Poprawienie ilości światła pomiędzy częściami utworu w plikach TXT wypluwanych przez...

[wolnelektury.git] / lib / librarian / bin / book2txt.py

diff --git a/lib/librarian/bin/book2txt.py b/lib/librarian/bin/book2txt.py
index 86f6f12..1ca4623 100755 (executable)
--- a/lib/librarian/bin/book2txt.py
+++ b/lib/librarian/bin/book2txt.py
@@ -1,25 +1,8 @@
 #!/usr/bin/env python
 #!/usr/bin/env python

-# -*- coding: utf-8 -*-
-import re

 import os
 import optparse
 import os
 import optparse

-import codecs

 
 

-
-REGEXES = [
-    (r'<rdf:RDF[^>]*>(.|\n)*?</rdf:RDF>', ''),
-    (r'<motyw[^>]*>(.|\n)*?</motyw>', ''),
-    ('<(begin|end)\\sid=[\'|"][b|e]\\d+[\'|"]\\s/>', ''),
-    (r'<extra>((<!--<(elementy_poczatkowe|tekst_glowny)>-->)|(<!--</(elementy_poczatkowe|tekst_glowny)>-->))</extra>', ''),
-    (r'<uwaga>[^<]*</uwaga>', ''),
-    (r'<p[a|e|r|t]>(.|\n)*?</p>', ''),
-    (r'<[^>]+>', ''),
-    (r'/$', ''),
-    (r'---', u'—'),
-    (r'--', u'-'),
-    (r',,', u'„'),
-    (r'"', u'”'),
-]
+from librarian import text

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


@@ -44,13 +27,5 @@ if __name__ == '__main__':
             print input_filename
         
         output_filename = os.path.splitext(input_filename)[0] + '.txt'
             print input_filename
         
         output_filename = os.path.splitext(input_filename)[0] + '.txt'

-        
-        xml = codecs.open(input_filename, 'r', encoding='utf-8').read()
-        for pattern, repl in REGEXES:
-            # print pattern, repl
-            xml, n = re.subn(pattern, repl, xml)
-            # print n
-            
-        output = codecs.open(output_filename, 'w', encoding='utf-8')
-        output.write(xml)
+        text.transform(input_filename, output_filename)