ignore charset_normalizer related warning

[graingert]

No description provided.

[Kludex]

I'll add more context for future reference.

This PR solves a UserWarning that is being raised by the requests package on the latest upgrade (2.26.0, 2021-07-13).

You can find the logs below:

Show test logs

__________________________________________________________________________________________ test_router[asyncio] ___________________________________________________________________________________________
client = <starlette.testclient.TestClient object at 0x7f9fd8775220>
def test_router(client):
    response = client.get("/")
    assert response.status_code == 200
    assert response.text == "Hello, world"

    response = client.post("/")
    assert response.status_code == 405
    assert response.text == "Method Not Allowed"

    response = client.get("/foo")
    assert response.status_code == 404
    assert response.text == "Not Found"

    response = client.get("/users")
    assert response.status_code == 200
    assert response.text == "All users"

    response = client.get("/users/tomchristie")
    assert response.status_code == 200
    assert response.text == "User tomchristie"

    response = client.get("/users/me")
    assert response.status_code == 200
    assert response.text == "User fixed me"

    response = client.get("/users/tomchristie/")
    assert response.status_code == 200
    assert response.url == "http://testserver/users/tomchristie"
    assert response.text == "User tomchristie"

    response = client.get("/users/nomatch")
    assert response.status_code == 200
    assert response.text == "User nomatch"

    response = client.get("/static/123")
    assert response.status_code == 200


  assert response.text == "xxxxx"


tests/test_routing.py:149:

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/requests/models.py:865: in text

encoding = self.apparent_encoding

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/requests/models.py:735: in apparent_encoding

return chardet.detect(self.content)['encoding']

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/charset_normalizer/legacy.py:23: in detect

r = from_bytes(byte_str).best()

sequences = b'xxxxx', steps = 1, chunk_size = 5, threshold = 0.2, cp_isolation = [], cp_exclusion = [], preemptive_behaviour = True, explain = False
def from_bytes(
        sequences: bytes,
        steps: int = 5,
        chunk_size: int = 512,
        threshold: float = 0.2,
        cp_isolation: List[str] = None,
        cp_exclusion: List[str] = None,
        preemptive_behaviour: bool = True,
        explain: bool = False
) -> CharsetMatches:
    """
    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
    If there is no results, it is a strong indicator that the source is binary/not text.
    By default, the process will extract 5 blocs of 512o each to assess the mess and coherence of a given sequence.
    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.

    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
    but never take it for granted. Can improve the performance.

    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
    purpose.

    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
    """

    if not explain:
        logger.setLevel(logging.CRITICAL)
    else:
        logger.setLevel(logging.INFO)

    length = len(sequences)  # type: int

    if length == 0:
        logger.warning("Given content is empty, stopping the process very early, returning empty utf_8 str match")
        return CharsetMatches(
            [
                CharsetMatch(
                    sequences,
                    "utf_8",
                    0.,
                    False,
                    [],
                    ""
                )
            ]
        )

    if cp_isolation is not None:
        logger.warning('cp_isolation is set. use this flag for debugging purpose. '
                       'limited list of encoding allowed : %s.',
                       ', '.join(cp_isolation))
        cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
    else:
        cp_isolation = []

    if cp_exclusion is not None:
        logger.warning(
            'cp_exclusion is set. use this flag for debugging purpose. '
            'limited list of encoding excluded : %s.',
            ', '.join(cp_exclusion))
        cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
    else:
        cp_exclusion = []

    if length <= (chunk_size * steps):
        logger.warning(
            'override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.',
            steps, chunk_size, length)
        steps = 1
        chunk_size = length

    if steps > 1 and length / steps < chunk_size:
        chunk_size = int(length / steps)

    is_too_small_sequence = len(sequences) < TOO_SMALL_SEQUENCE  # type: bool
    is_too_large_sequence = len(sequences) >= TOO_BIG_SEQUENCE  # type: bool

    if is_too_small_sequence:


      warn('Trying to detect encoding from a tiny portion of ({}) byte(s).'.format(length))


