rust/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-07-06 06:27:36 +02:00
Code Issues Releases Activity

deps: initial migration steps to regex 1.9

Browse Source 
This leaves the grep-regex crate in tatters. Pretty much the entire
thing needs to be re-worked. The upshot is that it should result in some
big simplifications. I hope.

The idea here is to drop down and actually use regex-automata 0.3
instead of the regex crate itself.
This commit is contained in:
Andrew Gallant
2023-06-11 21:25:23 -04:00
parent a7f1276021
commit 1035f6b1ff
15 changed files with 606 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
crates/regex/src/config.rs
View File

@ -71,7 +71,7 @@ impl Config {
let ast = self.ast(pattern)?;
let analysis = self.analysis(&ast)?;
let expr = hir::translate::TranslatorBuilder::new()
.allow_invalid_utf8(true)
.utf8(false)
.case_insensitive(self.is_case_insensitive(&analysis))
.multi_line(self.multi_line)
.dot_matches_new_line(self.dot_matches_new_line)
@ -172,7 +172,12 @@ impl ConfiguredHIR {
/// CRLF hack is enabled and the regex is line anchored at the end. In
/// this case, matches that end with a `\r` have the `\r` stripped.
pub fn needs_crlf_stripped(&self) -> bool {
self.config.crlf && self.expr.is_line_anchored_end()
self.config.crlf
&& self
.expr
.properties()
.look_set_suffix_any()
.contains(hir::Look::EndLF)
}
/// Returns the line terminator configured on this expression.
@ -202,7 +207,7 @@ impl ConfiguredHIR {
/// Returns true if and only if the underlying HIR has any text anchors.
fn is_any_anchored(&self) -> bool {
self.expr.is_any_anchored_start() || self.expr.is_any_anchored_end()
self.expr.properties().look_set().contains_anchor_haystack()
}
/// Builds a regular expression from this HIR expression.
@ -301,7 +306,7 @@ impl ConfiguredHIR {
let expr = ::regex_syntax::ParserBuilder::new()
.nest_limit(self.config.nest_limit)
.octal(self.config.octal)
.allow_invalid_utf8(true)
.utf8(false)
.multi_line(self.config.multi_line)
.dot_matches_new_line(self.config.dot_matches_new_line)
.unicode(self.config.unicode)