Merge branch 'release-0.1'

DESCRIPTION.txt

@@ -0,0 +1,3 @@
+Baleen is a tool for ingesting formal natural language data from the discourse of professional and amateur writers: e.g. bloggers and news outlets. Rather than performing web scraping, Baleen focuses on data ingestion through the use of RSS feeds. It performs as much raw data collection as it can, saving data into a Mongo document store.
+
+For more, please see the full documentation at: http://baleen-ingest.readthedocs.org/en/latest/

MANIFEST.in

@@ -0,0 +1,7 @@
+include *.md
+include *.txt
+include *.yml
+include Makefile
+recursive-include docs *.md
+recursive-include docs *.jpg
+recursive-include tests *.py

baleen/__init__.py

@@ -18,14 +18,10 @@
 ## Imports
 ##########################################################################
 
+from .version import get_version
+
 ##########################################################################
-## Vesioning
+## Package Version
 ##########################################################################
 
-__version__ = (0,1,0)
-
-def get_version():
-    """
-    Returns the string containing the version number
-    """
-    return "%i.%i.%i" % __version__
+__version__ = get_version()

baleen/version.py

@@ -0,0 +1,40 @@
+# baleen.version
+# Stores version information such that it can be read by setuptools.
+#
+# Author:   Benjamin Bengfort <benjamin@bengfort.com>
+# Created:  Thu Feb 18 20:14:16 2016 -0500
+#
+# Copyright (C) 2016 Bengfort.com
+# For license information, see LICENSE.txt
+#
+# ID: version.py [] benjamin@bengfort.com $
+
+"""
+Stores version information such that it can be read by setuptools.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+__version_info__ = {
+    'major': 0,
+    'minor': 1,
+    'micro': 0,
+    'releaselevel': 'final',
+    'serial': 0,
+}
+
+
+def get_version(short=False):
+    """
+    Computes a string representation of the version from __version_info__.
+    """
+    assert __version_info__['releaselevel'] in ('alpha', 'beta', 'final')
+    vers = ["%(major)i.%(minor)i" % __version_info__, ]
+    if __version_info__['micro']:
+        vers.append(".%(micro)i" % __version_info__)
+    if __version_info__['releaselevel'] != 'final' and not short:
+        vers.append('%s%i' % (__version_info__['releaselevel'][0],
+                              __version_info__['serial']))
+    return ''.join(vers)

setup.cfg

@@ -0,0 +1,2 @@
+[metadata]
+description-file = README.md

setup.py

@@ -1,45 +1,50 @@
 #!/usr/bin/env python
 # setup
-# Setup script for baleen
+# Setup script for installing baleen
 #
 # Author:   Benjamin Bengfort <benjamin@bengfort.com>
 # Created:  Fri Sep 19 10:59:24 2014 -0400
 #
-# Copyright (C) 2014 District Data Labs
+# Copyright (C) 2014 Bengfort.com
 # For license information, see LICENSE.txt and NOTICE.md
 #
 # ID: setup.py [] benjamin@bengfort.com $
 
 """
-Setup script for baleen
+Setup script for installing baleen.
+See http://bbengfort.github.io/programmer/2016/01/20/packaging-with-pypi.html
 """
 
 ##########################################################################
 ## Imports
 ##########################################################################
 
-try:
-    from setuptools import setup
-    from setuptools import find_packages
-except ImportError:
-    raise ImportError("Could not import \"setuptools\"."
-                      "Please install the setuptools package.")
+import os
+import re
+import codecs
+
+from setuptools import setup
+from setuptools import find_packages
 
 ##########################################################################
 ## Package Information
 ##########################################################################
 
-## Discover the packages
-packages = find_packages(where=".", exclude=("tests", "bin", "docs", "fixtures",))
+## Basic information
+NAME         = "baleen"
+DESCRIPTION  = "An automated ingestion service for blogs to construct a corpus for NLP research."
+AUTHOR       = "Benjamin Bengfort"
+EMAIL        = "benjamin@bengfort.com"
+LICENSE      = "MIT"
+REPOSITORY   = "https://github.com/bbengfort/baleen"
+PACKAGE      = "baleen"
 
