0eba2a3f0c
previously we parsed/returned large sections of the documents back index row in order to compute facet information. this would require parsing the protobuf of the entire back index row. unfortunately this creates considerable garbage. this new version introduces a visitor/callback approach to working with data inside the back index row. the benefit of this approach is that we can let the higher-level code see values, prior to any copies of data being made or intermediate garbage being created. implementations of the callback must copy any value which they would like to retain beyond the callback. NOTE: this approach is duplicates code from the automatically generated protobuf code NOTE: this approach assumes that the "field" field be serialized before the "terms" field. This is guaranteed by our currently generated protobuf encoder, and is recommended by the protobuf spec. But, decoders SHOULD support them occuring in any order, which we do not.
97 lines
2.0 KiB
Go
97 lines
2.0 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 facet
|
|
|
|
import (
|
|
"sort"
|
|
|
|
"github.com/blevesearch/bleve/search"
|
|
)
|
|
|
|
type TermsFacetBuilder struct {
|
|
size int
|
|
field string
|
|
termsCount map[string]int
|
|
total int
|
|
missing int
|
|
sawValue bool
|
|
}
|
|
|
|
func NewTermsFacetBuilder(field string, size int) *TermsFacetBuilder {
|
|
return &TermsFacetBuilder{
|
|
size: size,
|
|
field: field,
|
|
termsCount: make(map[string]int),
|
|
}
|
|
}
|
|
|
|
func (fb *TermsFacetBuilder) Field() string {
|
|
return fb.field
|
|
}
|
|
|
|
func (fb *TermsFacetBuilder) UpdateVisitor(field string, term []byte) {
|
|
if field == fb.field {
|
|
fb.sawValue = true
|
|
fb.termsCount[string(term)] = fb.termsCount[string(term)] + 1
|
|
fb.total++
|
|
}
|
|
}
|
|
|
|
func (fb *TermsFacetBuilder) StartDoc() {
|
|
fb.sawValue = false
|
|
}
|
|
|
|
func (fb *TermsFacetBuilder) EndDoc() {
|
|
if !fb.sawValue {
|
|
fb.missing++
|
|
}
|
|
}
|
|
|
|
func (fb *TermsFacetBuilder) Result() *search.FacetResult {
|
|
rv := search.FacetResult{
|
|
Field: fb.field,
|
|
Total: fb.total,
|
|
Missing: fb.missing,
|
|
}
|
|
|
|
rv.Terms = make([]*search.TermFacet, 0, len(fb.termsCount))
|
|
|
|
for term, count := range fb.termsCount {
|
|
tf := &search.TermFacet{
|
|
Term: term,
|
|
Count: count,
|
|
}
|
|
|
|
rv.Terms = append(rv.Terms, tf)
|
|
}
|
|
|
|
sort.Sort(rv.Terms)
|
|
|
|
// we now have the list of the top N facets
|
|
trimTopN := fb.size
|
|
if trimTopN > len(rv.Terms) {
|
|
trimTopN = len(rv.Terms)
|
|
}
|
|
rv.Terms = rv.Terms[:trimTopN]
|
|
|
|
notOther := 0
|
|
for _, tf := range rv.Terms {
|
|
notOther += tf.Count
|
|
}
|
|
rv.Other = fb.total - notOther
|
|
|
|
return &rv
|
|
}
|