Merge branch 'master' into fix/proxytrack-dav-default-doc

Union both sides' expected-skip entries and TESTS-tail additions,
deduplicating and restoring numeric order.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.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" | $CC -DHTS_USEZLIB=0 -I. -Isrc -fsyntax-only -xc - 2>/dev/null; then
+            echo "::error::-DHTS_USEZLIB=0 compiled; htsglobal.h must reject it"
+            exit 1
+          fi
           # a missing decoder would silently drop the coding from Accept-Encoding
           grep -q "define HTS_USEBROTLI 1" config.h
           grep -q "define HTS_USEZSTD 1" config.h
@@ -57,7 +79,10 @@ jobs:
       - name: Build
         run: make -j"$(nproc)"
 
+      # A backstop only: tests/test-timeout.sh bounds each test, and a healthy run
+      # is a minute here, two on macOS. Without it a stall ran to the job's 6h default.
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -97,6 +122,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test without python3
+        timeout-minutes: 20
         run: |
           set -euo pipefail
           # Hide every python3* so `command -v python3` fails like it does in the
@@ -151,6 +177,7 @@ jobs:
           sudo ifconfig lo0 alias 127.0.0.3 up
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -223,6 +250,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -280,6 +308,7 @@ jobs:
         env:
           ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
           UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -323,6 +352,7 @@ jobs:
       - name: Test (offline self-tests under MSan)
         env:
           MSAN_OPTIONS: abort_on_error=1:halt_on_error=1
+        timeout-minutes: 20
         run: |
           set -euo pipefail
           # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
@@ -404,6 +434,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
+        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -596,7 +627,12 @@ jobs:
           set -euo pipefail
           git fetch --no-tags origin \
             "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
-          base="origin/${{ github.base_ref }}"
+          # Merge base, not the branch tip: master moves during a run, and a
+          # tip-relative diff blames its new C on this PR.
+          if ! base="$(git merge-base "origin/${{ github.base_ref }}" HEAD)"; then
+            echo "::error::no merge base with origin/${{ github.base_ref }}; cannot scope the check."
+            exit 1
+          fi
           set +e
           diff="$(git clang-format --binary clang-format-19 --style=file \
                     --diff --extensions c,h "$base")"
@@ -638,6 +674,8 @@ jobs:
           git fetch --no-tags origin \
             "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
           base="origin/${{ github.base_ref }}"
+          # Three dots: merge-base scoped, so commits landing on master mid-run
+          # are not counted as this PR's.
           changed="$(git diff --name-only "$base"...HEAD)"
           has() { printf '%s\n' "$changed" | grep -qx "$1"; }
           if has man/httrack.1 && ! has html/httrack.man.html; then

.github/workflows/windows-build.yml

@@ -189,25 +189,53 @@ jobs:
           # A wedged crawl must not eat the job's timeout budget. timeout(1)'s
           # signals can't reap a native httrack.exe (MSYS signals don't reach it),
           # so a hang orphaned processes that starved the runner; run_with_timeout
-          # TerminateProcess-es the whole tree. 600s clears the slowest multi-pass
-          # crawl (a few passes at --max-time=120 each).
+          # TerminateProcess-es the whole tree. 600s is unchanged: it clears the
+          # 540s a three-pass crawl may legitimately take under local-crawl.sh's
+          # own watchdogs, against a slowest healthy test here of 39s.
           . ./testlib.sh
+          per_test=600
 
-          pass=0 fail=0 skip=0 failed="" skipped=""
+          # The whole suite must give up before the step timeout above. A cancelled
+          # step keeps neither its log nor the artifacts the later if:always()
+          # steps would upload, so an overrun that ends in a cancel tells us
+          # nothing; failing on our own terms keeps both. Healthy runs take 8-9
+          # min. The check sits between tests, so the step can still reach 25 min
+          # plus one per-test budget, and that worst case stays inside the 45.
+          suite_deadline=1500
+          started=$SECONDS
+
+          # Survives into the artifact even if the tail of the step log does not.
+          progress=suite-progress.log
+          : >"$progress"
+
+          pass=0 fail=0 skip=0 failed="" skipped="" deadline=0
           for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test \
                    *_local-*.test 13_crawl_proxy_https.test 58_watchdog.test \
                    60_crawl-log-salvage.test; do
+            elapsed=$((SECONDS - started))
+            if [ "$elapsed" -ge "$suite_deadline" ]; then
+              echo "::error::suite deadline: ${elapsed}s elapsed, stopping before $t"
+              echo "DEADLINE before $t after ${elapsed}s" >>"$progress"
+              # Per-test start times, so the slow ones are named rather than guessed.
+              sed 's/^/      /' "$progress"
+              deadline=1
+              break
+            fi
+            echo "RUN $t at ${elapsed}s" >>"$progress"
             rc=0
-            run_with_timeout 600 bash "$t" >"$t.log" 2>&1 || rc=$?
+            # Same guard "make check" uses on POSIX, so a wedge is diagnosed the
+            # same way on every platform. It dumps before it kills, which a bare
+            # run_with_timeout cannot: by the time that returns, the tree whose
+            # stack we wanted is already gone.
+            HTTRACK_TEST_TIMEOUT=$per_test bash ./test-timeout.sh "$t" >"$t.log" 2>&1 || rc=$?
             case "$rc" in
               0) pass=$((pass + 1)); echo "PASS $t" ;;
               77) skip=$((skip + 1)) skipped="$skipped $t"; echo "SKIP $t" ;;
               124)
                 fail=$((fail + 1)) failed="$failed $t"
+                # test-timeout.sh has already written the process list, the stacks
+                # and the killed crawl's own logs into $t.log.
                 echo "FAIL $t (timed out, tree killed)"
-                # Re-running a wedge traced would just hang again: salvage the
-                # killed crawl's own logs into the artifact instead.
-                dump_crawl_logs >>"$t.log"
                 tail -n 25 "$t.log" | sed 's/^/      /'
                 ;;
               *)
@@ -215,21 +243,30 @@ jobs:
                 echo "FAIL $t (exit $rc)"
                 # These assert with `test "$(...)" == "..." || exit 1`, which
                 # says nothing at all on failure. Re-run traced, still bounded.
-                run_with_timeout 600 bash -x "$t" >>"$t.log" 2>&1 || true
+                run_with_timeout "$per_test" bash -x "$t" >>"$t.log" 2>&1 || true
                 tail -n 25 "$t.log" | sed 's/^/      /'
                 ;;
             esac
+            echo "$rc $t" >>"$progress"
+            # An orphaned native httrack.exe spins and starves the runner, which
+            # is how this job dies with "lost communication" rather than a plain
+            # timeout. Clear them between tests and name whoever leaked them.
+            reap_leftover_processes "$t" | tee -a "$progress"
           done
           echo "ran=$((pass + fail + skip)) pass=$pass fail=$fail skip=$skip" |
             tee -a "$GITHUB_STEP_SUMMARY"
 
           # Every gate here exits 77, so an all-skipped suite would report green having
           # tested nothing: pin the skips, and floor the passes in case the glob empties.
-          # footer-overflow skips on Windows (needs a path past MAX_PATH); crange pending #581;
-          # webdav-mime needs a reapable background listener, which MSYS cannot give it;
+          # footer-overflow and purge-longpath skip on Windows (need a path past MAX_PATH);
+          # crange pending #581;
+          # webdav-default and webdav-mime need a reapable background listener, which MSYS cannot give them;
           # badmtime needs a filesystem that stores an mtime past gmtime's range;
-          # single-file ends on a GUI half needing htsserver, which this job does not build.
-          expected_skips=" 01_engine-footer-overflow.test 48_local-crange-memresume.test 71_local-crange-repaircache.test 79_local-proxytrack-webdav-mime.test 88_local-proxytrack-badmtime.test 94_local-single-file.test"
+          # single-file ends on a GUI half needing htsserver, which this job does not build;
+          # update-304-leak needs a LeakSanitizer build, which MSVC has no equivalent of.
+          expected_skips=" 01_engine-footer-overflow.test 100_local-purge-longpath.test 114_local-update-304-leak.test 120_local-proxytrack-webdav-default.test 48_local-crange-memresume.test 71_local-crange-repaircache.test 79_local-proxytrack-webdav-mime.test 88_local-proxytrack-badmtime.test 94_local-single-file.test"
+          # First, or the deadline reads as an unexplained shortfall in the gates below.
+          [ "$deadline" -eq 0 ] || { echo "::error::suite did not finish within ${suite_deadline}s"; exit 1; }
           [ "$pass" -ge 90 ] || { echo "::error::only $pass tests passed ($skip skipped)"; exit 1; }
           [ "$skipped" = "$expected_skips" ] || { echo "::error::unexpected skips:$skipped"; exit 1; }
           [ "$fail" -eq 0 ] || { echo "::error::failing:$failed"; exit 1; }

AGENTS.md

@@ -26,12 +26,18 @@ the operational checklist: toolchain, invariants, and how to ship a change.
   check`, or `PATH="<bld>/src:$PATH"` for a manual run.
 - Give new `.test` scripts `set -e`: the older ones predate the rule, so several
   `local-crawl.sh` calls with no `set -e` report PASS on any non-last failure.
-- Never assert with `cmd | grep -q MARKER && fail`. Under `pipefail` the
-  pipeline is non-zero both when `cmd` fails and when `grep -q` matches early
-  and SIGPIPEs it, so the `&&` never fires and a probe that proved nothing reads
-  as "marker absent". Capture the reply, assert the status line it must carry
-  (an empty, truncated or redirected one is marker-free too), then match with a
-  here-string.
+- Run teardown with errexit off: `trap 'set +e; cleanup' EXIT`. Under `set -e` a
+  failing cleanup command becomes the test's exit status (#773). Keep the other
+  signals on their own `trap` line, or errexit stays off for the rest of the run.
+  The guard also resets `$?`, so save it first if teardown reads it.
+- Never pipe into `grep -q`: it exits on the first match, so whatever the
+  producer had left to write takes SIGPIPE, and under `pipefail` that becomes
+  the pipeline's status. `cmd | grep -q M && fail` then never fires and a probe
+  that proved nothing reads as "marker absent"; `cmd | grep -q M || fail` fails
+  a test whose marker was present. bash issues one `write()` per line, so any
+  match that is not on the last line is exposed. Capture the reply, assert the
+  status line it must carry (an empty, truncated or redirected one is
+  marker-free too), then match with a here-string: `grep -q M <<<"$reply"`.
 
 ## Hard invariants
 - **Generated autotools files are NOT in git.** `configure`, every

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/fcguide.html

@@ -237,7 +237,7 @@ Build options:
   x  replace external html links by error pages (--replace-external)
  %x  do not include any password for external password protected websites (%x0 include) (--no-passwords)
  %q *include query string for local files (useless, for information purpose only) (%q0 don't include) (--include-query-string)
-  o *generate output html file in case of error (404..) (o0 don't generate) (--generate-errors)
+  o *save the server's error pages (404..) (o0 discard them) (--generate-errors)
   X *purge old files after update (X0 keep delete) (--purge-old[=N])
 
 Spider options:
@@ -413,7 +413,7 @@ site. Specifically, the defauls are:
   NN  name conversion type (0 *original structure, 1+: see below)
   LN  long names (L1 *long names / L0 8-3 conversion)
   K   keep original links (e.g. http://www.adr/link) (K0 *relative link)
-  o *generate output html file in case of error (404..) (o0 don't generate)
+  o *save the server's error pages (404..) (o0 discard them)
   X *purge old files after update (X0 keep delete)
   bN  accept cookies in cookies.txt (0=do not accept,* 1=accept)
   u check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)
@@ -473,11 +473,11 @@ store them with the same names used on the web site.
 URLs within this web site are adjusted to point to the files in the
 mirror.
 
