utils/test_toc_processor.py

import unittest
from toc_processor import merge_same_page_headers, clean_text, parse_raw_toc_output

class TestTOCProcessor(unittest.TestCase):
    
    def test_merge_same_page_headers(self):
        # Scenario: "American Government..." (Page 31) followed by "Divided World" (Page 31)
        input_toc = [
            [1, "Chapter 1 Intro", 5],
            [1, "American Government and Politics in a Racially", 31],
            [1, "Divided World", 31], 
            [1, "Chapter 2", 57]
        ]
        
        expected_toc = [
            [1, "Chapter 1 Intro", 5],
            [1, "American Government and Politics in a Racially Divided World", 31],
            [1, "Chapter 2", 57]
        ]
        
        result = merge_same_page_headers(input_toc)
        
        print(f"\nInput: {[e[1] for e in input_toc]}")
        print(f"Result: {[e[1] for e in result]}")
        
        self.assertEqual(len(result), 3)
        self.assertEqual(result[1][1], "American Government and Politics in a Racially Divided World")
        self.assertEqual(result[1][2], 31)
        
    def test_merge_same_page_headers_mixed_levels(self):
        # Scenario: Level 1 followed by Level 2 on same page (Should NOT merge)
        input_toc = [
            [1, "Chapter 1", 10],
            [2, "Section 1.1", 10]
        ]
        
        result = merge_same_page_headers(input_toc)
        self.assertEqual(len(result), 2)
        
    def test_clean_text(self):
        dirty = "Hello\xa0World\xad"
        clean = clean_text(dirty)
        self.assertEqual(clean, "Hello World")

if __name__ == '__main__':
    unittest.main()