is a no_op
         idx.insert(1, "1a34")?;
         assert_eq!(idx.nt.growable.len(), 1);
         assert_eq!(idx.find_hex("12")?, Some(0));
         assert_eq!(idx.find_hex("1a")?, Some(1));
 
         idx.insert(2, "1a01")?;
         assert_eq!(idx.nt.growable.len(), 2);
         assert_eq!(idx.find_hex("1a"), Err(NodeMapError::MultipleResults));
         assert_eq!(idx.find_hex("12")?, Some(0));
         assert_eq!(idx.find_hex("1a3")?, Some(1));
         assert_eq!(idx.find_hex("1a0")?, Some(2));
         assert_eq!(idx.find_hex("1a12")?, None);
 
         // now let's make it split and create more than one additional block
         idx.insert(3, "1a345")?;
         assert_eq!(idx.nt.growable.len(), 4);
         assert_eq!(idx.find_hex("1a340")?, Some(1));
         assert_eq!(idx.find_hex("1a345")?, Some(3));
         assert_eq!(idx.find_hex("1a341")?, None);
 
         // there's no readonly block to mask
         assert_eq!(idx.nt.masked_readonly_blocks(), 0);
         Ok(())
     }
 
     #[test]
     fn test_unique_prefix_len_zero_prefix() {
         let mut idx = TestNtIndex::new();
         idx.insert(0, "00000abcd").unwrap();
 
         assert_eq!(idx.find_hex("000"), Err(NodeMapError::MultipleResults));
         // in the nodetree proper, this will be found at the first nybble
         // yet the correct answer for unique_prefix_len is not 1, nor 1+1,
         // but the first difference with `NULL_NODE`
         assert_eq!(idx.unique_prefix_len_hex("00000a"), Ok(Some(6)));
         assert_eq!(idx.unique_prefix_len_hex("00000ab"), Ok(Some(6)));
 
         // same with odd result
         idx.insert(1, "00123").unwrap();
         assert_eq!(idx.unique_prefix_len_hex("001"), Ok(Some(3)));
         assert_eq!(idx.unique_prefix_len_hex("0012"), Ok(Some(3)));
 
         // these are unchanged of course
         assert_eq!(idx.unique_prefix_len_hex("00000a"), Ok(Some(6)));
         assert_eq!(idx.unique_prefix_len_hex("00000ab"), Ok(Some(6)));
     }
 
     #[test]
     fn test_insert_extreme_splitting() -> Result<(), NodeMapError> {
         // check that the splitting loop is long enough
         let mut nt_idx = TestNtIndex::new();
         let nt = &mut nt_idx.nt;
         let idx = &mut nt_idx.index;
 
         let node0_hex = hex_pad_right("444444");
         let mut node1_hex = hex_pad_right("444444").clone();
         node1_hex.pop();
         node1_hex.push('5');
         let node0 = Node::from_hex(&node0_hex).unwrap();
         let node1 = Node::from_hex(&node1_hex).unwrap();
 
         idx.insert(0, node0.clone());
         nt.insert(idx, &node0, 0)?;
         idx.insert(1, node1.clone());
         nt.insert(idx, &node1, 1)?;
 
         assert_eq!(nt.find_bin(idx, (&node0).into())?, Some(0));
         assert_eq!(nt.find_bin(idx, (&node1).into())?, Some(1));
         Ok(())
     }
 
     #[test]
     fn test_insert_partly_immutable() -> Result<(), NodeMapError> {
         let mut idx = TestNtIndex::new();
         idx.insert(0, "1234")?;
         idx.insert(1, "1235")?;
         idx.insert(2, "131")?;
         idx.insert(3, "cafe")?;
         let mut idx = idx.commit();
         assert_eq!(idx.find_hex("1234")?, Some(0));
         assert_eq!(idx.find_hex("1235")?, Some(1));
         assert_eq!(idx.find_hex("131")?, Some(2));
         assert_eq!(idx.find_hex("cafe")?, Some(3));
         // we did not add anything since init from readonly
         assert_eq!(idx.nt.masked_readonly_blocks(), 0);
 
         idx.insert(4, "123A")?;
         assert_eq!(idx.find_hex("1234")?, Some(0));
         assert_eq!(idx.find_hex("1235")?, Some(1));
         assert_eq!(idx.find_hex("131")?, Some(2));
         assert_eq!(idx.find_hex("cafe")?, Some(3));
         assert_eq!(idx.find_hex("123A")?, Some(4));
         // we masked blocks for all prefixes of "123", including the root
         assert_eq!(idx.nt.masked_readonly_blocks(), 4);
 
         eprintln!("{:?}", idx.nt);
         idx.insert(5, "c0")?;
         assert_eq!(idx.find_hex("cafe")?, Some(3));
         assert_eq!(idx.find_hex("c0")?, Some(5));
         assert_eq!(idx.find_hex("c1")?, None);
         assert_eq!(idx.find_hex("1234")?, Some(0));
         // inserting "c0" is just splitting the 'c' slot of the mutable root,
         // it doesn't mask anything
         assert_eq!(idx.nt.masked_readonly_blocks(), 4);
 
         Ok(())
     }
 
     #[test]
     fn test_invalidate_all() -> Result<(), NodeMapError> {
         let mut idx = TestNtIndex::new();
         idx.insert(0, "1234")?;
         idx.insert(1, "1235")?;
         idx.insert(2, "131")?;
         idx.insert(3, "cafe")?;
         let mut idx = idx.commit();
 
         idx.nt.invalidate_all();
 
         assert_eq!(idx.find_hex("1234")?, None);
         assert_eq!(idx.find_hex("1235")?, None);
         assert_eq!(idx.find_hex("131")?, None);
         assert_eq!(idx.find_hex("cafe")?, None);
         // all the readonly blocks have been masked, this is the
         // conventional expected response
         assert_eq!(idx.nt.masked_readonly_blocks(), idx.nt.readonly.len() + 1);
         Ok(())
     }
 
     #[test]
     fn test_into_added_empty() {
         assert!(sample_nodetree().into_readonly_and_added().1.is_empty());
         assert!(sample_nodetree()
             .into_readonly_and_added_bytes()
             .1
             .is_empty());
     }
 
     #[test]
     fn test_into_added_bytes() -> Result<(), NodeMapError> {
         let mut idx = TestNtIndex::new();
         idx.insert(0, "1234")?;
         let mut idx = idx.commit();
         idx.insert(4, "cafe")?;
         let (_, bytes) = idx.nt.into_readonly_and_added_bytes();
 
         // only the root block has been changed
         assert_eq!(bytes.len(), BLOCK_SIZE);
         // big endian for -2
         assert_eq!(&bytes[4..2 * 4], [255, 255, 255, 254]);
         // big endian for -6
         assert_eq!(&bytes[12 * 4..13 * 4], [255, 255, 255, 250]);
         Ok(())
     }
 }

rust/hg-core/src/utils.rs

@@ -1,168 +1,169
 // utils 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.
 
 //! Contains useful functions, traits, structs, etc. for use in core.
 
 use crate::utils::hg_path::HgPath;
 use std::{io::Write, ops::Deref};
 
 pub mod files;
 pub mod hg_path;
 pub mod path_auditor;
 
 /// Useful until rust/issues/56345 is stable
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::find_slice_in_slice;
 ///
 /// let haystack = b"This is the haystack".to_vec();
 /// assert_eq!(find_slice_in_slice(&haystack, b"the"), Some(8));
 /// assert_eq!(find_slice_in_slice(&haystack, b"not here"), None);
 /// ```
 pub fn find_slice_in_slice<T>(slice: &[T], needle: &[T]) -> Option<usize>
 where
     for<'a> &'a [T]: PartialEq,
 {
     slice
         .windows(needle.len())
         .position(|window| window == needle)
 }
 
 /// Replaces the `from` slice with the `to` slice inside the `buf` slice.
 ///
 /// # Examples
 ///
 /// ```
 /// use crate::hg::utils::replace_slice;
 /// let mut line = b"I hate writing tests!".to_vec();
 /// replace_slice(&mut line, b"hate", b"love");
 /// assert_eq!(
 ///     line,
 ///     b"I love writing tests!".to_vec()
 /// );
 /// ```
 pub fn replace_slice<T>(buf: &mut [T], from: &[T], to: &[T])
 where
     T: Clone + PartialEq,
 {
     if buf.len() < from.len() || from.len() != to.len() {
         return;
     }
     for i in 0..=buf.len() - from.len() {
         if buf[i..].starts_with(from) {
             buf[i..(i + from.len())].clone_from_slice(to);
         }
     }
 }
 
 pub trait SliceExt {
     fn trim_end(&self) -> &Self;
     fn trim_start(&self) -> &Self;
     fn trim(&self) -> &Self;
     fn drop_prefix(&self, needle: &Self) -> Option<&Self>;
 }
 
+#[allow(clippy::trivially_copy_pass_by_ref)]
 fn is_not_whitespace(c: &u8) -> bool {
     !(*c as char).is_whitespace()
 }
 
 impl SliceExt for [u8] {
     fn trim_end(&self) -> &[u8] {
         if let Some(last) = self.iter().rposition(is_not_whitespace) {
-            &self[..last + 1]
+            &self[..=last]
         } else {
             &[]
         }
     }
     fn trim_start(&self) -> &[u8] {
         if let Some(first) = self.iter().position(is_not_whitespace) {
             &self[first..]
         } else {
             &[]
         }
     }
 
     /// ```
     /// use hg::utils::SliceExt;
     /// assert_eq!(
     ///     b"  to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"to trim  ".trim(),
     ///     b"to trim"
     /// );
     /// assert_eq!(
     ///     b"  to trim".trim(),
     ///     b"to trim"
     /// );
     /// ```
     fn trim(&self) -> &[u8] {
         self.trim_start().trim_end()
     }
 
     fn drop_prefix(&self, needle: &Self) -> Option<&Self> {
         if self.starts_with(needle) {
             Some(&self[needle.len()..])
         } else {
             None
         }
     }
 }
 
 pub trait Escaped {
     /// Return bytes escaped for display to the user
     fn escaped_bytes(&self) -> Vec<u8>;
 }
 
 impl Escaped for u8 {
     fn escaped_bytes(&self) -> Vec<u8> {
         let mut acc = vec![];
         match self {
             c @ b'\'' | c @ b'\\' => {
                 acc.push(b'\\');
                 acc.push(*c);
             }
             b'\t' => {
                 acc.extend(br"\\t");
             }
             b'\n' => {
                 acc.extend(br"\\n");
             }
             b'\r' => {
                 acc.extend(br"\\r");
             }
             c if (*c < b' ' || *c >= 127) => {
                 write!(acc, "\\x{:x}", self).unwrap();
             }
             c => {
                 acc.push(*c);
             }
         }
         acc
     }
 }
 
 impl<'a, T: Escaped> Escaped for &'a [T] {
     fn escaped_bytes(&self) -> Vec<u8> {
-        self.iter().flat_map(|item| item.escaped_bytes()).collect()
+        self.iter().flat_map(Escaped::escaped_bytes).collect()
     }
 }
 
 impl<T: Escaped> Escaped for Vec<T> {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.deref().escaped_bytes()
     }
 }
 
 impl<'a> Escaped for &'a HgPath {
     fn escaped_bytes(&self) -> Vec<u8> {
         self.as_bytes().escaped_bytes()
     }
 }

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

@@ -1,384 +1,382
 // files.rs
 //
 // Copyright 2019
 // Raphaël Gomès <[e-mail]>,
 // Yuya Nishihara <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Functions for fiddling with files.
 
 use crate::utils::{
     hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
     path_auditor::PathAuditor,
     replace_slice,
 };
 use lazy_static::lazy_static;
 use same_file::is_same_file;
 use std::borrow::ToOwned;
 use std::fs::Metadata;
 use std::iter::FusedIterator;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(bytes);
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     // Perhaps, the return type would have to be Result<PathBuf>.
 
