parent
0441c6bef6
commit
9a777aaa80
@ -0,0 +1,47 @@
|
||||
// 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 truncate_token_filter
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"unicode/utf8"
|
||||
|
||||
"github.com/couchbaselabs/bleve/analysis"
|
||||
)
|
||||
|
||||
type TruncateTokenFilter struct {
|
||||
length int
|
||||
}
|
||||
|
||||
func NewTruncateTokenFilter(length int) *TruncateTokenFilter {
|
||||
return &TruncateTokenFilter{
|
||||
length: length,
|
||||
}
|
||||
}
|
||||
|
||||
func (s *TruncateTokenFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
|
||||
rv := make(analysis.TokenStream, 0)
|
||||
|
||||
for _, token := range input {
|
||||
wordLen := utf8.RuneCount(token.Term)
|
||||
if wordLen > s.length {
|
||||
runes := bytes.Runes(token.Term)[0:s.length]
|
||||
newterm := make([]byte, 0, s.length*4)
|
||||
for _, r := range runes {
|
||||
runeBytes := make([]byte, utf8.RuneLen(r))
|
||||
utf8.EncodeRune(runeBytes, r)
|
||||
newterm = append(newterm, runeBytes...)
|
||||
}
|
||||
token.Term = newterm
|
||||
}
|
||||
rv = append(rv, token)
|
||||
}
|
||||
|
||||
return rv
|
||||
}
|
@ -0,0 +1,73 @@
|
||||
// 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 truncate_token_filter
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"testing"
|
||||
|
||||
"github.com/couchbaselabs/bleve/analysis"
|
||||
)
|
||||
|
||||
func TestTruncateTokenFilter(t *testing.T) {
|
||||
|
||||
tests := []struct {
|
||||
length int
|
||||
input analysis.TokenStream
|
||||
output analysis.TokenStream
|
||||
}{
|
||||
{
|
||||
length: 5,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcdefgh"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("abcde"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
length: 3,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("こんにちは世界"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("こんに"),
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
length: 10,
|
||||
input: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("แยกคำภาษาไทยก็ทำได้นะจ้ะ"),
|
||||
},
|
||||
},
|
||||
output: analysis.TokenStream{
|
||||
&analysis.Token{
|
||||
Term: []byte("แยกคำภาษาไ"),
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
for _, test := range tests {
|
||||
truncateTokenFilter := NewTruncateTokenFilter(test.length)
|
||||
actual := truncateTokenFilter.Filter(test.input)
|
||||
if !reflect.DeepEqual(actual, test.output) {
|
||||
t.Errorf("expected %s, got %s", test.output[0].Term, actual[0].Term)
|
||||
}
|
||||
}
|
||||
}
|
@ -30,6 +30,7 @@ import (
|
||||
"github.com/couchbaselabs/bleve/analysis/token_filters/lower_case_filter"
|
||||
"github.com/couchbaselabs/bleve/analysis/token_filters/stemmer_filter"
|
||||
"github.com/couchbaselabs/bleve/analysis/token_filters/stop_words_filter"
|
||||
"github.com/couchbaselabs/bleve/analysis/token_filters/truncate_token_filter"
|
||||
"github.com/couchbaselabs/bleve/analysis/token_filters/unicode_normalize"
|
||||
|
||||
"github.com/couchbaselabs/bleve/search"
|
||||
@ -181,6 +182,7 @@ func init() {
|
||||
Config.Analysis.TokenFilters["long"] = length_filter.NewLengthFilter(-1, 255)
|
||||
Config.Analysis.TokenFilters["to_lower"] = lower_case_filter.NewLowerCaseFilter()
|
||||
Config.Analysis.TokenFilters["apostrophe"] = apostrophe_filter.NewApostropheFilter()
|
||||
Config.Analysis.TokenFilters["truncate_token"] = truncate_token_filter.NewTruncateTokenFilter(25)
|
||||
|
||||
// register stemmer filters
|
||||
Config.Analysis.TokenFilters["stemmer_da"] = stemmer_filter.MustNewStemmerFilter("danish")
|
||||
|
Loading…
Reference in New Issue
Block a user