Mercurial > cpython-lru_cache-weakref
annotate Lib/textwrap.py @ 70817:dd775b1561ba
Fix markup.
| author | Georg Brandl <georg@python.org> |
|---|---|
| date | Tue, 14 Jun 2011 21:09:55 +0200 |
| parents | c9bd62efe6ce |
| children | 3e26c9033306 8c17e898e0e8 |
| rev | line source |
|---|---|
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
1 """Text wrapping and filling. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
2 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
3 |
|
25757
0838c4247917
Fix copyright date: the core of this code actually dates back to 1999
Greg Ward <gward@python.net>
parents:
25534
diff
changeset
|
4 # Copyright (C) 1999-2001 Gregory P. Ward. |
| 29474 | 5 # Copyright (C) 2002, 2003 Python Software Foundation. |
|
23743
2e1def417ecb
Record copyright and author.
Greg Ward <gward@python.net>
parents:
23742
diff
changeset
|
6 # Written by Greg Ward <gward@python.net> |
|
2e1def417ecb
Record copyright and author.
Greg Ward <gward@python.net>
parents:
23742
diff
changeset
|
7 |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
8 __revision__ = "$Id$" |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
9 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
10 import string, re |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
11 |
|
50078
63ee6a0f7358
Manual merge of r67636 from py3k branch:
Georg Brandl <georg@python.org>
parents:
47067
diff
changeset
|
12 __all__ = ['TextWrapper', 'wrap', 'fill', 'dedent'] |
|
27630
6567f4829e7e
Add __all__ (suggested by Raymond Hettinger).
Greg Ward <gward@python.net>
parents:
26614
diff
changeset
|
13 |
|
26614
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
14 # Hardcode the recognized whitespace characters to the US-ASCII |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
15 # whitespace characters. The main reason for doing this is that in |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
16 # ISO-8859-1, 0xa0 is non-breaking whitespace, so in certain locales |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
17 # that character winds up in string.whitespace. Respecting |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
18 # string.whitespace in those cases would 1) make textwrap treat 0xa0 the |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
19 # same as any other whitespace char, which is clearly wrong (it's a |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
20 # *non-breaking* space), 2) possibly cause problems with Unicode, |
|
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
21 # since 0xa0 is not in range(128). |
|
27630
6567f4829e7e
Add __all__ (suggested by Raymond Hettinger).
Greg Ward <gward@python.net>
parents:
26614
diff
changeset
|
22 _whitespace = '\t\n\x0b\x0c\r ' |
|
26614
2c7bdbb50e76
Hardcode the recognized whitespace characters to the US-ASCII whitespace
Greg Ward <gward@python.net>
parents:
26600
diff
changeset
|
23 |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
24 class TextWrapper: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
25 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
26 Object for wrapping/filling text. The public interface consists of |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
27 the wrap() and fill() methods; the other methods are just there for |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
28 subclasses to override in order to tweak the default behaviour. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
29 If you want to completely replace the main wrapping algorithm, |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
30 you'll probably have to override _wrap_chunks(). |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
31 |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
32 Several instance attributes control various aspects of wrapping: |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
33 width (default: 70) |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
34 the maximum width of wrapped lines (unless break_long_words |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
35 is false) |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
36 initial_indent (default: "") |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
37 string that will be prepended to the first line of wrapped |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
38 output. Counts towards the line's width. |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
39 subsequent_indent (default: "") |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
40 string that will be prepended to all lines save the first |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
41 of wrapped output; also counts towards each line's width. |
|
23738
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
42 expand_tabs (default: true) |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
43 Expand tabs in input text to spaces before further processing. |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
44 Each tab will become 1 .. 8 spaces, depending on its position in |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
45 its line. If false, each tab is treated as a single character. |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
46 replace_whitespace (default: true) |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
47 Replace all whitespace characters in the input text by spaces |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
48 after tab expansion. Note that if expand_tabs is false and |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
49 replace_whitespace is true, every tab will be converted to a |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
50 single space! |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
51 fix_sentence_endings (default: false) |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
52 Ensure that sentence-ending punctuation is always followed |
| 27884 | 53 by two spaces. Off by default because the algorithm is |
|
23738
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
54 (unavoidably) imperfect. |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
55 break_long_words (default: true) |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
56 Break words longer than 'width'. If false, those words will not |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
57 be broken, and some lines might be longer than 'width'. |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
58 break_on_hyphens (default: true) |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
59 Allow breaking hyphenated words. If true, wrapping will occur |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
60 preferably on whitespaces and right after hyphens part of |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
61 compound words. |
|
41554
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
62 drop_whitespace (default: true) |
|
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
63 Drop leading and trailing whitespace from lines. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
64 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
65 |
|
26579
e8940d4cd8ca
Fix SF bug #622831 (I think): add unicode_whitespace_trans class
Greg Ward <gward@python.net>
parents:
25884
diff
changeset
|
66 unicode_whitespace_trans = {} |
|
41575
beacf40b5960
Rip out all the u"..." literals and calls to unicode().
