0
0
bleve/analysis/language/cjk/cjk_width_test.go
Marty Schoch 043a3bfb7c change cjk analyzer to use unicode tokenizer
change cjk bigram analyzer to work with multi-rune terms
add cjk width filter replaces full unicode normailzation

these changes make the cjk analyzer behave more like elasticsearch
they also remove the depenency on the whitespace analyzer
which is now free to also behave more like lucene/es

fixes #33
2016-06-10 13:04:40 -04:00

89 lines
2.0 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// Copyright (c) 2016 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 cjk
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/analysis"
)
func TestCJKWidthFilter(t *testing.T) {
tests := []struct {
input analysis.TokenStream
output analysis.TokenStream
}{
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte(""),
},
&analysis.Token{
Term: []byte(""),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("Test"),
},
&analysis.Token{
Term: []byte("1234"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("カタカナ"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("カタカナ"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("ヴィッツ"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("ヴィッツ"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("パナソニック"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("パナソニック"),
},
},
},
}
for _, test := range tests {
cjkWidthFilter := NewCJKWidthFilter()
actual := cjkWidthFilter.Filter(test.input)
if !reflect.DeepEqual(actual, test.output) {
t.Errorf("expected %s, got %s", test.output, actual)
}
}
}