mirror of
https://github.com/xroche/httrack.git
synced 2026-07-05 08:34:10 +03:00
Compare commits
3 Commits
fix-maxtim
...
wait-socke
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
75fd5ae90f | ||
|
|
1e7744865f | ||
|
|
dfafe28002 |
@@ -1359,6 +1359,18 @@ int back_flush_output(httrackp * opt, cache_back * cache, struct_back * sback,
|
||||
}
|
||||
|
||||
// effacer entrée
|
||||
/* Discard a cancelled mid-write .delayed placeholder (unusable across runs). */
|
||||
static void back_delayed_discard(httrackp *opt, lien_back *back) {
|
||||
if (back->r.out != NULL) {
|
||||
fclose(back->r.out);
|
||||
back->r.out = NULL;
|
||||
}
|
||||
back->r.is_write = 0;
|
||||
if (opt != NULL)
|
||||
url_savename_refname_remove(opt, back->url_adr, back->url_fil);
|
||||
(void) UNLINK(back->url_sav);
|
||||
}
|
||||
|
||||
int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
|
||||
const int p) {
|
||||
lien_back *const back = sback->lnk;
|
||||
@@ -1366,6 +1378,12 @@ int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
|
||||
|
||||
assertf(p >= 0 && p < back_max);
|
||||
if (p >= 0 && p < sback->count) { // on sait jamais..
|
||||
/* mid-write cancel: drop a .delayed placeholder; real-named partials
|
||||
survive for resume (--continue) */
|
||||
if (back[p].r.is_write && IS_DELAYED_EXT(back[p].url_sav) &&
|
||||
(back[p].status != STATUS_READY || back[p].r.statuscode <= 0)) {
|
||||
back_delayed_discard(opt, &back[p]);
|
||||
}
|
||||
// Vérificateur d'intégrité
|
||||
#if DEBUG_CHECKINT
|
||||
_CHECKINT(&back[p], "Appel back_delete")
|
||||
@@ -2419,6 +2437,34 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
|
||||
back_clean(opt, cache, sback);
|
||||
#endif
|
||||
|
||||
/* Time limit exceeded past grace: abort in-flight transfers so no wait loop
|
||||
starves (#481). FTP slots stay, their thread owns the socket. */
|
||||
if (!back_checkmirror(opt)) {
|
||||
int aborted = 0;
|
||||
unsigned int i;
|
||||
|
||||
for (i = 0; i < (unsigned int) back_max; i++) {
|
||||
if (back[i].status > 0 && back[i].status < STATUS_FTP_TRANSFER) {
|
||||
if (back[i].r.soc != INVALID_SOCKET) {
|
||||
deletehttp(&back[i].r);
|
||||
}
|
||||
back[i].r.soc = INVALID_SOCKET;
|
||||
/* drop a .delayed placeholder; real partials survive for resume */
|
||||
if (back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))
|
||||
back_delayed_discard(opt, &back[i]);
|
||||
back[i].r.statuscode = STATUSCODE_TIMEOUT;
|
||||
strcpybuff(back[i].r.msg, "Mirror Time Out");
|
||||
back[i].status = STATUS_READY;
|
||||
back_set_finished(sback, i);
|
||||
aborted++;
|
||||
}
|
||||
}
|
||||
if (aborted > 0)
|
||||
hts_log_print(opt, LOG_WARNING,
|
||||
"time limit reached, %d transfer(s) aborted", aborted);
|
||||
return;
|
||||
}
|
||||
|
||||
// recevoir tant qu'il y a des données (avec un maximum de max_loop boucles)
|
||||
do_wait = 0;
|
||||
gestion_timeout = 0;
|
||||
@@ -4164,6 +4210,11 @@ int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize)
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Grace left to the smooth stop before in-flight transfers are aborted. */
|
||||
static int back_maxtime_grace(const int maxtime) {
|
||||
return maximum(5, minimum(30, maxtime / 10));
|
||||
}
|
||||
|
||||
int back_checkmirror(httrackp * opt) {
|
||||
// Check max size
|
||||
if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
