Compare commits

..

1 Commits

Author SHA1 Message Date
Xavier Roche
2f15b7ec46 Release 3.49.12
Roll up 25 commits since 3.49.11 (July 5): security fixes in the
network-facing parsers (remote stack overflow and uninitialized read in
Content-Type/-Encoding handling, fuzzer-found over-reads in the filter,
URL and IDNA parsers, cache-index bounds, filter-pattern backtracking,
world-readable cookies.txt), crawl-correctness fixes (double-encoded UTF-8
links, gzip-mislabeled bodies, cache reconcile/corruption handling,
orphaned .delayed placeholders), the new --why filter diagnostic, and
build hardening (_FORTIFY_SOURCE, -fstack-protector-strong).

VERSION_INFO 3:3:0 -> 3:4:0: httrackp tail-appends why_url, no layout or
exported-signature break, so soname stays libhttrack.so.3 (revision bump).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>
2026-07-10 21:15:50 +02:00
15 changed files with 209 additions and 404 deletions

View File

@@ -55,9 +55,7 @@ jobs:
run: make -j"$(nproc)"
- name: Test
run: |
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs"
run: make check
- name: Print the test log on failure
if: failure()
@@ -101,8 +99,7 @@ jobs:
sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
-exec mv {} {}.hidden \;
! command -v python3
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs"
make check
- name: Print the test log on failure
if: failure()
@@ -136,15 +133,7 @@ jobs:
run: make -j"$(sysctl -n hw.ncpu)"
- name: Test
# bigcrawl's sustained -c8 crawl drops fetches on macOS's loopback when
# it competes with other crawls, flaking its exact file count (the #527
# macOS drop). Run everything else in parallel, then bigcrawl alone (its
# serial-safe condition). Linux tolerates the full parallel run.
run: |
jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
rest=$(cd tests && ls *.test | grep -v '^36_local-bigcrawl\.test$' | tr '\n' ' ')
make check -j"$jobs" TESTS="$rest"
make check TESTS=36_local-bigcrawl.test
run: make check
- name: Print the test log on failure
if: failure()
@@ -182,9 +171,7 @@ jobs:
run: make -j"$(nproc)"
- name: Test
run: |
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs"
run: make check
- name: Print the test log on failure
if: failure()
@@ -239,9 +226,7 @@ jobs:
env:
ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
run: |
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs"
run: make check
- name: Print the test log on failure
if: failure()
@@ -287,8 +272,7 @@ jobs:
# 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
# skipped here (uninstrumented libz floods MSan with false positives).
tests="$(cd tests && ls 01_engine-*.test | tr '\n' ' ')"
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs" TESTS="$tests"
make check TESTS="$tests"
- name: Print the test log on failure
if: failure()
@@ -363,9 +347,7 @@ jobs:
run: make -j"$(nproc)"
- name: Test
run: |
jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
make check -j"$jobs"
run: make check
- name: Print the test log on failure
if: failure()

View File

@@ -6,19 +6,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
## Build & test
- Fresh clone first: `git submodule update --init src/coucal`
- `./bootstrap` (regenerates `configure` via `autoreconf`; needs autoconf,
automake, libtool), then `bash configure && make -j"$(nproc)" && make check
-j"$(nproc)"`. Always pass `-j` to `make check`: the suite runs under
automake's parallel harness and each crawl test binds its own ephemeral-port
server, so `-j` never contends and a multi-minute serial run drops to
seconds. A new `.test` added to `$(TESTS)` is scheduled onto a free worker
automatically; only a test slower than the current longest raises the floor.
On a few-core Linux box, `-j` at 2x the core count is faster still: the tests
spend much of their wall time asleep (server trickles, httrack self-pacing),
so an idle core covers a sleeping one. CI uses `min(2*cores, 16)`. macOS runs
36_local-bigcrawl alone in a second pass: its sustained `-c8` crawl overloads
the macOS loopback when it competes with other crawls and flakes its exact
file count (Linux tolerates the full parallel run).
Or run `sh build.sh` to do bootstrap + configure + make in one shot.
automake, libtool), then `bash configure && make && make check`. Or run
`sh build.sh` to do bootstrap + configure + make in one shot.
## Hard invariants
- **Generated autotools files are NOT in git.** `configure`, every

