// conversion nom de fichier/dossier isolé vers 8-3 ou ISO9660
void longfile_to_83(int mode,char* n83,char* save) {
int j=0,max=0;
int i = 0;
char nom[256];
char ext[256];
nom[0]=ext[0]='\0';
switch(mode) {
case 1:
max=8;
break;
case 2:
max=31;
break;
default:
max=8;
break;
}
/* No starting . */
if (save[0] == '.') {
save[0]='_';
}
/* No multiple dots */
{
char* last_dot=strrchr(save, '.');
char* dot;
while((dot=strchr(save, '.'))) {
*dot = '_';
}
if (last_dot) {
*last_dot='.';
}
}
/*
Avoid: (ISO9660, but also suitable for 8-3)
(Thanks to [email protected] for te hint)
/:;?\#*~
0x00-0x1f and 0x80-0xff
*/
for(i = 0 ; save[i] != 0 ; i++) {
char a = save[i];
if (a >= 'a' && a <= 'z') {
a -= 'a' - 'A';
}
else if ( ! ( (a >= 'A' && a <= 'Z') || (a >= '0' && a <= '9') || a == '_' || a == '.') ) {
a = '_';
}
save[i] = a;
}
i=j=0;
while((i<max) && (save[j]) && (save[j]!='.')) {
if (save[j]!=' ') {
nom[i]=save[j];
i++;
}
j++;
} // recopier nom
nom[i]='\0';
if (save[j]) { // il reste au moins un point
i = (int) strlen(save)-1;
while((i>0) && (save[i]!='.') && (save[i]!='/')) i--; // rechercher dernier .
if (save[i]=='.') { // point!
int j=0;
i++;
while((j<3) && (save[i]) ) { if (save[i]!=' ') { ext[j]=save[i]; j++; } i++; }
ext[j]='\0';
}
}
// corriger vers 8-3
n83[0]='\0';
strncatbuff(n83,nom,max);
if (strnotempty(ext)) {
strcatbuff(n83,".");
strncatbuff(n83,ext,3);
}
}
// supercomparateur joker (tm)
// compare a et b (b=avec joker dedans), case insensitive [voir CI]
// renvoi l'adresse de la première lettre de la chaine
// (càd *[..]toto.. renvoi adresse de toto dans la chaine)
// accepte les délires du genre www.*.*/ * / * truc*.*
// cet algo est 'un peu' récursif mais ne consomme pas trop de tm
// * = toute lettre
// --?-- : spécifique à HTTrack et aux ?
HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * size,
int *size_flag) {
//int err=0;
if (strnotempty(joker) == 0) { // fin de chaine joker
if (strnotempty(chaine) == 0) // fin aussi pour la chaine: ok
return chaine;
else if (chaine[0] == '?')
return chaine; // --?-- pour les index.html?Choix=2
else
return NULL; // non trouvé
}
// on va progresser en suivant les 'mots' contenus dans le joker
// un mot peut être un * ou bien toute autre séquence de lettres
if (strcmp(joker, "*") == 0) { // ok, rien après
return chaine;
}
// 1er cas: jokers * ou jokers multiples *[..]
if (joker[0] == '*') { // comparer joker+reste (*toto/..)
int jmp; // nombre de caractères pour le prochain mot dans joker
int cut = 0; // interdire tout caractère superflu
char pass[256];
char LEFT = '[', RIGHT = ']';
int unique = 0;
switch (joker[1]) {
case '[':
LEFT = '[';
RIGHT = ']';
unique = 0;
break;
case '(':
LEFT = '(';
RIGHT = ')';
unique = 1;
break;
}
if ((joker[1] == LEFT) && (joker[2] != LEFT)) { // multijoker (tm)
int i;
for(i = 0; i < 256; i++)
pass[i] = 0;
// noms réservés
if ((strfield(joker + 2, "file")) || (strfield(joker + 2, "name"))) {
for(i = 0; i < 256; i++)
pass[i] = 1;
pass[(int) '?'] = 0;
//pass[(int) ';'] = 0;
pass[(int) '/'] = 0;
i = 2;
{
int len = (int) strlen(joker);
while((joker[i] != RIGHT) && (joker[i]) && (i < len))
i++;
}
} else if (strfield(joker + 2, "path")) {
for(i = 0; i < 256; i++)
pass[i] = 1;
pass[(int) '?'] = 0;
//pass[(int) ';'] = 0;
i = 2;
{
int len = (int) strlen(joker);
while((joker[i] != RIGHT) && (joker[i]) && (i < len))
i++;
}
} else if (strfield(joker + 2, "param")) {
if (chaine[0] == '?') { // il y a un paramètre juste là
for(i = 0; i < 256; i++)
pass[i] = 1;
} // sinon synonyme de 'rien'
i = 2;
{
int len = (int) strlen(joker);
while((joker[i] != RIGHT) && (joker[i]) && (i < len))
i++;
}
} else {
// décode les directives comme *[A-Z,âêîôû,0-9]
i = 2;
if (joker[i] == RIGHT) { // *[] signifie "plus rien après"
cut = 1; // caractère supplémentaire interdit
} else {
int len = (int) strlen(joker);
while((joker[i] != RIGHT) && (joker[i]) && (i < len)) {
if ((joker[i] == '<') || (joker[i] == '>')) { // *[<10]
int lsize = 0;
int lverdict;
i++;
if (sscanf(joker + i, "%d", &lsize) == 1) {
if (size) {
if (*size >= 0) {
if (size_flag)
*size_flag = 1; /* a joué */
if (joker[i - 1] == '<')
lverdict = (*size < lsize);
else
lverdict = (*size > lsize);
if (!lverdict) {
return NULL; // ne correspond pas
} else {
*size = lsize;
return chaine; // ok
}
} else
return NULL; // ne correspond pas
} else
return NULL; // ne correspond pas (test impossible)
// jump
while(isdigit((unsigned char) joker[i]))
i++;
}
} else if (joker[i + 1] == '-') { // 2 car, ex: *[A-Z]
if ((int) (unsigned char) joker[i + 2] >
(int) (unsigned char) joker[i]) {
int j;
for(j = (int) (unsigned char) joker[i];
j <= (int) (unsigned char) joker[i + 2]; j++)
pass[j] = 1;
}
// else err=1;
i += 3;
} else { // 1 car, ex: *[ ]
if (joker[i + 2] == '\\' && joker[i + 3] != 0) { // escaped char, such as *[\[] or *[\]]
i++;
}
pass[(int) (unsigned char) joker[i]] = 1;
i++;
}
if ((joker[i] == ',') || (joker[i] == ';'))
i++;
}
}
}
// à sauter dans joker
jmp = i;
if (joker[i])
jmp++;
//
} else { // tout autoriser
//
int i;
for(i = 0; i < 256; i++)
pass[i] = 1; // tout autoriser
jmp = 1;
////if (joker[2]==LEFT) jmp=3; // permet de recher *<crochet ouvrant>
}
{
int i, max;
const char *adr;
// la chaine doit se terminer exactement
if (cut) {
if (strnotempty(chaine))
return NULL; // perdu
else
return chaine; // ok
}
// comparaison en boucle, c'est ca qui consomme huhu..
// le tableau pass[256] indique les caractères ASCII autorisés
// tester sans le joker (pas ()+ mais ()*)
if (!unique) {
if ((adr = strjoker(chaine, joker + jmp, size, size_flag))) {
return adr;
}
}
// tester
i = 0;
if (!unique)
max = (int) strlen(chaine);
else /* *(a) only match a (not aaaaa) */
max = 1;
while(i < (int) max) {
if (pass[(int) (unsigned char) chaine[i]]) { // caractère autorisé
if ((adr = strjoker(chaine + i + 1, joker + jmp, size, size_flag))) {
return adr;
}
i++;
} else
i = max + 2; // sortir
}
// tester chaîne vide
if (i != max + 2) // avant c'est ok
if ((adr = strjoker(chaine + max, joker + jmp, size, size_flag)))
return adr;
return NULL; // perdu
}
} else { // comparer mot+reste (toto*..)
if (strnotempty(chaine)) {
int jmp = 0, ok = 1;
// comparer début de joker et début de chaine
while((joker[jmp] != '*') && (joker[jmp]) && (ok)) {
// CI : remplacer streql par une comparaison !=
if (!streql(chaine[jmp], joker[jmp])) {
ok = 0; // quitter
}
jmp++;
}
// comparaison ok?
if (ok) {
// continuer la comparaison.
if (strjoker(chaine + jmp, joker + jmp, size, size_flag))
return chaine; // retourner 1e lettre
}
} // strlen(a)
return NULL;
} // * ou mot
return NULL;
}
// forme à partir d'un lien et du contexte (origin_fil et origin_adr d'où il est tiré) adr et fil
// [adr et fil sont des buffers de 1ko]
// 0 : ok
// -1 : erreur
// -2 : protocole non supporté (ftp)
int ident_url_relatif(const char *lien,const char* origin_adr,const char* origin_fil,char* adr,char* fil) {
int ok=0;
int scheme=0;
adr[0]='\0'; fil[0]='\0'; //effacer buffers
// lien non vide!
if (strnotempty(lien)==0) return -1; // erreur!
// Scheme?
{
const char* a=lien;
while (isalpha((unsigned char)*a))
a++;
if (*a == ':')
scheme=1;
}
// filtrer les parazites (mailto & cie)
// scheme+authority (//)
if (
(strfield(lien,"http://")) // scheme+//
|| (strfield(lien,"file://")) // scheme+//
|| (strncmp(lien,"//",2)==0) // // sans scheme (-> default)
) {
if (ident_url_absolute(lien,adr,fil)==-1) {
ok=-1; // erreur URL
}
}
else if (strfield(lien,"ftp://")) {
// Note: ftp:foobar.gif is not valid
if (ftp_available()) { // ftp supporté
if (ident_url_absolute(lien,adr,fil)==-1) {
ok=-1; // erreur URL
}
} else {
ok=-2; // non supporté
}
#if HTS_USEMMS
} else if (strfield(lien,"mms://")) {
if (ident_url_absolute(lien,adr,fil)==-1) {
ok=-1; // erreur URL
}
#endif
#if HTS_USEOPENSSL
} else if (strfield(lien,"https://")) {
if (SSL_is_available) {
// Note: ftp:foobar.gif is not valid
if (ident_url_absolute(lien,adr,fil)==-1) {
ok=-1; // erreur URL
}
} else {
ok=-1;
}
#endif
} else if ((scheme) && (
(!strfield(lien,"http:"))
&& (!strfield(lien,"https:"))
&& (!strfield(lien,"ftp:"))
#if HTS_USEMMS
&& (!strfield(lien,"mms:"))
#endif
)) {
ok=-1; // unknown scheme
} else { // c'est un lien relatif
// On forme l'URL complète à partie de l'url actuelle
// et du chemin actuel si besoin est.
// copier adresse
if (((int) strlen(origin_adr)<HTS_URLMAXSIZE) && ((int) strlen(origin_fil)<HTS_URLMAXSIZE) && ((int) strlen(lien)<HTS_URLMAXSIZE)) {
/* patch scheme if necessary */
if (strfield(lien,"http:")) {
lien+=5;
strcpybuff(adr, jump_protocol(origin_adr)); // même adresse ; protocole vide (http)
} else if (strfield(lien,"https:")) {
lien+=6;
strcpybuff(adr, "https://"); // même adresse forcée en https
strcatbuff(adr, jump_protocol(origin_adr));
} else if (strfield(lien,"ftp:")) {
lien+=4;
strcpybuff(adr, "ftp://"); // même adresse forcée en ftp
strcatbuff(adr, jump_protocol(origin_adr));
#if HTS_USEMMS
} else if (strfield(lien,"mms:")) {
lien+=4;
strcpybuff(adr, "mms://"); // même adresse forcée en ftp
strcatbuff(adr, jump_protocol(origin_adr));
#endif
} else {
strcpybuff(adr,origin_adr); // même adresse ; et même éventuel protocole
}
if (*lien!='/') { // sinon c'est un lien absolu
if (*lien == '\0') {
strcpybuff(fil,origin_fil);
} else if (*lien == '?') { // example: a href="?page=2"
char* a;
strcpybuff(fil,origin_fil);
a=strchr(fil,'?');
if (a) *a='\0';
strcatbuff(fil,lien);
} else {
const char *a=strchr(origin_fil,'?');
if (a == NULL) a=origin_fil+strlen(origin_fil);
while((*a!='/') && ( a > origin_fil) ) a--;
if (*a=='/') { // ok on a un '/'
if ( (((int) (a - origin_fil))+1+strlen(lien)) < HTS_URLMAXSIZE) {
// copier chemin
strncpy(fil,origin_fil,((int) (a - origin_fil))+1);
*(fil + ((int) (a - origin_fil))+1)='\0';
// copier chemin relatif
if (((int) strlen(fil)+(int) strlen(lien)) < HTS_URLMAXSIZE) {
strcatbuff(fil,lien + ((*lien=='/')?1:0) );
// simplifier url pour les ../
fil_simplifie(fil);
} else
ok=-1; // erreur
} else { // erreur
ok=-1; // erreur URL
}
} else { // erreur
ok=-1; // erreur URL
}
}
} else { // chemin absolu
// copier chemin directement
strcatbuff(fil,lien);
fil_simplifie(fil);
} // *lien!='/'
} else
ok=-1;
} // test news: etc.
