Tighten the #630 comments

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

.github/dependabot.yml

@@ -6,9 +6,3 @@ updates:
     directory: /src
     schedule:
       interval: weekly
-
-  # Keep the workflow action pins current (they only rot manually otherwise).
-  - package-ecosystem: github-actions
-    directory: /
-    schedule:
-      interval: weekly

.github/workflows/ci.yml

@@ -31,7 +31,7 @@ jobs:
     env:
       CC: ${{ matrix.cc }}
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -46,32 +46,10 @@ jobs:
       - name: Configure
         run: |
           set -euo pipefail
-          # Regenerate: configure and the Makefile.in's are not tracked.
+          # Regenerate from configure.ac/Makefile.am to validate them; the
+          # committed generated files already let a plain checkout build.
           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" | $CC -DHTS_USEZLIB=0 -I. -Isrc -fsyntax-only -xc - 2>/dev/null; then
-            echo "::error::-DHTS_USEZLIB=0 compiled; htsglobal.h must reject it"
-            exit 1
-          fi
           # a missing decoder would silently drop the coding from Accept-Encoding
           grep -q "define HTS_USEBROTLI 1" config.h
           grep -q "define HTS_USEZSTD 1" config.h
@@ -79,10 +57,7 @@ jobs:
       - name: Build
         run: make -j"$(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"
@@ -100,7 +75,7 @@ jobs:
     name: build (no python3, Debian buildd)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -122,7 +97,6 @@ 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
@@ -145,7 +119,7 @@ jobs:
     name: build (macOS arm64, clang)
     runs-on: macos-14
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -177,7 +151,6 @@ 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"
@@ -193,7 +166,7 @@ jobs:
     name: webhttrack smoke (macOS arm64)
     runs-on: macos-14
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -226,7 +199,7 @@ jobs:
     name: build (linux i386, gcc -m32)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -250,7 +223,6 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -270,7 +242,7 @@ jobs:
     name: sanitize (ASan+UBSan, gcc)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -308,7 +280,6 @@ 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"
@@ -325,7 +296,7 @@ jobs:
     name: msan (MemorySanitizer, clang)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -352,7 +323,6 @@ 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
@@ -374,7 +344,7 @@ jobs:
     name: fuzz (libFuzzer corpus replay, clang)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -413,7 +383,7 @@ jobs:
     name: build (no openssl, --disable-https)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -434,7 +404,6 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        timeout-minutes: 20
         run: |
           jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
           make check -j"$jobs"
@@ -468,7 +437,7 @@ jobs:
             zlib1g-dev libssl-dev libbrotli-dev libzstd-dev \
             debhelper devscripts lintian fakeroot
 
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -499,7 +468,7 @@ jobs:
     name: distcheck (release tarball)
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -524,7 +493,7 @@ jobs:
     if: github.event_name == 'pull_request'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
@@ -568,7 +537,7 @@ jobs:
         tests/*.test
         tools/mkdeb.sh
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
 
       - name: Install linters
         run: |
@@ -603,7 +572,7 @@ jobs:
     if: github.event_name == 'pull_request'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
@@ -627,12 +596,7 @@ jobs:
           set -euo pipefail
           git fetch --no-tags origin \
             "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ 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/${{ github.base_ref }}; cannot scope the check."
-            exit 1
-          fi
+          base="origin/${{ github.base_ref }}"
           set +e
           diff="$(git clang-format --binary clang-format-19 --style=file \
                     --diff --extensions c,h "$base")"
@@ -654,33 +618,3 @@ jobs:
               echo "Fix locally with: git clang-format --binary clang-format-19 $base"
               exit 1 ;;
           esac
-
-  man-page-sync:
-    name: man page / html in sync
-    if: github.event_name == 'pull_request'
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          fetch-depth: 0
-
-      # html/httrack.man.html is groff-rendered from man/httrack.1 and committed.
-      # Rendering needs the full groff html device, so CI can't regenerate it;
-      # instead require the two to move together: a PR that touches httrack.1
-      # must also touch the html, catching the "regenerated roff, forgot html".
-      - name: httrack.1 changes must include html/httrack.man.html
-        run: |
-          set -euo pipefail
-          git fetch --no-tags origin \
-            "+refs/heads/${{ 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
-            echo "::error::man/httrack.1 changed but html/httrack.man.html did not."
-            echo "Regenerate it with: make -C man regen-man-html (needs the full groff package)."
-            exit 1
-          fi
-          echo "man/html sync OK."

.github/workflows/codeql.yml

@@ -26,7 +26,7 @@ jobs:
       # Upload findings to the repo's code-scanning dashboard.
       security-events: write
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -55,9 +55,6 @@ jobs:
             query-filters:
               - exclude:
                   id: cpp/world-writable-file-creation
-              # Models auth-bypass-by-spoofing; httrack has no auth surface, its +/- crawl filter is a mirror boundary, not a security one.
-              - exclude:
-                  id: cpp/user-controlled-bypass
 
       # Manual build: CodeQL traces the compiler, so build exactly what ships.
       - name: Build

.github/workflows/windows-build.yml

@@ -23,13 +23,8 @@ jobs:
       matrix:
         platform: [x64, Win32]
         configuration: [Release]
-    # Redirect vcpkg's default `files` binary cache into the workspace so
-    # actions/cache can persist it. vcpkg builds openssl/brotli/zlib/zstd from
-    # source otherwise, several minutes every run.
-    env:
-      VCPKG_DEFAULT_BINARY_CACHE: ${{ github.workspace }}\vcpkg_cache
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v4
         with:
           submodules: recursive   # coucal lives in src/coucal
 
@@ -49,24 +44,6 @@ jobs:
         shell: pwsh
         run: vcpkg integrate install
 
-      # vcpkg errors if VCPKG_DEFAULT_BINARY_CACHE points at a missing dir, and
-      # actions/cache does not create it on a miss.
-      - name: Create the vcpkg binary cache directory
-        shell: pwsh
-        run: New-Item -ItemType Directory -Force -Path $env:VCPKG_DEFAULT_BINARY_CACHE | Out-Null
-
-      # x-gha is gone (vcpkg-tool #1662 dropped it after GitHub changed the cache
-      # API), so cache the binary archives directly. Keyed on the manifest, which
-      # carries the builtin-baseline, so a Dependabot bump busts it; restore-keys
-      # still seeds the unchanged ports' archives, so only the bumped one rebuilds.
-      - name: Cache vcpkg binary archives
-        uses: actions/cache@v6
-        with:
-          path: ${{ github.workspace }}\vcpkg_cache
-          key: vcpkg-${{ matrix.platform }}-${{ hashFiles('src/vcpkg.json') }}
-          restore-keys: |
-            vcpkg-${{ matrix.platform }}-
-
       # The runner image's vcpkg checkout is pinned to some commit; our manifest's
       # builtin-baseline is usually newer, so `git show <baseline>:versions/...`
       # fails until that commit is local. Fetch exactly the pinned baseline (read
@@ -189,54 +166,25 @@ 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 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.
+          # TerminateProcess-es the whole tree. 600s clears the slowest multi-pass
+          # crawl (a few passes at --max-time=120 each).
           . ./testlib.sh
-          per_test=600
 
-          # 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
+          pass=0 fail=0 skip=0 failed="" skipped=""
           for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test \
                    *_local-*.test 13_crawl_proxy_https.test 58_watchdog.test \
-                   60_crawl-log-salvage.test 106_engine-repair-rename.test \
-                   108_engine-refetch-backup.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"
+                   60_crawl-log-salvage.test; do
             rc=0
-            # 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" >"$t.log" 2>&1 || rc=$?
+            run_with_timeout 600 bash "$t" >"$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/^/      /'
                 ;;
               *)
@@ -244,36 +192,24 @@ 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 "$per_test" bash -x "$t" >>"$t.log" 2>&1 || true
+                run_with_timeout 600 bash -x "$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 and purge-longpath skip on Windows (need a path past MAX_PATH);
-          # crange pending #581;
-          # webdav-mime needs a reapable background listener, which MSYS cannot give it;
-          # 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 100_local-purge-longpath.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 ${suite_deadline}s"; exit 1; }
+          expected_skips=" 48_local-crange-memresume.test 71_local-crange-repaircache.test"  # pending #581
           [ "$pass" -ge 90 ] || { echo "::error::only $pass tests passed ($skip skipped)"; exit 1; }
           [ "$skipped" = "$expected_skips" ] || { echo "::error::unexpected skips:$skipped"; exit 1; }
           [ "$fail" -eq 0 ] || { echo "::error::failing:$failed"; exit 1; }
 
       - name: Upload the test logs
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: engine-tests-${{ matrix.platform }}-${{ matrix.configuration }}
           path: tests/*.log
@@ -281,7 +217,7 @@ jobs:
 
       - name: Upload MSBuild logs
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: msbuild-${{ matrix.platform }}-${{ matrix.configuration }}
           path: msbuild-*.log

AGENTS.md

@@ -26,18 +26,6 @@ the operational checklist: toolchain, invariants, and how to ship a change.
   check`, or `PATH="<bld>/src:$PATH"` for a manual run.
 - Give new `.test` scripts `set -e`: the older ones predate the rule, so several
   `local-crawl.sh` calls with no `set -e` report PASS on any non-last failure.
-- Run teardown with errexit off: `trap 'set +e; cleanup' EXIT`. Under `set -e` a
-  failing cleanup command becomes the test's exit status (#773). Keep the other
-  signals on their own `trap` line, or errexit stays off for the rest of the run.
-  The guard also resets `$?`, 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
@@ -60,16 +48,6 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 - Bounds-check every copy. Overflow-safe form: put the untrusted value alone,
   `untrusted < limit - controlled` — never `controlled + untrusted < limit`,
   which can wrap and pass.
-- **Abort or clip is a decision, not a default.** The `*_safe_` helpers
-  (`strcpybuff`, `strlcpybuff`, `strcatbuff`) **abort** on overflow. Right for
-  our own data, wrong for anything read back from a cache, a header or the
-  wire, where it trades a memory smash for a crash on malformed input. Clip
-  with `dst[0] = '\0'; strlncatbuff(dst, src, size, size - 1)`.
-- **A warning class is not the unsafe set.** `-Wformat-truncation` fires only on
-  a *bounded* `snprintf` whose return is discarded, so an unbounded `sprintf`
-  into the same buffer never appears on it. Before scoping a hardening pass off
-  compiler output, grep the unguarded forms yourself (`\bsprintf\s*\(`,
-  `\bstrcpy\s*\(`, `\bstrcat\s*\(`).
 
 ## C conventions
 - **Use the `*t` allocator wrappers, never raw libc** (`htssafe.h`):
@@ -106,17 +84,6 @@ Before pushing, and when reviewing others, don't skim for bugs:
   layout/ABI, cache/wire format, or a security path? A static or unit check
   isn't enough; exercise the wrong behavior at runtime. Claude Code:
   `/review-recipe`.
-- **Poison a canary, never compare it against zero.** Checking that a
-  neighbouring field is still `'\0'` cannot see the stray NUL an off-by-one
-  terminator writes — the exact bug the canary is there for. Fill it with a
-  non-zero byte, and prove it by killing both the stray-`'X'` and the
-  stray-NUL mutant. Neither ASan nor `_FORTIFY_SOURCE` sees an overflow that
-  lands inside the same struct.
-- **Overshoot every destination, not one.** A bounds test that oversizes a
-  single field cannot tell a per-field bound from a one-size-fits-all one, nor
-  from a fix that bounds that field and leaves its neighbours raw. Exercise
-  each destination the path touches, spanning at least two capacities, and
-  check what the code actually emits before writing the expected values.
 
 ## Commits
 - **Sign-off is mandatory.** Every commit carries a `Signed-off-by` trailer:

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.14], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.13], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
 AC_COPYRIGHT([
 HTTrack Website Copier, Offline Browser for Windows and Unix
 Copyright (C) 1998-2015 Xavier Roche and other contributors
@@ -29,12 +29,13 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 3:6:0: 3.49.14 grows two installed structs from the inside (htsoptstate sits mid-
-# httrackp, htsblk mid-lien_back), so the fields after them shift: httrackp.cookies_file
-# +8, lien_back.http11 +48. Soname deliberately stays .so.3: the shifted fields are
-# 3.49-era additions no external consumer reaches, and a libhttrack3 rename isn't worth it.
+# 3:5:0: 3.49.13 leaves every installed struct layout and the exported symbol set
+# untouched vs 3.49.12; the 2 GB (_stat64) and UTF-8 export widenings are _WIN32-only,
+# and INTsys widened on POSIX (#600) but sits in no installed struct. Stays soname
+# .so.3; bump revision. x32 alone changes layout (LLint was 4 bytes there, #524), and
+# is not a release architecture.
 # (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
-VERSION_INFO="3:6:0"
+VERSION_INFO="3:5:0"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 
@@ -66,11 +67,10 @@ AC_SUBST(LT_CV_OBJDIR,$lt_cv_objdir)
 AC_SUBST(VERSION_INFO)
 
 ### Default CFLAGS
-# No -Wdeclaration-after-statement: nothing sets -std=, so this builds as gnu17.
 DEFAULT_CFLAGS="-Wall -Wformat -Wformat-security \
 -Wmultichar -Wwrite-strings -Wcast-qual -Wcast-align \
 -Wstrict-prototypes -Wmissing-prototypes \
--Wmissing-declarations \
+-Wmissing-declarations -Wdeclaration-after-statement \
 -Wpointer-arith -Wsequence-point -Wnested-externs \
 -D_REENTRANT"
 AC_SUBST(DEFAULT_CFLAGS)
@@ -78,30 +78,27 @@ DEFAULT_LDFLAGS=""
 AC_SUBST(DEFAULT_LDFLAGS)
 
 ### Additional flags (if supported)
-# -Werror on probes: exit-status-only checks let clang's warn-on-unknown-flag through.
-AX_CHECK_COMPILE_FLAG([-Wparentheses], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wparentheses"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Winit-self], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Winit-self"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Wunused-but-set-parameter], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wunused-but-set-parameter"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Waddress], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Waddress"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Wuninitialized], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wuninitialized"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Wformat=2], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wformat=2"], [], [-Werror])
-# -Wformat-nonliteral needs -Wformat in the probe or gcc rejects it as ignored.
-AX_CHECK_COMPILE_FLAG([-Wformat-nonliteral], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wformat-nonliteral"], [], [-Werror -Wformat])
-AX_CHECK_COMPILE_FLAG([-Wmissing-parameter-type], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wmissing-parameter-type"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Wold-style-definition], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wold-style-definition"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Wignored-qualifiers], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wignored-qualifiers"], [], [-Werror])
+AX_CHECK_COMPILE_FLAG([-Wparentheses], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wparentheses"])
+AX_CHECK_COMPILE_FLAG([-Winit-self], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Winit-self"])
+AX_CHECK_COMPILE_FLAG([-Wunused-but-set-parameter], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wunused-but-set-parameter"])
+AX_CHECK_COMPILE_FLAG([-Waddress], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Waddress"])
+AX_CHECK_COMPILE_FLAG([-Wuninitialized], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wuninitialized"])
+AX_CHECK_COMPILE_FLAG([-Wformat=2], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wformat=2"])
+AX_CHECK_COMPILE_FLAG([-Wformat-nonliteral], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wformat-nonliteral"])
+AX_CHECK_COMPILE_FLAG([-Wmissing-parameter-type], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wmissing-parameter-type"])
+AX_CHECK_COMPILE_FLAG([-Wold-style-definition], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wold-style-definition"])
+AX_CHECK_COMPILE_FLAG([-Wignored-qualifiers], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Wignored-qualifiers"])
 # Make htssafe.h's pointer-dest 'warning' attribute a hard error in our build
 # (migration is at zero; a new char* dest is a regression). gcc/clang each take
 # only their own spelling; downstream keeps the plain warning, not a build break.
-AX_CHECK_COMPILE_FLAG([-Werror=attribute-warning], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=attribute-warning"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-Werror=user-defined-warnings], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=user-defined-warnings"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-fstrict-aliasing -Wstrict-aliasing], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstrict-aliasing -Wstrict-aliasing"], [], [-Werror])
+AX_CHECK_COMPILE_FLAG([-Werror=attribute-warning], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=attribute-warning"])
+AX_CHECK_COMPILE_FLAG([-Werror=user-defined-warnings], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=user-defined-warnings"])
+AX_CHECK_COMPILE_FLAG([-fstrict-aliasing -Wstrict-aliasing], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstrict-aliasing -Wstrict-aliasing"])
 AX_CHECK_COMPILE_FLAG([-fstack-protector-strong], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector-strong"],
-	[AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector"], [], [-Werror])], [-Werror])
-AX_CHECK_COMPILE_FLAG([-fstack-clash-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-clash-protection"], [], [-Werror])
-AX_CHECK_COMPILE_FLAG([-fcf-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fcf-protection"], [], [-Werror])
-# No --discard-all: it drops the local symbols naming every static function, so
-# a trace misattributes them to the nearest surviving global. Costs 0.6% size.
+	[AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector"])])
+AX_CHECK_COMPILE_FLAG([-fstack-clash-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-clash-protection"])
+AX_CHECK_COMPILE_FLAG([-fcf-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fcf-protection"])
+AX_CHECK_LINK_FLAG([-Wl,--discard-all], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--discard-all"])
 AX_CHECK_LINK_FLAG([-Wl,--no-undefined], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--no-undefined"])
 AX_CHECK_LINK_FLAG([-Wl,-z,relro,-z,now], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,-z,relro,-z,now"])
 AX_CHECK_LINK_FLAG([-Wl,-z,noexecstack], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,-z,noexecstack"])
@@ -123,13 +120,13 @@ AC_SUBST([LIBC_FORCE_LINK])
 ### PIE
 CFLAGS_PIE=""
 LDFLAGS_PIE=""
-AX_CHECK_COMPILE_FLAG([-fpie], [CFLAGS_PIE="-fpie"], [], [-Werror])
+AX_CHECK_COMPILE_FLAG([-fpie -pie], [CFLAGS_PIE="-fpie -pie"])
 AX_CHECK_LINK_FLAG([-pie], [LDFLAGS_PIE="-pie"])
 AC_SUBST([CFLAGS_PIE])
 AC_SUBST([LDFLAGS_PIE])
 
-# Ties a crash trace from a stripped build back to its separate debug symbols.
-AX_CHECK_LINK_FLAG([-Wl,--build-id], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--build-id"])
+## Export all symbols for backtraces
+AX_CHECK_COMPILE_FLAG([-rdynamic], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -rdynamic"])
 
 ### Check for -fvisibility=hidden support
 gl_VISIBILITY
@@ -173,9 +170,9 @@ AC_CHECK_TYPE(sa_family_t, [], [AC_DEFINE([sa_family_t], [uint16_t], [sa_family_
 AX_CHECK_ALIGNED_ACCESS_REQUIRED
 
 # check for various headers
-AC_CHECK_HEADERS([execinfo.h sys/ioctl.h])
+AC_CHECK_HEADERS([execinfo.h])
 
-### zlib (mandatory)
+### zlib
 CHECK_ZLIB()
 
 ### brotli and zstd content codings (optional)

debian/changelog

@@ -1,11 +1,3 @@
-httrack (3.49.14-1) unstable; urgency=medium
-
-  * New upstream release: WARC/WACZ archive output, Windows long-path support,
-    named -%F footer fields, and encoding fixes for non-ASCII project paths;
-    full list in history.txt.
-
- -- Xavier Roche <xavier@debian.org>  Fri, 24 Jul 2026 08:01:43 +0200
-
 httrack (3.49.13-1) unstable; urgency=medium
 
   * New upstream release: SOCKS5 and CONNECT proxy support, brotli and zstd

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-sitemap
+	fuzz-htsparse
 endif
 
 AM_CPPFLAGS = \
@@ -27,8 +27,6 @@ fuzz_url_SOURCES = fuzz-url.c fuzz.h
 fuzz_header_SOURCES = fuzz-header.c fuzz.h
 fuzz_cachendx_SOURCES = fuzz-cachendx.c fuzz.h
 fuzz_htsparse_SOURCES = fuzz-htsparse.c fuzz.h
-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 \
@@ -49,10 +47,4 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/cachendx/regress-overadvance.bin \
 	corpus/cachendx/regress-truncated-entry.bin \
 	corpus/htsparse/basic.html corpus/htsparse/script-inscript.html \
-	corpus/htsparse/meta-usemap.html corpus/htsparse/malformed.html \
-	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/sitemap/urlset.xml corpus/sitemap/sitemapindex.xml \
-	corpus/sitemap/truncated.xml corpus/sitemap/urlset.xml.gz
+	corpus/htsparse/meta-usemap.html corpus/htsparse/malformed.html

fuzz/corpus/singlefile/img-src.html

@@ -1,3 +0,0 @@
-<img src="a.png">
-<img src=big.png alt=over-cap>
-<img src="../escape.png"><img src="/abs.png"><img src="data:,x">

fuzz/corpus/singlefile/link-rel.html

@@ -1,4 +0,0 @@
-<link rel="stylesheet" href="s.css">
-<link rel=icon href=a.png>
-<link rel="next" href="p2.html">
-<link rel="preload" href="j.js">

fuzz/corpus/singlefile/malformed.html

@@ -1,5 +0,0 @@
-<img src="unterminated.png
-<div style="background:url(a.png">
-<style>@import url(
-<!-- unterminated comment
-<a href=

fuzz/corpus/singlefile/many-attrs.html

@@ -1 +0,0 @@
-<img src="a.png" a0="v" a1="v" a2="v" a3="v" a4="v" a5="v" a6="v" a7="v" a8="v" a9="v" a10="v" a11="v" a12="v" a13="v" a14="v" a15="v" a16="v" a17="v" a18="v" a19="v" a20="v" a21="v" a22="v" a23="v" a24="v" a25="v" a26="v" a27="v" a28="v" a29="v" a30="v" a31="v" a32="v" a33="v" a34="v" a35="v" a36="v" a37="v" a38="v" a39="v" a40="v" a41="v" a42="v" a43="v" a44="v" a45="v" a46="v" a47="v" a48="v" a49="v" a50="v" a51="v" a52="v" a53="v" a54="v" a55="v" a56="v" a57="v" a58="v" a59="v" a60="v" a61="v" a62="v" a63="v" a64="v" a65="v" a66="v" a67="v" a68="v" a69="v">

fuzz/corpus/singlefile/rawtext.html

@@ -1,4 +0,0 @@
-<script>var s="</scripting>"; if(a</b) x=1;</script>
-<script src="j.js"></script>
-<textarea></textareas></textarea>
-<title></titles></title>

fuzz/corpus/singlefile/srcset.html

@@ -1,2 +0,0 @@
-<img srcset="a.png 1x, big.png 2x, a.png 100w">
-<source srcset="a.png,, a.png 2x," src="a.png">

fuzz/corpus/singlefile/style-attr.html

@@ -1,2 +0,0 @@
-<div style="background:url(a.png);list-style:url('a.png')"></div>
-<p style='background:url("a.png")'>x</p>

fuzz/corpus/singlefile/style-block.html

@@ -1,5 +0,0 @@
-<style>@import "s.css";
-@import url(sub/b.css);
-div{background:url(a.png)}
-/* url(a.png) */ p:after{content:"url(a.png)"}
-</style>

fuzz/corpus/sitemap/sitemapindex.xml

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

fuzz/corpus/sitemap/truncated.xml

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

fuzz/corpus/sitemap/urlset.xml

@@ -1 +0,0 @@
-
<?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-singlefile.c

@@ -1,131 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-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 --single-file rewriter (htssinglefile.c): hostile HTML walked
-   through the tag, CSS url()/@import and srcset parsers, then re-serialized.
-   The resolver is aimed at a private temp tree, so the inlining half (MIME
-   guess, base64, nested stylesheet) is reached and nothing else on disk is. */
-#include "fuzz.h"
-
-#include "httrack-library.h"
-#include "htssinglefile.h"
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/stat.h>
-
-/* Between a.png and big.png, so one input reaches both the inline path and the
-   over-cap fallback. */
-#define FUZZ_SF_CAP 64
-
-static char sf_root[512];
-static char sf_page[600];
-
-/* The asset tree, in removal order: the subdirectory comes after its file. */
-static const char *const sf_files[] = {"a.png",     "big.png", "j.js", "s.css",
-                                       "sub/b.css", "sub",     NULL};
-
-static void sf_cleanup(void) {
-  char path[700];
-  int i;
-
-  for (i = 0; sf_files[i] != NULL; i++) {
-    snprintf(path, sizeof(path), "%s/%s", sf_root, sf_files[i]);
-    (void) remove(path);
-  }
-  (void) remove(sf_root);
-}
-
-/* A missing asset would silently reduce the target to its parser half. */
-static void sf_write(const char *name, const char *data, size_t len) {
-  char path[700];
-  FILE *fp;
-
-  snprintf(path, sizeof(path), "%s/%s", sf_root, name);
-  fp = fopen(path, "wb");
-  if (fp == NULL || fwrite(data, 1, len, fp) != len)
-    abort();
-  fclose(fp);
-}
-
-static void sf_text(const char *name, const char *data) {
-  sf_write(name, data, strlen(data));
-}
-
-static void sf_init(void) {
-  static const char png[] = "\x89PNG\r\n\x1a\n";
-  static const char big[4096] = "\x89PNG";
-  const char *tmp = getenv("TMPDIR");
-  char path[700];
-
-  hts_init();
-  snprintf(sf_root, sizeof(sf_root), "%s/httrack-fuzz-sf-XXXXXX",
-           tmp != NULL && tmp[0] != '\0' ? tmp : "/tmp");
-  if (mkdtemp(sf_root) == NULL)
-    abort();
-  atexit(sf_cleanup);
-  snprintf(sf_page, sizeof(sf_page), "%s/page.html", sf_root);
-  snprintf(path, sizeof(path), "%s/sub", sf_root);
-  if (mkdir(path, 0700) != 0)
-    abort();
-  sf_write("a.png", png, sizeof(png) - 1);
-  sf_write("big.png", big, sizeof(big));
-  sf_text("j.js", "var x=1;\n");
-  /* @import plus a url(), so an inlined stylesheet recurses and its own
-     relative reference is rebased. */
-  sf_text("s.css", "@import url(sub/b.css);\ndiv{background:url(a.png)}\n");
-  sf_text("sub/b.css", "p{background:url(../a.png)}\n");
-}
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static int inited = 0;
-
-  String out = STRING_EMPTY;
-  httrackp *opt;
-  /* Exact-length, unterminated: the rewriter is span-based, so ASan bounds a
-     read past html_len instead of it landing on a terminator. */
-  char *html = malloct(size != 0 ? size : 1);
-
-  if (!inited) {
-    sf_init();
-    inited = 1;
-  }
-  memcpy(html, data, size);
-
-  opt = hts_create_opt();
-  opt->log = opt->errlog = NULL;
-  opt->single_file_max_size = FUZZ_SF_CAP;
-
-  StringClear(out);
-  (void) singlefile_rewrite_html(opt, sf_root, sf_page, html, size,
-                                 SINGLEFILE_MAX_PAGE_SIZE, &out);
-
-  StringFree(out);
-  freet(html);
-  hts_free_opt(opt);
-  return 0;
-}

fuzz/fuzz-sitemap.c

@@ -1,60 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-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;
-}

greetings.txt

@@ -5,7 +5,7 @@ Xavier Roche (xroche at httrack.com)
   project leader
   core engine, Windows/Linux GUI
 Yann Philippot (yphilippot at lemel.fr)
-  past contributor (java binary .class parser)
+  for the java binary .class parser
 
 With the help of:
 Leto Kauler (molotov at tasmail.com)

history.txt

@@ -4,23 +4,6 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
-3.49-14
-+ New: WARC/1.1 archive output (--warc), with a sorted CDXJ index (--warc-cdx) and WACZ packaging (--wacz), also available from webhttrack (#668)
-+ New: -%F takes named footer fields such as {url}, {lastmodified}, {mime}, {charset} and {status} instead of a fixed layout (#667)
-+ New: a command-line guide organized by task ships with the offline documentation (#649)
-+ Fixed: on Windows, paths beyond MAX_PATH truncated files, and mirroring into a long or non-ASCII directory silently failed (#133)
-+ Fixed: the top index showed mojibake for non-ASCII project names and categories on Windows (#216)
-+ Fixed: webhttrack handed the engine the web form's charset rather than UTF-8, so a non-ASCII path mirrored into a mojibake directory (#629)
-+ Fixed: a non-ASCII single -O left the logs and the cache in a mangled twin directory on Windows (#630)
-+ Fixed: a path-ceiling truncation dropped the .delayed marker, losing the file (#623)
-+ Fixed: an oversized -%F footer aborted the crawl instead of being skipped (#669)
-+ Fixed: a rejected 206 resume could loop and lose the file rather than refetch it whole (#581)
-+ Fixed: default-port stripping was scheme-blind and dropped explicit ports from https and ftp URLs, and a :80 written with leading zeros mangled the host (#627, #638)
-+ Fixed: -K silently reset the -c socket count (#650)
-+ Fixed: signed-shift undefined behaviour in the zip-repair local-header read (#639)
-+ Changed: the offline documentation drops stale facts, gains an Android help page, and documents the filter wildcards and the real long option forms
-+ Changed: multiple internal hardening, test and CI improvements
-
 3.49-13
 + New: SOCKS5 proxy support, with scheme-aware -P URLs (socks5://, socks5h://, connect://) and plain HTTP tunneled through a CONNECT-only proxy (#563, #564)
 + New: decode brotli and zstd content codings, advertised over TLS only as browsers do (#556)

html/abuse.html

@@ -217,7 +217,7 @@ school or
 shows. They might do that because they are connected through expensive modem connection,
 or because they would like to consult pages while travelling, or archive sites that may be
 removed
-one day, make some data mining, compiling information ("if only I could find this
+one day, make some data mining, comiling information ("if only I could find this
 website I saw one day..&quot;). <br>
 There are many good reasons to mirror websites, and this helps many good people.<br>
 As a webmaster, you might be interested to use such tools, too: test broken links, move a
@@ -229,7 +229,7 @@ test the webserver response and performances, index it..<br>
 Anyway, bandwidth abuse can be a problem. If your site is regularly &quot;clobbered&quot;
 by evil downloaders, you have <br>
 various solutions. You have radical solutions, and intermediate solutions. I strongly
-recommend not to use<br>
+recomment not to use<br>
 radical solutions, because of the previous remarks (good people often mirror websites).<br>
 <br>
 In general, for all solutions,<br>
@@ -244,7 +244,7 @@ or, to be extreme: if you unplug the wire, there will be no bandwidth abuse<br>
 Good: Will work with good people. Many good people just don't KNOW that they can slow down
 a network.<br>
 Bad: Will **only** work with good people<br>
-How to do: Obvious - place a note, a warning, an article, a draw, a poem or whatever you
+How to do: Obvious - place a note, a warning, an article, a draw, a poeme or whatever you
 want<br>
 <br>
 </li><li>Use &quot;robots.txt&quot; file<br>
@@ -266,7 +266,7 @@ Good: Efficient<br>
 Bad: Multiple users behind proxies will be slow down, not really easy to setup<br>
 How to do: Depends on webserver. Might be done with low-level IP rules (QoS)<br>
 <br>
-</li><li>Prioritize small files, against large files<br>
+</li><li>Priorize small files, against large files<br>
 Good: Efficient if large files are the cause of abuse<br>
 Bad: Not always efficient<br>
 How to do: Depends on the webserver<br>
@@ -283,7 +283,7 @@ How to do: Use routine QoS (fair queuing), or webserver options<br>
 <br>
 </li><li>Use technical tricks (like javascript) to hide URLs<br>
 Good: Efficient<br>
-Bad: The most efficient tricks will also cause your website to be heavy, and not
+Bad: The most efficient tricks will also cause your website to he heavy, and not
 user-friendly (and therefore less attractive, even for surfing users). Remember: clients
 or visitors might want to consult offline your website. Advanced users will also be still
 able to note the URLs and catch them. Will not work on non-javascript browsers. It will
@@ -335,7 +335,7 @@ Example: Use things like
 </li><li>Use technical tricks to temporarily ban IPs<br>
 Good: Efficient<br>
 Bad: Radical (your site will only be available online for all users), not easy to setup<br>
-How to do: Create fake links with &quot;killing&quot; targets<br>
+How to to: Create fake links with &quot;killing&quot; targets<br>
 Example: Use things like &lt;a href=&quot;killme.cgi&quot;&gt;&lt;nothing&gt;&lt;/a&gt;
 (again an example in php:)<br>
 <tt>
@@ -417,7 +417,7 @@ Example:<br>
 </li><li>Another one is to create images of emails<br>
 Good: Efficient, does not require javascript<br>
 Bad: There is still the problem of the link (mailto:), images are bigger than text, and it can cause problems for blind people (a good solution is use an ALT attribute with the email written like "smith at mycompany dot com")<br>
-How to do: Not so obvious if you do not want to create images by yourself<br>
+How to do: Not so obvious of you do not want to create images by yourself<br>
 Example: (php, Unix)<br>
 
 <tt>
@@ -491,7 +491,7 @@ echo <br>
 </li><li>You can also create temporary email aliases, each week, for all users<br>
 Good: Efficient, and you can give your real email in your reply-to address<br>
 Bad: Temporary emails<br>
-How to do: Not so hard to do<br>
+How to do: Not so hard todo<br>
 Example: (script &amp; php, Unix)<br>
 
 <tt>

html/changes.html

@@ -1,263 +0,0 @@
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
-
-<head>
-	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
-	<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" />
-	<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" />
-	<title>HTTrack Website Copier - Change report format specification</title>
-
-	<style type="text/css">
-	<!--
-
-body {
-	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
-	background: #77b;
-}
-body, td {
-	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
-	}
-
-#subTitle {
-	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
-	}
-
-#siteNavigation a, #siteNavigation .current {
-	font-weight: bold;  color: #448;
-	}
-#siteNavigation a:link    { text-decoration: none; }
-#siteNavigation a:visited { text-decoration: none; }
-
-#siteNavigation .current { background-color: #ccd; }
-
-#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
-#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
-
-
-a:link    { text-decoration: underline;  color: #00f; }
-a:visited { text-decoration: underline;  color: #000; }
-a:hover   { text-decoration: underline;  color: #c00; }
-a:active  { text-decoration: underline; }
-
-#pageContent {
-	clear: both;
-	border-bottom: 6px solid #000;
-	padding: 10px;  padding-top: 20px;
-	line-height: 1.65em;
-	background-image: url(images/bg_rings.gif);
-	background-repeat: no-repeat;
-	background-position: top right;
-	}
-
-#pageContent, #siteNavigation {
-	background-color: #ccd;
-	}
-
-
-.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
-.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
-
-hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
-
-h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
-h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
-h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
-h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
-
-.blak { background-color: #000; }
-.hide { display: none; }
-.tableWidth { min-width: 400px; }
-
-.tblRegular       { border-collapse: collapse; }
-.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
-.tblHeaderColor, .tblHeaderColor td { background: #99c; }
-.tblNoBorder td   { border: 0; }
-
-
-// -->
-</style>
-
-</head>
-
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-	<tr>
-	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
-	<tr>
-	<td id="subTitle">Open Source offline browser</td>
-	</tr>
-</table>
-<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
-<tr class="blak">
-<td>
-	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
-	<tr>
-	<td colspan="6"> 
-		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
-		<tr> 
-		<td id="pageContent"> 
-<!-- ==================== End prologue ==================== -->
-
-<h2 align="center"><em>Change report format specification</em></h2>
-
-<br />
-
-Run with <tt>--changes</tt> (<tt>-%d</tt>), HTTrack writes <tt>hts-changes.json</tt>
-in the project directory, next to <tt>hts-log.txt</tt>, describing what the crawl
-left new, changed, unchanged and gone compared to the previous mirror. The file is
-rewritten from scratch at the end of every run, and the log carries a one-line
-summary of the same counts.
-
-<br /><br />
-
-<h3>What "changed" means</h3>
-
-A resource is changed when its bytes differ, not when the server merely re-sent
-it. HTTrack compares the payload it just received against the copy the previous
-run left behind: for pages it parses, the previous payload comes from the cache
-(the file on disk carries the mirror footer and its crawl date, so its bytes
-differ on every run); for everything else, the mirrored file is the payload
-verbatim and is compared directly.
-
-<br /><br />
-
-Where no digest can be taken on either side, because the cache is disabled or
-the previous copy is gone, the report falls back to the transfer signal, and a
-server that answers 200 rather than 304 reads as changed. Keeping the cache on
-(the default) is what makes the report precise.
-
-<br /><br />
-
-<h3>With the cache off</h3>
-
-<tt>--cache=0</tt> costs the report more than the digest of a parsed page. The
-mirror's file index (<tt>hts-cache/new.lst</tt>) is what records which files a
-run produced, so without it there is no previous mirror to subtract from: nothing
-is reported <tt>gone</tt>, and whether the run is a first crawl cannot be decided
-at all, which <tt>first_crawl</tt> states as <tt>null</tt> rather than guess. What
-is on disk is still compared byte for byte, so the other three lists stay
-meaningful, except for the pages HTTrack parses: those have no cached payload to
-compare against and fall back to the transfer signal.
-
-<br /><br />
-
-<h3>Fields</h3>
-
-<ul>
-<li><tt>schema</tt>: format version, currently <tt>1</tt>. It is bumped only
-on an incompatible change; new fields may appear without one.</li>
-<li><tt>generator</tt>: the HTTrack build that wrote the file.</li>
-<li><tt>date</tt>: when the report was written, UTC, <tt>YYYY-MM-DDThh:mm:ssZ</tt>.</li>
-<li><tt>first_crawl</tt>: true when no index of a previous mirror
-(<tt>hts-cache/old.lst</tt>) was found, so there was nothing to compare against and
-everything is listed as new. Null when the run kept no index at all and the
-question cannot be answered (see above).</li>
-<li><tt>partial</tt>: true when the report ran out of memory and lists only
-part of the mirror.</li>
-<li><tt>purged</tt>: true when <tt>--purge-old</tt> was in effect, so the
-files under <tt>gone</tt> were also deleted from disk.</li>
-<li><tt>counts</tt>: the size of each of the four lists.</li>
-<li><tt>new</tt>, <tt>changed</tt>, <tt>unchanged</tt>, <tt>gone</tt>: the
-lists themselves. Every mirrored file appears in exactly one of them.</li>
-</ul>
-
-Each entry is an object:
-
-<ul>
-<li><tt>url</tt>: the absolute URL the file came from. Empty under
-<tt>gone</tt>: deletions are computed from the mirror's file index, which records
-paths, not URLs.</li>
-<li><tt>file</tt>: the path relative to the mirror root, with forward
-slashes. This is the entry's identity: a URL and a redirect that resolve to the
-same local file are one entry, not two.</li>
-<li><tt>size</tt>: the mirrored file's size in bytes, absent when the file
-is not on disk.</li>
-<li><tt>previous_size</tt>: under <tt>changed</tt> only, the size of the
-copy the previous run left.</li>
-</ul>
-
-<br />
-
-<h3>Encoding</h3>
-
-The file is JSON, UTF-8. URLs and local paths reach HTTrack as raw bytes and are
-not guaranteed to be valid UTF-8; any byte sequence that is not becomes
-U+FFFD (<tt>\ufffd</tt>), so the file always parses. Compare on <tt>file</tt>
-rather than on <tt>url</tt> when a mirror is known to carry legacy-charset URLs.
-
-<br /><br />
-
-<h3>Example</h3>
-
-<pre>
-{
-  "schema": 1,
-  "generator": "HTTrack Website Copier/3.49-14",
-  "date": "2026-07-26T15:29:03Z",
-  "first_crawl": false,
-  "partial": false,
-  "purged": true,
-  "counts": { "new": 1, "changed": 1, "unchanged": 1, "gone": 1 },
-  "new": [
-    { "url": "http://example.com/d.html", "file": "example.com/d.html", "size": 280 }
-  ],
-  "changed": [
-    { "url": "http://example.com/a.html", "file": "example.com/a.html", "size": 281, "previous_size": 273 }
-  ],
-  "unchanged": [
-    { "url": "http://example.com/b.html", "file": "example.com/b.html", "size": 277 }
-  ],
-  "gone": [
-    { "url": "", "file": "example.com/c.html" }
-  ]
-}
-</pre>
-
-<br /><br />
-
-<h3>Notes</h3>
-
-<ul>
-<li>A file listed under <tt>gone</tt> is only deleted when <tt>--purge-old</tt> is
-on. Left in place it drops out of the mirror's index, so it is reported once and
-not again.</li>
-<li>A resource whose local file name changed since the previous mirror (a new
-MIME type, say) is reported as <tt>new</tt> under its new name; the old name is
-reported as <tt>gone</tt> only if the file is still on disk. The two entries are
-not paired.</li>
-<li>A resource this run tried and failed to transfer also drops out of the
-mirror's index, but its previous copy is untouched, so it is reported
-<tt>unchanged</tt>. Under <tt>--purge-old</tt> that copy is deleted anyway, and
-the report says <tt>gone</tt> to match.</li>
-<li>A run that transfers no data at all is rolled back: HTTrack restores the
-previous cache generation and leaves the previous report in place, so a lost
-connection does not overwrite a good report with an empty one.</li>
-<li>Content diffs, and keeping the previous copy of a changed page, are out of
-scope: both change what a mirror directory contains.</li>
-</ul>
-
-<br /><br />
-
-<!-- ==================== Start epilogue ==================== -->
-		</td>
-		</tr>
-		</table>
-	</td>
-	</tr>
-	</table>
-</td>
-</tr>
-</table>
-
-<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
-	<tr>
-	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
-	</tr>
-</table>
-
-</body>
-
-</html>
-
-

html/cmddoc.html

@@ -0,0 +1,157 @@
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en">
+
+<head>
+	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
+	<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" />
+	<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" />
+	<title>HTTrack Website Copier - Offline Browser</title>
+
+	<style type="text/css">
+	<!--
+
+body {
+	margin: 0;  padding: 0;  margin-bottom: 15px;  margin-top: 8px;
+	background: #77b;
+}
+body, td {
+	font: 14px "Trebuchet MS", Verdana, Arial, Helvetica, sans-serif;
+	}
+
+#subTitle {
+	background: #000;  color: #fff;  padding: 4px;  font-weight: bold; 
+	}
+
+#siteNavigation a, #siteNavigation .current {
+	font-weight: bold;  color: #448;
+	}
+#siteNavigation a:link    { text-decoration: none; }
+#siteNavigation a:visited { text-decoration: none; }
+
+#siteNavigation .current { background-color: #ccd; }
+
+#siteNavigation a:hover   { text-decoration: none;  background-color: #fff;  color: #000; }
+#siteNavigation a:active  { text-decoration: none;  background-color: #ccc; }
+
+
+a:link    { text-decoration: underline;  color: #00f; }
+a:visited { text-decoration: underline;  color: #000; }
+a:hover   { text-decoration: underline;  color: #c00; }
+a:active  { text-decoration: underline; }
+
+#pageContent {
+	clear: both;
+	border-bottom: 6px solid #000;
+	padding: 10px;  padding-top: 20px;
+	line-height: 1.65em;
+	background-image: url(images/bg_rings.gif);
+	background-repeat: no-repeat;
+	background-position: top right;
+	}
+
+#pageContent, #siteNavigation {
+	background-color: #ccd;
+	}
+
+
+.imgLeft  { float: left;   margin-right: 10px;  margin-bottom: 10px; }
+.imgRight { float: right;  margin-left: 10px;   margin-bottom: 10px; }
+
+hr { height: 1px;  color: #000;  background-color: #000;  margin-bottom: 15px; }
+
+h1 { margin: 0;  font-weight: bold;  font-size: 2em; }
+h2 { margin: 0;  font-weight: bold;  font-size: 1.6em; }
+h3 { margin: 0;  font-weight: bold;  font-size: 1.3em; }
+h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
+
+.blak { background-color: #000; }
+.hide { display: none; }
+.tableWidth { min-width: 400px; }
+
+.tblRegular       { border-collapse: collapse; }
+.tblRegular td    { padding: 6px;  background-image: url(fade.gif);  border: 2px solid #99c; }
+.tblHeaderColor, .tblHeaderColor td { background: #99c; }
+.tblNoBorder td   { border: 0; }
+
+
+// -->
+</style>
+
+</head>
+
+<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
+	<tr>
+	<td><img src="images/header_title_4.gif" width="400" height="34" alt="HTTrack Website Copier" title="" border="0" id="title" /></td>
+	</tr>
+</table>
+<table width="76%" border="0" align="center" cellspacing="0" cellpadding="3" class="tableWidth">
+	<tr>
+	<td id="subTitle">Open Source offline browser</td>
+	</tr>
+</table>
+<table width="76%" border="0" align="center" cellspacing="0" cellpadding="0" class="tableWidth">
+<tr class="blak">
+<td>
+	<table width="100%" border="0" align="center" cellspacing="1" cellpadding="0">
+	<tr>
+	<td colspan="6"> 
+		<table width="100%" border="0" align="center" cellspacing="0" cellpadding="10">
+		<tr> 
+		<td id="pageContent"> 
+<!-- ==================== End prologue ==================== -->
+
+<h2 align="center"><em>Command-Line Documentation</em></h2>
+
+<br>
+
+The command-line version
+
+<ul>
+  <li><a href="cmdguide.html">Command-line Guide</a></li>
+  <br>A task-oriented guide: how to do the common things, and the defaults that surprise newcomers<br><br>
+  <li><a href="options.html">Command line Options</a></li>
+  <br>List of all powerful command line options<br><br>
+  <li>How to use httrack command-line version:</li>
+  <ul>
+    <li>Open a shell window</li>
+      <br>
+      <br>
+    <li>Type in <tt>httrack</tt> (or the complete path to the httrack executable)</li>
+      <br><small><tt>httrack</tt></small>
+      <br>
+      <br>
+    <li>Add the URLs, separated by a blank space</li>
+      <br><small><tt>httrack www.example.com/foo/</tt></small>
+      <br>
+      <br>
+    <li>If you need, add some options (see the <a href="options.html">option list</a>)</li>
+      <br><small><tt>httrack www.example.com/foo/ -O "/webs" -N4 -P proxy.myhost.com:3128</tt></small>
+      <br>
+      <br>
+    <li>Launch the command line, and wait until the mirror is finishing</li>
+      <br><small>You can (especially on the Unix release) press ^C to stop the mirror or put httrack in background</small>
+      <br>
+      <br>
+  </ul>
+</ul>
+
+<!-- ==================== Start epilogue ==================== -->
+		</td>
+		</tr>
+		</table>
+	</td>
+	</tr>
+	</table>
+</td>
+</tr>
+</table>
+
+<table width="76%" border="0" align="center" valign="bottom" cellspacing="0" cellpadding="0">
+	<tr>
+	<td id="footer"><small>&copy; 1998-2026 Xavier Roche & other contributors - Web Design: Leto Kauler.</small></td>
+	</tr>
+</table>
+
+</body>
+
+</html>
+

html/cmdguide.html

@@ -163,26 +163,8 @@ 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>
@@ -237,23 +219,6 @@ that a <tt>403 Forbidden</tt> is a server refusal, not a robots rule: robots
 options will not help there. That is an
 <a href="#identity">identity</a> problem.</p>
 
-<h4>Filter wildcards</h4>
-<p>Inside a filter pattern, <tt>*</tt> matches any run of characters; a few
-bracket forms match narrower sets. The full table, with size and mime rules, is on
-<a href="filters.html">the filters page</a>.</p>
-<table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Wildcard</b></td><td><b>Matches</b></td><td><b>Example</b></td></tr>
-  <tr><td><tt>*</tt></td><td>any run of characters</td><td><tt>+*.pdf</tt> &mdash; any URL ending <tt>.pdf</tt></td></tr>
-  <tr><td><tt>*[file]</tt>, <tt>*[name]</tt></td><td>one path segment (any char but <tt>/</tt> and <tt>?</tt>)</td><td><tt>example.com/*[file]/</tt> &mdash; a directory-index page</td></tr>
-  <tr><td><tt>*[path]</tt></td><td>a path, slashes allowed (any char but <tt>?</tt>)</td><td><tt>example.com/*[path].zip</tt></td></tr>
-  <tr><td><tt>*[param]</tt></td><td>an optional query string</td><td><tt>page.html*[param]</tt> matches with or without <tt>?...</tt></td></tr>
-  <tr><td><tt>*[a,b,c]</tt></td><td>any one character in the set</td><td><tt>*[a,b,c].txt</tt></td></tr>
-  <tr><td><tt>*[a-z]</tt></td><td>any one character in the range</td><td><tt>img*[0-9].gif</tt></td></tr>
-  <tr><td><tt>*[\x]</tt></td><td>the literal character x (escapes <tt>* [ ] \</tt>)</td><td><tt>*[\*]</tt> matches a real <tt>*</tt></td></tr>
-  <tr><td><tt>*[&lt;NN]</tt>, <tt>*[&gt;NN]</tt></td><td>file size in KB below / above NN</td><td><tt>-*.gif*[&lt;5]</tt> skips GIFs under 5&nbsp;KB</td></tr>
-  <tr><td><tt>*[]</tt></td><td>end anchor: nothing may follow</td><td><tt>*.html*[]</tt> rejects <tt>i.html?p=1</tt></td></tr>
-</table>
-
 <h3 id="limits">4. Limits and politeness</h3>
 
 <p>HTTrack ships cautious on purpose: it is easy to hammer a small site by
@@ -269,7 +234,7 @@ below let you go faster when you own the target, and slower when you do not.</p>
   <tr><td><tt>--max-time (-E)</tt></td><td>Stop after N seconds of wall-clock time.</td></tr>
   <tr><td><tt>--max-files (-m)</tt></td><td>Per-file size caps.</td></tr>
   <tr><td><tt>--timeout (-T), --retries (-R), --min-rate (-J), --host-control (-H)</tt></td><td>Idle timeout, retry count, minimum acceptable rate, and host-ban behavior for slow or dead hosts.</td></tr>
-  <tr><td><tt>--max-pause (-G), --pause (-%G)</tt></td><td>Pause the mirror at N bytes, or pause between files, to spread the load.</td></tr>
+  <tr><td><tt>--max-pause (-G), -%G</tt></td><td>Pause the mirror at N bytes, or pause between files, to spread the load.</td></tr>
 </table>
 
 <p><b>The security clamps.</b> To keep an accidental typo from turning into a flood,
@@ -292,8 +257,8 @@ really HTML.</p>
   <tr><td><tt>--structure (-N)</tt></td><td>The local path and name layout. Presets are numeric, and you can also give a template such as <tt>--structure "%h%p/%n%q.%t"</tt>.</td></tr>
   <tr><td><tt>--long-names (-L)</tt></td><td>Long names, 8.3 names, or ISO9660 for CD masters.</td></tr>
   <tr><td><tt>--assume (-%A)</tt></td><td>Assume a MIME type for an extension, for example <tt>--assume php=text/html</tt>. This also skips the extra HEAD probe HTTrack would otherwise send to learn the type.</td></tr>
-  <tr><td><tt>--delayed-type-check (-%N), --cached-delayed-type-check (-%D), --check-type (-u), -%t</tt></td><td>When and how the content type is checked, and whether the original extension is kept.</td></tr>
-  <tr><td><tt>--include-query-string (-%q), --strip-query (-%g)</tt></td><td>Whether the query string appears in the local filename, and whether query keys are stripped when deciding if two URLs are the same file.</td></tr>
+  <tr><td><tt>-%N, --cached-delayed-type-check (-%D), --check-type (-u), -%t</tt></td><td>When and how the content type is checked, and whether the original extension is kept.</td></tr>
+  <tr><td><tt>--include-query-string (-%q), -%g</tt></td><td>Whether the query string appears in the local filename, and whether query keys are stripped when deciding if two URLs are the same file.</td></tr>
 </table>
 
 <p>The <tt>-N</tt> presets are built from modular arithmetic on the name fields, so
@@ -318,7 +283,6 @@ ones it kept so the local copy browses offline. These options tune both halves.<
   <tr><td><tt>--preserve (-%p), --disable-passwords (-%x)</tt></td><td>Leave HTML untouched (no rewriting), and strip passwords out of saved links.</td></tr>
   <tr><td><tt>--extended-parsing (-%P), --parse-java (-j)</tt></td><td>Aggressive link discovery, and how much script content is parsed for links.</td></tr>
   <tr><td><tt>--mime-html (-%M)</tt></td><td>Save the whole mirror as a single MIME-encapsulated <tt>.mht</tt> archive (<tt>index.mht</tt>).</td></tr>
-  <tr><td><tt>--single-file (-%Z), --single-file-max-size N</tt></td><td>Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded as <tt>data:</tt> URIs. Assets over the cap (10&nbsp;MB by default) keep their link, as do audio, video, and the links from one page to another. A sibling of <tt>-%M</tt>, not a replacement: see the recipe below for which to pick.</td></tr>
   <tr><td><tt>--index (-I), --build-top-index (-%i), --search-index (-%I)</tt></td><td>Build a per-mirror index, a top index across projects, and a searchable keyword index.</td></tr>
 </table>
 
@@ -342,18 +306,10 @@ options control what HTTrack says about itself.</p>
   <tr><td><tt>--user-agent (-F)</tt></td><td>The <tt>User-Agent</tt>. Set a browser string to get past crawler blocks; <tt>--user-agent ""</tt> sends none.</td></tr>
   <tr><td><tt>--referer (-%R), --from (-%E), --language (-%l), --accept (-%a)</tt></td><td>Referer, From, Accept-Language and Accept headers.</td></tr>
   <tr><td><tt>--headers (-%X)</tt></td><td>Add raw header lines to every request.</td></tr>
-  <tr><td><tt>--footer (-%F)</tt></td><td>A footer written into saved pages (on disk, not a network header). See <b>Footer fields</b> below.</td></tr>
+  <tr><td><tt>--footer (-%F)</tt></td><td>A footer written into saved pages (on disk, not a network header).</td></tr>
   <tr><td><tt>--cookies (-b), --cookies-file (-%K)</tt></td><td>Accept cookies, and preload a Netscape <tt>cookies.txt</tt>.</td></tr>
 </table>
 
-<p><b>Footer fields.</b> A footer with no <tt>%s</tt> may reference named fields:
-<tt>{addr}</tt>, <tt>{path}</tt>, <tt>{url}</tt>, <tt>{date}</tt> (mirror time),
-<tt>{lastmodified}</tt> (the page's Last-Modified), <tt>{version}</tt>,
-<tt>{mime}</tt>, <tt>{charset}</tt>, <tt>{status}</tt> and <tt>{size}</tt>; write
-<tt>{{</tt> or <tt>}}</tt> for a literal brace. A footer that contains <tt>%s</tt>
-keeps the older positional form (host, path, date in that order). Example:
-<tt>-%F "&lt;!-- Mirrored from {url} on {date} --&gt;"</tt>.</p>
-
 <p><b>Login.</b> For HTTP Basic auth, put the credentials in the URL:
 <tt>http://user:pass@host/</tt>. An <tt>@</tt> inside the username must be written
 <tt>%40</tt>. Only Basic is supported, not Digest.</p>
@@ -373,7 +329,7 @@ across links at the same time.</p>
   <tr><td><tt>--proxy (-P)</tt></td><td>Route through a proxy. HTTP, SOCKS5 and CONNECT are supported: <tt>-P host:8080</tt>, <tt>-P socks5://host:1080</tt>, <tt>-P connect://host:443</tt>, with optional <tt>user:pass@</tt>.</td></tr>
   <tr><td><tt>--httpproxy-ftp (-%f)</tt></td><td>Send FTP requests through the HTTP proxy.</td></tr>
   <tr><td><tt>--protocol (-@i)</tt></td><td>Prefer IPv4 or IPv6.</td></tr>
-  <tr><td><tt>--http-10 (-%h), --keep-alive (-%k), --disable-compression (-%z)</tt></td><td>Force HTTP/1.0 (drops keep-alive and compression, useful for fragile CGI), toggle keep-alive, and toggle compression.</td></tr>
+  <tr><td><tt>--http-10 (-%h), --keep-alive (-%k), -%z</tt></td><td>Force HTTP/1.0 (drops keep-alive and compression, useful for fragile CGI), toggle keep-alive, and toggle compression.</td></tr>
   <tr><td><tt>--bind (-%b), --tolerant (-%B)</tt></td><td>Bind to a local address, and accept technically-bogus responses some servers send.</td></tr>
 </table>
 
@@ -397,7 +353,7 @@ away and you lose the ability to continue or update the mirror.</p>
   <tr><td><tt>--update</tt></td><td>Re-run the mirror, revalidating each page with the server (If-Modified-Since / If-None-Match) and downloading only what changed.</td></tr>
   <tr><td><tt>--purge-old=0 (-X0)</tt></td><td>Do not purge. By default an update deletes local files that are no longer part of the mirror; <tt>--purge-old=0</tt> keeps them.</td></tr>
   <tr><td><tt>--cache (-C)</tt></td><td>Cache mode. The default already does the right thing and switches to update-checking when it detects an existing mirror.</td></tr>
-  <tr><td><tt>--urlhack (-%u), --keep-www-prefix (-%j), --keep-double-slashes (-%o), --keep-query-order (-%y), --do-not-recatch (-%n), --updatehack (-%s), --store-all-in-cache (-k)</tt></td><td>URL-deduplication behavior and cache storage details.</td></tr>
+  <tr><td><tt>--urlhack (-%u), -%j, -%o, -%y, --do-not-recatch (-%n), --updatehack (-%s), --store-all-in-cache (-k)</tt></td><td>URL-deduplication behavior and cache storage details.</td></tr>
   <tr><td><tt>--debug-cache (-#C), --repair-cache (-#R), --clean</tt></td><td>Inspect the cache, repair its ZIP, and erase cache plus logs.</td></tr>
 </table>
 
@@ -448,16 +404,14 @@ host and stops the crawl; start from the final URL, or add
 rule wins.</small></p>
 
 <h4>Download the PDFs on a site</h4>
-<p><tt>httrack https://example.com/ "-*" "+https://example.com/*.html" "+https://example.com/*[path]/" "+https://example.com/*.pdf" --path mydir</tt><br>
-<small>HTTrack finds PDFs by parsing the site's HTML, so a plain
-<tt>"-*" "+example.com/*.pdf"</tt> is wrong: it prunes the pages that carry the
-links and keeps only PDFs reachable from the front page. Instead admit the HTML as
-scaffolding (<tt>*.html</tt> and <tt>*[path]/</tt> for directory-index pages at any
-depth, e.g. <tt>docs/</tt> or <tt>a/b/deep/</tt>; <tt>*[file]/</tt> would stop at one
-level), keep the PDFs, and let <tt>-*</tt> drop everything else (images,
-archives, off-site assets). PDFs on another host (a CDN or docs subdomain) are not
-included by default; allow that host too, e.g. <tt>"+docs.example.com/*.pdf"</tt>,
-or widen to <tt>"+*.pdf"</tt> for PDFs anywhere.</small></p>
+<p><tt>httrack https://example.com/ --path mydir</tt><br>
+<small>There is no PDF-only crawl. HTTrack discovers PDF links by parsing the
+site's HTML pages, so a <tt>"-*" "+example.com/*.pdf"</tt> filter blocks the very
+pages that carry the links and grabs only the PDFs linked from the front page. Let
+it crawl the site: the HTML pages come along as the scaffolding, and every reachable
+PDF is saved with them. If some PDFs live on another host (a CDN or a docs
+subdomain), allow that host too, for example
+<tt>"+docs.example.com/*.pdf"</tt>.</small></p>
 
 <h4>Keep page requisites, including off-host images</h4>
 <p><tt>httrack https://example.com/blog/ --near --path mydir</tt><br>
@@ -492,43 +446,6 @@ then:</small><br>
 lifts the built-in caps; use it only against infrastructure you are allowed to
 load.</small></p>
 
-<h4>Save a WARC archive of the crawl</h4>
-<p><tt>httrack https://example.com/ --warc --path mydir</tt><br>
-<small>Writes a standard WARC/1.1 file (<tt>httrack-&lt;timestamp&gt;.warc.gz</tt>) in
-the project folder alongside the browsable mirror, not instead of it. Set the name
-with <tt>--warc-file NAME</tt> and split a large crawl with <tt>--warc-max-size N</tt>;
-add <tt>--warc-cdx</tt> for a sorted CDXJ index, or <tt>--wacz</tt> to bundle the
-archive, index and pages into one WACZ for replay tools such as
-replayweb.page.</small></p>
-
-<h4>See what a re-crawl changed</h4>
-<p><tt>httrack https://example.com/ --update --changes --path mydir</tt><br>
-<small>Writes <tt>hts-changes.json</tt> in the project folder, listing every
-mirrored file as new, changed, unchanged or gone, plus a one-line summary in the
-log. &quot;Changed&quot; means the bytes really differ: a server that answers 200
-with the same content it served last time lands in <tt>unchanged</tt>. Deletions
-are reported whether or not <tt>--purge-old</tt> is deleting them. The format is
-documented in <a href="changes.html">the change report specification</a>.</small></p>
-
-<h4>Pages you can hand to someone as one file</h4>
-<p><tt>httrack https://example.com/ --single-file --path mydir</tt><br>
-<small>Rewrites each saved page after the crawl so its stylesheets, scripts,
-images and fonts are embedded as <tt>data:</tt> URIs. The mirror stays a normal
-browsable tree, with links between pages relative and the assets still on disk,
-but any single <tt>.html</tt> file can now be mailed or archived on its own.
-Raise or lower the 10&nbsp;MB per-asset limit with
-<tt>--single-file-max-size N</tt>; anything over it, plus audio and video, keeps
-its link. One caveat if you raise it: an inlined stylesheet becomes a
-<tt>data:</tt> URL, whose path is opaque, so an asset it referenced that stayed
-over the cap no longer resolves from inside it. Raising the cap past that asset
-embeds it too and the question goes away.<br>
-Reach for this when the file has to open for someone you cannot make assumptions
-about: it is plain HTML and needs no add-on. Reach for <tt>--mime-html</tt>
-instead when a Chromium-family browser is a given and the mirror is large: MIME
-carries text parts without the base64 tax, keeps each resource's original URL,
-and stores a shared asset once rather than re-embedding it in every page that
-uses it.</small></p>
-
 <h4>HTTrack as a fetch tool</h4>
 <p><tt>httrack --get https://host/file.bin --path tmp</tt><br>
 <small><tt>--get</tt> fetches one file with cache, index, depth, cookies and robots
@@ -537,8 +454,7 @@ all disabled.</small></p>
 <p><br>For the complete, always-current option list, see
 <a href="httrack.man.html">the manual page</a>. For the filter language, see
 <a href="filters.html">filters</a>; for the cache and updates, see
-<a href="cache.html">cache</a>; for the change report, see
-<a href="changes.html">changes</a>.</p>
+<a href="cache.html">cache</a>.</p>
 
 <!-- ==================== Start epilogue ==================== -->
 		</td>

html/contact.html

@@ -132,7 +132,7 @@ Xavier Roche (xroche at httrack dot com)
   for the main engine and Windows interface
   and maintainer for v2.0 and v3.0
 Yann Philippot (yphilippot at lemel dot fr)
-  past contributor (java binary .class parser)
+  for the java binary  dot class parser
 David Lawrie (dalawrie at lineone dot net)
 Robert Lagadec (rlagadec at yahoo dot fr)
   for checking both English & French translations

html/dev.html

@@ -129,9 +129,6 @@ The library can be used to write graphical GUIs for httrack, or to run mirrors f
 <li><a href="cache.html">Cache format</a></li><br>
 HTTrack stores original HTML data and references to downloaded files in a cache, located in the hts-cache directory.
 This page describes the HTTrack cache format.
-<li><a href="changes.html">Change report format</a></li><br>
-With --changes, HTTrack writes hts-changes.json describing what the crawl left new, changed, unchanged and gone
-compared to the previous mirror. This page describes that file.
 </ul>
 
 

html/faq.html

@@ -3,7 +3,7 @@
 <head>
 	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
 	<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" />
-	<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, linux, windows, macos, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
+	<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 vista, windows seven, windows 8, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
 	<title>HTTrack Website Copier - Offline Browser</title>
 
 	<style type="text/css">
@@ -135,7 +135,9 @@ clear language!
 
