Don't resolve or dial the origin ourselves when a proxy is set

The connect-fallback probe resolved the origin locally and, on a proxy-connect
failure, fell back to dialing the origin direct — bypassing the proxy, leaking
the origin's DNS query, and sending it the request (with the full absolute URI)
over a direct connection. Under a proxy the socket dials the proxy, not the
origin, so an origin-address list is meaningless here; gate the probe on
!proxy.active. A dead proxy now fails cleanly instead of falling open to the
origin.

Test 55 drives a crawl through a dead proxy at a two-address origin decoy and
asserts the decoy is never contacted; it fails on the pre-fix engine.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/codeql.yml

@@ -46,6 +46,12 @@ jobs:
           # fopen's umask-controlled 0666 is intended for mirror/cache/log
           # output; the one credential file (cookies.txt) is kept 0600 on Unix.
           config: |
+            paths-ignore:
+              # Demo callback samples, not part of libhttrack.
+              - libtest
+              # ProxyTrack: a separate legacy binary with no auth surface; its
+              # recv/cache-parse code trips taint queries by design.
+              - src/proxy
             query-filters:
               - exclude:
                   id: cpp/world-writable-file-creation

.github/workflows/windows-build.yml

@@ -123,9 +123,12 @@ jobs:
       # is Linux/macOS only. These are the offline ones, driven from Git Bash
       # against the native httrack.exe. They subsume the self-tests this step
       # used to run inline (codecs, cache, fsize).
+      # The *_local-* ones crawl the bundled Python server over loopback: the real
+      # TLS handshake, cache and file writer, which nothing else on Windows covers.
       - name: Run the engine test suite (offline tests)
         shell: bash
         working-directory: tests
+        timeout-minutes: 45
         run: |
           set -u
           bin="$(cygpath -u "$GITHUB_WORKSPACE")/src/${{ matrix.platform }}/${{ matrix.configuration }}"
@@ -141,13 +144,24 @@ jobs:
           TMPDIR="$(cygpath -m "$RUNNER_TEMP")"
           export TMPDIR
 
-          pass=0 fail=0 skip=0 failed=""
+          # Mirror what configure hands the suite. LC_ALL sets the codeset MSYS maps
-          for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test; do
+          # a UTF-8 mirror name onto UTF-16 with, which the intl crawls "test -f".
+          export HTTPS_SUPPORT=yes BROTLI_ENABLED=yes ZSTD_ENABLED=yes
+          export LC_ALL=C.UTF-8
+
+          # A wedged crawl must not eat the job's whole timeout budget.
+          watchdog=""
+          command -v timeout >/dev/null && watchdog="timeout 600"
+
+          pass=0 fail=0 skip=0 failed="" skipped=""
+          for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test \
+                   *_local-*.test 13_crawl_proxy_https.test; do
             rc=0
-            bash "$t" >"$t.log" 2>&1 || rc=$?
+            # shellcheck disable=SC2086
+            $watchdog bash "$t" >"$t.log" 2>&1 || rc=$?
             case "$rc" in
               0) pass=$((pass + 1)); echo "PASS $t" ;;
-              77) skip=$((skip + 1)); echo "SKIP $t" ;;
+              77) skip=$((skip + 1)) skipped="$skipped $t"; echo "SKIP $t" ;;
               *)
                 fail=$((fail + 1)) failed="$failed $t"
                 echo "FAIL $t (exit $rc)"
@@ -161,10 +175,11 @@ jobs:
           echo "ran=$((pass + fail + skip)) pass=$pass fail=$fail skip=$skip" |
             tee -a "$GITHUB_STEP_SUMMARY"
 
-          # Every gate in these scripts exits 77, so a suite that degraded to
+          # Every gate here exits 77, so an all-skipped suite would report green having
-          # all-skipped would report green having tested nothing: assert a floor
+          # tested nothing: pin the skips, and floor the passes in case the glob empties.
-          # on what actually ran, not just the absence of failures.
+          expected_skips=" 48_local-crange-memresume.test"  # pending #581
-          [ "$pass" -ge 45 ] || { echo "::error::only $pass tests passed ($skip skipped)"; exit 1; }
+          [ "$pass" -ge 90 ] || { echo "::error::only $pass tests passed ($skip skipped)"; exit 1; }
+          [ "$skipped" = "$expected_skips" ] || { echo "::error::unexpected skips:$skipped"; exit 1; }
           [ "$fail" -eq 0 ] || { echo "::error::failing:$failed"; exit 1; }
 
       - name: Upload the test logs

fuzz/Makefile.am

@@ -1,7 +1,8 @@
 # libFuzzer harnesses; built only with --enable-fuzzers (requires clang).
 if FUZZERS
 noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
-	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx
+	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx \
+	fuzz-htsparse
 endif
 
 AM_CPPFLAGS = \
@@ -25,6 +26,7 @@ fuzz_filters_SOURCES = fuzz-filters.c fuzz.h
 fuzz_url_SOURCES = fuzz-url.c fuzz.h
 fuzz_header_SOURCES = fuzz-header.c fuzz.h
 fuzz_cachendx_SOURCES = fuzz-cachendx.c fuzz.h
+fuzz_htsparse_SOURCES = fuzz-htsparse.c fuzz.h
 
 # List corpus files explicitly: automake does not expand EXTRA_DIST globs.
 EXTRA_DIST = README.md run-fuzzers.sh \
@@ -37,9 +39,12 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/filters/filter.bin corpus/filters/filter-size.bin \
 	corpus/filters/regress-empty-subject-unique.bin \
 	corpus/filters/redos-star-classes.bin \
+	corpus/filters/regress-classdepth-timeout.bin \
 	corpus/url/http-url.txt corpus/url/relative-path.txt \
 	corpus/url/regress-file-empty-path.txt corpus/url/regress-long-path-abort.txt \
 	corpus/header/full-response.txt corpus/header/redirect.txt \
 	corpus/cachendx/new-format.txt corpus/cachendx/old-format.txt \
 	corpus/cachendx/regress-overadvance.bin \
-	corpus/cachendx/regress-truncated-entry.bin
+	corpus/cachendx/regress-truncated-entry.bin \
+	corpus/htsparse/basic.html corpus/htsparse/script-inscript.html \
+	corpus/htsparse/meta-usemap.html corpus/htsparse/malformed.html

fuzz/corpus/htsparse/basic.html

@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html><head>
+<meta charset="utf-8">
+<base href="http://example.com/dir/">
+<title>Seed</title>
+<link rel="stylesheet" href="style.css">
+<script src="app.js"></script>
+</head><body>
+<h1>Hi</h1>
+<a href="page2.html">next</a>
+<a href="http://other.example.org/x?y=1#frag">abs</a>
+<img src="pic.png" srcset="a.png 1x, b.png 2x">
+<script>var u="inline.html"; document.write('<a href="gen.html">g</a>');</script>
+<form action="/cgi/submit"><input name="q"></form>
+</body></html>

fuzz/corpus/htsparse/malformed.html

@@ -0,0 +1,8 @@
+<a href="unclosed.html
+<img src='mix"ed.png>
+<a href=noquote.html >bare</a>
+<!-- comment <a href="incomment.html"> -->
+<a href="tab	newline
+.html">wsp</a>
+<script>unterminated "string and <a href=
+<a href=

fuzz/corpus/htsparse/meta-usemap.html

@@ -0,0 +1,11 @@
+<html><head>
+<meta http-equiv="refresh" content="0; url=redir.html">
+<base href="http://h/b/">
+<link rel="alternate" href="feed.xml">
+</head><body background="page-bg.jpg">
+<img src="map.png" usemap="#m">
+<map name="m"><area href="area1.html" coords="0,0,10,10"></map>
+<applet code="A.class" codebase="applets/"><param name="src" value="p.dat"></applet>
+<object data="o.swf"><embed src="e.svg"></object>
+<a href="&#104;ttp://ent/e.html">entity</a>
+</body></html>

fuzz/corpus/htsparse/script-inscript.html

@@ -0,0 +1,13 @@
+<html><body>
+<script type="text/javascript">
+var a = "http://x/1.html", b = 'q\'uote', c = "/*not*/comment";
+// line "with" quotes and http://y/2.html
+/* block 'with' <a href="notparsed"> */
+var re = /a\/b\//g;
+document.write('<img src="w1.png">');
+document.writeln("<a href='w2.html'>k</a>");
+element.onclick = "location='onh.html'";
+</script>
+<a href="after.html" onmouseover="go('ev.html')">x</a>
+<div style="background:url(bg.png)">z</div>
+</body></html>

fuzz/fuzz-htsparse.c

@@ -0,0 +1,175 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 2026 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* Fuzz the real htsparse() over a mocked engine: the minimal crawl state
+   httpmirror() builds, then a page walked through the parser and discarded. The
+   str/stre wiring below mirrors htsparse()'s call site in htscore.c; update it
+   in lockstep if those structs gain a field the parser reads. */
+#include "fuzz.h"
+
+#include "httrack-library.h"
+#include "htscore.h"
+#include "htsback.h"
+#include "htshash.h"
+#include "htsrobots.h"
+#include "htsparse.h"
+#include "htsmodules.h"
+#include "coucal.h"
+
+/* htsparse ignores str.addLink on the internal parse; stub it. */
+static int fuzz_addlink(htsmoduleStruct *str, char *link) {
+  (void) str;
+  (void) link;
+  return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
+  static int inited = 0;
+
+  httrackp *opt;
+  cache_back cache;
+  hash_struct hash;
+  robots_wizard robots;
+  struct_back *sback;
+  char **filters = NULL;
+  int filptr = 0;
+
+  htsblk r;
+  htsmoduleStruct str;
+  htsmoduleStructExtended stre;
+  int ptr, error = 0, store_errpage = 0;
+  int makeindex_done = 0, makeindex_links = 0;
+  FILE *makeindex_fp = NULL;
+  char makeindex_firstlink[HTS_URLMAXSIZE * 2] = "";
+  LLint stat_fragment = 0, makestat_total = 0;
+  int makestat_lnk = 0;
+  char base[HTS_URLMAXSIZE * 2] = "";
+  char codebase[HTS_URLMAXSIZE * 2] = "";
+  char err_msg[1024] = "";
+
+  if (!inited) {
+    hts_init();
+    inited = 1;
+  }
+
+  opt = hts_create_opt();
+  opt->log = opt->errlog = NULL;
+  opt->robots = 0;
+
+  memset(&cache, 0, sizeof(cache));
+  cache.type = 0; /* no on-disk cache */
+  cache.hashtable = coucal_new(0);
+  cache.cached_tests = coucal_new(0);
+  coucal_value_is_malloc(cache.cached_tests, 1);
+
+  memset(&robots, 0, sizeof(robots));
+  strcpybuff(robots.adr, "!");
+  opt->robotsptr = &robots;
+
+  opt->maxfilter = maximum(opt->maxfilter, 128);
+  filters_init(&filters, opt->maxfilter, 0);
+  opt->filters.filters = &filters;
+  opt->filters.filptr = &filptr;
+
+  opt->hash = &hash;
+  hts_record_init(opt);
+  hash_init(opt, &hash, opt->urlhack);
+  hash.liens = (const lien_url *const *const *) &opt->liens;
+
+  sback = back_new(opt, opt->maxsoc * 32 + 1024);
+
+  /* ptr=1 (index 1 is the parsed page) selects full HTML parsing + the
+     rewriter; urladr()/urlfil()/savename() alias heap(ptr), save=/dev/null. */
+  hts_record_link(opt, "example.com", "/", "/dev/null", "", "", NULL);
+  hts_record_link(opt, "example.com", "/index.html", "/dev/null", "", "", NULL);
+  ptr = 1;
+
+  /* NUL-terminated in a size+1 alloc: htsparse one-past-reads onto the NUL. */
+  hts_init_htsblk(&r);
+  r.statuscode = 200;
+  r.size = (LLint) size;
+  r.adr = malloct(size + 1);
+  if (size)
+    memcpy(r.adr, data, size);
+  r.adr[size] = '\0';
+  strcpybuff(r.contenttype, "text/html");
+
+  memset(&str, 0, sizeof(str));
+  memset(&stre, 0, sizeof(stre));
+  str.err_msg = err_msg;
+  str.filename = heap(ptr)->sav;
+  str.mime = r.contenttype;
+  str.url_host = heap(ptr)->adr;
+  str.url_file = heap(ptr)->fil;
+  str.size = (int) r.size;
+  str.addLink = fuzz_addlink;
+  str.opt = opt;
+  str.sback = sback;
+  str.cache = &cache;
+  str.hashptr = &hash;
+  str.numero_passe = 0;
+  str.ptr_ = &ptr;
+  str.page_charset_ = NULL;
+
+  stre.r_ = &r;
+  stre.error_ = &error;
+  stre.exit_xh_ = &opt->state.exit_xh;
+  stre.store_errpage_ = &store_errpage;
+  stre.base = base;
+  stre.codebase = codebase;
+  stre.filters_ = &filters;
+  stre.filptr_ = &filptr;
+  stre.robots_ = &robots;
+  stre.hash_ = &hash;
+  stre.makeindex_done_ = &makeindex_done;
+  stre.makeindex_fp_ = &makeindex_fp;
+  stre.makeindex_links_ = &makeindex_links;
+  stre.makeindex_firstlink_ = makeindex_firstlink;
+  stre.template_header_ = "";
+  stre.template_body_ = "";
+  stre.template_footer_ = "";
+  stre.stat_fragment_ = &stat_fragment;
+  stre.makestat_time = 0;
+  stre.makestat_fp = NULL;
+  stre.makestat_total_ = &makestat_total;
+  stre.makestat_lnk_ = &makestat_lnk;
+  stre.maketrack_fp = NULL;
+
+  (void) htsparse(&str, &stre);
+
+  freet(r.adr);
+  back_delete_all(opt, &cache, sback);
+  back_free(&sback);
+  hash_free(&hash);
+  coucal_delete(&cache.hashtable);
+  coucal_delete(&cache.cached_tests);
+  checkrobots_free(&robots);
+  if (filters != NULL) {
+    if (filters[0] != NULL)
+      freet(filters[0]);
+    freet(filters);
+  }
+  hts_record_free(opt);
+  hts_free_opt(opt);
+  return 0;
+}

html/server/option10.html

@@ -98,6 +98,15 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
+${LANG_PROXYTYPE}
+<select name="proxytype"
+			onMouseOver="info('${html:LANG_PROXYTYPETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+<option value=""${ztest:proxytype: selected:}>HTTP</option>
+<option value="1"${test:proxytype:: selected}>SOCKS5</option>
+</select>
+<br><br>
+
 ${LANG_IOPT10}:
 <input name="prox" value="${prox}" size="32"
 			onMouseOver="info('${html:LANG_G14}'); return true" onMouseOut="info('&nbsp;'); return true"

html/server/option5.html

@@ -148,6 +148,14 @@ ${LANG_I65}
 >
 </td></tr>
 
+<tr><td>
+${LANG_PAUSEFILES}
+</td><td>
+<input name="pausefiles" value="${pausefiles}" size="8"
+			onMouseOver="info('${html:LANG_PAUSEFILESTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+</td></tr>
+
 <tr><td>
 ${LANG_I52}
 </td><td>

html/server/option8.html

@@ -103,6 +103,12 @@ ${do:end-if}
 > ${LANG_I58}
 <br><br>
 
+${LANG_COOKIEFILE}
+<input name="cookiesfile" value="${cookiesfile}" size="40"
+			onMouseOver="info('${html:LANG_COOKIEFILETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+<br><br>
+
 ${LANG_I59}
 <br>
 <select name="checktype"
@@ -136,6 +142,27 @@ ${listid:robots:LISTDEF_8}
 > ${LANG_I62b2}
 <br><br>
 
+<input type="checkbox" name="keepwww" ${checked:keepwww}
+			onMouseOver="info('${html:LANG_KEEPWWWTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+> ${LANG_KEEPWWW}
+<br><br>
+
+<input type="checkbox" name="keepslashes" ${checked:keepslashes}
+			onMouseOver="info('${html:LANG_KEEPSLASHESTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+> ${LANG_KEEPSLASHES}
+<br><br>
+
+<input type="checkbox" name="keepqueryorder" ${checked:keepqueryorder}
+			onMouseOver="info('${html:LANG_KEEPQUERYORDERTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+> ${LANG_KEEPQUERYORDER}
+<br><br>
+
+${LANG_STRIPQUERY}
+<input name="stripquery" value="${stripquery}" size="40"
+			onMouseOver="info('${html:LANG_STRIPQUERYTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+<br><br>
+
 <input type="checkbox" name="toler" ${checked:toler}
 			onMouseOver="info('${html:LANG_I1i}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I62}

html/server/step2.html

@@ -129,15 +129,21 @@ ${do:copy:NoPwdInPages:hidepwd}
 ${do:copy:NoQueryStrings:hidequery}
 ${do:copy:NoPurgeOldFiles:nopurge}
 ${do:copy:Cookies:cookies}
+${do:copy:CookiesFile:cookiesfile}
 ${do:copy:CheckType:checktype}
 ${do:copy:ParseJava:parsejava}
 ${do:copy:HTTP10:http10}
 ${do:copy:TolerantRequests:toler}
 ${do:copy:UpdateHack:updhack}
 ${do:copy:URLHack:urlhack}
+${do:copy:KeepWww:keepwww}
+${do:copy:KeepSlashes:keepslashes}
+${do:copy:KeepQueryOrder:keepqueryorder}
+${do:copy:StripQuery:stripquery}
 ${do:copy:StoreAllInCache:cache2}
 ${do:copy:LogType:logtype}
 ${do:copy:UseHTTPProxyForFTP:ftpprox}
+${do:copy:ProxyType:proxytype}
 ${do:copy:Build:build}
 ${do:copy:PrimaryScan:filter}
 ${do:copy:Travel:travel}
@@ -148,6 +154,7 @@ ${do:copy:MaxHtml:maxhtml}
 ${do:copy:MaxOther:othermax}
 ${do:copy:MaxAll:sizemax}
 ${do:copy:MaxWait:pausebytes}
+${do:copy:PauseFiles:pausefiles}
 ${do:copy:Sockets:connexion}
 ${do:copy:Retry:retry}
 ${do:copy:MaxTime:maxtime}

html/server/step4.html

@@ -178,6 +178,12 @@ ${do:end-if}
 	${test:parsejava:--parse-java=0:}
 	${test:updhack:--updatehack}
 	${test:urlhack:--urlhack=0:--urlhack}
+	${test:keepwww:--keep-www-prefix}
+	${test:keepslashes:--keep-double-slashes}
+	${test:keepqueryorder:--keep-query-order}
+	${test:cookiesfile:--cookies-file "}${html:cookiesfile}${test:cookiesfile:"}
+	${test:pausefiles:--pause "}${pausefiles}${test:pausefiles:"}
+	${test:stripquery:--strip-query "}${html:stripquery}${test:stripquery:"}
 	${test:toler:--tolerant}
 	${test:http10:--http-10}
 	${test:cache2:--store-all-in-cache}
@@ -186,7 +192,7 @@ ${do:end-if}
 	${test:logtype:::--extra-log:--debug-log}
 	${test:index:--index=0:}
 	${test:index2:--search-index=0:--search-index}
-	${test:prox:--proxy "}${prox}${test:prox:\3A}${portprox}${test:prox:"}
+	${test:prox:--proxy "}${do:if-not-empty:prox}${test:proxytype:socks5\3A//}${do:end-if}${do:output-mode:html}${prox}${test:prox:\3A}${portprox}${test:prox:"}
 	${test:ftpprox:--httpproxy-ftp=0:--httpproxy-ftp}
 </textarea>
 
@@ -219,15 +225,21 @@ NoPwdInPages=${ztest:hidepwd:0:1}
 NoQueryStrings=${ztest:hidequery:0:1}
 NoPurgeOldFiles=${ztest:nopurge:0:1}
 Cookies=${ztest:cookies:0:1}
+CookiesFile=${cookiesfile}
 CheckType=${ztest:checktype:0:1:2}
 ParseJava=${ztest:parsejava:0:1}
 HTTP10=${ztest:http10:0:1}
 TolerantRequests=${ztest:toler:0:1}
 UpdateHack=${ztest:updhack:0:1}
 URLHack=${ztest:urlhack:0:1}
+KeepWww=${ztest:keepwww:0:1}
+KeepSlashes=${ztest:keepslashes:0:1}
+KeepQueryOrder=${ztest:keepqueryorder:0:1}
+StripQuery=${stripquery}
 StoreAllInCache=${ztest:cache2:0:1}
 LogType=${logtype}
 UseHTTPProxyForFTP=${ztest:ftpprox:0:1}
+ProxyType=${proxytype}
 Build=${build}
 PrimaryScan=${filter}
 Travel=${travel}
@@ -238,6 +250,7 @@ MaxHtml=${maxhtml}
 MaxOther=${othermax}
 MaxAll=${sizemax}
 MaxWait=${pausebytes}
+PauseFiles=${pausefiles}
 Sockets=${connexion}
 Retry=${retry}
 MaxTime=${maxtime}

lang.def

@@ -1006,3 +1006,31 @@ LANG_SERVEND
 Server terminated
 LANG_FATALERR
 A fatal error has occurred during this mirror
+LANG_PROXYTYPE
+Proxy type:
+LANG_PROXYTYPETIP
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+LANG_COOKIEFILE
+Load cookies from file:
+LANG_COOKIEFILETIP
+Preload cookies from a Netscape cookies.txt file before crawling.
+LANG_PAUSEFILES
+Pause between files:
+LANG_PAUSEFILESTIP
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+LANG_KEEPWWW
+Keep the www. prefix (do not merge www.host with host)
+LANG_KEEPWWWTIP
+Do not treat www.host and host as the same site.
+LANG_KEEPSLASHES
+Keep double slashes in URLs
+LANG_KEEPSLASHESTIP
+Do not collapse duplicate slashes in URLs.
+LANG_KEEPQUERYORDER
+Keep the original query-string order
+LANG_KEEPQUERYORDERTIP
+Do not reorder query-string parameters when deduplicating URLs.
+LANG_STRIPQUERY
+Strip query keys:
+LANG_STRIPQUERYTIP
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).

lang/Bulgarian.txt

@@ -928,3 +928,31 @@ Server terminated
 Ñúðâúðúò íå îòãîâàðÿ
 A fatal error has occurred during this mirror
 Ôàòàëíà ãðåøêà ïðè ñúçäàâàíåòî íà òîçè îãëåäàëåí ñàéò
+Proxy type:
+Òèï íà ïðîêñè:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Ïðîòîêîë íà ïðîêñè: HTTP èëè SOCKS5 (ñòàíäàðòíèÿò ïîðò íà SOCKS5 å 1080).
+Load cookies from file:
+Çàðåæäàíå íà 'áèñêâèòêè' îò ôàéë:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Ïðåäâàðèòåëíî çàðåæäàíå íà 'áèñêâèòêè' îò ôàéë Netscape cookies.txt ïðåäè îáõîæäàíåòî.
+Pause between files:
+Ïàóçà ìåæäó ôàéëîâåòå:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Ñëó÷àéíî çàáàâÿíå ìåæäó èçòåãëÿíèÿòà íà ôàéëîâå, â ñåêóíäè. Èçïîëçâàéòå MIN:MAX çà ñëó÷àåí äèàïàçîí (íàïðèìåð 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Çàïàçâàíå íà ïðåôèêñà www. (áåç ñëèâàíå íà www.host ñ host)
+Do not treat www.host and host as the same site.
+www.host è host äà íå ñå òðåòèðàò êàòî åäèí è ñúù ñàéò.
+Keep double slashes in URLs
+Çàïàçâàíå íà äâîéíèòå íàêëîíåíè ÷åðòè â URL
+Do not collapse duplicate slashes in URLs.
+Áåç ïðåìàõâàíå íà ïîâòàðÿùèòå ñå íàêëîíåíè ÷åðòè â URL.
+Keep the original query-string order
+Çàïàçâàíå íà îðèãèíàëíèÿ ðåä íà ïàðàìåòðèòå â çàÿâêàòà
+Do not reorder query-string parameters when deduplicating URLs.
+Áåç ïðåíàðåæäàíå íà ïàðàìåòðèòå íà çàÿâêàòà ïðè ïðåìàõâàíå íà äóáëèðàíè URL.
+Strip query keys:
+Ïðåìàõâàíå íà êëþ÷îâå îò çàÿâêàòà:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Êëþ÷îâå îò çàÿâêàòà, ðàçäåëåíè ñúñ çàïåòàÿ, êîèòî äà ñå ïðåìàõíàò îò èìåòî íà çàïèñàíèÿ ôàéë (íàïðèìåð sid,utm_source).

lang/Castellano.txt

@@ -928,3 +928,31 @@ Server terminated
 Servidor desconectado
 A fatal error has occurred during this mirror
 Ha ocurrido un error fatal durante esta copia
+Proxy type:
+Tipo de proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocolo del proxy: HTTP o SOCKS5 (el puerto SOCKS5 predeterminado es 1080).
+Load cookies from file:
+Cargar cookies desde un archivo:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Precargar cookies desde un archivo Netscape cookies.txt antes de comenzar la descarga.
+Pause between files:
+Pausa entre archivos:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Retardo aleatorio entre descargas de archivos, en segundos. Use MIN:MAX para un rango aleatorio (p. ej. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Mantener el prefijo www. (no combinar www.host con host)
+Do not treat www.host and host as the same site.
+No tratar www.host y host como el mismo sitio.
+Keep double slashes in URLs
+Mantener las barras dobles en las URL
+Do not collapse duplicate slashes in URLs.
+No colapsar las barras duplicadas en las URL.
+Keep the original query-string order
+Mantener el orden original de la query string
+Do not reorder query-string parameters when deduplicating URLs.
+No reordenar los parámetros de la query string al deduplicar las URL.
+Strip query keys:
+Eliminar claves de query string:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Claves de query string, separadas por comas, que se eliminarán del nombre de los archivos guardados (p. ej. sid,utm_source).

lang/Cesky.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Typ proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protokol proxy: HTTP nebo SOCKS5 (výchozí port SOCKS5 je 1080).
+Load cookies from file:
+Naèíst cookies ze souboru:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Naèíst cookies ze souboru Netscape cookies.txt pøed zahájením stahování.
+Pause between files:
+Prodleva mezi soubory:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Náhodná prodleva mezi stahováním souborù, v sekundách. Pro náhodný rozsah použijte MIN:MAX (napø. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Zachovat pøedponu www. (nesluèovat www.host s host)
+Do not treat www.host and host as the same site.
+Nepovažovat www.host a host za stejný web.
+Keep double slashes in URLs
+Zachovat dvojitá lomítka v URL
+Do not collapse duplicate slashes in URLs.
+Nesluèovat opakovaná lomítka v URL.
+Keep the original query-string order
+Zachovat pùvodní poøadí øetìzce dotazu
+Do not reorder query-string parameters when deduplicating URLs.
+Nemìnit poøadí parametrù øetìzce dotazu pøi odstraòování duplicitních URL.
+Strip query keys:
+Odebrat klíèe dotazu:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Klíèe dotazu oddìlené èárkami, které se vynechají z pojmenování ukládaných souborù (napø. sid,utm_source).

