Better handling of multipart DAISY.

[librarian.git] / scripts / genslugs

diff --git a/scripts/genslugs b/scripts/genslugs
index 9490c55..9745b68 100755 (executable)
--- a/scripts/genslugs
+++ b/scripts/genslugs
@@ -1,25 +1,11 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #

-#    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/>.
+# 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 print_function, unicode_literals
+

 import os
 import optparse
 
 import os
 import optparse
 


@@ -42,7 +28,7 @@ if __name__ == '__main__':
         help='print status messages to stdout')
     parser.add_option('-f', '--force', action='store_true', dest='force', default=False,
         help='overwrite current identifiers')
         help='print status messages to stdout')
     parser.add_option('-f', '--force', action='store_true', dest='force', default=False,
         help='overwrite current identifiers')

-    
+

     options, input_filenames = parser.parse_args()
 
     if len(input_filenames) < 1:
     options, input_filenames = parser.parse_args()
 
     if len(input_filenames) < 1:


@@ -52,15 +38,15 @@ if __name__ == '__main__':
     # Do some real work
     for input_filename in input_filenames:
         if options.verbose:
     # Do some real work
     for input_filename in input_filenames:
         if options.verbose:

-            print input_filename
-        
+            print(input_filename)
+

         doc = etree.parse(input_filename)
         try:
             title = doc.find('//{http://purl.org/dc/elements/1.1/}title').text
         except AttributeError:
         doc = etree.parse(input_filename)
         try:
             title = doc.find('//{http://purl.org/dc/elements/1.1/}title').text
         except AttributeError:

-            print '%s:error:Book title not found. Skipping.' % input_filename
+            print('%s:error:Book title not found. Skipping.' % input_filename)

             continue
             continue

-        
+

         parent = ''
         try:
             parent_url = doc.find('//{http://purl.org/dc/elements/1.1/}relation.isPartOf').text
         parent = ''
         try:
             parent_url = doc.find('//{http://purl.org/dc/elements/1.1/}relation.isPartOf').text


@@ -68,16 +54,16 @@ if __name__ == '__main__':
         except AttributeError:
             pass
         except IndexError:
         except AttributeError:
             pass
         except IndexError:

-            print '%s:error:Invalid parent URL "%s". Skipping.' % (input_filename, parent_url)
-            
+            print('%s:error:Invalid parent URL "%s". Skipping.' % (input_filename, parent_url))
+

         book_url = doc.find('//{http://purl.org/dc/elements/1.1/}identifier.url')
         if book_url is None:
             book_description = doc.find('//{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description')
             book_url = etree.SubElement(book_description, '{http://purl.org/dc/elements/1.1/}identifier.url')
         if not options.force and book_url.text.startswith('http://'):
         book_url = doc.find('//{http://purl.org/dc/elements/1.1/}identifier.url')
         if book_url is None:
             book_description = doc.find('//{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description')
             book_url = etree.SubElement(book_description, '{http://purl.org/dc/elements/1.1/}identifier.url')
         if not options.force and book_url.text.startswith('http://'):

-            print '%s:Notice:Book already has identifier URL "%s". Skipping.' % (input_filename, book_url.text)
+            print('%s:Notice:Book already has identifier URL "%s". Skipping.' % (input_filename, book_url.text))

             continue
             continue

-        
+

         book_url.text = BOOK_URL + slughifi(parent + title)[:60]
 
         doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')
         book_url.text = BOOK_URL + slughifi(parent + title)[:60]
 
         doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')