 <li><a href="#QG2">Where can I find French/other languages documentation?</a><br></li>
 
-<li><a href="#QG3">Which systems does HTTrack run on?</a><br></li>
+<li><a href="#QG3b">Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</a><br></li>
+
+<li><a href="#QG3">Is HTTrack working on Windows 95/98 ?</a><br></li>
 
 <li><a href="#QG4">What's the difference between HTTrack, WinHTTrack and WebHTTrack?</a><br></li>
 
@@ -318,10 +320,10 @@ This can easily done by using filters: go to the Option panel, select the 'Scan
 <tt>+www.example.com/gallery/trees/*<br>
 +www.example.com/photos/*</tt><br>
 <br>
-This means "accept all links beginning with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
+This means "accept all links begining with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
 - the <tt>+</tt> means "accept" and the final <tt>*</tt> means "any character will match after the previous ones".
 Remember the <tt>*.doc</tt> or <tt>*.zip</tt> encountered when you want to select all files from a certain type on your computer: 
-it is almost the same here, except the beginning "+"<br>
+it is almost the same here, except the begining "+"<br>
 <br>
 Now, we might want to exclude all links in <tt>www.example.com/gallery/trees/hugetrees/</tt>, because with the previous filter,
 we accepted too many files. Here again, you can add a filter rule to refuse these links. Modify the previous filters to:<br>
@@ -329,8 +331,8 @@ we accepted too many files. Here again, you can add a filter rule to refuse thes
 +www.example.com/photos/*<br>
 -www.example.com/gallery/trees/hugetrees/*</tt><br>
 <br>
-You have noticed the <tt>-</tt> in the beginning of the third rule: this means "refuse links matching the rule" 
-; and the rule is "any files beginning with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
+You have noticed the <tt>-</tt> in the begining of the third rule: this means "refuse links matching the rule" 
+; and the rule is "any files begining with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
 
 Voila! With these three rules, you have precisely defined what you wanted to capture.<br>
 <br>
@@ -359,12 +361,12 @@ You can freely download it, without paying any fees, copy it to your friends, an
 There are NO official/authorized resellers, because HTTrack is <b>NOT</b> a commercial product.
 But you can be charged for duplication fees, or any other services (example: software CDroms or shareware collections, or fees for maintenance), 
 but you should have been informed that the software was free software/GPL, and you <b><u>MUST</u></b> have received a copy of the GNU General Public License.
-Otherwise this is dishonest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
+Otherwise this is dishonnest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
 </em>
 
 <br><br><a NAME="QG0b">Q: <strong>Are there any risks of viruses with this software?</strong></a><br>
 A: <em>For the software itself: 
-All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free software and freeware inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
+All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free softwares and freewares inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
 For files you are downloading on the WWW using HTTrack: You may encounter websites which were corrupted by viruses, and downloading data on these websites might be dangerous if you execute downloaded executables, or if embedded pages contain infected material (as dangerous as if using a regular Browser). Always ensure that websites you are crawling are safe.
  (Note: remember that using an antivirus software is a good idea once you are connected to the Internet)</em>
 
@@ -374,8 +376,11 @@ A: <em>That's right. You can, however, install WinHTTrack on your own machine, a
 <br><br><a NAME="QG2">Q: <strong>Where can I find French/other languages documentation?</strong></a><br>
 A: <em>Windows interface is available on several languages, but not yet the documentation!</em>
 
-<br><br><a NAME="QG3">Q: <strong>Which systems does HTTrack run on?</strong></a><br>
-A: <em>HTTrack runs on current Windows, Linux and other Unix-like systems, and macOS. Very old platforms such as Windows 95/98 are no longer supported; you may try an older release (such as 3.33) on those.</em>
+<br><br><a NAME="QG3b">Q: <strong>Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</strong></a><br>
+A: <em>Yes, it does</em>
+
+<br><br><a NAME="QG3">Q: <strong>Is HTTrack working on Windows 95/98 ?</strong></a><br>
+A: <em>No, not anymore. You may try to pick an older release (such as 3.33)</em>
 
 <br><br><a NAME="QG4">Q: <strong>What's the difference between HTTrack, WinHTTrack and WebHTTrack?</strong></a><br>
 A: <em>WinHTTrack is the Windows GUI release of HTTrack (with a native graphic shell) and WebHTTrack is the Linux/Posix release of HTTrack (with an html graphic shell)</em>
@@ -389,7 +394,7 @@ A: <em>It should. The <tt>configure.ac</tt> may be modified in some cases, howev
 <br><br><a NAME="QG7">Q: <strong>I use HTTrack for professional purpose. What about restrictions/license fee?</strong></a><br>
 A: <em>HTTrack is covered by the GNU General Public License (GPL). There is no restrictions using HTTrack for professional purpose, 
 except if you develop a software which uses HTTrack components (parts of the source, or any other component).
-See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when redistributing downloaded material.
+See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when reditributing downloaded material.
 
 <br><br><a NAME="QG7b">Q: <strong>Is there any license royalties for distributing a mirror made with HTTrack?</strong></a><br>
 A: <em>On the HTTrack side, no. However, sharing, publishing or reusing copyrighted material downloaded from a site requires the authorization of the copyright holders, and possibly paying royalty fees. Always ask the authorization before creating a mirror of a site, even if the site appears to be royalty-free and/or without copyright notice.</em>
@@ -410,7 +415,7 @@ There are several reasons (and solutions) for a mirror to fail. Reading the log
 
 <ul>
  <li>Links within the site refers to external links, or links located in another (or upper) directories, not captured by default - the use of filters is generally THE solution, as this is one of the powerful option in HTTrack. <u>See the above questions/answers</u>.</li>
- <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbid access to several website parts - you can disable them, but only with great care!</li>
+ <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbide access to several website parts - you can disable them, but only with great care!</li>
  <li>HTTrack is filtered (by its default User-agent IDentity) - you can change the Browser User-Agent identity to an anonymous one (MSIE, Netscape..) - here again, use this option with care, as this measure might have been put to avoid some bandwidth abuse (see also the <a href="abuse.html">abuse faq</a>!)</li>
 </ul>
 
@@ -452,14 +457,14 @@ A: <em>Yes, HTTrack does support (since 3.20 release) ipv6 sites, using A/AAAA e
 A: <em>Check the build options (you may have selected user-defined structure with wrong parameters!)</em>
 
 <br><br><a NAME="QT5">Q: <strong>When capturing real audio/video links (.ram), I only get a shortcut!</a></strong></a></br>
-A: <em>The .ra/.rm associated file can be captured together with the shortcut, if proper filters are set. Streaming protocols such as rtsp:// are out of scope: HTTrack is an HTTP/FTP mirror and does not capture rtsp streams.</em>
+A: <em>Yes, but .ra/.rm associated file should be captured together - except if rtsp:// protocol is used (not supported by HTTrack yet), or if proper filters are needed</em>
 
 <br><br><a NAME="QT6">Q: <strong>Using user:password@address is not working!</a></strong></a></br>
 A: <em>Again, first check the <tt>hts-log.txt</tt> and <tt>hts-err.txt</tt> error log files - this can give you precious information<br>
 The site may have a different authentication scheme - form based authentication, for example.
 In this case, use the URL capture features of HTTrack, it might work.
 <br>Note: If your username and/or password contains a '<tt>@</tt>' character, you may have to replace all '<tt>@</tt>' 
-occurrences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
+occurences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
 You may have to do the same for all "special" characters like spaces (%20), quotes (%22)..</tt>
 </em>
 <br><br>
@@ -515,7 +520,7 @@ These rules, stored in a file called robots.txt, are given by the website, to sp
 - for example, /cgi-bin or large images files.
 They are followed by default by HTTrack, as it is advised. Therefore, you may miss some files that would have been downloaded without
 these rules - check in your logs if it is the case:<br>
-<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links beginning with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
+<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links begining with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
 </tt>
 <br>
 If you want to disable them, just change the corresponding option in the option list! (but only disable this option with great care, 
@@ -535,7 +540,7 @@ HTTrack must find one. Therefore, two index.html will be produced, one with the
 <br>
 It might be a good idea to consider that http://www.foobar.com/ and http://www.foobar.com/index.html are the same links, to avoid
 duplicate files, isn't it?
-NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be chosen,
+NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be choosen,
 or index.php3, mydog.jpg, or anything you may imagine. (some webmasters are really crazy)
 <br>
 <br>
@@ -590,7 +595,8 @@ A: <em>Simply use the <tt>--assume dat=application/x-zip</tt> option
 A: <em>You may need cookies! Cookies are specific data (for example, your username or password) that are sent to your browser once
 you have logged in certain sites so that you only have to log-in once. For example, after having entered your username in a website, you can
 view pages and articles, and the next time you will go to this site, you will not have to re-enter your username/password.<br>
-To supply your own cookies to an HTTrack project, put a Netscape-format <tt>cookies.txt</tt> file in your project folder, or point HTTrack at one with the <tt>--cookies-file</tt> option. You can export your browser's session cookies to that format with a browser extension.
+To "merge" your personnal cookies to an HTTrack project, just copy the cookies.txt file from your Netscape folder (or the cookies located into the Temporary Internet Files folder for IE)
+into your project folder (or even the HTTrack folder)
 </em>
 <br>
 <br>
@@ -655,7 +661,7 @@ Shell version, skip some slow files, too.</em><br>
 
 </a><a NAME="Q3b">Q: <strong>I want to update a site, but it's taking too much time! What's happening?</strong><br>
 A: <em>First, HTTrack always tries to minimize the download flow by interrogating the server about the
-file changes. But, because HTTrack has to rescan all files from the beginning to rebuild the local site structure, 
+file changes. But, because HTTrack has to rescan all files from the begining to rebuild the local site structure, 
 it can take some time. 
 Besides, some servers are not very smart and always consider that they get newer files, forcing HTTrack to reload them,
 even if no changes have been made!
@@ -734,7 +740,7 @@ retransferred.</em><br>
 </a><a NAME="Q7">Q: <strong>I just want to retrieve all ZIP files or other files in a web
 site/in a page. How do I do it?</strong><br>
 A: <em>You can use different methods. You can use the 'get files near a link' option if
-files are in a foreign domain. You can use, too, a filter address: adding <tt>+*.zip</tt>
+files are in a foreign domain. You can use, too, a filter adress: adding <tt>+*.zip</tt>
 in the URL list (or in the filter list) will accept all ZIP files, even if these files are
 outside the address. <br>
 Example : <tt>httrack www.example.com/someaddress.html +*.zip</tt> will allow

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 *save the server's error pages (404..) (o0 discard them) (--generate-errors)
+  o *generate output html file in case of error (404..) (o0 don't generate) (--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 *save the server's error pages (404..) (o0 discard them)
+  o *generate output html file in case of error (404..) (o0 don't generate)
   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 *save the server's error pages (404..) (o0 discard them) </i></b></pre>
+<pre><b><i>  o *generate output html file in case of error (404..) (o0 don't generate) </i></b></pre>
 
-<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.
+<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.
 
 <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 *save the server's error pages (404..) (o0 discard them)
+  o *generate output html file in case of error (404..) (o0 don't generate)
   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 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
+<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
 unnecessary files in operations where a working web site is not the
 desired result. 
 

html/filters.html

@@ -111,7 +111,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     starts links, the default mode is to mirror these links - i.e. if one of your start page is
     www.example.com/test/index.html, all links starting with www.example.com/test/ will be
     accepted. But links directly in www.example.com/.. will not be accepted, however, because
-    they are in a higher structure. This prevent HTTrack from mirroring the whole site. (All
+    they are in a higher strcuture. This prevent HTTrack from mirroring the whole site. (All
     files in structure levels equal or lower than the primary links will be retrieved.)<br>
     </i>
     <br>
@@ -127,15 +127,13 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     an authorization filter, like <b><tt>+*.gif</tt></b>. The pattern is a plus (this one: <b><tt>+</tt></b>),
     followed by a pattern composed of letters and wildcards (this one: <b><tt>*</tt></b>). 
     <br><br>
-    To forbid a family of links, define
+    To forbide a family of links, define
     an authorization filter, like <b><tt>-*.gif</tt></b>. The pattern is a dash (this one: <b><tt>-</tt></b>),
     followed by a the same kind of pattern as for the authorization filter.
     <br><br>
     Example: +*.gif will accept all files finished by .gif<br>
     Example: -*.gif will refuse all files finished by .gif<br>
     <br>
-    To see which rule accepted or blocked a given URL, run HTTrack with the <b><tt>--why</tt></b> (<b><tt>-%Y</tt></b>) option, described in <a href="httrack.man.html#OPTIONS">the manual page</a>.<br>
-    <br>
     
 <p>    
     <h4>Scan rules based on size (e.g. accept or refuse files bigger/smaller than a certain size)</h4>
@@ -145,7 +143,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
     size to ensure that you won't reach a defined limit.
     
     Example: You may want to accept all files on the domain www.example.com, using '+www.example.com/*', 
-    including gif files inside this domain and outside (external images), but not take to large images, 
+    including gif files inside this domain and outside (eternal images), but not take to large images, 
     or too small ones (thumbnails)<br>
     Excluding gif images smaller than 5KB and images larger than 100KB is therefore a good option;
     +www.example.com +*.gif -*.gif*[<5] -*.gif*[>100] 

html/index.html

@@ -109,12 +109,12 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
   <li>How to Use</li>
   <ul>
     <li><a href="shelldoc.html">WinHTTrack/WebHTTrack (GUI version for Windows or Linux/Unix)</a></li>
-    <br>HTTrack GUI documentation, with step-by-step example, for the Windows release (WinHTTrack) and the Linux/Unix release (WebHTTrack)<br>
+    <br>HTTrack GUI documentation, with step-by-step example, for the Windows release (WinHTTrack) and the Linux/Unix relese (WebHTTrack)<br>
     <br>
     <li><a href="android.html">HTTrack on Android</a></li>
     <br>Step-by-step guide for the Android app<br>
     <br>
-    <li><a href="httrack.man.html">Command-line version</a></li>
+    <li><a href="cmddoc.html">Command-line version</a></li>
     <br>How to run HTTrack from the command line, and where to find every option<br>
     <br>
     <li><a href="cmdguide.html">Command-line Guide</a></li>
@@ -123,7 +123,7 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
     <li><a href="fcguide.html">HTTrack Users Guide By Fred Cohen</a></li>
     <br>A tutorial that describes all command-line options, for Linux and Windows users<br>
     <br>
-    <li><a href="dev.html">Developer/Programming</a></li>
+    <li><a href="dev.html">Developper/Programming</a></li>
     <br>How to use HTTrack in batch files, and how to use the library<br>
   </ul>
   <br>

html/options.html

@@ -101,10 +101,6 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
 
 <h2 align="center"><em>Options</em></h2>
 
-<p><strong>Note:</strong> this is a legacy option list and may be out of date.
-For the authoritative, always-current reference see <a href="httrack.man.html">the httrack manual page</a>,
-and for a task-oriented walkthrough see the <a href="cmdguide.html">Command-line Guide</a>.</p>
-
 <ul>
   <li>Filters: <a href="filters.html">how to use them</a></li>
   <br><small>Here you can find informations on filters: how to accept all gif files in a mirror, for example</small>

html/server/finished.html

@@ -97,8 +97,9 @@ ${do:end-if}
 </pre>
 
 ${LANG_G8} : 
-${/* an http: page cannot navigate to file:, so the mirror is reached through the server */}
-<a href="/website/index.html" target="_new">
+${do:output-mode:html-urlescaped}
+<a href="file://${path}/${projname}/" target="_new">
+${do:output-mode:}
 ${path}/${projname}
 </a></li>
 <ul>

html/server/option10.html

@@ -98,9 +98,6 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="ftpprox" value="">
-
 ${LANG_PROXYTYPE}
 <select name="proxytype"
 			title='${html:LANG_PROXYTYPETIP}' onMouseOver="info('${html:LANG_PROXYTYPETIP}'); return true" onMouseOut="info('&nbsp;'); return true"

html/server/option2.html

@@ -98,14 +98,6 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="errpage" value="">
-<input type="hidden" name="external" value="">
-<input type="hidden" name="hidepwd" value="">
-<input type="hidden" name="hidequery" value="">
-<input type="hidden" name="nopurge" value="">
-<input type="hidden" name="singlefile" value="">
-
 ${LANG_I33}
 <br>
 <select name="build"
@@ -144,13 +136,6 @@ ${listid:build:LISTDEF_3}
 <tr><td><input type="checkbox" name="nopurge"   ${checked:nopurge}  
 			title='${html:LANG_I1a}' onMouseOver="info('${html:LANG_I1a}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I57}</td></tr>
-<tr><td><input type="checkbox" name="singlefile" ${checked:singlefile}
-			title='${html:LANG_SINGLEFILETIP}' onMouseOver="info('${html:LANG_SINGLEFILETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
-> ${LANG_SINGLEFILE}</td></tr>
-<tr><td>${LANG_SINGLEFILEMAX}
-<input name="singlefilemax" value="${singlefilemax}" size="12"
-			title='${html:LANG_SINGLEFILEMAXTIP}' onMouseOver="info('${html:LANG_SINGLEFILEMAXTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
-></td></tr>
 </table>
 
 <tr><td>

html/server/option2b.html

@@ -103,7 +103,7 @@ ${LANG_Q3}
 <tr><td>
 	<table width="100%">
 	<tr><td align="left">
-	<input type="submit" value="${LANG_OK}"
+	<input type="submit" value="${LANG_OK]" 
 ${do:output-mode:html-urlescaped}
 		onClick="if (confirm(str_replace(str_replace('${LANG_DIAL7}', '%20', ' '), '%0a', ' '))) { form.closeme.value=1; form.submit(); } return false;"
 ${do:output-mode:}

html/server/option3.html

@@ -98,9 +98,6 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="windebug" value="">
-
 ${LANG_I40c}
 <br>
 

html/server/option4.html

@@ -98,11 +98,6 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="ka" value="">
-<input type="hidden" name="remt" value="">
-<input type="hidden" name="rems" value="">
-
 <table border="0" width="100%" cellspacing="0">
 
 <tr><td>

html/server/option8.html

@@ -98,18 +98,6 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="cookies" value="">
-<input type="hidden" name="parsejava" value="">
-<input type="hidden" name="updhack" value="">
-<input type="hidden" name="urlhack" value="">
-<input type="hidden" name="keepwww" value="">
-<input type="hidden" name="keepslashes" value="">
-<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"
 > ${LANG_I58}
@@ -144,17 +132,6 @@ ${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/option9.html

@@ -98,35 +98,11 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-<!-- clear if not checked -->
-<input type="hidden" name="warc" value="">
-<input type="hidden" name="changes" value="">
-<input type="hidden" name="norecatch" value="">
-<input type="hidden" name="logf" value="">
-<input type="hidden" name="index" value="">
-<input type="hidden" name="index2" value="">
-
 <input type="checkbox" name="cache2" ${checked:cache2}
 			title='${html:LANG_I1e}' onMouseOver="info('${html:LANG_I1e}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I61}
 <br><br>
 
-<input type="checkbox" name="warc" ${checked:warc}
-			title='${html:LANG_WARCTIP}' onMouseOver="info('${html:LANG_WARCTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
-> ${LANG_WARC}
-<br><br>
-
-${LANG_WARCFILE}
-<input name="warcfile" value="${warcfile}" size="40"
-			title='${html:LANG_WARCFILETIP}' onMouseOver="info('${html:LANG_WARCFILETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
->
-<br><br>
-
-<input type="checkbox" name="changes" ${checked:changes}
-			title='${html:LANG_CHANGESTIP}' onMouseOver="info('${html:LANG_CHANGESTIP}'); return true" onMouseOut="info('&nbsp;'); return true"
-> ${LANG_CHANGES}
-<br><br>
-
 <input type="checkbox" name="norecatch" ${checked:norecatch}
 			title='${html:LANG_I5b}' onMouseOver="info('${html:LANG_I5b}'); return true" onMouseOut="info('&nbsp;'); return true"
 > ${LANG_I34b}

html/server/step2.html

@@ -141,13 +141,6 @@ ${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}
-${do:copy:SingleFile:singlefile}
-${do:copy:SingleFileMaxSize:singlefilemax}
 ${do:copy:LogType:logtype}
 ${do:copy:UseHTTPProxyForFTP:ftpprox}
 ${do:copy:ProxyType:proxytype}

html/server/step3.html

@@ -95,7 +95,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>${LANG_G44}</em></h2>
+	<h2 align="center"><em>Select URLs</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}

html/server/step4.html

@@ -77,7 +77,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>${LANG_J9}</em></h2>
+	<h2 align="center"><em>Start</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}
@@ -114,16 +114,16 @@ ${do:end-if}
 
 ${/* Real commands and ini file generated below */}
 
-<!-- engine commandline; ztest so a cleared default-on option still emits its disabling flag -->
+<!-- engine commandline -->
 ${do:output-mode:html}
 <textarea name="command" cols="50" rows="4" style="visibility:hidden">
 httrack \
 	--quiet \
 	--build-top-index \
 	${test:todo:--mirror:--mirror:--mirror-wizard:--get:--mirrorlinks:--testlinks:--continue:--update}
-	${unquoted:urls}
-	${test:filelist:-%L "}${arg:filelist}${test:filelist:"}
-	--path "${arg:path}/${arg:projname}" 
+	${urls}
+	${test:filelist:-%L "}${filelist}${test:filelist:"}
+	--path "${html:path}/${html:projname}" 
 \
 	${test:parseall:--near}
 	${test:link:--test}
@@ -131,7 +131,7 @@ httrack \
 	${test:htmlfirst::--priority=7}
 \
 ${do:if-not-empty:BuildString}
-	--structure "${arg:BuildString}"
+	--structure "${BuildString}"
 ${do:end-if}
 	${test:build:-N0:-N0:-N1:-N2:-N3:-N4:-N5:-N100:-N101:-N102:-N103:-N104:-N105:-N99:-N199:}
 \
@@ -150,57 +150,49 @@ ${do:end-if}
 	${test:travel3::--keep-links=0:--keep-links:--keep-links=3:--keep-links=4}
 	${test:windebug:--debug-headers}
 \
-	${test:connexion:--sockets=}${unquoted:connexion}
+	${test:connexion:--sockets=}${connexion}
 	${test:ka:--keep-alive}
-	${test:timeout:--timeout=}${unquoted:timeout}
+	${test:timeout:--timeout=}${timeout}
 	${test:remt:--host-control=1}
-	${test:retry:--retries=}${unquoted:retry}
-	${test:rate:--min-rate=}${unquoted:rate}
+	${test:retry:--retries=}${retry}
+	${test:rate:--min-rate=}${rate}
 	${test:rems:--host-control=2}
 \
-	${test:depth:--depth=}${unquoted:depth}
-	${test:depth2:--ext-depth=}${unquoted:depth2}
-${/* -m<n> resets the html limit, so the bare form must precede the -m,<n> one */}
-	${test:othermax:--max-files=}${unquoted:othermax}
-	${test:maxhtml:--max-files=,}${unquoted:maxhtml}
-	${test:sizemax:--max-size=}${unquoted:sizemax}
-	${test:pausebytes:--max-pause=}${unquoted:pausebytes}
-	${test:maxtime:--max-time=}${unquoted:maxtime}
-	${test:maxrate:--max-rate=}${unquoted:maxrate}
-	${test:maxconn:--connection-per-second=}${unquoted:maxconn}
-	${test:maxlinks:--advanced-maxlinks=}${unquoted:maxlinks}
+	${test:depth:--depth=}${depth}
+	${test:depth2:--ext-depth=}${depth2}
+	${test:maxhtml:--max-files=,}${maxhtml}
+	${test:othermax:--max-files=}${othermax}
+	${test:sizemax:--max-files=}${sizemax}
+	${test:pausebytes:--max-pause=}${pausebytes}
+	${test:maxtime:--max-time=}${maxtime}
+	${test:maxrate:--max-rate=}${maxrate}
+	${test:maxconn:--connection-per-second=}${maxconn}
+	${test:maxlinks:--advanced-maxlinks=}${maxlinks}
 \
-	--user-agent "${arg:user}"
-	--footer "${arg:footer}"
+	--user-agent "${html:user}"
+	--footer "${html:footer}"
 \
-	${unquoted:url2}
+	${url2}
 \
-	${ztest:cookies:--cookies=0:}
-	${ztest:parsejava:--parse-java=0:}
+	${test:cookies:--cookies=0:}
+	${test:parsejava:--parse-java=0:}
 	${test:updhack:--updatehack}
 	${test:urlhack:--urlhack=0:--urlhack}
 	${test:keepwww:--keep-www-prefix}
 	${test:keepslashes:--keep-double-slashes}
 	${test:keepqueryorder:--keep-query-order}
-	${test:cookiesfile:--cookies-file "}${arg:cookiesfile}${test:cookiesfile:"}
-	${test:pausefiles:--pause "}${arg:pausefiles}${test:pausefiles:"}
-	${test:stripquery:--strip-query "}${arg:stripquery}${test:stripquery:"}
+	${test:cookiesfile:--cookies-file "}${html:cookiesfile}${test:cookiesfile:"}
+	${test:pausefiles:--pause "}${pausefiles}${test:pausefiles:"}
+	${test:stripquery:--strip-query "}${html:stripquery}${test:stripquery:"}
 	${test:toler:--tolerant}
 	${test:http10:--http-10}
 	${test:cache2:--store-all-in-cache}
-	${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}
-	${test:singlefile:--single-file}
-	${test:singlefilemax:--single-file-max-size=}${unquoted:singlefilemax}
 	${test:norecatch:--do-not-recatch}
 	${test:logf:--single-log}
 	${test:logtype:::--extra-log:--debug-log}
 	${test:index:--index=0:}
 	${test:index2:--search-index=0:--search-index}
-	${test:prox:--proxy "}${do:if-not-empty:prox}${test:proxytype::socks5:connect}${test:proxytype:\3A//}${do:end-if}${do:output-mode:html}${arg:prox}${test:prox:\3A}${arg:portprox}${test:prox:"}
+	${test:prox:--proxy "}${do:if-not-empty:prox}${test:proxytype::socks5:connect}${test:proxytype:\3A//}${do:end-if}${do:output-mode:html}${prox}${test:prox:\3A}${portprox}${test:prox:"}
 	${test:ftpprox:--httpproxy-ftp=0:--httpproxy-ftp}
 </textarea>
 
@@ -219,7 +211,7 @@ ParseAll=${ztest:parseall:0:1}
 HTMLFirst=${ztest:htmlfirst:0:1}
 Cache=${ztest:cache:0:1}
 NoRecatch=${ztest:norecatch:0:1}
-Dos=${dos}
+Dos=${dos
 Index=${ztest:index:0:1}
 WordIndex=${ztest:index2:0:1}
 Log=${ztest:logf:0:1:2}
@@ -245,13 +237,6 @@ KeepSlashes=${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}
-SingleFile=${ztest:singlefile:0:1}
-SingleFileMaxSize=${singlefilemax}
 LogType=${logtype}
 UseHTTPProxyForFTP=${ztest:ftpprox:0:1}
 ProxyType=${proxytype}

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 save the error pages sent by the server (if a 404 error occurred, for example)
+  <br><small>Do not generate error pages (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

