U DAf @sddlZddlmZddlmZmZmZmZmZddl m Z m Z m Z ddl mZmZddlmZddlmZedZdd lmZW5QRXe eZe Gd d d ZdS) N)Path)AnyDictListOptionalUnion)Document componentlogging)get_bytestream_from_sourcenormalize_metadata) ByteStream) LazyImportzRun 'pip install python-pptx') Presentationc @szeZdZdZddZejedddZe j e e dd e e eeefee eeefe eeeffd d d ZdS) PPTXToDocumenta Converts PPTX files to Documents. Usage example: ```python from haystack.components.converters.pptx import PPTXToDocument converter = PPTXToDocument() results = converter.run(sources=["sample.pptx"], meta={"date_added": datetime.now().isoformat()}) documents = results["documents"] print(documents[0].content) # 'This is the text from the PPTX file.' ``` cCs tdS)z5 Create an PPTXToDocument component. N) pptx_importcheck)selfrG/tmp/pip-unpacked-wheel-z752163x/haystack/components/converters/pptx.py__init__&szPPTXToDocument.__init__) file_contentreturncCs\t|}g}|jD]:}g}|jD]}t|dr ||jq |d|qd|}|S)z1 Converts the PPTX file to text. text  )rZslidesZshapeshasattrappendrjoin)rrZpptx_presentationZtext_all_slidesZslideZ text_on_slideshaperrrr_convert,s    zPPTXToDocument._convert) documentsN)sourcesmetac Csg}t|t|d}t||D]\}}z t|}Wn:tk rl}ztjd||dWYqW5d}~XYnXz|t |j } Wn:tk r}ztjd||dWYqW5d}~XYnX|j |} | t | | dqd|iS)a Converts PPTX 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 )Z sources_countz4Could not read {source}. Skipping it. Error: {error})sourceerrorNzECould not read {source} and convert it to Document, skipping. {error})contentr#r!)r lenzipr Exceptionloggerwarningr ioBytesIOdatar#rr) rr"r#r!Z meta_listr$metadataZ bytestreamerZmerged_metadatarrrrun;s(  zPPTXToDocument.run)N)__name__ __module__ __qualname____doc__rr,r-strr r Z output_typesrrrrr rrrr1rrrrrs"r)r,pathlibrtypingrrrrrZhaystackrr r Z$haystack.components.converters.utilsr r Zhaystack.dataclassesr Zhaystack.lazy_importsrrZpptxr getLoggerr2r*rrrrrs