View File

@@ -68,15 +68,6 @@ static int slot_can_be_cached_on_disk(const lien_back * back);
static int slot_can_be_cleaned(const lien_back * back);
static int slot_can_be_finalized(httrackp * opt, const lien_back * back);
/* Which hard quota, if any, is currently aborting the mirror. */
typedef enum {
HTS_MIRROR_LIMIT_NONE = 0,
HTS_MIRROR_LIMIT_SIZE,
HTS_MIRROR_LIMIT_TIME,
} hts_mirror_limit;
static hts_mirror_limit back_mirror_limit(httrackp *opt);
struct_back *back_new(httrackp *opt, int back_max) {
int i;
struct_back *sback = calloct(1, sizeof(struct_back));
@@ -533,22 +524,22 @@ int back_nsoc_overall(const struct_back * sback) {
/* generate temporary file on lien_back */
/* Note: utf-8 */
static int create_back_tmpfile(httrackp *opt, lien_back *const back,
const char *ext) {
static int create_back_tmpfile(httrackp * opt, lien_back *const back) {
// do not use tempnam() but a regular filename
back->tmpfile_buffer[0] = '\0';
if (back->url_sav != NULL && back->url_sav[0] != '\0') {
snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.%s",
back->url_sav, ext);
snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.z",
back->url_sav);
back->tmpfile = back->tmpfile_buffer;
if (structcheck(back->tmpfile) != 0) {
hts_log_print(opt, LOG_WARNING, "can not create directory to %s",
hts_log_print(opt, LOG_WARNING, "can not create directory to %s",
back->tmpfile);
return -1;
}
} else {
snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s/tmp%d.%s",
StringBuff(opt->path_html_utf8), opt->state.tmpnameid++, ext);
snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer),
"%s/tmp%d.z", StringBuff(opt->path_html_utf8),
opt->state.tmpnameid++);
back->tmpfile = back->tmpfile_buffer;
}
/* OK */
@@ -556,32 +547,6 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
return 0;
}
/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
existing file moved the good copy to back->tmpfile before truncating url_sav.
commit keeps the new file and drops the backup; else restore it so an aborted
transfer leaves the previous copy intact. Skips the zlib .z temp. */
static void back_finalize_backup(httrackp *opt, lien_back *const back,
const hts_boolean commit) {
if (back->tmpfile == NULL || back->r.compressed)
return;
if (commit) {
(void) UNLINK(back->tmpfile); /* new copy is good; drop the backup */
} else {
if (back->r.out != NULL) {
fclose(back->r.out);
back->r.out = NULL;
}
(void) UNLINK(back->url_sav); /* drop the failed partial */
/* On rename failure keep the backup: it still holds the good copy, so
losing it would be worse than an orphaned temp. */
if (RENAME(back->tmpfile, back->url_sav) != 0)
hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
"could not restore %s; previous copy kept as %s",
back->url_sav, back->tmpfile);
}
back->tmpfile = NULL;
}
// objet (lien) téléchargé ou transféré depuis le cache
//
// fermer les paramètres de transfert,
@@ -617,7 +582,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
LLintP " got " LLintP "): %s%s", back[p].r.totalsize,
back[p].r.size, back[p].url_adr, back[p].url_fil);
}
back_finalize_backup(opt, &back[p], HTS_FALSE);
return -1;
}
@@ -636,7 +600,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
// en mémoire -> passage sur disque
if (!back[p].r.is_write) {
// do not use tempnam() but a regular filename
if (create_back_tmpfile(opt, &back[p], "z") == 0) {
if (create_back_tmpfile(opt, &back[p]) == 0) {
assertf(back[p].tmpfile != NULL);
/* note: tmpfile is utf-8 */
back[p].r.out = FOPEN(back[p].tmpfile, "wb");
@@ -709,9 +673,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
}
}
#endif
/* Body fully received: keep the freshly written url_sav, drop the
backup of the previous copy. */
back_finalize_backup(opt, &back[p], HTS_TRUE);