@@ -713,7 +713,7 @@ Disconnect when finished
 LANG_J17
 Disconnect modem on completion
 LANG_K1
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
 LANG_K2
 About WinHTTrack Website Copier
 LANG_K3
@@ -1034,31 +1034,3 @@ LANG_STRIPQUERY
 Strip query keys:
 LANG_STRIPQUERYTIP
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
-LANG_WARC
-Write a WARC archive of the crawl
-LANG_WARCTIP
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-LANG_WARCFILE
-WARC archive name:
-LANG_WARCFILETIP
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-LANG_CHANGES
-Report what changed since the previous mirror
-LANG_CHANGESTIP
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-LANG_SINGLEFILE
-Inline assets as data: URIs (self-contained pages)
-LANG_SINGLEFILETIP
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Ïðåêðàòè âðúçêàòà ñëåä êðàÿ íà îïåðàöèÿòà
 Disconnect modem on completion
 Ñëåä êðàÿ íà îïåðàöèÿòà ðàçêà÷è ìîäåìà
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Ìîëÿ óâåäîìåòå íè çà âñÿêà ãðåøêà èëè ïðîáëåì)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÏàÿê: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche è äðóãè ñúòðóäíèöè\r\nÌÍÎÃÎ ÁËÀÃÎÄÀÐÍÎÑÒÈ çà Áúëãàðñêèÿò ïðåâîä íà:\r\nÈëèÿ Ëèíäîâ (ilia@infomat-bg.com)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Ìîëÿ óâåäîìåòå íè çà âñÿêà ãðåøêà èëè ïðîáëåì)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÏàÿê: Xavier Roche\r\nJava Ðàçáîðíè Êëàñîâå: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche è äðóãè ñúòðóäíèöè\r\nÌÍÎÃÎ ÁËÀÃÎÄÀÐÍÎÑÒÈ çà Áúëãàðñêèÿò ïðåâîä íà:\r\nÈëèÿ Ëèíäîâ (ilia@infomat-bg.com)
 About WinHTTrack Website Copier
 Çà WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Ïðåìàõâàíå íà êëþ÷îâå îò çàÿâêàòà:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷îâå îò çàÿâêàòà, ðàçäåëåíè ñúñ çàïåòàÿ, êîèòî äà ñå ïðåìàõíàò îò èìåòî íà çàïèñàíèÿ ôàéë (íàïðèìåð sid,utm_source).
-Write a WARC archive of the crawl
-Çàïèñâàíå íà WARC àðõèâ íà îáõîæäàíåòî
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Çàïèñâàíå íà âñåêè èçòåãëåí îòãîâîð è â WARC/1.1 àðõèâ ïî ISO-28500, äî îãëåäàëîòî.
-WARC archive name:
-Èìå íà WARC àðõèâà:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Íåçàäúëæèòåëíî áàçîâî èìå çà WARC àðõèâà; îñòàâåòå ïðàçíî çà àâòîìàòè÷íî èìåíóâàíå â èçõîäíàòà äèðåêòîðèÿ.
-Report what changed since the previous mirror
-Îò÷åò çà ïðîìåíèòå ñïðÿìî ïðåäèøíîòî îãëåäàëî
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Çàïèñâàíå è íà hts-changes.json ñúñ ñïèñúê íà íîâèòå, ïðîìåíåíèòå, íåïðîìåíåíèòå è èç÷åçíàëèòå ôàéëîâå ñïðÿìî ïðåäèøíîòî îãëåäàëî.
-Inline assets as data: URIs (self-contained pages)
-Âãðàæäàíå íà ðåñóðñèòå êàòî data: URI (ñàìîñòîÿòåëíè ñòðàíèöè)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Ñëåä çàâúðøâàíå íà îãëåäàëîòî âñÿêà çàïàçåíà ñòðàíèöà ñå ïðåçàïèñâà ñ âãðàäåíè ñòèëîâå, ñêðèïòîâå, èçîáðàæåíèÿ è øðèôòîâå, òàêà ÷å ñòðàíèöàòà äà ìîæå äà ñå îòâîðè è ñàìîñòîÿòåëíî.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Desconectar al terminar la operación
 Disconnect modem on completion
 Desconectar el modem al terminar
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(notifíquenos fallos o problemas)\r\n\r\nDesarrollo:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Spanish translations to:\r\nJuan Pablo Barrio Lera (Universidad de León)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(notifíquenos fallos o problemas)\r\n\r\nDesarrollo:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Spanish translations to:\r\nJuan Pablo Barrio Lera (Universidad de León)
 About WinHTTrack Website Copier
 Acerca de...
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Eliminar claves de query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Claves de query string, separadas por comas, que se eliminarán del nombre de los archivos guardados (p. ej. sid,utm_source).
-Write a WARC archive of the crawl
-Escribir un archivo WARC del rastreo
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Guardar también cada respuesta descargada en un archivo WARC/1.1 ISO-28500, junto a la réplica.
-WARC archive name:
-Nombre del archivo WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nombre base opcional para el archivo WARC; déjelo en blanco para nombrarlo automáticamente en el directorio de salida.
-Report what changed since the previous mirror
-Informar de los cambios desde la copia anterior
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Escribir también hts-changes.json con la lista de lo que esta captura deja como nuevo, modificado, sin cambios o desaparecido respecto a la copia anterior.
-Inline assets as data: URIs (self-contained pages)
-Incrustar los recursos como URI data: (páginas autónomas)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Una vez terminada la copia, reescribir cada página guardada con sus hojas de estilo, scripts, imágenes y fuentes incrustadas, de modo que una página también pueda abrirse por sí sola.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Odpojit po dokonèení
 Disconnect modem on completion
 Odpojit modem po dokonèení
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Prosíme o podání hlášení o jakýchkoliv chybách)\r\n\r\nVývoj:\r\nRozhraní (Windows): Xavier Roche\r\nPavouk: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche a ostatní, kdo pøispìli\r\nÈeský pøeklad:\r\nAntonín Matìjèík (matejcik@volny.cz)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Prosíme o podání hlášení o jakýchkoliv chybách)\r\n\r\nVývoj:\r\nRozhraní (Windows): Xavier Roche\r\nPavouk: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche a ostatní, kdo pøispìli\r\nÈeský pøeklad:\r\nAntonín Matìjèík (matejcik@volny.cz)
 About WinHTTrack Website Copier
 O programu WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Odebrat klíèe dotazu:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Klíèe dotazu oddìlené èárkami, které se vynechají z pojmenování ukládaných souborù (napø. sid,utm_source).
-Write a WARC archive of the crawl
-Zapsat archiv WARC z procházení
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Uložit také každou staženou odpovìï do archivu WARC/1.1 podle ISO-28500 vedle zrcadla.
-WARC archive name:
-Název archivu WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Volitelný základní název archivu WARC; ponechte prázdné pro automatické pojmenování ve výstupním adresáøi.
-Report what changed since the previous mirror
-Hlásit, co se od pøedchozího zrcadlení zmìnilo
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zapsat také hts-changes.json se seznamem toho, co je oproti pøedchozímu zrcadlení nové, zmìnìné, nezmìnìné nebo chybìjící.
-Inline assets as data: URIs (self-contained pages)
-Vložit zdroje jako URI data: (samostatné stránky)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Po dokonèení zrcadlení pøepsat každou uloženou stránku s vloženými styly, skripty, obrázky a písmy, aby ji bylo možné otevøít i samostatnì.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 完成時切斷連線
 Disconnect modem on completion
 完成時切斷數據機
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(有任何程序錯誤或問題請聯絡我們)\r\n\r\n開發:\r\n界面設計 (Windows): Xavier Roche\r\n分析引擎: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\n感謝:\r\nDavid Hing Cheong Hung (DAVEHUNG@mtr.com.hk) 提供翻譯
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(有任何程序錯誤或問題請聯絡我們)\r\n\r\n開發:\r\n界面設計 (Windows): Xavier Roche\r\n分析引擎: Xavier Roche\r\nJava分析引擎: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\n感謝:\r\nDavid Hing Cheong Hung (DAVEHUNG@mtr.com.hk) 提供翻譯
 About WinHTTrack Website Copier
 關於WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 移除查詢鍵:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 以逗號分隔的查詢鍵，將其從儲存檔案的命名中移除 (例如 sid,utm_source)。
-Write a WARC archive of the crawl
-寫入此次抓取的 WARC 封存檔
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-同時將每個已擷取的回應儲存為 ISO-28500 WARC/1.1 封存檔，置於鏡像網站旁。
-WARC archive name:
-WARC 封存檔名稱：
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC 封存檔的選用基本名稱；留空則於輸出目錄中自動命名。
-Report what changed since the previous mirror
-回報自上次鏡射以來的變更
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-同時寫入 hts-changes.json，列出這次擷取相對於上次鏡射的新增、變更、未變更與消失的項目。
-Inline assets as data: URIs (self-contained pages)
-將資源內嵌為 data: URI（獨立網頁）
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-鏡射完成後，重寫每個已儲存的網頁，將樣式表、指令碼、圖片與字型內嵌其中，讓網頁也能單獨開啟。
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 完成时断掉连接
 Disconnect modem on completion
 完成时断掉调制解调器
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(有任何程序错误或问题请联系我们)\r\n\r\n开发:\r\n界面设计 (Windows): Xavier Roche\r\n解析引擎: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\n感谢:\r\nRobert Lagadec (rlagadec@yahoo.fr) 提供翻译技巧
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(有任何程序错误或问题请联系我们)\r\n\r\n开发:\r\n界面设计 (Windows): Xavier Roche\r\n解析引擎: Xavier Roche\r\nJava解析引擎: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\n感谢:\r\nRobert Lagadec (rlagadec@yahoo.fr) 提供翻译技巧
 About WinHTTrack Website Copier
 关于WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 剥离查询键:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 用逗号分隔的查询键，将其从保存文件的命名中删除 (例如 sid,utm_source)。
-Write a WARC archive of the crawl
-写入本次抓取的 WARC 归档
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-同时将每个已获取的响应保存为 ISO-28500 WARC/1.1 归档，置于镜像站点旁边。
-WARC archive name:
-WARC 归档名称：
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC 归档的可选基本名称；留空则在输出目录中自动命名。
-Report what changed since the previous mirror
-报告自上次镜像以来的变更
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-同时写入 hts-changes.json，列出本次抓取相对于上次镜像的新增、更改、未更改和消失的项目。
-Inline assets as data: URIs (self-contained pages)
-将资源内嵌为 data: URI（独立网页）
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-镜像完成后，重写每个已保存的网页，将样式表、脚本、图片和字体内嵌其中，使网页也能单独打开。
-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

@@ -636,8 +636,8 @@ Disconnect when finished
 Prekinuti vezu kada bude gotovo
 Disconnect modem on completion
 Po dovršetku odvojiti modemsku vezu
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Molimo da nas obavijestite o svim pogreškama i poteškoæama)\r\n\r\nRazvoj:\r\nSuèelje (Windows): Xavier Roche\r\nPauk: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche i drugi suradnici\r\nPUNO HVALA za prijevodne preporuke upuæujemo:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Molimo da nas obavijestite o svim pogreškama i poteškoæama)\r\n\r\nRazvoj:\r\nSuèelje (Windows): Xavier Roche\r\nPauk: Xavier Roche\r\nRazrediRašèlanjivaèaJave: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche i drugi suradnici\r\nPUNO HVALA za prijevodne preporuke upuæujemo:\r\nRobert Lagadec (rlagadec@yahoo.fr)
 About WinHTTrack Website Copier
 O programu WinHTTrack Website Copier
 Please visit our Web page
@@ -958,31 +958,3 @@ Strip query keys:
 Ukloniti kljuèeve upita:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Zarezom odvojeni kljuèevi upita koji se izostavljaju iz naziva spremljenih datoteka (npr. sid,utm_source).
-Write a WARC archive of the crawl
-Zapi¹i WARC arhivu obilaska
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Spremi i svaki preuzeti odgovor u ISO-28500 WARC/1.1 arhivu, uz zrcalo.
-WARC archive name:
-Naziv WARC arhive:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Neobavezni osnovni naziv WARC arhive; ostavite prazno za automatsko imenovanje u izlaznom direktoriju.
-Report what changed since the previous mirror
-Prijavi ¹to se promijenilo od prethodnog zrcaljenja
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zapi¹i i hts-changes.json s popisom onoga ¹to je u odnosu na prethodno zrcaljenje novo, promijenjeno, nepromijenjeno ili nestalo.
-Inline assets as data: URIs (self-contained pages)
-Ugradi resurse kao data: URI-je (samostalne stranice)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Nakon dovr¹etka zrcaljenja ponovno zapi¹i svaku spremljenu stranicu s ugraðenim stilskim listovima, skriptama, slikama i fontovima, tako da se stranica mo¾e otvoriti i zasebno.
-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

@@ -652,8 +652,8 @@ Disconnect when finished
 Afbryd forbindelsen når overførslen er færdig
 Disconnect modem on completion
 Afbryd modem når overførslen er færdig
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(finder du fejl eller opstår der problemer så kontakt os venligst)\r\n\r\nUdvikling:\r\nBrugerflade (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche og andre bidragydere\r\nMange tak for dansk oversættelse til:\r\nJesper Bramm (bramm@get2net.dk)\r\nscootergrisen
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(finder du fejl eller opstår der problemer så kontakt os venligst)\r\n\r\nUdvikling:\r\nBrugerflade (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche og andre bidragydere\r\nMange tak for dansk oversættelse til:\r\nJesper Bramm (bramm@get2net.dk)\r\nscootergrisen
 About WinHTTrack Website Copier
 Om WinHTTrack Website Copier
 Please visit our Web page
@@ -1004,31 +1004,3 @@ Strip query keys:
 Fjern forespørgselsnøgler:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerede forespørgselsnøgler, der udelades i navngivningen af gemte filer (f.eks. sid,utm_source).
-Write a WARC archive of the crawl
-Skriv et WARC-arkiv af gennemsøgningen
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Gem også hvert hentet svar i et ISO-28500 WARC/1.1-arkiv ved siden af spejlet.
-WARC archive name:
-Navn på WARC-arkiv:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Valgfrit basisnavn til WARC-arkivet; lad feltet stå tomt for automatisk navngivning i outputmappen.
-Report what changed since the previous mirror
-Rapportér hvad der er ændret siden den forrige spejling
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Skriv også hts-changes.json med en liste over, hvad denne gennemgang efterlader som nyt, ændret, uændret eller forsvundet i forhold til den forrige spejling.
-Inline assets as data: URIs (self-contained pages)
-Indlejr ressourcer som data:-URI'er (selvstændige sider)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Når spejlingen er færdig, omskrives hver gemt side med dens typografiark, scripts, billeder og skrifttyper indlejret, så en side også kan åbnes alene.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Nach der Aktion Verbindung trennen
 Disconnect modem on completion
 Modemverbindung trennen, wenn fertig
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Bitte benachrichtigen Sie uns über Fehler und Probleme)\r\n\r\nEntwicklung:\r\nOberfläche (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for German translations to:\r\nRainer Klueting (rainer@klueting.de)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Bitte benachrichtigen Sie uns über Fehler und Probleme)\r\n\r\nEntwicklung:\r\nOberfläche (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for German translations to:\r\nRainer Klueting (rainer@klueting.de)
 About WinHTTrack Website Copier
 Über WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Query-Schlüssel entfernen:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommagetrennte Query-Schlüssel, die bei der Benennung gespeicherter Dateien entfallen (z. B. sid,utm_source).
-Write a WARC archive of the crawl
-WARC-Archiv des Crawls schreiben
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Jede heruntergeladene Antwort zusätzlich in einem ISO-28500-WARC/1.1-Archiv neben dem Spiegel speichern.
-WARC archive name:
-Name des WARC-Archivs:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Optionaler Basisname für das WARC-Archiv; leer lassen, um es automatisch im Ausgabeverzeichnis zu benennen.
-Report what changed since the previous mirror
-Melden, was sich seit der vorherigen Spiegelung geändert hat
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zusätzlich hts-changes.json schreiben, das auflistet, was dieser Durchlauf gegenüber der vorherigen Spiegelung als neu, geändert, unverändert oder verschwunden hinterlässt.
-Inline assets as data: URIs (self-contained pages)
-Ressourcen als data:-URIs einbetten (eigenständige Seiten)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Nach Abschluss der Spiegelung jede gespeicherte Seite mit eingebetteten Stylesheets, Skripten, Bildern und Schriftarten neu schreiben, sodass eine Seite auch für sich allein geöffnet werden kann.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Lahuta ühendus, kui on lõpetatud
 Disconnect modem on completion
 Lahuta modem lõpetamisel
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Palun teata meile igast veast või probleemist)\r\n\r\nArendajad:\r\nKasutajaliides (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nEestikeelne tõlge: Tõnu Virma
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Palun teata meile igast veast või probleemist)\r\n\r\nArendajad:\r\nKasutajaliides (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nEestikeelne tõlge: Tõnu Virma
 About WinHTTrack Website Copier
 Info WinHTTrack Website Copier'i kohta
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Eemalda päringuvõtmed:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Komadega eraldatud päringuvõtmed, mis jäetakse salvestatud faili nimest välja (nt sid,utm_source).
-Write a WARC archive of the crawl
-Kirjuta läbimise WARC-arhiiv
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Salvesta iga alla laaditud vastus ka ISO-28500 WARC/1.1 arhiivi peegli kõrvale.
-WARC archive name:
-WARC-arhiivi nimi:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC-arhiivi valikuline põhinimi; jäta tühjaks, et see väljundkataloogis automaatselt nimetada.
-Report what changed since the previous mirror
-Teata, mis on eelmisest peegeldusest saadik muutunud
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Kirjuta ka hts-changes.json, mis loetleb, mis on võrreldes eelmise peegeldusega uus, muutunud, muutumatu või kadunud.
-Inline assets as data: URIs (self-contained pages)
-Manusta ressursid data: URI-dena (iseseisvad lehed)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Pärast peegelduse lõppu kirjuta iga salvestatud leht ümber, manustades selle laaditabelid, skriptid, pildid ja fondid, nii et lehte saab avada ka eraldi.
-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

@@ -652,8 +652,8 @@ Disconnect when finished
 Disconnect when finished
 Disconnect modem on completion
 Disconnect modem on completion
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
 About WinHTTrack Website Copier
 About WinHTTrack Website Copier
 Please visit our Web page
@@ -1004,31 +1004,3 @@ Strip query keys:
 Strip query keys:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
-Write a WARC archive of the crawl
-Write a WARC archive of the crawl
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-WARC archive name:
-WARC archive name:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Report what changed since the previous mirror
-Report what changed since the previous mirror
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Inline assets as data: URIs (self-contained pages)
-Inline assets as data: URIs (self-contained pages)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-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

@@ -636,8 +636,8 @@ Disconnect when finished
 Katkaise yhteys, kun on valmista
 Disconnect modem on completion
 Katkaise modeemiyhteys, kun on valmista
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Kerro meille bugeista ja ongelmista)\r\n\r\nKehitys:\r\nKäyttöliittymä (Windows): Xavier Roche\r\nNettirobotti: Xavier Roche\r\n\r\n(C) 1998-2003 Xavier Roche ja muut avustajat\r\nSuomentanut Mika Kähkönen 22.-24.7.2005\r\nmika.kahkonen@mbnet.fi\r\nhttp://koti.mbnet.fi/kahoset
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Kerro meille bugeista ja ongelmista)\r\n\r\nKehitys:\r\nKäyttöliittymä (Windows): Xavier Roche\r\nNettirobotti: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C) 1998-2003 Xavier Roche ja muut avustajat\r\nSuomentanut Mika Kähkönen 22.-24.7.2005\r\nmika.kahkonen@mbnet.fi\r\nhttp://koti.mbnet.fi/kahoset
 About WinHTTrack Website Copier
 Tietoja WinHTTrack Website Copier
 Please visit our Web page
@@ -958,31 +958,3 @@ Strip query keys:
 Poista kyselyavaimet:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Pilkuin erotellut kyselyavaimet, jotka jätetään pois tallennettujen tiedostojen nimeämisestä (esim. sid,utm_source).
-Write a WARC archive of the crawl
-Kirjoita imuroinnin WARC-arkisto
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Tallenna myös jokainen noudettu vastaus ISO-28500 WARC/1.1 -arkistoon peilin viereen.
-WARC archive name:
-WARC-arkiston nimi:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Valinnainen WARC-arkiston perusnimi; jätä tyhjäksi, jotta se nimetään automaattisesti tulostehakemistoon.
-Report what changed since the previous mirror
-Raportoi, mikä on muuttunut edellisen peilauksen jälkeen
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Kirjoita myös hts-changes.json, joka luettelee, mikä on edelliseen peilaukseen verrattuna uutta, muuttunutta, muuttumatonta tai kadonnutta.
-Inline assets as data: URIs (self-contained pages)
-Upota resurssit data:-URI-osoitteina (itsenäiset sivut)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Kun peilaus on valmis, kirjoita jokainen tallennettu sivu uudelleen niin, että sen tyylitiedostot, komentosarjat, kuvat ja fontit upotetaan, jolloin sivun voi avata myös yksinään.
-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

@@ -644,8 +644,8 @@ Disconnect when finished
 Déconnecter à la fin de l'opération
 Disconnect modem on completion
 Déconnecter le modem lorsque l'opération sera finie
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(signalez-nous tout bug ou problème)\r\n\r\nDéveloppement:\r\nInterface (Windows): Xavier Roche\r\nMoteur: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMERCI pour la relecture à:\r\nRobert Lagadec
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(signalez-nous tout bug ou problème)\r\n\r\nDéveloppement:\r\nInterface (Windows): Xavier Roche\r\nMoteur: Xavier Roche\r\nParseurClassesJava: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMERCI pour la relecture à:\r\nRobert Lagadec
 About WinHTTrack Website Copier
 A propos de WinHTTrack Website Copier
 Please visit our Web page
@@ -1004,31 +1004,3 @@ Strip query keys:
 Supprimer les clés de query string :
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Clés de query string à retirer du nommage des fichiers enregistrés, séparées par des virgules (par ex. sid,utm_source).
-Write a WARC archive of the crawl
-Écrire une archive WARC du crawl
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Enregistrer aussi chaque réponse téléchargée dans une archive WARC/1.1 (ISO-28500), à côté du miroir.
-WARC archive name:
-Nom de l'archive WARC :
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nom de base optionnel pour l'archive WARC ; laissez vide pour le générer automatiquement dans le répertoire de sortie.
-Report what changed since the previous mirror
-Signaler ce qui a changé depuis le miroir précédent
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Écrire aussi hts-changes.json, qui liste ce que ce crawl laisse nouveau, modifié, inchangé ou disparu par rapport au miroir précédent.
-Inline assets as data: URIs (self-contained pages)
-Intégrer les ressources en URI data: (pages autonomes)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Une fois le miroir terminé, réécrire chaque page enregistrée avec ses feuilles de style, scripts, images et polices intégrés, afin qu'une page puisse aussi être ouverte seule.
-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

@@ -636,8 +636,8 @@ Disconnect when finished
 Αποσύνδεση στο τέλος
 Disconnect modem on completion
 Αποσύνδεση του modem στο τέλος
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Παρακαλώ να μας ενημερώσετε για κάθε πρόβλημα ή bug)\r\n\r\nΑνάπτυξη:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Greek translations to:\r\nMichael Papadakis (mikepap at freemail dot gr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Παρακαλώ να μας ενημερώσετε για κάθε πρόβλημα ή bug)\r\n\r\nΑνάπτυξη:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Greek translations to:\r\nMichael Papadakis (mikepap at freemail dot gr)
 About WinHTTrack Website Copier
 Σχετικά με το WinHTTrack Website Copier
 Please visit our Web page
@@ -958,31 +958,3 @@ Strip query keys:
 Αφαίρεση κλειδιών ερωτήματος:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Κλειδιά ερωτήματος χωρισμένα με κόμμα, που θα αφαιρεθούν από την ονομασία των αποθηκευμένων αρχείων (π.χ. sid,utm_source).
-Write a WARC archive of the crawl
-Εγγραφή αρχείου WARC της ανίχνευσης
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Αποθήκευση κάθε ληφθείσας απόκρισης και σε αρχείο WARC/1.1 ISO-28500, δίπλα στο είδωλο.
-WARC archive name:
-Όνομα αρχείου WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Προαιρετικό βασικό όνομα για το αρχείο WARC. Αφήστε το κενό για αυτόματη ονομασία στον κατάλογο εξόδου.
-Report what changed since the previous mirror
-Αναφορά των αλλαγών από το προηγούμενο αντίγραφο
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Εγγραφή και του hts-changes.json, που παραθέτει τι είναι νέο, τι άλλαξε, τι έμεινε ίδιο και τι χάθηκε σε σχέση με το προηγούμενο αντίγραφο.
-Inline assets as data: URIs (self-contained pages)
-Ενσωμάτωση των πόρων ως URI data: (αυτόνομες σελίδες)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Μόλις ολοκληρωθεί το αντίγραφο, κάθε αποθηκευμένη σελίδα ξαναγράφεται με ενσωματωμένα τα φύλλα στυλ, τα σενάρια, τις εικόνες και τις γραμματοσειρές της, ώστε η σελίδα να μπορεί να ανοίξει και μόνη της.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Disconnetti alla fine
 Disconnect modem on completion
 Disconnetti il modem quando il mirror è finito
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(informateci degli errori o problemi)\r\n\rSviluppo:\r\nInterfacccia: Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Italian translations to:\r\nWitold Krakowski (wkrakowski@libero.it)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(informateci degli errori o problemi)\r\n\rSviluppo:\r\nInterfacccia: Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Italian translations to:\r\nWitold Krakowski (wkrakowski@libero.it)
 About WinHTTrack Website Copier
 Informazioni su WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Rimuovi chiavi della query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chiavi della query string, separate da virgole, da rimuovere dai nomi dei file salvati (ad es. sid,utm_source).
-Write a WARC archive of the crawl
-Scrivi un archivio WARC della scansione
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Salva anche ogni risposta scaricata in un archivio WARC/1.1 ISO-28500, accanto al mirror.
-WARC archive name:
-Nome dell'archivio WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nome di base facoltativo per l'archivio WARC; lascia vuoto per assegnarlo automaticamente nella directory di output.
-Report what changed since the previous mirror
-Segnala che cosa è cambiato dalla copia precedente
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Scrive anche hts-changes.json, che elenca ciò che questa scansione lascia come nuovo, modificato, invariato o scomparso rispetto alla copia precedente.
-Inline assets as data: URIs (self-contained pages)
-Incorpora le risorse come URI data: (pagine autonome)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Al termine della copia, riscrive ogni pagina salvata incorporando fogli di stile, script, immagini e caratteri, in modo che una pagina possa essere aperta anche da sola.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 終了したら接続を切断する
 Disconnect modem on completion
 完了したらモデムとの接続を切断する
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(バグまたは問題についてわれわれに知らせてください)\r\n\r\nDevelopment:\r\nInterface(Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nJapanese translation :TAPKAL(nakataka@mars.dti.ne.jp)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(バグまたは問題についてわれわれに知らせてください)\r\n\r\nDevelopment:\r\nInterface(Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nJapanese translation :TAPKAL(nakataka@mars.dti.ne.jp)
 About WinHTTrack Website Copier
 WinHTTrackについて
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 削除するクエリキー:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 保存ファイル名の生成から除外するクエリキーをカンマ区切りで指定します (例: sid,utm_source)。
-Write a WARC archive of the crawl
-クロールの WARC アーカイブを書き出す
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-取得した各レスポンスを ISO-28500 WARC/1.1 アーカイブとしてミラーの隣にも保存します。
-WARC archive name:
-WARC アーカイブ名:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC アーカイブの任意のベース名。空欄にすると出力ディレクトリ内で自動的に名前が付けられます。
-Report what changed since the previous mirror
-前回のミラーからの変更点を報告する
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-hts-changes.json も書き出し、前回のミラーと比べて新規、変更、変更なし、消滅となったものを一覧にします。
-Inline assets as data: URIs (self-contained pages)
-リソースを data: URI として埋め込む (単独で開けるページ)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-ミラーの完了後、保存された各ページを、スタイルシート、スクリプト、画像、フォントを埋め込んだ形で書き直します。ページ単体でも開けるようになります。
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Äèñêîíåêòèð༠ñå êîãà <20>å çàâðøè
 Disconnect modem on completion
 Äèñêîíåêòèð༠ãî ìîäåìîò íà êðà¼
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\Âå ìîëèìå èçâåñòåòå íå çà áèëî êàêâà ãðåøêà èëè ïðîáëåì)\r\n\r\nDevelopment:\r\nÈíòåðôå¼ñ (Windows):Xavier Roche\r\nSpider:Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche è äðóãè\r\nÌÍÎÃÓ ÁËÀÃÎÄÀÐÍÎÑÒ çà ìàêåäîíñêèîò ïðåâîä íà:\r\nÀëåêñàíäàð Ñàâè<C3A2> (aleks@macedonia.eu.org)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\Âå ìîëèìå èçâåñòåòå íå çà áèëî êàêâà ãðåøêà èëè ïðîáëåì)\r\n\r\nDevelopment:\r\nÈíòåðôå¼ñ (Windows):Xavier Roche\r\nSpider:Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche è äðóãè\r\nÌÍÎÃÓ ÁËÀÃÎÄÀÐÍÎÑÒ çà ìàêåäîíñêèîò ïðåâîä íà:\r\nÀëåêñàíäàð Ñàâè<C3A2> (aleks@macedonia.eu.org)
 About WinHTTrack Website Copier
 Çà WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 ¾âáâàÐÝØ ÚÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 ºÛãçÕÒØ ÞÔ ÑÐàÐúÕâÞ, ÞÔÔÕÛÕÝØ áÞ ×ÐßØàÚÐ, èâÞ áÕ ÞâáâàÐÝãÒÐÐâ ÞÔ ØÜÕâÞ ÝÐ ×ÐçãÒÐÝÐâÐ ÔÐâÞâÕÚÐ (ÝÐ ßàØÜÕà sid,utm_source).
-Write a WARC archive of the crawl
-·ÐßØèØ WARC ÐàåØÒÐ ÝÐ ßàÕÑÐàãÒÐúÕâÞ
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-·ÐçãÒÐø ÓÞ áÕÚÞø ßàÕ×ÕÜÕÝ ÞÔÓÞÒÞà Ø ÒÞ ISO-28500 WARC/1.1 ÐàåØÒÐ, ßÞÚàÐø ÞÓÛÕÔÐÛÞâÞ.
-WARC archive name:
-¸ÜÕ ÝÐ WARC ÐàåØÒÐâÐ:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-¸×ÑÞàÝÞ ÞáÝÞÒÝÞ ØÜÕ ×Ð WARC ÐàåØÒÐâÐ; ÞáâÐÒÕâÕ ßàÐ×ÝÞ ×Ð ÐÒâÞÜÐâáÚÞ ØÜÕÝãÒÐúÕ ÒÞ Ø×ÛÕ×ÝØÞâ ÔØàÕÚâÞàØãÜ.
-Report what changed since the previous mirror
-¸×ÒÕáâØ èâÞ Õ ßàÞÜÕÝÕâÞ ÞÔ ßàÕâåÞÔÝÞâÞ ÞÓÛÕÔÐÛÞ
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-·ÐßØèØ Ø hts-changes.json áÞ áßØáÞÚ ÝÐ âÞÐ èâÞ Õ ÝÞÒÞ, ßàÞÜÕÝÕâÞ, ÝÕßàÞÜÕÝÕâÞ ØÛØ ØáçÕ×ÝÐâÞ ÒÞ ÞÔÝÞá ÝÐ ßàÕâåÞÔÝÞâÞ ÞÓÛÕÔÐÛÞ.
-Inline assets as data: URIs (self-contained pages)
-²ÓàÐÔØ ÓØ àÕáãàáØâÕ ÚÐÚÞ data: URI (áÐÜÞáâÞøÝØ áâàÐÝØæØ)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-¿Þ ×ÐÒàèãÒÐúÕ ÝÐ ÞÓÛÕÔÐÛÞâÞ, áÕÚÞøÐ ×ÐçãÒÐÝÐ áâàÐÝØæÐ áÕ ßàÕßØèãÒÐ áÞ ÒÓàÐÔÕÝØ áâØÛáÚØ ÛØáâÞÒØ, áÚàØßâØ, áÛØÚØ Ø äÞÝâÞÒØ, ×Ð ÔÐ ÜÞÖÕ áâàÐÝØæÐâÐ ÔÐ áÕ ÞâÒÞàØ Ø áÐÜÞáâÞøÝÞ.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Vonalbontás, ha kész
 Disconnect modem on completion
 Modem leválasztása, ha kész
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Kérjük, jelezzen nekünk bármilyen hibát vagy problémát)\r\n\r\nFejlesztés:\r\nKezelõfelület (Windows): Xavier Roche\r\nIndexelés: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nEZER KÖSZÖNET a magyar fordításért:\r\nHerczeg József Tamásnak (hdodi@freemail.hu)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Kérjük, jelezzen nekünk bármilyen hibát vagy problémát)\r\n\r\nFejlesztés:\r\nKezelõfelület (Windows): Xavier Roche\r\nIndexelés: Xavier Roche\r\nJavaElemzõOsztályok: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nEZER KÖSZÖNET a magyar fordításért:\r\nHerczeg József Tamásnak (hdodi@freemail.hu)
 About WinHTTrack Website Copier
 WinHTTrack webhely másoló névjegye
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Lekérdezési kulcsok eltávolítása:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Vesszõvel elválasztott lekérdezési kulcsok, amelyeket el kell hagyni a mentett fájl elnevezésébõl (pl. sid,utm_source).
-Write a WARC archive of the crawl
-A bejárás WARC archívumának írása
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Minden letöltött válasz mentése ISO-28500 WARC/1.1 archívumba is, a tükör mellé.
-WARC archive name:
-WARC archívum neve:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-A WARC archívum opcionális alapneve; hagyja üresen az automatikus elnevezéshez a kimeneti könyvtárban.
-Report what changed since the previous mirror
-Jelentés arról, mi változott az elõzõ tükrözés óta
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-A hts-changes.json fájl írása is, amely felsorolja, mi új, mi változott, mi maradt változatlan és mi tûnt el az elõzõ tükrözéshez képest.
-Inline assets as data: URIs (self-contained pages)
-Erõforrások beágyazása data: URI-ként (önálló oldalak)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-A tükrözés befejezése után minden mentett oldal újraírása a stíluslapok, parancsfájlok, képek és betûtípusok beágyazásával, így az oldal önmagában is megnyitható.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Indien gedaan verbinding verbreken
 Disconnect modem on completion
 Indien gedaan modemverbinding verbreken
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Ons fouten en problemen mede te delen)\r\n\r\nOntwikkeling:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Dutch translations to:\r\nRudi Ferrari (Wyando@netcologne.de)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Ons fouten en problemen mede te delen)\r\n\r\nOntwikkeling:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Dutch translations to:\r\nRudi Ferrari (Wyando@netcologne.de)
 About WinHTTrack Website Copier
 Over WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Query-sleutels verwijderen:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Door komma's gescheiden query-sleutels die bij het benoemen van opgeslagen bestanden worden weggelaten (bijv. sid,utm_source).
-Write a WARC archive of the crawl
-Schrijf een WARC-archief van de crawl
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Sla ook elke opgehaalde respons op in een ISO-28500 WARC/1.1-archief, naast de mirror.
-WARC archive name:
-Naam van WARC-archief:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Optionele basisnaam voor het WARC-archief; laat leeg om het automatisch een naam te geven in de uitvoermap.
-Report what changed since the previous mirror
-Rapporteren wat er sinds de vorige spiegeling is gewijzigd
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Ook hts-changes.json schrijven met een overzicht van wat deze doorloop nieuw, gewijzigd, ongewijzigd of verdwenen laat ten opzichte van de vorige spiegeling.
-Inline assets as data: URIs (self-contained pages)
-Bronnen insluiten als data:-URI's (op zichzelf staande pagina's)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Zodra de spiegeling klaar is, elke opgeslagen pagina herschrijven met ingesloten stijlbladen, scripts, afbeeldingen en lettertypen, zodat een pagina ook los geopend kan worden.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Koble fra når fullført
 Disconnect modem on completion
 Koble fra modem når fullført
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Vennligst fortell oss om feil eller problemer med programmet)\r\n\r\nUtvikling (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche og andre bidragsytere\r\n\r\nNorwegian translation:\r\nTobias "Spug" Langhoff ( spug_enigma@hotmail.com )
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Vennligst fortell oss om feil eller problemer med programmet)\r\n\r\nUtvikling (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche og andre bidragsytere\r\n\r\nNorwegian translation:\r\nTobias "Spug" Langhoff ( spug_enigma@hotmail.com )
 About WinHTTrack Website Copier
 Om WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Fjern spørrenøkler:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerte spørrenøkler som utelates i navngivingen av lagrede filer (f.eks. sid,utm_source).
-Write a WARC archive of the crawl
-Skriv et WARC-arkiv av gjennomgangen
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Lagre også hvert nedlastet svar i et ISO-28500 WARC/1.1-arkiv ved siden av speilet.
-WARC archive name:
-Navn på WARC-arkiv:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Valgfritt basisnavn for WARC-arkivet; la feltet stå tomt for automatisk navngivning i utdatamappen.
-Report what changed since the previous mirror
-Rapporter hva som er endret siden forrige speiling
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Skriv også hts-changes.json som lister opp hva denne gjennomgangen etterlater som nytt, endret, uendret eller forsvunnet sammenlignet med forrige speiling.
-Inline assets as data: URIs (self-contained pages)
-Bygg inn ressurser som data:-URI-er (selvstendige sider)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Når speilingen er ferdig, skrives hver lagrede side om med stilark, skript, bilder og skrifter innebygd, slik at en side også kan åpnes alene.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Zakoñcz po³¹czenie z us³ugodawc¹ po pobraniu
 Disconnect modem on completion
 Po pobraniu roz³¹cz modem
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(proszê poinformowaæ nas o jakichkolwiek b³êdach w dzia³aniu programu)\r\n\r\nTwórcy:\r\nInterfejs(Windows): Xavier Roche\r\nMotor: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nPolska wersja jêzykowa: £ukasz Jokiel (Opole University of Technology, Lukasz.Jokiel@po.opole.pl)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(proszê poinformowaæ nas o jakichkolwiek b³êdach w dzia³aniu programu)\r\n\r\nTwórcy:\r\nInterfejs(Windows): Xavier Roche\r\nMotor: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nPolska wersja jêzykowa: £ukasz Jokiel (Opole University of Technology, Lukasz.Jokiel@po.opole.pl)
 About WinHTTrack Website Copier
 O... WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Usuñ klucze zapytania:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Rozdzielone przecinkami klucze zapytania pomijane przy nazywaniu zapisanych plików (np. sid,utm_source).
-Write a WARC archive of the crawl
-Zapisz archiwum WARC z indeksowania
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Zapisz te¿ ka¿d± pobran± odpowied¼ do archiwum WARC/1.1 ISO-28500, obok kopii lustrzanej.
-WARC archive name:
-Nazwa archiwum WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Opcjonalna nazwa bazowa archiwum WARC; pozostaw puste, aby nazwaæ je automatycznie w katalogu wyj¶ciowym.
-Report what changed since the previous mirror
-Zg³o¶, co zmieni³o siê od poprzedniej kopii
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zapisz równie¿ plik hts-changes.json z list± tego, co w porównaniu z poprzedni± kopi± jest nowe, zmienione, niezmienione lub usuniête.
-Inline assets as data: URIs (self-contained pages)
-Osad¼ zasoby jako identyfikatory data: URI (samodzielne strony)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Po zakoñczeniu tworzenia kopii przepisz ka¿d± zapisan± stronê z osadzonymi arkuszami stylów, skryptami, obrazami i czcionkami, aby stronê mo¿na by³o otworzyæ równie¿ samodzielnie.
-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

