o j @sddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZmZmZddlmZdd lmZmZmZerJdd lmZeeZGd d d e ZGd ddeeeeedfZGdddeZdS)N)BytesIO) TYPE_CHECKINGBinaryIOUnion)settings)safe_int) PDFException) PDFObjRef PDFStream dict_value int_value)PSEOF)KWD PSKeyword PSStackParser) PDFDocumentc@s eZdZdS)PDFSyntaxErrorN)__name__ __module__ __qualname__rrG/var/www/ai-app/venv/lib/python3.10/site-packages/pdfminer/pdfparser.pyrsrc@sreZdZdZdeddfddZdd d Zed Zed Z ed Z edZ edZ edZ dededdfddZdS) PDFParseraPDFParser fetch PDF objects from a file stream. It can handle indirect references by referring to a PDF document set by set_document method. It also reads XRefs at the end of every PDF file. Typical usage: parser = PDFParser(fp) parser.read_xref() parser.read_xref(fallback=True) # optional parser.set_document(doc) parser.seek(offset) parser.nextobject() fpreturnNcCst||d|_d|_dS)NF)r__init__docfallback)selfrrrrr's  zPDFParser.__init__rrcCs ||_dS)z0Associates the parser with a PDFDocument object.N)r)rrrrr set_document,s zPDFParser.set_documentRsnullsendobjsstreamsxrefs startxrefpostokenc Cs||j|jfvr|j|ddS||jur!|j|ddS||jur/||dfdS||jur_t|j dkr[|d\\}}}t |}|dur]t |j |}|||fdSdSdS||j ur^|d\\}}t|}d}|jszt|d}Wnty} ztjrtd|| WYd} ~ nd} ~ ww||z|\}} Wnty} ztjrtd| WYd} ~ dSd} ~ ww|t| 7}|j|t|j|} ||| z|\} } Wnty} ztjrtd| WYd} ~ n/d} ~ wwd | vr | d } || 7}|jr| | d| 7} n|t| 7}|jr.| | 7} q|||td |||| dd |j dusKJt|t| |j j }|||fdS|||fdS) zHandles PDF-related keywords.NrLengthz/Length is undefined: zUnexpected EOFs endstreamz-Stream: pos=%d, objlen=%d, dic=%r, data=%r... )! KEYWORD_XREFKEYWORD_STARTXREF add_resultspopKEYWORD_ENDOBJ KEYWORD_NULLpush KEYWORD_Rlencurstackrr rKEYWORD_STREAMr rr KeyErrorrSTRICTrseeknextliner r bytearrayreadindexlogdebugr bytesdecipher)rr!r"_ _object_id object_idobjdicobjlenerrlinedata_lineposistreamrrr do_keyword7s                zPDFParser.do_keyword)rrrN)rrr__doc__rrrrr/r-r,r2r(r)intrrJrrrrrs rc@sJeZdZdZdeddfddZdddZed Zd e d e ddfd d Z dS)PDFStreamParsera#PDFStreamParser is used to parse PDF content streams that is contained in each page and has instructions for rendering the page. A reference to a PDF document is needed because a PDF content stream can also have indirect references to other objects in the same document. rFrNcCst|t|dSN)rrr)rrFrrrrszPDFStreamParser.__init__cCs|j|dSrN)r*popall)rrrrflushszPDFStreamParser.flushsobjr!r"cCs~||jur%|d\\}}}t|}|dur#t|j|}|||fdS||j|jfvr6tj r4t ddS|||fdS)Nr%zKeyword endobj found in stream) r/r+rr rr. KEYWORD_OBJr,rr4r)rr!r"r>r?r@rArrrrJs  zPDFStreamParser.do_keyword)rN) rrrrKr<rrPrrQrLrrJrrrrrMs  rM) loggingiortypingrrrpdfminerrpdfminer.castingrpdfminer.pdfexceptionsrpdfminer.pdftypesr r r r pdfminer.psexceptionsr pdfminer.psparserrrrpdfminer.pdfdocumentr getLoggerrr:rrrMrrrrs        m