cmus/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 /*
  26  * @byte  any byte in UTF-8 string
  27  *
  28  * Returns 1 if @byte is the first byte of unicode char, 0 otherwise
  29  */
  30 static inline int u_is_first_byte(unsigned char byte)
  31 {
  32         return byte >> 6 != 2;
  33 }
  34
  35 /*
  36  * @uch  potential unicode character
  37  *
  38  * Returns 1 if @uch is valid unicode character, 0 otherwise
  39  */
  40 static inline int u_is_unicode(uchar uch)
  41 {
  42         return uch <= 0x0010ffffU;
  43 }
  44
  45 /*
  46  * Returns size of @uch in bytes
  47  */
  48 static inline int u_char_size(uchar uch)
  49 {
  50         if (uch <= 0x0000007fU) {
  51                 return 1;
  52         } else if (uch <= 0x000007ffU) {
  53                 return 2;
  54         } else if (uch <= 0x0000ffffU) {
  55                 return 3;
  56         } else if (uch <= 0x0010ffffU) {
  57                 return 4;
  58         } else {
  59                 return -1;
  60         }
  61 }
  62
  63 /*
  64  * Returns width of @uch (1 or 2)
  65  */
  66 extern int u_char_width(uchar uch);
  67
  68 /*
  69  * @str  any null-terminated string
  70  *
  71  * Returns 1 if @str is valid UTF-8 string, 0 otherwise.
  72  */
  73 extern int u_is_valid(const char *str);
  74
  75 /*
  76  * @str  null-terminated UTF-8 string
  77  *
  78  * Retuns length of @str in UTF-8 characters.
  79  */
  80 extern int u_strlen(const char *str);
  81
  82 /*
  83  * @str  null-terminated UTF-8 string
  84  *
  85  * Retuns width of @str.
  86  */
  87 extern int u_str_width(const char *str);
  88
  89 /*
  90  * @str  null-terminated UTF-8 string
  91  * @len  number of characters to measure
  92  *
  93  * Retuns width of the first @len characters in @str.
  94  */
  95 extern int u_str_nwidth(const char *str, int len);
  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(char *str, int *idx, uchar uch);
 110
 111 /*
 112  * @dst    destination buffer
 113  * @src    null-terminated UTF-8 string
 114  * @width  how much to copy
 115  *
 116  * Copies at most @count characters, less if null byte was hit.
 117  * Null byte is _never_ copied.
 118  * Actual width of copied characters is stored to @width.
 119  *
 120  * Returns number of _bytes_ copied.
 121  */
 122 extern int u_copy_chars(char *dst, const char *src, int *width);
 123
 124 /*
 125  * @str    null-terminated UTF-8 string, must be long enough
 126  * @width  how much to skip
 127  *
 128  * Skips @count UTF-8 characters.
 129  * Total width of skipped characters is stored to @width.
 130  * Returned @width can be the given @width + 1 if the last skipped
 131  * character was double width.
 132  *
 133  * Returns number of _bytes_ skipped.
 134  */
 135 extern int u_skip_chars(const char *str, int *width);
 136
 137 extern int u_strcasecmp(const char *a, const char *b);
 138 extern int u_strncasecmp(const char *a, const char *b, int len);
 139 extern char *u_strcasestr(const char *text, const char *part);
 140
 141 /* @text  filename (locale's encoding)
 142  * @part  UTF-8 string
 143  */
 144 extern char *u_strcasestr_filename(const char *text, const char *part);
 145
 146 #endif