X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/f8e5f031c04122d65d1066077be3920ae95518ae..01e9eecd54a34ddfc82f4092377f7b6cdcfadc31:/librarian/text.py diff --git a/librarian/text.py b/librarian/text.py index 972dd61..cfe4a4d 100644 --- a/librarian/text.py +++ b/librarian/text.py @@ -1,4 +1,8 @@ # -*- coding: utf-8 -*- +# +# This file is part of Librarian, licensed under GNU Affero GPLv3 or later. +# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. +# from librarian import dcparser, parser from lxml import etree import cStringIO @@ -54,9 +58,9 @@ def wrap_words(context, text, wrapping): text = ''.join(text) if not wrapping: return text - + words = re.split(r'\s', text) - + line_length = 0 lines = [[]] for word in words: @@ -79,7 +83,7 @@ ns['wrap_words'] = wrap_words def transform(input_filename, output_filename, is_file=True, parse_dublincore=True, **options): """Transforms file input_filename in XML to output_filename in TXT.""" # Parse XSLT - style_filename = os.path.join(os.path.dirname(__file__), 'book2txt.xslt') + style_filename = os.path.join(os.path.dirname(__file__), 'xslt/book2txt.xslt') style = etree.parse(style_filename) if is_file: @@ -90,7 +94,7 @@ def transform(input_filename, output_filename, is_file=True, parse_dublincore=Tr result = document.transform(style, **options) output_file = codecs.open(output_filename, 'wb', encoding='utf-8') - + if parse_dublincore: url = dcparser.parse(input_filename).url else: