review: trim comments to the one-line default

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.gitattributes

@@ -1,8 +0,0 @@
-# Resource scripts are Windows tooling input and must stay CRLF: the engine has no
-# encoding guard, so an autocrlf checkout could otherwise flatten them silently.
-*.rc text eol=crlf
-
-# The test scripts run under Git Bash on the Windows CI; a CRLF checkout makes
-# bash die on $'\r' on every line of them.
-*.test text eol=lf
-*.sh text eol=lf

.github/workflows/ci.yml

@@ -41,7 +41,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends \
             build-essential clang autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+            zlib1g-dev libssl-dev
 
       - name: Configure
         run: |
@@ -50,17 +50,12 @@ jobs:
           # committed generated files already let a plain checkout build.
           autoreconf -fi
           ./configure
-          # 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
 
       - name: Build
         run: make -j"$(nproc)"
 
       - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check
 
       - name: Print the test log on failure
         if: failure()
@@ -85,7 +80,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends \
             build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+            zlib1g-dev libssl-dev
 
       - name: Configure
         run: |
@@ -104,8 +99,7 @@ jobs:
           sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
             -exec mv {} {}.hidden \;
           ! command -v python3
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+          make check
 
       - name: Print the test log on failure
         if: failure()
@@ -126,70 +120,25 @@ jobs:
       - name: Install build dependencies
         run: |
           set -euo pipefail
-          brew install autoconf automake libtool autoconf-archive brotli zstd
+          brew install autoconf automake libtool autoconf-archive
 
       - name: Configure
         run: |
           set -euo pipefail
           ssl="$(brew --prefix openssl@3)"
-          brewp="$(brew --prefix)"
           autoreconf -fi
-          ./configure CPPFLAGS="-I${ssl}/include -I${brewp}/include" \
-            LDFLAGS="-L${ssl}/lib -L${brewp}/lib"
-          grep -q "define HTS_USEBROTLI 1" config.h
-          grep -q "define HTS_USEZSTD 1" config.h
+          ./configure CPPFLAGS="-I${ssl}/include" LDFLAGS="-L${ssl}/lib"
 
       - name: Build
         run: make -j"$(sysctl -n hw.ncpu)"
 
-      - name: Add loopback aliases (macOS lacks 127.0.0.2/.3)
-        # 19_local-connect-fallback needs the dead 127.0.0.2/.3 to refuse
-        # instantly like Linux; alias them onto lo0 so they don't stall to timeout.
-        run: |
-          set -euo pipefail
-          sudo ifconfig lo0 alias 127.0.0.2 up
-          sudo ifconfig lo0 alias 127.0.0.3 up
-
       - name: Test
-        run: |
-          jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check
 
       - name: Print the test log on failure
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
-  # Runtime smoke of the WebHTTrack launcher on macOS: it carries a Darwin-only
-  # browser path (open -W) and nothing else exercises htsserver. Install into a
-  # temp prefix, then check webhttrack brings up htsserver and serves the UI.
-  webhttrack-macos:
-    name: webhttrack smoke (macOS arm64)
-    runs-on: macos-14
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          brew install autoconf automake libtool autoconf-archive brotli zstd
-
-      - name: Build and install into a temp prefix
-        run: |
-          set -euo pipefail
-          ssl="$(brew --prefix openssl@3)"
-          brewp="$(brew --prefix)"
-          autoreconf -fi
-          ./configure CPPFLAGS="-I${ssl}/include -I${brewp}/include" \
-            LDFLAGS="-L${ssl}/lib -L${brewp}/lib" \
-            --prefix="$RUNNER_TEMP/inst"
-          make -j"$(sysctl -n hw.ncpu)"
-          make install
-
-      - name: Smoke-test webhttrack
-        run: bash tests/webhttrack-smoke.sh "$RUNNER_TEMP/inst"
-
   # Portability/hardening: 32-bit (i386) build on the x86-64 runner via multilib
   # -- no extra hardware. Exercises the 32-bit size_t/pointer ABI, where size
   # and bounds math can truncate or wrap in ways 64-bit never reveals (the axis
@@ -210,8 +159,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends \
             build-essential gcc-multilib autoconf automake libtool \
-            autoconf-archive zlib1g-dev:i386 libssl-dev:i386 \
-            libbrotli-dev:i386 libzstd-dev:i386
+            autoconf-archive zlib1g-dev:i386 libssl-dev:i386
 
