/usr/lib/python3/dist-packages/typogrify/packages/titlecase/__init__.py is in python3-typogrify 1:2.0.7-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #!/usr/bin/env python
# -*- coding: utf-8 -*-
# titlecase v0.5.1
# Copyright (C) 2008-2010, Stuart Colville.
# https://pypi.python.org/pypi/titlecase
"""
Original Perl version by: John Gruber http://daringfireball.net/ 10 May 2008
Python version by Stuart Colville http://muffinresearch.co.uk
License: http://www.opensource.org/licenses/mit-license.php
"""
import re
__all__ = ['titlecase']
__version__ = '0.5.1'
SMALL = 'a|an|and|as|at|but|by|en|for|if|in|of|on|or|the|to|v\.?|via|vs\.?'
PUNCT = r"""!"#$%&'‘()*+,\-./:;?@[\\\]_`{|}~"""
SMALL_WORDS = re.compile(r'^(%s)$' % SMALL, re.I)
INLINE_PERIOD = re.compile(r'[a-z][.][a-z]', re.I)
UC_ELSEWHERE = re.compile(r'[%s]*?[a-zA-Z]+[A-Z]+?' % PUNCT)
CAPFIRST = re.compile(r"^[%s]*?([A-Za-z])" % PUNCT)
SMALL_FIRST = re.compile(r'^([%s]*)(%s)\b' % (PUNCT, SMALL), re.I)
SMALL_LAST = re.compile(r'\b(%s)[%s]?$' % (SMALL, PUNCT), re.I)
SUBPHRASE = re.compile(r'([:.;?!][ ])(%s)' % SMALL)
APOS_SECOND = re.compile(r"^[dol]{1}['‘]{1}[a-z]+$", re.I)
ALL_CAPS = re.compile(r'^[A-Z\s%s]+$' % PUNCT)
UC_INITIALS = re.compile(r"^(?:[A-Z]{1}\.{1}|[A-Z]{1}\.{1}[A-Z]{1})+$")
MAC_MC = re.compile(r"^([Mm]a?c)(\w+)")
def titlecase(text):
"""
Titlecases input text
This filter changes all words to Title Caps, and attempts to be clever
about *un*capitalizing SMALL words like a/an/the in the input.
The list of "SMALL words" which are not capped comes from
the New York Times Manual of Style, plus 'vs' and 'v'.
"""
lines = re.split('[\r\n]+', text)
processed = []
for line in lines:
all_caps = ALL_CAPS.match(line)
words = re.split('[\t ]', line)
tc_line = []
for word in words:
if all_caps:
if UC_INITIALS.match(word):
tc_line.append(word)
continue
else:
word = word.lower()
if APOS_SECOND.match(word):
word = word.replace(word[0], word[0].upper())
word = word.replace(word[2], word[2].upper())
tc_line.append(word)
continue
if INLINE_PERIOD.search(word) or UC_ELSEWHERE.match(word):
tc_line.append(word)
continue
if SMALL_WORDS.match(word):
tc_line.append(word.lower())
continue
match = MAC_MC.match(word)
if match:
tc_line.append("%s%s" % (match.group(1).capitalize(),
match.group(2).capitalize()))
continue
hyphenated = []
for item in word.split('-'):
hyphenated.append(CAPFIRST.sub(lambda m: m.group(0).upper(), item))
tc_line.append("-".join(hyphenated))
result = " ".join(tc_line)
result = SMALL_FIRST.sub(lambda m: '%s%s' % (
m.group(1),
m.group(2).capitalize()
), result)
result = SMALL_LAST.sub(lambda m: m.group(0).capitalize(), result)
result = SUBPHRASE.sub(lambda m: '%s%s' % (
m.group(1),
m.group(2).capitalize()
), result)
processed.append(result)
return "\n".join(processed)
|