structuring search module

LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) <year> <copyright holders>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the Software), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED AS IS, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

entities/Article.py → search/Article.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from entities.Doc import Doc
+from search.Doc import Doc
 
 
 class Article(Doc):

entities/Review.py → search/Review.py

@@ -1,6 +1,6 @@
 import json
 from datetime import datetime
-from entities.Doc import Doc
+from search.Doc import Doc
 
 
 class Review(Doc):

search_engine.py → search/SearchEngine.py

@@ -1,11 +1,5 @@
-import os.path as path
-import sys
-import glob
-import xml.etree.ElementTree as ET
-
-from entities.Article import *
-from entities.Review import *
-from entities.Word import *
+from .Doc import *
+from .Word import *
 
 
 class SearchEngine:
@@ -71,32 +65,3 @@ def most_common(self, n:int):
         sorted_words = sorted(self.invert_tbl.values(), key=lambda word: word.total, reverse=True)
         sorted_words = [(word.key, word.total) for word in sorted_words]
         return sorted_words[:n]
-
-
-if __name__ == '__main__':
-
-    search_engine = SearchEngine(stopwords=path.abspath(sys.argv[1]))
-
-    # ./Corpus/sgml/reut2-00*.xml
-    # for file in sorted(glob.glob(path.abspath(sys.argv[2]))):
-    #     print(file)
-    #     root = ET.parse(file).getroot()
-    #     for article_xml in root.findall('REUTERS'):
-    #         article = Article(article_xml.get('NEWID'), article_xml)
-    #         search_engine.add(article)
-
-    # ./Corpus/review_data.txt
-    lines = open(path.abspath(sys.argv[2])).readlines()
-    for count, line in enumerate(lines):
-        review = Review(count, line)
-        search_engine.add(review)
-
-    search_words = ["Great", "product", "love", "happy"]
-    for word in search_words:
-        search_res = search_engine.search(word, 5)
-        print("{:20} : {:4} results.".format(word, len(search_res)))
-        print("\n".join(search_res))
-
-    print("Most Common Words")
-    for word, num_results in search_engine.most_common(10):
-        print("{:20} : {} results".format(word, num_results))

setup.py

@@ -0,0 +1,16 @@
+from setuptools import setup
+
+setup(
+    name='search-engine',
+    version='1.0.0',
+    author='Ziv Litmanowicz',
+    license='MIT',
+    description='A library for dealing with splittable files',
+    packages=['search'],
+    url='https://github.com/litmanowicziv/search-engine',
+    keywords=['search engine', 'text analysis'],
+    classifiers=[
+        'Intended Audience :: Developers',
+    ],
+    python_requires='>=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*',
+)

tests/TestDoc.py

@@ -1,5 +1,5 @@
 import unittest
-from entities.Doc import *
+from search.Doc import *
 
 
 class TestDoc(unittest.TestCase):