forked from Pissandshittium/pissandshittium
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathurl_canon_internal.cc
438 lines (398 loc) · 18.6 KB
/
url_canon_internal.cc
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
// Copyright 2013 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "url/url_canon_internal.h"
#include <errno.h>
#include <stddef.h>
#include <stdlib.h>
#include <cstdio>
#include <string>
#include "base/strings/utf_string_conversion_utils.h"
namespace url {
namespace {
template<typename CHAR, typename UCHAR>
void DoAppendStringOfType(const CHAR* source, int length,
SharedCharTypes type,
CanonOutput* output) {
for (int i = 0; i < length; i++) {
if (static_cast<UCHAR>(source[i]) >= 0x80) {
// ReadChar will fill the code point with kUnicodeReplacementCharacter
// when the input is invalid, which is what we want.
unsigned code_point;
ReadUTFChar(source, &i, length, &code_point);
AppendUTF8EscapedValue(code_point, output);
} else {
// Just append the 7-bit character, possibly escaping it.
unsigned char uch = static_cast<unsigned char>(source[i]);
if (!IsCharOfType(uch, type))
AppendEscapedChar(uch, output);
else
output->push_back(uch);
}
}
}
// This function assumes the input values are all contained in 8-bit,
// although it allows any type. Returns true if input is valid, false if not.
template<typename CHAR, typename UCHAR>
void DoAppendInvalidNarrowString(const CHAR* spec, int begin, int end,
CanonOutput* output) {
for (int i = begin; i < end; i++) {
UCHAR uch = static_cast<UCHAR>(spec[i]);
if (uch >= 0x80) {
// Handle UTF-8/16 encodings. This call will correctly handle the error
// case by appending the invalid character.
AppendUTF8EscapedChar(spec, &i, end, output);
} else if (uch <= ' ' || uch == 0x7f) {
// This function is for error handling, so we escape all control
// characters and spaces, but not anything else since we lack
// context to do something more specific.
AppendEscapedChar(static_cast<unsigned char>(uch), output);
} else {
output->push_back(static_cast<char>(uch));
}
}
}
// Overrides one component, see the Replacements structure for
// what the various combionations of source pointer and component mean.
void DoOverrideComponent(const char* override_source,
const Component& override_component,
const char** dest,
Component* dest_component) {
if (override_source) {
*dest = override_source;
*dest_component = override_component;
}
}
// Similar to DoOverrideComponent except that it takes a UTF-16 input and does
// not actually set the output character pointer.
//
// The input is converted to UTF-8 at the end of the given buffer as a temporary
// holding place. The component identifying the portion of the buffer used in
// the |utf8_buffer| will be specified in |*dest_component|.
//
// This will not actually set any |dest| pointer like DoOverrideComponent
// does because all of the pointers will point into the |utf8_buffer|, which
// may get resized while we're overriding a subsequent component. Instead, the
// caller should use the beginning of the |utf8_buffer| as the string pointer
// for all components once all overrides have been prepared.
bool PrepareUTF16OverrideComponent(const char16_t* override_source,
const Component& override_component,
CanonOutput* utf8_buffer,
Component* dest_component) {
bool success = true;
if (override_source) {
if (!override_component.is_valid()) {
// Non-"valid" component (means delete), so we need to preserve that.
*dest_component = Component();
} else {
// Convert to UTF-8.
dest_component->begin = utf8_buffer->length();
success = ConvertUTF16ToUTF8(&override_source[override_component.begin],
override_component.len, utf8_buffer);
dest_component->len = utf8_buffer->length() - dest_component->begin;
}
}
return success;
}
} // namespace
// See the header file for this array's declaration.
const unsigned char kSharedCharTypeTable[0x100] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x00 - 0x0f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x10 - 0x1f
0, // 0x20 ' ' (escape spaces in queries)
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x21 !
0, // 0x22 "
0, // 0x23 # (invalid in query since it marks the ref)
CHAR_QUERY | CHAR_USERINFO, // 0x24 $
CHAR_QUERY | CHAR_USERINFO, // 0x25 %
CHAR_QUERY | CHAR_USERINFO, // 0x26 &
0, // 0x27 ' (Try to prevent XSS.)
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x28 (
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x29 )
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x2a *
CHAR_QUERY | CHAR_USERINFO, // 0x2b +
CHAR_QUERY | CHAR_USERINFO, // 0x2c ,
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x2d -
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_COMPONENT, // 0x2e .
CHAR_QUERY, // 0x2f /
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x30 0
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x31 1
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x32 2
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x33 3
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x34 4
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x35 5
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x36 6
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_OCT | CHAR_COMPONENT, // 0x37 7
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_COMPONENT, // 0x38 8
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_DEC | CHAR_COMPONENT, // 0x39 9
CHAR_QUERY, // 0x3a :
CHAR_QUERY, // 0x3b ;
0, // 0x3c < (Try to prevent certain types of XSS.)
