1 #ifndef _UTFH_ 2 #define _UTFH_ 1 3 4 #include <stdint.h> 5 6 typedef signed int Rune; /* Code-point values in Unicode 4.0 are 21 bits wide.*/ 7 8 enum 9 { 10 UTFmax = 4, /* maximum bytes per rune */ 11 Runesync = 0x80, /* cannot represent part of a UTF sequence (<) */ 12 Runeself = 0x80, /* rune and UTF sequences are the same (<) */ 13 Runeerror = 0xFFFD, /* decoding error in UTF */ 14 Runemax = 0x10FFFF, /* maximum rune value */ 15 }; 16 17 #ifdef __cplusplus 18 extern "C" { 19 #endif 20 21 /* 22 * rune routines 23 */ 24 25 /* 26 * These routines were written by Rob Pike and Ken Thompson 27 * and first appeared in Plan 9. 28 * SEE ALSO 29 * utf (7) 30 * tcs (1) 31 */ 32 33 // runetochar copies (encodes) one rune, pointed to by r, to at most 34 // UTFmax bytes starting at s and returns the number of bytes generated. 35 36 int runetochar(char* s, const Rune* r); 37 38 39 // chartorune copies (decodes) at most UTFmax bytes starting at s to 40 // one rune, pointed to by r, and returns the number of bytes consumed. 41 // If the input is not exactly in UTF format, chartorune will set *r 42 // to Runeerror and return 1. 43 // 44 // Note: There is no special case for a "null-terminated" string. A 45 // string whose first byte has the value 0 is the UTF8 encoding of the 46 // Unicode value 0 (i.e., ASCII NULL). A byte value of 0 is illegal 47 // anywhere else in a UTF sequence. 48 49 int chartorune(Rune* r, const char* s); 50 51 52 // charntorune is like chartorune, except that it will access at most 53 // n bytes of s. If the UTF sequence is incomplete within n bytes, 54 // charntorune will set *r to Runeerror and return 0. If it is complete 55 // but not in UTF format, it will set *r to Runeerror and return 1. 56 // 57 // Added 2004-09-24 by Wei-Hwa Huang 58 59 int charntorune(Rune* r, const char* s, int n); 60 61 // isvalidcharntorune(str, n, r, consumed) 62 // is a convenience function that calls "*consumed = charntorune(r, str, n)" 63 // and returns an int (logically boolean) indicating whether the first 64 // n bytes of str was a valid and complete UTF sequence. 65 66 int isvalidcharntorune(const char* str, int n, Rune* r, int* consumed); 67 68 // runelen returns the number of bytes required to convert r into UTF. 69 70 int runelen(Rune r); 71 72 73 // runenlen returns the number of bytes required to convert the n 74 // runes pointed to by r into UTF. 75 76 int runenlen(const Rune* r, int n); 77 78 79 // fullrune returns 1 if the string s of length n is long enough to be 80 // decoded by chartorune, and 0 otherwise. This does not guarantee 81 // that the string contains a legal UTF encoding. This routine is used 82 // by programs that obtain input one byte at a time and need to know 83 // when a full rune has arrived. 84 85 int fullrune(const char* s, int n); 86 87 // The following routines are analogous to the corresponding string 88 // routines with "utf" substituted for "str", and "rune" substituted 89 // for "chr". 90 91 // utflen returns the number of runes that are represented by the UTF 92 // string s. (cf. strlen) 93 94 int utflen(const char* s); 95 96 97 // utfnlen returns the number of complete runes that are represented 98 // by the first n bytes of the UTF string s. If the last few bytes of 99 // the string contain an incompletely coded rune, utfnlen will not 100 // count them; in this way, it differs from utflen, which includes 101 // every byte of the string. (cf. strnlen) 102 103 int utfnlen(const char* s, long n); 104 105 106 // utfrune returns a pointer to the first occurrence of rune r in the 107 // UTF string s, or 0 if r does not occur in the string. The NULL 108 // byte terminating a string is considered to be part of the string s. 109 // (cf. strchr) 110 111 const char* utfrune(const char* s, Rune r); 112 113 114 // utfrrune returns a pointer to the last occurrence of rune r in the 115 // UTF string s, or 0 if r does not occur in the string. The