1 /* $Id: chars.c,v 1.66 2015/02/17 20:37:16 schwarze Exp $ */ 2 /* 3 * Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> 4 * Copyright (c) 2011, 2014 Ingo Schwarze <schwarze@openbsd.org> 5 * 6 * Permission to use, copy, modify, and distribute this software for any 7 * purpose with or without fee is hereby granted, provided that the above 8 * copyright notice and this permission notice appear in all copies. 9 * 10 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES 11 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF 12 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR 13 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES 14 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN 15 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF 16 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. 17 */ 18 #include "config.h" 19 20 #include <sys/types.h> 21 22 #include <assert.h> 23 #include <ctype.h> 24 #include <stdlib.h> 25 #include <string.h> 26 27 #include "mandoc.h" 28 #include "mandoc_aux.h" 29 #include "libmandoc.h" 30 31 #define PRINT_HI 126 32 #define PRINT_LO 32 33 34 struct ln { 35 struct ln *next; 36 const char *code; 37 const char *ascii; 38 int unicode; 39 }; 40 41 #define LINES_MAX 332 42 43 #define CHAR(in, ch, code) \ 44 { NULL, (in), (ch), (code) }, 45 46 #define CHAR_TBL_START static struct ln lines[LINES_MAX] = { 47 #define CHAR_TBL_END }; 48 49 #include "chars.in" 50 51 struct mchars { 52 struct ln **htab; 53 }; 54 55 static const struct ln *find(const struct mchars *, 56 const char *, size_t); 57 58 59 void 60 mchars_free(struct mchars *arg) 61 { 62 63 free(arg->htab); 64 free(arg); 65 } 66 67 struct mchars * 68 mchars_alloc(void) 69 { 70 struct mchars *tab; 71 struct ln **htab; 72 struct ln *pp; 73 int i, hash; 74 75 /* 76 * Constructs a very basic chaining hashtable. The hash routine 77 * is simply the integral value of the first character. 78 * Subsequent entries are chained in the order they're processed. 79 */ 80 81 tab = mandoc_malloc(sizeof(struct mchars)); 82 htab = mandoc_calloc(PRINT_HI - PRINT_LO + 1, sizeof(struct ln *)); 83 84 for (i = 0; i < LINES_MAX; i++) { 85 hash = (int)lines[i].code[0] - PRINT_LO; 86 87 if (NULL == (pp = htab[hash])) { 88 htab[hash] = &lines[i]; 89 continue; 90 } 91 92 for ( ; pp->next; pp = pp->next) 93 /* Scan ahead. */ ; 94 pp->next = &lines[i]; 95 } 96 97 tab->htab = htab; 98 return(tab); 99 } 100 101 int 102 mchars_spec2cp(const struct mchars *arg, const char *p, size_t sz) 103 { 104 const struct ln *ln; 105 106 ln = find(arg, p, sz); 107 return(ln != NULL ? ln->unicode : sz == 1 ? (unsigned char)*p : -1); 108 } 109 110 int 111 mchars_num2char(const char *p, size_t sz) 112 { 113 int i; 114 115 i = mandoc_strntoi(p, sz, 10); 116 return(i >= 0 && i < 256 ? i : -1); 117 } 118 119 int 120 mchars_num2uc(const char *p, size_t sz) 121 { 122 int i; 123 124 i = mandoc_strntoi(p, sz, 16); 125 assert(i >= 0 && i <= 0x10FFFF); 126 return(i); 127 } 128 129 const char * 130 mchars_spec2str(const struct mchars *arg, 131 const char *p, size_t sz, size_t *rsz) 132 { 133 const struct ln *ln; 134 135 ln = find(arg, p, sz); 136 if (ln == NULL) { 137 *rsz = 1; 138 return(sz == 1 ? p : NULL); 139 } 140 141 *rsz = strlen(ln->ascii); 142 return(ln->ascii); 143 } 144 145 const char * 146 mchars_uc2str(int uc) 147 { 148 int i; 149 150 for (i = 0; i < LINES_MAX; i++) 151 if (uc == lines[i].unicode) 152 return(lines[i].ascii); 153 return("<?>"); 154 } 155 156 static const struct ln * 157 find(const struct mchars *tab, const char *p, size_t sz) 158 { 159 const struct ln *pp; 160 int hash; 161 162 assert(p); 163 164 if (0 == sz || p[0] < PRINT_LO || p[0] > PRINT_HI) 165 return(NULL); 166 167 hash = (int)p[0] - PRINT_LO; 168 169 for (pp = tab->htab[hash]; pp; pp = pp->next) 170 if (0 == strncmp(pp->code, p, sz) && 171 '\0' == pp->code[(int)sz]) 172 return(pp); 173 174 return(NULL); 175 } 176