void reduce_do(char* buf, const size_t total, const std::string &out_folder){
yucha::tool::recursive_mkdir(out_folder.c_str());
size_t prev = 0;
size_t split = 0;
std::pair<size_t , size_t> p;
MyHash h(buf);
MyHashEq e(buf);
MYMAP uni(3 , h , e);
{
size_t spaces[3];
for(size_t i = 0 ; i < total; ++i){
prev = i;
unsigned short int count = 0;
bool error = false;
for(; buf[i] != '\n'; ++i){ //get freq
if(buf[i] == '\t'){
if (count==2){
error = true;
}
else{
spaces[count] = i;
++count;
};
};
};
if (count!=2 or error)
continue;
buf[spaces[0]] = ' ';
const size_t end_1 = spaces[0];
const size_t end_2 = spaces[1];
const size_t tail = i;
std::pair<size_t , size_t> word1(prev, end_1);
std::pair<size_t , size_t> word2(end_1+1 , end_2);
buf[tail] = '\0';
const unsigned long freq = atoi(&buf[end_2]);
add(uni, word1, freq);
add(uni, word2, freq);
};
}
printout(1, uni, out_folder, buf, 0);
};
/*
* PORTB:デコーダー1,2: p~i:PORTB 7~4 RB7:C RB6:B RB5:A RB4:G1 H~A:8~0 RB3:C RB2:B RB1:A RB0:G1
* PORTD:16~9 Anode: RD7~RD0
* PORTC:8~1 Anode: RC7~RC0
*/
void main( )
{
TRISB = 0x00;//PORTB output
TRISC = 0x00;//PORTC output
TRISD = 0x00;//PORTD output
PORTB = 0x00;//portb init
PORTC = 0x00;//portc init
PORTD = 0x00;//portd init
//メモリ足りない;配列は使えない。
unsigned int w1[16]={0x1024,0x0c24,0x0324,0xfffe,0x0122,0x8623,0xc0c1,0x6078,0x3800,0x0f00,0x01ff,0x0f00,0x3840,0x6070,0xc01c,0x8000};
unsigned int w2[16];
unsigned int tmp[16];
while(1){
copy(w1,tmp);
copy(w1,w2);
for(int i=0;i<30;i++){
word2(w2);
}
scroll(w2,tmp);
}
}
// la procedure ajout_mot comme son nom l'indique ajoute un mot donne
// dans l'index
void ajout_mot (mot **tableau,char chainn[50],int k){
mot *ptr,*ptr1,*ptr2;
page *ptrpg;
int z,f;
if(tableau[tolower(chainn[0]) - 'a'] == NULL){
ptr =(mot *)malloc(sizeof(mot ));
tableau[tolower(chainn[0]) - 'a'] = ptr ;
ptr->motindex=(char *)malloc(strlen(chainn)+1);
strcpy(ptr->motindex,chainn);
ptr->next=NULL;
ptr->prempg=(page *)malloc(sizeof(page ));
ptr->prempg->nbrocc=1;
ptr->prempg->numpg=k;
ptr->prempg->next=NULL;
ptr->derpg=(page *)malloc(sizeof(page));
ptr->derpg=ptr->prempg;
} else {
ptr = tableau[tolower(chainn[0]) - 'a'] ;
z = word(tableau,chainn,k);
printf("======================> Z :%d\n",z);
switch (z) {
case 3 :
ptrpg = ptr->prempg;
ptr->prempg=NULL;
ptr->prempg=(page *)malloc(sizeof(page));
ptr->prempg->nbrocc=1;
ptr->prempg->numpg=k;
ptr->prempg->next = ptrpg;
break ;
case 2 :
ptr = word2(tableau[tolower(chainn[0]) - 'a'],chainn,k);
if (ptr==NULL){
printf("we have an error \n");
}
ptr->derpg->nbrocc++;
ptr->derpg->next=NULL;
break ;
case 1:
ptr = word2(tableau[tolower(chainn[0]) - 'a'],chainn,k);
if (ptr == NULL) {
printf("we have problem");
}
ptrpg=(page *)malloc(sizeof(page ));
ptr->derpg->next=ptrpg;
ptr->derpg=ptrpg;
ptrpg->next=NULL;
ptrpg->nbrocc=1;
ptrpg->numpg=k;
break ;
case 0:
