Adding upstream version 2.5.1.
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
parent
c71cb8b61d
commit
982828099e
GPG key ID:
FBB4F0E80A80222F
783 changed files with 150650 additions and 0 deletions
118
analysis/token/edgengram/edgengram.go
Normal file
118
analysis/token/edgengram/edgengram.go
Normal file
|
|
@ -0,0 +1,118 @@
|
|||
// 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 edgengram
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"unicode/utf8"
|
||||
|
||||
"github.com/blevesearch/bleve/v2/analysis"
|
||||
"github.com/blevesearch/bleve/v2/registry"
|
||||
)
|
||||
|
||||
const Name = "edge_ngram"
|
||||
|
||||
type Side bool
|
||||
|
||||
const BACK Side = true
|
||||
const FRONT Side = false
|
||||
|
||||
type EdgeNgramFilter struct {
|
||||
back Side
|
||||
minLength int
|
||||
maxLength int
|
||||
}
|
||||
|
||||
func NewEdgeNgramFilter(side Side, minLength, maxLength int) *EdgeNgramFilter {
|
||||
return &EdgeNgramFilter{
|
||||
back: side,
|
||||
minLength: minLength,
|
||||
maxLength: maxLength,
|
||||
}
|
||||
}
|
||||
|
||||
func (s *EdgeNgramFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
|
||||
rv := make(analysis.TokenStream, 0, len(input))
|
||||
|
||||
for _, token := range input {
|
||||
runeCount := utf8.RuneCount(token.Term)
|
||||
runes := bytes.Runes(token.Term)
|
||||
if s.back {
|
||||
i := runeCount
|
||||
// index of the starting rune for this token
|
||||
for ngramSize := s.minLength; ngramSize <= s.maxLength; ngramSize++ {
|
||||
// build an ngram of this size starting at i
|
||||
if i-ngramSize >= 0 {
|
||||
ngramTerm := analysis.BuildTermFromRunes(runes[i-ngramSize : i])
|
||||
token := analysis.Token{
|
||||
Position: token.Position,
|
||||
Start: token.Start,
|
||||
End: token.End,
|
||||
Type: token.Type,
|
||||
Term: ngramTerm,
|
||||
}
|
||||
rv = append(rv, &token)
|
||||
}
|
||||
}
|
||||
} else {
|
||||
i := 0
|
||||
// index of the starting rune for this token
|
||||
for ngramSize := s.minLength; ngramSize <= s.maxLength; ngramSize++ {
|
||||
// build an ngram of this size starting at i
|
||||
if i+ngramSize <= runeCount {
|
||||
ngramTerm := analysis.BuildTermFromRunes(runes[i : i+ngramSize])
|
||||
token := analysis.Token{
|
||||
Position: token.Position,
|
||||
Start: token.Start,
|
||||
End: token.End,
|
||||
Type: token.Type,
|
||||
Term: ngramTerm,
|
||||
}
|
||||
rv = append(rv, &token)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return rv
|
||||
}
|
||||
|
||||
func EdgeNgramFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
|
||||
side := FRONT
|
||||
back, ok := config["back"].(bool)
|
||||
if ok && back {
|
||||
side = BACK
|
||||
}
|
||||
minVal, ok := config["min"].(float64)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("must specify min")
|
||||
}
|
||||
min := int(minVal)
|
||||
maxVal, ok := config["max"].(float64)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("must specify max")
|
||||
}
|
||||
max := int(maxVal)
|
||||
|
||||
return NewEdgeNgramFilter(side, min, max), nil
|
||||
}
|
||||
|
||||
func init() {
|
||||
err := registry.RegisterTokenFilter(Name, EdgeNgramFilterConstructor)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
}
|
||||
189
analysis/token/edgengram/edgengram_test.go
Normal file
189
analysis/token/edgengram/edgengram_test.go
Normal file
|
|
@ -0,0 +1,189 @@
|
|||
// 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 edgengram
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"testing"
|
||||
|
||||
"github.com/blevesearch/bleve/v2/analysis"
|
||||
)
|
||||
|
||||
func TestEdgeNgramFilter(t *testing.T) {
|
||||
|
||||
tests := []struct {
|
||||
side Side
|
||||
min int
|
||||
max int
|
||||
input analysis.TokenStream
|
||||
output analysis.TokenStream
|
||||
}{
|
||||
{
|
||||
side: FRONT,
|
||||
min: 1,
|
||||
max: 1,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("a"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: BACK,
|
||||
min: 1,
|
||||
max: 1,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("e"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: FRONT,
|
||||
min: 1,
|
||||
max: 3,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("a"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("ab"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("abc"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: BACK,
|
||||
min: 1,
|
||||
max: 3,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("e"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("de"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("cde"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: FRONT,
|
||||
min: 1,
|
||||
max: 3,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("vwxyz"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("a"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("ab"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("abc"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("v"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("vw"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("vwx"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: BACK,
|
||||
min: 3,
|
||||
max: 5,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("Beryl"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("ryl"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("eryl"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("Beryl"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
side: FRONT,
|
||||
min: 3,
|
||||
max: 5,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("Beryl"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("Ber"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("Bery"),
|
||||
},
|
||||
&analysis.Token{
|
||||
Term: []byte("Beryl"),
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
for _, test := range tests {
|
||||
edgeNgramFilter := NewEdgeNgramFilter(test.side, test.min, test.max)
|
||||
actual := edgeNgramFilter.Filter(test.input)
|
||||
if !reflect.DeepEqual(actual, test.output) {
|
||||
t.Errorf("expected %s, got %s", test.output, actual)
|
||||
}
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue