Tantivy analysis

This a collection of Tokenizer and TokenFilters for Tantivy that aims to replicate features available in Lucene.

It relies on Google's Rust ICU.

Breaking word rules are from Lucene.

Features

• icu feature includes the following components (they are also features) :
  • ICUTokenizer
  • ICUNormalizer2TokenFilter
  • ICUTransformTokenFilter
• commons features includes the following components
  • LengthTokenFilter
  • TrimTokenFilter
  • LimitTokenCountFilter
  • PathTokenizer
  • ReverseTokenFilter
  • ElisionTokenFilter
  • StopTokenFilter

By default, all features are included.

Example

```rust use tantivy::{doc, Index, ReloadPolicy}; use tantivy::collector::TopDocs; use tantivy::query::QueryParser; use tantivy::schema::{IndexRecordOption, SchemaBuilder, TextFieldIndexing, TextOptions}; use tantivy::tokenizer::TextAnalyzer; use tantivyanalysiscontrib::icu::{Direction, ICUTokenizer, ICUTransformTokenFilter};

const ANALYSIS_NAME: &str = "test";

fn main() -> Result<(), Box> { let options = TextOptions::default() .setindexingoptions( TextFieldIndexing::default() .settokenizer(ANALYSISNAME) .setindexoption(IndexRecordOption::WithFreqsAndPositions), ) .setstored(); let mut schema = SchemaBuilder::new(); schema.addtext_field("field", options); let schema = schema.build();

let transform = ICUTransformTokenFilter {
    compound_id: "Any-Latin; NFD; [:Nonspacing Mark:] Remove; Lower;  NFC".to_string(),
    rules: None,
    direction: Direction::Forward
};
let icu_analyzer = TextAnalyzer::from(ICUTokenizer).filter(transform);

let field = schema.get_field("field").expect("Can't get field.");

let index = Index::create_in_ram(schema);
index.tokenizers().register(ANALYSIS_NAME, icu_analyzer);

let mut index_writer = index.writer(3_000_000)?;

index_writer.add_document(doc!(
    field => "中国"
))?;
index_writer.add_document(doc!(
    field => "Another Document"
))?;

index_writer.commit()?;

let reader = index
    .reader_builder()
    .reload_policy(ReloadPolicy::OnCommit)
    .try_into()?;

let searcher = reader.searcher();

let query_parser = QueryParser::for_index(&index, vec![field]);

let query = query_parser.parse_query("zhong")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
let mut result: Vec<String> = Vec::new();
for (_, doc_address) in top_docs {
    let retrieved_doc = searcher.doc(doc_address)?;
    let values: Vec<&str> = retrieved_doc.get_all(field).map(|v| v.as_text().unwrap()).collect();
    for v in values {
        result.push(v.to_string());
    }
}
let expected: Vec<String> = vec!["中国".to_string()];
assert_eq!(expected, result);

let query = query_parser.parse_query("国")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
let mut result: Vec<String> = Vec::new();
for (_, doc_address) in top_docs {
    let retrieved_doc = searcher.doc(doc_address)?;
    let values: Vec<&str> = retrieved_doc.get_all(field).map(|v| v.as_text().unwrap()).collect();
    for v in values {
        result.push(v.to_string());
    }
}
let expected: Vec<String> = vec!["中国".to_string()];
assert_eq!(expected, result);
let query = query_parser.parse_query("document")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
let mut result: Vec<String> = Vec::new();
for (_, doc_address) in top_docs {
    let retrieved_doc = searcher.doc(doc_address)?;
    let values: Vec<&str> = retrieved_doc.get_all(field).map(|v| v.as_text().unwrap()).collect();
    for v in values {
        result.push(v.to_string());
    }
}
let expected: Vec<String> = vec!["Another Document".to_string()];
assert_eq!(expected, result);
Ok(())

} ```

License

Licensed under either of

• Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
• MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)

at your option.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.