A failed re-fetch overwrote the mirrored file with the aborted read's debris (#763)

* A failed re-fetch overwrote the mirrored file with the aborted read's debris

A transfer that dies before a complete response has no body, yet the save path
still consulted r.adr, which at that point holds whatever the aborted header
read left behind: raw status-line bytes, or an empty buffer that truncated the
file to zero on macOS. Require a successful transfer, as the empty-body half of
the condition already did.

Closes #748

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

* tests: assert the failed re-fetch keeps its bytes on every platform

Test 93 filtered reset.bin out of its bucket lists because a connection killed
before the status line surfaced differently per platform. It no longer does, so
assert the resource like any other: unchanged, with the bytes pass 1 mirrored.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

* tests: make the re-fetch assertions catch a crawl that never re-fetched

The new test passed with no second pass at all, so a regression that stopped
re-fetching would have looked green. Assert the failure the fixture provokes,
give stay.bin a fresh pass-2 body so a fix that stopped overwriting anything
fails, and compare reset.bin by checksum rather than by length.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

* tests: assert the retry exhaustion, not the per-platform failure message

The message a cut connection produces depends on whether any bytes arrived, so
matching it would fail on a runner that sees none.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

---------

Signed-off-by: Xavier Roche <roche@httrack.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

.github/workflows/ci.yml

@@ -46,10 +46,32 @@ jobs:
       - name: Configure
         run: |
           set -euo pipefail
-          # Regenerate from configure.ac/Makefile.am to validate them; the
-          # committed generated files already let a plain checkout build.
+          # Regenerate: configure and the Makefile.in's are not tracked.
           autoreconf -fi
+          # Disabling zlib must fail here rather than at link with a pile of
+          # undefined minizip references (#735). Both spellings, so a rewrite
+          # cannot keep one and lose the other. Probed out-of-tree to leave
+          # nothing behind.
+          nozlib="$RUNNER_TEMP/nozlib"
+          for arg in --without-zlib --with-zlib=no; do
+            rm -rf "$nozlib" && mkdir -p "$nozlib"
+            if (cd "$nozlib" && "$GITHUB_WORKSPACE/configure" "$arg" >out.log 2>&1); then
+              echo "::error::configure $arg succeeded; it must be rejected"
+              exit 1
+            fi
+            # ... and for the stated reason, not an unrelated configure failure.
+            grep -q "zlib cannot be disabled" "$nozlib/out.log" \
+              || { cat "$nozlib/out.log"; exit 1; }
+          done
           ./configure
+          # Same dead end from the compile side. The bare compile is the
+          # control: without it a broken probe would pass vacuously.
+          hdr='#include "htsglobal.h"'
+          echo "$hdr" | $CC -I. -Isrc -fsyntax-only -xc -
+          if echo "$hdr" | $CC -DHTS_USEZLIB=0 -I. -Isrc -fsyntax-only -xc - 2>/dev/null; then
+            echo "::error::-DHTS_USEZLIB=0 compiled; htsglobal.h must reject it"
+            exit 1
+          fi
           # a missing decoder would silently drop the coding from Accept-Encoding
           grep -q "define HTS_USEBROTLI 1" config.h
           grep -q "define HTS_USEZSTD 1" config.h

configure.ac

@@ -175,7 +175,7 @@ AX_CHECK_ALIGNED_ACCESS_REQUIRED
 # check for various headers
 AC_CHECK_HEADERS([execinfo.h sys/ioctl.h])
 
-### zlib
+### zlib (mandatory)
 CHECK_ZLIB()
 
 ### brotli and zstd content codings (optional)

fuzz/Makefile.am

@@ -2,7 +2,7 @@
 if FUZZERS
 noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
 	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx \
-	fuzz-htsparse fuzz-singlefile
+	fuzz-htsparse fuzz-singlefile fuzz-sitemap
 endif
 
 AM_CPPFLAGS = \
@@ -28,6 +28,7 @@ fuzz_header_SOURCES = fuzz-header.c fuzz.h
 fuzz_cachendx_SOURCES = fuzz-cachendx.c fuzz.h
 fuzz_htsparse_SOURCES = fuzz-htsparse.c fuzz.h
 fuzz_singlefile_SOURCES = fuzz-singlefile.c fuzz.h
+fuzz_sitemap_SOURCES = fuzz-sitemap.c fuzz.h
 
 # List corpus files explicitly: automake does not expand EXTRA_DIST globs.
 EXTRA_DIST = README.md run-fuzzers.sh \
@@ -52,4 +53,6 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/singlefile/img-src.html corpus/singlefile/link-rel.html \
 	corpus/singlefile/style-block.html corpus/singlefile/style-attr.html \
 	corpus/singlefile/srcset.html corpus/singlefile/rawtext.html \
-	corpus/singlefile/malformed.html corpus/singlefile/many-attrs.html
+	corpus/singlefile/malformed.html corpus/singlefile/many-attrs.html \
+	corpus/sitemap/urlset.xml corpus/sitemap/sitemapindex.xml \
+	corpus/sitemap/truncated.xml corpus/sitemap/urlset.xml.gz

fuzz/corpus/sitemap/sitemapindex.xml

@@ -0,0 +1 @@
+<sitemapindex><sitemap><loc>http://h.test/s2.xml.gz</loc></sitemap></sitemapindex>

fuzz/corpus/sitemap/truncated.xml

@@ -0,0 +1 @@
+<urlset><loc>http://h.test/x

fuzz/corpus/sitemap/urlset.xml

@@ -0,0 +1 @@
+
<?xml version="1.0"?><urlset><url><loc>http://h.test/a.html</loc></url><url><loc>https://h.test/b?x=1&amp;y=2</loc></url></urlset>

fuzz/fuzz-sitemap.c

@@ -0,0 +1,60 @@
+/* ------------------------------------------------------------ */
+/*
+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/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* Fuzz the sitemap <loc> scanner (htssitemap.c): raw XML, gzip-framed bodies
+   and truncated streams all arrive here straight off the network. */
+#include "fuzz.h"
+#include "htssitemap.h"
+
+static hts_boolean sm_count(void *arg, const char *url) {
+  int *const n = (int *) arg;
+
+  (void) url;
+  (*n)++;
+  return HTS_TRUE;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
+  static const int caps[] = {0, 1, 16, HTS_SITEMAP_MAX_URLS_DOC};
+  hts_boolean is_index;
+  char *body;
+  int n = 0, cap;
+
+  if (size == 0)
+    return 0;
+  cap = caps[data[0] % (sizeof(caps) / sizeof(caps[0]))];
+  data++, size--;
+  /* A heap copy of exactly `size` bytes: the scanner must never rely on a
+     terminator, and ASan turns any overread into a report. */
+  body = malloct(size != 0 ? size : 1);
+  memcpy(body, data, size);
+
+  (void) hts_sitemap_scan(body, size, cap, &is_index, sm_count, &n);
+
+  freet(body);
+  return 0;
+}

html/cmdguide.html

@@ -163,8 +163,26 @@ the index" problems disappear.</p>
   <tr><td><tt>--near (-n)</tt></td><td>Also fetch non-HTML files "near" a followed link, such as an image linked from a page you kept but hosted elsewhere.</td></tr>
   <tr><td><tt>--ext-depth (-%e)</tt></td><td>How many levels of external links to follow once the crawl leaves your scope (default 0).</td></tr>
   <tr><td><tt>--test (-t)</tt></td><td>Also HEAD-test links that fall outside the scope, which are normally refused, without downloading them: a way to see what scope is excluding.</td></tr>
+  <tr><td><tt>--sitemap (-%m), --sitemap-url URL (-%mu)</tt></td><td>Also take start URLs from the site's sitemap, for pages nothing links to. Off by default.</td></tr>
 </table>
 
+<p>Link-following only finds what something links to. Anything a site publishes
+solely in its sitemap is invisible to HTTrack unless you ask for it.
+<tt>--sitemap</tt> reads the start host's <tt>robots.txt</tt> for
+<tt>Sitemap:</tt> lines and falls back to <tt>/sitemap.xml</tt>;
+<tt>--sitemap-url</tt> names one directly. Nested <tt>sitemapindex</tt> files
+and gzipped <tt>.xml.gz</tt> sitemaps are followed. The URLs found become start
+URLs with the full depth budget, but they still go through your filters and
+scope rules, so a sitemap cannot widen a crawl you deliberately narrowed. It is
+off by default because a sitemap can list thousands of pages nothing links
+to.</p>
+
+<p>One surprise worth knowing: a sitemap you name with <tt>--sitemap-url</tt>,
+and one the site itself declares in <tt>robots.txt</tt>, are fetched even when
+<tt>robots.txt</tt> disallows that path, because naming or declaring a sitemap
+is an invitation to read it. Only the guessed <tt>/sitemap.xml</tt> obeys a
+<tt>Disallow</tt>. The URLs listed inside are gated normally either way.</p>
+
 <p>The single most common surprise is "only the home page came down." That is
 usually not a scope option at all: it is an off-host redirect. A start URL of
 <tt>http://example.com/</tt> that redirects to <tt>https://www.example.com/</tt>

html/httrack.man.html

@@ -87,8 +87,8 @@ offline browser : copy websites to a local directory</p>
 --host-control[=N]</b> ] [ <b>-%P,
 --extended-parsing[=N]</b> ] [ <b>-n, --near</b> ] [ <b>-t,
 --test</b> ] [ <b>-%L, --list</b> ] [ <b>-%S, --urllist</b>
-] [ <b>-NN, --structure[=N]</b> ] [ <b>-%N,
---delayed-type-check</b> ] [ <b>-%D,
+] [ <b>-%m, --sitemap</b> ] [ <b>-NN, --structure[=N]</b> ]
+[ <b>-%N, --delayed-type-check</b> ] [ <b>-%D,
 --cached-delayed-type-check</b> ] [ <b>-%M, --mime-html</b>
 ] [ <b>-%Z, --single-file</b> ] [ <b>-LN,
 --long-names[=N]</b> ] [ <b>-KN, --keep-links[=N]</b> ] [
@@ -577,6 +577,22 @@ URL per line) (--list &lt;param&gt;)</p></td></tr>
 
 <p>&lt;file&gt; add all scan rules located in this text
 file (one scan rule per line) (--urllist &lt;param&gt;)</p></td></tr>
+<tr valign="top" align="left">
+<td width="9%"></td>
+<td width="4%">
+
+
+<p>-%m</p></td>
+<td width="5%"></td>
+<td width="82%">
+
+
+<p>seed the crawl from the site&rsquo;s sitemap (robots.txt
+Sitemap:, then /sitemap.xml); --sitemap-url URL names one
+explicitly. A sitemap you name, or one the site declares, is
+fetched even under robots.txt Disallow; only the guessed
+/sitemap.xml obeys it. The URLs found still pass every
+filter and scope rule (--sitemap)</p></td></tr>
 </table>
 
 <h3>Build options:

html/server/option8.html

@@ -108,6 +108,7 @@ ${do:end-if}
 <input type="hidden" name="keepqueryorder" value="">
 <input type="hidden" name="toler" value="">
 <input type="hidden" name="http10" value="">
+<input type="hidden" name="sitemap" value="">
 
 <input type="checkbox" name="cookies" ${checked:cookies}
 			title='${html:LANG_I1b}' onMouseOver="info('${html:LANG_I1b}'); return true" onMouseOut="info('&nbsp;'); return true"
@@ -143,6 +144,17 @@ ${listid:robots:LISTDEF_8}
 </select>
 <br><br>
 
+<input type="checkbox" name="sitemap" ${checked:sitemap}
+			title='${html:LANG_SITEMAPTIP}' onMouseOver="info('${html:LANG_SITEMAPTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+> ${LANG_SITEMAP}
+<br><br>
+
+${LANG_SITEMAPURL}
+<input name="sitemapurl" value="${sitemapurl}" size="40"
+			title='${html:LANG_SITEMAPURLTIP}' onMouseOver="info('${html:LANG_SITEMAPURLTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
+>
+<br><br>
+
 <input type="checkbox" name="updhack" ${checked:updhack}
 			title='${html:LANG_I1k}' onMouseOver="info('${html:LANG_I1k}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I62b}

html/server/step2.html

@@ -141,6 +141,8 @@ ${do:copy:KeepSlashes:keepslashes}
 ${do:copy:KeepQueryOrder:keepqueryorder}
 ${do:copy:StripQuery:stripquery}
 ${do:copy:StoreAllInCache:cache2}
+${do:copy:Sitemap:sitemap}
+${do:copy:SitemapUrl:sitemapurl}
 ${do:copy:Warc:warc}
 ${do:copy:WarcFile:warcfile}
 ${do:copy:Changes:changes}

html/server/step4.html

@@ -188,6 +188,8 @@ ${/* -m<n> resets the html limit, so the bare form must precede the -m,<n> one *
 	${test:toler:--tolerant}
 	${test:http10:--http-10}
 	${test:cache2:--store-all-in-cache}
+	${test:sitemap:--sitemap}
+	${test:sitemapurl:--sitemap-url "}${html:sitemapurl}${test:sitemapurl:"}
 	${test:warc:--warc}
 	${test:warcfile:--warc-file "}${arg:warcfile}${test:warcfile:"}
 	${test:changes:--changes}
@@ -243,6 +245,8 @@ KeepSlashes=${ztest:keepslashes:0:1}
 KeepQueryOrder=${ztest:keepqueryorder:0:1}
 StripQuery=${stripquery}
 StoreAllInCache=${ztest:cache2:0:1}
+Sitemap=${ztest:sitemap:0:1}
+SitemapUrl=${sitemapurl}
 Warc=${ztest:warc:0:1}
 WarcFile=${warcfile}
 Changes=${ztest:changes:0:1}

lang.def

@@ -1054,3 +1054,11 @@ LANG_SINGLEFILEMAX
 Largest inlined asset (bytes):
 LANG_SINGLEFILEMAXTIP
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
+LANG_SITEMAP
+Seed the crawl from the site's sitemap
+LANG_SITEMAPTIP
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+LANG_SITEMAPURL
+Sitemap address:
+LANG_SITEMAPURLTIP
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.

lang/Bulgarian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Íàé-ãîëÿì âãðàäåí ðåñóðñ (áàéòîâå):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Ðåñóðñ íàä òîçè ðàçìåð çàïàçâà îáèêíîâåíà âðúçêà; îñòàâåòå ïðàçíî çà ñòîéíîñòòà ïî ïîäðàçáèðàíå îò 10485760 áàéòà.
+Seed the crawl from the site's sitemap
+Çàïî÷âàíå íà îáõîæäàíåòî îò êàðòàòà íà ñàéòà
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ïðî÷èòàíå íà êàðòàòà íà ñàéòà (ðåäîâåòå Sitemap: â robots.txt, ñëåä òîâà /sitemap.xml) è äîáàâÿíå íà âñåêè ïîñî÷åí URL àäðåñ êàòî íà÷àëåí.
+Sitemap address:
+Àäðåñ íà êàðòàòà íà ñàéòà:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Àäðåñ íà êàðòà íà ñàéòà, êîÿòî äà áúäå ïðî÷åòåíà âìåñòî ñîíäèðàíå íà ñàéòà; îñòàâåòå ïðàçíî, çà äà ñå ïðîâåðè robots.txt, ñëåä òîâà /sitemap.xml.

lang/Castellano.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Tamaño máximo del recurso incrustado (bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Un recurso mayor que este tamaño conserva un enlace normal; déjelo vacío para el valor predeterminado de 10485760 bytes.
+Seed the crawl from the site's sitemap
+Iniciar el rastreo desde el mapa del sitio
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Leer el mapa del sitio (líneas Sitemap: de robots.txt, luego /sitemap.xml) y añadir como dirección inicial cada URL que incluya.
+Sitemap address:
+Dirección del mapa del sitio:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Dirección de un mapa del sitio que leer en lugar de sondear el sitio; déjelo vacío para sondear robots.txt y luego /sitemap.xml.

lang/Cesky.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Nejvìtší vložený zdroj (bajty):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Zdroj vìtší než tato velikost si ponechá bìžný odkaz; ponechte prázdné pro výchozí hodnotu 10485760 bajtù.
+Seed the crawl from the site's sitemap
+Zahájit procházení z mapy webu
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Naèíst mapu webu (øádky Sitemap: v souboru robots.txt, poté /sitemap.xml) a pøidat každou uvedenou adresu URL jako výchozí.
+Sitemap address:
+Adresa mapy webu:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresa mapy webu, která se má naèíst místo zjiš<69>ování na webu; ponechte prázdné pro zjištìní z robots.txt a poté /sitemap.xml.

lang/Chinese-BIG5.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 內嵌資源大小上限（位元組）：
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 超過此大小的資源會保留一般連結；留空則使用預設的 10485760 位元組。
+Seed the crawl from the site's sitemap
+從網站的 Sitemap 開始擷取
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+讀取網站的 Sitemap（robots.txt 中的 Sitemap: 行，然後 /sitemap.xml），並將其中列出的每個網址加入為起始網址。
+Sitemap address:
+Sitemap 位址：
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+要讀取的 Sitemap 位址，用來取代自動探測；留空則先探測 robots.txt 再探測 /sitemap.xml。

lang/Chinese-Simplified.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 内嵌资源大小上限（字节）：
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 超过此大小的资源会保留普通链接；留空则使用默认的 10485760 字节。
+Seed the crawl from the site's sitemap
+从网站的 Sitemap 开始抓取
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+读取网站的 Sitemap（robots.txt 中的 Sitemap: 行，然后 /sitemap.xml），并将其中列出的每个网址添加为起始网址。
+Sitemap address:
+Sitemap 地址：
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+要读取的 Sitemap 地址，用来代替自动探测；留空则先探测 robots.txt 再探测 /sitemap.xml。

lang/Croatian.txt

@@ -978,3 +978,11 @@ Largest inlined asset (bytes):
 Najveæi ugraðeni resurs (bajtovi):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Resurs veæi od ove velièine zadr¾ava obiènu poveznicu; ostavite prazno za zadanih 10485760 bajtova.
+Seed the crawl from the site's sitemap
+Pokreni pretra¾ivanje iz karte web-mjesta
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Proèitaj kartu web-mjesta (retke Sitemap: iz robots.txt, zatim /sitemap.xml) i dodaj svaki navedeni URL kao poèetnu adresu.
+Sitemap address:
+Adresa karte web-mjesta:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresa karte web-mjesta koju treba proèitati umjesto ispitivanja web-mjesta; ostavite prazno za ispitivanje robots.txt pa /sitemap.xml.

lang/Dansk.txt

@@ -1024,3 +1024,11 @@ Largest inlined asset (bytes):
 Største indlejrede ressource (byte):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 En ressource over denne størrelse beholder et almindeligt link; lad feltet stå tomt for standardværdien på 10485760 byte.
+Seed the crawl from the site's sitemap
+Start gennemgangen fra webstedets sitemap
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Læs webstedets sitemap (Sitemap:-linjer i robots.txt, derefter /sitemap.xml) og tilføj hver angivet URL som startadresse.
+Sitemap address:
+Sitemap-adresse:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adressen på et sitemap, der skal læses i stedet for at undersøge webstedet; lad feltet stå tomt for at undersøge robots.txt og derefter /sitemap.xml.

lang/Deutsch.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Größte eingebettete Ressource (Bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Eine Ressource über dieser Größe behält einen gewöhnlichen Link; leer lassen für den Standardwert von 10485760 Bytes.
+Seed the crawl from the site's sitemap
+Erfassung mit der Sitemap der Website beginnen
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Die Sitemap der Website lesen (Sitemap:-Zeilen in robots.txt, dann /sitemap.xml) und jede dort aufgeführte URL als Startadresse hinzufügen.
+Sitemap address:
+Sitemap-Adresse:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresse einer Sitemap, die anstelle der Suche auf der Website gelesen wird; leer lassen, um robots.txt und dann /sitemap.xml zu prüfen.

lang/Eesti.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Suurim manustatud ressurss (baiti):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Sellest suurem ressurss säilitab tavalise lingi; jäta tühjaks vaikeväärtuse 10485760 baiti jaoks.
+Seed the crawl from the site's sitemap
+Alusta kogumist saidi saidikaardist
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Loe saidi saidikaarti (robots.txt-i Sitemap:-read, seejärel /sitemap.xml) ja lisa iga seal loetletud URL alguslingina.
+Sitemap address:
+Saidikaardi aadress:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Saidikaardi aadress, mida lugeda saidi sondeerimise asemel; jäta tühjaks, et kontrollida robots.txt-i ja seejärel /sitemap.xml-i.

lang/English.txt

@@ -1024,3 +1024,11 @@ Largest inlined asset (bytes):
 Largest inlined asset (bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
+Seed the crawl from the site's sitemap
+Seed the crawl from the site's sitemap
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Sitemap address:
+Sitemap address:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.

lang/Finnish.txt

@@ -978,3 +978,11 @@ Largest inlined asset (bytes):
 Suurin upotettu resurssi (tavua):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Tätä suurempi resurssi säilyttää tavallisen linkin; jätä tyhjäksi, jolloin käytetään oletusarvoa 10485760 tavua.
+Seed the crawl from the site's sitemap
+Aloita haku sivuston sivukartasta
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Lue sivuston sivukartta (robots.txt-tiedoston Sitemap:-rivit, sitten /sitemap.xml) ja lisää jokainen siinä lueteltu URL-osoite aloitusosoitteeksi.
+Sitemap address:
+Sivukartan osoite:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Luettavan sivukartan osoite sivuston luotaamisen sijaan; jätä tyhjäksi, jolloin tarkistetaan robots.txt ja sitten /sitemap.xml.

lang/Francais.txt

@@ -1024,3 +1024,11 @@ Largest inlined asset (bytes):
 Taille maximale d'une ressource intégrée (octets) :
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Au-delà de cette taille, la ressource reste un lien ordinaire ; laissez vide pour la valeur par défaut de 10485760 octets.
+Seed the crawl from the site's sitemap
+Partir du plan de site (sitemap)
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Lire le plan de site (lignes Sitemap: de robots.txt, puis /sitemap.xml) et ajouter chaque URL listée comme adresse de départ.
+Sitemap address:
+Adresse du plan de site :
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresse d'un plan de site à lire au lieu de sonder le site ; laissez vide pour sonder robots.txt puis /sitemap.xml.

