diff options
| author | Mauri de Souza Meneguzzo <mauri870@gmail.com> | 2023-07-29 20:26:00 +0000 |
|---|---|---|
| committer | Gopher Robot <gobot@golang.org> | 2023-07-31 19:52:57 +0000 |
| commit | ee61186b3301bb1c8610c0925fffd89e061909bb (patch) | |
| tree | 81eb81f16c4f7b9a3e25c1eba3db67e965e555ce /src/regexp/syntax/parse.go | |
| parent | 977e23a70766f8d0801e43bbfb68136bf54a84b7 (diff) | |
| download | go-ee61186b3301bb1c8610c0925fffd89e061909bb.tar.xz | |
regexp/syntax: accept (?<name>...) syntax as valid capture
Currently the only named capture supported by regexp is (?P<name>a).
The syntax (?<name>a) is also widely used and there is currently an effort from
the Rust regex and RE2 teams to also accept this syntax.
Fixes #58458
Change-Id: If22d44d3a5c4e8133ec68238ab130c151ca7c5c5
GitHub-Last-Rev: 31b50e6ab40cfb0f36df6f570525657d4680017f
GitHub-Pull-Request: golang/go#61624
Reviewed-on: https://go-review.googlesource.com/c/go/+/513838
Auto-Submit: Ian Lance Taylor <iant@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Ian Lance Taylor <iant@google.com>
Reviewed-by: Ian Lance Taylor <iant@google.com>
Diffstat (limited to 'src/regexp/syntax/parse.go')
| -rw-r--r-- | src/regexp/syntax/parse.go | 19 |
1 files changed, 14 insertions, 5 deletions
diff --git a/src/regexp/syntax/parse.go b/src/regexp/syntax/parse.go index accee9ab08..a4ccfe3bdb 100644 --- a/src/regexp/syntax/parse.go +++ b/src/regexp/syntax/parse.go @@ -1159,9 +1159,18 @@ func (p *parser) parsePerlFlags(s string) (rest string, err error) { // support all three as well. EcmaScript 4 uses only the Python form. // // In both the open source world (via Code Search) and the - // Google source tree, (?P<expr>name) is the dominant form, - // so that's the one we implement. One is enough. - if len(t) > 4 && t[2] == 'P' && t[3] == '<' { + // Google source tree, (?P<expr>name) and (?<expr>name) are the + // dominant forms of named captures and both are supported. + startsWithP := len(t) > 4 && t[2] == 'P' && t[3] == '<' + startsWithName := len(t) > 3 && t[2] == '<' + + if startsWithP || startsWithName { + // position of expr start + exprStartPos := 4 + if startsWithName { + exprStartPos = 3 + } + // Pull out name. end := strings.IndexRune(t, '>') if end < 0 { @@ -1171,8 +1180,8 @@ func (p *parser) parsePerlFlags(s string) (rest string, err error) { return "", &Error{ErrInvalidNamedCapture, s} } - capture := t[:end+1] // "(?P<name>" - name := t[4:end] // "name" + capture := t[:end+1] // "(?P<name>" or "(?<name>" + name := t[exprStartPos:end] // "name" if err = checkUTF8(name); err != nil { return "", err } |
