Rev 3247 | Go to most recent revision | Details | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 10 | reyssat | 1 | /* Copyright (C) 1998-2003 XIAO, Gang of Universite de Nice - Sophia Antipolis |
| 2 | * |
||
| 3 | * This program is free software; you can redistribute it and/or modify |
||
| 4 | * it under the terms of the GNU General Public License as published by |
||
| 5 | * the Free Software Foundation; either version 2 of the License, or |
||
| 6 | * (at your option) any later version. |
||
| 7 | * |
||
| 8 | * This program is distributed in the hope that it will be useful, |
||
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
||
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
||
| 11 | * GNU General Public License for more details. |
||
| 12 | * |
||
| 13 | * You should have received a copy of the GNU General Public License |
||
| 14 | * along with this program; if not, write to the Free Software |
||
| 15 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. |
||
| 16 | */ |
||
| 17 | |||
| 18 | /* Versatile translation according to a dictionary */ |
||
| 19 | |||
| 20 | /*************** Customization: change values hereafter ****************/ |
||
| 21 | |||
| 22 | /* limit of dictionary entries */ |
||
| 23 | #define entrylim 32768 |
||
| 24 | /* limit of dictionary length */ |
||
| 25 | #define diclim 1024*1024 |
||
| 26 | |||
| 27 | /***************** Nothing should need change hereafter *****************/ |
||
| 28 | |||
| 29 | char inpbuf[MAX_LINELEN+1], outbuf[2*MAX_LINELEN+2]; |
||
| 30 | char *dicbuf; |
||
| 31 | struct entry { |
||
| 32 | unsigned char *original, *replace; |
||
| 33 | int olen,earlier; |
||
| 34 | } entry[entrylim]; |
||
| 35 | int entrycount; |
||
| 36 | |||
| 37 | enum { |
||
| 38 | unk_delete, unk_leave, unk_replace |
||
| 39 | }; |
||
| 40 | |||
| 41 | int has_digits=0; |
||
| 42 | int unknown_type=unk_delete; |
||
| 43 | int nocase=0,leaveline=0; |
||
| 44 | char *unknown, unkbuf[1024]; |
||
| 45 | |||
| 46 | int compare(int i1, const char *s2) |
||
| 47 | { |
||
| 48 | int k; |
||
| 49 | if(nocase) k=strncasecmp(entry[i1].original,s2,entry[i1].olen); |
||
| 50 | else k=strncmp(entry[i1].original,s2,entry[i1].olen); |
||
| 51 | if(k==0 && (isalnum(*(s2+entry[i1].olen)) || (*(s2+entry[i1].olen)&128)!=0)) return -1; |
||
| 52 | else return k; |
||
| 53 | } |
||
| 54 | |||
| 55 | /* searches a list. Returns index if found, -1 if nomatch. |
||
| 56 | * Uses binary search, list must be sorted. */ |
||
| 57 | int search_list(struct entry *list, int items, size_t item_size, const char *str) |
||
| 58 | { |
||
| 59 | int i1,i2,j,k,t,t1; |
||
| 60 | unsigned char c; |
||
| 61 | |||
| 62 | if(items<=0) return -1; |
||
| 63 | j=0; c=str[0]; |
||
| 64 | k=list[0].original[0]-c; if(k==0) k=compare(0,str); |
||
| 65 | if(k==0) goto more; if(k>0) return -1; |
||
| 66 | j=items-1; k=list[j].original[0]-c; if(k==0) k=compare(j,str); |
||
| 67 | if(k==0) return j; |
||
| 68 | if(k>0) for(i1=0,i2=j;i2>i1+1;) { |
||
| 69 | j=i1+(i2-i1)/2; |
||
| 70 | k=list[j].original[0]-c; if(k==0) k=compare(j,str); |
||
| 71 | if(k==0) goto more; |
||
| 72 | if(k>0) {i2=j; continue;} |
||
| 73 | if(k<0) {i1=j; continue;} |
||
| 74 | } |
||
| 75 | if(k>0) {j--;k=compare(j,str);} |
||
| 76 | more: |
||
| 77 | if((t=list[j].earlier)<0) { |
||
| 78 | if(k==0) return j; else return -1; |
||
| 79 | } |
||
| 80 | if(compare(t,str)!=0) return -1; |
||
| 81 | for(j=t1=t,k=0;j<items && list[j].earlier==t1 && (k=compare(j,str))<=0; j++) |
||
| 82 | if(k==0) t=j; |
||
| 83 | return t; |
||
| 84 | } |
||
| 85 | |||
| 86 | /* change all spaces into ' ', and collapse multiple occurences */ |
||
| 87 | void singlespace(char *p) |
||
| 88 | { |
||
| 89 | char *pp, *p2; |
||
| 90 | for(pp=p;*pp;pp++) { |
||
| 91 | if(!isspace(*pp)) continue; |
||
| 92 | if(leaveline) { |
