Updating setup for version 0.1.0

README

@@ -2,7 +2,7 @@
 summa - textrank
 ================
 
-TextRank_ implementation for text summarization and keyword extraction in Python. An online version can be tested `here <http://104.131.76.203>`_.
+TextRank_ implementation for text summarization and keyword extraction in Python.
 
 .. _TextRank: http://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf
 
@@ -46,24 +46,19 @@ Installation
 ------------
 
 This software depends on `NumPy and Scipy <http://www.scipy.org/Download>`_, two Python packages for scientific computing.
-You must have them installed prior to installing `summa`::
+Pip will automatically install them along with `summa`::
 
     pip install summa
 
-
-If you are going to use the export function, you also need `NetworkX <https://networkx.github.io/download.html>`_.
 For a better performance of keyword extraction, install `Pattern <http://www.clips.ua.ac.be/pattern>`_
 
-This version has been tested under Python 2.7
-
 
 More examples
 -------------
 
 - Command-line usage::
 
-    cd path/to/folder/summa/
-    python textrank.py -t FILE
+    textrank -t FILE
 
 - Define length of the summary as a proportion of the text (also available in :code:`keywords`)::
 

setup.py

@@ -1,25 +1,26 @@
-from distutils.core import setup
+from setuptools import setup, find_packages
 
 setup(
     name = 'summa',
-    packages = ['summa', 'summa.preprocessing'],
+    packages = find_packages(exclude=['test']),
     package_data = {
         'summa': ['README', 'LICENSE']
     },
     version = '0.1.0',
-    description = 'A text summarization and keyword extraction package',
+    description = 'A text summarization and keyword extraction package based on textrank',
+    long_description=open('README').read(),
     author = 'Federico Barrios, Federico Lopez',
     author_email = '[email protected]',
     url = 'https://github.com/summanlp/textrank',
     download_url = 'https://github.com/summanlp/textrank/tarball/v0.1.0',
     keywords = ['summa', 'nlp', 'summarization', "NLP", "natural language processing", "automatic summarization",
         "keywords", "summary", "textrank", "pagerank"],
+    install_requires = [
+        'scipy >= 0.19'
+    ],
+    python_requires = '>=2.7, <3.0',
     classifiers = [
-        # How mature is this project? Common values are
-        #   3 - Alpha
-        #   4 - Beta
-        #   5 - Production/Stable
-        'Development Status :: 4 - Beta',
+        'Development Status :: 5 - Production/Stable',
 
         'License :: OSI Approved :: MIT License',
 
@@ -29,9 +30,13 @@
         'Topic :: Scientific/Engineering :: Information Analysis',
         'Topic :: Text Processing :: Linguistic',
 
-        # Specify the Python versions you support here. In particular, ensure
-        # that you indicate whether you support Python 2, Python 3 or both.
-        'Programming Language :: Python :: 2.7'
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 2 :: Only'
     ],
-    long_description = open('README').read()
+    test_suite="test",
+    entry_points={
+       'console_scripts': [
+           'textrank = summa.textrank:main',
+       ],
+    }
 )

summa/textrank.py

@@ -9,13 +9,17 @@
 WORD = 1
 
 
+def exit_with_error(err):
+    print "Error: " + str(err)
+    usage()
+    sys.exit(2)
+
 def get_arguments():
     try:
         opts, args = getopt.getopt(sys.argv[1:], "t:s:r:w:h", ["text=", "summary=", "ratio=", "words=", "help"])
     except getopt.GetoptError as err:
-        print str(err)
-        usage()
-        sys.exit(2)
+        exit_with_error(err)
+
     path = None
     summarize_by = SENTENCE
     ratio = 0.2
@@ -35,10 +39,13 @@ def get_arguments():
         else:
             assert False, "unhandled option"
 
+    if path is None:
+        exit_with_error("-t option is required.")
+
     return path, summarize_by, ratio, words
 
 
-help_text = """Usage: python textrank.py -t FILE
+help_text = """Usage: textrank -t FILE
 -s UNIT, --summary=UNIT:
 \tType of unit to summarize: sentence (0) or word (1). Default value: 0
 \t0: Sentence. 1: Word