Zig

Extract Embedded Files from PDF

Demonstrates how to get information about the embedded files (if any) contained within a PDF, and shows how to extract each file.

Note: This example requires Chilkat v9.5.0.95 or greater.

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

    // Note: The embedded file functionality was added in Chilkat v9.5.0.95

    // How many embedded files exist within the opened PDF?
    const num_files = pdf.getNumEmbeddedFiles();
    std.debug.print("Number of embedded files: {d}\n", .{num_files});

    const json = try chilkat.JsonObject.init();
    defer json.deinit();
    json.setEmitCompact(false);

    const bd = try chilkat.BinData.init();
    defer bd.deinit();

    // Get information about each file, and extract each to the filesystem.
    var i: i32 = 0;
    while (i < num_files) {
        pdf.getEmbeddedFileInfo(i, json) catch {
            std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
            return;
        };

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

        // Get the filename from the JSON.
        var filename: [:0]const u8 = "someFile.dat";

        // The filename SHOULD always be present..
        if (json.hasMember("filename")) {
            filename = try json.stringOf(alloc, "filename");
        }

        // Get the file data.
        pdf.getEmbeddedFileBd(i, bd) catch {
            std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
            return;
        };

        // Save the contents of the bd to the filename (in the current working directory) in the filesystem.
        bd.writeFile(filename) catch {
            std.debug.print("Failed to write output file.\n", .{});
        };

        i = i + 1;
    }

    // Sample output for the above code:

    // Number of embedded files: 3
    // {
    //   "filename": "employees.json",
    //   "desc": "JSON",
    //   "subType": "application/json",
    //   "size": 159,
    //   "creationDate": "D:20230715170506-05'00'",
    //   "modDate": "D:20160207153838-05'00'"
    // }
    //
    // {
    //   "filename": "rsaPubKey.pem",
    //   "desc": "RSA Public Key PEM",
    //   "size": 451,
    //   "creationDate": "D:20230715170546-05'00'",
    //   "modDate": "D:20150724133153-05'00'"
    // }
    //
    // {
    //   "filename": "starfish.jpg",
    //   "desc": "Starfish JPG",
    //   "subType": "image/jpeg",
    //   "size": 6229,
    //   "creationDate": "D:20230715170356-05'00'",
    //   "modDate": "D:20080529103055-05'00'"
    // }
}