rust/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2024-12-12 19:18:24 +02:00
Code Issues Releases Activity

Don't union inner literals of repetitions.

Browse Source 
If we do, this results in extracting `foofoofoo` from `(\wfoo){3}`,
which is wrong. This does prevent us from extracting `foofoofoo` from
`foo{3}`, which is unfortunate, but we miss plenty of other stuff too.
Literal extracting needs a good rethink (all the way down into the regex
engine).

Fixes #93
This commit is contained in:
Andrew Gallant 2016-09-25 20:10:28 -04:00
parent a13ac3e3d4
commit 6a8051b258
2 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
grep/src/literals.rs
View File

@ -8,7 +8,6 @@ Note that this implementation is incredibly suspicious. We need something more
principled.
*/
use std::cmp;
use std::iter;
use regex::bytes::Regex;
use syntax::{
@ -181,8 +180,6 @@ fn repeat_range_literals<F: FnMut(&Expr, &mut Literals)>(
lits: &mut Literals,
mut f: F,
) {
use syntax::Expr::*;
if min == 0 {
// This is a bit conservative. If `max` is set, then we could
// treat this as a finite set of alternations. For now, we
@ -190,8 +187,12 @@ fn repeat_range_literals<F: FnMut(&Expr, &mut Literals)>(
lits.cut();
} else {
let n = cmp::min(lits.limit_size(), min as usize);
let es = iter::repeat(e.clone()).take(n).collect();
f(&Concat(es), lits);
// We only extract literals from a single repetition, even though
// we could do more. e.g., `a{3}` will have `a` extracted instead of
// `aaa`. The reason is that inner literal extraction can't be unioned
// across repetitions. e.g., extracting `foofoofoo` from `(\w+foo){3}`
// is wrong.
f(e, lits);
if n < min as usize {
lits.cut();
}

9
tests/tests.rs
View File

@ -703,6 +703,15 @@ clean!(regression_90, "test", ".", |wd: WorkDir, mut cmd: Command| {
assert_eq!(lines, ".foo:test\n");
});
// See: https://github.com/BurntSushi/ripgrep/issues/93
clean!(regression_93, r"(\d{1,3}\.){3}\d{1,3}", ".",
|wd: WorkDir, mut cmd: Command| {
wd.create("foo", "192.168.1.1");
let lines: String = wd.stdout(&mut cmd);
assert_eq!(lines, "foo:192.168.1.1\n");
});
// See: https://github.com/BurntSushi/ripgrep/issues/20
sherlock!(feature_20, "Sherlock", ".", |wd: WorkDir, mut cmd: Command| {
cmd.arg("--no-filename");