Python errors.ParserError方法代码示例

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_malformed_chunks(all_parsers, nrows):
    data = """ignore
A,B,C
skip
1,2,3
3,5,10 # comment
1,2,3,4,5
2,3,4
"""
    parser = all_parsers
    msg = 'Expected 3 fields in line 6, saw 5'
    reader = parser.read_csv(StringIO(data), header=1, comment="#",
                             iterator=True, chunksize=1, skiprows=[2])

    with pytest.raises(ParserError, match=msg):
        reader.read(nrows) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_uneven_lines_with_usecols(all_parsers, usecols):
    # see gh-12203
    parser = all_parsers
    data = r"""a,b,c
0,1,2
3,4,5,6,7
8,9,10"""

    if usecols is None:
        # Make sure that an error is still raised
        # when the "usecols" parameter is not provided.
        msg = r"Expected \d+ fields in line \d+, saw \d+"
        with pytest.raises(ParserError, match=msg):
            parser.read_csv(StringIO(data))
    else:
        expected = DataFrame({
            "a": [0, 3, 8],
            "b": [1, 4, 9]
        })

        result = parser.read_csv(StringIO(data), usecols=usecols)
        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_multi_char_sep_quotes(python_parser_only, quoting):
    # see gh-13374
    kwargs = dict(sep=",,")
    parser = python_parser_only

    data = 'a,,b\n1,,a\n2,,"2,,b"'
    msg = "ignored when a multi-char delimiter is used"

    def fail_read():
        with pytest.raises(ParserError, match=msg):
            parser.read_csv(StringIO(data), quoting=quoting, **kwargs)

    if quoting == csv.QUOTE_NONE:
        # We expect no match, so there should be an assertion
        # error out of the inner context manager.
        with pytest.raises(AssertionError):
            fail_read()
    else:
        fail_read() 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_skipfooter_bad_row(python_parser_only, data, skipfooter):
    # see gh-13879 and gh-15910
    msg = "parsing errors in the skipped footer rows"
    parser = python_parser_only

    def fail_read():
        with pytest.raises(ParserError, match=msg):
            parser.read_csv(StringIO(data), skipfooter=skipfooter)

    if skipfooter:
        fail_read()
    else:
        # We expect no match, so there should be an assertion
        # error out of the inner context manager.
        with pytest.raises(AssertionError):
            fail_read() 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_error_rename():
    # see gh-12665
    from pandas.errors import ParserError
    from pandas.io.common import CParserError

    try:
        raise CParserError()
    except ParserError:
        pass

    try:
        raise ParserError()
    except CParserError:
        pass

    with catch_warnings(record=True):
        try:
            raise ParserError()
        except pd.parser.CParserError:
            pass 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_skipfooter_bad_row(self):
        # see gh-13879
        # see gh-15910

        msg = 'parsing errors in the skipped footer rows'

        for data in ('a\n1\n"b"a',
                     'a,b,c\ncat,foo,bar\ndog,foo,"baz'):
            with tm.assert_raises_regex(ParserError, msg):
                self.read_csv(StringIO(data), skipfooter=1)

            # We expect no match, so there should be an assertion
            # error out of the inner context manager.
            with pytest.raises(AssertionError):
                with tm.assert_raises_regex(ParserError, msg):
                    self.read_csv(StringIO(data)) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_bad_stream_exception(self):
        # Issue 13652:
        # This test validates that both python engine
        # and C engine will raise UnicodeDecodeError instead of
        # c engine raising ParserError and swallowing exception
        # that caused read to fail.
        codec = codecs.lookup("utf-8")
        utf8 = codecs.lookup('utf-8')

        if compat.PY3:
            msg = "'utf-8' codec can't decode byte"
        else:
            msg = "'utf8' codec can't decode byte"

        # stream must be binary UTF8
        with open(self.csv_shiftjs, "rb") as handle, codecs.StreamRecoder(
                handle, utf8.encode, utf8.decode, codec.streamreader,
                codec.streamwriter) as stream:

            with tm.assert_raises_regex(UnicodeDecodeError, msg):
                self.read_csv(stream) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def _alert_malformed(self, msg, row_num):
        """
        Alert a user about a malformed row.

        If `self.error_bad_lines` is True, the alert will be `ParserError`.
        If `self.warn_bad_lines` is True, the alert will be printed out.

