1. 模块列表
  2. 函数列表
  3. bs4.dammit.contains_replacement_characters()

Python bs4.dammit 模块，contains_replacement_characters() 实例源码

我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用bs4.dammit.contains_replacement_characters()。

项目：Gank-Alfred-Workflow    作者：hujiaweibujidao    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet
        try:
            bs4.dammit.chardet = None
            with warnings.catch_warnings(record=True) as w:
                dammit = UnicodeDammit(doc)
                self.assertEqual(True, dammit.contains_replacement_characters)
                self.assertTrue(u"\ufffd" in dammit.unicode_markup)

                soup = BeautifulSoup(doc, "html.parser")
                self.assertTrue(soup.contains_replacement_characters)

                msg = w[0].message
                self.assertTrue(isinstance(msg, UnicodeWarning))
                self.assertTrue("Some characters could not be decoded" in str(msg))
        finally:
            bs4.dammit.chardet = chardet
项目：Projects    作者：it2school    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：TACTIC-Handler    作者：listyque    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：UPBGE-CommunityAddon    作者：elmeunick9    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：llk    作者：Tycx2ry    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：harbour-sailfinder    作者：DylanVanAssche    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：harbour-sailfinder    作者：DylanVanAssche    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：B.E.N.J.I.    作者：the-ethan-hunt    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：Taigabot    作者：FrozenPigs    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：flickr_downloader    作者：Denisolt    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：isar    作者：ilbers    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：catchup4kodi    作者：catchup4kodi    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：catchup4kodi    作者：catchup4kodi    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ShelbySearch    作者：Agentscreech    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：respeaker_virtualenv    作者：respeaker    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：tellmeabout.coffee    作者：billyfung    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：Price-Comparator    作者：Thejas-1    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：-PunkScan    作者：swordli    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：-PunkScan    作者：swordli    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：GUIYoutube    作者：coltking    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：gerador-horarios    作者：colobas    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：Alexa-Chatter    作者：ekt1701    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ServerlessCrawler-VancouverRealState    作者：MarcelloLins    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ServerlessCrawler-VancouverRealState    作者：MarcelloLins    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ServerlessCrawler-VancouverRealState    作者：MarcelloLins    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：amazon_order_history_scraper    作者：drewctate    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：kekescan    作者：xiaoxiaoleo    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：mibici-tools    作者：regenhans    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ip138-alfred    作者：nemoTyrant    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：mit-inspire-2018    作者：pjrule    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：slack_scholar    作者：xLeitix    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：UAGS    作者：HoraceAndTheSpider    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：youtube-trending-music    作者：ishan-nitj    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：punkspider    作者：aiwennba    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：punkspider    作者：aiwennba    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：PortalAuth    作者：sud0nick    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：yetanotherhoneypot    作者：juansacco    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：EmojiTaco    作者：jeeftor    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：alfred-smzdm    作者：MikeAfc    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：UAEConfigMaker    作者：HoraceAndTheSpider    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：4channer    作者：fellchase    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ngDownloaderAPI    作者：manishbisht    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：youdao-alfred    作者：nemoTyrant    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：alfred3-mweb-workflow    作者：DarryO    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：spiderfoot    作者：ParrotSec    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：ftcommunity-apps    作者：ftCommunity    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：open-safari-simulator-applescript    作者：realjade    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet
        try:
            bs4.dammit.chardet = None
            with warnings.catch_warnings(record=True) as w:
                dammit = UnicodeDammit(doc)
                self.assertEqual(True, dammit.contains_replacement_characters)
                self.assertTrue(u"\ufffd" in dammit.unicode_markup)

                soup = BeautifulSoup(doc, "html.parser")
                self.assertTrue(soup.contains_replacement_characters)

                msg = w[0].message
                self.assertTrue(isinstance(msg, UnicodeWarning))
                self.assertTrue("Some characters could not be decoded" in str(msg))
        finally:
            bs4.dammit.chardet = chardet
项目：Stephanie-AI    作者：Elvargy    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue("\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：AstroCoffee    作者：abhimat    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet
项目：alfred-powerthesaurus    作者：clarencecastillo    | 项目源码 | 文件源码 
def test_last_ditch_entity_replacement(self):
        # This is a UTF-8 document that contains bytestrings
        # completely incompatible with UTF-8 (ie. encoded with some other
        # encoding).
        #
        # Since there is no consistent encoding for the document,
        # Unicode, Dammit will eventually encode the document as UTF-8
        # and encode the incompatible characters as REPLACEMENT
        # CHARACTER.
        #
        # If chardet is installed, it will detect that the document
        # can be converted into ISO-8859-1 without errors. This happens
        # to be the wrong encoding, but it is a consistent encoding, so the
        # code we're testing here won't run.
        #
        # So we temporarily disable chardet if it's present.
        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
        chardet = bs4.dammit.chardet_dammit
        logging.disable(logging.WARNING)
        try:
            def noop(str):
                return None
            bs4.dammit.chardet_dammit = noop
            dammit = UnicodeDammit(doc)
            self.assertEqual(True, dammit.contains_replacement_characters)
            self.assertTrue(u"\ufffd" in dammit.unicode_markup)

            soup = BeautifulSoup(doc, "html.parser")
            self.assertTrue(soup.contains_replacement_characters)
        finally:
            logging.disable(logging.NOTSET)
            bs4.dammit.chardet_dammit = chardet