ptr1 = tableau[tolower(chainn[0]) - 'a'] ;
f=0;
while(strcasecmp(chainn,ptr->motindex)>0){
f=1;
ptr1 = ptr;
ptr = ptr->next;
if (ptr == NULL){
break;
}
}
if (f==0){
ptr2 = (mot *)malloc(sizeof(mot ));
tableau[tolower(chainn[0]) - 'a'] =ptr2;
ptr2->next=ptr1;
ptr2->motindex=(char *)malloc(strlen(chainn)+1);
strcpy(ptr2->motindex,chainn);
ptr2->prempg=(page *)malloc(sizeof(page ));
ptr2->prempg->nbrocc=1;
ptr2->prempg->numpg=k;
ptr2->prempg->next=NULL;
ptr2->derpg = (page * )malloc(sizeof(page));
ptr2->derpg=ptr2->prempg;
}else {
ptr2 = (mot *)malloc(sizeof(mot ));
ptr2->motindex=(char *)malloc(strlen(chainn)+1);
strcpy(ptr2->motindex,chainn);
ptr2->prempg=(page *)malloc(sizeof(page ));
ptr2->prempg->nbrocc=1;
ptr2->prempg->numpg=k;
ptr2->prempg->next=NULL;
ptr2->derpg=(page *)malloc(sizeof(page));
ptr2->derpg=ptr2->prempg;
ptr2->next=ptr1->next;
ptr1->next=ptr2;
}
break ;
}
}
}
void creat_index (mot* *tab,char name[26]) {
page *ptrpg;
mot *ptr,*ptr1,*ptr2;
int s = 0, z = 0,f;
float num_page ;
for (s = 0 ; s <26 ; s++) {
tab[s]=NULL;
}
s=0 ; // on a utilise la variable s comme compteur pour compter le nbr du ligne :)
char chain[100],chain1[100];
FILE *fp;
fp = fopen(name,"rt");
if (fp == NULL) {
printf("\n\n\t Impossible d'ouvrir le fichier \n") ;
printf(" veuillez verifier Que le Fichier %s exist et dans le meme directory\n\n\n\n",name);
Sleep(5000);
exit (3);
} else {
while (fgets (chain,100,fp)!= NULL) { // on prend une ligne de 100 carectere
s = s +1 ; // on a utilise la variable s comme compteur pour compter le nbr du ligne :)
if (strlen(chain) != 1 ) { // on verifie si la chaine n'est pas vide or \n only
write(chain); // on ecrase et on ecrit la ligne dans un fichier tmp.txt
FILE *ft ; // on ouvre le fichier tmp.txt cette fois en mode lire seulement
ft = fopen("tmp.txt","rt");
while (fscanf(ft,"%s",chain1) != EOF) {
float j ;
j = s ; // on lit jusqu"a la fin du fichier tmp.txt Qui contient une seul ligne
num_page=ceil(j/lp);
if (check(chain1) !=1 && strlen(chain1) > 2 && isalpha(chain1[0])) {
if(tab[tolower(chain1[0]) - 'a'] == NULL){
ptr =(mot *)malloc(sizeof(mot ));
tab[tolower(chain1[0]) - 'a'] = ptr ;
ptr->motindex=(char *)malloc(strlen(chain1)+1);
strcpy(ptr->motindex,chain1);
ptr->next=NULL;
ptr->prempg=(page *)malloc(sizeof(page ));
ptr->prempg->nbrocc=1;
ptr->prempg->numpg=(int )num_page;
ptr->prempg->next=NULL;
ptr->derpg=(page *)malloc(sizeof(page));
ptr->derpg=ptr->prempg;
} else {
ptr = tab[tolower(chain1[0]) - 'a'];
z = word(tab,chain1,(int )num_page);
switch (z) {
case 3 :
ptrpg = ptr->prempg;
ptr->prempg=(page *)malloc(sizeof(page));
ptr->prempg->nbrocc=1;
ptr->prempg->numpg=(int )num_page;
ptr->prempg->next = ptrpg;
break ;
case 2 :
ptr = word2(tab[tolower(chain1[0]) - 'a'],chain1,(int )num_page);
if (ptr==NULL){
printf("we have an error \n");
}
ptr->derpg->nbrocc++;
break ;