-## Load the requirements
-requires = []
-with open('requirements.txt', 'r') as reqfile:
-    for line in reqfile:
-        requires.append(line.strip())
+## Define the keywords
+KEYWORDS     = ('nlp', 'baleen', 'ingestion', 'blogs', 'rss')
 
 ## Define the classifiers
-classifiers = (
+## See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+CLASSIFIERS  = (
     'Development Status :: 4 - Beta',
     'Environment :: Console',
     'Intended Audience :: Developers',
@@ -53,24 +58,71 @@
     'Topic :: Utilities',
 )
 
-## Define the keywords
-keywords = ('nlp', 'baleen', 'ingestion', 'blogs', 'rss')
+## Important Paths
+PROJECT      = os.path.abspath(os.path.dirname(__file__))
+REQUIRE_PATH = "requirements.txt"
+VERSION_PATH = os.path.join(PACKAGE, "version.py")
+PKG_DESCRIBE = "DESCRIPTION.txt"
+
+## Directories to ignore in find_packages
+EXCLUDES     = (
+    "tests", "bin", "docs", "fixtures", "register", "notebooks",
+)
+
+##########################################################################
+## Helper Functions
+##########################################################################
 
+def read(*parts):
+    """
+    Assume UTF-8 encoding and return the contents of the file located at the
+    absolute path from the REPOSITORY joined with *parts.
+    """
+    with codecs.open(os.path.join(PROJECT, *parts), 'rb', 'utf-8') as f:
+        return f.read()
+
+
+def get_version(path=VERSION_PATH):
+    """
+    Reads the __init__.py defined in the VERSION_PATH to find the get_version
+    function, and executes it to ensure that it is loaded correctly.
+    """
+    namespace = {}
+    exec(read(path), namespace)
+    return namespace['get_version']()
+
+
+def get_requires(path=REQUIRE_PATH):
+    """
+    Yields a generator of requirements as defined by the REQUIRE_PATH which
+    should point to a requirements.txt output by `pip freeze`.
+    """
+    for line in read(path).splitlines():
+        line = line.strip()
+        if line and not line.startswith('#'):
+            yield line
+
+##########################################################################
 ## Define the configuration
+##########################################################################
+
 config = {
-    "name": "baleen",
-    "version": "0.1.0",
-    "description": "An automated ingestion service for blogs to construct a corpus for NLP research.",
-    "license": "MIT",
-    "author": "Benjamin Bengfort",
-    "author_email": "benjamin@bengfort.com",
-    "url": "https://github.com/bbengfort/baleen",
-    "download_url": 'https://github.com/bbengfort/baleen/tarball/v0.1.0',
-    "packages": packages,
-    "install_requires": requires,
-    "classifiers": classifiers,
-    "keywords": keywords,
-    "zip_safe": True,
+    "name": NAME,
+    "version": get_version(),
+    "description": DESCRIPTION,
+    "long_description": read(PKG_DESCRIBE),
+    "license": LICENSE,
+    "author": AUTHOR,
+    "author_email": EMAIL,
+    "maintainer": AUTHOR,
+    "maintainer_email": EMAIL,
+    "url": REPOSITORY,
+    "download_url": "{}/tarball/v{}".format(REPOSITORY, get_version()),
+    "packages": find_packages(where=PROJECT, exclude=EXCLUDES),
+    "install_requires": list(get_requires()),
+    "classifiers": CLASSIFIERS,
+    "keywords": KEYWORDS,
+    "zip_safe": False,
     "scripts": ['bin/baleen'],
 }
 

tests/__init__.py

@@ -19,6 +19,12 @@
 
 import unittest
 
+##########################################################################
+## Module Constants
+##########################################################################
+
+TEST_VERSION = "0.1" ## Also the expected version onf the package
+
 ##########################################################################
 ## Test Cases
 ##########################################################################
@@ -45,4 +51,4 @@ def test_version(self):
         Assert that the version is sane
         """
         import baleen
-        self.assertEqual("0.1.0", baleen.get_version())
+        self.assertEqual(TEST_VERSION, baleen.__version__)