/* Write mode to disk */
if (back[p].r.is_write && back[p].r.adr != NULL) {
freet(back[p].r.adr);
@@ -940,9 +901,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
}
}
}
/* Aborted, error, or not ready: url_sav (if written) is broken; restore the
previous copy from the backup. */
back_finalize_backup(opt, &back[p], HTS_FALSE);
return -1;
}
@@ -2092,9 +2050,13 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
if (!back_trylive(opt, cache, sback, p)) {
#if HTS_XGETHOST
back[p].status = STATUS_WAIT_DNS; // host name resolution attempt
soc = INVALID_SOCKET; // not opened yet
if (host_wait(opt, &back[p])) { // ready (file, or cached dns)
#if HDEBUG
printf("back_solve..\n");
#endif
back[p].status = STATUS_WAIT_DNS; // tentative de résolution du nom de host
soc = INVALID_SOCKET; // pas encore ouverte
back_solve(opt, &back[p]); // préparer
if (host_wait(opt, &back[p])) { // prêt, par ex fichier ou dispo dans dns
#if HDEBUG
printf("ok, dns cache ready..\n");
#endif
@@ -2237,9 +2199,37 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
}
#if HTS_XGETHOST
// Resolution is synchronous inside the connect path; no pre-resolve step, so
// the host is always immediately ready.
int host_wait(httrackp *opt, lien_back *back) { return 1; }
// attendre que le host (ou celui du proxy) ait été résolu
// si c'est un fichier, la résolution est immédiate
// idem pour ftp://
void back_solve(httrackp * opt, lien_back * back) {
assertf(opt != NULL);
assertf(back != NULL);
if ((!strfield(back->url_adr, "file://"))
&& !strfield(back->url_adr, "ftp://")
) {
const char *a;
if (!(back->r.req.proxy.active))
a = back->url_adr;
else
a = back->r.req.proxy.name;
assertf(a != NULL);
a = jump_protocol_const(a);
if (check_hostname_dns(a)) {
hts_log_print(opt, LOG_DEBUG, "resolved: %s", a);
} else {
hts_log_print(opt, LOG_DEBUG, "failed to resolve: %s", a);
}
}
}
// détermine si le host a pu être résolu
int host_wait(httrackp * opt, lien_back * back) {
// Always synchronous. No more background DNS resolution
// (does not really improve performances)
return 1;
}
#endif
// élimine les fichiers non html en backing (anticipation)
@@ -2426,15 +2416,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
back_clean(opt, cache, sback);
#endif
/* Time/size limit exceeded past grace: abort in-flight transfers so no wait
loop starves (#481, #77). FTP slots stay, their thread owns the socket. */
/* 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)) {
const hts_mirror_limit limit = back_mirror_limit(opt);
const char *const reason =
(limit == HTS_MIRROR_LIMIT_SIZE) ? "size limit" : "time limit";
const char *const slotmsg = (limit == HTS_MIRROR_LIMIT_SIZE)
? "Mirror Size Limit"
: "Mirror Time Out";
int aborted = 0;
unsigned int i;
@@ -2448,15 +2432,15 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
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, slotmsg);
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, "%s reached, %d transfer(s) aborted",
reason, aborted);
hts_log_print(opt, LOG_WARNING,
"time limit reached, %d transfer(s) aborted", aborted);
return;
}
@@ -2946,8 +2930,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "gz") == 0
&& strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "tgz") == 0
) {
if (create_back_tmpfile(opt, &back[i], "z") ==
0) {
if (create_back_tmpfile(opt, &back[i]) == 0) {
assertf(back[i].tmpfile != NULL);
/* note: tmpfile is utf-8 */
if ((back[i].r.out =
@@ -2960,20 +2943,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
back[i].url_sav, 1, 1,
back[i].r.notmodified);
back[i].r.compressed = 0;
/* Re-fetch over an existing file (#77 follow-up):
move the good copy aside before truncating it
so an aborted transfer can restore it. url_sav
is still written normally (file list intact).
