// conversion chemin de fichier/dossier vers 8-3 ou ISO9660
void long_to_83(int mode, char *n83, char *save) {
n83[0] = '\0';
while(*save) {
char fn83[256], fnl[256];
size_t i, j;
fn83[0] = fnl[0] = '\0';
for(i = j = 0 ; save[i] && save[i] != '/' ; i++) {
if (j + 1 < sizeof(fnl)) {
fnl[j++] = save[i];
}
}
fnl[j] = '\0';
// conversion
longfile_to_83(mode, fn83, fnl);
strcatbuff(n83, fn83);
save += i;
if (*save == '/') {
strcatbuff(n83, "/");
save++;
}
}
}
// insertion chaine ins avant s
void cookie_insert(char *s, char *ins) {
char *buff;
if (strnotempty(s) == 0) { // rien à faire, juste concat
strcatbuff(s, ins);
} else {
buff = (char *) malloct(strlen(s) + 2);
if (buff) {
strcpybuff(buff, s); // copie temporaire
strcpybuff(s, ins); // insérer
strcatbuff(s, buff); // copier
freet(buff);
}
}
}
// conversion chemin de fichier/dossier vers 8-3 ou ISO9660
void long_to_83(int mode,char* n83,char* save) {
n83[0]='\0';
while(*save) {
char fn83[256],fnl[256];
int i=0;
fn83[0]=fnl[0]='\0';
while((save[i]) && (save[i]!='/')) { fnl[i]=save[i]; i++; }
fnl[i]='\0';
// conversion
longfile_to_83(mode,fn83,fnl);
strcatbuff(n83,fn83);
save+=i;
if (*save=='/') { strcatbuff(n83,"/"); save++; }
}
}
/* Convert ~/foo into /home/smith/foo */
void expand_home(String * str) {
if (StringSub(*str, 1) == '~') {
char BIGSTK tempo[HTS_URLMAXSIZE * 2];
strcpybuff(tempo, hts_gethome());
strcatbuff(tempo, StringBuff(*str) + 1);
StringCopy(*str, tempo);
}
}
void CNewProj::Changeprojname(CString stl) {
char catbuff[CATBUFF_SIZE];
CWaitCursor wait;
CString st;
//
if (stl.GetLength()==0 || stl.GetLength() > HTS_URLMAXSIZE) {
//m_ctl_idok.ModifyStyle(0,WS_DISABLED);
SetDlgItemTextCP(this, IDC_STATIC_comments,LANG(LANG_S30));
SetDlgItemTextCP(this, IDC_STATIC_projname,LANG(LANG_S11c));
this_CWizTab->SetWizardButtons(PSWIZB_BACK);
can_click_next=FALSE;
} else {
char tempo[HTS_URLMAXSIZE*2];
GetDlgItemText(IDC_projpath,st);
if (st.GetLength() + stl.GetLength() + 32 > sizeof(tempo)) {
can_click_next=FALSE;
} else {
strcpybuff(tempo,st);
strcatbuff(tempo,"/");
strcatbuff(tempo,stl);
strcatbuff(tempo,"/");
if (fexist(fconcat(catbuff,tempo,"hts-cache/winprofile.ini")) // un cache est présent
&& fsize(fconcat(catbuff,tempo,"hts-cache/winprofile.ini"))>0) { // taille log contrôle>0
CString strSection = "OptionsValues";
CString st = MyGetProfileString(fconcat(catbuff,tempo,"hts-cache/winprofile.ini"),strSection,"CurrentUrl");
CString st2 = MyGetProfileString(fconcat(catbuff,tempo,"hts-cache/winprofile.ini"),strSection,"Category");
//
SetDlgItemTextCP(this, IDC_STATIC_comments, st);
SetDlgItemTextCP(this, IDC_projcateg, st2);
// Static
SetDlgItemTextCP(this, IDC_STATIC_projname,LANG(LANG_S11b));
} else {
SetDlgItemTextCP(this, IDC_STATIC_comments,LANG(LANG_S31));
SetDlgItemTextCP(this, IDC_STATIC_projname,LANG(LANG_S11));
}
//m_ctl_idok.ModifyStyle(WS_DISABLED,0);
//if (!can_click_next)
this_CWizTab->SetWizardButtons(PSWIZB_BACK|PSWIZB_NEXT);
can_click_next=TRUE;
}
}
//m_ctl_idok.RedrawWindow();
}
BOOL CDialogHtmlHelp::OnInitDialog()
{
CDialog::OnInitDialog();
SetIcon(httrack_icon,false);
SetIcon(httrack_icon,true);
EnableToolTips(true); // TOOL TIPS
SetForegroundWindow(); // yop en premier plan!
