summaryrefslogtreecommitdiffstats
path: root/Lib
diff options
context:
space:
mode:
authorGreg Ward <gward@python.net>2002-06-07 21:56:16 (GMT)
committerGreg Ward <gward@python.net>2002-06-07 21:56:16 (GMT)
commit62e4f3bf224d6a3a17c04524a674caaa14270753 (patch)
tree9f3bb8d87941c55308f4a435aaeb762f89c08844 /Lib
parent00935824898a826f2dd6c65933667445075cdb2e (diff)
downloadcpython-62e4f3bf224d6a3a17c04524a674caaa14270753.zip
cpython-62e4f3bf224d6a3a17c04524a674caaa14270753.tar.gz
cpython-62e4f3bf224d6a3a17c04524a674caaa14270753.tar.bz2
Add fix_sentence_endings option to control whether we ensure that
sentences are separated by two spaces. Improve _fix_sentence_endings() a bit -- look for ".!?" instead of just ".", and factor out the list of sentence-ending punctuation characters to a class attribute.
Diffstat (limited to 'Lib')
-rw-r--r--Lib/textwrap.py41
1 files changed, 25 insertions, 16 deletions
diff --git a/Lib/textwrap.py b/Lib/textwrap.py
index 355c469..ef6c372 100644
--- a/Lib/textwrap.py
+++ b/Lib/textwrap.py
@@ -22,20 +22,23 @@ class TextWrapper:
Several instance attributes control various aspects of
wrapping:
- expand_tabs
- if true (default), tabs in input text will be expanded
- 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
- if true (default), all whitespace characters in the input
- text are replaced by spaces after tab expansion. Note
- that expand_tabs is false and replace_whitespace is true,
- every tab will be converted to a single space!
- break_long_words
- if true (default), words longer than the line width constraint
- will be broken. If false, those words will not be broken,
- and some lines might be longer than the width constraint.
+ 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 becaus the algorithm is
+ (unavoidably) imperfect.
+ break_long_words (default: true)
+ Break words longer than the line width constraint. If false,
+ those words will not be broken, and some lines might be longer
+ than the width constraint.
"""
whitespace_trans = string.maketrans(string.whitespace,
@@ -51,10 +54,14 @@ class TextWrapper:
r'\w{2,}-(?=\w{2,})|' # hyphenated words
r'(?<=\w)-{2,}(?=\w))') # em-dash
+ # Punctuation characters found at the end of a sentence.
+ sentence_end = ".?!"
+
def __init__ (self):
self.expand_tabs = 1
self.replace_whitespace = 1
+ self.fix_sentence_endings = 0
self.break_long_words = 1
@@ -100,10 +107,11 @@ class TextWrapper:
space to two.
"""
i = 0
+ punct = self.sentence_end
while i < len(chunks)-1:
# chunks[i] looks like the last word of a sentence,
# and it's followed by a single space.
- if (chunks[i][-1] == "." and
+ if (chunks[i][-1] in punct and
chunks[i+1] == " " and
islower(chunks[i][-2])):
chunks[i+1] = " "
@@ -207,7 +215,8 @@ class TextWrapper:
if len(text) <= width:
return [text]
chunks = self._split(text)
- self._fix_sentence_endings(chunks)
+ if self.fix_sentence_endings:
+ self._fix_sentence_endings(chunks)
return self._wrap_chunks(chunks, width)
def fill (self, text, width, initial_tab="", subsequent_tab=""):