@@ -652,8 +652,8 @@ Disconnect when finished
 Desconectar ao finalizar
 Disconnect modem on completion
 Desconectar o modem ao finalizar
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(por favor nos comunique sobre erros ou problemas)\r\n\r\nDesenvolvimento:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche e outros colaboradores\r\nTraduzido para o Português-Brasil por :\r\nPaulo Neto (layoutbr@lexxa.com.br)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(por favor nos comunique sobre erros ou problemas)\r\n\r\nDesenvolvimento:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche e outros colaboradores\r\nTraduzido para o Português-Brasil por :\r\nPaulo Neto (layoutbr@lexxa.com.br)
 About WinHTTrack Website Copier
 Sobre o WinHTTrack Website Copier
 Please visit our Web page
@@ -1004,31 +1004,3 @@ Strip query keys:
 Remover chaves da query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chaves da query string, separadas por vírgulas, a serem removidas da nomeação dos arquivos salvos (ex.: sid,utm_source).
-Write a WARC archive of the crawl
-Gravar um arquivo WARC do rastreamento
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Salvar também cada resposta baixada em um arquivo WARC/1.1 ISO-28500, ao lado do espelho.
-WARC archive name:
-Nome do arquivo WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nome base opcional para o arquivo WARC; deixe em branco para nomeá-lo automaticamente no diretório de saída.
-Report what changed since the previous mirror
-Relatar o que mudou desde o espelhamento anterior
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Gravar também hts-changes.json listando o que esta captura deixa como novo, alterado, inalterado ou removido em relação ao espelhamento anterior.
-Inline assets as data: URIs (self-contained pages)
-Incorporar os recursos como URIs data: (páginas autônomas)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Ao terminar o espelhamento, reescrever cada página salva com suas folhas de estilo, scripts, imagens e fontes incorporadas, para que a página também possa ser aberta sozinha.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Desligar no fim da operação
 Disconnect modem on completion
 Desconectar o modem no final
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Por favor avise-nos acerca de erros ou problemas)\r\n\r\nDesenvolvimento:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nAgradecimentos pela tradução para o Português para:\r\nRui Fernandes (CANTIC, ruiefe@mail.malhatlantica.pt)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Por favor avise-nos acerca de erros ou problemas)\r\n\r\nDesenvolvimento:\r\nInterface (Windows): Xavier Roche\r\nMotor: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nAgradecimentos pela tradução para o Português para:\r\nRui Fernandes (CANTIC, ruiefe@mail.malhatlantica.pt)
 About WinHTTrack Website Copier
 Acerca do WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Remover chaves da query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chaves da query string, separadas por vírgulas, a remover da nomeação dos ficheiros guardados (por ex. sid,utm_source).
-Write a WARC archive of the crawl
-Escrever um arquivo WARC do rastreio
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Guardar também cada resposta transferida num arquivo WARC/1.1 ISO-28500, ao lado do espelho.
-WARC archive name:
-Nome do arquivo WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nome base opcional para o arquivo WARC; deixe em branco para o nomear automaticamente no diretório de saída.
-Report what changed since the previous mirror
-Comunicar o que mudou desde o espelho anterior
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Escrever também hts-changes.json, que lista o que esta recolha deixa como novo, alterado, inalterado ou desaparecido em relação ao espelho anterior.
-Inline assets as data: URIs (self-contained pages)
-Incorporar os recursos como URI data: (páginas autónomas)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Depois de terminado o espelho, reescrever cada página guardada com as suas folhas de estilo, scripts, imagens e tipos de letra incorporados, para que a página também possa ser aberta sozinha.
-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

@@ -634,7 +634,7 @@ Disconnect when finished
 Deconectează şa terminare
 Disconnect modem on completion
 Deconectează modemul la terminare
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
 
 About WinHTTrack Website Copier
 Despre WinHTTrack Website Copier
@@ -956,31 +956,3 @@ Strip query keys:
 Elimina cheile din query string:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Chei din query string, separate prin virgula, de eliminat din denumirea fisierelor salvate (de ex. sid,utm_source).
-Write a WARC archive of the crawl
-Scrie o arhiva WARC a parcurgerii
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Salveaza si fiecare raspuns descarcat intr-o arhiva WARC/1.1 ISO-28500, langa oglinda.
-WARC archive name:
-Numele arhivei WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Nume de baza optional pentru arhiva WARC; lasati gol pentru a-l denumi automat in directorul de iesire.
-Report what changed since the previous mirror
-Raporteaza ce s-a schimbat fata de copia anterioara
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Scrie si hts-changes.json, care listeaza ce este nou, modificat, nemodificat sau disparut fata de copia anterioara.
-Inline assets as data: URIs (self-contained pages)
-Încorporeaza resursele ca URI data: (pagini de sine statatoare)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Dupa terminarea copiei, fiecare pagina salvata este rescrisa cu foile de stil, scripturile, imaginile si fonturile încorporate, astfel încât pagina sa poata fi deschisa si singura.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Îòñîåäèíèòüñÿ ïðè çàâåðøåíèè
 Disconnect modem on completion
 Îòñîåäèíèòü ïðè çàâåðøåíèè
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Ñîîáùèòå íàì, ïîæàëóéñòà, î çàìå÷åííûõ ïðîáëåìàõ è îøèáêàõ)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÊà÷àëêà (spider): Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Russian translations to:\r\nAndrei Iliev (andreiiliev@mail.ru)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Ñîîáùèòå íàì, ïîæàëóéñòà, î çàìå÷åííûõ ïðîáëåìàõ è îøèáêàõ)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÊà÷àëêà (spider): Xavier Roche\r\nÏàðñåð ÿâà-êëàññîâ: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Russian translations to:\r\nAndrei Iliev (andreiiliev@mail.ru)
 About WinHTTrack Website Copier
 Î ïðîãðàììå WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Óäàëÿòü êëþ÷è çàïðîñà:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷è çàïðîñà ÷åðåç çàïÿòóþ, óäàëÿåìûå èç èìåíè ñîõðàíÿåìîãî ôàéëà (íàïðèìåð, sid,utm_source).
-Write a WARC archive of the crawl
-Çàïèñàòü WARC-àðõèâ îáõîäà
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Ñîõðàíÿòü êàæäûé çàãðóæåííûé îòâåò òàêæå â àðõèâ WARC/1.1 ISO-28500 ðÿäîì ñ çåðêàëîì.
-WARC archive name:
-Èìÿ WARC-àðõèâà:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Íåîáÿçàòåëüíîå áàçîâîå èìÿ WARC-àðõèâà; îñòàâüòå ïóñòûì äëÿ àâòîìàòè÷åñêîãî èìåíîâàíèÿ â âûõîäíîì êàòàëîãå.
-Report what changed since the previous mirror
-Ñîîáùàòü, ÷òî èçìåíèëîñü ñ ïðåäûäóùåãî çåðêàëà
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Òàêæå çàïèñûâàòü hts-changes.json ñî ñïèñêîì òîãî, ÷òî ïî ñðàâíåíèþ ñ ïðåäûäóùèì çåðêàëîì ñòàëî íîâûì, èçìåí¸ííûì, íåèçìåí¸ííûì èëè èñ÷åçëî.
-Inline assets as data: URIs (self-contained pages)
-Âñòðàèâàòü ðåñóðñû êàê data: URI (ñàìîñòîÿòåëüíûå ñòðàíèöû)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Ïîñëå çàâåðøåíèÿ çåðêàëèðîâàíèÿ êàæäàÿ ñîõðàí¸ííàÿ ñòðàíèöà ïåðåçàïèñûâàåòñÿ ñî âñòðîåííûìè òàáëèöàìè ñòèëåé, ñöåíàðèÿìè, èçîáðàæåíèÿìè è øðèôòàìè, ÷òîáû ñòðàíèöó ìîæíî áûëî îòêðûòü îòäåëüíî.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Odpoji<EFBFBD>, ak je kopírovanie ukonèené
 Disconnect modem on completion
 Odpoji<EFBFBD> modem po dokonèení
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Oznám nám akúko¾vek chybu alebo problém)\r\n\r\nVývoj:\r\nProstredie (Windows): Xavier Roche\r\nPavúk: Xavier Roche\r\n\r\n(C)1998-2001 Xavier Roche a ostatní pomocníci\r\nVE¼KÉ POÏAKOVANIE za preklady:\r\nDr. Martin Sereday (sereday@slovanet.sk)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Oznám nám akúko¾vek chybu alebo problém)\r\n\r\nVývoj:\r\nProstredie (Windows): Xavier Roche\r\nPavúk: Xavier Roche\r\nKontrolór Javy: Yann Philippot\r\n\r\n(C)1998-2001 Xavier Roche a ostatní pomocníci\r\nVE¼KÉ POÏAKOVANIE za preklady:\r\nDr. Martin Sereday (sereday@slovanet.sk)
 About WinHTTrack Website Copier
 O WinHTTrack Website Copier...
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Odstráni» kµúèe dotazu:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kµúèe dotazu oddelené èiarkami, ktoré sa vynechajú z pomenovania ukladaných súborov (napr. sid,utm_source).
-Write a WARC archive of the crawl
-Zapísa» archív WARC z prehµadávania
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Ulo¾i» aj ka¾dú stiahnutú odpoveï do archívu WARC/1.1 ISO-28500 vedµa zrkadla.
-WARC archive name:
-Názov archívu WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Voliteµný základný názov archívu WARC; ponechajte prázdne pre automatické pomenovanie vo výstupnom adresári.
-Report what changed since the previous mirror
-Oznámi», èo sa od predchádzajúceho zrkadlenia zmenilo
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zapísa» aj hts-changes.json so zoznamom toho, èo je oproti predchádzajúcemu zrkadleniu nové, zmenené, nezmenené alebo chýbajúce.
-Inline assets as data: URIs (self-contained pages)
-Vlo¾i» zdroje ako URI data: (samostatné stránky)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Po dokonèení zrkadlenia prepísa» ka¾dú ulo¾enú stránku s vlo¾enými ¹týlmi, skriptmi, obrázkami a písmami, aby sa stránka dala otvori» aj samostatne.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Prekini povezavo, ko bo konèano
 Disconnect modem on completion
 Izkljuèi modem ob dokonèanju
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Prosimo Vas, da nas obvestite o kakršnih koli težavah ali napakah)\r\n\r\nRazvoj:\r\nVmesnik (Okna): Xavier Roche\r\nHitrost: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche in drugi sodelujoèi\r\nVELIKA ZAHVALA za namige prevodov gre:\r\nRobertu Lagadecu (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Prosimo Vas, da nas obvestite o kakršnih koli težavah ali napakah)\r\n\r\nRazvoj:\r\nVmesnik (Okna): Xavier Roche\r\nHitrost: Xavier Roche\r\nJavaParserRazredi: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche in drugi sodelujoèi\r\nVELIKA ZAHVALA za namige prevodov gre:\r\nRobertu Lagadecu (rlagadec@yahoo.fr)
 About WinHTTrack Website Copier
 O programu WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Odstrani kljuce poizvedbe:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Z vejicami loceni kljuci poizvedbe, ki se izpustijo pri poimenovanju shranjenih datotek (npr. sid,utm_source).
-Write a WARC archive of the crawl
-Zapisi arhiv WARC iz pregledovanja
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Shrani tudi vsak preneseni odgovor v arhiv WARC/1.1 ISO-28500 poleg zrcala.
-WARC archive name:
-Ime arhiva WARC:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Neobvezno osnovno ime arhiva WARC; pustite prazno za samodejno poimenovanje v izhodni mapi.
-Report what changed since the previous mirror
-Porocaj, kaj se je spremenilo od prejsnjega zrcaljenja
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Zapisi tudi hts-changes.json s seznamom tega, kar je v primerjavi s prejsnjim zrcaljenjem novo, spremenjeno, nespremenjeno ali izginilo.
-Inline assets as data: URIs (self-contained pages)
-Vgradi vire kot data: URI (samostojne strani)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Ko je zrcaljenje koncano, se vsaka shranjena stran prepise z vgrajenimi slogovnimi listi, skripti, slikami in pisavami, tako da jo je mogoce odpreti tudi samostojno.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Koppla ner förbindelsen när överföringen är klar
 Disconnect modem on completion
 Koppla ned modemet efter avslutning
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Hittar du fel eller uppstår det problem, kontakta oss)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Swedish translations to:\r\nStaffan Ström (staffan@fam-strom.org)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Hittar du fel eller uppstår det problem, kontakta oss)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Swedish translations to:\r\nStaffan Ström (staffan@fam-strom.org)
 About WinHTTrack Website Copier
 Om WinHTTrack Website Copier...
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Ta bort frågenycklar:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kommaseparerade frågenycklar som utelämnas vid namngivningen av sparade filer (t.ex. sid,utm_source).
-Write a WARC archive of the crawl
-Skriv ett WARC-arkiv av genomsökningen
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Spara även varje hämtat svar i ett ISO-28500 WARC/1.1-arkiv, bredvid spegeln.
-WARC archive name:
-WARC-arkivets namn:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Valfritt basnamn för WARC-arkivet; lämna tomt för att namnge det automatiskt i utdatakatalogen.
-Report what changed since the previous mirror
-Rapportera vad som ändrats sedan föregående spegling
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Skriv även hts-changes.json som listar vad den här genomgången lämnar som nytt, ändrat, oförändrat eller försvunnet jämfört med föregående spegling.
-Inline assets as data: URIs (self-contained pages)
-Bädda in resurser som data:-URI:er (fristående sidor)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-När speglingen är klar skrivs varje sparad sida om med sina formatmallar, skript, bilder och teckensnitt inbäddade, så att en sida också kan öppnas för sig.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Bittiðinde baðlantýyý kes
 Disconnect modem on completion
 Ýþlem tamamlandýðýnda modemden baðlantýyý kopar
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Lütfen bize her türlü hatayý ve problemi aktarýnýz)\r\n\r\nGeliþtirme:\r\nArayüz (Windows): Xavier Roche\r\nAð: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche ve diðerleri\r\nÇeviri ipuçlarý için teþekkürler: \r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Lütfen bize her türlü hatayý ve problemi aktarýnýz)\r\n\r\nGeliþtirme:\r\nArayüz (Windows): Xavier Roche\r\nAð: Xavier Roche\r\nJava Ayýklama Sýnýflarý: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche ve diðerleri\r\nÇeviri ipuçlarý için teþekkürler: \r\nRobert Lagadec (rlagadec@yahoo.fr)
 About WinHTTrack Website Copier
 WinHTTrack Website Copier Hakkýnda
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Sorgu anahtarlarýný çýkar:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Kaydedilen dosya adlandýrmasýndan çýkarýlacak, virgülle ayrýlmýþ sorgu anahtarlarý (örn. sid,utm_source).
-Write a WARC archive of the crawl
-Taramanýn WARC arþivini yaz
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Ýndirilen her yanýtý ayrýca aynanýn yanýna bir ISO-28500 WARC/1.1 arþivine kaydet.
-WARC archive name:
-WARC arþivi adý:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC arþivi için isteðe baðlý temel ad; çýktý dizininde otomatik adlandýrma için boþ býrakýn.
-Report what changed since the previous mirror
-Önceki yansýmadan bu yana deðiþenleri bildir
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Ayrýca hts-changes.json yazarak bu taramanýn önceki yansýmaya göre neyi yeni, deðiþmiþ, deðiþmemiþ veya kaybolmuþ býraktýðýný listele.
-Inline assets as data: URIs (self-contained pages)
-Kaynaklarý data: URI olarak göm (kendi kendine yeten sayfalar)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Yansýlama bittiðinde, kaydedilen her sayfa stil sayfalarý, betikleri, görselleri ve yazý tipleri gömülü olarak yeniden yazýlýr; böylece sayfa tek baþýna da açýlabilir.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 ³ä'ºäíàòèñü ïðè çàâåðøåíí³
 Disconnect modem on completion
 ³ä'ºäíàòè ïðè çàâåðøåíí³
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Ïîâ³äîìèòå íàì áóäü ëàñêà ïðî ïîì³÷åí³ ïðîáëåìè ³ ïîìèëêè)\r\n\r\nðàçðàáîòêà:\r\nèíòåðôåéñ (Windows): Xavier Roche\r\nêà÷àëêà (spider): Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Ukrainian translations to:\r\nAndrij Shevchuk (andrijsh@mail.lviv.ua) http://programy.com.ua, http://vic-info.com.ua
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Ïîâ³äîìèòå íàì áóäü ëàñêà ïðî ïîì³÷åí³ ïðîáëåìè ³ ïîìèëêè)\r\n\r\nðàçðàáîòêà:\r\nèíòåðôåéñ (Windows): Xavier Roche\r\nêà÷àëêà (spider): Xavier Roche\r\nïàðñåð java-êëàñ³â: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Ukrainian translations to:\r\nAndrij Shevchuk (andrijsh@mail.lviv.ua) http://programy.com.ua, http://vic-info.com.ua
 About WinHTTrack Website Copier
 Ïðî ïðîãðàìó WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Âèëó÷àòè êëþ÷³ çàïèòó:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Êëþ÷³ çàïèòó ÷åðåç êîìó, ÿê³ âèëó÷àþòüñÿ ç ³ìåí³ çáåðåæåíîãî ôàéëó (íàïðèêëàä, sid,utm_source).
-Write a WARC archive of the crawl
-Çàïèñàòè WARC-àðõ³â îáõîäó
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Çáåð³ãàòè êîæíó çàâàíòàæåíó â³äïîâ³äü òàêîæ ó àðõ³â WARC/1.1 ISO-28500 ïîðÿä ³ç äçåðêàëîì.
-WARC archive name:
-²ì'ÿ WARC-àðõ³âó:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-Íåîáîâ'ÿçêîâà áàçîâà íàçâà WARC-àðõ³âó; çàëèøòå ïîðîæí³ì äëÿ àâòîìàòè÷íîãî íàéìåíóâàííÿ ó âèõ³äíîìó êàòàëîç³.
-Report what changed since the previous mirror
-Ïîâ³äîìëÿòè, ùî çì³íèëîñÿ ç ïîïåðåäíüîãî äçåðêàëà
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-Òàêîæ çàïèñóâàòè hts-changes.json ç³ ñïèñêîì òîãî, ùî ïîð³âíÿíî ç ïîïåðåäí³ì äçåðêàëîì º íîâèì, çì³íåíèì, íåçì³íåíèì àáî çíèêëèì.
-Inline assets as data: URIs (self-contained pages)
-Âáóäîâóâàòè ðåñóðñè ÿê data: URI (ñàìîñò³éí³ ñòîð³íêè)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-ϳñëÿ çàâåðøåííÿ äçåðêàëþâàííÿ êîæíà çáåðåæåíà ñòîð³íêà ïåðåçàïèñóºòüñÿ ç âáóäîâàíèìè òàáëèöÿìè ñòèë³â, ñöåíàð³ÿìè, çîáðàæåííÿìè òà øðèôòàìè, ùîá ñòîð³íêó ìîæíà áóëî â³äêðèòè îêðåìî.
-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

@@ -634,8 +634,8 @@ Disconnect when finished
 Îòñîåäèíèòüñÿ ïðè çàâåðøåíèè
 Disconnect modem on completion
 Îòñîåäåíèòü ïðè çàâåðøåíèè
-\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
-\r\n(Ñîîáùèòå íàì ïîæàëóéñòà î çàìå÷åííûõ ïðîáëåìàõ è îøèáêàõ)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÊà÷àëêà (spider): Xavier Roche\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Russian translations to:\r\nAndrei Iliev (andreiiliev@mail.ru)
+\r\n(Please notify us of any bug or problem)\r\n\r\nDevelopment:\r\nInterface (Windows): Xavier Roche\r\nSpider: Xavier Roche\r\nJavaParserClasses: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for translation tips to:\r\nRobert Lagadec (rlagadec@yahoo.fr)
+\r\n(Ñîîáùèòå íàì ïîæàëóéñòà î çàìå÷åííûõ ïðîáëåìàõ è îøèáêàõ)\r\n\r\nÐàçðàáîòêà:\r\nÈíòåðôåéñ (Windows): Xavier Roche\r\nÊà÷àëêà (spider): Xavier Roche\r\nÏàðñåð ÿâà-êëàññîâ: Yann Philippot\r\n\r\n(C)1998-2003 Xavier Roche and other contributors\r\nMANY THANKS for Russian translations to:\r\nAndrei Iliev (andreiiliev@mail.ru)
 About WinHTTrack Website Copier
 Î ïðîãðàììå WinHTTrack Website Copier
 Please visit our Web page
@@ -956,31 +956,3 @@ Strip query keys:
 Olib tashlanadigan so’rov kalitlari:
 Comma-separated query keys to drop from the saved-file naming (e.g. sid,utm_source).
 Saqlangan fayl nomidan olib tashlanadigan, vergul bilan ajratilgan so’rov kalitlari (masalan, sid,utm_source).
-Write a WARC archive of the crawl
-Qidiruvning WARC arxivini yozish
-Also save every fetched response into an ISO-28500 WARC/1.1 archive, next to the mirror.
-Har bir yuklab olingan javobni ISO-28500 WARC/1.1 arxiviga ham, ko'zgu yonida saqlash.
-WARC archive name:
-WARC arxivi nomi:
-Optional base name for the WARC archive; leave blank to auto-name it under the output directory.
-WARC arxivi uchun ixtiyoriy asosiy nom; chiqish katalogida avtomatik nomlash uchun bo'sh qoldiring.
-Report what changed since the previous mirror
-Oldingi nusxadan beri nima o’zgarganini xabar qilish
-Also write hts-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror.
-hts-changes.json ham yoziladi: unda ushbu yig’ish oldingi nusxaga nisbatan nimani yangi, o’zgargan, o’zgarmagan yoki yo’qolgan holda qoldirgani ro’yxati bo’ladi.
-Inline assets as data: URIs (self-contained pages)
-Resurslarni data: URI sifatida joylash (mustaqil sahifalar)
-Once the mirror is finished, rewrite every saved page with its stylesheets, scripts, images and fonts embedded, so a page can also be opened on its own.
-Nusxalash tugagach, har bir saqlangan sahifa uslublar jadvallari, skriptlar, rasmlar va shriftlar joylangan holda qayta yoziladi, shunda sahifani alohida ham ochish mumkin.
-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.

libtest/callbacks-example-filenameiisbug.c

@@ -71,9 +71,7 @@ static int mysavename(t_hts_callbackarg * carg, httrackp * opt,
       for(j = 0; iisBogus[i][j] == a[j] && iisBogus[i][j] != '\0'; j++) ;
       if (iisBogus[i][j] == '\0'
           && (a[j] == '\0' || a[j] == '/' || a[j] == '\\')) {
-        /* j bytes matched, so j fit: copying j cannot overrun whatever the
-           table holds, and the tail must survive untouched */
-        memcpy(a, iisBogusReplace[i], (size_t) j);
+        strncpy(a, iisBogusReplace[i], strlen(iisBogusReplace[i]));
         break;
       }
     }

m4/check_zlib.m4

@@ -1,33 +1,82 @@
 dnl @synopsis CHECK_ZLIB()
 dnl
-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 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
-dnl Adds -lz to LIBS and defines HAVE_LIBZ.
 
-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])
+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 "${ZLIB_HOME}/include/zlib.h"
+then
+        ZLIB_HOME=/usr
 fi
-if test "$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="$LDFLAGS -L/usr/local/lib"
-fi
-AC_CHECK_HEADER([zlib.h], [],
-	[AC_MSG_ERROR([zlib.h not found; install the zlib development files or pass --with-zlib=DIR])])
-AC_CHECK_LIB([z], [inflateEnd], [],
-	[AC_MSG_ERROR([libz not found; install the zlib development files or pass --with-zlib=DIR])])
+])
+
+#
+# Locate zlib, if wanted
+#
+if test -n "${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
+fi
+
 ])

man/Makefile.am

@@ -16,11 +16,6 @@ regen-man: makeman.sh $(top_builddir)/src/httrack$(EXEEXT)
 
 # Render html/httrack.man.html from httrack.1. Needs the groff html device
 # (Debian: full "groff" package, not "groff-base"). Run by hand: make -C man regen-man-html
-# Strip groff's version-stamp and creation-date comments so the committed file
-# doesn't churn across groff versions or rebuilds; the ci man-page-sync guard
-# only requires this file to change whenever httrack.1 does.
 regen-man-html: httrack.1
-	groff -t -man -Thtml $(srcdir)/httrack.1 \
-		| sed -e 's/groff version [0-9][0-9.]*/groff/' -e '/^<!-- CreationDate:/d' \
-		> $(top_srcdir)/html/httrack.man.html
+	groff -t -man -Thtml $(srcdir)/httrack.1 > $(top_srcdir)/html/httrack.man.html
 .PHONY: regen-man-html

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 "27 July 2026" "httrack website copier"
+.TH httrack 1 "21 July 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -36,12 +36,9 @@ 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 ]
 [ \fB\-%M, \-\-mime\-html\fR ]
-[ \fB\-%Z, \-\-single\-file\fR ]
 [ \fB\-LN, \-\-long\-names[=N]\fR ]
 [ \fB\-KN, \-\-keep\-links[=N]\fR ]
 [ \fB\-x, \-\-replace\-external\fR ]
@@ -60,7 +57,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-sN, \-\-robots[=N]\fR ]
 [ \fB\-%h, \-\-http\-10\fR ]
 [ \fB\-%k, \-\-keep\-alive\fR ]
-[ \fB\-%z, \-\-disable\-compression\fR ]
 [ \fB\-%B, \-\-tolerant\fR ]
 [ \fB\-%s, \-\-updatehack\fR ]
 [ \fB\-%u, \-\-urlhack\fR ]
@@ -76,8 +72,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%X, \-\-headers\fR ]
 [ \fB\-C, \-\-cache[=N]\fR ]
 [ \fB\-k, \-\-store\-all\-in\-cache\fR ]
-[ \fB\-%r, \-\-warc\fR ]
-[ \fB\-%d, \-\-changes\fR ]
 [ \fB\-%n, \-\-do\-not\-recatch\fR ]
 [ \fB\-%v, \-\-display\fR ]
 [ \fB\-Q, \-\-do\-not\-log\fR ]
@@ -103,7 +97,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%!, \-\-disable\-security\-limits\fR ]
 [ \fB\-V, \-\-userdef\-cmd\fR ]
 [ \fB\-%W, \-\-callback\fR ]
-[ \fB\-y, \-\-background\-on\-suspend\fR ]
 [ \fB\-K, \-\-keep\-links[=N]\fR ]
 .SH DESCRIPTION
 .B httrack
@@ -190,23 +183,17 @@ 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])
 .br
 or user defined structure (\-N "%h%p/%n%q.%t")
 .IP \-%N
-delayed type check, don't make any link test but wait for files download to start instead (experimental) (%N0 don't use, %N1 use for unknown extensions, * %N2 always use) (\-\-delayed\-type\-check)
+delayed type check, don't make any link test but wait for files download to start instead (experimental) (%N0 don't use, %N1 use for unknown extensions, * %N2 always use)
 .IP \-%D
 cached delayed type check, don't wait for remote type during updates, to speedup them (%D0 wait, * %D1 don't wait) (\-\-cached\-delayed\-type\-check)
 .IP \-%M
 generate a RFC MIME\-encapsulated full\-archive (.mht) (\-\-mime\-html)
-.IP \-%Z
-after the mirror, rewrite each saved page with its stylesheets, scripts, images and fonts inlined as data: URIs, so any page opens by double\-click anywhere (links between pages stay relative; audio and video stay links); \-\-single\-file\-max\-size N caps each asset (default 10485760 bytes). %M is the better container where a Chromium\-family browser is a given: one archive, no base64 tax on text, a shared asset stored once (\-\-single\-file)
-.IP \-%t
-keep the original file extension, don't rewrite it from the MIME type (%t0 rewrite)
 .IP \-LN
 long names (L1 *long names / L0 8\-3 conversion / L2 ISO9660 compatible) (\-\-long\-names[=N])
 .IP \-KN
@@ -220,7 +207,7 @@ 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
-*save the server's error pages (404..) (o0 discard them) (\-\-generate\-errors)
+*generate output html file in case of error (404..) (o0 don't generate) (\-\-generate\-errors)
 .IP \-X
 *purge old files after update (X0 keep delete) (\-\-purge\-old[=N])
 .IP \-%p
@@ -244,8 +231,6 @@ follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always, 3=always
 force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (\-\-http\-10)
 .IP \-%k
 use keep\-alive if possible, greately reducing latency for small files and test requests (%k0 don't use) (\-\-keep\-alive)
-.IP \-%z
-do not request compressed content (%z0 request) (\-\-disable\-compression)
 .IP \-%B
 tolerant requests (accept bogus responses on some servers, but not standard!) (\-\-tolerant)
 .IP \-%s
@@ -272,7 +257,7 @@ default referer field sent in HTTP headers (\-\-referer <param>)
 .IP \-%E
 from email address sent in HTTP headers (\-\-from <param>)
 .IP \-%F
-footer string in Html code (\-%F "Mirrored from {url} on {date}"; fields {addr} {path} {url} {date} {lastmodified} {version} {mime} {charset} {status} {size}, or legacy %s) (\-\-footer <param>)
+footer string in Html code (\-%F "Mirrored [from host %s [file %s [at %s]]]" (\-\-footer <param>)
 .IP \-%l
 preferred language (\-%l "fr, en, jp, *" (\-\-language <param>)
 .IP \-%a
@@ -284,10 +269,6 @@ additional HTTP header line (\-%X "X\-Magic: 42" (\-\-headers <param>)
 create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before) (\-\-cache[=N])
 .IP \-k
 store all files in cache (not useful if files on disk) (\-\-store\-all\-in\-cache)
-.IP \-%r
-write an ISO\-28500 WARC/1.1 archive; \-\-warc\-file NAME sets the output name, \-\-warc\-max\-size N rotates segments past N bytes, \-\-warc\-cdx also writes a sorted CDXJ index, \-\-wacz packages it all as a WACZ file (\-\-warc)
-.IP \-%d
-write hts\-changes.json listing what this crawl left new, changed, unchanged and gone compared to the previous mirror (\-\-changes)
 .IP \-%n
 do not re\-download locally erased files (\-\-do\-not\-recatch)
 .IP \-%v
@@ -344,6 +325,8 @@ go everywhere on the web (\-\-go\-everywhere)
 .IP \-%H
 debug HTTP headers in logfile (\-\-debug\-headers)
 .SS Guru options: (do NOT use if possible)
+.IP \-#X
+*use optimized engine (limited memory boundary checks) (\-\-fast\-engine)
 .IP \-#test
 list engine self\-tests (run one with \-#test=NAME [args])
 .IP \-#C
@@ -368,6 +351,8 @@ maximum number of links (\-#L1000000) (\-\-advanced\-maxlinks[=N])
 display ugly progress information (\-\-advanced\-progressinfo)
 .IP \-#P
 catch URL (\-\-catch\-url)
+.IP \-#R
+old FTP routines (debug) (\-\-repair\-cache)
 .IP \-#T
 generate transfer ops. log every minutes (\-\-debug\-xfrstats)
 .IP \-#u
@@ -386,8 +371,6 @@ USE IT WITH EXTREME CARE
 execute system command after each files ($0 is the filename: \-V "rm \\$0") (\-\-userdef\-cmd <param>)
 .IP \-%W
 use an external library function as a wrapper (\-%W myfoo.so[,myparameters]) (\-\-callback <param>)
-.IP \-y
-go to background when suspended (y0 don't) (\-\-background\-on\-suspend)
 .SS Details: Option N
 .IP \-N0
 Site\-structure (default)

src/Makefile.am

@@ -32,9 +32,7 @@ AM_LDFLAGS = \
 
 bin_PROGRAMS = proxytrack httrack htsserver
 
-httrack_SOURCES = httrack.c htsbacktrace.c htsbacktrace.h
-# $(DL_LIBS): dladdr() in the crash handler, still in libdl on pre-2.34 glibc.
-httrack_LDADD = $(THREADS_LIBS) $(DL_LIBS) libhttrack.la
+httrack_LDADD = $(THREADS_LIBS) libhttrack.la
 htsserver_LDADD = $(THREADS_LIBS) $(SOCKET_LIBS) libhttrack.la
 proxytrack_LDADD = $(THREADS_LIBS) $(SOCKET_LIBS)
 
@@ -48,8 +46,7 @@ htsserver_LDFLAGS = $(AM_LDFLAGS) $(LDFLAGS_PIE)
 
 lib_LTLIBRARIES = libhttrack.la
 
-htsserver_SOURCES = htsserver.c htsserver.h htsweb.c htsweb.h htsstats.h \
-	htscmdline.c htscmdline.h \
+htsserver_SOURCES = htsserver.c htsserver.h htsweb.c htsweb.h \
 	htsurlport.c htsurlport.h
 proxytrack_SOURCES = proxy/main.c \
 	proxy/proxytrack.c proxy/store.c \
@@ -63,21 +60,21 @@ whttrackrun_SCRIPTS = webhttrack
 libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htscache_selftest.c htsdns_selftest.c htsselftest.c \
 	htscatchurl.c htsfilters.c htsftp.c htshash.c coucal/coucal.c \
-	htscmdline.c htshelp.c htslib.c htsurlport.c htscoremain.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 htssitemap.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
+	htsmd5.c htscodec.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 \
 	hts-indextmpl.h htsalias.h htsback.h htsbase.h htssafe.h \
 	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htsselftest.h htscatchurl.h  \
-	htscmdline.h htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
+	htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
 	htsfilters.h htsftp.h htsglobal.h htshash.h coucal/coucal.h \
 	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 htssitemap.h htsproxy.h htszlib.h  \
+	htstools.h htswizard.h htswrap.h htscodec.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 \
@@ -87,7 +84,7 @@ libhttrack_la_LIBADD = $(THREADS_LIBS) $(ZLIB_LIBS) $(BROTLI_LIBS) $(ZSTD_LIBS)
 libhttrack_la_CFLAGS = $(AM_CFLAGS) -DLIBHTTRACK_EXPORTS -DZLIB_CONST
 libhttrack_la_LDFLAGS = $(AM_LDFLAGS) -version-info $(VERSION_INFO)
 
-EXTRA_DIST = httrack.h htsstats.h webhttrack \
+EXTRA_DIST = httrack.h webhttrack \
 		version.rc \
 		libhttrack.rc \
 		httrack.rc \

src/hts-indextmpl.h

@@ -487,6 +487,141 @@ 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

@@ -114,25 +114,6 @@ const char *hts_optalias[][4] = {
    "strip [host/pattern=]key1,key2,... from URLs"},
   {"cookies-file", "-%K", "param1",
    "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",
-   "rotate the WARC archive once a segment passes N bytes (0: single file)"},
-  {"warc-cdx", "-%rc", "single",
-   "write a sorted CDXJ index next to the WARC archive"},
-  {"warc-cdxj", "-%rc", "single", ""},
-  {"wacz", "-%rz", "single",
-   "package the WARC archive, CDXJ index and pages as a WACZ file"},
-  {"single-file", "-%Z", "single",
-   "after the mirror, inline each page's assets as data: URIs"},
-  {"single-file-max-size", "-%Zs", "param1",
-   "per-asset cap for --single-file, in bytes (implies it; default 10485760)"},
   {"why", "-%Y", "param1",
    "explain which filter rule accepts or rejects a URL, then exit"},
   {"pause", "-%G", "param1",

src/htsback.c

@@ -37,8 +37,6 @@ Please visit our Website: http://www.httrack.com
 /* specific definitions */
 #include "htsnet.h"
 #include "htscore.h"
-#include "htswarc.h"
-#include "htschanges.h"
 #include "htsthread.h"
 #include <time.h>
 /* END specific definitions */
@@ -48,6 +46,11 @@ 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
@@ -121,22 +124,6 @@ void back_free(struct_back ** sback) {
    above a normal handshake. The last candidate still gets the full timeout. */
 #define HTS_CONNECT_FALLBACK_TIMEOUT 10
 
-void back_read_ftp_result(FILE *fp, htsblk *r) {
-  size_t j = 0;
-
-  if (fscanf(fp, "%d ", &r->statuscode) != 1)
-    r->statuscode = STATUSCODE_INVALID;
-  // an external helper writes this file: stop at capacity, not at EOF
-  while (j + 1 < sizeof(r->msg)) {
-    const int c = fgetc(fp);
-
-    if (c == EOF)
-      break;
-    r->msg[j++] = (char) c;
-  }
-  r->msg[j] = '\0';
-}
-
 int back_connect_fallback_due(int addr_index, int addr_count, int elapsed,
                               int timeout) {
   int deadline;
@@ -340,61 +327,12 @@ 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
-
-  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) {
@@ -596,54 +534,15 @@ int back_nsoc_overall(const struct_back * sback) {
   return n;
 }
 
-/* Reserved subdirectory holding a mirrored file's temporaries, beside it. */
-#define HTS_TMPDIR "hts-tmp"
-
-/* Build save's temporary as <dir>/hts-tmp/<name>.<ext>. Appending the extension
-   to save instead put it in the mirror namespace, so a site serving <path>.bak
-   had its copy taken as the backup and then unlinked (#774). HTS_FALSE (dest
-   emptied) if it would not fit. Note: utf-8. */
-static hts_boolean back_tmpname(char *dest, size_t size, const char *save,
-                                const char *ext) {
-  const char *const slash = strrchr(save, '/');
-  const int dirlen = slash != NULL ? (int) (slash - save) + 1 : 0;
-
-  if (!slprintfbuff(dest, size, "%.*s" HTS_TMPDIR "/%s.%s", dirlen, save,
-                    slash != NULL ? slash + 1 : save, ext)) {
-    dest[0] = '\0';
-    return HTS_FALSE;
-  }
-  return HTS_TRUE;
-}
-
-/* Note: utf-8 */
-void back_tmpdir_drop(const char *tmp) {
-  char BIGSTK dir[HTS_URLMAXSIZE * 2];
-  const char *slash;
-
-  if (tmp == NULL || (slash = strrchr(tmp, '/')) == NULL)
-    return;
-  if (!strclipbuff(dir, sizeof(dir), tmp))
-    return;
-  dir[slash - tmp] = '\0';
-  slash = strrchr(dir, '/');
-  if (strcmp(slash != NULL ? slash + 1 : dir, HTS_TMPDIR) == 0)
-    (void) RMDIR(dir);
-}
-
 /* generate temporary file on lien_back */
 /* Note: utf-8 */
 static int create_back_tmpfile(httrackp *opt, lien_back *const back,
                                const char *ext) {
   // do not use tempnam() but a regular filename
   back->tmpfile_buffer[0] = '\0';
-  if (back->url_sav[0] != '\0') {
-    if (!back_tmpname(back->tmpfile_buffer, sizeof(back->tmpfile_buffer),
-                      back->url_sav, ext)) {
-      hts_log_print(opt, LOG_WARNING, "temporary filename too long for %s",
-                    back->url_sav);
-      return -1;
-    }
+  if (back->url_sav != NULL && back->url_sav[0] != '\0') {
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.%s",
+             back->url_sav, ext);
     back->tmpfile = back->tmpfile_buffer;
     if (structcheck(back->tmpfile) != 0) {
       hts_log_print(opt, LOG_WARNING, "can not create directory to %s",
@@ -651,15 +550,8 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
       return -1;
     }
   } else {
-    /* truncation here would collide distinct tmpnameid's onto one name */
-    if (!sprintfbuff(back->tmpfile_buffer, "%s/tmp%d.%s",
-                     StringBuff(opt->path_html_utf8), opt->state.tmpnameid++,
-                     ext)) {
-      hts_log_print(opt, LOG_WARNING, "temporary filename too long in %s",
-                    StringBuff(opt->path_html_utf8));
-      back->tmpfile_buffer[0] = '\0';
-      return -1;
-    }
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s/tmp%d.%s",
+             StringBuff(opt->path_html_utf8), opt->state.tmpnameid++, ext);
     back->tmpfile = back->tmpfile_buffer;
   }
   /* OK */
@@ -667,62 +559,24 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
   return 0;
 }
 
-/* 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);
-      /* Another slot sharing the directory may have removed it between the
-         structcheck above and the rename: recreate it and try once more. */
-      if (!saved && structcheck(back->tmpfile) == 0)
-        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;
-  }
-}
-
-hts_boolean back_finalize_backup(httrackp *opt, lien_back *const back,
-                                 hts_boolean commit) {
-  const hts_boolean wanted = commit;
-
-  if (back->tmpfile == NULL || back->r.compressed)
+/* 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;
-  /* Nothing to commit to: filecreate() can fail after the backup was taken,
-     and dropping it then loses both copies (#775). */
-  if (commit && !fexist_utf8(back->url_sav)) {
-    hts_log_print(opt, LOG_WARNING, "%s was never created; restoring %s",
-                  back->url_sav, back->tmpfile);
-    commit = HTS_FALSE;
-  }
+  (void) UNLINK(dst);
+  return RENAME(src, dst) == 0 ? HTS_TRUE : HTS_FALSE;
+}
+
+/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
+   existing file moved the good copy to back->tmpfile before truncating url_sav.
+   commit keeps the new file and drops the backup; else restore it so an aborted
+   transfer leaves the previous copy intact. Skips the zlib .z temp. */
+static void back_finalize_backup(httrackp *opt, lien_back *const back,
+                                 const hts_boolean commit) {
+  if (back->tmpfile == NULL || back->r.compressed)
+    return;
   if (commit) {
     (void) UNLINK(back->tmpfile); /* new copy is good; drop the backup */
-    back_tmpdir_drop(back->tmpfile);
   } else {
     if (back->r.out != NULL) {
       fclose(back->r.out);
@@ -730,15 +584,12 @@ hts_boolean back_finalize_backup(httrackp *opt, lien_back *const back,
     }
     /* On failure keep the backup: an orphaned temp beats losing the good copy.
      */
-    if (!hts_rename_over(opt, back->tmpfile, back->url_sav))
+    if (!replace_file(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);
-    else
-      back_tmpdir_drop(back->tmpfile);
   }
   back->tmpfile = NULL;
-  return commit == wanted ? HTS_TRUE : HTS_FALSE;
 }
 
 // objet (lien) téléchargé ou transféré depuis le cache
@@ -840,29 +691,13 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                     hts_codec_parse(back[p].r.contentencoding);
                 /* Never decode over url_sav: a failed decode would destroy the
                    copy an --update re-fetch is supposed to refresh (#557). */
-                char BIGSTK unpacked[HTS_URLMAXSIZE * 2];
+                char BIGSTK unpacked[HTS_URLMAXSIZE * 2 + 4]; // room for ".u"
                 LLint size;
 
-                /* fits whenever the .z temp it decodes from did */
-                if (!back_tmpname(unpacked, sizeof(unpacked), back[p].url_sav,
-                                  "u")) {
-                  back[p].r.statuscode = STATUSCODE_INVALID;
-                  strcpybuff(back[p].r.msg, "Error when decompressing (the "
-                                            "temporary filename is too long)");
-                  /* as the decode-failure branch below: never let the coded
-                     bytes be committed as the page */
-                  if (!back[p].r.is_write)
-                    deleteaddr(&back[p].r);
-                } else if ((size = hts_codec_unpack(codec, back[p].tmpfile,
-                                                    unpacked)) >= 0) {
+                snprintf(unpacked, sizeof(unpacked), "%s.u", back[p].url_sav);
+                if ((size = hts_codec_unpack(codec, back[p].tmpfile,
+                                             unpacked)) >= 0) {
                   back[p].r.size = back[p].r.totalsize = size;
-                  if (back[p].r.is_write) {
-                    /* Sample the previous copy now: the rename below replaces
-                       it, and file_notify() only fires once it is gone. */
-                    hts_changes_notify(
-                        opt, back[p].url_adr, back[p].url_fil, back[p].url_sav,
-                        HTS_TRUE, back[p].r.notmodified ? HTS_TRUE : HTS_FALSE);
-                  }
                   if (!back[p].r.is_write) {
                     // fichier -> mémoire ; le fichier est écrit plus tard
                     deleteaddr(&back[p].r);
@@ -873,7 +708,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                                  "Read error when decompressing");
                     }
                     UNLINK(unpacked);
-                  } else if (hts_rename_over(opt, unpacked, back[p].url_sav)) {
+                  } else if (replace_file(unpacked, back[p].url_sav)) {
                     /* The temp bypassed filecreate(), which is what chmods. */
 #ifndef _WIN32
                     chmod(back[p].url_sav, HTS_ACCESS_FILE);
@@ -914,21 +749,9 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                     fexist_utf8(back[p].url_sav))
                   filenote(&opt->state.strc, back[p].url_sav, NULL);
               }
-              /* Keep the compressed spool so the WARC record stores the body
-                 verbatim (Content-Encoding preserved) instead of unlinking it.
-               */
-              if (StringNotEmpty(opt->warc_file)) {
-                warc_adopt_rawspool(&back[p].r, back[p].tmpfile);
-                if (back[p].r.warc_rawpath != NULL)
-                  back[p].tmpfile =
-                      NULL; /* adopted: freed via warc_free_request */
-              }
               /* ensure that no remaining temporary file exists */
-              if (back[p].tmpfile != NULL) {
-                unlink(back[p].tmpfile);
-                back_tmpdir_drop(back[p].tmpfile); /* the .u went with it */
-                back[p].tmpfile = NULL;
-              }
+              unlink(back[p].tmpfile);
+              back[p].tmpfile = NULL;
             }
             // stats
             HTS_STAT.total_packed += back[p].compressed_size;
@@ -939,14 +762,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
         }
         /* Body fully received: keep the freshly written url_sav, drop the
            backup of the previous copy. */
-        if (!back_finalize_backup(opt, &back[p], HTS_TRUE)) {
-          /* The previous copy is back because the new one was never created;
-             caching this response's validators against it would pin the stale
-             body on every later --update. */
-          if (fexist_utf8(back[p].url_sav))
-            filenote(&opt->state.strc, back[p].url_sav, NULL);
-          return -1;
-        }
+        back_finalize_backup(opt, &back[p], HTS_TRUE);
         /* Write mode to disk */
         if (back[p].r.is_write && back[p].r.adr != NULL) {
           freet(back[p].r.adr);
@@ -1059,7 +875,8 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
               HTS_STAT.stat_bytes += back[p].r.size;
               HTS_STAT.stat_files++;
               hts_log_print(opt, LOG_TRACE, "added file %s%s => %s",
-                            back[p].url_adr, back[p].url_fil, back[p].url_sav);
+                            back[p].url_adr, back[p].url_fil,
+                            back[p].url_sav != NULL ? back[p].url_sav : "");
             }
             if ((!back[p].r.notmodified) && (opt->is_update)) {
               HTS_STAT.stat_updated_files++;    // page modifiée
@@ -1162,10 +979,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
         // status finished callback
         RUN_CALLBACK1(opt, xfrstatus, &back[p]);
 
-        // WARC archive of the transaction (request + response/revisit)
-        if (StringNotEmpty(opt->warc_file))
-          warc_write_backtransaction(opt, &back[p]);
-
         return 0;
       } else {                  // testmode
         if (back[p].r.statuscode / 100 >= 3) {  /* Store 3XX, 4XX, 5XX test response codes, but NOT 2XX */
@@ -1179,14 +992,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
   /* Aborted, error, or not ready: url_sav (if written) is broken; restore the
      previous copy from the backup. */
   back_finalize_backup(opt, &back[p], HTS_FALSE);
-  /* 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;
 }
 
@@ -1250,11 +1055,6 @@ void back_copy_static(const lien_back * src, lien_back * dst) {
   dst->r.soc = INVALID_SOCKET;
   dst->r.adr = NULL;
   dst->r.headers = NULL;
-  dst->r.warc_reqhdr = NULL;
-  dst->r.warc_resphdr = NULL;
-  dst->r.warc_rawpath =
-      NULL; /* the spool stays owned by src (no double-unlink) */
-  dst->r.warc_truncated = 0;
   dst->r.out = NULL;
   dst->r.location = dst->location_buffer;
   dst->r.fp = NULL;
@@ -1318,10 +1118,6 @@ int back_unserialize(FILE * fp, lien_back ** dst) {
     (*dst)->chunk_adr = NULL;
     (*dst)->r.adr = NULL;
     (*dst)->r.out = NULL;
-    (*dst)->r.warc_reqhdr = NULL;
-    (*dst)->r.warc_resphdr = NULL;
-    (*dst)->r.warc_rawpath = NULL;
-    (*dst)->r.warc_truncated = 0;
     (*dst)->r.location = (*dst)->location_buffer;
     (*dst)->r.fp = NULL;
     (*dst)->r.soc = INVALID_SOCKET;
@@ -1782,7 +1578,6 @@ int back_clear_entry(lien_back * back) {
     // only for security
     if (back->tmpfile && back->tmpfile[0] != '\0') {
       (void) unlink(back->tmpfile);
-      back_tmpdir_drop(back->tmpfile);
       back->tmpfile = NULL;
     }
     // headers
@@ -1790,7 +1585,6 @@ int back_clear_entry(lien_back * back) {
       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;
@@ -1823,15 +1617,14 @@ int back_add_if_not_exists(struct_back * sback, httrackp * opt,
   back_clean(opt, cache, sback);        /* first cleanup the backlog to ensure that we have some entry left */
   if (!back_exist(sback, opt, adr, fil, save)) {
     return back_add(sback, opt, cache, adr, fil, save, referer_adr, referer_fil,
-                    test, HTS_FALSE);
+                    test);
   }
   return 0;
 }
 
-int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
-             const char *adr, const char *fil, const char *save,
-             const char *referer_adr, const char *referer_fil, int test,
-             hts_boolean refetch_whole) {
+int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char *adr,
+             const char *fil, const char *save, const char *referer_adr, const char *referer_fil,
+             int test) {
   lien_back *const back = sback->lnk;
   const int back_max = sback->count;
   int p = 0;
@@ -1908,12 +1701,6 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
     else if (strcmp(back[p].url_sav, BACK_ADD_TEST2) == 0)      // test en GET
       back[p].head_request = 2; // test en get
 
-    /* Forced whole refetch (#581): drop the stale temp-ref and skip the resume
-       branches below, so a surviving partial can't Range-loop. */
-    if (refetch_whole) {
-      url_savename_refname_remove(opt, adr, fil);
-    }
-
     /* Stop requested - abort backing */
     /* For update mode: second check after cache lookup not to lose all previous cache data ! */
     if (opt->state.stop && !opt->is_update) {
@@ -2169,9 +1956,8 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
         }
       }
       /* Not in cache ; maybe in temporary cache ? Warning: non-movable
-         "url_sav" (skipped on a forced whole refetch, #581) */
-      else if (!refetch_whole &&
-               back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
+         "url_sav" */
+      else if (back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
         const LLint file_size = fsize_utf8(itemback->url_sav);
 
         /* Found file on disk */
@@ -2205,9 +1991,8 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
         freet(itemback);        /* delete item */
         itemback = NULL;
       }
-      /* Not in cache or temporary cache ; found on disk ? (hack)
-         (skipped on a forced whole refetch, #581) */
-      else if (!refetch_whole && fexist_utf8(save)) {
+      /* Not in cache or temporary cache ; found on disk ? (hack) */
+      else if (fexist_utf8(save)) {
         const LLint sz = fsize_utf8(save);
 
         // Bon, là il est possible que le fichier ait été partiellement transféré
@@ -2482,24 +2267,26 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
               && slot_can_be_finalized(opt, &back[i]);
             int may_serialize = slot_can_be_cached_on_disk(&back[i]);
 
-            hts_log_print(
-                opt, LOG_DEBUG,
-                "back[%03d]: may_clean=%d, may_finalize_disk=%d, "
-                "may_serialize=%d:" LF "\t"
-                "finalized(%d), status(%d), locked(%d), delayed(%d), "
-                "test(%d), " LF "\t"
-                "statuscode(%d), size(%d), is_write(%d), may_hypertext(%d), " LF
-                "\t"
-                "contenttype(%s), url(%s%s), save(%s)",
-                i, may_clean, may_finalize, may_serialize, back[i].finalized,
-                back[i].status, back[i].locked, IS_DELAYED_EXT(back[i].url_sav),
-                back[i].testmode, back[i].r.statuscode, (int) back[i].r.size,
-                back[i].r.is_write,
-                may_be_hypertext_mime(opt, back[i].r.contenttype,
-                                      back[i].url_fil),
-                /* */
-                back[i].r.contenttype, back[i].url_adr, back[i].url_fil,
-                back[i].url_sav);
+            hts_log_print(opt, LOG_DEBUG,
+                          "back[%03d]: may_clean=%d, may_finalize_disk=%d, may_serialize=%d:"
+                          LF "\t"
+                          "finalized(%d), status(%d), locked(%d), delayed(%d), test(%d), "
+                          LF "\t"
+                          "statuscode(%d), size(%d), is_write(%d), may_hypertext(%d), "
+                          LF "\t" "contenttype(%s), url(%s%s), save(%s)", i,
+                          may_clean, may_finalize, may_serialize,
+                          back[i].finalized, back[i].status, back[i].locked,
+                          IS_DELAYED_EXT(back[i].url_sav), back[i].testmode,
+                          back[i].r.statuscode, (int) back[i].r.size,
+                          back[i].r.is_write, may_be_hypertext_mime(opt,
+                                                                    back[i].r.
+                                                                    contenttype,
+                                                                    back[i].
+                                                                    url_fil),
+                          /* */
+                          back[i].r.contenttype, back[i].url_adr,
+                          back[i].url_fil,
+                          back[i].url_sav ? back[i].url_sav : "<null>");
           }
         }
       }
@@ -2713,19 +2500,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
     for (i = 0; i < (unsigned int) back_max; i++) {
       if (back[i].status > 0 && back[i].status < STATUS_FTP_TRANSFER) {
-        /* A cap-truncated body is deliberate, not broken: archive what arrived
-           with WARC-Truncated before the abort overwrites the slot's real 2xx
-           status. HTTrack still treats the slot as incomplete afterwards. */
-        if (StringNotEmpty(opt->warc_file) && back[i].r.statuscode > 0 &&
-            back[i].r.warc_resphdr != NULL && back[i].r.size > 0 &&
-            !(back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))) {
-          if (back[i].r.is_write && back[i].r.out != NULL)
-            fflush(back[i].r.out);
-          back[i].r.warc_truncated = (limit == HTS_MIRROR_LIMIT_SIZE)
-                                         ? WARC_TRUNC_LENGTH
-                                         : WARC_TRUNC_TIME;
-          warc_write_backtransaction(opt, &back[i]);
-        }
         if (back[i].r.soc != INVALID_SOCKET) {
           deletehttp(&back[i].r);
         }
@@ -3035,8 +2809,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
               // new session
               back[i].r.ssl_con = SSL_new(openssl_ctx);
               if (back[i].r.ssl_con) {
-                /* non-const twin: the OpenSSL macro casts the qualifier away */
-                char *hostname = jump_protocol(back[i].url_adr);
+                const char* hostname = jump_protocol_const(back[i].url_adr);
                 // some servers expect the hostname on the clienthello (SNI TLS extension)
                 SSL_set_tlsext_host_name(back[i].r.ssl_con, hostname);
                 SSL_clear(back[i].r.ssl_con);
@@ -3128,7 +2901,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
               back[i].r.msg[0] = '\0';
               strncatbuff(back[i].r.msg, tmp, sizeof(back[i].r.msg) - 2);
               if (!strnotempty(back[i].r.msg)) {
-                htsblk_failf(&back[i].r, "SSL/TLS error %d", err_code);
+                sprintf(back[i].r.msg, "SSL/TLS error %d", err_code);
               }
               deletehttp(&back[i].r);
               back[i].r.soc = INVALID_SOCKET;
@@ -3201,7 +2974,16 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
             FOPEN(fconcat(OPT_GET_BUFF(opt), back[i].location_buffer, ".ok"),
                   "rb");
           if (fp) {
-            back_read_ftp_result(fp, &back[i].r);
+            int j = 0;
+
+            fscanf(fp, "%d ", &(back[i].r.statuscode));
+            while(!feof(fp)) {
+              int c = fgetc(fp);
+
+              if (c != EOF)
+                back[i].r.msg[j++] = c;
+            }
+            back[i].r.msg[j++] = '\0';
             fclose(fp);
             UNLINK(fconcat(OPT_GET_BUFF(opt), back[i].location_buffer, ".ok"));
             strcpybuff(fconcat
@@ -3300,7 +3082,20 @@ 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;
-                              back_refetch_backup(opt, &back[i]);
+                              /* Re-fetch over an existing file (#77 follow-up):
+                                 move the good copy aside before truncating it
+                                 so an aborted transfer can restore it. url_sav
+                                 is still written normally (file list intact).
+                               */
+                              back[i].tmpfile = NULL;
+                              if (fexist_utf8(back[i].url_sav)) {
+                                if (create_back_tmpfile(opt, &back[i], "bak") !=
+                                        0 ||
+                                    RENAME(back[i].url_sav, back[i].tmpfile) !=
+                                        0) {
+                                  back[i].tmpfile = NULL;
+                                }
+                              }
                               if ((back[i].r.out =
                                    filecreate(&opt->state.strc,
                                               back[i].url_sav)) == NULL) {
@@ -3489,11 +3284,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                   deleteaddr(&back[i].r);
                   if (back[i].r.size < back[i].r.totalsize)
                     back[i].r.statuscode = STATUSCODE_CONNERROR;        // recatch
-                  htsblk_failf(&back[i].r,
-                               "Incorrect length (" LLintP " Bytes, " LLintP
-                               " expected)",
-                               (LLint) back[i].r.size,
-                               (LLint) back[i].r.totalsize);
+                  sprintf(back[i].r.msg,
+                          "Incorrect length (" LLintP " Bytes, " LLintP
+                          " expected)", (LLint) back[i].r.size,
+                          (LLint) back[i].r.totalsize);
                 } else {
                   // Un warning suffira..
                   hts_log_print(opt, LOG_WARNING,
@@ -3828,10 +3622,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     deleteaddr(&back[i].r);
                     back[i].r.headers = block;
                   }
-                  // Stash the raw response headers for WARC (deletehttp frees
-                  // r.headers when the socket closes, before back_finalize)
-                  if (StringNotEmpty(opt->warc_file))
-                    warc_stash_response(&back[i].r, back[i].r.headers);
 
