view mercurial/filelog.py @ 37271:0194dac77c93

scmutil: add method for looking up a context given a revision symbol

changectx's constructor currently supports a mix if inputs:

  * integer revnums
  * binary nodeids
  * '.', 'tip', 'null'
  * stringified revnums
  * namespaced identifiers (e.g. bookmarks and tags)
  * hex nodeids
  * partial hex nodeids

The first two are always internal [1]. The other five can be specified
by the user. The third type ('.', 'tip', 'null') often comes from
either the user or internal callers. We probably have some internal
callers that pass hex nodeids too, perhaps even partial ones
(histedit?). There are only a few callers that pass user-supplied
strings: revsets.stringset, peer.lookup, webutil.changeidctx, and
maybe one or two more.

Supporting this mix of things in the constructor is convenient, but a
bit strange, IMO. For example, if repo[node] is given a node that's
not in the repo, it will first check if it's bookmark etc before
raising an exception. Of course, the risk of it being a bookmark is
extremely small, but it just feels ugly.

Also, a problem with having this code in the constructor (whether it
supports a mix of types or not) is that it's harder to override (I'd
like to override it, and that's how this series started).

This patch starts moving out the handling of user-supplied strings by
introducing scmutil.revsymbol(). So far, that just checks that the
input is indeed a string, and then delegates to repo[symbol]. The
patch also calls it from revsets.stringset to prove that it works.

 [1] Well, you probably can enter a 20-byte binary nodeid on the
     command line, but I don't think we should care to preserve
     support for that.

Differential Revision: https://phab.mercurial-scm.org/D3024

# 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.

from __future__ import absolute_import

import re
import struct

from . import (
    error,
    mdiff,
    revlog,
)

_mdre = re.compile('\1\n')
def parsemeta(text):
    """return (metadatadict, 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)
    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

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        super(filelog, self).__init__(opener,
                        "/".join(("data", path + ".i")))
        # full name of the user visible file, relative to the repository root
        self.filename = path

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

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

    def _peek_iscensored(self, baserev, delta, flush):
        """Quickly check if a delta produces a censored revision."""
        # Fragile heuristic: unless new file meta keys are added alphabetically
        # preceding "censored", all censored revisions are prefixed by
        # "\1\ncensored:". A delta producing such a censored revision must be a
        # full-replacement delta, so we inspect the first and only patch in the
        # delta for this prefix.
        hlen = struct.calcsize(">lll")
        if len(delta) <= hlen:
            return False

        oldlen = self.rawsize(baserev)
        newlen = len(delta) - hlen
        if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
            return False

        add = "\1\ncensored:"
        addlen = len(add)
        return newlen >= addlen and delta[hlen:hlen + addlen] == add