Added extraction of wiki_url from DublinCore.

[wolnelektury.git] / lib / librarian / bin / genslugs.py

diff --git a/lib/librarian/bin/genslugs.py b/lib/librarian/bin/genslugs.py
index 263e00f..3391d8e 100755 (executable)
--- a/lib/librarian/bin/genslugs.py
+++ b/lib/librarian/bin/genslugs.py
@@ -20,7 +20,9 @@ if __name__ == '__main__':
 
     parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
         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:
@@ -36,7 +38,7 @@ if __name__ == '__main__':
         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
         
         parent = ''
@@ -45,15 +47,18 @@ if __name__ == '__main__':
             parent = parent_url.rsplit('/', 1)[1] + ' '
         except AttributeError:
             pass
-        
+        except IndexError:
+            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')
-        elif book_url.text.startswith('http://'):
-            print '%s:notice:book already has identifier starting with http://, skipping' % input_filename
+        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)
             continue
-        book_url.text = BOOK_URL + slughifi(parent + title)
+        
+        book_url.text = BOOK_URL + slughifi(parent + title)[:60]
 
         doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')