Split -%u URL Hacks into independent www/slash/query toggles (#271)

-%u (--urlhack) bundled three dedup normalizations under one switch:
www.host == host, redundant // collapse, and query-argument reordering.
A mirror that needed one but not another (e.g. keep www. distinct) had to
turn the whole umbrella off. Add three opt-out sub-options, defaulting to
the umbrella so existing -%u/-%u0 behavior is unchanged:

  --keep-www-prefix      keep www.foo.com distinct from foo.com   (-%j)
  --keep-double-slashes  keep redundant // in the path            (-%o)
  --keep-query-order     keep query-argument order significant    (-%y)

The split is resolved once in hash_init() into norm_host/norm_slash/
norm_query and threaded through the dedup hash (htshash.c), the savename
lookup key (htsname.c) and the redirect-loop diagnostic (htsparse.c) so
all three stay consistent. fil_normalized() gains an internal
fil_normalized_ex(do_slash, do_query) core; the public
fil_normalized()/fil_normalized_filtered() keep their signatures.

Normalization (slash/query) now follows urlhack and its sub-flags
uniformly, while --strip-query stays orthogonal. So with urlhack off,
strip-query strips keys without sorting the remainder; the url_savename
urlhack-off branch is moved to the same do_slash=0/do_query=0 normalizer
the hash uses, so a URL is always looked up under the key it was stored
with (a self-lookup mismatch this otherwise introduced).

http/https are always merged in the dedup key (the scheme is stripped
regardless of -%u), so that part of the request needs no toggle.

The opt-outs are spelled positively (--keep-*) because httrack's generic
--no<opt> prefix only appends the disabling "0" for parametered options,
not "single" booleans, so --nowww-dedup would silently no-op.

opt grows three hts_boolean fields appended at the struct tail (offsets
stable, no soname bump, matching the strip_query addition in #112).

Tested by a -#test=urlhack engine self-test (hash_url_equals over each
flag combination) plus a -%u0 + --strip-query crawl case exercising the
urlhack-off savename branch.

Closes #271

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

debian/control

@@ -30,7 +30,7 @@ Description: Copy websites to your computer (Offline browser)
 Package: webhttrack
 Architecture: any
 Multi-Arch: foreign
-Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, chromium | firefox-esr | www-browser
+Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, firefox-esr | chromium | www-browser
 Replaces: webhttrack-common (<< 3.43.9-2)
 Breaks: webhttrack-common (<< 3.43.9-2)
 Suggests: httrack, httrack-doc

man/httrack.1

@@ -24,7 +24,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-EN, \-\-max\-time[=N]\fR ]
 [ \fB\-AN, \-\-max\-rate[=N]\fR ]
 [ \fB\-%cN, \-\-connection\-per\-second[=N]\fR ]
-[ \fB\-%G, \-\-pause\fR ]
 [ \fB\-GN, \-\-max\-pause[=N]\fR ]
 [ \fB\-cN, \-\-sockets[=N]\fR ]
 [ \fB\-TN, \-\-timeout[=N]\fR ]
@@ -50,7 +49,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%p, \-\-preserve\fR ]
 [ \fB\-%T, \-\-utf8\-conversion\fR ]
 [ \fB\-bN, \-\-cookies[=N]\fR ]
-[ \fB\-%K, \-\-cookies\-file\fR ]
 [ \fB\-u, \-\-check\-type[=N]\fR ]
 [ \fB\-j, \-\-parse\-java[=N]\fR ]
 [ \fB\-sN, \-\-robots[=N]\fR ]
@@ -156,8 +154,6 @@ maximum mirror time in seconds (60=1 minute, 3600=1 hour) (\-\-max\-time[=N])
 maximum transfer rate in bytes/seconds (1000=1KB/s max) (\-\-max\-rate[=N])
 .IP \-%cN
 maximum number of connections/seconds (*%c10) (\-\-connection\-per\-second[=N])
-.IP \-%G
-random pause of MIN[:MAX] seconds between files (e.g. %G5:10) (\-\-pause <param>)
 .IP \-GN
 pause transfer if N bytes reached, and wait until lock file is deleted (\-\-max\-pause[=N])
 .SS Flow control:
@@ -216,8 +212,6 @@ links conversion to UTF\-8 (\-\-utf8\-conversion)
 .SS Spider options:
 .IP \-bN
 accept cookies in cookies.txt (0=do not accept,* 1=accept) (\-\-cookies[=N])
-.IP \-%K
-load extra cookies from a Netscape cookies.txt (\-\-cookies\-file <param>)
 .IP \-u
 check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (\-\-check\-type[=N])
 .IP \-j