lang/Chinese-BIG5.txt

@@ -928,3 +928,31 @@ Server terminated
 伺服器已終止
 A fatal error has occurred during this mirror
 這鏡像發生了不可回復的錯誤
+Proxy type:
+proxy 類型:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+proxy 協定: HTTP 或 SOCKS5 (SOCKS5 的預設連接埠為 1080)。
+Load cookies from file:
+從檔案載入 cookies:
+Preload cookies from a Netscape cookies.txt file before crawling.
+在抓取前從 Netscape 格式的 cookies.txt 檔案預先載入 cookies。
+Pause between files:
+檔案之間暫停:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+檔案下載之間的隨機延遲（秒）。使用 MIN:MAX 指定隨機範圍 (例如 2:8)。
+Keep the www. prefix (do not merge www.host with host)
+保留 www. 前綴 (不將 www.host 與 host 合併)
+Do not treat www.host and host as the same site.
+不將 www.host 與 host 視為同一站點。
+Keep double slashes in URLs
+保留 URL 中的雙斜線
+Do not collapse duplicate slashes in URLs.
+不合併 URL 中重複的斜線。
+Keep the original query-string order
+保留查詢字串的原始順序
+Do not reorder query-string parameters when deduplicating URLs.
+在對 URL 去重時不重新排列查詢字串參數。
+Strip query keys:
+移除查詢鍵:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+以逗號分隔的查詢鍵，將其從儲存檔案的命名中移除 (例如 sid,utm_source)。

lang/Chinese-Simplified.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+代理类型:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+代理协议: HTTP 或 SOCKS5 (SOCKS5 的默认端口为 1080)。
+Load cookies from file:
+从文件加载 cookies:
+Preload cookies from a Netscape cookies.txt file before crawling.
+在抓取前从 Netscape 格式的 cookies.txt 文件预加载 cookies。
+Pause between files:
+文件间暂停:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+文件下载之间的随机延迟（秒）。使用 MIN:MAX 指定随机范围 (例如 2:8)。
+Keep the www. prefix (do not merge www.host with host)
+保留 www. 前缀 (不将 www.host 与 host 合并)
+Do not treat www.host and host as the same site.
+不把 www.host 和 host 视为同一站点。
+Keep double slashes in URLs
+保留 URL 中的双斜杠
+Do not collapse duplicate slashes in URLs.
+不合并 URL 中重复的斜杠。
+Keep the original query-string order
+保留查询字符串的原始顺序
+Do not reorder query-string parameters when deduplicating URLs.
+在对 URL 去重时不重新排列查询字符串参数。
+Strip query keys:
+剥离查询键:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+用逗号分隔的查询键，将其从保存文件的命名中删除 (例如 sid,utm_source)。

lang/Croatian.txt

@@ -930,3 +930,31 @@ Server terminated
 Poslužitelj je razriješen
 A fatal error has occurred during this mirror
 Tijekom ovog zrcaljenja je nastala fatalna pogreška
+Proxy type:
+Vrsta posrednika:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protokol posrednika: HTTP ili SOCKS5 (zadani port za SOCKS5 je 1080).
+Load cookies from file:
+Uèitati kolaèiæe iz datoteke:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Prije zrcaljenja uèitati kolaèiæe iz datoteke Netscape cookies.txt.
+Pause between files:
+Stanka izmeðu datoteka:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Nasumièna odgoda izmeðu preuzimanja datoteka, u sekundama. Za nasumièni raspon koristiti MIN:MAX (npr. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Zadr¾ati www. predmetak (ne spajati www.host s host)
+Do not treat www.host and host as the same site.
+www.host i host ne smatrati istim web-mjestom.
+Keep double slashes in URLs
+Zadr¾ati dvostruke kose crte u URL-ovima
+Do not collapse duplicate slashes in URLs.
+Ne sa¾imati ponovljene kose crte u URL-ovima.
+Keep the original query-string order
+Zadr¾ati izvorni redoslijed teksta za upite
+Do not reorder query-string parameters when deduplicating URLs.
+Ne mijenjati redoslijed parametara teksta za upite pri uklanjanju dvostrukih URL-ova.
+Strip query keys:
+Ukloniti kljuèeve upita:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Zarezom odvojeni kljuèevi upita koji se izostavljaju iz naziva spremljenih datoteka (npr. sid,utm_source).

lang/Dansk.txt

@@ -976,3 +976,31 @@ Click on this notification to restart the interrupted mirror
 Klik på denne notifikation for at genstarte den afbrudte spejlkopiering
 HTTrack: could not save profile for '%s'!
 HTTrack: kunne ikke gemme profil for '%s'!
+Proxy type:
+Proxytype:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxyprotokol: HTTP eller SOCKS5 (SOCKS5 bruger som standard port 1080).
+Load cookies from file:
+Indlæs cookies fra fil:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Indlæs cookies fra en Netscape cookies.txt-fil, før crawlingen starter.
+Pause between files:
+Pause mellem filer:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Tilfældig forsinkelse mellem filoverførsler, i sekunder. Brug MIN:MAX for et tilfældigt interval (f.eks. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Behold www.-præfikset (sammenlæg ikke www.host med host)
+Do not treat www.host and host as the same site.
+Behandl ikke www.host og host som det samme websted.
+Keep double slashes in URLs
+Behold dobbelte skråstreger i URL'er
+Do not collapse duplicate slashes in URLs.
+Sammenfold ikke gentagne skråstreger i URL'er.
+Keep the original query-string order
+Behold den oprindelige rækkefølge i forespørgselsstrengen
+Do not reorder query-string parameters when deduplicating URLs.
+Omorden ikke forespørgselsstrengens parametre, når dublerede URL'er fjernes.
+Strip query keys:
+Fjern forespørgselsnøgler:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kommaseparerede forespørgselsnøgler, der udelades i navngivningen af gemte filer (f.eks. sid,utm_source).

lang/Deutsch.txt

@@ -928,3 +928,31 @@ Server terminated
 Der Server wurde beendet
 A fatal error has occurred during this mirror
 Fataler Fehler während der Webseiten-Kopie
+Proxy type:
+Proxy-Typ:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxy-Protokoll: HTTP oder SOCKS5 (Standardport von SOCKS5 ist 1080).
+Load cookies from file:
+Cookies aus Datei laden:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Cookies aus einer Netscape-cookies.txt-Datei laden, bevor das Crawlen beginnt.
+Pause between files:
+Pause zwischen Dateien:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Zufällige Verzögerung zwischen Datei-Downloads, in Sekunden. MIN:MAX für einen Zufallsbereich verwenden (z. B. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+www.-Präfix beibehalten (www.host nicht mit host zusammenführen)
+Do not treat www.host and host as the same site.
+www.host und host nicht als dieselbe Website behandeln.
+Keep double slashes in URLs
+Doppelte Schrägstriche in URLs beibehalten
+Do not collapse duplicate slashes in URLs.
+Doppelte Schrägstriche in URLs nicht zusammenführen.
+Keep the original query-string order
+Ursprüngliche Reihenfolge des Query-Strings beibehalten
+Do not reorder query-string parameters when deduplicating URLs.
+Query-String-Parameter beim Entfernen doppelter URLs nicht neu anordnen.
+Strip query keys:
+Query-Schlüssel entfernen:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kommagetrennte Query-Schlüssel, die bei der Benennung gespeicherter Dateien entfallen (z. B. sid,utm_source).

lang/Eesti.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Proxy tüüp:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxy protokoll: HTTP või SOCKS5 (SOCKS5 vaikeport on 1080).
+Load cookies from file:
+Lae küpsised failist:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Lae küpsised eelnevalt Netscape cookies.txt failist enne kopeerimist.
+Pause between files:
+Paus failide vahel:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Juhuslik viivitus failide allalaadimiste vahel, sekundites. Juhusliku vahemiku jaoks kasuta MIN:MAX (nt 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Säilita www. eesliide (ära ühenda www.host ja host)
+Do not treat www.host and host as the same site.
+Ära käsitle www.host ja host sama saidina.
+Keep double slashes in URLs
+Säilita topeltkaldkriipsud URL-ides
+Do not collapse duplicate slashes in URLs.
+Ära ühenda korduvaid kaldkriipse URL-ides.
+Keep the original query-string order
+Säilita päringustringi algne järjekord
+Do not reorder query-string parameters when deduplicating URLs.
+Ära järjesta päringustringi parameetreid ümber URL-ide korduste eemaldamisel.
+Strip query keys:
+Eemalda päringuvõtmed:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Komadega eraldatud päringuvõtmed, mis jäetakse salvestatud faili nimest välja (nt sid,utm_source).

lang/English.txt

@@ -976,3 +976,31 @@ Click on this notification to restart the interrupted mirror
 Click on this notification to restart the interrupted mirror
 HTTrack: could not save profile for '%s'!
 HTTrack: could not save profile for '%s'!
+Proxy type:
+Proxy type:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Load cookies from file:
+Load cookies from file:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Preload cookies from a Netscape cookies.txt file before crawling.
+Pause between files:
+Pause between files:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Keep the www. prefix (do not merge www.host with host)
+Do not treat www.host and host as the same site.
+Do not treat www.host and host as the same site.
+Keep double slashes in URLs
+Keep double slashes in URLs
+Do not collapse duplicate slashes in URLs.
+Do not collapse duplicate slashes in URLs.
+Keep the original query-string order
+Keep the original query-string order
+Do not reorder query-string parameters when deduplicating URLs.
+Do not reorder query-string parameters when deduplicating URLs.
+Strip query keys:
+Strip query keys:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).

lang/Finnish.txt

@@ -931,3 +931,31 @@ Palvelin lopetettu
 A fatal error has occurred during this mirror
 Tällä peilillä tapahtui vakava virhe
 
+Proxy type:
+Välityspalvelimen tyyppi:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Välityspalvelimen protokolla: HTTP tai SOCKS5 (SOCKS5:n oletusportti on 1080).
+Load cookies from file:
+Lataa evästeet tiedostosta:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Lataa evästeet Netscape cookies.txt -tiedostosta ennen sivuston läpikäyntiä.
+Pause between files:
+Tauko tiedostojen välillä:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Satunnainen viive tiedostolatausten välillä, sekunteina. Käytä muotoa MIN:MAX satunnaista väliä varten (esim. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Säilytä www.-etuliite (älä yhdistä www.host- ja host-osoitteita)
+Do not treat www.host and host as the same site.
+Älä käsittele www.host- ja host-osoitteita samana sivustona.
+Keep double slashes in URLs
+Säilytä kaksoiskenoviivat URL-osoitteissa
+Do not collapse duplicate slashes in URLs.
+Älä yhdistä toistuvia kenoviivoja URL-osoitteissa.
+Keep the original query-string order
+Säilytä kyselymerkkijonon alkuperäinen järjestys
+Do not reorder query-string parameters when deduplicating URLs.
+Älä järjestä kyselymerkkijonon parametreja uudelleen, kun URL-osoitteiden kaksoiskappaleet poistetaan.
+Strip query keys:
+Poista kyselyavaimet:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Pilkuin erotellut kyselyavaimet, jotka jätetään pois tallennettujen tiedostojen nimeämisestä (esim. sid,utm_source).

lang/Francais.txt

@@ -976,3 +976,31 @@ Build a mail archive
 Construire une archive mail
 Default referer URL
 Champ referer par défaut
+Proxy type:
+Type de proxy :
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocole du proxy : HTTP ou SOCKS5 (le port SOCKS5 par défaut est 1080).
+Load cookies from file:
+Charger les cookies depuis un fichier :
+Preload cookies from a Netscape cookies.txt file before crawling.
+Précharger les cookies depuis un fichier Netscape cookies.txt avant la copie du site.
+Pause between files:
+Pause entre les fichiers :
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Délai aléatoire entre les téléchargements de fichiers, en secondes. Utilisez MIN:MAX pour une plage aléatoire (par ex. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Conserver le préfixe www. (ne pas fusionner www.host avec host)
+Do not treat www.host and host as the same site.
+Ne pas traiter www.host et host comme le même site.
+Keep double slashes in URLs
+Conserver les doubles barres obliques dans les URL
+Do not collapse duplicate slashes in URLs.
+Ne pas réduire les barres obliques en double dans les URL.
+Keep the original query-string order
+Conserver l'ordre d'origine de la query string
+Do not reorder query-string parameters when deduplicating URLs.
+Ne pas réordonner les paramètres de la query string lors de la déduplication des URL.
+Strip query keys:
+Supprimer les clés de query string :
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Clés de query string à retirer du nommage des fichiers enregistrés, séparées par des virgules (par ex. sid,utm_source).

lang/Greek.txt

@@ -930,3 +930,31 @@ Server terminated
 Ακυρώθηκε από τον εξυπηρετητή
 A fatal error has occurred during this mirror
 Ένα καταστροφικό σφάλμα προκλήθηκε κατά την αντιγραφή αυτού του τόπου
+Proxy type:
+Τύπος proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Πρωτόκολλο proxy: HTTP ή SOCKS5 (η προεπιλεγμένη θύρα του SOCKS5 είναι 1080).
+Load cookies from file:
+Φόρτωση cookies από αρχείο:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Προφόρτωση των cookies από ένα αρχείο Netscape cookies.txt πριν την ανίχνευση.
+Pause between files:
+Παύση μεταξύ αρχείων:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Τυχαία καθυστέρηση μεταξύ των λήψεων αρχείων, σε δευτερόλεπτα. Χρησιμοποιήστε MIN:MAX για τυχαίο εύρος (π.χ. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Διατήρηση του προθέματος www. (χωρίς συγχώνευση του www.host με το host)
+Do not treat www.host and host as the same site.
+Να μην θεωρούνται τα www.host και host ως ο ίδιος ιστότοπος.
+Keep double slashes in URLs
+Διατήρηση των διπλών καθέτων στα URL
+Do not collapse duplicate slashes in URLs.
+Να μην συμπτύσσονται οι διπλές κάθετοι στα URL.
+Keep the original query-string order
+Διατήρηση της αρχικής σειράς του ερωτήματος αναζήτησης
+Do not reorder query-string parameters when deduplicating URLs.
+Να μην αναδιατάσσονται οι παράμετροι του ερωτήματος αναζήτησης κατά την αφαίρεση διπλότυπων URL.
+Strip query keys:
+Αφαίρεση κλειδιών ερωτήματος:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Κλειδιά ερωτήματος χωρισμένα με κόμμα, που θα αφαιρεθούν από την ονομασία των αποθηκευμένων αρχείων (π.χ. sid,utm_source).