E           UserWarning: Trying to detect encoding from a tiny portion of (5) byte(s).
../../../anaconda3/envs/starlette/lib/python3.8/site-packages/charset_normalizer/api.py:105: UserWarning

____________________________________________________________________________________________ test_router[trio] ____________________________________________________________________________________________
client = <starlette.testclient.TestClient object at 0x7f9fd84e2340>
def test_router(client):
    response = client.get("/")
    assert response.status_code == 200
    assert response.text == "Hello, world"

    response = client.post("/")
    assert response.status_code == 405
    assert response.text == "Method Not Allowed"

    response = client.get("/foo")
    assert response.status_code == 404
    assert response.text == "Not Found"

    response = client.get("/users")
    assert response.status_code == 200
    assert response.text == "All users"

    response = client.get("/users/tomchristie")
    assert response.status_code == 200
    assert response.text == "User tomchristie"

    response = client.get("/users/me")
    assert response.status_code == 200
    assert response.text == "User fixed me"

    response = client.get("/users/tomchristie/")
    assert response.status_code == 200
    assert response.url == "http://testserver/users/tomchristie"
    assert response.text == "User tomchristie"

    response = client.get("/users/nomatch")
    assert response.status_code == 200
    assert response.text == "User nomatch"

    response = client.get("/static/123")
    assert response.status_code == 200


  assert response.text == "xxxxx"


tests/test_routing.py:149:

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/requests/models.py:865: in text

encoding = self.apparent_encoding

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/requests/models.py:735: in apparent_encoding

return chardet.detect(self.content)['encoding']

../../../anaconda3/envs/starlette/lib/python3.8/site-packages/charset_normalizer/legacy.py:23: in detect

r = from_bytes(byte_str).best()

sequences = b'xxxxx', steps = 1, chunk_size = 5, threshold = 0.2, cp_isolation = [], cp_exclusion = [], preemptive_behaviour = True, explain = False
def from_bytes(
        sequences: bytes,
        steps: int = 5,
        chunk_size: int = 512,
        threshold: float = 0.2,
        cp_isolation: List[str] = None,
        cp_exclusion: List[str] = None,
        preemptive_behaviour: bool = True,
        explain: bool = False
) -> CharsetMatches:
    """
    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
    If there is no results, it is a strong indicator that the source is binary/not text.
    By default, the process will extract 5 blocs of 512o each to assess the mess and coherence of a given sequence.
    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.

    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
    but never take it for granted. Can improve the performance.

    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
    purpose.

    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
    """

    if not explain:
        logger.setLevel(logging.CRITICAL)
    else:
        logger.setLevel(logging.INFO)

    length = len(sequences)  # type: int

    if length == 0:
        logger.warning("Given content is empty, stopping the process very early, returning empty utf_8 str match")
        return CharsetMatches(
            [
                CharsetMatch(
                    sequences,
                    "utf_8",
                    0.,
                    False,
                    [],
                    ""
                )
            ]
        )

    if cp_isolation is not None:
        logger.warning('cp_isolation is set. use this flag for debugging purpose. '
                       'limited list of encoding allowed : %s.',
                       ', '.join(cp_isolation))
        cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
    else:
        cp_isolation = []

    if cp_exclusion is not None:
        logger.warning(
            'cp_exclusion is set. use this flag for debugging purpose. '
            'limited list of encoding excluded : %s.',
            ', '.join(cp_exclusion))
        cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
    else:
        cp_exclusion = []

    if length <= (chunk_size * steps):
        logger.warning(
            'override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.',
            steps, chunk_size, length)
        steps = 1
        chunk_size = length

    if steps > 1 and length / steps < chunk_size:
        chunk_size = int(length / steps)

    is_too_small_sequence = len(sequences) < TOO_SMALL_SEQUENCE  # type: bool
    is_too_large_sequence = len(sequences) >= TOO_BIG_SEQUENCE  # type: bool

    if is_too_small_sequence:


      warn('Trying to detect encoding from a tiny portion of ({}) byte(s).'.format(length))


E           UserWarning: Trying to detect encoding from a tiny portion of (5) byte(s).

EDIT: More specifically, this was introduced by charset_normalizer (requests dependency) on their 2.0 release here.