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 "util/strings/utf8.h"
18 
19 namespace libtextclassifier2 {
IsValidUTF8(const char * src,int size)20 bool IsValidUTF8(const char *src, int size) {
21   for (int i = 0; i < size;) {
22     // Unexpected trail byte.
23     if (IsTrailByte(src[i])) {
24       return false;
25     }
26 
27     const int num_codepoint_bytes = GetNumBytesForUTF8Char(&src[i]);
28     if (num_codepoint_bytes <= 0 || i + num_codepoint_bytes > size) {
29       return false;
30     }
31 
32     // Check that remaining bytes in the codepoint are trailing bytes.
33     i++;
34     for (int k = 1; k < num_codepoint_bytes; k++, i++) {
35       if (!IsTrailByte(src[i])) {
36         return false;
37       }
38     }
39   }
40   return true;
41 }
42 }  // namespace libtextclassifier2
43