strcpybuff(home,"file://");
{
char* a=home+strlen(home);
::GetModuleFileName(NULL, a, sizeof(home)/sizeof(TCHAR) - 1 - strlen(home));
// strcatbuff(home,AfxGetApp()->m_pszHelpFilePath);
a = home + strlen(home) -1;
while( (*a!='\\') && ( a > home ) ) a--;
if (*a=='\\') {
*(a+1)='\0';
}
strcatbuff(home,"html\\");
strcpybuff(home_dir,home);
strcatbuff(home,"index.html");
}
// créer
if (m_page.CreateFromStatic(IDC_HTMLVIEW, this)) {
m_page.SetToolBar(false);
m_page.SetMenuBar(false);
m_page.SetStatusBar(false);
m_page.SetRegisterAsBrowser(false);
m_page.SetFullScreen(false);
if (page.GetLength()==0)
OnHome();
else
Go(page);
UpdateWindow();
} else {
EndDialog(IDCANCEL);
if (!ShellExecute(NULL,"open",home+strlen("file://"),"","",SW_RESTORE))
AfxMessageBox(LANG(LANG_DIAL1));
}
return TRUE;
}
void CDialogHtmlHelp::Go(CString st) {
if (st.Left(7)!="http://") {
char tempo[1024];
strcpybuff(tempo,home_dir);
strcatbuff(tempo,st);
m_page.Navigate2(tempo);
} else
m_page.Navigate2(st);
m_page.ShowWindow(SW_SHOW);
this->GetDlgItem(IDC_HTMLVIEW)->SetFocus();
}
/*
// Example:
find_handle h = hts_findfirst("/tmp");
if (h) {
do {
if (hts_findisfile(h))
printf("File: %s (%d octets)\n",hts_findgetname(h),hts_findgetsize(h));
else if (hts_findisdir(h))
printf("Dir: %s\n",hts_findgetname(h));
} while(hts_findnext(h));
hts_findclose(h);
}
*/
HTSEXT_API find_handle hts_findfirst(char* path) {
if (path) {
if (strnotempty(path)) {
find_handle_struct* find = (find_handle_struct*) calloc(1,sizeof(find_handle_struct));
if (find) {
memset(find, 0, sizeof(find_handle_struct));
#ifdef _WIN32
{
char BIGSTK rpath[1024*2];
strcpybuff(rpath,path);
if (rpath[0]) {
if (rpath[strlen(rpath)-1]!='\\')
strcatbuff(rpath,"\\");
}
strcatbuff(rpath,"*.*");
find->handle = FindFirstFileA(rpath,&find->hdata);
if (find->handle != INVALID_HANDLE_VALUE)
return find;
}
#else
strcpybuff(find->path,path);
{
if (find->path[0]) {
if (find->path[strlen(find->path)-1]!='/')
strcatbuff(find->path,"/");
}
}
find->hdir=opendir(path);
if (find->hdir != NULL) {
if (hts_findnext(find) == 1)
return find;
}
#endif
free((void*)find);
}
}
}
return NULL;
}
void COptionTab7::OnAdd2()
{
char s[1024]; s[0]='\0';
NewFilter(1,s);
if (strlen(s)>0) {
char tempo[HTS_URLMAXSIZE*16];
{
CString st;
GetDlgItemText(IDC_URL2,st);
if (st.GetLength() < sizeof(tempo) - 2)
strcpybuff(tempo,st);
else
tempo[0] = '\0';
}
if (strlen(tempo)>0) {
if ((tempo[strlen(tempo)-1]!=' ') && (tempo[strlen(tempo)-1]!='\n') && (tempo[strlen(tempo)-1]!=13))
strcatbuff(tempo,"\x0d\x0a");
}
strcatbuff(tempo,s);
// m_url2=tempo;
SetDlgItemTextCP(this, IDC_URL2,tempo);
}
}
char *bauth_prefix(char *prefix, char *adr, char *fil) {
char *a;
strcpybuff(prefix, jump_identification(adr));
strcatbuff(prefix, fil);
a = strchr(prefix, '?');
if (a)
*a = '\0';
if (strchr(prefix, '/')) {
a = prefix + strlen(prefix) - 1;
while(*a != '/')
a--;
*(a + 1) = '\0';
}
return prefix;
}
void Cinprogress::Oniplog(int mode) {
char catbuff[CATBUFF_SIZE];
if (!BackAffLog) { // pas encore lancé
strcpybuff(pathlog,dialog0->GetPath());
if (strlen(pathlog)>0)
if ((pathlog[strlen(pathlog)-1]!='/') && (pathlog[strlen(pathlog)-1]!='\\'))
strcatbuff(pathlog,"/");
// fichier log existe ou on est télécommandé par un !
if ( (fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-err.txt")))
|| (fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-log.txt")))
|| (ShellOptions != NULL && ShellOptions->choixdeb[0]=='!') ) {
if (mode)
form.type_log=0;
else
form.type_log=1;
strcpybuff(form.pathlog,pathlog);
BackAffLog = AfxBeginThread(AffLog,this);
} else {
char s[1024];
sprintf(s,LANG(LANG_H2 /*"No log files in %s!","Aucun fichier d'audit dans %s!"*/),pathlog);
AfxMessageBox(s,MB_OK+MB_ICONEXCLAMATION);
}
}
}
void NewFilter(int i,char* s) { // 0: forbid 1: accept
CAddFilter AddF;
AddF.type=i;
if (AddF.type==0)
AddF.m_addtype=LANG(LANG_B20); /*"Links following this rule will be forbidden:"*/
else
AddF.m_addtype=LANG(LANG_B21); // "Links following this rule will be accepted:";
if (AddF.DoModal()==IDOK) {
char query[2048],t[256],as[256];
char* q;
// error
if (AddF.m_afquery.GetLength() >= sizeof(query) - 2 ) {
return;
}
strcpybuff(s,"");
strcpybuff(query,AddF.m_afquery);
q=query;
if (AddF.m_aftype==10) {
if (i==0)
strcpybuff(s,"-");
else
strcpybuff(s,"+");
strcatbuff(s,"*");
} else {
while(strlen(q)>0) {
while ((*q==' ') || (*q==',')) q++;
strcpybuff(t,"");
{ // prochain (séparé par des ,)
char *a,*b;
a=strchr(q,' ');
b=strchr(q,',');
if (a && b) { // départager
if ( b < a)
a=b;
} else if (b) a=b;
if (a) {
strcpybuff (t,"");
strncat(t,q,a-q);
q=a+1;
} else {
strcpybuff(t,q);
strcpybuff(q,"");
}
}
if (strlen(t)>0) {
strcpybuff(as,"");
switch (AddF.m_aftype) {
case 0: // ext
sprintf(as,"*.%s",t);
break;
case 1: // contient
sprintf(as,"*/*%s*",t);
break;
case 2: // this one
sprintf(as,"*/%s",t);
break;
case 3: // folder contains
sprintf(as,"*/*%s*/*",t);
break;
case 4: // this folder
sprintf(as,"*/%s/*",t);
break;
case 5: // domaine
sprintf(as,"*[name].%s/*",t);
break;
case 6: // contien
sprintf(as,"*[name].*[name]%s*[name].*[name]/*",t);
break;
case 7: // host
sprintf(as,"%s/*",t);
break;
case 8: // link contient
sprintf(as,"*%s*",t);
break;
case 9: // lien exact
sprintf(as,"%s",t);
break;
}
if (strlen(as)>0) {
if (i==0)
strcatbuff(s,"-");
else
strcatbuff(s,"+");
strcatbuff(s,as);
strcatbuff(s,"\x0d\x0a");
}
}
}
}
} else strcpybuff(s,"");
}
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
}
/*
Check for alias in command-line
argc,argv as in main()
n_arg argument position
return_argv a char[2][] where to put result
return_error buffer in case of syntax error
return value: number of arguments treated (0 if error)
*/
int optalias_check(int argc, const char *const *argv, int n_arg,
int *return_argc, char **return_argv, char *return_error) {
return_error[0] = '\0';
*return_argc = 1;
if (argv[n_arg][0] == '-')
if (argv[n_arg][1] == '-') {
char command[1000];
char param[1000];
char addcommand[256];
/* */
char *position;
int need_param = 1;
//int return_param=0;
int pos;
command[0] = param[0] = addcommand[0] = '\0';
/* --sockets=8 */
if ((position = strchr(argv[n_arg], '='))) {
/* Copy command */
strncatbuff(command, argv[n_arg] + 2,
(int) (position - (argv[n_arg] + 2)));
/* Copy parameter */
strcpybuff(param, position + 1);
}
/* --nocache */
else if (strncmp(argv[n_arg] + 2, "no", 2) == 0) {
strcpybuff(command, argv[n_arg] + 4);
strcpybuff(param, "0");
}
/* --sockets 8 */
else {
if (strncmp(argv[n_arg] + 2, "wide-", 5) == 0) {
strcpybuff(addcommand, "c32");
strcpybuff(command, strchr(argv[n_arg] + 2, '-') + 1);
} else if (strncmp(argv[n_arg] + 2, "tiny-", 5) == 0) {
strcpybuff(addcommand, "c1");
strcpybuff(command, strchr(argv[n_arg] + 2, '-') + 1);
} else
strcpybuff(command, argv[n_arg] + 2);
need_param = 2;
}
/* Now solve the alias */
pos = optalias_find(command);
if (pos >= 0) {
/* Copy real name */
strcpybuff(command, hts_optalias[pos][1]);
/* With parameters? */
if (strncmp(hts_optalias[pos][2], "param", 5) == 0) {
/* Copy parameters? */
if (need_param == 2) {
if ((n_arg + 1 >= argc) || (argv[n_arg + 1][0] == '-')) { /* no supplemental parameter */
sprintf(return_error,
"Syntax error:\n\tOption %s needs to be followed by a parameter: %s <param>\n\t%s\n",
command, command, _NOT_NULL(optalias_help(command)));
return 0;
}
strcpybuff(param, argv[n_arg + 1]);
need_param = 2;
}
} else
need_param = 1;
/* Final result */
/* Must be alone (-P /tmp) */
if (strcmp(hts_optalias[pos][2], "param1") == 0) {
strcpybuff(return_argv[0], command);
strcpybuff(return_argv[1], param);
*return_argc = 2; /* 2 parameters returned */
}
/* Alone with parameter (+*.gif) */
else if (strcmp(hts_optalias[pos][2], "param0") == 0) {
/* Command */
strcpybuff(return_argv[0], command);
strcatbuff(return_argv[0], param);
}
/* Together (-c8) */
else {
/* Command */
strcpybuff(return_argv[0], command);
/* Parameters accepted */
if (strncmp(hts_optalias[pos][2], "param", 5) == 0) {
/* --cache=off or --index=on */
if (strcmp(param, "off") == 0)
strcatbuff(return_argv[0], "0");
else if (strcmp(param, "on") == 0) {
// on is the default
// strcatbuff(return_argv[0],"1");
} else
strcatbuff(return_argv[0], param);
}
*return_argc = 1; /* 1 parameter returned */
}
} else {
sprintf(return_error, "Unknown option: %s\n", command);
return 0;
}
return need_param;
}
/* Check -O <path> */
{
int pos;
if ((pos = optreal_find(argv[n_arg])) >= 0) {
if ((strcmp(hts_optalias[pos][2], "param1") == 0)
|| (strcmp(hts_optalias[pos][2], "param0") == 0)) {
if ((n_arg + 1 >= argc) || (argv[n_arg + 1][0] == '-')) { /* no supplemental parameter */
sprintf(return_error,
"Syntax error:\n\tOption %s needs to be followed by a parameter: %s <param>\n\t%s\n",
argv[n_arg], argv[n_arg],
_NOT_NULL(optalias_help(argv[n_arg])));
return 0;
}
/* Copy parameters */
strcpybuff(return_argv[0], argv[n_arg]);
strcpybuff(return_argv[1], argv[n_arg + 1]);
/* And return */
*return_argc = 2; /* 2 parameters returned */
return 2; /* 2 parameters used */
}
}
}
/* Copy and return other unknown option */
strcpybuff(return_argv[0], argv[n_arg]);
return 1;
}
/* 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;
}
// gestion des cookie
// ajoute, dans l'ordre
// !=0 : erreur
int cookie_add(t_cookie * cookie, char *cook_name, char *cook_value,
char *domain, char *path) {
char buffer[8192];
char *a = cookie->data;
char *insert;
char cook[16384];
// effacer éventuel cookie en double
cookie_del(cookie, cook_name, domain, path);
if ((int) strlen(cook_value) > 1024)
return -1; // trop long
if ((int) strlen(cook_name) > 256)
return -1; // trop long
if ((int) strlen(domain) > 256)
return -1; // trop long
if ((int) strlen(path) > 256)
return -1; // trop long
if ((int) (strlen(cookie->data)
+ strlen(cook_value)
+ strlen(cook_name)
+ strlen(domain)
+ strlen(path)
+ 256) > cookie->max_len)
return -1; // impossible d'ajouter
insert = a; // insérer ici
while(*a) {
if (strlen(cookie_get(buffer, a, 2)) < strlen(path)) // long. path (le + long est prioritaire)
a = cookie->data + strlen(cookie->data); // fin
else {
a = strchr(a, '\n'); // prochain champ
if (a == NULL)
a = cookie->data + strlen(cookie->data); // fin
else
a++;
while(*a == '\n')
a++;
insert = a; // insérer ici
}
}
// construction du cookie
strcpybuff(cook, domain);
strcatbuff(cook, "\t");
strcatbuff(cook, "TRUE");
strcatbuff(cook, "\t");
strcatbuff(cook, path);
strcatbuff(cook, "\t");
strcatbuff(cook, "FALSE");
strcatbuff(cook, "\t");
strcatbuff(cook, "1999999999");
strcatbuff(cook, "\t");
strcatbuff(cook, cook_name);
strcatbuff(cook, "\t");
strcatbuff(cook, cook_value);
strcatbuff(cook, "\n");
if (!(((int) strlen(cookie->data) + (int) strlen(cook)) < cookie->max_len))
return -1; // impossible d'ajouter
cookie_insert(insert, cook);
#if DEBUG_COOK
printf("add_new cookie: name=\"%s\" value=\"%s\" domain=\"%s\" path=\"%s\"\n",
cook_name, cook_value, domain, path);
//printf(">>>cook: %s<<<\n",cookie->data);
#endif
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,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;
}
void CNewProj::OnChangeprojpath()
{
CWaitCursor wait;
CString st;
CString old_name;
char tempo[HTS_URLMAXSIZE*2];
GetDlgItemText(IDC_projname,old_name);
GetDlgItemText(IDC_projpath,st);
if (st.GetLength() > MAX_PATH) {
SetDlgItemText(IDC_projpath, "");
return;
}
tempo[0] = '\0';
strcatbuff(tempo, st);
if ((tempo[strlen(tempo)-1]=='/') || (tempo[strlen(tempo)-1]=='\\')) {
tempo[strlen(tempo)-1]='\0';
//SetDlgItemTextCP(this, IDC_projpath,tempo);
}
strcatbuff(tempo,"\\");
TStamp t_start = mtime_local();
// chargement de la liste
m_ctl_projname.ResetContent();
m_ctl_projcateg.ResetContent();
WIN32_FIND_DATA find;
char pth[MAX_PATH + 32];
strcpybuff(pth,tempo);
strcatbuff(pth,"*.*");
HANDLE h = FindFirstFile(pth,&find);
if (h != INVALID_HANDLE_VALUE) {
do {
if (find.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY )
if (!(find.dwFileAttributes & (FILE_ATTRIBUTE_SYSTEM|FILE_ATTRIBUTE_HIDDEN) ))
if (strcmp(find.cFileName,".."))
if (strcmp(find.cFileName,".")) {
CString st;
st=tempo;
st=st+find.cFileName;
st=st+"\\hts-cache";
WIN32_FIND_DATA find2;
HANDLE h2 = FindFirstFile(st,&find2);
if (h2 != INVALID_HANDLE_VALUE) {
FindClose(h2);
m_ctl_projname.AddString(find.cFileName);
// Read category
st += "\\winprofile.ini";
CString strSection = "OptionsValues";
CString categ = MyGetProfileString(st, strSection, "Category");
if (categ.GetLength() > 0 && m_ctl_projcateg.FindStringExact(0, categ) < 0) {
m_ctl_projcateg.AddString(categ);
}
}
}
} while(FindNextFile(h,&find));
FindClose(h);
}
// nouveau nom!
SetDlgItemTextCP(this, IDC_projname,old_name);
TStamp t_proj = mtime_local();
OnChangeprojname();
TStamp t_end = mtime_local();
TStamp l_dir = t_proj - t_start;
TStamp l_proj = t_end - t_proj;
//CString a;
//a.Format("%s: build=%dms proj=%dms", __FUNCTION__, (int)l_dir, (int)l_proj);
//(void) AfxMessageBox(a, MB_OK);
}
// tester taille
int hts_testlinksize(httrackp* opt,
char* adr,char* fil,
LLint size) {
int jok=0;
if (size>=0) {
char BIGSTK l[HTS_URLMAXSIZE*2];
char BIGSTK lfull[HTS_URLMAXSIZE*2];
if (size>=0) {
LLint sz=size;
int size_flag=0;
// former URL complète du lien actuel
strcpybuff(l,jump_identification(adr));
if (*fil!='/') strcatbuff(l,"/");
strcatbuff(l,fil);
//
if (!link_has_authority(adr))
strcpybuff(lfull,"http://");
else
lfull[0]='\0';
strcatbuff(lfull,adr);
if (*fil!='/') strcatbuff(l,"/");
strcatbuff(lfull,fil);
// filters, 0=sait pas 1=ok -1=interdit
{
int jokDepth1=0,jokDepth2=0;
int jok1=0,jok2=0;
LLint sz1=size,sz2=size;
int size_flag1=0,size_flag2=0;
jok1 = fa_strjoker(/*url*/0, *opt->filters.filters,*opt->filters.filptr,lfull,&sz1,&size_flag1,&jokDepth1);
jok2 = fa_strjoker(/*url*/0, *opt->filters.filters,*opt->filters.filptr,l, &sz2,&size_flag2,&jokDepth2);
if (jok2 == 0) { // #2 doesn't know
jok = jok1; // then, use #1
sz = sz1;
size_flag = size_flag1;
} else if (jok1 == 0) { // #1 doesn't know
jok = jok2; // then, use #2
sz = sz2;
size_flag = size_flag2;