CHAR_QUERY, // 0x3d =
0, // 0x3e > (Try to prevent certain types of XSS.)
CHAR_QUERY, // 0x3f ?
CHAR_QUERY, // 0x40 @
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x41 A
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x42 B
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x43 C
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x44 D
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x45 E
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x46 F
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x47 G
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x48 H
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x49 I
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4a J
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4b K
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4c L
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4d M
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4e N
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x4f O
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x50 P
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x51 Q
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x52 R
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x53 S
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x54 T
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x55 U
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x56 V
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x57 W
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_COMPONENT, // 0x58 X
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x59 Y
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x5a Z
CHAR_QUERY, // 0x5b [
CHAR_QUERY, // 0x5c '\'
CHAR_QUERY, // 0x5d ]
CHAR_QUERY, // 0x5e ^
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x5f _
CHAR_QUERY, // 0x60 `
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x61 a
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x62 b
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x63 c
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x64 d
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x65 e
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_HEX | CHAR_COMPONENT, // 0x66 f
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x67 g
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x68 h
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x69 i
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6a j
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6b k
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6c l
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6d m
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6e n
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x6f o
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x70 p
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x71 q
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x72 r
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x73 s
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x74 t
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x75 u
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x76 v
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x77 w
CHAR_QUERY | CHAR_USERINFO | CHAR_IPV4 | CHAR_COMPONENT, // 0x78 x
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x79 y
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x7a z
CHAR_QUERY, // 0x7b {
CHAR_QUERY, // 0x7c |
CHAR_QUERY, // 0x7d }
CHAR_QUERY | CHAR_USERINFO | CHAR_COMPONENT, // 0x7e ~
0, // 0x7f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x80 - 0x8f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x90 - 0x9f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xa0 - 0xaf
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xb0 - 0xbf
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xc0 - 0xcf
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xd0 - 0xdf
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xe0 - 0xef
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xf0 - 0xff
};
const char kHexCharLookup[0x10] = {
'0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', 'A', 'B', 'C', 'D', 'E', 'F',
};
const char kCharToHexLookup[8] = {
0, // 0x00 - 0x1f
'0', // 0x20 - 0x3f: digits 0 - 9 are 0x30 - 0x39
'A' - 10, // 0x40 - 0x5f: letters A - F are 0x41 - 0x46
'a' - 10, // 0x60 - 0x7f: letters a - f are 0x61 - 0x66
0, // 0x80 - 0x9F
0, // 0xA0 - 0xBF
0, // 0xC0 - 0xDF
0, // 0xE0 - 0xFF
};
const char16_t kUnicodeReplacementCharacter = 0xfffd;
void AppendStringOfType(const char* source, int length,
SharedCharTypes type,
CanonOutput* output) {
DoAppendStringOfType<char, unsigned char>(source, length, type, output);
}
void AppendStringOfType(const char16_t* source,
int length,
SharedCharTypes type,
CanonOutput* output) {
DoAppendStringOfType<char16_t, char16_t>(source, length, type, output);
}
bool ReadUTFChar(const char* str, int* begin, int length,
unsigned* code_point_out) {
// This depends on ints and int32s being the same thing. If they're not, it
// will fail to compile.
// TODO(mmenke): This should probably be fixed.
if (!base::ReadUnicodeCharacter(str, length, begin, code_point_out) ||
!base::IsValidCharacter(*code_point_out)) {
*code_point_out = kUnicodeReplacementCharacter;
return false;
}
return true;
}
bool ReadUTFChar(const char16_t* str,
int* begin,
int length,
unsigned* code_point_out) {
// This depends on ints and int32s being the same thing. If they're not, it
// will fail to compile.
// TODO(mmenke): This should probably be fixed.
if (!base::ReadUnicodeCharacter(str, length, begin, code_point_out) ||
!base::IsValidCharacter(*code_point_out)) {
*code_point_out = kUnicodeReplacementCharacter;
return false;
}
return true;
}
void AppendInvalidNarrowString(const char* spec, int begin, int end,
CanonOutput* output) {
DoAppendInvalidNarrowString<char, unsigned char>(spec, begin, end, output);
}
void AppendInvalidNarrowString(const char16_t* spec,
int begin,
int end,
CanonOutput* output) {
DoAppendInvalidNarrowString<char16_t, char16_t>(spec, begin, end, output);
}
bool ConvertUTF16ToUTF8(const char16_t* input,
int input_len,
CanonOutput* output) {
bool success = true;
for (int i = 0; i < input_len; i++) {
unsigned code_point;
success &= ReadUTFChar(input, &i, input_len, &code_point);
AppendUTF8Value(code_point, output);
}
return success;
}
bool ConvertUTF8ToUTF16(const char* input,
int input_len,
CanonOutputT<char16_t>* output) {
bool success = true;
for (int i = 0; i < input_len; i++) {
unsigned code_point;
success &= ReadUTFChar(input, &i, input_len, &code_point);
AppendUTF16Value(code_point, output);
}
return success;
}
void SetupOverrideComponents(const char* base,
const Replacements<char>& repl,
URLComponentSource<char>* source,
Parsed* parsed) {
// Get the source and parsed structures of the things we are replacing.
