文章目錄
- 1 問題
- 2. 解決方案
- 3. 討論
- 4. 拓展
現有一個特別長的字符串，你希望對字符串進行重新格式化，以使其根據制定的寬度進行顯示。
對此，可以使用 textwrap 模塊來對輸出進行重新格式化。例如，你有以下長字符串：
s = "Look into my eyes, look into my eyes, the eyes, the eyes, \
the eyes, not around the eyes, don't look around the eyes, \
look into my eyes, you're under."
使用 textwrap 模塊，你可以實現如下效果：
>>> import textwrap
>>> print(textwrap.fill(s, 70))
Look into my eyes, look into my eyes, the eyes, the eyes, the eyes,
not around the eyes, don't look around the eyes, look into my eyes,
you're under.
>>> print(textwrap.fill(s, 40))
Look into my eyes, look into my eyes,
the eyes, the eyes, the eyes, not around
the eyes, don't look around the eyes,
look into my eyes, you're under.
>>> print(textwrap.fill(s, 40, initial_indent=' ')) # 首行縮進
Look into my eyes, look into my
eyes, the eyes, the eyes, the eyes, not
around the eyes, don't look around the
eyes, look into my eyes, you're under.
>>> print(textwrap.fill(s, 40, subsequent_indent=' ')) # 除首行外其他行縮進
Look into my eyes, look into my eyes,
the eyes, the eyes, the eyes, not
around the eyes, don't look around
the eyes, look into my eyes, you're
under.
textwrap 模塊還可以根據終端的實際大小對輸出文本進行適應性調整，如果希望實現這樣的效果，可以先使用下列方式獲取終端尺寸：
PS D:\MyCode\ProgrammingPython> python
Python 3.8.9 (tags/v3.8.9:a743f81, Apr 6 2021, 14:02:34) [MSC v.1928 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>>
>>> import os
>>> os.get_terminal_size()
os.terminal_size(columns=235, lines=21)
>>> os.get_terminal_size().columns
235
>>> os.get_terminal_size().columns
119
>>> os.get_terminal_size().columns
106
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 0 .. 'tabsize' spaces, depending on its position in its line. If false, each tab is treated as a single character. tabsize (default: 8) Expand tabs in input text to 0 .. 'tabsize' spaces, unless 'expand_tabs' is false. 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. max_lines (default: None) Truncate wrapped lines. placeholder (default: ' [...]') Append to the last line of truncated text. """
unicode_whitespace_trans = {
}
uspace = ord(' ')
for x in _whitespace:
unicode_whitespace_trans[ord(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).
word_punct = r'[\w!"\'&.,?]'
letter = r'[^\d\W]'
whitespace = r'[%s]' % re.escape(_whitespace)
nowhitespace = '[^' + whitespace[1:]
wordsep_re = re.compile(r''' ( # any whitespace %(ws)s+ | # em-dash between words (?<=%(wp)s) -{2,} (?=\w) | # word, possibly hyphenated %(nws)s+? (?: # hyphenated word -(?: (?<=%(lt)s{2}-) | (?<=%(lt)s-%(lt)s-)) (?= %(lt)s -? %(lt)s) | # end of word (?=%(ws)s|\Z) | # em-dash (?<=%(wp)s) (?=-{2,}\w) ) )''' % {
'wp': word_punct, 'lt': letter,
'ws': whitespace, 'nws': nowhitespace},
re.VERBOSE)
del word_punct, letter, nowhitespace
# This less funky little regex just split on recognized spaces. E.g.
# "Hello there -- you goof-ball, use the -b option!"
# splits into
# Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/
wordsep_simple_re = re.compile(r'(%s+)' % whitespace)
del whitespace
# XXX this is not locale- or charset-aware -- string.lowercase
# is US-ASCII only (and therefore English-only)
sentence_end_re = re.compile(r'[a-z]' # lowercase letter
r'[\.\!\?]' # sentence-ending punct.