lang/Greek.txt

@@ -978,3 +978,11 @@ Largest inlined asset (bytes):
 Μέγιστος ενσωματωμένος πόρος (byte):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Πόρος μεγαλύτερος από αυτό το μέγεθος διατηρεί κανονικό σύνδεσμο. Αφήστε το κενό για την προεπιλογή των 10485760 byte.
+Seed the crawl from the site's sitemap
+Έναρξη της ανίχνευσης από τον χάρτη του ιστότοπου
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ανάγνωση του χάρτη του ιστότοπου (γραμμές Sitemap: στο robots.txt, έπειτα /sitemap.xml) και προσθήκη κάθε διεύθυνσης URL που περιέχει ως αρχικής διεύθυνσης.
+Sitemap address:
+Διεύθυνση χάρτη ιστότοπου:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Διεύθυνση χάρτη ιστότοπου προς ανάγνωση αντί για αναζήτηση στον ιστότοπο. Αφήστε το κενό για έλεγχο του robots.txt και έπειτα του /sitemap.xml.

lang/Italiano.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Dimensione massima della risorsa incorporata (byte):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Una risorsa oltre questa dimensione mantiene un collegamento normale; lasciare vuoto per il valore predefinito di 10485760 byte.
+Seed the crawl from the site's sitemap
+Avvia la scansione dalla mappa del sito
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Legge la mappa del sito (righe Sitemap: in robots.txt, poi /sitemap.xml) e aggiunge come indirizzo iniziale ogni URL elencato.
+Sitemap address:
+Indirizzo della mappa del sito:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Indirizzo di una mappa del sito da leggere invece di sondare il sito; lasciare vuoto per sondare robots.txt e poi /sitemap.xml.

lang/Japanese.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 埋め込む最大サイズ (バイト):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 このサイズを超えるリソースは通常のリンクのままになります。空欄にすると既定値の 10485760 バイトになります。
+Seed the crawl from the site's sitemap
+サイトマップからミラーリングを開始する
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+サイトマップ (robots.txt の Sitemap: 行、次に /sitemap.xml) を読み込み、記載されているすべての URL を開始アドレスとして追加します。
+Sitemap address:
+サイトマップのアドレス:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+サイトを探索する代わりに読み込むサイトマップのアドレス。空欄にすると robots.txt、次に /sitemap.xml を探索します。

lang/Macedonian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 ½ÐøÓÞÛÕÜ ÒÓàÐÔÕÝ àÕáãàá (ÑÐøâØ):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 ÀÕáãàá ßÞÓÞÛÕÜ ÞÔ ÞÒÐÐ ÓÞÛÕÜØÝÐ ×ÐÔàÖãÒÐ ÞÑØçÝÐ ÒàáÚÐ; ÞáâÐÒÕâÕ ßàÐ×ÝÞ ×Ð áâÐÝÔÐàÔÝØâÕ 10485760 ÑÐøâØ.
+Seed the crawl from the site's sitemap
+·ÐßÞçÝØ ÓÞ ßàÕÑÐàãÒÐúÕâÞ ÞÔ ÚÐàâÐâÐ ÝÐ áÐøâÞâ
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+¿àÞçØâÐø øÐ ÚÐàâÐâÐ ÝÐ áÐøâÞâ (àÕÔÞÒØâÕ Sitemap: ÒÞ robots.txt, ßÞâÞÐ /sitemap.xml) Ø ÔÞÔÐø øÐ áÕÚÞøÐ ÝÐÒÕÔÕÝÐ URL ÐÔàÕáÐ ÚÐÚÞ ßÞçÕâÝÐ.
+Sitemap address:
+°ÔàÕáÐ ÝÐ ÚÐàâÐâÐ ÝÐ áÐøâÞâ:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+°ÔàÕáÐ ÝÐ ÚÐàâÐ ÝÐ áÐøâÞâ èâÞ âàÕÑÐ ÔÐ áÕ ßàÞçØâÐ ÝÐÜÕáâÞ ØáßØâãÒÐúÕ ÝÐ áÐøâÞâ; ÞáâÐÒÕâÕ ßàÐ×ÝÞ ×Ð ÔÐ áÕ ØáßØâÐ robots.txt, ßÐ /sitemap.xml.

lang/Magyar.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Legnagyobb beágyazott erõforrás (bájt):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Az ennél nagyobb erõforrás közönséges hivatkozás marad; hagyja üresen a 10485760 bájtos alapértelmezéshez.
+Seed the crawl from the site's sitemap
+A letöltés indítása a webhely webhelytérképérõl
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+A webhely webhelytérképének beolvasása (a robots.txt Sitemap: sorai, majd a /sitemap.xml), és a benne felsorolt összes URL felvétele kiindulási címként.
+Sitemap address:
+Webhelytérkép címe:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+A webhely vizsgálata helyett beolvasandó webhelytérkép címe; hagyja üresen a robots.txt, majd a /sitemap.xml vizsgálatához.

lang/Nederlands.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Grootste ingesloten bron (bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Een bron boven deze grootte houdt een gewone koppeling; laat leeg voor de standaardwaarde van 10485760 bytes.
+Seed the crawl from the site's sitemap
+De crawl starten vanaf de sitemap van de site
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+De sitemap van de site lezen (Sitemap:-regels in robots.txt, daarna /sitemap.xml) en elke vermelde URL als startadres toevoegen.
+Sitemap address:
+Sitemap-adres:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adres van een sitemap die gelezen moet worden in plaats van de site te onderzoeken; laat leeg om robots.txt en daarna /sitemap.xml te controleren.

lang/Norsk.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Største innebygde ressurs (byte):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 En ressurs over denne størrelsen beholder en vanlig lenke; la feltet stå tomt for standardverdien på 10485760 byte.
+Seed the crawl from the site's sitemap
+Start gjennomgangen fra nettstedets nettstedskart
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Les nettstedets nettstedskart (Sitemap:-linjer i robots.txt, deretter /sitemap.xml) og legg til hver oppført URL som startadresse.
+Sitemap address:
+Adresse til nettstedskart:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adressen til et nettstedskart som skal leses i stedet for å undersøke nettstedet; la feltet stå tomt for å undersøke robots.txt og deretter /sitemap.xml.

lang/Polski.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Najwiêkszy osadzony zasób (bajty):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Zasób wiêkszy ni¿ ten rozmiar zachowuje zwyk³y odno¶nik; pozostaw puste, aby u¿yæ domy¶lnych 10485760 bajtów.
+Seed the crawl from the site's sitemap
+Rozpocznij pobieranie od mapy witryny
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Odczytaj mapê witryny (wiersze Sitemap: w pliku robots.txt, nastêpnie /sitemap.xml) i dodaj ka¿dy wymieniony adres URL jako adres pocz±tkowy.
+Sitemap address:
+Adres mapy witryny:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adres mapy witryny do odczytania zamiast sondowania witryny; pozostaw puste, aby sprawdziæ robots.txt, a nastêpnie /sitemap.xml.

lang/Portugues-Brasil.txt

@@ -1024,3 +1024,11 @@ Largest inlined asset (bytes):
 Maior recurso incorporado (bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Um recurso acima desse tamanho mantém um link comum; deixe em branco para o padrão de 10485760 bytes.
+Seed the crawl from the site's sitemap
+Iniciar a captura pelo mapa do site
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ler o mapa do site (linhas Sitemap: do robots.txt, depois /sitemap.xml) e adicionar como endereço inicial cada URL nele listada.
+Sitemap address:
+Endereço do mapa do site:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Endereço de um mapa do site a ser lido em vez de sondar o site; deixe em branco para sondar robots.txt e depois /sitemap.xml.

lang/Portugues.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Maior recurso incorporado (bytes):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Um recurso acima deste tamanho mantém uma ligação normal; deixe em branco para o valor predefinido de 10485760 bytes.
+Seed the crawl from the site's sitemap
+Iniciar a recolha pelo mapa do site
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ler o mapa do site (linhas Sitemap: do robots.txt, depois /sitemap.xml) e adicionar como endereço inicial cada URL nele listado.
+Sitemap address:
+Endereço do mapa do site:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Endereço de um mapa do site a ler em vez de sondar o site; deixe em branco para sondar robots.txt e depois /sitemap.xml.

lang/Romanian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Cea mai mare resursa încorporata (octeti):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 O resursa mai mare decât aceasta dimensiune pastreaza o legatura obisnuita; lasati gol pentru valoarea implicita de 10485760 de octeti.
+Seed the crawl from the site's sitemap
+Porneste explorarea de la harta sitului
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Citeste harta sitului (liniile Sitemap: din robots.txt, apoi /sitemap.xml) si adauga fiecare URL listat ca adresa de pornire.
+Sitemap address:
+Adresa hartii sitului:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresa unei harti a sitului care sa fie citita în loc de sondarea sitului; lasati gol pentru a sonda robots.txt, apoi /sitemap.xml.

lang/Russian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Íàèáîëüøèé âñòðàèâàåìûé ðåñóðñ (áàéòû):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Ðåñóðñ áîëüøå ýòîãî ðàçìåðà ñîõðàíÿåò îáû÷íóþ ññûëêó; îñòàâüòå ïóñòûì äëÿ çíà÷åíèÿ ïî óìîë÷àíèþ 10485760 áàéò.
+Seed the crawl from the site's sitemap
+Íà÷èíàòü îáõîä ñ êàðòû ñàéòà
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ïðî÷èòàòü êàðòó ñàéòà (ñòðîêè Sitemap: â robots.txt, çàòåì /sitemap.xml) è äîáàâèòü êàæäûé óêàçàííûé â íåé URL êàê íà÷àëüíûé àäðåñ.
+Sitemap address:
+Àäðåñ êàðòû ñàéòà:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Àäðåñ êàðòû ñàéòà, êîòîðóþ íóæíî ïðî÷èòàòü âìåñòî îïðîñà ñàéòà; îñòàâüòå ïóñòûì, ÷òîáû ïðîâåðèòü robots.txt, çàòåì /sitemap.xml.

lang/Slovak.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Najväè¹í vlo¾ený zdroj (bajty):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Zdroj väè¹í ne¾ táto veµkos» si ponechá be¾ný odkaz; ponechajte prázdne pre predvolených 10485760 bajtov.
+Seed the crawl from the site's sitemap
+Zaèa» prehliadanie z mapy stránok
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Naèíta» mapu stránok (riadky Sitemap: v súbore robots.txt, potom /sitemap.xml) a prida» ka¾dú uvedenú adresu URL ako poèiatoènú.
+Sitemap address:
+Adresa mapy stránok:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adresa mapy stránok, ktorá sa má naèíta» namiesto zis»ovania na stránke; ponechajte prázdne na zistenie z robots.txt a potom /sitemap.xml.

lang/Slovenian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Najvecji vgrajeni vir (bajti):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Vir, vecji od te velikosti, ohrani obicajno povezavo; pustite prazno za privzetih 10485760 bajtov.
+Seed the crawl from the site's sitemap
+Zacni zajem z zemljevidom spletnega mesta
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Preberi zemljevid spletnega mesta (vrstice Sitemap: v robots.txt, nato /sitemap.xml) in dodaj vsak navedeni URL kot zacetni naslov.
+Sitemap address:
+Naslov zemljevida spletnega mesta:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Naslov zemljevida spletnega mesta, ki naj se prebere namesto preverjanja mesta; pustite prazno za preverjanje robots.txt in nato /sitemap.xml.

lang/Svenska.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Största inbäddade resurs (byte):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 En resurs över den här storleken behåller en vanlig länk; lämna tomt för standardvärdet 10485760 byte.
+Seed the crawl from the site's sitemap
+Starta insamlingen från webbplatsens webbplatskarta
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Läs webbplatsens webbplatskarta (Sitemap:-rader i robots.txt, sedan /sitemap.xml) och lägg till varje angiven URL som startadress.
+Sitemap address:
+Webbplatskartans adress:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Adress till en webbplatskarta som ska läsas i stället för att söka på webbplatsen; lämna tomt för att kontrollera robots.txt och sedan /sitemap.xml.

lang/Turkish.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 En büyük gömülü kaynak (bayt):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Bu boyutun üzerindeki bir kaynak sýradan baðlantýsýný korur; 10485760 baytlýk varsayýlan için boþ býrakýn.
+Seed the crawl from the site's sitemap
+Taramayý sitenin site haritasýndan baþlat
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Sitenin site haritasýný oku (robots.txt içindeki Sitemap: satýrlarý, ardýndan /sitemap.xml) ve listelenen her URL'yi baþlangýç adresi olarak ekle.
+Sitemap address:
+Site haritasý adresi:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Siteyi yoklamak yerine okunacak site haritasýnýn adresi; robots.txt ve ardýndan /sitemap.xml yoklamasý için boþ býrakýn.

lang/Ukrainian.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Íàéá³ëüøèé âáóäîâàíèé ðåñóðñ (áàéòè):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Ðåñóðñ, á³ëüøèé çà öåé ðîçì³ð, çáåð³ãຠçâè÷àéíå ïîñèëàííÿ; çàëèøòå ïîðîæí³ì äëÿ òèïîâîãî çíà÷åííÿ 10485760 áàéò³â.
+Seed the crawl from the site's sitemap
+Ïî÷èíàòè îáõ³ä ç êàðòè ñàéòó
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Ïðî÷èòàòè êàðòó ñàéòó (ðÿäêè Sitemap: ó robots.txt, ïîò³ì /sitemap.xml) ³ äîäàòè êîæíó âêàçàíó â í³é URL-àäðåñó ÿê ïî÷àòêîâó.
+Sitemap address:
+Àäðåñà êàðòè ñàéòó:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Àäðåñà êàðòè ñàéòó, ÿêó ñë³ä ïðî÷èòàòè çàì³ñòü îïèòóâàííÿ ñàéòó; çàëèøòå ïîðîæí³ì, ùîá ïåðåâ³ðèòè robots.txt, à ïîò³ì /sitemap.xml.

lang/Uzbek.txt

@@ -976,3 +976,11 @@ Largest inlined asset (bytes):
 Eng katta joylangan resurs (bayt):
 An asset above this size keeps an ordinary link; leave blank for the 10485760-byte default.
 Bu o’lchamdan katta resurs oddiy havolani saqlab qoladi; standart 10485760 bayt uchun bo’sh qoldiring.
+Seed the crawl from the site's sitemap
+Yig’ishni saytning sayt xaritasidan boshlash
+Read the site's sitemap (robots.txt Sitemap: lines, then /sitemap.xml) and add every URL it lists as a start URL.
+Saytning sayt xaritasini o’qish (robots.txt dagi Sitemap: qatorlari, so’ngra /sitemap.xml) va unda ko’rsatilgan har bir URL manzilni boshlang’ich manzil sifatida qo’shish.
+Sitemap address:
+Sayt xaritasi manzili:
+Address of a sitemap to read instead of probing the site; leave blank to probe robots.txt then /sitemap.xml.
+Saytni tekshirish o’rniga o’qiladigan sayt xaritasi manzili; robots.txt, so’ngra /sitemap.xml ni tekshirish uchun bo’sh qoldiring.

m4/check_zlib.m4

@@ -1,82 +1,33 @@
 dnl @synopsis CHECK_ZLIB()
 dnl
-dnl This macro searches for an installed zlib library. If nothing
-dnl was specified when calling configure, it searches first in /usr/local
-dnl and then in /usr. If the --with-zlib=DIR is specified, it will try
-dnl to find it in DIR/include/zlib.h and DIR/lib/libz.a. If --without-zlib
-dnl is specified, the library is not searched at all.
-dnl
-dnl If either the header file (zlib.h) or the library (libz) is not
-dnl found, the configuration exits on error, asking for a valid
-dnl zlib installation directory or --without-zlib.
-dnl
-dnl The macro defines the symbol HAVE_LIBZ if the library is found. You should
-dnl use autoheader to include a definition for this symbol in a config.h
-dnl file. Sample usage in a C/C++ source is as follows:
-dnl
-dnl   #ifdef HAVE_LIBZ
-dnl   #include <zlib.h>
-dnl   #endif /* HAVE_LIBZ */
-dnl
-dnl @version $Id$
-dnl @author Loic Dachary <loic@senga.org>
+dnl Look for zlib. It is a hard requirement, not an option: the cache and the
+dnl WARC output are zip/gzip containers, and the bundled minizip calls zlib
+dnl directly. --with-zlib=DIR points at a non-standard prefix.
 dnl
+dnl Adds -lz to LIBS and defines HAVE_LIBZ.
 
-AC_DEFUN([CHECK_ZLIB],
-#
-# Handle user hints
-#
-[AC_MSG_CHECKING(if zlib is wanted)
-AC_ARG_WITH(zlib,
-[  --with-zlib=DIR root directory path of zlib installation [defaults to
-                    /usr/local or /usr if not found in /usr/local]
-  --without-zlib to disable zlib usage completely],
-[if test "$withval" != no ; then
-  AC_MSG_RESULT(yes)
-  ZLIB_HOME="$withval"
-else
-  AC_MSG_RESULT(no)
-fi], [
-AC_MSG_RESULT(yes)
-ZLIB_HOME=/usr/local
-if test ! -f "${ZLIB_HOME}/include/zlib.h"
-then
-        ZLIB_HOME=/usr
+AC_DEFUN([CHECK_ZLIB], [
+AC_ARG_WITH([zlib],
+	[AS_HELP_STRING([--with-zlib=DIR],[root directory of the zlib installation])],
+	[zlib_want=$withval], [zlib_want=yes])
+if test "$zlib_want" = "no"; then
+	AC_MSG_ERROR([zlib cannot be disabled: the cache and the WARC output are zip/gzip containers, and the bundled minizip calls zlib directly])
 fi
-])
-
-#
-# Locate zlib, if wanted
-#
-if test -n "${ZLIB_HOME}"
-then
-        ZLIB_OLD_LDFLAGS=$LDFLAGS
-        ZLIB_OLD_CPPFLAGS=$LDFLAGS
-        LDFLAGS="$LDFLAGS -L${ZLIB_HOME}/lib"
-        CPPFLAGS="$CPPFLAGS -I${ZLIB_HOME}/include"
-        AC_LANG_SAVE
-        AC_LANG_C
-        AC_CHECK_LIB(z, inflateEnd, [zlib_cv_libz=yes], [zlib_cv_libz=no])
-        AC_CHECK_HEADER(zlib.h, [zlib_cv_zlib_h=yes], [zlib_cv_zlib_h=no])
-        AC_LANG_RESTORE
-        if test "$zlib_cv_libz" = "yes" -a "$zlib_cv_zlib_h" = "yes"
-        then
-                #
-                # If both library and header were found, use them
-                #
-                AC_CHECK_LIB(z, inflateEnd)
-                AC_MSG_CHECKING(zlib in ${ZLIB_HOME})
-                AC_MSG_RESULT(ok)
-        else
-                #
-                # If either header or library was not found, revert and bomb
-                #
-                AC_MSG_CHECKING(zlib in ${ZLIB_HOME})
-                LDFLAGS="$ZLIB_OLD_LDFLAGS"
-                CPPFLAGS="$ZLIB_OLD_CPPFLAGS"
-                AC_MSG_RESULT(failed)
-                AC_MSG_ERROR(either specify a valid zlib installation with --with-zlib=DIR or disable zlib usage with --without-zlib)
-        fi
+if test "$zlib_want" != "yes"; then
+	# An explicit prefix is authoritative: if the header is not under it,
+	# error rather than silently pick a system copy.
+	if test ! -f "$zlib_want/include/zlib.h"; then
+		AC_MSG_ERROR([zlib requested at $zlib_want but $zlib_want/include/zlib.h is missing])
+	fi
+	CPPFLAGS="$CPPFLAGS -I$zlib_want/include"
+	LDFLAGS="$LDFLAGS -L$zlib_want/lib"
+elif test -f /usr/local/include/zlib.h; then
+	# Where the BSD ports tree lands zlib, and not always searched by default.
+	CPPFLAGS="$CPPFLAGS -I/usr/local/include"
+	LDFLAGS="$LDFLAGS -L/usr/local/lib"
 fi
-
+AC_CHECK_HEADER([zlib.h], [],
+	[AC_MSG_ERROR([zlib.h not found; install the zlib development files or pass --with-zlib=DIR])])
+AC_CHECK_LIB([z], [inflateEnd], [],
+	[AC_MSG_ERROR([libz not found; install the zlib development files or pass --with-zlib=DIR])])
 ])

man/httrack.1

@@ -36,6 +36,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-t, \-\-test\fR ]
 [ \fB\-%L, \-\-list\fR ]
 [ \fB\-%S, \-\-urllist\fR ]
+[ \fB\-%m, \-\-sitemap\fR ]
 [ \fB\-NN, \-\-structure[=N]\fR ]
 [ \fB\-%N, \-\-delayed\-type\-check\fR ]
 [ \fB\-%D, \-\-cached\-delayed\-type\-check\fR ]
@@ -189,6 +190,8 @@ test all URLs (even forbidden ones) (\-\-test)
 <file> add all URL located in this text file (one URL per line) (\-\-list <param>)
 .IP \-%S
 <file> add all scan rules located in this text file (one scan rule per line) (\-\-urllist <param>)
+.IP \-%m
+seed the crawl from the site's sitemap (robots.txt Sitemap:, then /sitemap.xml); \-\-sitemap\-url URL names one explicitly. A sitemap you name, or one the site declares, is fetched even under robots.txt Disallow; only the guessed /sitemap.xml obeys it. The URLs found still pass every filter and scope rule (\-\-sitemap)
 .SS Build options:
 .IP \-NN
 structure type (0 *original structure, 1+: see below) (\-\-structure[=N])

src/Makefile.am

@@ -66,7 +66,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htscmdline.c htshelp.c htslib.c htsurlport.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
 	htsalias.c htsthread.c htsindex.c htsbauth.c \
-	htsmd5.c htscodec.c htswarc.c htschanges.c htssinglefile.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
+	htsmd5.c htscodec.c htswarc.c htschanges.c htssinglefile.c htssitemap.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
 	htsmodules.c htscharset.c punycode.c htsencoding.c htssniff.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
@@ -77,7 +77,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htshelp.h htsindex.h htslib.h htsurlport.h htsmd5.h \
 	htsmodules.h htsname.h htsnet.h htssniff.h \
 	htsopt.h htsrobots.h htsthread.h  \
-	htstools.h htswizard.h htswrap.h htscodec.h htswarc.h htschanges.h htssinglefile.h htsproxy.h htszlib.h  \
+	htstools.h htswizard.h htswrap.h htscodec.h htswarc.h htschanges.h htssinglefile.h htssitemap.h htsproxy.h htszlib.h  \
 	htsstrings.h htsarrays.h httrack-library.h \
 	htscharset.h punycode.h htsencoding.h \
 	htsentities.h htsentities.sh htsbasiccharsets.sh htscodepages.h \

src/htsalias.c

@@ -116,6 +116,10 @@ const char *hts_optalias[][4] = {
    "load extra cookies from a Netscape cookies.txt"},
   {"changes", "-%d", "single",
    "write hts-changes.json: what this crawl changed vs. the previous mirror"},
+  {"sitemap", "-%m", "single",
+   "seed the crawl from the start host's sitemap (robots.txt, then "
+   "/sitemap.xml)"},
+  {"sitemap-url", "-%mu", "param1", "seed the crawl from this sitemap URL"},
   {"warc", "-%r", "single", "write an ISO-28500 WARC/1.1 archive of the crawl"},
   {"warc-file", "-%rf", "param1", "write a WARC archive to the given base name"},
   {"warc-max-size", "-%rs", "param1",

src/htsback.c

@@ -48,11 +48,6 @@ Please visit our Website: http://www.httrack.com
 #include "htsftp.h"
 #include "htscodec.h"
 #include "htsproxy.h"
-#if HTS_USEZLIB
-#include "htszlib.h"
-#else
-#error HTS_USEZLIB not defined
-#endif
 
