j UddlmZmZmZddlmZddlmZmZddl m Z m Z ddl m Z ddlmZdZeed<ee e jed d d d d d d d gd f d eedeeedededeedeedeedeeededeefdZd S))IOListOptional)add_chunking_strategy)Elementprocess_metadata)FileTypeadd_metadata_with_filetype)convert_and_partition_html)apply_lang_metadataepubDETECTION_ORIGINNFTautofilenamefileinclude_page_breaksinclude_metadatametadata_filenamemetadata_last_modifiedchunking_strategy languagesdetect_language_per_elementreturnc zt|||||dt} tt| ||} | S)a[Partitions an EPUB document. The document is first converted to HTML and then partitioned using partition_html. Parameters ---------- filename A string defining the target filename path. file A file-like object using "rb" mode --> open(filename, "rb"). include_page_breaks If True, the output will include page breaks if the filetype supports it 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. r )rrrrr source_formatdetection_origin)rr)r rlistr ) rrrrrrrrrkwargselementss e/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/unstructured/partition/epub.pypartition_epubr! saJ* /+5)H (C   H O)typingrrrunstructured.chunkingrunstructured.documents.elementsrr unstructured.file_utils.filetyper r unstructured.partition.htmlr unstructured.partition.langr rstr__annotations__EPUBbytesboolr!r"r r/s%%%%%%%%%%%777777EEEEEEEEQQQQQQQQBBBBBB;;;;;;#HM**" $ %!'+,0'+&,X(-44sm4 2e9 44 4  } 4 %SM 4 }4S "4"&4 ']444+*444r"