mercurial/filelog.py

icasefs: make case-folding collision detection as deletion aware (issue3648)

Before this patch, case-folding collision is checked simply between
manifests of each merged revisions.

So, files may be considered as colliding each other, even though one
of them is already deleted on one of merged branches: in such case,
merge causes deleting it, so case-folding collision doesn't occur.

This patch checks whether both of files colliding each other still
remain after merge or not, and ignores collision if at least one of
them is deleted by merge.

In the case that one of colliding files is deleted on one of merged
branches and changed on another, file is considered to still remain
after merge, even though it may be deleted by merge, if "deleting" of
it is chosen in "manifestmerge()".

This avoids fail to merge by case-folding collisions after choices
from "changing" and "deleting" of files.

This patch adds only tests for "removed remotely" code paths in
"_remains()", because other ones are tested by existing tests in
"test-casecollision-merge.t".

# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import 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, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    keys = []
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
        keys.append(k)
    return meta, keys, (s + 2)

def _packmeta(meta, keys=None):
    if not keys:
        keys = sorted(meta.iterkeys())
    return "".join("%s: %s\n" % (k, meta[k]) for k in keys)

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        revlog.revlog.__init__(self, 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 = "\1\n%s\1\n%s" % (_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))

        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
        return revlog.revlog.size(self, 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 revlog.revlog.cmp(self, node, t)
        if samehashes:
            return False

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