rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-05-20 18:20:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove Index::tokenizer_for_field, fix BlockSegmentPostings doc comment

Browse Source 
tokenizer_for_field is a duplicate of SearcherContext::tokenizer_for_field.
This commit is contained in:
Pascal Seitz
2026-04-02 15:30:56 +08:00
parent 13567341c5
commit 548eb6ebc7
3 changed files with 3 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/core/tests.rs
View File

@@ -11,20 +11,6 @@ use crate::{
ReloadPolicy, Searcher, SearcherContext, TantivyDocument, Term,
};
#[test]
fn test_indexer_for_field() {
let mut schema_builder = Schema::builder();
let num_likes_field = schema_builder.add_u64_field("num_likes", INDEXED);
let body_field = schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
assert!(index.tokenizer_for_field(body_field).is_ok());
assert_eq!(
format!("{:?}", index.tokenizer_for_field(num_likes_field).err()),
"Some(SchemaError(\"\\\"num_likes\\\" is not a text field.\"))"
);
}
#[test]
fn test_set_tokenizer_manager() {
let mut schema_builder = Schema::builder();

34
src/index/index.rs
View File

@@ -23,8 +23,8 @@ use crate::indexer::segment_updater::save_metas;
use crate::indexer::{IndexWriter, SingleSegmentIndexWriter};
use crate::reader::{IndexReader, IndexReaderBuilder};
use crate::schema::document::Document;
use crate::schema::{Field, FieldType, Schema};
use crate::tokenizer::{TextAnalyzer, TokenizerManager};
use crate::schema::Schema;
use crate::tokenizer::TokenizerManager;
fn load_metas(
directory: &dyn Directory,
@@ -417,36 +417,6 @@ impl Index {
&self.fast_field_tokenizers
}
/// Get the tokenizer associated with a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> crate::Result<TextAnalyzer> {
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let tokenizer_manager: &TokenizerManager = self.tokenizers();
let indexing_options_opt = match field_type {
FieldType::JsonObject(options) => options.get_text_indexing_options(),
FieldType::Str(options) => options.get_indexing_options(),
_ => {
return Err(TantivyError::SchemaError(format!(
"{:?} is not a text field.",
field_entry.name()
)))
}
};
let indexing_options = indexing_options_opt.ok_or_else(|| {
TantivyError::InvalidArgument(format!(
"No indexing options set for field {field_entry:?}"
))
})?;
tokenizer_manager
.get(indexing_options.tokenizer())
.ok_or_else(|| {
TantivyError::InvalidArgument(format!(
"No Tokenizer found for field {field_entry:?}"
))
})
}
/// Create a default [`IndexReader`] for the given index.
///
/// See [`Index.reader_builder()`].

2
src/postings/block_segment_postings.rs
View File

@@ -79,7 +79,7 @@ fn split_into_skips_and_postings(
}
impl BlockSegmentPostings {
/// Opens a `StandardPostingsReader`.
/// Opens a `BlockSegmentPostings`.
/// `doc_freq` is the number of documents in the posting list.
/// `record_option` represents the amount of data available according to the schema.
/// `requested_option` is the amount of data requested by the user.