ruwex 0.1.0

//! ruwex — a fast Rust rewrite of [wikiextractor], extracting and cleaning
//! text from Wikimedia XML dumps.
//!
//! The crate is usable as a library; the `wikiextractor` binary is a thin
//! CLI wrapper over [`pipeline::run`]. See the README for usage and the
//! compatibility notes.
//!
//! [wikiextractor]: https://github.com/WikiExtractor/wikiextractor

pub mod clean;
pub mod config;
pub mod dump;
mod error;
pub mod expand;
pub mod output;
pub mod pipeline;
pub mod title_index;
pub mod tools;

pub use config::{ExtractorConfig, OutputFormat, default_namespaces, default_workers, parse_size};
pub use dump::reader::PageSource;
pub use dump::{Page, SiteInfo};
pub use error::{Error, Result};
pub use expand::{LazyTemplateSource, TemplateDb, TemplateSource};
pub use output::format::render_page;
pub use output::writer::{DocSink, ShardedWriter, StdoutSink};
pub use pipeline::{Stats, run, run_with_templates};
pub use title_index::TitleIndex;