 #ifdef _WIN32
 #ifndef __cplusplus
@@ -590,14 +585,6 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
   return 0;
 }
 
-/* Move src onto dst; RENAME does not clobber an existing target on Windows. */
-static hts_boolean replace_file(const char *src, const char *dst) {
-  if (RENAME(src, dst) == 0)
-    return HTS_TRUE;
-  (void) UNLINK(dst);
-  return RENAME(src, dst) == 0 ? HTS_TRUE : HTS_FALSE;
-}
-
 /* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
    existing file moved the good copy to back->tmpfile before truncating url_sav.
    commit keeps the new file and drops the backup; else restore it so an aborted
@@ -615,7 +602,7 @@ static void back_finalize_backup(httrackp *opt, lien_back *const back,
     }
     /* On failure keep the backup: an orphaned temp beats losing the good copy.
      */
-    if (!replace_file(back->tmpfile, back->url_sav))
+    if (!hts_rename_over(back->tmpfile, back->url_sav))
       hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
                     "could not restore %s; previous copy kept as %s",
                     back->url_sav, back->tmpfile);
@@ -746,7 +733,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                                  "Read error when decompressing");
                     }
                     UNLINK(unpacked);
-                  } else if (replace_file(unpacked, back[p].url_sav)) {
+                  } else if (hts_rename_over(unpacked, back[p].url_sav)) {
                     /* The temp bypassed filecreate(), which is what chmods. */
 #ifndef _WIN32
                     chmod(back[p].url_sav, HTS_ACCESS_FILE);

src/htscodec.c

@@ -72,7 +72,7 @@ hts_codec hts_codec_parse(const char *encoding) {
     return HTS_CODEC_IDENTITY;
   if (strfield2(encoding, "gzip") || strfield2(encoding, "x-gzip") ||
       strfield2(encoding, "deflate") || strfield2(encoding, "x-deflate"))
-    return HTS_USEZLIB ? HTS_CODEC_DEFLATE : HTS_CODEC_UNSUPPORTED;
+    return HTS_CODEC_DEFLATE;
   if (strfield2(encoding, "br"))
     return HTS_USEBROTLI ? HTS_CODEC_BROTLI : HTS_CODEC_UNSUPPORTED;
   if (strfield2(encoding, "zstd"))
@@ -98,16 +98,11 @@ hts_codec hts_codec_parse(const char *encoding) {
 const char *hts_acceptencoding(hts_boolean compressible, hts_boolean secure) {
   if (!compressible)
     return "identity";
-#if HTS_USEZLIB
   /* br and zstd over TLS only, as browsers do: a cleartext intermediary that
      rewrites a coding it can not read would corrupt the mirror. */
   if (secure)
     return "gzip, deflate" HTS_AE_BROTLI HTS_AE_ZSTD ", identity;q=0.9";
   return "gzip, deflate, identity;q=0.9";
-#else
-  (void) secure;
-  return "identity";
-#endif
 }
 
 hts_boolean hts_codec_is_archive_ext(hts_codec codec, const char *ext) {
@@ -300,11 +295,7 @@ int hts_codec_unpack(hts_codec codec, const char *filename,
     return -1;
   switch (codec) {
   case HTS_CODEC_DEFLATE:
-#if HTS_USEZLIB
     return hts_zunpack(filename, newfile);
-#else
-    return -1;
-#endif
   case HTS_CODEC_BROTLI:
   case HTS_CODEC_ZSTD:
     break;
@@ -348,10 +339,8 @@ size_t hts_codec_head(hts_codec codec, const void *in, size_t in_len, void *out,
   if (in == NULL || in_len == 0 || out == NULL || out_len == 0)
     return 0;
   switch (codec) {
-#if HTS_USEZLIB
   case HTS_CODEC_DEFLATE:
     return hts_zhead(in, in_len, out, out_len);
-#endif
 #if HTS_USEBROTLI
   case HTS_CODEC_BROTLI:
     return codec_head_brotli(in, in_len, out, out_len);

src/htscore.c

@@ -39,6 +39,7 @@ Please visit our Website: http://www.httrack.com
 
 /* File defs */
 #include "htscore.h"
+#include "htssitemap.h"
 #include "htswarc.h"
 #include "htschanges.h"
 #include "htssinglefile.h"
@@ -949,6 +950,22 @@ int httpmirror(char *url1, httrackp * opt) {
     heap_top()->premier = heap_top_index();        // premier lien, objet-père=objet              
     heap_top()->precedent = heap_top_index();      // lien précédent
 
+    /* --sitemap: queue the sitemap probe just after the seeds, so its URLs are
+       injected before the crawl gets far. */
+    hts_sitemap_free(opt); /* an earlier mirror may have left a doc list */
+    if (opt->sitemap || StringNotEmpty(opt->sitemap_url)) {
+      char BIGSTK first[HTS_URLMAXSIZE * 2];
+      const char *const eol = strchr(primary, '\n');
+      const size_t len = eol != NULL ? (size_t) (eol - primary) : 0;
+
+      first[0] = '\0';
+      if (len > 0 && len < sizeof(first)) {
+        memcpy(first, primary, len);
+        first[len] = '\0';
+      }
+      hts_sitemap_seed(opt, first);
+    }
+
     // Initialiser cache
     {
       opt->state._hts_in_html_parsing = 4;
@@ -1593,11 +1610,21 @@ int httpmirror(char *url1, httrackp * opt) {
         stre.maketrack_fp = maketrack_fp;
 
         /* Parse */
-        if (hts_mirror_check_moved(&str, &stre) != 0) {
-          XH_uninit;
-          return -1;
-        }
+        {
+          const int nlinks = opt->lien_tot;
 
+          if (hts_mirror_check_moved(&str, &stre) != 0) {
+            XH_uninit;
+            return -1;
+          }
+          /* A redirect re-queues the target as a fresh link; without carrying
+             the marking over, a moved sitemap is fetched and then ignored. */
+          if (opt->sitemap_state != NULL && opt->lien_tot > nlinks &&
+              hts_sitemap_pending(opt, urladr(), urlfil())) {
+            hts_sitemap_redirect(opt, urladr(), urlfil(), heap_top()->adr,
+                                 heap_top()->fil);
+          }
+        }
       }
 
     }                           // if !error
@@ -1615,6 +1642,29 @@ int httpmirror(char *url1, httrackp * opt) {
       /* Load file and decode if necessary, after redirect check. */
       LOAD_IN_MEMORY_IF_NECESSARY();
 
+      /* Sitemap document: turn its <loc> URLs into top-level seeds. They go
+         through htsAddLink, so the wizard's filters and scope rules decide, and
+         this link's max depth leaves them the full budget. */
+      if (opt->sitemap_state != NULL &&
+          hts_sitemap_pending(opt, urladr(), urlfil())) {
+        htsmoduleStruct BIGSTK smstr;
+        int smptr = ptr;
+
+        memset(&smstr, 0, sizeof(smstr));
+        smstr.opt = opt;
+        smstr.sback = sback;
+        smstr.cache = &cache;
+        smstr.hashptr = hashptr;
+        smstr.numero_passe = numero_passe;
+        smstr.ptr_ = &smptr; /* scratch: the ingester retargets the wizard */
+        smstr.addLink = htsAddLink;
+        smstr.url_host = urladr();
+        smstr.url_file = urlfil();
+        smstr.mime = r.contenttype;
+        hts_sitemap_ingest(opt, &smstr, urladr(), urlfil(), r.adr,
+                           r.adr != NULL && r.size > 0 ? (size_t) r.size : 0);
+      }
+
       // ------------------------------------------------------
       // ok, fichier chargé localement
       // ------------------------------------------------------
@@ -1825,6 +1875,9 @@ int httpmirror(char *url1, httrackp * opt) {
 
         if (strnotempty(savename()) == 0) {       // pas de chemin de sauvegarde
           if (strcmp(urlfil(), "/robots.txt") == 0) {     // robots.txt
+            char BIGSTK sitemaps[8192];
+
+            sitemaps[0] = '\0';
             if (r.adr) {
               char BIGSTK infobuff[8192];
 #ifdef IGNORE_RESTRICTIVE_ROBOTS
@@ -1836,7 +1889,8 @@ int httpmirror(char *url1, httrackp * opt) {
 #endif
 
               robots_parse(&robots, urladr(), r.adr, r.size, infobuff,
-                           sizeof(infobuff), keep_root);
+                           sizeof(infobuff), keep_root, sitemaps,
+                           sizeof(sitemaps));
               if (strnotempty(infobuff)) {
                 hts_log_print(opt, LOG_INFO,
                               "Note: robots.txt forbidden links for %s are: %s",
@@ -1846,6 +1900,10 @@ int httpmirror(char *url1, httrackp * opt) {
                               urladr(), infobuff);
               }
             }
+            /* After robots_parse, so the rules this very body carries already
+               gate the sitemap fetch. Runs even on a failed probe, which is
+               what falls back to the well-known location. */
+            hts_sitemap_robots(opt, urladr(), sitemaps);
           }
         } else if (r.is_write) {        // déja sauvé sur disque
           /*
@@ -1922,10 +1980,9 @@ int httpmirror(char *url1, httrackp * opt) {
           }
 
           // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!
-          // An empty body must not overwrite the file when the transfer failed
-          // (statuscode <= 0, e.g. an -M hard-stop): it would truncate a good
-          // copy to 0 (#77 follow-up).
-          if (r.adr != NULL || (r.size == 0 && r.statuscode > 0)) {
+          // A failed transfer has no body: r.adr holds debris from the aborted
+          // read, which would destroy the copy being re-fetched (#748).
+          if (r.statuscode > 0 && (r.adr != NULL || r.size == 0)) {
             file_notify(opt, urladr(), urlfil(), savename(), 1, 1, r.notmodified);
             if (filesave(opt, r.adr, (int) r.size, savename(), urladr(), urlfil()) !=
                 0) {
@@ -2286,6 +2343,7 @@ int httpmirror(char *url1, httrackp * opt) {
   usercommand(opt, 0, NULL, NULL, NULL, NULL);
   warc_close_opt(opt);
   hts_changes_close_opt(opt);
+  hts_sitemap_free(opt);
 
   // désallocation mémoire & buffers
   XH_uninit;
@@ -2634,7 +2692,11 @@ HTSEXT_API int structcheck(const char *path) {
       if (!S_ISDIR(st.st_mode)) {
 #if HTS_REMOVE_ANNOYING_INDEX
         if (S_ISREG(st.st_mode)) {      /* Regular file in place ; move it and create directory */
-          sprintf(tmpbuf, "%s.txt", file);
+          /* bounded here, not by the path-length guard far above */
+          if (!sprintfbuff(tmpbuf, "%s.txt", file)) {
+            errno = ENAMETOOLONG;
+            return -1;
+          }
           if (rename(file, tmpbuf) != 0) {      /* Can't rename regular file */
             return -1;
           }
@@ -2742,7 +2804,11 @@ HTSEXT_API int structcheck_utf8(const char *path) {
       if (!S_ISDIR(st.st_mode)) {
 #if HTS_REMOVE_ANNOYING_INDEX
         if (S_ISREG(st.st_mode)) {      /* Regular file in place ; move it and create directory */
-          sprintf(tmpbuf, "%s.txt", file);
+          /* bounded here, not by the path-length guard far above */
+          if (!sprintfbuff(tmpbuf, "%s.txt", file)) {
+            errno = ENAMETOOLONG;
+            return -1;
+          }
           if (RENAME(file, tmpbuf) != 0) {      /* Can't rename regular file */
             return -1;
           }
@@ -3684,6 +3750,10 @@ HTSEXT_API int copy_htsopt(const httrackp * from, httrackp * to) {
   to->single_file = from->single_file;
   if (from->single_file_max_size > 0)
     to->single_file_max_size = from->single_file_max_size;
+  if (from->sitemap)
+    to->sitemap = from->sitemap;
+  if (StringNotEmpty(from->sitemap_url))
+    StringCopyS(to->sitemap_url, from->sitemap_url);
 
   if (from->pause_max_ms > 0) {
     to->pause_min_ms = from->pause_min_ms;
@@ -3758,11 +3828,12 @@ int htsAddLink(htsmoduleStruct * str, char *link) {
         strcpybuff(codebase, heap(ptr)->fil);
       else
         strcpybuff(codebase, heap(heap(ptr)->precedent)->fil);
-      a = codebase + strlen(codebase) - 1;
+      // empty codebase has no last char; codebase-1 would underflow
+      a = codebase[0] != '\0' ? codebase + strlen(codebase) - 1 : codebase;
       while((*a) && (*a != '/') && (a > codebase))
         a--;
       if (*a == '/')
-        *(a + 1) = '\0';        // couper
+        *(a + 1) = '\0';        // cut
     } else {                    // couper http:// éventuel
       if (strfield(codebase, "http://")) {
         char BIGSTK tempo[HTS_URLMAXSIZE * 2];

src/htscoremain.c

@@ -1833,6 +1833,26 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                   }
                 }
                 break;
+              case 'm': // sitemap / sitemap-url: seed the crawl from sitemaps
+                if (*(com + 1) == 'u') { // --sitemap-url URL: explicit sitemap
+                  com++;
+                  if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
+                    HTS_PANIC_PRINTF(
+                        "Option sitemap-url needs a blank space and a URL");
+                    htsmain_free();
+                    return -1;
+                  }
+                  na++;
+                  if (strlen(argv[na]) >= HTS_URLMAXSIZE) {
+                    HTS_PANIC_PRINTF("Sitemap URL too long");
+                    htsmain_free();
+                    return -1;
+                  }
+                  StringCopy(opt->sitemap_url, argv[na]);
+                } else { // --sitemap: robots.txt probe, then /sitemap.xml
+                  opt->sitemap = HTS_TRUE;
+                }
+                break;
               case 'Y': // why: explain the filter verdict for a URL, no crawl
                 if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
                   HTS_PANIC_PRINTF("Option why needs a blank space and a URL");

src/htsglobal.h

@@ -138,10 +138,11 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DOSNAME 0
 #endif
 
-// utiliser zlib?
+// zlib is mandatory: the cache is a zip and minizip calls it regardless
 #ifndef HTS_USEZLIB
-// autoload
 #define HTS_USEZLIB 1
+#elif !HTS_USEZLIB
+#error HTS_USEZLIB=0 is not a supported configuration
 #endif
 
 // brotli and zstd content codings; off unless the build opted in (configure,

src/htshelp.c

@@ -526,6 +526,11 @@ void help(const char *app, int more) {
     (" %L <file> add all URL located in this text file (one URL per line)");
   infomsg
     (" %S <file> add all scan rules located in this text file (one scan rule per line)");
+  infomsg(" %m  seed the crawl from the site's sitemap (robots.txt Sitemap:, "
+          "then /sitemap.xml); --sitemap-url URL names one explicitly. A "
+          "sitemap you name, or one the site declares, is fetched even under "
+          "robots.txt Disallow; only the guessed /sitemap.xml obeys it. The "
+          "URLs found still pass every filter and scope rule");
   infomsg("");
   infomsg("Build options:");
   infomsg("  NN structure type (0 *original structure, 1+: see below)");

src/htslib.c

@@ -36,6 +36,7 @@ Please visit our Website: http://www.httrack.com
 // Fichier librairie .c
 
 #include "htscore.h"
+#include "htssitemap.h"
 #include "htswarc.h"
 #include "htschanges.h"
 #include "htssinglefile.h"
@@ -1130,12 +1131,10 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
 
       // Compression accepted ?
       if (retour->req.http11) {
-        hts_boolean compressible = HTS_FALSE;
+        hts_boolean compressible =
+            (!retour->req.range_used && !retour->req.nocompression);
         hts_boolean secure = HTS_FALSE;
 
-#if HTS_USEZLIB
-        compressible = (!retour->req.range_used && !retour->req.nocompression);
-#endif
 #if HTS_USEOPENSSL
         secure = retour->ssl ? HTS_TRUE : HTS_FALSE;
 #endif
@@ -6030,6 +6029,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   StringCopy(opt->strip_query, "");
   StringCopy(opt->cookies_file, "");
   StringCopy(opt->warc_file, "");
+  StringCopy(opt->sitemap_url, "");
   opt->warc_max_size = 0; /* no rotation unless --warc-max-size sets it */
   opt->changes = HTS_FALSE;
   opt->changes_state = NULL;
@@ -6187,6 +6187,8 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->cookies_file);
     StringFree(opt->why_url);
     StringFree(opt->warc_file);
+    StringFree(opt->sitemap_url);
+    hts_sitemap_free(opt); /* backstop: httpmirror's early-return paths */
 
     hts_changes_free_opt(opt);
 

src/htsname.c

@@ -43,9 +43,7 @@ Please visit our Website: http://www.httrack.com
 #include "htsencoding.h"
 #include "htssniff.h"
 #include "htscodec.h"
-#if HTS_USEZLIB
 #include "htszlib.h"
-#endif
 #include <ctype.h>
 #include <limits.h>
 

src/htsopt.h

@@ -557,6 +557,13 @@ struct httrackp {
   LLint single_file_max_size; /**< --single-file-max-size: per-asset cap in
                                    bytes; a bigger asset stays a link.
                                    Tail: ABI */
+  hts_boolean sitemap; /**< --sitemap: probe the start host's robots.txt for
+                            Sitemap: lines, else /sitemap.xml. Tail: ABI */
+  String sitemap_url;  /**< --sitemap-url: sitemap to ingest. Tail: ABI */
+  /* Live state, not an option: copy_htsopt must leave it alone. It sits here
+     rather than in htsoptstate because that struct is embedded by value, so
+     growing it would shift every httrackp field declared after it. */
+  void *sitemap_state; /**< hts_sitemap_state*, or NULL. Tail: ABI */
 };
 
 /* Running statistics for a mirror. */

src/htsrobots.c

@@ -147,7 +147,8 @@ static void robots_blob_add(char *blob, size_t blobsize, char marker,
 
 void robots_parse(robots_wizard *robots, const char *adr, const char *body,
                   size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow) {
+                  hts_boolean keep_root_disallow, char *sitemaps,
+                  size_t sitemapsize) {
   size_t bptr = 0;
   int record = 0;
   char BIGSTK line[1024];
@@ -156,6 +157,8 @@ void robots_parse(robots_wizard *robots, const char *adr, const char *body,
   blob[0] = '\0';
   if (info != NULL && infosize > 0)
     info[0] = '\0';
+  if (sitemaps != NULL && sitemapsize > 0)
+    sitemaps[0] = '\0';
 #if DEBUG_ROBOTS
   printf("robots.txt dump:\n%s\n", body);
 #endif
@@ -172,7 +175,19 @@ void robots_parse(robots_wizard *robots, const char *adr, const char *body,
       line[llen - 1] = '\0';
       llen--;
     }
-    if (strfield(line, "user-agent:")) {
+    if (sitemaps != NULL && strfield(line, "sitemap:")) {
+      // group-independent record (RFC 9309): collected whatever the group
+      char *a = line + 8;
+
+      while (is_realspace(*a))
+        a++;
+      /* A line at the buffer limit was truncated: a half URL is not one. */
+      if (strnotempty(a) && strlen(line) < sizeof(line) - 3 &&
+          strlen(a) + 2 < sitemapsize - strlen(sitemaps)) {
+        strlcatbuff(sitemaps, a, sitemapsize);
+        strlcatbuff(sitemaps, "\n", sitemapsize);
+      }
+    } else if (strfield(line, "user-agent:")) {
       char *a = line + 11;
 
       while (is_realspace(*a))

src/htsrobots.h

@@ -56,10 +56,12 @@ int checkrobots(robots_wizard * robots, const char *adr, const char *fil);
 void checkrobots_free(robots_wizard * robots);
 int checkrobots_set(robots_wizard * robots, const char *adr, const char *data);
 /* Parse robots.txt `body` for `adr`, storing the HTTrack group's rules; `info`
-   gets a disallow summary, `keep_root_disallow` FALSE drops "Disallow: /". */
+   gets a disallow summary, `keep_root_disallow` FALSE drops "Disallow: /", and
+   `sitemaps` (optional) collects the Sitemap: URLs, one per line. */
 void robots_parse(robots_wizard *robots, const char *adr, const char *body,
                   size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow);
+                  hts_boolean keep_root_disallow, char *sitemaps,
+                  size_t sitemapsize);
 #endif
 