        Parameters
        ----------
        msg : The error message to display.
        row_num : The row number where the parsing error occurred.
                  Because this row number is displayed, we 1-index,
                  even though we 0-index internally.
        """

        if self.error_bad_lines:
            raise ParserError(msg)
        elif self.warn_bad_lines:
            base = 'Skipping line {row_num}: '.format(row_num=row_num)
            sys.stderr.write(base + msg + '\n') 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def _load_df(self):
        if self._df is None:
            try:
                self._df = pd.read_csv(self.filename)
            except pd.errors.EmptyDataError:
                logger.warning(
                    'Trace %s is empty and needs to be resampled!' %
                    self.filename)
                os.remove(self.filename)
                self.corrupted_flag = True
            except CParserError:
                logger.warning(
                    'Trace %s has wrong size!' % self.filename)
                self.corrupted_flag = True
                os.remove(self.filename)

            if len(self.flat_names) == 0 and not self.corrupted_flag:
                self.flat_names, self.var_shapes = extract_variables_from_df(
                    self._df)
                self.varnames = list(self.var_shapes.keys()) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_bad_stream_exception(self):
        # Issue 13652:
        # This test validates that both python engine
        # and C engine will raise UnicodeDecodeError instead of
        # c engine raising ParserError and swallowing exception
        # that caused read to fail.
        handle = open(self.csv_shiftjs, "rb")
        codec = codecs.lookup("utf-8")
        utf8 = codecs.lookup('utf-8')
        # stream must be binary UTF8
        stream = codecs.StreamRecoder(
            handle, utf8.encode, utf8.decode, codec.streamreader,
            codec.streamwriter)
        if compat.PY3:
            msg = "'utf-8' codec can't decode byte"
        else:
            msg = "'utf8' codec can't decode byte"
        with tm.assert_raises_regex(UnicodeDecodeError, msg):
            self.read_csv(stream)
        stream.close() 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_error_rename():
    # see gh-12665
    from pandas.errors import ParserError
    from pandas.io.common import CParserError

    try:
        raise CParserError()
    except ParserError:
        pass

    try:
        raise ParserError()
    except CParserError:
        pass 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_computer_sales_page(self, datapath):
        data = datapath('io', 'data', 'computer_sales_page.html')
        msg = (r"Passed header=\[0,1\] are too many "
               r"rows for this multi_index of columns")
        with pytest.raises(ParserError, match=msg):
            self.read_html(data, header=[0, 1])

        data = datapath('io', 'data', 'computer_sales_page.html')
        assert self.read_html(data, header=[1, 2]) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_parser_error_on_empty_header_row(self):
        msg = (r"Passed header=\[0,1\] are too many "
               r"rows for this multi_index of columns")
        with pytest.raises(ParserError, match=msg):
            self.read_html("""
                <table>
                    <thead>
                        <tr><th></th><th></tr>
                        <tr><th>A</th><th>B</th></tr>
                    </thead>
                    <tbody>
                        <tr><td>a</td><td>b</td></tr>
                    </tbody>
                </table>
            """, header=[0, 1]) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_buffer_overflow(c_parser_only, malformed):
    # see gh-9205: test certain malformed input files that cause
    # buffer overflows in tokenizer.c
    msg = "Buffer overflow caught - possible malformed input file."
    parser = c_parser_only

    with pytest.raises(ParserError, match=msg):
        parser.read_csv(StringIO(malformed)) 

# 需要导入模块: from pandas import errors [as 别名]
# 或者: from pandas.errors import ParserError [as 别名]
def test_multi_index_unnamed(all_parsers, index_col, columns):
    # see gh-23687
    #
    # When specifying a multi-index header, make sure that
    # we don't error just because one of the rows in our header
    # has ALL column names containing the string "Unnamed". The
    # correct condition to check is whether the row contains
    # ALL columns that did not have names (and instead were given
    # placeholder ones).
    parser = all_parsers
    header = [0, 1]

    if index_col is None:
        data = ",".join(columns or ["", ""]) + "\n0,1\n2,3\n4,5\n"
    else:
        data = (",".join([""] + (columns or ["", ""])) +
                "\n,0,1\n0,2,3\n1,4,5\n")

    if columns is None:
        msg = (r"Passed header=\[0,1\] are too "
               r"many rows for this multi_index of columns")
        with pytest.raises(ParserError, match=msg):
            parser.read_csv(StringIO(data), header=header,
                            index_col=index_col)
    else:
        result = parser.read_csv(StringIO(data), header=header,
                                 index_col=index_col)
        template = "Unnamed: {i}_level_0"
        exp_columns = []

        for i, col in enumerate(columns):
            if not col:  # Unnamed.
                col = template.format(i=i if index_col is None else i + 1)

            exp_columns.append(col)

        columns = MultiIndex.from_tuples(zip(exp_columns, ["0", "1"]))
        expected = DataFrame([[2, 3], [4, 5]], columns=columns)
        tm.assert_frame_equal(result, expected)