Rust Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. Rust

// This example requires the Chilkat API to have been previously unlocked.
// See Global Unlock Sample for sample code.

// The three-page PDF used in this example is available at search_context.pdf

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

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

// The string to find.
let _ = json.update_string("query", "chilkat");

// The number of characters returned before and after each match.  The default is 40.
let _ = json.update_int("context", 30);

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

// "count" is the number of matches.  Each match has the page, the matched text as it appears
// in the PDF, and the text before and after it.
println!("Matches: {}", json_out.int_of("count"));

let mut i = 0;
let count_i = json_out.size_of_array("matches");
while i < count_i {
    json_out.set_i(i);
    println!("page {}: ...{}[{}]{}...", json_out.int_of("matches[i].page"), json_out.string_of("matches[i].before").unwrap_or_default(), json_out.string_of("matches[i].text").unwrap_or_default(), json_out.string_of("matches[i].after").unwrap_or_default());
    i = i + 1;
}

// The search ignores case by default.  Set caseSensitive to find only the exact spelling.
let _ = json.update_bool("caseSensitive", true);
let _ = json.update_string("query", "Chilkat");
if pdf.extract_text("search", &json, &json_out).is_err() {
    println!("{}", pdf.last_error_text());
    return;
}

println!("Case-sensitive matches for Chilkat: {}", json_out.int_of("count"));

// Sample output:

// Matches: 5
// page 1: ...[Chilkat] River Field Notes The Chilkat...
// page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
// page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
// page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
// page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
// Case-sensitive matches for Chilkat: 3