view mercurial/fancyopts.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.

# fancyopts.py - better command line parsing
#
#  Copyright 2005-2009 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 getopt

from .i18n import _
from . import error

def gnugetopt(args, options, longoptions):
    """Parse options mostly like getopt.gnu_getopt.

    This is different from getopt.gnu_getopt in that an argument of - will
    become an argument of - instead of vanishing completely.
    """
    extraargs = []
    if '--' in args:
        stopindex = args.index('--')
        extraargs = args[stopindex + 1:]
        args = args[:stopindex]
    opts, parseargs = getopt.getopt(args, options, longoptions)
    args = []
    while parseargs:
        arg = parseargs.pop(0)
        if arg and arg[0] == '-' and len(arg) > 1:
            parseargs.insert(0, arg)
            topts, newparseargs = getopt.getopt(parseargs, options, longoptions)
            opts = opts + topts
            parseargs = newparseargs
        else:
            args.append(arg)
    args.extend(extraargs)
    return opts, args


def fancyopts(args, options, state, gnu=False):
    """
    read args, parse options, and store options in state

    each option is a tuple of:

      short option or ''
      long option
      default value
      description
      option value label(optional)

    option types include:

      boolean or none - option sets variable in state to true
      string - parameter string is stored in state
      list - parameter string is added to a list
      integer - parameter strings is stored as int
      function - call function with parameter

    non-option args are returned
    """
    namelist = []
    shortlist = ''
    argmap = {}
    defmap = {}

    for option in options:
        if len(option) == 5:
            short, name, default, comment, dummy = option
        else:
            short, name, default, comment = option
        # convert opts to getopt format
        oname = name
        name = name.replace('-', '_')

        argmap['-' + short] = argmap['--' + oname] = name
        defmap[name] = default

        # copy defaults to state
        if isinstance(default, list):
            state[name] = default[:]
        elif callable(default):
            state[name] = None
        else:
            state[name] = default

        # does it take a parameter?
        if not (default is None or default is True or default is False):
            if short:
                short += ':'
            if oname:
                oname += '='
        if short:
            shortlist += short
        if name:
            namelist.append(oname)

    # parse arguments
    if gnu:
        parse = gnugetopt
    else:
        parse = getopt.getopt
    opts, args = parse(args, shortlist, namelist)

    # transfer result to state
    for opt, val in opts:
        name = argmap[opt]
        obj = defmap[name]
        t = type(obj)
        if callable(obj):
            state[name] = defmap[name](val)
        elif t is type(1):
            try:
                state[name] = int(val)
            except ValueError:
                raise error.Abort(_('invalid value %r for option %s, '
                                   'expected int') % (val, opt))
        elif t is type(''):
            state[name] = val
        elif t is type([]):
            state[name].append(val)
        elif t is type(None) or t is type(False):
            state[name] = True

    # return unparsed args
    return args