145 lines
4.7 KiB
Python
145 lines
4.7 KiB
Python
import re
|
|
|
|
from django.conf import settings
|
|
|
|
# Capitalizes the first letter of a string.
|
|
capfirst = lambda x: x and x[0].upper() + x[1:]
|
|
|
|
def wrap(text, width):
|
|
"""
|
|
A word-wrap function that preserves existing line breaks and most spaces in
|
|
the text. Expects that existing line breaks are posix newlines.
|
|
"""
|
|
def _generator():
|
|
it = iter(text.split(' '))
|
|
word = it.next()
|
|
yield word
|
|
pos = len(word) - word.rfind('\n') - 1
|
|
for word in it:
|
|
if "\n" in word:
|
|
lines = word.splitlines()
|
|
else:
|
|
lines = (word,)
|
|
pos += len(lines[0]) + 1
|
|
if pos > width:
|
|
yield '\n'
|
|
pos = len(lines[-1])
|
|
else:
|
|
yield ' '
|
|
if len(lines) > 1:
|
|
pos = len(lines[-1])
|
|
yield word
|
|
return "".join(_generator())
|
|
|
|
def truncate_words(s, num):
|
|
"Truncates a string after a certain number of words."
|
|
length = int(num)
|
|
words = s.split()
|
|
if len(words) > length:
|
|
words = words[:length]
|
|
if not words[-1].endswith('...'):
|
|
words.append('...')
|
|
return ' '.join(words)
|
|
|
|
def get_valid_filename(s):
|
|
"""
|
|
Returns the given string converted to a string that can be used for a clean
|
|
filename. Specifically, leading and trailing spaces are removed; other
|
|
spaces are converted to underscores; and all non-filename-safe characters
|
|
are removed.
|
|
>>> get_valid_filename("john's portrait in 2004.jpg")
|
|
'johns_portrait_in_2004.jpg'
|
|
"""
|
|
s = s.strip().replace(' ', '_')
|
|
return re.sub(r'[^-A-Za-z0-9_.]', '', s)
|
|
|
|
def get_text_list(list_, last_word='or'):
|
|
"""
|
|
>>> get_text_list(['a', 'b', 'c', 'd'])
|
|
'a, b, c or d'
|
|
>>> get_text_list(['a', 'b', 'c'], 'and')
|
|
'a, b and c'
|
|
>>> get_text_list(['a', 'b'], 'and')
|
|
'a and b'
|
|
>>> get_text_list(['a'])
|
|
'a'
|
|
>>> get_text_list([])
|
|
''
|
|
"""
|
|
if len(list_) == 0: return ''
|
|
if len(list_) == 1: return list_[0]
|
|
return '%s %s %s' % (', '.join([str(i) for i in list_][:-1]), last_word, list_[-1])
|
|
|
|
def normalize_newlines(text):
|
|
return re.sub(r'\r\n|\r|\n', '\n', text)
|
|
|
|
def recapitalize(text):
|
|
"Recapitalizes text, placing caps after end-of-sentence punctuation."
|
|
# capwords = ()
|
|
text = text.lower()
|
|
capsRE = re.compile(r'(?:^|(?<=[\.\?\!] ))([a-z])')
|
|
text = capsRE.sub(lambda x: x.group(1).upper(), text)
|
|
# for capword in capwords:
|
|
# capwordRE = re.compile(r'\b%s\b' % capword, re.I)
|
|
# text = capwordRE.sub(capword, text)
|
|
return text
|
|
|
|
def phone2numeric(phone):
|
|
"Converts a phone number with letters into its numeric equivalent."
|
|
letters = re.compile(r'[A-PR-Y]', re.I)
|
|
char2number = lambda m: {'a': '2', 'c': '2', 'b': '2', 'e': '3',
|
|
'd': '3', 'g': '4', 'f': '3', 'i': '4', 'h': '4', 'k': '5',
|
|
'j': '5', 'm': '6', 'l': '5', 'o': '6', 'n': '6', 'p': '7',
|
|
's': '7', 'r': '7', 'u': '8', 't': '8', 'w': '9', 'v': '8',
|
|
'y': '9', 'x': '9'}.get(m.group(0).lower())
|
|
return letters.sub(char2number, phone)
|
|
|
|
# From http://www.xhaus.com/alan/python/httpcomp.html#gzip
|
|
# Used with permission.
|
|
def compress_string(s):
|
|
import cStringIO, gzip
|
|
zbuf = cStringIO.StringIO()
|
|
zfile = gzip.GzipFile(mode='wb', compresslevel=6, fileobj=zbuf)
|
|
zfile.write(s)
|
|
zfile.close()
|
|
return zbuf.getvalue()
|
|
|
|
ustring_re = re.compile(u"([\u0080-\uffff])")
|
|
|
|
def javascript_quote(s, quote_double_quotes=False):
|
|
|
|
def fix(match):
|
|
return r"\u%04x" % ord(match.group(1))
|
|
|
|
if type(s) == str:
|
|
s = s.decode(settings.DEFAULT_CHARSET)
|
|
elif type(s) != unicode:
|
|
raise TypeError, s
|
|
s = s.replace('\\', '\\\\')
|
|
s = s.replace('\r', '\\r')
|
|
s = s.replace('\n', '\\n')
|
|
s = s.replace('\t', '\\t')
|
|
s = s.replace("'", "\\'")
|
|
if quote_double_quotes:
|
|
s = s.replace('"', '"')
|
|
return str(ustring_re.sub(fix, s))
|
|
|
|
smart_split_re = re.compile('("(?:[^"\\\\]*(?:\\\\.[^"\\\\]*)*)"|\'(?:[^\'\\\\]*(?:\\\\.[^\'\\\\]*)*)\'|[^\\s]+)')
|
|
def smart_split(text):
|
|
"""
|
|
Generator that splits a string by spaces, leaving quoted phrases together.
|
|
Supports both single and double quotes, and supports escaping quotes with
|
|
backslashes. In the output, strings will keep their initial and trailing
|
|
quote marks.
|
|
>>> list(smart_split('This is "a person\'s" test.'))
|
|
['This', 'is', '"a person\'s"', 'test.']
|
|
"""
|
|
for bit in smart_split_re.finditer(text):
|
|
bit = bit.group(0)
|
|
if bit[0] == '"':
|
|
yield '"' + bit[1:-1].replace('\\"', '"').replace('\\\\', '\\') + '"'
|
|
elif bit[0] == "'":
|
|
yield "'" + bit[1:-1].replace("\\'", "'").replace("\\\\", "\\") + "'"
|
|
else:
|
|
yield bit
|