U DAf] @sxddlmZddlmZmZmZmZmZddlm Z m Z m Z ddl m Z mZddlmZe eZe GdddZdS) )Path)AnyDictListOptionalUnion)Document componentlogging)get_bytestream_from_sourcenormalize_metadata) ByteStreamc @speZdZdZd edddZejee dd ee ee e fe e eeefeeeeffdd d ZdS) TextFileToDocumentai Converts text files to Documents. Usage example: ```python from haystack.components.converters.txt import TextFileToDocument converter = TextFileToDocument() results = converter.run(sources=["sample.txt"]) documents = results["documents"] print(documents[0].content) # 'This is the content from the txt file.' ``` utf-8encodingcCs ||_dS)a Create a TextFileToDocument component. :param encoding: The encoding of the text files. Note that if the encoding is specified in the metadata of a source ByteStream, it will override this value. Nr)selfrrF/tmp/pip-unpacked-wheel-z752163x/haystack/components/converters/txt.py__init__ s zTextFileToDocument.__init__) documentsN)sourcesmetac Csg}t|t|d}t||D]\}}z t|}Wn:tk rl}ztjd||dWYqW5d}~XYnXz |jd|j } |j | } Wn:tk r}ztjd||dWYqW5d}~XYnX|j|} t | | d} | | qd|iS) a Converts text 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 )Z sources_countz4Could not read {source}. Skipping it. Error: {error})sourceerrorNrzDCould not convert file {source}. Skipping it. Error message: {error})contentrr)r lenzipr Exceptionloggerwarningrgetrdatadecoderappend) rrrrZ meta_listrmetadataZ bytestreamertextZmerged_metadatadocumentrrrrun+s,    zTextFileToDocument.run)r)N)__name__ __module__ __qualname____doc__strrr Z output_typesrrrrr rrrr)rrrrrs "rN)pathlibrtypingrrrrrZhaystackrr r Z$haystack.components.converters.utilsr r Zhaystack.dataclassesr getLoggerr*rrrrrrs