Guido van Rossum <guido@python.org>
parents:
41554
diff
changeset
|
67 uspace = ord(' ') |
|
42142
a53e48be6df9
Merged revisions 56125-56153 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
41969
diff
changeset
|
68 for x in _whitespace: |
|
a53e48be6df9
Merged revisions 56125-56153 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
41969
diff
changeset
|
69 unicode_whitespace_trans[ord(x)] = uspace |
|
26579
e8940d4cd8ca
Fix SF bug #622831 (I think): add unicode_whitespace_trans class
Greg Ward <gward@python.net>
parents:
25884
diff
changeset
|
70 |
|
24263
e6033254df21
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
24111
diff
changeset
|
71 # This funky little regex is just the trick for splitting |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
72 # text up into word-wrappable chunks. E.g. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
73 # "Hello there -- you goof-ball, use the -b option!" |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
74 # splits into |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
75 # Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option! |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
76 # (after stripping out empty strings). |
|
34691
0725f0d5a5c7
SF #1149508: ensure textwrap handles hyphenated numbers correctly,
Greg Ward <gward@python.net>
parents:
34311
diff
changeset
|
77 wordsep_re = re.compile( |
|
0725f0d5a5c7
SF #1149508: ensure textwrap handles hyphenated numbers correctly,
Greg Ward <gward@python.net>
parents:
34311
diff
changeset
|
78 r'(\s+|' # any whitespace |
|
50157
740ce9a523ff
Issue #4163: textwrap module: allow word splitting on a hyphen preceded by a non-ASCII letter.
Antoine Pitrou <solipsis@pitrou.net>
parents:
50078
diff
changeset
|
79 r'[^\s\w]*\w+[^0-9\W]-(?=\w+[^0-9\W])|' # hyphenated words |
|
34691
0725f0d5a5c7
SF #1149508: ensure textwrap handles hyphenated numbers correctly,
Greg Ward <gward@python.net>
parents:
34311
diff
changeset
|
80 r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))') # em-dash |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
81 |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
82 # This less funky little regex just split on recognized spaces. E.g. |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
83 # "Hello there -- you goof-ball, use the -b option!" |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
84 # splits into |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
85 # Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/ |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
86 wordsep_simple_re = re.compile(r'(\s+)') |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
87 |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
88 # XXX this is not locale- or charset-aware -- string.lowercase |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
89 # is US-ASCII only (and therefore English-only) |
|
42544
077c68186e23
Quick fix for a new problem here -- using string.lowercase somehow caused
Guido van Rossum <guido@python.org>
parents:
42142
diff
changeset
|
90 sentence_end_re = re.compile(r'[a-z]' # lowercase letter |
|
23739
27f48314ba9d
Convert _fix_sentence_endings() to use a regex, and augment it to
Greg Ward <gward@python.net>
parents:
23738
diff
changeset
|
91 r'[\.\!\?]' # sentence-ending punct. |
|
27f48314ba9d
Convert _fix_sentence_endings() to use a regex, and augment it to
Greg Ward <gward@python.net>
parents:
23738
diff
changeset
|
92 r'[\"\']?' # optional end-of-quote |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
93 r'\Z') # end of chunk |
|
23738
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
94 |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
95 |
|
32088
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
96 def __init__(self, |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
97 width=70, |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
98 initial_indent="", |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
99 subsequent_indent="", |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
100 expand_tabs=True, |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
101 replace_whitespace=True, |
|
52fe93b656cf
SF #847346: merge from release23-maint branch: remove misguided
Greg Ward <gward@python.net>
parents:
30244
diff
changeset
|
102 fix_sentence_endings=False, |
|
41554
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
103 break_long_words=True, |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
104 drop_whitespace=True, |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
105 break_on_hyphens=True): |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
106 self.width = width |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
107 self.initial_indent = initial_indent |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
108 self.subsequent_indent = subsequent_indent |
|
23744
ea035490f624
Make all of TextWrapper's options keyword args to the constructor.