 #endif

src/htsselftest.c

@@ -43,6 +43,7 @@ Please visit our Website: http://www.httrack.com
 
 #include "htsglobal.h"
 #include "htscore.h"
+#include "htsmodules.h"
 #include "htsback.h"
 #include "htsdefines.h"
 #include "htslib.h"
@@ -59,12 +60,11 @@ Please visit our Website: http://www.httrack.com
 #include "htssniff.h"
 #include "htscodec.h"
 #include "htsproxy.h"
+#include "htssitemap.h"
 #include "htswarc.h"
 #include "htschanges.h"
 #include "htssinglefile.h"
-#if HTS_USEZLIB
 #include "htszlib.h"
-#endif
 #if HTS_USEZSTD
 #include <zstd.h>
 #endif
@@ -1762,6 +1762,22 @@ static int st_copyopt(httrackp *opt, int argc, char **argv) {
   if (to->single_file_max_size != 4096)
     err = 1;
 
+  /* sitemap pair: the flag latches on, the URL takes the String deep copy */
+  from->sitemap = HTS_TRUE;
+  StringCopy(from->sitemap_url, "http://h.test/sitemap.xml");
+  to->sitemap = HTS_FALSE;
+  StringCopy(to->sitemap_url, "");
+  copy_htsopt(from, to);
+  if (!to->sitemap ||
+      strcmp(StringBuff(to->sitemap_url), "http://h.test/sitemap.xml") != 0)
+    err = 1;
+  from->sitemap = HTS_FALSE;
+  StringCopy(from->sitemap_url, "");
+  copy_htsopt(from, to);
+  if (!to->sitemap ||
+      strcmp(StringBuff(to->sitemap_url), "http://h.test/sitemap.xml") != 0)
+    err = 1;
+
   /* #185 pause pair: copied when enabled (max>0), the 0 sentinel skips */
   from->pause_min_ms = 5000;
   from->pause_max_ms = 10000;
@@ -2606,6 +2622,68 @@ static int st_savename(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* an empty fil started htsAddLink's codebase walk before the buffer (#730) */
+static int st_addlink(httrackp *opt, int argc, char **argv) {
+  htsmoduleStruct BIGSTK str;
+  cache_back cache;
+  struct_back *sback;
+  hash_struct hash;
+  int ptr = 0;
+  int i;
+
+  (void) argc;
+  (void) argv;
+
+  memset(&cache, 0, sizeof(cache));
+  cache.hashtable = (void *) coucal_new(0);
+  sback = back_new(opt, opt->maxsoc * 32 + 1024);
+  /* same wiring as hts_mirror (htscore.c) */
+  hash_init(opt, &hash, opt->urlhack);
+  hash.liens = (const lien_url *const *const *) &opt->liens;
+  opt->hash = &hash;
+  hts_record_init(opt);
+
+  memset(&str, 0, sizeof(str));
+  str.opt = opt;
+  str.sback = sback;
+  str.cache = &cache;
+  str.hashptr = &hash;
+  str.ptr_ = &ptr;
+  str.addLink = htsAddLink;
+
+  /* [0] is the underflow; [1] and [2] are controls that the trim is unchanged.
+     A query-only link is the one that notices the trim at all: for the others
+     ident_url_relatif() re-derives the directory from the path it is given. */
+  for (i = 0; i < 3; i++) {
+    static const char *const fil[3] = {"", "/dir/page.html", "/dir/page.html"};
+    static const char *const lnk[3] = {"sub/page.html", "sub/page.html",
+                                       "?x=1"};
+    static const char *const want[3] = {
+        "untouched", "http://www.example.com/dir/sub/page.html",
+        "http://www.example.com/dir/?x=1"};
+    char BIGSTK loc[HTS_URLMAXSIZE * 2];
+    char BIGSTK link[HTS_URLMAXSIZE];
+
+    strcpybuff(loc, "untouched");
+    strcpybuff(link, lnk[i]);
+    str.localLink = loc;
+    str.localLinkSize = (int) sizeof(loc);
+    if (!hts_record_link(opt, "www.example.com", fil[i], "", "", "", ""))
+      return 1;
+    ptr = heap_top_index();
+    str.url_host = heap(ptr)->adr;
+    str.url_file = heap(ptr)->fil;
+    assertf(htsAddLink(&str, link) == 0); /* refused by the wizard either way */
+    if (strcmp(loc, want[i]) != 0) {
+      fprintf(stderr, "addlink[%d]: got '%s' want '%s'\n", i, loc, want[i]);
+      return 1;
+    }
+  }
+
+  printf("addlink self-test OK\n");
+  return 0;
+}
+
 static int st_cache(httrackp *opt, int argc, char **argv) {
   int err;
 
@@ -3247,6 +3325,81 @@ static int st_topindex(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Build a path of exactly len chars under base; returns that length. */
+static size_t st_structcheck_longpath(char *dst, size_t dstsize,
+                                      const char *base, size_t len) {
+  size_t n = strlen(base);
+
+  assertf(len < dstsize && n + 2 <= len);
+  memmove(dst, base, n);
+  while (n < len) {
+    size_t seg = len - n - 1;
+
+    if (seg > 200) /* stay under the usual 255-byte component limit */
+      seg = len - n == 202 ? 199 : 200; /* never leave a bare separator */
+    dst[n++] = '/';
+    memset(dst + n, 'x', seg);
+    n += seg;
+  }
+  dst[n] = '\0';
+  return n;
+}
+
+/* The path guard, and the <name>.txt rename structcheck() performs when a
+   regular file sits where a directory has to go (#745). */
+static int st_structcheck(httrackp *opt, int argc, char **argv) {
+  char BIGSTK path[HTS_URLMAXSIZE * 2];
+  char BIGSTK target[HTS_URLMAXSIZE * 2];
+  FILE *fp;
+
+  (void) opt;
+  if (argc < 1) {
+    fprintf(stderr, "usage: -#test=structcheck <writable directory>\n");
+    return 1;
+  }
+
+  /* over the guard: refused before a single directory is created */
+  st_structcheck_longpath(path, sizeof(path), argv[0], HTS_URLMAXSIZE + 1);
+  errno = 0;
+  assertf(structcheck(path) == -1);
+  assertf(errno == EINVAL);
+  errno = 0;
+  assertf(structcheck_utf8(path) == -1);
+  assertf(errno == EINVAL);
+  {
+    char *const sep = strchr(path + strlen(argv[0]) + 1, '/');
+
+    assertf(sep != NULL);
+    sep[1] = '\0'; /* the outermost component it would have created */
+    assertf(!dir_exists(path));
+  }
+
+  /* a regular file where a directory belongs is renamed to <name>.txt */
+  snprintf(path, sizeof(path), "%s/sc", argv[0]);
+  fp = fopen(path, "wb");
+  assertf(fp != NULL);
+  fclose(fp);
+  snprintf(path, sizeof(path), "%s/sc/sub/", argv[0]);
+  assertf(structcheck(path) == 0);
+  assertf(dir_exists(path));
+  snprintf(target, sizeof(target), "%s/sc.txt", argv[0]);
+  assertf(fexist(target));
+
+  /* the utf-8 entry point carries the same rename */
+  snprintf(path, sizeof(path), "%s/u8", argv[0]);
+  fp = FOPEN(path, "wb");
+  assertf(fp != NULL);
+  fclose(fp);
+  snprintf(path, sizeof(path), "%s/u8/sub/", argv[0]);
+  assertf(structcheck_utf8(path) == 0);
+  assertf(dir_exists(path));
+  snprintf(target, sizeof(target), "%s/u8.txt", argv[0]);
+  assertf(fexist_utf8(target));
+
+  printf("structcheck self-test OK\n");
+  return 0;
+}
+
 /* Each inplace_escape_*() must equal escape_*() on a copy. */
 static int st_inplace_escape(httrackp *opt, int argc, char **argv) {
   /* >255 bytes forces the helper's malloct path, not the stack buffer */
@@ -3360,7 +3513,6 @@ static int st_status(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-#if HTS_USEZLIB
 /* Deflate src->path at windowBits (16+ gzip, + zlib, - raw); 0 on success. */
 static int ae_write_packed(const char *path, int windowBits,
                            const unsigned char *src, size_t len) {
@@ -3434,7 +3586,6 @@ static int ae_write_collision(const char *path, const unsigned char *src,
   freet(buf);
   return ok ? 0 : 1;
 }
-#endif
 
 /* Write src[0..len) to path as-is; 0 on success. */
 static int ae_write_raw(const char *path, const unsigned char *src,
@@ -3484,7 +3635,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
   assertf(strstr(on, "br") == NULL && strstr(on, "zstd") == NULL);
   assertf((strstr(tls, ", br") != NULL) == (HTS_USEBROTLI != 0));
   assertf((strstr(tls, "zstd") != NULL) == (HTS_USEZSTD != 0));
-#if HTS_USEZLIB
   if (argc >= 1) {
     static const int windowBits[] = {16 + MAX_WBITS, MAX_WBITS, -MAX_WBITS};
     const unsigned char small[] =
@@ -3563,10 +3713,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
     }
     freet(body);
   }
-#else
-  (void) argc;
-  (void) argv;
-#endif
   printf("acceptencoding self-test OK: %s\n", on);
   return 0;
 }
@@ -3686,7 +3832,7 @@ static int rb_decide(robots_wizard *r, const char *txt, const char *path) {
   char host[64];
 
   snprintf(host, sizeof(host), "h%d.example", n++);
-  robots_parse(r, host, txt, strlen(txt), NULL, 0, HTS_TRUE);
+  robots_parse(r, host, txt, strlen(txt), NULL, 0, HTS_TRUE, NULL, 0);
   return checkrobots(r, host, path);
 }
 
@@ -3763,6 +3909,263 @@ static int st_robots(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Collect the URLs a sitemap scan hands out. */
+typedef struct sm_collect {
+  int n;
+  char url[8][HTS_URLMAXSIZE];
+} sm_collect;
+
+static hts_boolean sm_take(void *arg, const char *url) {
+  sm_collect *const c = (sm_collect *) arg;
+
+  if (c->n < (int) (sizeof(c->url) / sizeof(c->url[0])))
+    strcpybuff(c->url[c->n], url);
+  c->n++;
+  return HTS_TRUE;
+}
+
+/* Scan `doc` off a heap buffer with no NUL terminator, so a read past the
+   declared size is an ASan error rather than a silent pass. */
+static int sm_scan(const char *doc, int maxurls, hts_boolean *is_index,
+                   sm_collect *out) {
+  const size_t len = strlen(doc);
+  char *raw = malloct(len);
+  int n;
+
+  memset(out, 0, sizeof(*out));
+  assertf(raw != NULL);
+  memcpy(raw, doc, len);
+  n = hts_sitemap_scan(raw, len, maxurls, is_index, sm_take, out);
+  freet(raw);
+  return n;
+}
+
+static int st_sitemap(httrackp *opt, int argc, char **argv) {
+  sm_collect c;
+  hts_boolean idx;
+  (void) opt;
+  (void) argc;
+  (void) argv;
+
+  /* A urlset yields its <loc> URLs, in order, unescaped. */
+  assertf(sm_scan("<?xml version=\"1.0\"?><urlset>"
+                  "<url><loc>http://h.test/a.html</loc></url>"
+                  "<url><loc>  https://h.test/b?x=1&amp;y=2\n  </loc></url>"
+                  "</urlset>",
+                  100, &idx, &c) == 2);
+  assertf(!idx);
+  assertf(strcmp(c.url[0], "http://h.test/a.html") == 0);
+  assertf(strcmp(c.url[1], "https://h.test/b?x=1&y=2") == 0);
+
+  /* A sitemapindex is flagged: its URLs are child sitemaps, not pages. */
+  assertf(sm_scan("<sitemapindex><sitemap><loc>http://h.test/s2.xml.gz</loc>"
+                  "</sitemap></sitemapindex>",
+                  100, &idx, &c) == 1);
+  assertf(idx);
+
+  /* Root element decides even when the other name appears later as text. */
+  assertf(sm_scan("<urlset><url><loc>http://h.test/a</loc></url>"
+                  "<!-- sitemapindex --></urlset>",
+                  100, &idx, &c) == 1);
+  assertf(!idx);
+
+  /* Numeric character references, decimal and hex, decode to ASCII. */
+  assertf(sm_scan("<urlset><loc>http://h.test/a&#63;b&#x3D;c</loc></urlset>",
+                  100, &idx, &c) == 1);
+  assertf(strcmp(c.url[0], "http://h.test/a?b=c") == 0);
+
+  /* A reference decoding to a control byte is dropped: the shared decoder
+     writes the real character and the URL check refuses it. A reference the
+     decoder cannot represent (&#0;) stays verbatim, like an unknown entity. */
+  assertf(sm_scan("<urlset><loc>http://h.test/a&#10;b</loc></urlset>", 100,
+                  &idx, &c) == 0);
+  assertf(sm_scan("<urlset><loc>http://h.test/a&#9;b</loc></urlset>", 100, &idx,
+                  &c) == 0);
+  assertf(sm_scan("<urlset><loc>http://h.test/a&#0;b</loc></urlset>", 100, &idx,
+                  &c) == 1);
+  assertf(strcmp(c.url[0], "http://h.test/a&#0;b") == 0);
+
+  /* A comment naming the other root element must not flip the verdict. */
+  assertf(sm_scan("<!-- <sitemapindex> --><urlset><url>"
+                  "<loc>http://h.test/p</loc></url></urlset>",
+                  100, &idx, &c) == 1);
+  assertf(!idx);
+  assertf(sm_scan("<?xml version=\"1.0\"?><!-- <urlset> -->"
+                  "<sitemapindex><loc>http://h.test/s</loc></sitemapindex>",
+                  100, &idx, &c) == 1);
+  assertf(idx);
+
+  /* <location> is not <loc>. */
+  assertf(sm_scan("<urlset><location>http://h.test/a</location></urlset>", 100,
+                  &idx, &c) == 0);
+
+  /* Rejected: relative, non-http scheme, embedded space, empty. */
+  assertf(sm_scan("<urlset><loc>/a.html</loc><loc>ftp://h.test/a</loc>"
+                  "<loc>javascript:alert(1)</loc>"
+                  "<loc>http://h.test/a b</loc><loc></loc></urlset>",
+                  100, &idx, &c) == 0);
+
+  /* The URL length bound: one under fits, exactly at it is dropped rather than
+     truncated into a different URL. */
+  {
+    char BIGSTK doc[HTS_URLMAXSIZE * 2];
+    char BIGSTK url[HTS_URLMAXSIZE + 1];
+    size_t i;
+
+    strcpybuff(url, "http://h.test/");
+    for (i = strlen(url); i < HTS_URLMAXSIZE - 1; i++)
+      url[i] = 'a';
+    url[i] = '\0';
+    snprintf(doc, sizeof(doc), "<urlset><loc>%s</loc></urlset>", url);
+    assertf(sm_scan(doc, 100, &idx, &c) == 1);
+
+    url[i] = 'a';
+    url[i + 1] = '\0';
+    snprintf(doc, sizeof(doc), "<urlset><loc>%s</loc></urlset>", url);
+    assertf(sm_scan(doc, 100, &idx, &c) == 0);
+  }
+
+  /* The URL cap stops the scan. */
+  assertf(sm_scan("<urlset><loc>http://h.test/1</loc><loc>http://h.test/2</loc>"
+                  "<loc>http://h.test/3</loc></urlset>",
+                  2, &idx, &c) == 2);
+
+  /* The per-document cap at the value the engine actually uses. */
+  {
+    const int many = HTS_SITEMAP_MAX_URLS_DOC + 10;
+    const size_t cap = (size_t) many * 40 + 32;
+    char *big = malloct(cap);
+    size_t off;
+    int i;
+
+    assertf(big != NULL);
+    off = (size_t) snprintf(big, cap, "<urlset>");
+    assertf(off < cap);
+    for (i = 0; i < many; i++) {
+      const int len =
+          snprintf(big + off, cap - off, "<loc>http://h.test/%d</loc>", i);
+
+      assertf(len > 0 && (size_t) len < cap - off);
+      off += (size_t) len;
+    }
+    memset(&c, 0, sizeof(c));
+    assertf(hts_sitemap_scan(big, off, HTS_SITEMAP_MAX_URLS_DOC, &idx, sm_take,
+                             &c) == HTS_SITEMAP_MAX_URLS_DOC);
+    /* The handler count, not just the return: a call site hardcoding a smaller
+       cap would still return its own argument. */
+    assertf(c.n == HTS_SITEMAP_MAX_URLS_DOC);
+    freet(big);
+  }
+
+  /* A highly compressible document decodes without running away: the ratio
+     budget cannot bind (deflate tops out near 1032:1), so this pins the
+     decompression path itself rather than the 64 MiB ceiling. */
+  {
+    const char *const one = "<url><loc>http://h.test/bomb</loc></url>";
+    const size_t reps = 40000;
+    size_t xlen = 8 + reps * strlen(one) + 10, i;
+    char *x = malloct(xlen + 1);
+    uLongf zlen;
+    char *z;
+    z_stream zs;
+
+    assertf(x != NULL);
+    {
+      size_t w = (size_t) snprintf(x, xlen, "<urlset>");
+      int len;
+
+      assertf(w < xlen);
+      for (i = 0; i < reps; i++) {
+        len = snprintf(x + w, xlen - w, "%s", one);
+        assertf(len > 0 && (size_t) len < xlen - w);
+        w += (size_t) len;
+      }
+      len = snprintf(x + w, xlen - w, "</urlset>");
+      assertf(len > 0 && (size_t) len < xlen - w);
+      w += (size_t) len;
+      xlen = w;
+    }
+    zlen = compressBound((uLong) xlen) + 32;
+    z = malloct((size_t) zlen);
+    assertf(z != NULL);
+    memset(&zs, 0, sizeof(zs));
+    assertf(deflateInit2(&zs, 9, Z_DEFLATED, 16 + MAX_WBITS, 8,
+                         Z_DEFAULT_STRATEGY) == Z_OK);
+    zs.next_in = (const Bytef *) x;
+    zs.avail_in = (uInt) xlen;
+    zs.next_out = (Bytef *) z;
+    zs.avail_out = (uInt) zlen;
+    assertf(deflate(&zs, Z_FINISH) == Z_STREAM_END);
+    zlen = (uLongf) zs.total_out;
+    deflateEnd(&zs);
+    /* well over the 4096:1 budget's 1 MiB floor, and far under the 64 MiB cap
+     */
+    assertf(xlen > 1024 * 1024 && (size_t) zlen < xlen / 100);
+    memset(&c, 0, sizeof(c));
+    assertf(hts_sitemap_scan(z, (size_t) zlen, 10, &idx, sm_take, &c) == 10);
+    assertf(strcmp(c.url[0], "http://h.test/bomb") == 0);
+    freet(z);
+    freet(x);
+  }
+
+  /* An unterminated <loc> at end of buffer must not read past it. */
+  assertf(sm_scan("<urlset><loc>http://h.test/a", 100, &idx, &c) == 0);
+  assertf(sm_scan("<urlset><lo", 100, &idx, &c) == 0);
+
+  /* A gzip-framed document is decompressed before scanning. */
+  {
+    const char *const xml =
+        "<urlset><url><loc>http://h.test/gz.html</loc></url></urlset>";
+    uLongf zlen = compressBound((uLong) strlen(xml)) + 32;
+    char *z = malloct((size_t) zlen);
+    z_stream zs;
+
+    assertf(z != NULL);
+    memset(&zs, 0, sizeof(zs));
+    assertf(deflateInit2(&zs, 9, Z_DEFLATED, 16 + MAX_WBITS, 8,
+                         Z_DEFAULT_STRATEGY) == Z_OK);
+    zs.next_in = (const Bytef *) xml;
+    zs.avail_in = (uInt) strlen(xml);
+    zs.next_out = (Bytef *) z;
+    zs.avail_out = (uInt) zlen;
+    assertf(deflate(&zs, Z_FINISH) == Z_STREAM_END);
+    zlen = (uLongf) zs.total_out;
+    deflateEnd(&zs);
+
+    memset(&c, 0, sizeof(c));
+    assertf(hts_sitemap_scan(z, (size_t) zlen, 100, &idx, sm_take, &c) == 1);
+    assertf(strcmp(c.url[0], "http://h.test/gz.html") == 0);
+
+    /* Truncated gzip: refused, not scanned as plain text. */
+    memset(&c, 0, sizeof(c));
+    assertf(hts_sitemap_scan(z, 4, 100, &idx, sm_take, &c) == -1);
+    freet(z);
+  }
+
+  /* robots.txt: only Sitemap: records, comments stripped, case-insensitive,
+     and group-independent (no User-agent line needed). */
+  /* robots_parse collects Sitemap: whatever the user-agent group, strips the
+     comment and keeps the rules working alongside it. */
+  {
+    const char *const txt = "User-agent: *\nDisallow: /x\n"
+                            "SITEMAP:  http://h.test/s1.xml  # first\n"
+                            "Sitemapper: http://h.test/no.xml\n"
+                            "Sitemap:\thttps://h.test/s2.xml\n";
+    char BIGSTK maps[1024];
+    robots_wizard rb;
+
+    memset(&rb, 0, sizeof(rb));
+    robots_parse(&rb, "h.test", txt, strlen(txt), NULL, 0, HTS_TRUE, maps,
+                 sizeof(maps));
+    assertf(strcmp(maps, "http://h.test/s1.xml\nhttps://h.test/s2.xml\n") == 0);
+    assertf(checkrobots(&rb, "h.test", "/x") == -1);
+    checkrobots_free(&rb);
+  }
+
+  printf("sitemap self-test OK\n");
+  return 0;
+}
+
 /* Connected stream pair over loopback; Windows has no socketpair(). */
 static int st_socketpair(T_SOC sv[2]) {
   struct sockaddr_in sa;
@@ -3860,21 +4263,6 @@ static int st_ftpuser(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* Bounded substring search (records carry NUL bytes; strstr won't do). */
-static const char *warc_memstr(const char *hay, const char *needle,
-                               size_t haylen, size_t nlen) {
-  if (nlen == 0 || haylen < nlen)
-    return NULL;
-  {
-    size_t i;
-    for (i = 0; i + nlen <= haylen; i++) {
-      if (memcmp(hay + i, needle, nlen) == 0)
-        return hay + i;
-    }
-  }
-  return NULL;
-}
-
 /* Slurp a whole file into a malloc'd buffer; sets *len. NULL on error. */
 static unsigned char *warc_slurp(const char *path, size_t *len) {
   FILE *f = FOPEN(path, "rb");
@@ -3952,6 +4340,13 @@ static unsigned char *warc_next_member(const unsigned char **in,
    Content-Length == block length, the \r\n\r\n trailer intact, the response
    body round-trips, and the hop-by-hop Transfer-Encoding is dropped (a real
    Content-Encoding is kept verbatim; see warc-verbatim). */
+/* Argument order kept for the existing call sites; the search itself is the
+   shared hts_memstr. */
+static const char *warc_memstr(const char *hay, const char *needle,
+                               size_t haylen, size_t nlen) {
+  return hts_memstr(hay, haylen, needle, nlen);
+}
+
 static int st_warc(httrackp *opt, int argc, char **argv) {
   char path[HTS_URLMAXSIZE];
   warc_writer *w;
@@ -5819,6 +6214,116 @@ static int st_changes(httrackp *opt, int argc, char **argv) {
   return err;
 }
 
