src/unicoderange.cpp

   1 #include "unicoderange.h"
   2
   3 #include <stdlib.h>
   4 #include <string.h>
   5
   6 static unsigned int hex2int(char* s){
   7         int res=0;
   8         int i=0, mul=1;
   9         while(s[i+1]!='\0') i++;
  10
  11         while(i>=0){
  12                 if (s[i] > '9') res += mul * (s[i]-'A'+10);
  13                 else res += mul * (s[i]-'0');
  14                 i--;
  15                 mul*=16;
  16         }
  17         return res;
  18 }
  19
  20 UnicodeRange::UnicodeRange(const gchar* value){
  21         if (!value) return;
  22         gchar* val = (gchar*) value;
  23         while(val[0] != '\0'){
  24                 if (val[0]=='U' && val[1]=='+'){
  25                         val += add_range(val);
  26                 } else {
  27 //                      g_warning("adding unichar. unichar=%c", g_utf8_get_char(&val[0]));
  28                         this->unichars.push_back(g_utf8_get_char(&val[0]));
  29                         val++;
  30                 }
  31                 //skip spaces or commas
  32                 while(val[0]==' ' || val[0]==',') val++;
  33         }
  34 }
  35
  36 int
  37 UnicodeRange::add_range(gchar* val){
  38                 Urange r;
  39                 //U+
  40                 val+=2;
  41                 int i=0, count=2;
  42                 while(val[i]!='\0' && val[i]!='-' && val[i]!=' ' && val[i]!=',') i++;
  43                 r.start = (gchar*) malloc((i+1)*sizeof(gchar*));
  44                 strncpy(r.start, val, i);
  45                 r.start[i] = '\0';
  46                 val+=i;
  47                 count+=i;
  48                 i=0;
  49                 if (val[0]=='-'){
  50                         val++;
  51                         while(val[i]!='\0' && val[i]!='-' && val[i]!=' ' && val[i]!=',') i++;
  52                         r.end = (gchar*) malloc((i+1)*sizeof(gchar*));
  53                         strncpy(r.end, val, i);
  54                         r.end[i] = '\0';
  55                         val+=i;
  56                         count+=i;
  57                 } else {
  58                         r.end=NULL;
  59                 }
  60 //              g_warning("adding range. from %s to %s", r.start, r.end);
  61                 this->range.push_back(r);
  62                 return count+1;
  63 }
  64
  65 bool UnicodeRange::contains(gchar unicode){
  66         for(unsigned int i=0;i<this->unichars.size();i++){
  67                 if ((gunichar) unicode == this->unichars[i]) return true;
  68         }
  69
  70         unsigned int unival;
  71         unival = g_utf8_get_char (&unicode);
  72 //      g_warning("unival=%d", unival);
  73         char uni[9] = "00000000";
  74         uni[8]= '\0';
  75         unsigned char val;
  76         for (unsigned int i=7; unival>0; i--){
  77                 val = unival & 0xf;
  78                 unival = unival >> 4;
  79                 if (val < 10) uni[i] = '0' + val;
  80                 else uni[i] = 'A'+ val - 10;
  81         }
  82 //      g_warning("uni=%s", uni);
  83
  84         bool found;
  85         for(unsigned int i=0;i<this->range.size();i++){
  86                 Urange r = this->range[i];
  87                 if (r.end){
  88 //                      g_warning("hex2int: start=%d", hex2int(r.start));
  89 //                      g_warning("hex2int: end=%d", hex2int(r.end));
  90                         if (unival >= hex2int(r.start) && unival <= hex2int(r.end)) return true;
  91                 } else {
  92                         found = true;
  93                         for (int pos=0;pos<8;pos++){
  94                                 if (uni[pos]!='?' && uni[pos]!=r.start[pos]) found = false;
  95                         }
  96                         if (found) return true;
  97                 }
  98         }
  99         return false;
 100 }