NULL 116 // byte terminating a string is considered to be part of the string s. 117 // (cf. strrchr) 118 119 const char* utfrrune(const char* s, Rune r); 120 121 122 // utfutf returns a pointer to the first occurrence of the UTF string 123 // s2 as a UTF substring of s1, or 0 if there is none. If s2 is the 124 // null string, utfutf returns s1. (cf. strstr) 125 126 const char* utfutf(const char* s1, const char* s2); 127 128 129 // utfecpy copies UTF sequences until a null sequence has been copied, 130 // but writes no sequences beyond es1. If any sequences are copied, 131 // s1 is terminated by a null sequence, and a pointer to that sequence 132 // is returned. Otherwise, the original s1 is returned. (cf. strecpy) 133 134 char* utfecpy(char *s1, char *es1, const char *s2); 135 136 137 138 // These functions are rune-string analogues of the corresponding 139 // functions in strcat (3). 140 // 141 // These routines first appeared in Plan 9. 142 // SEE ALSO 143 // memmove (3) 144 // rune (3) 145 // strcat (2) 146 // 147 // BUGS: The outcome of overlapping moves varies among implementations. 148 149 Rune* runestrcat(Rune* s1, const Rune* s2); 150 Rune* runestrncat(Rune* s1, const Rune* s2, long n); 151 152 const Rune* runestrchr(const Rune* s, Rune c); 153 154 int runestrcmp(const Rune* s1, const Rune* s2); 155 int runestrncmp(const Rune* s1, const Rune* s2, long n); 156 157 Rune* runestrcpy(Rune* s1, const Rune* s2); 158 Rune* runestrncpy(Rune* s1, const Rune* s2, long n); 159 Rune* runestrecpy(Rune* s1, Rune* es1, const Rune* s2); 160 161 Rune* runestrdup(const Rune* s); 162 163 const Rune* runestrrchr(const Rune* s, Rune c); 164 long runestrlen(const Rune* s); 165 const Rune* runestrstr(const Rune* s1, const Rune* s2); 166 167 168 169 // The following routines test types and modify cases for Unicode 170 // characters. Unicode defines some characters as letters and 171 // specifies three cases: upper, lower, and title. Mappings among the 172 // cases are also defined, although they are not exhaustive: some 173 // upper case letters have no lower case mapping, and so on. Unicode 174 // also defines several character properties, a subset of which are 175 // checked by these routines. These routines are based on Unicode 176 // version 3.0.0. 177 // 178 // NOTE: The routines are implemented in C, so the boolean functions 179 // (e.g., isupperrune) return 0 for false and 1 for true. 180 // 181 // 182 // toupperrune, tolowerrune, and totitlerune are the Unicode case 183 // mappings. These routines return the character unchanged if it has 184 // no defined mapping. 185 186 Rune toupperrune(Rune r); 187 Rune tolowerrune(Rune r); 188 Rune totitlerune(Rune r); 189 190 191 // isupperrune tests for upper case characters, including Unicode 192 // upper case letters and targets of the toupper mapping. islowerrune 193 // and istitlerune are defined analogously. 194 195 int isupperrune(Rune r); 196 int islowerrune(Rune r); 197 int istitlerune(Rune r); 198 199 200 // isalpharune tests for Unicode letters; this includes ideographs in 201 // addition to alphabetic characters. 202 203 int isalpharune(Rune r); 204 205 206 // isdigitrune tests for digits. Non-digit numbers, such as Roman 207 // numerals, are not included. 208 209 int isdigitrune(Rune r); 210 211 212 // isideographicrune tests for ideographic characters and numbers, as 213 // defined by the Unicode standard. 214 215 int isideographicrune(Rune r); 216 217 218 // isspacerune tests for whitespace characters, including "C" locale 219 // whitespace, Unicode defined whitespace, and the "zero-width 220 // non-break space" character. 221 222 int isspacerune(Rune r); 223 224 225 // (The comments in this file were copied from the manpage files rune.3, 226 // isalpharune.3, and runestrcat.3. Some formatting changes were also made 227 // to conform to Google style. /JRM 11/11/05) 228 229 #ifdef __cplusplus 230 } 231 #endif 232 233 #endif 234