} else if (jokDepth1 >= jokDepth2) { // #1 matching rule is "after" #2, then it is prioritary
jok = jok1;
sz = sz1;
size_flag = size_flag1;
} else { // #2 matching rule is "after" #1, then it is prioritary
jok = jok2;
sz = sz2;
size_flag = size_flag2;
}
}
// log
if (jok==1) {
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"File confirmed (size test): %s%s ("LLintP")"LF,adr,fil,(LLint)(size));
}
} else if (jok==-1) {
if (size_flag) { /* interdit à cause de la taille */
if ((opt->debug>1) && (opt->log!=NULL)) {
HTS_LOG(opt,LOG_DEBUG); fprintf(opt->log,"File cancelled due to its size: %s%s ("LLintP", limit: "LLintP")"LF,adr,fil,(LLint)(size),(LLint)(sz));
}
} else {
jok=1;
}
}
}
}
return jok;
}
// 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;
}
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;
}
CDocument* CWinHTTrackApp::OpenDocumentFile( LPCTSTR lpszFileName)
{
// Eviter deux fenêtres (un seul document)
// Le CMultui..->CSingleDoc.. est trop complexe à changer (à cause du splitter-wnd)
int count=1;
{ /* Check if a document exists, and if exists if empty or not, and if name is different */
POSITION pos;
pos=GetFirstDocTemplatePosition();
if (pos) {
CDocTemplate* tmpl=GetNextDocTemplate(pos);
if (tmpl) {
pos=tmpl->GetFirstDocPosition();
if (pos) {
CDocument* doc = tmpl->GetNextDoc(pos);
if (doc) {
if (dialog0->GetName().GetLength()==0) {
CloseAllDocuments(FALSE);
count=0; /* No documents */
} else {
if (dialog0->GetPath0()+".whtt" == LPCSTR(lpszFileName))
return NULL;
}
}
} else
count=0; /* No documents */
}
}
}
// Ouvrir nouvelle instance
if (count) {
char cmdl[2048];
TCHAR ModulePath[MAX_PATH + 1];
ModulePath[0] = '\0';
::GetModuleFileName(NULL, ModulePath, sizeof(ModulePath)/sizeof(TCHAR) - 1);
CString name = ModulePath;
strcpybuff(cmdl,"\"");
strcatbuff(cmdl,lpszFileName);
strcatbuff(cmdl,"\"");
ShellExecute(NULL,"open",name,cmdl,"",SW_RESTORE);
return NULL;
}
// Ouvrir nouveau?
//if (count)
// return; // ne rien faire, car limité à 1 document
//count++;
/* Ouvrir */
/*
CWinApp* app=AfxGetApp();
POSITION pos;
pos=app->GetFirstDocTemplatePosition();
CDocTemplate* templ = app->GetNextDocTemplate(pos);
pos=templ->GetFirstDocPosition();
if (pos) {
CDocument* doc = templ->GetNextDoc(pos);
if (doc)
if (!doc->SaveModified())
return NULL;
}
CloseAllDocuments(FALSE);
*/
if (strlen(lpszFileName))
return CWinApp::OpenDocumentFile(lpszFileName);
else
CWinApp::OnFileNew();
return NULL;
}
/* Code mainly written by Nicolas BENOIT */
static int run_launch_mms(MMSDownloadStruct* pStruct) {
lien_back* back = pStruct->pBack;
httrackp* opt = pStruct->pOpt;
/* */
char url[HTS_URLMAXSIZE*2];
char catbuff[CATBUFF_SIZE];
char catbuff2[CATBUFF_SIZE];
MMS *mms;
FILE *f;
ssize_t len_written;
uint64_t total_len_written;
int delay = opt->mms_maxtime;
time_t end = time(NULL) + delay;
short checkPending = 0;
ssize_t existingSize = fsize(back->url_sav);
// effacer
strcpybuff(back->r.msg,"");
back->status=STATUS_FTP_TRANSFER;
back->r.statuscode=HTTP_OK;
back->r.size=0;
/* Create file */
if (existingSize > 0) {
/* back->r.out = fileappend(back->url_sav);
*/
(void) unlink(fconcat(catbuff,back->url_sav, ".old"));
if (rename(fconcat(catbuff,back->url_sav, ""), fconcat(catbuff2,back->url_sav, ".old")) == 0) {
checkPending = 1;
}
back->r.out = filecreate(&pStruct->pOpt->state.strc, back->url_sav);
} else {
back->r.out = filecreate(&pStruct->pOpt->state.strc, back->url_sav);
}
if ((f = back->r.out) != NULL) {
// create mms resource
strcpybuff(url, back->url_adr); /* mms:// */
strcatbuff(url, back->url_fil);
if ( ( mms = mms_create( url, f, NULL, 0, 1 ) ) != NULL ) {
