j |ddlmZmZmZmZddlmZddlmZm Z ddl m Z m Z ddl mZmZddlmZe e e jedddddddd gd f d eed eed ededeedeedeedeeedededeefdZdS))AnyBinaryIOListOptional)add_chunking_strategy)Elementprocess_metadata)FileTypeadd_metadata_with_filetype)get_last_modified_date get_last_modified_date_from_file)convert_and_partition_docxNTautoFfilenamefileinclude_metadatainfer_table_structuremetadata_filenamemetadata_last_modifiedchunking_strategy languagesdetect_language_per_elementkwargsreturnc ~d} |rt|} n|rt|} td|||||p| ||S)aXPartitions Open Office Documents in .odt 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"). 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. Nodt) source_formatrrrrrrr)r r r) rrrrrrrrrrlast_modification_dates d/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/unstructured/partition/odt.py partition_odtr sqP"H!7!A!A H!A$!G!G % 3+5O9O$?    )typingrrrrunstructured.chunkingrunstructured.documents.elementsrr unstructured.file_utils.filetyper r unstructured.partition.commonr r unstructured.partition.docxrODTstrboolr r!rr,s000000000000777777EEEEEEEEQQQQQQQQCBBBBBHL))"#!"&'+,0'+&,X(-44sm4 8 44 4  } 4 %SM 4 }4S "4"&44 ']444*)444r!