case 1 :
ptr = word2(tab[tolower(chain1[0]) - 'a'],chain1,( int )num_page);
if (ptr == NULL) {
printf("we have problem");
}
ptrpg=(page *)malloc(sizeof(page ));
ptr->derpg->next=ptrpg;
ptr->derpg=ptrpg;
ptrpg->next=NULL;
ptrpg->nbrocc=1;
ptrpg->numpg=(int )num_page;
break ;
case 0 :
ptr1 = tab[tolower(chain1[0]) - 'a'] ;
f=0;
while(strcasecmp(chain1,ptr->motindex)>0){
f=1;
ptr1 = ptr;
ptr = ptr->next;
if (ptr == NULL){
break;
}
}
if (f==0){
ptr2 = (mot *)malloc(sizeof(mot ));
tab[tolower(chain1[0]) - 'a'] =ptr2;
ptr2->next=ptr1;
ptr2->motindex=(char *)malloc(strlen(chain1)+1);
strcpy(ptr2->motindex,chain1);
ptr2->prempg=(page *)malloc(sizeof(page ));
ptr2->prempg->nbrocc=1;
ptr2->prempg->numpg=(int )num_page;
ptr2->prempg->next=NULL;
ptr2->derpg=ptr2->prempg;
}else {
ptr2 = (mot *)malloc(sizeof(mot ));
ptr2->motindex=(char *)malloc(strlen(chain1)+1);
strcpy(ptr2->motindex,chain1);
ptr2->prempg=(page *)malloc(sizeof(page ));
ptr2->prempg->nbrocc=1;
ptr2->prempg->numpg=(int)num_page;
ptr2->prempg->next=NULL;
ptr2->derpg=(page *)malloc(sizeof(page));
ptr2->derpg=ptr2->prempg;
ptr2->next=ptr1->next;
ptr1->next=ptr2;
}
break ;
default :
printf("i guess we have a problem here \n");
break ;
}
}
}
;
}fclose(ft);
}
}remove("tmp.txt");
}
}
void reduce_do(char* buf, const size_t total, const std::string &out_folder){
yucha::tool::recursive_mkdir(out_folder.c_str());
size_t prev = 0;
size_t split = 0;
std::pair<size_t , size_t> p;
MyHash h(buf);
MyHashEq e(buf);
MYMAP uni(3 , h , e);
MYMAP bi(3 , h , e);
MYMAP tri(3 , h , e);
{
size_t spaces[3];
for(size_t i = 0 ; i < total; ++i){
prev = i;
unsigned short int count = 0;
unsigned short int tab_count = 0;
bool error = false;
for(; buf[i] != '\n'; ++i){ //get freq
if (buf[i] == '\t'){
if (tab_count < 2){
buf[i] = '=';
}
else{
spaces[count] = i;
++count;
};
++tab_count;
}
else if(buf[i] == ' '){ //you can't use space
buf[i] = '_';
}
else if(buf[i] == ':'){ //SPLITTER is ':'
if (count==3){
error = true;
}
else{
spaces[count] = i;
++count;
};
};
};
if (count!=3 or error)
continue;
buf[spaces[0]] = ' ';
buf[spaces[1]] = ' ';
const size_t end_1 = spaces[0];
const size_t end_2 = spaces[1];
const size_t end_3 = spaces[2];
const size_t tail = i;
std::pair<size_t , size_t> word1(prev, end_1);
std::pair<size_t , size_t> word2(end_1+1 , end_2);
std::pair<size_t , size_t> bi1(prev, end_2);
std::pair<size_t , size_t> word3(end_2+1 , end_3);
std::pair<size_t , size_t> bi2(end_1+1, end_3);
std::pair<size_t , size_t> tri1(prev, end_3);
buf[tail] = '\0';
const unsigned long freq = atoi(&buf[end_3]);
add(uni, word1, freq);
add(uni, word2, freq);
add(uni, word3, freq);
add(bi, bi1, freq);
add(bi, bi2, freq);
add(tri, tri1, freq);
};
}
printout(1, uni, out_folder, buf, 0);
printout(2, bi, out_folder, buf, 10000000);
printout(3, tri, out_folder, buf, 10000000);
};