Added fallback for broken PDFs.

pdfminer/pdfinterp.py

@@ -18,7 +18,7 @@ from pdffont import PDFFontError
 from pdffont import PDFType1Font, PDFTrueTypeFont, PDFType3Font
 from pdffont import PDFCIDFont
 from pdfparser import PDFDocument, PDFParser
-from pdfparser import PDFPasswordIncorrect, PDFObjectNotFound
+from pdfparser import PDFPasswordIncorrect
 from pdfcolor import PDFColorSpace
 from pdfcolor import PREDEFINED_COLORSPACE
 from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB
@@ -335,10 +335,7 @@ class PDFPageInterpreter(object):
                     objid = None
                     if isinstance(spec, PDFObjRef):
                         objid = spec.objid
-                    try:
                     spec = dict_value(spec)
-                    except PDFObjectNotFound:
-                        spec = {}
                     self.fontmap[fontid] = self.rsrcmgr.get_font(objid, spec)
             elif k == 'ColorSpace':
                 for (csid,spec) in dict_value(v).iteritems():
@@ -634,6 +631,7 @@ class PDFPageInterpreter(object):
         except KeyError:
             if STRICT:
                 raise PDFInterpreterError('Undefined Font id: %r' % fontid)
+            self.textstate.font = self.rsrcmgr.get_font(None, {})
         self.textstate.fontsize = fontsize
         return
     # setrendering

pdfminer/pdfparser.py

@@ -15,7 +15,7 @@ from psparser import PSSyntaxError, PSEOF
 from psparser import literal_name
 from psparser import LIT, KWD, STRICT
 from pdftypes import PDFException, PDFTypeError, PDFNotImplementedError
-from pdftypes import PDFStream, PDFObjRef
+from pdftypes import PDFObjectNotFound, PDFStream, PDFObjRef
 from pdftypes import resolve1, decipher_all
 from pdftypes import int_value, float_value, num_value
 from pdftypes import str_value, list_value, dict_value, stream_value
@@ -31,7 +31,6 @@ class PDFNoValidXRef(PDFSyntaxError): pass
 class PDFNoOutlines(PDFException): pass
 class PDFDestinationNotFound(PDFException): pass
 class PDFEncryptionError(PDFException): pass
-class PDFObjectNotFound(PDFException): pass
 class PDFPasswordIncorrect(PDFEncryptionError): pass
 
 # some predefined literals and keywords.
@@ -330,23 +329,14 @@ class PDFDocument(object):
             # If there's an encryption info, remember it.
             if 'Encrypt' in trailer:
                 #assert not self.encryption
-                try:
                 self.encryption = (list_value(trailer['ID']),
                                    dict_value(trailer['Encrypt']))
-                except PDFObjectNotFound, e:
-                    pass
             if 'Info' in trailer:
-                try:
                 self.info.append(dict_value(trailer['Info']))
-                except PDFObjectNotFound, e:
-                    pass
             if 'Root' in trailer:
                 # Every PDF file must have exactly one /Root dictionary.
-                try:
                 self.catalog = dict_value(trailer['Root'])
                 break
-                except PDFObjectNotFound, e:
-                    pass
         else:
             raise PDFSyntaxError('No /Root object! - Is this really a PDF?')
         if self.catalog.get('Type') is not LITERAL_CATALOG:
@@ -529,12 +519,12 @@ class PDFDocument(object):
                 if 1 <= self.debug:
                     print >>sys.stderr, 'Page: %r' % tree
                 yield (objid, tree)
-        try:
+        pages = False
         if 'Pages' in self.catalog:
             for (objid,tree) in search(self.catalog['Pages'], self.catalog):
                 yield PDFPage(self, objid, tree)
-                return
-        except PDFObjectNotFound:
+                pages = True
+        if not pages:
             # fallback when /Pages is missing.
             for xref in self.xrefs:
                 for objid in xref.get_objids():

pdfminer/pdftypes.py

@@ -28,7 +28,8 @@ class PDFObject(PSObject): pass
 class PDFException(PSException): pass
 class PDFTypeError(PDFException): pass
 class PDFValueError(PDFException): pass
-class PDFNotImplementedError(PSException): pass
+class PDFObjectNotFound(PDFException): pass
+class PDFNotImplementedError(PDFException): pass
 
 
 ##  PDFObjRef
@@ -47,34 +48,37 @@ class PDFObjRef(PDFObject):
     def __repr__(self):
         return '<PDFObjRef:%d>' % (self.objid)
 
-    def resolve(self):
+    def resolve(self, default=None):
+        try:
             return self.doc.getobj(self.objid)
+        except PDFObjectNotFound:
+            return default
 
 
 # resolve
-def resolve1(x):
+def resolve1(x, default=None):
     """Resolves an object.
 
     If this is an array or dictionary, it may still contains
     some indirect objects inside.
     """
     while isinstance(x, PDFObjRef):
-        x = x.resolve()
+        x = x.resolve(default=default)
     return x
 
-def resolve_all(x):
+def resolve_all(x, default=None):
     """Recursively resolves the given object and all the internals.
     
     Make sure there is no indirect reference within the nested object.
     This procedure might be slow.
     """
     while isinstance(x, PDFObjRef):
-        x = x.resolve()
+        x = x.resolve(default=default)
     if isinstance(x, list):
-        x = [ resolve_all(v) for v in x ]
+        x = [ resolve_all(v, default=default) for v in x ]
     elif isinstance(x, dict):
         for (k,v) in x.iteritems():
-            x[k] = resolve_all(v)
+            x[k] = resolve_all(v, default=default)
     return x
 
 def decipher_all(decipher, objid, genno, x):

tools/dumppdf.py

@@ -9,7 +9,7 @@
 import sys, re
 from pdfminer.psparser import PSKeyword, PSLiteral
 from pdfminer.pdfparser import PDFDocument, PDFParser, PDFNoOutlines
-from pdfminer.pdfparser import PDFObjectNotFound
+from pdfminer.pdftypes import PDFObjectNotFound
 from pdfminer.pdftypes import PDFStream, PDFObjRef, resolve1, stream_value