pdf_ocr/lib.rs
1#![warn(missing_docs)]
2//! OCR integration for scanned PDFs with pluggable engine support.
3
4// Copyright (c) 2026 Innovation Trigger B.V.
5//
6// PDFluent is available under two licences, at your option: the GNU AGPLv3, or
7// the PDFluent Commercial Licence. See the LICENSE file in this repository --
8// that file travels with the copy you received, which a URL does not.
9
10pub mod engine;
11pub mod error;
12/// Integrity checking for anything fetched over the network. Compiled always,
13/// feature flags or not, so its tests cannot be skipped out of CI.
14pub mod integrity;
15pub mod pipeline;
16
17#[cfg(feature = "tesseract")]
18pub mod tesseract;
19
20#[cfg(feature = "paddle")]
21pub mod paddle;
22
23pub use engine::{NoOpEngine, OcrEngine, OcrPageResult, OcrWord};
24pub use error::{OcrError, Result};
25pub use pipeline::{make_searchable, OcrConfig, OcrPageReport, OcrReport};
26
27#[cfg(feature = "tesseract")]
28pub use tesseract::TesseractEngine;
29
30#[cfg(feature = "paddle")]
31pub use paddle::PaddleOcrEngine;