src/htsalias.c

@@ -112,10 +112,6 @@ const char *hts_optalias[][4] = {
   {"include-query-string", "-%q", "single", ""},
   {"strip-query", "-%g", "param1",
    "strip [host/pattern=]key1,key2,... from URLs"},
-  {"cookies-file", "-%K", "param1",
-   "load extra cookies from a Netscape cookies.txt"},
-  {"pause", "-%G", "param1",
-   "random pause of MIN[:MAX] seconds between files"},
   {"generate-errors", "-o", "single", ""},
   {"do-not-generate-errors", "-o0", "single", ""},
   {"purge-old", "-X", "param", ""},

src/htscore.c

@@ -35,7 +35,6 @@ Please visit our Website: http://www.httrack.com
 
 #include <fcntl.h>
 #include <ctype.h>
-#include <stdint.h> /* uint64_t for the pause mixer (already a hard dep via md5.h) */
 
 /* File defs */
 #include "htscore.h"
@@ -524,12 +523,9 @@ int httpmirror(char *url1, httrackp * opt) {
     opt->cookie = &cookie;
     cookie.max_len = 30000;     // max len
     strcpybuff(cookie.data, "");
-    // Load the mirror's cookies.txt, then the one in the current directory
+    // Charger cookies.txt par défaut ou cookies.txt du miroir
     cookie_load(opt->cookie, StringBuff(opt->path_log), "cookies.txt");
     cookie_load(opt->cookie, "", "cookies.txt");
-    // A user-supplied cookie file is merged last so it wins on conflicts
-    if (strnotempty(StringBuff(opt->cookies_file)))
-      cookie_load(opt->cookie, "", StringBuff(opt->cookies_file));
   } else
     opt->cookie = NULL;
 
@@ -3315,21 +3311,6 @@ HTS_INLINE int back_fillmax(struct_back * sback, httrackp * opt,
   return -1;                    /* plus de place */
 }
 
-/* Seed-derived: stable within a gap, rerolls per launch; a per-call rand()
-   would bias the delay toward min_ms (see header). Jitter, not crypto. */
-int hts_pause_target_ms(TStamp seed, int min_ms, int max_ms) {
-  uint64_t z = (uint64_t) seed;
-
-  if (max_ms <= min_ms)
-    return min_ms;
-  /* SplitMix64 finalizer: scrambles the low-entropy ms timestamp. */
-  z += 0x9E3779B97F4A7C15ULL;
-  z = (z ^ (z >> 30)) * 0xBF58476D1CE4E5B9ULL;
-  z = (z ^ (z >> 27)) * 0x94D049BB133111EBULL;
-  z ^= z >> 31;
-  return min_ms + (int) (z % (uint64_t) (max_ms - min_ms + 1));
-}
-
 int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt) {
   int n = opt->maxsoc - back_nsoc(sback);
 
@@ -3350,18 +3331,6 @@ int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt) {
     }
   }
 
-  // #185 randomized inter-file pause: non-blocking, one launch per gap
-  if (n > 0 && opt->pause_max_ms > 0 && HTS_STAT.last_connect > 0) {
-    TStamp opTime =
-        HTS_STAT.last_request ? HTS_STAT.last_request : HTS_STAT.last_connect;
-    TStamp lap = mtime_local() - opTime;
-
-    if (lap < hts_pause_target_ms(opTime, opt->pause_min_ms, opt->pause_max_ms))
-      n = 0;
-    else
-      n = 1;
-  }
-
   return n;
 }
 
@@ -3773,14 +3742,6 @@ HTSEXT_API int copy_htsopt(const httrackp * from, httrackp * to) {
   if (StringNotEmpty(from->strip_query))
     StringCopyS(to->strip_query, from->strip_query);
 
