Python compat.binary_type方法代码示例

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def test_repr_binary_type():
    import string
    letters = string.ascii_letters
    btype = compat.binary_type
    try:
        raw = btype(letters, encoding=cf.get_option('display.encoding'))
    except TypeError:
        raw = btype(letters)
    b = compat.text_type(compat.bytes_to_str(raw))
    res = printing.pprint_thing(b, quote_strings=True)
    assert res == repr(b)
    res = printing.pprint_thing(b, quote_strings=False)
    assert res == b 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def _unconvert_string_array(data, nan_rep=None, encoding=None,
                            errors='strict'):
    """
    inverse of _convert_string_array

    Parameters
    ----------
    data : fixed length string dtyped array
    nan_rep : the storage repr of NaN, optional
    encoding : the encoding of the data, optional
    errors : handler for encoding errors, default 'strict'

    Returns
    -------
    an object array of the decoded data

    """
    shape = data.shape
    data = np.asarray(data.ravel(), dtype=object)

    # guard against a None encoding in PY3 (because of a legacy
    # where the passed encoding is actually None)
    encoding = _ensure_encoding(encoding)
    if encoding is not None and len(data):

        itemsize = libwriters.max_len_string_array(_ensure_object(data))
        if compat.PY3:
            dtype = "U{0}".format(itemsize)
        else:
            dtype = "S{0}".format(itemsize)

        if isinstance(data[0], compat.binary_type):
            data = Series(data).str.decode(encoding, errors=errors).values
        else:
            data = data.astype(dtype, copy=False).astype(object, copy=False)

    if nan_rep is None:
        nan_rep = 'nan'

    data = libwriters.string_array_replace_from_nan_rep(data, nan_rep)
    return data.reshape(shape) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def _unconvert_string_array(data, nan_rep=None, encoding=None):
    """
    inverse of _convert_string_array

    Parameters
    ----------
    data : fixed length string dtyped array
    nan_rep : the storage repr of NaN, optional
    encoding : the encoding of the data, optional

    Returns
    -------
    an object array of the decoded data

    """
    shape = data.shape
    data = np.asarray(data.ravel(), dtype=object)

    # guard against a None encoding in PY3 (because of a legacy
    # where the passed encoding is actually None)
    encoding = _ensure_encoding(encoding)
    if encoding is not None and len(data):

        itemsize = lib.max_len_string_array(_ensure_object(data))
        if compat.PY3:
            dtype = "U{0}".format(itemsize)
        else:
            dtype = "S{0}".format(itemsize)

        if isinstance(data[0], compat.binary_type):
            data = Series(data).str.decode(encoding).values
        else:
            data = data.astype(dtype, copy=False).astype(object, copy=False)

    if nan_rep is None:
        nan_rep = 'nan'

    data = lib.string_array_replace_from_nan_rep(data, nan_rep)
    return data.reshape(shape) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
                           compression=None, mode=None):
    """
    If the filepath_or_buffer is a url, translate and return the buffer.
    Otherwise passthrough.

    Parameters
    ----------
    filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                         or buffer
    encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
    mode : str, optional

    Returns
    -------
    tuple of ({a filepath_ or buffer or S3File instance},
              encoding, str,
              compression, str,
              should_close, bool)
    """
    filepath_or_buffer = _stringify_path(filepath_or_buffer)

    if _is_url(filepath_or_buffer):
        req = _urlopen(filepath_or_buffer)
        content_encoding = req.headers.get('Content-Encoding', None)
        if content_encoding == 'gzip':
            # Override compression based on Content-Encoding header
            compression = 'gzip'
        reader = BytesIO(req.read())
        req.close()
        return reader, encoding, compression, True

    if is_s3_url(filepath_or_buffer):
        from pandas.io import s3
        return s3.get_filepath_or_buffer(filepath_or_buffer,
                                         encoding=encoding,
                                         compression=compression,
                                         mode=mode)

    if is_gcs_url(filepath_or_buffer):
        from pandas.io import gcs
        return gcs.get_filepath_or_buffer(filepath_or_buffer,
                                          encoding=encoding,
                                          compression=compression,
                                          mode=mode)

    if isinstance(filepath_or_buffer, (compat.string_types,
                                       compat.binary_type,
                                       mmap.mmap)):
        return _expand_user(filepath_or_buffer), None, compression, False

    if not is_file_like(filepath_or_buffer):
        msg = "Invalid file path or buffer object type: {_type}"
        raise ValueError(msg.format(_type=type(filepath_or_buffer)))

    return filepath_or_buffer, None, compression, False 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
                           compression=None, mode=None):
    """
    If the filepath_or_buffer is a url, translate and return the buffer.
    Otherwise passthrough.