     Path::new(os_str)
 }
 
 // TODO: need to convert from WTF8 to MBCS bytes on Windows.
 // that's why Vec<u8> is returned.
 #[cfg(unix)]
 pub fn get_bytes_from_path(path: impl AsRef<Path>) -> Vec<u8> {
     use std::os::unix::ffi::OsStrExt;
     path.as_ref().as_os_str().as_bytes().to_vec()
 }
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub struct Ancestors<'a> {
     next: Option<&'a HgPath>,
 }
 
 impl<'a> Iterator for Ancestors<'a> {
     type Item = &'a HgPath;
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some(s) if s.is_empty() => None,
             Some(s) => {
                 let p = s.bytes().rposition(|c| *c == b'/').unwrap_or(0);
                 Some(HgPath::new(&s.as_bytes()[..p]))
             }
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for Ancestors<'a> {}
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub(crate) struct AncestorsWithBase<'a> {
     next: Option<(&'a HgPath, &'a HgPath)>,
 }
 
 impl<'a> Iterator for AncestorsWithBase<'a> {
     type Item = (&'a HgPath, &'a HgPath);
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some((s, _)) if s.is_empty() => None,
             Some((s, _)) => Some(s.split_filename()),
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for AncestorsWithBase<'a> {}
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
-pub fn find_dirs<'a>(path: &'a HgPath) -> Ancestors<'a> {
+pub fn find_dirs(path: &HgPath) -> Ancestors {
     let mut dirs = Ancestors { next: Some(path) };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
-pub(crate) fn find_dirs_with_base<'a>(
-    path: &'a HgPath,
-) -> AncestorsWithBase<'a> {
+pub(crate) fn find_dirs_with_base(path: &HgPath) -> AncestorsWithBase {
     let mut dirs = AncestorsWithBase {
         next: Some((path, HgPath::new(b""))),
     };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// TODO more than ASCII?
 pub fn normalize_case(path: &HgPath) -> HgPathBuf {
     #[cfg(windows)] // NTFS compares via upper()
     return path.to_ascii_uppercase();
     #[cfg(unix)]
     path.to_ascii_lowercase()
 }
 
 lazy_static! {
     static ref IGNORED_CHARS: Vec<Vec<u8>> = {
         [
             0x200c, 0x200d, 0x200e, 0x200f, 0x202a, 0x202b, 0x202c, 0x202d,
             0x202e, 0x206a, 0x206b, 0x206c, 0x206d, 0x206e, 0x206f, 0xfeff,
         ]
         .iter()
         .map(|code| {
             std::char::from_u32(*code)
                 .unwrap()
                 .encode_utf8(&mut [0; 3])
                 .bytes()
                 .collect()
         })
         .collect()
     };
 }
 
 fn hfs_ignore_clean(bytes: &[u8]) -> Vec<u8> {
     let mut buf = bytes.to_owned();
     let needs_escaping = bytes.iter().any(|b| *b == b'\xe2' || *b == b'\xef');
     if needs_escaping {
         for forbidden in IGNORED_CHARS.iter() {
             replace_slice(&mut buf, forbidden, &[])
         }
         buf
     } else {
         buf
     }
 }
 
 pub fn lower_clean(bytes: &[u8]) -> Vec<u8> {
     hfs_ignore_clean(&bytes.to_ascii_lowercase())
 }
 
 #[derive(Eq, PartialEq, Ord, PartialOrd, Copy, Clone)]
 pub struct HgMetadata {
     pub st_dev: u64,
     pub st_mode: u32,
     pub st_nlink: u64,
     pub st_size: u64,
     pub st_mtime: i64,
     pub st_ctime: i64,
 }
 
 // TODO support other plaforms
 #[cfg(unix)]
 impl HgMetadata {
     pub fn from_metadata(metadata: Metadata) -> Self {
         use std::os::unix::fs::MetadataExt;
         Self {
             st_dev: metadata.dev(),
             st_mode: metadata.mode(),
             st_nlink: metadata.nlink(),
             st_size: metadata.size(),
             st_mtime: metadata.mtime(),
             st_ctime: metadata.ctime(),
         }
     }
 }
 
 /// Returns the canonical path of `name`, given `cwd` and `root`
 pub fn canonical_path(
     root: impl AsRef<Path>,
     cwd: impl AsRef<Path>,
     name: impl AsRef<Path>,
 ) -> Result<PathBuf, HgPathError> {
     // TODO add missing normalization for other platforms
     let root = root.as_ref();
     let cwd = cwd.as_ref();
     let name = name.as_ref();
 
     let name = if !name.is_absolute() {
         root.join(&cwd).join(&name)
     } else {
         name.to_owned()
     };
     let auditor = PathAuditor::new(&root);
     if name != root && name.starts_with(&root) {
         let name = name.strip_prefix(&root).unwrap();
         auditor.audit_path(path_to_hg_path_buf(name)?)?;
-        return Ok(name.to_owned());
+        Ok(name.to_owned())
     } else if name == root {
-        return Ok("".into());
+        Ok("".into())
     } else {
         // Determine whether `name' is in the hierarchy at or beneath `root',
         // by iterating name=name.parent() until it returns `None` (can't
         // check name == '/', because that doesn't work on windows).
         let mut name = name.deref();
         let original_name = name.to_owned();
         loop {
             let same = is_same_file(&name, &root).unwrap_or(false);
             if same {
                 if name == original_name {
                     // `name` was actually the same as root (maybe a symlink)
                     return Ok("".into());
                 }
                 // `name` is a symlink to root, so `original_name` is under
                 // root
                 let rel_path = original_name.strip_prefix(&name).unwrap();
                 auditor.audit_path(path_to_hg_path_buf(&rel_path)?)?;
                 return Ok(rel_path.to_owned());
             }
             name = match name.parent() {
                 None => break,
                 Some(p) => p,
             };
         }
         // TODO hint to the user about using --cwd
         // Bubble up the responsibility to Python for now
         Err(HgPathError::NotUnderRoot {
             path: original_name.to_owned(),
             root: root.to_owned(),
         })
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
         let mut dirs = super::find_dirs(HgPath::new(b"foo/bar/baz"));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo/bar")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn find_dirs_empty() {
         // looks weird, but mercurial.pathutil.finddirs(b"") yields b""
         let mut dirs = super::find_dirs(HgPath::new(b""));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_some() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b"foo/bar/baz"));
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo/bar"), HgPath::new(b"baz")))
         );
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo"), HgPath::new(b"bar")))
         );
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b"foo"))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_empty() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b""));
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b""))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_canonical_path() {
         let root = Path::new("/repo");
         let cwd = Path::new("/dir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/dir/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("repo/filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo/subdir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("subdir/filename"))
         );
     }
 
     #[test]
     fn test_canonical_path_not_rooted() {
         use std::fs::create_dir;
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let beneath_repo = base_dir_path.join("a");
         let root = base_dir_path.join("a/b");
         let out_of_repo = base_dir_path.join("c");
         let under_repo_symlink = out_of_repo.join("d");
 
         create_dir(&beneath_repo).unwrap();
         create_dir(&root).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
 
         assert_eq!(
             canonical_path(&root, Path::new(""), out_of_repo),
             Ok(PathBuf::from(""))
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &beneath_repo),
             Err(HgPathError::NotUnderRoot {
                 path: beneath_repo.to_owned(),
                 root: root.to_owned()
             })
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &under_repo_symlink),
             Ok(PathBuf::from("d"))
         );
     }
 }

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

@@ -1,768 +1,765
 // hg_path.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 std::borrow::Borrow;
 use std::ffi::{OsStr, OsString};
 use std::fmt;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 #[derive(Debug, Eq, PartialEq)]
 pub enum HgPathError {
     /// Bytes from the invalid `HgPath`
     LeadingSlash(Vec<u8>),
     ConsecutiveSlashes {
         bytes: Vec<u8>,
         second_slash_index: usize,
     },
     ContainsNullByte {
         bytes: Vec<u8>,
         null_byte_index: usize,
     },
     /// Bytes
     DecodeError(Vec<u8>),
     /// The rest come from audit errors
     EndsWithSlash(HgPathBuf),
     ContainsIllegalComponent(HgPathBuf),
     /// Path is inside the `.hg` folder
     InsideDotHg(HgPathBuf),
     IsInsideNestedRepo {
         path: HgPathBuf,
         nested_repo: HgPathBuf,
     },
     TraversesSymbolicLink {
         path: HgPathBuf,
         symlink: HgPathBuf,
     },
     NotFsCompliant(HgPathBuf),
     /// `path` is the smallest invalid path
     NotUnderRoot {
         path: PathBuf,
         root: PathBuf,
     },
 }
 
