Spaces:
Running
Running
File size: 3,588 Bytes
b110593 |
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 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
// _ _
// __ _____ __ ___ ___ __ _| |_ ___
// \ \ /\ / / _ \/ _` \ \ / / |/ _` | __/ _ \
// \ V V / __/ (_| |\ V /| | (_| | || __/
// \_/\_/ \___|\__,_| \_/ |_|\__,_|\__\___|
//
// Copyright © 2016 - 2024 Weaviate B.V. All rights reserved.
//
// CONTACT: [email protected]
//
package helpers
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/weaviate/weaviate/entities/models"
)
func TestTokenize(t *testing.T) {
input := " Hello You*-beautiful_world?!"
type testCase struct {
tokenization string
expected []string
}
t.Run("tokenize", func(t *testing.T) {
testCases := []testCase{
{
tokenization: models.PropertyTokenizationField,
expected: []string{"Hello You*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationWhitespace,
expected: []string{"Hello", "You*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationLowercase,
expected: []string{"hello", "you*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationWord,
expected: []string{"hello", "you", "beautiful", "world"},
},
}
for _, tc := range testCases {
terms := Tokenize(tc.tokenization, input)
assert.ElementsMatch(t, tc.expected, terms)
}
})
t.Run("tokenize with wildcards", func(t *testing.T) {
testCases := []testCase{
{
tokenization: models.PropertyTokenizationField,
expected: []string{"Hello You*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationWhitespace,
expected: []string{"Hello", "You*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationLowercase,
expected: []string{"hello", "you*-beautiful_world?!"},
},
{
tokenization: models.PropertyTokenizationWord,
expected: []string{"hello", "you*", "beautiful", "world?"},
},
}
for _, tc := range testCases {
terms := TokenizeWithWildcards(tc.tokenization, input)
assert.ElementsMatch(t, tc.expected, terms)
}
})
}
func TestTokenizeAndCountDuplicates(t *testing.T) {
input := "Hello You Beautiful World! hello you beautiful world!"
type testCase struct {
tokenization string
expected map[string]int
}
testCases := []testCase{
{
tokenization: models.PropertyTokenizationField,
expected: map[string]int{
"Hello You Beautiful World! hello you beautiful world!": 1,
},
},
{
tokenization: models.PropertyTokenizationWhitespace,
expected: map[string]int{
"Hello": 1,
"You": 1,
"Beautiful": 1,
"World!": 1,
"hello": 1,
"you": 1,
"beautiful": 1,
"world!": 1,
},
},
{
tokenization: models.PropertyTokenizationLowercase,
expected: map[string]int{
"hello": 2,
"you": 2,
"beautiful": 2,
"world!": 2,
},
},
{
tokenization: models.PropertyTokenizationWord,
expected: map[string]int{
"hello": 2,
"you": 2,
"beautiful": 2,
"world": 2,
},
},
}
for _, tc := range testCases {
t.Run(tc.tokenization, func(t *testing.T) {
terms, dups := TokenizeAndCountDuplicates(tc.tokenization, input)
assert.Len(t, terms, len(tc.expected))
assert.Len(t, dups, len(tc.expected))
for i := range terms {
assert.Contains(t, tc.expected, terms[i])
assert.Equal(t, tc.expected[terms[i]], dups[i])
}
})
}
}
|