pdf fix

[librarian.git] / librarian / parser.py

diff --git a/librarian/parser.py b/librarian/parser.py
index 2cd86ab..341eaf8 100644 (file)
--- a/librarian/parser.py
+++ b/librarian/parser.py
@@ -38,11 +38,11 @@ class WLDocument(object):
             self.book_info = None
 
     @classmethod
             self.book_info = None
 
     @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):


@@ -57,8 +57,13 @@ class WLDocument(object):
         if not isinstance(data, unicode):
             data = data.decode('utf-8')
 
         if not isinstance(data, unicode):
             data = data.decode('utf-8')
 

+        data = data.replace(u'\ufeff', '')
+

         if swap_endlines:
         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)
 
         try:
             parser = etree.XMLParser(remove_blank_text=False)


@@ -116,4 +121,14 @@ class WLDocument(object):
             except Exception, e:
                 unmerged.append( repr( (key, xpath, e) ) )
 
             except Exception, e:
                 unmerged.append( repr( (key, xpath, e) ) )
 

-        return unmerged
\ No newline at end of file
+        return unmerged
+
+    def clean_ed_note(self):
+        """ deletes forbidden tags from nota_red """
+
+        for node in self.edoc.xpath('|'.join('//nota_red//%s' % tag for tag in
+                    ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))):
+            tail = node.tail
+            node.clear()
+            node.tag = 'span'
+            node.tail = tail