 impl ToString for HgPathError {
     fn to_string(&self) -> String {
         match self {
             HgPathError::LeadingSlash(bytes) => {
                 format!("Invalid HgPath '{:?}': has a leading slash.", bytes)
             }
             HgPathError::ConsecutiveSlashes {
                 bytes,
                 second_slash_index: pos,
             } => format!(
                 "Invalid HgPath '{:?}': consecutive slashes at pos {}.",
                 bytes, pos
             ),
             HgPathError::ContainsNullByte {
                 bytes,
                 null_byte_index: pos,
             } => format!(
                 "Invalid HgPath '{:?}': contains null byte at pos {}.",
                 bytes, pos
             ),
             HgPathError::DecodeError(bytes) => {
                 format!("Invalid HgPath '{:?}': could not be decoded.", bytes)
             }
             HgPathError::EndsWithSlash(path) => {
                 format!("Audit failed for '{}': ends with a slash.", path)
             }
             HgPathError::ContainsIllegalComponent(path) => format!(
                 "Audit failed for '{}': contains an illegal component.",
                 path
             ),
             HgPathError::InsideDotHg(path) => format!(
                 "Audit failed for '{}': is inside the '.hg' folder.",
                 path
             ),
             HgPathError::IsInsideNestedRepo {
                 path,
                 nested_repo: nested,
             } => format!(
                 "Audit failed for '{}': is inside a nested repository '{}'.",
                 path, nested
             ),
             HgPathError::TraversesSymbolicLink { path, symlink } => format!(
                 "Audit failed for '{}': traverses symbolic link '{}'.",
                 path, symlink
             ),
             HgPathError::NotFsCompliant(path) => format!(
                 "Audit failed for '{}': cannot be turned into a \
                  filesystem path.",
                 path
             ),
             HgPathError::NotUnderRoot { path, root } => format!(
                 "Audit failed for '{}': not under root {}.",
                 path.display(),
                 root.display()
             ),
         }
     }
 }
 
 impl From<HgPathError> for std::io::Error {
     fn from(e: HgPathError) -> Self {
         std::io::Error::new(std::io::ErrorKind::InvalidData, e.to_string())
     }
 }
 
 /// This is a repository-relative path (or canonical path):
 ///     - no null characters
 ///     - `/` separates directories
 ///     - no consecutive slashes
 ///     - no leading slash,
 ///     - no `.` nor `..` of special meaning
 ///     - stored in repository and shared across platforms
 ///
 /// Note: there is no guarantee of any `HgPath` being well-formed at any point
 /// in its lifetime for performance reasons and to ease ergonomics. It is
 /// however checked using the `check_state` method before any file-system
 /// operation.
 ///
 /// This allows us to be encoding-transparent as much as possible, until really
 /// needed; `HgPath` can be transformed into a platform-specific path (`OsStr`
 /// or `Path`) whenever more complex operations are needed:
 /// On Unix, it's just byte-to-byte conversion. On Windows, it has to be
 /// decoded from MBCS to WTF-8. If WindowsUTF8Plan is implemented, the source
 /// character encoding will be determined on a per-repository basis.
 //
 // FIXME: (adapted from a comment in the stdlib)
 // `HgPath::new()` current implementation relies on `Slice` being
 // layout-compatible with `[u8]`.
 // When attribute privacy is implemented, `Slice` should be annotated as
 // `#[repr(transparent)]`.
 // Anyway, `Slice` representation and layout are considered implementation
 // detail, are not documented and must not be relied upon.
 #[derive(Eq, Ord, PartialEq, PartialOrd, Hash)]
 pub struct HgPath {
     inner: [u8],
 }
 
 impl HgPath {
     pub fn new<S: AsRef<[u8]> + ?Sized>(s: &S) -> &Self {
         unsafe { &*(s.as_ref() as *const [u8] as *const Self) }
     }
     pub fn is_empty(&self) -> bool {
         self.inner.is_empty()
     }
     pub fn len(&self) -> usize {
         self.inner.len()
     }
     fn to_hg_path_buf(&self) -> HgPathBuf {
         HgPathBuf {
             inner: self.inner.to_owned(),
         }
     }
     pub fn bytes(&self) -> std::slice::Iter<u8> {
         self.inner.iter()
     }
     pub fn to_ascii_uppercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_uppercase())
     }
     pub fn to_ascii_lowercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_lowercase())
     }
     pub fn as_bytes(&self) -> &[u8] {
         &self.inner
     }
     pub fn contains(&self, other: u8) -> bool {
         self.inner.contains(&other)
     }
     pub fn starts_with(&self, needle: impl AsRef<Self>) -> bool {
         self.inner.starts_with(needle.as_ref().as_bytes())
     }
     pub fn trim_trailing_slash(&self) -> &Self {
         Self::new(if self.inner.last() == Some(&b'/') {
             &self.inner[..self.inner.len() - 1]
         } else {
             &self.inner[..]
         })
     }
     /// Returns a tuple of slices `(base, filename)` resulting from the split
     /// at the rightmost `/`, if any.
     ///
     /// # Examples:
     ///
     /// ```
     /// use hg::utils::hg_path::HgPath;
     ///
     /// let path = HgPath::new(b"cool/hg/path").split_filename();
     /// assert_eq!(path, (HgPath::new(b"cool/hg"), HgPath::new(b"path")));
     ///
     /// let path = HgPath::new(b"pathwithoutsep").split_filename();
     /// assert_eq!(path, (HgPath::new(b""), HgPath::new(b"pathwithoutsep")));
     /// ```
     pub fn split_filename(&self) -> (&Self, &Self) {
         match &self.inner.iter().rposition(|c| *c == b'/') {
             None => (HgPath::new(""), &self),
             Some(size) => (
                 HgPath::new(&self.inner[..*size]),
                 HgPath::new(&self.inner[*size + 1..]),
             ),
         }
     }
     pub fn join<T: ?Sized + AsRef<Self>>(&self, other: &T) -> HgPathBuf {
         let mut inner = self.inner.to_owned();
-        if inner.len() != 0 && inner.last() != Some(&b'/') {
+        if !inner.is_empty() && inner.last() != Some(&b'/') {
             inner.push(b'/');
         }
         inner.extend(other.as_ref().bytes());
         HgPathBuf::from_bytes(&inner)
     }
     pub fn parent(&self) -> &Self {
         let inner = self.as_bytes();
         HgPath::new(match inner.iter().rposition(|b| *b == b'/') {
             Some(pos) => &inner[..pos],
             None => &[],
         })
     }
     /// Given a base directory, returns the slice of `self` relative to the
     /// base directory. If `base` is not a directory (does not end with a
     /// `b'/'`), returns `None`.
     pub fn relative_to(&self, base: impl AsRef<Self>) -> Option<&Self> {
         let base = base.as_ref();
         if base.is_empty() {
             return Some(self);
         }
         let is_dir = base.as_bytes().ends_with(b"/");
         if is_dir && self.starts_with(base) {
             Some(Self::new(&self.inner[base.len()..]))
         } else {
             None
         }
     }
 
     #[cfg(windows)]
     /// Copied from the Python stdlib's `os.path.splitdrive` implementation.
     ///
     /// Split a pathname into drive/UNC sharepoint and relative path
     /// specifiers. Returns a 2-tuple (drive_or_unc, path); either part may
     /// be empty.
     ///
     /// If you assign
     ///  result = split_drive(p)
     /// It is always true that:
     ///  result[0] + result[1] == p
     ///
     /// If the path contained a drive letter, drive_or_unc will contain
     /// everything up to and including the colon.
     /// e.g. split_drive("c:/dir") returns ("c:", "/dir")
     ///
     /// If the path contained a UNC path, the drive_or_unc will contain the
     /// host name and share up to but not including the fourth directory
     /// separator character.
     /// e.g. split_drive("//host/computer/dir") returns ("//host/computer",
     /// "/dir")
     ///
     /// Paths cannot contain both a drive letter and a UNC path.
     pub fn split_drive<'a>(&self) -> (&HgPath, &HgPath) {
         let bytes = self.as_bytes();
         let is_sep = |b| std::path::is_separator(b as char);
 
         if self.len() < 2 {
             (HgPath::new(b""), &self)
         } else if is_sep(bytes[0])
             && is_sep(bytes[1])
             && (self.len() == 2 || !is_sep(bytes[2]))
         {
             // Is a UNC path:
             // vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
             // \\machine\mountpoint\directory\etc\...
             //           directory ^^^^^^^^^^^^^^^
 
             let machine_end_index = bytes[2..].iter().position(|b| is_sep(*b));
             let mountpoint_start_index = if let Some(i) = machine_end_index {
                 i + 2
             } else {
                 return (HgPath::new(b""), &self);
             };
 
             match bytes[mountpoint_start_index + 1..]
                 .iter()
                 .position(|b| is_sep(*b))
             {
                 // A UNC path can't have two slashes in a row
                 // (after the initial two)
                 Some(0) => (HgPath::new(b""), &self),
                 Some(i) => {
                     let (a, b) =
                         bytes.split_at(mountpoint_start_index + 1 + i);
                     (HgPath::new(a), HgPath::new(b))
                 }
                 None => (&self, HgPath::new(b"")),
             }
         } else if bytes[1] == b':' {
             // Drive path c:\directory
             let (a, b) = bytes.split_at(2);
             (HgPath::new(a), HgPath::new(b))
         } else {
             (HgPath::new(b""), &self)
         }
     }
 
     #[cfg(unix)]
     /// Split a pathname into drive and path. On Posix, drive is always empty.
     pub fn split_drive(&self) -> (&HgPath, &HgPath) {
         (HgPath::new(b""), &self)
     }
 
     /// Checks for errors in the path, short-circuiting at the first one.
     /// This generates fine-grained errors useful for debugging.
     /// To simply check if the path is valid during tests, use `is_valid`.
     pub fn check_state(&self) -> Result<(), HgPathError> {
-        if self.len() == 0 {
+        if self.is_empty() {
             return Ok(());
         }
         let bytes = self.as_bytes();
         let mut previous_byte = None;
 
         if bytes[0] == b'/' {
             return Err(HgPathError::LeadingSlash(bytes.to_vec()));
         }
         for (index, byte) in bytes.iter().enumerate() {
             match byte {
                 0 => {
                     return Err(HgPathError::ContainsNullByte {
                         bytes: bytes.to_vec(),
                         null_byte_index: index,
                     })
                 }
                 b'/' => {
                     if previous_byte.is_some() && previous_byte == Some(b'/') {
                         return Err(HgPathError::ConsecutiveSlashes {
                             bytes: bytes.to_vec(),
                             second_slash_index: index,
                         });
                     }
                 }
                 _ => (),
             };
             previous_byte = Some(*byte);
         }
         Ok(())
     }
 
