{
"provenance": {
"source": "REAL thefuzz (not derived)",
"thefuzz_version": "0.22.1",
"rapidfuzz_version": "3.14.5",
"python_version": "3.14.7",
"generator": "genvec.py",
"notes": "expected_score values are exact integers as returned by thefuzz; scorer defaults: ratio/partial_ratio never preprocess; token/Q/W scorers use full_process with force_ascii=True unless the function name says otherwise.",
"amendment_1": {
"date": "2026-08-21",
"source": "REAL thefuzz (not derived)",
"thefuzz_version": "0.22.1",
"rapidfuzz_version": "3.14.5",
"generator": "genvec_amend1.py",
"notes": "Appends 72 combining_mark scorer vectors (Mn/Mc marks: Hebrew niqqud, Arabic harakat, Devanagari matras/anusvara/virama, combining Latin U+0363-036F, Greek ypogegrammeni U+0345), 18 wratio_half_boundary vectors (12 WRatio, 6 UWRatio) pinning normalized [0,1]-space composite scoring, and 18 full_process_cases for the same mark inputs. Every entry carries amendment: 1 and a provenance string. Pinned pre-amendment entries are unchanged."
}
},
"vector_count": 490,
"vectors": [
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "WRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new york mets",
"function": "QRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "ratio",
"expected_score": 69
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "partial_ratio",
"expected_score": 69
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "WRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "new york mets",
"input_b": "new YORK mets",
"function": "QRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "ratio",
"expected_score": 97
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "WRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "this is a test",
"input_b": "this is a test!",
"function": "QRatio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "ratio",
"expected_score": 91
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "partial_ratio",
"expected_score": 93
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "WRatio",
"expected_score": 95
},
{
"category": "ascii",
"input_a": "fuzzy wuzzy was a bear",
"input_b": "wuzzy fuzzy was a bear",
"function": "QRatio",
"expected_score": 91
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "ratio",
"expected_score": 72
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "partial_ratio",
"expected_score": 86
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "token_sort_ratio",
"expected_score": 72
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "token_set_ratio",
"expected_score": 72
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "partial_token_sort_ratio",
"expected_score": 86
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "partial_token_set_ratio",
"expected_score": 86
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "WRatio",
"expected_score": 77
},
{
"category": "ascii",
"input_a": "mysmilarstring",
"input_b": "myawfullysimilarstirng",
"function": "QRatio",
"expected_score": 72
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "partial_ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "token_sort_ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "partial_token_sort_ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "WRatio",
"expected_score": 0
},
{
"category": "ascii",
"input_a": "abcd",
"input_b": "XYZ",
"function": "QRatio",
"expected_score": 0
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "WRatio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "identical",
"input_b": "identical",
"function": "QRatio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "WRatio",
"expected_score": 100
},
{
"category": "identical",
"input_a": "a",
"input_b": "a",
"function": "QRatio",
"expected_score": 100
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "ratio",
"expected_score": 100
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "WRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "",
"function": "QRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "partial_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "partial_token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "WRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "",
"input_b": "nonempty",
"function": "QRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "partial_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "partial_token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "WRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": "some text",
"input_b": "",
"function": "QRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "partial_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "partial_token_sort_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "WRatio",
"expected_score": 0
},
{
"category": "empty",
"input_a": " ",
"input_b": "punct!!!",
"function": "QRatio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "partial_ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "token_sort_ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "partial_token_sort_ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "WRatio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "qwrt",
"input_b": "zxcv",
"function": "QRatio",
"expected_score": 0
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "ratio",
"expected_score": 23
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "partial_ratio",
"expected_score": 35
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "token_sort_ratio",
"expected_score": 31
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "token_set_ratio",
"expected_score": 31
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "partial_token_sort_ratio",
"expected_score": 35
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "partial_token_set_ratio",
"expected_score": 35
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "WRatio",
"expected_score": 29
},
{
"category": "disjoint",
"input_a": "one two three",
"input_b": "four five six",
"function": "QRatio",
"expected_score": 23