lang/Italiano.txt

@@ -928,3 +928,31 @@ Server terminated
 Server disconnesso
 A fatal error has occurred during this mirror
 Si è verificato un errore fatale durante la copia
+Proxy type:
+Tipo di proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocollo del proxy: HTTP o SOCKS5 (la porta SOCKS5 predefinita è 1080).
+Load cookies from file:
+Carica i cookie da un file:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Precarica i cookie da un file Netscape cookies.txt prima della copia.
+Pause between files:
+Pausa tra i file:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Ritardo casuale tra i download dei file, in secondi. Usa MIN:MAX per un intervallo casuale (ad es. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Mantieni il prefisso www. (non unire www.host con host)
+Do not treat www.host and host as the same site.
+Non trattare www.host e host come lo stesso sito.
+Keep double slashes in URLs
+Mantieni le doppie barre negli URL
+Do not collapse duplicate slashes in URLs.
+Non ridurre le barre duplicate negli URL.
+Keep the original query-string order
+Mantieni l'ordine originale della query string
+Do not reorder query-string parameters when deduplicating URLs.
+Non riordinare i parametri della query string durante la deduplicazione degli URL.
+Strip query keys:
+Rimuovi chiavi della query string:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Chiavi della query string, separate da virgole, da rimuovere dai nomi dei file salvati (ad es. sid,utm_source).

lang/Japanese.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+プロキシの種類:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+プロキシのプロトコル: HTTP または SOCKS5 (SOCKS5 の既定ポートは 1080)。
+Load cookies from file:
+クッキーをファイルから読み込む:
+Preload cookies from a Netscape cookies.txt file before crawling.
+クロールを開始する前に Netscape の cookies.txt ファイルからクッキーを読み込みます。
+Pause between files:
+ファイル間の待機:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+ファイルのダウンロード間のランダムな遅延（秒）。範囲を指定するには MIN:MAX を使用します (例: 2:8)。
+Keep the www. prefix (do not merge www.host with host)
+www. プレフィックスを保持する (www.host と host を統合しない)
+Do not treat www.host and host as the same site.
+www.host と host を同じサイトとして扱いません。
+Keep double slashes in URLs
+URL 内の二重スラッシュを保持する
+Do not collapse duplicate slashes in URLs.
+URL 内の連続したスラッシュをまとめません。
+Keep the original query-string order
+クエリ文字列の元の順序を保持する
+Do not reorder query-string parameters when deduplicating URLs.
+URL の重複排除時にクエリ文字列のパラメータを並べ替えません。
+Strip query keys:
+削除するクエリキー:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+保存ファイル名の生成から除外するクエリキーをカンマ区切りで指定します (例: sid,utm_source)。

lang/Macedonian.txt

@@ -928,3 +928,31 @@ Server terminated
 Ñåðâåðîò å ïðåêèíàò
 A fatal error has occurred during this mirror
 Íàñòàíà ôàòàëíà ãðåøêà ïðè îâî¼ mirror
+Proxy type:
+ÂØß ÝÐ ßàÞÚáØ:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+¿àÞâÞÚÞÛ ÝÐ ßàÞÚáØ: HTTP ØÛØ SOCKS5 (áâÐÝÔÐàÔÝÐâÐ ßÞàâÐ ÝÐ SOCKS5 Õ 1080).
+Load cookies from file:
+²çØâÐø ÚÞÛÐçØúÐ ÞÔ ÔÐâÞâÕÚÐ:
+Preload cookies from a Netscape cookies.txt file before crawling.
+¾ÔÝÐßàÕÔ ÒçØâÐø ÚÞÛÐçØúÐ ÞÔ ÔÐâÞâÕÚÐ Netscape cookies.txt ßàÕÔ ßàÕ×ÕÜÐúÕâÞ.
+Pause between files:
+¿Ðã×Ð ÜÕóã ÔÐâÞâÕÚØ:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+ÁÛãçÐøÝÞ ÔÞæÝÕúÕ ÜÕóã ßàÕ×ÕÜÐúÐâÐ ÝÐ ÔÐâÞâÕÚØ, ÒÞ áÕÚãÝÔØ. ºÞàØáâØ MIN:MAX ×Ð áÛãçÐÕÝ ÞßáÕÓ (ÝÐ ßàØÜÕà 2:8).
+Keep the www. prefix (do not merge www.host with host)
+·ÐÔàÖØ ÓÞ ßàÕäØÚáÞâ www. (ÝÕ áßÞøãÒÐø www.host áÞ host)
+Do not treat www.host and host as the same site.
+½Õ âàÕâØàÐø ÓØ www.host Ø host ÚÐÚÞ Øáâ áÐøâ.
+Keep double slashes in URLs
+·ÐÔàÖØ ÓØ ÔÒÞøÝØâÕ ÚÞáØ æàâØ ÒÞ URL
+Do not collapse duplicate slashes in URLs.
+½Õ ÞâáâàÐÝãÒÐø ÓØ ßÞÒâÞàÕÝØâÕ ÚÞáØ æàâØ ÒÞ URL.
+Keep the original query-string order
+·ÐÔàÖØ ÓÞ Ø×ÒÞàÝØÞâ àÕÔÞáÛÕÔ ÝÐ ßÐàÐÜÕâàØâÕ ÒÞ ÑÐàÐúÕâÞ
+Do not reorder query-string parameters when deduplicating URLs.
+½Õ ÜÕÝãÒÐø ÓÞ àÕÔÞáÛÕÔÞâ ÝÐ ßÐàÐÜÕâàØâÕ ÝÐ ÑÐàÐúÕâÞ ßàØ ÞâáâàÐÝãÒÐúÕ ÔãßÛØÚÐâØ URL.
+Strip query keys:
+¾âáâàÐÝØ ÚÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+ºÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ, ÞÔÔÕÛÕÝØ áÞ ×ÐßØàÚÐ, èâÞ áÕ ÞâáâàÐÝãÒÐÐâ ÞÔ ØÜÕâÞ ÝÐ ×ÐçãÒÐÝÐâÐ ÔÐâÞâÕÚÐ (ÝÐ ßàØÜÕà sid,utm_source).

lang/Magyar.txt

@@ -928,3 +928,31 @@ Server terminated
 A kiszolgáló befejezte a kapcsolatot
 A fatal error has occurred during this mirror
 Végzetes hiba történt a tükrözés közben
+Proxy type:
+Proxy típusa:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxy protokoll: HTTP vagy SOCKS5 (a SOCKS5 alapértelmezett portja 1080).
+Load cookies from file:
+Sütik betöltése fájlból:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Sütik elõzetes betöltése egy Netscape cookies.txt fájlból a tükrözés elõtt.
+Pause between files:
+Szünet a fájlok között:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Véletlenszerû késleltetés a fájlletöltések között, másodpercben. Véletlen tartományhoz használja a MIN:MAX formát (pl. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+A www. elõtag megtartása (ne vonja össze a www.host és a host címet)
+Do not treat www.host and host as the same site.
+Ne kezelje a www.host és a host címet ugyanazon webhelyként.
+Keep double slashes in URLs
+Dupla perjelek megtartása az URL-ekben
+Do not collapse duplicate slashes in URLs.
+Ne vonja össze az ismétlõdõ perjeleket az URL-ekben.
+Keep the original query-string order
+Az eredeti lekérdezési szöveg sorrendjének megtartása
+Do not reorder query-string parameters when deduplicating URLs.
+Ne rendezze át a lekérdezési szöveg paramétereit az ismétlõdõ URL-ek kiszûrésekor.
+Strip query keys:
+Lekérdezési kulcsok eltávolítása:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Vesszõvel elválasztott lekérdezési kulcsok, amelyeket el kell hagyni a mentett fájl elnevezésébõl (pl. sid,utm_source).

lang/Nederlands.txt

@@ -928,3 +928,31 @@ Server terminated
 Server beeindigd
 A fatal error has occurred during this mirror
 Een fatale fout is opgetreden tijdens deze spiegeling
+Proxy type:
+Proxytype:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxyprotocol: HTTP of SOCKS5 (standaardpoort van SOCKS5 is 1080).
+Load cookies from file:
+Cookies uit bestand laden:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Cookies vooraf laden uit een Netscape cookies.txt-bestand voordat het crawlen begint.
+Pause between files:
+Pauze tussen bestanden:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Willekeurige vertraging tussen bestandsdownloads, in seconden. Gebruik MIN:MAX voor een willekeurig bereik (bijv. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+www.-voorvoegsel behouden (www.host niet samenvoegen met host)
+Do not treat www.host and host as the same site.
+Behandel www.host en host niet als dezelfde site.
+Keep double slashes in URLs
+Dubbele schuine strepen in URL's behouden
+Do not collapse duplicate slashes in URLs.
+Dubbele schuine strepen in URL's niet samenvoegen.
+Keep the original query-string order
+Oorspronkelijke volgorde van de query string behouden
+Do not reorder query-string parameters when deduplicating URLs.
+Query string-parameters niet herordenen bij het ontdubbelen van URL's.
+Strip query keys:
+Query-sleutels verwijderen:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Door komma's gescheiden query-sleutels die bij het benoemen van opgeslagen bestanden worden weggelaten (bijv. sid,utm_source).

lang/Norsk.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Proxytype:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxyprotokoll: HTTP eller SOCKS5 (SOCKS5 bruker som standard port 1080).
+Load cookies from file:
+Last inn cookies fra fil:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Last inn cookies fra en Netscape cookies.txt-fil før crawlingen starter.
+Pause between files:
+Pause mellom filer:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Tilfeldig forsinkelse mellom filnedlastinger, i sekunder. Bruk MIN:MAX for et tilfeldig intervall (f.eks. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Behold www.-prefikset (slå ikke sammen www.host med host)
+Do not treat www.host and host as the same site.
+Behandle ikke www.host og host som samme nettsted.
+Keep double slashes in URLs
+Behold doble skråstreker i URL-er
+Do not collapse duplicate slashes in URLs.
+Slå ikke sammen gjentatte skråstreker i URL-er.
+Keep the original query-string order
+Behold den opprinnelige rekkefølgen i spørrestrengen
+Do not reorder query-string parameters when deduplicating URLs.
+Endre ikke rekkefølgen på spørrestrengens parametere når dupliserte URL-er fjernes.
+Strip query keys:
+Fjern spørrenøkler:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kommaseparerte spørrenøkler som utelates i navngivingen av lagrede filer (f.eks. sid,utm_source).

lang/Polski.txt

@@ -928,3 +928,31 @@ Server terminated
 Serwer zakonczyl prace
 A fatal error has occurred during this mirror
 Podczas tworzenia lustra wydarzyl sie fatalny blad.
+Proxy type:
+Typ proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protokó³ proxy: HTTP lub SOCKS5 (domy¶lny port SOCKS5 to 1080).
+Load cookies from file:
+Wczytaj ciasteczka z pliku:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Wczytaj ciasteczka z pliku Netscape cookies.txt przed rozpoczêciem pobierania.
+Pause between files:
+Pauza miêdzy plikami:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Losowe opó¼nienie miêdzy pobieraniem plików, w sekundach. U¿yj MIN:MAX dla losowego zakresu (np. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Zachowaj przedrostek www. (nie ³±cz www.host z host)
+Do not treat www.host and host as the same site.
+Nie traktuj www.host i host jako tej samej witryny.
+Keep double slashes in URLs
+Zachowaj podwójne uko¶niki w adresach URL
+Do not collapse duplicate slashes in URLs.
+Nie scalaj powtórzonych uko¶ników w adresach URL.
+Keep the original query-string order
+Zachowaj oryginaln± kolejno¶æ ci±gu zapytania
+Do not reorder query-string parameters when deduplicating URLs.
+Nie zmieniaj kolejno¶ci parametrów zapytania podczas usuwania duplikatów adresów URL.
+Strip query keys:
+Usuñ klucze zapytania:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Rozdzielone przecinkami klucze zapytania pomijane przy nazywaniu zapisanych plików (np. sid,utm_source).

lang/Portugues-Brasil.txt

@@ -976,3 +976,31 @@ Click on this notification to restart the interrupted mirror
 Clique nesta notificação para reiniciar o espelho interrompido
 HTTrack: could not save profile for '%s'!
 HTTrack: não foi possível salvar o perfil para '%s'!
+Proxy type:
+Tipo de proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocolo do proxy: HTTP ou SOCKS5 (a porta SOCKS5 padrão é 1080).
+Load cookies from file:
+Carregar cookies de um arquivo:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Pré-carregar cookies de um arquivo Netscape cookies.txt antes de iniciar a cópia.
+Pause between files:
+Pausa entre arquivos:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Atraso aleatório entre downloads de arquivos, em segundos. Use MIN:MAX para um intervalo aleatório (ex.: 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Manter o prefixo www. (não mesclar www.host com host)
+Do not treat www.host and host as the same site.
+Não tratar www.host e host como o mesmo site.
+Keep double slashes in URLs
+Manter as barras duplas nas URLs
+Do not collapse duplicate slashes in URLs.
+Não reduzir as barras duplicadas nas URLs.
+Keep the original query-string order
+Manter a ordem original da query string
+Do not reorder query-string parameters when deduplicating URLs.
+Não reordenar os parâmetros da query string ao remover URLs duplicadas.
+Strip query keys:
+Remover chaves da query string:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Chaves da query string, separadas por vírgulas, a serem removidas da nomeação dos arquivos salvos (ex.: sid,utm_source).

