
    j                        d dl Z d dlZd dlmZmZmZmZ d dlmZ d dl	m
Z
mZ d dlmZmZ d dlmZmZmZmZ d dlmZ  e             eej                   e            ddddddd	dd
gdf
dee         deee                  dededee         dee         dee         dee         deee                  dededee
         fd                                    ZdS )    N)IOAnyListOptional)add_chunking_strategy)Elementprocess_metadata)FileTypeadd_metadata_with_filetype)convert_office_docexactly_oneget_last_modified_date get_last_modified_date_from_file)partition_docxTzMS Word 2007 XMLautoFfilenamefileinclude_page_breaksinclude_metadatametadata_filenamemetadata_last_modifiedlibre_office_filterchunking_strategy	languagesdetect_language_per_elementkwargsreturnc
           
      P   | d} t          | |           t          |           dk    rt          j                            t          j                            |                     \  }}t          j                            |          \  }}t          j                            |           st          d|  d          t          |           }n|t          j        d          }|                    |                                           |                                 |j        } t          j                            t          j                            |j                            \  }}t          j                            |          \  }}t!          |          }t          j                    5 }t%          | |d	|
           t          j                            || d          }t)          |||||p|||	          }|r|D ]}||j        _        ddd           n# 1 swxY w Y   |S )a  Partitions Microsoft Word Documents in .doc format into its document elements.

    Parameters
    ----------
    filename
        A string defining the target filename path.
    file
        A file-like object using "rb" mode --> open(filename, "rb").
    metadata_last_modified
        The last modified date for the document.
    libre_office_filter
        The filter to use when coverting to .doc. The default is the
        filter that is required when using LibreOffice7. Pass in None
        if you do not want to apply any filter.
    languages
        User defined value for `metadata.languages` if provided. Otherwise language is detected
        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
        in either language.
        Additional Parameters:
            detect_language_per_element
                Detect language per element instead of at the document level.
    N )r   r   r   z	The file z does not exist.F)deletedocx)target_formattarget_filterz.docx)r   r   r   r   r   r   r   )r   lenospathsplitabspathsplitextexists
ValueErrorr   tempfileNamedTemporaryFilewritereadclosenamer   TemporaryDirectoryr   joinr   metadatar   )r   r   r   r   r   r   r   r   r   r   r   _filename_no_pathbase_filenamelast_modification_datetmptmpdirdocx_filenameelementselements                       d/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/unstructured/partition/doc.pypartition_docr?      sR   N ----
8}}q gmmBGOOH,E,EFF7++,<==qw~~h'' 	ECCCCDDD!7!A!A		)777		$))++		8 gmmBGOOCH,E,EFF7++,<==q!A$!G!G		$	&	& >& -		
 	
 	
 	
 V-D-D-DEE!"/ 3-#9#S=S(C
 
 
  	># > >,= )))> > > > > > > > > > > > > > >, Os   -A"HH"H)r%   r,   typingr   r   r   r   unstructured.chunkingr   unstructured.documents.elementsr   r	    unstructured.file_utils.filetyper
   r   unstructured.partition.commonr   r   r   r   unstructured.partition.docxr   DOCstrbytesboolr?        r>   <module>rL      s   				  * * * * * * * * * * * * 7 7 7 7 7 7 E E E E E E E E Q Q Q Q Q Q Q Q            7 6 6 6 6 6 HL))" $ $!'+,0);'+&,X(-P PsmP
2e9
P P 	P
  }P %SMP "#P  }P S	"P "&P P 
']P P P  *) P P PrK   