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "ratio",
"expected_score": 44
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "token_sort_ratio",
"expected_score": 44
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "WRatio",
"expected_score": 90
},
{
"category": "substring",
"input_a": "test",
"input_b": "this is a test",
"function": "QRatio",
"expected_score": 44
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "ratio",
"expected_score": 47
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "token_sort_ratio",
"expected_score": 47
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "WRatio",
"expected_score": 90
},
{
"category": "substring",
"input_a": "york",
"input_b": "new york city",
"function": "QRatio",
"expected_score": 47
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "ratio",
"expected_score": 52
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "token_sort_ratio",
"expected_score": 52
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "WRatio",
"expected_score": 90
},
{
"category": "substring",
"input_a": "similar",
"input_b": "somewhat similar-ish",
"function": "QRatio",
"expected_score": 52
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "ratio",
"expected_score": 44
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "partial_ratio",
"expected_score": 56
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "token_sort_ratio",
"expected_score": 81
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "token_set_ratio",
"expected_score": 81
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "partial_token_sort_ratio",
"expected_score": 82
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "WRatio",
"expected_score": 77
},
{
"category": "token_reorder",
"input_a": "great is scala",
"input_b": "java is great",
"function": "QRatio",
"expected_score": 44
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "ratio",
"expected_score": 45
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "partial_ratio",
"expected_score": 62
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "WRatio",
"expected_score": 95
},
{
"category": "token_reorder",
"input_a": "world hello",
"input_b": "hello world",
"function": "QRatio",
"expected_score": 45
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "ratio",
"expected_score": 43
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "partial_ratio",
"expected_score": 60
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "WRatio",
"expected_score": 95
},
{
"category": "token_reorder",
"input_a": "b a c d",
"input_b": "d c b a",
"function": "QRatio",
"expected_score": 43
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "ratio",
"expected_score": 62
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "token_sort_ratio",
"expected_score": 62
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "WRatio",
"expected_score": 90
},
{
"category": "dup_token",
"input_a": "fuzzy fuzzy fuzzy bear",
"input_b": "fuzzy bear",
"function": "QRatio",
"expected_score": 62
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "ratio",
"expected_score": 62
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "partial_ratio",
"expected_score": 78
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "token_sort_ratio",
"expected_score": 69
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "partial_token_sort_ratio",
"expected_score": 82
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "WRatio",
"expected_score": 95
},
{
"category": "dup_token",
"input_a": "the the the cat",
"input_b": "the cat sat",
"function": "QRatio",
"expected_score": 62
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "ratio",
"expected_score": 84
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "token_sort_ratio",
"expected_score": 84
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "partial_token_sort_ratio",
"expected_score": 90
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "WRatio",
"expected_score": 95
},
{
"category": "token_set",
"input_a": "fuzzy was a bear",
"input_b": "fuzzy fuzzy was a bear",
"function": "QRatio",
"expected_score": 84
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "ratio",
"expected_score": 45
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "partial_ratio",
"expected_score": 62
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "WRatio",
"expected_score": 95
},
{
"category": "token_set",
"input_a": "new york mets vs atlanta braves",
"input_b": "atlanta braves vs new york mets",
"function": "QRatio",
"expected_score": 45
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "ratio",
"expected_score": 42
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "partial_ratio",
"expected_score": 59
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "token_sort_ratio",
"expected_score": 87
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "token_set_ratio",
"expected_score": 95
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "partial_token_sort_ratio",
"expected_score": 83
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "WRatio",
"expected_score": 90
},
{
"category": "token_set",
"input_a": "chicago cubs vs new york mets",
"input_b": "new york city mets - chicago cubs",
"function": "QRatio",
"expected_score": 42
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "ratio",
"expected_score": 67
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "token_sort_ratio",
"expected_score": 67
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "token_set_ratio",
"expected_score": 67
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "WRatio",
"expected_score": 90
},
{
"category": "len_asym",
"input_a": "ab",
"input_b": "abcd",
"function": "QRatio",
"expected_score": 67
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "ratio",
"expected_score": 20
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "token_sort_ratio",
"expected_score": 20
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "token_set_ratio",
"expected_score": 20
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "WRatio",
