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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
use std::fmt;
use super::term_weight::TermWeight;
use crate::query::bm25::Bm25Weight;
use crate::query::{EnableScoring, Explanation, Query, Weight};
use crate::schema::IndexRecordOption;
use crate::Term;
/// A Term query matches all of the documents
/// containing a specific term.
///
/// The score associated is defined as
/// `idf` * sqrt(`term_freq` / `field norm`)
/// in which :
/// * `idf` - inverse document frequency.
/// * `term_freq` - number of occurrences of the term in the field
/// * `field norm` - number of tokens in the field.
///
/// ```rust
/// use tantivy::collector::{Count, TopDocs};
/// use tantivy::query::TermQuery;
/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
/// use tantivy::{doc, Index, IndexWriter, Term};
/// # fn test() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer: IndexWriter = index.writer(15_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ))?;
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ))?;
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ))?;
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ))?;
/// index_writer.commit()?;
/// }
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
/// let query = TermQuery::new(
/// Term::from_field_text(title, "diary"),
/// IndexRecordOption::Basic,
/// );
/// let (top_docs, count) = searcher.search(&query, &(TopDocs::with_limit(2), Count))?;
/// assert_eq!(count, 2);
/// Ok(())
/// # }
/// # assert!(test().is_ok());
/// ```
#[derive(Clone)]
pub struct TermQuery {
term: Term,
index_record_option: IndexRecordOption,
}
impl fmt::Debug for TermQuery {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "TermQuery({:?})", self.term)
}
}
impl TermQuery {
/// Creates a new term query.
pub fn new(term: Term, segment_postings_options: IndexRecordOption) -> TermQuery {
TermQuery {
term,
index_record_option: segment_postings_options,
}
}
/// The `Term` this query is built out of.
pub fn term(&self) -> &Term {
&self.term
}
/// Returns a weight object.
///
/// While `.weight(...)` returns a boxed trait object,
/// this method return a specific implementation.
/// This is useful for optimization purpose.
pub fn specialized_weight(
&self,
enable_scoring: EnableScoring<'_>,
) -> crate::Result<TermWeight> {
let schema = enable_scoring.schema();
let field_entry = schema.get_field_entry(self.term.field());
if !field_entry.is_indexed() {
let error_msg = format!("Field {:?} is not indexed.", field_entry.name());
return Err(crate::TantivyError::SchemaError(error_msg));
}
let bm25_weight = match enable_scoring {
EnableScoring::Enabled {
statistics_provider,
..
} => Bm25Weight::for_terms(statistics_provider, &[self.term.clone()])?,
EnableScoring::Disabled { .. } => {
Bm25Weight::new(Explanation::new("<no score>", 1.0f32), 1.0f32)
}
};
let scoring_enabled = enable_scoring.is_scoring_enabled();
let index_record_option = if scoring_enabled {
self.index_record_option
} else {
IndexRecordOption::Basic
};
Ok(TermWeight::new(
self.term.clone(),
index_record_option,
bm25_weight,
scoring_enabled,
))
}
}
impl Query for TermQuery {
fn weight(&self, enable_scoring: EnableScoring<'_>) -> crate::Result<Box<dyn Weight>> {
Ok(Box::new(self.specialized_weight(enable_scoring)?))
}
fn query_terms<'a>(&'a self, visitor: &mut dyn FnMut(&'a Term, bool)) {
visitor(&self.term, false);
}
}
#[cfg(test)]
mod tests {
use std::net::{IpAddr, Ipv6Addr};
use std::str::FromStr;
use columnar::MonotonicallyMappableToU128;
use crate::collector::{Count, TopDocs};
use crate::query::{Query, QueryParser, TermQuery};
use crate::schema::{IndexRecordOption, IntoIpv6Addr, Schema, INDEXED, STORED};
use crate::{Index, IndexWriter, Term};
#[test]
fn search_ip_test() {
let mut schema_builder = Schema::builder();
let ip_field = schema_builder.add_ip_addr_field("ip", INDEXED | STORED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let ip_addr_1 = IpAddr::from_str("127.0.0.1").unwrap().into_ipv6_addr();
let ip_addr_2 = Ipv6Addr::from_u128(10);
{
let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
index_writer
.add_document(doc!(
ip_field => ip_addr_1
))
.unwrap();
index_writer
.add_document(doc!(
ip_field => ip_addr_2
))
.unwrap();
index_writer.commit().unwrap();
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let assert_single_hit = |query| {
let (_top_docs, count) = searcher
.search(&query, &(TopDocs::with_limit(2), Count))
.unwrap();
assert_eq!(count, 1);
};
let query_from_text = |text: String| {
QueryParser::for_index(&index, vec![ip_field])
.parse_query(&text)
.unwrap()
};
let query_from_ip = |ip_addr| -> Box<dyn Query> {
Box::new(TermQuery::new(
Term::from_field_ip_addr(ip_field, ip_addr),
IndexRecordOption::Basic,
))
};
assert_single_hit(query_from_ip(ip_addr_1));
assert_single_hit(query_from_ip(ip_addr_2));
assert_single_hit(query_from_text("127.0.0.1".to_string()));
assert_single_hit(query_from_text("\"127.0.0.1\"".to_string()));
assert_single_hit(query_from_text(format!("\"{ip_addr_1}\"")));
assert_single_hit(query_from_text(format!("\"{ip_addr_2}\"")));
}
}