j.dZddlmZddlmZmZddlmZddlm Z m Z m Z ddl m Z ddlmZe rddlmZdd lmZdd lmZmZmZdd lmZe d Gd dedeZe ddddddd ddZe ddddddd ddZe dddddddd ddZy)z# Read SAS sas7bdat or xport files. ) annotations)ABCabstractmethod)Iterator) TYPE_CHECKINGSelfoverload) set_module)stringify_path)Hashable) TracebackType)CompressionOptionsFilePath ReadBuffer) DataFramezpandas.api.typingcVeZdZdZedddZed dZd dZ d dZy) SASReaderz< Abstract class for XportReader and SAS7BDATReader. NcyN)selfnrowss X/root/aria/tools/markitdown-venv/lib/python3.12/site-packages/pandas/io/sas/sasreader.pyreadzSASReader.read)s;>cyrrrs rclosezSASReader.close,s rc|Srrrs r __enter__zSASReader.__enter__/s rc$|jyr)r)rexc_type exc_value tracebacks r__exit__zSASReader.__exit__2s rr)r int | Nonereturnr)r'None)r'r)r"ztype[BaseException] | Noner#zBaseException | Noner$zTracebackType | Noner'r() __name__ __module__ __qualname____doc__rrrr r%rrrrr#sU>>  ,((   rrr.)formatindexencoding chunksizeiterator compressioncyrrfilepath_or_bufferr-r.r/r0r1r2s rread_sasr6;srcyrrr4s rr6r6Hs rpandasNFinferc|Td}t|}t|ts t||j }d|vrd}nd|vrd}ntd||j dk(rdd lm} | ||||| } n2|j dk(rdd lm} | ||||| } n td |s|r| S| 5| jcdddS#1swYyxYw) a Read SAS files stored as either XPORT or SAS7BDAT format files. Parameters ---------- filepath_or_buffer : str, path object, or file-like object String, path object (implementing ``os.PathLike[str]``), or file-like object implementing a binary ``read()`` function. 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.sas7bdat``. 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. compression : str or dict, default 'infer' For on-the-fly decompression of on-disk data. If 'infer' and 'filepath_or_buffer' is path-like, then detect compression from the following extensions: '.gz', '.bz2', '.zip', '.xz', '.zst', '.tar', '.tar.gz', '.tar.xz' or '.tar.bz2' (otherwise no compression). Set to ``None`` for no decompression. Can also be a dict with key ``'method'`` set to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'xz'``, ``'tar'``} and other key-value pairs are forwarded to ``zipfile.ZipFile``, ``gzip.GzipFile``, ``bz2.BZ2File``, ``zstandard.ZstdCompressor``, ``lzma.LZMAFile`` or ``tarfile.TarFile``, respectively. As an example, the following could be passed for faster compression and to create a reproducible gzip archive: ``compression={'method': 'gzip', 'compresslevel': 1, 'mtime': 1}``. Returns ------- DataFrame, SAS7BDATReader, or XportReader DataFrame if iterator=False and chunksize=None, else SAS7BDATReader or XportReader, file format is inferred from file extension. See Also -------- read_csv : Read a comma-separated values (csv) file into a DataFrame. read_excel : Read an Excel file into a pandas DataFrame. read_spss : Read an SPSS file into a pandas DataFrame. read_orc : Load an ORC object into a pandas DataFrame. read_feather : Load a feather-format object into a pandas DataFrame. Examples -------- >>> df = pd.read_sas("sas_data.sas7bdat") # doctest: +SKIP NzVIf this is a buffer object rather than a string name, you must specify a format stringz.xptxportz .sas7bdatsas7bdatz2unable to infer format of SAS file from filename: r) XportReader)r.r/r0r2)SAS7BDATReaderzunknown SAS format) r isinstancestr ValueErrorlowerpandas.io.sas.sas_xportr=pandas.io.sas.sas7bdatr>r) r5r-r.r/r0r1r2buffer_error_msgfnamer=readerr>s rr6r6Us D~ C ,,>?,c2-. ."((* U?F E !FDUIN  ||~ 7 #   : %9 #  -..9 {{}s 8CC)r5FilePath | ReadBuffer[bytes]r- str | Noner.Hashable | Noner/rIr0intr1boolr2rr'r)r5rHr-rIr.rJr/rIr0r(r1rLr2rr'DataFrame | SASReader)r5rHr-rIr.rJr/rIr0r&r1rLr2rr'rM)r, __future__rabcrrcollections.abcrtypingrrr pandas.util._decoratorsr pandas.io.commonr r typesr pandas._typingrrrr8rrr6rrrrVs#% /+(# !  %s!.  &) 4          $      &)  4              $        H! &-o4o o  o  o  oo$ooor