+/* #747: a thread is outstanding from the moment hts_newthread() returns, not
+   from the moment it starts running, or a wait right after the spawn joins
+   nothing. One thread per round is what makes the old bug visible: the wait
+   had to find the counter at zero, and a batch of spawns gives the earlier
+   threads time to raise it. Unfixed, one round in two caught it, so the round
+   count is what turns that into a reliable failure. */
+#define THREADWAIT_N 8
+#define THREADWAIT_ROUNDS 16
+#define THREADWAIT_SLEEP_MS 50
+#define THREADWAIT_GATE_MS 10000
+
+static htsmutex threadwait_lock = HTSMUTEX_INIT;
+static int threadwait_done = 0;
+static hts_boolean threadwait_gated = HTS_FALSE;
+
+static int threadwait_count(void) {
+  int n;
+
+  hts_mutexlock(&threadwait_lock);
+  n = threadwait_done;
+  hts_mutexrelease(&threadwait_lock);
+  return n;
+}
+
+static void threadwait_thread(void *arg) {
+  (void) arg;
+  Sleep(THREADWAIT_SLEEP_MS);
+  hts_mutexlock(&threadwait_lock);
+  threadwait_done++;
+  hts_mutexrelease(&threadwait_lock);
+}
+
+/* Stays outstanding until the gate clears, so wait_n() can be asked to leave a
+   known number of live threads behind. Bounded: a wait_n() that wrongly drains
+   them would otherwise never return, and hang the suite instead of failing. */
+static void threadwait_gated_thread(void *arg) {
+  int waited;
+
+  (void) arg;
+  for (waited = 0; waited < THREADWAIT_GATE_MS; waited += 10) {
+    hts_boolean gated;
+
+    hts_mutexlock(&threadwait_lock);
+    gated = threadwait_gated;
+    hts_mutexrelease(&threadwait_lock);
+    if (!gated)
+      break;
+    Sleep(10);
+  }
+  hts_mutexlock(&threadwait_lock);
+  threadwait_done++;
+  hts_mutexrelease(&threadwait_lock);
+}
+
+static int st_threadwait(httrackp *opt, int argc, char **argv) {
+  int err = 0;
+  int i, round;
+
+  (void) opt;
+  (void) argc;
+  (void) argv;
+
+  /* htsthread_wait() joins a thread spawned just before it */
+  for (round = 0; round < THREADWAIT_ROUNDS && !err; round++) {
+    hts_mutexlock(&threadwait_lock);
+    threadwait_done = 0;
+    hts_mutexrelease(&threadwait_lock);
+    if (hts_newthread(threadwait_thread, NULL) != 0) {
+      fprintf(stderr, "threadwait: cannot spawn\n");
+      return 1;
+    }
+    htsthread_wait();
+    if (threadwait_count() != 1) {
+      fprintf(stderr, "threadwait: round %d returned before the thread ran\n",
+              round);
+      err = 1;
+    }
+  }
+
+  /* htsthread_wait_n(n) leaves n behind rather than draining everything */
+  hts_mutexlock(&threadwait_lock);
+  threadwait_done = 0;
+  threadwait_gated = HTS_TRUE;
+  hts_mutexrelease(&threadwait_lock);
+  for (i = 0; i < THREADWAIT_N; i++) {
+    if (hts_newthread(threadwait_gated_thread, NULL) != 0) {
+      fprintf(stderr, "threadwait: cannot spawn a gated thread\n");
+      return 1;
+    }
+  }
+  htsthread_wait_n(THREADWAIT_N);
+  if (threadwait_count() != 0) {
+    fprintf(stderr, "threadwait: wait_n(%d) joined %d gated threads\n",
+            THREADWAIT_N, threadwait_count());
+    err = 1;
+  }
+  hts_mutexlock(&threadwait_lock);
+  threadwait_gated = HTS_FALSE;
+  hts_mutexrelease(&threadwait_lock);
+  htsthread_wait();
+  if (threadwait_count() != THREADWAIT_N) {
+    fprintf(stderr, "threadwait: wait left %d/%d gated threads running\n",
+            THREADWAIT_N - threadwait_count(), THREADWAIT_N);
+    err = 1;
+  }
+
+  printf("threadwait self-test: %s\n", err ? "FAIL" : "OK");
+  return err;
+}
+
 #define CHANGES_RACE_FILES 8
 #define CHANGES_RACE_ROUNDS 400
 
@@ -5833,11 +6338,8 @@ static void changes_race_notify(httrackp *opt, int n) {
   hts_changes_notify(opt, "race.example", fil, save, HTS_TRUE, HTS_FALSE);
 }
 
-/* htsthread_wait() counts a thread only once it is running, so it can return
-   before any of them started; join on our own counter instead. */
 static htsmutex changes_race_lock = HTSMUTEX_INIT;
 static int changes_race_started = 0;
-static int changes_race_live = 0;
 
 static int changes_race_count(int *which) {
   int n;
@@ -5857,9 +6359,6 @@ static void changes_race_thread(void *arg) {
   hts_mutexrelease(&changes_race_lock);
   for (i = 0; i < CHANGES_RACE_ROUNDS; i++)
     changes_race_notify(opt, i % CHANGES_RACE_FILES);
-  hts_mutexlock(&changes_race_lock);
-  changes_race_live--;
-  hts_mutexrelease(&changes_race_lock);
 }
 
 /* A transfer thread the crawl never joins (FTP) reaches hts_changes_notify()
@@ -5914,7 +6413,6 @@ static int st_changes_race(httrackp *opt, int argc, char **argv) {
      threads reaching a fresh one together race on the init itself. */
   hts_mutexlock(&changes_race_lock);
   changes_race_started = 0;
-  changes_race_live = 4;
   hts_mutexrelease(&changes_race_lock);
   for (i = 0; i < 4; i++) {
     if (hts_newthread(changes_race_thread, opt) != 0) {
@@ -5928,8 +6426,7 @@ static int st_changes_race(httrackp *opt, int argc, char **argv) {
   for (i = 0; i < 64; i++)
     hts_changes_report(opt, &out);
   hts_changes_close_opt(opt);
-  while (changes_race_count(&changes_race_live) > 0)
-    Sleep(10);
+  htsthread_wait();
 
   /* Sealed: a straggler must be dropped, not start a report nobody writes. */
   changes_race_notify(opt, CHANGES_RACE_FILES + 1);
@@ -6007,6 +6504,8 @@ static const struct selftest_entry {
      st_changes},
     {"changes-race", "<dir>", "--changes under a late transfer thread (#714)",
      st_changes_race},
+    {"threadwait", "", "htsthread_wait() joins threads spawned just before it",
+     st_threadwait},
     {"pause", "", "randomized inter-file pause target self-test", st_pause},
     {"relative", "<link> <curr-file>", "relative link between two paths",
      st_relative},
@@ -6037,6 +6536,8 @@ static const struct selftest_entry {
     {"fsize", "<dir>", "file size past the 2GB signed-32-bit wrap", st_fsize},
     {"growsize", "", "buffer capacity for a 64-bit file size (no int wrap)",
      st_growsize},
+    {"addlink", "", "htsAddLink codebase walk over an empty current path",
+     st_addlink},
     {"cache", "<dir>", "cache read/write round-trip self-test", st_cache},
     {"cacheindex", "", "cache-index (.ndx) parse must stay in bounds",
      st_cacheindex},
@@ -6060,6 +6561,9 @@ static const struct selftest_entry {
     {"useragent", "", "default User-Agent self-test", st_useragent},
     {"makeindex", "[dir]", "hts_finish_makeindex footer/refresh self-test",
      st_makeindex},
+    {"structcheck", "<dir>",
+     "structcheck path guard and the <name>.txt rename it performs",
+     st_structcheck},
     {"topindex", "[dir]",
      "hts_buildtopindex charset handling of a non-ASCII project dir",
      st_topindex},
@@ -6075,6 +6579,8 @@ static const struct selftest_entry {
      st_contentcodings},
     {"robots", "", "robots.txt RFC 9309 Allow/Disallow precedence self-test",
      st_robots},
+    {"sitemap", "",
+     "sitemap <loc> extraction, caps and robots.txt Sitemap:", st_sitemap},
     {"ftp-line", "", "get_ftp_line bounds a hostile FTP reply line",
      st_ftpline},
     {"ftp-userpass", "", "ftp_split_userpass bounds URL userinfo", st_ftpuser},

src/htssinglefile.c

@@ -1108,13 +1108,8 @@ hts_boolean singlefile_rewrite_file(httrackp *opt, const char *root,
       (void) chmod(fconv(catbuff, sizeof(catbuff), StringBuff(tmp)),
                    HTS_ACCESS_FILE);
 #endif
-    if (ok) {
-      /* RENAME does not clobber an existing target on Windows. */
-      if (RENAME(StringBuff(tmp), page_path) != 0) {
-        (void) UNLINK(page_path);
-        ok = RENAME(StringBuff(tmp), page_path) == 0 ? HTS_TRUE : HTS_FALSE;
-      }
-    }
+    if (ok)
+      ok = hts_rename_over(StringBuff(tmp), page_path);
     if (!ok) {
       hts_log_print(opt, LOG_ERROR, "single-file: could not rewrite %s",
                     page_path);

