def infer_compression(
filepath_or_buffer: FilePathOrBuffer, compression: str | None
) -> str | None:
"""
Get the compression method for filepath_or_buffer. If compression='infer',
the inferred compression method is returned. Otherwise, the input
compression method is returned unchanged, unless it's invalid, in which
case an error is raised.
Parameters
----------
filepath_or_buffer : str or file handle
File path or object.
compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}
If 'infer' and `filepath_or_buffer` is path-like, then detect
compression from the following extensions: '.gz', '.bz2', '.zip',
or '.xz' (otherwise no compression).
Returns
-------
string or None
Raises
------
ValueError on invalid compression specified.
"""
if compression is None:
return None
# Infer compression
if compression == "infer":
# Convert all path types (e.g. pathlib.Path) to strings
filepath_or_buffer = stringify_path(filepath_or_buffer, convert_file_like=True)
if not isinstance(filepath_or_buffer, str):
# Cannot infer compression of a buffer, assume no compression
return None
# Infer compression from the filename/URL extension
for compression, extension in _compression_to_extension.items():
if filepath_or_buffer.lower().endswith(extension):
return compression
return None
# Compression has been specified. Check that it's valid
if compression in _compression_to_extension:
return compression
# https://github.com/python/mypy/issues/5492
# Unsupported operand types for + ("List[Optional[str]]" and "List[str]")
valid = ["infer", None] + sorted(
_compression_to_extension
) # type: ignore[operator]
msg = (
f"Unrecognized compression type: {compression}\n"
f"Valid compression types are {valid}"
)
raise ValueError(msg)
def infer_compression(
filepath_or_buffer: FilePathOrBuffer, compression: Optional[str]
) -> Optional[str]:
"""
Get the compression method for filepath_or_buffer. If compression='infer',
the inferred compression method is returned. Otherwise, the input
compression method is returned unchanged, unless it's invalid, in which
case an error is raised.
Parameters
----------
filepath_or_buffer : str or file handle
File path or object.
compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}
If 'infer' and `filepath_or_buffer` is path-like, then detect
compression from the following extensions: '.gz', '.bz2', '.zip',
or '.xz' (otherwise no compression).
Returns
-------
string or None
Raises
------
ValueError on invalid compression specified.
"""
# No compression has been explicitly specified
if compression is None:
return None
# Infer compression
if compression == "infer":
# Convert all path types (e.g. pathlib.Path) to strings
filepath_or_buffer = stringify_path(filepath_or_buffer)
if not isinstance(filepath_or_buffer, str):
# Cannot infer compression of a buffer, assume no compression
return None
# Infer compression from the filename/URL extension
for compression, extension in _compression_to_extension.items():
if filepath_or_buffer.lower().endswith(extension):
return compression
return None
# Compression has been specified. Check that it's valid
if compression in _compression_to_extension:
return compression
msg = f"Unrecognized compression type: {compression}"
valid = ["infer", None] + sorted(_compression_to_extension)
msg += f"\nValid compression types are {valid}"
raise ValueError(msg)
def read_sas(
filepath_or_buffer: FilePathOrBuffer,
format: Optional[str] = None,
index: Optional[Label] = None,
encoding: Optional[str] = None,
chunksize: Optional[int] = None,
iterator: bool = False,
) -> Union["DataFrame", ReaderBase]:
"""
Read SAS files stored as either XPORT or SAS7BDAT format files.
Parameters
----------
filepath_or_buffer : str, path object or file-like object
Any valid string path is acceptable. The string could be a URL. Valid
URL schemes include http, ftp, s3, and file. For file URLs, a host is
expected. A local file could be:
``file://localhost/path/to/table.sas``.
If you want to pass in a path object, pandas accepts any
``os.PathLike``.
By file-like object, we refer to objects with a ``read()`` method,
such as a file handle (e.g. via builtin ``open`` function)
or ``StringIO``.
format : str {'xport', 'sas7bdat'} or None
If None, file format is inferred from file extension. If 'xport' or
'sas7bdat', uses the corresponding format.
index : identifier of index column, defaults to None
Identifier of column that should be used as index of the DataFrame.
encoding : str, default is None
Encoding for text data. If None, text data are stored as raw bytes.
chunksize : int
Read file `chunksize` lines at a time, returns iterator.
iterator : bool, defaults to False
If True, returns an iterator for reading the file incrementally.
Returns
-------
DataFrame if iterator=False and chunksize=None, else SAS7BDATReader
or XportReader
"""
if format is None:
buffer_error_msg = (
"If this is a buffer object rather "
"than a string name, you must specify a format string")
filepath_or_buffer = stringify_path(filepath_or_buffer)
if not isinstance(filepath_or_buffer, str):
raise ValueError(buffer_error_msg)
fname = filepath_or_buffer.lower()
if fname.endswith(".xpt"):
format = "xport"
elif fname.endswith(".sas7bdat"):
format = "sas7bdat"
else:
raise ValueError("unable to infer format of SAS file")
reader: ReaderBase
if format.lower() == "xport":
from pandas.io.sas.sas_xport import XportReader
reader = XportReader(
filepath_or_buffer,
index=index,
encoding=encoding,
chunksize=chunksize,
)
elif format.lower() == "sas7bdat":
from pandas.io.sas.sas7bdat import SAS7BDATReader
reader = SAS7BDATReader(
filepath_or_buffer,
index=index,
encoding=encoding,
chunksize=chunksize,
)
else:
raise ValueError("unknown SAS format")
if iterator or chunksize:
return reader
return reader.read()