     #[cfg(test)]
     /// Only usable during tests to force developers to handle invalid states
     fn is_valid(&self) -> bool {
         self.check_state().is_ok()
     }
 }
 
 impl fmt::Debug for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPath({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
-#[derive(Eq, Ord, Clone, PartialEq, PartialOrd, Hash)]
+#[derive(Default, Eq, Ord, Clone, PartialEq, PartialOrd, Hash)]
 pub struct HgPathBuf {
     inner: Vec<u8>,
 }
 
 impl HgPathBuf {
     pub fn new() -> Self {
-        Self { inner: Vec::new() }
+        Default::default()
     }
     pub fn push(&mut self, byte: u8) {
         self.inner.push(byte);
     }
     pub fn from_bytes(s: &[u8]) -> HgPathBuf {
         HgPath::new(s).to_owned()
     }
     pub fn into_vec(self) -> Vec<u8> {
         self.inner
     }
-    pub fn as_ref(&self) -> &[u8] {
-        self.inner.as_ref()
-    }
 }
 
 impl fmt::Debug for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPathBuf({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl Deref for HgPathBuf {
     type Target = HgPath;
 
     #[inline]
     fn deref(&self) -> &HgPath {
         &HgPath::new(&self.inner)
     }
 }
 
 impl From<Vec<u8>> for HgPathBuf {
     fn from(vec: Vec<u8>) -> Self {
         Self { inner: vec }
     }
 }
 
 impl<T: ?Sized + AsRef<HgPath>> From<&T> for HgPathBuf {
     fn from(s: &T) -> HgPathBuf {
         s.as_ref().to_owned()
     }
 }
 
 impl Into<Vec<u8>> for HgPathBuf {
     fn into(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl Borrow<HgPath> for HgPathBuf {
     fn borrow(&self) -> &HgPath {
         &HgPath::new(self.as_bytes())
     }
 }
 
 impl ToOwned for HgPath {
     type Owned = HgPathBuf;
 
     fn to_owned(&self) -> HgPathBuf {
         self.to_hg_path_buf()
     }
 }
 
 impl AsRef<HgPath> for HgPath {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl AsRef<HgPath> for HgPathBuf {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl Extend<u8> for HgPathBuf {
     fn extend<T: IntoIterator<Item = u8>>(&mut self, iter: T) {
         self.inner.extend(iter);
     }
 }
 
 /// TODO: Once https://www.mercurial-scm.org/wiki/WindowsUTF8Plan is
 /// implemented, these conversion utils will have to work differently depending
 /// on the repository encoding: either `UTF-8` or `MBCS`.
 
 pub fn hg_path_to_os_string<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<OsString, HgPathError> {
     hg_path.as_ref().check_state()?;
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(&hg_path.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     Ok(os_str.to_os_string())
 }
 
 pub fn hg_path_to_path_buf<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<PathBuf, HgPathError> {
     Ok(Path::new(&hg_path_to_os_string(hg_path)?).to_path_buf())
 }
 
 pub fn os_string_to_hg_path_buf<S: AsRef<OsStr>>(
     os_string: S,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_string.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 pub fn path_to_hg_path_buf<P: AsRef<Path>>(
     path: P,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     let os_str = path.as_ref().as_os_str();
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_str.as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn test_path_states() {
         assert_eq!(
             Err(HgPathError::LeadingSlash(b"/".to_vec())),
             HgPath::new(b"/").check_state()
         );
         assert_eq!(
             Err(HgPathError::ConsecutiveSlashes {
                 bytes: b"a/b//c".to_vec(),
                 second_slash_index: 4
             }),
             HgPath::new(b"a/b//c").check_state()
         );
         assert_eq!(
             Err(HgPathError::ContainsNullByte {
                 bytes: b"a/b/\0c".to_vec(),
                 null_byte_index: 4
             }),
             HgPath::new(b"a/b/\0c").check_state()
         );
         // TODO test HgPathError::DecodeError for the Windows implementation.
         assert_eq!(true, HgPath::new(b"").is_valid());
         assert_eq!(true, HgPath::new(b"a/b/c").is_valid());
         // Backslashes in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(br"a\b/c").is_valid());
         // Dots in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(b"a/b/../c/").is_valid());
         assert_eq!(true, HgPath::new(b"./a/b/../c/").is_valid());
     }
 
     #[test]
     fn test_iter() {
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'c'), iter.next_back());
         assert_eq!(Some(&b'b'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'b'), iter.next());
         assert_eq!(Some(&b'c'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let iter = path.bytes();
         let mut vec = Vec::new();
         vec.extend(iter);
         assert_eq!(vec![b'a', b'b', b'c'], vec);
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(2), iter.rposition(|c| *c == b'c'));
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(None, iter.rposition(|c| *c == b'd'));
     }
 
     #[test]
     fn test_join() {
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"b"));
         assert_eq!(b"a/b", path.as_bytes());
 
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"b/c"));
         assert_eq!(b"a/b/c", path.as_bytes());
 
         // No leading slash if empty before join
         let path = HgPathBuf::new().join(HgPath::new(b"b/c"));
         assert_eq!(b"b/c", path.as_bytes());
 
         // The leading slash is an invalid representation of an `HgPath`, but
         // it can happen. This creates another invalid representation of
         // consecutive bytes.
         // TODO What should be done in this case? Should we silently remove
         // the extra slash? Should we change the signature to a problematic
         // `Result<HgPathBuf, HgPathError>`, or should we just keep it so and
         // let the error happen upon filesystem interaction?
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
     }
 
     #[test]
     fn test_relative_to() {
         let path = HgPath::new(b"");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"path");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"a");
         let base = HgPath::new(b"b");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a/");
         assert_eq!(Some(HgPath::new(b"b")), path.relative_to(base));
 
         let path = HgPath::new(b"nested/path/to/b");
         let base = HgPath::new(b"nested/path/");
         assert_eq!(Some(HgPath::new(b"to/b")), path.relative_to(base));
 
         let path = HgPath::new(b"ends/with/dir/");
         let base = HgPath::new(b"ends/");
         assert_eq!(Some(HgPath::new(b"with/dir/")), path.relative_to(base));
     }
 
     #[test]
     #[cfg(unix)]
     fn test_split_drive() {
         // Taken from the Python stdlib's tests
         assert_eq!(
             HgPath::new(br"/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"foo:bar"))
         );
         assert_eq!(
             HgPath::new(br":foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br":foo:bar"))
         );
         // Also try NT paths; should not split them
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(b""),
                 HgPath::new(br"\\conky\mountpoint\foo\bar")
             )
         );
     }
 
     #[test]
     #[cfg(windows)]
     fn test_split_drive() {
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br"\\conky\mountpoint"),
                 HgPath::new(br"\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br"//conky/mountpoint"),
                 HgPath::new(br"/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\\conky\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"///conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"///conky/mountpoint/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\conky\\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\conky\\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky//mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"//conky//mountpoint/foo/bar")
             )
         );
         // UNC part containing U+0130
         assert_eq!(
             HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT/foo/bar").split_drive(),
             (
                 HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT"),
                 HgPath::new(br"/foo/bar")
             )
         );
     }
 
     #[test]
     fn test_parent() {
         let path = HgPath::new(b"");
         assert_eq!(path.parent(), path);
 
         let path = HgPath::new(b"a");
         assert_eq!(path.parent(), HgPath::new(b""));
 
         let path = HgPath::new(b"a/b");
         assert_eq!(path.parent(), HgPath::new(b"a"));
 
         let path = HgPath::new(b"a/other/b");
         assert_eq!(path.parent(), HgPath::new(b"a/other"));
     }
 }

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

@@ -1,232 +1,232
 // path_auditor.rs
 //
 // Copyright 2020
 // 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::{
     files::lower_clean,
     find_slice_in_slice,
     hg_path::{hg_path_to_path_buf, HgPath, HgPathBuf, HgPathError},
 };
 use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 use std::sync::{Mutex, RwLock};
 
 /// Ensures that a path is valid for use in the repository i.e. does not use
 /// any banned components, does not traverse a symlink, etc.
 #[derive(Debug, Default)]
 pub struct PathAuditor {
     audited: Mutex<HashSet<HgPathBuf>>,
     audited_dirs: RwLock<HashSet<HgPathBuf>>,
     root: PathBuf,
 }
 
 impl PathAuditor {
     pub fn new(root: impl AsRef<Path>) -> Self {
         Self {
             root: root.as_ref().to_owned(),
             ..Default::default()
         }
     }
     pub fn audit_path(
         &self,
         path: impl AsRef<HgPath>,
     ) -> Result<(), HgPathError> {
         // TODO windows "localpath" normalization
         let path = path.as_ref();
         if path.is_empty() {
             return Ok(());
         }
         // TODO case normalization
         if self.audited.lock().unwrap().contains(path) {
             return Ok(());
         }
         // AIX ignores "/" at end of path, others raise EISDIR.
         let last_byte = path.as_bytes()[path.len() - 1];
         if last_byte == b'/' || last_byte == b'\\' {
             return Err(HgPathError::EndsWithSlash(path.to_owned()));
         }
         let parts: Vec<_> = path
             .as_bytes()
             .split(|b| std::path::is_separator(*b as char))
             .collect();
 
         let first_component = lower_clean(parts[0]);
         let first_component = first_component.as_slice();
         if !path.split_drive().0.is_empty()
             || (first_component == b".hg"
                 || first_component == b".hg."
                 || first_component == b"")
             || parts.iter().any(|c| c == b"..")
         {
             return Err(HgPathError::InsideDotHg(path.to_owned()));
         }
 
         // Windows shortname aliases
         for part in parts.iter() {
             if part.contains(&b'~') {
                 let mut split = part.splitn(2, |b| *b == b'~');
                 let first =
                     split.next().unwrap().to_owned().to_ascii_uppercase();
                 let last = split.next().unwrap();
                 if last.iter().all(u8::is_ascii_digit)
                     && (first == b"HG" || first == b"HG8B6C")
                 {
                     return Err(HgPathError::ContainsIllegalComponent(
                         path.to_owned(),
                     ));
                 }
             }
         }
         let lower_path = lower_clean(path.as_bytes());
         if find_slice_in_slice(&lower_path, b".hg").is_some() {
             let lower_parts: Vec<_> = path
                 .as_bytes()
                 .split(|b| std::path::is_separator(*b as char))
                 .collect();
             for pattern in [b".hg".to_vec(), b".hg.".to_vec()].iter() {
                 if let Some(pos) = lower_parts[1..]
                     .iter()
                     .position(|part| part == &pattern.as_slice())
                 {
                     let base = lower_parts[..=pos]
                         .iter()
                         .fold(HgPathBuf::new(), |acc, p| {
                             acc.join(HgPath::new(p))
                         });
                     return Err(HgPathError::IsInsideNestedRepo {
                         path: path.to_owned(),
                         nested_repo: base,
                     });
                 }
             }
         }
 
         let parts = &parts[..parts.len().saturating_sub(1)];
 
