Zig Requires Chilkat v11.7.0+

Extract One Section of a PDF by its Heading

See more PDF Text Extraction Examples

Demonstrates "labelValue": "section", which returns everything from a heading up to the next heading of the same or higher level. With the "markdown" operation the section keeps its own sub-headings. 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.

    // The PDF used in this example is available at sectioned_doc.pdf

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();
    pdf.loadFile("qa_data/pdf/sectioned_doc.pdf") catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

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

    // The document has the sections Introduction, Opening Hours, Terms and Conditions (with the
    // sub-sections Admission, Safety and Liability) and Contact.  Get the Terms and Conditions:
    // everything after that heading up to the next heading of the same level (Contact).  The heading
    // itself is not part of the value; labelMatches[0].label has it.
    json.updateString("label", "Terms and Conditions") catch {};
    json.updateString("labelValue", "section") catch {};

    pdf.extractText("markdown", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("{s}\n", .{try json_out.stringOf(alloc, "markdown")});

    // The same with the "text" operation gives the section as plain text.
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("---- as text ----\n", .{});
    std.debug.print("{s}\n", .{try json_out.stringOf(alloc, "text")});

    // Sample output:

    // ### Admission
    //
    // Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
    //
    // ### Safety
    //
    // No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
    //
    // ### Liability
    //
    // Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.
    // ---- as text ----
    // Admission
    //
    // Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
    //
    // Safety
    //
    // No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
    //
    // Liability
    //
    // Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.
}