r'[\"\']?' # optional end-of-quote
r'\Z') # end of chunk
def __init__(self,
width=70,
initial_indent="",
subsequent_indent="",
expand_tabs=True,
replace_whitespace=True,
fix_sentence_endings=False,
break_long_words=True,
drop_whitespace=True,
break_on_hyphens=True,
tabsize=8,
*,
max_lines=None,
placeholder=' [...]'):
self.width = width
self.initial_indent = initial_indent
self.subsequent_indent = subsequent_indent
self.expand_tabs = expand_tabs
self.replace_whitespace = replace_whitespace
self.fix_sentence_endings = fix_sentence_endings
self.break_long_words = break_long_words
self.drop_whitespace = drop_whitespace
self.break_on_hyphens = break_on_hyphens
self.tabsize = tabsize
self.max_lines = max_lines
self.placeholder = placeholder
# -- Private methods -----------------------------------------------
# (possibly useful for subclasses to override)
def _munge_whitespace(self, text):
"""_munge_whitespace(text : string) -> string Munge whitespace in text: expand tabs and convert all other whitespace characters to spaces. Eg. " foo\\tbar\\n\\nbaz" becomes " foo bar baz". """
if self.expand_tabs:
text = text.expandtabs(self.tabsize)
if self.replace_whitespace:
text = text.translate(self.unicode_whitespace_trans)
return text
def _split(self, text):
"""_split(text : string) -> [string] Split the text to wrap into indivisible chunks. Chunks are not quite the same as words; see _wrap_chunks() for full details. As an example, the text Look, goof-ball -- use the -b option! breaks into the following chunks: 'Look,', ' ', 'goof-', 'ball', ' ', '--', ' ', 'use', ' ', 'the', ' ', '-b', ' ', 'option!' if break_on_hyphens is True, or in: 'Look,', ' ', 'goof-ball', ' ', '--', ' ', 'use', ' ', 'the', ' ', '-b', ' ', option!' otherwise. """
if self.break_on_hyphens is True:
chunks = self.wordsep_re.split(text)
else:
chunks = self.wordsep_simple_re.split(text)
chunks = [c for c in chunks if c]
return chunks
def _fix_sentence_endings(self, chunks):
"""_fix_sentence_endings(chunks : [string]) Correct for sentence endings buried in 'chunks'. Eg. when the original text contains "... foo.\\nBar ...", munge_whitespace() and split() will convert that to [..., "foo.", " ", "Bar", ...] which has one too few spaces; this method simply changes the one space to two. """
i = 0
patsearch = self.sentence_end_re.search
while i < len(chunks)-1:
if chunks[i+1] == " " and patsearch(chunks[i]):
chunks[i+1] = " "
i += 2
else:
i += 1
def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
"""_handle_long_word(chunks : [string], cur_line : [string], cur_len : int, width : int) Handle a chunk of text (most likely a word, not whitespace) that is too long to fit in any line. """
# Figure out when indent is larger than the specified width, and make
# sure at least one character is stripped off on every pass
if width < 1:
space_left = 1
else:
space_left = width - cur_len
# If we're allowed to break long words, then do so: put as much
# of the next chunk onto the current line as will fit.
if self.break_long_words:
cur_line.append(reversed_chunks[-1][:space_left])
reversed_chunks[-1] = reversed_chunks[-1][space_left:]
# Otherwise, we have to preserve the long word intact. Only add
# it to the current line if there's nothing already there --
# that minimizes how much we violate the width constraint.
elif not cur_line:
cur_line.append(reversed_chunks.pop())
