mirror of
https://github.com/grafana/grafana.git
synced 2025-07-29 17:12:29 +08:00
827da46c51
* WIP adding custom analyzer so we can do substring search efficiently * Adding unit tests for title search * formatting * adds more title search unit tests * organize helpers * fixes issue caused by having two title mappings * Removes camelcase token filter since it prevents you from searching for a substring of chars and numbers. Adds regression test. * adds back mapping for title_phrase * use simple analyzer for input query string so it doesn't filter out english stop words * ran bleve tests, table snapshots updated * ignore linter for "unused" test functions. They are very helpful for troubleshooting search. Keeping them. * only log total hits and query cost if result not nil * fixes failing test - one more field because there are two title mappings now * fix test * fixes test - only take first item when its the title * Adds separate internal field for title ngram mapping. When searching with a query, results are sorted by score desc. When searching without a query, results are sorted by title desc. Adjusts ngram max to be 10. Text queries are a disjunction of an exact match, phrase match, and a match. Boosted to have priority in that order. Adds more unit tests for searching. * linter * fix test * ran tests - generated new test dash json * sort by title phrase instead of title * fix test - not relying on /apis/dashboard/search to apply title sorting anymore
49 lines
1.5 KiB
Go
49 lines
1.5 KiB
Go
package search
|
|
|
|
import (
|
|
"github.com/blevesearch/bleve/v2/analysis/analyzer/custom"
|
|
"github.com/blevesearch/bleve/v2/analysis/token/edgengram"
|
|
"github.com/blevesearch/bleve/v2/analysis/token/lowercase"
|
|
"github.com/blevesearch/bleve/v2/analysis/token/unique"
|
|
"github.com/blevesearch/bleve/v2/analysis/tokenizer/whitespace"
|
|
"github.com/blevesearch/bleve/v2/mapping"
|
|
)
|
|
|
|
const TITLE_ANALYZER = "title_analyzer"
|
|
|
|
func RegisterCustomAnalyzers(mapper *mapping.IndexMappingImpl) error {
|
|
return registerTitleAnalyzer(mapper)
|
|
}
|
|
|
|
// The registerTitleAnalyzer function defines a custom analyzer for the title field.
|
|
// The edgeNgramTokenFilter will create n-grams anchored to the front of each token.
|
|
// For example, the token "hello" will be tokenized into "hel", "hell", "hello".
|
|
func registerTitleAnalyzer(mapper *mapping.IndexMappingImpl) error {
|
|
// Define an N-Gram tokenizer (for substring search)
|
|
edgeNgramTokenFilter := map[string]interface{}{
|
|
"type": edgengram.Name,
|
|
"min": 3.0,
|
|
"max": 10.0,
|
|
"back": edgengram.FRONT,
|
|
}
|
|
err := mapper.AddCustomTokenFilter("edge_ngram_filter", edgeNgramTokenFilter)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
//Create a custom analyzer using the N-Gram tokenizer
|
|
ngramAnalyzer := map[string]interface{}{
|
|
"type": custom.Name,
|
|
"tokenizer": whitespace.Name,
|
|
"token_filters": []string{"edge_ngram_filter", lowercase.Name, unique.Name},
|
|
//"char_filters": //TODO IF NEEDED
|
|
}
|
|
|
|
err = mapper.AddCustomAnalyzer(TITLE_ANALYZER, ngramAnalyzer)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
return nil
|
|
}
|