"expected_score": 60
},
{
"category": "len_asym",
"input_a": "abc",
"input_b": "abcdefghijklmnopqrstuvwxyz0",
"function": "QRatio",
"expected_score": 20
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "ratio",
"expected_score": 14
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "token_sort_ratio",
"expected_score": 14
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "WRatio",
"expected_score": 60
},
{
"category": "len_asym",
"input_a": "test",
"input_b": "this is a somewhat longer test sentence with many words",
"function": "QRatio",
"expected_score": 14
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "ratio",
"expected_score": 6
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "token_sort_ratio",
"expected_score": 6
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "token_set_ratio",
"expected_score": 6
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "WRatio",
"expected_score": 60
},
{
"category": "len_asym",
"input_a": "x",
"input_b": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"function": "QRatio",
"expected_score": 6
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "ratio",
"expected_score": 75
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "partial_ratio",
"expected_score": 86
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "token_sort_ratio",
"expected_score": 86
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "token_set_ratio",
"expected_score": 86
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "WRatio",
"expected_score": 86
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "QRatio",
"expected_score": 86
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "UWRatio",
"expected_score": 75
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "UQRatio",
"expected_score": 75
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 75
},
{
"category": "unicode_accent",
"input_a": "café",
"input_b": "cafe",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 75
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "ratio",
"expected_score": 89
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "partial_ratio",
"expected_score": 94
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "token_sort_ratio",
"expected_score": 47
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "token_set_ratio",
"expected_score": 94
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "partial_token_sort_ratio",
"expected_score": 67
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "WRatio",
"expected_score": 94
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "QRatio",
"expected_score": 94
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "UWRatio",
"expected_score": 89
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "UQRatio",
"expected_score": 89
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 89
},
{
"category": "unicode_accent",
"input_a": "über cool",
"input_b": "uber cool",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 89
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "WRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "QRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "UWRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "UQRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "naïve",
"input_b": "naïve",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "ratio",
"expected_score": 87
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "partial_ratio",
"expected_score": 91
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "WRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "QRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "UWRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "UQRatio",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_accent",
"input_a": "Ähnlichkeit",
"input_b": "ähnlichkeit!",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "ratio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "token_sort_ratio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "token_set_ratio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "WRatio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "QRatio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "UWRatio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "UQRatio",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "こんにちは世界",
"input_b": "こんにちは",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 83
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "ratio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "token_sort_ratio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "token_set_ratio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "WRatio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "QRatio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "UWRatio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "UQRatio",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "北京烤鸭",
"input_b": "北京烤鸭店",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 89
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "ratio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "partial_ratio",
"expected_score": 80
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "token_sort_ratio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "token_set_ratio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "partial_token_sort_ratio",
"expected_score": 80
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "partial_token_set_ratio",
"expected_score": 80
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "WRatio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "QRatio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "UWRatio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "UQRatio",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "서울특별시",
"input_b": "서울시",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 75
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "ratio",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "token_sort_ratio",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "token_set_ratio",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "WRatio",