       - name: Configure
         run: |
@@ -223,9 +171,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check
 
       - name: Print the test log on failure
         if: failure()
@@ -252,7 +198,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends \
             build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+            zlib1g-dev libssl-dev
 
       - name: Configure (sanitized)
         run: |
@@ -280,9 +226,7 @@ jobs:
         env:
           ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
           UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check
 
       - name: Print the test log on failure
         if: failure()
@@ -328,52 +272,12 @@ jobs:
           # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
           # skipped here (uninstrumented libz floods MSan with false positives).
           tests="$(cd tests && ls 01_engine-*.test | tr '\n' ' ')"
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs" TESTS="$tests"
+          make check TESTS="$tests"
 
       - name: Print the test log on failure
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
-  # libFuzzer smoke: build the fuzz/ harnesses over the pure hostile-input
-  # parsers and replay each seed corpus under ASan+UBSan+LeakSanitizer. Replay
-  # (not open-ended mutation) keeps CI deterministic -- it can't hit strjoker's
-  # catastrophic backtracking -- and pins the regression seeds for the bugs the
-  # fuzzers found. Deep discovery is a maintainer / OSS-Fuzz activity.
-  fuzz:
-    name: fuzz (libFuzzer corpus replay, clang)
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential clang autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
-
-      - name: Configure (fuzzers, static)
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure CC=clang \
-            CFLAGS="-fsanitize=address,undefined -fno-sanitize-recover=all -g -O1 -fno-omit-frame-pointer" \
-            LDFLAGS="-fsanitize=address,undefined" \
-            --enable-fuzzers --disable-shared
-
-      - name: Build
-        run: make -j"$(nproc)"
-
-      - name: Replay corpora
-        env:
-          ASAN_OPTIONS: detect_leaks=1:abort_on_error=1:halt_on_error=1
-          UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
-        run: bash fuzz/run-fuzzers.sh fuzz check
-
   # Optional-dependency build: compile and test with HTTPS/OpenSSL disabled --
   # the configuration users on minimal systems build, and one libssl is not even
   # installed here so configure cannot silently re-enable it. The matrix above
@@ -404,9 +308,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check
 
       - name: Print the test log on failure
         if: failure()
@@ -434,7 +336,7 @@ jobs:
           apt-get install -y --no-install-recommends \
             ca-certificates git \
             build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev \
+            zlib1g-dev libssl-dev \
             debhelper devscripts lintian fakeroot
 
       - uses: actions/checkout@v6
@@ -478,7 +380,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends \
             build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev libbrotli-dev libzstd-dev
+            zlib1g-dev libssl-dev
 
       - name: distcheck
         run: |
@@ -554,16 +456,6 @@ jobs:
       - name: shfmt
         run: shfmt -d -i 4 $SHELL_SCRIPTS
 
-      # MSBuild rejects a malformed .vcxproj with a bare MSB4025 and no build, so
-      # catch it here in seconds rather than on a Windows runner minutes in.
-      - name: XML well-formedness (MSBuild project files)
-        run: |
-          set -euo pipefail
-          for f in src/*.vcxproj; do
-            python3 -c "import sys,xml.dom.minidom; xml.dom.minidom.parse(sys.argv[1])" "$f"
-            echo "ok $f"
-          done
-
   # Check clang-format on CHANGED LINES ONLY. The engine predates clang-format
   # (it was shaped by an old Visual Studio formatter) and does not round-trip,
   # so we never reformat the whole tree -- only the lines a PR touches.

