1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
//! This library aims to bring some [Lucene](https://lucene.apache.org/core/) components into [Tantivy](https://github.com/quickwit-oss/tantivy)
//!
//! Currently it contains
//! * ICU related components :
//! * [ICUTokenizer](crate::icu::ICUTokenizer) that is an equivalent
//! of [Lucene's ICUTokenizer](https://lucene.apache.org/core/9_0_0/analysis/icu/org/apache/lucene/analysis/icu/segmentation/ICUTokenizer.html)
//! without support of emojis.
//! * [ICUNormalizer2TokenFilter](crate::icu::ICUNormalizer2TokenFilter) that normalize text. It is an equivalent of
//! [Lucene's ICUNormalizer2Filter](https://lucene.apache.org/core/9_0_0/analysis/icu/org/apache/lucene/analysis/icu/ICUNormalizer2Filter.html).
//! * [ICUTransformTokenFilter](crate::icu::ICUTransformTokenFilter) which is an equivalent of
//! [Lucene's ICUTransformFilter](https://lucene.apache.org/core/9_0_0/analysis/icu/org/apache/lucene/analysis/icu/ICUNormalizer2Filter.html)
//! * Commons components :
//! * [PathTokenizer](crate::commons::PathTokenizer) which tokenize a hierarchical path (equivalent of
//! [PathHierarchyTokenizer](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/path/PathHierarchyTokenizer.html) and
//! [ReversePathHierarchyTokenizer](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/path/ReversePathHierarchyTokenizer.html))
//! * [LengthTokenFilter](crate::commons::LengthTokenFilter) that remove tokens which doesn't are above or below certain limits (see
//! [LengthFilter](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/miscellaneous/LengthFilter.html))
//! * [LimitTokenCountFilter](crate::commons::LimitTokenCountFilter) that limits the number of token, see
//! [LimitTokenCountFilter](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/miscellaneous/LimitTokenCountFilter.html)
//! * [ReverseTokenFilter](crate::commons::ReverseTokenFilter) that reverse a string see
//! [ReverseStringFilter](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/reverse/ReverseStringFilter.html)
//! * [ElisionTokenFilter](crate::commons::ElisionTokenFilter) that remove elisions, see
//! [ElisionFilter](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/util/ElisionFilter.html)
//! * [EdgeNgramTokenFilter](crate::commons::EdgeNgramTokenFilter) that generate ngram prefixes of tokens, see
//! [EdgeNGramTokenFilter](https://lucene.apache.org/core/9_1_0/analysis/common/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.html)
//! * Phonetic :
//! * [PhoneticTokenFilter](crate::phonetic::PhoneticTokenFilter) a token filter to apply phonetic algorithm on tokens.
//!
//! # Example
//!
//! Here is a full example of how tokenize using [icu::ICUTokenizer] and do transliteration and lowercase each tokens using [icu::ICUTransformTokenFilter]:
//! ```rust
//! # fn main() -> Result<(), Box<dyn std::error::Error>> {
//! use tantivy::collector::TopDocs;
//! use tantivy::query::QueryParser;
//! use tantivy::schema::{
//! IndexRecordOption, SchemaBuilder, TextFieldIndexing, TextOptions, Value,
//! };
//! use tantivy::tokenizer::TextAnalyzer;
//! use tantivy::{doc, Index, ReloadPolicy, TantivyDocument};
//! use tantivy_analysis_contrib::icu::{Direction, ICUTokenizer, ICUTransformTokenFilter};
//!
//! const ANALYSIS_NAME: &str = "test";
//!
//! let options = TextOptions::default()
//! .set_indexing_options(
//! TextFieldIndexing::default()
//! .set_tokenizer(ANALYSIS_NAME)
//! .set_index_option(IndexRecordOption::WithFreqsAndPositions),
//! )
//! .set_stored();
//! let mut schema = SchemaBuilder::new();
//! schema.add_text_field("field", options);
//! let schema = schema.build();
//!
//! let transform = ICUTransformTokenFilter::new(
//! "Any-Latin; NFD; [:Nonspacing Mark:] Remove; Lower; NFC".to_string(),
//! None,
//! Direction::Forward,
//! )?;
//! let icu_analyzer = TextAnalyzer::builder(ICUTokenizer)
//! .filter(transform)
//! .build();
//!
//! 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(15_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::Manual)
//! .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::<TantivyDocument>(doc_address)?;
//! result = retrieved_doc
//! .get_all(field)
//! .map(|v| v.as_str().unwrap().to_string())
//! .collect();
//! }
//! 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::<TantivyDocument>(doc_address)?;
//! result = retrieved_doc
//! .get_all(field)
//! .map(|v| v.as_str().unwrap().to_string())
//! .collect();
//! }
//! 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::<TantivyDocument>(doc_address)?;
//! result = retrieved_doc
//! .get_all(field)
//! .map(|v| v.as_str().unwrap().to_string())
//! .collect();
//! }
//! let expected: Vec<String> = vec!["Another Document".to_string()];
//! assert_eq!(expected, result);
//!
//! # Ok(())
//! }
//! ```
//!
//! ## Feature flags
#![doc = document_features::document_features!()]
#![cfg_attr(test, deny(warnings))]
#![warn(
missing_copy_implementations,
missing_debug_implementations,
missing_docs,
trivial_numeric_casts,
unsafe_code,
unused_extern_crates,
unused_import_braces,
unused_qualifications
)]
#![cfg_attr(docsrs, feature(doc_auto_cfg))]
#[cfg(feature = "commons")]
#[macro_use]
extern crate derive_builder;
#[cfg(feature = "commons")]
pub mod commons;
#[cfg(feature = "icu")]
pub mod icu;
#[cfg(feature = "phonetic")]
pub mod phonetic;