feat: add pre commit to repo

.github/workflows/ci.yml

@@ -36,4 +36,4 @@ jobs:
         flake8
         pylint scripts/ --rcfile=setup.cfg --fail-under=9
         mypy -p scripts --ignore-missing-imports --disallow-incomplete-defs
-    continue-on-error: true  # This is equivalent to allow_failure in GitLab CI
+    continue-on-error: true

.pre-commit-config.yaml

@@ -0,0 +1,30 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.4.0
+    hooks:
+      - id: black
+        args: ['--line-length=120', '--verbose']
+
+  - repo: https://github.com/pycqa/flake8
+    rev: '7.0.0'
+    hooks:
+      - id: flake8
+
+  - repo: https://github.com/pre-commit/mirrors-pylint
+    rev: v3.0.0a5
+    hooks:
+      - id: pylint
+        name: pylint
+        entry: pylint
+        language: system
+        args: ['.', '--rcfile=setup.cfg', '--fail-under=8']
+        types: [python]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.9.0
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: python3 -m mypy
+        args: ['--explicit-package-bases', '--ignore-missing-imports', '--disallow-incomplete-defs']
+        language: system

scripts/html_utils.py

@@ -5,6 +5,7 @@
 It returns colors depending on the similarity score.
 
 """
+
 import difflib
 from operator import itemgetter
 from typing import List, Tuple

scripts/html_writing.py

@@ -6,6 +6,7 @@
 It inserts comparison results in corresponding html files
 
 """
+
 from os import fsync, rename, path
 from random import randint
 from shutil import copy

scripts/processing_files.py

@@ -1,4 +1,5 @@
 """ This module is used to process text in docx, odt, txt and pdf files """
+
 import re
 import zipfile
 from os import path

scripts/similarity.py

@@ -7,6 +7,7 @@
 - overlapping words
 
 """
+
 import difflib
 
 from utils import remove_numbers, remove_stop_words, lemmatize

scripts/utils.py

@@ -6,6 +6,7 @@
 It can lemmatize, remove stop words, remove numbers for text processing
 
 """
+
 import argparse
 from os import path, listdir
 from time import sleep

tests/scripts/test_utils.py

@@ -12,12 +12,22 @@
 
 
 class TestUtils(unittest.TestCase):
+    """
+    Tests utils.py
+    """
+
     @classmethod
     def setUpClass(cls):
+        """
+        Sets up the test class.
+        """
         # Download NLTK stopwords
         nltk.download("stopwords")
 
     def test_parse_options(self):
+        """
+        Tests parse_options()
+        """
         # Mock the arguments and test the parse_options function
         test_args = ["program", "input_dir", "-o", "output_dir", "-s", "5"]
         with patch("sys.argv", test_args):
@@ -27,44 +37,65 @@ def test_parse_options(self):
             self.assertEqual(args.block_size, 5)
 
     def test_is_float(self):
+        """
+        Tests is_float()
+        """
         # Test cases for is_float function
         self.assertTrue(is_float(3.14))
         self.assertFalse(is_float(-1))
         self.assertFalse(is_float("not a float"))
 
     def test_wait_for_file(self):
+        """
+        Tests wait_for_file()
+        """
         # Test the wait_for_file function with a mock path.isfile
         with patch("os.path.isfile", return_value=True):
             self.assertTrue(wait_for_file("dummy_file"))
 
     def test_remove_numbers(self):
+        """
+        Tests remove_numbers()
+        """
         # Test the remove_numbers function
         words_list = ["hello", "world", 123, 4.56]
         expected = ["hello", "world"]
         self.assertEqual(remove_numbers(words_list), expected)
 
     def test_remove_stop_words(self):
+        """
+        Tests remove_stop_words()
+        """
         # Test the remove_stop_words function
         with patch("nltk.corpus.stopwords.words", return_value=["a", "the"]):
             words_list = ["a", "quick", "brown", "fox"]
             expected = ["quick", "brown", "fox"]
             self.assertEqual(remove_stop_words(words_list), expected)
 
     def test_remove_stop_words_only_stopwords(self):
+        """
+        Tests remove_stop_words()
+        """
         # Test with only stopwords
         with patch("nltk.corpus.stopwords.words", return_value=["a", "the"]):
             words_list = ["a", "the"]
             expected = []
             self.assertEqual(remove_stop_words(words_list), expected)
 
     def test_remove_stop_words_no_stopwords(self):
+        """
+        Tests remove_stop_words()
+        """
         # Test with no stopwords
         with patch("nltk.corpus.stopwords.words", return_value=["a", "the"]):
             words_list = ["quick", "brown", "fox"]
             expected = ["quick", "brown", "fox"]
             self.assertEqual(remove_stop_words(words_list), expected)
 
     def test_lemmatize(self):
+        """
+        Tests lemmatize()
+        """
         # Test the lemmatize function
         with patch("nltk.stem.WordNetLemmatizer.lemmatize", side_effect=lambda x: x + "_lemmatized"):
             words_list = ["running", "jumps"]