-<pre><b><i>  o *generate output html file in case of error (404..) (o0 don't generate) </i></b></pre>
+<pre><b><i>  o *save the server's error pages (404..) (o0 discard them) </i></b></pre>
 
-<p align=justify> IF there are errors in downloading, create a file that
-indicates that the URL was not found.  This makes browsing go a lot
-smoother.
+<p align=justify> IF a page cannot be downloaded, the error page the
+server sent is saved in its place, so a broken link still lands on the
+site's own 'not found' page.  This makes browsing go a lot smoother.
 
 <pre><b><i>  X *purge old files after update (X0 keep delete) </i></b></pre>
 
@@ -1011,7 +1011,7 @@ Build options:
   LN  long names (L1 *long names / L0 8-3 conversion)
   K   keep original links (e.g. http://www.adr/link) (K0 *relative link)
   x   replace external html links by error pages
-  o *generate output html file in case of error (404..) (o0 don't generate)
+  o *save the server's error pages (404..) (o0 discard them)
   X *purge old files after update (X0 keep delete)
   %x  do not include any password for external password protected websites (%x0 include) (--no-passwords)
   %q *include query string for local files (information only) (%q0 don't include) (--include-query-string)
@@ -1118,9 +1118,9 @@ deactivated byt his process.
 httrack http://www.shoesizes.com -O /tmp/shoesizes -x
 </i></b></pre>
 
-<p align=justify> This option prevents the generation of '404' error
-files to replace files that were not found even though there were URLs
-pointing to them.  It is useful for saving space as well as eliminating
+<p align=justify> This option keeps the server's '404' error pages out
+of the mirror, even though there were URLs pointing to the missing
+files.  It is useful for saving space as well as eliminating
 unnecessary files in operations where a working web site is not the
 desired result. 
 

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:
@@ -761,8 +777,8 @@ information purpose only) (%q0 don&rsquo;t include)
 <td width="82%">
 
 
-<p>*generate output html file in case of error (404..) (o0
-don&rsquo;t generate) (--generate-errors)</p></td></tr>
+<p>*save the server&rsquo;s error pages (404..) (o0 discard
+them) (--generate-errors)</p></td></tr>
 <tr valign="top" align="left">
 <td width="9%"></td>
 <td width="4%">

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}

html/step9_opt5.html

@@ -122,7 +122,7 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
   </small><br><br>
 <!-- -->
   <li>No error pages</li>
-  <br><small>Do not generate error pages (if a 404 error occurred, for example)
+  <br><small>Do not save the error pages sent by the server (if a 404 error occurred, for example)
   <br>If a page is missing on the remote site, there will not be any warning on the local site
   </small><br><br>
 <!-- -->

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

@@ -3,7 +3,7 @@
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
 .\" SPDX-License-Identifier: GPL-3.0-or-later
-.TH httrack 1 "26 July 2026" "httrack website copier"
+.TH httrack 1 "27 July 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -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])
@@ -217,7 +220,7 @@ do not include any password for external password protected websites (%x0 includ
 .IP \-%g
 strip query keys for dedup ([host/pattern=]key1,key2,...) (\-\-strip\-query <param>)
 .IP \-o
-*generate output html file in case of error (404..) (o0 don't generate) (\-\-generate\-errors)
+*save the server's error pages (404..) (o0 discard them) (\-\-generate\-errors)
 .IP \-X
 *purge old files after update (X0 keep delete) (\-\-purge\-old[=N])
 .IP \-%p

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/hts-indextmpl.h

@@ -487,141 +487,6 @@ regen:
 
 #define HTS_DATA_UNKNOWN_HTML_LEN 0
 
-#define HTS_DATA_ERROR_HTML "<html>"LF\
-  "<html xmlns=\"http://www.w3.org/1999/xhtml\" lang=\"en\">"LF\
-  ""LF\
-  "<head>"LF\
-  "	<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />"LF\
-  "	<meta name=\"description\" content=\"HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help\" />"LF\
-  "	<meta name=\"keywords\" content=\"httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows 95, windows 98, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software\" />"LF\
-  "	<title>Page not retrieved! - HTTrack Website Copier</title>"LF\
-  "	<style type=\"text/css\">"LF\
-  "	<!--"LF\
-  ""LF\
-  "body {"LF\
-  "	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;"LF\
-  "	background: #77b;"LF\
-  "}"LF\
-  "body, td {"LF\
-  "	font: 14px \"Trebuchet MS\", Verdana, Arial, Helvetica, sans-serif;"LF\
-  "	}"LF\
-  ""LF\
-  "#subTitle {"LF\
-  "	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; "LF\
-  "	}"LF\
-  ""LF\
-  "#siteNavigation a, #siteNavigation .current {"LF\
-  "	font-weight: bold;  color: #448;"LF\
-  "	}"LF\
-  "#siteNavigation a:link    { text-decoration: none; }"LF\
-  "#siteNavigation a:visited { text-decoration: none; }"LF\
-  ""LF\
-  "#siteNavigation .current { background-color: #ccd; }"LF\
-  ""LF\
-  "#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }"LF\
-  "#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }"LF\
-  ""LF\
-  ""LF\
-  "a:link    { text-decoration: underline;  color: #00f; }"LF\
-  "a:visited { text-decoration: underline;  color: #000; }"LF\
-  "a:hover   { text-decoration: underline;  color: #c00; }"LF\
-  "a:active  { text-decoration: underline; }"LF\
-  ""LF\
-  "#pageContent {"LF\
-  "	clear: both;"LF\
-  "	border-bottom: 6px solid #000;"LF\
-  "	padding: 10px;  padding-top: 20px;"LF\
-  "	line-height: 1.65em;"LF\
-	" background-image: url(backblue.gif);"LF\
-	" background-repeat: no-repeat;"LF\
-	" background-position: top right;"LF\
-  "	}"LF\
-  ""LF\
-  "#pageContent, #siteNavigation {"LF\
-  "	background-color: #ccd;"LF\
-  "	}"LF\
-  ""LF\
-  ""LF\
-  ".imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }"LF\
-  ".imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }"LF\
-  ""LF\
-  "hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }"LF\
-  ""LF\
-  "h1 { margin: 0;  font-weight: bold;  font-size: 2em; }"LF\
-  "h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }"LF\
-  "h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }"LF\
-  "h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }"LF\
-  ""LF\
-  ".blak { background-color: #000; }"LF\
-  ".hide { display: none; }"LF\
-  ".tableWidth { min-width: 400px; }"LF\
-  ""LF\
-  ".tblRegular       { border-collapse: collapse; }"LF\
-  ".tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }"LF\
-  ".tblHeaderColor, .tblHeaderColor td { background: #99c; }"LF\
-  ".tblNoBorder td   { border: 0; }"LF\
-  ""LF\
-  ""LF\
-  "// -->"LF\
-  "</style>"LF\
-  ""LF\
-  "</head>"LF\
-  ""LF\
-  "<table width=\"76%%\" border=\"0\" align=\"center\" cellspacing=\"0\" cellpadding=\"3\" class=\"tableWidth\">"LF\
-  "	<tr>"LF\
-  "	<td id=\"subTitle\">HTTrack Website Copier - Open Source offline browser</td>"LF\
-  "	</tr>"LF\
-  "</table>"LF\
-  "<table width=\"76%%\" border=\"0\" align=\"center\" cellspacing=\"0\" cellpadding=\"0\" class=\"tableWidth\">"LF\
-  "<tr class=\"blak\">"LF\
-  "<td>"LF\
-  "	<table width=\"100%%\" border=\"0\" align=\"center\" cellspacing=\"1\" cellpadding=\"0\">"LF\
-  "	<tr>"LF\
-  "	<td colspan=\"6\"> "LF\
-  "		<table width=\"100%%\" border=\"0\" align=\"center\" cellspacing=\"0\" cellpadding=\"10\">"LF\
-  "		<tr> "LF\
-  "		<td id=\"pageContent\"> "LF\
-  "<!-- ==================== End prologue ==================== -->"LF\
-  "<h1><strong><u>Oops!...</u></strong></h1>"LF\
-  "<h3>This page has <font color=\"red\"><em>not</em></font> been retrieved by HTTrack Website Copier (%s). </h3>"LF\
-  "<script language=\"Javascript\">"LF\
-  "<!--"LF\
-  "  var loc=document.location.toString();"LF\
-  "  if (loc) {"LF\
-  "    var pos=loc.indexOf('link=');"LF\
-  "    if (pos>0) {"LF\
-  "      document.write('Clic to the link <b>below</b> to go to the online location!<br><a href=\"'+loc.substring(pos+5)+'\">'+loc.substring(pos+5)+'</a><br>');"LF\
-  "    } else"LF\
-  "      document.write('(no location defined)');"LF\
-  "  }"LF\
-  "// -->"LF\
-  "</script>"LF\
-  "<h6 align=\"right\">Mirror by HTTrack Website Copier</h6>"LF\
-  "</body>"LF\
-  "</html>"LF\
-  "<!-- ==================== Start epilogue ==================== -->"LF\
-  "		</td>"LF\
-  "		</tr>"LF\
-  "		</table>"LF\
-  "	</td>"LF\
-  "	</tr>"LF\
-  "	</table>"LF\
-  "</td>"LF\
-  "</tr>"LF\
-  "</table>"LF\
-  ""LF\
-  "<table width=\"76%%\" height=\"100%%\" border=\"0\" align=\"center\" valign=\"bottom\" cellspacing=\"0\" cellpadding=\"0\">"LF\
-  "	<tr>"LF\
-  "	<td id=\"footer\"><small>&copy; 2014 Xavier Roche & other contributors - Web Design: Kauler Leto.</small></td>"LF\
-  "	</tr>"LF\
-  "</table>"LF\
-  ""LF\
-  "</body>"LF\
-  ""LF\
-  "</html>"LF\
-  ""LF\
-  ""LF
-
 // image gif "unknown"
 #define HTS_DATA_UNKNOWN_GIF \
   "\x47\x49\x46\x38\x39\x61\x20\x0\x20\x0\xf7\xff\x0\xc0\xc0\xc0\xff\x0\x0\xfc\x3\x0\xf8\x6\x0\xf6\x9\x0\xf2\xc\x0\xf0\xf\x0\xf0\xe\x0\xed\x11\x0\xec\x13\x0\xeb\x14\x0\xe9\x15\x0\xe8\x18\x0\xe6\x18\x0\xe5\x1a\x0\xe3\x1c\x0\xe2\x1d\x0\xe1\x1e\x0\xdf\x20\x0\xdd\x23\x0\xdd\x22\x0\xdb\x23\x0\xda\x25\x0\xd9\x25\x0\xd8\x27\x0\xd6\x29\x0\xd5\x2a\x0\xd3\x2c\x0\xd2\x2d\x0"\

