mercurial/filelog.py
author Yuya Nishihara <yuya@tcha.org>
Fri, 20 Mar 2015 00:22:37 +0900
changeset 24389 93d3e1a8bfb0
parent 24255 4bfe9f2d9761
child 25948 34bd1a5eef5b
permissions -rw-r--r--
test-revert-interactive: eliminate bashism in wildcard pattern The test failed with Debian dash.
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
24255
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
     8
import error, mdiff, revlog
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
     9
import re, struct
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
22596
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
    30
def _censoredtext(text):
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
    31
    m, offs = parsemeta(text)
24117
9cfd7c4f22f5 filelog: allow censored files to contain padding data
Mike Edgar <adgar@google.com>
parents: 24003
diff changeset
    32
    return m and "censored" in m
22596
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
    33
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    34
class filelog(revlog.revlog):
4258
b11a2fb59cf5 revlog: simplify revlog version handling
Matt Mackall <mpm@selenic.com>
parents: 4257
diff changeset
    35
    def __init__(self, opener, path):
19148
3bda242bf244 filelog: use super() for calling base functions
Durham Goode <durham@fb.com>
parents: 14287
diff changeset
    36
        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
    37
                        "/".join(("data", path + ".i")))
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    38
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    39
    def read(self, node):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    40
        t = self.revision(node)
686
d7d68d27ebe5 Reapply startswith() changes that got lost with stale edit
Matt Mackall <mpm@selenic.com>
parents: 681
diff changeset
    41
        if not t.startswith('\1\n'):
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    42
            return t
2579
0875cda033fd use __contains__, index or split instead of str.find
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2470
diff changeset
    43
        s = t.index('\1\n', 2)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 10263
diff changeset
    44
        return t[s + 2:]
360
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    45
10519e4cbd02 filelog: add metadata support
mpm@selenic.com
parents: 358
diff changeset
    46
    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
    47
        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
    48
            text = packmeta(meta, text)
0
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    49
        return self.addrevision(text, transaction, link, p1, p2)
9117c6561b0b Add back links from file revisions to changeset revisions
mpm@selenic.com
parents:
diff changeset
    50
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    51
    def renamed(self, node):
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    52
        if self.parents(node)[0] != revlog.nullid:
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    53
            return False
13240
e5060aa22043 filelog: move metadata parsing to a helper function
Matt Mackall <mpm@selenic.com>
parents: 11541
diff changeset
    54
        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
    55
        m = parsemeta(t)[0]
5915
d0576d065993 Prefer i in d over d.has_key(i)
Christian Ebert <blacktrash@gmx.net>
parents: 4635
diff changeset
    56
        if m and "copy" in m:
7634
14a4337a9b9b revlog: kill from-style imports
Matt Mackall <mpm@selenic.com>
parents: 7622
diff changeset
    57
            return (m["copy"], revlog.bin(m["copyrev"]))
1116
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    58
        return False
0cdd73b0767c Add some rename debugging support
mpm@selenic.com
parents: 1089
diff changeset
    59
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    60
    def size(self, rev):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    61
        """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
    62
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    63
        # 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
    64
        node = self.node(rev)
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    65
        if self.renamed(node):
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    66
            return len(self.read(node))
24118
76f6ae06ddf5 revlog: add "iscensored()" to revlog public API
Mike Edgar <adgar@google.com>
parents: 24117
diff changeset
    67
        if self.iscensored(rev):
22597
58ec36686f0e filelog: censored files compare against empty data, have 0 size
Mike Edgar <adgar@google.com>
parents: 22596
diff changeset
    68
            return 0
2898
db397c38005d merge: use file size stored in revlog index
Matt Mackall <mpm@selenic.com>
parents: 2895
diff changeset
    69
11540
2370e270a29a filelog: test behaviour for data starting with "\1\n"
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11539
diff changeset
    70
        # 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
    71
        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
    72
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    73
    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
    74
        """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
    75
a463e3c50212 cmp: document the fact that we return True if content is different
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 10706
diff changeset
    76
        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
    77
        """
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
        t = text
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    80
