Extremely fast phrase search implementation.
This implementation follows some of the ideas proposed in this blog post by Doug Turnbull. The full explanation on how the internals work can be found in here.
This crate uses the [log] crate for logging during indexing.
It's highly recommended to compile this crate with -C llvm-args=-align-all-functions=6.
use phrase_search::{CommonTokens, Indexer, SimdIntersect};
// Creates a new indexer that can be reused, it will index 300_000 documents
// in each batch and will use the top 50 most common tokens to speed up the search,
// by merging them.
let indexer = Indexer::new(Some(300_000), Some(CommonTokens::FixedNum(50)));
let docs = vec![
("look at my beautiful cat", 0),
("this is a document", 50),
("look at my dog", 25),
("look at my beautiful hamster", 35),
];
let index_name = "./index";
let db_size = 1024 * 1024;
// Indexes the documents returned by the iterator `it`.
// The index will be created at `index_name` with the given `db_size`.
let (searcher, num_indexed_documents) = indexer.index(docs, index_name, db_size)?;
// Search by the string "78"
let result = searcher.search::<SimdIntersect>("at my beautiful")?;
// This should return `[0, 35]`
let documents = result.get_documents()?;