-  if (StringNotEmpty(from->cookies_file))
-    StringCopyS(to->cookies_file, from->cookies_file);
-
-  if (from->pause_max_ms > 0) {
-    to->pause_min_ms = from->pause_min_ms;
-    to->pause_max_ms = from->pause_max_ms;
-  }
-
   if (from->retry > -1)
     to->retry = from->retry;
 

src/htscore.h

@@ -418,10 +418,6 @@ int back_pluggable_sockets(struct_back * sback, httrackp * opt);
 
 int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt);
 
-/* 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);
-
 /* Schedule more links from the heap into free slots. Returns the number queued,
    or <=0 if none could be added (no free slot / paused / stopped). */
 int back_fill(struct_back * sback, httrackp * opt, cache_back * cache,

src/htscoremain.c

@@ -1976,51 +1976,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                   StringCat(opt->strip_query, argv[na]);
                 }
                 break;
-              case 'K': // cookies-file: extra Netscape cookies.txt to preload
-                if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
-                  HTS_PANIC_PRINTF(
-                      "Option cookies-file needs a blank space and "
-                      "a cookies.txt path");
-                  printf("Example: --cookies-file \"/home/me/cookies.txt\"\n");
-                  htsmain_free();
-                  return -1;
-                } else {
-                  na++;
-                  if (strlen(argv[na]) >= 1024) {
-                    HTS_PANIC_PRINTF("Cookie file path too long");
-                    htsmain_free();
-                    return -1;
-                  }
-                  StringCopy(opt->cookies_file, argv[na]);
-                }
-                break;
-              case 'G': // pause: randomized inter-file delay MIN[:MAX] seconds
-                if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
-                  HTS_PANIC_PRINTF("Option pause needs a blank space and a "
-                                   "delay in seconds (MIN[:MAX])");
-                  printf("Example: --pause 5:10\n");
-                  htsmain_free();
-                  return -1;
-                } else {
-                  double pmin = 0, pmax = 0;
-                  int nf;
-
-                  na++;
-                  nf = sscanf(argv[na], "%lf:%lf", &pmin, &pmax);
-                  if (nf < 2)
-                    pmax = pmin; /* a single value means a fixed delay */
-                  /* positive-form bounds: NaN fails every comparison, so this
-                     rejects it before the undefined (int)(NaN*1000) cast */
-                  if (nf < 1 || !(pmin >= 0 && pmax >= pmin && pmax <= 86400)) {
-                    HTS_PANIC_PRINTF("Invalid --pause range (expected "
-                                     "MIN[:MAX] seconds, 0<=MIN<=MAX<=86400)");
-                    htsmain_free();
-                    return -1;
-                  }
-                  opt->pause_min_ms = (int) (pmin * 1000.0);
-                  opt->pause_max_ms = (int) (pmax * 1000.0);
-                }
-                break;
               case 't':        /* do not change type (ending) of filenames according to the MIME type */
                 opt->no_type_change = 1;
                 if (*(com+1)=='0') { opt->no_type_change = 0; com++; }

src/htshelp.c

@@ -521,7 +521,6 @@ void help(const char *app, int more) {
   infomsg("  EN maximum mirror time in seconds (60=1 minute, 3600=1 hour)");
   infomsg("  AN maximum transfer rate in bytes/seconds (1000=1KB/s max)");
   infomsg(" %cN maximum number of connections/seconds (*%c10)");
-  infomsg(" %G  random pause of MIN[:MAX] seconds between files (e.g. %G5:10)");
   infomsg
     ("  GN pause transfer if N bytes reached, and wait until lock file is deleted");
   infomsg("");
@@ -573,7 +572,6 @@ void help(const char *app, int more) {
   infomsg("");
   infomsg("Spider options:");
   infomsg("  bN accept cookies in cookies.txt (0=do not accept,* 1=accept)");
-  infomsg(" %K  load extra cookies from a Netscape cookies.txt");
   infomsg
     ("  u  check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)");
   infomsg

src/htslib.c

@@ -6045,9 +6045,6 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->no_query_dedup = HTS_FALSE;
   StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
   StringCopy(opt->strip_query, "");
-  StringCopy(opt->cookies_file, "");
-  opt->pause_min_ms = 0;
-  opt->pause_max_ms = 0;
   opt->ftp_proxy = HTS_TRUE;
   opt->convert_utf8 = HTS_TRUE;
   StringCopy(opt->filelist, "");
@@ -6193,7 +6190,6 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->footer);
     StringFree(opt->mod_blacklist);
     StringFree(opt->strip_query);
-    StringFree(opt->cookies_file);
 
