U DAf @sddlZddlmZddlmZmZmZmZmZm Z ddl m Z m Z m Z mZmZddlmZmZddlmZddlmZddlmZed Zdd lmZW5QRXeeZGd d d eZGd ddZ e GdddZ!dS)N)Path)AnyDictListOptionalProtocolUnion)Document componentdefault_from_dictdefault_to_dictlogging)get_bytestream_from_sourcenormalize_metadata) ByteStream) LazyImport)deserialize_typezRun 'pip install pypdf') PdfReaderc@s4eZdZdZdedddZddZedd Zd S) PyPDFConverterzt A protocol that defines a converter which takes a PdfReader object and converts it into a Document object. rreaderreturncCsdSN)selfrrrH/tmp/pip-unpacked-wheel-z752163x/haystack/components/converters/pypdf.pyconvertszPyPDFConverter.convertcCsdSrrrrrrto_dictszPyPDFConverter.to_dictcCsdSrrclsdatarrr from_dict!szPyPDFConverter.from_dictN __name__ __module__ __qualname____doc__r rr classmethodr"rrrrrs rc@s4eZdZdZdedddZddZedd Zd S) DefaultConverterzp The default converter class that extracts text from a PdfReader object's pages and returns a Document. rrcCs ddd|jD}t|dS)zMExtract text from the PDF and return a Document object with the text content. css|]}|VqdSr)Z extract_text).0pagerrr -sz+DefaultConverter.convert..)content)joinZpagesr )rrtextrrrr+szDefaultConverter.convertcCst|S)z(Serialize the converter to a dictionary.)r rrrrr0szDefaultConverter.to_dictcCs t||S)z,Deserialize the converter from a dictionary.)r rrrrr"4szDefaultConverter.from_dictNr#rrrrr)&s r)c @seZdZdZdeedddZddZedd Z e j e e d de eeeefeeeeefe eeeffd d d ZdS)PyPDFToDocumenta# Converts PDF files to Documents. Uses `pypdf` compatible converters to convert PDF files to Documents. A default text extraction converter is used if one is not provided. Usage example: ```python from haystack.components.converters.pypdf import PyPDFToDocument converter = PyPDFToDocument() results = converter.run(sources=["sample.pdf"], meta={"date_added": datetime.now().isoformat()}) documents = results["documents"] print(documents[0].content) # 'This is a text from the PDF file.' ``` N convertercCst|pt|_dS)z Create an PyPDFToDocument component. :param converter: An instance of a PyPDFConverter compatible class. N) pypdf_importcheckr)r3)rr3rrr__init__NszPyPDFToDocument.__init__cCst||jdS)z{ Serializes the component to a dictionary. :returns: Dictionary with serialized data. r2)r r3rrrrrrYszPyPDFToDocument.to_dictcCs8t|ddd}||dd|dd<t||S)z Deserializes the component from a dictionary. :param data: Dictionary with serialized data. :returns: Deserialized component. Zinit_parametersr3type)rr"r )r r!Zconverter_classrrrr"bs zPyPDFToDocument.from_dict) documents)sourcesmetac Csg}t|t|d}t||D]\}}z t|}Wn:tk rl}ztjd||dWYqW5d}~XYnXz tt |j } |j | } Wn:tk r}ztjd||dWYqW5d}~XYnX|j |} | | _ || qd|iS)a Converts PDF 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}r8)rlenzipr ExceptionloggerwarningrioBytesIOr!r3rr:append) rr9r:r8Z meta_listr;metadataZ bytestreameZ pdf_readerdocumentZmerged_metadatarrrrunqs,   zPyPDFToDocument.run)N)N)r$r%r&r'rrr6rr(r"r Z output_typesrr rstrrrrrrHrrrrr1:s   "r1)"rBpathlibrtypingrrrrrrZhaystackr r r r r Z$haystack.components.converters.utilsrrZhaystack.dataclassesrZhaystack.lazy_importsrZ!haystack.utils.type_serializationrr4Zpypdfr getLoggerr$r@rr)r1rrrrs