first commit

Author: Hämäläinen, Mika K

DESCRIPTION.rst

@@ -0,0 +1,26 @@
+=====================
+Korp API for Python
+=====================
+
+This library provides an easy way to query `Korp <https://spraakbanken.gu.se/swe/forskning/infrastruktur/korp/>`_ systems for language corpora. This library is brought to you by `Mika Hämäläinen <https://mikakalevi.com>`_.
+
+*****
+Usage
+*****
+You can initialise Korp with either service_name (`språkbanken <https://spraakbanken.gu.se/korp/#?lang=sv>`_, `kielipankki <https://korp.csc.fi/>`_ or `GT <http://gtweb.uit.no/korp/>`_) or url to your Korp's API interface such as https://korp.csc.fi/cgi-bin/korp.cgi .
+
+An example for getting all concordances for North Sami corpora in Giellatekno Korp for query *[pos="A"] "go" [pos="N"]*.
+
+    ``from korp import Korp``
+
+    ``korppi = Korp(service_name="GT") #uses Giellatekno``
+
+    ``corpora = korppi.list_corpora("SME") #lists corpora returns the ones starting with the North Sami language code``
+
+    ``number_of_results, concordances = korppi.all_concordances('[pos="A"] "go" [pos="N"]', corpora)``
+
+****************
+More information
+****************
+
+For more information, see `the GitHub page <https://github.com/mikahama/python-korp>`_ and `Wiki for tutorials <https://github.com/mikahama/python-korp/wiki>`_.

setup.cfg

@@ -0,0 +1,2 @@
+[bdist_wheel]
+universal=1

setup.py

@@ -0,0 +1,99 @@
+# -*- coding: utf-8 -*-
+"""A setuptools based setup module.
+See:
+https://packaging.python.org/en/latest/distributing.html
+https://github.com/pypa/sampleproject
+"""
+
+# Always prefer setuptools over distutils
+from setuptools import setup, find_packages
+# To use a consistent encoding
+from codecs import open
+from os import path
+
+here = path.abspath(path.dirname(__file__))
+
+# Get the long description from the relevant file
+with open(path.join(here, 'DESCRIPTION.rst'), encoding='utf-8') as f:
+    long_description = f.read()
+
+setup(
+    name='korp',
+
+    # Versions should comply with PEP440.  For a discussion on single-sourcing
+    # the version across setup.py and the project code, see
+    # https://packaging.python.org/en/latest/single_source_version.html
+    version='1.0.2',
+
+    description='Korp API library for Python',
+    long_description=long_description,
+
+    # The project's main homepage.
+    url='https://mikakalevi.com/nlp/python-korp/',
+
+    # Author details
+    author='Mika Hämäläinen, Dept. of  Modern Languages, University of Helsinki',
+    author_email='[email protected]',
+
+    # Choose your license
+    license='Apache License, Version 2.0',
+
+    # See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+    classifiers=[
+        # How mature is this project? Common values are
+        #   3 - Alpha
+        #   4 - Beta
+        #   5 - Production/Stable
+        'Development Status :: 5 - Production/Stable',
+
+        # Indicate who your project is intended for
+        'Intended Audience :: Developers',
+        "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',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 2.6',
+        'Programming Language :: Python :: 2.7',
+
+    ],
+
+    # What does your project relate to?
+    keywords='Korp API',
+
+    # You can just specify the packages manually here if your project is
+    # simple. Or you can use find_packages().
+    packages=["korp"],
+    package_dir={'korp': 'korp'},
+
+    # List run-time dependencies here.  These will be installed by pip when
+    # your project is installed. For an analysis of "install_requires" vs pip's
+    # requirements files see:
+    # https://packaging.python.org/en/latest/requirements.html
+    install_requires=["requests"],
+
+    # List additional groups of dependencies here (e.g. development
+    # dependencies). You can install these using the following syntax,
+    # for example:
+    # $ pip install -e .[dev,test]
+    extras_require={},
+
+    # If there are data files included in your packages that need to be
+    # installed, specify them here.  If using Python 2.6 or less, then these
+    # have to be included in MANIFEST.in as well.
+    package_data={
+        'korp': ['*.json'],
+    },
+
+    # Although 'package_data' is the preferred approach, in some case you may
+    # need to place data files outside of your packages. See:
+    # http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files # noqa
+    # In this case, 'data_file' will be installed into '<sys.prefix>/my_data'
+    data_files=[],
+
+    # To provide executable scripts, use entry points in preference to the
+    # "scripts" keyword. Entry points provide cross-platform support and allow
+    # pip to create the appropriate form of executable for the target platform.
+    entry_points={},
+)

test_uralicnlp.py

@@ -0,0 +1,11 @@
+#encoding: utf-8
+from uralicNLP import uralicApi
+print uralicApi.supported_languages()
+
+print uralicApi.analyze("voita", "fin")
+
+print uralicApi.generate("käsi+N+Sg+Par", "fin")
+
+print uralicApi.dictionary_search("car", "sms")
+
+print uralicApi.lemmatize("voita", "fin")

uralicNLP/__init__.py

@@ -0,0 +1,22 @@
+import requests
+
+api_url = "http://sanat.csc.fi:8000/smsxml/"
+
+def supported_languages():
+	return __send_request("listLanguages/", {"user": "uralicApi"})
+
+def analyze(word, language):
+	return __send_request("analyze/", {"word": word, "language": language})
+
+def generate(query, language):
+	return __send_request("generate/", {"query": query, "language": language})
+
+def dictionary_search(word, language):
+	return __send_request("search/", {"word": word, "language": language})
+
+def lemmatize(word, language):
+	return __send_request("lemmatize/", {"word": word, "language": language})
+
+def __send_request(url, data):
+	r = requests.get(api_url + url, params=data)
+	return r.json()