Function test_extendable_textpage

tests/test_textextract.py:664–846

()

def test_extendable_textpage():
    
    # 2025-01-28:
    #
    # We can create a pdf with two pages whose text is adjacent when stitched
    # together vertically:
    #
    # Page 1:
    # 
    #     aaaa
    #    
    #     bbbb
    #     cccc
    #     
    #     dddd
    #     
    # Page 2:
    #     
    #     eeee
    #     
    #     ffff
    #     gggg
    #     
    #     hhhh
    #
    #
    # Create a textpage for both of these pages. Then when extracting text,
    # we need to get (specifically the `dddd` and `eeee` sequences need to be
    # treated as the same block):
    #
    #     aaaa
    #    
    #     bbbb
    #     cccc
    #     
    #     dddd
    #     eeee
    #     
    #     ffff
    #     gggg
    #     
    #     hhhh
    #
    print()
    
    path = os.path.normpath(f'{__file__}/../../tests/test_extendable_textpage.pdf')
    with pymupdf.open(filetype='pdf') as document:
        document.new_page()
        document.new_page()
        page0 = document[0]
        page1 = document[1]
        y = 100
        line_height = 9.6
        for i in range(4):
            page0.insert_text((100, y+line_height), 'abcd'[i] * 16)
            page1.insert_text((100, y+line_height), 'efgh'[i] * 16)
            y += line_height
            if i%2 == 0: