chroma/delegate_test.go at master · alecthomas/chroma · GitHub

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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
package chroma

import (
	"iter"
	"slices"
	"testing"

	assert "github.com/alecthomas/assert/v2"
)

type countingLexer struct {
	Lexer
	tokens   []Token
	consumed int
	texts    []string
}

func (l *countingLexer) Tokenise(_ *TokeniseOptions, text string) (iter.Seq[Token], error) {
	l.texts = append(l.texts, text)
	return func(yield func(Token) bool) {
		for _, token := range l.tokens {
			l.consumed++
			if !yield(token) {
				return
			}
		}
	}, nil
}

func makeDelegationTestLexers(t *testing.T) (lang Lexer, root Lexer) {
	t.Helper()
	return mustNewLexer(t, nil, Rules{ // nolint: forbidigo
			"root": {
				{`\<\?`, CommentPreproc, Push("inside")},
				{`.`, Other, nil},
			},
			"inside": {
				{`\?\>`, CommentPreproc, Pop(1)},
				{`\bwhat\b`, Keyword, nil},
				{`\s+`, Whitespace, nil},
			},
		}),
		mustNewLexer(t, nil, Rules{ // nolint: forbidigo
			"root": {
				{`\bhello\b`, Keyword, nil},
				{`\b(world|there)\b`, Name, nil},
				{`\s+`, Whitespace, nil},
			},
		})
}

func TestDelegate(t *testing.T) {
	testdata := []struct {
		name     string
		source   string
		expected []Token
	}{
		{"SourceInMiddle", `hello world <? what ?> there`, []Token{
			{Keyword, "hello"},
			{TextWhitespace, " "},
			{Name, "world"},
			{TextWhitespace, " "},
			// lang
			{CommentPreproc, "<?"},
			{Whitespace, " "},
			{Keyword, "what"},
			{Whitespace, " "},
			{CommentPreproc, "?>"},
			// /lang
			{TextWhitespace, " "},
			{Name, "there"},
		}},
		{"SourceBeginning", `<? what ?> hello world there`, []Token{
			{CommentPreproc, "<?"},
			{TextWhitespace, " "},
			{Keyword, "what"},
			{TextWhitespace, " "},
			{CommentPreproc, "?>"},
			{TextWhitespace, " "},
			{Keyword, "hello"},
			{TextWhitespace, " "},
			{Name, "world"},
			{TextWhitespace, " "},
			{Name, "there"},
		}},
		{"SourceEnd", `hello world <? what there`, []Token{
			{Keyword, "hello"},
			{TextWhitespace, " "},
			{Name, "world"},
			{TextWhitespace, " "},
			// lang
			{CommentPreproc, "<?"},
			{Whitespace, " "},
			{Keyword, "what"},
			{TextWhitespace, " "},
			{Error, "there"},
		}},
		{"SourceMultiple", "hello world <? what ?> hello there <? what ?> hello", []Token{
			{Keyword, "hello"},
			{TextWhitespace, " "},
			{Name, "world"},
			{TextWhitespace, " "},
			{CommentPreproc, "<?"},
			{TextWhitespace, " "},
			{Keyword, "what"},
			{TextWhitespace, " "},
			{CommentPreproc, "?>"},
			{TextWhitespace, " "},
			{Keyword, "hello"},
			{TextWhitespace, " "},
			{Name, "there"},
			{TextWhitespace, " "},
			{CommentPreproc, "<?"},
			{TextWhitespace, " "},
			{Keyword, "what"},
			{TextWhitespace, " "},
			{CommentPreproc, "?>"},
			{TextWhitespace, " "},
			{Keyword, "hello"},
		}},
	}
	lang, root := makeDelegationTestLexers(t)
	delegate := DelegatingLexer(root, lang)
	for _, test := range testdata {
		t.Run(test.name, func(t *testing.T) {
			it, err := delegate.Tokenise(nil, test.source)
			assert.NoError(t, err)
			actual := slices.Collect(it)
			assert.Equal(t, test.expected, actual)
		})
	}
}

func TestDelegateStreamsRootTokens(t *testing.T) {
	root := &countingLexer{tokens: []Token{
		{Name, "a"},
		{Text, "c"},
		{Name, "e"},
	}}
	language := &countingLexer{tokens: []Token{
		{Other, "a"},
		{Keyword, "b"},
		{Other, "c"},
		{Keyword, "d"},
		{Other, "e"},
	}}
	it, err := DelegatingLexer(root, language).Tokenise(nil, "abcde")
	assert.NoError(t, err)
	assert.Equal(t, 0, root.consumed)
	assert.Equal(t, 5, language.consumed)

	var actual Token
	for token := range it {
		actual = token
		break
	}
	assert.Equal(t, Token{Name, "a"}, actual)
	assert.Equal(t, 2, root.consumed)
	assert.Equal(t, 7, language.consumed)
}

func TestDelegateSplitsRootTokens(t *testing.T) {
	root := &countingLexer{tokens: []Token{{Text, "before  after"}}}
	language := &countingLexer{tokens: []Token{
		{Other, "before "},
		{Keyword, "embedded"},
		{Other, " after"},
	}}
	it, err := DelegatingLexer(root, language).Tokenise(nil, "before embedded after")
	assert.NoError(t, err)
	assert.Equal(t, []string{"before  after"}, root.texts)
	assert.Equal(t, []Token{
		{Text, "before "},
		{Keyword, "embedded"},
		{Text, " after"},
	}, slices.Collect(it))
}