// case insensitive pour adresse
{
char *a=jump_identification(adr);
while(*a) {
if ((*a>='A') && (*a<='Z'))
*a+='a'-'A';
a++;
}
}
return ok;
}
static int __cdecl htsshow_loop(t_hts_callbackarg *carg, httrackp *opt,
lien_back* back, int back_max, int back_index, int lien_n,
int lien_tot, int stat_time, hts_stat_struct* stats) { // appel� � chaque boucle de HTTrack
static TStamp prev_mytime = 0; /* ok */
static t_InpInfo SInfo; /* ok */
//
TStamp mytime;
long int rate = 0;
char st[256];
//
int stat_written = -1;
int stat_updated = -1;
int stat_errors = -1;
int stat_warnings = -1;
int stat_infos = -1;
int nbk = -1;
LLint nb = -1;
int stat_nsocket = -1;
LLint stat_bytes = -1;
LLint stat_bytes_recv = -1;
int irate = -1;
if (stats) {
stat_written = stats->stat_files;
stat_updated = stats->stat_updated_files;
stat_errors = stats->stat_errors;
stat_warnings = stats->stat_warnings;
stat_infos = stats->stat_infos;
nbk = stats->nbk;
stat_nsocket = stats->stat_nsocket;
irate = (int) stats->rate;
nb = stats->nb;
stat_bytes = stats->nb;
stat_bytes_recv = stats->HTS_TOTAL_RECV;
}
if (!use_show)
return 1;
mytime = mtime_local();
if ((stat_time > 0) && (stat_bytes_recv > 0))
rate = (int) (stat_bytes_recv / stat_time);
else
rate = 0; // pas d'infos
/* Infos */
if (stat_bytes >= 0)
SInfo.stat_bytes = stat_bytes; // bytes
if (stat_time >= 0)
SInfo.stat_time = stat_time; // time
if (lien_tot >= 0)
SInfo.lien_tot = lien_tot; // nb liens
if (lien_n >= 0)
SInfo.lien_n = lien_n; // scanned
SInfo.stat_nsocket = stat_nsocket; // socks
if (rate > 0)
SInfo.rate = rate; // rate
if (irate >= 0)
SInfo.irate = irate; // irate
if (SInfo.irate < 0)
SInfo.irate = SInfo.rate;
if (nbk >= 0)
SInfo.stat_back = nbk;
if (stat_written >= 0)
SInfo.stat_written = stat_written;
if (stat_updated >= 0)
SInfo.stat_updated = stat_updated;
if (stat_errors >= 0)
SInfo.stat_errors = stat_errors;
if (stat_warnings >= 0)
SInfo.stat_warnings = stat_warnings;
if (stat_infos >= 0)
SInfo.stat_infos = stat_infos;
if (((mytime - prev_mytime) > 100) || ((mytime - prev_mytime) < 0)) {
strc_int2bytes2 strc, strc2, strc3;
prev_mytime = mytime;
st[0] = '\0';
qsec2str(st, stat_time);
vt_home();
printf(VT_GOTOXY("1","1")
VT_CLREOL
STYLE_STATTEXT "Bytes saved:"
STYLE_STATVALUES " \t%s"
"\t"
VT_CLREOL
VT_GOTOXY("40","1")
STYLE_STATTEXT "Links scanned:"
STYLE_STATVALUES " \t%d/%d (+%d)"
VT_CLREOL"\n"VT_CLREOL
VT_GOTOXY("1","2")
STYLE_STATTEXT "Time:"
" \t"
STYLE_STATVALUES "%s"
"\t"
VT_CLREOL
VT_GOTOXY("40","2")
STYLE_STATTEXT "Files written:"
" \t"
STYLE_STATVALUES "%d"
VT_CLREOL"\n"VT_CLREOL
VT_GOTOXY("1","3")
STYLE_STATTEXT "Transfer rate:"
" \t"
STYLE_STATVALUES "%s (%s)"
"\t"
VT_CLREOL
VT_GOTOXY("40","3")
STYLE_STATTEXT "Files updated:"
" \t"
STYLE_STATVALUES "%d"
VT_CLREOL"\n"VT_CLREOL
VT_GOTOXY("1","4")
STYLE_STATTEXT "Active connections:"
" \t"
STYLE_STATVALUES "%d"
"\t"
VT_CLREOL
VT_GOTOXY("40","4")
STYLE_STATTEXT "Errors:"
STYLE_STATVALUES " \t"
STYLE_STATVALUES "%d"
VT_CLREOL"\n"
STYLE_STATRESET,
/* */
(char*) int2bytes(&strc, SInfo.stat_bytes), (int) lien_n,
(int) SInfo.lien_tot, (int) nbk, (char*) st,
(int) SInfo.stat_written,
(char*) int2bytessec(&strc2, SInfo.irate),
(char*) int2bytessec(&strc3, SInfo.rate),
(int) SInfo.stat_updated, (int) SInfo.stat_nsocket,
(int) SInfo.stat_errors
/* */
);
// parcourir registre des liens
if (back_index >= 0) { // seulement si index pass�
int j, k;
int index = 0;
int ok = 0; // idem
int l; // idem
//
t_StatsBuffer StatsBuffer[NStatsBuffer];
{
int i;
for (i = 0; i < NStatsBuffer; i++) {
strcpybuff(StatsBuffer[i].state,"");
strcpybuff(StatsBuffer[i].name,"");
strcpybuff(StatsBuffer[i].file,"");
strcpybuff(StatsBuffer[i].url_sav,"");
StatsBuffer[i].back = 0;
StatsBuffer[i].size = 0;
StatsBuffer[i].sizetot = 0;
}
}
for (k = 0; k < 2; k++) { // 0: lien en cours 1: autres liens
for (j = 0; (j < 3) && (index < NStatsBuffer); j++) { // passe de priorit�
int _i;
for (_i = 0 + k; (_i < max(back_max*k,1)) && (index
< NStatsBuffer); _i++) { // no lien
int i = (back_index + _i) % back_max; // commencer par le "premier" (l'actuel)
if (back[i].status >= 0) { // signifie "lien actif"
// int ok=0; // OPTI
ok = 0;
switch (j) {
case 0: // prioritaire
if ((back[i].status > 0) && (back[i].status
< 99)) {
strcpybuff(StatsBuffer[index].state,"receive");
ok = 1;
}
break;
case 1:
if (back[i].status == STATUS_WAIT_HEADERS) {
strcpybuff(StatsBuffer[index].state,"request");
ok = 1;
} else if (back[i].status == STATUS_CONNECTING) {
strcpybuff(StatsBuffer[index].state,"connect");
ok = 1;
} else if (back[i].status == STATUS_WAIT_DNS) {
strcpybuff(StatsBuffer[index].state,"search");
ok = 1;
} else if (back[i].status
== STATUS_FTP_TRANSFER) { // ohh le beau ftp
sprintf(StatsBuffer[index].state,
"ftp: %s", back[i].info);
ok = 1;
}
break;
default:
if (back[i].status == STATUS_READY) { // pr�t
if ((back[i].r.statuscode == 200)) {
strcpybuff(StatsBuffer[index].state,"ready");
ok = 1;
} else if ((back[i].r.statuscode >= 100)
&& (back[i].r.statuscode <= 599)) {
char tempo[256];
tempo[0] = '\0';
infostatuscode(tempo,
back[i].r.statuscode);
strcpybuff(StatsBuffer[index].state,tempo);
ok = 1;
} else {
strcpybuff(StatsBuffer[index].state,"error");
ok = 1;
}
}
break;
}
if (ok) {
char BIGSTK s[HTS_URLMAXSIZE * 2];
//
StatsBuffer[index].back = i; // index pour + d'infos
//
s[0] = '\0';
strcpybuff(StatsBuffer[index].url_sav,back[i].url_sav); // pour cancel
if (strcmp(back[i].url_adr, "file://"))
strcatbuff(s,back[i].url_adr);
else
strcatbuff(s,"localhost");
if (back[i].url_fil[0] != '/')
strcatbuff(s,"/");
strcatbuff(s,back[i].url_fil);
StatsBuffer[index].file[0] = '\0';
{
char* a = strrchr(s, '/');
if (a) {
strncatbuff(StatsBuffer[index].file,a,200);
*a = '\0';
}
}
if ((l = (int) strlen(s)) < MAX_LEN_INPROGRESS)
strcpybuff(StatsBuffer[index].name,s);
else {
// couper
StatsBuffer[index].name[0] = '\0';
strncatbuff(StatsBuffer[index].name,s,MAX_LEN_INPROGRESS/2-2);
strcatbuff(StatsBuffer[index].name,"...");
strcatbuff(StatsBuffer[index].name,s+l-MAX_LEN_INPROGRESS/2+2);
}
if (back[i].r.totalsize > 0) { // taille pr�d�finie
StatsBuffer[index].sizetot
= back[i].r.totalsize;
StatsBuffer[index].size = back[i].r.size;
} else { // pas de taille pr�d�finie
if (back[i].status == STATUS_READY) { // pr�t
StatsBuffer[index].sizetot
= back[i].r.size;
StatsBuffer[index].size
= back[i].r.size;
} else {
StatsBuffer[index].sizetot = 8192;
StatsBuffer[index].size
= (back[i].r.size % 8192);
}
}
index++;
}
}
}
}
}
/* LF */
printf("%s\n", VT_CLREOL);
/* Display current job */
{
int parsing = 0;
printf("Current job: ");
if (!(parsing = hts_is_parsing(opt, -1)))
printf("receiving files");
else {
switch (hts_is_testing(opt)) {
case 0:
printf("parsing HTML file (%d%%)", parsing);
break;
case 1:
printf("parsing HTML file: testing links (%d%%)",
parsing);
break;
case 2:
printf("purging files");
break;
case 3:
printf("loading cache");
break;
case 4:
printf("waiting (scheduler)");
break;
case 5:
printf("waiting (throttle)");
break;
}
}
printf("%s\n", VT_CLREOL);
}
/* Display background jobs */
{
int i;
for (i = 0; i < NStatsBuffer; i++) {
if (strnotempty(StatsBuffer[i].state)) {
printf(VT_CLREOL" %s - \t%s%s \t%s / \t%s",
StatsBuffer[i].state, StatsBuffer[i].name,
StatsBuffer[i].file,
int2bytes(&strc, StatsBuffer[i].size),
int2bytes(&strc2, StatsBuffer[i].sizetot));
}
printf("%s\n", VT_CLREOL);
}
}
}
}
return 1;
}
static void arg_init(struct hts_proj *proj) {
char * a;
char cmd[4096] = { 0x00 };
char str[256] = {0x00};
proj->argc = 1;
if (proj->cache == -1) proj->cache = 2; //cache default is best chose
if (proj->conns == -1) proj->conns = 10; //10 limits the number of connections per second
if (proj->timeout == -1) proj->timeout = 10;
if (strnotempty(proj->name) == 0) proj->errorno = 1;
if (strnotempty(proj->urls) == 0) proj->errorno = 2;
while ((a = strchr(proj->urls, ','))) *a = ' ';
while ((a = strchr(proj->urls, '\t'))) *a = ' ';
strcat(cmd, proj->urls);
strcat(cmd, " ");
//connections limit
sprintf(str, "-%%c%d ", proj->conns);
strcat(cmd, str);
//timeout
sprintf(str, "-T%d ", proj->timeout);
strcat(cmd, str);
if (strnotempty(proj->savepath) == 0) {
strcat(proj->savepath, getenv("HOME"));
strcat(proj->savepath, "/websites/");
}
if (strnotempty(proj->savepath)){
if ((proj->savepath[strlen(proj->savepath)-1]!='/') &&
(proj->savepath[strlen(proj->savepath)-1]!='\\')) {
strcat(proj->savepath, "/");
}
}
strcat(cmd, "-q ");
if (strnotempty(proj->linklist)) {
strcat(cmd, "-%L");
strcat(cmd, proj->linklist);
strcat(cmd, " ");
}
sprintf(str, "-C%d ", proj->cache);
strcat(cmd, str);
switch (proj->action) {
case ACTION_ALL_SITES:
strcat(cmd, "-w ");
break;
case ACTION_ONLY_FILES:
strcat(cmd, "-g ");
break;
case ACTION_WITH_CACHE:
strcat(cmd, "-i ");
break;
case ACTION_FIST_LEVEL:
strcat(cmd, "-Y ");
break;
}
strcat(cmd," --path \"");
strcat(cmd, proj->savepath);
strcat(cmd, proj->name);
strcat(cmd, "\" ");
sprintf(str, "-p%d ", proj->priority);
strcat(cmd, str);
if (strnotempty(proj->proxy_port) == 0) {
sprintf(proj->proxy_port,"%s", "8080");
}
if (proj->retries) {
sprintf(str, "-R%d ", proj->retries);
strcat(cmd, str);
}
if (strnotempty(proj->proxy)) {
strcat(cmd, "--proxy ");
strcat(cmd, proj->proxy);
strcat(cmd, ":");
strcat(cmd, proj->proxy_port);
}
if (proj->depth > 0) {
sprintf(str,"-r%d ", proj->depth);
strcat(cmd, str);
}
proj->argv[0] = "httrack";
proj->argc++;
proj->argv[1] = cmd;
fprintf(stderr, "%s\n", cmd);
int i = 0;
int g = 0;
while (cmd[i]) {
if (cmd[i] == '\"') g = !g;
if (cmd[i] == ' ') {
if (!g) {
cmd[i] = '\0';
proj->argv[proj->argc++] = cmd + i + 1;
}
}
i++;
}
}
// lire cookies.txt
// lire également (Windows seulement) les *@*.txt (cookies IE copiés)
// !=0 : erreur
int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
char catbuff[CATBUFF_SIZE];
char buffer[8192];
// cookie->data[0]='\0';
// Fusionner d'abord les éventuels cookies IE
#ifdef _WIN32
{
WIN32_FIND_DATAA find;
HANDLE h;
char pth[MAX_PATH + 32];
strcpybuff(pth, fpath);
strcatbuff(pth, "*@*.txt");
h = FindFirstFileA((char *) pth, &find);
if (h != INVALID_HANDLE_VALUE) {
do {
if (!(find.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY))
if (!(find.dwFileAttributes & FILE_ATTRIBUTE_SYSTEM)) {
FILE *fp = fopen(fconcat(catbuff, fpath, find.cFileName), "rb");
if (fp) {
char cook_name[256];
char cook_value[1000];
char domainpathpath[512];
char dummy[512];
//
char domain[256]; // domaine cookie (.netscape.com)
char path[256]; // chemin (/)
int cookie_merged = 0;
//
// Read all cookies
while(!feof(fp)) {
cook_name[0] = cook_value[0] = domainpathpath[0]
= dummy[0] = domain[0] = path[0] = '\0';
linput(fp, cook_name, 250);
if (!feof(fp)) {
linput(fp, cook_value, 250);
if (!feof(fp)) {
int i;
linput(fp, domainpathpath, 500);
/* Read 6 other useless values */
for(i = 0; !feof(fp) && i < 6; i++) {
linput(fp, dummy, 500);
}
if (strnotempty(cook_name)
&& strnotempty(cook_value)
&& strnotempty(domainpathpath)) {
if (ident_url_absolute(domainpathpath, domain, path) >= 0) {
cookie_add(cookie, cook_name, cook_value, domain, path);
cookie_merged = 1;
}
}
}
}
}
fclose(fp);
if (cookie_merged)
remove(fconcat(catbuff, fpath, find.cFileName));
} // if fp
}
} while(FindNextFileA(h, &find));
FindClose(h);
}
}
#endif
// Ensuite, cookies.txt
{
FILE *fp = fopen(fconcat(catbuff, fpath, name), "rb");
if (fp) {
char BIGSTK line[8192];
while((!feof(fp)) && (((int) strlen(cookie->data)) < cookie->max_len)) {
rawlinput(fp, line, 8100);
if (strnotempty(line)) {
if (strlen(line) < 8000) {
if (line[0] != '#') {
char domain[256]; // domaine cookie (.netscape.com)
char path[256]; // chemin (/)
char cook_name[1024]; // nom cookie (MYCOOK)
char BIGSTK cook_value[8192]; // valeur (ID=toto,S=1234)
strcpybuff(domain, cookie_get(buffer, line, 0)); // host
strcpybuff(path, cookie_get(buffer, line, 2)); // path
strcpybuff(cook_name, cookie_get(buffer, line, 5)); // name
strcpybuff(cook_value, cookie_get(buffer, line, 6)); // value
#if DEBUG_COOK
printf("%s\n", line);
#endif
cookie_add(cookie, cook_name, cook_value, domain, path);
}
}
}
}
fclose(fp);
return 0;
}
}
return -1;
}
// catch_url
// returns 0 if error
// url: buffer where URL must be stored - or ip:port in case of failure
// data: 32Kb
HTSEXT_API int catch_url(T_SOC soc, char *url, char *method, char *data) {
int retour = 0;
// connexion (accept)
if (soc != INVALID_SOCKET) {
T_SOC soc2;
while((soc2 = (T_SOC) accept(soc, NULL, NULL)) == INVALID_SOCKET) ;
/*
#ifdef _WIN32
closesocket(soc);
#else
close(soc);
#endif
*/
soc = soc2;
/* INFOS */
{
SOCaddr server2;
SOClen len = SOCaddr_capacity(server2);
if (getpeername(soc, &SOCaddr_sockaddr(server2), &len) == 0) {
char dot[256 + 2];
SOCaddr_inetntoa(dot, sizeof(dot), server2);
sprintf(url, "%s:%d", dot, ntohs(SOCaddr_sinport(server2)));
}
}
/* INFOS */
// réception
if (soc != INVALID_SOCKET) {
char line[1000];
char protocol[256];
line[0] = protocol[0] = '\0';
//
socinput(soc, line, 1000);
if (strnotempty(line)) {
if (sscanf(line, "%s %s %s", method, url, protocol) == 3) {
lien_adrfil af;
// méthode en majuscule
size_t i;
int r = 0;
af.adr[0] = af.fil[0] = '\0';
//
for(i = 0; method[i] != '\0'; i++) {
if ((method[i] >= 'a') && (method[i] <= 'z'))
method[i] -= ('a' - 'A');
}
// adresse du lien
if (ident_url_absolute(url, &af) >= 0) {
// Traitement des en-têtes
char BIGSTK loc[HTS_URLMAXSIZE * 2];
htsblk blkretour;
hts_init_htsblk(&blkretour);
//memset(&blkretour, 0, sizeof(htsblk)); // effacer
blkretour.location = loc; // si non nul, contiendra l'adresse véritable en cas de moved xx
// Lire en têtes restants
sprintf(data, "%s %s %s\r\n", method, af.fil, protocol);
while(strnotempty(line)) {
socinput(soc, line, 1000);
treathead(NULL, NULL, NULL, &blkretour, line); // traiter
strcatbuff(data, line);
strcatbuff(data, "\r\n");
}
// CR/LF final de l'en tête inutile car déja placé via la ligne vide juste au dessus
//strcatbuff(data,"\r\n");
if (blkretour.totalsize > 0) {
int len = (int) min(blkretour.totalsize, 32000);
int pos = (int) strlen(data);
// Copier le reste (post éventuel)
while((len > 0)
&& ((r = recv(soc, (char *) data + pos, len, 0)) > 0)) {
pos += r;
len -= r;
data[pos] = '\0'; // terminer par NULL
}
}
// Envoyer page
sprintf(line, CATCH_RESPONSE);
send(soc, line, (int) strlen(line), 0);
// OK!
retour = 1;
}
}
} // sinon erreur
}
}
if (soc != INVALID_SOCKET) {
#ifdef _WIN32
closesocket(soc);
/*
WSACleanup();
*/
#else
close(soc);
#endif
}
return retour;
}
static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
htsmoduleStruct * str) {
/* The wrapper_name memebr has changed: not for us anymore */
if (str->wrapper_name == NULL || strcmp(str->wrapper_name, libName) != 0) {
/* Call parent functions if multiple callbacks are chained. */
if (CALLBACKARG_PREV_FUN(carg, parse) != NULL) {
return CALLBACKARG_PREV_FUN(carg, parse) (CALLBACKARG_PREV_CARG(carg),
opt, str);
}
strcpy(str->err_msg,
"unexpected error: bad wrapper_name and no previous wrapper");
return 0; /* Unexpected error */
} else {
if (detect_mime(str)) {
/* (Legacy code) */
char catbuff[CATBUFF_SIZE];
FILE *fpout;
JAVA_HEADER header;
RESP_STRUCT *tab;
const char *file = str->filename;
str->relativeToHtmlLink = 1;
#if JAVADEBUG
printf("fopen\n");
#endif
if ((fpout = FOPEN(fconv(catbuff, sizeof(catbuff), file), "r+b")) == NULL) {
//fprintf(stderr, "Cannot open input file.\n");
sprintf(str->err_msg, "Unable to open file %s", file);
return 0; // une erreur..
}
#if JAVADEBUG
printf("fread\n");
#endif
//if (fread(&header,1,sizeof(JAVA_HEADER),fpout) != sizeof(JAVA_HEADER)) { // pas complet..
if (fread(&header, 1, 10, fpout) != 10) { // pas complet..
fclose(fpout);
sprintf(str->err_msg, "File header too small (file len = " LLintP ")",
(LLint) fsize(file));
return 0;
}
#if JAVADEBUG
printf("header\n");
#endif
// tester en tête
if (reverse_endian()) {
header.magic = hts_swap32(header.magic);
header.count = hts_swap16(header.count);
}
if (header.magic != 0xCAFEBABE) {
sprintf(str->err_msg, "non java file");
if (fpout) {
fclose(fpout);
fpout = NULL;
}
return 0;
}
tab = (RESP_STRUCT *) calloc(header.count, sizeof(RESP_STRUCT));
if (!tab) {
sprintf(str->err_msg, "Unable to alloc %d bytes",
(int) sizeof(RESP_STRUCT));
if (fpout) {
fclose(fpout);
fpout = NULL;
}
return 0; // erreur..
}
#if JAVADEBUG
printf("calchead\n");
#endif
{
int i;
for(i = 1; i < header.count; i++) {
int err = 0; // ++
tab[i] = readtable(str, fpout, tab[i], &err);
if (!err) {
if ((tab[i].type == HTS_LONG) || (tab[i].type == HTS_DOUBLE))
i++; //2 element si double ou float
} else { // ++ une erreur est survenue!
if (strnotempty(str->err_msg) == 0)
strcpy(str->err_msg, "Internal readtable error");
free(tab);
if (fpout) {
fclose(fpout);
fpout = NULL;
}
return 0;
}
}
}
#if JAVADEBUG
printf("addfiles\n");
#endif
{
//unsigned int acess;
unsigned int Class;
unsigned int SClass;
int i;
//acess = readshort(fpout);
Class = readshort(fpout);
SClass = readshort(fpout);
for(i = 1; i < header.count; i++) {
if (tab[i].type == HTS_CLASS) {
if ((tab[i].index1 < header.count) && (tab[i].index1 >= 0)) {
if ((tab[i].index1 != SClass) && (tab[i].index1 != Class)
&& (tab[tab[i].index1].name[0] != '[')) {
if (!strstr(tab[tab[i].index1].name, "java/")) {
char BIGSTK tempo[1024];
tempo[0] = '\0';
sprintf(tempo, "%s.class", tab[tab[i].index1].name);
#if JAVADEBUG
printf("add %s\n", tempo);
#endif
if (tab[tab[i].index1].file_position >= 0)
str->addLink(str, tempo); /* tab[tab[i].index1].file_position */
}
}
} else {
i = header.count; // exit
}
}
}
}
#if JAVADEBUG
printf("end\n");
#endif
free(tab);
if (fpout) {
fclose(fpout);
fpout = NULL;
}
return 1;
} else {
strcpy(str->err_msg, "bad MIME type");
}
}
return 0; /* Error */
}
void help_wizard(httrackp* opt) {
char* urls = (char*) malloct(HTS_URLMAXSIZE*2);
char* mainpath = (char*) malloct(256);
char* projname = (char*) malloct(256);
char* stropt = (char*) malloct(2048); // options
char* stropt2 = (char*) malloct(2048); // options longues
char* strwild = (char*) malloct(2048); // wildcards
char* cmd = (char*) malloct(4096);
char* str = (char*) malloct(256);
char** argv = (char**) malloct(256 * sizeof(char*));
//
char* a;
//
if (urls == NULL || mainpath == NULL || projname == NULL || stropt == NULL
|| stropt2 == NULL || strwild == NULL || cmd == NULL || str == NULL || argv == NULL) {
fprintf(stderr, "* memory exhausted in %s, line %d\n", __FILE__, __LINE__);
return;
}
urls[0] = mainpath[0] = projname[0] = stropt[0] = stropt2[0] = strwild[0] = cmd[0] = str[0] = '\0';
//
strcpybuff(stropt,"-");
mainpath[0]=projname[0]=stropt2[0]=strwild[0]='\0';
//
printf("\n");
printf("Welcome to HTTrack Website Copier (Offline Browser) "HTTRACK_VERSION"%s\n", hts_get_version_info(opt));
printf("Copyright (C) Xavier Roche and other contributors\n");
#ifdef _WIN32
printf("Note: You are running the commandline version,\n");
printf("run 'WinHTTrack.exe' to get the GUI version.\n");
#endif
#ifdef HTTRACK_AFF_WARNING
printf("NOTE: "HTTRACK_AFF_WARNING"\n");
#endif
#ifdef HTS_PLATFORM_NAME
#if USE_BEGINTHREAD
printf("[compiled: "HTS_PLATFORM_NAME" - MT]\n");
#else
printf("[compiled: "HTS_PLATFORM_NAME"]\n");
#endif
#endif
printf("To see the option list, enter a blank line or try httrack --help\n");
//
// Project name
while(strnotempty(projname)==0) {
printf("\n");
printf("Enter project name :");
fflush(stdout);
linput(stdin,projname,250);
if (strnotempty(projname)==0)
help("httrack",1);
}
//
// Path
if (strnotempty(hts_gethome()))
printf("\nBase path (return=%s/websites/) :",hts_gethome());
else
printf("\nBase path (return=current directory) :");
linput(stdin,str,250);
if (!strnotempty(str)) {
strcatbuff(str,hts_gethome());
strcatbuff(str,"/websites/");
}
if (strnotempty(str))
if ((str[strlen(str)-1]!='/') && (str[strlen(str)-1]!='\\'))
strcatbuff(str,"/");
strcatbuff(stropt2,"-O \""); strcatbuff(stropt2,str); strcatbuff(stropt2,projname); strcatbuff(stropt2,"\" ");
// Créer si ce n'est fait un index.html 1er niveau
make_empty_index(str);
//
printf("\n");
printf("Enter URLs (separated by commas or blank spaces) :");
fflush(stdout);
linput(stdin,urls,250);
if (strnotempty(urls)) {
while( (a=strchr(urls,',')) ) *a=' ';
while( (a=strchr(urls,'\t')) ) *a=' ';
// Action
printf("\nAction:\n");
switch(help_query("Mirror Web Site(s)|Mirror Web Site(s) with Wizard|Just Get Files Indicated|Mirror ALL links in URLs (Multiple Mirror)|Test Links In URLs (Bookmark Test)|Update/Continue a Mirror",1)) {
case 1: break;
case 2: strcatbuff(stropt,"W"); break;
case 3: strcatbuff(stropt2,"--get "); break;
case 4: strcatbuff(stropt2,"--mirrorlinks "); break;
case 5: strcatbuff(stropt2,"--testlinks "); break;
case 6: strcatbuff(stropt2,"--update "); break;
case 0: return; break;
}
// Proxy
printf("\nProxy (return=none) :");
linput(stdin,str,250);
if (strnotempty(str)) {
while( (a=strchr(str,' ')) ) *a=':'; // port
if (!strchr(jump_identification(str),':')) {
char str2[256];
printf("\nProxy port (return=8080) :");
linput(stdin,str2,250);
strcatbuff(str,":");
if (strnotempty(str2)==0)
strcatbuff(str,"8080");
else
strcatbuff(str,str2);
}
strcatbuff(stropt2,"-P "); strcatbuff(stropt2,str); strcatbuff(stropt2," ");
}
// Display
strcatbuff(stropt2," -%v ");
// Wildcards
printf("\nYou can define wildcards, like: -*.gif +www.*.com/*.zip -*img_*.zip\n");
printf("Wildcards (return=none) :");
linput(stdin,strwild,250);
// Options
do {
printf("\nYou can define additional options, such as recurse level (-r<number>), separed by blank spaces\n");
printf("To see the option list, type help\n");
printf("Additional options (return=none) :");
linput(stdin,str,250);
if (strfield2(str,"help")) {
help("httrack",2);
} else if (strnotempty(str)) {
strcatbuff(stropt2,str);
strcatbuff(stropt2," ");
}
} while(strfield2(str,"help"));
{
int argc=1;
int g=0;
int i=0;
//
printf("\n");
if (strlen(stropt)==1)
stropt[0]='\0'; // aucune
sprintf(cmd,"%s %s %s %s",urls,stropt,stropt2,strwild);
printf("---> Wizard command line: httrack %s\n\n",cmd);
printf("Ready to launch the mirror? (Y/n) :");
fflush(stdout);
linput(stdin,str,250);
if (strnotempty(str)) {
if (!((str[0]=='y') || (str[0]=='Y')))
return ;
}
printf("\n");
// couper en morceaux
argv[0]="winhttrack";
argv[1]=cmd;
argc++;
while(cmd[i]) {
if(cmd[i]=='\"') g=!g;
if(cmd[i]==' '){
if(!g){
cmd[i]='\0';
argv[argc++]=cmd+i+1;
}
}
i++;
}
hts_main(argc,argv);
}
//} else {
// help("httrack",1);
}
/* Free buffers */
freet(urls);
freet(mainpath);
freet(projname);
freet(stropt);
freet(stropt2);
freet(strwild);
freet(cmd);
freet(str);
}
// la véritable fonction une fois lancées les routines thread/fork
int run_launch_ftp(FTPDownloadStruct * pStruct) {
lien_back *back = pStruct->pBack;
httrackp *opt = pStruct->pOpt;
char user[256] = "anonymous";
char pass[256] = "user@";
char line_retr[2048];
int port = 21;
#if FTP_PASV
int port_pasv = 0;
#endif
char BIGSTK adr_ip[1024];
char *adr, *real_adr;
char *ftp_filename = "";
int timeout = 300; // timeout
int timeout_onfly = 8; // attente réponse supplémentaire
int transfer_list = 0; // directory
int rest_understood = 0; // rest command understood
t_fullhostent fullhostent_buffer; // buffer pour resolver
//
T_SOC soc_ctl = INVALID_SOCKET;
T_SOC soc_servdat = INVALID_SOCKET;
T_SOC soc_dat = INVALID_SOCKET;
//
SOCaddr server_data;
int server_data_size = sizeof(server_data);
//
line_retr[0] = adr_ip[0] = '\0';
timeout = 300;
// effacer
strcpybuff(back->r.msg, "");
back->r.statuscode = 0;
back->r.size = 0;
// récupérer user et pass si présents, et sauter user:id@ dans adr
real_adr = strchr(back->url_adr, ':');
if (real_adr)
real_adr++;
else
real_adr = back->url_adr;
while(*real_adr == '/')
real_adr++; // sauter /
if ((adr = jump_identification(real_adr)) != real_adr) { // user
int i = -1;
pass[0] = '\0';
do {
i++;
user[i] = real_adr[i];
} while((real_adr[i] != ':') && (real_adr[i]));
user[i] = '\0';
if (real_adr[i] == ':') { // pass
int j = -1;
i++; // oui on saute aussi le :
do {
j++;
pass[j] = real_adr[i + j];
} while(((&real_adr[i + j + 1]) < adr) && (real_adr[i + j]));
pass[j] = '\0';
}
}
// Calculer RETR <nom>
{
char *a;
#if 0
a = back->url_fil + strlen(back->url_fil) - 1;
while((a > back->url_fil) && (*a != '/'))
a--;
if (*a != '/') {
a = NULL;
}
#else
a = back->url_fil;
#endif
if (a != NULL && *a != '\0') {
#if 0
a++; // sauter /
#endif
ftp_filename = a;
if (strnotempty(a)) {
char catbuff[CATBUFF_SIZE];
char *ua = unescape_http(catbuff, a);
int len_a = (int) strlen(ua);
if (len_a > 0 && ua[len_a - 1] == '/') { /* obviously a directory listing */
transfer_list = 1;
snprintf(line_retr, sizeof(line_retr), "LIST -A %s", ua);
} else if ((strchr(ua, ' '))
|| (strchr(ua, '\"'))
|| (strchr(ua, '\''))
) {
snprintf(line_retr, sizeof(line_retr), "RETR \"%s\"", ua);
} else { /* Regular one */
snprintf(line_retr, sizeof(line_retr), "RETR %s", ua);
}
} else {
transfer_list = 1;
snprintf(line_retr, sizeof(line_retr), "LIST -A");
}
} else {
strcpybuff(back->r.msg, "Unexpected PORT error");
// back->status=STATUS_FTP_READY; // fini
back->r.statuscode = STATUSCODE_INVALID;
}
}
#if FTP_DEBUG
printf("Connecting to %s...\n", adr);
#endif
// connexion
{
SOCaddr server;
int server_size = sizeof(server);
t_hostent *hp;
char *a;
char _adr[256];
const char *error = "unknown error";
_adr[0] = '\0';
//T_SOC soc_ctl;
// effacer structure
memset(&server, 0, sizeof(server));
// port
a = strchr(adr, ':'); // port
if (a) {
sscanf(a + 1, "%d", &port);
strncatbuff(_adr, adr, (int) (a - adr));
} else
strcpybuff(_adr, adr);
// récupérer adresse résolue
strcpybuff(back->info, "host name");
hp = hts_gethostbyname2(opt, _adr, &fullhostent_buffer, &error);
if (hp == NULL) {
snprintf(back->r.msg, sizeof(back->r.msg),
"Unable to get server's address: %s", error);
// back->status=STATUS_FTP_READY; // fini
back->r.statuscode = STATUSCODE_NON_FATAL;
_HALT_FTP return 0;
}
_CHECK_HALT_FTP;
// copie adresse
SOCaddr_copyaddr(server, server_size, hp->h_addr_list[0], hp->h_length);
// copie adresse pour cnx data
SOCaddr_copyaddr(server_data, server_data_size, hp->h_addr_list[0],
hp->h_length);
// memcpy(&server.sin_addr, hp->h_addr, hp->h_length);
// créer ("attachement") une socket (point d'accès) internet,en flot
soc_ctl = (T_SOC) socket(SOCaddr_sinfamily(server), SOCK_STREAM, 0);
if (soc_ctl == INVALID_SOCKET) {
strcpybuff(back->r.msg, "Unable to create a socket");
// back->status=STATUS_FTP_READY; // fini
back->r.statuscode = STATUSCODE_INVALID;
_HALT_FTP return 0;
}
void LANG_LOAD(char* limit_to) {
CWaitCursor wait;
//
extern int NewLangStrSz;
extern coucal NewLangStr;
extern int NewLangStrKeysSz;
extern coucal NewLangStrKeys;
//
int selected_lang=LANG_T(-1);
//
if (!limit_to) {
LANG_DELETE();
NewLangStr=coucal_new(NewLangStrSz);
NewLangStrKeys=coucal_new(NewLangStrKeysSz);
if ((NewLangStr==NULL) || (NewLangStrKeys==NULL)) {
AfxMessageBox("Error in lang.h: not enough memory");
} else {
coucal_value_is_malloc(NewLangStr,1);
coucal_value_is_malloc(NewLangStrKeys,1);
}
}
TCHAR ModulePath[MAX_PATH + 1];
ModulePath[0] = '\0';
::GetModuleFileName(NULL, ModulePath, sizeof(ModulePath)/sizeof(TCHAR) - 1);
TCHAR* pos = _tcsrchr(ModulePath, '\\');
if (pos != NULL)
{
* ( pos + 1) = '\0';
} else {
ModulePath[0] = '\0';
}
/* Load master file (list of keys and internal keys) */
CString app = ModulePath;
if (!limit_to) {
CString mname=app+"lang.def";
if (!fexist((char*)LPCTSTR(mname)))
mname="lang.def";
FILE* fp=fopen(mname,"rb");
if (fp) {
char intkey[8192];
char key[8192];
while(!feof(fp)) {
linput_cpp(fp,intkey,8000);
linput_cpp(fp,key,8000);
if (strnotempty(intkey) && strnotempty(key)) {
char* test=LANGINTKEY(key);
/* Increment for multiple definitions */
if (strnotempty(test)) {
int increment=0;
size_t pos = strlen(key);
do {
increment++;
sprintf(key+pos,"%d",increment);
test=LANGINTKEY(key);
} while (strnotempty(test));
}
if (!strnotempty(test)) { // éviter doublons
// conv_printf(key,key);
size_t len;
char* buff;
len=strlen(intkey);
buff=(char*)malloc(len+2);
if (buff) {
strcpybuff(buff,intkey);
coucal_add(NewLangStrKeys,key,(intptr_t)buff);
}
}
} // if
} // while
fclose(fp);
} else {
AfxMessageBox("FATAL ERROR\r\n'lang.def' file NOT FOUND!\r\nEnsure that the installation was complete!");
exit(0);
}
}
/* Language Name? */
char* hashname;
{
char name[256];
sprintf(name,"LANGUAGE_%d",selected_lang+1);
hashname=LANGINTKEY(name);
}
/* Get only language name */
if (limit_to) {
if (hashname)
strcpybuff(limit_to,hashname);
else
strcpybuff(limit_to,"???");
return;
}
/* Error */
if (!hashname)
return;
// xxc TEST
/*
setlocale( LC_ALL, "Japanese");
_setmbcp(932); // shift-jis
setlocale( LC_ALL, ".932" );
setlocale( LC_ALL, "[.932]" );
CString st="";
int lid=SetThreadLocale(MAKELCID(MAKELANGID(LANG_JAPANESE,SUBLANG_NEUTRAL),SORT_DEFAULT ));
*/
/* Load specific language file */
{
int loops;
CString err_msg="";
// 2nd loop: load undefined strings
for(loops=0;loops<2;loops++) {
CString lbasename;
{
char name[256];
sprintf(name,"LANGUAGE_%d",(loops==0)?(selected_lang+1):1);
hashname=LANGINTKEY(name);
}
lbasename.Format("lang/%s.txt",hashname);
CString lname=app+lbasename;
if (!fexist((char*)LPCTSTR(lname)))
lname=lbasename;
FILE* fp=fopen(lname,"rb");
if (fp) {
char extkey[8192];
TCHAR value[8192];
while(!feof(fp)) {
//int ssz;
linput_cpp(fp,extkey,8000);
linput_cpp(fp,value,8000);
/*
ssz=linput_cpp(fp,value,8000);
CString st=value;
AfxMessageBox(st);
if (ssz>0) {
int tst=0;
int test=IsTextUnicode(value,ssz,&tst);
unsigned short st2[1024];
int ret=MultiByteToWideChar(CP_UTF8,0,(char*)value,ssz,st2,1024);
if (ret>0) {
char st3[1024]="";
int ret2=WideCharToMultiByte(CP_THREAD_ACP,0,st2,ret,(char*)st3,1024,NULL,FALSE);
if (ret2>0) {
AfxMessageBox(st3);
}
}
}
*/
if (strnotempty(extkey) && strnotempty(value)) {
int len;
char* buff;
char* intkey;
intkey=LANGINTKEY(extkey);
if (strnotempty(intkey)) {
/* Increment for multiple definitions */
{
char* test=LANGSEL(intkey);
if (strnotempty(test)) {
if (loops == 0) {
int increment=0;
size_t pos=strlen(extkey);
do {
increment++;
sprintf(extkey+pos,"%d",increment);
intkey=LANGINTKEY(extkey);
if (strnotempty(intkey))
test=LANGSEL(intkey);
else
test="";
} while (strnotempty(test));
} else
intkey="";
} else {
if (loops > 0) {
err_msg += intkey;
err_msg += " ";
}
}
}
/* Add key */
if (strnotempty(intkey)) {
len = (int) strlen(value);
buff = (char*)malloc(len+2);
if (buff) {
conv_printf(value,buff);
coucal_add(NewLangStr,intkey,(intptr_t)buff);
}
}
}
} // if
} // while
fclose(fp);
} else {
AfxMessageBox("FATAL ERROR\r\n'lang.def' file NOT FOUND!\r\nEnsure that the installation was complete!");
exit(0);
}
}
if (err_msg.GetLength()>0) {
// AfxMessageBox("Error: undefined strings follows:\r\n"+err_msg);
}
}
#if 0
app=app+"lang.h";
if (!fexist((char*)LPCTSTR(app)))
app="lang.h";
FILE* fp=fopen(app,"rb");
if (fp) {
char s[8192];
while(!feof(fp)) {
linput_cpp(fp,s,8000);
if (!strncmp(s,"#define ",8)) {
char* a;
char* name=s+8;
a=name;
while((*a!=' ') && (*a)) a++;
if ((*a) && (strlen(name)>0) && (((int) a - (int) name)<64)) {
