Rust 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. Rust

// 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

let pdf = chilkat::Pdf::new();
if pdf.load_file("qa_data/pdf/code_block.pdf").is_err() {
    println!("{}", pdf.last_error_text());
    return;
}

let json = chilkat::JsonObject::new();
let json_out = chilkat::JsonObject::new();

if pdf.extract_text("markdown", &json, &json_out).is_err() {
    println!("{}", pdf.last_error_text());
    return;
}

println!("---- default (code: true) ----");
println!("{}", json_out.string_of("markdown").unwrap_or_default());

let _ = json.update_bool("code", false);
if pdf.extract_text("markdown", &json, &json_out).is_err() {
    println!("{}", pdf.last_error_text());
    return;
}

println!("---- code: false ----");
println!("{}", json_out.string_of("markdown").unwrap_or_default());

// 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.