*/
back[i].tmpfile = NULL;
if (fexist_utf8(back[i].url_sav)) {
if (create_back_tmpfile(opt, &back[i], "bak") !=
0 ||
RENAME(back[i].url_sav, back[i].tmpfile) !=
0) {
back[i].tmpfile = NULL;
}
}
if ((back[i].r.out =
filecreate(&opt->state.strc,
back[i].url_sav)) == NULL) {
@@ -3540,20 +3509,22 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
if (back[i].r.statuscode == 406) { // 'Not Acceptable'
back[i].r.statuscode = HTTP_OK;
}
// On update, keep the good copy on error (mask as 304); skip
// resume paths so a stale-partial 416 still re-fetches.
if (HTTP_IS_ERROR(back[i].r.statuscode) &&
back[i].is_update && !back[i].testmode &&
back[i].range_req_size == 0 && back[i].url_sav[0] &&
fexist_utf8(back[i].url_sav)) {
hts_log_print(opt, LOG_DEBUG,
"Error %d (%s) ignored on update, keeping "
"existing copy: %s%s",
back[i].r.statuscode, back[i].r.msg,
back[i].url_adr, back[i].url_fil);
back[i].r.statuscode = HTTP_NOT_MODIFIED;
deletehttp(&back[i].r);
back[i].r.soc = INVALID_SOCKET;
// 'do not erase already downloaded file'
// on an updated file
// with an error : consider a 304 error
if (!opt->delete_old) {
if (HTTP_IS_ERROR(back[i].r.statuscode) && back[i].is_update
&& !back[i].testmode) {
if (back[i].url_sav[0] && fexist_utf8(back[i].url_sav)) {
hts_log_print(opt, LOG_DEBUG,
"Error ignored %d (%s) because of 'no purge' option for %s%s",
back[i].r.statuscode, back[i].r.msg,
back[i].url_adr, back[i].url_fil);
back[i].r.statuscode = HTTP_NOT_MODIFIED;
deletehttp(&back[i].r);
back[i].r.soc = INVALID_SOCKET;
}
}
}
// Various hacks to limit re-transfers when updating a mirror
// Force update if same size detected
@@ -4174,43 +4145,38 @@ static int back_maxtime_grace(const int maxtime) {
return maximum(5, minimum(30, maxtime / 10));
}
/* Bytes the smooth stop may overrun before in-flight transfers are aborted.
No floor (unlike the time grace): a size overrun should abort promptly. */
static LLint back_maxsize_grace(const LLint maxsite) { return maxsite / 10; }
/* Which cap has overrun its grace and must hard-stop the mirror (#77, #481). */
static hts_mirror_limit back_mirror_limit(httrackp *opt) {
if (opt->maxsite > 0 && HTS_STAT.stat_bytes >= opt->maxsite &&
HTS_STAT.stat_bytes - opt->maxsite >= back_maxsize_grace(opt->maxsite))
return HTS_MIRROR_LIMIT_SIZE;
int back_checkmirror(httrackp * opt) {
// Check max size
if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
if (!opt->state.stop) { /* not yet stopped */
hts_log_print(opt, LOG_ERROR,
"More than " LLintP
" bytes have been transferred.. giving up",
(LLint) opt->maxsite);
/* cancel mirror smoothly */
hts_request_stop(opt, 0);
}
return 1; /* don'k break mirror too sharply for size limits, but stop requested */
/*return 0;
*/
}
// Check max time
if (opt->maxtime > 0) {
const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;
if (elapsed >= opt->maxtime &&
elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
return HTS_MIRROR_LIMIT_TIME;
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 HTS_MIRROR_LIMIT_NONE;
}
int back_checkmirror(httrackp *opt) {
/* request a smooth stop the first time each cap is reached */
if (opt->maxsite > 0 && HTS_STAT.stat_bytes >= opt->maxsite &&
!opt->state.stop) {
hts_log_print(opt, LOG_ERROR,
"More than " LLintP
" bytes have been transferred.. giving up",
(LLint) opt->maxsite);
hts_request_stop(opt, 0);
}
if (opt->maxtime > 0 && !opt->state.stop &&
(time_local() - HTS_STAT.stat_timestart) >= opt->maxtime) {
hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
opt->maxtime);
hts_request_stop(opt, 0);
}
/* hard stop once a cap overruns its grace (callers must stop waiting) */
return back_mirror_limit(opt) == HTS_MIRROR_LIMIT_NONE;
return 1; /* Ok, go on */
}
// octets transférés + add

