##// END OF EJS Templates
copies: use the rust code for `combine_changeset_copies`...
copies: use the rust code for `combine_changeset_copies` Changeset centric copy tracing now use the rust code. The rust code focussed on simplicity and will be optimised later. So the performance is not great yet. Now that all the pieces are in place we can start working on performance in the coming changesets. Below is a table that summarize how slower we got: Repo Cases Source-Rev Dest-Rev Py-time Rust-time Difference Factor ------------------------------------------------------------------------------------------------------------------------------------ mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000049 s, 0.000046 s, -0.000003 s, × 0.9388 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.000112 s, 0.000173 s, +0.000061 s, × 1.5446 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.004216 s, 0.006303 s, +0.002087 s, × 1.4950 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.000204 s, 0.000229 s, +0.000025 s, × 1.1225 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.000058 s, 0.000056 s, -0.000002 s, × 0.9655 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.000112 s, 0.000143 s, +0.000031 s, × 1.2768 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.000339 s, 0.001166 s, +0.000827 s, × 3.4395 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.010214 s, 0.022931 s, +0.012717 s, × 2.2451 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 0.047497 s, 0.852446 s, +0.804949 s, × 17.9474 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 0.075297 s, 2.221824 s, +2.146527 s, × 29.5075 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 0.057322 s, 1.194162 s, +1.136840 s, × 20.8325 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 0.796264 s, 62.468362 s, +61.672098 s, × 78.4518 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 0.020491 s, 0.022116 s, +0.001625 s, × 1.0793 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 0.121612 s, 2.972788 s, +2.851176 s, × 24.4449 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.000143 s, 0.000180 s, +0.000037 s, × 1.2587 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.000112 s, 0.000123 s, +0.000011 s, × 1.0982 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.000232 s, 0.000315 s, +0.000083 s, × 1.3578 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.000721 s, 0.001297 s, +0.000576 s, × 1.7989 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.010115 s, 0.024884 s, +0.014769 s, × 2.4601 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.015461 s, 0.032653 s, +0.017192 s, × 2.1120 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.060756 s, 4.230118 s, +4.169362 s, × 69.6247 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 0.605842 s, killed mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.000164 s, 0.000197 s, +0.000033 s, × 1.2012 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.000331 s, 0.000622 s, +0.000291 s, × 1.8792 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.000249 s, 0.000296 s, +0.000047 s, × 1.1888 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.000711 s, 0.001626 s, +0.000915 s, × 2.2869 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.003438 s, 0.006218 s, +0.002780 s, × 1.8086 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.069869 s, 0.132760 s, +0.062891 s, × 1.9001 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.005701 s, 0.029001 s, +0.023300 s, × 5.0870 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.005757 s, 0.005886 s, +0.000129 s, × 1.0224 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 0.061826 s, 3.619850 s, +3.558024 s, × 58.5490 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.043354 s, 0.058678 s, +0.015324 s, × 1.3535 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 0.198979 s, 11.926587 s, +11.727608 s, × 59.9389 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 2.067096 s, killed mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 3.102616 s, killed mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.001212 s, 0.001204 s, -0.000008 s, × 0.9934 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.001237 s, 0.001217 s, -0.000020 s, × 0.9838 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.000557 s, 0.000605 s, +0.000048 s, × 1.0862 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.001532 s, 0.001876 s, +0.000344 s, × 1.2245 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 0.035166 s, 0.078190 s, +0.043024 s, × 2.2235 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.070336 s, 0.135428 s, +0.065092 s, × 1.9254 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.006080 s, 0.029123 s, +0.023043 s, × 4.7900 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.006099 s, 0.006141 s, +0.000042 s, × 1.0069 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 0.064317 s, 4.857827 s, +4.793510 s, × 75.5294 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.303263 s, 10.674920 s, +10.371657 s, × 35.2002 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.292804 s, 9.789462 s, +9.496658 s, × 33.4335 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 0.107594 s, 1.087890 s, +0.980296 s, × 10.1111 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.045202 s, 0.060556 s, +0.015354 s, × 1.3397 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 1.926277 s, killed mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 0.794492 s, killed mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 84.521497 s, killed mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 0.965937 s, 19.647038 s, +18.681101 s, × 20.3399 mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 83.367146 s, killed mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 84.260895 s, killed mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 3.274537 s, killed mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 42.235843 s, killed mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 49.872829 s, killed Differential Revision: https://phab.mercurial-scm.org/D9299

File last commit:

r46182:75f78588 default
r46576:a66568f2 default
Show More
matchers.rs
923 lines | 29.1 KiB | application/rls-services+xml | RustLexer
// matchers.rs
//
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
//
// 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: &HgPath) -> bool;
/// Returns whether `filename` is matched by this matcher
fn matches(&self, filename: &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: &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$")), true);
/// ```
#[derive(Debug)]
pub struct AlwaysMatcher;
impl Matcher for AlwaysMatcher {
fn file_set(&self) -> Option<&HashSet<&HgPath>> {
None
}
fn exact_match(&self, _filename: &HgPath) -> bool {
false
}
fn matches(&self, _filename: &HgPath) -> bool {
true
}
fn visit_children_set(&self, _directory: &HgPath) -> VisitChildrenSet {
VisitChildrenSet::Recursive
}
fn matches_everything(&self) -> bool {
true
}
fn is_exact(&self) -> bool {
false
}
}
/// Matches the input files exactly. They are interpreted as paths, not
/// patterns.
///
///```
/// use hg::{ matchers::{Matcher, FileMatcher}, utils::hg_path::{HgPath, HgPathBuf} };
///
/// let files = [HgPathBuf::from_bytes(b"a.txt"), HgPathBuf::from_bytes(br"re:.*\.c$")];
/// 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 [HgPathBuf]) -> Result<Self, DirstateMapError> {
Ok(Self {
files: HashSet::from_iter(files.iter().map(AsRef::as_ref)),
dirs: DirsMultiset::from_manifest(files)?,
})
}
fn inner_matches(&self, filename: &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: &HgPath) -> bool {
self.inner_matches(filename)
}
fn matches(&self, filename: &HgPath) -> bool {
self.inner_matches(filename)
}
fn visit_children_set(&self, directory: &HgPath) -> VisitChildrenSet {
if self.files.is_empty() || !self.dirs.contains(&directory) {
return VisitChildrenSet::Empty;
}
let dirs_as_set = self.dirs.iter().map(Deref::deref).collect();
let mut candidates: HashSet<&HgPath> =
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: &HgPath) -> bool {
false
}
fn matches(&self, filename: &HgPath) -> bool {
(self.match_fn)(filename.as_ref())
}
fn visit_children_set(&self, directory: &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(ToOwned::to_owned),
);
parents.extend(
DirsMultiset::from_manifest(&roots)
.map_err(|e| match e {
DirstateMapError::InvalidPath(e) => e,
_ => unreachable!(),
})?
.iter()
.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[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![HgPathBuf::from_bytes(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![
HgPathBuf::from_bytes(b"rootfile.txt"),
HgPathBuf::from_bytes(b"a/file1.txt"),
HgPathBuf::from_bytes(b"a/b/file2.txt"),
// No file in a/b/c
HgPathBuf::from_bytes(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
);
}
}