lang/Portugues.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Tipo de proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocolo do proxy: HTTP ou SOCKS5 (a porta SOCKS5 predefinida é 1080).
+Load cookies from file:
+Carregar cookies de um ficheiro:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Pré-carregar cookies de um ficheiro Netscape cookies.txt antes de iniciar a cópia.
+Pause between files:
+Pausa entre ficheiros:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Atraso aleatório entre transferências de ficheiros, em segundos. Utilize MIN:MAX para um intervalo aleatório (por ex. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Manter o prefixo www. (não combinar www.host com host)
+Do not treat www.host and host as the same site.
+Não tratar www.host e host como o mesmo site.
+Keep double slashes in URLs
+Manter as barras duplas nos URL
+Do not collapse duplicate slashes in URLs.
+Não reduzir as barras duplicadas nos URL.
+Keep the original query-string order
+Manter a ordem original da query string
+Do not reorder query-string parameters when deduplicating URLs.
+Não reordenar os parâmetros da query string ao eliminar URL duplicados.
+Strip query keys:
+Remover chaves da query string:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Chaves da query string, separadas por vírgulas, a remover da nomeação dos ficheiros guardados (por ex. sid,utm_source).

lang/Romanian.txt

@@ -928,3 +928,31 @@ Server terminated
 Server terminat
 A fatal error has occurred during this mirror
 A survenit o eroare fatală în timpul acestei clonări.
+Proxy type:
+Tip proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protocol proxy: HTTP sau SOCKS5 (portul SOCKS5 implicit este 1080).
+Load cookies from file:
+Încarca cookies dintr-un fisier:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Preîncarca cookies dintr-un fisier Netscape cookies.txt înainte de copiere.
+Pause between files:
+Pauza între fisiere:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Întârziere aleatoare între descarcari de fisiere, în secunde. Folositi MIN:MAX pentru un interval aleatoriu (de ex. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Pastreaza prefixul www. (nu combina www.host cu host)
+Do not treat www.host and host as the same site.
+Nu trata www.host si host ca fiind acelasi site.
+Keep double slashes in URLs
+Pastreaza barele duble din URL-uri
+Do not collapse duplicate slashes in URLs.
+Nu comprima barele duplicate din URL-uri.
+Keep the original query-string order
+Pastreaza ordinea originala din query string
+Do not reorder query-string parameters when deduplicating URLs.
+Nu reordona parametrii din query string la eliminarea URL-urilor duplicate.
+Strip query keys:
+Elimina cheile din query string:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Chei din query string, separate prin virgula, de eliminat din denumirea fisierelor salvate (de ex. sid,utm_source).

lang/Russian.txt

@@ -928,3 +928,31 @@ Server terminated
 Server terminated
 A fatal error has occurred during this mirror
 Âî âðåìÿ òåêóùåé çàêà÷êè ïðîèçîøëà ôàòàëüíàÿ îøèáêà
+Proxy type:
+Òèï ïðîêñè:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Ïðîòîêîë ïðîêñè: HTTP èëè SOCKS5 (ïî óìîë÷àíèþ SOCKS5 èñïîëüçóåò ïîðò 1080).
+Load cookies from file:
+Çàãðóçèòü cookies èç ôàéëà:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Ïðåäâàðèòåëüíî çàãðóçèòü cookies èç ôàéëà Netscape cookies.txt ïåðåä çàêà÷êîé.
+Pause between files:
+Ïàóçà ìåæäó ôàéëàìè:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Ñëó÷àéíàÿ çàäåðæêà ìåæäó çàêà÷êàìè ôàéëîâ, â ñåêóíäàõ. Èñïîëüçóéòå MIN:MAX äëÿ ñëó÷àéíîãî äèàïàçîíà (íàïðèìåð, 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Ñîõðàíÿòü ïðåôèêñ www. (íå îáúåäèíÿòü www.host ñ host)
+Do not treat www.host and host as the same site.
+Íå ñ÷èòàòü www.host è host îäíèì è òåì æå ñàéòîì.
+Keep double slashes in URLs
+Ñîõðàíÿòü äâîéíûå ñëýøè â URL
+Do not collapse duplicate slashes in URLs.
+Íå óäàëÿòü ïîâòîðÿþùèåñÿ ñëýøè â URL.
+Keep the original query-string order
+Ñîõðàíÿòü èñõîäíûé ïîðÿäîê ïàðàìåòðîâ çàïðîñà
+Do not reorder query-string parameters when deduplicating URLs.
+Íå ìåíÿòü ïîðÿäîê ïàðàìåòðîâ ñòðîêè çàïðîñà ïðè óäàëåíèè äóáëèêàòîâ URL.
+Strip query keys:
+Óäàëÿòü êëþ÷è çàïðîñà:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Êëþ÷è çàïðîñà ÷åðåç çàïÿòóþ, óäàëÿåìûå èç èìåíè ñîõðàíÿåìîãî ôàéëà (íàïðèìåð, sid,utm_source).

lang/Slovak.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Typ proxy:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protokol proxy: HTTP alebo SOCKS5 (predvolený port SOCKS5 je 1080).
+Load cookies from file:
+Naèíta» cookies zo súboru:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Naèíta» cookies zo súboru Netscape cookies.txt pred zaèatím s»ahovania.
+Pause between files:
+Prestávka medzi súbormi:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Náhodné oneskorenie medzi s»ahovaním súborov, v sekundách. Pre náhodný rozsah pou¾ite MIN:MAX (napr. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Zachova» predponu www. (nezluèova» www.host s host)
+Do not treat www.host and host as the same site.
+Nepova¾ova» www.host a host za tú istú lokalitu.
+Keep double slashes in URLs
+Zachova» dvojité lomky v URL
+Do not collapse duplicate slashes in URLs.
+Nezluèova» opakované lomky v URL.
+Keep the original query-string order
+Zachova» pôvodné poradie re»azca dotazu
+Do not reorder query-string parameters when deduplicating URLs.
+Nemeni» poradie parametrov re»azca dotazu pri odstraòovaní duplicitných URL.
+Strip query keys:
+Odstráni» kµúèe dotazu:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kµúèe dotazu oddelené èiarkami, ktoré sa vynechajú z pomenovania ukladaných súborov (napr. sid,utm_source).

lang/Slovenian.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Vrsta proxyja:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Protokol proxy: HTTP ali SOCKS5 (privzeta vrata SOCKS5 so 1080).
+Load cookies from file:
+Nalozi piskotke iz datoteke:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Predhodno nalozi piskotke iz datoteke Netscape cookies.txt pred zajemanjem.
+Pause between files:
+Premor med datotekami:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Nakljucni zamik med prenosi datotek, v sekundah. Za nakljucni obseg uporabite MIN:MAX (npr. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Ohrani predpono www. (ne zdruzi www.host z host)
+Do not treat www.host and host as the same site.
+www.host in host ne obravnavaj kot isto spletno mesto.
+Keep double slashes in URLs
+Ohrani dvojne posevnice v URL-jih
+Do not collapse duplicate slashes in URLs.
+Ne zdruzuj podvojenih posevnic v URL-jih.
+Keep the original query-string order
+Ohrani izvirni vrstni red poizvedovalnega niza
+Do not reorder query-string parameters when deduplicating URLs.
+Pri odstranjevanju podvojenih URL-jev ne spreminjaj vrstnega reda parametrov poizvedbe.
+Strip query keys:
+Odstrani kljuce poizvedbe:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Z vejicami loceni kljuci poizvedbe, ki se izpustijo pri poimenovanju shranjenih datotek (npr. sid,utm_source).

lang/Svenska.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Proxytyp:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxyprotokoll: HTTP eller SOCKS5 (SOCKS5 använder som standard port 1080).
+Load cookies from file:
+Läs in cookies från fil:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Läs in cookies från en Netscape cookies.txt-fil innan crawlningen börjar.
+Pause between files:
+Paus mellan filer:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Slumpmässig fördröjning mellan filnedladdningar, i sekunder. Använd MIN:MAX för ett slumpmässigt intervall (t.ex. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Behåll www.-prefixet (slå inte ihop www.host med host)
+Do not treat www.host and host as the same site.
+Behandla inte www.host och host som samma webbplats.
+Keep double slashes in URLs
+Behåll dubbla snedstreck i URL:er
+Do not collapse duplicate slashes in URLs.
+Slå inte ihop upprepade snedstreck i URL:er.
+Keep the original query-string order
+Behåll frågesträngens ursprungliga ordning
+Do not reorder query-string parameters when deduplicating URLs.
+Ändra inte ordningen på frågesträngens parametrar när dubbletter av URL:er tas bort.
+Strip query keys:
+Ta bort frågenycklar:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kommaseparerade frågenycklar som utelämnas vid namngivningen av sparade filer (t.ex. sid,utm_source).

lang/Turkish.txt

@@ -928,3 +928,31 @@ Server terminated
 Sunucu sonlandýrdý
 A fatal error has occurred during this mirror
 Bu yansýlama iþlemi sýrasýnda ölümcül bir hata oluþtu
+Proxy type:
+Proxy türü:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proxy protokolü: HTTP veya SOCKS5 (SOCKS5 varsayýlan portu 1080).
+Load cookies from file:
+Çerezleri dosyadan yükle:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Taramadan önce bir Netscape cookies.txt dosyasýndan çerezleri önceden yükle.
+Pause between files:
+Dosyalar arasýnda bekleme:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Dosya indirmeleri arasýnda saniye cinsinden rastgele gecikme. Rastgele bir aralýk için MIN:MAX kullanýn (örn. 2:8).
+Keep the www. prefix (do not merge www.host with host)
+www. önekini koru (www.host ile host'u birleþtirme)
+Do not treat www.host and host as the same site.
+www.host ve host'u ayný site olarak deðerlendirme.
+Keep double slashes in URLs
+URL'lerdeki çift eðik çizgileri koru
+Do not collapse duplicate slashes in URLs.
+URL'lerdeki yinelenen eðik çizgileri birleþtirme.
+Keep the original query-string order
+Özgün sorgu dizesi sýrasýný koru
+Do not reorder query-string parameters when deduplicating URLs.
+URL'lerin yinelenenlerini ayýklarken sorgu dizesi parametrelerini yeniden sýralama.
+Strip query keys:
+Sorgu anahtarlarýný çýkar:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Kaydedilen dosya adlandýrmasýndan çýkarýlacak, virgülle ayrýlmýþ sorgu anahtarlarý (örn. sid,utm_source).

lang/Ukrainian.txt

@@ -928,3 +928,31 @@ Server terminated
 
 A fatal error has occurred during this mirror
 
+Proxy type:
+Òèï ïðîêñ³:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Ïðîòîêîë ïðîêñ³: HTTP àáî SOCKS5 (çà çàìîâ÷óâàííÿì SOCKS5 âèêîðèñòîâóº ïîðò 1080).
+Load cookies from file:
+Çàâàíòàæèòè cookies ç ôàéëó:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Ïîïåðåäíüî çàâàíòàæèòè cookies ç ôàéëó Netscape cookies.txt ïåðåä çàâàíòàæåííÿì.
+Pause between files:
+Ïàóçà ì³æ ôàéëàìè:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Âèïàäêîâà çàòðèìêà ì³æ çàâàíòàæåííÿìè ôàéë³â, ó ñåêóíäàõ. Âèêîðèñòîâóéòå MIN:MAX äëÿ âèïàäêîâîãî ä³àïàçîíó (íàïðèêëàä, 2:8).
+Keep the www. prefix (do not merge www.host with host)
+Çáåð³ãàòè ïðåô³êñ www. (íå îá'ºäíóâàòè www.host ç host)
+Do not treat www.host and host as the same site.
+Íå ââàæàòè www.host ³ host îäíèì ³ òèì ñàìèì ñàéòîì.
+Keep double slashes in URLs
+Çáåð³ãàòè ïîäâ³éí³ ñëåø³ â URL
+Do not collapse duplicate slashes in URLs.
+Íå âèäàëÿòè ïîâòîðþâàí³ ñëåø³ â URL.
+Keep the original query-string order
+Çáåð³ãàòè ïî÷àòêîâèé ïîðÿäîê ïàðàìåòð³â çàïèòó
+Do not reorder query-string parameters when deduplicating URLs.
+Íå çì³íþâàòè ïîðÿäîê ïàðàìåòð³â ðÿäêà çàïèòó ï³ä ÷àñ óñóíåííÿ äóáë³êàò³â URL.
+Strip query keys:
+Âèëó÷àòè êëþ÷³ çàïèòó:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Êëþ÷³ çàïèòó ÷åðåç êîìó, ÿê³ âèëó÷àþòüñÿ ç ³ìåí³ çáåðåæåíîãî ôàéëó (íàïðèêëàä, sid,utm_source).