|
||||
@@ -4180,13 +4231,19 @@ int back_checkmirror(httrackp * opt) {
|
||||
*/
|
||||
}
|
||||
// Check max time
|
||||
if ((opt->maxtime > 0)
|
||||
&& ((time_local() - HTS_STAT.stat_timestart) >= opt->maxtime)) {
|
||||
if (!opt->state.stop) { /* not yet stopped */
|
||||
hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
|
||||
opt->maxtime);
|
||||
/* cancel mirror smoothly */
|
||||
hts_request_stop(opt, 0);
|
||||
if (opt->maxtime > 0) {
|
||||
const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;
|
||||
|
||||
if (elapsed >= opt->maxtime) {
|
||||
if (!opt->state.stop) { /* not yet stopped */
|
||||
hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
|
||||
opt->maxtime);
|
||||
/* cancel mirror smoothly */
|
||||
hts_request_stop(opt, 0);
|
||||
}
|
||||
/* smooth stop starved past the grace period: stop waiting (#481) */
|
||||
if (elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return 1; /* Ok, go on */
|
||||
|
||||
@@ -136,6 +136,8 @@ void back_solve(httrackp * opt, lien_back * sback);
|
||||
int host_wait(httrackp * opt, lien_back * sback);
|
||||
#endif
|
||||
int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize);
|
||||
/* Enforce -M/-E quotas: requests a smooth stop when reached; returns 0 once
|
||||
the -E deadline overran its grace period (callers must stop waiting). */
|
||||
int back_checkmirror(httrackp * opt);
|
||||
|
||||
#endif
|
||||
|
||||
@@ -3371,6 +3371,41 @@ int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt) {
|
||||
return n;
|
||||
}
|
||||
|
||||
/* One engine-loop tick: refresh the transfer stats and run the loop callback
|
||||
for slot b (-1 = none). HTS_FALSE = the callback requested an abort. */
|
||||
hts_boolean hts_loop_tick(struct_back *sback, httrackp *opt, int b, int ptr) {
|
||||
engine_stats();
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
return RUN_CALLBACK7(
|
||||
opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)
|
||||
? HTS_TRUE
|
||||
: HTS_FALSE;
|
||||
}
|
||||
|
||||
/* Single implementation of the historical WAIT_FOR_AVAILABLE_SOCKET macros. */
|
||||
hts_boolean hts_wait_available_socket(struct_back *sback, httrackp *opt,
|
||||
cache_back *cache, int ptr) {
|
||||
const int prev = opt->state._hts_in_html_parsing;
|
||||
|
||||
while (back_pluggable_sockets_strict(sback, opt) <= 0) {
|
||||
opt->state._hts_in_html_parsing = 6;
|
||||
back_wait(sback, opt, cache, 0);
|
||||
/* time limit (-E) exceeded: stop waiting for a socket (#481) */
|
||||
if (!back_checkmirror(opt))
|
||||
break;
|
||||
if (!hts_loop_tick(sback, opt, -1, ptr))
|
||||
return HTS_FALSE;
|
||||
}
|
||||
opt->state._hts_in_html_parsing = prev;
|
||||
return HTS_TRUE;
|
||||
}
|
||||
|
||||
int back_pluggable_sockets(struct_back * sback, httrackp * opt) {
|
||||
int n;
|
||||
|
||||
|
||||
@@ -432,6 +432,15 @@ int back_pluggable_sockets(struct_back * sback, httrackp * opt);
|
||||
|
||||
int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt);
|
||||
|
||||
/* One engine-loop tick: refresh the transfer stats and run the loop callback
|
||||
for slot b (-1 = none). HTS_FALSE = the callback requested an abort. */
|
||||
hts_boolean hts_loop_tick(struct_back *sback, httrackp *opt, int b, int ptr);
|
||||
|
||||
/* Wait until a test socket can be plugged, pumping transfers, stats and the
|
||||
