sbase

suckless unix tools
git clone git://git.2f30.org/sbase
Log | Files | Refs | README | LICENSE

rune.c (4243B)


      1 /* MIT/X Consortium Copyright (c) 2012 Connor Lane Smith <cls@lubutu.com>
      2  *
      3  * Permission is hereby granted, free of charge, to any person obtaining a
      4  * copy of this software and associated documentation files (the "Software"),
      5  * to deal in the Software without restriction, including without limitation
      6  * the rights to use, copy, modify, merge, publish, distribute, sublicense,
      7  * and/or sell copies of the Software, and to permit persons to whom the
      8  * Software is furnished to do so, subject to the following conditions:
      9  *
     10  * The above copyright notice and this permission notice shall be included in
     11  * all copies or substantial portions of the Software.
     12  *
     13  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
     14  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
     15  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
     16  * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
     17  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
     18  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
     19  * DEALINGS IN THE SOFTWARE.
     20  */
     21 #include "../utf.h"
     22 
     23 #define MIN(x,y)  ((x) < (y) ? (x) : (y))
     24 
     25 #define UTFSEQ(x) ((((x) & 0x80) == 0x00) ? 1 /* 0xxxxxxx */ \
     26                  : (((x) & 0xC0) == 0x80) ? 0 /* 10xxxxxx */ \
     27                  : (((x) & 0xE0) == 0xC0) ? 2 /* 110xxxxx */ \
     28                  : (((x) & 0xF0) == 0xE0) ? 3 /* 1110xxxx */ \
     29                  : (((x) & 0xF8) == 0xF0) ? 4 /* 11110xxx */ \
     30                  : (((x) & 0xFC) == 0xF8) ? 5 /* 111110xx */ \
     31                  : (((x) & 0xFE) == 0xFC) ? 6 /* 1111110x */ \
     32                                           : 0 )
     33 
     34 #define BADRUNE(x) ((x) < 0 || (x) > Runemax \
     35                 || ((x) & 0xFFFE) == 0xFFFE \
     36                 || ((x) >= 0xD800 && (x) <= 0xDFFF) \
     37                 || ((x) >= 0xFDD0 && (x) <= 0xFDEF))
     38 
     39 int
     40 runetochar(char *s, const Rune *p)
     41 {
     42 	Rune r = *p;
     43 
     44 	switch(runelen(r)) {
     45 	case 1: /* 0aaaaaaa */
     46 		s[0] = r;
     47 		return 1;
     48 	case 2: /* 00000aaa aabbbbbb */
     49 		s[0] = 0xC0 | ((r & 0x0007C0) >>  6); /* 110aaaaa */
     50 		s[1] = 0x80 |  (r & 0x00003F);        /* 10bbbbbb */
     51 		return 2;
     52 	case 3: /* aaaabbbb bbcccccc */
     53 		s[0] = 0xE0 | ((r & 0x00F000) >> 12); /* 1110aaaa */
     54 		s[1] = 0x80 | ((r & 0x000FC0) >>  6); /* 10bbbbbb */
     55 		s[2] = 0x80 |  (r & 0x00003F);        /* 10cccccc */
     56 		return 3;
     57 	case 4: /* 000aaabb bbbbcccc ccdddddd */
     58 		s[0] = 0xF0 | ((r & 0x1C0000) >> 18); /* 11110aaa */
     59 		s[1] = 0x80 | ((r & 0x03F000) >> 12); /* 10bbbbbb */
     60 		s[2] = 0x80 | ((r & 0x000FC0) >>  6); /* 10cccccc */
     61 		s[3] = 0x80 |  (r & 0x00003F);        /* 10dddddd */
     62 		return 4;
     63 	default:
     64 		return 0; /* error */
     65 	}
     66 }
     67 
     68 int
     69 chartorune(Rune *p, const char *s)
     70 {
     71 	return charntorune(p, s, UTFmax);
     72 }
     73 
     74 int
     75 charntorune(Rune *p, const char *s, size_t len)
     76 {
     77 	unsigned int i, n;
     78 	Rune r;
     79 
     80 	if(len == 0) /* can't even look at s[0] */
     81 		return 0;
     82 
     83 	switch((n = UTFSEQ(s[0]))) {
     84 	case 1: r = s[0];        break; /* 0xxxxxxx */
     85 	case 2: r = s[0] & 0x1F; break; /* 110xxxxx */
     86 	case 3: r = s[0] & 0x0F; break; /* 1110xxxx */
     87 	case 4: r = s[0] & 0x07; break; /* 11110xxx */
     88 	case 5: r = s[0] & 0x03; break; /* 111110xx */
     89 	case 6: r = s[0] & 0x01; break; /* 1111110x */
     90 	default: /* invalid sequence */
     91 		*p = Runeerror;
     92 		return 1;
     93 	}
     94 	/* add values from continuation bytes */
     95 	for(i = 1; i < MIN(n, len); i++)
     96 		if((s[i] & 0xC0) == 0x80) {
     97 			/* add bits from continuation byte to rune value
     98 			 * cannot overflow: 6 byte sequences contain 31 bits */
     99 			r = (r << 6) | (s[i] & 0x3F); /* 10xxxxxx */
    100 		}
    101 		else { /* expected continuation */
    102 			*p = Runeerror;
    103 			return i;
    104 		}
    105 
    106 	if(i < n) /* must have reached len limit */
    107 		return 0;
    108 
    109 	/* reject invalid or overlong sequences */
    110 	if(BADRUNE(r) || runelen(r) < (int)n)
    111 		r = Runeerror;
    112 
    113 	*p = r;
    114 	return n;
    115 }
    116 
    117 int
    118 runelen(Rune r)
    119 {
    120 	if(BADRUNE(r))
    121 		return 0; /* error */
    122 	else if(r <= 0x7F)
    123 		return 1;
    124 	else if(r <= 0x07FF)
    125 		return 2;
    126 	else if(r <= 0xFFFF)
    127 		return 3;
    128 	else
    129 		return 4;
    130 }
    131 
    132 size_t
    133 runenlen(const Rune *p, size_t len)
    134 {
    135 	size_t i, n = 0;
    136 
    137 	for(i = 0; i < len; i++)
    138 		n += runelen(p[i]);
    139 	return n;
    140 }
    141 
    142 int
    143 fullrune(const char *s, size_t len)
    144 {
    145 	Rune r;
    146 
    147 	return charntorune(&r, s, len) > 0;
    148 }