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
|
package spec
import (
"strings"
"testing"
)
func TestLexer_Run(t *testing.T) {
tests := []struct {
caption string
src string
tokens []*token
err error
}{
{
caption: "the lexer can recognize all kinds of tokens",
src: `id"terminal":|;#'()$1...`,
tokens: []*token{
newIDToken("id"),
newTerminalPatternToken("terminal"),
newSymbolToken(tokenKindColon),
newSymbolToken(tokenKindOr),
newSymbolToken(tokenKindSemicolon),
newSymbolToken(tokenKindDirectiveMarker),
newSymbolToken(tokenKindTreeNodeOpen),
newSymbolToken(tokenKindTreeNodeClose),
newPositionToken(1),
newSymbolToken(tokenKindExpantion),
newEOFToken(),
},
},
{
caption: "the lexer can recognize keywords",
src: `fragment`,
tokens: []*token{
newSymbolToken(tokenKindKWFragment),
newEOFToken(),
},
},
{
caption: "the lexer can recognize character sequences and escape sequences in terminal",
src: `"abc\"\\"`,
tokens: []*token{
newTerminalPatternToken(`abc"\\`),
newEOFToken(),
},
},
{
caption: "the lexer can recognize newlines and combine consecutive newlines into one",
src: "\u000A | \u000D | \u000D\u000A | \u000A\u000A \u000D\u000D \u000D\u000A\u000D\u000A",
tokens: []*token{
newSymbolToken(tokenKindNewline),
newSymbolToken(tokenKindOr),
newSymbolToken(tokenKindNewline),
newSymbolToken(tokenKindOr),
newSymbolToken(tokenKindNewline),
newSymbolToken(tokenKindOr),
newSymbolToken(tokenKindNewline),
newEOFToken(),
},
},
{
caption: "the lexer ignores line comments",
src: `
// This is the first comment.
foo
// This is the second comment.
// This is the third comment.
bar // This is the fourth comment.
`,
tokens: []*token{
newSymbolToken(tokenKindNewline),
newIDToken("foo"),
newSymbolToken(tokenKindNewline),
newIDToken("bar"),
newSymbolToken(tokenKindNewline),
newEOFToken(),
},
},
{
caption: "an unclosed terminal is not a valid token",
src: `"abc`,
err: synErrUnclosedTerminal,
},
{
caption: "an incompleted terminal is not a valid token",
src: `"\`,
err: synErrIncompletedEscSeq,
},
{
caption: "a position must be greater than or equal to 1",
src: `$0`,
err: synErrZeroPos,
},
{
caption: "the lexer can recognize valid tokens following an invalid token",
src: `abc!!!def`,
tokens: []*token{
newIDToken("abc"),
newInvalidToken("!!!"),
newIDToken("def"),
newEOFToken(),
},
},
{
caption: "the lexer skips white spaces",
// \u0009: HT
// \u0020: SP
src: "a\u0009b\u0020c",
tokens: []*token{
newIDToken("a"),
newIDToken("b"),
newIDToken("c"),
newEOFToken(),
},
},
}
for _, tt := range tests {
t.Run(tt.caption, func(t *testing.T) {
l, err := newLexer(strings.NewReader(tt.src))
if err != nil {
t.Fatal(err)
}
n := 0
for {
var tok *token
tok, err = l.next()
if err != nil {
break
}
testToken(t, tok, tt.tokens[n])
n++
if tok.kind == tokenKindEOF {
break
}
}
if err != tt.err {
t.Fatalf("unexpected error; want: %v, got: %v", tt.err, err)
}
})
}
}
func testToken(t *testing.T, tok, expected *token) {
t.Helper()
if tok.kind != expected.kind || tok.text != expected.text || tok.num != expected.num {
t.Fatalf("unexpected token; want: %+v, got: %+v", expected, tok)
}
}
|
