view mercurial/pure/bdiff.py @ 39631:b9e453d683a1

exchangev2: fetch changeset revisions

All Mercurial repository data is derived from changesets:
you can't do anything unless you have changesets. Therefore,
it makes sense for changesets to be the first piece of data
that we transfer as part of pull.

To do this, we call our new "changesetdata" command, requesting
parents and revision data. This gives us all the data that a
changegroup delta group would give us. We simply normalize
this data into what addgroup() expects and call that API on
the changelog to bulk insert revisions into the changelog.

Code in this commit is heavily borrowed from
changegroup.cg1unpacker.apply().

Differential Revision: https://phab.mercurial-scm.org/D4482

# bdiff.py - Python implementation of bdiff.c
#
# Copyright 2009 Matt Mackall <[e-mail]> and others
#
# 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 difflib
import re
import struct

def splitnewlines(text):
    '''like str.splitlines, but only split on newlines.'''
    lines = [l + '\n' for l in text.split('\n')]
    if lines:
        if lines[-1] == '\n':
            lines.pop()
        else:
            lines[-1] = lines[-1][:-1]
    return lines

def _normalizeblocks(a, b, blocks):
    prev = None
    r = []
    for curr in blocks:
        if prev is None:
            prev = curr
            continue
        shift = 0

        a1, b1, l1 = prev
        a1end = a1 + l1
        b1end = b1 + l1

        a2, b2, l2 = curr
        a2end = a2 + l2
        b2end = b2 + l2
        if a1end == a2:
            while (a1end + shift < a2end and
                   a[a1end + shift] == b[b1end + shift]):
                shift += 1
        elif b1end == b2:
            while (b1end + shift < b2end and
                   a[a1end + shift] == b[b1end + shift]):
                shift += 1
        r.append((a1, b1, l1 + shift))
        prev = a2 + shift, b2 + shift, l2 - shift
    r.append(prev)
    return r

def bdiff(a, b):
    a = bytes(a).splitlines(True)
    b = bytes(b).splitlines(True)

    if not a:
        s = "".join(b)
        return s and (struct.pack(">lll", 0, 0, len(s)) + s)

    bin = []
    p = [0]
    for i in a:
        p.append(p[-1] + len(i))

    d = difflib.SequenceMatcher(None, a, b).get_matching_blocks()
    d = _normalizeblocks(a, b, d)
    la = 0
    lb = 0
    for am, bm, size in d:
        s = "".join(b[lb:bm])
        if am > la or s:
            bin.append(struct.pack(">lll", p[la], p[am], len(s)) + s)
        la = am + size
        lb = bm + size

    return "".join(bin)

def blocks(a, b):
    an = splitnewlines(a)
    bn = splitnewlines(b)
    d = difflib.SequenceMatcher(None, an, bn).get_matching_blocks()
    d = _normalizeblocks(an, bn, d)
    return [(i, i + n, j, j + n) for (i, j, n) in d]

def fixws(text, allws):
    if allws:
        text = re.sub('[ \t\r]+', '', text)
    else:
        text = re.sub('[ \t\r]+', ' ', text)
        text = text.replace(' \n', '\n')
    return text

def splitnewlines(text):
    '''like str.splitlines, but only split on newlines.'''
    lines = [l + '\n' for l in text.split('\n')]
    if lines:
        if lines[-1] == '\n':
            lines.pop()
        else:
            lines[-1] = lines[-1][:-1]
    return lines