def test_explain_false_handler_set_behavior(self, caplog):
test_sequence = b'This is a test sequence of bytes that should be sufficient'
set_logging_handler(level=TRACE, format_string="%(message)s")
from_bytes(test_sequence, steps=1, chunk_size=50, explain=False)
assert any(
isinstance(hdl, logging.StreamHandler)
for hdl in self.logger.handlers)
for record in caplog.records:
assert record.levelname in ["Level 5", "DEBUG"]
assert "Encoding detection: ascii is most likely the one." in caplog.text
def test_alphabets_property():
best_guess = from_bytes(
"😀 Hello World! How affairs are going? 😀".encode("utf_8")).best()
assert "Basic Latin" in best_guess.alphabets
assert "Emoticons range(Emoji)" in best_guess.alphabets
assert best_guess.alphabets.count("Basic Latin") == 1
def test_empty_but_with_bom_or_sig(payload, expected_encoding):
best_guess = from_bytes(payload).best()
assert best_guess is not None, "Empty detection but with SIG/BOM has failed!"
assert best_guess.encoding == expected_encoding, "Empty detection but with SIG/BOM is wrongly detected!"
assert best_guess.raw == payload, "The RAW property should contain the original payload given for detection."
assert best_guess.byte_order_mark is True, "The BOM/SIG property should return True"
assert str(best_guess) == "", "The cast to str SHOULD be empty"
def test_bool_matches():
guesses_not_empty = from_bytes(b'')
guesses_empty = CharsetMatches([])
assert bool(
guesses_not_empty
) is True, "Bool behaviour of CharsetMatches altered, should be True"
assert bool(
guesses_empty
) is False, "Bool behaviour of CharsetMatches altered, should be False"
def test_mb_cutting_chk():
# This payload should be wrongfully split and the autofix should ran automatically
# on chunks extraction.
payload = b"\xbf\xaa\xbb\xe7\xc0\xfb \xbf\xb9\xbc\xf6 " \
b" \xbf\xac\xb1\xb8\xc0\xda\xb5\xe9\xc0\xba \xba\xb9\xc0\xbd\xbc\xad\xb3\xaa " * 128
guesses = from_bytes(payload, cp_isolation=["cp949"])
best_guess = guesses.best()
assert len(
guesses
) == 1, "cp isolation is set and given seq should be clear CP949!"
assert best_guess.encoding == "cp949"
def test_obviously_utf8_content(payload):
best_guess = from_bytes(payload).best()
assert best_guess is not None, "Dead-simple UTF-8 detection has failed!"
assert best_guess.encoding == "utf_8", "Dead-simple UTF-8 detection is wrongly detected!"
def test_obviously_ascii_content(payload):
best_guess = from_bytes(payload).best()
assert best_guess is not None, "Dead-simple ASCII detection has failed!"
assert best_guess.encoding == "ascii", "Dead-simple ASCII detection is wrongly detected!"
def test_empty():
best_guess = from_bytes(b'').best()
assert best_guess is not None, "Empty bytes payload SHOULD NOT return None"
assert best_guess.encoding == "utf_8", "Empty bytes payload SHOULD be guessed as UTF-8 (arbitrary)"
assert len(best_guess.alphabets) == 0, ""
def test_content_with_bom_or_sig(payload, expected_encoding):
best_guess = from_bytes(payload).best()
assert best_guess is not None, "Detection but with SIG/BOM has failed!"
assert best_guess.encoding == expected_encoding, "Detection but with SIG/BOM is wrongly detected!"
assert best_guess.byte_order_mark is True, "The BOM/SIG property should return True"
def test_explain_true_behavior(self, caplog):
test_sequence = b'This is a test sequence of bytes that should be sufficient'
from_bytes(test_sequence, steps=1, chunk_size=50, explain=True)
assert explain_handler not in self.logger.handlers
for record in caplog.records:
assert record.levelname in ["Level 5", "DEBUG"]
