Zig Requires Chilkat v11.7.0+

Code Blocks and Code Spans in PDF to Markdown

See more PDF Text Extraction Examples

Demonstrates how monospaced text is converted by the "markdown" operation: a monospaced block becomes a fenced code block and a monospaced run inside a sentence becomes a code span. Set "code" to false to treat it as ordinary text. 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 code_block.pdf

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

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

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

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

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

    // Sample output:

    // ---- default (code: true) ----
    // <!-- page 1 -->
    //
    // # Extracting Text
    //
    // Load the PDF and call `ExtractText` with the operation and an options object. The result is returned as JSON:
    //
    // ```
    // new Pdf pdf;
    // success = pdf.LoadFile("report.pdf");
    // new JsonObject json;
    // new JsonObject jsonOut;
    // success = pdf.ExtractText("text",json,jsonOut);
    // println jsonOut.StringOf("text");
    // ```
    //
    // An empty options object extracts every page with the default clean-up. Set `pages` to limit the extraction.
    // ---- code: false ----
    // <!-- page 1 -->
    //
    // # Extracting Text
    //
    // Load the PDF and call ExtractText with the operation and an options object. The result is returned as JSON:
    //
    // new Pdf pdf; success = pdf.LoadFile("report.pdf"); new JsonObject json; new JsonObject jsonOut; success = pdf.ExtractText("text",json,jsonOut); println jsonOut.StringOf("text");
    //
    // An empty options object extracts every page with the default clean-up. Set pages to limit the extraction.
}