Merge pull request #3 from hughsie/setup

Add Setup and other minor updates for a release

.gitignore

@@ -55,3 +55,4 @@ docs/_build/
 
 # PyBuilder
 target/
+/tmp/

.travis.yml

@@ -0,0 +1,10 @@
+language: python
+
+python:
+  - 2.7.13
+
+install:
+  - sudo apt-get install cabextract
+
+script:
+  - python test.py

cabarchive/__init__.py

@@ -18,6 +18,9 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
-from file import CabFile
-from archive import CabArchive
-from errors import CorruptionError, NotSupportedError
+from __future__ import absolute_import
+from __future__ import print_function
+
+from cabarchive.file import CabFile
+from cabarchive.archive import CabArchive
+from cabarchive.errors import CorruptionError, NotSupportedError

cabarchive/archive.py

@@ -18,14 +18,17 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
+from __future__ import absolute_import
+from __future__ import print_function
+
 import os
 import struct
 import fnmatch
 import zlib
-import datetime
 
-from file import CabFile
-from errors import *
+from cabarchive.file import CabFile
+from cabarchive.errors import CorruptionError, NotSupportedError
+
 
 FMT_CFHEADER = '<4sxxxxIxxxxIxxxxBBHHHHH'
 FMT_CFFOLDER = '<IHH'
@@ -100,7 +103,7 @@ def _parse_cffile(self, offset):
 
         # debugging
         if os.getenv('PYTHON_CABARCHIVE_DEBUG'):
-            print "CFFILE", vals
+            print("CFFILE", vals)
 
         # parse filename
         offset += struct.calcsize(fmt)
@@ -137,7 +140,7 @@ def _parse_cffolder(self, idx, offset):
 
         # debugging
         if os.getenv('PYTHON_CABARCHIVE_DEBUG'):
-            print "CFFOLDER", vals
+            print("CFFOLDER", vals)
 
         # no data blocks?
         if vals[1] == 0:
@@ -159,7 +162,7 @@ def _parse_cffolder(self, idx, offset):
         # parse CDATA
         self._folder_data.append(bytearray())
         offset = vals[0]
-        for i in range(vals[1]):
+        for _ in range(vals[1]):
             offset += self._parse_cfdata(idx, offset, is_zlib)
 
     def _parse_cfdata(self, idx, offset, is_zlib):
@@ -173,7 +176,7 @@ def _parse_cfdata(self, idx, offset, is_zlib):
             raise CorruptionError(str(e))
         # debugging
         if os.getenv('PYTHON_CABARCHIVE_DEBUG'):
-            print "CFDATA", vals
+            print("CFDATA", vals)
         if not is_zlib and vals[1] != vals[2]:
             raise CorruptionError('Mismatched data %i != %i' % (vals[1], vals[2]))
         hdr_sz = struct.calcsize(fmt)
@@ -234,7 +237,7 @@ def parse(self, buf):
 
         # debugging
         if os.getenv('PYTHON_CABARCHIVE_DEBUG'):
-            print "CFHEADER", vals
+            print("CFHEADER", vals)
 
         # check magic bytes
         if vals[0] != b'MSCF':

cabarchive/errors.py

@@ -18,7 +18,13 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
+from __future__ import absolute_import
+from __future__ import print_function
+
+
 class CorruptionError(Exception):
     pass
+
+
 class NotSupportedError(Exception):
     pass

cabarchive/file.py

@@ -18,25 +18,31 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
+from __future__ import absolute_import
+from __future__ import print_function
+
 import datetime
 
+
 def _is_ascii(text):
     """ Check if a string is ASCII only """
     return all(ord(c) < 128 for c in text)
 
+
 class CabFile(object):
 
     """An object representing a file in a Cab archive """
+
     def __init__(self, filename, contents=None):
         self.filename = filename
         self.contents = contents
         self.date = datetime.date.today()
         self.time = datetime.datetime.now().time()
-        self.is_readonly = False    # file is read-only
-        self.is_hidden = False      # file is hidden
-        self.is_system = False      # file is a system file
-        self.is_arch = True         # file modified since last backup
-        self.is_exec = False        # file is executable
+        self.is_readonly = False  # file is read-only
+        self.is_hidden = False  # file is hidden
+        self.is_system = False  # file is a system file
+        self.is_arch = True  # file modified since last backup
+        self.is_exec = False  # file is executable
         self.is_name_utf8 = not _is_ascii(filename)
 
     def _attr_encode(self):

fix-checksum.py

@@ -18,14 +18,18 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
+from __future__ import absolute_import
+from __future__ import print_function
+
 import cabarchive as cab
 import struct
 import sys
 
+
 def main():
 
     if len(sys.argv) == 1:
-        print "No input files given"
+        print("No input files given")
         return 1
 
     for arg in sys.argv[1:]:
@@ -42,12 +46,13 @@ def main():
                 break
             except cab.CorruptionError as e:
                 offset = e[1]
-                buf = buf[:offset] + struct.pack('<I', e[3]) + buf[offset+4:]
+                buf = buf[:offset] + struct.pack('<I', e[3]) + buf[offset + 4:]
 
