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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
|
// Copyright 2009 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.
// JSON (JavaScript Object Notation) parser.
// See http://www.json.org/
package json
import (
"fmt";
"io";
"math";
"strconv";
"strings";
"utf8";
)
// Strings
//
// Double quoted with escapes: \" \\ \/ \b \f \n \r \t \uXXXX.
// No literal control characters, supposedly.
// Have also seen \' and embedded newlines.
func _UnHex(p string, r, l int) (v int, ok bool) {
v = 0;
for i := r; i < l; i++ {
if i >= len(p) {
return 0, false
}
v *= 16;
switch {
case '0' <= p[i] && p[i] <= '9':
v += int(p[i] - '0');
case 'a' <= p[i] && p[i] <= 'f':
v += int(p[i] - 'a' + 10);
case 'A' <= p[i] && p[i] <= 'F':
v += int(p[i] - 'A' + 10);
default:
return 0, false;
}
}
return v, true;
}
func Unquote(s string) (t string, ok bool) {
if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
return
}
b := make([]byte, len(s));
w := 0;
for r := 1; r < len(s)-1; {
switch {
case s[r] == '\\':
r++;
if r >= len(s)-1 {
return
}
switch s[r] {
default:
return;
case '"', '\\', '/', '\'':
b[w] = s[r];
r++;
w++;
case 'b':
b[w] = '\b';
r++;
w++;
case 'f':
b[w] = '\f';
r++;
w++;
case 'n':
b[w] = '\n';
r++;
w++;
case 'r':
b[w] = '\r';
r++;
w++;
case 't':
b[w] = '\t';
r++;
w++;
case 'u':
r++;
rune, ok := _UnHex(s, r, 4);
if !ok {
return
}
r += 4;
w += utf8.EncodeRune(rune, b[w:len(b)]);
}
// Control characters are invalid, but we've seen raw \n.
case s[r] < ' ' && s[r] != '\n':
if s[r] == '\n' {
b[w] = '\n';
r++;
w++;
break;
}
return;
// ASCII
case s[r] < utf8.RuneSelf:
b[w] = s[r];
r++;
w++;
// Coerce to well-formed UTF-8.
default:
rune, size := utf8.DecodeRuneInString(s, r);
r += size;
w += utf8.EncodeRune(rune, b[w:len(b)]);
}
}
return string(b[0:w]), true
}
func Quote(s string) string {
chr := make([]byte, utf8.UTFMax);
chr0 := chr[0:1];
b := new(io.ByteBuffer);
chr[0] = '"';
b.Write(chr0);
for i := 0; i < len(s); i++ {
switch {
case s[i]=='"' || s[i]=='\\':
chr[0] = '\\';
chr[1] = s[i];
b.Write(chr[0:2]);
case s[i] == '\b':
chr[0] = '\\';
chr[1] = 'b';
b.Write(chr[0:2]);
case s[i] == '\f':
chr[0] = '\\';
chr[1] = 'f';
b.Write(chr[0:2]);
case s[i] == '\n':
chr[0] = '\\';
chr[1] = 'n';
b.Write(chr[0:2]);
case s[i] == '\r':
chr[0] = '\\';
chr[1] = 'r';
b.Write(chr[0:2]);
case s[i] == '\t':
chr[0] = '\\';
chr[1] = 't';
b.Write(chr[0:2]);
case 0x20 <= s[i] && s[i] < utf8.RuneSelf:
chr[0] = s[i];
b.Write(chr0);
}
}
chr[0] = '"';
b.Write(chr0);
return string(b.Data());
}
// _Lexer
type _Lexer struct {
s string;
i int;
kind int;
token string;
}
func punct(c byte) bool {
return c=='"' || c=='[' || c==']' || c==':' || c=='{' || c=='}' || c==','
}
func white(c byte) bool {
return c==' ' || c=='\t' || c=='\n' || c=='\v'
}
func skipwhite(p string, i int) int {
for i < len(p) && white(p[i]) {
i++
}
return i
}
func skiptoken(p string, i int) int {
for i < len(p) && !punct(p[i]) && !white(p[i]) {
i++
}
return i
}
func skipstring(p string, i int) int {
for i++; i < len(p) && p[i] != '"'; i++ {