lang/Uzbek.txt

@@ -928,3 +928,31 @@ Server terminated
 Server terminated
 A fatal error has occurred during this mirror
 Joriy ko’chirish vaqtida jiddiy xatolik yuz berdi
+Proxy type:
+Proksi turi:
+Proxy protocol: HTTP, or SOCKS5 (SOCKS5 default port is 1080).
+Proksi protokoli: HTTP yoki SOCKS5 (SOCKS5 ning standart porti 1080).
+Load cookies from file:
+Fayldan cookies yuklamoq:
+Preload cookies from a Netscape cookies.txt file before crawling.
+Ko’chirib olishdan oldin Netscape cookies.txt faylidan cookies’ni oldindan yuklamoq.
+Pause between files:
+Fayllar orasidagi pauza:
+Random delay between file downloads, in seconds. Use MIN:MAX for a random range (e.g. 2:8).
+Fayllarni ko’chirib olish orasidagi tasodifiy kechikish, soniyalarda. Tasodifiy diapazon uchun MIN:MAX dan foydalaning (masalan, 2:8).
+Keep the www. prefix (do not merge www.host with host)
+www. prefiksini saqlash (www.host ni host bilan birlashtirmaslik)
+Do not treat www.host and host as the same site.
+www.host va host ni bir xil sayt deb hisoblamaslik.
+Keep double slashes in URLs
+URL lardagi qo’sh sleshlarni saqlash
+Do not collapse duplicate slashes in URLs.
+URL lardagi takroriy sleshlarni olib tashlamaslik.
+Keep the original query-string order
+So’rov satrining asl tartibini saqlash
+Do not reorder query-string parameters when deduplicating URLs.
+URL dublikatlarini olib tashlashda so’rov satri parametrlari tartibini o’zgartirmaslik.
+Strip query keys:
+Olib tashlanadigan so’rov kalitlari:
+Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
+Saqlangan fayl nomidan olib tashlanadigan, vergul bilan ajratilgan so’rov kalitlari (masalan, sid,utm_source).

src/htsback.c

@@ -628,6 +628,10 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                       back[p].r.size, back[p].url_adr, back[p].url_fil);
       }
       back_finalize_backup(opt, &back[p], HTS_FALSE);
+      /* Keep the surviving copy in new.lst, else the update purge drops the
+         file we refused to overwrite with the partial body (#562). */
+      if (fexist_utf8(back[p].url_sav))
+        filenote(&opt->state.strc, back[p].url_sav, NULL);
       return -1;
     }
 
@@ -2692,9 +2696,12 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
         int dispo = 0;
 
         // probe the resolved address list once per fresh connect (cache hit:
-        // the host was resolved when this connect was opened)
+        // the host was resolved when this connect was opened). Not under a
+        // proxy: the socket dials the proxy, so resolving the origin here leaks
+        // its DNS and lets a proxy-connect failure fall back to dialing it
+        // direct.
         if (cf->addr_count < 0 && back[i].r.soc != INVALID_SOCKET &&
-            !back[i].r.is_file) {
+            !back[i].r.is_file && !back[i].r.req.proxy.active) {
           SOCaddr scratch[HTS_MAXADDRNUM];
 
           cf->addr_count = hts_dns_resolve_all(opt, back[i].url_adr, scratch,
@@ -3306,16 +3313,26 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                         back[i].chunk_blocksize = -1;   /* ending */
                       back[i].r.totalsize += chunk_size;        // noter taille
                       if (back[i].r.adr != NULL || !back[i].r.is_write) {       // Not to disk
-                        back[i].r.adr =
+                        // totalsize sums attacker-declared chunk sizes; past
-                          (char *) realloct(back[i].r.adr,
+                        // 2GB the (size_t) cast below truncates on 32-bit and
-                                            (size_t) back[i].r.totalsize + 1);
+                        // under-allocates. Mark the chunk invalid so the shared
-                        if (!back[i].r.adr) {
+                        // error path tears the transfer down.
-                          if (cache->log != NULL) {
+                        if (back[i].r.totalsize > INT32_MAX) {
-                            hts_log_print(opt, LOG_ERROR,
+                          hts_log_print(opt, LOG_WARNING,
-                                          "not enough memory (" LLintP
+                                        "Chunked resource too large for %s%s",
-                                          ") for %s%s",
+                                        back[i].url_adr, back[i].url_fil);
-                                          (LLint) back[i].r.totalsize,
+                          chunk_size = -1;
-                                          back[i].url_adr, back[i].url_fil);
+                        } else {
+                          back[i].r.adr = (char *) realloct(
+                              back[i].r.adr, (size_t) back[i].r.totalsize + 1);
+                          if (!back[i].r.adr) {
+                            if (cache->log != NULL) {
+                              hts_log_print(opt, LOG_ERROR,
+                                            "not enough memory (" LLintP
+                                            ") for %s%s",
+                                            (LLint) back[i].r.totalsize,
+                                            back[i].url_adr, back[i].url_fil);
+                            }
                           }
                         }
                       }

src/htscharset.c

@@ -385,7 +385,7 @@ char *hts_convertStringFromUTF8(const char *s, size_t size, const char *charset)
   return hts_convertStringCPFromUTF8(s, size, cp);
 }
 
-char *hts_convertStringSystemToUTF8(const char *s, size_t size) {
+HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size) {
   return hts_convertStringCPToUTF8(s, size, GetACP());
 }
 

src/htscharset.h

@@ -175,7 +175,7 @@ extern char *hts_convertUCS2StringToUTF8(LPWSTR woutput, int wsize);
  * Convert current system codepage to UTF-8.
  * This function is WIN32 specific.
  **/
-extern char *hts_convertStringSystemToUTF8(const char *s, size_t size);
+HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size);
 
 /**
  * Replace the CRT's ANSI argv by a UTF-8 one decoded from the real UTF-16

src/htsfilters.c

@@ -154,12 +154,14 @@ static const char *strjoker_rec(strjoker_memo *memo, const char *chaine,
 
   if (depth > memo->maxdepth)
     memo->maxdepth = depth;
+  /* Charge the budget before the depth cap: cut disables the memo, so uncounted
+     deep calls would let the sub-cap search explode (OSS-Fuzz 535114376). */
+  if (memo->nsteps != NULL && ++*memo->nsteps > STRJOKER_MAXSTEPS)
+    return NULL; /* work budget spent: fail the match safely */
   if (depth >= STRJOKER_MAXDEPTH) {
     memo->cut = HTS_TRUE;
     return NULL; /* nesting beyond any real filter: fail the branch safely */
   }
-  if (memo->nsteps != NULL && ++*memo->nsteps > STRJOKER_MAXSTEPS)
-    return NULL; /* work budget spent: fail the match safely */
   if (memo->failed) {
     bit = (size_t) (chaine - memo->chaine0) * memo->stride +
           (size_t) (joker - memo->joker0);

src/htslib.c

@@ -6030,6 +6030,8 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->referer);
     StringFree(opt->from);
     StringFree(opt->lang_iso);
+    StringFree(opt->accept);
+    StringFree(opt->headers);
     StringFree(opt->sys_com);
     StringFree(opt->mimedefs);
     StringFree(opt->filelist);

src/htsselftest.c

@@ -794,6 +794,20 @@ static int st_filterbounds(httrackp *opt, int argc, char **argv) {
   memset(subj, 'a', 32);
   subj[32] = '\0';
   assertf(strjoker(subj, pat, NULL, NULL) != NULL);
+  /* Same pin for the class-branch shape users actually write (*[..]), against a
+     long subject: it must match with room to spare under the work cap. */
+  {
+    const char *seg = "*[A-Z,a-z,0-9]";
+    const size_t seglen = strlen(seg), nseg = 16;
+
+    for (i = 0; i < (int) nseg; i++)
+      memcpy(pat + i * seglen, seg, seglen);
+    pat[nseg * seglen] = '\0';
+    memset(subj, 'a', 512);
+    subj[512] = '\0';
+    assertf(strjoker_bounds(subj, pat, &steps, &maxsteps, NULL, NULL) != NULL);
+    assertf(steps < maxsteps);
+  }
   freet(pat);
   freet(subj);
   printf("filterbounds: OK\n");

tests/13_crawl_proxy_https.test

@@ -8,22 +8,26 @@ set -euo pipefail
 
 : "${top_srcdir:=..}"
 
+# shellcheck source=tests/testlib.sh
+. "$top_srcdir/tests/testlib.sh"
+
 if test "${HTTPS_SUPPORT:-}" == "no"; then
     echo "no https support compiled, skipping"
     exit 77
 fi
-if ! command -v python3 >/dev/null 2>&1 || ! command -v openssl >/dev/null 2>&1; then
+python=$(find_python) || python=
+if test -z "$python" || ! command -v openssl >/dev/null 2>&1; then
     echo "python3/openssl missing, skipping"
     exit 77
 fi
 
-server="$top_srcdir/tests/proxy-https-server.py"
+server=$(nativepath "$top_srcdir/tests/proxy-https-server.py")
 tmpdir=$(mktemp -d)
 pids=
 
 cleanup() {
     for pid in $pids; do
-        kill "$pid" 2>/dev/null || true
+        stop_server "$pid"
     done
     rm -rf "$tmpdir"
 }
@@ -38,10 +42,13 @@ cat "$tmpdir/key.pem" "$tmpdir/cert.pem" >"$tmpdir/both.pem"
 # start_server <logdir> <mode>: launches a proxy+origin pair, sets $origin_port
 # and $proxy_port from its announced ephemeral ports.
 start_server() {
-    local dir="$1" mode="$2" ports
+    local dir="$1" mode="$2" ports pem
     mkdir -p "$dir"
     ports="$dir/ports.txt"
-    python3 "$server" "$tmpdir/both.pem" "$dir" "$mode" \
+    pem=$(nativepath "$tmpdir/both.pem")
+    dir_native=$(nativepath "$dir")
+    : >"$ports"
+    "$python" "$server" "$pem" "$dir_native" "$mode" \
         >"$ports" 2>"$dir/server.err" &
     pids="$pids $!"
     for _ in $(seq 1 100); do

tests/19_local-connect-fallback.test

@@ -12,14 +12,17 @@ set -euo pipefail
 
 : "${top_srcdir:=..}"
 
+# shellcheck source=tests/testlib.sh
+. "$top_srcdir/tests/testlib.sh"
+
 if test "${V6_SUPPORT:-}" == "no"; then
     echo "no IPv6 support (resolver list/override is IPv6-only), skipping"
     exit 77
 fi
-if ! command -v python3 >/dev/null 2>&1; then
+python=$(find_python) || {
     echo "python3 missing, skipping"
     exit 77
-fi
+}
 # The fixture needs a second loopback IP (dead 127.0.0.2 + live 127.0.0.1) for
 # the fallback to have a target; GNU/Hurd has only 127.0.0.1, so skip there.
 case "$(uname -s)" in
@@ -29,23 +32,20 @@ GNU | GNU/*)
     ;;
 esac
 
-server="$top_srcdir/tests/local-server.py"
+server=$(nativepath "$top_srcdir/tests/local-server.py")
-root="$top_srcdir/tests/server-root"
+root=$(nativepath "$top_srcdir/tests/server-root")
 tmpdir=$(mktemp -d)
 serverpid=
 
 cleanup() {
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null || true
-        wait "$serverpid" 2>/dev/null || true
-    fi
     rm -rf "$tmpdir"
     return 0
 }
 trap cleanup EXIT
 
 # bind the live server to 127.0.0.1 only, so 127.0.0.2 refuses the connect
-python3 "$server" --root "$root" --bind 127.0.0.1 >"$tmpdir/srv.out" 2>"$tmpdir/srv.err" &
+"$python" "$server" --root "$root" --bind 127.0.0.1 >"$tmpdir/srv.out" 2>"$tmpdir/srv.err" &
 serverpid=$!
 port=
 for _ in $(seq 1 50); do

tests/20_local-resume-loop.test

@@ -5,19 +5,19 @@ set -u
 
 : "${top_srcdir:=..}"
 testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
+server=$(nativepath "${testdir}/local-server.py")
+root=$(nativepath "${testdir}/server-root")
 
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77
 
 tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_206.XXXXXX") || exit 1
 serverpid=
 crawlpid=
 cleanup() {
     test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
     rm -rf "$tmpdir"
 }
 trap cleanup EXIT HUP INT QUIT PIPE TERM
@@ -25,8 +25,9 @@ trap cleanup EXIT HUP INT QUIT PIPE TERM
 # --- start the server, discover its ephemeral port --------------------------
 # RESUME_COUNTER gets a byte per /resume/blob.txt request (pass-2 delta bounds re-gets).
 serverlog="${tmpdir}/server.log"
+: >"$serverlog"
 counter="${tmpdir}/blobcount"
-RESUME_COUNTER="$counter" python3 "$server" --root "${testdir}/server-root" >"$serverlog" 2>&1 &
+RESUME_COUNTER="$counter" "$python" "$server" --root "$root" >"$serverlog" 2>&1 &
 serverpid=$!
 port=
 for _ in $(seq 1 50); do

tests/24_local-resume-overlap.test

@@ -9,29 +9,30 @@ set -eu
 
 : "${top_srcdir:=..}"
 testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
+server=$(nativepath "${testdir}/local-server.py")
+root=$(nativepath "${testdir}/server-root")
 
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77
 
 tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_198.XXXXXX") || exit 1
 serverpid=
 crawlpid=
 cleanup() {
     if test -n "$crawlpid"; then kill -9 "$crawlpid" 2>/dev/null || true; fi
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null || true
-        wait "$serverpid" 2>/dev/null || true
-    fi
     rm -rf "$tmpdir"
 }
 trap cleanup EXIT HUP INT QUIT PIPE TERM
 
 # OVERLAP_COUNTER gets a byte per flaky.bin request so pass 1 knows when to interrupt.
 serverlog="${tmpdir}/server.log"
+: >"$serverlog"
 counter="${tmpdir}/hits"
 resumed="${tmpdir}/resumed" # gets a byte when the server serves a resume 206
 OVERLAP_COUNTER="$counter" OVERLAP_RESUMED="$resumed" \
-    python3 "$server" --root "${testdir}/server-root" \
+    "$python" "$server" --root "$root" \
     >"$serverlog" 2>&1 &
 serverpid=$!
 port=

tests/28_local-pause.test

@@ -9,9 +9,12 @@ set -e
 
 : "${top_srcdir:=..}"
 
