Added extraction of wiki_url from DublinCore.

[wolnelektury.git] / lib / librarian / dcparser.py

diff --git a/lib/librarian/dcparser.py b/lib/librarian/dcparser.py
index 9281325..a410686 100644 (file)
--- a/lib/librarian/dcparser.py
+++ b/lib/librarian/dcparser.py
@@ -45,7 +45,7 @@ def str_to_unicode(value, previous):
 def str_to_unicode_list(value, previous):
     if previous is None:
         previous = []
-    previous.append(str_to_unicode(value))
+    previous.append(str_to_unicode(value, None))
     return previous
 
 
@@ -76,7 +76,7 @@ def str_to_date(value, previous):
 # ==========
 class ParseError(Exception):
     def __init__(self, message):
-        super(self, Exception).__init__(message)
+        super(ParseError, self).__init__(message)
 
 
 class XMLNamespace(object):
@@ -134,6 +134,8 @@ class BookInfo(object):
             raise ParseError(e)
 
         description = tree.find('//' + book_info.RDF('Description'))
+        book_info.wiki_url = description.get(cls.RDF('about'), None)
+        
         if description is None:
             raise ParseError('no Description tag found in document')
         
@@ -157,6 +159,9 @@ class BookInfo(object):
         root = etree.Element(self.RDF('RDF'))
         description = etree.SubElement(root, self.RDF('Description'))
         
+        if self.wiki_url:
+            description.set(self.RDF('about'), self.wiki_url)
+        
         for tag, (attribute, converter) in self.mapping.iteritems():
             if hasattr(self, attribute):
                 e = etree.Element(tag)
@@ -165,6 +170,17 @@ class BookInfo(object):
         
         return unicode(etree.tostring(root, 'utf-8'), 'utf-8')
 
+    def to_dict(self):
+        etree._namespace_map[str(self.RDF)] = 'rdf'
+        etree._namespace_map[str(self.DC)] = 'dc'
+        
+        result = {'about': self.wiki_url}
+        for tag, (attribute, converter) in self.mapping.iteritems():
+            if hasattr(self, attribute):
+                result[attribute] = unicode(getattr(self, attribute))
+        
+        return result
+
 
 def parse(file_name):
     return BookInfo.from_file(file_name)