"expected_score": 90
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "QRatio",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "UWRatio",
"expected_score": 90
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "UQRatio",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 60
},
{
"category": "unicode_cjk",
"input_a": "日本語のテスト",
"input_b": "テスト",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 60
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "ratio",
"expected_score": 92
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "partial_ratio",
"expected_score": 82
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "WRatio",
"expected_score": 95
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "QRatio",
"expected_score": 92
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "UWRatio",
"expected_score": 95
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "UQRatio",
"expected_score": 92
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "hello 👋 world",
"input_b": "hello world",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "ratio",
"expected_score": 50
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "partial_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "token_set_ratio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "partial_token_set_ratio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "WRatio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "QRatio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "UWRatio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "UQRatio",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "🦀🦀🦀",
"input_b": "🦀",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 0
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "ratio",
"expected_score": 36
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "partial_ratio",
"expected_score": 53
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "WRatio",
"expected_score": 95
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "QRatio",
"expected_score": 36
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "UWRatio",
"expected_score": 95
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "UQRatio",
"expected_score": 36
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_emoji",
"input_a": "rust 🦀 lang",
"input_b": "lang 🦀 rust",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "ratio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "partial_ratio",
"expected_score": 50
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "token_sort_ratio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "token_set_ratio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "partial_token_sort_ratio",
"expected_score": 50
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "partial_token_set_ratio",
"expected_score": 50
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "WRatio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "QRatio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "UWRatio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "UQRatio",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "αβγδε",
"input_b": "abγδe",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 40
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "ratio",
"expected_score": 71
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "partial_ratio",
"expected_score": 83
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "WRatio",
"expected_score": 95
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "QRatio",
"expected_score": 71
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "UWRatio",
"expected_score": 95
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "UQRatio",
"expected_score": 71
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "Здравствуй мир",
"input_b": "мир Здравствуй",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "ratio",
"expected_score": 77
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "partial_ratio",
"expected_score": 91
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "token_sort_ratio",
"expected_score": 83
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "partial_token_sort_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "partial_token_set_ratio",
"expected_score": 100
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "WRatio",
"expected_score": 95
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "QRatio",
"expected_score": 83
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "UWRatio",
"expected_score": 77
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "UQRatio",
"expected_score": 77
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "token_sort_ratio(force_ascii=False)",
"expected_score": 77
},
{
"category": "unicode_mixed",
"input_a": "éclair",
"input_b": "éclair",
"function": "token_set_ratio(force_ascii=False)",
"expected_score": 77
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "token_sort_ratio",
"expected_score": 60,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "token_set_ratio",
"expected_score": 60,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "partial_token_sort_ratio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "partial_token_set_ratio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "WRatio",
"expected_score": 73,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "QRatio",
"expected_score": 73,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "UWRatio",
"expected_score": 73,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם",
"input_b": "שלום",
"function": "UQRatio",
"expected_score": 73,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "token_sort_ratio",
"expected_score": 48,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "token_set_ratio",
"expected_score": 52,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "partial_token_sort_ratio",
