mercurial/filelog.py
author Matt Mackall <mpm@selenic.com>
Thu, 12 Aug 2010 18:09:03 -0500
changeset 11832 7fa36341e7a0
parent 11541 ab9fa7a85dd9
child 13240 e5060aa22043
permissions -rw-r--r--
merge with stable
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
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
     9
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    10
class filelog(revlog.revlog):
4258
b11a2fb59cf5 revlog: simplify revlog version handling
Matt Mackall <mpm@selenic.com>
parents: 4257
diff changeset
    11
    def __init__(self, opener, path):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    12
        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
    13
                        "/".join(("data", path + ".i")))
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    14
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    15
    def read(self, node):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    16
        t = self.revision(node)
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    17
        if not t.startswith('\1\n'):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    18
            return t
2579
0875cda033fd use __contains__, index or split instead of str.find
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2470
diff changeset
    19
        s = t.index('\1\n', 2)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 10263
diff changeset
    20
        return t[s + 2:]
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    21
3123
4ea58eb3f0c9 filelog: make metadata method private
Matt Mackall <mpm@selenic.com>
parents: 2948
diff changeset
    22
    def _readmeta(self, node):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    23
        t = self.revision(node)
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    24
        if not t.startswith('\1\n'):
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    25
            return {}
2579
0875cda033fd use __contains__, index or split instead of str.find
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2470
diff changeset
    26
        s = t.index('\1\n', 2)
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    27
        mt = t[2:s]
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    28
        m = {}
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    29
        for l in mt.splitlines():
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    30
            k, v = l.split(": ", 1)
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    31
            m[k] = v
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    32
        return m
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    33
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    34
    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
    35
        if meta or text.startswith('\1\n'):
10705
194342b34870 filelog: no need to optimize an uncommon case, assume meta = {}
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 10490
diff changeset
    36
            mt = ["%s: %s\n" % (k, v) for k, v in sorted(meta.iteritems())]
1540
8ca9f5b17257 minor optimization: save some string trash
twaldmann@thinkmo.de
parents: 1117
diff changeset
    37
            text = "\1\n%s\1\n%s" % ("".join(mt), text)
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    38
        return self.addrevision(text, transaction, link, p1, p2)
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    39
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    40
    def renamed(self, node):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    41
        if self.parents(node)[0] != revlog.nullid:
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    42
            return False
3123
4ea58eb3f0c9 filelog: make metadata method private
Matt Mackall <mpm@selenic.com>
parents: 2948
diff changeset
    43
        m = self._readmeta(node)
5915
d0576d065993 Prefer i in d over d.has_key(i)
Christian Ebert <blacktrash@gmx.net>
parents: 4635
diff changeset
    44
        if m and "copy" in m:
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    45
            return (m["copy"], revlog.bin(m["copyrev"]))
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    46
        return False
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    47
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    48
    def size(self, rev):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    49
        """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
    50
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    51
        # 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
    52
        node = self.node(rev)
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    53
        if self.renamed(node):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    54
            return len(self.read(node))
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    55
11540
2370e270a29a filelog: test behaviour for data starting with "\1\n"
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11539
diff changeset
    56
        # 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
    57
        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
    58
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    59
    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
    60
        """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
    61
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    62
        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
    63
        """
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    64
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    65
        t = text
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    66
        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
    67
            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
    68
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    69
        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
    70
        if samehashes:
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    71
            return False
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    72
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    73
        # 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
    74
        # 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
    75
        if self.renamed(node):
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    76
            t2 = self.read(node)
2895
21631c2c09a5 filelog.cmp: return 0 for equality
Matt Mackall <mpm@selenic.com>
parents: 2890
diff changeset
    77
            return t2 != text
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    78
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    79
        return True