From 3a0d9340810a8808d963135a884f50d08442ac67 Mon Sep 17 00:00:00 2001 From: nsfisis Date: Thu, 25 Jun 2026 16:27:53 +0900 Subject: test: port 59 autoload/vcs/installer/util/command tests; fix output capture Port autoload_generator (24), bitbucket (14), suggested_packages (11), git_driver (6), archive_manager (3), and a bump command test. Fix the ApplicationTester output-capture root cause (php://memory streams must be readable regardless of fopen mode). Implement posix_getuid/geteuid, the PCRE 'A' anchored modifier, php_strip_whitespace, stream_get_wrappers, is_callable scalars; fix preg_quote angle-bracket escaping and class-map parser regexes. Co-Authored-By: Claude Opus 4.8 (1M context) --- .../src/class_map_generator.rs | 9 ++++++++- .../shirabe-class-map-generator/src/php_file_cleaner.rs | 12 +++++++++++- .../shirabe-class-map-generator/src/php_file_parser.rs | 17 +++++++++++++---- 3 files changed, 32 insertions(+), 6 deletions(-) (limited to 'crates/shirabe-class-map-generator') diff --git a/crates/shirabe-class-map-generator/src/class_map_generator.rs b/crates/shirabe-class-map-generator/src/class_map_generator.rs index 5359f12..f591811 100644 --- a/crates/shirabe-class-map-generator/src/class_map_generator.rs +++ b/crates/shirabe-class-map-generator/src/class_map_generator.rs @@ -181,7 +181,14 @@ impl ClassMapGenerator { file_path = format!("{}/{}", cwd, file_path); file_path = Self::normalize_path(&file_path); } else { - file_path = Preg::replace(r"{(?])` anchored (`A`): it consumes the single char + // before the keyword (`.`), requires a word boundary there (`\b`) and forbids + // that char being `$`, `:` or `>`. The `regex` crate has no look-behind, so the + // consumed char plus both guards collapse into one negated class + // `[^a-zA-Z0-9_$:>]` (the `\w` set reproducing `\b`, plus the three operators). + // The possessive quantifiers (`++`, `*+`) are performance-only and become plain + // `+`/`*`. The leftmost-match semantics of `captures_at(.., offset)` stand in for + // the dropped `A` (anchored) modifier, since the keyword is known to sit exactly + // one char past the search offset. pattern: format!( - "{{.\\b(?]){}\\s++[a-zA-Z_\\x7f-\\xff:][a-zA-Z0-9_\\x7f-\\xff:\\-]*+}}Ais", + "{{[^a-zA-Z0-9_$:>]{}\\s+[a-zA-Z_\\x7f-\\xff:][a-zA-Z0-9_\\x7f-\\xff:\\-]*}}is", r#type ), }, diff --git a/crates/shirabe-class-map-generator/src/php_file_parser.rs b/crates/shirabe-class-map-generator/src/php_file_parser.rs index ae98a5c..7d7c722 100644 --- a/crates/shirabe-class-map-generator/src/php_file_parser.rs +++ b/crates/shirabe-class-map-generator/src/php_file_parser.rs @@ -77,12 +77,21 @@ impl PhpFileParser { let contents = p.clean(); drop(p); + // Regex pattern compatibility: + // PHP uses `\b(?])` to require the keyword to start at a word boundary and + // not be preceded by `\`, `$`, `:` or `>` (so `MyClass::class`, `$class`, `\class`, + // `Foo->class` are skipped). The `regex` crate has no look-behind, so `\b` + the negative + // look-behind are fused into a single consuming class `(?:^|[^...])` that excludes both the + // identifier characters (reproducing `\b`) and the four operator characters. The consumed + // separator lands in match group 0 only; the named groups are unaffected. The PCRE + // possessive quantifiers (`++`, `*+`) are performance-only and become plain `+`/`*`. let pattern2 = format!( - r"(?ix) + r"{{ (?: - \b(?])(?Pclass|interface|trait{et}) \s++ (?P[a-zA-Z_\x7f-\xff:][a-zA-Z0-9_\x7f-\xff:\-]*+) - | \b(?])(?Pnamespace) (?P\s++[a-zA-Z_\x7f-\xff][a-zA-Z0-9_\x7f-\xff]*+(?:\s*+\\\\\s*+[a-zA-Z_\x7f-\xff][a-zA-Z0-9_\x7f-\xff]*+)*+)? \s*+ [\{{;] - )", + (?:^|[^\\$:>a-zA-Z0-9_\x7f-\xff])(?Pclass|interface|trait{et}) \s+ (?P[a-zA-Z_\x7f-\xff:][a-zA-Z0-9_\x7f-\xff:\-]*) + | (?:^|[^\\$:>a-zA-Z0-9_\x7f-\xff])(?Pnamespace) (?P\s+[a-zA-Z_\x7f-\xff][a-zA-Z0-9_\x7f-\xff]*(?:\s*\\\s*[a-zA-Z_\x7f-\xff][a-zA-Z0-9_\x7f-\xff]*)*)? \s* [\{{;] + ) + }}ix", et = extra_types ); let mut matches: IndexMap<_, _> = IndexMap::new(); -- cgit v1.3.1