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
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
|
// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package syntax
import (
"fmt"
"os"
"testing"
)
func TestScanner(t *testing.T) {
if testing.Short() {
t.Skip("skipping test in short mode")
}
src, err := os.Open("parser.go")
if err != nil {
t.Fatal(err)
}
defer src.Close()
var s scanner
s.init(src, nil)
for {
s.next()
if s.tok == _EOF {
break
}
switch s.tok {
case _Name:
fmt.Println(s.line, s.tok, "=>", s.lit)
case _Operator:
fmt.Println(s.line, s.tok, "=>", s.op, s.prec)
default:
fmt.Println(s.line, s.tok)
}
}
}
func TestTokens(t *testing.T) {
// make source
var buf []byte
for i, s := range sampleTokens {
buf = append(buf, "\t\t\t\t"[:i&3]...) // leading indentation
buf = append(buf, s.src...) // token
buf = append(buf, " "[:i&7]...) // trailing spaces
buf = append(buf, "/* foo */ // bar\n"...) // comments
}
// scan source
var got scanner
got.init(&bytesReader{buf}, nil)
got.next()
for i, want := range sampleTokens {
nlsemi := false
if got.line != i+1 {
t.Errorf("got line %d; want %d", got.line, i+1)
}
if got.tok != want.tok {
t.Errorf("got tok = %s; want %s", got.tok, want.tok)
continue
}
switch want.tok {
case _Name, _Literal:
if got.lit != want.src {
t.Errorf("got lit = %q; want %q", got.lit, want.src)
continue
}
nlsemi = true
case _Operator, _AssignOp, _IncOp:
if got.op != want.op {
t.Errorf("got op = %s; want %s", got.op, want.op)
continue
}
if got.prec != want.prec {
t.Errorf("got prec = %s; want %s", got.prec, want.prec)
continue
}
nlsemi = want.tok == _IncOp
case _Rparen, _Rbrack, _Rbrace, _Break, _Continue, _Fallthrough, _Return:
nlsemi = true
}
if nlsemi {
got.next()
if got.tok != _Semi {
t.Errorf("got tok = %s; want ;", got.tok)
continue
}
}
got.next()
}
if got.tok != _EOF {
t.Errorf("got %q; want _EOF", got.tok)
}
}
var sampleTokens = [...]struct {
tok token
src string
op Operator
prec int
}{
// name samples
{_Name, "x", 0, 0},
{_Name, "X123", 0, 0},
{_Name, "foo", 0, 0},
{_Name, "Foo123", 0, 0},
{_Name, "foo_bar", 0, 0},
{_Name, "_", 0, 0},
{_Name, "_foobar", 0, 0},
{_Name, "a۰۱۸", 0, 0},
{_Name, "foo६४", 0, 0},
{_Name, "bar９８７６", 0, 0},
{_Name, "ŝ", 0, 0},
{_Name, "ŝfoo", 0, 0},
// literal samples
{_Literal, "0", 0, 0},
{_Literal, "1", 0, 0},
{_Literal, "12345", 0, 0},
{_Literal, "123456789012345678890123456789012345678890", 0, 0},
{_Literal, "01234567", 0, 0},
{_Literal, "0x0", 0, 0},
{_Literal, "0xcafebabe", 0, 0},
{_Literal, "0.", 0, 0},
{_Literal, "0.e0", 0, 0},
{_Literal, "0.e-1", 0, 0},
{_Literal, "0.e+123", 0, 0},
{_Literal, ".0", 0, 0},
{_Literal, ".0E00", 0, 0},
{_Literal, ".0E-0123", 0, 0},
{_Literal, ".0E+12345678901234567890", 0, 0},
{_Literal, ".45e1", 0, 0},
{_Literal, "3.14159265", 0, 0},
{_Literal, "1e0", 0, 0},
{_Literal, "1e+100", 0, 0},
{_Literal, "1e-100", 0, 0},
{_Literal, "2.71828e-1000", 0, 0},
{_Literal, "0i", 0, 0},
{_Literal, "1i", 0, 0},
{_Literal, "012345678901234567889i", 0, 0},
{_Literal, "123456789012345678890i", 0, 0},
{_Literal, "0.i", 0, 0},
{_Literal, ".0i", 0, 0},
{_Literal, "3.14159265i", 0, 0},
{_Literal, "1e0i", 0, 0},
{_Literal, "1e+100i", 0, 0},
{_Literal, "1e-100i", 0, 0},
{_Literal, "2.71828e-1000i", 0, 0},
{_Literal, "'a'", 0, 0},
{_Literal, "'\\000'", 0, 0},
{_Literal, "'\\xFF'", 0, 0},
{_Literal, "'\\uff16'", 0, 0},