         // We don't want to add "foo/bar/baz" to `audited_dirs` before checking
         // if there's a "foo/.hg" directory. This also means we won't
         // accidentally traverse a symlink into some other filesystem (which
         // is potentially expensive to access).
         for index in 0..parts.len() {
-            let prefix = &parts[..index + 1].join(&b'/');
+            let prefix = &parts[..=index].join(&b'/');
             let prefix = HgPath::new(prefix);
             if self.audited_dirs.read().unwrap().contains(prefix) {
                 continue;
             }
             self.check_filesystem(&prefix, &path)?;
             self.audited_dirs.write().unwrap().insert(prefix.to_owned());
         }
 
         self.audited.lock().unwrap().insert(path.to_owned());
 
         Ok(())
     }
 
     pub fn check_filesystem(
         &self,
         prefix: impl AsRef<HgPath>,
         path: impl AsRef<HgPath>,
     ) -> Result<(), HgPathError> {
         let prefix = prefix.as_ref();
         let path = path.as_ref();
         let current_path = self.root.join(
             hg_path_to_path_buf(prefix)
                 .map_err(|_| HgPathError::NotFsCompliant(path.to_owned()))?,
         );
         match std::fs::symlink_metadata(&current_path) {
             Err(e) => {
                 // EINVAL can be raised as invalid path syntax under win32.
                 if e.kind() != std::io::ErrorKind::NotFound
                     && e.kind() != std::io::ErrorKind::InvalidInput
                     && 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
                     return Err(HgPathError::NotFsCompliant(path.to_owned()));
                 }
             }
             Ok(meta) => {
                 if meta.file_type().is_symlink() {
                     return Err(HgPathError::TraversesSymbolicLink {
                         path: path.to_owned(),
                         symlink: prefix.to_owned(),
                     });
                 }
                 if meta.file_type().is_dir()
                     && current_path.join(".hg").is_dir()
                 {
                     return Err(HgPathError::IsInsideNestedRepo {
                         path: path.to_owned(),
                         nested_repo: prefix.to_owned(),
                     });
                 }
             }
         };
 
         Ok(())
     }
 
     pub fn check(&self, path: impl AsRef<HgPath>) -> bool {
         self.audit_path(path).is_ok()
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::utils::files::get_path_from_bytes;
     use crate::utils::hg_path::path_to_hg_path_buf;
 
     #[test]
     fn test_path_auditor() {
         let auditor = PathAuditor::new(get_path_from_bytes(b"/tmp"));
 
         let path = HgPath::new(b".hg/00changelog.i");
         assert_eq!(
             auditor.audit_path(path),
             Err(HgPathError::InsideDotHg(path.to_owned()))
         );
         let path = HgPath::new(b"this/is/nested/.hg/thing.txt");
         assert_eq!(
             auditor.audit_path(path),
             Err(HgPathError::IsInsideNestedRepo {
                 path: path.to_owned(),
                 nested_repo: HgPathBuf::from_bytes(b"this/is/nested")
             })
         );
 
         use std::fs::{create_dir, File};
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let a = base_dir_path.join("a");
         let b = base_dir_path.join("b");
         create_dir(&a).unwrap();
         let in_a_path = a.join("in_a");
         File::create(in_a_path).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&a, &b).unwrap();
 
         let buf = b.join("in_a").components().skip(2).collect::<PathBuf>();
         eprintln!("buf: {}", buf.display());
         let path = path_to_hg_path_buf(buf).unwrap();
         assert_eq!(
             auditor.audit_path(&path),
             Err(HgPathError::TraversesSymbolicLink {
                 path: path,
                 symlink: path_to_hg_path_buf(
                     b.components().skip(2).collect::<PathBuf>()
                 )
                 .unwrap()
             })
         );
     }
 }

rust/hg-cpython/src/cindex.rs

@@ -1,179 +1,176
 // cindex.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 to use the Index defined by the parsers C extension
 //!
 //! Ideally, we should use an Index entirely implemented in Rust,
 //! but this will take some time to get there.
 
 use cpython::{
     exc::ImportError, ObjectProtocol, PyClone, PyErr, PyObject, PyResult,
     PyTuple, Python, PythonObject,
 };
 use hg::revlog::{Node, RevlogIndex};
 use hg::{Graph, GraphError, Revision, WORKING_DIRECTORY_REVISION};
 use libc::c_int;
 
 const REVLOG_CABI_VERSION: c_int = 2;
 
 #[repr(C)]
 pub struct Revlog_CAPI {
     abi_version: c_int,
     index_length:
         unsafe extern "C" fn(index: *mut revlog_capi::RawPyObject) -> c_int,
     index_node: unsafe extern "C" fn(
         index: *mut revlog_capi::RawPyObject,
         rev: c_int,
     ) -> *const Node,
     index_parents: unsafe extern "C" fn(
         index: *mut revlog_capi::RawPyObject,
         rev: c_int,
         ps: *mut [c_int; 2],
     ) -> c_int,
 }
 
 py_capsule!(
     from mercurial.cext.parsers import revlog_CAPI
         as revlog_capi for Revlog_CAPI);
 
 /// A `Graph` backed up by objects and functions from revlog.c
 ///
 /// This implementation of the `Graph` trait, relies on (pointers to)
 /// - the C index object (`index` member)
 /// - the `index_get_parents()` function (`parents` member)
 ///
 /// # Safety
 ///
 /// The C index itself is mutable, and this Rust exposition is **not
 /// protected by the GIL**, meaning that this construct isn't safe with respect
 /// to Python threads.
 ///
 /// All callers of this `Index` must acquire the GIL and must not release it
 /// while working.
 ///
 /// # TODO find a solution to make it GIL safe again.
 ///
 /// This is non trivial, and can wait until we have a clearer picture with
 /// more Rust Mercurial constructs.
 ///
 /// One possibility would be to a `GILProtectedIndex` wrapper enclosing
 /// a `Python<'p>` marker and have it be the one implementing the
 /// `Graph` trait, but this would mean the `Graph` implementor would become
 /// likely to change between subsequent method invocations of the `hg-core`
 /// objects (a serious change of the `hg-core` API):
 /// either exposing ways to mutate the `Graph`, or making it a non persistent
 /// parameter in the relevant methods that need one.
 ///
 /// Another possibility would be to introduce an abstract lock handle into
 /// the core API, that would be tied to `GILGuard` / `Python<'p>`
 /// in the case of the `cpython` crate bindings yet could leave room for other
 /// mechanisms in other contexts.
 pub struct Index {
     index: PyObject,
     capi: &'static Revlog_CAPI,
 }
 
 impl Index {
     pub fn new(py: Python, index: PyObject) -> PyResult<Self> {
         let capi = unsafe { revlog_capi::retrieve(py)? };
         if capi.abi_version != REVLOG_CABI_VERSION {
             return Err(PyErr::new::<ImportError, _>(
                 py,
                 format!(
                     "ABI version mismatch: the C ABI revlog version {} \
                      does not match the {} expected by Rust hg-cpython",
                     capi.abi_version, REVLOG_CABI_VERSION
                 ),
             ));
         }
-        Ok(Index {
-            index: index,
-            capi: capi,
-        })
+        Ok(Index { index, capi })
     }
 
     /// return a reference to the CPython Index object in this Struct
     pub fn inner(&self) -> &PyObject {
         &self.index
     }
 
     pub fn append(&mut self, py: Python, tup: PyTuple) -> PyResult<PyObject> {
         self.index.call_method(
             py,
             "append",
             PyTuple::new(py, &[tup.into_object()]),
             None,
         )
     }
 }
 
 impl Clone for Index {
     fn clone(&self) -> Self {
         let guard = Python::acquire_gil();
         Index {
             index: self.index.clone_ref(guard.python()),
             capi: self.capi,
         }
     }
 }
 
 impl PyClone for Index {
     fn clone_ref(&self, py: Python) -> Self {
         Index {
             index: self.index.clone_ref(py),
             capi: self.capi,
         }
     }
 }
 
 impl Graph for Index {
     /// wrap a call to the C extern parents function
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         if rev == WORKING_DIRECTORY_REVISION {
             return Err(GraphError::WorkingDirectoryUnsupported);
         }
         let mut res: [c_int; 2] = [0; 2];
         let code = unsafe {
             (self.capi.index_parents)(
                 self.index.as_ptr(),
                 rev as c_int,
                 &mut res as *mut [c_int; 2],
             )
         };
         match code {
             0 => Ok(res),
             _ => Err(GraphError::ParentOutOfRange(rev)),
         }
     }
 }
 
 impl RevlogIndex for Index {
     /// Note C return type is Py_ssize_t (hence signed), but we shall
     /// force it to unsigned, because it's a length
     fn len(&self) -> usize {
         unsafe { (self.capi.index_length)(self.index.as_ptr()) as usize }
     }
 
-    fn node<'a>(&'a self, rev: Revision) -> Option<&'a Node> {
+    fn node(&self, rev: Revision) -> Option<&Node> {
         let raw = unsafe {
             (self.capi.index_node)(self.index.as_ptr(), rev as c_int)
         };
         if raw.is_null() {
             None
         } else {
             // TODO it would be much better for the C layer to give us
             // a length, since the hash length will change in the near
             // future, but that's probably out of scope for the nodemap
             // patch series.
             //
             // The root of that unsafety relies in the signature of
             // `capi.index_node()` itself: returning a `Node` pointer
             // whereas it's a `char *` in the C counterpart.
             Some(unsafe { &*raw })
         }
     }
 }

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

@@ -1,118 +1,118
 // copymap.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 `hg::dirstate::dirstate_map::CopyMap` provided by the
 //! `hg-core` package.
 
 use cpython::{
     PyBytes, PyClone, PyDict, PyObject, PyResult, Python, UnsafePyLeaked,
 };
 use std::cell::RefCell;
 
 use crate::dirstate::dirstate_map::DirstateMap;
 use hg::{utils::hg_path::HgPathBuf, CopyMapIter};
 
 py_class!(pub class CopyMap |py| {
     data dirstate_map: DirstateMap;
 
     def __getitem__(&self, key: PyObject) -> PyResult<PyBytes> {
         (*self.dirstate_map(py)).copymapgetitem(py, key)
     }
 
     def __len__(&self) -> PyResult<usize> {
         self.dirstate_map(py).copymaplen(py)
     }
 
     def __contains__(&self, key: PyObject) -> PyResult<bool> {
         self.dirstate_map(py).copymapcontains(py, key)
     }
 
     def get(
         &self,
         key: PyObject,
         default: Option<PyObject> = None
     ) -> PyResult<Option<PyObject>> {
         self.dirstate_map(py).copymapget(py, key, default)
     }
 
     def pop(
         &self,
         key: PyObject,
         default: Option<PyObject> = None
     ) -> PyResult<Option<PyObject>> {
         self.dirstate_map(py).copymappop(py, key, default)
     }
 
     def __iter__(&self) -> PyResult<CopyMapKeysIterator> {
         self.dirstate_map(py).copymapiter(py)
     }
 