if ( mms_connect ( mms ) == 0 ) {
if ( mms_handshake ( mms ) == 0 ) {
if ( ( len_written = mms_write_stream_header ( mms ) ) != -1 ) {
total_len_written = len_written;
HTS_STAT.HTS_TOTAL_RECV += len_written;
/* not modified */
if (checkPending) {
if (mms->is_live != MMS_LIVE
&& mms->expected_file_size == existingSize + 50 /* Why 50 additional bytes declared ?? */
) // abort download
{
fclose(back->r.out);
f = back->r.out = NULL;
if (unlink(fconcat(catbuff, back->url_sav, "")) == 0
&& rename(fconcat(catbuff, back->url_sav, ".old"), fconcat(catbuff2, back->url_sav, "")) == 0)
{
back->r.notmodified = 1;
back->r.statuscode = HTTP_OK;
strcpybuff(back->r.msg, "Not modified");
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Unable to rename previous file (not updated)");
}
} else {
(void) unlink(fconcat(catbuff, back->url_sav, ".old"));
}
}
/* begin rip */
if ( f != NULL && mms_begin_rip ( mms ) == 0 ) {
if ( mms->is_live != MMS_LIVE ) {
back->r.totalsize = mms->expected_file_size;
back->r.totalsize -= 50; /* Why 50 additional bytes declared ?? */
} else
back->r.totalsize = -1;
/* Start download */
while ( !stop_mms(back) ) {
len_written = mms_write_stream_data ( mms );
if ( len_written == 0 ) {
break;
} else if ( len_written == -1 ) {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Unable to write stream data");
break;
}
total_len_written += len_written;
back->r.size = total_len_written;
HTS_STAT.HTS_TOTAL_RECV += len_written;
fflush ( f );
if ( delay != 0 && end <= time(NULL) ) {
delay = -1;
back->r.statuscode = HTTP_OK;
strcpybuff(back->r.msg, "Download interrupted");
break;
}
} // while
back->r.statuscode = HTTP_OK; /* Finished */
} else if (f != NULL) {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Can not begin ripping");
}
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Can not write stream header");
}
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Can not handshake");
}
mms_disconnect ( mms );
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Can not connect");
}
mms_destroy ( mms );
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Can not create mms resource");
}
} else {
back->r.statuscode = HTTP_INTERNAL_SERVER_ERROR;
strcpybuff(back->r.msg, "Unable to open local output file");
}
return 0;
}
// créer dans s, à partir du chemin courant curr_fil, le lien vers link (absolu)
// un ident_url_relatif a déja été fait avant, pour que link ne soit pas un chemin relatif
int lienrelatif(char* s,const char* link,const char* curr_fil) {
char BIGSTK _curr[HTS_URLMAXSIZE*2];
char BIGSTK newcurr_fil[HTS_URLMAXSIZE*2],newlink[HTS_URLMAXSIZE*2];
char* curr;
//int n=0;
char* a;
int slash=0;
//
newcurr_fil[0]='\0'; newlink[0]='\0';
//
// patch: éliminer les ? (paramètres) sinon bug
{
const char* a;
if ( (a=strchr(curr_fil,'?')) ) {
strncatbuff(newcurr_fil,curr_fil,(int) (a - curr_fil));
curr_fil = newcurr_fil;
}
if ( (a=strchr(link,'?')) ) {
strncatbuff(newlink,link,(int) (a - link));
link = newlink;
}
}
// recopier uniquement le chemin courant
curr=_curr;
strcpybuff(curr,curr_fil);
if ((a=strchr(curr,'?'))==NULL) // couper au ? (params)
a=curr+strlen(curr)-1; // pas de params: aller à la fin
while((*a!='/') && ( a> curr)) a--; // chercher dernier / du chemin courant
if (*a=='/') *(a+1)='\0'; // couper dernier /
// "effacer" s
s[0]='\0';
// sauter ce qui est commun aux 2 chemins
{
const char *l,*c;
if (*link=='/') link++; // sauter slash
if (*curr=='/') curr++;
l=link;
c=curr;
// couper ce qui est commun
while ((streql(*link,*curr)) && (*link!=0)) {link++; curr++; }
// mais on veut un répertoirer entier!