+# shellcheck source=tests/testlib.sh
+. "$top_srcdir/tests/testlib.sh"
+
 # python3 runs the local server (mirror local-crawl.sh); skip when absent, else
 # run() swallows its exit-77 and the serverless 0s/0s crawl looks like a fail.
-command -v python3 >/dev/null || {
+find_python >/dev/null || {
     echo "python3 not found; skipping local crawl tests"
     exit 77
 }

tests/46_local-update-304-resume.test

@@ -7,27 +7,28 @@ set -u
 
 : "${top_srcdir:=..}"
 testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
+server=$(nativepath "${testdir}/local-server.py")
+root=$(nativepath "${testdir}/server-root")
 
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77
 
 tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_c7.XXXXXX") || exit 1
 serverpid=
 crawlpid=
 cleanup() {
     test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
     rm -rf "$tmpdir"
 }
 trap cleanup EXIT HUP INT QUIT PIPE TERM
 
 serverlog="${tmpdir}/server.log"
+: >"$serverlog"
 counter="${tmpdir}/reqcount"
 mark="${tmpdir}/got304"
-RESUME304_COUNTER="$counter" RESUME304_MARK="$mark" python3 "$server" --root "${testdir}/server-root" >"$serverlog" 2>&1 &
+RESUME304_COUNTER="$counter" RESUME304_MARK="$mark" "$python" "$server" --root "$root" >"$serverlog" 2>&1 &
 serverpid=$!
 port=
 for _ in $(seq 1 50); do

tests/47_local-crange-overflow.test

@@ -8,25 +8,26 @@ set -u
 
 : "${top_srcdir:=..}"
 testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
+server=$(nativepath "${testdir}/local-server.py")
+root=$(nativepath "${testdir}/server-root")
 
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77
 
 tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_crange.XXXXXX") || exit 1
 serverpid=
 crawlpid=
 cleanup() {
     test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
     rm -rf "$tmpdir"
 }
 trap cleanup EXIT HUP INT QUIT PIPE TERM
 
 serverlog="${tmpdir}/server.log"
-python3 "$server" --root "${testdir}/server-root" >"$serverlog" 2>&1 &
+: >"$serverlog"
+"$python" "$server" --root "$root" >"$serverlog" 2>&1 &
 serverpid=$!
 port=
 for _ in $(seq 1 50); do

tests/48_local-crange-memresume.test

@@ -8,25 +8,34 @@ set -u
 
 : "${top_srcdir:=..}"
 testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
+server=$(nativepath "${testdir}/local-server.py")
+root=$(nativepath "${testdir}/server-root")
 
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77
+
+# The resume needs a graceful pass-1 interrupt (a clean cache), which MSYS can't
+# deliver to a native exe, and the restart-whole path fails on a repaired cache
+# (#581); TODO: drop once that lands.
+if is_windows; then
+    echo "Windows: interrupted-resume restart fails on a repaired cache (#581), skipping"
+    exit 77
+fi
 
 tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_crangemem.XXXXXX") || exit 1
 serverpid=
 crawlpid=
 cleanup() {
     test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
     rm -rf "$tmpdir"
 }
 trap cleanup EXIT HUP INT QUIT PIPE TERM
 
 serverlog="${tmpdir}/server.log"
-python3 "$server" --root "${testdir}/server-root" >"$serverlog" 2>&1 &
+: >"$serverlog"
+"$python" "$server" --root "$root" >"$serverlog" 2>&1 &
 serverpid=$!
 port=
 for _ in $(seq 1 50); do
@@ -77,7 +86,14 @@ echo "OK (temp-ref present)"
 
 # --- pass 2: --continue -> resume -> hostile INT64_MAX Content-Range ----------
 printf '[pass 2: hostile 206, no overflow, refetch] ..\t'
-httrack "${common[@]}" --continue "${base}/crange206mem/index.html" >"${tmpdir}/log2" 2>&1
+rc=0
+httrack "${common[@]}" --continue "${base}/crange206mem/index.html" >"${tmpdir}/log2" 2>&1 || rc=$?
+# a crash here would otherwise read as a clean "terminated"
+test "$rc" -eq 0 || {
+    echo "FAIL: httrack exited $rc"
+    cat "${tmpdir}/log2" >&2
+    exit 1
+}
 echo "OK (terminated)"
 
 blob=$(find "$out" -name blob.bin 2>/dev/null | head -1)

tests/52_local-socks5.test

@@ -8,11 +8,15 @@ set -euo pipefail
 
 : "${top_srcdir:=..}"
 
+# shellcheck source=tests/testlib.sh
+. "$top_srcdir/tests/testlib.sh"
+
 if test "${HTTPS_SUPPORT:-}" == "no"; then
     echo "no https support compiled, skipping"
     exit 77
 fi
-if ! command -v python3 >/dev/null 2>&1 || ! command -v openssl >/dev/null 2>&1; then
+python=$(find_python) || python=
+if test -z "$python" || ! command -v openssl >/dev/null 2>&1; then
     echo "python3/openssl missing, skipping"
     exit 77
 fi
@@ -20,13 +24,13 @@ fi
 # a .invalid name never resolves (RFC 6761): reaching the page at all proves the
 # proxy did the DNS
 host="socks-origin.invalid"
-server="$top_srcdir/tests/socks5-server.py"
+server=$(nativepath "$top_srcdir/tests/socks5-server.py")
 tmpdir=$(mktemp -d)
 pids=
 
 cleanup() {
     for pid in $pids; do
-        kill "$pid" 2>/dev/null || true
+        stop_server "$pid"
     done
     rm -rf "$tmpdir"
 }
@@ -39,10 +43,13 @@ cat "$tmpdir/key.pem" "$tmpdir/cert.pem" >"$tmpdir/both.pem"
 
 # start_server <logdir> <mode>: sets $tls_port/$http_port/$socks_port
 start_server() {
-    local dir="$1" mode="$2" ports
+    local dir="$1" mode="$2" ports pem
     mkdir -p "$dir"
     ports="$dir/ports.txt"
-    python3 "$server" "$tmpdir/both.pem" "$dir" "$mode" \
+    pem=$(nativepath "$tmpdir/both.pem")
+    dir_native=$(nativepath "$dir")
+    : >"$ports"
+    "$python" "$server" "$pem" "$dir_native" "$mode" \
         >"$ports" 2>"$dir/server.err" &
     pids="$pids $!"
     for _ in $(seq 1 100); do

tests/54_local-update-truncate-purge.test

@@ -0,0 +1,23 @@
+#!/bin/bash
+#
+# An --update re-fetch that comes in short must not delete the mirrored file (#562).
+# Pass 1 mirrors page.html (in-memory) and file.bin (direct-to-disk); pass 2 serves
+# both with the full declared Content-Length but half the body, then closes. httrack
+# refuses the partial ("will be retried") — and unfixed, the end-of-update purge then
+# deletes the good pass-1 copy, which was never overwritten. stay.html is the control:
+# fully served both passes, it must update to V2.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" \
+    --rerun-args '--update' \
+    --log-found 'incomplete transfer.*uptrunc/page\.html' \
+    --log-found 'incomplete transfer.*uptrunc/file\.bin' \
+    --file-matches 'uptrunc/page.html' 'MIRRORED-PAGE-V1' \
+    --file-matches 'uptrunc/file.bin' 'MIRRORED-BIN-V1' \
+    --file-min-bytes 'uptrunc/file.bin' 32768 \
+    --file-matches 'uptrunc/stay.html' 'STAY-V2' \
+    --file-not-matches 'uptrunc/stay.html' 'STAY-V1' \
+    httrack 'BASEURL/uptrunc/index.html'

tests/55_local-chunked.test

@@ -0,0 +1,18 @@
+#!/bin/bash
+# A well-formed Transfer-Encoding: chunked response mirrors intact: the chunk
+# automaton (htsback.c) joins the bodies and the 2GB in-RAM cap stays quiet.
+# The 76-char run spans a 64-byte chunk boundary (only contiguous once joined);
+# a CR anywhere would be leftover framing; '</body>' proves no truncation.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --found 'chunked/page.html' \
+    --file-matches 'chunked/page.html' \
+    'chunk-body chunk-body chunk-body chunk-body chunk-body chunk-body chunk-body' \
+    --file-matches 'chunked/page.html' '</body>' \
+    --file-not-matches 'chunked/page.html' $'\r' \
+    --log-not-found 'too large' \
+    httrack 'BASEURL/chunked/index.html'

tests/56_local-proxy-noleak.test

@@ -0,0 +1,93 @@
+#!/bin/bash
+#
+# A crawl through a proxy must never resolve or dial the origin itself: the proxy
+# does that. A dead proxy + a multi-address origin used to fall back to dialing
+# the origin direct (bypassing the proxy, leaking its DNS and IP). The decoy
+# origin here must therefore receive nothing.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+# shellcheck source=tests/testlib.sh
+. "$top_srcdir/tests/testlib.sh"
+
+if test "${V6_SUPPORT:-}" == "no"; then
+    echo "no IPv6 support (resolver override compiled out), skipping"
+    exit 77
+fi
+python=$(find_python) || {
+    echo "python3 missing, skipping"
+    exit 77
+}
+
+server=$(nativepath "$top_srcdir/tests/local-server.py")
+root=$(nativepath "$top_srcdir/tests/server-root")
+tmpdir=$(mktemp -d)
+serverpid=
+
+cleanup() {
+    stop_server "$serverpid"
+    rm -rf "$tmpdir"
+    return 0
+}
+trap cleanup EXIT
+
+# decoy origin: it must stay silent. LOCAL_SERVER_VERBOSE logs any request it gets.
+LOCAL_SERVER_VERBOSE=1 "$python" "$server" --root "$root" --bind 127.0.0.1 \
+    >"$tmpdir/srv.out" 2>"$tmpdir/srv.err" &
+serverpid=$!
+port=
+for _ in $(seq 1 50); do
+    line=$(head -n1 "$tmpdir/srv.out" 2>/dev/null || true)
+    if test "${line%% *}" == "PORT"; then
+        port="${line#PORT }"
+        break
+    fi
+    kill -0 "$serverpid" 2>/dev/null || {
+        echo "server exited early: $(cat "$tmpdir/srv.err")"
+        exit 1
+    }
+    sleep 0.1
+done
+test -n "$port" || {
+    echo "could not discover server port"
+    exit 1
+}
+
+# a proxy port nothing listens on: grab a free one and let it close (refuses).
+deadproxy=$("$python" -c \
+    'import socket; s=socket.socket(); s.bind(("127.0.0.1",0)); print(s.getsockname()[1]); s.close()')
+
+# origin resolves to two addresses so a fallback would have a second to dial;
+# 127.0.0.1 (the decoy) is the one the old bypass reached.
+out="$tmpdir/crawl"
+HTTRACK_DEBUG_RESOLVE="decoyhost:127.0.0.2,127.0.0.1" \
+    httrack "http://decoyhost:$port/simple/basic.html" -O "$out" \
+    -P "127.0.0.1:$deadproxy" -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z \
+    >"$tmpdir/log" 2>&1
+
+log="$out/hts-log.txt"
+
+# the origin must have seen no connection (no leak/bypass)
+if grep -qE '"(GET|POST|HEAD|CONNECT) ' "$tmpdir/srv.err"; then
+    echo "FAIL: origin was contacted directly, bypassing the proxy"
+    cat "$tmpdir/srv.err"
+    exit 1
+fi
+
+# the crawl must fail at the proxy (proves it really tried the proxy, not a no-op)
+grep -q 'Connect Error' "$log" || {
+    echo "FAIL: expected a proxy connect error"
+    cat "$log"
+    exit 1
+}
+
+# and it must not have tried an origin-address fallback under the proxy
+if grep -q "trying next address" "$log"; then
+    echo "FAIL: fell back to an origin address under a proxy"
+    cat "$log"
+    exit 1
+fi
+
+echo "OK: a dead proxy fails cleanly without dialing the origin"

tests/Makefile.am

@@ -3,7 +3,7 @@
 # silently drop it from the dist tarball and break "make distcheck".
 EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
 	proxy-https-server.py socks5-server.py \
-	local-crawl.sh local-server.py server.crt server.key \
+	local-crawl.sh local-server.py testlib.sh server.crt server.key \
 	server-root/simple/basic.html server-root/simple/link.html \
 	server-root/stripquery/index.html server-root/stripquery/a.html \
 	server-root/fraglink/index.html server-root/fraglink/target.html \
@@ -130,6 +130,9 @@ TESTS = \
 	50_local-contentcodings.test \
 	51_local-update-codec.test \
 	52_local-socks5.test \
-	53_local-proxytrack-cache-corrupt.test
+	53_local-proxytrack-cache-corrupt.test \
+	54_local-update-truncate-purge.test \
+	55_local-chunked.test \
+	56_local-proxy-noleak.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -38,6 +38,8 @@
 set -u
 
 testdir=$(cd "$(dirname "$0")" && pwd)
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
 server="${testdir}/local-server.py"
 root="${LOCAL_SERVER_ROOT:-${testdir}/server-root}"
 cert="${testdir}/server.crt"
@@ -72,12 +74,8 @@ function cleanup {
         kill -9 "$crawlpid" 2>/dev/null
         crawlpid=
     fi
-    if test -n "$serverpid"; then
+    stop_server "$serverpid"
-        kill "$serverpid" 2>/dev/null
+    serverpid=
-        # Reap it so the port is released before we rm the tmpdir/log.
-        wait "$serverpid" 2>/dev/null
-        serverpid=
-    fi
     if test -n "$tmpdir" && test -d "$tmpdir"; then
         test -n "$nopurge" || rm -rf "$tmpdir"
     fi
@@ -96,7 +94,7 @@ nopurge=
 trap cleanup EXIT HUP INT QUIT PIPE TERM
 
 # python3 is required; mirror check-network.sh's skip-with-77 convention.
-command -v python3 >/dev/null || ! echo "python3 not found; skipping local crawl tests" || exit 77
+python=$(find_python) || ! echo "python3 not found; skipping local crawl tests" >&2 || exit 77
 
 tmptopdir=${TMPDIR:-/tmp}
 test -d "$tmptopdir" || mkdir -p "$tmptopdir" || die "no temporary directory; set TMPDIR"
@@ -158,12 +156,12 @@ done
 # --- start the server --------------------------------------------------------
 test -r "$server" || die "cannot read $server"
 serverlog="${tmpdir}/server.log"
-serverargs=(--root "$root")
+serverargs=(--root "$(nativepath "$root")")
 if test -n "$tls"; then
-    serverargs+=(--tls --cert "$cert" --key "$key")
+    serverargs+=(--tls --cert "$(nativepath "$cert")" --key "$(nativepath "$key")")
 fi
-debug "starting python3 $server ${serverargs[*]}"
+debug "starting $python $server ${serverargs[*]}"
-python3 "$server" "${serverargs[@]}" >"$serverlog" 2>&1 &
+"$python" "$(nativepath "$server")" "${serverargs[@]}" >"$serverlog" 2>&1 &
 serverpid=$!
 
