Zig Requires Chilkat v11.7.0+

Rejoin Words Hyphenated at Line Ends

See more PDF Text Extraction Examples

Demonstrates the "dehyphenate" clean-up option (true by default). A word broken at the end of a line ("docu-" / "ment") is rejoined, while a hyphen that belongs to the word ("self-service") is kept. Set the option to false to keep the lines exactly as printed. 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 hyphenated.pdf

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();
    pdf.loadFile("qa_data/pdf/hyphenated.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 paragraph breaks "document", "self-service", "underlying" and "re-issued" at line ends.
    // The default rejoins them.  "self-service" keeps its hyphen because the word appears with it,
    // unbroken, elsewhere on the page; "re-issued" appears nowhere else, so it becomes "reissued".
    pdf.extractText("text", json, json_out) catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

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

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

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

    // Sample output:

    // ---- default (dehyphenate: true) ----
    // Self-Service Kiosk Notes
    //
    // The new self-service kiosk in the lobby prints a visitor badge from the document number on the reservation. Staff should direct first-time visitors to the self-service kiosk rather than the desk, and should keep the paper tray topped up. The underlying software restarts itself overnight; a badge that fails to print is reissued at the desk on request.
    // ---- dehyphenate: false ----
    // Self-Service Kiosk Notes
    //
    // The new self-service kiosk in the lobby prints a visitor badge from the docu- ment number on the reservation. Staff should direct first-time visitors to the self- service kiosk rather than the desk, and should keep the paper tray topped up. The under- lying software restarts itself overnight; a badge that fails to print is re- issued at the desk on request.
}