back to Reference (Gold) summary

Reference (Gold): chardet

Pytest Summary for test .

status	count
passed	375
xpassed	1
xfailed	6
failed	1
total	383
collected	383

Failed pytests:

disabled.gr.xml-iso-8859-7]

disabled.gr.xml-iso-8859-7]

wikitop_tr_ISO-8859-9.txt-iso-8859-9]

wikitop_tr_ISO-8859-9.txt-iso-8859-9]

file_name = 'tests/iso-8859-9-turkish/wikitop_tr_ISO-8859-9.txt'
encoding = 'iso-8859-9'

    @pytest.mark.parametrize("file_name, encoding", gen_test_params())
    def test_encoding_detection(file_name, encoding):
        with open(file_name, "rb") as f:
            input_bytes = f.read()
            result = chardet.detect(input_bytes)
            try:
                expected_unicode = input_bytes.decode(encoding)
            except LookupError:
                expected_unicode = ""
            try:
                detected_unicode = input_bytes.decode(result["encoding"])
            except (LookupError, UnicodeDecodeError, TypeError):
                detected_unicode = ""
        if result:
            encoding_match = (result["encoding"] or "").lower() == encoding
        else:
            encoding_match = False
        # Only care about mismatches that would actually result in different
        # behavior when decoding
        if not encoding_match and expected_unicode != detected_unicode:
            wrapped_expected = "\n".join(textwrap.wrap(expected_unicode, 100)) + "\n"
            wrapped_detected = "\n".join(textwrap.wrap(detected_unicode, 100)) + "\n"
            diff = "".join(
                list(
                    ndiff(
                        wrapped_expected.splitlines(True), wrapped_detected.splitlines(True)
                    )
                )[:20]
            )
            all_encodings = chardet.detect_all(input_bytes, ignore_threshold=True)
        else:
            diff = ""
            encoding_match = True
            all_encodings = [result]
>       assert encoding_match, (
            f"Expected {encoding}, but got {result} for {file_name}.  First 20 "
            f"lines of character differences: \n{diff}\n"
            f"All encodings: {pformat(all_encodings)}"
        )
E       AssertionError: Expected iso-8859-9, but got {'encoding': 'ISO-8859-1', 'confidence': 0.73, 'language': ''} for tests/iso-8859-9-turkish/wikitop_tr_ISO-8859-9.txt.  First 20 lines of character differences: 
E         - İstanbul, Türkiye'nin en kalabalık, iktisadi ve kültürel açıdan en önemli şehri.[2][3][4] İktisadi
E         ? ^                               ^                          ^              ^               ^
E         + Ýstanbul, Türkiye'nin en kalabalýk, iktisadi ve kültürel açýdan en önemli þehri.[2][3][4] Ýktisadi
E         ? ^                               ^                          ^              ^               ^
E         - büyüklük açıdan dünyada 34., nüfus açısından belediye sınırları göz önüne alınarak yapılan
E         ?            ^                         ^ ^               ^ ^    ^             ^         ^
E         + büyüklük açýdan dünyada 34., nüfus açýsýndan belediye sýnýrlarý göz önüne alýnarak yapýlan
E         ?            ^                         ^ ^               ^ ^    ^             ^         ^
E         - sıralamaya göre Avrupa'da birinci sırada gelir.[5][6]   İstanbul Türkiye'nin kuzeybatısında, Marmara
E         ?  ^                                 ^                    ^                            ^ ^
