forgejo/golang-github-blevesearch-bleve
1
0
Fork 0
Code Issues Activity

Adding upstream version 2.5.1.

Browse source 
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-05-19 00:20:02 +02:00
parent c71cb8b61d
commit 982828099e
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
783 changed files with 150650 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

251
analysis/lang/hi/hindi_normalize_test.go Normal file
View file

@ -0,0 +1,251 @@
// 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 hi
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
)
func TestHindiNormalizeFilter(t *testing.T) {
tests := []struct {
input analysis.TokenStream
output analysis.TokenStream
}{
// basics
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अँगरेज़ी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अँगरेजी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अँग्रेज़ी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अँग्रेजी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेज़ी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंग्रेज़ी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंग्रेजी"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अंगरेजि"),
},
},
},
// test decompositions
// removing nukta dot
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("क़िताब"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("किताब"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("फ़र्ज़"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("फरज"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("क़र्ज़"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("करज"),
},
},
},
// some other composed nukta forms
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("ऱऴख़ग़ड़ढ़य़"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("रळखगडढय"),
},
},
},
// removal of format (ZWJ/ZWNJ)
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("शार्‍मा"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("शारमा"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("शार्‌मा"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("शारमा"),
},
},
},
// removal of chandra
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("ॅॆॉॊऍऎऑऒ\u0972"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("ेेोोएएओओअ"),
},
},
},
// vowel shortening
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("आईऊॠॡऐऔीूॄॣैौ"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("अइउऋऌएओिुृॢेो"),
},
},
},
// empty
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte(""),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte(""),
},
},
},
}
hindiNormalizeFilter := NewHindiNormalizeFilter()
for _, test := range tests {
actual := hindiNormalizeFilter.Filter(test.input)
if !reflect.DeepEqual(actual, test.output) {
t.Errorf("expected %#v, got %#v", test.output, actual)
t.Errorf("expected % x, got % x", test.output[0].Term, actual[0].Term)
}
}
}