uPj*dZddlmZdededzfdZy)z` PDF text extraction utilities. Provides text extraction from PDF files using pypdf or PyPDF2. )verbose_logger file_contentreturnNc ddlm} ddlm}||}||}g}|jD]&}|j }|s|j |(|r2dj|}tjdt||S ddl m} ||}| |}g}|jD]&}|j }|s|j |(|r2dj|}tjdt||S y #t$rtjdYwxYw#t$rtjdYy wxYw#t$r } tjd | Yd } ~ y d } ~ wwxYw) z Extract text from PDF using pypdf if available. Args: file_content: Raw PDF bytes Returns: Extracted text or None if extraction fails r)BytesIO) PdfReaderz z,Extracted %s characters from PDF using pypdfz"pypdf not available, trying PyPDF2z-Extracted %s characters from PDF using PyPDF2zIPyPDF2 not available, PDF extraction requires OCR or pypdf/PyPDF2 libraryzPDF text extraction failed: %sN)iorpypdfrpages extract_textappendjoinrdebuglen ImportErrorPyPDF2 Exception) rr PypdfReaderpdf_filereader text_partspagetextextracted_text PyPDF2Readeres r/home/oem/CyberBrain26-unified/.venv/lib/python3.12/site-packages/litellm/rag/ingestion/file_parsers/pdf_parser.pyextract_text_from_pdfr s.B G 6|,H *FJ  ,((*%%d+ , !'Z!8$$%SUXYgUhi%% n 8|,H!(+FJ  ,((*%%d+ , !'Z!8$$%TVYZhVij%% 7 G  !E F G* n  !l m   n B=qAA BsfE9DAD E 9D3AD3D0-E/D00E3EEEE F E;;F)__doc__litellm._loggingrbytesstrrrr%s& ,::#*:r$