Greg Ward <gward@python.net>
parents:
23743
diff
changeset
|
109 self.expand_tabs = expand_tabs |
|
ea035490f624
Make all of TextWrapper's options keyword args to the constructor.
Greg Ward <gward@python.net>
parents:
23743
diff
changeset
|
110 self.replace_whitespace = replace_whitespace |
|
ea035490f624
Make all of TextWrapper's options keyword args to the constructor.
Greg Ward <gward@python.net>
parents:
23743
diff
changeset
|
111 self.fix_sentence_endings = fix_sentence_endings |
|
ea035490f624
Make all of TextWrapper's options keyword args to the constructor.
Greg Ward <gward@python.net>
parents:
23743
diff
changeset
|
112 self.break_long_words = break_long_words |
|
41554
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
113 self.drop_whitespace = drop_whitespace |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
114 self.break_on_hyphens = break_on_hyphens |
|
24263
e6033254df21
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
24111
diff
changeset
|
115 |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
116 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
117 # -- Private methods ----------------------------------------------- |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
118 # (possibly useful for subclasses to override) |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
119 |
|
23740
a2136ae9d4f7
Conform to the bloody coding standards: "def foo()" not "def foo ()".
Greg Ward <gward@python.net>
parents:
23739
diff
changeset
|
120 def _munge_whitespace(self, text): |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
121 """_munge_whitespace(text : string) -> string |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
122 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
123 Munge whitespace in text: expand tabs and convert all other |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
124 whitespace characters to spaces. Eg. " foo\tbar\n\nbaz" |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
125 becomes " foo bar baz". |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
126 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
127 if self.expand_tabs: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
128 text = text.expandtabs() |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
129 if self.replace_whitespace: |
|
43144
5c30f15a6b87
string.maketrans() now produces translation tables for bytes.translate() -- wrong module?
Georg Brandl <georg@python.org>
parents:
42544
diff
changeset
|
130 text = text.translate(self.unicode_whitespace_trans) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
131 return text |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
132 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
133 |
|
23740
a2136ae9d4f7
Conform to the bloody coding standards: "def foo()" not "def foo ()".
Greg Ward <gward@python.net>
parents:
23739
diff
changeset
|
134 def _split(self, text): |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
135 """_split(text : string) -> [string] |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
136 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
137 Split the text to wrap into indivisible chunks. Chunks are |
|
56368
c9bd62efe6ce
Merged revisions 75231 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents:
50157
diff
changeset
|
138 not quite the same as words; see _wrap_chunks() for full |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
139 details. As an example, the text |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
140 Look, goof-ball -- use the -b option! |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
141 breaks into the following chunks: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
142 'Look,', ' ', 'goof-', 'ball', ' ', '--', ' ', |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
143 'use', ' ', 'the', ' ', '-b', ' ', 'option!' |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
144 if break_on_hyphens is True, or in: |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
145 'Look,', ' ', 'goof-ball', ' ', '--', ' ', |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
146 'use', ' ', 'the', ' ', '-b', ' ', option!' |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
147 otherwise. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
148 """ |
|
47067
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
149 if self.break_on_hyphens is True: |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
150 chunks = self.wordsep_re.split(text) |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
151 else: |
|
960ade856078
Merged revisions 62998-63003,63005-63006,63009-63012,63014-63017,63019-63020,63022-63024,63026-63029,63031-63041,63043-63045,63047-63054,63056-63062 via svnmerge from
Alexandre Vassalotti <alexandre@peadrop.com>
parents:
46664
diff
changeset
|
152 chunks = self.wordsep_simple_re.split(text) |
|
42142
a53e48be6df9
Merged revisions 56125-56153 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
41969
diff
changeset
|
153 chunks = [c for c in chunks if c] |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
154 return chunks |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
155 |
|
23740
a2136ae9d4f7
Conform to the bloody coding standards: "def foo()" not "def foo ()".
