Merge pull request #18 from nlevitt/0.3

0.3

.travis.yml

@@ -1,8 +1,18 @@
+# http://docs.travis-ci.com/user/migrating-from-legacy/
+sudo: false
+
 language: python
 python:
-  - "2.6"
-  - "2.7"
-install: pip install -r requirements.txt
-script:
-  - py.test --doctest-modules -v surt/
-  - pylint --disable=all --enable=W0312 --reports=n surt/
+    - 2.6
+    - 2.7
+    - 3.3
+    - 3.4
+    - 3.5
+    - 3.5-dev
+    - nightly
+    - pypy
+    - pypy3
+
+install: pip install . pytest pytest-cov
+script: py.test -v --cov=surt tests/
+

README.rst

@@ -0,0 +1,37 @@
+Sort-friendly URI Reordering Transform (SURT) python package.
+
+Usage:
+
+::
+
+    >>> from surt import surt
+    >>> surt("http://archive.org/goo/?a=2&b&a=1")
+    'org,archive)/goo?a=1&a=2&b'
+
+Installation:
+
+::
+
+    pip install surt
+
+Or install the dev version from git:
+
+::
+
+    pip install git+https://github.com/internetarchive/surt.git#egg=surt
+
+More information about SURTs:
+http://crawler.archive.org/articles/user\_manual/glossary.html#surt
+
+This is mostly a python port of the webarchive-commons org.archive.url
+package. The original java version of the org.archive.url package is
+here:
+https://github.com/iipc/webarchive-commons/tree/master/src/main/java/org/archive/url
+
+This module depends on the ``tldextract`` module to query the Public
+Suffix List. ``tldextract`` can be installed via ``pip``
+
+|Build Status|
+
+.. |Build Status| image:: https://travis-ci.org/internetarchive/surt.svg
+   :target: https://travis-ci.org/internetarchive/surt

setup.py

@@ -1,18 +1,39 @@
 from setuptools import setup
+from setuptools.command.test import test as TestCommand
+
+class PyTest(TestCommand):
+    def finalize_options(self):
+        TestCommand.finalize_options(self)
+        self.test_suite = True
+
+    def run_tests(self):
+        import pytest
+        import sys
+        cmdline = ' -v --cov surt tests/'
+        errcode = pytest.main(cmdline)
+        sys.exit(errcode)
+
+
 setup(name='surt',
-      version='0.2',
+      version='0.3.0',
       author='rajbot',
       author_email='[email protected]',
       classifiers=[
         'License :: OSI Approved :: GNU Affero General Public License v3',
       ],
       description='Sort-friendly URI Reordering Transform (SURT) python package.',
-      long_description=open('README.md').read(),
-      url='https://github.com/rajbot/surt',
+      long_description=open('README.rst').read(),
+      url='https://github.com/internetarchive/surt',
+      zip_safe=True,
       install_requires=[
-          'tldextract',
+          'six',
+          'tldextract>=2.0',
       ],
       provides=[ 'surt' ],
       packages=[ 'surt' ],
       scripts=[],
+      # Tests
+      tests_require=[ 'pytest', 'pytest-cov' ],
+      test_suite='',
+      cmdclass={'test': PyTest},
      )

surt/DefaultIAURLCanonicalizer.py

@@ -21,45 +21,20 @@
 
 """This is a python port of DefaultIAURLCanonicalizer.java:
 http://archive-access.svn.sourceforge.net/viewvc/archive-access/trunk/archive-access/projects/archive-commons/src/main/java/org/archive/url/DefaultIAURLCanonicalizer.java?view=markup
-
-The doctests are copied from DefaultIAURLCanonicalizerTest.java:
-http://archive-access.svn.sourceforge.net/viewvc/archive-access/trunk/archive-access/projects/archive-commons/src/test/java/org/archive/url/DefaultIAURLCanonicalizerTest.java?view=markup
 """
+from __future__ import absolute_import
+
+import surt.GoogleURLCanonicalizer
+import surt.IAURLCanonicalizer
 
-import GoogleURLCanonicalizer
-import IAURLCanonicalizer
 
 # canonicalize()
 #_______________________________________________________________________________
 def canonicalize(url, **options):
     """The input url is a handyurl instance
-
-    These doctests are from DefaultIAURLCanonicalizerTest.java:
-
-    >>> from handyurl import handyurl
-    >>> canonicalize(handyurl.parse("http://www.alexa.com/")).getURLString()
-    'http://alexa.com/'
-    >>> canonicalize(handyurl.parse("http://archive.org/index.html")).getURLString()
-    'http://archive.org/index.html'
-    >>> canonicalize(handyurl.parse("http://archive.org/index.html?")).getURLString()
-    'http://archive.org/index.html'
-    >>> canonicalize(handyurl.parse("http://archive.org/index.html?a=b")).getURLString()
-    'http://archive.org/index.html?a=b'
-    >>> canonicalize(handyurl.parse("http://archive.org/index.html?b=b&a=b")).getURLString()
-    'http://archive.org/index.html?a=b&b=b'
-    >>> canonicalize(handyurl.parse("http://archive.org/index.html?b=a&b=b&a=b")).getURLString()
-    'http://archive.org/index.html?a=b&b=a&b=b'
-    >>> canonicalize(handyurl.parse("http://www34.archive.org/index.html?b=a&b=b&a=b")).getURLString()
-    'http://archive.org/index.html?a=b&b=a&b=b'
     """
 
-    url = GoogleURLCanonicalizer.canonicalize(url, **options)
-    url = IAURLCanonicalizer.canonicalize(url, **options)
+    url = surt.GoogleURLCanonicalizer.canonicalize(url, **options)
+    url = surt.IAURLCanonicalizer.canonicalize(url, **options)
 
     return url
-
-# main()
-#_______________________________________________________________________________
-if __name__ == "__main__":
-    import doctest
-    doctest.testmod()