// si on a /toto/.. et /toto2/.. on ne veut pas sauter /toto !
while(((*link!='/') || (*curr!='/')) && ( link > l)) { link--; curr--; }
//if (*link=='/') link++;
//if (*curr=='/') curr++;
}
// calculer la profondeur du répertoire courant et remonter
// LES ../ ONT ETE SIMPLIFIES
a=curr;
if (*a=='/') a++;
while(*a) if (*(a++)=='/') strcatbuff(s,"../");
//if (strlen(s)==0) strcatbuff(s,"/");
if (slash) strcatbuff(s,"/"); // garder absolu!!
// on est dans le répertoire de départ, copier
strcatbuff(s,link + ((*link=='/')?1:0) );
/* Security check */
if (strlen(s) >= HTS_URLMAXSIZE)
return -1;
// on a maintenant une chaine de la forme ../../test/truc.html
return 0;
}
LRESULT Cinprogress::OnEndMirror(WPARAM /* wP*/, LPARAM /*lP*/) {
char catbuff[CATBUFF_SIZE];
char catbuff2[CATBUFF_SIZE];
//this_CSplitterFrame->SetNewView(0,1,RUNTIME_CLASS(Cinfoend));
// Copie de trans.cpp
this_CWizTab->ModifyStyle(WS_VISIBLE,0,0);
this_CWizTab->RedrawWindow();
//
//{
// CWizTab* tmp;
// tmp=this_CWizTab;
this_CWizTab=this_intCWizTab;
// this_CWizTab2=tmp;
//}
//
this_CWizTab->ModifyStyle(0,WS_VISIBLE,0);
this_CWizTab->ModifyStyle(WS_DISABLED,0,0);
this_CSplitterFrame->RedrawWindow();
// Fin de Copie de trans.cpp
this_CWizTab->EndInProgress();
if (IsWindow(this_Cinfoend->m_hWnd))
SetDlgItemTextCP(this_Cinfoend, IDC_infoend,end_mirror_msg);
if (hts_is_exiting(global_opt) == 1) { /* Interrupted mirror! */
char pathlog[HTS_URLMAXSIZE*2];
strcpybuff(pathlog,dialog0->GetPath());
if (strlen(pathlog)>0) {
if ((pathlog[strlen(pathlog)-1]!='/') && (pathlog[strlen(pathlog)-1]!='\\'))
strcatbuff(pathlog,"/");
}
// Aborted updated.. restore old cache?!
if (
fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.zip"))
||
(fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.dat")))
&& (fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.ndx")))
) {
if (AfxMessageBox(LANG_F22b,MB_YESNO|MB_DEFBUTTON2) == IDYES) {
if (fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.dat"))
&& fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.ndx"))) {
if (remove(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/new.dat"))) {
AfxMessageBox(LANG_F24 );
}
if (remove(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/new.ndx"))) {
AfxMessageBox(LANG_F24 );
}
}
if (remove(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/new.lst"))) {
AfxMessageBox(LANG_F24 );
}
if (fexist(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.zip"))) {
if (remove(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/new.zip"))) {
AfxMessageBox(LANG_F24 );
}
}
remove(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/new.txt"));
rename(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.zip"),fconcat(catbuff2,sizeof(catbuff2),pathlog,"hts-cache/new.zip"));
rename(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.dat"),fconcat(catbuff2,sizeof(catbuff2),pathlog,"hts-cache/new.dat"));
rename(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.ndx"),fconcat(catbuff2,sizeof(catbuff2),pathlog,"hts-cache/new.ndx"));
rename(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.lst"),fconcat(catbuff2,sizeof(catbuff2),pathlog,"hts-cache/new.lst"));
rename(fconcat(catbuff,sizeof(catbuff),pathlog,"hts-cache/old.txt"),fconcat(catbuff2,sizeof(catbuff2),pathlog,"hts-cache/new.txt"));
}
}
} else if (hts_is_exiting(global_opt) == 2) { /* No connection! */
AfxMessageBox(LANG_F22c );
}
return S_OK;
}
// 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);
}
}
// 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;
}
void help_wizard(httrackp * opt) {
help_wizard_buffers *buffers = malloct(sizeof(help_wizard_buffers));
#undef urls
#undef mainpath
#undef projname
#undef stropt
#undef stropt2
#undef strwild
#undef cmd
#undef str
#undef argv
#define urls (buffers->urls)
#define mainpath (buffers->mainpath)
#define projname (buffers->projname)
#define stropt (buffers->stropt)
#define stropt2 (buffers->stropt2)
#define strwild (buffers->strwild)
#define cmd (buffers->cmd)
#define str (buffers->str)
#define argv (buffers->argv)
//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) 1998-2016 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_const(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>), separated 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] = strdup("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 */
free(buffers);
#undef urls
#undef mainpath
#undef projname
#undef stropt
#undef stropt2
#undef strwild
#undef cmd
#undef str
#undef argv
}
// 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;
}