View File

@@ -138,11 +138,12 @@ LLint back_transferred(LLint add, struct_back * sback);
// hostback
#if HTS_XGETHOST
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: smooth-stops when reached; returns 0 once the -M cap
or -E deadline overruns its grace period (callers must stop waiting). */
/* 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

View File

@@ -1904,11 +1904,8 @@ int httpmirror(char *url1, httrackp * opt) {
}
}
// ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!
// An empty body must not overwrite the file when the transfer failed
// (statuscode <= 0, e.g. an -M hard-stop): it would truncate a good
// copy to 0 (#77 follow-up).
if (r.adr != NULL || (r.size == 0 && r.statuscode > 0)) {
// ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!
if (r.adr != NULL || r.size == 0) {
file_notify(opt, urladr(), urlfil(), savename(), 1, 1, r.notmodified);
if (filesave(opt, r.adr, (int) r.size, savename(), urladr(), urlfil()) !=
0) {
@@ -1929,6 +1926,7 @@ int httpmirror(char *url1, httrackp * opt) {
*/
}
}
}
/* Parsing of other media types (java, ram..) */

View File

@@ -297,26 +297,6 @@ int dns_selftests(httrackp *opt) {
IPV6_resolver = 0;
}
/* "host:port" resolves as the bare host: the cache/connect path strips
":port" before both the backend and the cache key (#181). */
mock_reset_calls();
{
SOCaddr a;
char ip[64];
const char *err = NULL;
/* cache miss: the backend is hit with the stripped host, not "host:port" */
CHECK(hts_dns_resolve2(opt, "v6only.test:8080", &a, &err) != NULL);
CHECK(mock_find("v6only.test")->calls == 1);
/* the bare host shares that one cache entry (stripped key) */
CHECK(hts_dns_resolve2(opt, "v6only.test", &a, &err) != NULL);
CHECK(mock_find("v6only.test")->calls == 1);
/* a port variant of an already-cached host also hits, right address */
CHECK(hts_dns_resolve2(opt, "v4only.test:1234", &a, &err) != NULL);
SOCaddr_inetntoa(ip, sizeof(ip), a);
CHECK(strcmp(ip, "1.2.3.4") == 0);
}
/* newhttp_addr() must connect to the addr_index-th address, not always the
first: this is what back_connect_next relies on to reach the fallback. */
{

View File

@@ -56,10 +56,6 @@ Please visit our Website: http://www.httrack.com
// Platform detection (sizes, feature macros)
#include "htsconfig.h"
// Fixed-width integer types + PRI* format macros for the LLint/TStamp typedefs
#include <stdint.h>
#include <inttypes.h>
// WIN32 types
#ifdef _WIN32
#ifndef SIZEOF_LONG
@@ -115,6 +111,29 @@ Please visit our Website: http://www.httrack.com
#define HTS_DO_NOT_USE_UID
#endif
#ifndef HTS_LONGLONG
#ifdef SIZEOF_LONG_LONG
#if SIZEOF_LONG_LONG == 8
#define HTS_LONGLONG 1
#endif
#endif
#ifndef HTS_LONGLONG
#ifdef __sun
#define HTS_LONGLONG 0
#endif
#ifdef __osf__
#define HTS_LONGLONG 0
#endif
#ifdef __linux
#define HTS_LONGLONG 1
#endif
#ifdef _WIN32
#define HTS_LONGLONG 1
#endif
#endif
#endif
#ifdef DLLIB
#define HTS_DLOPEN 1
#else
@@ -307,11 +326,59 @@ typedef int hts_tristate;
#define HTS_DEPRECATED(msg)
#endif
/* LLint/TStamp: signed exact-width 64-bit; -1 is a sentinel engine-wide. */
typedef int64_t LLint;
typedef int64_t TStamp;
/* Full printf conversion, '%' included (PRId64 has none): "X: " LLintP. */
#define LLintP "%" PRId64
#ifndef HTS_LONGLONG
#ifdef HTS_NO_64_BIT
#define HTS_LONGLONG 0
#else
#define HTS_LONGLONG 1
#endif
#endif
/* Wide integer types, chosen per platform.
LLint: signed 64-bit counter for byte counts and large sizes (falls back to
plain int where 64-bit is unavailable).
TStamp: timestamp/duration in the same width (a double in the no-64-bit
fallback).
LLintP: the printf conversion for an LLint. */
#if HTS_LONGLONG
#ifdef LLINT_FORMAT
typedef LLINT_TYPE LLint;
typedef LLINT_TYPE TStamp;
#define LLintP LLINT_FORMAT
#else
#ifdef _WIN32
typedef __int64 LLint;
typedef __int64 TStamp;
#define LLintP "%I64d"
#elif (defined(_LP64) || defined(__x86_64__) || defined(__powerpc64__) || \
defined(__64BIT__))
typedef long int LLint;
typedef long int TStamp;
#define LLintP "%ld"
#else
typedef long long int LLint;
typedef long long int TStamp;
#define LLintP "%lld"
#endif
#endif /* HTS_LONGLONG */
#else
typedef int LLint;
#define LLintP "%d"
typedef double TStamp;
#endif
/* Integer type for file offsets/sizes passed to the C library. Widens to
LLint (with HTS_FSEEKO for fseeko/ftello) under large-file support, plain

View File

@@ -3038,11 +3038,12 @@ HTSEXT_API char *int2char(strc_int2bytes2 * strc, int n) {
/* See http://physics.nist.gov/cuu/Units/binary.html */
#define ToLLint(a) ((LLint)(a))
#define ToLLintKiB (ToLLint(1024))
#define ToLLintMiB (ToLLintKiB * ToLLintKiB)
#define ToLLintGiB (ToLLintKiB * ToLLintKiB * ToLLintKiB)
#define ToLLintTiB (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
#define ToLLintPiB \
(ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
#define ToLLintMiB (ToLLintKiB*ToLLintKiB)
#ifdef HTS_LONGLONG
#define ToLLintGiB (ToLLintKiB*ToLLintKiB*ToLLintKiB)
#define ToLLintTiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
#define ToLLintPiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
#endif
HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
if (n < ToLLintKiB) {
sprintf(strc->buff1, "%d", (int) (LLint) n);
@@ -3051,7 +3052,9 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / ToLLintKiB)),
(int) ((LLint) ((n % ToLLintKiB) * 100) / ToLLintKiB));
strcpybuff(strc->buff2, "KiB");
} else if (n < ToLLintGiB) {
}
#ifdef HTS_LONGLONG
else if (n < ToLLintGiB) {
sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
(int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
strcpybuff(strc->buff2, "MiB");
@@ -3068,6 +3071,13 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
(int) ((LLint) (((n % (ToLLintPiB)) * 100) / (ToLLintPiB))));
strcpybuff(strc->buff2, "PiB");
}
#else
else {
sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
(int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
strcpybuff(strc->buff2, "MiB");
}
#endif
strc->buffadr[0] = strc->buff1;
strc->buffadr[1] = strc->buff2;
return strc->buffadr;

