X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/5f92f5a341c58a30c0a5c0d64ba3ed498bb9db85..1f8cf8e0244045ed2b2a8efcff5d6db967ac2b11:/librarian/functions.py?ds=sidebyside diff --git a/librarian/functions.py b/librarian/functions.py index 659bb94..e5a47d6 100644 --- a/librarian/functions.py +++ b/librarian/functions.py @@ -3,12 +3,15 @@ # This file is part of Librarian, licensed under GNU Affero GPLv3 or later. # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # +from __future__ import unicode_literals + from lxml import etree import re from librarian.dcparser import Person from librarian import get_resource + def _register_function(f): """ Register extension function with lxml """ ns = etree.FunctionNamespace('http://wolnelektury.pl/functions') @@ -16,7 +19,7 @@ def _register_function(f): def reg_substitute_entities(): - ENTITY_SUBSTITUTIONS = [ + entity_substitutions = [ (u'---', u'—'), (u'--', u'–'), (u'...', u'…'), @@ -28,7 +31,7 @@ def reg_substitute_entities(): """XPath extension function converting all entites in passed text.""" if isinstance(text, list): text = ''.join(text) - for entity, substitutution in ENTITY_SUBSTITUTIONS: + for entity, substitutution in entity_substitutions: text = text.replace(entity, substitutution) return text @@ -103,22 +106,23 @@ def reg_texcommand(): 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) + 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.read().decode('latin1').split('\n'): + list = line.strip().split('|') + if list[0] == text: + result = list[2] + if result == '': + return text + else: + return result + _register_function(lang_code_3to2) def mathml_latex(context, trees): @@ -128,11 +132,14 @@ def mathml_latex(context, trees): text = text.replace(u'\u2062', '') return text + def reg_mathml_latex(): _register_function(mathml_latex) + def reg_mathml_epub(zipf): from librarian.embeds.mathml import MathML + def mathml(context, trees): data = MathML(trees[0]).to_latex().to_png().data name = "math%d.png" % mathml.count @@ -141,4 +148,3 @@ def reg_mathml_epub(zipf): return name mathml.count = 0 _register_function(mathml) -