     StringFree(opt->path_html);
     StringFree(opt->path_html_utf8);

src/htsopt.h

@@ -535,10 +535,6 @@ struct httrackp {
       no_www_dedup; /**< with urlhack, keep www.host distinct from host */
   hts_boolean no_slash_dedup; /**< with urlhack, keep redundant // in paths */
   hts_boolean no_query_dedup; /**< with urlhack, keep query-argument order */
-  String cookies_file;        /**< extra Netscape cookies.txt to preload
-                                 (--cookies-file) */
-  int pause_min_ms; /**< inter-file pause lower bound, ms (0=off, #185) */
-  int pause_max_ms; /**< inter-file pause upper bound, ms */
 };
 
 /* Running statistics for a mirror. */

src/htsselftest.c

@@ -899,71 +899,12 @@ static int st_copyopt(httrackp *opt, int argc, char **argv) {
   if (to->parseall != HTS_TRUE)
     err = 1;
 
-  /* String field: a non-empty source deep-copies across, an empty source
-     leaves the target intact (StringNotEmpty guard). Covers the exported
-     copy_htsopt String path that no crawl test reaches. */
-  StringCopy(from->cookies_file, "/tmp/jar.txt");
-  StringCopy(to->cookies_file, "");
-  copy_htsopt(from, to);
-  if (strcmp(StringBuff(to->cookies_file), "/tmp/jar.txt") != 0)
-    err = 1;
-  StringCopy(from->cookies_file, "");
-  copy_htsopt(from, to);
-  if (strcmp(StringBuff(to->cookies_file), "/tmp/jar.txt") != 0)
-    err = 1;
-
-  /* #185 pause pair: copied when enabled (max>0), the 0 sentinel skips */
-  from->pause_min_ms = 5000;
-  from->pause_max_ms = 10000;
-  to->pause_min_ms = to->pause_max_ms = 0;
-  copy_htsopt(from, to);
-  if (to->pause_min_ms != 5000 || to->pause_max_ms != 10000)
-    err = 1;
-  from->pause_min_ms = from->pause_max_ms = 0;
-  copy_htsopt(from, to);
-  if (to->pause_min_ms != 5000 || to->pause_max_ms != 10000)
-    err = 1;
-
   hts_free_opt(from);
   hts_free_opt(to);
   printf("copy-htsopt: %s\n", err ? "FAIL" : "OK");
   return err;
 }
 
-static int st_pause(httrackp *opt, int argc, char **argv) {
-  int err = 0, i, seen_low = 0, seen_high = 0;
-
-  (void) opt;
-  (void) argc;
-  (void) argv;
-  /* Consecutive-ms seeds (production shape: launch timestamps a few ms apart)
-     must stay in range and spread, not collapse to a bound -- worst case for a
-     weak low-bit mixer. */
-  for (i = 0; i < 10000; i++) {
-    int t = hts_pause_target_ms((TStamp) (1719500000000LL + i), 5000, 10000);
-
-    if (t < 5000 || t > 10000)
-      err = 1;
-    seen_low |= (t < 6000);
-    seen_high |= (t > 9000);
-  }
-  if (!seen_low || !seen_high)
-    err = 1;
-  if (hts_pause_target_ms(12345, 8000, 8000) != 8000) /* equal bounds = fixed */
-    err = 1;
-  /* deterministic: a seed yields the same target even after an intervening call
-     with another seed (no global PRNG state to perturb it) */
-  {
-    int a = hts_pause_target_ms(99, 5000, 10000);
-
-    (void) hts_pause_target_ms(54321, 5000, 10000);
-    if (hts_pause_target_ms(99, 5000, 10000) != a)
-      err = 1;
-  }
-  printf("pause: %s\n", err ? "FAIL" : "OK");
-  return err;
-}
-
 static int st_relative(httrackp *opt, int argc, char **argv) {
   char s[HTS_URLMAXSIZE * 2];
 
