add ranking by frequency

Author: shmelevik

.coverage

@@ -6,11 +6,16 @@ def search(docs: list, word: str) -> list:
     """
     def preprocess(text):
         return re.sub(r'[^\w\s]', '', text).lower()
-    
+
     result = []
     word = preprocess(word)
+
     for doc in docs:
         cleaned_text = preprocess(doc['text'])
-        if word in cleaned_text.split():
-            result.append(doc['id'])
-    return result
+        word_count = cleaned_text.split().count(word)
+
+        if word_count:
+            result.append((doc['id'], word_count))
+
+    result.sort(key=lambda x: x[1], reverse=True)
+    return [id for id, _ in result]

search_engine/search_engine.py

@@ -68,12 +68,30 @@ def test_search_empty_word(self, word):
         assert search(docs, word) == [], f'Expected [], but got {search(docs, word)}'
 
 
-    def test_with_punctuation(self):
+    def test_search_word_with_punctuation(self):
         """
         Test that the search word can be with puntcuation
         """
         doc1 = {'id': 'doc1', 'text': "I can't shoot straight unless I've had a pint!"}
         docs = [doc1]
 
         assert search(docs, 'pint') == ['doc1']
-        assert search(docs, 'pint!') == ['doc1']
+        assert search(docs, 'pint!') == ['doc1']
+        
+    def test_search_ranging(self):
+        """
+        Test that the search function returns results sorted by the frequency 
+        of the search word's occurrence in the document text.
+        """
+        doc1 = "I can't shoot straight unless I've had a pint!"
+        doc2 = "Don't shoot shoot shoot that thing at me."
+        doc3 = "I'm your shooter."
+
+        docs = [
+            {'id': 'doc1', 'text': doc1},
+            {'id': 'doc2', 'text': doc2},
+            {'id': 'doc3', 'text': doc3},
+        ]
+
+        result = search(docs, 'shoot')
+        assert result == ['doc2', 'doc1']