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
@@ -345,12 +340,111 @@ static int back_index_ready(httrackp * opt, struct_back * sback, const char *adr
 }
 
 static int slot_can_be_cached_on_disk(const lien_back * back) {
+  /* A pending backup or spool means the slot is not finalized, and the swap
+     would unlink it through back_clear_entry() (#771). */
+  if (back->tmpfile != NULL && back->tmpfile[0] != '\0')
+    return 0;
   return (back->status == STATUS_READY && back->locked == 0
           && back->url_sav[0] != '\0'
           && strcmp(back->url_sav, BACK_ADD_TEST) != 0);
   /* Note: not checking !IS_DELAYED_EXT(back->url_sav) or it will quickly cause the slots to be filled! */
 }
 
+int back_selftest_slot_swap(void) {
+  lien_back back;
+  int err = 0;
+
+#define CHECK(want, why)                                                       \
+  do {                                                                         \
+    if (slot_can_be_cached_on_disk(&back) != (want)) {                         \
+      fprintf(stderr, "backswap: expected %d for %s\n", (want), (why));        \
+      err = 1;                                                                 \
+    }                                                                          \
+  } while (0)
+
+  memset(&back, 0, sizeof(back));
+  back.status = STATUS_READY;
+  strcpybuff(back.url_sav, "/tmp/httrack-selftest.bin");
+  CHECK(1, "a plain ready slot");
+
+  back.tmpfile = back.tmpfile_buffer;
+  strcpybuff(back.tmpfile_buffer, "/tmp/httrack-selftest.bin.bak");
+  CHECK(0, "a slot still holding a re-fetch backup");
+
+  /* Callers clear a spent temporary by emptying the name, not the pointer. */
+  back.tmpfile_buffer[0] = '\0';
+  CHECK(1, "a slot whose temporary was already dropped");
+
+  back.tmpfile = NULL;
+  back.locked = 1;
+  CHECK(0, "a locked slot");
+  back.locked = 0;
+
+  back.status = STATUS_TRANSFER;
+  CHECK(0, "a slot still transferring");
+  back.status = STATUS_READY;
+
+  back.url_sav[0] = '\0';
+  CHECK(0, "a slot with no save name");
+
+  strcpybuff(back.url_sav, BACK_ADD_TEST);
+  CHECK(0, "the dummy test slot");
+#undef CHECK
+
+  /* The swap round-trip must not lose the size of a slot whose body is already
+     at url_sav, or the link writer blanks the file (#797). */
+  {
+    static const char body[] = "swapped body";
+    int c;
+
+    for (c = 0; c < 2; c++) {
+      const hts_boolean inmemory = c == 0 ? HTS_TRUE : HTS_FALSE;
+      FILE *const fp = tmpfile();
+      lien_back *copy = NULL;
+
+      memset(&back, 0, sizeof(back));
+      back.status = STATUS_READY;
+      strcpybuff(back.url_sav, "/tmp/httrack-selftest.bin");
+      back.r.size = (LLint) sizeof(body) - 1;
+      if (inmemory) {
+        back.r.adr = strdupt(body);
+      }
+      if (fp == NULL || back_serialize(fp, &back) != 0 ||
+          fseek(fp, 0, SEEK_SET) != 0 || back_unserialize(fp, &copy) != 0) {
+        fprintf(stderr, "backswap: round-trip failed for a %s slot\n",
+                inmemory ? "buffered" : "direct-to-disk");
+        err = 1;
+      } else {
+        if (copy->r.size != back.r.size) {
+          fprintf(stderr,
+                  "backswap: %s slot came back with size " LLintP
+                  ", expected " LLintP "\n",
+                  inmemory ? "buffered" : "direct-to-disk", copy->r.size,
+                  back.r.size);
+          err = 1;
+        }
+        if (inmemory && (copy->r.adr == NULL ||
+                         memcmp(copy->r.adr, body, sizeof(body) - 1) != 0)) {
+          fprintf(stderr, "backswap: buffered slot lost its body\n");
+          err = 1;
+        }
+        if (!inmemory && copy->r.adr != NULL) {
+          fprintf(stderr, "backswap: direct-to-disk slot gained a body\n");
+          err = 1;
+        }
+        back_clear_entry(copy);
+        freet(copy);
+      }
+      if (fp != NULL)
+        fclose(fp);
+      freet(back.r.adr);
+    }
+  }
+
+  printf("backswap self-test: %s\n", err ? "FAIL" : "OK");
+  return err;
+}
+
 /* Put all backing entries that are ready in the storage hashtable to spare space and CPU */
 int back_cleanup_background(httrackp * opt, cache_back * cache,
                             struct_back * sback) {
@@ -590,12 +684,40 @@ 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;
+/* Note: utf-8 */
+void back_refetch_backup(httrackp *opt, lien_back *const back) {
+  back->tmpfile = NULL;
+  if (fexist_utf8(back->url_sav)) {
+    hts_boolean saved = HTS_FALSE;
+
+    if (create_back_tmpfile(opt, back, "bak") == 0) {
+      /* clobber a .bak a killed run left behind, or the guard stays off for
+         good (#758) */
+      if (fexist_utf8(back->tmpfile))
+        hts_log_print(opt, LOG_WARNING, "replacing leftover backup %s",
+                      back->tmpfile);
+      saved = hts_rename_over(opt, back->url_sav, back->tmpfile);
+    }
+    if (!saved) {
+      hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
+                    "could not back up %s; an aborted re-fetch will lose it",
+                    back->url_sav);
+      back->tmpfile = NULL;
+    }
+  }
+}
+
+/* Did the fetch fail to produce a response, as opposed to the engine
+   deliberately passing the resource over? Only the latter may be purged. */
+static hts_boolean back_transfer_failed(const int statuscode) {
+  switch (statuscode) {
+  case STATUSCODE_TOO_BIG:
+  case STATUSCODE_EXCLUDED:
+  case STATUSCODE_TEST_OK:
+    return HTS_FALSE;
+  default:
+    return statuscode <= 0 ? HTS_TRUE : HTS_FALSE;
+  }
 }
 
 /* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
@@ -615,7 +737,7 @@ 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(opt, 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 +868,7 @@ 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(opt, unpacked, back[p].url_sav)) {
                     /* The temp bypassed filecreate(), which is what chmods. */
 #ifndef _WIN32
                     chmod(back[p].url_sav, HTS_ACCESS_FILE);
@@ -1044,6 +1166,14 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
   /* Aborted, error, or not ready: url_sav (if written) is broken; restore the
      previous copy from the backup. */
   back_finalize_backup(opt, &back[p], HTS_FALSE);
+  /* Note the surviving copy, or the end-of-update purge drops what this run
+     never managed to replace (#746). */
+  if (!back[p].testmode && back_transfer_failed(back[p].r.statuscode) &&
+      back[p].url_sav[0] != '\0' && fexist_utf8(back[p].url_sav)) {
+    filenote(&opt->state.strc, back[p].url_sav, NULL);
+    file_notify(opt, back[p].url_adr, back[p].url_fil, back[p].url_sav, 0, 0,
+                back[p].r.notmodified);
+  }
   return -1;
 }
 
@@ -1093,6 +1223,13 @@ void back_connxfr(htsblk * src, htsblk * dst) {
   src->debugid = 0;
 }
 
+/* Release the buffers a response owns. The connection members are left alone:
+   back_connxfr() moves those, and the file handles are closed elsewhere. */
+static void back_free_response(htsblk *r) {
+  deleteaddr(r);
+  warc_free_request(r);
+}
+
 void back_move(lien_back * src, lien_back * dst) {
   memcpy(dst, src, sizeof(lien_back));
   memset(src, 0, sizeof(lien_back));
@@ -1186,7 +1323,10 @@ int back_unserialize(FILE * fp, lien_back ** dst) {
     (*dst)->r.ssl_con = NULL;
 #endif
     if (back_data_unserialize(fp, (void **) &(*dst)->r.adr, &size) == 0) {
-      (*dst)->r.size = size;
+      /* A bodyless slot already wrote its bytes to url_sav (FTP, direct to
+         disk); zeroing r.size makes the writer blank that file (#797). */
+      if ((*dst)->r.adr != NULL)
+        (*dst)->r.size = size;
       (*dst)->r.headers = NULL;
       if (back_string_unserialize(fp, &(*dst)->r.headers) == 0)
         return 0;               /* ok */
@@ -1625,10 +1765,7 @@ int back_clear_entry(lien_back * back) {
       back->r.soc = INVALID_SOCKET;
     }
 
-    if (back->r.adr != NULL) {  // reste un bloc à désallouer
-      freet(back->r.adr);
-      back->r.adr = NULL;
-    }
+    back_free_response(&back->r);
     if (back->chunk_adr != NULL) {      // reste un bloc à désallouer
       freet(back->chunk_adr);
       back->chunk_adr = NULL;
@@ -1641,12 +1778,6 @@ int back_clear_entry(lien_back * back) {
       (void) unlink(back->tmpfile);
       back->tmpfile = NULL;
     }
-    // headers
-    if (back->r.headers != NULL) {
-      freet(back->r.headers);
-      back->r.headers = NULL;
-    }
-    warc_free_request(&back->r);
     // Tout nettoyer
     memset(back, 0, sizeof(lien_back));
     back->r.soc = INVALID_SOCKET;
@@ -3156,20 +3287,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                           back[i].url_sav, 1, 1,
                                           back[i].r.notmodified);
                               back[i].r.compressed = 0;
-                              /* Re-fetch over an existing file (#77 follow-up):
-                                 move the good copy aside before truncating it
-                                 so an aborted transfer can restore it. url_sav
-                                 is still written normally (file list intact).
-                               */
-                              back[i].tmpfile = NULL;
-                              if (fexist_utf8(back[i].url_sav)) {
-                                if (create_back_tmpfile(opt, &back[i], "bak") !=
-                                        0 ||
-                                    RENAME(back[i].url_sav, back[i].tmpfile) !=
-                                        0) {
-                                  back[i].tmpfile = NULL;
-                                }
-                              }
+                              back_refetch_backup(opt, &back[i]);
                               if ((back[i].r.out =
                                    filecreate(&opt->state.strc,
                                               back[i].url_sav)) == NULL) {
@@ -3964,6 +4082,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
                       memset(&tmp, 0, sizeof(tmp));
                       back_connxfr(&back[i].r, &tmp);
+                      /* the cache entry overwrites the whole struct, so drop
+                         what the 304 response still owns first (#782) */
+                      back_free_response(&back[i].r);
                       back[i].r =
                         cache_read(opt, cache, back[i].url_adr, back[i].url_fil,
                                    back[i].url_sav, back[i].location_buffer);

src/htsback.h

@@ -139,6 +139,12 @@ int back_trylive(httrackp * opt, cache_back * cache, struct_back * sback,
                  const int p);
 int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                   const int p);
+/* Move the previous copy of back->url_sav to back->tmpfile so back_finalize()
+   can put it back when the re-fetch fails (#77 follow-up). Call right before
+   truncating url_sav; tmpfile stays NULL when there is nothing to save. */
+void back_refetch_backup(httrackp *opt, lien_back *const back);
+/* -#test=backswap: slots eligible for the on-disk ready table. */
+int back_selftest_slot_swap(void);
 void back_info(struct_back * sback, int i, int j, FILE * fp);
 void back_infostr(struct_back *sback, int i, int j, char *s, size_t size);
 LLint back_transferred(LLint add, struct_back * sback);

src/htscache.c

@@ -855,13 +855,6 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
   return r;
 }
 
