mirror of
https://github.com/quickwit-oss/tantivy.git
synced 2025-12-22 18:19:58 +00:00
63c66005db
* Refactoring of the score tweaker into `SortKeyComputer`s to unlock two features. - Allow lazy evaluation of score. As soon as we identified that a doc won't reach the topK threshold, we can stop the evaluation. - Allow for a different segment level score, segment level score and their conversion. This PR breaks public API, but fixing code is straightforward. * Bumping tantivy version --------- Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com>
78 lines
2.7 KiB
Rust
78 lines
2.7 KiB
Rust
// # DateTime field example
|
|
//
|
|
// This example shows how the DateTime field can be used
|
|
|
|
use tantivy::collector::TopDocs;
|
|
use tantivy::query::QueryParser;
|
|
use tantivy::schema::{DateOptions, Document, Schema, Value, INDEXED, STORED, STRING};
|
|
use tantivy::{Index, IndexWriter, TantivyDocument};
|
|
|
|
fn main() -> tantivy::Result<()> {
|
|
// # Defining the schema
|
|
let mut schema_builder = Schema::builder();
|
|
let opts = DateOptions::from(INDEXED)
|
|
.set_stored()
|
|
.set_fast()
|
|
.set_precision(tantivy::schema::DateTimePrecision::Seconds);
|
|
// Add `occurred_at` date field type
|
|
let occurred_at = schema_builder.add_date_field("occurred_at", opts);
|
|
let event_type = schema_builder.add_text_field("event", STRING | STORED);
|
|
let schema = schema_builder.build();
|
|
|
|
// # Indexing documents
|
|
let index = Index::create_in_ram(schema.clone());
|
|
|
|
let mut index_writer: IndexWriter = index.writer(50_000_000)?;
|
|
// The dates are passed as string in the RFC3339 format
|
|
let doc = TantivyDocument::parse_json(
|
|
&schema,
|
|
r#"{
|
|
"occurred_at": "2022-06-22T12:53:50.53Z",
|
|
"event": "pull-request"
|
|
}"#,
|
|
)?;
|
|
index_writer.add_document(doc)?;
|
|
let doc = TantivyDocument::parse_json(
|
|
&schema,
|
|
r#"{
|
|
"occurred_at": "2022-06-22T13:00:00.22Z",
|
|
"event": "comment"
|
|
}"#,
|
|
)?;
|
|
index_writer.add_document(doc)?;
|
|
index_writer.commit()?;
|
|
|
|
let reader = index.reader()?;
|
|
let searcher = reader.searcher();
|
|
|
|
// # Search
|
|
let query_parser = QueryParser::for_index(&index, vec![event_type]);
|
|
{
|
|
// Simple exact search on the date
|
|
let query = query_parser.parse_query("occurred_at:\"2022-06-22T12:53:50.53Z\"")?;
|
|
let count_docs = searcher.search(&*query, &TopDocs::with_limit(5).order_by_score())?;
|
|
assert_eq!(count_docs.len(), 1);
|
|
}
|
|
{
|
|
// Range query on the date field
|
|
let query = query_parser
|
|
.parse_query(r#"occurred_at:[2022-06-22T12:58:00Z TO 2022-06-23T00:00:00Z}"#)?;
|
|
let count_docs = searcher.search(&*query, &TopDocs::with_limit(4).order_by_score())?;
|
|
assert_eq!(count_docs.len(), 1);
|
|
for (_score, doc_address) in count_docs {
|
|
let retrieved_doc = searcher.doc::<TantivyDocument>(doc_address)?;
|
|
assert!(retrieved_doc
|
|
.get_first(occurred_at)
|
|
.unwrap()
|
|
.as_value()
|
|
.as_datetime()
|
|
.is_some(),);
|
|
assert_eq!(
|
|
retrieved_doc.to_json(&schema),
|
|
r#"{"event":["comment"],"occurred_at":["2022-06-22T13:00:00.22Z"]}"#
|
|
);
|
|
}
|
|
}
|
|
Ok(())
|
|
}
|