loop callback; gives up past the -E deadline. HTS_FALSE = callback abort. */
|
||||
hts_boolean hts_wait_available_socket(struct_back *sback, httrackp *opt,
|
||||
cache_back *cache, int ptr);
|
||||
|
||||
/* Randomized inter-file pause target in [min_ms,max_ms] (#185), derived from a
|
||||
timestamp seed so it is stable within one gap and rerolls per launch. */
|
||||
int hts_pause_target_ms(TStamp seed, int min_ms, int max_ms);
|
||||
|
||||
@@ -74,31 +74,6 @@ static const char *hts_tbdev[] = {
|
||||
""
|
||||
};
|
||||
|
||||
#define URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET() do { \
|
||||
int prev = opt->state._hts_in_html_parsing; \
|
||||
while(back_pluggable_sockets_strict(sback, opt) <= 0) { \
|
||||
opt->state. _hts_in_html_parsing = 6; \
|
||||
/* Wait .. */ \
|
||||
back_wait(sback,opt,cache,0); \
|
||||
/* Transfer rate */ \
|
||||
engine_stats(); \
|
||||
/* Refresh various stats */ \
|
||||
HTS_STAT.stat_nsocket=back_nsoc(sback); \
|
||||
HTS_STAT.stat_errors=fspc(opt,NULL,"error"); \
|
||||
HTS_STAT.stat_warnings=fspc(opt,NULL,"warning"); \
|
||||
HTS_STAT.stat_infos=fspc(opt,NULL,"info"); \
|
||||
HTS_STAT.nbk=backlinks_done(sback,opt->liens,opt->lien_tot,ptr); \
|
||||
HTS_STAT.nb=back_transferred(HTS_STAT.stat_bytes,sback); \
|
||||
/* Check */ \
|
||||
{ \
|
||||
if (!RUN_CALLBACK7(opt, loop, sback->lnk, sback->count,-1,ptr,opt->lien_tot,(int) (time_local()-HTS_STAT.stat_timestart),&HTS_STAT)) { \
|
||||
return -1; \
|
||||
} \
|
||||
} \
|
||||
} \
|
||||
opt->state._hts_in_html_parsing = prev; \
|
||||
} while(0)
|
||||
|
||||
/* Strip all // */
|
||||
static void cleanDoubleSlash(char *s) {
|
||||
int i, j;
|
||||
@@ -652,11 +627,10 @@ int url_savename(lien_adrfilsave *const afs,
|
||||
int has_been_moved = 0;
|
||||
lien_adrfil current;
|
||||
|
||||
/* Ensure we don't use too many sockets by using a "testing" one
|
||||
If we have only 1 simultaneous connection authorized, wait for pending download
|
||||
Wait for an available slot
|
||||
/* Wait for an available test slot, honoring the connection limits
|
||||
*/
|
||||
URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
|
||||
if (!hts_wait_available_socket(sback, opt, cache, ptr))
|
||||
return -1;
|
||||
|
||||
/* Rock'in */
|
||||
current.adr[0] = current.fil[0] = '\0';
|
||||
@@ -686,24 +660,11 @@ int url_savename(lien_adrfilsave *const afs,
|
||||
if (ptr >= 0) {
|
||||
back_fillmax(sback, opt, cache, ptr, numero_passe);
|
||||
}
|
||||
// on est obligé d'appeler le shell pour le refresh..
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart),
|
||||
&HTS_STAT)) {
|
||||
if (!hts_loop_tick(sback, opt, b, ptr)) {
|
||||
return -1;
|
||||
} else if (opt->state._hts_cancel || !back_checkmirror(opt)) { // cancel 2 ou 1 (cancel parsing)
|
||||
} else if (opt->state._hts_cancel ||
|
||||
!back_checkmirror(
|
||||
opt)) { // cancel level 2 or 1 (cancel parsing)
|
||||
back_delete(opt, cache, sback, b); // cancel test
|
||||
stop_looping = 1;
|
||||
}
|
||||
@@ -768,8 +729,9 @@ int url_savename(lien_adrfilsave *const afs,
|
||||
"Loop with HEAD request (during prefetch) at %s%s",
|
||||
current.adr, current.fil);
|
||||
}
|
||||
// Ajouter
|
||||
URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
|
||||
if (!hts_wait_available_socket(sback, opt,
|
||||
cache, ptr))
|
||||
return -1;
|
||||
if (back_add(sback, opt, cache, moved.adr, moved.fil, methode, referer_adr, referer_fil, 1) != -1) { // OK
|
||||
hts_log_print(opt, LOG_DEBUG,
|
||||
"(during prefetch) %s (%d) to link %s at %s%s",
|
||||
|
||||
104
src/htsparse.c
104
src/htsparse.c
@@ -3399,20 +3399,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
|
||||
back_wait(sback, opt, cache, HTS_STAT.stat_timestart);
|
||||
back_fillmax(sback, opt, cache, ptr, numero_passe);
|
||||
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, 0, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)) {
|
||||
if (!hts_loop_tick(sback, opt, 0, ptr)) {
|
||||
hts_log_print(opt, LOG_ERROR, "Exit requested by shell or user");
|
||||
*stre->exit_xh_ = 1; // exit requested
|
||||
XH_uninit;
|
||||
@@ -3423,7 +3410,6 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
|
||||
nofollow = 1; // moins violent
|
||||
opt->state._hts_cancel = 0;
|
||||
}
|
||||
|
||||
}
|
||||
// refresh the backing system each 2 seconds
|
||||
if (engine_stats()) {
|
||||
@@ -3960,22 +3946,8 @@ void hts_mirror_process_user_interaction(htsmoduleStruct * str,
|
||||
{
|
||||
back_wait(sback, opt, cache, HTS_STAT.stat_timestart);
|
||||
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
b = 0;
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)
|
||||
|| !back_checkmirror(opt)) {
|
||||
if (!hts_loop_tick(sback, opt, b, ptr) || !back_checkmirror(opt)) {
|
||||
hts_log_print(opt, LOG_ERROR, "Exit requested by shell or user");
|
||||
*stre->exit_xh_ = 1; // exit requested
|
||||
XH_uninit;
|
||||
@@ -4077,21 +4049,11 @@ void hts_mirror_process_user_interaction(htsmoduleStruct * str,
|
||||
while(opt->state._hts_setpause || back_pluggable_sockets_strict(sback, opt) <= 0) { // on fait la pause..
|
||||
opt->state._hts_in_html_parsing = 6;
|
||||
back_wait(sback, opt, cache, HTS_STAT.stat_timestart);
|
||||
/* time limit (-E) exceeded: stop waiting for a socket (#481) */
|
||||
if (!back_checkmirror(opt))
|
||||
break;
|
||||
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)) {
|
||||
if (!hts_loop_tick(sback, opt, b, ptr)) {
|
||||
hts_log_print(opt, LOG_ERROR, "Exit requested by shell or user");
|
||||
*stre->exit_xh_ = 1; // exit requested
|
||||
XH_uninit;
|
||||
@@ -4278,26 +4240,12 @@ int hts_mirror_wait_for_next_file(htsmoduleStruct * str,
|
||||
freet(s);
|
||||
}
|
||||
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)) {
|
||||
if (!hts_loop_tick(sback, opt, b, ptr)) {
|
||||
hts_log_print(opt, LOG_ERROR, "Exit requested by shell or user");
|
||||
*stre->exit_xh_ = 1; // exit requested
|
||||
XH_uninit;
|
||||
return 0;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
#if HTS_POLL
|
||||
@@ -4530,10 +4478,9 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
|
||||
IS_DELAYED_EXT(afs->save) && continue_loop && loops < 7; loops++) {
|
||||
continue_loop = 0;
|
||||
|
||||
/*
|
||||
Wait for an available slot
|
||||
*/
|
||||
WAIT_FOR_AVAILABLE_SOCKET();
|
||||
/* Wait for an available slot */
|
||||
if (!hts_wait_available_socket(sback, opt, cache, ptr))
|
||||
return -1;
|
||||
|
||||
/* We can lookup directly in the cache to speedup this mess */
|
||||
if (opt->delayed_cached) {
|
||||
@@ -4679,29 +4626,14 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
|
||||
if (ptr >= 0) {
|
||||
back_fillmax(sback, opt, cache, ptr, numero_passe);
|
||||
}
|
||||
// on est obligé d'appeler le shell pour le refresh..