        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
    81
            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
    82
19148
3bda242bf244 filelog: use super() for calling base functions
Durham Goode <durham@fb.com>
parents: 14287
diff changeset
    83
        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
    84
        if samehashes:
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    85
            return False
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    86
22597
58ec36686f0e filelog: censored files compare against empty data, have 0 size
Mike Edgar <adgar@google.com>
parents: 22596
diff changeset
    87
        # censored files compare against the empty file
24118
76f6ae06ddf5 revlog: add "iscensored()" to revlog public API
Mike Edgar <adgar@google.com>
parents: 24117
diff changeset
    88
        if self.iscensored(self.rev(node)):
22597
58ec36686f0e filelog: censored files compare against empty data, have 0 size
Mike Edgar <adgar@google.com>
parents: 22596
diff changeset
    89
            return text != ''
58ec36686f0e filelog: censored files compare against empty data, have 0 size
Mike Edgar <adgar@google.com>
parents: 22596
diff changeset
    90
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    91
        # 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
    92
        # 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
    93
        if self.renamed(node):
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    94
            t2 = self.read(node)
2895
21631c2c09a5 filelog.cmp: return 0 for equality
Matt Mackall <mpm@selenic.com>
parents: 2890
diff changeset
    95
            return t2 != text
2887
05257fd28591 filelog: add hash-based comparisons
Matt Mackall <mpm@selenic.com>
parents: 2859
diff changeset
    96
11541
ab9fa7a85dd9 filelog: cmp: don't read data if hashes are identical (issue2273)
Nicolas Dumazet <nicdumz.commits@gmail.com>
parents: 11540
diff changeset
    97
        return True
14287
7c231754a621 filelog: add file function to open other filelogs
Sune Foldager <cryo@cyanite.org>
parents: 14074
diff changeset
    98
22596
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
    99
    def checkhash(self, text, p1, p2, node, rev=None):
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   100
        try:
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   101
            super(filelog, self).checkhash(text, p1, p2, node, rev=rev)
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   102
        except error.RevlogError:
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   103
            if _censoredtext(text):
24190
903c7e8c97ad changegroup: emit full-replacement deltas if either revision is censored
Mike Edgar <adgar@google.com>
parents: 24118
diff changeset
   104
                raise error.CensoredNodeError(self.indexfile, node, text)
22596
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   105
            raise
27e2317efe89 filelog: raise CensoredNodeError when hash checks fail with censor metadata
Mike Edgar <adgar@google.com>
parents: 22422
diff changeset
   106
24118
76f6ae06ddf5 revlog: add "iscensored()" to revlog public API
Mike Edgar <adgar@google.com>
parents: 24117
diff changeset
   107
    def iscensored(self, rev):
22597
58ec36686f0e filelog: censored files compare against empty data, have 0 size
Mike Edgar <adgar@google.com>
parents: 22596
diff changeset
   108
        """Check if a file revision is censored."""
23858
22a979d1ae56 filelog: use censored revlog flag bit to quickly check if a node is censored
Mike Edgar <adgar@google.com>
parents: 22597
diff changeset
   109
        return self.flags(rev) & revlog.REVIDX_ISCENSORED
24255
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   110
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   111
    def _peek_iscensored(self, baserev, delta, flush):
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   112
        """Quickly check if a delta produces a censored revision."""
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   113
        # Fragile heuristic: unless new file meta keys are added alphabetically
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   114
        # preceding "censored", all censored revisions are prefixed by
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   115
        # "\1\ncensored:". A delta producing such a censored revision must be a
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   116
        # full-replacement delta, so we inspect the first and only patch in the
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   117
        # delta for this prefix.
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   118
        hlen = struct.calcsize(">lll")
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   119
        if len(delta) <= hlen:
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   120
            return False
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   121
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   122
        oldlen = self.rawsize(baserev)
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   123
        newlen = len(delta) - hlen
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   124
        if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   125
            return False
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   126
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   127
        add = "\1\ncensored:"
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   128
        addlen = len(add)
4bfe9f2d9761 revlog: addgroup checks if incoming deltas add censored revs, sets flag bit
Mike Edgar <adgar@google.com>
parents: 24190
diff changeset
   129
        return newlen >= addlen and delta[hlen:hlen + addlen] == add