# If we're not allowed to break long words, and there's already
# text on the current line, do nothing. Next time through the
# main loop of _wrap_chunks(), we'll wind up here again, but
# cur_len will be zero, so the next line will be entirely
# devoted to the long word that we can't handle right now.
def _wrap_chunks(self, chunks):
"""_wrap_chunks(chunks : [string]) -> [string] Wrap a sequence of text chunks and return a list of lines of length 'self.width' or less. (If 'break_long_words' is false, some lines may be longer than this.) Chunks correspond roughly to words and the whitespace between them: each chunk is indivisible (modulo 'break_long_words'), but a line break can come between any two chunks. Chunks should not have internal whitespace; ie. a chunk is either all whitespace or a "word". Whitespace chunks will be removed from the beginning and end of lines, but apart from that whitespace is preserved. """
lines = []
if self.width <= 0:
raise ValueError("invalid width %r (must be > 0)" % self.width)
if self.max_lines is not None:
if self.max_lines > 1:
indent = self.subsequent_indent
else:
indent = self.initial_indent
if len(indent) + len(self.placeholder.lstrip()) > self.width:
raise ValueError("placeholder too large for max width")
# Arrange in reverse order so items can be efficiently popped
# from a stack of chucks.
chunks.reverse()
while chunks:
# Start the list of chunks that will make up the current line.
# cur_len is just the length of all the chunks in cur_line.
cur_line = []
cur_len = 0
# Figure out which static string will prefix this line.
if lines:
indent = self.subsequent_indent
else:
indent = self.initial_indent
# Maximum width for this line.
width = self.width - len(indent)
# First chunk on line is whitespace -- drop it, unless this
# is the very beginning of the text (ie. no lines started yet).
if self.drop_whitespace and chunks[-1].strip() == '' and lines:
del chunks[-1]
while chunks:
l = len(chunks[-1])
# Can at least squeeze this chunk onto the current line.
if cur_len + l <= width:
cur_line.append(chunks.pop())
cur_len += l
# Nope, this line is full.
else:
break
# The current line is full, and the next chunk is too big to
# fit on *any* line (not just this one).
if chunks and len(chunks[-1]) > width:
self._handle_long_word(chunks, cur_line, cur_len, width)
cur_len = sum(map(len, cur_line))
# If the last chunk on this line is all whitespace, drop it.
if self.drop_whitespace and cur_line and cur_line[-1].strip() == '':
cur_len -= len(cur_line[-1])
del cur_line[-1]
if cur_line:
if (self.max_lines is None or
len(lines) + 1 < self.max_lines or
(not chunks or
self.drop_whitespace and
len(chunks) == 1 and
not chunks[0].strip()) and cur_len <= width):
# Convert current line back to a string and store it in
# list of all lines (return value).
lines.append(indent + ''.join(cur_line))
else:
while cur_line:
if (cur_line[-1].strip() and
cur_len + len(self.placeholder) <= width):
cur_line.append(self.placeholder)
lines.append(indent + ''.join(cur_line))
break
cur_len -= len(cur_line[-1])
del cur_line[-1]
else:
if lines:
prev_line = lines[-1].rstrip()
if (len(prev_line) + len(self.placeholder) <=
self.width):
lines[-1] = prev_line + self.placeholder
break
lines.append(indent + self.placeholder.lstrip())
break
return lines
def _split_chunks(self, text):
text = self._munge_whitespace(text)
return self._split(text)
# -- Public interface ----------------------------------------------
def wrap(self, text):
"""wrap(text : string) -> [string] Reformat the single paragraph in 'text' so it fits in lines of no more than 'self.width' columns, and return a list of wrapped lines. Tabs in 'text' are expanded with string.expandtabs(), and all other whitespace characters (including newline) are converted to space. """
chunks = self._split_chunks(text)
if self.fix_sentence_endings:
self._fix_sentence_endings(chunks)
return self._wrap_chunks(chunks)
def fill(self, text):
"""fill(text : string) -> string Reformat the single paragraph in 'text' to fit in lines of no more than 'self.width' columns, and return a new string containing the entire wrapped paragraph. """
return "\n".join(self.wrap(text))
gs:
self._fix_sentence_endings(chunks)
return self._wrap_chunks(chunks)
def fill(self, text):
"""fill(text : string) -> string
Reformat the single paragraph in 'text' to fit in lines of no
more than 'self.width' columns, and return a new string
containing the entire wrapped paragraph.
"""
return "\n".join(self.wrap(text))
