More typos.

[librarian.git] / librarian / parser.py

diff --git a/librarian/parser.py b/librarian/parser.py
index 55b4e4b..225000b 100644 (file)
--- a/librarian/parser.py
+++ b/librarian/parser.py
@@ -1,6 +1,26 @@
 # -*- coding: utf-8 -*-
 # -*- coding: utf-8 -*-

+#
+#    This file is part of Librarian.
+#
+#    Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska <fundacja@nowoczesnapolska.org.pl>
+#    
+#    For full list of contributors see AUTHORS file. 
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU Affero General Public License as published by
+#    the Free Software Foundation, either version 3 of the License, or
+#    (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#

 from librarian import ValidationError, NoDublinCore,  ParseError
 from librarian import ValidationError, NoDublinCore,  ParseError

-from librarian import RDFNS, DCNS
+from librarian import RDFNS

 from librarian import dcparser
 
 from xml.parsers.expat import ExpatError
 from librarian import dcparser
 
 from xml.parsers.expat import ExpatError


@@ -57,23 +77,20 @@ class WLDocument(object):
             data = cls.LINE_SWAP_EXPR.sub(u'<br />\n', data)
     
         try:
             data = cls.LINE_SWAP_EXPR.sub(u'<br />\n', data)
     
         try:

-            parser = etree.XMLParser(remove_blank_text=True)
+            parser = etree.XMLParser(remove_blank_text=False)

             return cls(etree.parse(StringIO(data), parser), parse_dublincore=parse_dublincore)
         except (ExpatError, XMLSyntaxError, XSLTApplyError), e:
             raise ParseError(e)                  
 
             return cls(etree.parse(StringIO(data), parser), parse_dublincore=parse_dublincore)
         except (ExpatError, XMLSyntaxError, XSLTApplyError), e:
             raise ParseError(e)                  
 

-    def part_as_text(self, path):
+    def chunk(self, path):

         # convert the path to XPath        
         # convert the path to XPath        

-        print "[L] Retrieving part:", path
+        expr = self.path_to_xpath(path)
+        elems = self.edoc.xpath(expr)

 
 

-        elems = self.edoc.xpath(self.path_to_xpath(path))
-        print "[L] xpath", elems
-        

         if len(elems) == 0:
         if len(elems) == 0:

-            return None        
-
-        return etree.tostring(elems[0], encoding=unicode, pretty_print=True)
-
+            return None
+        else:        
+            return elems[0]

 
     def path_to_xpath(self, path):
         parts = []
 
     def path_to_xpath(self, path):
         parts = []


@@ -84,7 +101,7 @@ class WLDocument(object):
                 parts.append(part)
             else:
                 tag, n = match.groups()
                 parts.append(part)
             else:
                 tag, n = match.groups()

-                parts.append("node()[position() = %d and name() = '%s']" % (int(n), tag) )
+                parts.append("*[%d][name() = '%s']" % (int(n)+1, tag) )

 
         if parts[0] == '.':
             parts[0] = ''
 
         if parts[0] == '.':
             parts[0] = ''


@@ -95,8 +112,9 @@ class WLDocument(object):
         return self.edoc.xslt(stylesheet, **options)
 
     def update_dc(self):
         return self.edoc.xslt(stylesheet, **options)
 
     def update_dc(self):

-        parent = self.rdf_elem.getparent()
-        parent.replace( self.rdf_elem, self.book_info.to_etree(parent) )
+        if self.book_info:
+            parent = self.rdf_elem.getparent()
+            parent.replace( self.rdf_elem, self.book_info.to_etree(parent) )

 
     def serialize(self):
         self.update_dc()
 
     def serialize(self):
         self.update_dc()


@@ -108,8 +126,8 @@ class WLDocument(object):
         for key, data in chunk_dict.iteritems():
             try:
                 xpath = self.path_to_xpath(key)
         for key, data in chunk_dict.iteritems():
             try:
                 xpath = self.path_to_xpath(key)

-                node = self.edoc.xpath(xpath)[0]                
-                repl = etree.fromstring(data)
+                node = self.edoc.xpath(xpath)[0]
+                repl = etree.fromstring(u"<%s>%s</%s>" %(node.tag, data, node.tag) )

                 node.getparent().replace(node, repl);
             except Exception, e:
                 unmerged.append( repr( (key, xpath, e) ) )
                 node.getparent().replace(node, repl);
             except Exception, e:
                 unmerged.append( repr( (key, xpath, e) ) )