forked from tdewolff/parse
-
Notifications
You must be signed in to change notification settings - Fork 0
/
util.go
481 lines (431 loc) · 14.8 KB
/
util.go
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
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
package parse
import (
"bytes"
"fmt"
"strconv"
"unicode"
)
// Copy returns a copy of the given byte slice.
func Copy(src []byte) (dst []byte) {
dst = make([]byte, len(src))
copy(dst, src)
return
}
// ToLower converts all characters in the byte slice from A-Z to a-z.
func ToLower(src []byte) []byte {
for i, c := range src {
if c >= 'A' && c <= 'Z' {
src[i] = c + ('a' - 'A')
}
}
return src
}
// EqualFold returns true when s matches case-insensitively the targetLower (which must be lowercase).
func EqualFold(s, targetLower []byte) bool {
if len(s) != len(targetLower) {
return false
}
for i, c := range targetLower {
d := s[i]
if d != c && (d < 'A' || d > 'Z' || d+('a'-'A') != c) {
return false
}
}
return true
}
// Printable returns a printable string for given rune
func Printable(r rune) string {
if unicode.IsGraphic(r) {
return fmt.Sprintf("%c", r)
} else if r < 128 {
return fmt.Sprintf("0x%02X", r)
}
return fmt.Sprintf("%U", r)
}
var whitespaceTable = [256]bool{
// ASCII
false, false, false, false, false, false, false, false,
false, true, true, false, true, true, false, false, // tab, new line, form feed, carriage return
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
true, false, false, false, false, false, false, false, // space
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
// non-ASCII
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
}
// IsWhitespace returns true for space, \n, \r, \t, \f.
func IsWhitespace(c byte) bool {
return whitespaceTable[c]
}
var newlineTable = [256]bool{
// ASCII
false, false, false, false, false, false, false, false,
false, false, true, false, false, true, false, false, // new line, carriage return
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
// non-ASCII
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
}
// IsNewline returns true for \n, \r.
func IsNewline(c byte) bool {
return newlineTable[c]
}
// IsAllWhitespace returns true when the entire byte slice consists of space, \n, \r, \t, \f.
func IsAllWhitespace(b []byte) bool {
for _, c := range b {
if !IsWhitespace(c) {
return false
}
}
return true
}
// TrimWhitespace removes any leading and trailing whitespace characters.
func TrimWhitespace(b []byte) []byte {
n := len(b)
start := n
for i := 0; i < n; i++ {
if !IsWhitespace(b[i]) {
start = i
break
}
}
end := n
for i := n - 1; i >= start; i-- {
if !IsWhitespace(b[i]) {
end = i + 1
break
}
}
return b[start:end]
}
// ReplaceMultipleWhitespace replaces character series of space, \n, \t, \f, \r into a single space or newline (when the serie contained a \n or \r).
func ReplaceMultipleWhitespace(b []byte) []byte {
j, k := 0, 0 // j is write position, k is start of next text section
for i := 0; i < len(b); i++ {
if IsWhitespace(b[i]) {
start := i
newline := IsNewline(b[i])
i++
for ; i < len(b) && IsWhitespace(b[i]); i++ {
if IsNewline(b[i]) {
newline = true
}
}
if newline {
b[start] = '\n'
} else {
b[start] = ' '
}
if 1 < i-start { // more than one whitespace
if j == 0 {
j = start + 1
} else {
j += copy(b[j:], b[k:start+1])
}
k = i
}
}
}
if j == 0 {
return b
} else if j == 1 { // only if starts with whitespace
b[k-1] = b[0]
return b[k-1:]
} else if k < len(b) {
j += copy(b[j:], b[k:])
}
return b[:j]
}
// replaceEntities will replace in b at index i, assuming that b[i] == '&' and that i+3<len(b). The returned int will be the last character of the entity, so that the next iteration can safely do i++ to continue and not miss any entitites.
func replaceEntities(b []byte, i int, entitiesMap map[string][]byte, revEntitiesMap map[byte][]byte) ([]byte, int) {
const MaxEntityLength = 31 // longest HTML entity: CounterClockwiseContourIntegral
var r []byte
j := i + 1
if b[j] == '#' {
j++
if b[j] == 'x' {
j++
c := 0
for ; j < len(b) && (b[j] >= '0' && b[j] <= '9' || b[j] >= 'a' && b[j] <= 'f' || b[j] >= 'A' && b[j] <= 'F'); j++ {
if b[j] <= '9' {
c = c<<4 + int(b[j]-'0')
} else if b[j] <= 'F' {
c = c<<4 + int(b[j]-'A') + 10
} else if b[j] <= 'f' {
c = c<<4 + int(b[j]-'a') + 10
}
}
if j <= i+3 || 10000 <= c {
return b, j - 1
}
if c < 128 {
r = []byte{byte(c)}
} else {
r = append(r, '&', '#')
r = strconv.AppendInt(r, int64(c), 10)
r = append(r, ';')
}
} else {
c := 0
for ; j < len(b) && c < 128 && b[j] >= '0' && b[j] <= '9'; j++ {
c = c*10 + int(b[j]-'0')
}
if j <= i+2 || 128 <= c {
return b, j - 1
}
r = []byte{byte(c)}
}
} else {
for ; j < len(b) && j-i-1 <= MaxEntityLength && b[j] != ';'; j++ {
}
if j <= i+1 || len(b) <= j {
return b, j - 1
}
var ok bool
r, ok = entitiesMap[string(b[i+1:j])]
if !ok {
return b, j
}
}
// j is at semicolon
n := j + 1 - i
if j < len(b) && b[j] == ';' && 2 < n {
if len(r) == 1 {
if q, ok := revEntitiesMap[r[0]]; ok {
if len(q) == len(b[i:j+1]) && bytes.Equal(q, b[i:j+1]) {
return b, j
}
r = q
} else if r[0] == '&' {
// check if for example & is followed by something that could potentially be an entity
k := j + 1
if k < len(b) && (b[k] >= '0' && b[k] <= '9' || b[k] >= 'a' && b[k] <= 'z' || b[k] >= 'A' && b[k] <= 'Z' || b[k] == '#') {
return b, k
}
}
}
copy(b[i:], r)
copy(b[i+len(r):], b[j+1:])
b = b[:len(b)-n+len(r)]
return b, i + len(r) - 1
}
return b, i
}
// ReplaceEntities replaces all occurrences of entites (such as ") to their respective unencoded bytes.