E         + sýralamaya göre Avrupa'da birinci sýrada gelir.[5][6]   Ýstanbul Türkiye'nin kuzeybatýsýnda, Marmara
E         ?  ^                                 ^                    ^                            ^ ^
E         - kıyısı ve Boğaziçi boyunca, Haliç'i de çevreleyecek şekilde kurulmuştur.[7] İstanbul kıtalararası
E         ?  ^ ^ ^      ^                                       ^              ^        ^         ^         ^
E         + kýyýsý ve Boðaziçi boyunca, Haliç'i de çevreleyecek þekilde kurulmuþtur.[7] Ýstanbul kýtalararasý
E         ?  ^ ^ ^      ^                                       ^              ^        ^         ^         ^
E         - bir şehir olup, Avrupa'daki bölümüne Avrupa Yakası veya Rumeli Yakası, Asya'daki bölümüne ise
E         ?     ^                                            ^                  ^
E         + bir þehir olup, Avrupa'daki bölümüne Avrupa Yakasý veya Rumeli Yakasý, Asya'daki bölümüne ise
E         ?     ^                                            ^                  ^
E         
E         All encodings: [{'confidence': 0.73, 'encoding': 'ISO-8859-1', 'language': ''},
E          {'confidence': 0.6997099512799791,
E           'encoding': 'ISO-8859-9',
E           'language': 'Turkish'},
E          {'confidence': 0.0728976103273897,
E           'encoding': 'windows-1255',
E           'language': 'Hebrew'},
E          {'confidence': 0.06145438079925295,
E           'encoding': 'windows-1255',
E           'language': 'Hebrew'},
E          {'confidence': 0.05435984154374254,
E           'encoding': 'windows-1251',
E           'language': 'Russian'},
E          {'confidence': 0.04977581541603081,
E           'encoding': 'MacCyrillic',
E           'language': 'Russian'},
E          {'confidence': 0.023217049356810692,
E           'encoding': 'ISO-8859-7',
E           'language': 'Greek'},
E          {'confidence': 0.023217049356810692,
E           'encoding': 'windows-1253',
E           'language': 'Greek'},
E          {'confidence': 0.010753368357922309,
E           'encoding': 'IBM855',
E           'language': 'Russian'},
E          {'confidence': 0.010000000000000009, 'encoding': 'utf-8', 'language': ''},
E          {'confidence': 0.01, 'encoding': 'CP932', 'language': 'Japanese'},
E          {'confidence': 0.01, 'encoding': 'EUC-JP', 'language': 'Japanese'},
E          {'confidence': 0.01, 'encoding': 'GB2312', 'language': 'Chinese'},
E          {'confidence': 0.01, 'encoding': 'EUC-KR', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'CP949', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'Big5', 'language': 'Chinese'},
E          {'confidence': 0.01, 'encoding': 'EUC-TW', 'language': 'Taiwan'},
E          {'confidence': 0.01, 'encoding': 'Johab', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'ISO-8859-5', 'language': 'Russian'},
E          {'confidence': 0.01, 'encoding': 'IBM866', 'language': 'Russian'},
E          {'confidence': 0.01, 'encoding': 'TIS-620', 'language': 'Thai'},
E          {'confidence': 0.0026171872740159445,
E           'encoding': 'windows-1251',
E           'language': 'Bulgarian'},
E          {'confidence': 0.0, 'encoding': 'KOI8-R', 'language': 'Russian'},
E          {'confidence': 0.0, 'encoding': 'ISO-8859-5', 'language': 'Bulgarian'},
E          {'confidence': 0.0, 'encoding': 'windows-1255', 'language': 'Hebrew'}]
E       assert False

