i ddlZddlZddlZddlZddlmZej eZde de fdZ de de fdZ de de de fdZ y) N)Union file_contentreturnc tjtj|}d}t |j D]:\}} |j }|r ||dzz }ntjd|d<|S#t$r'}tjd|d|dYd }~jd }~wwxYw#t$r-}tjd |dtd |d }~wwxYw) z< Extracts text from a PDF file with error handling.  z No text extracted from PDF page .z$Error extracting text from PDF page : Texc_infoNzFailed to parse PDF file: z&Invalid PDF format or corrupted file: ) PyPDF2 PdfReaderioBytesIO enumeratepages extract_textloggerwarning Exceptionerror ValueError)r pdf_readertextipage page_textpage_erres 6/var/www/html/strategist-ai/app/services/extraction.pyextract_text_from_pdfr! sG%%bjj&>?  !1!12 dGAt d --/ I,,DNN%EaS#JK  d  d CA3b S^b cc d G 1!5 EA!EFFGsBAB34B<B3 B0 B+&B3+B00B33 C)<(C$$C)c tjtj|}d}|jD]}||j dzz }|S#t $r-}tjd|dtd|d}~wwxYw)z= Extracts text from a DOCX file with error handling. rrzFailed to parse DOCX file: Tr z'Invalid DOCX format or corrupted file: N) docxDocumentrr paragraphsrrrrr)rdocrparars r extract_text_from_docxr(sHmmBJJ|45NN %D DII$ $D % H 21#6 FB1#FGGHsAA B(BBfilenamec&tjd||jjdd}|dk(r t |S|dk(r t |S|dvr |j dStjd|d|td|d#t$rltjd|d  |j d d cYS#t$r0}tjd |d|dtd|d}~wwxYwwxYw)zD Dispatcher for content extraction based on file extension. zExtracting content from: r pdfr#)txtmdjsoncsvzutf-8zUTF-8 decode failed for z, trying latin-1...zlatin-1ignore)errorszFailed to decode text file r Tr z$Unsupported encoding for text file: NzUnsupported file extension: z for file zUnsupported file format: z1. Supported types: PDF, DOCX, TXT, MD, JSON, CSV.) rinfolowersplitr!r(decodeUnicodeDecodeErrorrrrr)rr)extrs r extract_text_from_bytesr9,s4 KK+H:67 ..   %b )C e|$\22 %l33 , , T&&w/ /  3C5 8*MN4SE9jkll" T NN5hZ?RS T T#**9X*FF T :8*BqcJUY Z #Gz!RSS T  Ts0 B"D>CD D +DD  D)rr r#loggingtypingr getLogger__name__rbytesstrr!r(r9r rBsp    8 $GG#G* H H3 Hm%m3m3mrA