-// lecture d'un fichier dans le cache
-// si save==null alors test unqiquement
-static int hts_rename(httrackp * opt, const char *a, const char *b) {
-  hts_log_print(opt, LOG_DEBUG, "Cache: rename %s -> %s (%p %p)", a, b, a, b);
-  return RENAME(a, b);
-}
-
 /* Open the cache ZIP via hts_fopen_utf8 so a non-ASCII path_log isn't mangled
    to ANSI (#630); 64-bit funcs keep multi-GB caches whole on Windows LLP64. */
 static voidpf ZCALLBACK hts_zip_fopen_utf8(voidpf opaque, const void *filename,
@@ -991,29 +984,16 @@ void cache_init(cache_back * cache, httrackp * opt) {
               OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
               StringBuff(opt->path_log),
               "hts-cache/new.zip")))) { // a previous cache exists.. rename it
-        /* Remove OLD cache */
-        if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                StringBuff(opt->path_log),
-                                "hts-cache/old.zip"))) {
-          if (UNLINK(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                             StringBuff(opt->path_log), "hts-cache/old.zip")) !=
-              0) {
-            hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
-                          "Cache: error while moving previous cache");
-          }
-        }
-
-        /* Rename */
-        if (hts_rename
-            (opt,
-             fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
-                     "hts-cache/new.zip"), fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                                   StringBuff(opt->path_log),
-                                                   "hts-cache/old.zip")) != 0) {
+        if (!hts_rename_over(
+                opt,
+                fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                        StringBuff(opt->path_log), "hts-cache/new.zip"),
+                fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                        StringBuff(opt->path_log), "hts-cache/old.zip"))) {
           hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
                         "Cache: error while moving previous cache");
         } else {
-          hts_log_print(opt, LOG_DEBUG, "Cache: successfully renamed");
+          hts_log_print(opt, LOG_DEBUG, "Cache: rotated new.zip to old.zip");
         }
       }
     } else {

src/htscache_selftest.c

@@ -676,7 +676,7 @@ int cache_selftests(httrackp *opt, const char *dir) {
     char base[HTS_URLMAXSIZE];
 
     strcpybuff(base, dir);
-    if (base[0] != '\0' && base[strlen(base) - 1] != '/') {
+    if (base[0] != '\0' && hts_lastchar(base) != '/') {
       strcatbuff(base, "/");
     }
     StringCopy(opt->path_log, base);
@@ -856,7 +856,7 @@ static void golden_setup(httrackp *opt, const char *dir) {
   char base[HTS_URLMAXSIZE];
 
   strcpybuff(base, dir);
-  if (base[0] != '\0' && base[strlen(base) - 1] != '/') {
+  if (base[0] != '\0' && hts_lastchar(base) != '/') {
     strcatbuff(base, "/");
   }
   StringCopy(opt->path_log, base);

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"
@@ -772,7 +773,7 @@ int httpmirror(char *url1, httrackp * opt) {
         // sauter les + sans rien après..
         if (strnotempty(tempo)) {
           if ((plus == 0) && (type == 1)) {     // implicite: *www.edf.fr par exemple
-            if (tempo[strlen(tempo) - 1] != '*') {
+            if (hts_lastchar(tempo) != '*') {
               strcatbuff(tempo, "*");   // ajouter un *
             }
           }
@@ -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
       // ------------------------------------------------------
@@ -1769,62 +1819,11 @@ int httpmirror(char *url1, httrackp * opt) {
         // -- -- --
         // sauver fichier
 
-        /* En cas d'erreur, vérifier que fichier d'erreur existe */
-        if (strnotempty(savename()) == 0) {       // chemin de sauvegarde existant
-          if (strcmp(urlfil(), "/robots.txt") == 0) {     // pas robots.txt
-            if (store_errpage) {        // c'est une page d'erreur
-              int create_html_warning = 0;
-              int create_gif_warning = 0;
-
-              switch (ishtml(opt, urlfil())) {    /* pas fichier html */
-              case 0:          /* non html */
-                {
-                  char buff[256];
-
-                  guess_httptype_sized(opt, buff, sizeof(buff), urlfil());
-                  if (strcmp(buff, "image/gif") == 0)
-                    create_gif_warning = 1;
-                }
-                break;
-              case 1:          /* html */
-                if (!r.adr) {
-                }
-                break;
-              default:         /* don't know.. */
-                break;
-              }
-              /* Créer message d'erreur ? */
-              if (create_html_warning) {
-                char *adr =
-                  (char *) malloct(strlen(HTS_DATA_ERROR_HTML) + 1100);
-                hts_log_print(opt, LOG_INFO, "Creating HTML warning file (%s)",
-                              r.msg);
-                if (adr) {
-                  if (r.adr) {
-                    freet(r.adr);
-                    r.adr = NULL;
-                  }
-                  sprintf(adr, HTS_DATA_ERROR_HTML, r.msg);
-                  r.adr = adr;
-                }
-              } else if (create_gif_warning) {
-                char *adr = (char *) malloct(HTS_DATA_UNKNOWN_GIF_LEN);
-
-                hts_log_print(opt, LOG_INFO, "Creating GIF dummy file (%s)",
-                              r.msg);
-                if (r.adr) {
-                  freet(r.adr);
-                  r.adr = NULL;
-                }
-                memcpy(adr, HTS_DATA_UNKNOWN_GIF, HTS_DATA_UNKNOWN_GIF_LEN);
-                r.adr = adr;
-              }
-            }
-          }
-        }
-
         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 +1835,8 @@ 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 +1846,10 @@ 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 +1926,9 @@ 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) {
@@ -2133,7 +2136,9 @@ int httpmirror(char *url1, httrackp * opt) {
                   continue;
                 strcpybuff(file, StringBuff(opt->path_html));
                 strcatbuff(file, line + 1);
-                file[strlen(file) - 1] = '\0';
+                /* strip filenote()'s ']', absent when linput() truncated the
+                   line */
+                hts_striplastchar(file, ']');
                 hts_changes_previous(opt, file + StringLength(opt->path_html));
                 if (!strstr(adr, line)) { // not found in the new list?
                   if (fexist_utf8(file)) { // still on disk
@@ -2160,12 +2165,11 @@ int httpmirror(char *url1, httrackp * opt) {
                 fseek(old_lst, 0, SEEK_SET);
                 while(!feof(old_lst)) {
                   linput(old_lst, line, 1000);
-                  while(strnotempty(line) && (line[strlen(line) - 1] != '/')
-                        && (line[strlen(line) - 1] != '\\')) {
-                    line[strlen(line) - 1] = '\0';
+                  while (strnotempty(line) && (hts_lastchar(line) != '/') &&
+                         (hts_lastchar(line) != '\\')) {
+                    hts_choplastchar(line);
                   }
-                  if (strnotempty(line))
-                    line[strlen(line) - 1] = '\0';
+                  hts_choplastchar(line);
                   if (strnotempty(line))
                     if (!strstr(adr, line)) {   // non trouvé?
                       char BIGSTK file[HTS_URLMAXSIZE * 2];
@@ -2178,13 +2182,12 @@ int httpmirror(char *url1, httrackp * opt) {
                         if (opt->log) {
                           hts_log_print(opt, LOG_INFO, "Purging directory %s/",
                                         file);
-                          while(strnotempty(file)
-                                && (file[strlen(file) - 1] != '/')
-                                && (file[strlen(file) - 1] != '\\')) {
-                            file[strlen(file) - 1] = '\0';
+                          while (strnotempty(file) &&
+                                 (hts_lastchar(file) != '/') &&
+                                 (hts_lastchar(file) != '\\')) {
+                            hts_choplastchar(file);
                           }
-                          if (strnotempty(file))
-                            file[strlen(file) - 1] = '\0';
+                          hts_choplastchar(file);
                         }
                       }
                     }
@@ -2286,6 +2289,7 @@ 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 +2638,11 @@ 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 +2750,11 @@ 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 +3696,10 @@ 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 +3774,12 @@ 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/htscore.h

@@ -376,8 +376,8 @@ void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
                           const char *template_footer, const char *adr,
                           const char *fil);
 
-// Flush ht_buff[0..ht_len] to save on disk (skip if MD5 unchanged); *fp
-// closed+NULLed on write. Precondition: ht_len>0.
+// Flush ht_buff[0..ht_len] to save on disk; *fp closed+NULLed on write.
+// Precondition: ht_len>0.
 void hts_finish_html_file(httrackp *opt, cache_back *cache, htsblk *r,
                           FILE **fp, const char *ht_buff, size_t ht_len,
                           const char *adr, const char *fil, const char *save);

src/htscoremain.c

@@ -357,7 +357,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
           char BIGSTK tempo[HTS_CDLMAXSIZE];
 
           strcpybuff(tempo, argv[na] + 1);
-          if (tempo[0] == '\0' || tempo[strlen(tempo) - 1] != '"') {
+          if (hts_lastchar(tempo) != '"') {
             char BIGSTK s[HTS_CDLMAXSIZE];
 
             sprintf(s, "Missing quote in %s", argv[na]);
@@ -365,7 +365,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
             htsmain_free();
             return -1;
           }
-          tempo[strlen(tempo) - 1] = '\0';
+          hts_choplastchar(tempo);
           /* tempo is argv[na] minus its surrounding quotes, so it fits in place
            */
           strlcpybuff(argv[na], tempo, strlen(argv[na]) + 1);
@@ -863,7 +863,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
         char BIGSTK tempo[HTS_CDLMAXSIZE + 256];
 
         strcpybuff(tempo, argv[na] + 1);
-        if (tempo[0] == '\0' || tempo[strlen(tempo) - 1] != '"') {
+        if (hts_lastchar(tempo) != '"') {
           char s[HTS_CDLMAXSIZE + 256];
 
           sprintf(s, "Missing quote in %s", argv[na]);
@@ -871,7 +871,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
           htsmain_free();
           return -1;
         }
-        tempo[strlen(tempo) - 1] = '\0';
+        hts_choplastchar(tempo);
         /* tempo is argv[na] minus its surrounding quotes, so it fits in place
          */
         strlcpybuff(argv[na], tempo, strlen(argv[na]) + 1);
@@ -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");
@@ -2704,10 +2724,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
       char *a;
 
       strcpybuff(rpath, StringBuff(opt->path_html));
-      if (rpath[0]) {
-        if (rpath[strlen(rpath) - 1] == '/')
-          rpath[strlen(rpath) - 1] = '\0';
-      }
+      hts_striplastchar(rpath, '/');
       a = strrchr(rpath, '/');
       if (a) {
         *a = '\0';

src/htsftp.c

@@ -483,16 +483,19 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                     back->r.totalsize = size;
                   }
                 }
-                // REST?
-                if (fexist(back->url_sav) && (transfer_list == 0)) {
+                /* Only over a copy back_add() judged partial: on --update every
+                   mirrored file exists, and resuming a complete one splices the
+                   old body into the new (#798). */
+                if (back->range_req_size > 0 && (transfer_list == 0)) {
                   strcpybuff(back->info, "rest");
-                  snprintf(line, sizeof(line), "REST " LLintP, (LLint) fsize(back->url_sav));
+                  snprintf(line, sizeof(line), "REST " LLintP,
+                           (LLint) back->range_req_size);
                   send_line(soc_ctl, line);
                   get_ftp_line(soc_ctl, line, sizeof(line), timeout);
                   _CHECK_HALT_FTP;
                   if ((line[0] == '3') || (line[0] == '2')) {   // ok
                     rest_understood = 1;
-                  }             // sinon tant pis 
+                  } // else never mind
                 }
               }                 // sinon tant pis 
             }
@@ -617,13 +620,19 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
         // Ok, connexion initiée
         //
         if (soc_dat != INVALID_SOCKET) {
-          if (rest_understood) {        // REST envoyée et comprise
+          if (rest_understood) { // REST sent and understood
             file_notify(opt, back->url_adr, back->url_fil, back->url_sav, 0, 1,
                         0);
+            /* The bytes already on disk count too, or the completeness check
+               below rejects every resumed transfer (#798). */
+            back->r.size = back->range_req_size;
             back->r.fp = fileappend(&opt->state.strc, back->url_sav);
           } else {
             file_notify(opt, back->url_adr, back->url_fil, back->url_sav, 1, 1,
                         0);
+            /* Every failure exit below would else leave the mirror truncated
+               (#771); the resume branch appends and needs no backup. */
+            back_refetch_backup(opt, back);
             back->r.fp = filecreate(&opt->state.strc, back->url_sav);
           }
           strcpybuff(back->info, "receiving");

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

@@ -83,9 +83,8 @@ void infomsg(const char *msg) {
               /* try the flag as-is, then strip a trailing N as the numeric-arg
                  placeholder (cN -> c); this order keeps -%N from becoming -% */
               p = optreal_find(cmd);
-              if (p < 0 && (int) strlen(cmd) > 2 &&
-                  cmd[strlen(cmd) - 1] == 'N') {
-                cmd[strlen(cmd) - 1] = '\0';
+              if (p < 0 && (int) strlen(cmd) > 2 && hts_lastchar(cmd) == 'N') {
+                hts_striplastchar(cmd, 'N');
                 p = optreal_find(cmd);
               }
               if (p >= 0) {
@@ -211,7 +210,7 @@ void help_wizard(httrackp * opt) {
     strcatbuff(str, "/websites/");
   }
   if (strnotempty(str))
-    if ((str[strlen(str) - 1] != '/') && (str[strlen(str) - 1] != '\\'))
+    if ((hts_lastchar(str) != '/') && (hts_lastchar(str) != '\\'))
       strcatbuff(str, "/");
   strcatbuff(stropt2, "-O \"");
   strcatbuff(stropt2, str);
@@ -526,6 +525,11 @@ 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)");
@@ -554,8 +558,7 @@ void help(const char *app, int more) {
   infomsg
     (" %q *include query string for local files (useless, for information purpose only) (%q0 don't include)");
   infomsg(" %g  strip query keys for dedup ([host/pattern=]key1,key2,...)");
-  infomsg
-    ("  o *generate output html file in case of error (404..) (o0 don't generate)");
+  infomsg("  o *save the server's error pages (404..) (o0 discard them)");
   infomsg("  X *purge old files after update (X0 keep delete)");
   infomsg(" %p  preserve html files 'as is' (identical to '-K4 -%F \"\"')");
   infomsg(" %T  links conversion to UTF-8");

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
@@ -2704,17 +2703,8 @@ void hts_now_iso8601(char out[32]) {
   time_t t = time(NULL);
   struct tm tmv;
 
-#if defined(_WIN32)
-  struct tm *g = gmtime(&t);
-
-  if (g != NULL)
-    tmv = *g;
-  else
+  if (!hts_gmtime(t, &tmv))
     memset(&tmv, 0, sizeof(tmv));
-#else
-  if (gmtime_r(&t, &tmv) == NULL)
-    memset(&tmv, 0, sizeof(tmv));
-#endif
   strftime(out, 32, "%Y-%m-%dT%H:%M:%SZ", &tmv);
 }
 
@@ -5079,7 +5069,7 @@ static int hts_dns_resolve_nocache_list(const char *const hostname,
   if (!strnotempty(hostname) || max <= 0) {
     return 0;
   }
-  if ((hostname[0] == '[') && (hostname[strlen(hostname) - 1] == ']')) {
+  if ((hostname[0] == '[') && (hts_lastchar(hostname) == ']')) {
     size_t size = strlen(hostname);
     char *copy = malloct(size + 1);
     int count;
@@ -5492,9 +5482,8 @@ void cut_path(char *fullpath, char *path, size_t path_size, char *pname,
               size_t pname_size) {
   path[0] = pname[0] = '\0';
   if (strnotempty(fullpath)) {
-    if ((fullpath[strlen(fullpath) - 1] == '/')
-        || (fullpath[strlen(fullpath) - 1] == '\\'))
-      fullpath[strlen(fullpath) - 1] = '\0';
+    if (!hts_striplastchar(fullpath, '/'))
+      hts_striplastchar(fullpath, '\\');
     if (strlen(fullpath) > 1) {
       char *a;
 
@@ -5792,7 +5781,8 @@ HTSEXT_API void hts_log_vprint(httrackp * opt, int type, const char *format, va_
   if (hts_log_print_callback != NULL) {
     va_list args_copy;
     va_copy(args_copy, args);
-    hts_log_print_callback(opt, type, format, args);
+    /* the copy, so the vfprintf() below still has an unread list */
+    hts_log_print_callback(opt, type, format, args_copy);
     va_end(args_copy);
   }
   if (opt != NULL && opt->log != NULL) {
@@ -6030,6 +6020,7 @@ 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 +6178,8 @@ 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);
 
@@ -6646,9 +6639,12 @@ int hts_rename_utf8(const char *oldpath, const char *newpath) {
   LPWSTR wnewpath = hts_pathToUCS2(newpath);
   if (woldpath != NULL && wnewpath != NULL) {
     const int result = _wrename(woldpath, wnewpath);
+    /* Save errno: callers key off it (#779) and free() may clobber it. */
+    const int err = errno;
 
     free(woldpath);
     free(wnewpath);
+    errno = err;
     return result;
   } else {
     if (woldpath != NULL)

src/htslib.h

@@ -157,6 +157,19 @@ struct t_dnscache {
   char host_addr[HTS_MAXADDRNUM][HTS_MAXADDRLEN];
 };
 
+/* Break t down as UTC into the caller's buffer, HTS_FALSE if that failed.
+   gmtime()'s static is shared, and both the engine and ProxyTrack convert on
+   worker threads. */
+static HTS_INLINE HTS_UNUSED hts_boolean hts_gmtime(time_t t,
+                                                    struct tm *tmbuf) {
+#ifdef _WIN32
+  /* Microsoft's gmtime_s takes the destination first, unlike C11 Annex K. */
+  return gmtime_s(tmbuf, &t) == 0 ? HTS_TRUE : HTS_FALSE;
+#else
+  return gmtime_r(&t, tmbuf) != NULL ? HTS_TRUE : HTS_FALSE;
+#endif
+}
+
 /* Library internal definictions */
 #ifdef HTS_INTERNAL_BYTECODE
 

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>
 
@@ -439,9 +437,7 @@ int url_savename(lien_adrfilsave *const afs,
 
       strcpybuff(fil_complete_patche, normfil);
       // Version avec ou sans /
-      if (fil_complete_patche[strlen(fil_complete_patche) - 1] == '/')
-        fil_complete_patche[strlen(fil_complete_patche) - 1] = '\0';
-      else
+      if (!hts_striplastchar(fil_complete_patche, '/'))
         strcatbuff(fil_complete_patche, "/");
       i = hash_read(hash, normadr, fil_complete_patche, HASH_STRUCT_ORIGINAL_ADR_PATH);       // recherche table 2 (former->adr+former->fil)
       if (i >= 0) {
@@ -517,7 +513,8 @@ int url_savename(lien_adrfilsave *const afs,
         && protocol != PROTOCOL_FTP
       ) {
       // tester type avec requète HEAD si on ne connait pas le type du fichier
-      if (!((opt->check_type == 1) && (fil[strlen(fil) - 1] == '/')))   // slash doit être html?
+      if (!((opt->check_type == 1) &&
+            (hts_lastchar(fil) == '/'))) // slash doit être html?
         if (opt->savename_delayed == HTS_SAVENAME_DELAYED_HARD ||
             ishtml(opt, fil) < 0) { // unsure whether it's html or a file
           // lire dans le cache
@@ -812,7 +809,7 @@ int url_savename(lien_adrfilsave *const afs,
   // - - - DEBUT NOMMAGE - - -
 
   // Donner nom par défaut?
-  if (fil[strlen(fil) - 1] == '/') {
+  if (hts_lastchar(fil) == '/') {
     if (!strfield(adr_complete, "ftp://")
       ) {
       strcatbuff(fil, DEFAULT_HTML);    // nommer page par défaut!!
@@ -1286,7 +1283,7 @@ int url_savename(lien_adrfilsave *const afs,
 
     hts_lowcase(afs->save);
 
-    if (afs->save[strlen(afs->save) - 1] == '/')
+    if (hts_lastchar(afs->save) == '/')
       strcatbuff(afs->save, DEFAULT_HTML);   // nommer page par défaut!!
   }
 

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/htsparse.c

@@ -1701,7 +1701,8 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 #endif
                                     )   // ok pas de problème
                                     url_ok = 1;
-                                  else if (tempo[strlen(tempo) - 1] == '/') {   // un slash: ok..
+                                  else if (hts_lastchar(tempo) ==
+                                           '/') {       // un slash: ok..
                                     if (inscript)       // sinon si pas javascript, méfiance (répertoire style base?)
                                       url_ok = 1;
                                   }
@@ -2005,9 +2006,8 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
               if (eadr - html - 1 < HTS_URLMAXSIZE) {        // pas trop long?
                 strncpy(lien, html, eadr - html - 1);
                 lien[eadr - html - 1] = '\0';
-                // supprimer les espaces
-                while((lien[strlen(lien) - 1] == ' ') && (strnotempty(lien)))
-                  lien[strlen(lien) - 1] = '\0';
+                while (hts_striplastchar(lien, ' ')) {
+                }
 
               } else
                 lien[0] = '\0'; // erreur
@@ -2207,7 +2207,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 // supposition dangereuse?
                 // OUI!!
 #if HTS_TILDE_SLASH
-                if (lien[strlen(lien) - 1] != '/') {
+                if (hts_lastchar(lien) != '/') {
                   char *a = lien + strlen(lien) - 1;
 
