| 1 | /* |
| 2 | * This file is part of DisOrder |
| 3 | * Copyright (C) 2004, 2007 Richard Kettlewell |
| 4 | * |
| 5 | * This program is free software; you can redistribute it and/or modify |
| 6 | * it under the terms of the GNU General Public License as published by |
| 7 | * the Free Software Foundation; either version 2 of the License, or |
| 8 | * (at your option) any later version. |
| 9 | * |
| 10 | * This program is distributed in the hope that it will be useful, but |
| 11 | * WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 13 | * General Public License for more details. |
| 14 | * |
| 15 | * You should have received a copy of the GNU General Public License |
| 16 | * along with this program; if not, write to the Free Software |
| 17 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 |
| 18 | * USA |
| 19 | */ |
| 20 | |
| 21 | #include <config.h> |
| 22 | #include "types.h" |
| 23 | |
| 24 | #include <string.h> |
| 25 | #include <stddef.h> |
| 26 | |
| 27 | #include "mem.h" |
| 28 | #include "vector.h" |
| 29 | #include "table.h" |
| 30 | #include "words.h" |
| 31 | #include "utf8.h" |
| 32 | #include "log.h" |
| 33 | #include "charset.h" |
| 34 | |
| 35 | #include "unidata.h" |
| 36 | |
| 37 | const char *casefold(const char *ptr) { |
| 38 | struct dynstr d; |
| 39 | uint32_t c; |
| 40 | const char *s = ptr; |
| 41 | |
| 42 | dynstr_init(&d); |
| 43 | while(*s) { |
| 44 | /* Convert UTF-8 to UCS-32 */ |
| 45 | PARSE_UTF8(s, c, return ptr); |
| 46 | /* Normalize */ |
| 47 | if(c < UNICODE_NCHARS) { |
| 48 | /* If this a known character, convert it to lower case */ |
| 49 | const struct unidata *const ud = &unidata[c / 256][c % 256]; |
| 50 | c += ud->lower_offset; |
| 51 | } |
| 52 | /* Convert UCS-4 back to UTF-8 */ |
| 53 | one_ucs42utf8(c, &d); |
| 54 | } |
| 55 | dynstr_terminate(&d); |
| 56 | return d.vec; |
| 57 | } |
| 58 | |
| 59 | static enum unicode_gc_cat cat(uint32_t c) { |
| 60 | if(c < UNICODE_NCHARS) { |
| 61 | /* If this a known character, convert it to lower case */ |
| 62 | const struct unidata *const ud = &unidata[c / 256][c % 256]; |
| 63 | return ud->gc; |
| 64 | } else |
| 65 | return unicode_gc_Cn; |
| 66 | } |
| 67 | |
| 68 | /* XXX this is a bit kludgy */ |
| 69 | |
| 70 | char **words(const char *s, int *nvecp) { |
| 71 | struct vector v; |
| 72 | struct dynstr d; |
| 73 | const char *start; |
| 74 | uint32_t c; |
| 75 | int in_word = 0; |
| 76 | |
| 77 | vector_init(&v); |
| 78 | while(*s) { |
| 79 | start = s; |
| 80 | PARSE_UTF8(s, c, return 0); |
| 81 | /* special cases first */ |
| 82 | switch(c) { |
| 83 | case '/': |
| 84 | case '.': |
| 85 | case '+': |
| 86 | case '&': |
| 87 | case ':': |
| 88 | case '_': |
| 89 | case '-': |
| 90 | goto separator; |
| 91 | } |
| 92 | /* do the rest on category */ |
| 93 | switch(cat(c)) { |
| 94 | case unicode_gc_Ll: |
| 95 | case unicode_gc_Lm: |
| 96 | case unicode_gc_Lo: |
| 97 | case unicode_gc_Lt: |
| 98 | case unicode_gc_Lu: |
| 99 | case unicode_gc_Nd: |
| 100 | case unicode_gc_Nl: |
| 101 | case unicode_gc_No: |
| 102 | case unicode_gc_Sc: |
| 103 | case unicode_gc_Sk: |
| 104 | case unicode_gc_Sm: |
| 105 | case unicode_gc_So: |
| 106 | /* letters, digits and symbols are considered to be part of |
| 107 | * words */ |
| 108 | if(!in_word) { |
| 109 | dynstr_init(&d); |
| 110 | in_word = 1; |
| 111 | } |
| 112 | dynstr_append_bytes(&d, start, s - start); |
| 113 | break; |
| 114 | |
| 115 | case unicode_gc_Cc: |
| 116 | case unicode_gc_Cf: |
| 117 | case unicode_gc_Co: |
| 118 | case unicode_gc_Cs: |
| 119 | case unicode_gc_Zl: |
| 120 | case unicode_gc_Zp: |
| 121 | case unicode_gc_Zs: |
| 122 | case unicode_gc_Pe: |
| 123 | case unicode_gc_Ps: |
| 124 | separator: |
| 125 | if(in_word) { |
| 126 | dynstr_terminate(&d); |
| 127 | vector_append(&v, d.vec); |
| 128 | in_word = 0; |
| 129 | } |
| 130 | break; |
| 131 | |
| 132 | case unicode_gc_Mc: |
| 133 | case unicode_gc_Me: |
| 134 | case unicode_gc_Mn: |
| 135 | case unicode_gc_Pc: |
| 136 | case unicode_gc_Pd: |
| 137 | case unicode_gc_Pf: |
| 138 | case unicode_gc_Pi: |
| 139 | case unicode_gc_Po: |
| 140 | case unicode_gc_Cn: |
| 141 | /* control and punctuation is completely ignored */ |
| 142 | break; |
| 143 | |
| 144 | } |
| 145 | } |
| 146 | if(in_word) { |
| 147 | /* pick up the final word */ |
| 148 | dynstr_terminate(&d); |
| 149 | vector_append(&v, d.vec); |
| 150 | } |
| 151 | vector_terminate(&v); |
| 152 | if(nvecp) |
| 153 | *nvecp = v.nvec; |
| 154 | return v.vec; |
| 155 | } |
| 156 | |
| 157 | /* |
| 158 | Local Variables: |
| 159 | c-basic-offset:2 |
| 160 | comment-column:40 |
| 161 | End: |
| 162 | */ |