View File

@@ -9,7 +9,7 @@ set -euo pipefail
: "${top_srcdir:=..}"
bash "$top_srcdir/tests/local-crawl.sh" --rerun \
--errors-content 4 --files 361 \
--errors 4 --files 361 \
--found 'big/p/95.html' \
--found 'big/a/d1/d2/d3/d4/d5/d6/d7/d8/deep.png' \
--found 'big/a/f2-2x.png' \

View File

@@ -1,21 +0,0 @@
#!/bin/bash
#
# -M byte cap under a slow server (#77): p0 overruns -M at once while p1..p3
# trickle for a minute; the cap must abort the in-flight transfers, not wait
# them out. Unfixed, the smooth stop drains the trickle at server pace.
set -euo pipefail
: "${top_srcdir:=..}"
start=$(date +%s)
bash "$top_srcdir/tests/local-crawl.sh" \
--log-found 'More than 400000 bytes have been transferred.. giving up' \
httrack 'BASEURL/bigtrickle/index.html' -M400000 -c4
wall=$(($(date +%s) - start))
# trickle runs 60s; a smooth-only stop waits it out, the hard stop lands near 8s.
# Wall clock is the discriminating check: the log line above fires either way.
if [ "$wall" -ge 30 ]; then
echo "crawl took ${wall}s, -M hard stop did not engage" >&2
exit 1
fi

View File

@@ -1,24 +0,0 @@
#!/bin/bash
#
# -M hard-abort must not destroy already-complete files (#77 follow-up).
# Pass 1 mirrors bigtrunc fully. Pass 2 re-fetches under --update -M: fast.bin
# overruns the cap, its abort tears down slow.bin's stalled re-fetch. Both were
# complete on disk from pass 1, and both must survive the aborted update:
# - slow.bin's re-fetch is incomplete; the direct-to-disk write must not be
# left truncated (the previous copy is restored).
# - fast.bin fully arrives but is torn down; the aborted slot must not overwrite
# it with an empty body.
# Unfixed, slow.bin is truncated and fast.bin is zeroed while the cache still
# records them complete.
set -euo pipefail
: "${top_srcdir:=..}"
bash "$top_srcdir/tests/local-crawl.sh" \
--rerun-args '--update -M400000' \
--log-found 'More than 400000 bytes have been transferred.. giving up' \
--found bigtrunc/slow.bin \
--file-min-bytes bigtrunc/slow.bin 655360 \
--file-min-bytes bigtrunc/fast.bin 655360 \
httrack 'BASEURL/bigtrunc/index.html' -c2

View File

@@ -1,13 +0,0 @@
#!/bin/bash
# Issue #176: on --update a page that 200'd on the first crawl but now 403s must
# keep its good local copy, not be overwritten by the error body nor purged.
set -euo pipefail
: "${top_srcdir:=..}"
bash "$top_srcdir/tests/local-crawl.sh" --rerun \
--found 'errmask/keep.dat' \
--file-min-bytes 'errmask/keep.dat' 1024 \
--file-matches 'errmask/keep.dat' '^KEEP' \
--file-not-matches 'errmask/keep.dat' 'error 403' \
httrack 'BASEURL/errmask/index.html'

View File

@@ -110,9 +110,6 @@ TESTS = \
38_local-update-304.test \
39_local-delayed-cancel.test \
40_local-why.test \
41_local-utf8-link.test \
42_local-maxsize-slow.test \
43_local-update-truncate.test \
44_local-update-errormask.test
41_local-utf8-link.test
CLEANFILES = check-network_sh.cache

