src/utf8.c

   1 /*
   2  * Copyright (C) the libgit2 contributors. All rights reserved.
   3  *
   4  * This file is part of libgit2, distributed under the GNU GPL v2 with
   5  * a Linking Exception. For full terms see the included COPYING file.
   6  */
   7
   8 #include "utf8.h"
   9
  10 #include "common.h"
  11
  12 /*
  13  * git_utf8_iterate is taken from the utf8proc project,
  14  * http://www.public-software-group.org/utf8proc
  15  *
  16  * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
  17  *
  18  * Permission is hereby granted, free of charge, to any person obtaining a
  19  * copy of this software and associated documentation files (the ""Software""),
  20  * to deal in the Software without restriction, including without limitation
  21  * the rights to use, copy, modify, merge, publish, distribute, sublicense,
  22  * and/or sell copies of the Software, and to permit persons to whom the
  23  * Software is furnished to do so, subject to the following conditions:
  24  *
  25  * The above copyright notice and this permission notice shall be included in
  26  * all copies or substantial portions of the Software.
  27  *
  28  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  29  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  30  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  31  * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  32  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  33  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  34  * DEALINGS IN THE SOFTWARE.
  35  */
  36
  37 static const uint8_t utf8proc_utf8class[256] = {
  38         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  39         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  40         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  41         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  42         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  43         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  44         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  45         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  46         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  47         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  48         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  49         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  50         2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  51         2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  52         3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
  53         4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0
  54 };
  55
  56 static int utf8_charlen(const uint8_t *str, size_t str_len)
  57 {
  58         uint8_t length;
  59         size_t i;
  60
  61         length = utf8proc_utf8class[str[0]];
  62         if (!length)
  63                 return -1;
  64
  65         if (str_len > 0 && length > str_len)
  66                 return -1;
  67
  68         for (i = 1; i < length; i++) {
  69                 if ((str[i] & 0xC0) != 0x80)
  70                         return -1;
  71         }
  72
  73         return (int)length;
  74 }
  75
  76 int git_utf8_iterate(uint32_t *out, const char *_str, size_t str_len)
  77 {
  78         const uint8_t *str = (const uint8_t *)_str;
  79         uint32_t uc = 0;
  80         int length;
  81
  82         *out = 0;
  83
  84         if ((length = utf8_charlen(str, str_len)) < 0)
  85                 return -1;
  86
  87         switch (length) {
  88                 case 1:
  89                         uc = str[0];
  90                         break;
  91                 case 2:
  92                         uc = ((str[0] & 0x1F) <<  6) + (str[1] & 0x3F);
  93                         if (uc < 0x80) uc = -1;
  94                         break;
  95                 case 3:
  96                         uc = ((str[0] & 0x0F) << 12) + ((str[1] & 0x3F) <<  6)
  97                                 + (str[2] & 0x3F);
  98                         if (uc < 0x800 || (uc >= 0xD800 && uc < 0xE000) ||
  99                                         (uc >= 0xFDD0 && uc < 0xFDF0)) uc = -1;
 100                         break;
 101                 case 4:
 102                         uc = ((str[0] & 0x07) << 18) + ((str[1] & 0x3F) << 12)
 103                                 + ((str[2] & 0x3F) <<  6) + (str[3] & 0x3F);
 104                         if (uc < 0x10000 || uc >= 0x110000) uc = -1;
 105                         break;
 106                 default:
 107                         return -1;
 108         }
 109
 110         if ((uc & 0xFFFF) >= 0xFFFE)
 111                 return -1;
 112
 113         *out = uc;
 114         return length;
 115 }
 116
 117 size_t git_utf8_char_length(const char *_str, size_t str_len)
 118 {
 119         const uint8_t *str = (const uint8_t *)_str;
 120         size_t offset = 0, count = 0;
 121
 122         while (offset < str_len) {
 123                 int length = utf8_charlen(str + offset, str_len - offset);
 124
 125                 if (length < 0)
 126                         length = 1;
 127
 128                 offset += length;
 129                 count++;
 130         }
 131
 132         return count;
 133 }
 134
 135 size_t git_utf8_valid_buf_length(const char *_str, size_t str_len)
 136 {
 137         const uint8_t *str = (const uint8_t *)_str;
 138         size_t offset = 0;
 139
 140         while (offset < str_len) {
 141                 int length = utf8_charlen(str + offset, str_len - offset);
 142
 143                 if (length < 0)
 144                         break;
 145
 146                 offset += length;
 147         }
 148
 149         return offset;
 150 }