void read_grammar(char *filename)
{
char buffer[1000];
FILE *file;
init_lexicons();
if(GDEBUG) fprintf(stderr,"Initialised lexicons\n");
init_grammar();
if(GDEBUG) fprintf(stderr,"Initialised grammar\n");
strcpy(buffer,filename);
strcat(buffer,".nts");
file = fopen(buffer,"r");
read_nonterminals(file);
file = fopen(buffer,"r");
read_nonterminals2(file);
if(GDEBUG) fprintf(stderr,"Loaded non-terminals\n");
strcpy(buffer,filename);
strcat(buffer,".lexicon");
file = fopen(buffer,"r");
read_lexicon(file);
if(GDEBUG) fprintf(stderr,"Loaded lexicon\n");
strcpy(buffer,filename);
strcat(buffer,".grm");
file = fopen(buffer,"r");
read_grm(file);
if(GDEBUG) fprintf(stderr,"Loaded grammar\n");
}
int main(int argc, char **argv)
{
char ch[TailleLigne];
int nb,nbentries,i,j;
lia_avl_t t_lexique, t_unknown,*table;
FILE *file;
unsigned long total;
if (argc<=2)
{
fprintf(stderr,"Syntaxe : %s <lexicon> <name report>\n",argv[0]);
exit(0);
}
t_lexique=read_lexicon(argv[1]);
t_unknown=checking_corpus(stdin,t_lexique);
fprintf(stderr,"- report OOV words\n");
sprintf(ch,"%s.oov",argv[2]);
if (!(file=fopen(ch,"wt"))) ERREUR("can't write in :",ch);
table=lia_avl_tree2table_freq(t_unknown,&nb);
fprintf(stderr,"\t-> %d entree inconnues dans le corpus\n",nb);
for(i=0;i<nb;i++)
fprintf(file,"\t%5d \t %s\n",table[i]->nb,table[i]->info);
fclose(file);
free(table);
fprintf(stderr,"done\n");
fprintf(stderr,"- report ZEROTON words\n");
sprintf(ch,"%s.zeroton",argv[2]);
if (!(file=fopen(ch,"wt"))) ERREUR("can't write in :",ch);
table=lia_avl_tree2table_freq(t_lexique,&nb);
for(i=j=0;i<nb;i++) if (table[i]->nb==1) { j++; fprintf(file,"%s\n",table[i]->info); }
fclose(file);
fprintf(stderr,"\t-> %d ZEROTON dans le corpus\n",j);
fprintf(stderr,"done\n");
fprintf(stderr,"- report words from the lexicon in the corpus\n");
sprintf(ch,"%s.occ",argv[2]);
if (!(file=fopen(ch,"wt"))) ERREUR("can't write in :",ch);
for(nbentries=0,i=0,total=0;i<nb;i++) if (table[i]->nb>1)
{ nbentries++; total+=(unsigned long)(table[i]->nb-1); fprintf(file,"\t%5d \t %s\n",table[i]->nb-1,table[i]->info); }
free(table);
fclose(file);
fprintf(stderr,"\t-> %ld occurences for %d entries\n",total,nbentries);
fprintf(stderr,"done\n");
exit(0);
}
int main(int argc, char **argv)
{
char ch[TailleLigne],*pt,*ptbak1,*ptbak2,test[TailleLigne];
int nb;
lia_avl_t t_lexique;
if (argc<2)
{
fprintf(stderr,"Syntaxe : %s <lexicon>\n",argv[0]);
exit(0);
}
t_lexique=read_lexicon(argv[1]);
while(fgets(ch,TailleLigne,stdin))
{
ptbak2=ptbak1=NULL;
for(pt=strtok(ch," \t\n");(ptbak2!=pt)||(ptbak1!=pt);)
{
if ((ptbak1)&&(ptbak1[strlen(ptbak1)-1]=='\''))
{
if ((ptbak2)&&(ptbak1[0]=='\''))
{
sprintf(test,"%s'%s",ptbak2,pt);
/*fprintf(stderr,"test=[%s]\n",test);*/
if (lia_recherche_avl(t_lexique,test,&nb))
{
printf(" %s",test);
/*fprintf(stderr,"test=[%s]\n",test);*/
/*
ptbak2=strtok(NULL," \t\n");
if (ptbak2) ptbak1=strtok(NULL," \t\n"); else ptbak1=NULL;
if (ptbak1) pt=strtok(NULL," \t\n"); else pt=NULL;
*/
ptbak2=NULL;
ptbak1=strtok(NULL," \t\n");
if (ptbak1) pt=strtok(NULL," \t\n"); else pt=NULL;
}
else
{
sprintf(test,"%s'",ptbak2);
/*fprintf(stderr,"test=[%s]\n",test);*/
if (lia_recherche_avl(t_lexique,test,&nb))
{
printf(" %s",test);
ptbak2=NULL;
ptbak1=pt;
if (pt) pt=strtok(NULL," \t\n");
}
else
{
printf(" %s",ptbak2);
ptbak2=ptbak1; ptbak1=pt; if (pt) pt=strtok(NULL," \t\n");
}
}
}
else
{
sprintf(test,"%s%s",ptbak1,pt);
/*fprintf(stderr,"test=[%s]\n",test);*/
if (lia_recherche_avl(t_lexique,test,&nb))
{
/*fprintf(stderr,"\tOK\n");*/
if (ptbak2) printf(" %s",ptbak2);
printf(" %s",test);
/*
ptbak2=strtok(NULL," \t\n");
if (ptbak2) ptbak1=strtok(NULL," \t\n"); else ptbak1=NULL;
if (ptbak1) pt=strtok(NULL," \t\n"); else pt=NULL;
*/
ptbak2=NULL;
ptbak1=strtok(NULL," \t\n");
if (ptbak1) pt=strtok(NULL," \t\n"); else pt=NULL;
}
else
{
if (ptbak2) printf(" %s",ptbak2);
ptbak2=ptbak1; ptbak1=pt; if (pt) pt=strtok(NULL," \t\n");
}
}
}
else
{
if (ptbak2) printf(" %s",ptbak2);
ptbak2=ptbak1; ptbak1=pt; if (pt) pt=strtok(NULL," \t\n");
}
}
printf("\n");
}
exit(0);
}