code.delx.au - pulseaudio/blob - src/polyp/utf8.c

   1 /* $Id */
   2
   3 /* This file is based on the GLIB utf8 validation functions. The
   4  * original license text follows. */
   5
   6 /* gutf8.c - Operations on UTF-8 strings.
   7  *
   8  * Copyright (C) 1999 Tom Tromey
   9  * Copyright (C) 2000 Red Hat, Inc.
  10  *
  11  * This library is free software; you can redistribute it and/or
  12  * modify it under the terms of the GNU Lesser General Public
  13  * License as published by the Free Software Foundation; either
  14  * version 2 of the License, or (at your option) any later version.
  15  *
  16  * This library is distributed in the hope that it will be useful,
  17  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  18  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  19  * Lesser General Public License for more details.
  20  *
  21  * You should have received a copy of the GNU Lesser General Public
  22  * License along with this library; if not, write to the
  23  * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  24  * Boston, MA 02111-1307, USA.
  25  */
  26
  27 #ifdef HAVE_CONFIG_H
  28 #include <config.h>
  29 #endif
  30
  31 #include <assert.h>
  32 #include <stdlib.h>
  33 #include <inttypes.h>
  34 #include <string.h>
  35
  36 #include "utf8.h"
  37 #include "xmalloc.h"
  38
  39 #define FILTER_CHAR '_'
  40
  41 static inline int is_unicode_valid(uint32_t ch) {
  42     if (ch >= 0x110000) /* End of unicode space */
  43         return 0;
  44     if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */
  45         return 0;
  46     if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */
  47         return 0;
  48     if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */
  49         return 0;
  50     return 1;
  51 }
  52
  53 static inline int is_continuation_char(uint8_t ch) {
  54     if ((ch & 0xc0) != 0x80) /* 10xxxxxx */
  55         return 0;
  56     return 1;
  57 }
  58
  59 static inline void merge_continuation_char(uint32_t *u_ch, uint8_t ch) {
  60     *u_ch <<= 6;
  61     *u_ch |= ch & 0x3f;
  62 }
  63
  64 static char* utf8_validate(const char *str, char *output) {
  65     uint32_t val = 0;
  66     uint32_t min = 0;
  67     const uint8_t *p, *last;
  68     int size;
  69     uint8_t *o;
  70
  71     o = (uint8_t*) output;
  72     for (p = (const uint8_t*) str; *p; p++) {
  73         if (*p < 128) {
  74             if (o)
  75                 *o = *p;
  76         } else {
  77             last = p;
  78
  79             if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */
  80                 size = 2;
  81                 min = 128;
  82                 val = *p & 0x1e;
  83                 goto ONE_REMAINING;
  84             } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/
  85                 size = 3;
  86                 min = (1 << 11);
  87                 val = *p & 0x0f;
  88                 goto TWO_REMAINING;
  89             } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */
  90                 size = 4;
  91                 min = (1 << 16);
  92                 val = *p & 0x07;
  93             } else {
  94                 size = 1;
  95                 goto error;
  96             }
  97
  98             p++;
  99             if (!is_continuation_char(*p))
 100                 goto error;
 101             merge_continuation_char(&val, *p);
 102
 103 TWO_REMAINING:
 104             p++;
 105             if (!is_continuation_char(*p))
 106                 goto error;
 107             merge_continuation_char(&val, *p);
 108
 109 ONE_REMAINING:
 110             p++;
 111             if (!is_continuation_char(*p))
 112                 goto error;
 113             merge_continuation_char(&val, *p);
 114
 115             if (val < min)
 116                 goto error;
 117
 118             if (!is_unicode_valid(val))
 119                 goto error;
 120
 121             if (o) {
 122                 memcpy(o, last, size);
 123                 o += size - 1;
 124             }
 125
 126             if (o)
 127                 o++;
 128
 129             continue;
 130
 131 error:
 132             if (o) {
 133                 *o = FILTER_CHAR;
 134                 p = last; /* We retry at the next character */
 135             } else
 136                 goto failure;
 137         }
 138
 139         if (o)
 140             o++;
 141     }
 142
 143     if (o) {
 144         *o = '\0';
 145         return output;
 146     }
 147
 148     return (char*) str;
 149
 150 failure:
 151     return NULL;
 152 }
 153
 154 const char* pa_utf8_valid (const char *str) {
 155     return utf8_validate(str, NULL);
 156 }
 157
 158 char* pa_utf8_filter (const char *str) {
 159     char *new_str;
 160
 161     new_str = pa_xnew(char, strlen(str) + 1);
 162
 163     return utf8_validate(str, new_str);
 164 }