view mercurial/pycompat.py @ 29322:66dbdd3cc2b9 stable

bdiff: extend matches across popular lines

For very large diffs that have large numbers of identical lines (JSON
dumps) that also have large blocks of identical text, bdiff could become
confused about which block matches which because it can only match
very limited regions. The result is very large diffs for small sets of edits.

The earlier recursion rebalancing fix made this behavior more frequent because
it's now more prone to match block 1 to block 2. One frequent user of
large JSON files reported being unable to pass the resulting diffs
through their code review system.

Prior to this change, bdiff would calculate the length of a match at
(i, j) as 1 + length found at (i-1, j-1). With large number of popular
(ignored) lines, this often meant matches couldn't be extended
backwards at all and thus all matching regions were very small.
Disabling the popularity threshold is not an option because it brings
back quadratic behavior.

Instead, we extend a match backwards until we either found a previously
discovered match or we find a mismatching line. This thus successfully
bridges over any popular lines inside and before a matching region.
The larger regions then significant reduce the probability of confusion.

# pycompat.py - portability shim for python 3
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""Mercurial portability shim for python 3.

This contains aliases to hide python version-specific details from the core.
"""

from __future__ import absolute_import

try:
    import cStringIO as io
    stringio = io.StringIO
except ImportError:
    import io
    stringio = io.StringIO

try:
    import Queue as _queue
    _queue.Queue
except ImportError:
    import queue as _queue
empty = _queue.Empty
queue = _queue.Queue

class _pycompatstub(object):
    pass

def _alias(alias, origin, items):
    """ populate a _pycompatstub

    copies items from origin to alias
    """
    def hgcase(item):
        return item.replace('_', '').lower()
    for item in items:
        try:
            setattr(alias, hgcase(item), getattr(origin, item))
        except AttributeError:
            pass

urlreq = _pycompatstub()
urlerr = _pycompatstub()
try:
    import urllib2
    import urllib
    _alias(urlreq, urllib, (
        "addclosehook",
        "addinfourl",
        "ftpwrapper",
        "pathname2url",
        "quote",
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "unquote",
        "url2pathname",
        "urlencode",
        "urlencode",
    ))
    _alias(urlreq, urllib2, (
        "AbstractHTTPHandler",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "HTTPHandler",
        "HTTPPasswordMgrWithDefaultRealm",
        "HTTPSHandler",
        "install_opener",
        "ProxyHandler",
        "Request",
        "urlopen",
    ))
    _alias(urlerr, urllib2, (
        "HTTPError",
        "URLError",
    ))

except ImportError:
    import urllib.request
    _alias(urlreq, urllib.request, (
        "AbstractHTTPHandler",
        "addclosehook",
        "addinfourl",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "ftpwrapper",
        "HTTPHandler",
        "HTTPSHandler",
        "install_opener",
        "pathname2url",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "ProxyHandler",
        "quote",
        "Request",
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "unquote",
        "url2pathname",
        "urlopen",
    ))
    import urllib.error
    _alias(urlerr, urllib.error, (
        "HTTPError",
        "URLError",
    ))

try:
    xrange
except NameError:
    import builtins
    builtins.xrange = range