1 /*
2 * Copyright (C) 2017 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17 #include "slicer/dex_format.h"
18
19 namespace dex {
20
21 // Retrieve the next UTF-16 character from a UTF-8 string.
22 // Advances "*pUtf8Ptr" to the start of the next character.
23 //
24 // NOTE: If a string is corrupted by dropping a '\0' in the middle
25 // of a 3-byte sequence, you can end up overrunning the buffer with
26 // reads (and possibly with the writes if the length was computed and
27 // cached before the damage). For performance reasons, this function
28 // assumes that the string being parsed is known to be valid (e.g., by
29 // already being verified).
GetUtf16FromUtf8(const char ** pUtf8Ptr)30 static u2 GetUtf16FromUtf8(const char** pUtf8Ptr) {
31 u4 one = *(*pUtf8Ptr)++;
32 if ((one & 0x80) != 0) {
33 // two- or three-byte encoding
34 u4 two = *(*pUtf8Ptr)++;
35 if ((one & 0x20) != 0) {
36 // three-byte encoding
37 u4 three = *(*pUtf8Ptr)++;
38 return ((one & 0x0f) << 12) | ((two & 0x3f) << 6) | (three & 0x3f);
39 } else {
40 // two-byte encoding
41 return ((one & 0x1f) << 6) | (two & 0x3f);
42 }
43 } else {
44 // one-byte encoding
45 return one;
46 }
47 }
48
Utf8Cmp(const char * s1,const char * s2)49 int Utf8Cmp(const char* s1, const char* s2) {
50 for (;;) {
51 if (*s1 == '\0') {
52 if (*s2 == '\0') {
53 return 0;
54 }
55 return -1;
56 } else if (*s2 == '\0') {
57 return 1;
58 }
59
60 int utf1 = GetUtf16FromUtf8(&s1);
61 int utf2 = GetUtf16FromUtf8(&s2);
62 int diff = utf1 - utf2;
63
64 if (diff != 0) {
65 return diff;
66 }
67 }
68 }
69
70 } // namespace dex
71