ld-lucivy 0.26.1

//! Tokenizer are in charge of chopping text into a stream of tokens
//! ready for indexing.
//!
//! You must define in your schema which tokenizer should be used for
//! each of your fields :
//!
//! ```rust
//! use lucivy::schema::*;
//!
//! let mut schema_builder = Schema::builder();
//!
//! let text_options = TextOptions::default()
//!     .set_indexing_options(
//!         TextFieldIndexing::default()
//!             .set_tokenizer("en_stem")
//!             .set_index_option(IndexRecordOption::Basic)
//!     )
//!     .set_stored();
//!
//! let id_options = TextOptions::default()
//!     .set_indexing_options(
//!         TextFieldIndexing::default()
//!             .set_tokenizer("raw_ids")
//!             .set_index_option(IndexRecordOption::WithFreqsAndPositions)
//!     )
//!     .set_stored();
//!
//! schema_builder.add_text_field("title", text_options.clone());
//! schema_builder.add_text_field("text", text_options);
//! schema_builder.add_text_field("uuid", id_options);
//!
//! let schema = schema_builder.build();
//! ```
//!
//! By default, `lucivy` offers the following tokenizers:
//!
//! ## `default`
//!
//! `default` is the tokenizer that will be used if you do not
//! assign a specific tokenizer to your text field.
//! It will chop your text on punctuation and whitespaces,
//! removes tokens that are longer than 40 chars, and lowercase your text.
//!
//! ## `raw`
//! Does not actual tokenizer your text. It keeps it entirely unprocessed.
//! It can be useful to index uuids, or urls for instance.
//!
//! ## `en_stem`
//!
//! In addition to what `default` does, the `en_stem` tokenizer also
//! apply stemming to your tokens. Stemming consists in trimming words to
//! remove their inflection. This tokenizer is slower than the default one,
//! but is recommended to improve recall.
//!
//! # Custom tokenizer Library
//! Avoid using lucivy as dependency and prefer `lucivy-tokenizer-api` instead.
//!
//! # Custom tokenizers
//!
//! You can write your own tokenizer by implementing the [`Tokenizer`] trait
//! or you can extend an existing [`Tokenizer`] by chaining it with several
//! [`TokenFilter`]s.
//!
//! For instance, the `en_stem` is defined as follows.
//!
//! ```rust
//! use lucivy::tokenizer::*;
//!
//! let en_stem = TextAnalyzer::builder(SimpleTokenizer::default())
//!     .filter(RemoveLongFilter::limit(40))
//!     .filter(LowerCaser)
//!     .filter(Stemmer::new(Language::English))
//!     .build();
//! ```
//!
//! Once your tokenizer is defined, you need to
//! register it with a name in your index's [`TokenizerManager`].
//!
//! ```rust
//! # use lucivy::schema::Schema;
//! # use lucivy::tokenizer::*;
//! # use lucivy::Index;
//! #
//! let custom_en_tokenizer = SimpleTokenizer::default();
//! # let schema = Schema::builder().build();
//! let index = Index::create_in_ram(schema);
//! index.tokenizers()
//!      .register("custom_en", custom_en_tokenizer);
//! ```
//!
//! If you built your schema programmatically, a complete example
//! could like this for instance.
//!
//! Note that tokens with a len greater or equal to
//! [`MAX_TOKEN_LEN`].
//!
//! # Example
//!
//! ```rust
//! use lucivy::schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
//! use lucivy::tokenizer::*;
//! use lucivy::Index;
//!
//! let mut schema_builder = Schema::builder();
//! let text_field_indexing = TextFieldIndexing::default()
//!     .set_tokenizer("custom_en")
//!     .set_index_option(IndexRecordOption::WithFreqsAndPositions);
//! let text_options = TextOptions::default()
//!     .set_indexing_options(text_field_indexing)
//!     .set_stored();
//! schema_builder.add_text_field("title", text_options);
//! let schema = schema_builder.build();
//! let index = Index::create_in_ram(schema);
//!
//! // We need to register our tokenizer :
//! let custom_en_tokenizer = TextAnalyzer::builder(SimpleTokenizer::default())
//!     .filter(RemoveLongFilter::limit(40))
//!     .filter(LowerCaser)
//!     .build();
//! index
//!     .tokenizers()
//!     .register("custom_en", custom_en_tokenizer);
//! ```
mod alphanum_only;
mod ascii_folding_filter;
mod empty_tokenizer;
mod facet_tokenizer;
mod lower_caser;
mod ngram_tokenizer;
mod raw_tokenizer;
mod regex_tokenizer;
mod remove_long;
mod simple_tokenizer;
mod split_compound_words;
mod stop_word_filter;
mod tokenized_string;
mod tokenizer;
mod tokenizer_manager;
mod whitespace_tokenizer;

#[cfg(feature = "stemmer")]
mod stemmer;
pub use tokenizer_api::{BoxTokenStream, Token, TokenFilter, TokenStream, Tokenizer};

pub use self::alphanum_only::AlphaNumOnlyFilter;
pub use self::ascii_folding_filter::{AsciiFoldingFilter, to_ascii};
pub use self::facet_tokenizer::FacetTokenizer;
pub use self::lower_caser::LowerCaser;
pub use self::ngram_tokenizer::NgramTokenizer;
pub use self::raw_tokenizer::RawTokenizer;
pub use self::regex_tokenizer::RegexTokenizer;
pub use self::remove_long::RemoveLongFilter;
pub use self::simple_tokenizer::{SimpleTokenStream, SimpleTokenizer};
pub use self::split_compound_words::SplitCompoundWords;
#[cfg(feature = "stemmer")]
pub use self::stemmer::{Language, Stemmer};
pub use self::stop_word_filter::StopWordFilter;
pub use self::tokenized_string::{PreTokenizedStream, PreTokenizedString};
pub use self::tokenizer::{TextAnalyzer, TextAnalyzerBuilder};
pub use self::tokenizer_manager::TokenizerManager;
pub use self::whitespace_tokenizer::WhitespaceTokenizer;

/// Maximum authorized len (in bytes) for a token.
///
/// Tokenizers are in charge of not emitting tokens larger than this value.
/// Currently, if a faulty tokenizer implementation emits tokens with a length larger than
/// `2^16 - 1 - 5`, the token will simply be ignored downstream.
pub const MAX_TOKEN_LEN: usize = u16::MAX as usize - 5;

#[cfg(test)]
pub(crate) mod tests {
    use super::{Token, TokenizerManager};

    /// This is a function that can be used in tests and doc tests
    /// to assert a token's correctness.
    pub fn assert_token(token: &Token, position: usize, text: &str, from: usize, to: usize) {
        assert_eq!(
            token.position, position,
            "expected position {position} but {token:?}"
        );
        assert_eq!(token.text, text, "expected text {text} but {token:?}");
        assert_eq!(
            token.offset_from, from,
            "expected offset_from {from} but {token:?}"
        );
        assert_eq!(token.offset_to, to, "expected offset_to {to} but {token:?}");
    }

    #[test]
    fn test_raw_tokenizer2() {
        let tokenizer_manager = TokenizerManager::default();
        let mut en_tokenizer = tokenizer_manager.get("raw").unwrap();
        let mut tokens: Vec<Token> = vec![];
        {
            let mut add_token = |token: &Token| {
                tokens.push(token.clone());
            };
            en_tokenizer
                .token_stream("Hello, happy tax payer!")
                .process(&mut add_token);
        }
        assert_eq!(tokens.len(), 1);
        assert_token(&tokens[0], 0, "Hello, happy tax payer!", 0, 23);
    }

    #[test]
    fn test_tokenizer_does_not_exist() {
        let tokenizer_manager = TokenizerManager::default();
        assert!(tokenizer_manager.get("en_doesnotexist").is_none());
    }

    #[test]
    fn test_tokenizer_empty() {
        let tokenizer_manager = TokenizerManager::default();
        let mut en_tokenizer = tokenizer_manager.get("default").unwrap();
        {
            let mut tokens: Vec<Token> = vec![];
            {
                let mut add_token = |token: &Token| {
                    tokens.push(token.clone());
                };
                en_tokenizer.token_stream(" ").process(&mut add_token);
            }
            assert!(tokens.is_empty());
        }
        {
            let mut tokens: Vec<Token> = vec![];
            {
                let mut add_token = |token: &Token| {
                    tokens.push(token.clone());
                };
                en_tokenizer.token_stream(" ").process(&mut add_token);
            }
            assert!(tokens.is_empty());
        }
    }

    #[test]
    fn test_whitespace_tokenizer() {
        let tokenizer_manager = TokenizerManager::default();
        let mut ws_tokenizer = tokenizer_manager.get("whitespace").unwrap();
        let mut tokens: Vec<Token> = vec![];
        {
            let mut add_token = |token: &Token| {
                tokens.push(token.clone());
            };
            ws_tokenizer
                .token_stream("Hello, happy tax payer!")
                .process(&mut add_token);
        }

        assert_eq!(tokens.len(), 4);
        assert_token(&tokens[0], 0, "Hello,", 0, 6);
        assert_token(&tokens[1], 1, "happy", 7, 12);
        assert_token(&tokens[2], 2, "tax", 13, 16);
        assert_token(&tokens[3], 3, "payer!", 17, 23);
    }
}