                   // éviter aussi index~1.html
@@ -2272,7 +2272,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                     // Vérifier les codebase=applet (au lieu de applet/)
                     if (p_type == -2) { // codebase
                       if (strnotempty(lien)) {
-                        if (lien[strlen(lien) - 1] != '/') {     // pas répertoire
+                        if (hts_lastchar(lien) != '/') { // pas répertoire
                           strcatbuff(lien, "/");
                         }
                       }
@@ -2688,9 +2688,11 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                             int cat_data_len = 0;
 
                             // ajouter lien external
-                            switch ((link_has_authority(afs.af.adr)) ? 1
-                                    : ((afs.af.fil[strlen(afs.af.fil) - 1] ==
-                                        '/') ? 1 : (ishtml(opt, afs.af.fil)))) {
+                            switch ((link_has_authority(afs.af.adr))
+                                        ? 1
+                                        : ((hts_lastchar(afs.af.fil) == '/')
+                                               ? 1
+                                               : (ishtml(opt, afs.af.fil)))) {
                             case 1:
                             case -2:   // html ou répertoire
                               if (opt->getmode & HTS_GETMODE_HTML) {
@@ -2733,7 +2735,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                                 cat_data_len = HTS_DATA_UNKNOWN_HTML_LEN;
                               }
                               break;
-                            }   // html,gif
+                            } // html,gif
 
                             if (patch_it) {
                               char BIGSTK save[HTS_URLMAXSIZE * 2];

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/htssafe.h

@@ -539,6 +539,36 @@ static HTS_INLINE HTS_UNUSED HTS_PRINTF_FUN(3, 4) void slprintfbuff_clip(
 #define sprintfbuff(ARR, ...) slprintfbuff((ARR), sizeof(ARR), __VA_ARGS__)
 #endif
 
+/* Last character of s, or '\0' when s is empty. Replaces s[strlen(s) - 1],
+   which indexes one byte before the buffer on an empty string. */
+static HTS_INLINE HTS_UNUSED char hts_lastchar(const char *s) {
+  const size_t len = strlen(s);
+
+  return len != 0 ? s[len - 1] : '\0';
+}
+
+/* Drop a trailing c from s if present; HTS_TRUE if one was dropped. */
+static HTS_INLINE HTS_UNUSED hts_boolean hts_striplastchar(char *s, char c) {
+  const size_t len = strlen(s);
+
+  if (len != 0 && s[len - 1] == c) {
+    s[len - 1] = '\0';
+    return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
+/* Drop the last character of s whatever it is; HTS_TRUE if s was not empty. */
+static HTS_INLINE HTS_UNUSED hts_boolean hts_choplastchar(char *s) {
+  const size_t len = strlen(s);
+
+  if (len != 0) {
+    s[len - 1] = '\0';
+    return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
 /* Thin aliases over the libc allocator/memcpy (historical "t" suffix); no
    added bounds checking. freet() also NULLs the freed pointer and tolerates
    NULL. memcpybuff() despite the name is a raw memcpy: the caller owns the

src/htsserver.c

@@ -1050,9 +1050,9 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
                 if (!linput(fp, line, sizeof(line) - 2)) {
                   *str = '\0';
                 }
-                if (*str && str[strlen(str) - 1] == '\\') {
+                if (hts_lastchar(str) == '\\') {
                   nocr = 1;
-                  str[strlen(str) - 1] = '\0';
+                  hts_striplastchar(str, '\\');
                 }
                 while(*str) {
                   char *pos;
@@ -1169,11 +1169,8 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
                           char *rpath = (char *) adr;
 
                           //find_handle h;
-                          if (rpath[0]) {
-                            if (rpath[strlen(rpath) - 1] == '/') {
-                              rpath[strlen(rpath) - 1] = '\0';  /* note: patching stored (inhash) value */
-                            }
-                          }
+                          /* note: patching stored (inhash) value */
+                          hts_striplastchar(rpath, '/');
                           {
                             const char *profiles = hts_getcategories(rpath, 0);
                             const char *categ = hts_getcategories(rpath, 1);

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(opt, 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) {
@@ -970,10 +985,7 @@ HTSEXT_API int hts_buildtopindex(httrackp * opt, const char *path,
       && toptemplate_bodycat) {
 
     strcpybuff(rpath, path);
-    if (rpath[0]) {
-      if (rpath[strlen(rpath) - 1] == '/')
-        rpath[strlen(rpath) - 1] = '\0';
-    }
+    hts_striplastchar(rpath, '/');
 
     fpo = fopen(fconcat(catbuff, sizeof(catbuff), rpath, "/index.html"), "wb");
     if (fpo) {
@@ -1186,11 +1198,8 @@ HTSEXT_API char *hts_getcategories(char *path, int type) {
   find_handle h;
   coucal hashCateg = NULL;
 
-  if (rpath[0]) {
-    if (rpath[strlen(rpath) - 1] == '/') {
-      rpath[strlen(rpath) - 1] = '\0';  /* note: patching stored (inhash) value */
-    }
-  }
+  /* note: patching stored (inhash) value */
+  hts_striplastchar(rpath, '/');
   h = hts_findfirst(rpath);
   if (h) {
     String iname = STRING_EMPTY;
@@ -1287,7 +1296,7 @@ HTSEXT_API find_handle hts_findfirst(char *path) {
 
           strcpybuff(rpath, path);
           if (rpath[0]) {
-            if (rpath[strlen(rpath) - 1] != '\\')
+            if (hts_lastchar(rpath) != '\\')
               strcatbuff(rpath, "\\");
           }
           strcatbuff(rpath, "*.*");
@@ -1299,7 +1308,7 @@ HTSEXT_API find_handle hts_findfirst(char *path) {
         strcpybuff(find->path, path);
         {
           if (find->path[0]) {
-            if (find->path[strlen(find->path) - 1] != '/')
+            if (hts_lastchar(find->path) != '/')
               strcatbuff(find->path, "/");
           }
         }
@@ -1428,3 +1437,76 @@ HTSEXT_API hts_boolean hts_findissystem(find_handle find) {
   }
   return 0;
 }
+
+/* Park cdst under a free sibling name; caside receives it. */
+static hts_boolean rename_park_aside(char *caside, size_t size,
+                                     const char *cdst) {
+  int i;
+
+  for (i = 0; i < 16; i++) {
+    if (!slprintfbuff(caside, size, "%s.hts-old%d", cdst, i))
+      return HTS_FALSE;
+    /* Skip a name the mirror already holds: POSIX rename() would clobber it
+       (#774). A non-regular entry reads as free and the rename refuses it. */
+    if (fexist_utf8(caside))
+      continue;
+    if (RENAME(cdst, caside) == 0)
+      return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
+/* cdst is in the way of the move: park it, retry, and put it back if the retry
+   fails too. Unlinking it instead would leave nothing at all (#790). */
+static hts_boolean rename_over_aside(httrackp *opt, const char *csrc,
+                                     const char *cdst) {
+  char caside[CATBUFF_SIZE];
+  int err;
+
+  /* Only a regular file may be parked: a directory in the way is not what the
+     caller asked to replace, and parking it orphans it (UNLINK cannot drop). */
+  if (!fexist_utf8(cdst))
+    return HTS_FALSE;
+  if (!rename_park_aside(caside, sizeof(caside), cdst))
+    return HTS_FALSE;
+  if (RENAME(csrc, cdst) == 0) {
+    (void) UNLINK(caside);
+    return HTS_TRUE;
+  }
+  err = errno;
+  /* Retry once, then name the parked copy: nothing else on disk or in the log
+     points at it, and an --update purge would delete it unnoticed. */
+  if (RENAME(caside, cdst) != 0 && RENAME(caside, cdst) != 0)
+    hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
+                  "could not put %s back; its previous content is now %s", cdst,
+                  caside);
+  errno = err;
+  return HTS_FALSE;
+}
+
+hts_boolean hts_rename_over(httrackp *opt, 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;
+  /* Only a dst in the way is something the fallback can clear, and the CRT maps
+     that to EEXIST; it keeps EACCES for a src another process holds, where the
+     retry would fail the same way. The src check covers a CRT that reports
+     neither. */
+  const int err = errno;
+
+  if (err != EEXIST || !fexist_utf8(src))
+    return HTS_FALSE;
+  return rename_over_aside(opt, csrc, cdst);
+}
+
+hts_boolean hts_rename_over_aside_selftest(httrackp *opt, const char *src,
+                                           const char *dst) {
+  char csrc[CATBUFF_SIZE], cdst[CATBUFF_SIZE];
+
+  fconv(csrc, sizeof(csrc), src);
+  fconv(cdst, sizeof(cdst), dst);
+  return rename_over_aside(opt, csrc, cdst);
+}

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 +137,18 @@ 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. A dst in the way is parked under a sibling name rather than
+   removed, so the old content survives a failure: back at dst, or under that
+   sibling (named in the log) when the move back failed too. Not atomic: a crash
+   between the two renames leaves dst absent and its content beside it. */
+hts_boolean hts_rename_over(httrackp *opt, const char *src, const char *dst);
+
+/* Selftest hook: run the aside fallback directly, on a platform whose rename()
+   never reaches it. Both paths are fconv()'d. */
+hts_boolean hts_rename_over_aside_selftest(httrackp *opt, const char *src,
+                                           const char *dst);
+
 #endif
 
 #endif

src/htswarc.c

@@ -57,6 +57,9 @@ Please visit our Website: http://www.httrack.com
 /* opt->state.warc value meaning "open failed once, do not retry". */
 #define WARC_DISABLED ((void *) ~(uintptr_t) 0)
 
+/* Suffix of the in-progress archive when a previous one must survive it. */
+#define WARC_TMP_SUFFIX ".tmp"
+
 struct warc_writer {
   FILE *f;
   httrackp *opt;   /* kept for close-time logging (warc_wacz_package) */
@@ -86,6 +89,11 @@ struct warc_writer {
   char *base_path;      /* resolved archive path minus .warc[.gz] suffix */
   const char *base_ext; /* ".warc.gz" or ".warc" (static) */
   char *arc_path;    /* full single-file archive path (NULL under rotation) */
+  /* A re-run must not destroy an archive it cannot replace (#759). */
+  hts_boolean protect_prev;   /* previous archive present: build in a temp */
+  hts_boolean opened;         /* open completed; a failed one swaps nothing */
+  hts_boolean failed;         /* a record or segment was lost: swap nothing */
+  uint64_t unbacked_revisits; /* revisits whose payload no file here holds */
   char **page_lines; /* one JSON page line per 200 text/html response, owned */
   size_t page_count;
   size_t page_cap;
@@ -119,24 +127,32 @@ static void wbuf_free(wbuf *b) {
   b->len = b->cap = 0;
 }
 
