tests for handling "2 poł XIX w." dates + utf8 check

[librarian.git] / scripts / book2txt

diff --git a/scripts/book2txt b/scripts/book2txt
index 1ca4623..1b4c0ef 100755 (executable)
--- a/scripts/book2txt
+++ b/scripts/book2txt
@@ -1,31 +1,29 @@
 #!/usr/bin/env python
-import os
-import optparse
-
-from librarian import text
+# -*- 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.
+#
+from librarian.book2anything import Book2Anything, Option
+from librarian.parser import WLDocument
+
+
+class Book2Txt(Book2Anything):
+    format_name = "TXT"
+    ext = "txt"
+    uses_cover = False
+    uses_provider = False
+    parser_args = [
+        Option('-i', '--ignore-dublin-core', dest='parse_dublincore', 
+                action='store_false', default=True,
+                help='don\'t try to parse dublin core metadata')
+    ]
+    transform_args = [
+        Option('-w', '--wrap', action='store', type='int', dest='wrapping', default=0,
+                help='set line wrap column')
+    ]
+    transform = WLDocument.as_text
 
 
 if __name__ == '__main__':
-    # Parse commandline arguments
-    usage = """Usage: %prog [options] SOURCE [SOURCE...]
-    Convert SOURCE files to TXT format."""
-
-    parser = optparse.OptionParser(usage=usage)
-
-    parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
-        help='print status messages to stdout')
-
-    options, input_filenames = parser.parse_args()
-
-    if len(input_filenames) < 1:
-        parser.print_help()
-        exit(1)
-
-    # Do some real work
-    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)
-
+    Book2Txt.run()