Mercurial > hg
view mercurial/pure/bdiff.py @ 42155:57539e5ea2e0
verify: introduce a notion of "level"
Some checks are slower than others, to help the user to run the checks he needs,
we are about to introduce new flag to select faster vs deeper runs. This put
the scaffolding in place to do this.
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Wed, 17 Apr 2019 01:12:21 +0200 |
parents | 8b7973d40a01 |
children | 2372284d9457 |
line wrap: on
line source
# bdiff.py - Python implementation of bdiff.c # # Copyright 2009 Matt Mackall <mpm@selenic.com> 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