func ReplaceEntities(b []byte, entitiesMap map[string][]byte, revEntitiesMap map[byte][]byte) []byte {
for i := 0; i < len(b); i++ {
if b[i] == '&' && i+3 < len(b) {
b, i = replaceEntities(b, i, entitiesMap, revEntitiesMap)
}
}
return b
}
// ReplaceMultipleWhitespaceAndEntities is a combination of ReplaceMultipleWhitespace and ReplaceEntities. It is faster than executing both sequentially.
func ReplaceMultipleWhitespaceAndEntities(b []byte, entitiesMap map[string][]byte, revEntitiesMap map[byte][]byte) []byte {
j, k := 0, 0 // j is write position, k is start of next text section
for i := 0; i < len(b); i++ {
if IsWhitespace(b[i]) {
start := i
newline := IsNewline(b[i])
i++
for ; i < len(b) && IsWhitespace(b[i]); i++ {
if IsNewline(b[i]) {
newline = true
}
}
if newline {
b[start] = '\n'
} else {
b[start] = ' '
}
if 1 < i-start { // more than one whitespace
if j == 0 {
j = start + 1
} else {
j += copy(b[j:], b[k:start+1])
}
k = i
}
}
if i+3 < len(b) && b[i] == '&' {
b, i = replaceEntities(b, i, entitiesMap, revEntitiesMap)
}
}
if j == 0 {
return b
} else if j == 1 { // only if starts with whitespace
b[k-1] = b[0]
return b[k-1:]
} else if k < len(b) {
j += copy(b[j:], b[k:])
}
return b[:j]
}
// URLEncodingTable is a charmap for which characters need escaping in the URL encoding scheme
var URLEncodingTable = [256]bool{
// ASCII
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, false, true, true, true, true, true, false, // space, ", #, $, %, &
false, false, false, true, true, false, false, true, // +, comma, /
false, false, false, false, false, false, false, false,
false, false, true, true, true, true, true, true, // :, ;, <, =, >, ?
true, false, false, false, false, false, false, false, // @
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, true, true, true, true, false, // [, \, ], ^
true, false, false, false, false, false, false, false, // `
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, true, true, true, false, true, // {, |, }, DEL
// non-ASCII
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
}
// DataURIEncodingTable is a charmap for which characters need escaping in the Data URI encoding scheme
// Escape only non-printable characters, unicode and %, #, &.
// IE11 additionally requires encoding of \, [, ], ", <, >, `, {, }, |, ^ which is not required by Chrome, Firefox, Opera, Edge, Safari, Yandex
// To pass the HTML validator, restricted URL characters must be escaped: non-printable characters, space, <, >, #, %, "
var DataURIEncodingTable = [256]bool{
// ASCII
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, false, true, true, false, true, true, false, // space, ", #, %, &
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, true, false, true, false, // <, >
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, true, true, true, true, false, // [, \, ], ^
true, false, false, false, false, false, false, false, // `
false, false, false, false, false, false, false, false,
false, false, false, false, false, false, false, false,
false, false, false, true, true, true, false, true, // {, |, }, DEL
// non-ASCII
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
true, true, true, true, true, true, true, true,
}
// EncodeURL encodes bytes using the URL encoding scheme
func EncodeURL(b []byte, table [256]bool) []byte {
for i := 0; i < len(b); i++ {
c := b[i]
if table[c] {
b = append(b, 0, 0)
copy(b[i+3:], b[i+1:])
b[i+0] = '%'
b[i+1] = "0123456789ABCDEF"[c>>4]
b[i+2] = "0123456789ABCDEF"[c&15]
}
}
return b
}
// DecodeURL decodes an URL encoded using the URL encoding scheme
func DecodeURL(b []byte) []byte {
for i := 0; i < len(b); i++ {
if b[i] == '%' && i+2 < len(b) {
j := i + 1
c := 0
for ; j < i+3 && (b[j] >= '0' && b[j] <= '9' || b[j] >= 'a' && b[j] <= 'f' || b[j] >= 'A' && b[j] <= 'F'); j++ {
if b[j] <= '9' {
c = c<<4 + int(b[j]-'0')
} else if b[j] <= 'F' {
c = c<<4 + int(b[j]-'A') + 10
} else if b[j] <= 'f' {
c = c<<4 + int(b[j]-'a') + 10
}
}
if j == i+3 && c < 128 {
b[i] = byte(c)
b = append(b[:i+1], b[i+3:]...)
}
} else if b[i] == '+' {
b[i] = ' '
}
}
return b
}