{_Literal, "'\\U0000ff16'", 0, 0},
{_Literal, "`foobar`", 0, 0},
{_Literal, "`foo\tbar`", 0, 0},
{_Literal, "`\r`", 0, 0},
// operators
{_Operator, "||", OrOr, precOrOr},
{_Operator, "&&", AndAnd, precAndAnd},
{_Operator, "==", Eql, precCmp},
{_Operator, "!=", Neq, precCmp},
{_Operator, "<", Lss, precCmp},
{_Operator, "<=", Leq, precCmp},
{_Operator, ">", Gtr, precCmp},
{_Operator, ">=", Geq, precCmp},
{_Operator, "+", Add, precAdd},
{_Operator, "-", Sub, precAdd},
{_Operator, "|", Or, precAdd},
{_Operator, "^", Xor, precAdd},
{_Star, "*", Mul, precMul},
{_Operator, "/", Div, precMul},
{_Operator, "%", Rem, precMul},
{_Operator, "&", And, precMul},
{_Operator, "&^", AndNot, precMul},
{_Operator, "<<", Shl, precMul},
{_Operator, ">>", Shr, precMul},
// assignment operations
{_AssignOp, "+=", Add, precAdd},
{_AssignOp, "-=", Sub, precAdd},
{_AssignOp, "|=", Or, precAdd},
{_AssignOp, "^=", Xor, precAdd},
{_AssignOp, "*=", Mul, precMul},
{_AssignOp, "/=", Div, precMul},
{_AssignOp, "%=", Rem, precMul},
{_AssignOp, "&=", And, precMul},
{_AssignOp, "&^=", AndNot, precMul},
{_AssignOp, "<<=", Shl, precMul},
{_AssignOp, ">>=", Shr, precMul},
// other operations
{_IncOp, "++", Add, precAdd},
{_IncOp, "--", Sub, precAdd},
{_Assign, "=", 0, 0},
{_Define, ":=", 0, 0},
{_Arrow, "<-", 0, 0},
// delimiters
{_Lparen, "(", 0, 0},
{_Lbrack, "[", 0, 0},
{_Lbrace, "{", 0, 0},
{_Rparen, ")", 0, 0},
{_Rbrack, "]", 0, 0},
{_Rbrace, "}", 0, 0},
{_Comma, ",", 0, 0},
{_Semi, ";", 0, 0},
{_Colon, ":", 0, 0},
{_Dot, ".", 0, 0},
{_DotDotDot, "...", 0, 0},
// keywords
{_Break, "break", 0, 0},
{_Case, "case", 0, 0},
{_Chan, "chan", 0, 0},
{_Const, "const", 0, 0},
{_Continue, "continue", 0, 0},
{_Default, "default", 0, 0},
{_Defer, "defer", 0, 0},
{_Else, "else", 0, 0},
{_Fallthrough, "fallthrough", 0, 0},
{_For, "for", 0, 0},
{_Func, "func", 0, 0},
{_Go, "go", 0, 0},
{_Goto, "goto", 0, 0},
{_If, "if", 0, 0},
{_Import, "import", 0, 0},
{_Interface, "interface", 0, 0},
{_Map, "map", 0, 0},
{_Package, "package", 0, 0},
{_Range, "range", 0, 0},
{_Return, "return", 0, 0},
{_Select, "select", 0, 0},
{_Struct, "struct", 0, 0},
{_Switch, "switch", 0, 0},
{_Type, "type", 0, 0},
{_Var, "var", 0, 0},
}
func TestScanErrors(t *testing.T) {
for _, test := range []struct {
src, msg string
}{
// rune-level errors
{"fo\x00o", "invalid NUL character"},
{"fo\ufeffo", "invalid BOM in the middle of the file"},
{"\xff", "invalid UTF-8 encoding"},
// token-level errors
{"~", "bitwise complement operator is ^"},
{"$", "invalid rune '$'"},
{"0xyz", "malformed hex constant"},
{"08", "malformed octal constant"},
{"1.0e+x", "malformed floating-point constant exponent"},
{`"foo`, "string not terminated"},
{"`foo", "string not terminated"},
{"/* foo", "comment not terminated"},
{`"foo\z"`, "unknown escape sequence"},
// {`"\x`, "escape sequence not terminated"},
{`"\x"`, "illegal character U+0022 '\"' in escape sequence"},
{`"\Uffffffff"`, "escape sequence is invalid Unicode code point"},
} {
var s scanner
hasError := false
s.init(&bytesReader{[]byte(test.src)}, func(_, line int, msg string) {
hasError = true
// TODO(gri) test exact position as well
if line != 1 {
t.Errorf("got line = %d; want 1", line)
}
if msg != test.msg {
t.Errorf("got msg = %q; want %q", msg, test.msg)
}
})
s.next()
if !hasError {
t.Errorf("%q: got no error; want %q", test.src, test.msg)
}
}
}
|
