mercurial/filelog.py
author Mike Edgar <adgar@google.com>
Tue, 02 Sep 2014 14:42:30 -0400
changeset 22422 75bb7c702317
parent 22421 30a610424eff
child 22596 27e2317efe89
permissions -rw-r--r--
filelog: parsemeta stops returning unused key list Currently, only the returned meta dictionary is used. An upcoming change will use the returned text offset.
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')
22421
30a610424eff filelog: make parsemeta a public module function, to be used by censor module
Mike Edgar <adgar@google.com>
parents: 22420
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':
22422
75bb7c702317 filelog: parsemeta stops returning unused key list
Mike Edgar <adgar@google.com>
parents: 22421
diff changeset
    16
        return None, None
14074
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
    for l in mtext.splitlines():
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    21
        k, v = l.split(": ", 1)
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    22
        meta[k] = v
22422
75bb7c702317 filelog: parsemeta stops returning unused key list
Mike Edgar <adgar@google.com>
parents: 22421
diff changeset
    23
    return meta, (s + 2)
14074
e8271159c8c2 filelog: extract metadata parsing and packing
Sune Foldager <cryo@cyanite.org>
parents: 13240
diff changeset
    24
22420
4669e26747c3 filelog: make packmeta a public module function, to be used by censor
Mike Edgar <adgar@google.com>
parents: 19148
diff changeset
    25
def packmeta(meta, text):
4669e26747c3 filelog: make packmeta a public module function, to be used by censor
Mike Edgar <adgar@google.com>
parents: 19148
diff changeset
    26
    keys = sorted(meta.iterkeys())
4669e26747c3 filelog: make packmeta a public module function, to be used by censor
Mike Edgar <adgar@google.com>
parents: 19148
diff changeset
    27
    metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
4669e26747c3 filelog: make packmeta a public module function, to be used by censor
Mike Edgar <adgar@google.com>
parents: 19148
diff changeset
    28
    return "\1\n%s\1\n%s" % (metatext, text)
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    29
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    30
class filelog(revlog.revlog):
4258
b11a2fb59cf5 revlog: simplify revlog version handling
Matt Mackall <mpm@selenic.com>
parents: 4257
diff changeset
    31
    def __init__(self, opener, path):
19148
3bda242bf244 filelog: use super() for calling base functions
Durham Goode <durham@fb.com>
parents: 14287
diff changeset
    32
        super(filelog, self).__init__(opener,
8531
810387f59696 filelog encoding: move the encoding/decoding into store
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 8225
diff changeset
    33
                        "/".join(("data", path + ".i")))
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    34
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    35
    def read(self, node):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    36
        t = self.revision(node)
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    37
        if not t.startswith('\1\n'):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    38
            return t
2579
0875cda033fd use __contains__, index or split instead of str.find
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2470
diff changeset
    39
        s = t.index('\1\n', 2)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 10263
diff changeset
    40
        return t[s + 2:]
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    41
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    42
    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
    43
        if meta or text.startswith('\1\n'):
22420
4669e26747c3 filelog: make packmeta a public module function, to be used by censor
Mike Edgar <adgar@google.com>
parents: 19148
diff changeset
    44
            text = packmeta(meta, text)
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    45
        return self.addrevision(text, transaction, link, p1, p2)
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    46
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    47
    def renamed(self, node):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    48
        if self.parents(node)[0] != revlog.nullid:
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    49
            return False
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    50
        t = self.revision(node)
22421
30a610424eff filelog: make parsemeta a public module function, to be used by censor module
Mike Edgar <adgar@google.com>
parents: 22420
diff changeset
    51
        m = parsemeta(t)[0]
5915
d0576d065993 Prefer i in d over d.has_key(i)
Christian Ebert <blacktrash@gmx.net>
parents: 4635
diff changeset
    52
        if m and "copy" in m:
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    53
            return (m["copy"], revlog.bin(m["copyrev"]))
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    54
        return False
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    55
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    56
    def size(self, rev):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    57
        """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
    58
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    59
        # 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
    60
        node = self.node(rev)
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    61
        if self.renamed(node):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    62
            return len(self.read(node))
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    63
11540
2370e270a29a filelog: test behaviour for data starting with "\1\n"
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11539
diff changeset
    64
        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
19148
3bda242bf244 filelog: use super() for calling base functions
Durham Goode <durham@fb.com>
parents: 14287
diff changeset
    65
        return super(filelog, self).size(rev)
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    66
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    67
    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
    68
        """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
    69
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    70
        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
    71
        """
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    72
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    73
        t = text
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    74
        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
    75
            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
    76
19148
3bda242bf244 filelog: use super() for calling base functions
Durham Goode <durham@fb.com>
parents: 14287
diff changeset
    77
        samehashes = not super(filelog, self).cmp(node, t)
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    78
        if samehashes:
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    79
            return False
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    80
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    81
        # 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
    82
        # 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
    83
        if self.renamed(node):
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    84
            t2 = self.read(node)
2895
21631c2c09a5 filelog.cmp: return 0 for equality
Matt Mackall <mpm@selenic.com>
parents: 2890
diff changeset
    85
            return t2 != text
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    86
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    87
        return True
14287
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    88
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    89
    def _file(self, f):
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    90
        return filelog(self.opener, f)