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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
|
package compiler
import (
"strings"
"testing"
)
func TestLexer(t *testing.T) {
tests := []struct {
caption string
src string
tokens []*token
err error
}{
{
caption: "lexer can recognize ordinaly characters",
src: "123abcいろは",
tokens: []*token{
newToken(tokenKindChar, '1'),
newToken(tokenKindChar, '2'),
newToken(tokenKindChar, '3'),
newToken(tokenKindChar, 'a'),
newToken(tokenKindChar, 'b'),
newToken(tokenKindChar, 'c'),
newToken(tokenKindChar, 'い'),
newToken(tokenKindChar, 'ろ'),
newToken(tokenKindChar, 'は'),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "lexer can recognize the special characters in default mode",
src: ".*+?|()[",
tokens: []*token{
newToken(tokenKindAnyChar, nullChar),
newToken(tokenKindRepeat, nullChar),
newToken(tokenKindRepeatOneOrMore, nullChar),
newToken(tokenKindOption, nullChar),
newToken(tokenKindAlt, nullChar),
newToken(tokenKindGroupOpen, nullChar),
newToken(tokenKindGroupClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "lexer can recognize the escape sequences in default mode",
src: "\\\\\\.\\*\\+\\?\\|\\(\\)\\[",
tokens: []*token{
newToken(tokenKindChar, '\\'),
newToken(tokenKindChar, '.'),
newToken(tokenKindChar, '*'),
newToken(tokenKindChar, '+'),
newToken(tokenKindChar, '?'),
newToken(tokenKindChar, '|'),
newToken(tokenKindChar, '('),
newToken(tokenKindChar, ')'),
newToken(tokenKindChar, '['),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "] is treated as an ordinary character in default mode",
src: "]",
tokens: []*token{
newToken(tokenKindChar, ']'),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "lexer can recognize the special characters in bracket expression mode",
src: "[a-z][^a-z]",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "lexer can recognize the escape sequences in bracket expression mode",
src: "[\\^a\\-z]",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '^'),
newToken(tokenKindChar, 'a'),
newToken(tokenKindChar, '-'),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "in a bracket expression, the special characters are also handled as normal characters",
src: "[\\\\.*+?|()[",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '\\'),
newToken(tokenKindChar, '.'),
newToken(tokenKindChar, '*'),
newToken(tokenKindChar, '+'),
newToken(tokenKindChar, '?'),
newToken(tokenKindChar, '|'),
newToken(tokenKindChar, '('),
newToken(tokenKindChar, ')'),
newToken(tokenKindChar, '['),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "hyphen symbols that appear in bracket expressions are handled as the character range symbol or ordinary characters",
// [...-...][...-][-...][-]
// ~~~~~~~ ~ ~ ~
// ^ ^ ^ ^
// | | | `-- Ordinary Character (b)
// | | `-- Ordinary Character (b)
// | `-- Ordinary Character (b)
// `-- Character Range (a)
//
// a. *-* is handled as a character range expression.
// b. *-, -*, or - are handled as ordinary characters.
src: "[a-z][a-][-z][-][--][---][^a-z][^a-][^-z][^-][^--][^---]",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, 'a'),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindChar, 'z'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindCharRange, nullChar),
newToken(tokenKindChar, '-'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "caret symbols that appear in bracket expressions are handled as the logical inverse symbol or ordinary characters",
// [^...^...][^]
// ~~ ~ ~~
// ^ ^ ^^
// | | |`-- Ordinary Character (c)
// | | `-- Bracket Expression
// | `-- Ordinary Character (b)
// `-- Inverse Bracket Expression (a)
//
// a. Bracket expressions that have a caret symbol at the beginning are handled as logical inverse expressions.
// b. caret symbols that appear as the second and the subsequent symbols are handled as ordinary symbols.
// c. When a bracket expression has just one symbol, a caret symbol at the beginning is handled as an ordinary character.
src: "[^^][^]",
tokens: []*token{
newToken(tokenKindInverseBExpOpen, nullChar),
newToken(tokenKindChar, '^'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindBExpOpen, nullChar),
newToken(tokenKindChar, '^'),
newToken(tokenKindBExpClose, nullChar),
newToken(tokenKindEOF, nullChar),
},
},
{
caption: "lexer raises an error when an invalid escape sequence appears",
src: "\\@",
err: synErrInvalidEscSeq,
},
{
caption: "lexer raises an error when the incomplete escape sequence (EOF following \\) appears",
src: "\\",
err: synErrIncompletedEscSeq,
},
{
caption: "lexer raises an error when an invalid escape sequence appears",
src: "[\\@",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
},
err: synErrInvalidEscSeq,
},
{
caption: "lexer raises an error when the incomplete escape sequence (EOF following \\) appears",
src: "[\\",
tokens: []*token{
newToken(tokenKindBExpOpen, nullChar),
},
err: synErrIncompletedEscSeq,
},
}
for _, tt := range tests {
t.Run(tt.caption, func(t *testing.T) {
lex := newLexer(strings.NewReader(tt.src))
var err error
var tok *token
i := 0
for {
tok, err = lex.next()
if err != nil {
break
}
if i >= len(tt.tokens) {
break
}
eTok := tt.tokens[i]
i++
testToken(t, tok, eTok)
if tok.kind == tokenKindEOF {
break
}
}
if err != tt.err {
t.Fatalf("unexpected error; want: %v, got: %v", tt.err, err)
}
if i < len(tt.tokens) {
t.Fatalf("expecte more tokens")
}
})
}
}
func testToken(t *testing.T, a, e *token) {
t.Helper()
if e.kind != a.kind || e.char != a.char {
t.Fatalf("unexpected token; want: %v, got: %v", e, a)
}
}
|