NgddlmZddlZddlZddlmZmZmZddlm Z ddl m Z ddl m Z mZddlmZddlmZ dddZdS)) annotationsN)IOAnyOptional)Element)FileType)convert_office_doc exactly_one)get_last_modified_date)partition_docxMS Word 2007 XMLfilename Optional[str]fileOptional[IO[bytes]]metadata_filenamemetadata_last_modifiedlibre_office_filterkwargsrreturn list[Element]c Zt|||rt|nd}|2tj|st d|dt j5}||dn|}|J|Ot|d5} | | dddn #1swxYwYt||d|tj tj |\} } tj| \} } tj|| d } t!d | |p|t"j|p|d |}dddn #1swxYwY|r|D]}||j_|S) aPartitions Microsoft Word Documents in .doc format into its document elements. All parameters available on `partition_docx()` are also available here. 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. starting_page_number Indicates what page number should be assigned to the first page in the document. This information will be reflected in elements' metadata and can be be especially useful when partitioning a document that is part of a larger document. )rrNz The file z does not exist.z /document.docwbdocx) target_format target_filterz.docx)rrmetadata_file_typer)r r ospathexists ValueErrortempfileTemporaryDirectoryopenwritereadr splitabspathsplitextjoinr rDOCmetadatar)rrrrrr last_modified target_dirsource_file_pathf_filename_no_path base_filenametarget_file_pathelementselements V/var/www/html/ai-engine/env/lib/python3.11/site-packages/unstructured/partition/doc.py partition_docr9sfH----8@J*8444dMBGNN8$<$<?X???@@@  $ & &! *;?;Kj7777QY+++  &-- % $$$ % % % % % % % % % % % % % % %    -     !gmmBGOOrBs"""""" $$$$$$$$$$333333222222PPPPPPPPIIIIII666666# $'+,0); YYYYYYYrA