Function get_ocmd

src_classic/utils.py:4639–4702

Return the definition of an OCMD (optional content membership dictionary). Recognizes PDF dict keys /OCGs (PDF array of OCGs), /P (policy string) and /VE (visibility expression, PDF array). Via string manipulation, this info is converted to a Python dictionary with keys "xref", "ocgs",

(doc: Document, xref: int)

def get_ocmd(doc: Document, xref: int) -> dict:
    """Return the definition of an OCMD (optional content membership dictionary).

    Recognizes PDF dict keys /OCGs (PDF array of OCGs), /P (policy string) and
    /VE (visibility expression, PDF array). Via string manipulation, this
    info is converted to a Python dictionary with keys "xref", "ocgs", "policy"
    and "ve" - ready to recycle as input for 'set_ocmd()'.
    """

    if xref not in range(doc.xref_length()):
        raise ValueError("bad xref")
    text = doc.xref_object(xref, compressed=True)
    if "/Type/OCMD" not in text:
        raise ValueError("bad object type")
    textlen = len(text)

    p0 = text.find("/OCGs[")  # look for /OCGs key
    p1 = text.find("]", p0)
    if p0 < 0 or p1 < 0:  # no OCGs found
        ocgs = None
    else:
        ocgs = text[p0 + 6 : p1].replace("0 R", " ").split()
        ocgs = list(map(int, ocgs))

    p0 = text.find("/P/")  # look for /P policy key
    if p0 < 0:
        policy = None
    else:
        p1 = text.find("ff", p0)
        if p1 < 0:
            p1 = text.find("on", p0)
        if p1 < 0:  # some irregular syntax
            raise ValueError("bad object at xref")
        else:
            policy = text[p0 + 3 : p1 + 2]

    p0 = text.find("/VE[")  # look for /VE visibility expression key
    if p0 < 0:  # no visibility expression found
        ve = None
    else:
        lp = rp = 0  # find end of /VE by finding last ']'.
        p1 = p0
        while lp < 1 or lp != rp:
            p1 += 1
            if not p1 < textlen:  # some irregular syntax
                raise ValueError("bad object at xref")
            if text[p1] == "[":
                lp += 1
            if text[p1] == "]":
                rp += 1
        # p1 now positioned at the last "]"
        ve = text[p0 + 3 : p1 + 1]  # the PDF /VE array
        ve = (
            ve.replace("/And", '"and",')
            .replace("/Not", '"not",')
            .replace("/Or", '"or",')
        )
        ve = ve.replace(" 0 R]", "]").replace(" 0 R", ",").replace("][", "],[")