X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/239d66922f4b83ee5baaa284a9c33a32bfcb99a4..c4494a95679cd041e15c4f6b42d4927f107b2db7:/bin/book2html.py

diff --git a/bin/book2html.py b/bin/book2html.py
index 5bd2bb527..3907de38c 100755
--- a/bin/book2html.py
+++ b/bin/book2html.py
@@ -9,39 +9,42 @@ import sys
 from lxml import etree
 
 
-# Parse args
-usage = """Usage: %prog [options] SOURCE [SOURCE...]
-Convert SOURCE files to HTML 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)
-
-# Parse XSLT
-style = etree.parse('book2html.xslt')
-    
-# Do some real work
-for input_filename in input_filenames:
-    if options.verbose:
-        print input_filename
-    
-    output_filename = os.path.splitext(input_filename)[0] + '.html'
-    
-    # Transform
+ENTITY_SUBSTITUTIONS = [
+    (u'---', u'—'),
+    (u'--', u'–'),
+    (u'...', u'…'),
+    (u',,', u'„'),
+    (u'"', u'”'),
+]
+
+
+def substitute_entities(context, text):
+    """XPath extension function converting all entites in passed text."""
+    if isinstance(text, list):
+        text = ''.join(text)
+    for entity, substitutution in ENTITY_SUBSTITUTIONS:
+        text = text.replace(entity, substitutution)
+    return text
+
+
+# Register substitute_entities function with lxml
+ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
+ns['substitute_entities'] = substitute_entities
+
+
+def transform(input_filename, output_filename):
+    """Transforms file input_filename in XML to output_filename in XHTML."""
+    # Parse XSLT
+    style_filename = os.path.join(os.path.dirname(__file__), 'book2html.xslt')
+    style = etree.parse(style_filename)
+
     doc_file = cStringIO.StringIO()
     expr = re.compile(r'/\s', re.MULTILINE | re.UNICODE);
 
     f = open(input_filename, 'r')
     for line in f:
         line = line.decode('utf-8')
-        line = expr.sub(u'<br/>\n', line).replace(u'---', u'—').replace(u',,', u'„')
+        line = expr.sub(u'<br/>\n', line)
         doc_file.write(line.encode('utf-8'))
     f.close()
 
@@ -53,3 +56,28 @@ for input_filename in input_filenames:
     result = doc.xslt(style)
     result.write(output_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')
 
+
+if __name__ == '__main__':
+    # Parse commandline arguments
+    usage = """Usage: %prog [options] SOURCE [SOURCE...]
+    Convert SOURCE files to HTML 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] + '.html'
+        transform(input_filename, output_filename)
+