 # Wait for the "PORT <n>" line (server prints it once bound).
@@ -203,7 +201,7 @@ if test "${#cookies[@]}" -gt 0; then
 fi
 
 # --- run httrack -------------------------------------------------------------
-which httrack >/dev/null || die "could not find httrack"
+command -v httrack >/dev/null || die "could not find httrack"
 ver=$(httrack -O /dev/null --version | sed -e 's/HTTrack version //')
 test -n "$ver" || die "could not run httrack"
 
@@ -278,8 +276,7 @@ if test -n "$rerun_dead"; then
     test -s "$zip" || die "no cache was written by the first pass"
     cp "$zip" "${tmpdir}/cache-before.zip"
     cp "${out}/hts-log.txt" "${tmpdir}/log-before.txt"
-    kill "$serverpid" 2>/dev/null
+    stop_server "$serverpid"
-    wait "$serverpid" 2>/dev/null
     serverpid=
     info "re-running httrack against the stopped server"
     httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
@@ -441,12 +438,18 @@ while test "$i" -lt "${#audit[@]}"; do
     --file-mode)
         path="${audit[$((i + 1))]}"
         i=$((i + 2))
-        mode=$(stat -c '%a' "${hostroot}/${path}" 2>/dev/null ||
+        if is_windows; then
-            stat -f '%Lp' "${hostroot}/${path}" 2>/dev/null)
+            # No POSIX modes, and the engine only chmods #ifndef _WIN32.
-        info "checking ${path} mode ${mode:-none} is ${audit[$i]}"
+            info "checking ${path} mode"
-        if test "$mode" = "${audit[$i]}"; then result "OK"; else
+            result "SKIP (no POSIX modes)"
-            result "wrong mode"
+        else
-            exit 1
+            mode=$(stat -c '%a' "${hostroot}/${path}" 2>/dev/null ||
+                stat -f '%Lp' "${hostroot}/${path}" 2>/dev/null)
+            info "checking ${path} mode ${mode:-none} is ${audit[$i]}"
+            if test "$mode" = "${audit[$i]}"; then result "OK"; else
+                result "wrong mode"
+                exit 1
+            fi
         fi
         ;;
     esac

tests/local-server.py

@@ -18,6 +18,7 @@ import base64
 import gzip
 import hashlib
 import os
+import sys
 import time
 from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
 from urllib.parse import quote, unquote, urlsplit
@@ -699,15 +700,17 @@ class Handler(SimpleHTTPRequestHandler):
     # Pass 1 mirrors each file from a valid gzip body; pass 2 (--update) serves
     # a body that cannot be decoded. The previously-mirrored copy must survive.
     # fresh.html is the control: its pass-2 body decodes, so it must be updated.
-    UPCODEC_SEEN = {}
+    # Per-path body-fetch counter shared by the update-refetch routes; paths are
+    # distinct so one dict serves all of them.
+    REFETCH_SEEN = {}
 
-    def upcodec_pass(self):
+    def refetch_pass(self):
-        """1 on the first body fetch of this path, 2 on the next ones. HEADs
+        """1 on the first body fetch of this path, N on the Nth. HEADs don't
-        don't count, so a stray one can't shift which pass gets the bad body."""
+        count, so a stray one can't shift which pass gets the special body."""
         if self.command == "HEAD":
             return 1
-        seen = Handler.UPCODEC_SEEN.get(self.path, 0) + 1
+        seen = Handler.REFETCH_SEEN.get(self.path, 0) + 1
-        Handler.UPCODEC_SEEN[self.path] = seen
+        Handler.REFETCH_SEEN[self.path] = seen
         return seen
 
     @staticmethod
@@ -739,36 +742,78 @@ class Handler(SimpleHTTPRequestHandler):
     UNSUP_V1 = b"<html><body><p>MIRRORED-UNSUP-V1</p></body></html>"
 
     def route_upcodec_mem(self):
-        if self.upcodec_pass() == 1:
+        if self.refetch_pass() == 1:
             self.send_coded(self.gzipped(self.MEM_V1), "text/html")
         else:
             self.send_coded(self.bad_gzip(self.MEM_V1), "text/html")
 
     def route_upcodec_disk(self):
-        if self.upcodec_pass() == 1:
+        if self.refetch_pass() == 1:
             self.send_coded(self.gzipped(self.DISK_V1), "application/octet-stream")
         else:
             self.send_coded(self.bad_gzip(self.DISK_V1), "application/octet-stream")
 
     # Pass 2 switches to a coding we have no decoder for.
     def route_upcodec_unsup(self):
-        if self.upcodec_pass() == 1:
+        if self.refetch_pass() == 1:
             self.send_coded(self.gzipped(self.UNSUP_V1), "text/html")
         else:
             self.send_coded(self.UNSUP_V1, "text/html", coding="compress")
 
     def route_upcodec_fresh(self):
-        pass1 = self.upcodec_pass() == 1
+        pass1 = self.refetch_pass() == 1
         body = b"<html><body><p>FRESH-V%d</p></body></html>" % (1 if pass1 else 2)
         self.send_coded(self.gzipped(body), "text/html")
 
     # Same, direct-to-disk: the update pass decodes, so the temp is renamed over
     # an existing mirror file.
     def route_upcodec_freshdisk(self):
-        pass1 = self.upcodec_pass() == 1
+        pass1 = self.refetch_pass() == 1
         body = b"FRESHDISK-V%d\n" % (1 if pass1 else 2) + b"\x03\x02\x01\xfe" * 8192
         self.send_coded(self.gzipped(body), "application/octet-stream")
 
+    # #562: pass 1 mirrors fully; pass 2 (--update) declares the full
+    # Content-Length but delivers half then closes, so httrack refuses the partial.
+    PAGE_V1 = b"<html><body><p>MIRRORED-PAGE-V1</p></body></html>"
+    BIN_V1 = b"MIRRORED-BIN-V1\n" + b"\x00\x01\x02\xff" * 8192
+
+    def route_uptrunc_index(self):
+        self.send_html(
+            '\t<a href="page.html">page</a>\n'
+            '\t<a href="file.bin">file</a>\n'
+            '\t<a href="stay.html">stay</a>\n'
+        )
+
+    def send_truncated(self, body, content_type):
+        self.send_response(200)
+        self.send_header("Content-Type", content_type)
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        if self.command == "HEAD":
+            return
+        try:
+            self.wfile.write(body[: len(body) // 2])  # short, then close
+            self.wfile.flush()
+        except OSError:
+            pass
+
+    def route_uptrunc_page(self):
+        if self.refetch_pass() == 1:
+            self.send_raw(self.PAGE_V1, "text/html")
+        else:
+            self.send_truncated(self.PAGE_V1, "text/html")
+
+    def route_uptrunc_file(self):
+        if self.refetch_pass() == 1:
+            self.send_raw(self.BIN_V1, "application/octet-stream")
+        else:
+            self.send_truncated(self.BIN_V1, "application/octet-stream")
+
+    # Control: fully served both passes, so a normal --update still lands.
+    def route_uptrunc_stay(self):
+        v = 1 if self.refetch_pass() == 1 else 2
+        self.send_raw(b"<html><body><p>STAY-V%d</p></body></html>" % v, "text/html")
+
     # Echo what httrack advertised, so a crawl can assert the header.
     def route_codec_ae(self):
         self.send_raw(
@@ -1170,6 +1215,28 @@ class Handler(SimpleHTTPRequestHandler):
         if self.command != "HEAD":
             self.wfile.write(body)
 
+    def route_chunked_index(self):
+        self.send_html('\t<a href="page.html">chunked</a>\n')
+
+    def route_chunked_page(self):
+        # Transfer-Encoding: chunked over many small chunks: drives the engine's
+        # chunk automaton (htsback.c). The mirrored file must equal the joined
+        # chunk bodies, so the 2GB in-RAM cap doesn't fire on ordinary traffic.
+        blob = big_html("chunked", "<p>" + "chunk-body " * 300 + "</p>")
+        self.protocol_version = "HTTP/1.1"
+        self.send_response(200)
+        self.send_header("Content-Type", "text/html; charset=utf-8")
+        self.send_header("Transfer-Encoding", "chunked")
+        self.send_header("Connection", "close")
+        self.end_headers()
+        if self.command == "HEAD":
+            return
+        step = 64
+        for off in range(0, len(blob), step):
+            piece = blob[off : off + step]
+            self.wfile.write(b"%X\r\n" % len(piece) + piece + b"\r\n")
+        self.wfile.write(b"0\r\n\r\n")
+
     # Content-Disposition naming: the attachment filename replaces the
     # URL-derived name; path components in it are stripped (RFC 2616).
     CDISPO_NAMES = {
@@ -1472,6 +1539,10 @@ class Handler(SimpleHTTPRequestHandler):
         "/upcodec/unsup.html": route_upcodec_unsup,
         "/upcodec/fresh.html": route_upcodec_fresh,
         "/upcodec/freshdisk.bin": route_upcodec_freshdisk,
+        "/uptrunc/index.html": route_uptrunc_index,
+        "/uptrunc/page.html": route_uptrunc_page,
+        "/uptrunc/file.bin": route_uptrunc_file,
+        "/uptrunc/stay.html": route_uptrunc_stay,
         "/types/index.html": route_types_index,
         "/types/control.php": route_types,
         "/types/photo.png": route_types,
@@ -1505,6 +1576,8 @@ class Handler(SimpleHTTPRequestHandler):
         "/crange206mem/blob.bin": route_crange206mem,
         "/size/index.html": route_size_index,
         "/size/oversize.bin": route_size_oversize,
+        "/chunked/index.html": route_chunked_index,
+        "/chunked/page.html": route_chunked_page,
         "/errpage/index.html": route_errpage_index,
         "/errpage/good.html": route_errpage_good,
         "/errpage/missing.html": route_errpage_missing,
@@ -1817,7 +1890,8 @@ def main():
         httpd.socket = ctx.wrap_socket(httpd.socket, server_side=True)
 
     port = httpd.socket.getsockname()[1]
-    # The launcher reads this line to discover the ephemeral port.
+    # Keep the port line the launcher parses LF: Windows would emit \r\n.
+    sys.stdout.reconfigure(newline="\n")
     print(f"PORT {port}", flush=True)
 
     try:

tests/proxy-https-server.py

@@ -141,6 +141,8 @@ def main():
         open(os.path.join(logdir, name), "w").close()
     origin_port = start_origin(certfile, logdir)
     proxy_port = start_proxy(logdir, mode)
+    # Keep the port lines the caller parses LF: Windows would emit \r\n.
+    sys.stdout.reconfigure(newline="\n")
     print("ORIGIN %d" % origin_port, flush=True)
     print("PROXY %d" % proxy_port, flush=True)
     print("ready", flush=True)

tests/socks5-server.py

@@ -217,6 +217,8 @@ def main():
     tls_port = start_origin(logdir, certfile)
     http_port = start_origin(logdir, None)
     socks_port = start_socks(logdir, mode)
+    # Keep the port lines the caller parses LF: Windows would emit \r\n.
+    sys.stdout.reconfigure(newline="\n")
     print("TLS %d" % tls_port, flush=True)
     print("HTTP %d" % http_port, flush=True)
     print("SOCKS %d" % socks_port, flush=True)

tests/testlib.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+#
+# Helpers shared by the crawl tests. Sourced, not run.
+
+# Python 3 interpreter, or empty: Windows only installs python.exe, and a bare
+# "python" may be 2.x or the Store stub.
+find_python() {
+    local py
+    for py in "${PYTHON:-}" python3 python; do
+        test -n "$py" || continue
+        "$py" -c 'import sys; sys.exit(sys.version_info[0] != 3)' 2>/dev/null || continue
+        printf '%s\n' "$py"
+        return 0
+    done
+    return 1
+}
+
+# Native form of a path: a non-MSYS binary cannot resolve Git Bash's /d/a/... ones.
+nativepath() {
+    if is_windows && command -v cygpath >/dev/null 2>&1; then
+        cygpath -m "$1"
+    else
+        printf '%s\n' "$1"
+    fi
+}
+
+is_windows() {
+    case "$(uname -s)" in
+    MINGW* | MSYS* | CYGWIN*) return 0 ;;
+    *) return 1 ;;
+    esac
+}
+
+# Stop a backgrounded server and reap it; MSYS cannot signal a native python.exe,
+# so only -9 lands. Every step is "|| true": callers run under set -e, and reaping
+# a server we just signalled makes wait return 143.
+stop_server() {
+    test -n "${1:-}" || return 0
+    kill "$1" 2>/dev/null || true
+    if is_windows; then
+        kill -9 "$1" 2>/dev/null || true
+    fi
+    wait "$1" 2>/dev/null || true
+    return 0
+}