Greg Ward <gward@python.net>
parents:
23739
diff
changeset
|
156 def _fix_sentence_endings(self, chunks): |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
157 """_fix_sentence_endings(chunks : [string]) |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
158 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
159 Correct for sentence endings buried in 'chunks'. Eg. when the |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
160 original text contains "... foo.\nBar ...", munge_whitespace() |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
161 and split() will convert that to [..., "foo.", " ", "Bar", ...] |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
162 which has one too few spaces; this method simply changes the one |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
163 space to two. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
164 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
165 i = 0 |
|
56368
c9bd62efe6ce
Merged revisions 75231 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents:
50157
diff
changeset
|
166 patsearch = self.sentence_end_re.search |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
167 while i < len(chunks)-1: |
|
56368
c9bd62efe6ce
Merged revisions 75231 via svnmerge from
Benjamin Peterson <benjamin@python.org>
parents:
50157
diff
changeset
|
168 if chunks[i+1] == " " and patsearch(chunks[i]): |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
169 chunks[i+1] = " " |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
170 i += 2 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
171 else: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
172 i += 1 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
173 |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
174 def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width): |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
175 """_handle_long_word(chunks : [string], |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
176 cur_line : [string], |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
177 cur_len : int, width : int) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
178 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
179 Handle a chunk of text (most likely a word, not whitespace) that |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
180 is too long to fit in any line. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
181 """ |
|
44782
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
182 # Figure out when indent is larger than the specified width, and make |
|
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
183 # sure at least one character is stripped off on every pass |
|
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
184 if width < 1: |
|
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
185 space_left = 1 |
|
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
186 else: |
|
ca2683a67943
Merged revisions 60080-60089,60091-60093 via svnmerge from
Georg Brandl <georg@python.org>
parents:
43144
diff
changeset
|
187 space_left = width - cur_len |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
188 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
189 # If we're allowed to break long words, then do so: put as much |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
190 # of the next chunk onto the current line as will fit. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
191 if self.break_long_words: |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
192 cur_line.append(reversed_chunks[-1][:space_left]) |
|
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
193 reversed_chunks[-1] = reversed_chunks[-1][space_left:] |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
194 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
195 # Otherwise, we have to preserve the long word intact. Only add |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
196 # it to the current line if there's nothing already there -- |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
197 # that minimizes how much we violate the width constraint. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
198 elif not cur_line: |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
199 cur_line.append(reversed_chunks.pop()) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
200 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
201 # If we're not allowed to break long words, and there's already |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
202 # text on the current line, do nothing. Next time through the |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
203 # main loop of _wrap_chunks(), we'll wind up here again, but |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
204 # cur_len will be zero, so the next line will be entirely |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
205 # devoted to the long word that we can't handle right now. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
206 |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
207 def _wrap_chunks(self, chunks): |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
208 """_wrap_chunks(chunks : [string]) -> [string] |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
209 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
210 Wrap a sequence of text chunks and return a list of lines of |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
211 length 'self.width' or less. (If 'break_long_words' is false, |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
212 some lines may be longer than this.) Chunks correspond roughly |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
213 to words and the whitespace between them: each chunk is |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
214 indivisible (modulo 'break_long_words'), but a line break can |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
215 come between any two chunks. Chunks should not have internal |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
216 whitespace; ie. a chunk is either all whitespace or a "word". |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
217 Whitespace chunks will be removed from the beginning and end of |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
218 lines, but apart from that whitespace is preserved. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
219 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
220 lines = [] |
|
29005
3055c9bdff5f
SF #726446: raise ValueError if width <= 0.
Greg Ward <gward@python.net>
parents:
27884
diff
changeset
|
221 if self.width <= 0: |
|
3055c9bdff5f
SF #726446: raise ValueError if width <= 0.
