NgddlmZddlZddlZddlmZmZmZmZddl m Z ddl m Z ddl mZddlmZddlmZdd lmZ ddddd ddZedddZdS)) annotationsN)IOAnyOptionalcast)Element)FileType) exactly_one)get_last_modified_date)partition_docx)requires_dependencies)filemetadata_filenamemetadata_last_modifiedfilename Optional[str]rOptional[IO[bytes]]rrkwargsrreturn list[Element]c |rt|nd}tj5}t|||}t d||p|t j|p|d|}dddn #1swxYwY|S)aPartitions Open Office Documents in .odt format into its document elements. All parameters that are 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"). infer_table_structure If True, any Table elements that are extracted will also have a metadata field named "text_as_html" where the table's text content is rendered into an html string. I.e., rows and cells are preserved. Whether True or False, the "text" field is always present in any Table element and is the text content of the table (no structure). metadata_last_modified The last modified date for the document. 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)rrmetadata_file_typer)r tempfileTemporaryDirectory_convert_odt_to_docxr r ODT) rrrrr last_modified target_dir docx_pathelementss V/var/www/html/ai-engine/env/lib/python3.11/site-packages/unstructured/partition/odt.py partition_odtr#sF9AJ*8444dM  $ & & *(XtDD ! /;8'|#9#J]                      Os1A$$A(+A(pypandocrstrclt|||2tj|st d|d||dnt t |}|Ot|d5}|| dddn #1swxYwYtj |}tj |\}}tj ||d}ddl } | |d d | |S) a{Convert ODT document to DOCX returning the new .docx file's path. Parameters ---------- target_dir The str directory-path to use for conversion purposes. The new DOCX file is written to this directory. When passed as a file-like object, a copy of the source file is written here as well. It is the caller's responsibility to remove this directory and its contents when they are no longer needed. filename A str file-path specifying the location of the source ODT file on the local filesystem. file A file-like object open for reading in binary mode ("rb" mode). )rrNz The file z does not exist.z /document.odtwbz.docxrdocxodt)format outputfile)r ospathexists ValueErrorrr%openwritereadbasenamesplitextjoinr$ convert_file) rrrsource_file_pathf file_name base_name_target_docx_pathr$s r"rrAs$----BGNN8$<$<?X???@@@ 8<7G*3333TRUW_M`M`  "D ) ) !Q GGDIIKK  ! ! ! ! ! ! ! ! ! ! ! ! ! ! !   !122I7##I..LIqw||J90C0C0CDDOOO #  s4(B((B,/B,)N) rrrrrrrrrrrr)rr%rrrrrr%) __future__rr,rtypingrrrrunstructured.documents.elementsrunstructured.file_utils.modelr $unstructured.partition.common.commonr &unstructured.partition.common.metadatar unstructured.partition.docxr unstructured.utilsr r#rrr"rFs#"""""" ************333333222222<<<<<<IIIIII666666444444#/!%'+,0 //////dz""222#"222rE