-/* Append n bytes; returns 0 on success, -1 on OOM/overflow. */
-static int wbuf_add(wbuf *b, const void *p, size_t n) {
+/* Make room for n more bytes; returns 0 on success, -1 on OOM/overflow. */
+static int wbuf_reserve(wbuf *b, size_t n) {
+  size_t ncap;
+  char *nd;
   if (n > (size_t) -1 - b->len)
     return -1;
-  if (b->len + n > b->cap) {
-    size_t ncap = b->cap ? b->cap : 256;
-    char *nd;
-    while (ncap < b->len + n) {
-      if (ncap > (size_t) -1 / 2)
-        return -1;
-      ncap *= 2;
-    }
-    nd = realloct(b->data, ncap);
-    if (nd == NULL)
+  if (b->len + n <= b->cap)
+    return 0;
+  ncap = b->cap ? b->cap : 256;
+  while (ncap < b->len + n) {
+    if (ncap > (size_t) -1 / 2)
       return -1;
-    b->data = nd;
-    b->cap = ncap;
+    ncap *= 2;
   }
+  nd = realloct(b->data, ncap);
+  if (nd == NULL)
+    return -1;
+  b->data = nd;
+  b->cap = ncap;
+  return 0;
+}
+
+/* Append n bytes; returns 0 on success, -1 on OOM/overflow. */
+static int wbuf_add(wbuf *b, const void *p, size_t n) {
+  if (wbuf_reserve(b, n) != 0)
+    return -1;
   memcpy(b->data + b->len, p, n);
   b->len += n;
   return 0;
@@ -148,16 +164,32 @@ static int wbuf_puts(wbuf *b, const char *s) {
 
 static int wbuf_printf(wbuf *b, const char *fmt, ...) HTS_PRINTF_FUN(2, 3);
 
+/* A header line carrying a URL has no useful bound, and giving up here loses
+   the whole record, so anything past the stack buffer is formatted into the
+   wbuf itself rather than rejected (#785). */
 static int wbuf_printf(wbuf *b, const char *fmt, ...) {
   char tmp[1024];
+  size_t need;
   int n;
   va_list ap;
   va_start(ap, fmt);
   n = vsnprintf(tmp, sizeof(tmp), fmt, ap);
   va_end(ap);
-  if (n < 0 || (size_t) n >= sizeof(tmp))
+  if (n < 0)
     return -1;
-  return wbuf_add(b, tmp, (size_t) n);
+  if ((size_t) n < sizeof(tmp))
+    return wbuf_add(b, tmp, (size_t) n);
+  need = (size_t) n + 1; /* +1: vsnprintf always writes the NUL */
+  if (wbuf_reserve(b, need) != 0)
+    return -1;
+  va_start(ap, fmt);
+  n = vsnprintf(b->data + b->len, need, fmt, ap);
+  va_end(ap);
+  /* Never advance past what was reserved, whatever the second pass returns. */
+  if (n < 0 || (size_t) n >= need)
+    return -1;
+  b->len += (size_t) n; /* the NUL is scratch, overwritten by the next append */
+  return 0;
 }
 
 /* ---- gzip-per-record member writer (mirrors ae_write_packed) ---- */
@@ -964,16 +996,6 @@ 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 +1114,7 @@ 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(w->opt, tmppath, waczpath)) {
     (void) UNLINK(fconv(catbuff, sizeof(catbuff), tmppath));
     hts_log_print(w->opt, LOG_WARNING | LOG_ERRNO,
                   "WACZ: could not finalize %s", waczpath);
@@ -1139,13 +1161,17 @@ static int warc_emit(warc_writer *w, const char *type, const char *content_type,
      never split a record, and never rotate a warcinfo (it opens a segment). */
   if (w->max_size > 0 && w->seg_base != NULL && w->offset >= w->max_size &&
       strcmp(type, "warcinfo") != 0) {
-    if (warc_rotate(w) != 0)
+    if (warc_rotate(w) != 0) {
+      w->failed = HTS_TRUE;
       return -1;
+    }
   }
 
   /* F4: overflow-safe block length; http_hdr_len+sep is provably small. */
-  if (payload > (size_t) -1 - http_hdr_len - sep)
+  if (payload > (size_t) -1 - http_hdr_len - sep) {
+    w->failed = HTS_TRUE;
     return -1;
+  }
   block_len = http_hdr_len + sep + payload;
 
   memset(&hdr, 0, sizeof(hdr));
@@ -1251,11 +1277,23 @@ static int warc_emit(warc_writer *w, const char *type, const char *content_type,
   rc = 0;
 done:
   wbuf_free(&hdr);
+  if (rc != 0)
+    w->failed = HTS_TRUE; /* a truncated run must not replace a whole one */
   return rc;
 }
 
 /* ---- segment rotation (--warc-max-size) ---- */
 
+/* Path to open for the segment whose final path is `final`: that path itself,
+   or a sibling temp while a previous archive must survive until close. */
+static const char *warc_open_path(warc_writer *w, const char *final, char *buf,
+                                  size_t bufsz) {
+  if (!w->protect_prev)
+    return final;
+  snprintf(buf, bufsz, "%s" WARC_TMP_SUFFIX, final);
+  return buf;
+}
+
 /* Emit the warcinfo that heads a segment; sets w->info_id for its records. */
 static int warc_write_warcinfo_record(warc_writer *w) {
   w->info_id[0] = '\0'; /* warcinfo itself carries no WARC-Warcinfo-ID */
@@ -1267,17 +1305,23 @@ static int warc_write_warcinfo_record(warc_writer *w) {
 
 static int warc_rotate(warc_writer *w) {
   char namebuf[HTS_URLMAXSIZE * 2];
+  char openbuf[HTS_URLMAXSIZE * 2 + sizeof(WARC_TMP_SUFFIX)];
   char catbuff[CATBUFF_SIZE];
-  if (w->f != NULL) {
-    fclose(w->f);
-    w->f = NULL;
-  }
-  w->seg++;
-  snprintf(namebuf, sizeof(namebuf), "%s-%05u%s", w->seg_base, w->seg,
+  const unsigned next = w->seg + 1;
+  FILE *f;
+  snprintf(namebuf, sizeof(namebuf), "%s-%05u%s", w->seg_base, next,
            w->seg_ext);
-  w->f = FOPEN(fconv(catbuff, sizeof(catbuff), namebuf), "wb");
-  if (w->f == NULL)
+  /* Open before advancing: w->seg must only ever name a segment that exists,
+     or close-time packaging and swapping would work on a missing file. */
+  f = FOPEN(fconv(catbuff, sizeof(catbuff),
+                  warc_open_path(w, namebuf, openbuf, sizeof(openbuf))),
+            "wb");
+  if (f == NULL)
     return -1;
+  if (w->f != NULL)
+    fclose(w->f);
+  w->f = f;
+  w->seg = next;
   w->offset = 0;
   if (w->cdx_on) {
     freet(w->cur_seg);
@@ -1334,6 +1378,7 @@ void warc_adopt_rawspool(htsblk *r, const char *tmpfile_path) {
 warc_writer *warc_open(httrackp *opt, const char *path) {
   warc_writer *w;
   char namebuf[HTS_URLMAXSIZE * 2];
+  char openbuf[HTS_URLMAXSIZE * 2 + sizeof(WARC_TMP_SUFFIX)];
   char catbuff[CATBUFF_SIZE];
   wbuf info;
   const char *robots;
@@ -1347,16 +1392,8 @@ warc_writer *warc_open(httrackp *opt, const char *path) {
     char ts[32];
     time_t t = time(NULL);
     struct tm tmv;
-#if defined(_WIN32)
-    struct tm *g = gmtime(&t);
-    if (g != NULL)
-      tmv = *g;
-    else
+    if (!hts_gmtime(t, &tmv))
       memset(&tmv, 0, sizeof(tmv));
-#else
-    if (gmtime_r(&t, &tmv) == NULL)
-      memset(&tmv, 0, sizeof(tmv));
-#endif
     strftime(ts, sizeof(ts), "%Y%m%d%H%M%S", &tmv);
     snprintf(catbuff, sizeof(catbuff), "httrack-%s.warc.gz", ts);
     path =
@@ -1484,35 +1521,105 @@ warc_writer *warc_open(httrackp *opt, const char *path) {
     path = namebuf;
   }
 
-  w->f = FOPEN(fconv(catbuff, sizeof(catbuff), path), "wb");
+  if (w->max_size == 0 && (w->arc_path = strdupt(path)) == NULL) {
+    warc_close(w);
+    return NULL;
+  }
+  /* Set only once arc_path is recorded, so a half-built writer never swaps. */
+  w->protect_prev = fsize_utf8(path) > 0 ? HTS_TRUE : HTS_FALSE;
+  w->f = FOPEN(fconv(catbuff, sizeof(catbuff),
+                     warc_open_path(w, path, openbuf, sizeof(openbuf))),
+               "wb");
   if (w->f == NULL) {
     warc_close(w);
     return NULL;
   }
   if (w->cdx_on)
     w->cur_seg = path_basename_dup(path);
-  if (w->wacz_on && w->max_size == 0)
-    w->arc_path = strdupt(path); /* single-file: package this exact path */
 
   if (warc_write_warcinfo_record(w) != 0) {
     warc_close(w);
     return NULL;
   }
+  w->opened = HTS_TRUE;
   return w;
 }
 
