Mercurial > hg
comparison mercurial/store.py @ 40494:9aeb9e2d28a7
store: introduce _matchtrackedpath() and use it to filter store files
This patch introduces a function to filter store files on the basis of the path
which they are tracking.
The function assumes that the entries can be of two types, 'meta/*' and 'data/*'
which means it will just work on revlog based storage and not with another
storage ways.
For the 'data/*' entries, we remove the 'data/' part and '.i/.d' part from the
beginning and the end then pass that to matcher.
For the 'meta/*' entries, we remove the 'meta/' and '/00manifest.(i/d)' part from
beginning and end then call matcher.visitdir() with it to make sure all the
parent directories are also downloaded.
Since the storage filtering for narrow stream clones is implemented with this
patch, we remove the un-implemented error message, add some more tests and add
the treemanifest case to tests too.
The tests demonstrate that it works correctly.
After this patch, we have now narrow stream clones working. Narrow stream clones
are a very important feature for large repositories who have good internet
connection because they use streamclones for cloning and if they do normal
narrow clone, that takes more time then a full streamclone. Also narrow-stream
clone will drastically speed up clone timings.
Differential Revision: https://phab.mercurial-scm.org/D5139
author | Pulkit Goyal <pulkit@yandex-team.ru> |
---|---|
date | Wed, 17 Oct 2018 17:42:32 +0300 |
parents | 2d45b549392f |
children | a694a7159125 |
comparison
equal
deleted
inserted
replaced
40493:a2c4502e409b | 40494:9aeb9e2d28a7 |
---|---|
21 util, | 21 util, |
22 vfs as vfsmod, | 22 vfs as vfsmod, |
23 ) | 23 ) |
24 | 24 |
25 parsers = policy.importmod(r'parsers') | 25 parsers = policy.importmod(r'parsers') |
26 | |
27 def _matchtrackedpath(path, matcher): | |
28 """parses a fncache entry and returns whether the entry is tracking a path | |
29 matched by matcher or not. | |
30 | |
31 If matcher is None, returns True""" | |
32 | |
33 if matcher is None: | |
34 return True | |
35 path = decodedir(path) | |
36 if path.startswith('data/'): | |
37 return matcher(path[len('data/'):-len('.i')]) | |
38 elif path.startswith('meta/'): | |
39 return matcher.visitdir(path[len('meta/'):-len('/00manifest.i')] or '.') | |
26 | 40 |
27 # This avoids a collision between a file named foo and a dir named | 41 # This avoids a collision between a file named foo and a dir named |
28 # foo.i or foo.d | 42 # foo.i or foo.d |
29 def _encodedir(path): | 43 def _encodedir(path): |
30 ''' | 44 ''' |
411 self.vfs = vfsmod.filtervfs(vfs, encodefilename) | 425 self.vfs = vfsmod.filtervfs(vfs, encodefilename) |
412 self.opener = self.vfs | 426 self.opener = self.vfs |
413 | 427 |
414 def datafiles(self, matcher=None): | 428 def datafiles(self, matcher=None): |
415 for a, b, size in super(encodedstore, self).datafiles(): | 429 for a, b, size in super(encodedstore, self).datafiles(): |
430 if not _matchtrackedpath(a, matcher): | |
431 continue | |
416 try: | 432 try: |
417 a = decodefilename(a) | 433 a = decodefilename(a) |
418 except KeyError: | 434 except KeyError: |
419 a = None | 435 a = None |
420 yield a, b, size | 436 yield a, b, size |
540 def getsize(self, path): | 556 def getsize(self, path): |
541 return self.rawvfs.stat(path).st_size | 557 return self.rawvfs.stat(path).st_size |
542 | 558 |
543 def datafiles(self, matcher=None): | 559 def datafiles(self, matcher=None): |
544 for f in sorted(self.fncache): | 560 for f in sorted(self.fncache): |
561 if not _matchtrackedpath(f, matcher): | |
562 continue | |
545 ef = self.encode(f) | 563 ef = self.encode(f) |
546 try: | 564 try: |
547 yield f, ef, self.getsize(ef) | 565 yield f, ef, self.getsize(ef) |
548 except OSError as err: | 566 except OSError as err: |
549 if err.errno != errno.ENOENT: | 567 if err.errno != errno.ENOENT: |