pandas._libs.parsers.TextReader('中文文件名-chinese-in-filename.csv') OSError: Initializing from file failed

[QGB]

kwargs={'delimiter': ',', 'doublequote': True, 'escapechar': None, 'quotechar': '"', 'quoting': 0, 'skipinitialspace': False, 'lineterminator': None, 'header': 0, 'index_col': None, 'names': None, 'skiprows': None, 'na_values': {'nan', '', 'NaN', 'N/A', '-NaN', 'null', '#N/A N/A', 'n/a', '-nan', '-1.#QNAN', 'NA', '1.#IND', '-1.#IND', '1.#QNAN', 'NULL', '#NA', '#N/A'}, 'true_values': None, 'false_values': None, 'converters': {}, 'dtype': None, 'keep_default_na': True, 'thousands': None, 'comment': None, 'decimal': b'.', 'usecols': None, 'verbose': False, 'encoding': 'gb2312', 'compression': None, 'mangle_dupe_cols': True, 'tupleize_cols': False, 'skip_blank_lines': True, 'delim_whitespace': False, 'na_filter': True, 'low_memory': True, 'memory_map': False, 'error_bad_lines': True, 'warn_bad_lines': True, 'float_precision': None, 'na_fvalues': set(), 'allow_leading_cols': True}

parsers.TextReader('中文文件名-chinese-in-filename.csv',**kwargs)

Traceback (most recent call last)
in ()
----> 1 parsers.TextReader(f,**_2)

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.cinit()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._setup_parser_source()

OSError: Initializing from file failed

[WillAyd]

This isn't part of the API - what error are you getting from user-facing methods?

[QGB]

@willweil

In [70]: pd.read_csv(f, delimiter=',',encoding='gb2312')
---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
<ipython-input-70-4d1e02136d2f> in <module>()
----> 1 pd.read_csv(f, delimiter=',',encoding='gb2312')

E:\QGB\Anaconda3\lib\site-packages\pandas\io\parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, doublequote, delim_whitespace, low_memory, memory_map, float_precision)
    676                     skip_blank_lines=skip_blank_lines)
    677
--> 678         return _read(filepath_or_buffer, kwds)
    679
    680     parser_f.__name__ = name

E:\QGB\Anaconda3\lib\site-packages\pandas\io\parsers.py in _read(filepath_or_buffer, kwds)
    438
    439     # Create the parser.
--> 440     parser = TextFileReader(filepath_or_buffer, **kwds)
    441
    442     if chunksize or iterator:

E:\QGB\Anaconda3\lib\site-packages\pandas\io\parsers.py in __init__(self, f, engine, **kwds)
    785             self.options['has_index_names'] = kwds['has_index_names']
    786
--> 787         self._make_engine(self.engine)
    788
    789     def close(self):

E:\QGB\Anaconda3\lib\site-packages\pandas\io\parsers.py in _make_engine(self, engine)
   1012     def _make_engine(self, engine='c'):
   1013         if engine == 'c':
-> 1014             self._engine = CParserWrapper(self.f, **self.options)
   1015         else:
   1016             if engine == 'python':

E:\QGB\Anaconda3\lib\site-packages\pandas\io\parsers.py in __init__(self, src, **kwds)
   1706         kwds['usecols'] = self.usecols
   1707
-> 1708         self._reader = parsers.TextReader(src, **kwds)
   1709
   1710         passed_names = self.names is None

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._setup_parser_source()

OSError: Initializing from file failed

[WillAyd]

Hmm still not able to reproduce. Can you post the output of pd.show_versions? Have you tried on master?

[peterpanmj]

@QGB
It is a bug in previous version. I ran into that in 0.23.4.
I cant reporduce it in 0.24.2 or in current master.

In [4]: import pandas as pd
   ...: df = pd.DataFrame({"A":[1]})
   ...: df.to_csv("./中文.csv")
   ...: pd.read_csv("./中文.csv")

In [5]: pd.__version__
Out[5]: '0.24.2'

Works Fine.

In 0.23.4, you can still work around it by using
pd.read_csv(f, engine="python")

[WillAyd]

I think if someone wanted to add a test case for this can close out

[naveenkaushik2504]

I have submitted a PR for this. This is my first contribution, so please guide if anything is not done in the right way. Thanks.