                   /* 
                      Status code and header-response hacks
@@ -4057,8 +3847,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     deletehttp(&back[i].r);
                     back[i].r.soc = INVALID_SOCKET;
                     back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                    back[i].r.refetch_wholefile =
-                        HTS_TRUE; // retry whole, no Range (#581)
                     strcpybuff(back[i].r.msg,
                                "Bogus 304 on resume, restarting");
                     back[i].status = STATUS_READY;
@@ -4330,9 +4118,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                         }
                         back[i].r.soc = INVALID_SOCKET;
                         back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                        // the resume was rejected: the retry must GET the whole
-                        // file, never re-Range a surviving partial/ref (#581)
-                        back[i].r.refetch_wholefile = HTS_TRUE;
                         if (strnotempty(back[i].r.msg))
                           strcpybuff(back[i].r.msg,
                                      "Error attempting to solve status 206 (partial file)");

src/htsback.h

@@ -74,10 +74,6 @@ void back_free(struct_back ** sback);
 // backing
 #define BACK_ADD_TEST "(dummy)"
 #define BACK_ADD_TEST2 "(dummy2)"
-/* Parse an external FTP helper's "<statuscode> <message>" result file into r,
-   clipping the message to r->msg. */
-void back_read_ftp_result(FILE *fp, htsblk *r);
-
 int back_index(httrackp * opt, struct_back * sback, const char *adr, const char *fil,
                const char *sav);
 int back_available(const struct_back * sback);
@@ -87,12 +83,9 @@ HTS_INLINE int back_exist(struct_back * sback, httrackp * opt, const char *adr,
                           const char *fil, const char *sav);
 int back_nsoc(const struct_back * sback);
 int back_nsoc_overall(const struct_back * sback);
-/* refetch_whole: force a whole-file GET, ignoring any partial/temp-ref resume
-   (set when a prior 206 was rejected as unusable, #581). */
-int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
-             const char *adr, const char *fil, const char *save,
-             const char *referer_adr, const char *referer_fil, int test,
-             hts_boolean refetch_whole);
+int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char *adr,
+             const char *fil, const char *save, const char *referer_adr, const char *referer_fil,
+             int test);
 int back_add_if_not_exists(struct_back * sback, httrackp * opt,
                            cache_back * cache, const char *adr, const char *fil, const char *save,
                            const char *referer_adr, const char *referer_fil, int test);
@@ -139,24 +132,6 @@ 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);
-/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
-   existing file moved the good copy to back->tmpfile before truncating url_sav.
-   commit keeps the new file and drops the backup, unless url_sav was never
-   created; else restore it so an aborted transfer leaves the previous copy
-   intact. Skips the zlib .z temp. HTS_FALSE when a requested commit had to
-   restore instead: the caller then holds the OLD body and must not cache this
-   response's validators against it. */
-hts_boolean back_finalize_backup(httrackp *opt, lien_back *const back,
-                                 hts_boolean commit);
-/* Remove the reserved directory a temporary sat in, once the last slot sharing
-   it is done; a non-empty one just refuses. No-op outside that directory. */
-void back_tmpdir_drop(const char *tmp);
-/* -#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/htsbacktrace.c

@@ -1,238 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 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: crash backtrace printer                                 */
-/* Author: Xavier Roche                                          */
-/* ------------------------------------------------------------ */
-
-/* Before every header: glibc gates dladdr() on it. */
-#if defined(__linux) && !defined(_GNU_SOURCE)
-#define _GNU_SOURCE
-#endif
-
-#include "htsbacktrace.h"
-
-#include "htsglobal.h"
-
-#include <stdlib.h>
-#include <string.h>
-#ifdef _WIN32
-#include <io.h> /* write */
-#endif
-#ifdef HAVE_UNISTD_H
-#include <unistd.h>
-#endif
-#if (defined(__linux) && defined(HAVE_EXECINFO_H))
-#include <dlfcn.h>
-#include <errno.h>
-#include <execinfo.h>
-#include <signal.h>
-#include <time.h>
-#include <sys/wait.h>
-#define USES_BACKTRACE
-#endif
-
-#ifdef USES_BACKTRACE
-#define BT_MAX_FRAMES 64     /* frames we try to name */
-#define BT_MAX_MODULES 8     /* distinct modules, one child each */
-#define BT_HEX_SIZE 19       /* "0x" + 16 nibbles + NUL */
-#define BT_PATH_SIZE 1024    /* module path; longer is skipped */
-#define BT_WAIT_TICKS 300    /* 10ms ticks, shared: cap a slow child */
-#define BT_NO_SYMBOLIZER 127 /* child exit: execvp() found none */
-
-static hts_boolean symbolize_crash = HTS_TRUE;
-
-/* "0x"-prefixed hex: the handler must stay stdio-free. */
-static void print_hex(char *buffer, uintptr_t value) {
-  static const char digits[] = "0123456789abcdef";
-  size_t i = 2, a, b;
-
-  buffer[0] = '0';
-  buffer[1] = 'x';
-  do {
-    buffer[i++] = digits[value & 0xf];
-    value >>= 4;
-  } while (value != 0);
-  buffer[i] = '\0';
-  for (a = 2, b = i - 1; a < b; a++, b--) {
-    const char c = buffer[a];
-
-    buffer[a] = buffer[b];
-    buffer[b] = c;
-  }
-}
-
-/* HTS_FALSE if src does not fit: a truncated module path would point the
-   symbolizer at the wrong file. */
-static hts_boolean copy_bounded(char *dest, size_t size, const char *src) {
-  size_t i;
-
-  for (i = 0; i < size - 1 && src[i] != '\0'; i++) {
-    dest[i] = src[i];
-  }
-  dest[i] = '\0';
-  return src[i] == '\0' ? HTS_TRUE : HTS_FALSE;
-}
-
-/* Run the symbolizer on argv, output on fd, within *budget ticks. HTS_FALSE
-   only if none could be run at all; otherwise silent, the raw trace stands. */
-static hts_boolean spawn_symbolizer(char **argv, int fd, int *budget) {
-  const pid_t pid = fork();
-  int status = 0;
-
-  if (pid == -1)
-    return HTS_FALSE;
-  if (pid == 0) {
-    static char llvm_prog[] = "llvm-symbolizer";
-    static char llvm_opts[] = "-p";
-
-    dup2(fd, 1); /* both symbolizers write on stdout */
-    execvp(argv[0], argv);
-    argv[0] = llvm_prog; /* an LLVM-only install ships no addr2line */
-    argv[1] = llvm_opts;
-    execvp(argv[0], argv);
-    _exit(BT_NO_SYMBOLIZER);
-  }
-  for (; *budget > 0; (*budget)--) {
-    const struct timespec tick = {0, 10 * 1000 * 1000};
-    const pid_t reaped = waitpid(pid, &status, WNOHANG);
-
-    if (reaped == pid)
-      return WIFEXITED(status) && WEXITSTATUS(status) == BT_NO_SYMBOLIZER
-                 ? HTS_FALSE
-                 : HTS_TRUE;
-    if (reaped == -1 && errno != EINTR)
-      return HTS_TRUE;
-    nanosleep(&tick, NULL);
-  }
-  kill(pid, SIGKILL);
-  waitpid(pid, NULL, 0);
-  return HTS_TRUE;
-}
-
-/* Name the frames backtrace_symbols_fd() leaves as module+offset:
-   -fvisibility=hidden keeps them out of .dynsym, but DWARF has them. dladdr()
-   is not formally async-signal-safe; accepted, this path is already fatal. */
-static void symbolize_backtrace(void *const *stack, int size, int fd) {
-  static char prog[] = "addr2line";
-  static char opts[] = "-Cfipa";
-  static char dashe[] = "-e";
-  char hex[BT_MAX_FRAMES][BT_HEX_SIZE];
-  const void *base[BT_MAX_FRAMES];
-  const char *name[BT_MAX_FRAMES];
-  hts_boolean grouped[BT_MAX_FRAMES];
-  char module[BT_PATH_SIZE];
-  char *argv[4 + BT_MAX_FRAMES + 1];
-  int budget = BT_WAIT_TICKS;
-  int i, spawned;
-
-  if (size > BT_MAX_FRAMES)
-    size = BT_MAX_FRAMES;
-
-  for (i = 0; i < size; i++) {
-    Dl_info info;
-
-    grouped[i] = HTS_TRUE; /* skipped unless dladdr() places the frame */
-    if (dladdr(stack[i], &info) == 0 || info.dli_fname == NULL ||
-        info.dli_fname[0] == '\0')
-      continue;
-    base[i] = info.dli_fbase;
-    name[i] = info.dli_fname;
-    print_hex(hex[i], (uintptr_t) ((const char *) stack[i] -
-                                   (const char *) info.dli_fbase));
-    grouped[i] = HTS_FALSE;
-  }
-
-  /* One child per module: addr2line takes a single -e. Each frame is claimed
-     once, so argc cannot exceed argv[]. */
-  for (spawned = 0; spawned < BT_MAX_MODULES; spawned++) {
-    int first, j, argc = 0;
-
-    for (first = 0; first < size && grouped[first]; first++)
-      ;
-    if (first >= size)
-      break;
-    argv[argc++] = prog;
-    argv[argc++] = opts;
-    argv[argc++] = dashe;
-    argv[argc++] = module;
-    for (j = first; j < size; j++) {
-      if (grouped[j] || base[j] != base[first])
-        continue;
-      grouped[j] = HTS_TRUE;
-      argv[argc++] = hex[j];
-    }
-    argv[argc] = NULL;
-    /* access(): skip pseudo-modules like linux-vdso, which have no file and
-       would draw nothing but an addr2line complaint. */
-    if (copy_bounded(module, sizeof(module), name[first]) &&
-        access(module, R_OK) == 0) {
-      const size_t len = strlen(module);
-
-      /* addr2line -a prints offsets only: say which module they are in. */
-      (void) (write(fd, module, len) == (ssize_t) len);
-      (void) (write(fd, ":\n", 2) == 2);
-      if (!spawn_symbolizer(argv, fd, &budget))
-        break; /* no symbolizer: stop at one header */
-    }
-  }
-}
-#endif
-
-void hts_backtrace_init(void) {
-#ifdef USES_BACKTRACE
-  symbolize_crash =
-      getenv("HTTRACK_NO_SYMBOLIZE") == NULL ? HTS_TRUE : HTS_FALSE;
-#endif
-}
-
-void hts_print_backtrace(int fd) {
-#ifdef USES_BACKTRACE
-  void *stack[256];
-  const int size = backtrace(stack, sizeof(stack) / sizeof(stack[0]));
-
-  /* A fault inside the handler lands back here: symbolizing twice interleaves
-     two traces on fd and spends a second budget. */
-  static volatile sig_atomic_t entered = 0;
-
-  if (size != 0) {
-    backtrace_symbols_fd(stack, size, fd);
-    if (symbolize_crash && entered == 0) {
-      entered = 1;
-      symbolize_backtrace(stack, size, fd);
-      entered = 0;
-    }
-  }
-#else
-  const char msg[] = "No stack trace available on this OS :(\n";
-
-  if (write(fd, msg, sizeof(msg) - 1) != sizeof(msg) - 1) {
-    /* sorry GCC */
-  }
-#endif
-}

src/htsbacktrace.h

@@ -1,45 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 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: crash backtrace printer                                 */
-/* Author: Xavier Roche                                          */
-/* ------------------------------------------------------------ */
-
-#ifndef HTSBACKTRACE_DEFH
-#define HTSBACKTRACE_DEFH
-
-/* Sample HTTRACK_NO_SYMBOLIZE before any crash: getenv() is not signal-safe.
-   Call once, from the process that installs the fatal-signal handlers. */
-void hts_backtrace_init(void);
-
-/* Write the calling thread's stack to fd, callable from a fatal signal handler:
-   raw frames first, then whatever an external symbolizer can name. Allocates
-   nothing; prints a one-line notice where the OS has no backtrace(). */
-void hts_print_backtrace(int fd);
-
-#endif

src/htsbauth.c

@@ -39,9 +39,6 @@ Please visit our Website: http://www.httrack.com
 #include "htsglobal.h"
 #include "htslib.h"
 #include "htscore.h"
-#ifdef _WIN32
-#include "htscharset.h" /* hts_pathToUCS2, hts_convertUCS2StringToUTF8 */
-#endif
 
 /* END specific definitions */
 
@@ -203,36 +200,28 @@ char *cookie_nextfield(char *a) {
   return a;
 }
 
-// Read cookies.txt (+ copied IE cookies *@*.txt on Windows); !=0 on error.
+// lire cookies.txt
+// lire également (Windows seulement) les *@*.txt (cookies IE copiés)
+// !=0 : erreur
 int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
   char catbuff[CATBUFF_SIZE];
   char buffer[8192];
 
-  // Merge any IE cookies first
+  // Fusionner d'abord les éventuels cookies IE
 #ifdef _WIN32
   {
-    WIN32_FIND_DATAW find;
+    WIN32_FIND_DATAA find;
     HANDLE h;
-    char pth[HTS_URLMAXSIZE];
-    LPWSTR wpth;
+    char pth[MAX_PATH + 32];
 
     strcpybuff(pth, fpath);
     strcatbuff(pth, "*@*.txt");
-    // Wide glob so a long or non-ASCII IE-cookie folder is scanned (#133).
-    wpth = hts_pathToUCS2(pth);
-    h = wpth != NULL ? FindFirstFileW(wpth, &find) : INVALID_HANDLE_VALUE;
-    freet(wpth);
+    h = FindFirstFileA((char *) pth, &find);
     if (h != INVALID_HANDLE_VALUE) {
       do {
         if (!(find.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY))
           if (!(find.dwFileAttributes & FILE_ATTRIBUTE_SYSTEM)) {
-            // cFileName is UTF-16: convert to UTF-8 so the mirror path and
-            // file wrappers stay UTF-8 (no CP_ACP mojibake).
-            char *u = hts_convertUCS2StringToUTF8(find.cFileName, -1);
-            FILE *fp =
-                u != NULL
-                    ? FOPEN(fconcat(catbuff, sizeof(catbuff), fpath, u), "rb")
-                    : NULL;
+            FILE *fp = fopen(fconcat(catbuff, sizeof(catbuff), fpath, find.cFileName), "rb");
 
             if (fp) {
               char cook_name[256];
@@ -240,9 +229,11 @@ int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
               char domainpathpath[512];
               char dummy[512];
 
-              lien_adrfil af; // host + path (/)
+              //
+              lien_adrfil af;   // chemin (/)
               int cookie_merged = 0;
 
+              //
               // Read all cookies
               while(!feof(fp)) {
                 cook_name[0] = cook_value[0] = domainpathpath[0]
@@ -271,11 +262,10 @@ int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
               }
               fclose(fp);
               if (cookie_merged)
-                UNLINK(fconcat(catbuff, sizeof(catbuff), fpath, u));
+                remove(fconcat(catbuff, sizeof(catbuff), fpath, find.cFileName));
             }                   // if fp
-            freet(u);
           }
-      } while (FindNextFileW(h, &find));
+      } while(FindNextFileA(h, &find));
       FindClose(h);
     }
   }
@@ -283,7 +273,7 @@ int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
 
   // Ensuite, cookies.txt
   {
-    FILE *fp = FOPEN(fconcat(catbuff, sizeof(catbuff), fpath, name), "rb");
+    FILE *fp = fopen(fconcat(catbuff, sizeof(catbuff), fpath, name), "rb");
 
     if (fp) {
       char BIGSTK line[8192];
@@ -325,7 +315,7 @@ int cookie_save(t_cookie * cookie, const char *name) {
   if (strnotempty(cookie->data)) {
     char BIGSTK line[8192];
 #ifdef _WIN32
-    FILE *fp = FOPEN(fconv(catbuff, sizeof(catbuff), name), "wb");
+    FILE *fp = fopen(fconv(catbuff, sizeof(catbuff), name), "wb");
 #else
     const int fd = open(fconv(catbuff, sizeof(catbuff), name),
                         O_WRONLY | O_CREAT | O_TRUNC, HTS_PROTECT_FILE);

src/htscache.c

@@ -142,12 +142,10 @@ struct cache_back_zip_entry {
   int compressionMethod;
 };
 
-/* A corrupt cache can carry a field wider than ours; clipping it keeps the
-   entry, where aborting would take the crawl down. */
 #define ZIP_READFIELD_STRING(line, value, refline, refvalue, refvalue_size)    \
   do {                                                                         \
     if (line[0] != '\0' && strfield2(line, refline)) {                         \
-      (void) strclipbuff(refvalue, refvalue_size, value);                      \
+      strlcpybuff(refvalue, value, refvalue_size);                             \
       line[0] = '\0';                                                          \
     }                                                                          \
   } while (0)
@@ -631,8 +629,8 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                 // File exists on disk with declared cache name (this is expected!)
                 if (fexist_utf8(fconv(catbuff, sizeof(catbuff), previous_save))) {       // un fichier existe déja
                   // Expected size ?
-                  const LLint fsize = fsize_utf8(
-                      fconv(catbuff, sizeof(catbuff), previous_save));
+                  const size_t fsize =
+                    fsize_utf8(fconv(catbuff, sizeof(catbuff), previous_save));
                   if (fsize == r.size) {
                     // Target name is the previous name, and the file looks good: nothing to do!
                     if (strcmp(previous_save, target_save) == 0) {
@@ -668,8 +666,7 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                 // Suppose a broken mirror, with a file being renamed: OK
                 else if (fexist_utf8(fconv(catbuff, sizeof(catbuff), target_save))) {
                   // Expected size ?
-                  const LLint fsize =
-                      fsize_utf8(fconv(catbuff, sizeof(catbuff), target_save));
+                  const size_t fsize = fsize_utf8(fconv(catbuff, sizeof(catbuff), target_save));
 
                   if (fsize == r.size) {
                     // So far so good
@@ -855,6 +852,13 @@ 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,
@@ -957,35 +961,6 @@ htsblk *cache_header(httrackp * opt, cache_back * cache, const char *adr,
     return NULL;
 }
 
-const char *cache_repair(httrackp *opt, const char *name,
-                         unsigned long *entries, unsigned long *bytes) {
-  char BIGSTK repairname[HTS_URLMAXSIZE * 2];
-  unzFile zip;
-
-  *entries = 0;
-  *bytes = 0;
-  if (!slprintfbuff(repairname, sizeof(repairname), "%s%s",
-                    StringBuff(opt->path_log), "hts-cache/repair.zip"))
-    return "the repair path is too long";
-  if (unzRepair(name, repairname,
-                fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                        StringBuff(opt->path_log), "hts-cache/repair.tmp"),
-                entries, bytes) != Z_OK)
-    return "could not repair the cache";
-  /* unzRepair writes an end-of-central-directory record whatever it found, so
-     an input holding no local file header at all yields a valid empty archive
-     and a short write yields a truncated one. Only an archive that holds
-     something and opens may replace the cache (#824). */
-  if (*entries == 0)
-    return "the repaired cache holds no entry, keeping the damaged one";
-  if ((zip = hts_unzOpen_utf8(repairname)) == NULL)
-    return "the repaired cache does not open, keeping the damaged one";
-  unzClose(zip);
-  if (!hts_rename_over(opt, repairname, name))
-    return "could not put the repaired cache in place";
-  return NULL;
-}
-
 // Initialisation du cache: créer nouveau, renomer ancien, charger..
 void cache_init(cache_back * cache, httrackp * opt) {
   // ---
@@ -1013,16 +988,29 @@ 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
-        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"))) {
+        /* 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) {
           hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
                         "Cache: error while moving previous cache");
         } else {
-          hts_log_print(opt, LOG_DEBUG, "Cache: rotated new.zip to old.zip");
+          hts_log_print(opt, LOG_DEBUG, "Cache: successfully renamed");
         }
       }
     } else {
@@ -1055,9 +1043,8 @@ void cache_init(cache_back * cache, httrackp * opt) {
       // Corrupted ZIP file ? Try to repair!
       if (cache->zipInput == NULL && !cache->ro) {
         char *name;
-        const char *why;
-        unsigned long repaired = 0;
-        unsigned long repairedBytes = 0;
+        uLong repaired = 0;
+        uLong repairedBytes = 0;
 
         if (!cache->ro) {
           name =
@@ -1070,16 +1057,25 @@ void cache_init(cache_back * cache, httrackp * opt) {
         }
         hts_log_print(opt, LOG_WARNING,
                       "Cache: damaged cache, trying to repair");
-        why = cache_repair(opt, name, &repaired, &repairedBytes);
-        if (why != NULL) {
-          hts_log_print(opt, LOG_WARNING | LOG_ERRNO, "Cache: %s", why);
-        } else if ((cache->zipInput = hts_unzOpen_utf8(name)) != NULL) {
+        /* mztools has no UTF-8 hook, so repairing a corrupt cache under a
+           non-ASCII path_log fails cleanly (re-crawl), never forks a twin. */
+        if (unzRepair
+            (name,
+             fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                     "hts-cache/repair.zip"), fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                                                      StringBuff(opt->path_log),
+                                                      "hts-cache/repair.tmp"),
+             &repaired, &repairedBytes) == Z_OK) {
+          UNLINK(name);
+          RENAME(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                         StringBuff(opt->path_log), "hts-cache/repair.zip"),
+                 name);
+          cache->zipInput = hts_unzOpen_utf8(name);
           hts_log_print(opt, LOG_WARNING,
                         "Cache: %d bytes successfully recovered in %d entries",
                         (int) repairedBytes, (int) repaired);
         } else {
-          hts_log_print(opt, LOG_WARNING,
-                        "Cache: the repaired cache could not be reopened");
+          hts_log_print(opt, LOG_WARNING, "Cache: could not repair the cache");
         }
       }
       // Opened ?
@@ -1298,17 +1294,12 @@ char *readfile2(const char *fil, LLint * size) {
 }
 
 /* Note: utf-8 */
-char *readfile_utf8(const char *fil) { return readfile2_utf8(fil, NULL); }
-
-/* Note: utf-8 */
-char *readfile2_utf8(const char *fil, LLint *size) {
+char *readfile_utf8(const char *fil) {
   char *adr = NULL;
   char catbuff[CATBUFF_SIZE];
   const LLint len = fsize_utf8(fil);
   const size_t buflen = len >= 0 ? llint_to_size_t(len) : (size_t) -1;
 
-  if (size != NULL)
-    *size = len;
   if (buflen != (size_t) -1) { // exists, and is addressable (see readfile2)
     FILE *const fp = FOPEN(fconv(catbuff, sizeof(catbuff), fil), "rb");
 
@@ -1449,7 +1440,7 @@ int cache_brstr(char *adr, char *s, size_t s_size) {
 
 /* binput bounded to a NUL-terminated buffer: refuse to start a read at or
    past `end`, so a prior over-advance can't walk a cache-index parse OOB. */
-int cache_binput(const char *adr, const char *end, char *s, int max) {
+int cache_binput(char *adr, const char *end, char *s, int max) {
   if (adr >= end) {
     s[0] = '\0';
     return 0;

src/htscache.h

@@ -78,14 +78,6 @@ htsblk *cache_header(httrackp * opt, cache_back * cache, const char *adr,
                      const char *fil, htsblk * r);
 void cache_init(cache_back * cache, httrackp * opt);
 
-/* Recover the damaged cache at name into hts-cache/repair.zip and move it over
-   name, storing what was recovered in *entries and *bytes. Returns NULL on
-   success, else a reason the caller reports: a recovery that is empty or does
-   not open never replaces the cache, and neither does one that cannot be moved
-   into place (#786, #824). Note: utf-8. */
-const char *cache_repair(httrackp *opt, const char *name,
-                         unsigned long *entries, unsigned long *bytes);
-
 /* Which hts-cache/ generation (new.* vs old.*) is authoritative. */
 typedef enum {
   CACHE_RECONCILE_PROMOTE,     /* no new cache: promote the old generation */
@@ -101,7 +93,7 @@ void cache_rstr(FILE *fp, char *s, size_t s_size);
 char *cache_rstr_addr(FILE * fp);
 int cache_brstr(char *adr, char *s, size_t s_size);
 /* binput over a NUL-terminated buffer, bounded: no read starts at/past end. */
-int cache_binput(const char *adr, const char *end, char *s, int max);
+int cache_binput(char *adr, const char *end, char *s, int max);
 int cache_brint(char *adr, int *i);
 void cache_rint(FILE * fp, int *i);
 void cache_rLLint(FILE * fp, LLint * i);

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' && hts_lastchar(base) != '/') {
+    if (base[0] != '\0' && base[strlen(base) - 1] != '/') {
       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' && hts_lastchar(base) != '/') {
+  if (base[0] != '\0' && base[strlen(base) - 1] != '/') {
     strcatbuff(base, "/");
   }
   StringCopy(opt->path_log, base);
@@ -1195,12 +1195,6 @@ int cache_legacy_refused_selftest(httrackp *opt, const char *dir) {
 
 /* --- read-side corruption injection --------------------------------------- */
 
-/* 100 'A's: a placeholder header line long enough to be overwritten by a
-   forged, over-long X-StatusMessage of the same byte length. */
-#define CORRUPT_LONG_ETAG                                                      \
-  "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"                         \
-  "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
-
 /* canary read back intact after each corruption; victim gets the byte surgery
  */
 #define CORRUPT_ADR "corrupt.example.com"
@@ -1225,24 +1219,6 @@ static void corrupt_build(httrackp *opt) {
   selftest_close(&cache);
 }
 
-/* Like corrupt_build, but the victim carries a 100-char Etag placeholder. */
-static void corrupt_build_longetag(httrackp *opt) {
-  cache_back cache;
-
-  memset(corrupt_body_a, 'a', sizeof(corrupt_body_a) - 1);
-  memset(corrupt_body_b, 'b', sizeof(corrupt_body_b) - 1);
-  remove(reconcile_st_path(opt, "hts-cache/new.zip"));
-  remove(reconcile_st_path(opt, "hts-cache/old.zip"));
-  selftest_open_for_write(&cache, opt);
-  store_entry(opt, &cache, CORRUPT_ADR, "/canary.html", "canary.html", 200,
-              "OK", "text/html", "utf-8", "", "", "", "", corrupt_body_a,
-              strlen(corrupt_body_a));
-  store_entry(opt, &cache, CORRUPT_ADR, "/victim.html", "victim.html", 200,
-              "OK", "text/html", "utf-8", "", CORRUPT_LONG_ETAG, "", "",
-              corrupt_body_b, strlen(corrupt_body_b));
-  selftest_close(&cache);
-}
-
 /* Like corrupt_build, but the victim carries a 20-char Etag whose header line
    is later overwritten with a forged oversized X-Size (same byte length). */
 static void corrupt_build_etag(httrackp *opt) {
@@ -1427,48 +1403,6 @@ static int corrupt_expect_disk_header(httrackp *opt, LLint wantsize,
   return fail;
 }
 
-/* An over-long field from a foreign cache must clip, not abort: the entry
-   still reads, clipped to capacity, and the canary survives. */
-static int corrupt_expect_victim_clipped(httrackp *opt, size_t wantmsg,
-                                         size_t wantlastmod, const char *what) {
-  cache_back cache;
-  htsblk v, c;
-  char BIGSTK lv[HTS_URLMAXSIZE * 2];
-  char BIGSTK lc[HTS_URLMAXSIZE * 2];
-  int fail = 0;
-
-  selftest_open_for_read(&cache, opt);
-  lv[0] = lc[0] = '\0';
-  v = cache_readex(opt, &cache, CORRUPT_ADR, "/victim.html", "", lv, NULL, 1);
-  if (v.statuscode != 200) {
-    fprintf(stderr, "%s: %s: status %d, expected 200\n", selftest_tag, what,
-            v.statuscode);
-    fail++;
-  }
-  if (wantmsg != (size_t) -1 && strlen(v.msg) != wantmsg) {
-    fprintf(stderr, "%s: %s: msg len %u, expected %u\n", selftest_tag, what,
-            (unsigned) strlen(v.msg), (unsigned) wantmsg);
-    fail++;
-  }
-  if (wantlastmod != (size_t) -1 && strlen(v.lastmodified) != wantlastmod) {
-    fprintf(stderr, "%s: %s: lastmodified len %u, expected %u\n", selftest_tag,
-            what, (unsigned) strlen(v.lastmodified), (unsigned) wantlastmod);
-    fail++;
-  }
-  c = cache_readex(opt, &cache, CORRUPT_ADR, "/canary.html", "", lc, NULL, 1);
-  if (c.statuscode != 200) {
-    fprintf(stderr, "%s: %s: canary tainted (status %d)\n", selftest_tag, what,
-            c.statuscode);
-    fail++;
-  }
-  if (v.adr != NULL)
-    freet(v.adr);
-  if (c.adr != NULL)
-    freet(c.adr);
-  selftest_close(&cache);
-  return fail;
-}
-
 /* One zip corruption case: build, patch, then check victim+canary in-session.
  */
 static int corrupt_case_zip(httrackp *opt, const char *pat, const char *rep,
@@ -1505,31 +1439,6 @@ int cache_corruption_selftest(httrackp *opt, const char *dir) {
   failures += corrupt_expect_victim(opt, "Cache Read Error : Read Data",
                                     "garbled deflate stream");
 