*a++='\0';
if (limit_to) {
if (strcmp(name,limit_to))
a=NULL;
}
if (a) {
char* data;
data=a;
int toggle=0;
char* start_str=NULL;
int count=0;
while(*a) {
if (*a=='\"') {
toggle++;
if ((toggle%2)==1) {
if (count==selected_lang) {
start_str=a+1;
}
count++;
} else {
if (start_str) {
char* buff;
int len;
len=(int) a - (int) start_str;
if (len) {
buff=(char*)malloc(len+2);
if (buff) {
int i=0,j=0;
buff[0]='\0';
//strncatbuff(buff,start_str,len);
while(i<len) {
switch(start_str[i]) {
case '\\':
i++;
switch(start_str[i]) {
case 'a': buff[j]='\a'; break;
case 'b': buff[j]='\b'; break;
case 'f': buff[j]='\f'; break;
case 'n': buff[j]='\n'; break;
case 'r': buff[j]='\r'; break;
case 't': buff[j]='\t'; break;
case 'v': buff[j]='\v'; break;
case '\'': buff[j]='\''; break;
case '\"': buff[j]='\"'; break;
case '\\': buff[j]='\\'; break;
case '?': buff[j]='\?'; break;
default: buff[j]=start_str[i]; break;
}
break;
default:
buff[j]=start_str[i];
break;
}
i++;
j++;
}
buff[j++]='\0';
if (!limit_to)
coucal_add(NewLangStr,name,(intptr_t)buff);
else {
strcpybuff(limit_to,buff);
free(buff);
return;
}
}
}
start_str=NULL;
}
}
}
a++;
}
}
//NewLangStr.SetAt(sname,st);
/*
} else {
CString info;
info.Format("Error in lang.h: %s",name);
AfxMessageBox(info);
*/
}
}
}
fclose(fp);
} else {
AfxMessageBox("FATAL ERROR\r\n'lang.h' file NOT FOUND!\r\nEnsure that the installation was complete!");
exit(0);
}
#endif
// Control limit_to
if (limit_to)
limit_to[0]='\0';
// Set locale
if (!limit_to) {
CString charset = LANGUAGE_CHARSET;
charset.TrimLeft();
charset.TrimRight();
charset.MakeLower();
NewLangCP = CP_THREAD_ACP;
NewLangFileCP = CP_THREAD_ACP;
#if 0
if (charset.GetLength() > 0) {
if (charset.Left(9) == "iso-8859-") {
int iso = 0;
int isoCP[] = {0, /* 0 */
1252, /* ISO-8859-1 */
1250, /* ISO-8859-2 */
0, /* ISO-8859-3 */
0, /* ISO-8859-4 */
1251, /* ISO-8859-5 */
1256, /* ISO-8859-6 */
1253, /* ISO-8859-7 */
1255, /* ISO-8859-8 */
1254, /* ISO-8859-9 */
};
if (sscanf(charset.GetBuffer(0) + 9, "%d", &iso) == 1) {
if (iso < sizeof(isoCP)/sizeof(isoCP[0])) {
if (isoCP[iso] != 0) {
NewLangFileCP = isoCP[iso];
}
}
}
} else if (charset.Left(8) == "windows-") {
int windows = 0;
if (sscanf(charset.GetBuffer(0) + 8, "%d", &windows) == 1) {
NewLangFileCP = windows;
}
} else if (charset == "shift-jis") {
NewLangFileCP = 932;
} else if (charset == "big5") {
NewLangFileCP = 950;
} else if (charset == "gb2312") {
NewLangFileCP = 936;
} else {
NewLangFileCP = CP_THREAD_ACP;
}
}
WORD acp = GetACP();
if (NewLangFileCP != CP_THREAD_ACP && NewLangFileCP != acp) {
char* currName = LANGUAGE_WINDOWSID;
LCID thl = GetThreadLocale();
WORD sid = SORTIDFROMLCID(thl);
WORD lid = 0;
WinLangid* lids;
if (currName[0]) {
for( lids = (WinLangid*)&WINDOWS_LANGID ; lids->name != NULL ; lids++ ) {
if (strcmp(currName, lids->name) == 0) {
lid = lids->langId;
break;
}
}
if (lid != 0) {
SetThreadLocale(MAKELCID(lid, sid));
}
}
}
#endif
}
}
/*
Indexing system
A little bit dirty, (quick'n dirty, in fact)
But should be okay on most cases
Tags and javascript handled (ignored)
*/
int index_keyword(const char* html_data,LLint size,const char* mime,const char* filename,const char* indexpath) {
#if HTS_MAKE_KEYWORD_INDEX
char catbuff[CATBUFF_SIZE];
int intag=0,inscript=0,incomment=0;
char keyword[KEYW_LEN+32];
int i=0;
//
int WordIndexSize=1024;
inthash WordIndexHash=NULL;
FILE *tmpfp=NULL;
//
// Check parameters
if (!html_data)
return 0;
if (!size)
return 0;
if (!mime)
return 0;
if (!filename)
return 0;
// Init ?
if (hts_index_init) {
remove(concat(catbuff,indexpath,"index.txt"));
remove(concat(catbuff,indexpath,"sindex.html"));
hts_index_init=0;
}
// Check MIME type
if (is_html_mime_type(mime)) {
inscript=0;
}
// FIXME - temporary fix for image/svg+xml (svg)
// "IN XML" (html like, in fact :) )
else if (
(strfield2(mime,"image/svg+xml"))
||
(strfield2(mime,"image/svg-xml"))
#if HTS_USEMMS
||
strfield2(mime,"video/x-ms-asf")
#endif
) {
inscript=0;
}
else if (
(strfield2(mime,"application/x-javascript"))
|| (strfield2(mime,"text/css"))
) {
inscript=1;
//} else if (strfield2(mime, "text/vnd.wap.wml")) { // humm won't work in many cases
// inscript=0;
} else
return 0;
// Temporary file
tmpfp = tmpfile();
if (!tmpfp)
return 0;
// Create hash structure
// Hash tables rulez da world!
WordIndexHash=inthash_new(WordIndexSize);
if (!WordIndexHash)
return 0;
// Start indexing this page
keyword[0]='\0';
while(i<size) {
if (strfield(html_data + i , "<script")) {
inscript=1;
}
else if (strfield(html_data + i , "<!--")) {
incomment=1;
}
else if (strfield(html_data + i , "</script")) {
if (!incomment)
inscript=0;
}
else if (strfield(html_data + i , "-->")) {
incomment=0;
}
else if (html_data[i]=='<') {
if (!inscript)
intag=1;
}
else if (html_data[i]=='>') {
intag=0;
}
else {
// Okay, parse keywords
if ( (!inscript) && (!incomment) && (!intag) ) {
char cchar=html_data[i];
int pos;
int len = (int) strlen(keyword);
// Replace (ignore case, and so on..)
if ((pos=strcpos(KEYW_TRANSCODE_FROM,cchar))>=0)
cchar=KEYW_TRANSCODE_TO[pos];
if (strchr(KEYW_ACCEPT,cchar)) {
/* Ignore some characters at begining */
if ((len>0) || (!strchr(KEYW_IGNORE_BEG,cchar))) {
keyword[len++]=cchar;
keyword[len]='\0';
}
} else if ( (strchr(KEYW_SPACE,cchar)) || (!cchar) ) {
/* Avoid these words */
if (len>0) {
if (strchr(KEYW_NOT_BEG,keyword[0])) {
keyword[(len=0)]='\0';
}
}
/* Strip ending . and so */
{
int ok=0;
while((len = (int) strlen(keyword)) && (!ok)) {
if (strchr(KEYW_STRIP_END,keyword[len-1])) { /* strip it */
keyword[len-1]='\0';
} else
ok=1;
}
}
/* Store it ? */
if (len >= KEYW_MIN_LEN ) {
hts_primindex_words++;
if (inthash_inc(WordIndexHash,keyword)) { /* added new */
fprintf(tmpfp,"%s\n",keyword);
}
}
keyword[(len=0)]='\0';
} else /* Invalid */
keyword[(len=0)]='\0';
if (len>KEYW_LEN) {
keyword[(len=0)]='\0';
}
}
}
i++;
}
// Reset temp file
fseek(tmpfp,0,SEEK_SET);
// Process indexing for this page
{
//FILE* fp=NULL;
//fp=fopen(concat(indexpath,"index.txt"),"ab");
if (fp_tmpproject) {
while(!feof(tmpfp)) {
char line[KEYW_LEN + 32];
linput(tmpfp,line,KEYW_LEN + 2);
if (strnotempty(line)) {
intptr_t e=0;
if (inthash_read(WordIndexHash,line,&e)) {
//if (e) {
char BIGSTK savelst[HTS_URLMAXSIZE*2];
e++; /* 0 means "once" */
if (strncmp((const char*)fslash(catbuff,(char*)indexpath),filename,strlen(indexpath))==0) // couper
strcpybuff(savelst,filename+strlen(indexpath));
else
strcpybuff(savelst,filename);
// Add entry for this file and word
fprintf(fp_tmpproject,"%s %d %s\n",line,(int) (KEYW_SORT_MAXCOUNT - e),savelst);
hts_primindex_size++;
//}
}
}
}
//fclose(fp);
}
}
// Delete temp file
fclose(tmpfp);
tmpfp=NULL;
// Clear hash table
inthash_delete(&WordIndexHash);
#endif
return 1;
}
int __cdecl htsshow_loop(t_hts_callbackarg *carg, httrackp *opt, lien_back* back,int back_max,int back_index,int lien_n,int lien_tot,int stat_time, hts_stat_struct* stats) { // appelé à chaque boucle de HTTrack
static TStamp prev_mytime=0; /* ok */
static t_InpInfo SInfo; /* ok */
//
TStamp mytime;
long int rate=0;
//
int stat_written=-1;
int stat_updated=-1;
int stat_errors=-1;
int stat_warnings=-1;
int stat_infos=-1;
int nbk=-1;
LLint nb=-1;
int stat_nsocket=-1;
LLint stat_bytes=-1;
LLint stat_bytes_recv=-1;
int irate=-1;
//
char st[256];
/* Exit now */
if (commandEndRequested == 2)
return 0;
/* Lock */
webhttrack_lock();
if (stats) {
stat_written=stats->stat_files;
stat_updated=stats->stat_updated_files;
stat_errors=stats->stat_errors;
stat_warnings=stats->stat_warnings;
stat_infos=stats->stat_infos;
nbk=stats->nbk;
stat_nsocket=stats->stat_nsocket;
irate=(int)stats->rate;
nb=stats->nb;
stat_bytes=stats->nb;
stat_bytes_recv=stats->HTS_TOTAL_RECV;
}
mytime=mtime_local();
if ((stat_time>0) && (stat_bytes_recv>0))
rate=(int)(stat_bytes_recv/stat_time);
else
rate=0; // pas d'infos
/* Infos */
if (stat_bytes>=0) SInfo.stat_bytes=stat_bytes; // bytes
if (stat_time>=0) SInfo.stat_time=stat_time; // time
if (lien_tot>=0) SInfo.lien_tot=lien_tot; // nb liens
if (lien_n>=0) SInfo.lien_n=lien_n; // scanned
SInfo.stat_nsocket=stat_nsocket; // socks
if (rate>0) SInfo.rate=rate; // rate
if (irate>=0) SInfo.irate=irate; // irate
if (SInfo.irate<0) SInfo.irate=SInfo.rate;
if (nbk>=0) SInfo.stat_back=nbk;
if (stat_written>=0) SInfo.stat_written=stat_written;
if (stat_updated>=0) SInfo.stat_updated=stat_updated;
if (stat_errors>=0) SInfo.stat_errors=stat_errors;
if (stat_warnings>=0) SInfo.stat_warnings=stat_warnings;
if (stat_infos>=0) SInfo.stat_infos=stat_infos;
st[0]='\0';
qsec2str(st,stat_time);
/* Set keys */
smallserver_setkeyint("info.stat_bytes", SInfo.stat_bytes);
smallserver_setkeyint("info.stat_time", SInfo.stat_time);
smallserver_setkeyint("info.lien_tot", SInfo.lien_tot);
smallserver_setkeyint("info.lien_n", SInfo.lien_n);
smallserver_setkeyint("info.stat_nsocket", SInfo.stat_nsocket);
smallserver_setkeyint("info.rate", SInfo.rate);
smallserver_setkeyint("info.irate", SInfo.irate);
smallserver_setkeyint("info.stat_back", SInfo.stat_back);
smallserver_setkeyint("info.stat_written", SInfo.stat_written);
smallserver_setkeyint("info.stat_updated", SInfo.stat_updated);
smallserver_setkeyint("info.stat_errors", SInfo.stat_errors);
smallserver_setkeyint("info.stat_warnings", SInfo.stat_warnings);
smallserver_setkeyint("info.stat_infos", SInfo.stat_infos);
/* */
smallserver_setkey("info.stat_time_str", st);
if ( ((mytime - prev_mytime)>100) || ((mytime - prev_mytime)<0) ) {
prev_mytime=mytime;
// parcourir registre des liens
if (back_index>=0 && back_max > 0) { // seulement si index passé
int j,k;
int index=0;
int ok=0; // idem
int l; // idem
//
t_StatsBuffer StatsBuffer[NStatsBuffer];
{
int i;
for(i=0;i<NStatsBuffer;i++) {
strcpybuff(StatsBuffer[i].state,"");
strcpybuff(StatsBuffer[i].name,"");
strcpybuff(StatsBuffer[i].file,"");
strcpybuff(StatsBuffer[i].url_sav,"");
StatsBuffer[i].back=0;
StatsBuffer[i].size=0;
StatsBuffer[i].sizetot=0;
}
}
for(k=0;k<2;k++) { // 0: lien en cours 1: autres liens
for(j=0;(j<3) && (index<NStatsBuffer);j++) { // passe de priorité
int _i;
for(_i=0+k;(_i< max(back_max*k,1) ) && (index<NStatsBuffer);_i++) { // no lien
int i=(back_index+_i)%back_max; // commencer par le "premier" (l'actuel)
if (back[i].status>=0) { // signifie "lien actif"
// int ok=0; // OPTI
ok=0;
switch(j) {
case 0: // prioritaire
