1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
|
# -*- test-case-name: twisted.test.test_text -*-
#
# Copyright (c) Twisted Matrix Laboratories.
# See LICENSE for details.
"""
Miscellany of text-munging functions.
"""
def stringyString(object, indentation=''):
"""
Expansive string formatting for sequence types.
C{list.__str__} and C{dict.__str__} use C{repr()} to display their
elements. This function also turns these sequence types
into strings, but uses C{str()} on their elements instead.
Sequence elements are also displayed on seperate lines, and nested
sequences have nested indentation.
"""
braces = ''
sl = []
if type(object) is dict:
braces = '{}'
for key, value in object.items():
value = stringyString(value, indentation + ' ')
if isMultiline(value):
if endsInNewline(value):
value = value[:-len('\n')]
sl.append("%s %s:\n%s" % (indentation, key, value))
else:
# Oops. Will have to move that indentation.
sl.append("%s %s: %s" % (indentation, key,
value[len(indentation) + 3:]))
elif type(object) is tuple or type(object) is list:
if type(object) is tuple:
braces = '()'
else:
braces = '[]'
for element in object:
element = stringyString(element, indentation + ' ')
sl.append(element.rstrip() + ',')
else:
sl[:] = map(lambda s, i=indentation: i + s,
str(object).split('\n'))
if not sl:
sl.append(indentation)
if braces:
sl[0] = indentation + braces[0] + sl[0][len(indentation) + 1:]
sl[-1] = sl[-1] + braces[-1]
s = "\n".join(sl)
if isMultiline(s) and not endsInNewline(s):
s = s + '\n'
return s
def isMultiline(s):
"""
Returns C{True} if this string has a newline in it.
"""
return (s.find('\n') != -1)
def endsInNewline(s):
"""
Returns C{True} if this string ends in a newline.
"""
return (s[-len('\n'):] == '\n')
def greedyWrap(inString, width=80):
"""
Given a string and a column width, return a list of lines.
Caveat: I'm use a stupid greedy word-wrapping
algorythm. I won't put two spaces at the end
of a sentence. I don't do full justification.
And no, I've never even *heard* of hypenation.
"""
outLines = []
#eww, evil hacks to allow paragraphs delimited by two \ns :(
if inString.find('\n\n') >= 0:
paragraphs = inString.split('\n\n')
for para in paragraphs:
outLines.extend(greedyWrap(para, width) + [''])
return outLines
inWords = inString.split()
column = 0
ptr_line = 0
while inWords:
column = column + len(inWords[ptr_line])
ptr_line = ptr_line + 1
if (column > width):
if ptr_line == 1:
# This single word is too long, it will be the whole line.
pass
else:
# We've gone too far, stop the line one word back.
ptr_line = ptr_line - 1
(l, inWords) = (inWords[0:ptr_line], inWords[ptr_line:])
outLines.append(' '.join(l))
ptr_line = 0
column = 0
elif not (len(inWords) > ptr_line):
# Clean up the last bit.
outLines.append(' '.join(inWords))
del inWords[:]
else:
# Space
column = column + 1
# next word
return outLines
wordWrap = greedyWrap
def removeLeadingBlanks(lines):
ret = []
for line in lines:
if ret or line.strip():
ret.append(line)
return ret
def removeLeadingTrailingBlanks(s):
lines = removeLeadingBlanks(s.split('\n'))
lines.reverse()
lines = removeLeadingBlanks(lines)
lines.reverse()
return '\n'.join(lines)+'\n'
def splitQuoted(s):
"""
Like a string split, but don't break substrings inside quotes.
>>> splitQuoted('the "hairy monkey" likes pie')
['the', 'hairy monkey', 'likes', 'pie']
Another one of those "someone must have a better solution for
this" things. This implementation is a VERY DUMB hack done too
quickly.
"""
out = []
quot = None
phrase = None
for word in s.split():
if phrase is None:
if word and (word[0] in ("\"", "'")):
quot = word[0]
word = word[1:]
phrase = []
if phrase is None:
out.append(word)
else:
if word and (word[-1] == quot):
word = word[:-1]
phrase.append(word)
out.append(" ".join(phrase))
phrase = None
else:
phrase.append(word)
return out
def strFile(p, f, caseSensitive=True):
"""
Find whether string C{p} occurs in a read()able object C{f}.
@rtype: C{bool}
"""
buf = ""
buf_len = max(len(p), 2**2**2**2)
if not caseSensitive:
p = p.lower()
while 1:
r = f.read(buf_len-len(p))
if not caseSensitive:
r = r.lower()
bytes_read = len(r)
if bytes_read == 0:
return False
l = len(buf)+bytes_read-buf_len
if l <= 0:
buf = buf + r
else:
buf = buf[l:] + r
if buf.find(p) != -1:
return True
|