Class OcrReadOptions

Namespace

Egami.Ocr

Assembly

Egami.dll

Limits for reading hOCR and ALTO files, which may come from an untrusted engine or file.

public sealed record OcrReadOptions : IEquatable<OcrReadOptions>

Inheritance

object

OcrReadOptions

Implements

IEquatable<OcrReadOptions>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Examples

// Read hOCR from Tesseract or any other engine, under limits for files you did not make.
using FileStream file = File.OpenRead("page.hocr");
IReadOnlyList<OcrResult> pages = Hocr.Read(file, new OcrReadOptions { MaxWords = 100_000 });
Console.WriteLine($"{pages.Count} page, {pages[0].Words.Count()} words: {pages[0].Lines[0].Text}");

// Write results back as hOCR (or Alto.Write for ALTO).
using FileStream copy = File.Create("copy.hocr");
Hocr.Write(copy, pages);

Properties

Default

Gets the default options.

public static OcrReadOptions Default { get; }

Property Value

OcrReadOptions

Dpi

Gets the resolution, in pixels per inch, that turns ALTO positions in 1/10 mm or 1/1200 inch into pixels. Defaults to 300.

public double Dpi { get; init; }

Property Value

double

MaxBytes

Gets the largest file, in bytes. Defaults to 256 MB.

public long MaxBytes { get; init; }

Property Value

long

MaxWords

Gets the most words in one file, over all pages. Defaults to 4,000,000.

public int MaxWords { get; init; }

Property Value

int