outline bug fixed

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@249 1aa58f4a-7d42-0410-adbc-911cccaed67c

pdfminer/pdfparser.py

@@ -30,6 +30,7 @@ from utils import decode_text, ObjIdRange
 class PDFSyntaxError(PDFException): pass
 class PDFNoValidXRef(PDFSyntaxError): pass
 class PDFNoOutlines(PDFException): pass
+class PDFDestinationNotFound(PDFException): pass
 class PDFEncryptionError(PDFException): pass
 class PDFPasswordIncorrect(PDFEncryptionError): pass
 
@@ -517,7 +518,7 @@ class PDFDocument(object):
 
     def get_outlines(self):
         if 'Outlines' not in self.catalog:
-            raise PDFNoOutlines('No /Outlines defined!')
+            raise PDFNoOutlines
         def search(entry, level):
             entry = dict_value(entry)
             if 'Title' in entry:
@@ -558,6 +559,20 @@ class PDFDocument(object):
             raise KeyError((cat,key))
         return lookup(d0)
 
+    def get_dest(self, name):
+        try:
+            # PDF-1.2 or later
+            obj = self.lookup_name('Dests', name)
+        except KeyError:
+            # PDF-1.1 or prior
+            if 'Dests' not in self.catalog:
+                raise PDFDestinationNotFound(name)
+            d0 = dict_value(self.catalog['Dests'])
+            if name not in d0:
+                raise PDFDestinationNotFound(name)
+            obj = d0[name]
+        return obj
+
 
 ##  PDFParser
 ##

tools/dumppdf.py

@@ -113,24 +113,28 @@ def dumpoutline(outfp, fname, objids, pagenos, password='',
     doc.set_parser(parser)
     doc.initialize(password)
     pages = dict( (page.pageid, pageno) for (pageno,page) in enumerate(doc.get_pages()) )
+    def resolve_dest(dest):
+        if isinstance(dest, str):
+            dest = resolve1(doc.get_dest(dest))
+        elif isinstance(dest, PSLiteral):
+            dest = resolve1(doc.get_dest(dest.name))
+        if isinstance(dest, dict):
+            dest = dest['D']
+        return dest
     try:
         outlines = doc.get_outlines()
         outfp.write('<outlines>\n')
         for (level,title,dest,a,se) in outlines:
             pageno = None
             if dest:
-                dest = resolve1(doc.lookup_name('Dests', dest))
+                dest = resolve_dest(dest)
-                if isinstance(dest, dict):
+                pageno = pages[dest[0].objid]
-                    dest = dest['D']
-                    pageno = pages[dest[0].objid]
             elif a:
                 action = a.resolve()
                 if isinstance(action, dict):
                     subtype = action.get('S')
                     if subtype and repr(subtype) == '/GoTo' and action.get('D'):
-                        dest = action['D']
+                        dest = resolve_dest(action['D'])
-                        if isinstance(dest, str):
-                            dest = resolve1(doc.lookup_name('Dests', dest))
                         pageno = pages[dest[0].objid]
             s = e(title).encode('utf-8', 'xmlcharrefreplace')
             outfp.write('<outline level="%r" title="%s">\n' % (level, s))