Fix #235

src/libprs500/ebooks/lrf/__init__.py

@@ -18,6 +18,8 @@ The LRF file format is documented at U{http://www.sven.de/librie/Librie/LrfForma
 """
 import sys, os
 from optparse import OptionParser, OptionValueError
+from htmlentitydefs import name2codepoint
+
 from ttfquery import describe, findsystem
 from fontTools.ttLib import TTLibError
 
@@ -289,3 +291,11 @@ def Book(options, logger, font_delta=0, header=None,
         elif not fonts[family].has_key('normal'):
             raise ConversionError, 'Could not find the normal version of the ' + family + ' font'
     return book, fonts
+
+def entity_to_unicode(self, match):
+    ent = match.group(1)
+    if ent.startswith(u'#x'):
+        return unichr(int(ent[2:], 16))
+    if ent.startswith(u'#'):
+        return unichr(int(ent[1:]))
+    return unichr(name2codepoint[ent])

src/libprs500/ebooks/lrf/objects.py

@@ -12,6 +12,7 @@
 ##    You should have received a copy of the GNU General Public License along
 ##    with this program; if not, write to the Free Software Foundation, Inc.,
 ##    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+from libprs500.ebooks.lrf import entity_to_unicode
 import struct, array, zlib, cStringIO, collections, re
 from htmlentitydefs import name2codepoint
 
@@ -606,20 +607,11 @@ class Text(LRFStream):
     adjustment_map = {1: 'top', 2: 'center', 3: 'baseline', 4: 'bottom'}
     lineposition_map = {1:'before', 2:'after'}
     
-    
-    def handle_entity(self, match):
-        ent = match.group(1)
-        if ent.startswith(u'#x'):
-            return unichr(int(ent[2:], 16))
-        if ent.startswith(u'#'):
-            return unichr(int(ent[1:]))
-        return unichr(name2codepoint[ent])
-    
     def add_text(self, text):
         s = unicode(text, "utf-16-le")
         if s:
             s = s.translate(self.text_map)            
-            self.content.append(self.entity_pattern.sub(self.handle_entity, s))
+            self.content.append(self.entity_pattern.sub(entity_to_unicode, s))
     
     def end_container(self, tag, stream):
         self.content.append(None)

src/libprs500/ebooks/metadata/opf.py

@@ -14,13 +14,16 @@
 ##    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 '''Read/Write metadata from Open Packaging Format (.opf) files.'''
 
-import sys
+import sys, re
 
 from libprs500.ebooks.metadata import MetaInformation
 from libprs500.ebooks.BeautifulSoup import BeautifulStoneSoup
+from libprs500.ebooks.lrf import entity_to_unicode
 
 class OPFReader(MetaInformation):
     
+    ENTITY_PATTERN = re.compile(r'&(\S+);')
+    
     def __init__(self, stream):
         self.default_title = stream.name if hasattr(stream, 'name') else 'Unknown' 
         if hasattr(stream, 'seek'):
@@ -34,7 +37,7 @@ class OPFReader(MetaInformation):
         def fget(self):
             title = self.soup.package.metadata.find('dc:title')
             if title:
-                return title.string
+                return self.ENTITY_PATTERN.sub(entity_to_unicode, title.string)
             return self.default_title
         return property(doc=doc, fget=fget)
     
@@ -52,7 +55,7 @@ class OPFReader(MetaInformation):
                     ans = []
                     for i in au:
                         ans.extend(i.split('&'))
-                    return ans
+                    return self.ENTITY_PATTERN.sub(entity_to_unicode, ans)
             return None
         return property(doc=doc, fget=fget)
     
@@ -67,7 +70,7 @@ class OPFReader(MetaInformation):
                     role = elem.get('opf:role')
                 if role == 'aut':
                     fa = elem.get('file-as')
-                    return fa if fa else None
+                    return self.ENTITY_PATTERN.sub(entity_to_unicode, fa) if fa else None
         return property(doc=doc, fget=fget)
         
     @apply
@@ -83,7 +86,7 @@ class OPFReader(MetaInformation):
         def fget(self):
             comments = self.soup.find('dc:description')
             if comments:
-                return comments.string
+                return self.ENTITY_PATTERN.sub(entity_to_unicode, comments.string)
             return None
         return property(doc=doc, fget=fget)
     
@@ -93,7 +96,7 @@ class OPFReader(MetaInformation):
         def fget(self):
             category = self.soup.find('dc:type')
             if category:
-                return category.string
+                return self.ENTITY_PATTERN.sub(entity_to_unicode, category.string)
             return None
         return property(doc=doc, fget=fget)
     
@@ -103,7 +106,7 @@ class OPFReader(MetaInformation):
         def fget(self):
             publisher = self.soup.find('dc:publisher')
             if publisher:
-                return publisher.string
+                return self.ENTITY_PATTERN.sub(entity_to_unicode, publisher.string)
             return None
         return property(doc=doc, fget=fget)