.github/workflows/codeql.yml

@@ -1,63 +0,0 @@
-# CodeQL static analysis (C). The security-extended suite covers the classes
-# this codebase actually fights: overflows, tainted-size allocs, format bugs.
-name: CodeQL
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-  schedule:
-    # Weekly re-scan of master so new/updated queries land without a push.
-    - cron: "17 4 * * 1"
-
-permissions:
-  contents: read
-
-concurrency:
-  group: codeql-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  analyze:
-    name: analyze (c-cpp)
-    runs-on: ubuntu-24.04
-    permissions:
-      contents: read
-      # Upload findings to the repo's code-scanning dashboard.
-      security-events: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev
-
-      - uses: github/codeql-action/init@v4
-        with:
-          languages: c-cpp
-          build-mode: manual
-          queries: security-extended
-          # fopen's umask-controlled 0666 is intended for mirror/cache/log
-          # output; the one credential file (cookies.txt) is kept 0600 on Unix.
-          config: |
-            query-filters:
-              - exclude:
-                  id: cpp/world-writable-file-creation
-
-      # Manual build: CodeQL traces the compiler, so build exactly what ships.
-      - name: Build
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure
-          make -j"$(nproc)"
-
-      - uses: github/codeql-action/analyze@v4
-        with:
-          category: "/language:c-cpp"

.github/workflows/windows-build.yml

@@ -1,199 +0,0 @@
-# Windows build of the engine (VS2022 v143 + vcpkg): libhttrack, the CLI,
-# webhttrack, proxytrack.
-#
-# The autotools CI covers the unix builds; this covers the MSVC one, which had
-# no coverage at all and had drifted (the old .vcproj pinned OpenSSL 1.0.1j).
-# libhttrack.dll is what the WinHTTrack GUI links against.
-name: windows-build
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  libhttrack:
-    runs-on: windows-2022
-    strategy:
-      fail-fast: false
-      matrix:
-        platform: [x64, Win32]
-        configuration: [Release]
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive   # coucal lives in src/coucal
-
-      # Located through vswhere rather than microsoft/setup-msbuild: the repo
-      # only allows GitHub-owned actions.
-      - name: Find MSBuild
-        shell: pwsh
-        run: |
-          $vswhere = "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe"
-          $msbuild = & $vswhere -latest -products * -requires Microsoft.Component.MSBuild `
-            -find MSBuild\**\Bin\MSBuild.exe | Select-Object -First 1
-          if (-not $msbuild) { throw "MSBuild not found" }
-          Write-Host "MSBuild: $msbuild"
-          "MSBUILD=$msbuild" | Out-File -FilePath $env:GITHUB_ENV -Append
-
-      - name: Enable vcpkg MSBuild integration
-        shell: pwsh
-        run: vcpkg integrate install
-
-      # httrack and webhttrack carry a ProjectReference to libhttrack, so building
-      # them builds it first; proxytrack is standalone.
-      - name: Build
-        shell: pwsh
-        run: |
-          foreach ($proj in @("libhttrack", "httrack", "webhttrack", "proxytrack")) {
-            & $env:MSBUILD "src\$proj.vcxproj" `
-              /m `
-              /p:Configuration=${{ matrix.configuration }} `
-              /p:Platform=${{ matrix.platform }} `
-              /p:VcpkgEnableManifest=true `
-              /flp:LogFile=msbuild-$proj.log`;Verbosity=normal
-            if ($LASTEXITCODE -ne 0) { throw "$proj failed" }
-          }
-
-      # WinHTTrack links src\$(Platform)\$(Configuration)\libhttrack.lib, so the
-      # import lib and the DLL both have to land there under that exact name.
-      - name: Check the binaries landed where they are expected
-        shell: pwsh
-        run: |
-          $dir = "src\${{ matrix.platform }}\${{ matrix.configuration }}"
-          $want = @("libhttrack.dll", "libhttrack.lib", "httrack.exe",
-                    "webhttrack.exe", "proxytrack.exe")
-          foreach ($f in $want) {
-            if (-not (Test-Path "$dir\$f")) { throw "missing $dir\$f" }
-            Write-Host "found $dir\$f"
-          }
-
-      # A CRT split across the exe/DLL boundary links fine and crashes on the
-      # first cross-heap free, so assert both sides import the *same* vcruntime.
-      # Also assert the machine type: Test-Path alone would accept an x64 binary
-      # sitting in the Win32 output dir.
-      - name: Check the CRT is shared across the boundary
-        shell: pwsh
-        run: |
-          $ErrorActionPreference = "Stop"
-          $dir = "src\${{ matrix.platform }}\${{ matrix.configuration }}"
-          $dumpbin = & "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe" `
-            -latest -find VC\Tools\MSVC\**\bin\Host*\*\dumpbin.exe | Select-Object -First 1
-          if (-not $dumpbin) { throw "dumpbin not found" }
-          $wantMachine = if ("${{ matrix.platform }}" -eq "x64") { "x64" } else { "x86" }
-
-          function Get-Crt($path) {
-            $out = & $dumpbin /dependents /headers $path
-            if ($LASTEXITCODE -ne 0) { throw "dumpbin failed on $path" }
-            ,@($out | Select-String -Pattern '^\s*(vcruntime\d+d?\.dll)$' |
-               ForEach-Object { $_.Matches[0].Groups[1].Value.ToLower() })
-          }
-
-          # Negative control: cmd.exe links the old msvcrt, not vcruntime140. If
-          # this came back non-empty the detector would match anything, and the
-          # assertion below would pass on a mismatched CRT too.
-          if ((Get-Crt "$env:SystemRoot\System32\cmd.exe").Count -ne 0) {
-            throw "negative control failed: the vcruntime detector matches anything"
-          }
-
-          $crts = @{}
-          foreach ($f in @("libhttrack.dll", "httrack.exe")) {
-            $crt = Get-Crt "$dir\$f"
-            if ($crt.Count -eq 0) { throw "$f imports no vcruntime: static or mismatched CRT" }
-            $crts[$f] = $crt
-
-            $hdr = & $dumpbin /headers "$dir\$f"
-            if (-not ($hdr | Select-String -SimpleMatch "machine ($wantMachine)")) {
-              throw "$f is not $wantMachine"
-            }
-            Write-Host "$f -> $($crt -join ',') ($wantMachine)"
-          }
-
-          $a = $crts["libhttrack.dll"] | Sort-Object
-          $b = $crts["httrack.exe"] | Sort-Object
-          if (Compare-Object $a $b) {
-            throw "CRT mismatch across the boundary: libhttrack.dll=$a httrack.exe=$b"
-          }
-
-      # The engine ships ~90 tests and none had ever run on Windows: "make check"
-      # is Linux/macOS only. These are the offline ones, driven from Git Bash
-      # against the native httrack.exe. They subsume the self-tests this step
-      # used to run inline (codecs, cache, fsize).
-      # The *_local-* ones crawl the bundled Python server over loopback: the real
-      # TLS handshake, cache and file writer, which nothing else on Windows covers.
-      - name: Run the engine test suite (offline tests)
-        shell: bash
-        working-directory: tests
-        timeout-minutes: 45
-        run: |
-          set -u
-          bin="$(cygpath -u "$GITHUB_WORKSPACE")/src/${{ matrix.platform }}/${{ matrix.configuration }}"
-          export PATH="$bin:$PATH"
-          command -v httrack >/dev/null || { echo "::error::no httrack.exe in $bin"; exit 1; }
-
-          # httrack.exe is native, so MSYS rewrites any argument shaped like a
-          # POSIX path, and a URL path is shaped exactly like one: "/a/b.html"
-          # reached the engine as "C:/Program Files/Git/a/b.html". Switch that
-          # off, and hand the tests a TMPDIR that is already a Windows path.
-          export MSYS_NO_PATHCONV=1
-          export MSYS2_ARG_CONV_EXCL='*'
-          TMPDIR="$(cygpath -m "$RUNNER_TEMP")"
-          export TMPDIR
-
-          # Mirror what configure hands the suite. LC_ALL sets the codeset MSYS maps
-          # a UTF-8 mirror name onto UTF-16 with, which the intl crawls "test -f".
-          export HTTPS_SUPPORT=yes BROTLI_ENABLED=yes ZSTD_ENABLED=yes
-          export LC_ALL=C.UTF-8
-
-          # A wedged crawl must not eat the job's whole timeout budget.
-          watchdog=""
-          command -v timeout >/dev/null && watchdog="timeout 600"
-
-          pass=0 fail=0 skip=0 failed="" skipped=""
-          for t in 00_runnable.test 01_engine-*.test 01_zlib-*.test \
-                   *_local-*.test 13_crawl_proxy_https.test; do
-            rc=0
-            # shellcheck disable=SC2086
-            $watchdog bash "$t" >"$t.log" 2>&1 || rc=$?
-            case "$rc" in
-              0) pass=$((pass + 1)); echo "PASS $t" ;;
-              77) skip=$((skip + 1)) skipped="$skipped $t"; echo "SKIP $t" ;;
-              *)
-                fail=$((fail + 1)) failed="$failed $t"
-                echo "FAIL $t (exit $rc)"
-                # These assert with `test "$(...)" == "..." || exit 1`, which
-                # says nothing at all on failure. Re-run traced.
-                bash -x "$t" >>"$t.log" 2>&1 || true
-                tail -n 25 "$t.log" | sed 's/^/      /'
-                ;;
-            esac
-          done
-          echo "ran=$((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.
-          expected_skips=" 48_local-crange-memresume.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:$failed"; exit 1; }
-
-      - name: Upload the test logs
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: engine-tests-${{ matrix.platform }}-${{ matrix.configuration }}
-          path: tests/*.log
-          if-no-files-found: warn
-
-      - name: Upload MSBuild logs
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: msbuild-${{ matrix.platform }}-${{ matrix.configuration }}
-          path: msbuild-*.log
-          if-no-files-found: ignore