     // Python's `dict()` builtin works with either a subclass of dict
     // or an abstract mapping. Said mapping needs to implement `__getitem__`
     // and `keys`.
     def keys(&self) -> PyResult<CopyMapKeysIterator> {
         self.dirstate_map(py).copymapiter(py)
     }
 
     def items(&self) -> PyResult<CopyMapItemsIterator> {
         self.dirstate_map(py).copymapitemsiter(py)
     }
 
     def iteritems(&self) -> PyResult<CopyMapItemsIterator> {
         self.dirstate_map(py).copymapitemsiter(py)
     }
 
     def __setitem__(
         &self,
         key: PyObject,
         item: PyObject
     ) -> PyResult<()> {
         self.dirstate_map(py).copymapsetitem(py, key, item)?;
         Ok(())
     }
 
     def copy(&self) -> PyResult<PyDict> {
         self.dirstate_map(py).copymapcopy(py)
     }
 
 });
 
 impl CopyMap {
     pub fn from_inner(py: Python, dm: DirstateMap) -> PyResult<Self> {
         Self::create_instance(py, dm)
     }
     fn translate_key(
         py: Python,
         res: (&HgPathBuf, &HgPathBuf),
     ) -> PyResult<Option<PyBytes>> {
-        Ok(Some(PyBytes::new(py, res.0.as_ref())))
+        Ok(Some(PyBytes::new(py, res.0.as_bytes())))
     }
     fn translate_key_value(
         py: Python,
         res: (&HgPathBuf, &HgPathBuf),
     ) -> PyResult<Option<(PyBytes, PyBytes)>> {
         let (k, v) = res;
         Ok(Some((
-            PyBytes::new(py, k.as_ref()),
-            PyBytes::new(py, v.as_ref()),
+            PyBytes::new(py, k.as_bytes()),
+            PyBytes::new(py, v.as_bytes()),
         )))
     }
 }
 
 py_shared_iterator!(
     CopyMapKeysIterator,
     UnsafePyLeaked<CopyMapIter<'static>>,
     CopyMap::translate_key,
     Option<PyBytes>
 );
 
 py_shared_iterator!(
     CopyMapItemsIterator,
     UnsafePyLeaked<CopyMapIter<'static>>,
     CopyMap::translate_key_value,
     Option<(PyBytes, PyBytes)>
 );

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

@@ -1,140 +1,140
 // dirs_multiset.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::dirs_multiset` file provided by the
 //! `hg-core` package.
 
 use std::cell::RefCell;
 use std::convert::TryInto;
 
 use cpython::{
     exc, ObjectProtocol, PyBytes, PyClone, PyDict, PyErr, PyObject, PyResult,
     Python, UnsafePyLeaked,
 };
 
 use crate::dirstate::extract_dirstate;
 use hg::{
     utils::hg_path::{HgPath, HgPathBuf},
     DirsMultiset, DirsMultisetIter, DirstateMapError, DirstateParseError,
     EntryState,
 };
 
 py_class!(pub class Dirs |py| {
     @shared data inner: DirsMultiset;
 
     // `map` is either a `dict` or a flat iterator (usually a `set`, sometimes
     // a `list`)
     def __new__(
         _cls,
         map: PyObject,
         skip: Option<PyObject> = None
     ) -> PyResult<Self> {
         let mut skip_state: Option<EntryState> = None;
         if let Some(skip) = skip {
             skip_state = Some(
                 skip.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
             );
         }
         let inner = if let Ok(map) = map.cast_as::<PyDict>(py) {
             let dirstate = extract_dirstate(py, &map)?;
             DirsMultiset::from_dirstate(&dirstate, skip_state)
                 .map_err(|e| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 })?
         } else {
             let map: Result<Vec<HgPathBuf>, PyErr> = map
                 .iter(py)?
                 .map(|o| {
                     Ok(HgPathBuf::from_bytes(
                         o?.extract::<PyBytes>(py)?.data(py),
                     ))
                 })
                 .collect();
             DirsMultiset::from_manifest(&map?)
                 .map_err(|e| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 })?
         };
 
         Self::create_instance(py, inner)
     }
 
     def addpath(&self, path: PyObject) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().add_path(
             HgPath::new(path.extract::<PyBytes>(py)?.data(py)),
         ).and(Ok(py.None())).or_else(|e| {
             match e {
                 DirstateMapError::EmptyPath => {
                     Ok(py.None())
                 },
                 e => {
                     Err(PyErr::new::<exc::ValueError, _>(
                         py,
                         e.to_string(),
                     ))
                 }
             }
         })
     }
 
     def delpath(&self, path: PyObject) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().delete_path(
             HgPath::new(path.extract::<PyBytes>(py)?.data(py)),
         )
             .and(Ok(py.None()))
             .or_else(|e| {
                 match e {
                     DirstateMapError::EmptyPath => {
                         Ok(py.None())
                     },
                     e => {
                         Err(PyErr::new::<exc::ValueError, _>(
                             py,
                             e.to_string(),
                         ))
                     }
                 }
             })
     }
     def __iter__(&self) -> PyResult<DirsMultisetKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirsMultisetKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def __contains__(&self, item: PyObject) -> PyResult<bool> {
         Ok(self.inner(py).borrow().contains(HgPath::new(
             item.extract::<PyBytes>(py)?.data(py).as_ref(),
         )))
     }
 });
 
 impl Dirs {
     pub fn from_inner(py: Python, d: DirsMultiset) -> PyResult<Self> {
         Self::create_instance(py, d)
     }
 
     fn translate_key(
         py: Python,
         res: &HgPathBuf,
     ) -> PyResult<Option<PyBytes>> {
-        Ok(Some(PyBytes::new(py, res.as_ref())))
+        Ok(Some(PyBytes::new(py, res.as_bytes())))
     }
 }
 
 py_shared_iterator!(
     DirsMultisetKeysIterator,
     UnsafePyLeaked<DirsMultisetIter<'static>>,
     Dirs::translate_key,
     Option<PyBytes>
 );

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

@@ -1,586 +1,590
 // 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.
 
 //! Bindings for the `hg::dirstate::dirstate_map` file provided by the
 //! `hg-core` package.
 
 use std::cell::{Ref, RefCell};
 use std::convert::TryInto;
 use std::time::Duration;
 
 use cpython::{
     exc, ObjectProtocol, PyBool, PyBytes, PyClone, PyDict, PyErr, PyList,
     PyObject, PyResult, PyString, PyTuple, Python, PythonObject, ToPyObject,
     UnsafePyLeaked,
 };
 
 use crate::{
     dirstate::copymap::{CopyMap, CopyMapItemsIterator, CopyMapKeysIterator},
     dirstate::non_normal_entries::{
         NonNormalEntries, NonNormalEntriesIterator,
     },
     dirstate::{dirs_multiset::Dirs, make_dirstate_tuple},
 };
 use hg::{
     utils::hg_path::{HgPath, HgPathBuf},
     DirsMultiset, DirstateEntry, DirstateMap as RustDirstateMap,
     DirstateMapError, DirstateParents, DirstateParseError, EntryState,
     StateMapIter, PARENT_SIZE,
 };
 
 // TODO
 //     This object needs to share references to multiple members of its Rust
 //     inner struct, namely `copy_map`, `dirs` and `all_dirs`.
 //     Right now `CopyMap` is done, but it needs to have an explicit reference
 //     to `RustDirstateMap` which itself needs to have an encapsulation for
 //     every method in `CopyMap` (copymapcopy, etc.).
 //     This is ugly and hard to maintain.
 //     The same logic applies to `dirs` and `all_dirs`, however the `Dirs`
 //     `py_class!` is already implemented and does not mention
 //     `RustDirstateMap`, rightfully so.
 //     All attributes also have to have a separate refcount data attribute for
 //     leaks, with all methods that go along for reference sharing.
 py_class!(pub class DirstateMap |py| {
     @shared data inner: RustDirstateMap;
 
     def __new__(_cls, _root: PyObject) -> PyResult<Self> {
         let inner = RustDirstateMap::default();
         Self::create_instance(py, inner)
     }
 
     def clear(&self) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().clear();
         Ok(py.None())
     }
 
     def get(
         &self,
         key: PyObject,
         default: Option<PyObject> = None
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self.inner(py).borrow().get(HgPath::new(key.data(py))) {
             Some(entry) => {
                 Ok(Some(make_dirstate_tuple(py, entry)?))
             },
             None => Ok(default)
         }
     }
 
     def addfile(
         &self,
         f: PyObject,
         oldstate: PyObject,
         state: PyObject,
         mode: PyObject,
         size: PyObject,
         mtime: PyObject
     ) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().add_file(
             HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
             oldstate.extract::<PyBytes>(py)?.data(py)[0]
                 .try_into()
                 .map_err(|e: DirstateParseError| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 })?,
             DirstateEntry {
                 state: state.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
                 mode: mode.extract(py)?,
                 size: size.extract(py)?,
                 mtime: mtime.extract(py)?,
             },
         ).and(Ok(py.None())).or_else(|e: DirstateMapError| {
             Err(PyErr::new::<exc::ValueError, _>(py, e.to_string()))
         })
     }
 
     def removefile(
         &self,
         f: PyObject,
         oldstate: PyObject,
         size: PyObject
     ) -> PyResult<PyObject> {
         self.inner(py).borrow_mut()
             .remove_file(
                 HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
                 oldstate.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
                 size.extract(py)?,
             )
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })?;
         Ok(py.None())
     }
 
     def dropfile(
         &self,
         f: PyObject,
         oldstate: PyObject
     ) -> PyResult<PyBool> {
         self.inner(py).borrow_mut()
             .drop_file(
                 HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
                 oldstate.extract::<PyBytes>(py)?.data(py)[0]
                     .try_into()
                     .map_err(|e: DirstateParseError| {
                         PyErr::new::<exc::ValueError, _>(py, e.to_string())
                     })?,
             )
             .and_then(|b| Ok(b.to_py_object(py)))
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })
     }
 
