view mercurial/pure/bdiff.py @ 25878:800e090e9c64 stable

localrepo: make journal.dirstate contain in-memory changes before transaction

Before this patch, in-memory dirstate changes aren't written out at
opening transaction, even though 'journal.dirstate' is created
directly from '.hg/dirstate'.

Therefore, subsequent 'hg rollback' uses incomplete 'undo.dirstate' to
restore dirstate, if dirstate is changed and isn't written out before
opening transaction.

In cases below, the condition "dirstate is changed and isn't written
out before opening transaction" isn't satisfied and this problem
doesn't appear:

  - "wlock scope" and "transaction scope" are almost equivalent

    e.g. 'commit --amend', 'import' and so on

  - dirstate changes are written out before opening transaction

    e.g. 'rebase' (via 'dirstateguard') and 'commit -A' (by separated
    wlock scopes)

On the other hand, 'backout' may satisfy the condition above.

To make 'journal.dirstate' contain in-memory changes before opening
transaction, this patch explicitly invokes 'dirstate.write()' in
'localrepository.transaction()'.

'dirstate.write()' is placed before not "writing journal files out"
but "invoking pretxnopen hooks" for visibility of dirstate changes to
external hook processes.

BTW, in the test script, 'touch -t 200001010000' and 'hg status' are
invoked to make file 'c' surely clean in dirstate, because "clean but
unsure" files indirectly cause 'dirstate.write()' at 'repo.status()'
in 'repo.commit()' (see fe03f522dda9 for detail) and prevents from
certainly reproducing the issue.

# 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.

import struct, difflib, re

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 = str(a).splitlines(True)
    b = str(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