view mercurial/filelog.py @ 24008:0188c2d90356

trydiff: check only if added file is a copy target, not source When creating a diff with copy/rename enabled, we consider added files and check if they are either copy sources or targets. However, an added file should never be a copy source. The test suite seems to agree with this: all tests pass if we raise an exception when an added file is a copy source. So, let's simplify the code by dropping the conditions that are never true. For those interested in the historical reasons: Before commit d1f209bb9564 (patch: separate reverse copy data (issue1959), 2010-02-11), 'copy' seems to have been a bidirectional map. Then that commit split it up into two unidirectional maps and duplicated the logic to look in both maps. It was still needed at that point to look in both maps, as the copy detection was poor and could sometimes be reported in reverse. A little later came 91eb4512edd0 (copies: rewrite copy detection for non-merge users, 2012-01-04). That commit fixed the copy detection to be backwards when it should, and made the hacks in trydiff unnecessary.
author Martin von Zweigbergk <martinvonz@google.com>
date Fri, 16 Jan 2015 17:01:58 -0800 (2015-01-17)
parents 22a979d1ae56
children b95a5bb58653
line wrap: on
line source
# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import error, revlog
import re

_mdre = re.compile('\1\n')
def parsemeta(text):
    """return (metadatadict, keylist, metadatasize)"""
    # text can be buffer, so we can't use .startswith or .index
    if text[:2] != '\1\n':
        return None, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
    return meta, (s + 2)

def packmeta(meta, text):
    keys = sorted(meta.iterkeys())
    metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
    return "\1\n%s\1\n%s" % (metatext, text)

def _censoredtext(text):
    m, offs = parsemeta(text)
    return m and "censored" in m and not text[offs:]

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        super(filelog, self).__init__(opener,
                        "/".join(("data", path + ".i")))

    def read(self, node):
        t = self.revision(node)
        if not t.startswith('\1\n'):
            return t
        s = t.index('\1\n', 2)
        return t[s + 2:]

    def add(self, text, meta, transaction, link, p1=None, p2=None):
        if meta or text.startswith('\1\n'):
            text = packmeta(meta, text)
        return self.addrevision(text, transaction, link, p1, p2)

    def renamed(self, node):
        if self.parents(node)[0] != revlog.nullid:
            return False
        t = self.revision(node)
        m = parsemeta(t)[0]
        if m and "copy" in m:
            return (m["copy"], revlog.bin(m["copyrev"]))
        return False

    def size(self, rev):
        """return the size of a given revision"""

        # for revisions with renames, we have to go the slow way
        node = self.node(rev)
        if self.renamed(node):
            return len(self.read(node))
        if self._iscensored(rev):
            return 0

        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
        return super(filelog, self).size(rev)

    def cmp(self, node, text):
        """compare text with a given file revision

        returns True if text is different than what is stored.
        """

        t = text
        if text.startswith('\1\n'):
            t = '\1\n\1\n' + text

        samehashes = not super(filelog, self).cmp(node, t)
        if samehashes:
            return False

        # censored files compare against the empty file
        if self._iscensored(self.rev(node)):
            return text != ''

        # renaming a file produces a different hash, even if the data
        # remains unchanged. Check if it's the case (slow):
        if self.renamed(node):
            t2 = self.read(node)
            return t2 != text

        return True

    def checkhash(self, text, p1, p2, node, rev=None):
        try:
            super(filelog, self).checkhash(text, p1, p2, node, rev=rev)
        except error.RevlogError:
            if _censoredtext(text):
                raise error.CensoredNodeError(self.indexfile, node)
            raise

    def _file(self, f):
        return filelog(self.opener, f)

    def _iscensored(self, rev):
        """Check if a file revision is censored."""
        return self.flags(rev) & revlog.REVIDX_ISCENSORED