1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
|
// Copyright 2024 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package path
import (
"fmt"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/analysis/tokenizer/unicode"
"github.com/stretchr/testify/assert"
)
type Scenario struct {
Input string
Tokens []string
}
func TestTokenFilter(t *testing.T) {
scenarios := []struct {
Input string
Terms []string
}{
{
Input: "Dockerfile",
Terms: []string{"Dockerfile"},
},
{
Input: "Dockerfile.rootless",
Terms: []string{"Dockerfile.rootless"},
},
{
Input: "a/b/c/Dockerfile.rootless",
Terms: []string{"a", "a/b", "a/b/c", "a/b/c/Dockerfile.rootless", "Dockerfile.rootless", "Dockerfile.rootless/c", "Dockerfile.rootless/c/b", "Dockerfile.rootless/c/b/a"},
},
{
Input: "",
Terms: []string{},
},
}
for _, scenario := range scenarios {
t.Run(fmt.Sprintf("ensure terms of '%s'", scenario.Input), func(t *testing.T) {
terms := extractTerms(scenario.Input)
assert.Len(t, terms, len(scenario.Terms))
for _, term := range terms {
assert.Contains(t, scenario.Terms, term)
}
})
}
}
func extractTerms(input string) []string {
tokens := tokenize(input)
filteredTokens := filter(tokens)
terms := make([]string, 0, len(filteredTokens))
for _, token := range filteredTokens {
terms = append(terms, string(token.Term))
}
return terms
}
func filter(input analysis.TokenStream) analysis.TokenStream {
filter := NewTokenFilter()
return filter.Filter(input)
}
func tokenize(input string) analysis.TokenStream {
tokenizer := unicode.NewUnicodeTokenizer()
return tokenizer.Tokenize([]byte(input))
}
|