"expected_score": 63,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "partial_token_set_ratio",
"expected_score": 63,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "WRatio",
"expected_score": 77,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "QRatio",
"expected_score": 77,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "UWRatio",
"expected_score": 77,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "שָׁלוֹם עֲלֵיכֶם",
"input_b": "שלום עליכם",
"function": "UQRatio",
"expected_score": 77,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "token_sort_ratio",
"expected_score": 36,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "token_set_ratio",
"expected_score": 44,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "partial_token_sort_ratio",
"expected_score": 57,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "partial_token_set_ratio",
"expected_score": 57,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "QRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "مُحَمَّدٌ",
"input_b": "محمد",
"function": "UQRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "token_sort_ratio",
"expected_score": 50,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "token_set_ratio",
"expected_score": 53,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "partial_token_sort_ratio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "partial_token_set_ratio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "WRatio",
"expected_score": 74,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "QRatio",
"expected_score": 74,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "UWRatio",
"expected_score": 74,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "اللُّغَةُ العَرَبِيَّةُ",
"input_b": "اللغة العربية",
"function": "UQRatio",
"expected_score": 74,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "token_sort_ratio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "token_set_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "partial_token_sort_ratio",
"expected_score": 80,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "partial_token_set_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "WRatio",
"expected_score": 95,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "QRatio",
"expected_score": 89,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "UWRatio",
"expected_score": 95,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "हिन्दी",
"input_b": "हिंदी",
"function": "UQRatio",
"expected_score": 89,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "token_sort_ratio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "token_set_ratio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "partial_token_sort_ratio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "partial_token_set_ratio",
"expected_score": 80,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "WRatio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "QRatio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "UWRatio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "दिल्ली",
"input_b": "दलल",
"function": "UQRatio",
"expected_score": 75,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "token_sort_ratio",
"expected_score": 35,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "token_set_ratio",
"expected_score": 35,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "partial_token_sort_ratio",
"expected_score": 50,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "partial_token_set_ratio",
"expected_score": 50,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "WRatio",
"expected_score": 71,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "QRatio",
"expected_score": 71,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "UWRatio",
"expected_score": 71,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "uͣnͤcͥiͦaͧl",
"input_b": "uncial",
"function": "UQRatio",
"expected_score": 71,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "token_sort_ratio",
"expected_score": 17,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "token_set_ratio",
"expected_score": 17,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "partial_token_sort_ratio",
"expected_score": 36,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "partial_token_set_ratio",
"expected_score": 36,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "WRatio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "QRatio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "UWRatio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"input_b": "overlaid",
"function": "UQRatio",
"expected_score": 70,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "token_sort_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "token_set_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "partial_token_sort_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "partial_token_set_ratio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "WRatio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "QRatio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "UWRatio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "combining_mark",
"input_a": "γλωσσᾳ",
"input_b": "γλωσσα",
"function": "UQRatio",
"expected_score": 100,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"category": "wratio_half_boundary",
"input_a": "xxyyxxyyy",
"input_b": " xxyxy x yy y yxxyx yx ",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "xx xx xxy ",
"input_b": "x yy x x yxyyxx ",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "xxy xx yxx yxyy yy",
"input_b": " xyxyyxy x ",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " y yyx xxx",
"input_b": " xxyyxxxyyxxyxyyyxxxxxyy ",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " xyy xx yxy xxyy yxy",
"input_b": " x xxxxy y",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " yyx y y x",
"input_b": " xy xyxxy xyy xy",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " yy yxyyxy",
"input_b": "xy xy x xxy yyy",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "xxy xxx y y",
