vcs.maemo.org Git - navit-package/blob - navit/linguistics.c

   1 #include <string.h>
   2 #include <stdio.h>
   3 #include <glib.h>
   4 #include "debug.h"
   5 #include "linguistics.h"
   6
   7 static const char *special[][3]={
   8 /* Capital Diacritics */
   9 /* ¨ Diaresis */
  10 {"Ä","A","AE"},
  11 {"Ö","O","OE"},
  12 {"Ü","U","UE"},
  13 /* ˝ Double Acute Accent */
  14 {"Ő","O"},
  15 {"Ű","U"},
  16 /* ´ Acute Accent */
  17 {"Á","A"},
  18 {"Ć","C"},
  19 {"É","E"},
  20 {"Í","I"},
  21 {"Ń","N"},
  22 {"Ó","O"},
  23 {"Ś","S"},
  24 {"Ú","U"},
  25 {"Ý","Y"},
  26 {"Ź","Z"},
  27 /* ˛ Ogonek */
  28 {"Ą","A"},
  29 {"Ę","E"},
  30 /* ˙ Dot */
  31 {"Ż","Z"},
  32 /* – Stroke */
  33 {"Ł","L"},
  34 /* ˚ Ring */
  35 {"Ů","U"},
  36 /* ˇ Caron */
  37 {"Č","C"},
  38 {"Ď","D"},
  39 {"Ě","E"},
  40 {"Ň","N"},
  41 {"Ř","R"},
  42 {"Š","S"},
  43 {"Ť","T"},
  44 {"Ž","Z"},
  45 /* Small Diacritics */
  46 /* ¨ Diaresis */
  47 {"ä","a","ae"},
  48 {"ö","o","oe"},
  49 {"ü","u","ue"},
  50 /* ˝ Double Acute Accent */
  51 {"ő","o"},
  52 {"ű","u"},
  53 /* ´ Acute Accent */
  54 {"á","a"},
  55 {"ć","c"},
  56 {"é","e"},
  57 {"í","i"},
  58 {"ń","n"},
  59 {"ó","o"},
  60 {"ś","s"},
  61 {"ú","u"},
  62 {"ý","y"},
  63 {"ź","z"},
  64 /* ˛ Ogonek */
  65 {"ą","a"},
  66 {"ę","e"},
  67 /* ˙ Dot */
  68 {"ż","z"},
  69 /* – Stroke */
  70 {"ł","l"},
  71 /* ˚ Ring */
  72 {"ů","u"},
  73 /* ˇ Caron */
  74 {"č","c"},
  75 {"ď","d"},
  76 {"ě","e"},
  77 {"Ň","N"},
  78 {"ř","r"},
  79 {"š","s"},
  80 {"ť","t"},
  81 {"ž","z"},
  82 /* ligatures */
  83 {"ß","s","ss"},
  84 };
  85
  86 char *
  87 linguistics_expand_special(char *str, int mode)
  88 {
  89         char *in=str;
  90         char *out,*ret;
  91         int found=0;
  92         out=ret=g_strdup(str);
  93         if (!mode)
  94                 return ret;
  95         while (*in) {
  96                 char *next=g_utf8_find_next_char(in, NULL);
  97                 int i,len=next-in;
  98                 int match=0;
  99                 if (len > 1) {
 100                         for (i = 0 ; i < sizeof(special)/sizeof(special[0]); i++) {
 101                                 const char *search=special[i][0];
 102                                 if (!strncmp(in,search,len)) {
 103                                         const char *replace=special[i][mode];
 104                                         if (replace) {
 105                                                 int replace_len=strlen(replace);
 106                                                 dbg_assert(replace_len <= len);
 107                                                 dbg(1,"found %s %s %d %s %d\n",in,search,len,replace,replace_len);
 108                                                 strcpy(out, replace);
 109                                                 out+=replace_len;
 110                                                 match=1;
 111                                                 break;
 112                                         }
 113                                 }
 114                         }
 115                 }
 116                 if (match) {
 117                         found=1;
 118                         in=next;
 119                 } else {
 120                         while (len-- > 0)
 121                                 *out++=*in++;
 122                 }
 123         }
 124         *out++='\0';
 125         if (!found) {
 126                 g_free(ret);
 127                 ret=NULL;
 128         }
 129         return ret;
 130 }
 131
 132 char *
 133 linguistics_next_word(char *str)
 134 {
 135         int len=strcspn(str, " -");
 136         if (!str[len] || !str[len+1])
 137                 return NULL;
 138         return str+len+1;
 139 }
 140
 141 void
 142 linguistics_init(void)
 143 {
 144 }