test.py:110: AssertionError

subtitle.srt-iso-8859-9]

subtitle.srt-iso-8859-9]

file_name = 'tests/iso-8859-9-turkish/subtitle.srt', encoding = 'iso-8859-9'

    @pytest.mark.parametrize("file_name, encoding", gen_test_params())
    def test_encoding_detection(file_name, encoding):
        with open(file_name, "rb") as f:
            input_bytes = f.read()
            result = chardet.detect(input_bytes)
            try:
                expected_unicode = input_bytes.decode(encoding)
            except LookupError:
                expected_unicode = ""
            try:
                detected_unicode = input_bytes.decode(result["encoding"])
            except (LookupError, UnicodeDecodeError, TypeError):
                detected_unicode = ""
        if result:
            encoding_match = (result["encoding"] or "").lower() == encoding
        else:
            encoding_match = False
        # Only care about mismatches that would actually result in different
        # behavior when decoding
        if not encoding_match and expected_unicode != detected_unicode:
            wrapped_expected = "\n".join(textwrap.wrap(expected_unicode, 100)) + "\n"
            wrapped_detected = "\n".join(textwrap.wrap(detected_unicode, 100)) + "\n"
            diff = "".join(
                list(
                    ndiff(
                        wrapped_expected.splitlines(True), wrapped_detected.splitlines(True)
                    )
                )[:20]
            )
            all_encodings = chardet.detect_all(input_bytes, ignore_threshold=True)
        else:
            diff = ""
            encoding_match = True
            all_encodings = [result]
>       assert encoding_match, (
            f"Expected {encoding}, but got {result} for {file_name}.  First 20 "
            f"lines of character differences: \n{diff}\n"
            f"All encodings: {pformat(all_encodings)}"
        )
E       AssertionError: Expected iso-8859-9, but got {'encoding': 'ISO-8859-1', 'confidence': 0.73, 'language': ''} for tests/iso-8859-9-turkish/subtitle.srt.  First 20 lines of character differences: 
E         - 1 00:00:03,273 --> 00:00:04,416 Benim adım Abaddon.  2 00:00:04,417 --> 00:00:06,051 Cehennemin
E         ?                                         ^
E         + 1 00:00:03,273 --> 00:00:04,416 Benim adým Abaddon.  2 00:00:04,417 --> 00:00:06,051 Cehennemin
E         ?                                         ^
E         - Savaşçısı'da kim?  3 00:00:06,053 --> 00:00:07,085 Ben senin kralınım.  4 00:00:07,087 -->
E         ?     ^ ^ ^                                                        ^ ^
E         + Savaþçýsý'da kim?  3 00:00:06,053 --> 00:00:07,085 Ben senin kralýným.  4 00:00:07,087 -->
E         ?     ^ ^ ^                                                        ^ ^
E           00:00:08,353 Ona gelirsek...  5 00:00:09,824 --> 00:00:12,641 Bana yine yalan söyledin.  6
E         - 00:00:12,643 --> 00:00:14,893 Başka seçeneğim yoktu.  7 00:00:14,895 --> 00:00:20,783 Ne yani
E         ?                                 ^         ^
E         + 00:00:12,643 --> 00:00:14,893 Baþka seçeneðim yoktu.  7 00:00:14,895 --> 00:00:20,783 Ne yani
E         ?                                 ^         ^
E         - psikopat bir meleğin bedenime girmesine mi izin verdin?  8 00:00:20,785 --> 00:00:25,037 Gerçekte
E         ?                  ^
E         + psikopat bir meleðin bedenime girmesine mi izin verdin?  8 00:00:20,785 --> 00:00:25,037 Gerçekte
E         ?                  ^
E         - kim olduğunu biliyorum Gadreel.  9 00:00:25,039 --> 00:00:27,039 Yardımcın olarak sana katılmayı
E         ?         ^                                                            ^  ^                 ^    ^
E         + kim olduðunu biliyorum Gadreel.  9 00:00:25,039 --> 00:00:27,039 Yardýmcýn olarak sana katýlmayý
E         
E         All encodings: [{'confidence': 0.73, 'encoding': 'ISO-8859-1', 'language': ''},
E          {'confidence': 0.6073294729263563,
E           'encoding': 'ISO-8859-9',
E           'language': 'Turkish'},
E          {'confidence': 0.05229003972282906,
E           'encoding': 'windows-1255',
E           'language': 'Hebrew'},
E          {'confidence': 0.046634525116845425,
E           'encoding': 'MacCyrillic',
E           'language': 'Russian'},
E          {'confidence': 0.04636530721981003,
E           'encoding': 'ISO-8859-7',
E           'language': 'Greek'},
E          {'confidence': 0.04636530721981003,
E           'encoding': 'windows-1253',
E           'language': 'Greek'},
E          {'confidence': 0.043329031095888974,
E           'encoding': 'windows-1251',
E           'language': 'Russian'},
E          {'confidence': 0.038795835923389296,
E           'encoding': 'windows-1255',
E           'language': 'Hebrew'},
E          {'confidence': 0.010000000000000009, 'encoding': 'utf-8', 'language': ''},
E          {'confidence': 0.01, 'encoding': 'SHIFT_JIS', 'language': 'Japanese'},
E          {'confidence': 0.01, 'encoding': 'EUC-JP', 'language': 'Japanese'},
E          {'confidence': 0.01, 'encoding': 'GB2312', 'language': 'Chinese'},
E          {'confidence': 0.01, 'encoding': 'EUC-KR', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'CP949', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'Big5', 'language': 'Chinese'},
E          {'confidence': 0.01, 'encoding': 'EUC-TW', 'language': 'Taiwan'},
E          {'confidence': 0.01, 'encoding': 'Johab', 'language': 'Korean'},
E          {'confidence': 0.01, 'encoding': 'ISO-8859-5', 'language': 'Russian'},
E          {'confidence': 0.01, 'encoding': 'IBM866', 'language': 'Russian'},
E          {'confidence': 0.01, 'encoding': 'IBM855', 'language': 'Russian'},
E          {'confidence': 0.01, 'encoding': 'TIS-620', 'language': 'Thai'},
E          {'confidence': 0.009743324015662668,
E           'encoding': 'windows-1251',
E           'language': 'Bulgarian'},
E          {'confidence': 0.0, 'encoding': 'KOI8-R', 'language': 'Russian'},
E          {'confidence': 0.0, 'encoding': 'ISO-8859-5', 'language': 'Bulgarian'},
E          {'confidence': 0.0, 'encoding': 'windows-1255', 'language': 'Hebrew'}]
E       assert False

