rust/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-11-23 21:54:45 +02:00
Code Issues Releases Activity

Refactor and test glob sets.

Browse Source 
This commit goes a long way toward refactoring glob sets so that the
code is easier to maintain going forward. In particular, it makes the
literal optimizations that glob sets used a lot more structured and much
easier to extend. Tests have also been modified to include glob sets.

There's still a bit of polish work left to do before a release.

This also fixes the immediate issue where large gitignore files were
causing ripgrep to slow way down. While we don't technically fix it for
good, we're a lot better about reducing the number of regexes we
compile. In particular, if a gitignore file contains thousands of
patterns that can't be matched more simply using literals, then ripgrep
will slow down again. We could fix this for good by avoiding RegexSet if
the number of regexes grows too large.

Fixes #134.
This commit is contained in:
Andrew Gallant
2016-10-04 20:22:13 -04:00
parent 89811d43d4
commit 175406df01
8 changed files with 1941 additions and 978 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
src/types.rs
View File

@@ -11,7 +11,7 @@ use std::path::Path;
use regex;
use gitignore::{Match, Pattern};
use globset::{self, MatchOptions};
use globset::{self, PatternBuilder, Set, SetBuilder};
const TYPE_EXTENSIONS: &'static [(&'static str, &'static [&'static str])] = &[
("asm", &["*.asm", "*.s", "*.S"]),
@@ -161,8 +161,8 @@ impl FileTypeDef {
#[derive(Clone, Debug)]
pub struct Types {
defs: Vec<FileTypeDef>,
selected: Option<globset::SetYesNo>,
negated: Option<globset::SetYesNo>,
selected: Option<Set>,
negated: Option<Set>,
has_selected: bool,
unmatched_pat: Pattern,
}
@@ -175,8 +175,8 @@ impl Types {
/// If has_selected is true, then at least one file type was selected.
/// Therefore, any non-matches should be ignored.
fn new(
selected: Option<globset::SetYesNo>,
negated: Option<globset::SetYesNo>,
selected: Option<Set>,
negated: Option<Set>,
has_selected: bool,
defs: Vec<FileTypeDef>,
) -> Types {
@@ -265,14 +265,11 @@ impl TypesBuilder {
/// Build the current set of file type definitions *and* selections into
/// a file type matcher.
pub fn build(&self) -> Result<Types, Error> {
let opts = MatchOptions {
require_literal_separator: true, ..MatchOptions::default()
};
let selected_globs =
if self.selected.is_empty() {
None
} else {
let mut bset = globset::SetBuilder::new();
let mut bset = SetBuilder::new();
for name in &self.selected {
let globs = match self.types.get(name) {
Some(globs) => globs,
@@ -282,16 +279,19 @@ impl TypesBuilder {
}
};
for glob in globs {
try!(bset.add_with(glob, &opts));
let pat = try!(
PatternBuilder::new(glob)
.literal_separator(true).build());
bset.add(pat);
}
}
Some(try!(bset.build_yesno()))
Some(try!(bset.build()))
};
let negated_globs =
if self.negated.is_empty() {
None
} else {
let mut bset = globset::SetBuilder::new();
let mut bset = SetBuilder::new();
for name in &self.negated {
let globs = match self.types.get(name) {
Some(globs) => globs,
@@ -301,10 +301,13 @@ impl TypesBuilder {
}
};
for glob in globs {
try!(bset.add_with(glob, &opts));
let pat = try!(
PatternBuilder::new(glob)
.literal_separator(true).build());
bset.add(pat);
}
}
Some(try!(bset.build_yesno()))
Some(try!(bset.build()))
};
Ok(Types::new(
selected_globs,