     def clearambiguoustimes(
         &self,
         files: PyObject,
         now: PyObject
     ) -> PyResult<PyObject> {
         let files: PyResult<Vec<HgPathBuf>> = files
             .iter(py)?
             .map(|filename| {
                 Ok(HgPathBuf::from_bytes(
                     filename?.extract::<PyBytes>(py)?.data(py),
                 ))
             })
             .collect();
         self.inner(py).borrow_mut()
             .clear_ambiguous_times(files?, now.extract(py)?);
         Ok(py.None())
     }
 
     def other_parent_entries(&self) -> PyResult<PyObject> {
         let mut inner_shared = self.inner(py).borrow_mut();
         let (_, other_parent) =
             inner_shared.get_non_normal_other_parent_entries();
 
         let locals = PyDict::new(py);
         locals.set_item(
             py,
             "other_parent",
             other_parent
                 .iter()
-                .map(|v| PyBytes::new(py, v.as_ref()))
+                .map(|v| PyBytes::new(py, v.as_bytes()))
                 .collect::<Vec<PyBytes>>()
                 .to_py_object(py),
         )?;
 
         py.eval("set(other_parent)", None, Some(&locals))
     }
 
     def non_normal_entries(&self) -> PyResult<NonNormalEntries> {
         NonNormalEntries::from_inner(py, self.clone_ref(py))
     }
 
     def non_normal_entries_contains(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self
             .inner(py)
             .borrow_mut()
             .get_non_normal_other_parent_entries().0
             .contains(HgPath::new(key.data(py))))
     }
 
     def non_normal_entries_display(&self) -> PyResult<PyString> {
         Ok(
             PyString::new(
                 py,
                 &format!(
                     "NonNormalEntries: {:?}",
                     self
                         .inner(py)
                         .borrow_mut()
                         .get_non_normal_other_parent_entries().0
                         .iter().map(|o| o))
                 )
             )
     }
 
     def non_normal_entries_remove(&self, key: PyObject) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         self
             .inner(py)
             .borrow_mut()
             .non_normal_entries_remove(HgPath::new(key.data(py)));
         Ok(py.None())
     }
 
     def non_normal_entries_union(&self, other: PyObject) -> PyResult<PyList> {
         let other: PyResult<_> = other.iter(py)?
                     .map(|f| {
                         Ok(HgPathBuf::from_bytes(
                             f?.extract::<PyBytes>(py)?.data(py),
                         ))
                     })
                     .collect();
 
         let res = self
             .inner(py)
             .borrow_mut()
             .non_normal_entries_union(other?);
 
         let ret = PyList::new(py, &[]);
         for filename in res.iter() {
             let as_pystring = PyBytes::new(py, filename.as_bytes());
             ret.append(py, as_pystring.into_object());
         }
         Ok(ret)
     }
 
     def non_normal_entries_iter(&self) -> PyResult<NonNormalEntriesIterator> {
         // Make sure the sets are defined before we no longer have a mutable
         // reference to the dmap.
         self.inner(py)
             .borrow_mut()
             .set_non_normal_other_parent_entries(false);
 
         let leaked_ref = self.inner(py).leak_immutable();
 
         NonNormalEntriesIterator::from_inner(py, unsafe {
             leaked_ref.map(py, |o| {
                 o.get_non_normal_other_parent_entries_panic().0.iter()
             })
         })
     }
 
     def hastrackeddir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_tracked_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def hasdir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def parents(&self, st: PyObject) -> PyResult<PyTuple> {
         self.inner(py).borrow_mut()
             .parents(st.extract::<PyBytes>(py)?.data(py))
             .and_then(|d| {
                 Ok((PyBytes::new(py, &d.p1), PyBytes::new(py, &d.p2))
                     .to_py_object(py))
             })
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })
     }
 
     def setparents(&self, p1: PyObject, p2: PyObject) -> PyResult<PyObject> {
         let p1 = extract_node_id(py, &p1)?;
         let p2 = extract_node_id(py, &p2)?;
 
         self.inner(py).borrow_mut()
             .set_parents(&DirstateParents { p1, p2 });
         Ok(py.None())
     }
 
     def read(&self, st: PyObject) -> PyResult<Option<PyObject>> {
         match self.inner(py).borrow_mut()
             .read(st.extract::<PyBytes>(py)?.data(py))
         {
             Ok(Some(parents)) => Ok(Some(
                 (PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
                     .to_py_object(py)
                     .into_object(),
             )),
             Ok(None) => Ok(Some(py.None())),
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
     def write(
         &self,
         p1: PyObject,
         p2: PyObject,
         now: PyObject
     ) -> PyResult<PyBytes> {
         let now = Duration::new(now.extract(py)?, 0);
         let parents = DirstateParents {
             p1: extract_node_id(py, &p1)?,
             p2: extract_node_id(py, &p2)?,
         };
 
         match self.inner(py).borrow_mut().pack(parents, now) {
             Ok(packed) => Ok(PyBytes::new(py, &packed)),
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
 
     def filefoldmapasdict(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for (key, value) in
             self.inner(py).borrow_mut().build_file_fold_map().iter()
         {
-            dict.set_item(py, key.as_ref().to_vec(), value.as_ref().to_vec())?;
+            dict.set_item(
+                py,
+                key.as_bytes().to_vec(),
+                value.as_bytes().to_vec(),
+            )?;
         }
         Ok(dict)
     }
 
     def __len__(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().len())
     }
 
     def __contains__(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow().contains_key(HgPath::new(key.data(py))))
     }
 
     def __getitem__(&self, key: PyObject) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let key = HgPath::new(key.data(py));
         match self.inner(py).borrow().get(key) {
             Some(entry) => {
                 Ok(make_dirstate_tuple(py, entry)?)
             },
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.as_bytes()),
             )),
         }
     }
 
     def keys(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def items(&self) -> PyResult<DirstateMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def __iter__(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def getdirs(&self) -> PyResult<Dirs> {
         // TODO don't copy, share the reference
         self.inner(py).borrow_mut().set_dirs()
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?;
         Dirs::from_inner(
             py,
             DirsMultiset::from_dirstate(
                 &self.inner(py).borrow(),
                 Some(EntryState::Removed),
             )
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?,
         )
     }
     def getalldirs(&self) -> PyResult<Dirs> {
         // TODO don't copy, share the reference
         self.inner(py).borrow_mut().set_all_dirs()
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?;
         Dirs::from_inner(
             py,
             DirsMultiset::from_dirstate(
                 &self.inner(py).borrow(),
                 None,
             ).map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?,
         )
     }
 
     // TODO all copymap* methods, see docstring above
     def copymapcopy(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for (key, value) in self.inner(py).borrow().copy_map.iter() {
             dict.set_item(
                 py,
-                PyBytes::new(py, key.as_ref()),
-                PyBytes::new(py, value.as_ref()),
+                PyBytes::new(py, key.as_bytes()),
+                PyBytes::new(py, value.as_bytes()),
             )?;
         }
         Ok(dict)
     }
 
     def copymapgetitem(&self, key: PyObject) -> PyResult<PyBytes> {
         let key = key.extract::<PyBytes>(py)?;
         match self.inner(py).borrow().copy_map.get(HgPath::new(key.data(py))) {
-            Some(copy) => Ok(PyBytes::new(py, copy.as_ref())),
+            Some(copy) => Ok(PyBytes::new(py, copy.as_bytes())),
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.data(py)),
             )),
         }
     }
     def copymap(&self) -> PyResult<CopyMap> {
         CopyMap::from_inner(py, self.clone_ref(py))
     }
 
     def copymaplen(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().copy_map.len())
     }
     def copymapcontains(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         Ok(self
             .inner(py)
             .borrow()
             .copy_map
             .contains_key(HgPath::new(key.data(py))))
     }
     def copymapget(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow()
             .copy_map
             .get(HgPath::new(key.data(py)))
         {
             Some(copy) => Ok(Some(
-                PyBytes::new(py, copy.as_ref()).into_object(),
+                PyBytes::new(py, copy.as_bytes()).into_object(),
             )),
             None => Ok(default),
         }
     }
     def copymapsetitem(
         &self,
         key: PyObject,
         value: PyObject
     ) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let value = value.extract::<PyBytes>(py)?;
         self.inner(py).borrow_mut().copy_map.insert(
             HgPathBuf::from_bytes(key.data(py)),
             HgPathBuf::from_bytes(value.data(py)),
         );
         Ok(py.None())
     }
     def copymappop(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow_mut()
             .copy_map
             .remove(HgPath::new(key.data(py)))
         {
             Some(_) => Ok(None),
             None => Ok(default),
         }
     }
 
     def copymapiter(&self) -> PyResult<CopyMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map.iter()) },
         )
     }
 
     def copymapitemsiter(&self) -> PyResult<CopyMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map.iter()) },
         )
     }
 
 });
 
 impl DirstateMap {
     pub fn get_inner<'a>(
         &'a self,
         py: Python<'a>,
     ) -> Ref<'a, RustDirstateMap> {
         self.inner(py).borrow()
     }
     fn translate_key(
         py: Python,
         res: (&HgPathBuf, &DirstateEntry),
     ) -> PyResult<Option<PyBytes>> {
-        Ok(Some(PyBytes::new(py, res.0.as_ref())))
+        Ok(Some(PyBytes::new(py, res.0.as_bytes())))
     }
     fn translate_key_value(
         py: Python,
         res: (&HgPathBuf, &DirstateEntry),
     ) -> PyResult<Option<(PyBytes, PyObject)>> {
         let (f, entry) = res;
         Ok(Some((
-            PyBytes::new(py, f.as_ref()),
+            PyBytes::new(py, f.as_bytes()),
             make_dirstate_tuple(py, entry)?,
         )))
     }
 }
 
 py_shared_iterator!(
     DirstateMapKeysIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key,
     Option<PyBytes>
 );
 
 py_shared_iterator!(
     DirstateMapItemsIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key_value,
     Option<(PyBytes, PyObject)>
 );
 
 fn extract_node_id(py: Python, obj: &PyObject) -> PyResult<[u8; PARENT_SIZE]> {
     let bytes = obj.extract::<PyBytes>(py)?;
     match bytes.data(py).try_into() {
         Ok(s) => Ok(s),
         Err(e) => Err(PyErr::new::<exc::ValueError, _>(py, e.to_string())),
     }
 }

