U DAf @sddlZddlmZddlmZddlmZddlmZmZm Z m Z m Z ddl m Z mZmZddlmZmZddlmZdd lmZeeZed ZddlZdd lm ZW5QRXeGd d d ZeGdddZdS)N) dataclass)datetime)Path)AnyDictListOptionalUnion)Document componentlogging)get_bytestream_from_sourcenormalize_metadata) ByteStream) LazyImportzRun 'pip install python-docx')r c@seZdZUdZeed<eed<eed<eed<eeed<eed<eed<eed <eed <eeed <eeed <eed <eed<eed<eed<dS) DOCXMetadataa Describes the metadata of Docx file. :param author: The author :param category: The category :param comments: The comments :param content_status: The content status :param created: The creation date :param identifier: The identifier :param keywords: Available keywords :param language: The language of the document :param last_modified_by: The last modified by user date :param last_printed: The last printed date :param modified: The last modification date :param revision: The revision number :param subject: The subject :param title: The title :param version: The version authorcategorycommentscontent_statuscreated identifierkeywordslanguagelast_modified_by last_printedmodifiedrevisionsubjecttitleversionN) __name__ __module__ __qualname____doc__str__annotations__rrintr(r(G/tmp/pip-unpacked-wheel-z752163x/haystack/components/converters/docx.pyrs    rc @sxeZdZdZddZejeedd ee e e e fe e ee efeee effdddZd ed d d ZdS)DOCXToDocumenta# Converts DOCX files to Documents. Uses `python-docx` library to convert the DOCX file to a document. This component does not preserve page breaks in the original document. Usage example: ```python from haystack.components.converters.docx import DOCXToDocument converter = DOCXToDocument() results = converter.run(sources=["sample.docx"], meta={"date_added": datetime.now().isoformat()}) documents = results["documents"] print(documents[0].content) # 'This is a text from the DOCX file.' ``` cCs tdS)z4 Create a DOCXToDocument component. N) docx_importcheck)selfr(r(r)__init__RszDOCXToDocument.__init__) documentsN)sourcesmetac Csg}t|t|d}t||D]\}}z t|}Wn:tk rl}ztjd||dWYqW5d}~XYnXz0tt |j } dd| j D} d | } Wn:tk r}ztjd||dWYqW5d}~XYnX|j| d } |j|d | i} t| | d }||qd |iS) a Converts DOCX files to Documents. :param sources: List of file paths or ByteStream objects. :param meta: Optional metadata to attach to the Documents. This value can be either a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the metadata of all produced Documents. If it's a list, the length of the list must match the number of sources, because the two lists will be zipped. If `sources` contains ByteStream objects, their `meta` will be added to the output Documents. :returns: A dictionary with the following keys: - `documents`: Created Documents )r1Z sources_countz4Could not read {source}. Skipping it. Error: {error})sourceerrorNcSsg|] }|jqSr()text).0parar(r(r) zsz&DOCXToDocument.run.. zSCould not read {source} and convert it to a DOCX Document, skipping. Error: {error})documentdocx)contentr1r/)rlenzipr Exceptionloggerwarningr:r ioBytesIOdata paragraphsjoin_get_docx_metadatar1append)r-r0r1r/Z meta_listr2metadataZ bytestreamefilerDr4Z docx_metadataZmerged_metadatar9r(r(r)runXs0    zDOCXToDocument.run DocxDocument)r9returncCsbt|jj|jj|jj|jj|jj|jj|jj|jj |jj |jj |jj |jj |jj|jj|jjdS)a) Get all relevant data from the 'core_properties' attribute from a DOCX Document. :param document: The DOCX Document you want to extract metadata from :returns: A `DOCXMetadata` dataclass all the relevant fields from the 'core_properties' )rrrrrrrrrrrrrrr )rZcore_propertiesrrrrrrrrrrrrrrr )r-r9r(r(r)rFs" z!DOCXToDocument._get_docx_metadata)N)r!r"r#r$r.r Z output_typesrr r r%rrrrrrKrrFr(r(r(r)r*>s"2r*) rAZ dataclassesrrpathlibrtypingrrrrr Zhaystackr r r Z$haystack.components.converters.utilsr rZhaystack.dataclassesrZhaystack.lazy_importsr getLoggerr!r?r+r:Z docx.documentrLrr*r(r(r(r)s        &