    Parameters
    ----------
    filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                         or buffer
    encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
    mode : str, optional

    Returns
    -------
    tuple of ({a filepath_ or buffer or S3File instance},
              encoding, str,
              compression, str,
              should_close, bool)
    """
    filepath_or_buffer = _stringify_path(filepath_or_buffer)

    if _is_url(filepath_or_buffer):
        req = _urlopen(filepath_or_buffer)
        content_encoding = req.headers.get('Content-Encoding', None)
        if content_encoding == 'gzip':
            # Override compression based on Content-Encoding header
            compression = 'gzip'
        reader = BytesIO(req.read())
        req.close()
        return reader, encoding, compression, True

    if is_s3_url(filepath_or_buffer):
        from pandas.io import s3
        return s3.get_filepath_or_buffer(filepath_or_buffer,
                                         encoding=encoding,
                                         compression=compression,
                                         mode=mode)

    if isinstance(filepath_or_buffer, (compat.string_types,
                                       compat.binary_type,
                                       mmap.mmap)):
        return _expand_user(filepath_or_buffer), None, compression, False

    if not is_file_like(filepath_or_buffer):
        msg = "Invalid file path or buffer object type: {_type}"
        raise ValueError(msg.format(_type=type(filepath_or_buffer)))

    return filepath_or_buffer, None, compression, False 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
                           compression=None):
    """
    If the filepath_or_buffer is a url, translate and return the buffer.
    Otherwise passthrough.

    Parameters
    ----------
    filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                         or buffer
    encoding : the encoding to use to decode py3 bytes, default is 'utf-8'

    Returns
    -------
    a filepath_or_buffer, the encoding, the compression
    """
    filepath_or_buffer = _stringify_path(filepath_or_buffer)

    if _is_url(filepath_or_buffer):
        req = _urlopen(filepath_or_buffer)
        content_encoding = req.headers.get('Content-Encoding', None)
        if content_encoding == 'gzip':
            # Override compression based on Content-Encoding header
            compression = 'gzip'
        reader = BytesIO(req.read())
        return reader, encoding, compression

    if _is_s3_url(filepath_or_buffer):
        from pandas.io import s3
        return s3.get_filepath_or_buffer(filepath_or_buffer,
                                         encoding=encoding,
                                         compression=compression)

    if isinstance(filepath_or_buffer, (compat.string_types,
                                       compat.binary_type,
                                       mmap.mmap)):
        return _expand_user(filepath_or_buffer), None, compression

    if not is_file_like(filepath_or_buffer):
        msg = "Invalid file path or buffer object type: {_type}"
        raise ValueError(msg.format(_type=type(filepath_or_buffer)))

    return filepath_or_buffer, None, compression 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import binary_type [as 别名]
def read_msgpack(path_or_buf, encoding='utf-8', iterator=False, **kwargs):
    """
    Load msgpack pandas object from the specified
    file path

    THIS IS AN EXPERIMENTAL LIBRARY and the storage format
    may not be stable until a future release.

    Parameters
    ----------
    path_or_buf : string File path, BytesIO like or string
    encoding: Encoding for decoding msgpack str type
    iterator : boolean, if True, return an iterator to the unpacker
               (default is False)

    Returns
    -------
    obj : type of object stored in file

    """
    path_or_buf, _, _ = get_filepath_or_buffer(path_or_buf)
    if iterator:
        return Iterator(path_or_buf)

    def read(fh):
        l = list(unpack(fh, encoding=encoding, **kwargs))
        if len(l) == 1:
            return l[0]
        return l

    # see if we have an actual file
    if isinstance(path_or_buf, compat.string_types):

        try:
            exists = os.path.exists(path_or_buf)
        except (TypeError, ValueError):
            exists = False

        if exists:
            with open(path_or_buf, 'rb') as fh:
                return read(fh)

    # treat as a binary-like
    if isinstance(path_or_buf, compat.binary_type):
        fh = None
        try:
            fh = compat.BytesIO(path_or_buf)
            return read(fh)
        finally:
            if fh is not None:
                fh.close()

    # a buffer like
    if hasattr(path_or_buf, 'read') and compat.callable(path_or_buf.read):
        return read(path_or_buf)

    raise ValueError('path_or_buf needs to be a string file path or file-like')