set language

[librarian.git] / scripts / book2txt

diff --git a/scripts/book2txt b/scripts/book2txt
index 41a3978..9cfdef2 100755 (executable)
--- a/scripts/book2txt
+++ b/scripts/book2txt
@@ -1,9 +1,14 @@
 #!/usr/bin/env python
 #!/usr/bin/env python

+# -*- 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.
+#

 import os
 import optparse
 
 import os
 import optparse
 

-from librarian import text
-from librarian import dcparser, ParseError
+from librarian import ParseError
+from librarian.parser import WLDocument

 
 
 if __name__ == '__main__':
 
 
 if __name__ == '__main__':


@@ -17,9 +22,11 @@ if __name__ == '__main__':
         help='print status messages to stdout')
     parser.add_option('-w', '--wrap', action='store', type='int', dest='wrapping', default=0,
         help='set line wrap column')
         help='print status messages to stdout')
     parser.add_option('-w', '--wrap', action='store', type='int', dest='wrapping', default=0,
         help='set line wrap column')

-    
+    parser.add_option('-i', '--ignore-dublin-core', action='store_false', dest='parse_dublincore', default=True,
+        help='don\'t try to parse dublin core metadata')
+

     options, input_filenames = parser.parse_args()
     options, input_filenames = parser.parse_args()

-    
+

     if len(input_filenames) < 1:
         parser.print_help()
         exit(1)
     if len(input_filenames) < 1:
         parser.print_help()
         exit(1)


@@ -28,15 +35,18 @@ if __name__ == '__main__':
     for input_filename in input_filenames:
         if options.verbose:
             print input_filename
     for input_filename in input_filenames:
         if options.verbose:
             print input_filename

-        
+

         output_filename = os.path.splitext(input_filename)[0] + '.txt'
         try:
         output_filename = os.path.splitext(input_filename)[0] + '.txt'
         try:

-            text.transform(input_filename, output_filename, wrapping=str(options.wrapping))
+            doc = WLDocument.from_file(input_filename,
+                parse_dublincore=options.parse_dublincore)
+            html = doc.as_text(wrapping=str(options.wrapping))
+            doc.save_output_file(html, output_path=output_filename)

         except ParseError, e:
             print '%(file)s:%(name)s:%(message)s' % {
                 'file': input_filename,
                 'name': e.__class__.__name__,
         except ParseError, e:
             print '%(file)s:%(name)s:%(message)s' % {
                 'file': input_filename,
                 'name': e.__class__.__name__,

-                'message': e.message
+                'message': e

             }
         except IOError, e:
             print '%(file)s:%(name)s:%(message)s' % {
             }
         except IOError, e:
             print '%(file)s:%(name)s:%(message)s' % {


@@ -48,6 +58,6 @@ if __name__ == '__main__':
             print '%(file)s:%(etype)s:%(message)s' % {
                 'file': input_filename,
                 'etype': e.__class__.__name__,
             print '%(file)s:%(etype)s:%(message)s' % {
                 'file': input_filename,
                 'etype': e.__class__.__name__,

-                'message': e.message,
+                'message': e,

             }
             }

-            raise e
+            raise