1
     €ГВ„ eЯБА ?ч     """Text wrapping and filling.
"""

# Copyright (C) 1999-2001 Gregory P. Ward.
# Copyright (C) 2002, 2003 Python Software Foundation.
# Written by Greg Ward <gward@python.net>

__revision__ = "$Id$"

import string, re

try:
    _unicode = unicode
except NameError:
    # If Python is built without Unicode support, the unicode type
    # will not exist. Fake one.
    class _unicode(object):
        pass

# Do the right thing with boolean values for all known Python versions
# (so this module can be copied to projects that don't depend on Python
# 2.3, e.g. Optik and Docutils) by uncommenting the block of code below.
#try:
#    True, False
#except NameError:
#    (True, False) = (1, 0)

__all__ = ['TextWrapper', 'wrap', 'fill', 'dedent']

# Hardcode the recognized whitespace characters to the US-ASCII
# whitespace characters.  The main reason for doing this is that in
# ISO-8859-1, 0xa0 is non-breaking whitespace, so in certain locales
# that character winds up in string.whitespace.  Respecting
# string.whitespace in those cases would 1) make textwrap treat 0xa0 the
# same as any other whitespace char, which is clearly wrong (it's a
# *non-breaking* space), 2) possibly cause problems with Unicode,
# since 0xa0 is not in range(128).
_whitespace = '\t\n\x0b\x0c\r '

class TextWrapper:
    """
    Object for wrapping/filling text.  The public interface consists of
    the wrap() and fill() methods; the other methods are just there for
    subclasses to override in order to tweak the default behaviour.
    If you want to completely replace the main wrapping algorithm,
    you'll probably have to override _wrap_chunks().

    Several instance attributes control various aspects of wrapping:
      width (default: 70)
        the maximum width of wrapped lines (unless break_long_words
        is false)
      initial_indent (default: "")
        string that will be prepended to the first line of wrapped
        output.  Counts towards the line's width.
      subsequent_indent (default: "")
        string that will be prepended to all lines save the first
        of wrapped output; also counts towards each line's width.
      expand_tabs (default: true)
        Expand tabs in input text to spaces before further processing.
        Each tab will become 1 .. 8 spaces, depending on its position in
        its line.  If false, each tab is treated as a single character.
      replace_whitespace (default: true)
        Replace all whitespace characters in the input text by spaces
        after tab expansion.  Note that if expand_tabs is false and
        replace_whitespace is true, every tab will be converted to a
        single space!
      fix_sentence_endings (default: false)
        Ensure that sentence-ending punctuation is always followed
        by two spaces.  Off by default because the algorithm is
        (unavoidably) imperfect.
      break_long_words (default: true)
        Break words longer than 'width'.  If false, those words will not
        be broken, and some lines might be longer than 'width'.
      break_on_hyphens (default: true)
        Allow breaking hyphenated words. If true, wrapping will occur
        preferably on whitespaces and right after hyphens part of
        compound words.
      drop_whitespace (default: true)
        Drop leading and trailing whitespace from lines.
    """

    whitespace_trans = string.maketrans(_whitespace, ' ' * len(_whitespace))

    unicode_whitespace_trans = {}
    uspace = ord(u' ')
    for x in map(ord, _whitespace):
        unicode_whitespace_trans[x] = uspace

    # This funky little regex is just the trick for splitting
    # text up into word-wrappable chunks.  E.g.
    #   "Hello there -- you goof-ball, use the -b option!"
    # splits into
    #   Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option!
    # (after stripping out empty strings).
    wordsep_re = re.compile(
        r'(\s+|'                                  # any whitespace
        r'[^\s\w]*\w+[^0-9\W]-(?=\w+[^0-9\W])|'   # hyphenated words
        r'(?<=[\w\!\"\'\&\.