( )⚙ D8545 grep: grep the working copy faster

This is an archive of the discontinued Mercurial Phabricator instance.

Differential D8545

grep: grep the working copy faster
ClosedPublic

Authored by valentin.gatienbaron on May 17 2020, 8:48 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG708ad5cf5e5a: grep: grep the working copy faster
Summary

hg grep qqqq in the mercurial repo:
before: 0,859s
after: 0,233s

hg grep somethingwithnomatch in mozilla-central:
before: 51s
after: 19s

This is probably also a tiny bug fix, because the code was looking up
a node for filename pfn on a filelog for filename fn, which are
most of the time the same filename, but don't have to be.

Ignoring performance and the bug fix, the code should have the same
behavior.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

valentin.gatienbaron added a commit: rHG708ad5cf5e5a: grep: grep the working copy faster.May 18 2020, 1:10 PM
This revision was not accepted when it landed; it landed in state Needs Review.
Closed by commit rHG708ad5cf5e5a: grep: grep the working copy faster (authored by valentin.gatienbaron). · Explain Why
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/commands.py (55 lines)

Diff 21423

mercurial/commands.py

skip = set() skip = set()
revfiles = {} revfiles = {}
match = scmutil.match(repo[None], pats, opts) match = scmutil.match(repo[None], pats, opts)
found = False found = False
follow = opts.get(b'follow') follow = opts.get(b'follow')
getrenamed = scmutil.getrenamedfn(repo) getrenamed = scmutil.getrenamedfn(repo)
def get_file_content(filename, filelog, filenode, context, revision): def readfile(ctx, fn):
rev = ctx.rev()
if rev is None:
fctx = ctx[fn]
try: try:
content = filelog.read(filenode) return fctx.data()
except error.WdirUnsupported: except IOError as e:
content = context[filename].data() if e.errno != errno.ENOENT:
raise
else:
flog = getfile(fn)
fnode = ctx.filenode(fn)
try:
return flog.read(fnode)
except error.CensoredNodeError: except error.CensoredNodeError:
content = None
ui.warn( ui.warn(
_(b'cannot search in censored file: %(filename)s:%(revnum)s\n') _(
% {b'filename': filename, b'revnum': pycompat.bytestr(revision)} b'cannot search in censored file: %(filename)s:%(revnum)s\n'
)
% {b'filename': fn, b'revnum': pycompat.bytestr(rev),}
) )
return content
def prep(ctx, fns): def prep(ctx, fns):
rev = ctx.rev() rev = ctx.rev()
pctx = ctx.p1() pctx = ctx.p1()
matches.setdefault(rev, {}) matches.setdefault(rev, {})
if diff: if diff:
parent = pctx.rev() parent = pctx.rev()
matches.setdefault(parent, {}) matches.setdefault(parent, {})
files = revfiles.setdefault(rev, []) files = revfiles.setdefault(rev, [])
for fn in fns: for fn in fns:
flog = getfile(fn) # fn might not exist in the revision (could be a file removed by the
try: # revision). We could check `fn not in ctx` even when rev is None,
fnode = ctx.filenode(fn) # but it's less racy to protect againt that in readfile.
except error.LookupError: if rev is not None and fn not in ctx:
continue continue
copy = None copy = None
if follow: if follow:
copy = getrenamed(fn, rev) copy = getrenamed(fn, rev)
if copy: if copy:
copies.setdefault(rev, {})[fn] = copy copies.setdefault(rev, {})[fn] = copy
if fn in skip: if fn in skip:
skip.add(copy) skip.add(copy)
if fn in skip: if fn in skip:
continue continue
files.append(fn) files.append(fn)
if fn not in matches[rev]: if fn not in matches[rev]:
content = get_file_content(fn, flog, fnode, ctx, rev) grepbody(fn, rev, readfile(ctx, fn))
grepbody(fn, rev, content)
if diff: if diff:
pfn = copy or fn pfn = copy or fn
if pfn not in matches[parent]: if pfn not in matches[parent] and pfn in pctx:
try: grepbody(pfn, parent, readfile(pctx, pfn))
pfnode = pctx.filenode(pfn)
pcontent = get_file_content(
pfn, flog, pfnode, pctx, parent
)
grepbody(pfn, parent, pcontent)
except error.LookupError:
pass
ui.pager(b'grep') ui.pager(b'grep')
fm = ui.formatter(b'grep', opts) fm = ui.formatter(b'grep', opts)
for ctx in cmdutil.walkchangerevs(repo, match, opts, prep): for ctx in cmdutil.walkchangerevs(repo, match, opts, prep):
rev = ctx.rev() rev = ctx.rev()
parent = ctx.p1().rev() parent = ctx.p1().rev()
for fn in sorted(revfiles.get(rev, [])): for fn in sorted(revfiles.get(rev, [])):
states = matches[rev][fn] states = matches[rev][fn]