iJ6dZddlmZddlmZdedeefdZy)z` PDF text extraction utilities. Provides text extraction from PDF files using pypdf or PyPDF2. )Optional)verbose_logger file_contentreturnc ddlm} ddlm}||}||}g}|jD]&}|j }|s|j |(|r5dj|}tjdt|d|S ddl m} ||}| |}g}|jD]&}|j }|s|j |(|r5dj|}tjdt|d|S y #t$rtjdYwxYw#t$rtjd Yy 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 z characters from PDF using pypdfz"pypdf not available, trying PyPDF2z! characters from PDF using PyPDF2zIPyPDF2 not available, PDF extraction requires OCR or pypdf/PyPDF2 libraryzPDF text extraction failed: N)iorpypdfr pages extract_textappendjoinrdebuglen ImportErrorPyPDF2 Exception) rr PypdfReaderpdf_filereader text_partspagetextextracted_text PyPDF2Readeres ~/Users/manta/Documents/Projects/TheRoad-I1/.venv/lib/python3.12/site-packages/litellm/rag/ingestion/file_parsers/pdf_parser.pyextract_text_from_pdfr s4A G 6|,H *FJ ((*%%d+% !'Z!8$$ ^!4 55UV&%   8|,H!(+FJ ((*%%d+% !'Z!8$$ ^!4 55VW&%  ? G  !E F G.   [    A;A3?@@ AsfE9DA D E9D9 A D9D63E5D66E9EEEE F&FFN)__doc__typingrlitellm._loggingrbytesstrrrr's, +@@(3-@r&