View File

@@ -13,21 +13,15 @@
#
# Usage:
# bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
# [--rerun-args 'ARGS'] \
# --errors N --errors-content N --files N --found PATH ... --directory PATH ... \
# --errors N --files N --found PATH ... --directory PATH ... \
# --log-found REGEX ... --log-not-found REGEX ... \
# --file-matches PATH REGEX ... --file-not-matches PATH REGEX ... \
# --file-min-bytes PATH N --max-mirror-bytes N \
# --max-mirror-bytes N \
# httrack BASEURL/some/path [httrack-args...]
# --errors counts every "Error:" log line; --errors-content drops transient
# network failures (codes -2..-6) that flake on busy loopback under -c8.
# --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
# --max/--min-mirror-bytes bound the mirrored content bytes (host root).
# --file-matches/--file-not-matches grep (ERE) a mirrored file (PATH under the
# host root), to assert rewritten link/content survived the crawl.
# --file-min-bytes asserts a mirrored file (PATH) is at least N bytes.
# --rerun-args runs a second pass (same server and mirror dir) with the given
# extra httrack args appended, e.g. an --update run under a cap.
# --cookie writes a Netscape cookies.txt (scoped to the discovered host:port,
# which the ephemeral port forces into the cookie domain) and passes it to
# httrack via --cookies-file, to exercise preloaded cookies.
@@ -45,7 +39,6 @@ key="${testdir}/server.key"
tls=
verbose=
rerun=
rerun_args=
rerun_dead=
tmpdir=
serverpid=
@@ -129,11 +122,7 @@ while test "$pos" -lt "$nargs"; do
pos=$((pos + 1))
cookies+=("${args[$pos]}")
;;
--rerun-args)
pos=$((pos + 1))
rerun_args="${args[$pos]}"
;;
--errors | --errors-content | --files)
--errors | --files)
audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
pos=$((pos + 1))
;;
@@ -141,7 +130,7 @@ while test "$pos" -lt "$nargs"; do
audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
pos=$((pos + 1))
;;
--file-matches | --file-not-matches | --file-min-bytes)
--file-matches | --file-not-matches)
audit+=("${args[$pos]}" "${args[$((pos + 1))]}" "${args[$((pos + 2))]}")
pos=$((pos + 2))
;;
@@ -252,25 +241,6 @@ if test -n "$rerun"; then
fi
fi
# --- optional second pass with extra args (e.g. an --update run under a cap) ---
# Same server and mirror dir as the first pass, so the second pass sees the
# cache the first pass wrote. Used to exercise re-fetch/update behaviour.
if test -n "$rerun_args"; then
read -ra extra <<<"$rerun_args"
info "re-running httrack with ${rerun_args}"
httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" \
"${moreargs[@]}" "${hts[@]}" "${extra[@]}" >"${log}.2" 2>&1 &
crawlpid=$!
wait "$crawlpid"
crawlres=$?
crawlpid=
test "$crawlres" -eq 0 || ! result "second pass exited $crawlres" || {
cat "${log}.2" >&2
exit 1
}
result "OK (second pass)"
fi
# --- optional dead pass: server stopped, the cache must survive the rollback --
if test -n "$rerun_dead"; then
zip="${out}/hts-cache/new.zip"
@@ -336,14 +306,6 @@ while test "$i" -lt "${#audit[@]}"; do
assert_equals "checking errors" "${audit[$i]}" \
"$(grep -iEc "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")"
;;
--errors-content)
i=$((i + 1))
total=$(grep -icE "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")
# transient network failures (statuscode -2..-6) flake on busy loopback;
# the code parens are followed by " at link" or " after N retries at link"
transient=$(grep -cE '\(-[2-6]\) (at link|after )' "${out}/hts-log.txt" || true)
assert_equals "checking content errors" "${audit[$i]}" "$((total - transient))"
;;
--files)
i=$((i + 1))
nFiles=$(grep -E "^HTTrack Website Copier/[^ ]* mirror complete in " "${out}/hts-log.txt" |
@@ -426,16 +388,6 @@ while test "$i" -lt "${#audit[@]}"; do
exit 1
else result "OK"; fi
;;
--file-min-bytes)
path="${audit[$((i + 1))]}"
i=$((i + 2))
sz=$(wc -c <"${hostroot}/${path}" 2>/dev/null | tr -d '[:space:]')
info "checking ${path} size ${sz:-0} >= ${audit[$i]} bytes"
if test -n "$sz" && test "$sz" -ge "${audit[$i]}"; then result "OK"; else
result "file too small (or missing)"
exit 1
fi
;;
esac
i=$((i + 1))
done

