Class PDFParser

pattern/web/pdf/pdfparser.py:581–755

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.set_d

##  PDFParser
##
class PDFParser(PSStackParser):

    """
    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.set_document(doc)
      parser.seek(offset)
      parser.nextobject()
    
    """

    def __init__(self, fp):
        PSStackParser.__init__(self, fp)
        self.doc = None
        self.fallback = False
        return

    def set_document(self, doc):
        """Associates the parser with a PDFDocument object."""
        self.doc = doc
        return

    KEYWORD_R = KWD('R')
    KEYWORD_NULL = KWD('null')
    KEYWORD_ENDOBJ = KWD('endobj')
    KEYWORD_STREAM = KWD('stream')
    KEYWORD_XREF = KWD('xref')
    KEYWORD_STARTXREF = KWD('startxref')
    def do_keyword(self, pos, token):
        """Handles PDF-related keywords."""
        
        if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
            self.add_results(*self.pop(1))
        
        elif token is self.KEYWORD_ENDOBJ:
            self.add_results(*self.pop(4))

        elif token is self.KEYWORD_NULL:
            # null object
            self.push((pos, None))

        elif token is self.KEYWORD_R:
            # reference to indirect object
            try:
                ((_,objid), (_,genno)) = self.pop(2)
                (objid, genno) = (int(objid), int(genno))
                obj = PDFObjRef(self.doc, objid, genno)
                self.push((pos, obj))
            except PSSyntaxError:
                pass

        elif token is self.KEYWORD_STREAM: