Zig

Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF. Zig

const std = @import("std");
const chilkat = @import("chilkat");

pub fn main(init: std.process.Init) !void {
    const alloc = init.arena.allocator();

    // This example requires the Chilkat API to have been previously unlocked.
    // See Global Unlock Sample for sample code.

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();

    pdf.loadFile("qa_data/pdf/blank_with_metadata.pdf") catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    const sb_xml = try chilkat.StringBuilder.init();
    defer sb_xml.deinit();
    // Note: Not all PDF files have metadata.  Metadata is optional.
    pdf.getMetadata(sb_xml) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    const xml = try chilkat.Xml.init();
    defer xml.deinit();
    xml.loadSb(sb_xml, true) catch {};

    std.debug.print("{s}\n", .{try xml.getXml(alloc)});

    // Sample PDF metadata XML:
    // (Code for parsing follows)

    // Use this online tool to generate parsing code from sample XML:
    // Generate Parsing Code from XML

    // <?xml version="1.0" encoding="utf-8"?>
    // <x:xmpmeta xmlns:x="adobe:ns:meta/" x:xmptk="Adobe XMP Core 9.1-c001 79.675d0f7, 2023/06/11-19:21:16        ">
    //     <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
    //         <rdf:Description rdf:about="" xmlns:xmp="http://ns.adobe.com/xap/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/" xmlns:pdf="http://ns.adobe.com/pdf/1.3/" xmlns:xmpRights="http://ns.adobe.com/xap/1.0/rights/">
    //             <xmp:ModifyDate>2024-11-27T11:33:12-06:00</xmp:ModifyDate>
    //             <xmp:CreateDate>2024-11-27T11:28:23-06:00</xmp:CreateDate>
    //             <xmp:MetadataDate>2024-11-27T11:33:12-06:00</xmp:MetadataDate>
    //             <xmp:CreatorTool>Adobe Acrobat Pro (32-bit) 24.3.20112</xmp:CreatorTool>
    //             <dc:format>application/pdf</dc:format>
    //             <dc:title>
    //                 <rdf:Alt>
    //                     <rdf:li xml:lang="x-default">Blank</rdf:li>
    //                 </rdf:Alt>
    //             </dc:title>
    //             <dc:creator>
    //                 <rdf:Bag>
    //                     <rdf:li>Chilkat Software</rdf:li>
    //                 </rdf:Bag>
    //             </dc:creator>
    //             <dc:description>
    //                 <rdf:Alt>
    //                     <rdf:li xml:lang="x-default">Blank Document</rdf:li>
    //                 </rdf:Alt>
    //             </dc:description>
    //             <dc:subject>
    //                 <rdf:Bag>
    //                     <rdf:li>blank</rdf:li>
    //                     <rdf:li>metadata</rdf:li>
    //                     <rdf:li>document</rdf:li>
    //                 </rdf:Bag>
    //             </dc:subject>
    //             <xmpMM:DocumentID>uuid:34535ffa-b632-43f1-b1fd-80cea6fdc351</xmpMM:DocumentID>
    //             <xmpMM:InstanceID>uuid:69ace620-4c54-407f-8d45-6eebc90f34c2</xmpMM:InstanceID>
    //             <pdf:Producer>Adobe Acrobat Pro (32-bit) 24.3.20112</pdf:Producer>
    //             <pdf:Keywords>blank; metadata; document</pdf:Keywords>
    //             <xmpRights:WebStatement>https://www.chilkatsoft.com/</xmpRights:WebStatement>
    //         </rdf:Description>
    //     </rdf:RDF>
    // </x:xmpmeta>

    _ = try xml.getAttrValue(alloc, "xmlns:x");
    _ = try xml.getAttrValue(alloc, "x:xmptk");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|(xmlns:rdf)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(rdf:about)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(xmlns:xmp)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(xmlns:dc)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(xmlns:xmpMM)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(xmlns:pdf)");
    _ = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|(xmlns:xmpRights)");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmp:ModifyDate");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmp:CreateDate");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmp:MetadataDate");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmp:CreatorTool");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|dc:format");
    var rdf_li_xml_lang: [:0]const u8 = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)");
    var rdf_li: [:0]const u8 = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li");
    rdf_li = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li");
    rdf_li_xml_lang = try xml.chilkatPath(alloc, "rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)");
    rdf_li = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li");
    var i: i32 = 0;
    const count_i = xml.numChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li");
    while (i < count_i) {
        xml.setI(i);
        rdf_li = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]");
        i = i + 1;
    }

    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmpMM:DocumentID");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmpMM:InstanceID");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|pdf:Producer");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|pdf:Keywords");
    _ = try xml.getChildContent(alloc, "rdf:RDF|rdf:Description|xmpRights:WebStatement");
}