File size: 5,058 Bytes
1ce1659
 
 
 
 
 
0542c93
1ce1659
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
from collections import Counter
import os
import string
import requests
from dotenv import load_dotenv
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from sklearn.feature_extraction.text import TfidfVectorizer

from src.application.text.identity import extract_entities

load_dotenv() 
GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
SEARCH_ENGINE_ID = os.getenv("SEARCH_ENGINE_ID")

def search_by_google(
    query, 
    num_results=10,
    is_exact_terms = False
    ) -> dict:
    """
    Searches the Google Custom Search Engine for the given query.

    Args:
        query: The search query.
        is_exact_terms: Whether to use exact terms search (True) or regular search (False).
        num_results: The number of results to return (default: 10).

    Returns:
        A dictionary containing the search results or None if there was an error.
    """
    
    url = "https://www.googleapis.com/customsearch/v1"
    params = {
        "key": GOOGLE_API_KEY,
        "cx": SEARCH_ENGINE_ID,
        "num": num_results,
    }
    if is_exact_terms:
        params["exactTerms"] = query
    else:
        params["q"] = query.replace('"', "")
    
    response = requests.get(url, params=params)
    if response.status_code == 200:
        return response.json()
    else:
        print(f"Error: {response.status_code}, {response.text}")
        return None

def get_most_frequent_words(input_text, number_word=32):
    """
    Gets the top words from the input text, excluding stop words and punctuation.

    Args:
        input_text: The input text as a string.
        number_word: The number of top words to return.

    Returns:
        A list of tuples, where each tuple contains a word and its frequency.
        Returns an empty list if input is not a string or is empty.
    """
    if not isinstance(input_text, str) or not input_text:
        return []

    words = word_tokenize(input_text.lower())  # Tokenize and lowercase

    stop_words = set(stopwords.words('english'))
    punctuation = set(string.punctuation) # get all punctuation
    filtered_words = [
        word for word in words
        if word.isalnum() and word not in stop_words and word not in punctuation
    ]
    word_frequencies = Counter(filtered_words)
    top_words = word_frequencies.most_common(number_word)
    
    for top_word in top_words:
        words.append(top_word[0])
    
    if len(words) > 32:
        search_phrase = " ".join(words[:32])
    else:
        search_phrase = " ".join(words[:number_word])

    return search_phrase

def get_chunk(input_text, chunk_length=32, num_chunk=3):
    """
    Splits the input text into chunks of a specified length.

    Args:
        input_text: The input text as a string.
        num_chunk: The maximum number of chunks to create.
        chunk_length: The desired length of each chunk (in words).

    Returns:
        A list of string chunks. 
        Returns an empty list if input is invalid.
    """
    if not isinstance(input_text, str):
        return []

    chunks = []
    input_words = input_text.split()  # Split by any whitespace

    for i in range(num_chunk):
        start_index = i * chunk_length
        end_index = (i + 1) * chunk_length
        chunk = " ".join(input_words[start_index:end_index])
        if chunk:  # Only append non-empty chunks
            chunks.append(chunk)

    return chunks

def get_keywords(text, num_keywords=5):
    """Return top k keywords from a doc using TF-IDF method"""
    
    # Create a TF-IDF Vectorizer
    vectorizer = TfidfVectorizer(stop_words='english')
    
    # Fit and transform the text
    tfidf_matrix = vectorizer.fit_transform([text])
    
    # Get feature names (words)
    feature_names = vectorizer.get_feature_names_out()
    
    # Get TF-IDF scores
    tfidf_scores = tfidf_matrix.toarray()[0]
    
    # Sort words by TF-IDF score
    word_scores = list(zip(feature_names, tfidf_scores))
    word_scores.sort(key=lambda x: x[1], reverse=True)
    
    # Return top keywords
    return [word for word, score in word_scores[:num_keywords]]


def generate_search_phrases(input_text):
    """
    Generates different types of phrases for search purposes.

    Args:
        input_text: The input text.

    Returns:
        A list containing:
        - A list of most frequent words.
        - The original input text.
        - A list of text chunks.
    """
    if not isinstance(input_text, str):
        return []
    
    search_phrases = []
    
    # Method 1: Get most frequent words
    search_phrases.append(get_most_frequent_words(input_text))
    
    # Method 2: Get the whole text
    search_phrases.append(input_text)
    
    # Method 3: Split text by chunks
    search_phrases.extend(get_chunk(input_text))
    
    # Method 4: Get most identities and key words
    entities = extract_entities(input_text)
    keywords = get_keywords(input_text, 16)
    search_phrase = " ".join(entities) + " " + " ".join(keywords)
    search_phrases.append(search_phrase)
    
    return search_phrases