-  /* A corrupt cache can hold a field wider than ours. Clipping keeps the
-     entry; aborting would take the crawl down. Overwrite the placeholder Etag
-     line in place, same byte length, so the zip offsets stay intact. */
-  corrupt_build_longetag(opt);
-  corrupt_patch(opt, "Etag: " CORRUPT_LONG_ETAG, 106,
-                "X-StatusMessage: " /* 17 + 89 = 106 */
-                "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
-                "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
-                1, 1);
-  failures +=
-      corrupt_expect_victim_clipped(opt, sizeof(((htsblk *) 0)->msg) - 1,
-                                    (size_t) -1, "over-long X-StatusMessage");
-
-  /* lastmodified[64] is narrower than msg[80]: one hardcoded clip length
-     cannot satisfy both. */
-  corrupt_build_longetag(opt);
-  corrupt_patch(opt, "Etag: " CORRUPT_LONG_ETAG, 106,
-                "Last-Modified: " /* 15 + 91 = 106 */
-                "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
-                "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
-                1, 1);
-  failures += corrupt_expect_victim_clipped(
-      opt, (size_t) -1, sizeof(((htsblk *) 0)->lastmodified) - 1,
-      "over-long Last-Modified");
-
   /* An X-Size above INT_MAX is positive as int64 (slips a bare sign check) but
      truncates negative in the (int) cast the malloc uses: a wraparound alloc.
      cache_add asserts size fits an int, so such a value only reaches the reader

src/htschanges.c

@@ -1,679 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-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: htschanges.c subroutines:                              */
-/*       --changes: what this crawl changed vs. the previous    */
-/*       mirror (hts-changes.json)                              */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-#define HTS_INTERNAL_BYTECODE
-
-#include "htschanges.h"
-
-#include "htscache.h"
-#include "htscharset.h"
-#include "htscore.h"
-#include "htslib.h"
-#include "htsmd5.h"
-#include "htssafe.h"
-#include "htsthread.h"
-#include "htstools.h"
-#include "coucal/coucal.h"
-#include "md5.h"
-
-#include <stdlib.h>
-#include <string.h>
-#include <time.h>
-
-#define DIGEST_SIZE 16
-
-typedef struct hts_changes hts_changes;
-
-/* One mirrored file. The mirror-relative path is the key, not the URL: a
-   redirect and its target can share a save name, and counting that file twice
-   would put it in two buckets. */
-typedef struct {
-  char *url;               /* absolute URL, "" for an engine-generated file */
-  char *file;              /* mirror-relative path, as listed in new.lst */
-  hts_boolean rewritten;   /* the crawl wrote over the local copy */
-  hts_boolean not_updated; /* transfer signal: the server reported no change */
-  hts_boolean existed;     /* the file was part of the previous mirror */
-  hts_boolean on_disk;     /* a copy was on disk when the crawl first saw it */
-  hts_boolean listed_prev; /* the previous mirror's index listed this file */
-  hts_boolean has_prev;    /* prev_digest holds the previous payload's digest */
-  hts_boolean has_new;     /* new_digest was taken from the payload, not disk */
-  unsigned char prev_digest[DIGEST_SIZE];
-  unsigned char new_digest[DIGEST_SIZE];
-  LLint prev_size; /* -1 when unknown */
-  LLint size;      /* size after the crawl, -1 when unknown */
-  hts_change_bucket bucket;
-} changes_entry;
-
-struct hts_changes {
-  coucal index; /* mirror-relative path -> entry slot + 1 */
-  changes_entry *entries;
-  size_t count;
-  size_t capacity;
-  hts_boolean has_index; /* the run keeps a mirror index (the cache is on) */
-  hts_boolean old_index; /* the previous mirror's index was read */
-  hts_boolean overflow;  /* an allocation failed; the report is partial */
-  hts_boolean closed;    /* reported: late notifies are dropped, not recorded */
-};
-
-/* ------------------------------------------------------------ */
-/* JSON                                                          */
-/* ------------------------------------------------------------ */
-
-/* Length of the UTF-8 sequence led by c, or 0 if c cannot lead one. */
-static size_t utf8_lead_length(unsigned char c) {
-  if (c >= 0xc2 && c <= 0xdf)
-    return 2;
-  if (c >= 0xe0 && c <= 0xef)
-    return 3;
-  if (c >= 0xf0 && c <= 0xf4)
-    return 4;
-  return 0;
-}
-
-void hts_changes_json_string(String *out, const char *s) {
-  const unsigned char *p = (const unsigned char *) s;
-
-  StringAddchar(*out, '"');
-  while (*p != '\0') {
-    const unsigned char c = *p;
-
-    if (c == '"' || c == '\\') {
-      StringAddchar(*out, '\\');
-      StringAddchar(*out, (char) c);
-      p++;
-    } else if (c < 0x20 || c == 0x7f) {
-      char esc[8];
-
-      snprintf(esc, sizeof(esc), "\\u%04x", (unsigned) c);
-      StringCat(*out, esc);
-      p++;
-    } else if (c < 0x80) {
-      StringAddchar(*out, (char) c);
-      p++;
-    } else {
-      /* Non-ASCII: emit it verbatim only if it is a well-formed sequence, so
-         a legacy-charset URL cannot produce unparseable JSON. */
-      const size_t len = utf8_lead_length(c);
-
-      if (len != 0 && strnlen((const char *) p, len) == len &&
-          hts_isStringUTF8((const char *) p, len)) {
-        StringMemcat(*out, (const char *) p, len);
-        p += len;
-      } else {
-        StringCat(*out, "\\ufffd");
-        p++;
-      }
-    }
-  }
-  StringAddchar(*out, '"');
-}
-
-/* ------------------------------------------------------------ */
-/* Accumulator                                                   */
-/* ------------------------------------------------------------ */
-
-static hts_changes *changes_new(void) {
-  hts_changes *changes = calloct(1, sizeof(*changes));
-
-  if (changes == NULL)
-    return NULL;
-  changes->index = coucal_new(0);
-  if (changes->index == NULL) {
-    freet(changes);
-    return NULL;
-  }
-  return changes;
-}
-
-static void changes_free(hts_changes **pchanges) {
-  hts_changes *changes = *pchanges;
-
-  if (changes == NULL)
-    return;
-  if (changes->entries != NULL) {
-    size_t i;
-
-    for (i = 0; i < changes->count; i++) {
-      freet(changes->entries[i].url);
-      freet(changes->entries[i].file);
-    }
-    freet(changes->entries);
-  }
-  if (changes->index != NULL)
-    coucal_delete(&changes->index);
-  freet(changes);
-  *pchanges = NULL;
-}
-
-/* Slot of `file`, or -1 when it has not been recorded. */
-static intptr_t changes_find(const hts_changes *changes, const char *file) {
-  intptr_t slot = 0;
-
-  return coucal_read(changes->index, file, &slot) ? slot - 1 : -1;
-}
-
-/* Slot of `file`, appending a fresh entry when it is new; -1 if allocation
-   failed, which flags the report partial. */
-static intptr_t changes_slot(hts_changes *changes, const char *file,
-                             hts_boolean *is_new) {
-  intptr_t slot = 0;
-
-  *is_new = HTS_FALSE;
-  if (coucal_read(changes->index, file, &slot))
-    return slot - 1;
-
-  if (changes->count == changes->capacity) {
-    const size_t capacity = changes->capacity != 0 ? changes->capacity * 2 : 64;
-    changes_entry *const entries =
-        realloct(changes->entries, capacity * sizeof(*entries));
-
-    if (entries == NULL) {
-      changes->overflow = HTS_TRUE;
-      return -1;
-    }
-    changes->entries = entries;
-    changes->capacity = capacity;
-  }
-  slot = (intptr_t) changes->count;
-  memset(&changes->entries[slot], 0, sizeof(changes->entries[slot]));
-  changes->entries[slot].file = strdupt(file);
-  changes->entries[slot].prev_size = -1;
-  changes->entries[slot].size = -1;
-  if (changes->entries[slot].file == NULL) {
-    changes->overflow = HTS_TRUE;
-    return -1;
-  }
-  changes->count++;
-  coucal_write(changes->index, file, slot + 1);
-  *is_new = HTS_TRUE;
-  return slot;
-}
-
-/* MD5 of the file at `path`; not a security boundary. Never call it holding
-   changes_mutex: hashing a large file would stall every other connection.
-   HTS_FALSE if it cannot be read. */
-static hts_boolean digest_file(const char *path,
-                               unsigned char digest[DIGEST_SIZE]) {
-  const int endian = 1;
-  struct MD5Context ctx;
-  char BIGSTK buffer[32768];
-  FILE *fp = FOPEN(path, "rb");
-  size_t nread;
-
-  if (fp == NULL)
-    return HTS_FALSE;
-  MD5Init(&ctx, *((const char *) &endian));
-  while ((nread = fread(buffer, 1, sizeof(buffer), fp)) > 0)
-    MD5Update(&ctx, (const unsigned char *) buffer, (unsigned int) nread);
-  if (ferror(fp) != 0) {
-    fclose(fp);
-    return HTS_FALSE;
-  }
-  fclose(fp);
-  MD5Final(digest, &ctx);
-  return HTS_TRUE;
-}
-
-static void digest_mem(const char *buffer, size_t len,
-                       unsigned char digest[DIGEST_SIZE]) {
-  domd5mem(buffer, len, (char *) digest, 0);
-}
-
-hts_change_bucket hts_changes_classify(hts_boolean rewritten,
-                                       hts_boolean existed,
-                                       hts_boolean not_updated,
-                                       hts_boolean have_digests,
-                                       hts_boolean digests_equal) {
-  if (!rewritten)
-    return HTS_CHANGE_UNCHANGED; /* the crawl left the copy alone */
-  if (!existed)
-    return HTS_CHANGE_NEW;
-  if (have_digests)
-    return digests_equal ? HTS_CHANGE_UNCHANGED : HTS_CHANGE_CHANGED;
-  /* No digest to compare: a server with no validators answers 200 with the
-     same bytes, so this signal alone over-reports. */
-  return not_updated ? HTS_CHANGE_UNCHANGED : HTS_CHANGE_CHANGED;
-}
-
-/* ------------------------------------------------------------ */
-/* Engine hooks                                                  */
-/* ------------------------------------------------------------ */
-
-/* FTP transfers reach file_notify() from a thread the crawl never joins, so
-   every entry point below, report and teardown included, takes this lock. */
-static htsmutex changes_mutex = HTSMUTEX_INIT;
-
-/* The live accumulator, created on first use; NULL when --changes is off or
-   the report is already written. Call under the lock. */
-static hts_changes *changes_get(httrackp *opt) {
-  hts_changes *changes = (hts_changes *) opt->changes_state;
-
-  if (!opt->changes)
-    return NULL;
-  if (changes == NULL) {
-    changes = changes_new();
-    opt->changes_state = changes;
-  }
-  return changes != NULL && !changes->closed ? changes : NULL;
-}
-
-void hts_changes_notify(httrackp *opt, const char *adr, const char *fil,
-                        const char *save, hts_boolean rewritten,
-                        hts_boolean not_updated) {
-  hts_changes *changes;
-  char BIGSTK file[HTS_URLMAXSIZE * 2];
-  char BIGSTK url[HTS_URLMAXSIZE * 4 + 8]; /* holds adr + fil + a scheme */
-  unsigned char prev_digest[DIGEST_SIZE];
-  hts_boolean has_prev = HTS_FALSE;
-  hts_boolean is_new = HTS_FALSE;
-  intptr_t slot = -1;
-  LLint prev_size;
-
-  if (!opt->changes)
-    return;
-  /* Engine-generated scaffolding (the top index) carries no URL and is not a
-     mirrored resource. */
-  if (save == NULL || !strnotempty(save) || adr == NULL || fil == NULL ||
-      (!strnotempty(adr) && !strnotempty(fil)))
-    return;
-
-  hts_savename_listed(StringBuff(opt->path_html), save, file, sizeof(file));
-
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  if (changes != NULL) {
-    slot = changes_slot(changes, file, &is_new);
-    if (slot >= 0 && !is_new) {
-      /* Retry, or a second call site for the same file: the pre-run state was
-         already sampled and the copy on disk may no longer be it. */
-      changes->entries[slot].rewritten =
-          changes->entries[slot].rewritten || rewritten;
-    }
-  }
-  hts_mutexrelease(&changes_mutex);
-  if (slot < 0 || !is_new)
-    return;
-
-  url[0] = '\0';
-  if (!link_has_authority(adr))
-    strlcatbuff(url, "http://", sizeof(url));
-  strlcatbuff(url, adr, sizeof(url));
-  strlcatbuff(url, fil, sizeof(url));
-
-  /* Unlocked: hashing a large file would stall every other connection. Hash
-     it only when it is about to be overwritten, the last moment it exists. */
-  prev_size = fsize_utf8(save);
-  if (prev_size >= 0 && rewritten)
-    has_prev = digest_file(save, prev_digest);
-
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  /* The slot index is stable, entries being append-only; the array is not. */
-  if (changes != NULL && (size_t) slot < changes->count) {
-    changes_entry *const entry = &changes->entries[slot];
-
-    entry->url = strdupt(url);
-    if (entry->url == NULL)
-      changes->overflow = HTS_TRUE;
-    entry->rewritten = entry->rewritten || rewritten;
-    entry->not_updated = not_updated;
-    entry->prev_size = prev_size;
-    entry->on_disk = prev_size >= 0;
-    /* hts_changes_html() compares payloads, and its digests win. */
-    if (has_prev && !entry->has_new) {
-      entry->has_prev = HTS_TRUE;
-      memcpy(entry->prev_digest, prev_digest, DIGEST_SIZE);
-    }
-  }
-  hts_mutexrelease(&changes_mutex);
-}
-
-void hts_changes_html(httrackp *opt, cache_back *cache, const htsblk *r,
-                      const char *adr, const char *fil, const char *save) {
-  hts_changes *changes;
-  char BIGSTK file[HTS_URLMAXSIZE * 2];
-  char BIGSTK location[HTS_URLMAXSIZE * 2];
-  unsigned char new_digest[DIGEST_SIZE];
-  unsigned char prev_digest[DIGEST_SIZE];
-  hts_boolean has_prev = HTS_FALSE;
-  intptr_t slot;
-  htsblk prev;
-
-  /* Ahead of the digest and the cache read: off must cost nothing. */
-  if (!opt->changes)
-    return;
-  if (r->adr == NULL || r->size < 0 || save == NULL || !strnotempty(save))
-    return;
-
-  /* On disk this is the payload plus rewritten links and a footer dated by the
-     crawl, so it differs every run; compare payloads, the previous one being
-     the body the cache kept. */
-  digest_mem(r->adr, (size_t) r->size, new_digest);
-  prev = cache_read_ro(opt, cache, adr, fil, "", location);
-  if (HTTP_IS_OK(prev.statuscode) && prev.adr != NULL && prev.size >= 0) {
-    digest_mem(prev.adr, (size_t) prev.size, prev_digest);
-    has_prev = HTS_TRUE;
-  }
-  freet(prev.adr);
-
-  /* Only now take the lock and look the entry up: cache_read_ro() can itself
-     reach file_notify(), which would move the entries array. */
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  /* file_notify() records the entry; this call only refines it. */
-  if (changes != NULL) {
-    hts_savename_listed(StringBuff(opt->path_html), save, file, sizeof(file));
-    slot = changes_find(changes, file);
-    if (slot >= 0) {
-      changes_entry *const entry = &changes->entries[slot];
-
-      entry->has_new = HTS_TRUE;
-      memcpy(entry->new_digest, new_digest, DIGEST_SIZE);
-      entry->has_prev = has_prev;
-      if (has_prev)
-        memcpy(entry->prev_digest, prev_digest, DIGEST_SIZE);
-    }
-  }
-  hts_mutexrelease(&changes_mutex);
-}
-
-void hts_changes_dropped(httrackp *opt, const char *file, hts_boolean kept) {
-  hts_changes *changes;
-  hts_boolean is_new;
-  intptr_t slot;
-
-  if (!opt->changes || file == NULL || !strnotempty(file))
-    return;
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  if (changes != NULL) {
-    slot = changes_slot(changes, file, &is_new);
-    if (slot >= 0 && is_new) {
-      changes->entries[slot].url = strdupt("");
-      changes->entries[slot].listed_prev = HTS_TRUE;
-      /* A kept file leaves rewritten clear, which resolves to unchanged. */
-      if (!kept)
-        changes->entries[slot].bucket = HTS_CHANGE_GONE;
-    }
-  }
-  hts_mutexrelease(&changes_mutex);
-}
-
-void hts_changes_previous(httrackp *opt, const char *file) {
-  hts_changes *changes;
-  intptr_t slot;
-
-  if (!opt->changes || file == NULL)
-    return;
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  if (changes != NULL) {
-    changes->has_index = HTS_TRUE;
-    changes->old_index = HTS_TRUE;
-    slot = changes_find(changes, file);
-    if (slot >= 0)
-      changes->entries[slot].listed_prev = HTS_TRUE;
-  }
-  hts_mutexrelease(&changes_mutex);
-}
-
-void hts_changes_indexed(httrackp *opt) {
-  hts_changes *changes;
-
-  if (!opt->changes)
-    return;
-  hts_mutexlock(&changes_mutex);
-  changes = changes_get(opt);
-  if (changes != NULL)
-    changes->has_index = HTS_TRUE;
-  hts_mutexrelease(&changes_mutex);
-}
-
-/* ------------------------------------------------------------ */
-/* Report                                                        */
-/* ------------------------------------------------------------ */
-
-/* Assign each entry its final bucket from the bytes now on disk. */
-static void changes_resolve(hts_changes *changes, httrackp *opt) {
-  char catbuff[CATBUFF_SIZE];
-  size_t i;
-
-  for (i = 0; i < changes->count; i++) {
-    changes_entry *const entry = &changes->entries[i];
-    const char *path;
-    unsigned char digest[DIGEST_SIZE];
-    hts_boolean have_digests = HTS_FALSE;
-    hts_boolean digests_equal = HTS_FALSE;
-
-    if (entry->bucket == HTS_CHANGE_GONE)
-      continue;
-
-    /* The previous mirror's index is the authority on what was there before:
-       a partial left by this crawl's own failed attempt is on disk but was
-       never part of the previous mirror. Without an index, fall back to what
-       the first notify saw on disk. */
-    entry->existed = changes->old_index ? entry->listed_prev : entry->on_disk;
-    path = fconcat(catbuff, sizeof(catbuff), StringBuff(opt->path_html),
-                   entry->file);
-    entry->size = fsize_utf8(path);
-    if (entry->rewritten && entry->existed) {
-      /* The size shortcut only holds when both digests describe the file on
-         disk; has_new means they are payload digests, and a parsed page's
-         rendered size moves with its links and footer. */
-      if (!entry->has_new && entry->size >= 0 && entry->prev_size >= 0 &&
-          entry->size != entry->prev_size) {
-        have_digests = HTS_TRUE; /* different lengths: no need to hash */
-        digests_equal = HTS_FALSE;
-      } else if (entry->has_prev &&
-                 (entry->has_new
-                      ? (memcpy(digest, entry->new_digest, DIGEST_SIZE), 1)
-                      : digest_file(path, digest))) {
-        have_digests = HTS_TRUE;
-        digests_equal = memcmp(digest, entry->prev_digest, DIGEST_SIZE) == 0
-                            ? HTS_TRUE
-                            : HTS_FALSE;
-      }
-    }
-    entry->bucket =
-        hts_changes_classify(entry->rewritten, entry->existed,
-                             entry->not_updated, have_digests, digests_equal);
-  }
-}
-
-static const char *const bucket_names[HTS_CHANGE_BUCKETS] = {
-    "new", "changed", "unchanged", "gone"};
-
-/* Serialize the report. Call under changes_mutex. */
-static void changes_serialize(httrackp *opt, String *out) {
-  hts_changes *const changes = (hts_changes *) opt->changes_state;
-  size_t counts[HTS_CHANGE_BUCKETS];
-  char date[32];
-  char scratch[64];
-  int bucket;
-  size_t i;
-
-  StringClear(*out);
-  if (changes == NULL)
-    return;
-  changes_resolve(changes, opt);
-
-  memset(counts, 0, sizeof(counts));
-  for (i = 0; i < changes->count; i++)
-    counts[changes->entries[i].bucket]++;
-
-  hts_now_iso8601(date);
-  StringCat(*out, "{\n  \"schema\": ");
-  snprintf(scratch, sizeof(scratch), "%d", HTS_CHANGES_SCHEMA);
-  StringCat(*out, scratch);
-  StringCat(*out, ",\n  \"generator\": ");
-  hts_changes_json_string(out, "HTTrack Website Copier/" HTTRACK_VERSION);
-  StringCat(*out, ",\n  \"date\": ");
-  hts_changes_json_string(out, date);
-  StringCat(*out, ",\n  \"first_crawl\": ");
-  StringCat(*out, !changes->has_index
-                      ? "null"
-                      : (changes->old_index ? "false" : "true"));
-  StringCat(*out, ",\n  \"partial\": ");
-  StringCat(*out, changes->overflow ? "true" : "false");
-  StringCat(*out, ",\n  \"purged\": ");
-  StringCat(*out, opt->delete_old ? "true" : "false");
-
-  StringCat(*out, ",\n  \"counts\": {");
-  for (bucket = 0; bucket < HTS_CHANGE_BUCKETS; bucket++) {
-    StringCat(*out, bucket != 0 ? ", " : " ");
-    hts_changes_json_string(out, bucket_names[bucket]);
-    snprintf(scratch, sizeof(scratch), ": %d", (int) counts[bucket]);
-    StringCat(*out, scratch);
-  }
-  StringCat(*out, " }");
-
-  for (bucket = 0; bucket < HTS_CHANGE_BUCKETS; bucket++) {
-    hts_boolean first = HTS_TRUE;
-
-    StringCat(*out, ",\n  ");
-    hts_changes_json_string(out, bucket_names[bucket]);
-    StringCat(*out, ": [");
-    for (i = 0; i < changes->count; i++) {
-      const changes_entry *const entry = &changes->entries[i];
-
-      if (entry->bucket != bucket)
-        continue;
-      StringCat(*out, first ? "\n    { \"url\": " : ",\n    { \"url\": ");
-      first = HTS_FALSE;
-      hts_changes_json_string(out, entry->url != NULL ? entry->url : "");
-      StringCat(*out, ", \"file\": ");
-      hts_changes_json_string(out, entry->file);
-      if (entry->size >= 0) {
-        snprintf(scratch, sizeof(scratch), ", \"size\": " LLintP,
-                 (LLint) entry->size);
-        StringCat(*out, scratch);
-      }
-      if (bucket == HTS_CHANGE_CHANGED && entry->prev_size >= 0) {
-        snprintf(scratch, sizeof(scratch), ", \"previous_size\": " LLintP,
-                 (LLint) entry->prev_size);
-        StringCat(*out, scratch);
-      }
-      StringCat(*out, " }");
-    }
-    StringCat(*out, first ? "]" : "\n  ]");
-  }
-  StringCat(*out, "\n}\n");
-}
-
-void hts_changes_report(httrackp *opt, String *out) {
-  hts_mutexlock(&changes_mutex);
-  changes_serialize(opt, out);
-  hts_mutexrelease(&changes_mutex);
-}
-
-void hts_changes_close_opt(httrackp *opt) {
-  char catbuff[CATBUFF_SIZE];
-  const char *path;
-  String report = STRING_EMPTY;
-  size_t counts[HTS_CHANGE_BUCKETS];
-  size_t total;
-  hts_boolean has_index, old_index;
-  FILE *fp;
-
-  hts_mutexlock(&changes_mutex);
-  {
-    /* changes_get(), not the raw field: a crawl that mirrored nothing still
-       owes the user a report, and a stale one from the previous run must not
-       survive on disk as if it described this one. */
-    hts_changes *const changes = changes_get(opt);
-    size_t i;
-
-    if (changes == NULL) {
-      hts_mutexrelease(&changes_mutex);
-      return;
-    }
-    changes_serialize(opt, &report);
-    memset(counts, 0, sizeof(counts));
-    for (i = 0; i < changes->count; i++)
-      counts[changes->entries[i].bucket]++;
-    total = changes->count;
-    has_index = changes->has_index;
-    old_index = changes->old_index;
-    /* Sticky: whatever the crawl's stragglers do next is not in this report. */
-    changes->closed = HTS_TRUE;
-  }
-  hts_mutexrelease(&changes_mutex);
-
-  path = fconcat(catbuff, sizeof(catbuff), StringBuff(opt->path_log),
-                 HTS_CHANGES_FILE);
-  fp = FOPEN(path, "wb");
-  if (fp != NULL) {
-    const size_t len = StringLength(report);
-
-    if (len != 0 && fwrite(StringBuff(report), 1, len, fp) != len)
-      hts_log_print(opt, LOG_ERROR | LOG_ERRNO,
-                    "Unable to write the change report %s", path);
-    fclose(fp);
-  } else {
-    hts_log_print(opt, LOG_ERROR | LOG_ERRNO,
-                  "Unable to create the change report %s", path);
-  }
-
-  if (!has_index) {
-    hts_log_print(opt, LOG_NOTICE,
-                  "Change report: no mirror index (the cache is off), %d files "
-                  "mirrored, deletions not detected (%s)",
-                  (int) total, HTS_CHANGES_FILE);
-  } else if (!old_index) {
-    hts_log_print(opt, LOG_NOTICE,
-                  "Change report: first crawl, %d files mirrored, nothing to "
-                  "compare against (%s)",
-                  (int) total, HTS_CHANGES_FILE);
-  } else {
-    hts_log_print(opt, LOG_NOTICE,
-                  "Change report: %d new, %d changed, %d unchanged, %d gone "
-                  "(%s)",
-                  (int) counts[HTS_CHANGE_NEW],
-                  (int) counts[HTS_CHANGE_CHANGED],
-                  (int) counts[HTS_CHANGE_UNCHANGED],
-                  (int) counts[HTS_CHANGE_GONE], HTS_CHANGES_FILE);
-  }
-
-  StringFree(report);
-}
-
-void hts_changes_free_opt(httrackp *opt) {
-  hts_changes *changes;
-
-  hts_mutexlock(&changes_mutex);
-  changes = (hts_changes *) opt->changes_state;
-  changes_free(&changes);
-  opt->changes_state = NULL;
-  hts_mutexrelease(&changes_mutex);
-}

src/htschanges.h

@@ -1,125 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-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 change report (--changes). Internal, not installed.
-   Accumulates what the crawl did to each mirrored file, compares the bytes
-   against the copy the previous run left behind, and writes
-   hts-changes.json next to the log. */
-/* ------------------------------------------------------------ */
-
-#ifndef HTS_CHANGES_DEFH
-#define HTS_CHANGES_DEFH
-
-#include "htsopt.h"
-#include "htsstrings.h"
-
-#ifndef HTS_DEF_FWSTRUCT_cache_back
-#define HTS_DEF_FWSTRUCT_cache_back
-typedef struct cache_back cache_back;
-#endif
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* Report file name, written under the project's log directory. */
-#define HTS_CHANGES_FILE "hts-changes.json"
-
-/* Schema version carried by the report; bump on an incompatible change. */
-#define HTS_CHANGES_SCHEMA 1
-
-/* Which side of the comparison a mirrored file ended up on. */
-typedef enum {
-  HTS_CHANGE_NEW = 0,   /* no local copy before this run */
-  HTS_CHANGE_CHANGED,   /* rewritten, and the bytes differ */
-  HTS_CHANGE_UNCHANGED, /* the bytes are those of the previous mirror */
-  HTS_CHANGE_GONE,      /* in the previous mirror, absent from this one */
-  HTS_CHANGE_BUCKETS
-} hts_change_bucket;
-
-/* Record what this crawl is doing to the local file `save` (absolute path;
-   adr/fil form its URL, either may be empty for an engine-generated file).
-   `rewritten` means the copy on disk is being written over, `not_updated` is
-   the 200-versus-304 signal, used only when no digest can be taken. Only the
-   first call for a file samples the previous copy, so a retried or
-   twice-notified resource is counted once. No-op unless --changes is on. */
-void hts_changes_notify(httrackp *opt, const char *adr, const char *fil,
-                        const char *save, hts_boolean rewritten,
-                        hts_boolean not_updated);
-
-/* Refine the entry for a parsed HTML file: its local copy carries rewritten
-   links and a footer dated by the crawl, so it differs every run. Compares the
-   payload `r` holds against the body the previous run left in the cache. */
-void hts_changes_html(httrackp *opt, cache_back *cache, const htsblk *r,
-                      const char *adr, const char *fil, const char *save);
-
-/* Record `file` (mirror-relative, as listed in new.lst) as listed by the
-   previous mirror's index and absent from this run's. `kept` means its local
-   copy survives the run because the crawl tried and failed to replace it: a
-   failed transfer is not a deletion, so it is reported unchanged, not gone. */
-void hts_changes_dropped(httrackp *opt, const char *file, hts_boolean kept);
-
-/* Record that the previous mirror's index listed `file`. That index, not the
-   file's presence on disk, decides what counts as already mirrored. */
-void hts_changes_previous(httrackp *opt, const char *file);
-
-/* Record that this run keeps a mirror index. Without one (the cache is off)
-   deletions and first_crawl are undecidable, and the report says so. */
-void hts_changes_indexed(httrackp *opt);
-
-/* Resolve every entry against the bytes now on disk and serialize the report
-   into `out` (replaced). Exposed for the self-tests. */
-void hts_changes_report(httrackp *opt, String *out);
-
-/* Write the report and log a one-line summary. Idempotent, and seals the
-   accumulator: a late notify is dropped rather than starting a second one. */
-void hts_changes_close_opt(httrackp *opt);
-
-/* Drop the accumulator, for a run that never reached its end and to start the
-   next one clean. Null-safe and idempotent. */
-void hts_changes_free_opt(httrackp *opt);
-
-/* Bucket for one entry, from what was observed. No filesystem access:
-   `have_digests` says both sides could be hashed, `digests_equal` compares
-   them, and `not_updated` is the fallback signal when they could not. */
-hts_change_bucket hts_changes_classify(hts_boolean rewritten,
-                                       hts_boolean existed,
-                                       hts_boolean not_updated,
-                                       hts_boolean have_digests,
-                                       hts_boolean digests_equal);
-
-/* Append `s` to `out` as a quoted JSON string. Byte sequences that are not
-   valid UTF-8 become U+FFFD, so a mirror carrying legacy-charset URLs still
-   produces parseable JSON. */
-void hts_changes_json_string(String *out, const char *s);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

src/htscharset.c

@@ -390,10 +390,6 @@ HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size) {
   return hts_convertStringCPToUTF8(s, size, GetACP());
 }
 
-HTSEXT_API char *hts_convertStringUTF8ToSystem(const char *s, size_t size) {
-  return hts_convertStringCPFromUTF8(s, size, GetACP());
-}
-
 HTSEXT_API void hts_argv_utf8(int *pargc, char ***pargv) {
   int wargc = 0;
   LPWSTR *const wargv = CommandLineToArgvW(GetCommandLineW(), &wargc);

src/htscharset.h

@@ -171,25 +171,12 @@ extern LPWSTR hts_convertUTF8StringToUCS2(const char *s, int size, int *pwsize);
  **/
 extern char *hts_convertUCS2StringToUTF8(LPWSTR woutput, int wsize);
 
-/**
- * UTF-8 path to UCS-2 for the wide file/FindFirst APIs, \\?\-prefixed above
- * MAX_PATH (#133). Internal, not exported; caller frees.
- * This function is WIN32 specific.
- **/
-extern LPWSTR hts_pathToUCS2(const char *path);
-
 /**
  * Convert current system codepage to UTF-8.
  * This function is WIN32 specific.
  **/
 HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size);
 
-/**
- * Convert UTF-8 to the current system codepage. Caller frees; NULL upon error.
- * This function is WIN32 specific.
- **/
-HTSEXT_API char *hts_convertStringUTF8ToSystem(const char *s, size_t size);
-
 /**
  * Replace the CRT's ANSI argv by a UTF-8 one decoded from the real UTF-16
  * command line: every char* is UTF-8 on Windows (FOPEN, STAT, ... convert at

src/htscmdline.c

@@ -1,95 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 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: command line splitter, shared by the engine and         */
-/*       htsserver                                               */
-/* Author: Xavier Roche                                          */
-/* ------------------------------------------------------------ */
-
-#include "htscmdline.h"
-
-#include "htssafe.h"
-
-#include <limits.h>
-#include <stdint.h>
-
-char **hts_split_cmdline(char *cmd, int *nargs) {
-  size_t nsep = 0;
-  size_t capacity;
-  size_t r;
-  size_t w;
-  int argc = 0;
-  hts_boolean quoted = HTS_FALSE;
-  char **argv;
-
-  *nargs = 0;
-
-  /* fold the other separators, so counting them sizes the vector exactly */
-  for (r = 0; cmd[r] != '\0'; r++) {
-    if (cmd[r] == '\t' || cmd[r] == '\r' || cmd[r] == '\n') {
-      cmd[r] = ' ';
-    }
-    if (cmd[r] == ' ') {
-      nsep++;
-    }
-  }
-
-  /* at most one argument per separator, plus the leading one and the NULL */
-  if (nsep > (size_t) INT_MAX - 1 || nsep > SIZE_MAX / sizeof(char *) - 2) {
-    return NULL;
-  }
-  capacity = nsep + 2;
-  argv = (char **) malloct(capacity * sizeof(char *));
-  if (argv == NULL) {
-    return NULL;
-  }
-
-  argv[argc++] = cmd;
-  for (r = 0, w = 0; cmd[r] != '\0';) {
-    if (quoted && cmd[r] == '\\' &&
-        (cmd[r + 1] == '\\' || cmd[r + 1] == '\"')) {
-      r++;
-      cmd[w++] = cmd[r++];
-    } else if (cmd[r] == '\"') {
-      quoted = !quoted;
-      cmd[w++] = cmd[r++];
-    } else if (cmd[r] == ' ' && !quoted) {
-      cmd[w++] = '\0';
-      assertf((size_t) argc < capacity - 1); /* the last slot holds the NULL */
-      argv[argc++] = cmd + w;
-      r++;
-    } else {
-      cmd[w++] = cmd[r++];
-    }
-  }
-  cmd[w] = '\0';
-  argv[argc] = NULL; /* callers may rely on argv[argc] == NULL */
-
-  *nargs = argc;
-  return argv;
-}

src/htscmdline.h

@@ -1,45 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 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: command line splitter, shared by the engine and         */
-/*       htsserver                                               */
-/* Author: Xavier Roche                                          */
-/* ------------------------------------------------------------ */
-
-#ifndef HTSCMDLINE_DEFH
-#define HTSCMDLINE_DEFH
-
-#include "htsglobal.h"
-
-/* Split "cmd" in place into a NULL-terminated argv vector of *nargs entries,
-   argv[0] being the program name and quotes left for the engine to strip.
-   Returns a malloct'ed vector of pointers into cmd (freet the vector, never its
-   entries), or NULL when it cannot be sized or allocated. */
-char **hts_split_cmdline(char *cmd, int *nargs);
-
-#endif