df-ocr-switcher 0.1.0

//! df-ocr-switcher — pipeline OCR documento in puro Rust.
//!
//! ## Architettura
//!
//! ```text
//! Input (TIFF/PNG/JPEG)
//!   └── DocPipeline
//!         ├── DocOrientationClassifier (ppocr-rs PP-LCNet)  → rotazione
//!         ├── LayoutAnalyzer           (ppocr-rs PP-DocLayoutV3) → regioni
//!         └── OcrEngine (impl):
//!               ├── PpOcrEngine   → detect_with_layout (PP-OCRv6)
//!               └── TesseractEngine → Ocr5Engine + layout assignment
//!   └── Output
//!         ├── Markdown  (to_markdown)
//!         └── JSON      (serde_json)
//! ```
//!
//! ## Quickstart
//!
//! ```no_run
//! use df_ocr_switcher::{DocPipeline, OutputFormat, PpOcrEngineConfig, engine::ppocr::PpOcrEngine};
//! use std::path::PathBuf;
//!
//! let engine = PpOcrEngine::new(PpOcrEngineConfig::default()).unwrap();
//! let mut pipeline = DocPipeline::new(
//!     Box::new(engine),
//!     "models/paddleocr/layout/PP-DocLayoutV3.onnx",
//! ).unwrap();
//!
//! let md = pipeline.process_file("scan.tiff", OutputFormat::Markdown).unwrap();
//! println!("{md}");
//! ```

pub mod engine;
pub mod error;
pub mod input;
pub mod output;
pub mod pipeline;

pub use engine::{OcrBlock, OcrEngine, OcrFormula, OcrLayoutBox, OcrPageResult, OcrTable, OcrWord};
pub use engine::ppocr::{OcrModelPaths, PpOcrEngine, PpOcrEngineConfig, TableModelPaths};
#[cfg(feature = "tesseract-engine")]
pub use engine::tesseract::{TesseractEngine, TesseractEngineConfig};
pub use error::{Error, Result};
pub use output::markdown::{page_to_markdown, to_markdown};
pub use pipeline::{DocPipeline, OutputFormat};