Greg Ward <gward@python.net>
parents:
27884
diff
changeset
|
222 raise ValueError("invalid width %r (must be > 0)" % self.width) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
223 |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
224 # Arrange in reverse order so items can be efficiently popped |
|
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
225 # from a stack of chucks. |
|
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
226 chunks.reverse() |
|
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
227 |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
228 while chunks: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
229 |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
230 # Start the list of chunks that will make up the current line. |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
231 # cur_len is just the length of all the chunks in cur_line. |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
232 cur_line = [] |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
233 cur_len = 0 |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
234 |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
235 # Figure out which static string will prefix this line. |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
236 if lines: |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
237 indent = self.subsequent_indent |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
238 else: |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
239 indent = self.initial_indent |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
240 |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
241 # Maximum width for this line. |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
242 width = self.width - len(indent) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
243 |
|
26580
d4b76817c9e6
Fix SF bug #622849: in _wrap_chunks(), ensure that leading whitespace in
Greg Ward <gward@python.net>
parents:
26579
diff
changeset
|
244 # First chunk on line is whitespace -- drop it, unless this |
|
d4b76817c9e6
Fix SF bug #622849: in _wrap_chunks(), ensure that leading whitespace in
Greg Ward <gward@python.net>
parents:
26579
diff
changeset
|
245 # is the very beginning of the text (ie. no lines started yet). |
|
41554
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
246 if self.drop_whitespace and chunks[-1].strip() == '' and lines: |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
247 del chunks[-1] |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
248 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
249 while chunks: |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
250 l = len(chunks[-1]) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
251 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
252 # Can at least squeeze this chunk onto the current line. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
253 if cur_len + l <= width: |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
254 cur_line.append(chunks.pop()) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
255 cur_len += l |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
256 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
257 # Nope, this line is full. |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
258 else: |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
259 break |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
260 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
261 # The current line is full, and the next chunk is too big to |
|
24263
e6033254df21
Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents:
24111
diff
changeset
|
262 # fit on *any* line (not just this one). |
|
35235
f9c5ae69c16e
textwrap now processes text chucks at O(n) speed instead of O(n**2).
Raymond Hettinger <python@rcn.com>
parents:
34691
diff
changeset
|
263 if chunks and len(chunks[-1]) > width: |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
264 self._handle_long_word(chunks, cur_line, cur_len, width) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
265 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
266 # If the last chunk on this line is all whitespace, drop it. |
|
41554
06145fbc7ab9
Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents:
40775
diff
changeset
|
267 if self.drop_whitespace and cur_line and cur_line[-1].strip() == '': |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
268 del cur_line[-1] |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
269 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
270 # Convert current line back to a string and store it in list |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
271 # of all lines (return value). |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
272 if cur_line: |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
273 lines.append(indent + ''.join(cur_line)) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
274 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
275 return lines |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
276 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
277 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
278 # -- Public interface ---------------------------------------------- |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
279 |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
280 def wrap(self, text): |
|
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
281 """wrap(text : string) -> [string] |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
282 |
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
283 Reformat the single paragraph in 'text' so it fits in lines of |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
284 no more than 'self.width' columns, and return a list of wrapped |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
285 lines. Tabs in 'text' are expanded with string.expandtabs(), |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
286 and all other whitespace characters (including newline) are |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
287 converted to space. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
288 """ |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
289 text = self._munge_whitespace(text) |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
290 chunks = self._split(text) |
|
23738
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
291 if self.fix_sentence_endings: |
|
a68d2466d94b
Add fix_sentence_endings option to control whether we ensure that
Greg Ward <gward@python.net>
parents:
23737
diff
changeset
|
292 self._fix_sentence_endings(chunks) |
|
23766
1cbcddca33b0
Make 'width' an instance attribute rather than an argument to the wrap()
Greg Ward <gward@python.net>
parents:
23744
diff
changeset
|
293 return self._wrap_chunks(chunks) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
294 |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
295 def fill(self, text): |
|
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
296 """fill(text : string) -> string |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
297 |
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
298 Reformat the single paragraph in 'text' to fit in lines of no |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
299 more than 'self.width' columns, and return a new string |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
300 containing the entire wrapped paragraph. |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
301 """ |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
302 return "\n".join(self.wrap(text)) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
303 |
|
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
304 |
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
305 # -- Convenience interface --------------------------------------------- |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
306 |
|
23767
5fb08d832eac
Allow the standalone wrap() and fill() functions to take arbitrary
Greg Ward <gward@python.net>
parents:
23766
diff
changeset
|
307 def wrap(text, width=70, **kwargs): |
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
308 """Wrap a single paragraph of text, returning a list of wrapped lines. |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
