Mercurial > public > mercurial-scm > hg-stable
diff mercurial/match.py @ 50695:1c31b343e514
match: add `filepath:` pattern to match an exact filepath relative to the root
It's useful in certain automated workflows to make sure we recurse in
directories whose name conflicts with files in other revisions.
In addition it makes it possible to avoid building a potentially costly regex,
improving performance when the set of files to match explicitly is large.
The benchmark below are run in the following configuration :
# data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
# benchmark.name = files
# benchmark.variants.rev = tip
# benchmark.variants.files = all-list-filepath-sorted
# bin-env-vars.hg.flavor = no-rust
It also includes timings using the re2 engine (through the `google-re2` module)
to show how much can be saved by just using a better regexp engine.
Pattern time (seconds) time using re2
-----------------------------------------------------------
just "." 0.4 0.4
list of "filepath:?" 1.3 1.3
list of "path:?" 25.7 3.9
list of patterns 29.7 10.4
As you can see, Without re2, using "filepath:" instead of "path:" is a huge
win. With re2, it is still about three times faster to not have to build the
regex.
| author | Rapha?l Gom?s <rgomes@octobus.net> |
|---|---|
| date | Mon, 12 Jun 2023 16:51:08 +0200 |
| parents | 81c7d04f4722 |
| children | b32c3146ec34 |
line wrap: on
line diff
--- a/mercurial/match.py Sun Jun 18 00:09:39 2023 +0200 +++ b/mercurial/match.py Mon Jun 12 16:51:08 2023 +0200 @@ -30,6 +30,7 @@ b're', b'glob', b'path', + b'filepath', b'relglob', b'relpath', b'relre', @@ -181,6 +182,8 @@ 're:<regexp>' - a regular expression 'path:<path>' - a path relative to repository root, which is matched recursively + 'filepath:<path>' - an exact path to a single file, relative to the + repository root 'rootfilesin:<path>' - a path relative to repository root, which is matched non-recursively (will not match subdirectories) 'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs) @@ -334,10 +337,18 @@ """Convert 'kind:pat' from the patterns list to tuples with kind and normalized and rooted patterns and with listfiles expanded.""" kindpats = [] + kinds_to_normalize = ( + b'relglob', + b'path', + b'filepath', + b'rootfilesin', + b'rootglob', + ) + for kind, pat in [_patsplit(p, default) for p in patterns]: if kind in cwdrelativepatternkinds: pat = pathutil.canonpath(root, cwd, pat, auditor=auditor) - elif kind in (b'relglob', b'path', b'rootfilesin', b'rootglob'): + elif kind in kinds_to_normalize: pat = util.normpath(pat) elif kind in (b'listfile', b'listfile0'): try: @@ -1340,6 +1351,10 @@ return b'' if kind == b're': return pat + if kind == b'filepath': + raise error.ProgrammingError( + "'filepath:' patterns should not be converted to a regex" + ) if kind in (b'path', b'relpath'): if pat == b'.': return b'' @@ -1444,7 +1459,14 @@ """ try: allgroups = [] - regexps = [_regex(k, p, globsuffix) for (k, p, s) in kindpats] + regexps = [] + exact = set() + for (kind, pattern, _source) in kindpats: + if kind == b'filepath': + exact.add(pattern) + continue + regexps.append(_regex(kind, pattern, globsuffix)) + fullregexp = _joinregexes(regexps) startidx = 0 @@ -1469,9 +1491,20 @@ allgroups.append(_joinregexes(group)) allmatchers = [_rematcher(g) for g in allgroups] func = lambda s: any(m(s) for m in allmatchers) - return fullregexp, func + + actualfunc = func + if exact: + # An empty regex will always match, so only call the regex if + # there were any actual patterns to match. + if not regexps: + actualfunc = lambda s: s in exact + else: + actualfunc = lambda s: s in exact or func(s) + return fullregexp, actualfunc except re.error: for k, p, s in kindpats: + if k == b'filepath': + continue try: _rematcher(_regex(k, p, globsuffix)) except re.error: @@ -1502,7 +1535,7 @@ break root.append(p) r.append(b'/'.join(root)) - elif kind in (b'relpath', b'path'): + elif kind in (b'relpath', b'path', b'filepath'): if pat == b'.': pat = b'' r.append(pat)