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 tika')parserc @speZdZdZd edddZejee dd ee ee e fe e eeefeeeeffdd d ZdS) TikaDocumentConvertera Converts files of different types to Documents. This component uses [Apache Tika](https://tika.apache.org/) for parsing the files and, therefore, requires a running Tika server. For more options on running Tika, see the [official documentation](https://github.com/apache/tika-docker/blob/main/README.md#usage). Usage example: ```python from haystack.components.converters.tika import TikaDocumentConverter converter = TikaDocumentConverter() results = converter.run( sources=["sample.docx", "my_document.rtf", "archive.zip"], meta={"date_added": datetime.now().isoformat()} ) documents = results["documents"] print(documents[0].content) # 'This is a text from the docx file.' ``` http://localhost:9998/tika)tika_urlcCst||_dS)zr Create a TikaDocumentConverter component. :param tika_url: Tika server URL. N) tika_importcheckr)selfrrG/tmp/pip-unpacked-wheel-z752163x/haystack/components/converters/tika.py__init__-szTikaDocumentConverter.__init__) documentsN)sourcesmetac Csg}t|t|d}t||D]\}}z t|}Wn:tk rl}ztjd||dWYqW5d}~XYnXz tjt |j |j dd} Wn:tk r} ztjd|| dWYqW5d} ~ XYnX|j |} t| | d} || qd |iS) a Converts files to Documents. :param sources: List of HTML 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 )rZ sources_countz4Could not read {source}. Skipping it. Error: {error})sourceerrorN)ZserverEndpointcontentzAFailed to extract text from {source}. Skipping it. Error: {error})rrr)r lenzipr Exceptionloggerwarning tika_parser from_bufferioBytesIOdatarrrappend) rrrrZ meta_listrmetadataZ bytestreametextZ conversion_eZmerged_metadatadocumentrrrrun7s*     zTikaDocumentConverter.run)r)N)__name__ __module__ __qualname____doc__strrr Z output_typesrrrrr rrrr.rrrrrs "r)r&pathlibrtypingrrrrrZhaystackrr r Z$haystack.components.converters.utilsr r Zhaystack.dataclassesr Zhaystack.lazy_importsrrZtikarr$ getLoggerr/r"rrrrrs