+/* Final path of segment s (the run's only archive when rotation is off). */
+static const char *warc_seg_path(warc_writer *w, unsigned s, char *buf,
+                                 size_t bufsz) {
+  if (w->max_size == 0)
+    return w->arc_path;
+  snprintf(buf, bufsz, "%s-%05u%s", w->seg_base, s, w->seg_ext);
+  return buf;
+}
+
+/* Swap this run's archive into place, unless it only holds revisits naming
+   bodies the previous archive still has and this one does not (#759).
+   HTS_FALSE: the previous archive was kept, so leave its .cdx and .wacz too. */
+static hts_boolean warc_commit(warc_writer *w) {
+  char finalbuf[HTS_URLMAXSIZE * 2];
+  char tmpbuf[HTS_URLMAXSIZE * 2 + sizeof(WARC_TMP_SUFFIX)];
+  char catbuff[CATBUFF_SIZE];
+  const unsigned nseg = (w->max_size > 0) ? w->seg + 1 : 1;
+  hts_boolean swap;
+  unsigned s;
+
+  if (!w->protect_prev)
+    return HTS_TRUE; /* nothing was there to lose: written in place */
+
+  /* All or nothing: a swap stopping halfway would mix this run's segments with
+     the previous one's, so require every temp before renaming any. */
+  swap = w->opened && !w->failed && w->unbacked_revisits == 0;
+  for (s = 0; s < nseg && swap; s++) {
+    snprintf(tmpbuf, sizeof(tmpbuf), "%s" WARC_TMP_SUFFIX,
+             warc_seg_path(w, s, finalbuf, sizeof(finalbuf)));
+    swap = fsize_utf8(tmpbuf) > 0;
+  }
+
+  if (swap) {
+    for (s = 0; s < nseg; s++) {
+      const char *final = warc_seg_path(w, s, finalbuf, sizeof(finalbuf));
+      snprintf(tmpbuf, sizeof(tmpbuf), "%s" WARC_TMP_SUFFIX, final);
+      if (!hts_rename_over(w->opt, tmpbuf, final)) {
+        hts_log_print(w->opt, LOG_ERROR | LOG_ERRNO,
+                      "WARC: could not replace %s", final);
+        return HTS_FALSE;
+      }
+    }
+    return HTS_TRUE;
+  }
+
+  for (s = 0; s < nseg; s++) {
+    snprintf(tmpbuf, sizeof(tmpbuf), "%s" WARC_TMP_SUFFIX,
+             warc_seg_path(w, s, finalbuf, sizeof(finalbuf)));
+    (void) UNLINK(fconv(catbuff, sizeof(catbuff), tmpbuf));
+  }
+  if (w->unbacked_revisits > 0)
+    hts_log_print(
+        w->opt, LOG_ERROR,
+        "WARC: this pass revisited %llu URL(s) without re-downloading them, so "
+        "its archive would name bodies no file holds; kept the previous %s "
+        "(re-run with -C0, or --warc-file with a name of its own)",
+        (unsigned long long) w->unbacked_revisits,
+        warc_seg_path(w, 0, finalbuf, sizeof(finalbuf)));
+  return HTS_FALSE;
+}
+
 void warc_close(warc_writer *w) {
   size_t i;
   if (w == NULL)
     return;
-  warc_cdx_flush(w); /* sort + write <base>.cdx before tearing down */
   if (w->f != NULL)
     fclose(w->f);
   w->f = NULL;
+  if (warc_commit(w)) {
+    warc_cdx_flush(w); /* sort + write <base>.cdx beside the archive */
 #if HTS_USEOPENSSL
-  if (w->wacz_on) /* package once the segment(s) + .cdx are closed on disk */
-    warc_wacz_package(w);
+    if (w->wacz_on) /* package once the segment(s) + .cdx are closed on disk */
+      warc_wacz_package(w);
 #endif
+  }
   if (w->seen != NULL)
     coucal_delete(&w->seen);
   for (i = 0; i < w->cdx_count; i++)
@@ -1593,6 +1700,12 @@ int warc_write_transaction(warc_writer *w, const char *target_uri,
   if (is_update_unchanged) {
     is_revisit = 1;
     profile = "http://netpreserve.org/warc/1.1/revisit/server-not-modified";
+    /* Replay resolves a revisit by this field alone, and a 304 stands in for
+       the same URL. No WARC-Refers-To-Date to go with it: the cache keeps the
+       document's Last-Modified, never the previous capture time. */
+    refers_uri = target_uri;
+    /* Served from cache: the payload sits in the previous archive, not here. */
+    w->unbacked_revisits++;
   } else if (have_pdig && w->seen != NULL) {
     void *prev = NULL;
     if (coucal_read_pvoid(w->seen, pdig, &prev) && prev != NULL) {

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" />

src/proxy/proxytrack.c

@@ -520,12 +520,13 @@ static void proxytrack_add_DAV_Item(String * item, String * buff,
                                     const char *filename, size_t size,
                                     time_t timestamp, const char *mime,
                                     int isDir, int isRoot, int isDefault) {
-  struct tm *timetm;
+  struct tm timetmbuf;
+  struct tm *timetm = &timetmbuf;
 
   if (timestamp == (time_t) 0 || timestamp == (time_t) - 1) {
     timestamp = time(NULL);
   }
-  if ((timetm = gmtime(&timestamp)) != NULL) {
+  if (hts_gmtime(timestamp, timetm)) {
     char tms[256 + 1];
     const char *name;
 
@@ -747,7 +748,8 @@ static PT_Element proxytrack_process_DAV_Request(PT_Indexes indexes,
             const char *thisUrl = list[i];
             const char *mimeType = "application/octet-stream";
             unsigned int thisUrlLen = (unsigned int) strlen(thisUrl);
-            int thisIsDir = (thisUrl[thisUrlLen - 1] == '/') ? 1 : 0;
+            /* the folder's default document is enumerated as an empty name */
+            int thisIsDir = (hts_lastchar(thisUrl) == '/') ? 1 : 0;
 
             /* Item URL */
             StringRoom(itemUrl,
@@ -852,8 +854,7 @@ static PT_Element proxytrack_process_HTTP_List(PT_Indexes indexes,
     for(isDir = 1; isDir >= 0; isDir--) {
       for(i = 0; list[i] != NULL; i++) {
         char *thisUrl = list[i];
-        unsigned int thisUrlLen = (unsigned int) strlen(thisUrl);
-        int thisIsDir = (thisUrl[thisUrlLen - 1] == '/') ? 1 : 0;
+        int thisIsDir = (hts_lastchar(thisUrl) == '/') ? 1 : 0;
 
         if (thisIsDir == isDir) {
           if (isDir)

src/proxy/proxytrack.h

@@ -360,21 +360,14 @@ HTS_UNUSED static struct tm *convert_time_rfc822(struct tm *result, const char *
 HTS_UNUSED static struct tm PT_GetTime(time_t t) {
   struct tm tmbuf;
 
-#ifdef _WIN32
-  struct tm *tm = gmtime(&t);
-#else
-  struct tm *tm = gmtime_r(&t, &tmbuf);
-#endif
-  if (tm != NULL)
-    return *tm;
-  else {
+  if (!hts_gmtime(t, &tmbuf)) {
     /* an all-zero tm has tm_mday == 0, which the ARC date field prints as a
        day of "00"; the epoch is the conventional "date unknown" */
     memset(&tmbuf, 0, sizeof(tmbuf));
     tmbuf.tm_year = 70;
     tmbuf.tm_mday = 1;
-    return tmbuf;
   }
+  return tmbuf;
 }
 HTS_UNUSED static int set_filetime(const char *file, struct tm *tm_time) {
   struct utimbuf tim;

tests/01_engine-addlink.test

@@ -0,0 +1,8 @@
+#!/bin/bash
+#
+# an empty current path underflowed htsAddLink's codebase walk (#730).
+
+set -euo pipefail
+
+out=$(httrack -O /dev/null -#test=addlink)
+grep -q "addlink self-test OK" <<<"$out"

tests/01_engine-backswap.test

@@ -0,0 +1,9 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# A ready slot still owning a temporary must stay in memory: swapping it out
+# clears the entry, which unlinks the re-fetch backup (#771).
+out=$(httrack -O /dev/null -#test=backswap)
+grep -q "backswap self-test: OK" <<<"$out"

tests/01_engine-changes.test

@@ -3,25 +3,13 @@
 
 set -euo pipefail
 
-tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_changes_st.XXXXXX") || exit 1
-trap 'rm -rf "$tmpdir"' EXIT HUP INT QUIT PIPE TERM
+testdir=$(cd "$(dirname "$0")" && pwd)
+# shellcheck source=tests/testlib.sh
+. "${testdir}/testlib.sh"
 
-# 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: ${out}"
-        exit 1
-        ;;
-    esac
-}
+tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_changes_st.XXXXXX") || exit 1
+trap 'set +e; rm -rf "$tmpdir"' EXIT
+trap 'rm -rf "$tmpdir"' HUP INT QUIT PIPE TERM
 
 # --changes bucket accounting and JSON escaping (#714).
 expect_ok "changes self-test" httrack -O "${tmpdir}/o1" -#test=changes run

tests/01_engine-cmdline-split.test

@@ -5,4 +5,5 @@ set -euo pipefail
 
 # webhttrack posts its command line as one string: the argv split must grow past
 # 1024 arguments and keep a quote inside a value out of the option parser.
-httrack -O /dev/null -#test=cmdline-split run | grep -q "cmdline-split self-test OK"
+out=$(httrack -O /dev/null -#test=cmdline-split run)
+grep -q "cmdline-split self-test OK" <<<"$out"

tests/01_engine-cmdline.test

@@ -11,7 +11,8 @@
 set -euo pipefail
 
 tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_cmdline.XXXXXX") || exit 1
-trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+trap 'set +e; rm -rf "$tmp"' EXIT
+trap 'rm -rf "$tmp"' HUP INT QUIT PIPE TERM
 
 echo '<html><body>hello</body></html>' >"$tmp/index.html"
 

tests/01_engine-cookieimport.test

@@ -7,6 +7,7 @@ set -euo pipefail
 # cookies *@*.txt) from a long, non-ASCII folder through the UTF-8/long-path
 # file wrappers (#133,#630).
 dir=$(mktemp -d)
-trap 'rm -rf "$dir"' EXIT
+trap 'set +e; rm -rf "$dir"' EXIT
 
-httrack -O /dev/null -#test=cookieimport "$dir" | grep -q "cookieimport:.*OK"
+out=$(httrack -O /dev/null -#test=cookieimport "$dir")
+grep -q "cookieimport:.*OK" <<<"$out"

tests/01_engine-direnum.test

@@ -6,6 +6,7 @@ set -euo pipefail
 # Drives -#test=direnum: enumerate a long+non-ASCII directory through the
 # opendir/readdir wrappers, checking each child round-trips as UTF-8 (#133,#630).
 dir=$(mktemp -d)
-trap 'rm -rf "$dir"' EXIT
+trap 'set +e; rm -rf "$dir"' EXIT
 
-httrack -O /dev/null -#test=direnum "$dir" | grep -q "direnum:.*OK"
+out=$(httrack -O /dev/null -#test=direnum "$dir")
+grep -q "direnum:.*OK" <<<"$out"

tests/01_engine-doitlog.test

@@ -28,7 +28,8 @@ case "$bin" in
 esac
 
 tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_doitlog.XXXXXX") || exit 1
-trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+trap 'set +e; rm -rf "$tmp"' EXIT
+trap 'rm -rf "$tmp"' HUP INT QUIT PIPE TERM
 
 site="$tmp/site"
 out="$tmp/out"

tests/01_engine-escape-room.test

@@ -4,4 +4,5 @@
 set -euo pipefail
 
 # HT_ADD_HTMLESCAPED* must reserve the escaper's worst case (6 for _full).
-httrack -O /dev/null -#test=escape-room run | grep -q "escape-room self-test OK"
+out=$(httrack -O /dev/null -#test=escape-room run)
+grep -q "escape-room self-test OK" <<<"$out"

tests/01_engine-filelist.test

@@ -8,7 +8,8 @@
 set -euo pipefail
 
 tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_filelist.XXXXXX") || exit 1
-trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+trap 'set +e; rm -rf "$tmp"' EXIT
+trap 'rm -rf "$tmp"' HUP INT QUIT PIPE TERM
 
 echo '<html><body>hi</body></html>' >"$tmp/index.html"
 

tests/01_engine-footer-overflow.test

@@ -18,7 +18,7 @@ MINGW* | MSYS* | CYGWIN*) exit 77 ;;
 esac
 
 dir=$(mktemp -d)
-trap 'rm -rf "$dir"' EXIT
+trap 'set +e; rm -rf "$dir"' EXIT
 
 # A few-hundred-char file path (kept well under the URL length limit) makes the
 # {path} field long.
@@ -50,7 +50,7 @@ httrack "file://$deep/index.html" -O "$mir" -%F "$footer" -q -s0 -%v0 \
 
 # The crawled page must exist (proves the URL wasn't rejected for length, so the
 # footer path ran). Look under file/, not $mir, to skip the makeindex top index.
-find "$mir/file" -name index.html | grep -q . || {
+test -n "$(find "$mir/file" -name index.html)" || {
     echo "page not mirrored; the oversized-footer path was not exercised" >&2
     exit 1
 }