From 805fa32d184f9b163e7355dd335abc96440f0d2b Mon Sep 17 00:00:00 2001 From: Andrew Gallant Date: Mon, 27 Nov 2023 21:07:23 -0500 Subject: searcher: work around NUL line terminator bug As the FIXME comment says, ripgrep is not yet using the new line terminator option in regex-automata exposed for exactly this purpose. Because of that, line anchors like `(?m:^)` and `(?m:$)` will only match `\n` as a line terminator. This means that when --null-data is used in combination with --line-regexp, the anchors inserted by --line-regexp will not match correctly. This is only a big deal in the "fast" path, which requires the regex engine to deal with line terminators itself correctly. The slow path strips line terminators regardless of what they are, and so the line anchors can match (begin/end of haystack). Fixes #2658 --- tests/regression.rs | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tests') diff --git a/tests/regression.rs b/tests/regression.rs index 54490b98..dc463aa3 100644 --- a/tests/regression.rs +++ b/tests/regression.rs @@ -1210,3 +1210,10 @@ rgtest!(r2574, |dir: Dir, mut cmd: TestCommand| { .stdout(); eqnice!("some.domain.com\nsome.domain.com\n", got); }); + +// See: https://github.com/BurntSushi/ripgrep/issues/2658 +rgtest!(r2658_null_data_line_regexp, |dir: Dir, mut cmd: TestCommand| { + dir.create("haystack", "foo\0bar\0quux\0"); + let got = cmd.args(&["--null-data", "--line-regexp", r"bar"]).stdout(); + eqnice!("haystack:bar\0", got); +}); -- cgit v1.2.3