fix expected html output to contain secX anchors

[librarian.git] / scripts / book2txt

diff --git a/scripts/book2txt b/scripts/book2txt
index 1ca4623..9cfdef2 100755 (executable)
--- a/scripts/book2txt
+++ b/scripts/book2txt
@@ -1,8 +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 ParseError
+from librarian.parser import WLDocument

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


@@ -14,6 +20,10 @@ if __name__ == '__main__':
 
     parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
         help='print status messages to stdout')
 
     parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
         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()
 


@@ -25,7 +35,29 @@ 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'
-        text.transform(input_filename, output_filename)

 
 

+        output_filename = os.path.splitext(input_filename)[0] + '.txt'
+        try:
+            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__,
+                'message': e
+            }
+        except IOError, e:
+            print '%(file)s:%(name)s:%(message)s' % {
+                'file': input_filename,
+                'name': e.__class__.__name__,
+                'message': e.strerror,
+            }
+        except BaseException, e:
+            print '%(file)s:%(etype)s:%(message)s' % {
+                'file': input_filename,
+                'etype': e.__class__.__name__,
+                'message': e,
+            }
+            raise