@@ -1310,7 +1251,6 @@ static const struct selftest_entry {
     {"strsafe", "[overflow|overflow-buff [str]]", "bounded string-op self-test",
      st_strsafe},
     {"copyopt", "", "copy_htsopt option-copy self-test", st_copyopt},
-    {"pause", "", "randomized inter-file pause target self-test", st_pause},
     {"relative", "<link> <curr-file>", "relative link between two paths",
      st_relative},
     {"resolve", "<link> <adr> <fil>", "resolve a link against an origin",

tests/01_engine-cmdline.test

@@ -90,16 +90,4 @@ refused "dangling-quote argument not refused cleanly"
 run_only "$tmp/q-lone" '"'
 refused "lone-quote argument not refused cleanly"
 
-# --pause (#185): valid MIN[:MAX] accepted; malformed, reversed, over-range and
-# non-finite values refused cleanly. NaN defeats naive `<`/`>` checks (it
-# compares false to everything), so it must not slip through to the int cast.
-run "$tmp/pause-ok" --pause 0.2:0.4
-accepted "$tmp/pause-ok" "#185: valid --pause range rejected"
-run "$tmp/pause-fix" --pause 0.2
-accepted "$tmp/pause-fix" "#185: valid fixed --pause rejected"
-for bad in nan nan:5 5:nan inf 10:5 99999; do
-    run "$tmp/pause-bad" --pause "$bad"
-    refused "#185: invalid --pause '$bad' not refused cleanly"
-done
-
 exit 0

tests/01_engine-pause.test

@@ -1,15 +0,0 @@
-#!/bin/bash
-#
-# --pause (#185): the inter-file pause target must stay in [min,max] and spread
-# across it (a per-call rand() would collapse it toward min). Driven by the
-# in-process 'httrack -#test=pause' test. POSIX-portable ($(BASH) is /bin/sh on macOS).
-
-set -eu
-
-# 'run' is an ignored placeholder argument.
-out=$(httrack -#test=pause run)
-
-test "$out" = "pause: OK" || {
-    echo "expected 'pause: OK', got: $out" >&2
-    exit 1
-}

tests/27_local-cookies-file.test

@@ -1,22 +0,0 @@
-#!/bin/bash
-#
-# End-to-end --cookies-file (#215): /gated/secret.php needs a cookie no page
-# ever Set-Cookies, so it is reachable only when the option preloads it from a
-# Netscape cookies.txt. Locks the CLI->opt->cookie_load->wire plumbing.
-
-set -e
-
-: "${top_srcdir:=..}"
-
-# preloaded cookie -> secret page is served. -o0 means a 500 leaves no file, so
-# --found/--files only hold when the secret is genuinely fetched (200).
-bash "$top_srcdir/tests/local-crawl.sh" --cookie 'session=opensesame' \
-    --errors 0 --files 2 \
-    --found 'gated/index.html' --found 'gated/secret.html' \
-    httrack 'BASEURL/gated/index.php' -o0
-
-# control: without the cookie the secret 500s; -o0 suppresses the error page so
-# its absence is real (error + missing file)
-bash "$top_srcdir/tests/local-crawl.sh" --errors 1 \
-    --found 'gated/index.html' --not-found 'gated/secret.html' \
-    httrack 'BASEURL/gated/index.php' -o0

tests/28_local-pause.test

@@ -1,29 +0,0 @@
-#!/bin/bash
-#
-# --pause (#185): a fixed inter-file delay must slow a multi-file crawl. Measure
-# the same crawl with and without --pause and compare: the harness overhead
-# cancels, leaving only the pause. Integer seconds keep it portable (BSD date
-# has no %N); a lower bound is not timing-flaky since a pause only adds time.
-
-set -e
-
-: "${top_srcdir:=..}"
-
-run() { # echoes the wall-clock seconds of one crawl
-    local t0 t1
-    t0=$(date +%s)
-    bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
-        httrack 'BASEURL/types/index.html' -c1 "$@" >/dev/null 2>&1
-    t1=$(date +%s)
-    echo $((t1 - t0))
-}
-
-base=$(run)
-paused=$(run --pause 0.5)
-delta=$((paused - base))
-
-echo "crawl: ${base}s, with --pause 0.5: ${paused}s (delta ${delta}s)"
-if [ "$delta" -lt 2 ]; then
-    echo "FAIL: --pause did not delay the crawl (delta ${delta}s)" >&2
-    exit 1
-fi