|
||||
{
|
||||
|
||||
// Transfer rate
|
||||
engine_stats();
|
||||
|
||||
// Refresh various stats
|
||||
HTS_STAT.stat_nsocket = back_nsoc(sback);
|
||||
HTS_STAT.stat_errors = fspc(opt, NULL, "error");
|
||||
HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
|
||||
HTS_STAT.stat_infos = fspc(opt, NULL, "info");
|
||||
HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
|
||||
HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
|
||||
|
||||
if (!RUN_CALLBACK7
|
||||
(opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
|
||||
(int) (time_local() - HTS_STAT.stat_timestart), &HTS_STAT)) {
|
||||
back_set_unlocked(sback, b);
|
||||
return -1;
|
||||
} else if (opt->state._hts_cancel || !back_checkmirror(opt)) { // cancel 2 ou 1 (cancel parsing)
|
||||
back_delete(opt, cache, sback, b); // cancel test
|
||||
break;
|
||||
}
|
||||
if (!hts_loop_tick(sback, opt, b, ptr)) {
|
||||
back_set_unlocked(sback, b);
|
||||
return -1;
|
||||
} else if (opt->state._hts_cancel ||
|
||||
!back_checkmirror(
|
||||
opt)) { // cancel level 2 or 1 (cancel parsing)
|
||||
back_delete(opt, cache, sback, b); // cancel test
|
||||
break;
|
||||
}
|
||||
} while (
|
||||
/* dns/connect/request */
|
||||
|
||||
@@ -175,27 +175,4 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
|
||||
/* Apply changes */ \
|
||||
* str->ptr_ = ptr
|
||||
|
||||
#define WAIT_FOR_AVAILABLE_SOCKET() do { \
|
||||
int prev = opt->state._hts_in_html_parsing; \
|
||||
while(back_pluggable_sockets_strict(sback, opt) <= 0) { \
|
||||
opt->state._hts_in_html_parsing = 6; \
|
||||
/* Wait .. */ \
|
||||
back_wait(sback,opt,cache,0); \
|
||||
/* Transfer rate */ \
|
||||
engine_stats(); \
|
||||
/* Refresh various stats */ \
|
||||
HTS_STAT.stat_nsocket=back_nsoc(sback); \
|
||||
HTS_STAT.stat_errors=fspc(opt,NULL,"error"); \
|
||||
HTS_STAT.stat_warnings=fspc(opt,NULL,"warning"); \
|
||||
HTS_STAT.stat_infos=fspc(opt,NULL,"info"); \
|
||||
HTS_STAT.nbk=backlinks_done(sback,opt->liens,opt->lien_tot,ptr); \
|
||||
HTS_STAT.nb=back_transferred(HTS_STAT.stat_bytes,sback); \
|
||||
/* Check */ \
|
||||
if (!RUN_CALLBACK7(opt, loop, sback->lnk, sback->count, -1,ptr,opt->lien_tot,(int) (time_local()-HTS_STAT.stat_timestart),&HTS_STAT)) { \
|
||||
return -1; \
|
||||
} \
|
||||
} \
|
||||
opt->state._hts_in_html_parsing = prev; \
|
||||
} while(0)
|
||||
|
||||
#endif
|
||||
|
||||
21
tests/34_local-maxtime.test
Normal file
21
tests/34_local-maxtime.test
Normal file
@@ -0,0 +1,21 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# -E time limit (#481): server pages trickle for minutes; the engine must stop
|
||||
# on its own at -E plus grace, aborting the in-flight transfers.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
: "${top_srcdir:=..}"
|
||||
|
||||
# cancelled crawls can orphan .delayed placeholders (#483): skip that audit
|
||||
start=$(date +%s)
|
||||
bash "$top_srcdir/tests/local-crawl.sh" \
|
||||
--skip-delayed-audit \
|
||||
--log-found 'More than 2 seconds passed' \
|
||||
httrack 'BASEURL/trickle/index.html' -E2 -c4
|
||||
wall=$(($(date +%s) - start))
|
||||
# hard stop is due at -E2 + 5s grace; near TRICKLE_SECONDS means it never fired
|
||||
if [ "$wall" -ge 30 ]; then
|
||||
echo "crawl took ${wall}s, -E hard stop did not engage" >&2
|
||||
exit 1
|
||||
fi
|
||||
@@ -96,6 +96,7 @@ TESTS = \
|
||||
30_local-fragment-link.test \
|
||||
31_local-javaclass.test \
|
||||
32_local-cdispo.test \
|
||||
33_local-delayed.test
|
||||
33_local-delayed.test \
|
||||
34_local-maxtime.test
|
||||
|
||||