View File

@@ -934,33 +934,6 @@ class Handler(SimpleHTTPRequestHandler):
def route_mini304_page(self):
self.big_send(b"<html><body>tiny cacheable page</body></html>\n", "text/html")
# --- /errmask/: issue #176 — a page that 200'd on the first crawl but 403s
# on the update fetch must keep its good copy, not be overwritten nor purged.
ERRMASK_GOOD = b"KEEP" + b"." * 1020 # 1024 B distinctive non-HTML body
ERRMASK_ERR = b"<html><body>error 403</body></html>\n"
def route_errmask_index(self):
self.send_html('\t<a href="keep.dat">keep</a>\n')
def route_errmask_keep(self):
# First crawl (no validator) gets the 1024 B body + Last-Modified; the
# update sends a conditional and gets a 403 error page.
if self.headers.get("If-Modified-Since") or self.headers.get("If-None-Match"):
self.send_response(403, "Forbidden")
self.send_header("Content-Type", "text/html")
self.send_header("Content-Length", str(len(self.ERRMASK_ERR)))
self.end_headers()
if self.command != "HEAD":
self.wfile.write(self.ERRMASK_ERR)
return
self.send_response(200)
self.send_header("Content-Type", "application/octet-stream")
self.send_header("Last-Modified", BIG_LASTMOD)
self.send_header("Content-Length", str(len(self.ERRMASK_GOOD)))
self.end_headers()
if self.command != "HEAD":
self.wfile.write(self.ERRMASK_GOOD)
# --- delayed-type degenerate paths (issues #5/#107) --------------------
def route_delayed_index(self):
self.send_html(
@@ -1062,48 +1035,6 @@ class Handler(SimpleHTTPRequestHandler):
def route_bigfile(self):
self.send_raw(b"x" * self.BIGFILE_BYTES, "application/octet-stream")
# -M under a slow server (#77): p0 is a fast 640KB file that alone overruns
# -M; p1..p3 trickle for a minute. The cap must abort those in-flight
# transfers, not wait them out.
def route_bigtrickle_index(self):
self.send_html(
"".join('\t<a href="p%d.bin">p%d</a>\n' % (i, i) for i in range(4))
)
# -M hard-abort must not destroy an already-complete file (#77 follow-up).
# "fast.bin" alone overruns -M and completes; "slow.bin" transfers fully on
# its first fetch (initial mirror) but stalls on every later fetch (the
# --update re-fetch), so the -M abort tears it down mid-body. An engine that
# truncates the good local copy on the aborted re-fetch loses data.
slow_seen = 0
def route_bigtrunc_index(self):
self.send_html('\t<a href="fast.bin">fast</a>\n\t<a href="slow.bin">slow</a>\n')
def route_bigtrunc_slow(self):
self.send_response(200)
self.send_header("Content-Type", "application/octet-stream")
self.send_header("Content-Length", str(self.BIGFILE_BYTES))
self.end_headers()
if self.command == "HEAD":
return
# Count body fetches only, so a stray HEAD can't shift which pass stalls.
Handler.slow_seen += 1
first = Handler.slow_seen == 1
try:
if first:
self.wfile.write(b"x" * self.BIGFILE_BYTES)
self.wfile.flush()
else:
self.wfile.write(b"x" * 4096)
self.wfile.flush()
for _ in range(120):
self.wfile.write(b"x")
self.wfile.flush()
time.sleep(1.0)
except OSError:
pass
ROUTES = {
"/cookies/entrance.php": route_entrance,
"/cookies/second.php": route_second,
@@ -1176,14 +1107,6 @@ class Handler(SimpleHTTPRequestHandler):
"/bigfiles/p5.bin": route_bigfile,
"/bigfiles/p6.bin": route_bigfile,
"/bigfiles/p7.bin": route_bigfile,
"/bigtrickle/index.html": route_bigtrickle_index,
"/bigtrickle/p0.bin": route_bigfile,
"/bigtrickle/p1.bin": route_trickle_page,
"/bigtrickle/p2.bin": route_trickle_page,
"/bigtrickle/p3.bin": route_trickle_page,
"/bigtrunc/index.html": route_bigtrunc_index,
"/bigtrunc/fast.bin": route_bigfile,
"/bigtrunc/slow.bin": route_bigtrunc_slow,
"/delayed/noloc.php": route_delayed_noloc,
"/delayed/selfloop.php": route_delayed_selfloop,
"/delayed/redir.php": route_delayed_redir,
@@ -1204,8 +1127,6 @@ class Handler(SimpleHTTPRequestHandler):
"/redir/target.html": route_redir_target,
"/mini304/index.html": route_mini304_index,
"/mini304/page.html": route_mini304_page,
"/errmask/index.html": route_errmask_index,
"/errmask/keep.dat": route_errmask_keep,
}
# --- /big/ seeded pseudo-site ------------------------------------------