||
| 93 | if(*pp==13) strcpy(pp,pp+1); |
||
| 94 | if(*pp=='\n') { |
||
| 95 | pp++; |
||
| 96 | gopt: for(p2=pp; isspace(*p2) && *p2!='\n'; p2++); |
||
| 97 | if(p2>pp) strcpy(pp,p2); pp--; |
||
| 98 | } |
||
| 99 | else { |
||
| 100 | pp++; if(!isspace(*pp) || *pp=='\n') continue; |
||
| 101 | goto gopt; |
||
| 102 | } |
||
| 103 | } |
||
| 104 | else { |
||
| 105 | if(*pp!=' ') *pp=' '; |
||
| 106 | if(!isspace(*(pp+1))) continue; |
||
| 107 | for(pp++,p2=pp;isspace(*p2);p2++); |
||
| 108 | strcpy(pp,p2); pp--; |
||
| 109 | } |
||
| 110 | } |
||
| 111 | } |
||
| 112 | |||
| 113 | #include "suffix.c" |
||
| 114 | |||
| 115 | /* Prepare dictionary */ |
||
| 116 | void prepare_dic(char *fname) |
||
| 117 | { |
||
| 118 | int i,l; |
||
| 119 | FILE *dicf; |
||
| 120 | char *p1, *p2, *pp; |
||
| 121 | long int flen; |
||
| 122 | |||
| 123 | entrycount=0; |
||
| 124 | dicf=fopen(fname,"r"); if(dicf==NULL) return; |
||
| 125 | fseek(dicf,0,SEEK_END);flen=ftell(dicf); fseek(dicf,0,SEEK_SET); |
||
| 126 | if(flen>diclim) return; |
||
| 127 | dicbuf=xmalloc(flen+16);flen=fread(dicbuf,1,flen,dicf); |
||
| 128 | fclose(dicf); |
||
| 129 | if(flen>0 && flen<diclim) dicbuf[flen]=0; |
||
| 130 | else return; |
||
| 131 | for(i=0,p1=dicbuf;p1!=NULL && *p1!=0 && i<entrylim;p1=p2) { |
||
| 132 | p2=strchr(p1+1,'\n'); if(p2>p1) *p2++=0; |
||
| 133 | pp=strchr(p1,':'); if(pp==NULL) continue; |
||
| 134 | *pp++=0; |
||
| 135 | strip_trailing_spaces(p1); strip_trailing_spaces(pp); |
||
| 136 | singlespace(p1); |
||
| 137 | p1=find_word_start(p1); pp=find_word_start(pp); |
||
| 138 | if(*p1==0) continue; |
||
| 139 | if(has_digits==0) { |
||
| 140 | char *p; |
||
| 141 | for(p=p1;*p!=0 && p<pp && !isdigit(*p);p++); |
||
| 142 | if(isdigit(*p)) has_digits=1; |
||
| 143 | } |
||
| 144 | entry[i].original=p1; entry[i].replace=pp; |
||
| 145 | entry[i].olen=l=strlen(p1); entry[i].earlier=-1; |
||
| 146 | if(i>0) { |
||
| 147 | int l1,l2; |
||
| 148 | l1=entry[i-1].earlier; if(l1>=0) l2=entry[l1].olen; |
||
| 149 | else {l2=entry[i-1].olen;l1=i-1;} |
||
| 150 | if(l>l2 && isspace(p1[l2]) |
||
| 151 | && strncmp(entry[l1].original,p1,l2)==0) |
||
| 152 | entry[i].earlier=entry[i-1].earlier=l1; |
||
| 153 | } |
||
| 154 | i++; |
||
| 155 | } |
||
| 156 | entrycount=i; |
||
| 157 | } |
||
| 158 | |||
| 159 | /* now make the translation. */ |
||
| 160 | void translate(char *p) |
||
| 161 | { |
||
| 162 | char *p1, *p2, *pp; |
||
| 163 | int t; |
||
| 164 | |||
| 165 | if(entrycount<=0 && suffixcnt<=0) return; |
||
| 166 | snprintf(outbuf,sizeof(outbuf),"%s",p); |
||
| 167 | for(p1=find_word_start(outbuf); |
||
| 168 | p1!=NULL && p1-outbuf<MAX_LINELEN && *p1!=0; |
||
| 169 | p1=p2) { |
||
| 170 | p2=find_word_end(p1); |
||
| 171 | for(pp=p1;pp<p2 && |
||
| 172 | ((!has_digits && isalpha(*pp)) || |
||
| 173 | (has_digits && isalnum(*pp)) || (*pp&128)!=0 || |
||
| 174 | strchr("_",*pp)!=NULL);pp++); |
||
| 175 | p2=find_word_start(p2); |
||
| 176 | if(pp==p1 || |
||
| 177 | (has_digits==0 && isdigit(*pp)) || |
||
| 178 | (*pp!=0 && !isspace(*pp) && strchr(",.?!/;",*pp)==NULL)) continue; |
||
| 179 | t=search_list(entry,entrycount,sizeof(entry[0]),p1); |
||
| 180 | if(t<0) { |
||
| 181 | switch(unknown_type) { |
||
| 182 | case unk_leave: break; |
||
| 183 | case unk_delete: { |
||
| 184 | strcpy(p1,find_word_start(pp)); p2=p1; |
||
| 185 | break; |
||
| 186 | } |
||
| 187 | case unk_replace: { |
||
| 188 | string_modify(outbuf,p1,pp,unkbuf); |
||
| 189 | p2=find_word_start(p1+strlen(unkbuf)); |
||
| 190 | } |
||
| 191 | } |
||
| 192 | continue; |
||
| 193 | } |
||
| 194 | string_modify(outbuf,p1,p1+strlen(entry[t].original), |
||
| 195 | entry[t].replace); |
||
| 196 | p2=find_word_start(p1+strlen(entry[t].replace)); |
||
| 197 | } |
||
| 198 | snprintf(p,MAX_LINELEN,"%s",outbuf); |
||
| 199 | } |
||
| 200 |