orbok_extract/lib.rs
1//! # orbok-extract
2//!
3//! Text extraction (RFC-005): pluggable extractors turn boundary-
4//! validated source files into normalized, line-located segments.
5//! Extraction output is derived data — cacheable, rebuildable, never
6//! authoritative.
7
8pub mod normalize;
9pub mod registry;
10pub mod types;
11
12mod markdown;
13mod text;
14
15#[cfg(test)]
16mod tests;
17
18pub use registry::ExtractorRegistry;
19pub use types::{DocumentExtractor, ExtractOutput, ExtractedSegment, LocationQuality, SegmentKind};