309 |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
310 Reformat the single paragraph in 'text' so it fits in lines of no |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
311 more than 'width' columns, and return a list of wrapped lines. By |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
312 default, tabs in 'text' are expanded with string.expandtabs(), and |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
313 all other whitespace characters (including newline) are converted to |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
314 space. See TextWrapper class for available keyword args to customize |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
315 wrapping behaviour. |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
316 """ |
|
23767
5fb08d832eac
Allow the standalone wrap() and fill() functions to take arbitrary
Greg Ward <gward@python.net>
parents:
23766
diff
changeset
|
317 w = TextWrapper(width=width, **kwargs) |
|
5fb08d832eac
Allow the standalone wrap() and fill() functions to take arbitrary
Greg Ward <gward@python.net>
parents:
23766
diff
changeset
|
318 return w.wrap(text) |
|
23737
df1a275ff4f2
Initial revision. Currently biased towards English in a fixed-width font,
Greg Ward <gward@python.net>
parents:
diff
changeset
|
319 |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
320 def fill(text, width=70, **kwargs): |
|
24111
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
321 """Fill a single paragraph of text, returning a new string. |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
322 |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
323 Reformat the single paragraph in 'text' to fit in lines of no more |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
324 than 'width' columns, and return a new string containing the entire |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
325 wrapped paragraph. As with wrap(), tabs are expanded and other |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
326 whitespace characters converted to space. See TextWrapper class for |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
327 available keyword args to customize wrapping behaviour. |
|
34d7137098a7
Docstring improvements. In particular, added docstrings for the
Greg Ward <gward@python.net>
parents:
23770
diff
changeset
|
328 """ |
|
23767
5fb08d832eac
Allow the standalone wrap() and fill() functions to take arbitrary
Greg Ward <gward@python.net>
parents:
23766
diff
changeset
|
329 w = TextWrapper(width=width, **kwargs) |
|
23770
f6b2719fbf11
Took initial_tab and subsequent_tab away from the fill() method and
Greg Ward <gward@python.net>
parents:
23767
diff
changeset
|
330 return w.fill(text) |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
331 |
|
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
332 |
|
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
333 # -- Loosely related functionality ------------------------------------- |
|
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
334 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
335 _whitespace_only_re = re.compile('^[ \t]+$', re.MULTILINE) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
336 _leading_whitespace_re = re.compile('(^[ \t]*)(?:[^ \t\n])', re.MULTILINE) |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
337 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
338 def dedent(text): |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
339 """Remove any common leading whitespace from every line in `text`. |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
340 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
341 This can be used to make triple-quoted strings line up with the left |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
342 edge of the display, while still presenting them in the source code |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
343 in indented form. |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
344 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
345 Note that tabs and spaces are both treated as whitespace, but they |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
346 are not equal: the lines " hello" and "\thello" are |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
347 considered to have no common leading whitespace. (This behaviour is |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
348 new in Python 2.5; older versions of this module incorrectly |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
349 expanded tabs before searching for common leading whitespace.) |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
350 """ |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
351 # Look for the longest leading string of spaces and tabs common to |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
352 # all lines. |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
353 margin = None |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
354 text = _whitespace_only_re.sub('', text) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
355 indents = _leading_whitespace_re.findall(text) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
356 for indent in indents: |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
357 if margin is None: |
|
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
358 margin = indent |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
359 |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
360 # Current line more deeply indented than previous winner: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
361 # no change (previous winner is still on top). |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
362 elif indent.startswith(margin): |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
363 pass |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
364 |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
365 # Current line consistent with and no deeper than previous winner: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
366 # it's the new winner. |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
367 elif margin.startswith(indent): |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
368 margin = indent |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
369 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
370 # Current line and previous winner have no common whitespace: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
371 # there is no margin. |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
372 else: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
373 margin = "" |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
374 break |
|
29022
2f743de8c5e2
SF patch #598163 (Ville Vainio, vvainio@users.sourceforge.net):
Greg Ward <gward@python.net>
parents:
29007
diff
changeset
|
375 |
|
39442
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
376 # sanity check (testing/debugging only) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
377 if 0 and margin: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
378 for line in text.split("\n"): |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
379 assert not line or line.startswith(margin), \ |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
380 "line = %r, margin = %r" % (line, margin) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
381 |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
382 if margin: |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
383 text = re.sub(r'(?m)^' + margin, '', text) |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
384 return text |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
385 |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
386 if __name__ == "__main__": |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
387 #print dedent("\tfoo\n\tbar") |
|
654c380cf8b9
Merged revisions 46753-51188 via svnmerge from
Thomas Wouters <thomas@python.org>
parents:
35235
diff
changeset
|
388 #print dedent(" \thello there\n \t how are you?") |
|
40775
4cdf21a0dbbc
Fix most trivially-findable print statements.
Guido van Rossum <guido@python.org>
parents:
39442
diff
changeset
|
389 print(dedent("Hello there.\n This is indented.")) |
