Zig Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. 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 (three receipts, one per page) is available at three_receipts.pdf

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();
    pdf.loadFile("qa_data/pdf/three_receipts.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();

    // Each of the three pages is a receipt with a "Total:" line.
    json.updateString("label", "Total") catch {};
    json.updateString("labelValue", "right") catch {};

    // By default only the first occurrence (in reading order) is used.
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

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

    // labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
    // by line breaks, and labelMatches has one entry per occurrence with its page.
    json.updateString("labelOccurrence", "all") catch {};
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    var i: i32 = 0;
    const count_i = json_out.sizeOfArray("labelMatches");
    while (i < count_i) {
        json_out.setI(i);
        std.debug.print("Page {d} total: {s}\n", .{ json_out.intOf("labelMatches[i].page"), try json_out.stringOf(alloc, "labelMatches[i].text") });
        i = i + 1;
    }

    // A number selects one occurrence: 2 is the second.
    json.updateInt("labelOccurrence", 2) catch {};
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

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

    // The occurrences are counted over the selected pages, so combining "pages" with the label
    // is another way to pick one receipt:
    json.updateString("labelOccurrence", "first") catch {};
    json.updateString("pages", "3") catch {};
    json.updateString("label", "Receipt No.") catch {};
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("Receipt number on page 3: {s}\n", .{try json_out.stringOf(alloc, "text")});

    // Sample output:

    // First total: $19.86
    // Page 1 total: $19.86
    // Page 2 total: $17.34
    // Page 3 total: $23.62
    // Second total: $17.34
    // Receipt number on page 3: 1003
}