1 // Copyright 2017 Google Inc. All rights reserved.
2 //
3 // Licensed under the Apache License, Version 2.0 (the "License");
4 // you may not use this file except in compliance with the License.
5 // You may obtain a copy of the License at
6 //
7 // http://www.apache.org/licenses/LICENSE-2.0
8 //
9 // Unless required by applicable law or agreed to in writing, software
10 // distributed under the License is distributed on an "AS IS" BASIS,
11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 // See the License for the specific language governing permissions and
13 // limitations under the License.
14
15 #include "src/utf8_fix.h"
16
17 #include <algorithm>
18 #include <cassert>
19
20 namespace protobuf_mutator {
21
22 namespace {
23
StoreCode(char * e,char32_t code,uint8_t size,uint8_t prefix)24 void StoreCode(char* e, char32_t code, uint8_t size, uint8_t prefix) {
25 while (--size) {
26 *(--e) = 0x80 | (code & 0x3F);
27 code >>= 6;
28 }
29 *(--e) = prefix | code;
30 }
31
FixCode(char * b,const char * e,RandomEngine * random)32 char* FixCode(char* b, const char* e, RandomEngine* random) {
33 const char* start = b;
34 assert(b < e);
35
36 e = std::min<const char*>(e, b + 4);
37 char32_t c = *b++;
38 for (; b < e && (*b & 0xC0) == 0x80; ++b) {
39 c = (c << 6) + (*b & 0x3F);
40 }
41 uint8_t size = b - start;
42 switch (size) {
43 case 1:
44 c &= 0x7F;
45 StoreCode(b, c, size, 0);
46 break;
47 case 2:
48 c &= 0x7FF;
49 if (c < 0x80) {
50 // Use uint32_t because uniform_int_distribution does not support
51 // char32_t on Windows.
52 c = std::uniform_int_distribution<uint32_t>(0x80, 0x7FF)(*random);
53 }
54 StoreCode(b, c, size, 0xC0);
55 break;
56 case 3:
57 c &= 0xFFFF;
58
59 // [0xD800, 0xE000) are reserved for UTF-16 surrogate halves.
60 if (c < 0x800 || (c >= 0xD800 && c < 0xE000)) {
61 uint32_t halves = 0xE000 - 0xD800;
62 c = std::uniform_int_distribution<uint32_t>(0x800,
63 0xFFFF - halves)(*random);
64 if (c >= 0xD800) c += halves;
65 }
66 StoreCode(b, c, size, 0xE0);
67 break;
68 case 4:
69 c &= 0x1FFFFF;
70 if (c < 0x10000 || c > 0x10FFFF) {
71 c = std::uniform_int_distribution<uint32_t>(0x10000, 0x10FFFF)(*random);
72 }
73 StoreCode(b, c, size, 0xF0);
74 break;
75 default:
76 assert(false && "Unexpected size of UTF-8 sequence");
77 }
78 return b;
79 }
80
81 } // namespace
82
FixUtf8String(std::string * str,RandomEngine * random)83 void FixUtf8String(std::string* str, RandomEngine* random) {
84 if (str->empty()) return;
85 char* b = &(*str)[0];
86 const char* e = b + str->size();
87 while (b < e) {
88 b = FixCode(b, e, random);
89 }
90 }
91
92 } // namespace protobuf_mutator
93