src/htssitemap.c

@@ -0,0 +1,615 @@
+/* ------------------------------------------------------------ */
+/*
+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/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: sitemap ingestion (sitemaps.org 0.9)                   */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#define HTS_INTERNAL_BYTECODE
+
+#include "htscore.h"
+#include "htssitemap.h"
+
+#include "htsbase.h"
+#include "htscodec.h"
+#include "htsencoding.h"
+#include "htsfilters.h"
+#include "htshash.h"
+#include "htsmodules.h"
+#include "htslib.h"
+#include "htsrobots.h"
+#include "htssafe.h"
+#include "htstools.h"
+
+#include <ctype.h>
+#include <string.h>
+
+/* One queued sitemap document awaiting ingestion. */
+typedef struct sitemap_doc {
+  char adr[HTS_URLMAXSIZE];
+  char fil[HTS_URLMAXSIZE];
+  int level;
+  hts_sitemap_source src;
+  hts_boolean done;
+  struct sitemap_doc *next;
+} sitemap_doc;
+
+struct hts_sitemap_state {
+  sitemap_doc *docs;
+  int ndocs; /* documents queued, capped by HTS_SITEMAP_MAX_DOCS */
+  int nurls; /* URLs seeded, capped by HTS_SITEMAP_MAX_URLS_TOTAL */
+  hts_boolean probe_done;    /* the robots.txt probe has been answered */
+  hts_boolean fallback_done; /* the /sitemap.xml fallback was already queued */
+  /* The crawl's own start URL. Seeded URLs are judged against it, so a site
+     cannot widen a subtree crawl by putting its sitemap at the root. */
+  char anchor_adr[HTS_URLMAXSIZE];
+  char anchor_fil[HTS_URLMAXSIZE];
+};
+typedef struct hts_sitemap_state hts_sitemap_state;
+
+/* --------------------------------------------------------------------- */
+/* Document parsing (no engine state: fuzzable and self-testable)         */
+/* --------------------------------------------------------------------- */
+
+/* Accept only an absolute http(s) URL with no space or control byte. */
+static hts_boolean sitemap_url_ok(const char *url) {
+  const char *p;
+
+  if (!strfield(url, "http://") && !strfield(url, "https://"))
+    return HTS_FALSE;
+  for (p = url; *p != '\0'; p++) {
+    if ((unsigned char) *p <= ' ' || (unsigned char) *p == 0x7f)
+      return HTS_FALSE;
+  }
+  return HTS_TRUE;
+}
+
+/* Skip to the character after the next '>' at or after p, or NULL. */
+static const char *sitemap_tag_end(const char *p, const char *end) {
+  while (p < end && *p != '>')
+    p++;
+  return p < end ? p + 1 : NULL;
+}
+
+/* HTS_TRUE when the document's root element is `name`. Skips the XML
+   declaration, comments and processing instructions first, so a comment
+   mentioning the other root element cannot decide the document type. */
+static hts_boolean sitemap_root_is(const char *doc, size_t size,
+                                   const char *name) {
+  const size_t nlen = strlen(name);
+  size_t i = 0;
+
+  if (size >= 3 && memcmp(doc, "\xef\xbb\xbf", 3) == 0)
+    i = 3; /* UTF-8 BOM */
+  while (i < size) {
+    if (isspace((unsigned char) doc[i])) {
+      i++;
+    } else if (doc[i] != '<') {
+      return HTS_FALSE; /* character data before any element: not XML */
+    } else if (i + 4 <= size && memcmp(doc + i, "<!--", 4) == 0) {
+      const char *const e = hts_memstr(doc + i, size - i, "-->", 3);
+
+      if (e == NULL)
+        return HTS_FALSE;
+      i = (size_t) (e - doc) + 3;
+    } else if (i + 2 <= size && (doc[i + 1] == '?' || doc[i + 1] == '!')) {
+      while (i < size && doc[i] != '>')
+        i++;
+      i++;
+    } else {
+      size_t j = i + 1;
+
+      /* an optional namespace prefix: <sm:sitemapindex> is the same element */
+      while (j < size && doc[j] != ':' && doc[j] != '>' &&
+             !isspace((unsigned char) doc[j]))
+        j++;
+      if (j >= size || doc[j] != ':')
+        j = i + 1;
+      else
+        j++;
+      return j + nlen <= size && memcmp(doc + j, name, nlen) == 0 &&
+                     (j + nlen == size ||
+                      isspace((unsigned char) doc[j + nlen]) ||
+                      doc[j + nlen] == '>' || doc[j + nlen] == '/')
+                 ? HTS_TRUE
+                 : HTS_FALSE;
+    }
+  }
+  return HTS_FALSE;
+}
+
+/* Decompress a gzip-framed body into a fresh buffer. The 64 MiB cap is what
+   binds in practice; deflate tops out near 1032:1, so the tree's codec budget
+   only matters as the shared policy for a coding that could go further. */
+static char *sitemap_gunzip(const char *body, size_t size, size_t *outsize) {
+  const LLint budget = hts_codec_maxout((LLint) size);
+  size_t cap = budget < (LLint) HTS_SITEMAP_MAX_BYTES
+                   ? (size_t) budget
+                   : (size_t) HTS_SITEMAP_MAX_BYTES;
+  char *out;
+  size_t n;
+
+  if (cap == 0)
+    return NULL;
+  out = malloct(cap + 1);
+  if (out == NULL)
+    return NULL;
+  n = hts_codec_head(HTS_CODEC_DEFLATE, body, size, out, cap);
+  if (n == 0) {
+    freet(out);
+    return NULL;
+  }
+  out[n] = '\0';
+  *outsize = n;
+  return out;
+}
+
+int hts_sitemap_scan(const char *body, size_t size, int maxurls,
+                     hts_boolean *is_index, hts_sitemap_handler handler,
+                     void *arg) {
+  char *unpacked = NULL;
+  const char *doc;
+  const char *end;
+  const char *p;
+  int n = 0;
+
+  if (is_index != NULL)
+    *is_index = HTS_FALSE;
+  if (body == NULL || size < 2 || handler == NULL)
+    return 0;
+
+  /* Content-Encoding gzip is undone upstream; only the container is left. */
+  if ((unsigned char) body[0] == 0x1f && (unsigned char) body[1] == 0x8b) {
+    unpacked = sitemap_gunzip(body, size, &size);
+    if (unpacked == NULL)
+      return -1;
+    doc = unpacked;
+  } else {
+    if (size > (size_t) HTS_SITEMAP_MAX_BYTES)
+      size = (size_t) HTS_SITEMAP_MAX_BYTES;
+    doc = body;
+  }
+  end = doc + size;
+
+  /* Set before the first callback: the handler reads the verdict. */
+  if (is_index != NULL)
+    *is_index = sitemap_root_is(doc, size, "sitemapindex");
+
+  for (p = doc; n < maxurls;) {
+    const char *loc = hts_memstr(p, (size_t) (end - p), "<loc", 4);
+    const char *val;
+    const char *stop;
+    size_t len;
+    char BIGSTK url[HTS_URLMAXSIZE];
+
+    if (loc == NULL)
+      break;
+    /* "<loc>" or "<loc xmlns:..>", never "<location>" */
+    if (loc + 4 >= end || (loc[4] != '>' && !isspace((unsigned char) loc[4]))) {
+      p = loc + 4;
+      continue;
+    }
+    val = sitemap_tag_end(loc + 4, end);
+    if (val == NULL)
+      break;
+    for (stop = val; stop < end && *stop != '<'; stop++)
+      ;
+    /* No closing tag: truncated document, so the value may be a partial URL. */
+    if (stop == end)
+      break;
+    p = stop;
+    while (val < stop && isspace((unsigned char) *val))
+      val++;
+    while (stop > val && isspace((unsigned char) *(stop - 1)))
+      stop--;
+    len = (size_t) (stop - val);
+    /* Overflow-safe: the untrusted length alone against the room left. */
+    if (len == 0 || len >= sizeof(url))
+      continue;
+    memcpy(url, val, len);
+    url[len] = '\0';
+    /* hts_unescapeEntities decodes in place and tolerates src == dest; a
+       reference to a control byte survives as one and sitemap_url_ok drops it.
+     */
+    if (hts_unescapeEntities(url, url, sizeof(url)) != 0 ||
+        !sitemap_url_ok(url))
+      continue;
+    n++;
+    if (!handler(arg, url))
+      break;
+  }
+
+  if (unpacked != NULL)
+    freet(unpacked);
+  return n;
+}
+
+/* --------------------------------------------------------------------- */
+/* Engine glue                                                           */
+/* --------------------------------------------------------------------- */
+
+static hts_sitemap_state *sitemap_get_state(httrackp *opt) {
+  if (opt->sitemap_state == NULL)
+    opt->sitemap_state = calloct(1, sizeof(hts_sitemap_state));
+  return (hts_sitemap_state *) opt->sitemap_state;
+}
+
+static sitemap_doc *sitemap_find(httrackp *opt, const char *adr,
+                                 const char *fil) {
+  hts_sitemap_state *const st = (hts_sitemap_state *) opt->sitemap_state;
+  sitemap_doc *d;
+
+  if (st == NULL)
+    return NULL;
+  for (d = st->docs; d != NULL; d = d->next) {
+    if (strfield2(d->adr, adr) && strcmp(d->fil, fil) == 0)
+      return d;
+  }
+  return NULL;
+}
+
+/* Who asked for this document decides how far it is gated. The wizard proper
+   is not usable here: it wants a referring link, and its up/down travel rules
+   would judge a child sitemap against the parent sitemap's directory. */
+static hts_boolean sitemap_fetch_allowed(httrackp *opt, const char *adr,
+                                         const char *fil,
+                                         hts_sitemap_source src) {
+  /* adr and fil are each capped just under HTS_URLMAXSIZE, and lfull prefixes
+     a scheme and a slash on top of both: 2 * HTS_URLMAXSIZE does not fit. */
+  char BIGSTK l[HTS_URLMAXSIZE * 2 + 16], lfull[HTS_URLMAXSIZE * 2 + 16];
+  int jokdepth = 0, jok;
+
+  hts_boolean refused;
+
+  /* The user naming a sitemap is the same intent as naming a start URL, which
+     the wizard admits unconditionally. */
+  if (src == HTS_SITEMAP_SRC_USER)
+    return HTS_TRUE;
+  strcpybuff(l, jump_identification_const(adr));
+  if (*fil != '/')
+    strcatbuff(l, "/");
+  strcatbuff(l, fil);
+  strcpybuff(lfull, link_has_authority(adr) ? "" : "http://");
+  strcatbuff(lfull, adr);
+  if (*fil != '/')
+    strcatbuff(lfull, "/");
+  strcatbuff(lfull, fil);
+  jok = fa_strjoker_dual(0, *opt->filters.filters, *opt->filters.filptr, lfull,
+                         l, NULL, NULL, &jokdepth);
+  refused = (jok == -1) ? HTS_TRUE : HTS_FALSE;
+  if (refused) {
+    hts_log_print(opt, LOG_NOTICE, "Sitemap: filter rule #%d refuses %s%s",
+                  jokdepth + 1, adr, fil);
+    return HTS_FALSE;
+  }
+  /* A Sitemap: line, or a sitemapindex entry, is the site inviting the fetch;
+     a Disallow elsewhere in the same file does not retract it. The well-known
+     location is only ever a guess, so there a Disallow wins. */
+  if (src == HTS_SITEMAP_SRC_GUESSED &&
+      hts_robots_forbids(opt, adr, fil, (jok != 0) ? HTS_TRUE : HTS_FALSE,
+                         refused)) {
+    hts_log_print(opt, LOG_NOTICE, "Sitemap: robots.txt forbids %s%s", adr,
+                  fil);
+    return HTS_FALSE;
+  }
+  return HTS_TRUE;
+}
+
+/* Record the link with save="" so the body stays in memory: a sitemap is
+   ingested, never mirrored. */
+static hts_boolean sitemap_queue_(httrackp *opt, const char *adr,
+                                  const char *fil, int level,
+                                  hts_sitemap_source src, hts_boolean link_it) {
+  hts_sitemap_state *const st = sitemap_get_state(opt);
+  sitemap_doc *d;
+
+  if (st == NULL)
+    return HTS_FALSE;
+  if (st->ndocs >= HTS_SITEMAP_MAX_DOCS || level > HTS_SITEMAP_MAX_LEVEL) {
+    hts_log_print(opt, LOG_WARNING, "Sitemap: cap reached, skipping %s%s", adr,
+                  fil);
+    return HTS_FALSE;
+  }
+  if (strlen(adr) >= sizeof(d->adr) || strlen(fil) >= sizeof(d->fil))
+    return HTS_FALSE;
+  if (sitemap_find(opt, adr, fil) != NULL)
+    return HTS_FALSE;
+  if (!sitemap_fetch_allowed(opt, adr, fil, src))
+    return HTS_FALSE;
+  d = calloct(1, sizeof(sitemap_doc));
+  if (d == NULL)
+    return HTS_FALSE;
+  strcpybuff(d->adr, adr);
+  strcpybuff(d->fil, fil);
+  d->level = level;
+  d->src = src;
+  d->next = st->docs;
+  st->docs = d;
+  st->ndocs++;
+
+  if (!link_it)
+    return HTS_TRUE;
+  if (!hts_record_link(opt, adr, fil, "", "", "", NULL))
+    return HTS_FALSE;
+  heap_top()->testmode = 0;
+  heap_top()->link_import = 0;
+  heap_top()->depth = opt->depth + 1;
+  heap_top()->pass2 = 0;
+  heap_top()->retry = opt->retry;
+  heap_top()->premier = heap_top_index();
+  heap_top()->precedent = heap_top_index();
+  hts_log_print(opt, LOG_INFO, "Sitemap: queued %s%s", adr, fil);
+  return HTS_TRUE;
+}
+
+static hts_boolean sitemap_queue(httrackp *opt, const char *adr,
+                                 const char *fil, int level,
+                                 hts_sitemap_source src) {
+  return sitemap_queue_(opt, adr, fil, level, src, HTS_TRUE);
+}
+
+void hts_sitemap_redirect(httrackp *opt, const char *adr, const char *fil,
+                          const char *newadr, const char *newfil) {
+  sitemap_doc *const d = sitemap_find(opt, adr, fil);
+
+  if (d == NULL || d->done)
+    return;
+  d->done = HTS_TRUE; /* the body lives at the target now */
+  /* The engine already queued the target link, so only the marking moves. */
+  (void) sitemap_queue_(opt, newadr, newfil, d->level, d->src, HTS_FALSE);
+  hts_log_print(opt, LOG_NOTICE, "Sitemap: %s%s redirects to %s%s", adr, fil,
+                newadr, newfil);
+}
+
+void hts_sitemap_seed(httrackp *opt, const char *starturl) {
+  char BIGSTK url[HTS_URLMAXSIZE * 2];
+  lien_adrfil af;
+
+  if (StringNotEmpty(opt->sitemap_url)) {
+    if (strlen(StringBuff(opt->sitemap_url)) >= sizeof(url)) {
+      hts_log_print(opt, LOG_ERROR, "Sitemap URL too long");
+    } else {
+      strcpybuff(url, StringBuff(opt->sitemap_url));
+      if (strstr(url, ":/") == NULL)
+        hts_log_print(opt, LOG_ERROR, "Sitemap URL must be absolute: %s", url);
+      else if (ident_url_absolute(url, &af) >= 0)
+        (void) sitemap_queue(opt, af.adr, af.fil, 0, HTS_SITEMAP_SRC_USER);
+    }
+  }
+  if (starturl == NULL || starturl[0] == '\0' ||
+      strlen(starturl) >= sizeof(url))
+    return;
+  strcpybuff(url, starturl);
+  if (ident_url_absolute(url, &af) < 0)
+    return;
+  {
+    hts_sitemap_state *const st = sitemap_get_state(opt);
+
+    if (st != NULL && strlen(af.adr) < sizeof(st->anchor_adr) &&
+        strlen(af.fil) < sizeof(st->anchor_fil)) {
+      strcpybuff(st->anchor_adr, af.adr);
+      strcpybuff(st->anchor_fil, af.fil);
+    }
+  }
+  if (!opt->sitemap)
+    return;
+  /* Answered in hts_sitemap_robots, once the parsed rules are installed. */
+  if (hts_record_link(opt, af.adr, "/robots.txt", "", "", "", NULL)) {
+    heap_top()->testmode = 0;
+    heap_top()->link_import = 0;
+    heap_top()->depth = 0;
+    heap_top()->pass2 = 0;
+    heap_top()->retry = opt->retry;
+    heap_top()->premier = heap_top_index();
+    heap_top()->precedent = heap_top_index();
+    /* Claim the host so the parser does not queue robots.txt a second time. */
+    if (opt->robotsptr != NULL)
+      (void) checkrobots_set((robots_wizard *) opt->robotsptr, af.adr, "");
+  }
+}
+
+void hts_sitemap_robots(httrackp *opt, const char *adr, const char *sitemaps) {
+  hts_sitemap_state *const st = (hts_sitemap_state *) opt->sitemap_state;
+  int queued = 0;
+
+  if (st == NULL || !opt->sitemap || st->probe_done ||
+      !strfield2(st->anchor_adr, adr))
+    return;
+  st->probe_done = HTS_TRUE;
+  if (sitemaps != NULL) {
+    const char *p = sitemaps;
+
+    while (*p != '\0') {
+      const char *const eol = strchr(p, '\n');
+      const size_t len = eol != NULL ? (size_t) (eol - p) : strlen(p);
+      char BIGSTK line[HTS_URLMAXSIZE];
+      lien_adrfil af;
+
+      if (len > 0 && len < sizeof(line)) {
+        memcpy(line, p, len);
+        line[len] = '\0';
+        /* Same host: a Sitemap: line must not aim the fetcher elsewhere. */
+        if (sitemap_url_ok(line) && ident_url_absolute(line, &af) >= 0 &&
+            strfield2(af.adr, adr) &&
+            sitemap_queue(opt, af.adr, af.fil, 0, HTS_SITEMAP_SRC_DECLARED))
+          queued++;
+      }
+      if (eol == NULL)
+        break;
+      p = eol + 1;
+    }
+  }
+  if (queued == 0 && !st->fallback_done) {
+    st->fallback_done = HTS_TRUE;
+    if (sitemap_queue(opt, adr, "/sitemap.xml", 0, HTS_SITEMAP_SRC_GUESSED))
+      queued++;
+  }
+  hts_log_print(opt, LOG_NOTICE, "Sitemap: %d sitemap(s) queued for %s", queued,
+                adr);
+}
+
+hts_boolean hts_sitemap_pending(httrackp *opt, const char *adr,
+                                const char *fil) {
+  const sitemap_doc *const d = sitemap_find(opt, adr, fil);
+
+  return d != NULL && !d->done ? HTS_TRUE : HTS_FALSE;
+}
+
+/* Handler context: seeding URLs from one document. */
+typedef struct sitemap_ingest_ctx {
+  httrackp *opt;
+  htsmoduleStruct *str;
+  const char *adr; /* host of the document being ingested */
+  int level;
+  hts_boolean is_index;
+  int accepted; /* URLs seeded or documents queued, not merely parsed */
+} sitemap_ingest_ctx;
+
+/* A <loc> of a <urlset>: hand it to the wizard as a top-level seed.
+   The wizard is pointed at the crawl's own start URL, not at the sitemap: the
+   site picks where its sitemap lives, so anchoring travel there would let a
+   root sitemap widen a subtree crawl to the whole host. The URL then becomes
+   its own anchor, exactly as a command-line seed does. */
+static hts_boolean sitemap_seed_url(void *arg, const char *url) {
+  sitemap_ingest_ctx *const c = (sitemap_ingest_ctx *) arg;
+  httrackp *const opt = c->opt;
+  hts_sitemap_state *const st = sitemap_get_state(opt);
+  char BIGSTK buff[HTS_URLMAXSIZE];
+  int before;
+
+  if (st == NULL || st->nurls >= HTS_SITEMAP_MAX_URLS_TOTAL) {
+    hts_log_print(opt, LOG_WARNING,
+                  "Sitemap: URL cap reached, ignoring the rest");
+    return HTS_FALSE;
+  }
+  /* strcpybuff aborts rather than truncating: never feed it unchecked input. */
+  if (strlen(url) >= sizeof(buff))
+    return HTS_TRUE;
+  st->nurls++;
+  strcpybuff(buff, url);
+  before = opt->lien_tot;
+  if (htsAddLink(c->str, buff))
+    c->accepted++;
+  if (opt->lien_tot > before)
+    heap_top()->premier = heap_top_index(); /* a seed anchors on itself */
+  return HTS_TRUE;
+}
+
+/* A <loc> of a <sitemapindex>: cross-host children are dropped, so a hostile
+   sitemap cannot aim the fetcher elsewhere. */
+static hts_boolean sitemap_seed_child(void *arg, const char *url) {
+  sitemap_ingest_ctx *const c = (sitemap_ingest_ctx *) arg;
+  char BIGSTK buff[HTS_URLMAXSIZE];
+  lien_adrfil af;
+
+  if (strlen(url) >= sizeof(buff))
+    return HTS_TRUE;
+  strcpybuff(buff, url);
+  if (ident_url_absolute(buff, &af) < 0)
+    return HTS_TRUE;
+  if (!strfield2(af.adr, c->adr)) {
+    hts_log_print(c->opt, LOG_WARNING,
+                  "Sitemap: ignoring off-host child sitemap %s%s", af.adr,
+                  af.fil);
+    return HTS_TRUE;
+  }
+  if (sitemap_queue(c->opt, af.adr, af.fil, c->level + 1,
+                    HTS_SITEMAP_SRC_DECLARED))
+    c->accepted++;
+  return HTS_TRUE;
+}
+
+/* The scan classifies the document before the first callback. */
+static hts_boolean sitemap_seed_any(void *arg, const char *url) {
+  sitemap_ingest_ctx *const c = (sitemap_ingest_ctx *) arg;
+
+  return c->is_index ? sitemap_seed_child(arg, url)
+                     : sitemap_seed_url(arg, url);
+}
+
+void hts_sitemap_ingest(httrackp *opt, htsmoduleStruct *str, const char *adr,
+                        const char *fil, const char *body, size_t size) {
+  sitemap_doc *const d = sitemap_find(opt, adr, fil);
+  hts_sitemap_state *const st = (hts_sitemap_state *) opt->sitemap_state;
+  sitemap_ingest_ctx ctx;
+  int n, anchor, saved_depth;
+
+  if (d == NULL || d->done)
+    return;
+  d->done = HTS_TRUE;
+  /* str->ptr_ is a scratch int owned by the caller, so nothing else moves. */
+  anchor = *str->ptr_;
+  if (st != NULL && st->anchor_adr[0] != '\0' && opt->hash != NULL) {
+    const int i = hash_read((const hash_struct *) opt->hash, st->anchor_adr,
+                            st->anchor_fil, 1);
+
+    if (i >= 0)
+      anchor = i;
+  }
+  *str->ptr_ = anchor;
+  /* Borrow the anchor's position but keep a seed's full depth budget. */
+  saved_depth = heap(anchor)->depth;
+  heap(anchor)->depth = opt->depth + 1;
+  ctx.opt = opt;
+  ctx.str = str;
+  ctx.adr = adr;
+  ctx.level = d->level;
+  ctx.is_index = HTS_FALSE;
+  ctx.accepted = 0;
+
+  n = hts_sitemap_scan(body, size, HTS_SITEMAP_MAX_URLS_DOC, &ctx.is_index,
+                       sitemap_seed_any, &ctx);
+  heap(anchor)->depth = saved_depth;
+  if (n < 0) {
+    hts_log_print(opt, LOG_ERROR, "Sitemap: could not decompress %s%s", adr,
+                  fil);
+    return;
+  }
+  if (ctx.is_index)
+    hts_log_print(opt, LOG_NOTICE,
+                  "Sitemap: %d of %d child sitemap(s) listed by %s%s",
+                  ctx.accepted, n, adr, fil);
+  else
+    hts_log_print(opt, LOG_NOTICE, "Sitemap: %d of %d URL(s) added from %s%s",
+                  ctx.accepted, n, adr, fil);
+}
+
+void hts_sitemap_free(httrackp *opt) {
+  hts_sitemap_state *const st = (hts_sitemap_state *) opt->sitemap_state;
+
+  if (st == NULL)
+    return;
+  while (st->docs != NULL) {
+    sitemap_doc *const next = st->docs->next;
+
+    freet(st->docs);
+    st->docs = next;
+  }
+  freet(opt->sitemap_state);
+  opt->sitemap_state = NULL;
+}

src/htssitemap.h

@@ -0,0 +1,108 @@
+/* ------------------------------------------------------------ */
+/*
+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/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* HTTrack sitemap ingestion (sitemaps.org 0.9). Internal, not installed.
+   Reads <urlset>/<sitemapindex> documents, plain or gzip-framed, and feeds
+   their <loc> URLs to the crawl as top-level seeds. The whole input is
+   attacker-controlled, so every entry point below is capped. */
+/* ------------------------------------------------------------ */
+
+#ifndef HTS_SITEMAP_DEFH
+#define HTS_SITEMAP_DEFH
+
+#include "htsdefines.h"
+#include "htsopt.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Caps. sitemaps.org allows 50000 URLs and 50 MB uncompressed per document;
+   the byte cap sits above that so a conformant sitemap always fits. */
+#define HTS_SITEMAP_MAX_URLS_DOC 50000           /* <loc> per document */
+#define HTS_SITEMAP_MAX_URLS_TOTAL 200000        /* <loc> per mirror */
+#define HTS_SITEMAP_MAX_DOCS 256                 /* documents per mirror */
+#define HTS_SITEMAP_MAX_LEVEL 4                  /* sitemapindex nesting */
+#define HTS_SITEMAP_MAX_BYTES (64 * 1024 * 1024) /* decompressed document */
+
+/* Who asked for a sitemap document, which decides how far its fetch is gated.
+   The user naming one is the same intent as a start URL; a site declaring one
+   invites the fetch; the well-known location is only ever our guess. */
+typedef enum {
+  HTS_SITEMAP_SRC_USER,     /**< --sitemap-url */
+  HTS_SITEMAP_SRC_DECLARED, /**< a Sitemap: line or a sitemapindex entry */
+  HTS_SITEMAP_SRC_GUESSED   /**< the /sitemap.xml fallback */
+} hts_sitemap_source;
+
+/* Per-URL handler; returning HTS_FALSE stops the scan. */
+typedef hts_boolean (*hts_sitemap_handler)(void *arg, const char *url);
+
+/* Scan one sitemap document, plain or gzip-framed, handing every acceptable
+   absolute http(s) <loc> URL to `handler`. Stops after `maxurls` URLs, or when
+   the handler refuses. `is_index` (optional) reports a <sitemapindex>, whose
+   URLs are child sitemaps rather than pages. Returns the number of URLs handed
+   out, or -1 when the document could not be decompressed within the caps. */
+int hts_sitemap_scan(const char *body, size_t size, int maxurls,
+                     hts_boolean *is_index, hts_sitemap_handler handler,
+                     void *arg);
+
+/* --- Engine glue (needs a live httrackp). --- */
+
+/* Queue the first sitemap document of the mirror: the explicit --sitemap-url,
+   or the start host's /robots.txt probe for --sitemap. `starturl` is the first
+   command-line seed. No-op when neither option is set. */
+void hts_sitemap_seed(httrackp *opt, const char *starturl);
+
+/* Act on the start host's robots.txt once its rules are installed: queue the
+   Sitemap: URLs it names (newline-separated, from robots_parse), or the
+   well-known /sitemap.xml when it names none. No-op unless --sitemap. */
+void hts_sitemap_robots(httrackp *opt, const char *adr, const char *sitemaps);
+
+/* Carry the sitemap marking of (adr,fil) over to the target of a redirect the
+   engine has already queued, so a moved sitemap is still ingested. */
+void hts_sitemap_redirect(httrackp *opt, const char *adr, const char *fil,
+                          const char *newadr, const char *newfil);
+
+/* HTS_TRUE when (adr,fil) is a queued sitemap document awaiting ingestion. */
+hts_boolean hts_sitemap_pending(httrackp *opt, const char *adr,
+                                const char *fil);
+
+/* Ingest a fetched sitemap document (or the robots.txt probe): seed its URLs
+   through the wizard via htsAddLink, and queue nested sitemaps. `str` supplies
+   the parser context of the document being processed. */
+void hts_sitemap_ingest(httrackp *opt, htsmoduleStruct *str, const char *adr,
+                        const char *fil, const char *body, size_t size);
+
+/* Release the ingestion state held in opt (NULL-safe, idempotent). */
+void hts_sitemap_free(httrackp *opt);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

src/htsthread.c

@@ -44,9 +44,18 @@ Please visit our Website: http://www.httrack.com
 #endif
 #endif
 
+/* Outstanding threads, counted at spawn rather than by the child at entry, so
+   that a caller which spawns and immediately waits still joins them (#747). */
 static int process_chain = 0;
 static htsmutex process_chain_mutex = HTSMUTEX_INIT;
 
+static void process_chain_add(int delta) {
+  hts_mutexlock(&process_chain_mutex);
+  process_chain += delta;
+  assertf(process_chain >= 0);
+  hts_mutexrelease(&process_chain_mutex);
+}
+
 HTSEXT_API void htsthread_wait(void) {
   htsthread_wait_n(0);
 }
@@ -99,20 +108,12 @@ static void *hts_entry_point(void *tharg)
   void *const arg = s_args->arg;
   void (*fun) (void *arg) = s_args->fun;
 
-  free(tharg);
-
-  hts_mutexlock(&process_chain_mutex);
-  process_chain++;
-  assertf(process_chain > 0);
-  hts_mutexrelease(&process_chain_mutex);
+  freet(tharg);
 
   /* run */
   fun(arg);
 
-  hts_mutexlock(&process_chain_mutex);
-  process_chain--;
-  assertf(process_chain >= 0);
-  hts_mutexrelease(&process_chain_mutex);
+  process_chain_add(-1);
 #ifdef _WIN32
   return 0;
 #else
@@ -122,18 +123,20 @@ static void *hts_entry_point(void *tharg)
 
 /* create a thread */
 HTSEXT_API int hts_newthread(void (*fun) (void *arg), void *arg) {
-  hts_thread_s *s_args = malloc(sizeof(hts_thread_s));
+  hts_thread_s *s_args = malloct(sizeof(hts_thread_s));
 
   assertf(s_args != NULL);
   s_args->arg = arg;
   s_args->fun = fun;
+  process_chain_add(1);
 #ifdef _WIN32
   {
     unsigned int idt;
     HANDLE handle =
       (HANDLE) _beginthreadex(NULL, 0, hts_entry_point, s_args, 0, &idt);
     if (handle == 0) {
-      free(s_args);
+      process_chain_add(-1);
+      freet(s_args);
       return -1;
     } else {
       /* detach the thread from the main process so that is can be independent */
@@ -151,7 +154,8 @@ HTSEXT_API int hts_newthread(void (*fun) (void *arg), void *arg) {
         || pthread_attr_setstacksize(&attr, stackSize) != 0
         || (retcode =
             pthread_create(&handle, &attr, hts_entry_point, s_args)) != 0) {
-      free(s_args);
+      process_chain_add(-1);
+      freet(s_args);
       return -1;
     } else {
       /* detach the thread from the main process so that is can be independent */

src/htstools.c

@@ -276,6 +276,21 @@ int ident_url_relatif(const char *lien, const char *origin_adr,
   return ok;
 }
 
+/* Bounded substring search: bodies and archive records carry NUL bytes, so
+   strstr() would stop at the first one. */
+const char *hts_memstr(const char *hay, size_t haylen, const char *needle,
+                       size_t nlen) {
+  size_t i;
+
+  if (nlen == 0 || haylen < nlen)
+    return NULL;
+  for (i = 0; i + nlen <= haylen; i++) {
+    if (hay[i] == *needle && memcmp(hay + i, needle, nlen) == 0)
+      return hay + i;
+  }
+  return NULL;
+}
+
 // créer dans s, à partir du chemin courant curr_fil, le lien vers link (absolu)
 // un ident_url_relatif a déja été fait avant, pour que link ne soit pas un chemin relatif
 int lienrelatif(char *s, size_t ssize, const char *link, const char *curr_fil) {
@@ -1428,3 +1443,15 @@ HTSEXT_API hts_boolean hts_findissystem(find_handle find) {
   }
   return 0;
 }
+
+hts_boolean hts_rename_over(const char *src, const char *dst) {
+  char csrc[CATBUFF_SIZE], cdst[CATBUFF_SIZE];
+
+  fconv(csrc, sizeof(csrc), src);
+  fconv(cdst, sizeof(cdst), dst);
+  if (RENAME(csrc, cdst) == 0)
+    return HTS_TRUE;
+  /* RENAME does not clobber an existing target on Windows. */
+  (void) UNLINK(cdst);
+  return RENAME(csrc, cdst) == 0 ? HTS_TRUE : HTS_FALSE;
+}

src/htstools.h

@@ -61,6 +61,11 @@ typedef struct lien_adrfilsave lien_adrfilsave;
 int ident_url_relatif(const char *lien, const char *origin_adr,
                       const char *origin_fil,
                       lien_adrfil* const adrfil);
+/* Bounded substring search over data that may hold NUL bytes; NULL if absent.
+ */
+const char *hts_memstr(const char *hay, size_t haylen, const char *needle,
+                       size_t nlen);
+
 int lienrelatif(char *s, size_t ssize, const char *link, const char *curr);
 int link_has_authority(const char *lien);
 int link_has_authorization(const char *lien);
@@ -132,6 +137,10 @@ HTSEXT_API hts_boolean hts_findisdir(find_handle find);
 HTSEXT_API hts_boolean hts_findisfile(find_handle find);
 HTSEXT_API hts_boolean hts_findissystem(find_handle find);
 
