i ZSrSSKJr SSKJrJrJrJr SSKJ r SSK J r "SS\ 5r g) %Read PDF files using PyMuPDF library.)Path)DictListOptionalUnion) BaseReader)Documentc \rSrSrSrS S\\\4S\S\ \ S\ \ 4Sjjr S S\\\4S\S\ \ S\ \ 4S jjrS rg) PyMuPDFReader rN file_pathmetadata extra_inforeturnc"URXUS9$)zXLoads list of documents from PDF file and also accepts extra information in dict format.)rr)load)selfrrrs `/home/james-whalen/.local/lib/python3.13/site-packages/llama_index/readers/file/pymu_pdf/base.py load_dataPyMuPDFReader.load_data syy*yMMc vSSKn[U[5(d [U[5(d [ S5eUR U5nU(a [U[ 5(d [ S5eU(awU(d0n[U5US'[U5US'UVs/sHDn[UR5RS5[ U40SURS -0D6S 9PMF sn$UVs/sH3n[UR5RS5U=(d 0S 9PM5 sn$s snfs snf) a! Loads list of documents from PDF file and also accepts extra information in dict format. Args: file_path (Union[Path, str]): file path of PDF file (accepts string or Path). metadata (bool, optional): if metadata to be included or not. Defaults to True. extra_info (Optional[Dict], optional): extra information related to each document in dict format. Defaults to None. Raises: TypeError: if extra_info is not a dictionary. TypeError: if file_path is not a string or Path. Returns: List[Document]: list of documents. rNz#file_path must be a string or Path.z extra_info must be a dictionary. total_pagesrzutf-8source)textr) fitz isinstancestrr TypeErroropendictlenr get_textencodenumber)rrrrrdocpages rrPyMuPDFReader.loads<, )S))*Y2M2MAB Bii " j$// BCC  (+CJ} %&))nJ{ #   D//8#" %q(9    $  D//8ZEUSU   s "A D14:D6)TN)__name__ __module__ __qualname____firstlineno____doc__rrr boolrrrr rr__static_attributes__r+rrr r s/ %) Ns#NNTN N h N%) ?s#??TN ? h ??rr N) r0pathlibrtypingrrrrllama_index.core.readers.baser llama_index.core.schemar r r+rrr7s%+..4,KJKr