Merge pull request #33 from pudo/backports

Backport changes in pdfminer since this summer

.gitattributes

@@ -1 +0,0 @@
-*.py text eol=lf

LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2004-2016  Yusuke Shinyama <yusuke at shinyama dot jp>
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or
+sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
+KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
+WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
+PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -1,4 +1,5 @@
 include Makefile
+include LICENSE
 include *.md
 include *.py
 graft docs

pdfminer/glyphlist.py

@@ -7,7 +7,7 @@ Unicode characters instead of using decimal/hex character code.
 
 The following data was taken by
 
-  $ wget http://www.adobe.com/devnet/opentype/archives/glyphlist.txt
+  $ wget https://partners.adobe.com/public/developer/en/opentype/glyphlist.txt
   $ python tools/conv_glyphlist.py glyphlist.txt > glyphlist.py
 
 """

pdfminer/latin_enc.py

@@ -162,6 +162,7 @@ ENCODING = [
   ('mu', None, 181, 181, 181),
   ('multiply', None, None, 215, 215),
   ('n', 110, 110, 110, 110),
+  ('nbspace', None, 202, 160, None),
   ('nine', 57, 57, 57, 57),
   ('ntilde', None, 150, 241, 241),
   ('numbersign', 35, 35, 35, 35),

pdfminer/pdffont.py

@@ -543,7 +543,7 @@ class PDFSimpleFont(PDFFont):
             encoding = LITERAL_STANDARD_ENCODING
         if isinstance(encoding, dict):
             name = literal_name(encoding.get('BaseEncoding', LITERAL_STANDARD_ENCODING))
-            diff = list_value(encoding.get('Differences', None))
+            diff = list_value(encoding.get('Differences', []))
             self.cid2unicode = EncodingDB.get_encoding(name, diff)
         else:
             self.cid2unicode = EncodingDB.get_encoding(literal_name(encoding))

pdfminer/pdftypes.py

@@ -229,7 +229,10 @@ class PDFStream(PDFObject):
         if not isinstance(filters, list):
             filters = [filters]
         if not isinstance(params, list):
-            params = [params]
+            # Make sure the parameters list is the same as filters.
+            params = [params] * len(filters)
+        if settings.STRICT and len(params) != len(filters):
+            raise PDFException("Parameters len filter mismatch")
         return zip(filters, params)
 
     def decode(self):

pdfminer/psparser.py

@@ -138,7 +138,7 @@ KEYWORD_DICT_END = KWD(b'>>')
 def literal_name(x):
     if not isinstance(x, PSLiteral):
         if settings.STRICT:
-            raise PSTypeError('Literal required: %r' % x)
+            raise PSTypeError('Literal required: %r' % (x,))
         else:
             name=x
     else:

pdfminer/utils.py

@@ -46,8 +46,9 @@ def compatible_encode_method(bytesorstring, encoding='utf-8', erraction='ignore'
 def apply_png_predictor(pred, colors, columns, bitspercomponent, data):
     if bitspercomponent != 8:
         # unsupported
-        raise ValueError(bitspercomponent)
-    nbytes = colors*columns*bitspercomponent//8
+        raise ValueError("Unsupported `bitspercomponent': %d" %
+                         bitspercomponent)
+    nbytes = colors * columns * bitspercomponent // 8
     i = 0
     buf = b''
     line0 = b'\x00' * columns
@@ -86,7 +87,7 @@ def apply_png_predictor(pred, colors, columns, bitspercomponent, data):
                 line2 += six.int2byte(c)
         else:
             # unsupported
-            raise ValueError(ft)
+            raise ValueError("Unsupported predictor value: %d" % ft)
         buf += line2
         line0 = line2
     return buf

setup.py

@@ -4,12 +4,16 @@ from setuptools import setup
 from pdfminer import __version__
 import sys
 
+requires = ['six', 'pycrypto']
+if sys.version_info >= (3, 0):
+    requires.append('chardet')
+
 setup(
     name='pdfminer.six',
     version=__version__,
-    packages=['pdfminer',],
+    packages=['pdfminer'],
     package_data={'pdfminer': ['cmap/*.pickle.gz']},
-    install_requires=['six', 'chardet'] if sys.version_info >= (3, 0) else ['six'],
+    install_requires=requires,
     description='PDF parser and analyzer',
     long_description='''fork of PDFMiner using six for Python 2+3 compatibility