if ((back[i].status>0) && (back[i].status<99)) {
strcpybuff(StatsBuffer[index].state,"receive"); ok=1;
}
break;
case 1:
if (back[i].status==STATUS_WAIT_HEADERS) {
strcpybuff(StatsBuffer[index].state,"request"); ok=1;
}
else if (back[i].status==STATUS_CONNECTING) {
strcpybuff(StatsBuffer[index].state,"connect"); ok=1;
}
else if (back[i].status==STATUS_WAIT_DNS) {
strcpybuff(StatsBuffer[index].state,"search"); ok=1;
}
else if (back[i].status==STATUS_FTP_TRANSFER) { // ohh le beau ftp
char proto[] = "ftp";
if (back[i].url_adr[0]) {
char* ep = strchr(back[i].url_adr, ':');
char* eps = strchr(back[i].url_adr, '/');
int count;
if (ep != NULL && ep < eps && (count = (int) (ep - back[i].url_adr) ) < 4) {
proto[0] = '\0';
strncat(proto, back[i].url_adr, count);
}
}
sprintf(StatsBuffer[index].state,"%s: %s",proto,back[i].info); ok=1;
}
break;
default:
if (back[i].status==STATUS_READY) { // prêt
if ((back[i].r.statuscode==HTTP_OK)) {
strcpybuff(StatsBuffer[index].state,"ready"); ok=1;
}
else if ((back[i].r.statuscode>=100) && (back[i].r.statuscode<=599)) {
char tempo[256]; tempo[0]='\0';
infostatuscode(tempo,back[i].r.statuscode);
strcpybuff(StatsBuffer[index].state,tempo); ok=1;
}
else {
strcpybuff(StatsBuffer[index].state,"error"); ok=1;
}
}
break;
}
if (ok) {
char s[HTS_URLMAXSIZE*2];
//
StatsBuffer[index].back=i; // index pour + d'infos
//
s[0]='\0';
strcpybuff(StatsBuffer[index].url_sav,back[i].url_sav); // pour cancel
if (strcmp(back[i].url_adr,"file://"))
strcatbuff(s,back[i].url_adr);
else
strcatbuff(s,"localhost");
if (back[i].url_fil[0]!='/')
strcatbuff(s,"/");
strcatbuff(s,back[i].url_fil);
StatsBuffer[index].file[0]='\0';
{
char* a=strrchr(s,'/');
if (a) {
strncatbuff(StatsBuffer[index].file,a,200);
*a='\0';
}
}
if ((l = (int) strlen(s))<MAX_LEN_INPROGRESS)
strcpybuff(StatsBuffer[index].name,s);
else {
// couper
StatsBuffer[index].name[0]='\0';
strncatbuff(StatsBuffer[index].name,s,MAX_LEN_INPROGRESS/2-2);
strcatbuff(StatsBuffer[index].name,"...");
strcatbuff(StatsBuffer[index].name,s+l-MAX_LEN_INPROGRESS/2+2);
}
if (back[i].r.totalsize>0) { // taille prédéfinie
StatsBuffer[index].sizetot=back[i].r.totalsize;
StatsBuffer[index].size=back[i].r.size;
} else { // pas de taille prédéfinie
if (back[i].status==STATUS_READY) { // prêt
StatsBuffer[index].sizetot=back[i].r.size;
StatsBuffer[index].size=back[i].r.size;
} else {
StatsBuffer[index].sizetot=8192;
StatsBuffer[index].size=(back[i].r.size % 8192);
}
}
index++;
}
}
}
}
}
/* Display current job */
{
int parsing=0;
if (commandEndRequested)
smallserver_setkey("info.currentjob", "finishing pending transfers - Select [Cancel] to stop now!");
else if (!(parsing=hts_is_parsing(opt, -1)))
smallserver_setkey("info.currentjob", "receiving files");
else {
char tmp[1024];
tmp[0] = '\0';
switch(hts_is_testing(opt)) {
case 0:
sprintf(tmp, "parsing HTML file (%d%%)",parsing);
break;
case 1:
sprintf(tmp, "parsing HTML file: testing links (%d%%)",parsing);
break;
case 2:
sprintf(tmp, "purging files");
break;
case 3:
sprintf(tmp, "loading cache");
break;
case 4:
sprintf(tmp, "waiting (scheduler)");
break;
case 5:
sprintf(tmp, "waiting (throttle)");
break;
}
smallserver_setkey("info.currentjob", tmp);
}
}
/* Display background jobs */
{
int i;
for(i=0;i<NStatsBuffer;i++) {
if (strnotempty(StatsBuffer[i].state)) {
strc_int2bytes2 strc;
smallserver_setkeyarr("info.state[", i, "]", StatsBuffer[i].state);
smallserver_setkeyarr("info.name[", i, "]", StatsBuffer[i].name);
smallserver_setkeyarr("info.file[", i, "]", StatsBuffer[i].file);
smallserver_setkeyarr("info.size[", i, "]", int2bytes(&strc,StatsBuffer[i].size));
smallserver_setkeyarr("info.sizetot[", i, "]", int2bytes(&strc,StatsBuffer[i].sizetot));
smallserver_setkeyarr("info.url_adr[", i, "]", StatsBuffer[i].url_adr);
smallserver_setkeyarr("info.url_fil[", i, "]", StatsBuffer[i].url_fil);
smallserver_setkeyarr("info.url_sav[", i, "]", StatsBuffer[i].url_sav);
}
}
}
}
}
/* UnLock */
webhttrack_release();
return 1;
}
static int hts_acceptlink_(httrackp* opt,
int ptr,int lien_tot,lien_url** liens,
char* adr,char* fil,
char* tag, char* attribute,
int* set_prio_to,
int* just_test_it)
{
int forbidden_url=-1;
int meme_adresse;
int embedded_triggered = 0;
#define _FILTERS (*opt->filters.filters)
#define _FILTERS_PTR (opt->filters.filptr)
#define _ROBOTS ((robots_wizard*)opt->robotsptr)
int may_set_prio_to=0;
// -------------------- PHASE 0 --------------------
/* Infos */
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"wizard test begins: %s%s"LF,adr,fil);
test_flush;
}
/* Already exists? Then, we know that we knew that this link had to be known */
if (adr[0] != '\0'
&& fil[0] != '\0'
&& opt->hash != NULL
&& hash_read(opt->hash, adr, fil, 1, opt->urlhack) >= 0
) {
return 0; /* Yokai */
}
// -------------------- PRELUDE OF PHASE 3-BIS --------------------
/* Built-in known tags (<img src=..>, ..) */
if (forbidden_url != 0 && opt->nearlink && tag != NULL && attribute != NULL) {
int i;
for(i = 0 ; hts_detect_embed[i].tag != NULL ; i++) {
if (cmp_token(tag, hts_detect_embed[i].tag)
&& cmp_token(attribute, hts_detect_embed[i].attr)
)
{
embedded_triggered = 1;
break;
}
}
}
// -------------------- PHASE 1 --------------------
/* Doit-on traiter les non html? */
if ((opt->getmode & 2)==0) { // non on ne doit pas
if (!ishtml(opt,fil)) { // non il ne faut pas
//adr[0]='\0'; // ne pas traiter ce lien, pas traiter
forbidden_url=1; // interdire récupération du lien
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"non-html file ignored at %s : %s"LF,adr,fil);
test_flush;
}
}
}
/* Niveau 1: ne pas parser suivant! */
if (ptr>0) {
if ( ( liens[ptr]->depth <= 0 ) || ( liens[ptr]->depth <= 1 && !embedded_triggered ) ) {
forbidden_url=1; // interdire récupération du lien
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"file from too far level ignored at %s : %s"LF,adr,fil);
test_flush;
}
}
}
/* en cas d'échec en phase 1, retour immédiat! */
if (forbidden_url == 1) {
return forbidden_url;
}
// -------------------- PHASE 2 --------------------
// ------------------------------------------------------
// doit-on traiter ce lien?.. vérifier droits de déplacement
meme_adresse=strfield2(adr,urladr);
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG);
if (meme_adresse)
fprintf(opt->log,"Compare addresses: %s=%s"LF,adr,urladr);
else
fprintf(opt->log,"Compare addresses: %s!=%s"LF,adr,urladr);
test_flush;
}
if (meme_adresse) { // même adresse
{ // tester interdiction de descendre
// MODIFIE : en cas de remontée puis de redescente, il se pouvait qu'on ne puisse pas atteindre certains fichiers
// problème: si un fichier est virtuellement accessible via une page mais dont le lien est sur une autre *uniquement*..
char BIGSTK tempo[HTS_URLMAXSIZE*2];
char BIGSTK tempo2[HTS_URLMAXSIZE*2];
tempo[0] = tempo2[0] = '\0';
// note (up/down): on calcule à partir du lien primaire, ET du lien précédent.
// ex: si on descend 2 fois on peut remonter 1 fois
if (lienrelatif(tempo,fil,liens[liens[ptr]->premier]->fil)==0) {
if (lienrelatif(tempo2,fil,liens[ptr]->fil)==0) {
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"build relative links to test: %s %s (with %s and %s)"LF,tempo,tempo2,liens[liens[ptr]->premier]->fil,liens[ptr]->fil);
test_flush;
}
// si vient de primary, ne pas tester lienrelatif avec (car host "différent")
/*if (liens[liens[ptr]->premier] == 0) { // vient de primary
}
*/
// NEW: finalement OK, sauf pour les moved repérés par link_import
// PROBLEME : annulé a cause d'un lien éventuel isolé accepté..qui entrainerait un miroir
// (test même niveau (NOUVEAU à cause de certains problèmes de filtres non intégrés))
// NEW
if (
(tempo[0] != '\0' && tempo[1] != '\0' && strchr(tempo+1,'/') == 0)
||
(tempo2[0] != '\0' && tempo2[1] != '\0' && strchr(tempo2+1,'/') == 0)
) {
if (!liens[ptr]->link_import) { // ne résulte pas d'un 'moved'
forbidden_url=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"same level link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
// down
if ( (strncmp(tempo,"../",3)) || (strncmp(tempo2,"../",3))) { // pas montée sinon ne nbous concerne pas
int test1,test2;
if (!strncmp(tempo,"../",3))
test1=0;
else
test1 = (strchr(tempo +((*tempo =='/')?1:0),'/')!=NULL);
if (!strncmp(tempo2,"../",3))
test2=0;
else
test2 = (strchr(tempo2+((*tempo2=='/')?1:0),'/')!=NULL);
if ( (test1) && (test2) ) { // on ne peut que descendre
if ((opt->seeker & 1)==0) { // interdiction de descendre
forbidden_url=1;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"lower link canceled: %s%s"LF,adr,fil);
test_flush;
}
} else { // autorisé à priori - NEW
if (!liens[ptr]->link_import) { // ne résulte pas d'un 'moved'
forbidden_url=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"lower link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
} else if ( (test1) || (test2) ) { // on peut descendre pour accéder au lien
if ((opt->seeker & 1)!=0) { // on peut descendre - NEW
if (!liens[ptr]->link_import) { // ne résulte pas d'un 'moved'
forbidden_url=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"lower link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
}
}
// up
if ( (!strncmp(tempo,"../",3)) && (!strncmp(tempo2,"../",3)) ) { // impossible sans monter
if ((opt->seeker & 2)==0) { // interdiction de monter
forbidden_url=1;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"upper link canceled: %s%s"LF,adr,fil);
test_flush;
}
} else { // autorisé à monter - NEW
if (!liens[ptr]->link_import) { // ne résulte pas d'un 'moved'
forbidden_url=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"upper link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
} else if ( (!strncmp(tempo,"../",3)) || (!strncmp(tempo2,"../",3)) ) { // Possible en montant
if ((opt->seeker & 2)!=0) { // autorisé à monter - NEW
if (!liens[ptr]->link_import) { // ne résulte pas d'un 'moved'
forbidden_url=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"upper link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
} // sinon autorisé en descente
}
} else {
if (opt->log) {
fprintf(opt->log,"Error building relative link %s and %s"LF,fil,liens[ptr]->fil);
test_flush;
}
}
} else {
if (opt->log) {
fprintf(opt->log,"Error building relative link %s and %s"LF,fil,liens[liens[ptr]->premier]->fil);
test_flush;
}
}
} // tester interdiction de descendre?
