##// END OF EJS Templates
copies: iterate over children directly (instead of parents)...
copies: iterate over children directly (instead of parents) Before this change we would gather all parent → child edges and iterate on all parent, gathering copy information for children and aggregating them from there. They are not strict requirement for edges to be processed in that specific order. We could also simply iterate over all "children" revision and aggregate data from both parents at the same time. This patch does that. It make various things simpler: * since both parents are processed at the same time, we no longer need to cache data for merge (see next changeset for details), * we no longer need nested loop to process data, * we no longer need to store partial merge data for a rev from distinct loop interaction to another when processing merges, * we no longer need to build a full parent -> children mapping (we only rely on a simpler "parent -> number of children" map (for memory efficiency), * the data access pattern is now simpler (from lower revisions to higher revisions) and entirely predicable. That predictability open the way to prefetching and parallel processing. So that new iterations order requires simpler code and open the way to interesting optimisation. The effect on performance is quite good. In the worse case, we don't see any significant negative impact. And in the best case, the reduction of roundtrip to Python provide us with a significant speed. Some example below: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev # full comparison between the previous changeset and this one Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000048 s, 0.000041 s, -0.000007 s, × 0.8542, 41 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000153 s, 0.000102 s, -0.000051 s, × 0.6667, 17 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004209 s, 0.004254 s, +0.000045 s, × 1.0107, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000203 s, 0.000282 s, +0.000079 s, × 1.3892, 31 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000059 s, 0.000048 s, -0.000011 s, × 0.8136, 48 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000194 s, 0.000211 s, +0.000017 s, × 1.0876, 30 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000380 s, 0.000375 s, -0.000005 s, × 0.9868, 375 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010588 s, 0.010574 s, -0.000014 s, × 0.9987, 1762 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.048961 s, 0.049974 s, +0.001013 s, × 1.0207, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.083612 s, 0.084300 s, +0.000688 s, × 1.0082, 12 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.058579 s, 0.060128 s, +0.001549 s, × 1.0264, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.736783 s, 0.686542 s, -0.050241 s, × 0.9318, 15 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.022050 s, 0.009277 s, -0.012773 s, × 0.4207, 4638 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120800 s, 0.114733 s, -0.006067 s, × 0.9498, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000140 s, 0.000081 s, -0.000059 s, × 0.5786, 40 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000114 s, 0.000107 s, -0.000007 s, × 0.9386, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000224 s, 0.000173 s, -0.000051 s, × 0.7723, 57 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000723 s, 0.000698 s, -0.000025 s, × 0.9654, 77 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009665 s, 0.009248 s, -0.000417 s, × 0.9569, 6 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.014820 s, 0.015446 s, +0.000626 s, × 1.0422, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.076049 s, 0.074373 s, -0.001676 s, × 0.9780, 12 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.683603 s, 0.639870 s, -0.043733 s, × 0.9360, 9 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000161 s, 0.000088 s, -0.000073 s, × 0.5466, 44 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000234 s, 0.000199 s, -0.000035 s, × 0.8504, 24 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000247 s, 0.000171 s, -0.000076 s, × 0.6923, 19 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000630 s, 0.000592 s, -0.000038 s, × 0.9397, 84 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003286 s, 0.003151 s, -0.000135 s, × 0.9589, 1050 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062441 s, 0.061612 s, -0.000829 s, × 0.9867, 10268 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005423 s, 0.005381 s, -0.000042 s, × 0.9923, 3 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005919 s, 0.003742 s, -0.002177 s, × 0.6322, 91 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.062597 s, 0.061983 s, -0.000614 s, × 0.9902, 7 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.043551 s, 0.019861 s, -0.023690 s, × 0.4560, 32 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.192475 s, 0.188101 s, -0.004374 s, × 0.9773, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.955575 s, 1.806696 s, -0.148879 s, × 0.9239, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.886501 s, 2.682987 s, -0.203514 s, × 0.9295, 13 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.001181 s, 0.000852 s, -0.000329 s, × 0.7214, 426 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.001189 s, 0.000859 s, -0.000330 s, × 0.7225, 429 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000563 s, 0.000150 s, -0.000413 s, × 0.2664, 37 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001548 s, 0.001158 s, -0.000390 s, × 0.7481, 579 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027782 s, 0.027240 s, -0.000542 s, × 0.9805, 27240 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062781 s, 0.062824 s, +0.000043 s, × 1.0007, 10470 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005778 s, 0.005463 s, -0.000315 s, × 0.9455, 3 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.006192 s, 0.004238 s, -0.001954 s, × 0.6844, 103 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065391 s, 0.064113 s, -0.001278 s, × 0.9805, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.317216 s, 0.294063 s, -0.023153 s, × 0.9270, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.303119 s, 0.281493 s, -0.021626 s, × 0.9287, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.045739 s, 0.020390 s, -0.025349 s, × 0.4458, 33 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.098021 s, 3.023879 s, -0.074142 s, × 0.9761, 31 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.771480 s, 0.735549 s, -0.035931 s, × 0.9534, 14 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.813422 s, 18.568900 s, -0.244522 s, × 0.9870, 51 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.684923 s, 18.356645 s, -0.328278 s, × 0.9824, 50 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.296305 s, 18.250393 s, -0.045912 s, × 0.9975, 50 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 3.061887 s, 2.792459 s, -0.269428 s, × 0.9120, 14 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s, +3.827623 s, × 1.0369, 470 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 64.262957 s, 63.961040 s, -0.301917 s, × 0.9953, 167 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9422

File last commit:

r45500:26114bd6 default
r46764:294d5aca default
Show More
filepatterns.rs
670 lines | 20.3 KiB | application/rls-services+xml | RustLexer
// filepatterns.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.
//! 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, ..
} = &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_else(|| source_root.deref());
let path = source_root.join(get_path_from_bytes(pattern));
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()),
);
}
}