Class PDFXRef

pattern/web/pdf/pdfparser.py:60–147

##  PDFXRef
##
class PDFXRef(PDFBaseXRef):
    
    def __init__(self):
        self.offsets = {}
        self.trailer = {}
        return

    def load(self, parser, debug=0):
        while 1:
            try:
                (pos, line) = parser.nextline()
                if not line.strip(): continue
            except PSEOF:
                raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
            if not line:
                raise PDFNoValidXRef('Premature eof: %r' % parser)
            if line.startswith('trailer'):
                parser.seek(pos)
                break
            f = line.strip().split(' ')
            if len(f) != 2:
                raise PDFNoValidXRef('Trailer not found: %r: line=%r' % (parser, line))
            try:
                (start, nobjs) = map(long, f)
            except ValueError:
                raise PDFNoValidXRef('Invalid line: %r: line=%r' % (parser, line))
            for objid in xrange(start, start+nobjs):
                try:
                    (_, line) = parser.nextline()
                except PSEOF:
                    raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
                f = line.strip().split(' ')
                if len(f) != 3:
                    raise PDFNoValidXRef('Invalid XRef format: %r, line=%r' % (parser, line))
                (pos, genno, use) = f
                if use != 'n': continue
                self.offsets[objid] = (int(genno), long(pos))
        if 1 <= debug:
            print >>sys.stderr, 'xref objects:', self.offsets
        self.load_trailer(parser)
        return

    KEYWORD_TRAILER = KWD('trailer')
    def load_trailer(self, parser):
        try:
            (_,kwd) = parser.nexttoken()
            assert kwd is self.KEYWORD_TRAILER
            (_,dic) = parser.nextobject()
        except PSEOF:
            x = parser.pop(1)
            if not x:
                raise PDFNoValidXRef('Unexpected EOF - file corrupted')
            (_,dic) = x[0]
        self.trailer.update(dict_value(dic))
        return

    PDFOBJ_CUE = re.compile(r'^(\d+)\s+(\d+)\s+obj\b')
    def load_fallback(self, parser, debug=0):