         # save file
         f = open(arg, 'wb')
         f.write(buf);
         f.close();
 
+
 if __name__ == "__main__":
     main()

setup.cfg

@@ -0,0 +1,2 @@
+[metadata]
+license_file = LICENSE

setup.py

@@ -1,7 +1,46 @@
 #!/usr/bin/env python
-import setuptools
 
-setuptools.setup(
-    name="cabarchive",
-    packages=["cabarchive"],
+from __future__ import absolute_import
+from __future__ import print_function
+
+from setuptools import setup
+
+# note: this is a repeat of the README, to evolve, good enough for now.
+long_desc = '''
+If you want to parse Microsoft Cabinet files in Python you probably
+should just install gcab, and use the GObjectIntrospection bindings
+for that. GCab is a much better library than this and handles many more
+kinds of archive.
+
+If GCab is not available to you (e.g. you're trying to run in an
+OpenShift instance on RHEL 6.2), this project might be somewhat useful.
+
+Contributors welcome, either adding new functionality or fixing bugs.
+
+See also: https://msdn.microsoft.com/en-us/library/bb417343.aspx
+'''
+
+setup(
+    name='cabarchive',
+    version='0.1.0',
+    license='LGPL-2.1-or-later',
+    description='A pure-python library for creating and extracting cab files',
+    long_description=long_desc,
+    author='Richard Hughes',
+    author_email='[email protected]',
+    url='https://github.com/hughsie/python-cabarchive',
+    packages=['cabarchive', ],
+    include_package_data=True,
+    zip_safe=False,
+    classifiers=[
+        # complete classifier list: http://pypi.python.org/pypi?%3Aaction=list_classifiers
+        'Development Status :: 4 - Beta',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+)',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2.7',
+        'Topic :: Utilities',
+        'Topic :: System :: Archiving',
+    ],
+    keywords=['cabextract', 'cab', 'archive', 'extract'],
 )

test.py

@@ -18,49 +18,50 @@
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA 02110-1301, USA
 
+from __future__ import absolute_import
+from __future__ import print_function
+
 import cabarchive as cab
 import datetime
 import subprocess
 import time
 import hashlib
 
-def check_archive(filename):
+
+def check_archive(filename, expected_rc=0):
     argv = ['cabextract', '--test', '/tmp/test.cab']
     rc = subprocess.call(argv)
-    assert rc == 0
+    assert rc == expected_rc, "invalid return code: %r" % rc
+
 
 def check_range(data, expected):
     assert data
     assert expected
     failures = 0
     if len(data) != len(expected):
-        print "different sizes, got %i expected %i" % (len(data), len(expected))
+        print("different sizes, got %i expected %i" % (len(data), len(expected)))
         failures += 1
     for i in range(0, len(data)):
         if data[i] != expected[i]:
-            print "@0x%02x got 0x%02x expected 0x%02x" % (i, data[i], expected[i])
+            print("@0x%02x got 0x%02x expected 0x%02x" % (i, data[i], expected[i]))
             failures += 1
             if failures > 10:
-                print "More than 10 failures, giving up..."
+                print("More than 10 failures, giving up...")
                 break
     assert failures == 0, "Data is not the same"
 
+
 def main():
 
     # parse junk
     arc = cab.CabArchive()
     try:
         arc.parse('hello')
-    except cab.CorruptionError as e:
+    except cab.CorruptionError:
         pass
 
     # parse junk
-    arc = cab.CabArchive()
-    arc.set_decompressor('cabextract')
-    try:
-        arc.parse('hello')
-    except cab.CorruptionError as e:
-        pass
+    check_archive('hello', expected_rc=1)
 
     # test checksum function
     csum = cab.archive._checksum_compute('hello123')
@@ -72,7 +73,7 @@ def main():
     data = open('data/random.bin').read()
     start = time.time()
     csum = cab.archive._checksum_compute(data)
-    print "profile checksum: %fms" % ((time.time() - start) * 1000)
+    print("profile checksum: %fms" % ((time.time() - start) * 1000))
 
     # parse test files
     for fn in ['data/simple.cab',
@@ -81,7 +82,7 @@ def main():
                'data/large.cab',
                'data/large-compressed.cab']:
         arc = cab.CabArchive()
-        print 'Parsing:', fn
+        print('Parsing:', fn)
         old = open(fn, 'rb').read()
         arc.parse(old)
         assert len(arc.files) == 1
@@ -173,7 +174,7 @@ def main():
     # open a folder with multiple folders
     for fn in ['data/multi-folder.cab', 'data/ddf-fixed.cab']:
         arc = cab.CabArchive()
-        print 'Parsing:', fn
+        print('Parsing:', fn)
         old = open(fn, 'rb').read()
         arc.parse(old)
         assert len(arc.files) == 2, len(arc.files)
@@ -187,5 +188,6 @@ def main():
     except cab.NotSupportedError as e:
         pass
 
+
 if __name__ == "__main__":
     main()