edgeparse_core/pdf/
mod.rs

1//! PDF loading layer — document loading, text extraction, line extraction.
2
3pub mod annotation_enrichment;
4pub mod annotation_extractor;
5pub mod bookmark_extractor;
6pub mod chunk_parser;
7pub mod encryption;
8pub mod font;
9pub mod font_style;
10pub mod font_type3;
11/// Type 3 CharProc → Unicode OCR cache (requires `image`).
12#[cfg(feature = "image")]
13pub mod font_type3_ocr;
14pub mod form_extractor;
15pub mod graphics_state;
16pub mod hyperlink_extractor;
17pub mod image_extractor;
18/// Image XObject codecs (DCT / Flate / JBIG2 / JPX) for the OCR path.
19#[cfg(feature = "image")]
20pub mod image_codecs;
21/// Cheap image-region classifier + OCR budget (native + WASM).
22pub mod image_region;
23/// In-memory Image-XObject → table lattice (WASM-safe; no pdfimages).
24pub mod inmem_raster;
25pub mod line_extractor;
26pub mod loader;
27pub mod metadata_writer;
28/// Optional Content Group default visibility.
29pub mod ocg;
30/// Pluggable raster OCR engines (Tesseract CLI / ocrs).
31pub mod ocr;
32pub mod page_info;
33pub mod pdf_string;
34#[cfg(not(target_arch = "wasm32"))]
35pub mod raster_table_ocr;
36pub mod text_extractor;
edgeparse_core/pdf/mod.rs

edgeparse_core/pdf/
mod.rs
