From 0caac63bacefb9a1f62848636d47fca07f592bba Mon Sep 17 00:00:00 2001 From: nsfisis Date: Tue, 18 Aug 2026 01:57:02 +0900 Subject: refactor(preg): split PregMatches reads into get() and name() PregMatches keyed both forms of a capture group through CaptureKey, so every read built one: a usize wrapped in an enum, or worse, a String allocated to name a group that regex::Captures can look up from a &str. It now mirrors regex::Captures instead -- get() takes the group number, name() the group name -- and the enum drops out of the type entirely. That is 285 call sites across 59 files, and the named ones carry most of the win: `matches.get(&CaptureKey::ByName("host".to_string()))` reads as `matches.name("host")`. ProcessExecutor loses a `user_key` binding that existed only to build the key once. CaptureKey stays as the key type of PregMatchesAll and PregMatchesAllWithOffsets, where numbered and named entries share one IndexMap and a key type is the point. Five files still name it. Also retargets the two preg_match_all comments that described the occurrence count through `matches[&CaptureKey::ByIndex(0)].len()`, an Index impl these types no longer carry. Co-Authored-By: Claude Opus 5 (1M context) --- crates/shirabe/src/util/url.rs | 40 +++++++++++++++++----------------------- 1 file changed, 17 insertions(+), 23 deletions(-) (limited to 'crates/shirabe/src/util/url.rs') diff --git a/crates/shirabe/src/util/url.rs b/crates/shirabe/src/util/url.rs index 8b751b2a..eb533a06 100644 --- a/crates/shirabe/src/util/url.rs +++ b/crates/shirabe/src/util/url.rs @@ -2,7 +2,7 @@ use crate::config::Config; use crate::util::GitHub; -use shirabe_pcre::{CaptureKey, Preg}; +use shirabe_pcre::Preg; use shirabe_php_shim::{PhpMixed, in_array_strict, parse_url, php_regex}; pub struct Url; @@ -22,9 +22,9 @@ impl Url { ) { url = format!( "https://api.github.com/repos/{}/{}/{}ball/{}", - m.get(&CaptureKey::ByIndex(1)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(2)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(3)).unwrap_or_default(), + m.get(1).unwrap_or_default(), + m.get(2).unwrap_or_default(), + m.get(3).unwrap_or_default(), r#ref ); } else if let Some(m) = Preg::match3( @@ -35,9 +35,9 @@ impl Url { ) { url = format!( "https://api.github.com/repos/{}/{}/{}ball/{}", - m.get(&CaptureKey::ByIndex(1)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(2)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(3)).unwrap_or_default(), + m.get(1).unwrap_or_default(), + m.get(2).unwrap_or_default(), + m.get(3).unwrap_or_default(), r#ref ); } else if let Some(m) = Preg::match3( @@ -48,9 +48,9 @@ impl Url { ) { url = format!( "https://api.github.com/repos/{}/{}/{}ball/{}", - m.get(&CaptureKey::ByIndex(1)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(2)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(3)).unwrap_or_default(), + m.get(1).unwrap_or_default(), + m.get(2).unwrap_or_default(), + m.get(3).unwrap_or_default(), r#ref ); } @@ -63,10 +63,10 @@ impl Url { ) { url = format!( "https://bitbucket.org/{}/{}/get/{}.{}", - m.get(&CaptureKey::ByIndex(1)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(2)).unwrap_or_default(), + m.get(1).unwrap_or_default(), + m.get(2).unwrap_or_default(), r#ref, - m.get(&CaptureKey::ByIndex(4)).unwrap_or_default() + m.get(4).unwrap_or_default() ); } } else if host == "gitlab.com" || host == "www.gitlab.com" { @@ -78,8 +78,8 @@ impl Url { ) { url = format!( "https://gitlab.com/api/v4/projects/{}/repository/archive.{}?sha={}", - m.get(&CaptureKey::ByIndex(1)).unwrap_or_default(), - m.get(&CaptureKey::ByIndex(2)).unwrap_or_default(), + m.get(1).unwrap_or_default(), + m.get(2).unwrap_or_default(), r#ref ); } @@ -163,14 +163,8 @@ impl Url { Preg::replace_callback( php_regex!(r"{^(?P[a-z0-9]+://)?(?P[^:/\s@]+):(?P[^@\s/]+)@}i"), |m| { - let user = m - .get(&CaptureKey::ByName("user".to_string())) - .unwrap_or_default() - .to_string(); - let prefix = m - .get(&CaptureKey::ByName("prefix".to_string())) - .unwrap_or_default() - .to_string(); + let user = m.name("user").unwrap_or_default().to_string(); + let prefix = m.name("prefix").unwrap_or_default().to_string(); // if the username looks like a long (12char+) hex string, or a modern github token (e.g. ghp_xxx, github_pat_xxx) we obfuscate that if Preg::is_match(GitHub::GITHUB_TOKEN_REGEX, &user) { format!("{}***:***@", prefix) -- cgit v1.3.1-4-g156e