test.py:110: AssertionError

divxplanet.com.xml-iso-8859-9]

divxplanet.com.xml-iso-8859-9]

file_name = 'tests/iso-8859-9-turkish/divxplanet.com.xml'
encoding = 'iso-8859-9'

    @pytest.mark.parametrize("file_name, encoding", gen_test_params())
    def test_encoding_detection(file_name, encoding):
        with open(file_name, "rb") as f:
            input_bytes = f.read()
            result = chardet.detect(input_bytes)
            try:
                expected_unicode = input_bytes.decode(encoding)
            except LookupError:
                expected_unicode = ""
            try:
                detected_unicode = input_bytes.decode(result["encoding"])
            except (LookupError, UnicodeDecodeError, TypeError):
                detected_unicode = ""
        if result:
            encoding_match = (result["encoding"] or "").lower() == encoding
        else:
            encoding_match = False
        # Only care about mismatches that would actually result in different
        # behavior when decoding
        if not encoding_match and expected_unicode != detected_unicode:
            wrapped_expected = "\n".join(textwrap.wrap(expected_unicode, 100)) + "\n"
            wrapped_detected = "\n".join(textwrap.wrap(detected_unicode, 100)) + "\n"
            diff = "".join(
                list(
                    ndiff(
                        wrapped_expected.splitlines(True), wrapped_detected.splitlines(True)
                    )
                )[:20]
            )
            all_encodings = chardet.detect_all(input_bytes, ignore_threshold=True)
        else:
            diff = ""
            encoding_match = True
            all_encodings = [result]
>       assert encoding_match, (
            f"Expected {encoding}, but got {result} for {file_name}.  First 20 "
            f"lines of character differences: \n{diff}\n"
            f"All encodings: {pformat(all_encodings)}"
        )
E       AssertionError: Expected iso-8859-9, but got {'encoding': 'ISO-8859-1', 'confidence': 0.73, 'language': ''} for tests/iso-8859-9-turkish/divxplanet.com.xml.  First 20 lines of character differences: 
E               http://divxplanet.com DiVXPLanet.com Son
E           Altyazilarhttp://divxplanet.com/sub/s/307345/Arctic-Air.htmlArctic
E         ?       ^ ^
E         + altyazýsýhttp://divxplanet.com/sub/s/307345/Arctic-Air.htmlArctic
E         ?       ^ ^
E         - Air English 1 CD altyazısıhttp://divxplanet.com/sub/s/307344/Two-Lane-
E         ?       ^ ^
E         + altyazýsýhttp://divxplanet.com/sub/s/307344/Two-Lane-
E         ?       ^ ^
E           Blacktop.htmlTwo-Lane Blacktop Türkçe 1 CD
E         - altyazısı