rust-matchers: add `Matcher` trait and implement `AlwaysMatcher`

In our quest of a faster Mercurial, we have arrived at the point where we need
to implement the matchers in Rust.
This RFC mainly for the `Matcher` trait to see if the changes proposed feel
fine to people with more experience on the matter. While the `AlwaysMatcher`
implementation is here as a trivial example, it should be the first step
towards matchers use in Rust as it is currently the only supported one.

Notable changes:
    - `exact` is renamed to `exact_match`
    - enums for `visit*` methods with `Recursive` instead of `'all'`, etc.
    - a new `roots`, separate from `file_set`
    - no `bad`, `explicitdir` or `traversedir` functions as they can be passed
      to the high functions instead of the matchers

Thanks to Martin for suggesting the last two (most important) changes and for
reaching out to help a few weeks ago.

Differential Revision: https://phab.mercurial-scm.org/D7178

rust/hg-core/src/matchers.rs

@@ -0,0 +1,105 b''
+// matchers.rs
+//
+// Copyright 2019 Raphaël Gomès <[e-mail]>
+//
+// This software may be used and distributed according to the terms of the
+// GNU General Public License version 2 or any later version.
+
+//! Structs and types for matching files and directories.
+
+use crate::utils::hg_path::{HgPath, HgPathBuf};
+use std::collections::HashSet;
+
+pub enum VisitChildrenSet {
+    /// Don't visit anything
+    Empty,
+    /// Only visit this directory
+    This,
+    /// Visit this directory and these subdirectories
+    /// TODO Should we implement a `NonEmptyHashSet`?
+    Set(HashSet<HgPathBuf>),
+    /// Visit this directory and all subdirectories
+    Recursive,
+}
+
+pub trait Matcher {
+    /// Explicitly listed files
+    fn file_set(&self) -> HashSet<&HgPath>;
+    /// Returns whether `filename` is in `file_set`
+    fn exact_match(&self, _filename: impl AsRef<HgPath>) -> bool {
+        false
+    }
+    /// Returns whether `filename` is matched by this matcher
+    fn matches(&self, _filename: impl AsRef<HgPath>) -> bool {
+        false
+    }
+    /// 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).
+    ///
+    /// ```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 {
+        VisitChildrenSet::This
+    }
+    /// Matcher will match everything and `files_set()` will be empty:
+    /// optimization might be possible.
+    fn matches_everything(&self) -> bool {
+        false
+    }
+    /// Matcher will match exactly the files in `files_set()`: optimization
+    /// might be possible.
+    fn is_exact(&self) -> bool {
+        false
+    }
+}
+
+/// Matches everything.
+#[derive(Debug)]
+pub struct AlwaysMatcher;
+
+impl Matcher for AlwaysMatcher {
+    fn file_set(&self) -> HashSet<&HgPath> {
+        HashSet::new()
+    }
+
+    fn visit_children_set(
+        &self,
+        _directory: impl AsRef<HgPath>,
+    ) -> VisitChildrenSet {
+        VisitChildrenSet::Recursive
+    }
+}

rust/hg-core/src/lib.rs

@@ -1,151 +1,152 b''
 // 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.
 mod ancestors;
 pub mod dagops;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 mod dirstate;
 pub mod discovery;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     dirstate_map::DirstateMap,
     parsers::{pack_dirstate, parse_dirstate, PARENT_SIZE},
     status::status,
     CopyMap, CopyMapIter, DirstateEntry, DirstateParents, EntryState,
     StateMap, StateMapIter,
 };
 mod filepatterns;
+pub mod matchers;
 pub mod utils;
 
 use crate::utils::hg_path::HgPathBuf;
 pub use filepatterns::{
     build_single_regex, read_pattern_file, PatternSyntax, PatternTuple,
 };
 
 /// 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 that 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`
 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>;
 }
 
 pub type LineNumber = usize;
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
     WorkingDirectoryUnsupported,
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum DirstateParseError {
     TooLittleData,
     Overflow,
     CorruptedEntry(String),
     Damaged,
 }
 
 impl From<std::io::Error> for DirstateParseError {
     fn from(e: std::io::Error) -> Self {
         DirstateParseError::CorruptedEntry(e.to_string())
     }
 }
 
 impl ToString for DirstateParseError {
     fn to_string(&self) -> String {
         use crate::DirstateParseError::*;
         match self {
             TooLittleData => "Too little data for dirstate.".to_string(),
             Overflow => "Overflow in dirstate.".to_string(),
             CorruptedEntry(e) => format!("Corrupted entry: {:?}.", e),
             Damaged => "Dirstate appears to be damaged.".to_string(),
         }
     }
 }
 
 #[derive(Debug, PartialEq)]
 pub enum DirstatePackError {
     CorruptedEntry(String),
     CorruptedParent,
     BadSize(usize, usize),
 }
 
 impl From<std::io::Error> for DirstatePackError {
     fn from(e: std::io::Error) -> Self {
         DirstatePackError::CorruptedEntry(e.to_string())
     }
 }
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
 }
 
 pub enum DirstateError {
     Parse(DirstateParseError),
     Pack(DirstatePackError),
     Map(DirstateMapError),
     IO(std::io::Error),
 }
 
 impl From<DirstateParseError> for DirstateError {
     fn from(e: DirstateParseError) -> Self {
         DirstateError::Parse(e)
     }
 }
 
 impl From<DirstatePackError> for DirstateError {
     fn from(e: DirstatePackError) -> Self {
         DirstateError::Pack(e)
     }
 }
 
 #[derive(Debug)]
 pub enum PatternError {
     UnsupportedSyntax(String),
 }
 
 #[derive(Debug)]
 pub enum PatternFileError {
     IO(std::io::Error),
     Pattern(PatternError, LineNumber),
 }
 
 impl From<std::io::Error> for PatternFileError {
     fn from(e: std::io::Error) -> Self {
         PatternFileError::IO(e)
     }
 }
 
 impl From<DirstateMapError> for DirstateError {
     fn from(e: DirstateMapError) -> Self {
         DirstateError::Map(e)
     }
 }
 
 impl From<std::io::Error> for DirstateError {
     fn from(e: std::io::Error) -> Self {
         DirstateError::IO(e)
     }
 }