uchar.h

   1 /*
   2  * Copyright 2004-2005 Timo Hirvonen
   3  *
   4  * This program is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU General Public License as
   6  * published by the Free Software Foundation; either version 2 of the
   7  * License, or (at your option) any later version.
   8  *
   9  * This program is distributed in the hope that it will be useful, but
  10  * WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12  * General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU General Public License
  15  * along with this program; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  17  * 02111-1307, USA.
  18  */
  19
  20 #ifndef _UCHAR_H
  21 #define _UCHAR_H
  22
  23 typedef unsigned int uchar;
  24
  25 extern const char hex_tab[16];
  26
  27 /*
  28  * Invalid bytes are or'ed with this
  29  * for example 0xff -> 0x100000ff
  30  */
  31 #define U_INVALID_MASK 0x10000000U
  32
  33 /*
  34  * @uch  potential unicode character
  35  *
  36  * Returns 1 if @uch is valid unicode character, 0 otherwise
  37  */
  38 static inline int u_is_unicode(uchar uch)
  39 {
  40         return uch <= 0x0010ffffU;
  41 }
  42
  43 /*
  44  * Returns size of @uch in bytes
  45  */
  46 static inline int u_char_size(uchar uch)
  47 {
  48         if (uch <= 0x0000007fU) {
  49                 return 1;
  50         } else if (uch <= 0x000007ffU) {
  51                 return 2;
  52         } else if (uch <= 0x0000ffffU) {
  53                 return 3;
  54         } else if (uch <= 0x0010ffffU) {
  55                 return 4;
  56         } else {
  57                 return 1;
  58         }
  59 }
  60
  61 /*
  62  * Returns width of @uch (normally 1 or 2, 4 for invalid chars (<xx>))
  63  */
  64 extern int u_char_width(uchar uch);
  65
  66 /*
  67  * @str  any null-terminated string
  68  *
  69  * Returns 1 if @str is valid UTF-8 string, 0 otherwise.
  70  */
  71 extern int u_is_valid(const char *str);
  72
  73 /*
  74  * @str  null-terminated UTF-8 string
  75  *
  76  * Retuns length of @str in UTF-8 characters.
  77  */
  78 extern int u_strlen(const char *str);
  79
  80 /*
  81  * @str  null-terminated UTF-8 string
  82  *
  83  * Retuns width of @str.
  84  */
  85 extern int u_str_width(const char *str);
  86
  87 /*
  88  * @str  null-terminated UTF-8 string
  89  * @len  number of characters to measure
  90  *
  91  * Retuns width of the first @len characters in @str.
  92  */
  93 extern int u_str_nwidth(const char *str, int len);
  94
  95 extern void u_prev_char_pos(const char *str, int *idx);
  96
  97 /*
  98  * @str  null-terminated UTF-8 string
  99  * @idx  pointer to byte index in @str (not UTF-8 character index!)
 100  * @uch  pointer to returned unicode character
 101  */
 102 extern void u_get_char(const char *str, int *idx, uchar *uch);
 103
 104 /*
 105  * @str  destination buffer
 106  * @idx  pointer to byte index in @str (not UTF-8 character index!)
 107  * @uch  unicode character
 108  */
 109 extern void u_set_char_raw(char *str, int *idx, uchar uch);
 110 extern void u_set_char(char *str, int *idx, uchar uch);
 111
 112 /*
 113  * @dst    destination buffer
 114  * @src    null-terminated UTF-8 string
 115  * @width  how much to copy
 116  *
 117  * Copies at most @count characters, less if null byte was hit.
 118  * Null byte is _never_ copied.
 119  * Actual width of copied characters is stored to @width.
 120  *
 121  * Returns number of _bytes_ copied.
 122  */
 123 extern int u_copy_chars(char *dst, const char *src, int *width);
 124
 125 /*
 126  * @str    null-terminated UTF-8 string, must be long enough
 127  * @width  how much to skip
 128  *
 129  * Skips @count UTF-8 characters.
 130  * Total width of skipped characters is stored to @width.
 131  * Returned @width can be the given @width + 1 if the last skipped
 132  * character was double width.
 133  *
 134  * Returns number of _bytes_ skipped.
 135  */
 136 extern int u_skip_chars(const char *str, int *width);
 137
 138 extern int u_strcasecmp(const char *a, const char *b);
 139 extern int u_strncasecmp(const char *a, const char *b, int len);
 140 extern char *u_strcasestr(const char *haystack, const char *needle);
 141
 142 static inline char *u_strcasestr_filename(const char *haystack, const char *needle)
 143 {
 144         return u_strcasestr(haystack, needle);
 145 }
 146
 147 #endif