File size: 5,697 Bytes
f2fb12f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c562ed5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Tests for data loading functionality."""

import pytest
import pandas as pd
from pathlib import Path

import sys
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))

from phising_detection.data import load_phishing_urls


class TestLoadPhishingUrls:
    """Tests for load_phishing_urls function."""

    def test_load_phishing_urls_basic(self, temp_phishing_file, sample_phishing_urls):
        """Test basic loading of phishing URLs."""
        df = load_phishing_urls(temp_phishing_file)

        # Check DataFrame shape
        assert len(df) == len(sample_phishing_urls)
        assert df.shape[1] == 3  # url_id, url, is_phishing

        # Check column names
        assert list(df.columns) == ['url_id', 'url', 'is_phishing']

        # Check data types
        assert df['url_id'].dtype == 'int64'
        assert df['url'].dtype == 'object'
        assert df['is_phishing'].dtype == 'int64'

    def test_load_phishing_urls_content(self, temp_phishing_file, sample_phishing_urls):
        """Test that URLs are loaded correctly."""
        df = load_phishing_urls(temp_phishing_file)

        # Check URLs match
        assert df['url'].tolist() == sample_phishing_urls

        # Check url_ids are sequential
        assert df['url_id'].tolist() == list(range(len(sample_phishing_urls)))

        # Check all are labeled as phishing
        assert all(df['is_phishing'] == 1)

    def test_load_phishing_urls_with_label_false(self, temp_phishing_file):
        """Test loading URLs without phishing label."""
        df = load_phishing_urls(temp_phishing_file, is_phishing=False)

        # Check that is_phishing is 0
        assert all(df['is_phishing'] == 0)

    def test_load_phishing_urls_file_not_found(self):
        """Test error handling for non-existent file."""
        with pytest.raises(FileNotFoundError) as exc_info:
            load_phishing_urls("non_existent_file.txt")

        assert "File not found" in str(exc_info.value)

    def test_load_phishing_urls_empty_file(self, temp_empty_file):
        """Test loading from empty file."""
        df = load_phishing_urls(temp_empty_file)

        # Should return empty DataFrame with correct columns
        assert len(df) == 0
        assert list(df.columns) == ['url_id', 'url', 'is_phishing']

    def test_load_phishing_urls_with_blank_lines(
        self, temp_file_with_blank_lines, sample_phishing_urls
    ):
        """Test that blank lines are filtered out."""
        df = load_phishing_urls(temp_file_with_blank_lines)

        # Should only have 4 URLs (blank lines removed)
        assert len(df) == 4

        # Check that only non-empty URLs are present
        assert sample_phishing_urls[0] in df['url'].values
        assert sample_phishing_urls[1] in df['url'].values
        assert sample_phishing_urls[2] in df['url'].values
        assert sample_phishing_urls[3] in df['url'].values

    def test_load_phishing_urls_pathlib_path(self, temp_phishing_file):
        """Test that function accepts pathlib.Path objects."""
        path = Path(temp_phishing_file)
        df = load_phishing_urls(path)

        assert isinstance(df, pd.DataFrame)
        assert len(df) > 0

    def test_load_phishing_urls_string_path(self, temp_phishing_file):
        """Test that function accepts string paths."""
        df = load_phishing_urls(str(temp_phishing_file))

        assert isinstance(df, pd.DataFrame)
        assert len(df) > 0

    def test_load_phishing_urls_returns_dataframe(self, temp_phishing_file):
        """Test that function returns a pandas DataFrame."""
        result = load_phishing_urls(temp_phishing_file)

        assert isinstance(result, pd.DataFrame)

    def test_load_phishing_urls_url_id_uniqueness(self, temp_phishing_file):
        """Test that url_id values are unique."""
        df = load_phishing_urls(temp_phishing_file)

        assert df['url_id'].is_unique
        assert len(df['url_id'].unique()) == len(df)


class TestLoadLegitimateUrls:
    """Tests for loading legitimate URLs using load_phishing_urls with is_phishing=False."""

    def test_load_legitimate_urls_basic(self, temp_legitimate_file, sample_legitimate_urls):
        """Test basic loading of legitimate URLs."""
        df = load_phishing_urls(temp_legitimate_file, is_phishing=False)

        # Check DataFrame shape
        assert len(df) == len(sample_legitimate_urls)
        assert df.shape[1] == 3  # url_id, url, is_phishing

        # Check all are labeled as non-phishing
        assert all(df['is_phishing'] == 0)

    def test_load_legitimate_urls_content(self, temp_legitimate_file, sample_legitimate_urls):
        """Test that legitimate URLs are loaded correctly."""
        df = load_phishing_urls(temp_legitimate_file, is_phishing=False)

        # Check URLs match
        assert df['url'].tolist() == sample_legitimate_urls

        # Check url_ids are sequential
        assert df['url_id'].tolist() == list(range(len(sample_legitimate_urls)))

    def test_combined_phishing_and_legitimate(
        self, temp_phishing_file, temp_legitimate_file
    ):
        """Test loading and combining phishing and legitimate URLs."""
        phishing_df = load_phishing_urls(temp_phishing_file, is_phishing=True)
        legitimate_df = load_phishing_urls(temp_legitimate_file, is_phishing=False)

        # Combine datasets
        combined_df = pd.concat([phishing_df, legitimate_df], ignore_index=True)

        # Check that we have both types
        assert (combined_df['is_phishing'] == 1).sum() == len(phishing_df)
        assert (combined_df['is_phishing'] == 0).sum() == len(legitimate_df)
        assert len(combined_df) == len(phishing_df) + len(legitimate_df)