o f @sddlZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z ddl m Z dd l mZdd l mZdd lmZdd lmZdd lmZddlmZddlmZer`ddlmZeeZGddde ZGdddeeee e dfZGdddeZdS)N)BytesIO)BinaryIO TYPE_CHECKINGOptionalUnion)settings) PDFException) PDFObjRef) PDFStream) dict_value) int_value)KWD)PSEOF) PSKeyword) PSStackParser) PSSyntaxError) PDFDocumentc@s eZdZdS)PDFSyntaxErrorN)__name__ __module__ __qualname__rrK/home/ubuntu/webapp/venv/lib/python3.10/site-packages/pdfminer/pdfparser.pyrsrc@sreZdZdZdeddfddZdd d Zed Zed Z ed Z edZ edZ edZ dededdfddZdS) PDFParsera PDFParser 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)r rrrr set_document2s zPDFParser.set_documentRsnullsendobjsstreamsxrefs startxrefpostokenc Cs||j|jfvr|j|ddS||jur!|j|ddS||jur/||dfdS||jurtt|j dkrrz,|d\\}}\}}t |t |}}|j dusWJt |j ||}|||fWdSt yqYdSwdS||jurS|d\\}}t|}d}|jszt|d}Wntytjrtd|Ynw||z|\}} WntytjrtdYdSw|t| 7}|j|t|j|} ||| z|\} } WntytjrtdYn+wd | vr| d } || 7}|jr| | d| 7} n|t| 7}|jr#| | 7} q|||td |||| dd |j dus@Jt|t | |j j!} ||| fdS|||fdS) zHandles PDF-related keywords.rNrLengthz/Length is undefined: %rzUnexpected EOFs endstreamz-Stream: pos=%d, objlen=%d, dic=%r, data=%r... )" KEYWORD_XREFKEYWORD_STARTXREF add_resultspopKEYWORD_ENDOBJ KEYWORD_NULLpush KEYWORD_Rlencurstackintrr rKEYWORD_STREAMr rr KeyErrorrSTRICTrseeknextlinerr bytearrayreadindexlogdebugr bytesdecipher)r r#r$_objidgennoobjdicobjlenlinedatalineposistreamrrr do_keyword=s                zPDFParser.do_keyword)rrrN)rrr__doc__rrr!rr0r.r-r4r)r*r3rrKrrrrrs rc@sJeZdZdZdeddfddZdddZed Zd e d e ddfd d Z dS)PDFStreamParsera( PDFStreamParser is used to parse PDF content streams that is contained in each page and has instructions for rendering the page. A reference to a PDF document is needed because a PDF content stream can also have indirect references to other objects in the same document. rGrNcCst|t|dSN)rrr)r rGrrrrszPDFStreamParser.__init__cCs|j|dSrN)r+popall)r rrrflushszPDFStreamParser.flushsobjr#r$cCs||jur5z%|d\\}}\}}t|t|}}t|j||}|||fWdSty4YdSw||j|jfvrFt j rDt ddS|||fdS)Nr&zKeyword endobj found in stream) r0r,r3r rr/r KEYWORD_OBJr-rr6r)r r#r$r@rArBrCrrrrKs  zPDFStreamParser.do_keyword)rN) rrrrLr>rrPrrQr3rrKrrrrrMs  rM)loggingiortypingrrrrrpdftypesr r r r r psparserrrrrr pdfdocumentr getLoggerrr<rrrMrrrrs(               q