tests/Makefile.am

@@ -41,7 +41,6 @@ TESTS = \
 	01_engine-idna.test \
 	01_engine-mime.test \
 	01_engine-parse.test \
-	01_engine-pause.test \
 	01_engine-rcfile.test \
 	01_engine-relative.test \
 	01_engine-savename.test \
@@ -73,8 +72,6 @@ TESTS = \
 	23_local-errpage.test \
 	24_local-resume-overlap.test \
 	25_local-mime-exclude.test \
-	26_local-strip-query.test \
-	27_local-cookies-file.test \
-	28_local-pause.test
+	26_local-strip-query.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -12,14 +12,11 @@
 # the mirror directory name.
 #
 # Usage:
-#   bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
+#   bash local-crawl.sh [--tls] [--root DIR] \
 #       --errors N --files N --found PATH ... --directory PATH ... \
 #       --log-found REGEX ... --log-not-found REGEX ... \
 #       httrack BASEURL/some/path [httrack-args...]
 # --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
-# --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.
 
 set -u
 
@@ -88,7 +85,6 @@ tmpdir=$(mktemp -d "${tmptopdir}/httrack_local.XXXXXX") || die "could not create
 
 # --- parse leading control flags --------------------------------------------
 declare -a audit=()
-declare -a cookies=()
 scheme=http
 pos=0
 args=("$@")
@@ -109,10 +105,6 @@ while test "$pos" -lt "$nargs"; do
         pos=$((pos + 1))
         root="${args[$pos]}"
         ;;
-    --cookie)
-        pos=$((pos + 1))
-        cookies+=("${args[$pos]}")
-        ;;
     --errors | --files)
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
@@ -166,17 +158,6 @@ while test "$pos" -lt "$nargs"; do
     pos=$((pos + 1))
 done
 
-# --- materialize any --cookie entries into a cookies.txt ---------------------
-if test "${#cookies[@]}" -gt 0; then
-    jar="${tmpdir}/cookies.txt"
-    : >"$jar"
-    for spec in "${cookies[@]}"; do
-        printf '127.0.0.1:%s\tTRUE\t/\tFALSE\t1999999999\t%s\t%s\n' \
-            "$port" "${spec%%=*}" "${spec#*=}" >>"$jar"
-    done
-    hts+=(--cookies-file "$jar")
-fi
-
 # --- run httrack -------------------------------------------------------------
 which httrack >/dev/null || die "could not find httrack"
 ver=$(httrack -O /dev/null --version | sed -e 's/HTTrack version //')

tests/local-server.py

@@ -110,19 +110,6 @@ class Handler(SimpleHTTPRequestHandler):
             return self.fail_cookie("badger")
         self.send_html("\tThis is a test.")
 
-    # --cookies-file (#215): the secret page needs a cookie no page ever sets,
-    # so it is reachable only when --cookies-file preloads it.
-    GATE_COOKIE = ("session", "opensesame")
-
-    def route_gated_index(self):
-        self.send_html('\tThis is a <a href="secret.php">link</a>')
-
-    def route_gated_secret(self):
-        name, value = self.GATE_COOKIE
-        if self.request_cookies().get(name) != value:
-            return self.fail_cookie(name)
-        self.send_html("\tThis is the secret.")
-
     def route_robots(self):
         body = b"User-agent: *\nDisallow:\n"
         self.send_response(200)
@@ -358,8 +345,6 @@ class Handler(SimpleHTTPRequestHandler):
         "/cookies/entrance.php": route_entrance,
         "/cookies/second.php": route_second,
         "/cookies/third.php": route_third,
-        "/gated/index.php": route_gated_index,
-        "/gated/secret.php": route_gated_secret,
         "/robots.txt": route_robots,
         "/types/index.html": route_types_index,
         "/types/control.php": route_types,