Zig Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. 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 long_report.pdf

    const pdf = try chilkat.Pdf.init();
    defer pdf.deinit();
    pdf.loadFile("qa_data/pdf/long_report.pdf") catch {
        std.debug.print("{s}\n", .{try pdf.getLastErrorText(alloc)});
        return;
    };

    std.debug.print("Number of pages: {d}\n", .{pdf.getNumPages()});

    // ExtractTextSb takes the same operation and options as ExtractText, but the text
    // goes to a StringBuilder.  This avoids building a very large JSON string for
    // documents with many pages.
    const json = try chilkat.JsonObject.init();
    defer json.deinit();
    const sb_text = try chilkat.StringBuilder.init();
    defer sb_text.deinit();
    const json_out = try chilkat.JsonObject.init();
    defer json_out.deinit();

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

    std.debug.print("Extracted {d} characters.\n", .{sb_text.getLength()});

    // Save the text to a file.
    sb_text.writeFile("qa_output/long_report.txt", "utf-8", false) catch {
        std.debug.print("{s}\n", .{try sb_text.getLastErrorText(alloc)});
        return;
    };

    // The JSON output does not contain the text, but it still has the quality report.
    std.debug.print("Quality: {s}\n", .{try json_out.stringOf(alloc, "quality.rating")});
    std.debug.print("Pages with no text (need OCR): [{s}]\n", .{try json_out.stringOf(alloc, "quality.pagesNeedingOcr")});

    // Sample output:

    // Number of pages: 3
    // Extracted 4522 characters.
    // Quality: good
    // Pages with no text (need OCR): []
}