const URLComponentSource<char>& repl_source = repl.sources();
const Parsed& repl_parsed = repl.components();
DoOverrideComponent(repl_source.scheme, repl_parsed.scheme,
&source->scheme, &parsed->scheme);
DoOverrideComponent(repl_source.username, repl_parsed.username,
&source->username, &parsed->username);
DoOverrideComponent(repl_source.password, repl_parsed.password,
&source->password, &parsed->password);
// Our host should be empty if not present, so override the default setup.
DoOverrideComponent(repl_source.host, repl_parsed.host,
&source->host, &parsed->host);
if (parsed->host.len == -1)
parsed->host.len = 0;
DoOverrideComponent(repl_source.port, repl_parsed.port,
&source->port, &parsed->port);
DoOverrideComponent(repl_source.path, repl_parsed.path,
&source->path, &parsed->path);
DoOverrideComponent(repl_source.query, repl_parsed.query,
&source->query, &parsed->query);
DoOverrideComponent(repl_source.ref, repl_parsed.ref,
&source->ref, &parsed->ref);
}
bool SetupUTF16OverrideComponents(const char* base,
const Replacements<char16_t>& repl,
CanonOutput* utf8_buffer,
URLComponentSource<char>* source,
Parsed* parsed) {
bool success = true;
// Get the source and parsed structures of the things we are replacing.
const URLComponentSource<char16_t>& repl_source = repl.sources();
const Parsed& repl_parsed = repl.components();
success &= PrepareUTF16OverrideComponent(
repl_source.scheme, repl_parsed.scheme,
utf8_buffer, &parsed->scheme);
success &= PrepareUTF16OverrideComponent(
repl_source.username, repl_parsed.username,
utf8_buffer, &parsed->username);
success &= PrepareUTF16OverrideComponent(
repl_source.password, repl_parsed.password,
utf8_buffer, &parsed->password);
success &= PrepareUTF16OverrideComponent(
repl_source.host, repl_parsed.host,
utf8_buffer, &parsed->host);
success &= PrepareUTF16OverrideComponent(
repl_source.port, repl_parsed.port,
utf8_buffer, &parsed->port);
success &= PrepareUTF16OverrideComponent(
repl_source.path, repl_parsed.path,
utf8_buffer, &parsed->path);
success &= PrepareUTF16OverrideComponent(
repl_source.query, repl_parsed.query,
utf8_buffer, &parsed->query);
success &= PrepareUTF16OverrideComponent(
repl_source.ref, repl_parsed.ref,
utf8_buffer, &parsed->ref);
// PrepareUTF16OverrideComponent will not have set the data pointer since the
// buffer could be resized, invalidating the pointers. We set the data
// pointers for affected components now that the buffer is finalized.
if (repl_source.scheme) source->scheme = utf8_buffer->data();
if (repl_source.username) source->username = utf8_buffer->data();
if (repl_source.password) source->password = utf8_buffer->data();
if (repl_source.host) source->host = utf8_buffer->data();
if (repl_source.port) source->port = utf8_buffer->data();
if (repl_source.path) source->path = utf8_buffer->data();
if (repl_source.query) source->query = utf8_buffer->data();
if (repl_source.ref) source->ref = utf8_buffer->data();
return success;
}
#ifndef WIN32
int _itoa_s(int value, char* buffer, size_t size_in_chars, int radix) {
const char* format_str;
if (radix == 10)
format_str = "%d";
else if (radix == 16)
format_str = "%x";
else
return EINVAL;
int written = snprintf(buffer, size_in_chars, format_str, value);
if (static_cast<size_t>(written) >= size_in_chars) {
// Output was truncated, or written was negative.
return EINVAL;
}
return 0;
}
int _itow_s(int value, char16_t* buffer, size_t size_in_chars, int radix) {
if (radix != 10)
return EINVAL;
// No more than 12 characters will be required for a 32-bit integer.
// Add an extra byte for the terminating null.
char temp[13];
int written = snprintf(temp, sizeof(temp), "%d", value);
if (static_cast<size_t>(written) >= size_in_chars) {
// Output was truncated, or written was negative.
return EINVAL;
}
for (int i = 0; i < written; ++i) {
buffer[i] = static_cast<char16_t>(temp[i]);
}
buffer[written] = '\0';
return 0;
}
#endif // !WIN32
} // namespace url