a265218f76
Boostable, Fieldable, Validatable broken out into separate interfaces. This allows them to be discoverable when needed, but ignorable otherwise. The top-level bleve package only every cares about Validatable and even that is optional. Also, this change goes further to make the structure names more reasonable, for cases where you're directly interacting with the structures.
104 lines
3.0 KiB
Go
104 lines
3.0 KiB
Go
// Copyright (c) 2014 Couchbase, Inc.
|
|
// Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file
|
|
// except in compliance with the License. You may obtain a copy of the License at
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
// Unless required by applicable law or agreed to in writing, software distributed under the
|
|
// License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
|
|
// either express or implied. See the License for the specific language governing permissions
|
|
// and limitations under the License.
|
|
|
|
package query
|
|
|
|
import (
|
|
"fmt"
|
|
|
|
"github.com/blevesearch/bleve/analysis"
|
|
"github.com/blevesearch/bleve/index"
|
|
"github.com/blevesearch/bleve/mapping"
|
|
"github.com/blevesearch/bleve/search"
|
|
)
|
|
|
|
type MatchPhraseQuery struct {
|
|
MatchPhrase string `json:"match_phrase"`
|
|
Field string `json:"field,omitempty"`
|
|
Analyzer string `json:"analyzer,omitempty"`
|
|
Boost *Boost `json:"boost,omitempty"`
|
|
}
|
|
|
|
// NewMatchPhraseQuery creates a new Query object
|
|
// for matching phrases in the index.
|
|
// An Analyzer is chosen based on the field.
|
|
// Input text is analyzed using this analyzer.
|
|
// Token terms resulting from this analysis are
|
|
// used to build a search phrase. Result documents
|
|
// must match this phrase. Queried field must have been indexed with
|
|
// IncludeTermVectors set to true.
|
|
func NewMatchPhraseQuery(matchPhrase string) *MatchPhraseQuery {
|
|
return &MatchPhraseQuery{
|
|
MatchPhrase: matchPhrase,
|
|
}
|
|
}
|
|
|
|
func (q *MatchPhraseQuery) SetBoost(b float64) {
|
|
boost := Boost(b)
|
|
q.Boost = &boost
|
|
}
|
|
|
|
func (q *MatchPhraseQuery) SetField(f string) {
|
|
q.Field = f
|
|
}
|
|
|
|
func (q *MatchPhraseQuery) Searcher(i index.IndexReader, m mapping.IndexMapping, explain bool) (search.Searcher, error) {
|
|
field := q.Field
|
|
if q.Field == "" {
|
|
field = m.DefaultSearchField()
|
|
}
|
|
|
|
analyzerName := ""
|
|
if q.Analyzer != "" {
|
|
analyzerName = q.Analyzer
|
|
} else {
|
|
analyzerName = m.AnalyzerNameForPath(field)
|
|
}
|
|
analyzer := m.AnalyzerNamed(analyzerName)
|
|
if analyzer == nil {
|
|
return nil, fmt.Errorf("no analyzer named '%s' registered", q.Analyzer)
|
|
}
|
|
|
|
tokens := analyzer.Analyze([]byte(q.MatchPhrase))
|
|
if len(tokens) > 0 {
|
|
phrase := tokenStreamToPhrase(tokens)
|
|
phraseQuery := NewPhraseQuery(phrase, field)
|
|
phraseQuery.SetBoost(q.Boost.Value())
|
|
return phraseQuery.Searcher(i, m, explain)
|
|
}
|
|
noneQuery := NewMatchNoneQuery()
|
|
return noneQuery.Searcher(i, m, explain)
|
|
}
|
|
|
|
func tokenStreamToPhrase(tokens analysis.TokenStream) []string {
|
|
firstPosition := int(^uint(0) >> 1)
|
|
lastPosition := 0
|
|
for _, token := range tokens {
|
|
if token.Position < firstPosition {
|
|
firstPosition = token.Position
|
|
}
|
|
if token.Position > lastPosition {
|
|
lastPosition = token.Position
|
|
}
|
|
}
|
|
phraseLen := lastPosition - firstPosition + 1
|
|
if phraseLen > 0 {
|
|
rv := make([]string, phraseLen)
|
|
for i := 0; i < phraseLen; i++ {
|
|
rv[i] = ""
|
|
}
|
|
for _, token := range tokens {
|
|
pos := token.Position - firstPosition
|
|
rv[pos] = string(token.Term)
|
|
}
|
|
return rv
|
|
}
|
|
return nil
|
|
}
|