Miscellaneous bug fixes (#47)

* utils.decode_text: fix "TypeError: ord() expected string of length 1, but int found"

fixes https://github.com/goulu/pdfminer/issues/24

* pdfinterp.execute: don't assume that every keyword name can be decoded as utf-8

fixes "'str' does not support the buffer interface", https://github.com/goulu/pdfminer/issues/23

* default settings.STRICT to False, for compatibility with the original pdfminer

* PDFCIDFont: handle font registry/orderings that may be PDFObjRefs

* utils.nunpack: handle 8-byte integers

pdfminer/pdffont.py

@@ -640,8 +640,8 @@ class PDFCIDFont(PDFFont):
                 raise PDFFontError('BaseFont is missing')
             self.basefont = 'unknown'
         self.cidsysteminfo = dict_value(spec.get('CIDSystemInfo', {}))
-        self.cidcoding = '%s-%s' % (self.cidsysteminfo.get('Registry', b'unknown').decode("latin1"),
-                                    self.cidsysteminfo.get('Ordering', b'unknown').decode("latin1"))
+        self.cidcoding = '%s-%s' % (resolve1(self.cidsysteminfo.get('Registry', b'unknown')).decode("latin1"),
+                                    resolve1(self.cidsysteminfo.get('Ordering', b'unknown')).decode("latin1"))
         try:
             name = literal_name(spec['Encoding'])
         except KeyError:

pdfminer/psparser.py

@@ -160,10 +160,7 @@ def keyword_name(x):
     else:
         name=x.name
         if six.PY3:
-            try:
-                name = str(name,'utf-8')
-            except:
-                pass
+            name = str(name,'utf-8','ignore')
     return name
 
 

pdfminer/settings.py

@@ -1,4 +1,4 @@
-STRICT = True
+STRICT = False
 
 try:
     from django.conf import settings

pdfminer/utils.py

@@ -211,7 +211,7 @@ def choplist(n, seq):
 
 # nunpack
 def nunpack(s, default=0):
-    """Unpacks 1 to 4 byte integers (big endian)."""
+    """Unpacks 1 to 4 or 8 byte integers (big endian)."""
     l = len(s)
     if not l:
         return default
@@ -223,6 +223,8 @@ def nunpack(s, default=0):
         return struct.unpack('>L', b'\x00'+s)[0]
     elif l == 4:
         return struct.unpack('>L', s)[0]
+    elif l == 8:
+        return struct.unpack('>Q', s)[0]
     else:
         raise TypeError('invalid length: %d' % l)
 
@@ -269,7 +271,7 @@ def decode_text(s):
     if s.startswith(b'\xfe\xff'):
         return six.text_type(s[2:], 'utf-16be', 'ignore')
     else:
-        return ''.join(PDFDocEncoding[ord(c)] for c in s)
+        return ''.join(PDFDocEncoding[c] for c in s)
 
 
 # enc