if p[i] == '\\' {
i++
}
}
if i >= len(p) {
return i
}
return i+1
}
func (t *_Lexer) Next() {
i, s := t.i, t.s;
i = skipwhite(s, i);
if i >= len(s) {
t.kind = 0;
t.token = "";
t.i = len(s);
return;
}
c := s[i];
switch {
case c == '-' || '0' <= c && c <= '9':
j := skiptoken(s, i);
t.kind = '1';
t.token = s[i:j];
i = j;
case 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z':
j := skiptoken(s, i);
t.kind = 'a';
t.token = s[i:j];
i = j;
case c == '"':
j := skipstring(s, i);
t.kind = '"';
t.token = s[i:j];
i = j;
case c == '[', c == ']', c == ':', c == '{', c == '}', c == ',':
t.kind = int(c);
t.token = s[i:i+1];
i++;
default:
t.kind = '?';
t.token = s[i:i+1];
}
t.i = i;
}
// Parser
//
// Implements parsing but not the actions. Those are
// carried out by the implementation of the Builder interface.
// A Builder represents the object being created.
// Calling a method like Int64(i) sets that object to i.
// Calling a method like Elem(i) or Key(s) creates a
// new builder for a subpiece of the object (logically,
// an array element or a map key).
//
// There are two Builders, in other files.
// The JsonBuilder builds a generic Json structure
// in which maps are maps.
// The StructBuilder copies data into a possibly
// nested data structure, using the "map keys"
// as struct field names.
type _Value interface {}
type Builder interface {
// Set value
Int64(i int64);
Uint64(i uint64);
Float64(f float64);
String(s string);
Bool(b bool);
Null();
Array();
Map();
// Create sub-Builders
Elem(i int) Builder;
Key(s string) Builder;
}
func parse(lex *_Lexer, build Builder) bool {
ok := false;
Switch:
switch lex.kind {
case 0:
break;
case '1':
// If the number is exactly an integer, use that.
if i, err := strconv.Atoi64(lex.token); err == nil {
build.Int64(i);
ok = true;
}
else if i, err := strconv.Atoui64(lex.token); err == nil {
build.Uint64(i);
ok = true;
}
// Fall back to floating point.
else if f, err := strconv.Atof64(lex.token); err == nil {
build.Float64(f);
ok = true;
}
case 'a':
switch lex.token {
case "true":
build.Bool(true);
ok = true;
case "false":
build.Bool(false);
ok = true;
case "null":
build.Null();
ok = true;
}
case '"':
if str, ok1 := Unquote(lex.token); ok1 {
build.String(str);
ok = true;
}
case '[':
// array
build.Array();
lex.Next();
n := 0;
for lex.kind != ']' {
if n > 0 {
if lex.kind != ',' {
break Switch;
}
lex.Next();
}
if !parse(lex, build.Elem(n)) {
break Switch;
}
n++;
}
ok = true;
case '{':
// map
lex.Next();
build.Map();
n := 0;
for lex.kind != '}' {
if n > 0 {
if lex.kind != ',' {
break Switch;
}
lex.Next();
}
if lex.kind != '"' {
break Switch;
}
key, ok := Unquote(lex.token);
if !ok {
break Switch;
}
lex.Next();
if lex.kind != ':' {
break Switch;
}
lex.Next();
if !parse(lex, build.Key(key)) {
break Switch;
}
n++;
}
ok = true;
}
if ok {
lex.Next();
}
return ok;
}
func Parse(s string, build Builder) (ok bool, errindx int, errtok string) {
lex := new(_Lexer);
lex.s = s;
lex.Next();
if parse(lex, build) {
if lex.kind == 0 { // EOF
return true, 0, ""
}
}
return false, lex.i, lex.token
}
|