{ // tester interdiction de monter
char BIGSTK tempo[HTS_URLMAXSIZE*2];
char BIGSTK tempo2[HTS_URLMAXSIZE*2];
if (lienrelatif(tempo,fil,liens[liens[ptr]->premier]->fil)==0) {
if (lienrelatif(tempo2,fil,liens[ptr]->fil)==0) {
} else {
if (opt->log) {
fprintf(opt->log,"Error building relative link %s and %s"LF,fil,liens[ptr]->fil);
test_flush;
}
}
} else {
if (opt->log) {
fprintf(opt->log,"Error building relative link %s and %s"LF,fil,liens[liens[ptr]->premier]->fil);
test_flush;
}
}
} // fin tester interdiction de monter
} else { // adresse différente, sortir?
//if (!opt->wizard) { // mode non wizard
// doit-on traiter ce lien?.. vérifier droits de sortie
switch((opt->travel & 255)) {
case 0:
if (!opt->wizard) // mode non wizard
forbidden_url=1; break; // interdicton de sortir au dela de l'adresse
case 1: { // sortie sur le même dom.xxx
size_t i = strlen(adr)-1;
size_t j = strlen(urladr)-1;
while( (i>0) && (adr[i]!='.')) i--;
while( (j>0) && (urladr[j]!='.')) j--;
i--; j--;
while( (i>0) && (adr[i]!='.')) i--;
while( (j>0) && (urladr[j]!='.')) j--;
if ((i>0) && (j>0)) {
if (!strfield2(adr+i,urladr+j)) { // !=
if (!opt->wizard) { // mode non wizard
//printf("refused: %s\n",adr);
forbidden_url=1; // pas même domaine
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"foreign domain link canceled: %s%s"LF,adr,fil);
test_flush;
}
}
} else {
if (opt->wizard) { // mode wizard
forbidden_url=0; // même domaine
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"same domain link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
} else
forbidden_url=1;
}
break;
case 2: { // sortie sur le même .xxx
size_t i = strlen(adr)-1;
size_t j = strlen(urladr)-1;
while( (i>0) && (adr[i]!='.')) i--;
while( (j>0) && (urladr[j]!='.')) j--;
if ((i>0) && (j>0)) {
if (!strfield2(adr+i,urladr+j)) { // !-
if (!opt->wizard) { // mode non wizard
//printf("refused: %s\n",adr);
forbidden_url=1; // pas même .xx
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"foreign location link canceled: %s%s"LF,adr,fil);
test_flush;
}
}
} else {
if (opt->wizard) { // mode wizard
forbidden_url=0; // même domaine
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"same location link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
} else forbidden_url=1;
}
break;
case 7: // everywhere!!
if (opt->wizard) { // mode wizard
forbidden_url=0;
break;
}
} // switch
// ANCIENNE POS -- récupérer les liens à côtés d'un lien (nearlink)
} // fin test adresse identique/différente
// -------------------- PHASE 3 --------------------
// récupérer les liens à côtés d'un lien (nearlink) (nvelle pos)
if (forbidden_url != 0 && opt->nearlink) {
if (!ishtml(opt,fil)) { // non html
//printf("ok %s%s\n",ad,fil);
forbidden_url=0; // autoriser
may_set_prio_to=1+1; // set prio to 1 (parse but skip urls) if near is the winner
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"near link authorized: %s%s"LF,adr,fil);
test_flush;
}
}
}
// -------------------- PHASE 3-BIS --------------------
/* Built-in known tags (<img src=..>, ..) */
if (forbidden_url != 0 && embedded_triggered) {
forbidden_url=0; // autoriser
may_set_prio_to=1+1; // set prio to 1 (parse but skip urls) if near is the winner
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"near link authorized (friendly tag): %s%s"LF,adr,fil);
test_flush;
}
}
// -------------------- PHASE 4 --------------------
// ------------------------------------------------------
// Si wizard, il se peut qu'on autorise ou qu'on interdise
// un lien spécial avant même de tester sa position, sa hiérarchie etc.
// peut court-circuiter le forbidden_url précédent
if (opt->wizard) { // le wizard entre en action..
//
int question=1; // poser une question
int force_mirror=0; // pour mirror links
int filters_answer=0; // décision prise par les filtres
char BIGSTK l[HTS_URLMAXSIZE*2];
char BIGSTK lfull[HTS_URLMAXSIZE*2];
if (forbidden_url!=-1) question=0; // pas de question, résolu
// former URL complète du lien actuel
strcpybuff(l,jump_identification(adr));
if (*fil!='/') strcatbuff(l,"/");
strcatbuff(l,fil);
// full version (http://foo:[email protected]/bar.html)
if (!link_has_authority(adr))
strcpybuff(lfull,"http://");
else
lfull[0]='\0';
strcatbuff(lfull,adr);
if (*fil!='/') strcatbuff(lfull,"/");
strcatbuff(lfull,fil);
// tester filters (URLs autorisées ou interdites explicitement)
// si lien primaire on saute le joker, on est pas lémur
if (ptr==0) { // lien primaire, autoriser
question=1; // la question sera résolue automatiquement
forbidden_url=0;
may_set_prio_to=0; // clear may-set flag
} else {
// eternal depth first
// vérifier récursivité extérieure
if (opt->extdepth>0) {
if ( /*question && */ (ptr>0) && (!force_mirror)) {
// well, this is kinda a hak
// we don't want to mirror EVERYTHING, and we have to decide where to stop
// there is no way yet to tag "external" links, and therefore links that are
// "weak" (authorized depth < external depth) are just not considered for external
// hack
if (liens[ptr]->depth > opt->extdepth) {
// *set_prio_to = opt->extdepth + 1;
*set_prio_to = 1 + (opt->extdepth);
may_set_prio_to=0; // clear may-set flag
forbidden_url=0; // autorisé
question=0; // résolution auto
if ((opt->debug>1) && (opt->log!=NULL)) {
if (question) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) ambiguous link accepted (external depth): link %s at %s%s"LF,l,urladr,urlfil);
} else {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) forced to accept link (external depth): link %s at %s%s"LF,l,urladr,urlfil);
}
test_flush;
}
}
}
}
// filters
{
int jok;
char* mdepth="";
// filters, 0=sait pas 1=ok -1=interdit
{
int jokDepth1=0,jokDepth2=0;
int jok1=0,jok2=0;
jok1 = fa_strjoker(/*url*/0, _FILTERS,*_FILTERS_PTR,lfull,NULL,NULL,&jokDepth1);
jok2 = fa_strjoker(/*url*/0, _FILTERS,*_FILTERS_PTR,l, NULL,NULL,&jokDepth2);
if (jok2 == 0) { // #2 doesn't know
jok = jok1; // then, use #1
mdepth = _FILTERS[jokDepth1];
} else if (jok1 == 0) { // #1 doesn't know
jok = jok2; // then, use #2
mdepth = _FILTERS[jokDepth2];
} else if (jokDepth1 >= jokDepth2) { // #1 matching rule is "after" #2, then it is prioritary
jok = jok1;
mdepth = _FILTERS[jokDepth1];
} else { // #2 matching rule is "after" #1, then it is prioritary
jok = jok2;
mdepth = _FILTERS[jokDepth2];
}
}
if (jok == 1) { // autorisé
filters_answer=1; // décision prise par les filtres
question=0; // ne pas poser de question, autorisé
forbidden_url=0; // URL autorisée
may_set_prio_to=0; // clear may-set flag
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) explicit authorized (%s) link: link %s at %s%s"LF,mdepth,l,urladr,urlfil);
test_flush;
}
} else if (jok == -1) { // forbidden
filters_answer=1; // décision prise par les filtres
question=0; // ne pas poser de question:
forbidden_url=1; // URL interdite
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) explicit forbidden (%s) link: link %s at %s%s"LF,mdepth,l,urladr,urlfil);
test_flush;
}
} // sinon on touche à rien
}
}
// vérifier mode mirror links
if (question) {
if (opt->mirror_first_page) { // mode mirror links
if (liens[ptr]->precedent==0) { // parent=primary!
forbidden_url=0; // autorisé
may_set_prio_to=0; // clear may-set flag
question=1; // résolution auto
force_mirror=5; // mirror (5)
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) explicit mirror link: link %s at %s%s"LF,l,urladr,urlfil);
test_flush;
}
}
}
}
// on doit poser la question.. peut on la poser?
// (oui je sais quel preuve de délicatesse, merci merci)
if ((question) && (ptr>0) && (!force_mirror)) {
if (opt->wizard==2) { // éliminer tous les liens non répertoriés comme autorisés (ou inconnus)
question=0;
forbidden_url=1;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) ambiguous forbidden link: link %s at %s%s"LF,l,urladr,urlfil);
test_flush;
}
}
}
// vérifier robots.txt
if (opt->robots) {
int r = checkrobots(_ROBOTS,adr,fil);
if (r == -1) { // interdiction
#if DEBUG_ROBOTS
printf("robots.txt forbidden: %s%s\n",adr,fil);
#endif
// question résolue, par les filtres, et mode robot non strict
if ((!question) && (filters_answer) && (opt->robots == 1) && (forbidden_url!=1)) {
r=0; // annuler interdiction des robots
if (!forbidden_url) {
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"Warning link followed against robots.txt: link %s at %s%s"LF,l,adr,fil);
test_flush;
}
}
}
if (r == -1) { // interdire
forbidden_url=1;
question=0;
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(robots.txt) forbidden link: link %s at %s%s"LF,l,adr,fil);
test_flush;
}
}
}
}
if (!question) {
if ((opt->debug>1) && (opt->log!=NULL)) {
if (!forbidden_url) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) shared foreign domain link: link %s at %s%s"LF,l,urladr,urlfil);
} else {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"(wizard) cancelled foreign domain link: link %s at %s%s"LF,l,urladr,urlfil);
}
test_flush;
}
#if BDEBUG==3
printf("at %s in %s, wizard says: url %s ",urladr,urlfil,l);
if (forbidden_url) printf("cancelled"); else printf(">SHARED<");
printf("\n");
#endif
}
/* en cas de question, ou lien primaire (enregistrer autorisations) */
if (question || (ptr==0)) {
const char* s;
int n=0;
// si primaire (plus bas) alors ...
if ((ptr!=0) && (force_mirror==0)) {
char BIGSTK tempo[HTS_URLMAXSIZE*2];
tempo[0]='\0';
strcatbuff(tempo,adr);
strcatbuff(tempo,fil);
s = RUN_CALLBACK1(opt, query3, tempo);
if (strnotempty(s)==0) // entrée
n=0;
else if (isdigit((unsigned char)*s))
sscanf(s,"%d",&n);
else {
switch(*s) {
case '*': n=-1; break;
case '!': n=-999; {
/*char *a;
int i;
a=copie_de_adr-128;
if (a<r.adr) a=r.adr;
for(i=0;i<256;i++) {
if (a==copie_de_adr) printf("\nHERE:\n");
printf("%c",*a++);
}
printf("\n\n");
*/
}
break;
default: n=-999; printf("What did you say?\n"); break;
}
}
io_flush;
} else { // lien primaire: autoriser répertoire entier
if (!force_mirror) {
if ((opt->seeker & 1)==0) { // interdiction de descendre
n=7;
} else {
n=5; // autoriser miroir répertoires descendants (lien primaire)
}
} else // forcer valeur (sub-wizard)
n=force_mirror;
}
/* sanity check - reallocate filters HERE */
if ((*_FILTERS_PTR) + 1 >= opt->maxfilter) {
opt->maxfilter += HTS_FILTERSINC;
if (filters_init(&_FILTERS, opt->maxfilter, HTS_FILTERSINC) == 0) {
printf("PANIC! : Too many filters : >%d [%d]\n", (*_FILTERS_PTR),__LINE__);
fflush(stdout);
if (opt->log) {
fprintf(opt->log,LF"Too many filters, giving up..(>%d)"LF, (*_FILTERS_PTR) );
fprintf(opt->log,"To avoid that: use #F option for more filters (example: -#F5000)"LF);
test_flush;
}
assertf("too many filters - giving up" == NULL); // wild..