CLEANFILES = check-network_sh.cache
|
||||
|
||||
@@ -92,6 +92,7 @@ tmpdir=$(mktemp -d "${tmptopdir}/httrack_local.XXXXXX") || die "could not create
|
||||
# --- parse leading control flags --------------------------------------------
|
||||
declare -a audit=()
|
||||
declare -a cookies=()
|
||||
skip_delayed_audit=""
|
||||
scheme=http
|
||||
pos=0
|
||||
args=("$@")
|
||||
@@ -116,6 +117,9 @@ while test "$pos" -lt "$nargs"; do
|
||||
pos=$((pos + 1))
|
||||
cookies+=("${args[$pos]}")
|
||||
;;
|
||||
--skip-delayed-audit)
|
||||
skip_delayed_audit=1
|
||||
;;
|
||||
--errors | --files)
|
||||
audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
|
||||
pos=$((pos + 1))
|
||||
@@ -246,12 +250,15 @@ done
|
||||
test -n "$hostroot" || die "could not find host root under $out"
|
||||
debug "host root: $hostroot"
|
||||
|
||||
# A completed crawl must leave no .delayed temporaries (issue #107)
|
||||
info "checking for leftover .delayed files"
|
||||
leftovers=$(find "$out" -name '*.delayed' 2>/dev/null | head -5)
|
||||
if test -z "$leftovers"; then result "OK"; else
|
||||
result "leftover: $leftovers"
|
||||
exit 1
|
||||
# A completed crawl must leave no .delayed temporaries (issue #107).
|
||||
# --skip-delayed-audit: a cancelled crawl can orphan placeholders (issue #483)
|
||||
if test -z "$skip_delayed_audit"; then
|
||||
info "checking for leftover .delayed files"
|
||||
leftovers=$(find "$out" -name '*.delayed' 2>/dev/null | head -5)
|
||||
if test -z "$leftovers"; then result "OK"; else
|
||||
result "leftover: $leftovers"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- audit -------------------------------------------------------------------
|
||||
|
||||
@@ -464,6 +464,30 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
def route_delayed_empty(self):
|
||||
self.send_raw(b"", "text/html") # 200 + Content-Length: 0
|
||||
|
||||
# -E time-limit (#481): pages that trickle far longer than any -E budget,
|
||||
# so only an engine-side abort can end the crawl.
|
||||
TRICKLE_SECONDS = 60
|
||||
|
||||
def route_trickle_index(self):
|
||||
self.send_html(
|
||||
"".join('\t<a href="p%d.bin">p%d</a>\n' % (i, i) for i in range(8))
|
||||
)
|
||||
|
||||
def route_trickle_page(self):
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/octet-stream")
|
||||
self.send_header("Content-Length", str(2 * self.TRICKLE_SECONDS))
|
||||
self.end_headers()
|
||||
if self.command == "HEAD":
|
||||
return
|
||||
try:
|
||||
for _ in range(self.TRICKLE_SECONDS):
|
||||
self.wfile.write(b"xy")
|
||||
self.wfile.flush()
|
||||
time.sleep(1.0)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
ROUTES = {
|
||||
"/cookies/entrance.php": route_entrance,
|
||||
"/cookies/second.php": route_second,
|
||||
@@ -509,6 +533,15 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
"/cdispo/fetch.php": route_cdispo,
|
||||
"/cdispo/evil.php": route_cdispo,
|
||||
"/delayed/index.html": route_delayed_index,
|
||||
"/trickle/index.html": route_trickle_index,
|
||||
"/trickle/p0.bin": route_trickle_page,
|
||||
"/trickle/p1.bin": route_trickle_page,
|
||||
"/trickle/p2.bin": route_trickle_page,
|
||||
"/trickle/p3.bin": route_trickle_page,
|
||||
"/trickle/p4.bin": route_trickle_page,
|
||||
"/trickle/p5.bin": route_trickle_page,
|
||||
"/trickle/p6.bin": route_trickle_page,
|
||||
"/trickle/p7.bin": route_trickle_page,
|
||||
"/delayed/noloc.php": route_delayed_noloc,
|
||||
"/delayed/selfloop.php": route_delayed_selfloop,
|
||||
"/delayed/redir.php": route_delayed_redir,
|
||||
|
||||
Reference in New Issue
Block a user