view mercurial/filelog.py @ 10189:e451e599fbcf

patch: support diff data loss detection and upgrade

In worst case, generating diff in upgrade mode can be two times more expensive
than generating it in git mode directly: we may have to regenerate the whole
diff again whenever a git feature is detected. Also, the first diff attempt is
completely buffered instead of being streamed. That said, even without having
profiled it yet, I am convinced we can fast-path the upgrade mode if necessary
were it to be used in regular diff commands, and not only in mq where avoiding
data loss is worth the price.

# 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, incorporated herein by reference.

import revlog

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 _readmeta(self, node):
        t = self.revision(node)
        if not t.startswith('\1\n'):
            return {}
        s = t.index('\1\n', 2)
        mt = t[2:s]
        m = {}
        for l in mt.splitlines():
            k, v = l.split(": ", 1)
            m[k] = v
        return m

    def add(self, text, meta, transaction, link, p1=None, p2=None):
        if meta or text.startswith('\1\n'):
            mt = ""
            if meta:
                mt = ["%s: %s\n" % (k, v) for k, v in meta.iteritems()]
            text = "\1\n%s\1\n%s" % ("".join(mt), text)
        return self.addrevision(text, transaction, link, p1, p2)

    def renamed(self, node):
        if self.parents(node)[0] != revlog.nullid:
            return False
        m = self._readmeta(node)
        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))

        return revlog.revlog.size(self, rev)

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

        # for renames, we have to go the slow way
        if self.renamed(node):
            t2 = self.read(node)
            return t2 != text

        return revlog.revlog.cmp(self, node, text)