"input_b": " xyyyyyyxyx xyxyyyxyxxy x x x",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "yxyyxxy x",
"input_b": "xyxxx xyx y",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " x yyyy xy xx y yyyxx ",
"input_b": "yxy yxxyxy",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "yyyxxxxy yyx y",
"input_b": "xyy yxyxyy",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "x yxxyx y",
"input_b": "xx xyyyy yxxxxxx yxx ",
"function": "WRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " yyyyyāy yy xy yyyxyxxyx ",
"input_b": "ā xxy y y y",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "āyxx y xxyyx xy yxx x x x",
"input_b": " ā xyx yyx ",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " yāx yxyxy",
"input_b": "āxxxy yxy yy y yxx xx",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": " āyxx xyxyxx yxyy xxx x",
"input_b": " yy yy āyy xx",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "āyy yy yxy y y y ",
"input_b": "yyyyy ā x",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
},
{
"category": "wratio_half_boundary",
"input_a": "āx y xx yy xx yxxx y xy",
"input_b": " yyyāx yxy",
"function": "UWRatio",
"expected_score": 67,
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "[0,100]-space arithmetic yields 66"
}
],
"full_process_cases": [
{
"input": "Lorem Ipsum!!! 123",
"force_ascii": true,
"output": "lorem ipsum 123"
},
{
"input": " spaced\tout ",
"force_ascii": true,
"output": "spaced out"
},
{
"input": "Café-au-lait №5",
"force_ascii": true,
"output": "caf au lait 5"
},
{
"input": "Café-au-lait №5",
"force_ascii": false,
"output": "café au lait 5"
},
{
"input": "北京 Beijing!",
"force_ascii": true,
"output": "北京 beijing"
},
{
"input": "北京 Beijing!",
"force_ascii": false,
"output": "北京 beijing"
},
{
"input": "ÀÉÎÕÜ",
"force_ascii": true,
"output": ""
},
{
"input": "ÀÉÎÕÜ",
"force_ascii": false,
"output": "àéîõü"
},
{
"input": "__under_score__",
"force_ascii": true,
"output": "under score"
},
{
"input": "שָׁלוֹם",
"force_ascii": true,
"output": "ש לו ם",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"input": "שָׁלוֹם",
"force_ascii": false,
"output": "ש לו ם",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_word"
},
{
"input": "שָׁלוֹם עֲלֵיכֶם",
"force_ascii": true,
"output": "ש לו ם ע ל יכ ם",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"input": "שָׁלוֹם עֲלֵיכֶם",
"force_ascii": false,
"output": "ש לו ם ע ל יכ ם",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "hebrew_niqqud_phrase"
},
{
"input": "مُحَمَّدٌ",
"force_ascii": true,
"output": "م ح م د",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"input": "مُحَمَّدٌ",
"force_ascii": false,
"output": "م ح م د",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_word"
},
{
"input": "اللُّغَةُ العَرَبِيَّةُ",
"force_ascii": true,
"output": "الل غ ة الع ر ب ي ة",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"input": "اللُّغَةُ العَرَبِيَّةُ",
"force_ascii": false,
"output": "الل غ ة الع ر ب ي ة",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "arabic_harakat_phrase"
},
{
"input": "हिन्दी",
"force_ascii": true,
"output": "ह न द",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"input": "हिन्दी",
"force_ascii": false,
"output": "ह न द",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_mc_mn"
},
{
"input": "दिल्ली",
"force_ascii": true,
"output": "द ल ल",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"input": "दिल्ली",
"force_ascii": false,
"output": "द ल ल",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "devanagari_matras"
},
{
"input": "uͣnͤcͥiͦaͧl",
"force_ascii": true,
"output": "u n c i a l",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"input": "uͣnͤcͥiͦaͧl",
"force_ascii": false,
"output": "u n c i a l",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0363"
},
{
"input": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"force_ascii": true,
"output": "o v e r l a i d",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"input": "oͨvͩeͪrͫlͬaͭiͮdͯ",
"force_ascii": false,
"output": "o v e r l a i d",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "combining_latin_0368_036F"
},
{
"input": "γλωσσᾳ",
"force_ascii": true,
"output": "γλωσσα",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
},
{
"input": "γλωσσᾳ",
"force_ascii": false,
"output": "γλωσσα",
"amendment": 1,
"provenance": "amendment-1: thefuzz==0.22.1 rapidfuzz==3.14.5 python 3.14.7",
"note": "greek_ypogegrammeni_0345"
}
],
"process_cases": {
"extract_default": {
"query": "brave new cubs",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"limit": 3,
"result": [
[
"new york mets vs chicago cubs",
86
],
[
"chicago cubs vs chicago white sox",
86
],
[
"braves vs mets",
57
]
]
},
"extractOne_default": {
"query": "cubs vs mets",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"result": [
"new york mets vs chicago cubs",
86
]
},
"extractOne_cutoff_none": {
"query": "zzzzzz",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"score_cutoff": 60,
"result": null
},
"extractOne_unicode": {
"query": "東京タワー",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"result": [
"東京タワー",
100
]
},
"extract_scorer_ratio": {
"query": "cubs",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"scorer": "ratio",
"limit": 2,
"result": [
[
"new york mets vs chicago cubs",
24
],
[
"braves vs mets",
22
]
]
},
"extractWithoutOrder_cutoff50": {
"query": "chicago cubs",
"choices": [
"new york mets vs chicago cubs",
"chicago cubs vs chicago white sox",
"philladelphia phillies vs atlanta braves",
"braves vs mets",
"東京タワー"
],
"score_cutoff": 50,
"result": [
[
"new york mets vs chicago cubs",
90
],
[
"chicago cubs vs chicago white sox",
90
]
]
},
"dedupe_default": {
"input": [
"Frodo Baggin",
"Frodo Baggins",
"F. Baggins",
"Samwise G.",
"Gandalf",
"Bilbo Baggins"
],
"threshold": 70,
"result": [
"Frodo Baggins",
"Gandalf",
"Samwise G."
]
},
"dedupe_no_dupes_returns_original": {
"input": [
"alpha",
"omega"
],
"threshold": 70,
"result": [
"alpha",
"omega"
]
}
}
}