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

@@ -1,76 +1,76
 // non_normal_other_parent_entries.rs
 //
 // Copyright 2020 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 cpython::{
     exc::NotImplementedError, CompareOp, ObjectProtocol, PyBytes, PyClone,
     PyErr, PyList, PyObject, PyResult, PyString, Python, PythonObject,
     ToPyObject, UnsafePyLeaked,
 };
 
 use crate::dirstate::DirstateMap;
 use hg::utils::hg_path::HgPathBuf;
 use std::cell::RefCell;
 use std::collections::hash_set;
 
 py_class!(pub class NonNormalEntries |py| {
     data dmap: DirstateMap;
 
     def __contains__(&self, key: PyObject) -> PyResult<bool> {
         self.dmap(py).non_normal_entries_contains(py, key)
     }
     def remove(&self, key: PyObject) -> PyResult<PyObject> {
         self.dmap(py).non_normal_entries_remove(py, key)
     }
     def union(&self, other: PyObject) -> PyResult<PyList> {
         self.dmap(py).non_normal_entries_union(py, other)
     }
     def __richcmp__(&self, other: PyObject, op: CompareOp) -> PyResult<bool> {
         match op {
             CompareOp::Eq => self.is_equal_to(py, other),
             CompareOp::Ne => Ok(!self.is_equal_to(py, other)?),
             _ => Err(PyErr::new::<NotImplementedError, _>(py, ""))
         }
     }
     def __repr__(&self) -> PyResult<PyString> {
         self.dmap(py).non_normal_entries_display(py)
     }
 
     def __iter__(&self) -> PyResult<NonNormalEntriesIterator> {
         self.dmap(py).non_normal_entries_iter(py)
     }
 });
 
 impl NonNormalEntries {
     pub fn from_inner(py: Python, dm: DirstateMap) -> PyResult<Self> {
         Self::create_instance(py, dm)
     }
 
     fn is_equal_to(&self, py: Python, other: PyObject) -> PyResult<bool> {
         for item in other.iter(py)? {
             if !self.dmap(py).non_normal_entries_contains(py, item?)? {
                 return Ok(false);
             }
         }
         Ok(true)
     }
 
     fn translate_key(
         py: Python,
         key: &HgPathBuf,
     ) -> PyResult<Option<PyBytes>> {
-        Ok(Some(PyBytes::new(py, key.as_ref())))
+        Ok(Some(PyBytes::new(py, key.as_bytes())))
     }
 }
 
 type NonNormalEntriesIter<'a> = hash_set::Iter<'a, HgPathBuf>;
 
 py_shared_iterator!(
     NonNormalEntriesIterator,
     UnsafePyLeaked<NonNormalEntriesIter<'static>>,
     NonNormalEntries::translate_key,
     Option<PyBytes>
 );

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

@@ -1,303 +1,301
 // 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,
     collect_traversed_dirs: 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,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                     collect_traversed_dirs,
                 },
             )
             .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,
                 StatusOptions {
                     check_exec,
                     last_normal_time,
                     list_clean,
                     list_ignored,
                     list_unknown,
                     collect_traversed_dirs,
                 },
             )
             .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,
                     collect_traversed_dirs,
                 },
             )
             .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),
-            ));
-        }
+        e => 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 traversed = collect_pybytes_list(py, status_res.traversed.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(),
             traversed.into_object(),
         ][..],
     ))
 }

rust/hg-cpython/src/parsers.rs

@@ -1,175 +1,175
 // parsers.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::parsers` module provided by the
 //! `hg-core` package.
 //!
 //! From Python, this will be seen as `mercurial.rustext.parsers`
 use cpython::{
     exc, PyBytes, PyDict, PyErr, PyInt, PyModule, PyResult, PyTuple, Python,
     PythonObject, ToPyObject,
 };
 use hg::{
     pack_dirstate, parse_dirstate, utils::hg_path::HgPathBuf,
     DirstatePackError, DirstateParents, DirstateParseError, FastHashMap,
     PARENT_SIZE,
 };
 use std::convert::TryInto;
 
 use crate::dirstate::{extract_dirstate, make_dirstate_tuple};
 use std::time::Duration;
 
 fn parse_dirstate_wrapper(
     py: Python,
     dmap: PyDict,
     copymap: PyDict,
     st: PyBytes,
 ) -> PyResult<PyTuple> {
     let mut dirstate_map = FastHashMap::default();
     let mut copies = FastHashMap::default();
 
     match parse_dirstate(&mut dirstate_map, &mut copies, st.data(py)) {
         Ok(parents) => {
             for (filename, entry) in &dirstate_map {
                 dmap.set_item(
                     py,
-                    PyBytes::new(py, filename.as_ref()),
+                    PyBytes::new(py, filename.as_bytes()),
                     make_dirstate_tuple(py, entry)?,
                 )?;
             }
             for (path, copy_path) in copies {
                 copymap.set_item(
                     py,
-                    PyBytes::new(py, path.as_ref()),
-                    PyBytes::new(py, copy_path.as_ref()),
+                    PyBytes::new(py, path.as_bytes()),
+                    PyBytes::new(py, copy_path.as_bytes()),
                 )?;
             }
             Ok(
                 (PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
                     .to_py_object(py),
             )
         }
         Err(e) => Err(PyErr::new::<exc::ValueError, _>(
             py,
             match e {
                 DirstateParseError::TooLittleData => {
                     "too little data for parents".to_string()
                 }
                 DirstateParseError::Overflow => {
                     "overflow in dirstate".to_string()
                 }
                 DirstateParseError::CorruptedEntry(e) => e,
                 DirstateParseError::Damaged => {
                     "dirstate appears to be damaged".to_string()
                 }
             },
         )),
     }
 }
 
 fn pack_dirstate_wrapper(
     py: Python,
     dmap: PyDict,
     copymap: PyDict,
     pl: PyTuple,
     now: PyInt,
 ) -> PyResult<PyBytes> {
     let p1 = pl.get_item(py, 0).extract::<PyBytes>(py)?;
     let p1: &[u8] = p1.data(py);
     let p2 = pl.get_item(py, 1).extract::<PyBytes>(py)?;
     let p2: &[u8] = p2.data(py);
 
     let mut dirstate_map = extract_dirstate(py, &dmap)?;
 
     let copies: Result<FastHashMap<HgPathBuf, HgPathBuf>, PyErr> = copymap
         .items(py)
         .iter()
         .map(|(key, value)| {
             Ok((
                 HgPathBuf::from_bytes(key.extract::<PyBytes>(py)?.data(py)),
                 HgPathBuf::from_bytes(value.extract::<PyBytes>(py)?.data(py)),
             ))
         })
         .collect();
 
     if p1.len() != PARENT_SIZE || p2.len() != PARENT_SIZE {
         return Err(PyErr::new::<exc::ValueError, _>(
             py,
             "expected a 20-byte hash".to_string(),
         ));
     }
 
     match pack_dirstate(
         &mut dirstate_map,
         &copies?,
         DirstateParents {
             p1: p1.try_into().unwrap(),
             p2: p2.try_into().unwrap(),
         },
         Duration::from_secs(now.as_object().extract::<u64>(py)?),
     ) {
         Ok(packed) => {
             for (filename, entry) in &dirstate_map {
                 dmap.set_item(
                     py,
-                    PyBytes::new(py, filename.as_ref()),
+                    PyBytes::new(py, filename.as_bytes()),
                     make_dirstate_tuple(py, entry)?,
                 )?;
             }
             Ok(PyBytes::new(py, &packed))
         }
         Err(error) => Err(PyErr::new::<exc::ValueError, _>(
             py,
             match error {
                 DirstatePackError::CorruptedParent => {
                     "expected a 20-byte hash".to_string()
                 }
                 DirstatePackError::CorruptedEntry(e) => e,
                 DirstatePackError::BadSize(expected, actual) => {
                     format!("bad dirstate size: {} != {}", actual, expected)
                 }
             },
         )),
     }
 }
 
 /// Create the module, with `__package__` given from parent
 pub fn init_parsers_module(py: Python, package: &str) -> PyResult<PyModule> {
     let dotted_name = &format!("{}.parsers", package);
     let m = PyModule::new(py, dotted_name)?;
 
     m.add(py, "__package__", package)?;
     m.add(py, "__doc__", "Parsers - Rust implementation")?;
 
     m.add(
         py,
         "parse_dirstate",
         py_fn!(
             py,
             parse_dirstate_wrapper(dmap: PyDict, copymap: PyDict, st: PyBytes)
         ),
     )?;
     m.add(
         py,
         "pack_dirstate",
         py_fn!(
             py,
             pack_dirstate_wrapper(
                 dmap: PyDict,
                 copymap: PyDict,
                 pl: PyTuple,
                 now: PyInt
             )
         ),
     )?;
 
     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/utils.rs

@@ -1,47 +1,44
 use cpython::exc::ValueError;
 use cpython::{PyBytes, PyDict, PyErr, PyObject, PyResult, PyTuple, Python};
 use hg::revlog::Node;
 use std::convert::TryFrom;
 
 #[allow(unused)]
 pub fn print_python_trace(py: Python) -> PyResult<PyObject> {
     eprintln!("===============================");
     eprintln!("Printing Python stack from Rust");
     eprintln!("===============================");
     let traceback = py.import("traceback")?;
     let sys = py.import("sys")?;
     let kwargs = PyDict::new(py);
     kwargs.set_item(py, "file", sys.get(py, "stderr")?)?;
     traceback.call(py, "print_stack", PyTuple::new(py, &[]), Some(&kwargs))
 }
 
 // Necessary evil for the time being, could maybe be moved to
 // a TryFrom in Node itself
 const NODE_BYTES_LENGTH: usize = 20;
 type NodeData = [u8; NODE_BYTES_LENGTH];
 
 /// Copy incoming Python bytes given as `PyObject` into `Node`,
 /// doing the necessary checks
 pub fn node_from_py_object<'a>(
     py: Python,
     bytes: &'a PyObject,
 ) -> PyResult<Node> {
     let as_py_bytes: &'a PyBytes = bytes.extract(py)?;
     node_from_py_bytes(py, as_py_bytes)
 }
 
 /// Clone incoming Python bytes given as `PyBytes` as a `Node`,
 /// doing the necessary checks.
-pub fn node_from_py_bytes<'a>(
-    py: Python,
-    bytes: &'a PyBytes,
-) -> PyResult<Node> {
+pub fn node_from_py_bytes(py: Python, bytes: &PyBytes) -> PyResult<Node> {
     <NodeData>::try_from(bytes.data(py))
         .map_err(|_| {
             PyErr::new::<ValueError, _>(
                 py,
                 format!("{}-byte hash required", NODE_BYTES_LENGTH),
             )
         })
-        .map(|n| n.into())
+        .map(Into::into)
 }