Zig Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. 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 packing slip used in this example is available at packing_slip.pdf

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();
    pdf.loadFile("qa_data/pdf/packing_slip.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 packing slip has the captions "Bill To" and "Ship To" side by side,
    // each with an address block below it.
    json.updateString("label", "Ship To") catch {};

    // "below" means the value is the block of text directly under the label.
    json.updateString("labelValue", "below") catch {};

    // With the default "flow" layout the lines of the block would be joined into one paragraph.
    // "lines" keeps each line of the address on its own line.
    json.updateString("layout", "lines") catch {};

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

    std.debug.print("Ship To:\n", .{});
    std.debug.print("{s}\n", .{try json_out.stringOf(alloc, "text")});
    std.debug.print("\n", .{});

    json.updateString("label", "Bill To") catch {};
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("Bill To:\n", .{});
    std.debug.print("{s}\n", .{try json_out.stringOf(alloc, "text")});
    std.debug.print("\n", .{});

    // A caption over a short paragraph works the same way.  Here the flow layout is better,
    // because the two lines are one piece of text.
    json.updateString("label", "Special Instructions") catch {};
    json.updateString("layout", "flow") catch {};
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("Special Instructions:\n", .{});
    std.debug.print("{s}\n", .{try json_out.stringOf(alloc, "text")});

    // Sample output:

    // Ship To:
    // Frank Delgado
    // c/o Harbor Pet Boarding
    // 9 Ferry Lane
    // Portside, WA 98001
    //
    // Bill To:
    // Frank Delgado
    // Apartment 3B
    // 41 Mill Street
    // Portside, WA 98000
    //
    // Special Instructions:
    // Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.
}