Created
August 3, 2015 18:19
-
-
Save bsmithgall/3a94e0cbce94e56831dc to your computer and use it in GitHub Desktop.
python titlecase filter for jinja
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# modified from https://gist.github.com/bsmithgall/372de43205804a2279c9 | |
SMALL_WORDS = re.compile(r'^(a|an|and|as|at|but|by|en|etc|for|if|in|nor|of|on|or|per|the|to|vs?\.?|via)$', re.I) | |
SPACE_SPLIT = re.compile(r'[\t ]') | |
# taken from http://stackoverflow.com/a/267405 | |
CAP_WORDS = re.compile(r'^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$') | |
PUNC_REGEX = re.compile(r'[{}]'.format(re.escape(string.punctuation))) | |
# taken from python-titlecase: https://github.com/ppannuto/python-titlecase/blob/master/titlecase/__init__.py#L27 | |
UC_INITIALS = re.compile(r'^(?:[A-Z]{1}\.{1}|[A-Z]{1}\.{1}[A-Z]{1})+$', re.I) | |
def better_title(string): | |
'''drop in replacement for jinja default title filter | |
modified from https://gist.github.com/bsmithgall/372de43205804a2279c9 | |
''' | |
rv = [] | |
for word in re.split(SPACE_SPLIT, string): | |
_cleaned_word = PUNC_REGEX.sub('', word) | |
if re.match(UC_INITIALS, word): | |
rv.append(word.upper()) | |
elif re.match(SMALL_WORDS, _cleaned_word.strip()): | |
rv.append(word.lower()) | |
elif word.startswith('('): | |
new_string = '(' | |
new_string += better_title(word.lstrip('(')) | |
rv.append(new_string) | |
elif re.match(CAP_WORDS, _cleaned_word): | |
rv.append(word.upper()) | |
else: | |
rv.append(word[0].upper() + word[1:].lower()) | |
return ' '.join(rv) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment