Merge pull request #15 from maxpmaxp/v0.1.3rc1

V0.1.3rc1

MANIFEST.in

@@ -10,6 +10,7 @@ recursive-include doc *.conf
 recursive-include doc *.png
 recursive-include doc *.pdf
 prune venv
+prune .venv
 prune doc/_build
 prune dist
 exclude example-crash-markdown.txt extract-logo.png fax-from-p8.png mask.png sample-cmap.txt sample-font.type1

doc/examples/extract_fonts.rst

@@ -32,13 +32,12 @@ Now let's see what fonts the very first page uses:
 .. doctest::
 
   >>> page = next(doc.pages())
-  >>> page.Resources.Font
-  {'T1_0': <IndirectReference:n=22,g=0>, ... <IndirectReference:n=41,g=0>}
-
+  >>> sorted(page.Resources.Font.keys())
+  ['T1_0', 'T1_1', 'T1_2', 'TT0', 'TT1']
 
 We see 5 fonts named `T1_0`, `T1_1`, `T1_2`, `TT0` and `TT1`.
-As *pdfreader* is a lazy reader the font data has not been read yet. We just see the names and
-the references to the objects.
+As *pdfreader* is a lazy reader the font data has not been read yet.
+We just have the names and the references to the objects.
 
 Let's have a look at font `T1_0`.
 

doc/examples/extract_form_text.rst

@@ -53,8 +53,8 @@ listed under page resources. The viewer puts them on canvas:
 
 .. doctest::
 
-  >>> list(viewer.canvas.forms.keys())
-  ['Fm1', 'Fm2', ... 'Fm29', 'Fm30', 'Fm31']
+  >>> sorted(list(viewer.canvas.forms.keys()))
+  ['Fm1', 'Fm10', 'Fm11', 'Fm12', 'Fm13', 'Fm14',...]
 
 As Form is a kind of "sub-document" every entry in *viewer.canvas.forms* dictionary maps to
 :class:`~pdfreader.viewer.SimpleCanvas` instance:

pdfreader/CHANGELOG.txt

@@ -0,0 +1,6 @@
+pdfreader 0.1.3, 2019-12-20
+---------------------------
+ - CMap-based text decoding issue fixed
+ - Multiple filters support for inline images added
+ - nbspace added to MacRomanEncoding and WinAnsiEncoding
+ - GraphicsState issue issue related to loosing some state attributes fixed

pdfreader/__init__.py

@@ -5,4 +5,4 @@
 register_pdf_encodings()
 
 #: package version
-__version__ = version = '0.1.3rc1'
+__version__ = version = '0.1.3'

pdfreader/parsers/base.py

@@ -361,8 +361,11 @@ def dictionary(self):
         ...                                 /Item4 (OK)
         ...                           >>
         ...         >>'''
-        >>> BasicTypesParser(s, 0).dictionary()
-        {'Type': 'Example', 'Subtype': 'DictExample', 'Version': Decimal('0.01'), 'IntegerItem': 12, 'StringItem': b'a string', 'ArrayItem': [1, 2], 'ObjRef': <IndirectReference:n=12,g=0>, 'SubDictionary': {'Item1': True, 'Item2': False, 'Item3': None, 'Item4': b'OK'}}
+        >>> expected = {'Type': 'Example', 'Subtype': 'DictExample', 'Version': Decimal('0.01'), 'IntegerItem': 12,
+        ... 'StringItem': b'a string', 'ArrayItem': [1, 2], 'ObjRef': IndirectReference(12, 0),
+        ... 'SubDictionary': {'Item1': True, 'Item2': False, 'Item3': None, 'Item4': b'OK'}}
+        >>> BasicTypesParser(s, 0).dictionary() == expected
+        True
 
         """
         pfx = self.read(2)

pdfreader/parsers/document.py

@@ -194,8 +194,10 @@ def trailer(self):
             ... /ID [<0102AA> <0102BB>]
             ... >>'''
             >>> p = PDFParser(s, 0)
-            >>> p.trailer()
-            <Trailer: {'Size': 22, 'Root': <IndirectReference:n=2,g=0>, 'Info': <IndirectReference:n=1,g=0>, 'ID': ['0102AA', '0102BB']}>
+            >>> expected_params = {'Size': 22, 'Root': IndirectReference(2,0),
+            ... 'Info': IndirectReference(1,0), 'ID': ['0102AA', '0102BB']}
+            >>> p.trailer() == Trailer(expected_params)
+            True
         """
         token = self.read(7)
         if token != b'trailer':

setup.py

@@ -9,7 +9,7 @@
 if sys.version_info[:2] < (3, 6):
     warnings.warn("Python version >= 3.6 required.")
 
-version = '0.1.3rc1'
+version = '0.1.3'
 
 
 import os.path