Pack the /P (ermissions) entry from the /Encrypt dictionionary in the…

… file trailer, as unsigned long (#352)

Fixes #186 

* Tread the permissions (the /P entry) as unsigned long, fix #186

* handle negative values for p

* Extract function for resolving an twos-complement

* Add test for issue #352

* Add line to CHANGELOG.md

* Only ints can be converted to a uint using two's-complement method

* Standardize import style; multiple imports from same module on one line

Co-authored-by: Pieter Marsman <pietermarsman@gmail.com>

CHANGELOG.md

@@ -5,7 +5,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
-Nothing here
+### Fixed
+- Interpret two's complement integer as unsigned integer ([#352](https://github.com/pdfminer/pdfminer.six/pull/352))
 
 ## [20200104] - 2019-01-04
 

pdfminer/pdfdocument.py

@@ -1,34 +1,21 @@
+import hashlib as md5
+import logging
 import re
 import struct
-import logging
-import hashlib as md5
+
 try:
-    from Crypto.Cipher import ARC4
-    from Crypto.Cipher import AES
+    from Crypto.Cipher import ARC4, AES
     from Crypto.Hash import SHA256
 except ImportError:
     AES = SHA256 = None
     from . import arcfour as ARC4
-from .psparser import PSEOF
-from .psparser import literal_name
-from .psparser import LIT
-from .psparser import KWD
+from .psparser import PSEOF, literal_name, LIT, KWD
 from . import settings
-from .pdftypes import PDFException
-from .pdftypes import PDFTypeError
-from .pdftypes import PDFStream
-from .pdftypes import PDFObjectNotFound
-from .pdftypes import decipher_all
-from .pdftypes import int_value
-from .pdftypes import str_value
-from .pdftypes import list_value
-from .pdftypes import dict_value
-from .pdftypes import stream_value
-from .pdfparser import PDFSyntaxError
-from .pdfparser import PDFStreamParser
-from .utils import choplist
-from .utils import nunpack
-from .utils import decode_text
+from .pdftypes import PDFException, uint_value, PDFTypeError, PDFStream, \
+    PDFObjectNotFound, decipher_all, int_value, str_value, list_value, \
+    dict_value, stream_value
+from .pdfparser import PDFSyntaxError, PDFStreamParser
+from .utils import choplist, nunpack, decode_text
 
 
 log = logging.getLogger(__name__)
@@ -307,7 +294,7 @@ def init(self):
     def init_params(self):
         self.v = int_value(self.param.get('V', 0))
         self.r = int_value(self.param['R'])
-        self.p = int_value(self.param['P'])
+        self.p = uint_value(self.param['P'], 32)
         self.o = str_value(self.param['O'])
         self.u = str_value(self.param['U'])
         self.length = int_value(self.param.get('Length', 40))
@@ -348,7 +335,8 @@ def compute_encryption_key(self, password):
         password = (password + self.PASSWORD_PADDING)[:32]  # 1
         hash = md5.md5(password)  # 2
         hash.update(self.o)  # 3
-        hash.update(struct.pack('<l', self.p))  # 4
+        # See https://github.com/pdfminer/pdfminer.six/issues/186
+        hash.update(struct.pack('<L', self.p))  # 4
         hash.update(self.docid[0])  # 5
         if self.r >= 4:
             if not self.encrypt_metadata:

pdfminer/pdftypes.py

@@ -139,6 +139,15 @@ def num_value(x):
     return x
 
 
+def uint_value(x, n_bits):
+    """Resolve number and interpret it as a two's-complement unsigned number"""
+    x = int_value(x)
+    if x > 0:
+        return x
+    else:
+        return x + 2**n_bits
+
+
 def str_value(x):
     x = resolve1(x)
     if not isinstance(x, bytes):

pdfminer/utils.py

@@ -124,7 +124,7 @@ def apply_matrix_norm(m, v):
 #  Utility functions
 
 def isnumber(x):
-    return isinstance(x, ((int,), float))
+    return isinstance(x, (int, float))
 
 
 def uniq(objs):

tests/test_tools_pdf2txt.py

@@ -35,7 +35,8 @@ def test_sample_one_byte_identity_encode(self):
 
     def test_nonfree_175(self):
         """Regression test for:
-        https://github.com/pdfminer/pdfminer.six/issues/65"""
+        https://github.com/pdfminer/pdfminer.six/issues/65
+        """
         run('nonfree/175.pdf')
 
     def test_nonfree_dmca(self):
@@ -63,6 +64,13 @@ def test_scancode_patchelf(self):
         """Regression test for # https://github.com/euske/pdfminer/issues/96"""
         run('scancode/patchelf.pdf')
 
+    def test_contrib_hash_two_complement(self):
+        """Check that unsigned integer is added correctly to encryption hash.
+
+        See https://github.com/pdfminer/pdfminer.six/issues/186
+        """
+        run('contrib/issue-00352-hash-twos-complement.pdf')
+
 
 class TestDumpImages: