twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-08-06 23:22:02 -07:00
Code Issues Packages Projects Releases Wiki 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

33
crates/regex/src/strip.rs
View File

@@ -42,17 +42,11 @@ fn strip_from_match_ascii(expr: Hir, byte: u8) -> Result<Hir, Error> {
Ok(match expr.into_kind() {
HirKind::Empty => Hir::empty(),
HirKind::Literal(hir::Literal::Unicode(c)) => {
if c == chr {
HirKind::Literal(hir::Literal(lit)) => {
if lit.iter().find(|&&b| b == byte).is_some() {
return invalid();
}
Hir::literal(hir::Literal::Unicode(c))
}
HirKind::Literal(hir::Literal::Byte(b)) => {
if b as char == chr {
return invalid();
}
Hir::literal(hir::Literal::Byte(b))
Hir::literal(lit)
}
HirKind::Class(hir::Class::Unicode(mut cls)) => {
let remove = hir::ClassUnicode::new(Some(
@@ -74,15 +68,14 @@ fn strip_from_match_ascii(expr: Hir, byte: u8) -> Result<Hir, Error> {
}
Hir::class(hir::Class::Bytes(cls))
}
HirKind::Anchor(x) => Hir::anchor(x),
HirKind::WordBoundary(x) => Hir::word_boundary(x),
HirKind::Look(x) => Hir::look(x),
HirKind::Repetition(mut x) => {
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
x.sub = Box::new(strip_from_match_ascii(*x.sub, byte)?);
Hir::repetition(x)
}
HirKind::Group(mut x) => {
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
Hir::group(x)
HirKind::Capture(mut x) => {
x.sub = Box::new(strip_from_match_ascii(*x.sub, byte)?);
Hir::capture(x)
}
HirKind::Concat(xs) => {
let xs = xs
@@ -131,11 +124,11 @@ mod tests {
#[test]
fn various() {
assert_eq!(roundtrip(r"[a\n]", b'\n'), "[a]");
assert_eq!(roundtrip(r"[a\n]", b'a'), "[\n]");
assert_eq!(roundtrip_crlf(r"[a\n]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r\n]"), "[a]");
assert_eq!(roundtrip(r"[a\n]", b'\n'), "a");
assert_eq!(roundtrip(r"[a\n]", b'a'), "\n");
assert_eq!(roundtrip_crlf(r"[a\n]"), "a");
assert_eq!(roundtrip_crlf(r"[a\r]"), "a");
assert_eq!(roundtrip_crlf(r"[a\r\n]"), "a");
assert_eq!(roundtrip(r"(?-u)\s", b'a'), r"(?-u:[\x09-\x0D\x20])");
assert_eq!(roundtrip(r"(?-u)\s", b'\n'), r"(?-u:[\x09\x0B-\x0D\x20])");