+/* Move src onto dst, replacing an existing dst; HTS_TRUE on success. Both
+   paths are fconv()'d. */
+hts_boolean hts_rename_over(const char *src, const char *dst);
+
 #endif
 
 #endif

src/htswarc.c

@@ -964,16 +964,6 @@ static zipFile wacz_zip_open(const char *path) {
   return zipOpen2_64(path, 0 /*create*/, NULL, &ff);
 }
 
-/* Move src onto dst (UTF-8/Windows-safe); RENAME won't clobber on Windows, so
-   fall back to unlink+rename. Returns 0 on success. */
-static int wacz_rename_over(const char *src, const char *dst) {
-  char cs[CATBUFF_SIZE], cd[CATBUFF_SIZE];
-  if (RENAME(fconv(cs, sizeof(cs), src), fconv(cd, sizeof(cd), dst)) == 0)
-    return 0;
-  (void) UNLINK(fconv(cd, sizeof(cd), dst));
-  return RENAME(fconv(cs, sizeof(cs), src), fconv(cd, sizeof(cd), dst));
-}
-
 /* Package the segment(s) + .cdx + a generated pages.jsonl into <base>.wacz at
    crawl end (the archive file(s) and .cdx are already closed on disk). */
 static void warc_wacz_package(warc_writer *w) {
@@ -1092,7 +1082,7 @@ static void warc_wacz_package(warc_writer *w) {
     hts_log_print(w->opt, LOG_WARNING,
                   "WACZ: packaging failed, kept existing %s untouched",
                   waczpath);
-  } else if (wacz_rename_over(tmppath, waczpath) != 0) {
+  } else if (!hts_rename_over(tmppath, waczpath)) {
     (void) UNLINK(fconv(catbuff, sizeof(catbuff), tmppath));
     hts_log_print(w->opt, LOG_WARNING | LOG_ERRNO,
                   "WACZ: could not finalize %s", waczpath);

src/htsweb.c

@@ -101,8 +101,8 @@ static void htsweb_sig_brpipe(int code) {
   /* ignore */
 }
 
-/* Number of background threads */
-static int background_threads = 0;
+/* Threads that never return; no wait may count on them draining. */
+static int nonjoinable_threads = 0;
 
 /* Server/client ping handling */
 static htsmutex pingMutex = HTSMUTEX_INIT;
@@ -224,9 +224,7 @@ int main(int argc, char *argv[]) {
 #ifdef HTS_USESWF
   smallserver_setkey("USESWF", "1");
 #endif
-#ifdef HTS_USEZLIB
   smallserver_setkey("USEZLIB", "1");
-#endif
 #ifdef _WIN32
   smallserver_setkey("WIN32", "1");
 #endif
@@ -299,15 +297,19 @@ int main(int argc, char *argv[]) {
 
   /* pinger */
   if (parentPid > 0) {
-    hts_newthread(client_ping, (void *) (uintptr_t) parentPid);
-    background_threads++; /* Do not wait for this thread! */
+    if (hts_newthread(client_ping, (void *) (uintptr_t) parentPid) == 0) {
+#ifndef _WIN32
+      nonjoinable_threads++; /* client_ping() only ever leaves through exit() */
+#endif
+    }
     smallserver_setpinghandler(pingHandler, NULL);
   }
 
   /* launch */
   ret = help_server(argv[1], defaultPort, bindAddr);
 
-  htsthread_wait_n(background_threads - 1);
+  /* Drain everything a mirror may still have in flight, the pinger aside. */
+  htsthread_wait_n(nonjoinable_threads);
   hts_uninit();
 
 #ifdef _WIN32
@@ -382,7 +384,6 @@ void webhttrack_main(char *cmd) {
   commandRunning = 1;
   DEBUG(fprintf(stderr, "commandRunning=1\n"));
   hts_newthread(back_launch_cmd, (void *) strdup(cmd));
-  background_threads++; /* Do not wait for this thread! */
 }
 
 void webhttrack_lock(void) {
@@ -423,8 +424,8 @@ static int webhttrack_runmain(httrackp * opt, int argc, char **argv) {
   /* Rock'in! */
   ret = hts_main2(argc, argv, opt);
 
-  /* Wait for pending threads to finish */
-  htsthread_wait_n(background_threads);
+  /* Wait for pending threads to finish; the pinger and this thread stay. */
+  htsthread_wait_n(nonjoinable_threads + 1);
 
   return ret;
 }

src/htswizard.c

@@ -151,6 +151,23 @@ static hts_boolean is_embed_pair(const htspair_t *table, const char *tag,
   return HTS_FALSE;
 }
 
+/* The engine's robots.txt verdict for (adr,fil). Under HTS_ROBOTS_SOMETIMES an
+   explicit filter acceptance overrides the ban, which is why the filter outcome
+   is an input; the sitemap fetcher asks the same question outside the wizard.
+ */
+hts_boolean hts_robots_forbids(httrackp *opt, const char *adr, const char *fil,
+                               hts_boolean filters_decided,
+                               hts_boolean filters_refused) {
+  if (!opt->robots || opt->robotsptr == NULL)
+    return HTS_FALSE;
+  if (checkrobots((robots_wizard *) opt->robotsptr, adr, fil) != -1)
+    return HTS_FALSE;
+  if (filters_decided && !filters_refused &&
+      opt->robots == HTS_ROBOTS_SOMETIMES)
+    return HTS_FALSE;
+  return HTS_TRUE;
+}
+
 static int hts_acceptlink_(httrackp * opt, int ptr,
                            const char *adr, const char *fil, const char *tag,
                            const char *attribute, int *set_prio_to,
@@ -576,30 +593,26 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
       }
     }
     // vérifier robots.txt
-    if (opt->robots) {
-      int r = checkrobots(_ROBOTS, adr, fil);
-
-      if (r == -1) {            // interdiction
+    if (opt->robots && checkrobots(_ROBOTS, adr, fil) == -1) {
 #if DEBUG_ROBOTS
-        printf("robots.txt forbidden: %s%s\n", adr, fil);
+      printf("robots.txt forbidden: %s%s\n", adr, fil);
 #endif
-        // question résolue, par les filtres, et mode robot non strict
-        if ((!question) && (filters_answer) &&
-            (opt->robots == HTS_ROBOTS_SOMETIMES) && (forbidden_url != 1)) {
-          r = 0;                // annuler interdiction des robots
-          if (!forbidden_url) {
-            hts_log_print(opt, LOG_DEBUG,
-                          "Warning link followed against robots.txt: link %s at %s%s",
-                          l, adr, fil);
-          }
-        }
-        if (r == -1) {          // interdire
-          forbidden_url = 1;
-          question = 0;
-          hts_log_print(opt, LOG_DEBUG,
-                        "(robots.txt) forbidden link: link %s at %s%s", l, adr,
-                        fil);
+      if (!hts_robots_forbids(opt, adr, fil,
+                              (!question && filters_answer) ? HTS_TRUE
+                                                            : HTS_FALSE,
+                              (forbidden_url == 1) ? HTS_TRUE : HTS_FALSE)) {
+        if (!forbidden_url) {
+          hts_log_print(
+              opt, LOG_DEBUG,
+              "Warning link followed against robots.txt: link %s at %s%s", l,
+              adr, fil);
         }
+      } else {
+        forbidden_url = 1;
+        question = 0;
+        hts_log_print(opt, LOG_DEBUG,
+                      "(robots.txt) forbidden link: link %s at %s%s", l, adr,
+                      fil);
       }
     }
 

src/htswizard.h

@@ -49,6 +49,13 @@ typedef struct httrackp httrackp;
 typedef struct lien_url lien_url;
 #endif
 
+/* The engine's robots.txt verdict for (adr,fil): HTS_TRUE when the fetch is
+   forbidden. `filters_decided`/`filters_refused` carry the filter outcome,
+   which overrides a ban under -s1 (HTS_ROBOTS_SOMETIMES). */
+hts_boolean hts_robots_forbids(httrackp *opt, const char *adr, const char *fil,
+                               hts_boolean filters_decided,
+                               hts_boolean filters_refused);
+
 int hts_acceptlink(httrackp * opt, int ptr,
                    const char *adr, const char *fil,
                    const char *tag, const char *attribute,

src/htszlib.c

@@ -40,7 +40,6 @@ Please visit our Website: http://www.httrack.com
 #include "htscodec.h"
 #include "htszlib.h"
 
-#if HTS_USEZLIB
 /* zlib */
 /*
 #include <zlib.h>
@@ -274,4 +273,3 @@ const char *hts_get_zerror(int err) {
     break;
   }
 }
-#endif

src/httrack.c

@@ -306,8 +306,8 @@ int main(int argc, char **argv) {
     fprintf(stderr, "* %s\n", hts_errmsg(opt));
   }
   global_opt = NULL;
+  htsthread_wait(); /* pending threads still read opt */
   hts_free_opt(opt);
-  htsthread_wait();             /* wait for pending threads */
   hts_uninit();
 
 #ifdef _WIN32

src/libhttrack.vcxproj

@@ -140,6 +140,7 @@
     <ClCompile Include="htszlib.c" />
     <ClCompile Include="htswarc.c" />
     <ClCompile Include="htschanges.c" />
+    <ClCompile Include="htssitemap.c" />
     <ClCompile Include="md5.c" />
     <ClCompile Include="minizip\ioapi.c" />
     <ClCompile Include="minizip\iowin32.c" />

tests/01_engine-addlink.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+# an empty current path underflowed htsAddLink's codebase walk (#730).
+
+set -euo pipefail
+
+httrack -O /dev/null -#test=addlink | grep -q "addlink self-test OK"

tests/01_engine-structcheck.test

@@ -0,0 +1,12 @@
+#!/bin/bash
+#
+# structcheck(): the path-length guard, and the <name>.txt rename that once
+# built its target with an unbounded sprintf (#745).
+
+set -euo pipefail
+
+dir=$(mktemp -d)
+trap 'rm -rf "$dir"' EXIT
+
+httrack -O /dev/null -#test=structcheck "$dir" |
+    grep -q "structcheck self-test OK"

tests/01_engine-threadwait.test

@@ -0,0 +1,28 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_threadwait_st.XXXXXX") || exit 1
+trap 'rm -rf "$tmpdir"' EXIT HUP INT QUIT PIPE TERM
+
+# No pipe into grep: SIGPIPE would mask a failing exit status.
+expect_ok() {
+    local label="$1" out
+    shift
+    out=$("$@" 2>&1) || {
+        echo "FAIL: ${label} exited non-zero: ${out}"
+        exit 1
+    }
+    case "$out" in
+    *"${label}: OK"*) ;;
+    *)
+        echo "FAIL: ${out}"
+        exit 1
+        ;;
+    esac
+}
+
+# A thread is outstanding from the moment hts_newthread() returns, so a wait
+# that follows the spawn joins it, and wait_n(n) still leaves n behind (#747).
+expect_ok "threadwait self-test" httrack -O "${tmpdir}/o1" -#test=threadwait

tests/01_zlib-sitemap.test

@@ -0,0 +1,10 @@
+#!/bin/bash
+#
+# Sitemap parser self-test: <loc> extraction, entity decoding, URL and length
+# rejections, the URL cap, gzip framing and robots.txt Sitemap: records.
+
+set -euo pipefail
+
+out=$(httrack -O /dev/null '-#test=sitemap')
+echo "$out"
+test "$out" = "sitemap self-test OK"

tests/43_local-update-truncate.test

@@ -18,6 +18,7 @@ set -euo pipefail
 bash "$top_srcdir/tests/local-crawl.sh" \
     --rerun-args '--update -M400000' \
     --log-found 'More than 400000 bytes have been transferred.. giving up' \
+    --log-not-found 'could not restore' \
     --found bigtrunc/slow.bin \
     --file-min-bytes bigtrunc/slow.bin 655360 \
     --file-min-bytes bigtrunc/fast.bin 655360 \

tests/65_port-siblings.test

@@ -79,6 +79,29 @@ done
 # 65535 is a valid port the old "< 65535" bound refused
 web_accepted 65535
 
+# --- htsserver returns from main() instead of blocking at exit -------------
+# The exit wait must exclude exactly the threads that never return (#753).
+# $tmp has no lang.def, so the server fails right after announcing and main()
+# reaches the wait on its own; rc, not EXITED, carries the verdict.
+
+web_exits() {
+    local rc=0
+
+    : >"$tmp/exit.log"
+    run_with_timeout 30 htsserver "$tmp" "$@" >"$tmp/exit.log" 2>&1 || rc=$?
+    grep -q "^EXITED" "$tmp/exit.log" ||
+        ! echo "FAIL: #753: htsserver ${*:-(no options)} never finished serving" || exit 1
+    # exactly 1, not merely "not 124": a crash or an assertf abort also escapes
+    # the wait, and would otherwise read as a pass
+    test "$rc" -eq 1 ||
+        ! echo "FAIL: #753: htsserver ${*:-(no options)} exited $rc, want 1" || exit 1
+}
+
+# no pinger: the excluded count went negative
+web_exits
+# a pinger, which never returns and so must stay excluded
+web_exits --ppid $$
+
 # --- proxytrack <proxy-addr:port> <ICP-addr:port> --------------------------
 # A bad argument falls through to the usage screen; it had no range check at
 # all, so 65616 quietly listened on port 80. A valid one binds and blocks.

tests/74_local-warc-wacz.test

@@ -5,11 +5,16 @@
 # real gate: STORE-mode entries, the fixed layout, recomputed sha256 digests and
 # the datapackage-digest chain (plus py-wacz/pywb when importable). The crawl
 # skips cleanly on a build without OpenSSL (no conformant SHA-256 -> no package).
+#
+# The cacheless second pass repackages over the .wacz the first one left: the
+# clobber, not the happy rename, is what breaks when a platform refuses to
+# rename onto an existing file (#726).
 
 set -eu
 
 : "${top_srcdir:=..}"
 
 bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --wacz-validate \
+    --rerun-args '-C0' --log-not-found 'could not finalize' \
     --found 'mini304/index.html' --found 'mini304/page.html' \
     httrack 'BASEURL/mini304/index.html' --warc-file warc-out --wacz

tests/90_webhttrack-checkbox-clear.test

@@ -149,6 +149,7 @@ BOXES = [
     ("keepqueryorder", "KeepQueryOrder", "--keep-query-order", None),
     ("toler", "TolerantRequests", "--tolerant", None),
     ("http10", "HTTP10", "--http-10", None),
+    ("sitemap", "Sitemap", "--sitemap", None),
     ("warc", "Warc", "--warc", None),
     ("changes", "Changes", "--changes", None),
     ("norecatch", "NoRecatch", "--do-not-recatch", None),

tests/93_local-changes.test

@@ -94,10 +94,7 @@ expect_counts_match() {
     echo "OK"
 }
 lines() { printf '%s\n' "$@" | sort; }
-# A connection killed before the status line surfaces differently per platform
-# (macOS truncates the file, #748; Linux leaves it), so reset.bin is asserted on
-# its own and kept out of the exact lists.
-listed_but_reset() { listed "$1" | grep -v '/reset\.bin$' | sort; }
+digest() { cksum <"$1" | tr -d '[:space:]'; }
 
 # --- pass 1: nothing to compare against --------------------------------------
 httrack "${common[@]}" -O "$out" --purge-old=0 "${base}/changes/index.html" \
@@ -120,6 +117,7 @@ grep -aq "first crawl" "${out}/hts-log.txt" || {
 }
 
 host="127.0.0.1_${port}"
+resetdigest=$(digest "${out}/${host}/changes/reset.bin")
 # A leftover from some earlier failed attempt, at a name pass 2 fetches for the
 # first time: on disk, but never part of the previous mirror, so it is new.
 printf 'leftover junk' >"${out}/${host}/changes/fresh.html"
@@ -144,21 +142,19 @@ expect "gone is doomed.html and the old redirect target" \
 expect "changed is exactly the four moved resources" \
     "$(lines "${host}/changes/coded.bin" "${host}/changes/index.html" \
         "${host}/changes/moved.bin" "${host}/changes/moved.html")" \
-    "$(listed_but_reset changed)"
+    "$(listed changed | sort)"
 # Re-served byte for byte, 200, no Last-Modified, no ETag. flaky.bin gets there
 # through a failed transfer and a retry, so its file is notified twice;
 # redirtarget.html arrives behind a 302. sized.html has a byte-identical
 # payload, but the rewritten link to the renamed redirect target makes the file
-# on disk change length.
-expect "unchanged is exactly the six stable resources" \
+# on disk change length. reset.bin never completes a transfer (#746), so its
+# previous copy stands.
+expect "unchanged is exactly the seven stable resources" \
     "$(lines "${host}/changes/codedstable.bin" "${host}/changes/flaky.bin" \
-        "${host}/changes/redirtarget.html" "${host}/changes/sized.html" \
-        "${host}/changes/stable.bin" "${host}/changes/stable.html")" \
-    "$(listed_but_reset unchanged)"
-# reset.bin never completes a transfer, so it drops out of new.lst with its
-# mirrored copy still there. Whatever else it is, it is not a deletion.
-expect "a failed re-fetch is never reported gone" "" \
-    "$(listed gone | grep '/reset\.bin$' || true)"
+        "${host}/changes/redirtarget.html" "${host}/changes/reset.bin" \
+        "${host}/changes/sized.html" "${host}/changes/stable.bin" \
+        "${host}/changes/stable.html")" \
+    "$(listed unchanged | sort)"
 expect_counts_match "pass 2 counts match its lists"
 
 # Every mirrored file appears once and only once, across all four buckets.
@@ -192,19 +188,15 @@ test -f "${out}/${host}/changes/doomed.html" || {
     exit 1
 }
 echo "OK"
-printf '[a failed transfer keeps its file] ..\t'
-test -f "${out}/${host}/changes/reset.bin" || {
-    echo "FAIL: reset.bin lost its previous copy"
-    exit 1
-}
-echo "OK"
+expect "a failed transfer keeps its bytes" "$resetdigest" \
+    "$(digest "${out}/${host}/changes/reset.bin")"
 
 # --- pass 3: the same run with purging on ------------------------------------
 httrack "${common[@]}" -O "$out" --update "${base}/changes/index.html" \
     >"${tmpdir}/log3" 2>&1
 expect "the report says files were purged" "true" "$(field purged)"
 expect "gone is the page that only pass 2 linked" \
-    "${host}/changes/transient.html" "$(listed_but_reset gone)"
+    "${host}/changes/transient.html" "$(listed gone | sort)"
 printf '[a purged file is off disk] ..\t'
 test ! -f "${out}/${host}/changes/transient.html" || {
     echo "FAIL: transient.html survived --purge-old"

tests/95_local-sitemap.test

@@ -0,0 +1,134 @@
+#!/bin/bash
+#
+# --sitemap seeds the crawl from robots.txt -> sitemapindex -> gzipped urlset.
+# start.html links to nothing, so orphan*.html can only arrive through the
+# sitemap; deep1.html proves the seeds keep a full depth budget under -r2, and
+# the off-host page and child sitemap must both be refused.
+
+set -eu
+
+: "${top_srcdir:=..}"
+
+crawl() { bash "$top_srcdir/tests/local-crawl.sh" "$@"; }
+
+# robots.txt Sitemap: -> index -> .xml.gz, seeds behaving like -r2 seeds. The
+# log assertions pin which route was taken: the two documents are served from
+# both /sitemapdir/index.xml and the well-known /sitemap.xml, so "some sitemap
+# was read" would pass either way. --not-found pins ingestion-only: the sitemap
+# documents feed the crawl but never land in the mirror.
+# --rerun also walks the update path over a mirror holding sitemap seeds.
+crawl --errors 0 --rerun \
+    --found 'sitemapdir/orphan1.html' \
+    --found 'sitemapdir/orphan2.html' \
+    --found 'sitemapdir/deep1.html' \
+    --not-found 'sitemapdir/index.xml' \
+    --not-found 'sitemapdir/pages.xml.gz' \
+    --log-found '2 of 3 URL\(s\) added from 127\.0\.0\.1:[0-9]+/sitemapdir/pages\.xml\.gz' \
+    --log-found '1 of 2 child sitemap\(s\) listed by 127\.0\.0\.1:[0-9]+/sitemapdir/index\.xml' \
+    --log-found 'ignoring off-host child sitemap' \
+    --log-not-found '/sitemap\.xml' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2
+
+# Negative control: without the option nothing but the start page is reached.
+crawl --errors 0 \
+    --found 'sitemapdir/start.html' \
+    --not-found 'sitemapdir/orphan1.html' \
+    --not-found 'sitemapdir/orphan2.html' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2
+
+# Sitemap URLs are not a filter bypass: a -*orphan2* rule still rejects one.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --not-found 'sitemapdir/orphan2.html' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2 '-*orphan2*'
+
+# A robots.txt naming no sitemap falls back to the well-known /sitemap.xml.
+# The test server drops its Sitemap: record for this User-Agent.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --log-found 'listed by 127\.0\.0\.1:[0-9]+/sitemap\.xml' \
+    --log-not-found 'sitemapdir/index\.xml' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2 -F 'nositemap-agent'
+
+# --sitemap-url alone reads the named document and probes nothing.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --found 'sitemapdir/orphan2.html' \
+    --log-not-found 'sitemapdir/index\.xml' \
+    --log-not-found '/sitemap\.xml' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 \
+    --sitemap-url 'BASEURL/sitemapdir/pages.xml.gz'
+
+# The two options are additive: an unfetchable --sitemap-url is parsed as an
+# empty document and does not stop --sitemap from seeding the crawl.
+crawl --errors-content 1 \
+    --found 'sitemapdir/orphan1.html' \
+    --log-found 'Sitemap: 0 of 0 URL\(s\) added' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2 \
+    --sitemap-url 'BASEURL/sitemapdir/missing.xml'
+
+# The sitemapindex nesting cap stops the chain before its deepest urlset. The
+# positive control is the page one level inside the cap: without it, a cap
+# mutated to 0 (nothing followed) would pass this just as well.
+crawl --errors 0 \
+    --found 'sitemapdir/cap3.html' \
+    --not-found 'sitemapdir/cap4.html' \
+    --log-found 'Sitemap: cap reached' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 \
+    --sitemap-url 'BASEURL/sitemapdir/chain0.xml'
+
+# A site cannot widen a subtree crawl by putting its sitemap at the root: the
+# page below the start directory is seeded, the one above it is refused.
+crawl --errors 0 \
+    --found 'deep/dir/below.html' \
+    --not-found 'elsewhere/updir.html' \
+    httrack 'BASEURL/deep/dir/start.html' --sitemap -r3 -F 'scopesitemap-agent'
+
+# How far a sitemap fetch is gated depends on who asked for it, so the three
+# cases below have to differ: one "robots is honoured" assertion would hide a
+# regression in either direction. The harness disables robots, hence -s2 here.
+
+# We guessed /sitemap.xml, so a Disallow on it wins.
+crawl --errors 0 \
+    --not-found 'sitemapdir/orphan1.html' \
+    --log-found 'Sitemap: robots.txt forbids' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2 -s2 \
+    -F 'denysitemap-agent'
+
+# The site declared it through a Sitemap: line, which the same Disallow does
+# not retract.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --log-not-found 'Sitemap: robots.txt forbids' \
+    httrack 'BASEURL/sitemapdir/start.html' --sitemap -r2 -s2 \
+    -F 'denydeclared-agent'
+
+# The user named it, which is the same intent as a start URL: not refused
+# either, even though robots.txt forbids that exact path.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --log-not-found 'Sitemap: robots.txt forbids' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 -s2 -F 'denysitemap-agent' \
+    --sitemap-url 'BASEURL/sitemap.xml'
+
+# A child sitemap is a fetch like any other: a filter rejecting it stops the
+# whole subtree, so the page only it lists is never reached.
+crawl --errors 0 \
+    --not-found 'sitemapdir/gated.html' \
+    --log-found 'Sitemap: filter rule #[0-9]+ refuses' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 '-*filtered.xml*' \
+    --sitemap-url 'BASEURL/sitemapdir/gatedindex.xml'
+
+# Control: without that filter the same chain does reach the page.
+crawl --errors 0 \
+    --found 'sitemapdir/gated.html' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 \
+    --sitemap-url 'BASEURL/sitemapdir/gatedindex.xml'
+
+# A redirected sitemap is still ingested: the marking follows the 301.
+crawl --errors 0 \
+    --found 'sitemapdir/orphan1.html' \
+    --log-found 'moved\.xml redirects to .*pages\.xml\.gz' \
+    --log-found 'URL\(s\) added from 127\.0\.0\.1:[0-9]+/sitemapdir/pages\.xml\.gz' \
+    httrack 'BASEURL/sitemapdir/start.html' -r2 \
+    --sitemap-url 'BASEURL/sitemapdir/moved.xml'

