mercurial/filelog.py
author Pierre-Yves David <pierre-yves.david@ens-lyon.org>
Wed, 04 Jul 2012 02:00:36 +0200
changeset 17124 f1b7683f3f95
parent 14287 7c231754a621
child 19148 3bda242bf244
permissions -rw-r--r--
obsolete: move obsolete markers read/write logic to obsstore object This is the first step toward incremental writing of obsolete marker within a transaction. For this purpose, obsstore is now given its repo sopener. This make it able to handles read and write to the obsstore file itself. Most IO logic is removed from localrepo and handled by obsstore object directly.
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
1089
142b5d5ec9cc Break apart hg.py
mpm@selenic.com
parents: 1072
diff changeset
     1
# filelog.py - file history class for mercurial
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
     2
#
4635
63b9d2deed48 Updated copyright notices and add "and others" to "hg version"
Thomas Arendsen Hein <thomas@intevation.de>
parents: 4258
diff changeset
     3
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
     4
#
8225
46293a0c7e9f updated license to be explicit about GPL version 2
Martin Geisler <mg@lazybytes.net>
parents: 7634
diff changeset
     5
# This software may be used and distributed according to the terms of the
10263
25e572394f5c Update license to GPLv2+
Matt Mackall <mpm@selenic.com>
parents: 8531
diff changeset
     6
# GNU General Public License version 2 or any later version.
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
     7
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
     8
import revlog
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
     9
import re
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    10
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    11
_mdre = re.compile('\1\n')
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    12
def _parsemeta(text):
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    13
    """return (metadatadict, keylist, metadatasize)"""
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    14
    # text can be buffer, so we can't use .startswith or .index
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    15
    if text[:2] != '\1\n':
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    16
        return None, None, None
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    17
    s = _mdre.search(text, 2).start()
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    18
    mtext = text[2:s]
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    19
    meta = {}
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    20
    keys = []
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    21
    for l in mtext.splitlines():
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    22
        k, v = l.split(": ", 1)
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    23
        meta[k] = v
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    24
        keys.append(k)
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    25
    return meta, keys, (s + 2)
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    26
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    27
def _packmeta(meta, keys=None):
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    28
    if not keys:
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    29
        keys = sorted(meta.iterkeys())
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    30
    return "".join("%s: %s\n" % (k, meta[k]) for k in keys)
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    31
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    32
class filelog(revlog.revlog):
4258
b11a2fb59cf5 revlog: simplify revlog version handling
Matt Mackall <mpm@selenic.com>
parents: 4257
diff changeset
    33
    def __init__(self, opener, path):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    34
        revlog.revlog.__init__(self, opener,
8531
810387f59696 filelog encoding: move the encoding/decoding into store
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 8225
diff changeset
    35
                        "/".join(("data", path + ".i")))
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    36
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    37
    def read(self, node):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    38
        t = self.revision(node)
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    39
        if not t.startswith('\1\n'):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    40
            return t
2579
0875cda033fd use __contains__, index or split instead of str.find
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2470
diff changeset
    41
        s = t.index('\1\n', 2)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 10263
diff changeset
    42
        return t[s + 2:]
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    43
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    44
    def add(self, text, meta, transaction, link, p1=None, p2=None):
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    45
        if meta or text.startswith('\1\n'):
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    46
            text = "\1\n%s\1\n%s" % (_packmeta(meta), text)
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    47
        return self.addrevision(text, transaction, link, p1, p2)
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    48
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    49
    def renamed(self, node):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    50
        if self.parents(node)[0] != revlog.nullid:
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    51
            return False
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    52
        t = self.revision(node)
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    53
        m = _parsemeta(t)[0]
5915
d0576d065993 Prefer i in d over d.has_key(i)
Christian Ebert <blacktrash@gmx.net>
parents: 4635
diff changeset
    54
        if m and "copy" in m:
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    55
            return (m["copy"], revlog.bin(m["copyrev"]))
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    56
        return False
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    57
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    58
    def size(self, rev):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    59
        """return the size of a given revision"""
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    60
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    61
        # for revisions with renames, we have to go the slow way
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    62
        node = self.node(rev)
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    63
        if self.renamed(node):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    64
            return len(self.read(node))
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    65
11540
2370e270a29a filelog: test behaviour for data starting with "\1\n"
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11539
diff changeset
    66
        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    67
        return revlog.revlog.size(self, rev)
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    68
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    69
    def cmp(self, node, text):
11539
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    70
        """compare text with a given file revision
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    71
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    72
        returns True if text is different than what is stored.
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    73
        """
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    74
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    75
        t = text
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    76
        if text.startswith('\1\n'):
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    77
            t = '\1\n\1\n' + text
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    78
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    79
        samehashes = not revlog.revlog.cmp(self, node, t)
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    80
        if samehashes:
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    81
            return False
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    82
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    83
        # renaming a file produces a different hash, even if the data
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    84
        # remains unchanged. Check if it's the case (slow):
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    85
        if self.renamed(node):
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    86
            t2 = self.read(node)
2895
21631c2c09a5 filelog.cmp: return 0 for equality
Matt Mackall <mpm@selenic.com>
parents: 2890
diff changeset
    87
            return t2 != text
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    88
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    89
        return True
14287
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    90
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    91
    def _file(self, f):
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    92
        return filelog(self.opener, f)