Minor fixed to README.

[librarian.git] / librarian / text.py

diff --git a/librarian/text.py b/librarian/text.py
index 0754a99..70d98c4 100644 (file)
--- a/librarian/text.py
+++ b/librarian/text.py
@@ -1,12 +1,30 @@
 # -*- coding: utf-8 -*-
-import os
+#
+#    This file is part of Librarian.
+#
+#    Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska <fundacja@nowoczesnapolska.org.pl>
+#    
+#    For full list of contributors see AUTHORS file. 
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU Affero General Public License as published by
+#    the Free Software Foundation, either version 3 of the License, or
+#    (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+from librarian import dcparser, parser
+from lxml import etree
 import cStringIO
-import re
 import codecs
-
-from lxml import etree
-
-from librarian import dcparser
+import os
+import re
 
 
 ENTITY_SUBSTITUTIONS = [
@@ -78,22 +96,27 @@ ns['substitute_entities'] = substitute_entities
 ns['wrap_words'] = wrap_words
 
 
-def transform(input_filename, output_filename, **options):
+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:
-        document = WLDocument.from_file(input, True)
+        document = parser.WLDocument.from_file(input_filename, True, parse_dublincore=parse_dublincore)
     else:
-        document = WLDocument.from_string(input, True)
+        document = parser.WLDocument.from_string(input_filename, True, parse_dublincore=parse_dublincore)
 
     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:
+        url = '*' * 10
     output_file.write(TEMPLATE % {
-        'url': dcparser.parse(input_filename).url,
+        'url': url,
         'text': unicode(result),
     })