tests/96_local-refetch-keep.test

@@ -0,0 +1,28 @@
+#!/bin/bash
+#
+# A re-fetch cut mid-header must leave the mirrored file alone (#748): unfixed,
+# the aborted read's leftover buffer lands on it. err.bin is the control, an
+# HTTP 500 on the same resource already keeping its copy; stay.bin answers
+# normally with a new body, so a fix that stopped overwriting anything fails.
+#
+# Purging is off: an update purge deletes both files for an unrelated reason
+# (#746), which would hide what this asserts.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" \
+    --rerun-args '--update --purge-old=0' \
+    --log-found 'after 2 retries at link .*keep/page\.html' \
+    --log-found 'after 2 retries at link .*keep/data\.bin' \
+    --file-matches 'keep/page.html' 'KEEP-PAGE-V1' \
+    --file-not-matches 'keep/page.html' 'HTTP/1\.0 200' \
+    --file-matches 'keep/data.bin' 'KEEP-BIN-V1' \
+    --file-not-matches 'keep/data.bin' 'HTTP/1\.0 200' \
+    --file-min-bytes 'keep/data.bin' 2048 \
+    --file-matches 'keep/err.bin' 'KEEP-ERR-V1' \
+    --file-min-bytes 'keep/err.bin' 2048 \
+    --file-matches 'keep/stay.bin' 'KEEP-STAY-V2' \
+    --file-min-bytes 'keep/stay.bin' 2048 \
+    httrack 'BASEURL/keep/index.html' --retries=2

tests/Makefile.am

@@ -30,6 +30,7 @@ TEST_EXTENSIONS = .test
 TEST_LOG_COMPILER = $(BASH)
 TESTS = \
 	00_runnable.test \
+	01_engine-addlink.test \
 	01_engine-changes.test \
 	01_engine-charset.test \
 	01_engine-cmdline.test \
@@ -81,7 +82,9 @@ TESTS = \
 	01_engine-status.test \
 	01_engine-stripquery.test \
 	01_engine-strsafe.test \
+	01_engine-structcheck.test \
 	01_engine-syscharset.test \
+	01_engine-threadwait.test \
 	01_engine-topindex.test \
 	01_engine-urlhack.test \
 	01_engine-unescape-bounds.test \
@@ -91,6 +94,7 @@ TESTS = \
 	01_engine-xfread.test \
 	01_zlib-acceptencoding.test \
 	01_zlib-warc.test \
+	01_zlib-sitemap.test \
 	01_zlib-warc-cdx.test \
 	01_zlib-warc-wacz.test \
 	01_zlib-contentcodings.test \
@@ -192,6 +196,8 @@ TESTS = \
 	91_webhttrack-directory.test \
 	92_local-proxytrack-ndx-fields.test \
 	93_local-changes.test \
-	94_local-single-file.test
+	94_local-single-file.test \
+	95_local-sitemap.test \
+	96_local-refetch-keep.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -57,6 +57,8 @@ rerun_dead=
 tmpdir=
 serverpid=
 crawlpid=
+wacz_poisoned=
+wacz_poison="stale-wacz-that-a-second-pass-must-replace"
 
 function warning {
     echo "** $*" >&2
@@ -272,6 +274,14 @@ if test -n "$warc_validate"; then
     test -z "$w1" || cp "$w1" "${tmpdir}/warc-pass1.gz"
 fi
 
+# Poison the first-pass .wacz when a second pass follows: repackaging moves the
+# new archive over it, so the marker must be gone afterwards (#726). Poisoning
+# beats comparing the two packages, which can come out byte-identical.
+if test -n "$wacz_validate" && test -n "${rerun}${rerun_args}"; then
+    wacz_poisoned=$(find "$mirrorroot" -maxdepth 2 -name '*.wacz' 2>/dev/null | sort | tail -n1)
+    test -z "$wacz_poisoned" || echo "$wacz_poison" >"$wacz_poisoned"
+fi
+
 # --- optional second pass: re-mirror into the same dir (cache/update path) ----
 if test -n "$rerun"; then
     info "re-running httrack (update pass)"
@@ -416,6 +426,12 @@ if test -n "$wacz_validate"; then
         fi
         die "no .wacz file produced under $mirrorroot"
     fi
+    if test -n "$wacz_poisoned"; then
+        info "checking the second pass replaced the .wacz"
+        grep -q "$wacz_poison" "$wacz_poisoned" 2>/dev/null &&
+            die "stale .wacz kept: $wacz_poisoned"
+        result "OK"
+    fi
     validator=$(nativepath "${testdir}/wacz-validate.py")
     info "validating WACZ package"
     "$python" "$validator" "$(nativepath "$wacz")" >&2 || die "WACZ validation failed"

tests/local-server.py

@@ -18,6 +18,7 @@ import base64
 import gzip
 import hashlib
 import os
+import re
 import sys
 import time
 from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
@@ -542,8 +543,36 @@ class Handler(SimpleHTTPRequestHandler):
             return self.fail_cookie(name)
         self.send_html("\tThis is the secret.")
 
+    # A User-Agent carrying NO_SITEMAP_UA gets a robots.txt with no Sitemap:
+    # record, so a test can drive the /sitemap.xml fallback instead.
+    NO_SITEMAP_UA = "nositemap"
+    # ... and one that additionally Disallows the well-known location, so the
+    # fallback has to be refused by the rules this very body carries.
+    DENY_SITEMAP_UA = "denysitemap"
+    # ... the same Disallow, but with the sitemap also declared: the
+    # declaration is the site inviting the fetch and must win.
+    DENY_DECLARED_UA = "denydeclared"
+    # ... and one that points the sitemap at the site root, to check a subtree
+    # crawl is not widened by where the site chooses to put its sitemap.
+    SCOPE_SITEMAP_UA = "scopesitemap"
+
     def route_robots(self):
-        body = b"User-agent: *\nDisallow:\n"
+        # The Sitemap: record is group-independent; only --sitemap acts on it.
+        ua = self.headers.get("User-Agent") or ""
+        host = self.headers.get("Host")
+        body = "User-agent: *\nDisallow:\n"
+        if self.DENY_DECLARED_UA in ua:
+            body = (
+                "User-agent: *\nDisallow: /sitemap.xml\n"
+                f"Sitemap: http://{host}/sitemap.xml\n"
+            )
+        elif self.DENY_SITEMAP_UA in ua:
+            body = "User-agent: *\nDisallow: /sitemap.xml\n"
+        elif self.SCOPE_SITEMAP_UA in ua:
+            body += f"Sitemap: http://{host}/scopesitemap.xml\n"
+        elif self.NO_SITEMAP_UA not in ua:
+            body += f"Sitemap: http://{host}/sitemapdir/index.xml\n"
+        body = body.encode()
         self.send_response(200)
         self.send_header("Content-Type", "text/plain")
         self.send_header("Content-Length", str(len(body)))
@@ -551,6 +580,132 @@ class Handler(SimpleHTTPRequestHandler):
         if self.command != "HEAD":
             self.wfile.write(body)
 
+    # --- sitemap ingestion (issue #712) ------------------------------------
+    # start.html links to nothing, so orphan*.html are reachable only through
+    # the sitemap. deep1.html proves the seeds keep a full depth budget; the
+    # off-host page <loc> must be dropped by the travel scope, and the off-host
+    # child sitemap by the ingester's same-host rule. The index is served both
+    # from /sitemapdir/ (named by robots.txt) and from the well-known
+    # /sitemap.xml (the fallback).
+
+    def route_sitemap_index(self):
+        host = self.headers.get("Host")
+        self.send_raw(
+            '<?xml version="1.0" encoding="UTF-8"?>\n'
+            '<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">'
+            f"<sitemap><loc>http://{host}/sitemapdir/pages.xml.gz</loc></sitemap>"
+            "<sitemap><loc>http://sitemap-offhost.invalid/s.xml</loc></sitemap>"
+            "</sitemapindex>\n".encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_pages(self):
+        host = self.headers.get("Host")
+        xml = (
+            '<?xml version="1.0" encoding="UTF-8"?>\n'
+            '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">'
+            f"<url><loc>http://{host}/sitemapdir/orphan1.html</loc></url>"
+            "<url><loc>http://sitemap-offhost.invalid/x.html</loc></url>"
+            f"<url><loc>http://{host}/sitemapdir/orphan2.html</loc></url>"
+            "</urlset>\n"
+        ).encode()
+        self.send_raw(gzip.compress(xml), "application/x-gzip")
+
+    def route_sitemap_start(self):
+        self.send_html("\tNothing links to the sitemap pages.")
+
+    def route_sitemap_orphan1(self):
+        self.send_html('\t<a href="deep1.html">deeper</a>')
+
+    def route_sitemap_orphan2(self):
+        self.send_html("\tSecond orphan.")
+
+    def route_sitemap_deep1(self):
+        self.send_html("\tOne level below an orphan.")
+
+    # chainN is a sitemapindex at nesting level N, listing chain(N+1) and a
+    # urlset capN.xml whose single page is capN.html. Levels up to
+    # HTS_SITEMAP_MAX_LEVEL are followed, so capN.html appears for N below the
+    # cap and stops appearing at it: the pair pins the boundary, which a cap
+    # mutated either way would break.
+    def route_sitemap_chain(self):
+        host = self.headers.get("Host")
+        level = int(self.path.rsplit("/", 1)[-1][len("chain") : -len(".xml")])
+        self.send_raw(
+            (
+                '<?xml version="1.0" encoding="UTF-8"?>\n<sitemapindex>'
+                f"<sitemap><loc>http://{host}/sitemapdir/chain{level + 1}.xml"
+                "</loc></sitemap>"
+                f"<sitemap><loc>http://{host}/sitemapdir/cap{level}.xml"
+                "</loc></sitemap></sitemapindex>\n"
+            ).encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_capset(self):
+        host = self.headers.get("Host")
+        level = self.path.rsplit("/", 1)[-1][len("cap") : -len(".xml")]
+        self.send_raw(
+            (
+                '<?xml version="1.0" encoding="UTF-8"?>\n<urlset>'
+                f"<url><loc>http://{host}/sitemapdir/cap{level}.html</loc></url>"
+                "</urlset>\n"
+            ).encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_cappage(self):
+        self.send_html("\tReached through a nested sitemapindex.")
+
+    def route_sitemap_gatedindex(self):
+        host = self.headers.get("Host")
+        self.send_raw(
+            '<?xml version="1.0" encoding="UTF-8"?><sitemapindex>'
+            f"<sitemap><loc>http://{host}/sitemapdir/filtered.xml</loc></sitemap>"
+            "</sitemapindex>\n".encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_filtered(self):
+        host = self.headers.get("Host")
+        self.send_raw(
+            '<?xml version="1.0" encoding="UTF-8"?><urlset>'
+            f"<url><loc>http://{host}/sitemapdir/gated.html</loc></url>"
+            "</urlset>\n".encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_gated(self):
+        self.send_html("\tListed only by the filtered child sitemap.")
+
+    # A moved sitemap: the marking has to follow the redirect.
+    # A root sitemap naming a page below the crawl's start directory and one
+    # above it. Only the first may be seeded when the crawl started at /deep/dir/.
+    def route_sitemap_scope(self):
+        host = self.headers.get("Host")
+        self.send_raw(
+            '<?xml version="1.0" encoding="UTF-8"?><urlset>'
+            f"<url><loc>http://{host}/deep/dir/below.html</loc></url>"
+            f"<url><loc>http://{host}/elsewhere/updir.html</loc></url>"
+            "</urlset>\n".encode(),
+            "application/xml",
+        )
+
+    def route_sitemap_deepstart(self):
+        self.send_html("\tA start page in a subdirectory, linking nothing.")
+
+    def route_sitemap_below(self):
+        self.send_html("\tBelow the start directory.")
+
+    def route_sitemap_updir(self):
+        self.send_html("\tAbove the start directory.")
+
+    def route_sitemap_moved(self):
+        self.send_response(301)
+        self.send_header("Location", "/sitemapdir/pages.xml.gz")
+        self.send_header("Content-Length", "0")
+        self.end_headers()
+
     # --- type/extension matrix (issue #267 family) -------------------------
 
     def send_raw(self, body, content_type, extra_headers=()):
@@ -845,6 +1000,62 @@ class Handler(SimpleHTTPRequestHandler):
         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")
 
+    # --- re-fetch cut mid-header, so nothing is stored (#746, #748) ---------
+    KEEP_PAGE = b"<html><body><p>KEEP-PAGE-V1</p></body></html>"
+    KEEP_BIN = b"KEEP-BIN-V1\n" + b"\x51\x52\x53\x54" * 512
+    KEEP_ERR = b"KEEP-ERR-V1\n" + b"\x61\x62\x63\x64" * 512
+
+    def send_cut_headers(self):
+        """Hang up mid-header: the response never becomes parseable."""
+        self.close_connection = True
+        try:
+            self.wfile.write(b"HTTP/1.0 200 OK\r\nContent-Ty")
+            self.wfile.flush()
+        except OSError:
+            pass
+        self.connection.close()
+
+    def route_keep_index(self):
+        self.refetch_pass()
+        self.send_html(
+            '\t<a href="page.html">page</a>\n'
+            '\t<a href="data.bin">data</a>\n'
+            '\t<a href="err.bin">err</a>\n'
+            '\t<a href="stay.bin">stay</a>\n'
+        )
+
+    def route_keep_page(self):
+        if self.refetch_pass() == 1:
+            self.send_raw(self.KEEP_PAGE, "text/html")
+        else:
+            self.send_cut_headers()
+
+    def route_keep_data(self):
+        if self.refetch_pass() == 1:
+            self.send_raw(self.KEEP_BIN, "application/octet-stream")
+        else:
+            self.send_cut_headers()
+
+    # Control: an HTTP error on the same resource already keeps the copy, so
+    # the cut-header routes above must end up indistinguishable from it.
+    def route_keep_err(self):
+        if self.refetch_pass() == 1:
+            self.send_raw(self.KEEP_ERR, "application/octet-stream")
+        else:
+            self.send_response(500)
+            self.send_header("Content-Type", "text/html")
+            self.send_header("Content-Length", "0")
+            self.end_headers()
+
+    # Control: answers normally, with a new body on pass 2, so a fix that
+    # stopped overwriting mirrored files altogether would be caught.
+    def route_keep_stay(self):
+        v = 1 if self.refetch_pass() == 1 else 2
+        self.send_raw(
+            b"KEEP-STAY-V%d\n" % v + b"\x71\x72\x73\x74" * 512,
+            "application/octet-stream",
+        )
+
     # Echo what httrack advertised, so a crawl can assert the header.
     def route_codec_ae(self):
         self.send_raw(
@@ -1739,6 +1950,21 @@ class Handler(SimpleHTTPRequestHandler):
         "/gated/index.php": route_gated_index,
         "/gated/secret.php": route_gated_secret,
         "/robots.txt": route_robots,
+        "/sitemapdir/index.xml": route_sitemap_index,
+        "/sitemap.xml": route_sitemap_index,
+        "/sitemapdir/pages.xml.gz": route_sitemap_pages,
+        "/sitemapdir/start.html": route_sitemap_start,
+        "/sitemapdir/orphan1.html": route_sitemap_orphan1,
+        "/sitemapdir/orphan2.html": route_sitemap_orphan2,
+        "/sitemapdir/deep1.html": route_sitemap_deep1,
+        "/sitemapdir/gatedindex.xml": route_sitemap_gatedindex,
+        "/sitemapdir/filtered.xml": route_sitemap_filtered,
+        "/sitemapdir/gated.html": route_sitemap_gated,
+        "/sitemapdir/moved.xml": route_sitemap_moved,
+        "/scopesitemap.xml": route_sitemap_scope,
+        "/deep/dir/start.html": route_sitemap_deepstart,
+        "/deep/dir/below.html": route_sitemap_below,
+        "/elsewhere/updir.html": route_sitemap_updir,
         "/warcgz/index.html": route_warcgz_index,
         "/warcgz/page.html": route_warcgz_page,
         "/warcgz/data.bin": route_warcgz_data,
@@ -1780,6 +2006,11 @@ class Handler(SimpleHTTPRequestHandler):
         "/uptrunc/page.html": route_uptrunc_page,
         "/uptrunc/file.bin": route_uptrunc_file,
         "/uptrunc/stay.html": route_uptrunc_stay,
+        "/keep/index.html": route_keep_index,
+        "/keep/page.html": route_keep_page,
+        "/keep/data.bin": route_keep_data,
+        "/keep/err.bin": route_keep_err,
+        "/keep/stay.bin": route_keep_stay,
         "/types/index.html": route_types_index,
         "/types/control.php": route_types,
         "/types/photo.png": route_types,
@@ -2084,6 +2315,13 @@ class Handler(SimpleHTTPRequestHandler):
             return True
         # Match percent-encoded paths (accented #157 route) by their decoded form.
         handler = self.ROUTES.get(path) or self.ROUTES.get(unquote(path))
+        if handler is None:
+            if re.fullmatch(r"/sitemapdir/chain\d+\.xml", path):
+                handler = type(self).route_sitemap_chain
+            elif re.fullmatch(r"/sitemapdir/cap\d+\.xml", path):
+                handler = type(self).route_sitemap_capset
+            elif re.fullmatch(r"/sitemapdir/cap\d+\.html", path):
+                handler = type(self).route_sitemap_cappage
         if handler is not None:
             handler(self)
             return True

tests/webhttrack-smoke.sh

@@ -46,17 +46,20 @@ cat >"$stubdir/x-www-browser" <<EOF
 echo "stub browser invoked with: \$1" >&2
 # Also fetch an option page and require a rendered title='' tooltip: proves the
 # option template expands and the \${html:} filter escapes into the attribute.
-# option9 additionally proves the WARC and change-report controls render with
-# their expanded labels, and option2 the --single-file pair: on field names plus
-# the absence of an unexpanded key, since the default locale here is French.
+# option9 additionally proves the WARC and change-report controls and
+# option2 the --single-file pair render with their expanded labels, and
+# option8 the sitemap ones. option2 also pins the absence of an
+# unexpanded key, since the default locale here is French.
 opturl="\${1%/}/server/option2.html"
 warcurl="\${1%/}/server/option9.html"
+smurl="\${1%/}/server/option8.html"
 if body="\$(curl -fsSL --max-time 20 "\$1")" && printf '%s' "\$body" | grep -qai httrack && printf '%s' "\$body" | grep -qaF step2.html &&
     opt="\$(curl -fsSL --max-time 20 "\$opturl")" && printf '%s' "\$opt" | grep -qaF "title='" &&
     printf '%s' "\$opt" | grep -qaF 'name="singlefile"' && printf '%s' "\$opt" | grep -qaF 'name="singlefilemax"' &&
     ! printf '%s' "\$opt" | grep -qaF '\${LANG_SINGLEFILE}' &&
     warc="\$(curl -fsSL --max-time 20 "\$warcurl")" && printf '%s' "\$warc" | grep -qaF 'name="warcfile"' && printf '%s' "\$warc" | grep -qaF WARC &&
-    printf '%s' "\$warc" | grep -qaF 'name="changes"' && printf '%s' "\$warc" | grep -qaF hts-changes.json; then
+    printf '%s' "\$warc" | grep -qaF 'name="changes"' && printf '%s' "\$warc" | grep -qaF hts-changes.json &&
+    sm="\$(curl -fsSL --max-time 20 "\$smurl")" && printf '%s' "\$sm" | grep -qaF 'name="sitemapurl"' && printf '%s' "\$sm" | grep -qaF 'name="sitemap"'; then
     echo PASS >"$marker"
 else
     echo "FAIL: unexpected response from \$1" >"$marker"