mirror of
https://github.com/quickwit-oss/tantivy.git
synced 2026-01-03 15:52:55 +00:00
POC: Tantivy documents as a trait (#2071)
* fix windows build (#1) * Fix windows build * Add doc traits * Add field value iter * Add value and serialization * Adjust order * Fix bug * Correct type * Fix generic bugs * Reformat code * Add generic to index writer which I forgot about * Fix missing generics on single segment writer * Add missing type export * Add default methods for convenience * Cleanup * Fix more-like-this query to use standard types * Update API and fix tests * Add doc traits * Add field value iter * Add value and serialization * Adjust order * Fix bug * Correct type * Rebase main and fix conflicts * Reformat code * Merge upstream * Fix missing generics on single segment writer * Add missing type export * Add default methods for convenience * Cleanup * Fix more-like-this query to use standard types * Update API and fix tests * Add tokenizer improvements from previous commits * Add tokenizer improvements from previous commits * Reformat * Fix unit tests * Fix unit tests * Use enum in changes * Stage changes * Add new deserializer logic * Add serializer integration * Add document deserializer * Implement new (de)serialization api for existing types * Fix bugs and type errors * Add helper implementations * Fix errors * Reformat code * Add unit tests and some code organisation for serialization * Add unit tests to deserializer * Add some small docs * Add support for deserializing serde values * Reformat * Fix typo * Fix typo * Change repr of facet * Remove unused trait methods * Add child value type * Resolve comments * Fix build * Fix more build errors * Fix more build errors * Fix the tests I missed * Fix examples * fix numerical order, serialize PreTok Str * fix coverage * rename Document to TantivyDocument, rename DocumentAccess to Document add Binary prefix to binary de/serialization * fix coverage --------- Co-authored-by: Pascal Seitz <pascal.seitz@gmail.com>
This commit is contained in:
@@ -12,7 +12,7 @@ use tantivy::aggregation::agg_result::AggregationResults;
|
||||
use tantivy::aggregation::AggregationCollector;
|
||||
use tantivy::query::AllQuery;
|
||||
use tantivy::schema::{self, IndexRecordOption, Schema, TextFieldIndexing, FAST};
|
||||
use tantivy::Index;
|
||||
use tantivy::{Index, IndexWriter, TantivyDocument};
|
||||
|
||||
fn main() -> tantivy::Result<()> {
|
||||
// # Create Schema
|
||||
@@ -132,10 +132,10 @@ fn main() -> tantivy::Result<()> {
|
||||
|
||||
let stream = Deserializer::from_str(data).into_iter::<Value>();
|
||||
|
||||
let mut index_writer = index.writer(50_000_000)?;
|
||||
let mut index_writer: IndexWriter = index.writer(50_000_000)?;
|
||||
let mut num_indexed = 0;
|
||||
for value in stream {
|
||||
let doc = schema.parse_document(&serde_json::to_string(&value.unwrap())?)?;
|
||||
let doc = TantivyDocument::parse_json(&schema, &serde_json::to_string(&value.unwrap())?)?;
|
||||
index_writer.add_document(doc)?;
|
||||
num_indexed += 1;
|
||||
if num_indexed > 4 {
|
||||
|
||||
Reference in New Issue
Block a user