}
}
// here we have enough room for a new filter if necessary
switch(n) {
case -1: // sauter tout le reste
forbidden_url=1;
opt->wizard=2; // sauter tout le reste
break;
case 0: // interdire les mêmes liens: adr/fil
forbidden_url=1;
HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"-");
strcatbuff(_FILTERS[0],jump_identification(adr));
if (*fil!='/') strcatbuff(_FILTERS[0],"/");
strcatbuff(_FILTERS[0],fil);
break;
case 1: // éliminer répertoire entier et sous rép: adr/path/ *
forbidden_url=1;
{
size_t i = strlen(fil)-1;
while((fil[i]!='/') && (i>0)) i--;
if (fil[i]=='/') {
HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"-");
strcatbuff(_FILTERS[0],jump_identification(adr));
if (*fil!='/') strcatbuff(_FILTERS[0],"/");
strncatbuff(_FILTERS[0] ,fil,i);
if (_FILTERS[0][strlen(_FILTERS[0])-1]!='/')
strcatbuff(_FILTERS[0],"/");
strcatbuff(_FILTERS[0],"*");
}
}
// ** ...
break;
case 2: // adresse adr*
forbidden_url=1;
HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"-");
strcatbuff(_FILTERS[0],jump_identification(adr));
strcatbuff(_FILTERS[0],"*");
break;
case 3: // ** A FAIRE
forbidden_url=1;
/*
{
int i=strlen(adr)-1;
while((adr[i]!='/') && (i>0)) i--;
if (i>0) {
}
}*/
break;
//
case 4: // same link
// PAS BESOIN!!
/*HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"+");
strcatbuff(_FILTERS[0],adr);
if (*fil!='/') strcatbuff(_FILTERS[0],"/");
strcatbuff(_FILTERS[0],fil);*/
// étant donné le renversement wizard/primary filter (les primary autorisent up/down ET interdisent)
// il faut éviter d'un lien isolé effectue un miroir total..
*set_prio_to = 0+1; // niveau de récursion=0 (pas de miroir)
break;
case 5: // autoriser répertoire entier et fils
if ((opt->seeker & 2)==0) { // interdiction de monter
size_t i = strlen(fil)-1;
while((fil[i]!='/') && (i>0)) i--;
if (fil[i]=='/') {
HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"+");
strcatbuff(_FILTERS[0],jump_identification(adr));
if (*fil!='/') strcatbuff(_FILTERS[0],"/");
strncatbuff(_FILTERS[0],fil,i+1);
strcatbuff(_FILTERS[0],"*");
}
} else { // autoriser domaine alors!!
HT_INSERT_FILTERS0; // insérer en 0 strcpybuff(filters[filptr],"+");
strcpybuff(_FILTERS[0],"+");
strcatbuff(_FILTERS[0],jump_identification(adr));
strcatbuff(_FILTERS[0],"*");
}
break;
case 6: // same domain
HT_INSERT_FILTERS0; // insérer en 0 strcpybuff(filters[filptr],"+");
strcpybuff(_FILTERS[0],"+");
strcatbuff(_FILTERS[0],jump_identification(adr));
strcatbuff(_FILTERS[0],"*");
break;
//
case 7: // autoriser ce répertoire
{
size_t i = strlen(fil)-1;
while((fil[i]!='/') && (i>0)) i--;
if (fil[i]=='/') {
HT_INSERT_FILTERS0; // insérer en 0
strcpybuff(_FILTERS[0],"+");
strcatbuff(_FILTERS[0],jump_identification(adr));
if (*fil!='/') strcatbuff(_FILTERS[0],"/");
strncatbuff(_FILTERS[0],fil,i+1);
strcatbuff(_FILTERS[0],"*[file]");
}
}
break;
case 50: // on fait rien
break;
} // switch
} // test du wizard sur l'url
} // fin du test wizard..
// -------------------- PHASE 5 --------------------
// lien non autorisé, peut-on juste le tester?
if (just_test_it) {
if (forbidden_url==1) {
if (opt->travel&256) { // tester tout de même
if (strfield(adr,"ftp://")==0
#if HTS_USEMMS
&& strfield(adr,"mms://")==0
#endif
) { // PAS ftp!
forbidden_url=1; // oui oui toujours interdit (note: sert à rien car ==1 mais c pour comprendre)
*just_test_it=1; // mais on teste
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"Testing link %s%s"LF,adr,fil);
}
}
}
}
//adr[0]='\0'; // cancel
}
// -------------------- FINAL PHASE --------------------
// Test if the "Near" test won
if (may_set_prio_to && forbidden_url == 0) {
*set_prio_to = may_set_prio_to;
}
return forbidden_url;
#undef _FILTERS
#undef _FILTERS_PTR
#undef _ROBOTS
}
/* Note: NOT utf-8 */
int optinclude_file(const char *name, int *argc, char **argv, char *x_argvblk,
int *x_ptr) {
FILE *fp;
fp = fopen(name, "rb");
if (fp) {
char line[256];
int insert_after = 1; /* first, insert after program filename */
while(!feof(fp)) {
char *a, *b;
int result;
/* read line */
linput(fp, line, 250);
hts_lowcase(line);
if (strnotempty(line)) {
/* no comment line: # // ; */
if (strchr("#/;", line[0]) == NULL) {
/* right trim */
a = line + strlen(line) - 1;
while(is_realspace(*a))
*(a--) = '\0';
/* jump "set " and spaces */
a = line;
while(is_realspace(*a))
a++;
if (strncmp(a, "set", 3) == 0) {
if (is_realspace(*(a + 3))) {
a += 4;
}
}
while(is_realspace(*a))
a++;
/* delete = ("sockets=8") */
if ((b = strchr(a, '=')))
*b = ' ';
/* isolate option and parameter */
b = a;
while((!is_realspace(*b)) && (*b))
b++;
if (*b) {
*b = '\0';
b++;
}
/* a is now the option, b the parameter */
{
int return_argc;
char return_error[256];
char _tmp_argv[4][HTS_CDLMAXSIZE];
char *tmp_argv[4];
tmp_argv[0] = _tmp_argv[0];
tmp_argv[1] = _tmp_argv[1];
tmp_argv[2] = _tmp_argv[2];
tmp_argv[3] = _tmp_argv[3];
strcpybuff(_tmp_argv[0], "--");
strcatbuff(_tmp_argv[0], a);
strcpybuff(_tmp_argv[1], b);
result =
optalias_check(2, (const char *const *) tmp_argv, 0, &return_argc,
(tmp_argv + 2), return_error);
if (!result) {
printf("%s\n", return_error);
} else {
int insert_after_argc;
/* Insert parameters BUT so that they can be in the same order */
/* temporary argc: Number of parameters after minus insert_after_argc */
insert_after_argc = (*argc) - insert_after;
cmdl_ins((tmp_argv[2]), insert_after_argc, (argv + insert_after),
x_argvblk, (*x_ptr));
*argc = insert_after_argc + insert_after;
insert_after++;
/* Second one */
if (return_argc > 1) {
insert_after_argc = (*argc) - insert_after;
cmdl_ins((tmp_argv[3]), insert_after_argc,
(argv + insert_after), x_argvblk, (*x_ptr));
*argc = insert_after_argc + insert_after;
insert_after++;
}
/* increment to nbr of used parameters */
/* insert_after+=result; */
}
}
}
}
}
fclose(fp);
return 1;
}
return 0;
}
// forme à partir d'un lien et du contexte (origin_fil et origin_adr d'où il est tiré) adr et fil
// [adr et fil sont des buffers de 1ko]
// 0 : ok
// -1 : erreur
// -2 : protocole non supporté (ftp)
int ident_url_relatif(const char *lien, const char *origin_adr,
const char *origin_fil,
lien_adrfil* const adrfil) {
int ok = 0;
int scheme = 0;
assertf(adrfil != NULL);
adrfil->adr[0] = '\0';
adrfil->fil[0] = '\0'; //effacer buffers
// lien non vide!
if (strnotempty(lien) == 0)
return -1; // erreur!
// Scheme?
{
const char *a = lien;
while(isalpha((unsigned char) *a))
a++;
if (*a == ':')
scheme = 1;
}
// filtrer les parazites (mailto & cie)
// scheme+authority (//)
if ((strfield(lien, "http://")) // scheme+//
|| (strfield(lien, "file://")) // scheme+//
|| (strncmp(lien, "//", 2) == 0) // // sans scheme (-> default)
) {
if (ident_url_absolute(lien, adrfil) == -1) {
ok = -1; // erreur URL
}
} else if (strfield(lien, "ftp://")) {
// Note: ftp:foobar.gif is not valid
if (ftp_available()) { // ftp supporté
if (ident_url_absolute(lien, adrfil) == -1) {
ok = -1; // erreur URL
}
} else {
ok = -2; // non supporté
}
#if HTS_USEOPENSSL
} else if (strfield(lien, "https://")) {
// Note: ftp:foobar.gif is not valid
if (ident_url_absolute(lien, adrfil) == -1) {
ok = -1; // erreur URL
}
#endif
} else if ((scheme) && ((!strfield(lien, "http:"))
&& (!strfield(lien, "https:"))
&& (!strfield(lien, "ftp:"))
)) {
ok = -1; // unknown scheme
} else { // c'est un lien relatif
// On forme l'URL complète à partie de l'url actuelle
// et du chemin actuel si besoin est.
// sanity check
if (origin_adr == NULL || origin_fil == NULL
|| *origin_adr == '\0' || *origin_fil == '\0') {
return -1;
}
// copier adresse
if (((int) strlen(origin_adr) < HTS_URLMAXSIZE)
&& ((int) strlen(origin_fil) < HTS_URLMAXSIZE)
&& ((int) strlen(lien) < HTS_URLMAXSIZE)) {
/* patch scheme if necessary */
if (strfield(lien, "http:")) {
lien += 5;
strcpybuff(adrfil->adr, jump_protocol_const(origin_adr)); // même adresse ; protocole vide (http)
} else if (strfield(lien, "https:")) {
lien += 6;
strcpybuff(adrfil->adr, "https://"); // même adresse forcée en https
strcatbuff(adrfil->adr, jump_protocol_const(origin_adr));
} else if (strfield(lien, "ftp:")) {
lien += 4;
strcpybuff(adrfil->adr, "ftp://"); // même adresse forcée en ftp
strcatbuff(adrfil->adr, jump_protocol_const(origin_adr));
} else {
strcpybuff(adrfil->adr, origin_adr); // même adresse ; et même éventuel protocole
}
if (*lien != '/') { // sinon c'est un lien absolu
if (*lien == '\0') {
strcpybuff(adrfil->fil, origin_fil);
} else if (*lien == '?') { // example: a href="?page=2"
char *a;
strcpybuff(adrfil->fil, origin_fil);
a = strchr(adrfil->fil, '?');
if (a)
*a = '\0';
strcatbuff(adrfil->fil, lien);
} else {
const char *a = strchr(origin_fil, '?');
if (a == NULL)
a = origin_fil + strlen(origin_fil);
while((*a != '/') && (a > origin_fil))
a--;
if (*a == '/') { // ok on a un '/'
if ((((int) (a - origin_fil)) + 1 + strlen(lien)) < HTS_URLMAXSIZE) {
// copier chemin
strncpy(adrfil->fil, origin_fil, ((int) (a - origin_fil)) + 1);
*(adrfil->fil + ((int) (a - origin_fil)) + 1) = '\0';
// copier chemin relatif
if (((int) strlen(adrfil->fil) + (int) strlen(lien)) < HTS_URLMAXSIZE) {
strcatbuff(adrfil->fil, lien + ((*lien == '/') ? 1 : 0));
// simplifier url pour les ../
fil_simplifie(adrfil->fil);
} else
ok = -1; // erreur
} else { // erreur
ok = -1; // erreur URL
}
} else { // erreur
ok = -1; // erreur URL
}
}
} else { // chemin absolu
// copier chemin directement
strcatbuff(adrfil->fil, lien);
fil_simplifie(adrfil->fil);
} // *lien!='/'
} else
ok = -1;
} // test news: etc.
// case insensitive pour adresse
{
char *a = jump_identification(adrfil->adr);
while(*a) {
if ((*a >= 'A') && (*a <= 'Z'))
*a += 'a' - 'A';
a++;
}
}
// IDNA / RFC 3492 (Punycode) handling for HTTP(s)
if (!link_has_authority(adrfil->adr) || strfield(adrfil->adr, "https:")) {
char *const a = jump_identification(adrfil->adr);
// Non-ASCII characters (theorically forbidden, but browsers are lenient)
if (!hts_isStringAscii(a, strlen(a))) {
char *const idna = hts_convertStringUTF8ToIDNA(a, strlen(a));
if (idna != NULL) {
if (strlen(idna) < HTS_URLMAXSIZE) {
strcpybuff(a, idna);
}
free(idna);
}
}
}
return ok;
}
