pdf with motifs (dirty hack for marginpar-orphan problem)

[librarian.git] / librarian / parser.py

diff --git a/librarian/parser.py b/librarian/parser.py
index 225000b..b470957 100644 (file)
--- a/librarian/parser.py
+++ b/librarian/parser.py
@@ -1,23 +1,7 @@
 # -*- 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/>.
+# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.

 #
 from librarian import ValidationError, NoDublinCore,  ParseError
 from librarian import RDFNS
 #
 from librarian import ValidationError, NoDublinCore,  ParseError
 from librarian import RDFNS


@@ -37,9 +21,9 @@ class WLDocument(object):
         self.edoc = edoc
 
         root_elem = edoc.getroot()
         self.edoc = edoc
 
         root_elem = edoc.getroot()

-       
+

         dc_path = './/' + RDFNS('RDF')
         dc_path = './/' + RDFNS('RDF')

-        
+

         if root_elem.tag != 'utwor':
             raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
 
         if root_elem.tag != 'utwor':
             raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
 


@@ -48,17 +32,17 @@ class WLDocument(object):
 
             if self.rdf_elem is None:
                 raise NoDublinCore('Document has no DublinCore - which is required.')
 
             if self.rdf_elem is None:
                 raise NoDublinCore('Document has no DublinCore - which is required.')

-            
+

             self.book_info = dcparser.BookInfo.from_element(self.rdf_elem)
         else:
             self.book_info = None
             self.book_info = dcparser.BookInfo.from_element(self.rdf_elem)
         else:
             self.book_info = None

-    
+

     @classmethod
     @classmethod

-    def from_string(cls, xml, swap_endlines=False, parse_dublincore=True):
-        return cls.from_file(StringIO(xml), swap_endlines, parse_dublincore=parse_dublincore)
+    def from_string(cls, xml, *args, **kwargs):
+        return cls.from_file(StringIO(xml), *args, **kwargs)

 
     @classmethod
 
     @classmethod

-    def from_file(cls, xmlfile, swap_endlines=False, parse_dublincore=True):
+    def from_file(cls, xmlfile, swap_endlines=False, parse_dublincore=True, preserve_lines=True):

 
         # first, prepare for parsing
         if isinstance(xmlfile, basestring):
 
         # first, prepare for parsing
         if isinstance(xmlfile, basestring):


@@ -74,22 +58,25 @@ class WLDocument(object):
             data = data.decode('utf-8')
 
         if swap_endlines:
             data = data.decode('utf-8')
 
         if swap_endlines:

-            data = cls.LINE_SWAP_EXPR.sub(u'<br />\n', data)
-    
+            sub = u'<br/>'
+            if preserve_lines:
+                sub += u'\n'
+            data = cls.LINE_SWAP_EXPR.sub(sub, data)
+

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

 
     def chunk(self, path):
 
     def chunk(self, path):

-        # convert the path to XPath        
+        # convert the path to XPath

         expr = self.path_to_xpath(path)
         elems = self.edoc.xpath(expr)
 
         if len(elems) == 0:
             return None
         expr = self.path_to_xpath(path)
         elems = self.edoc.xpath(expr)
 
         if len(elems) == 0:
             return None

-        else:        
+        else:

             return elems[0]
 
     def path_to_xpath(self, path):
             return elems[0]
 
     def path_to_xpath(self, path):