import re
from librarian.dcparser import Person
+from librarian import get_resource
def _register_function(f):
""" Register extension function with lxml """
ns[f.__name__] = f
-def reg_substitute_entities():
+def reg_substitute_entities():
ENTITY_SUBSTITUTIONS = [
(u'---', u'—'),
(u'--', u'–'),
""" Converts "Name, Forename" to "Forename Name" """
if isinstance(text, list):
text = ''.join(text)
- p = Person.from_text(text)
- return ' '.join(p.first_names + (p.last_name,))
+ return Person.from_text(text).readable()
_register_function(person_name)
+def reg_texcommand():
+ def texcommand(context, text):
+ """Remove non-letters"""
+ if isinstance(text, list):
+ text = ''.join(text)
+ return re.sub(r'[^a-zA-Z]', '', text).strip()
+ _register_function(texcommand)
+
+def reg_lang_code_3to2():
+ def lang_code_3to2(context, text):
+ """Convert 3-letter language code to 2-letter code"""
+ result = ''
+ text = ''.join(text)
+ with open(get_resource('res/ISO-639-2_8859-1.txt'), 'rb') as f:
+ for line in f:
+ list = line.strip().split('|')
+ if list[0] == text:
+ result=list[2]
+ if result == '':
+ return text
+ else:
+ return result
+ _register_function(lang_code_3to2)
+
+