.gitignore

@@ -34,9 +34,8 @@ Makefile
 *.so.*
 *.a
 
-# make dist output; dist/ holds httrack-gh-release staging artifacts.
+# make dist output.
 /httrack-*.tar.gz
-/dist/
 
 # Editor / autotools backup files.
 *~

AGENTS.md

@@ -6,19 +6,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 ## Build & test
 - Fresh clone first: `git submodule update --init src/coucal`
 - `./bootstrap` (regenerates `configure` via `autoreconf`; needs autoconf,
-  automake, libtool), then `bash configure && make -j"$(nproc)" && make check
-  -j"$(nproc)"`. Always pass `-j` to `make check`: the suite runs under
-  automake's parallel harness and each crawl test binds its own ephemeral-port
-  server, so `-j` never contends and a multi-minute serial run drops to
-  seconds. A new `.test` added to `$(TESTS)` is scheduled onto a free worker
-  automatically; only a test slower than the current longest raises the floor.
-  On a few-core Linux box, `-j` at 2x the core count is faster still: the tests
-  spend much of their wall time asleep (server trickles, httrack self-pacing),
-  so an idle core covers a sleeping one. CI uses `min(2*cores, 16)` on every
-  platform, macOS included: the test server raises its listen backlog
-  (`request_queue_size`) so macOS/BSD don't drop connections under a parallel
-  `-c16` bigcrawl the way Python's default backlog of 5 did.
-  Or run `sh build.sh` to do bootstrap + configure + make in one shot.
+  automake, libtool), then `bash configure && make && make check`. Or run
+  `sh build.sh` to do bootstrap + configure + make in one shot.
 
 ## Hard invariants
 - **Generated autotools files are NOT in git.** `configure`, every

CLAUDE.local.md

@@ -1 +0,0 @@
-/home/roche/git/httrack-works/CLAUDE.httrack.local.md

Makefile.am

@@ -1,5 +1,5 @@
 
-SUBDIRS = src man m4 libtest templates lang html tests fuzz
+SUBDIRS = src man m4 libtest templates lang html tests
 
 ACLOCAL_AMFLAGS = -I m4
 

README

@@ -40,6 +40,7 @@ These are the principals limits of HTTrack for that moment. Note that we did not
 that would have solved them.
 
 - Several scripts generating complex filenames may not find them (ex: img.src='image'+a+Mobj.dst+'.gif')
+- Some java classes may not find some files on them (class included)
 - Cgi-bin links may not work properly in some cases (parameters needed). To avoid them: use filters like -*cgi-bin*
 
 

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.12], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.11], [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
@@ -29,11 +29,11 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 3:4:0: 3.49.12 tail-appends one field (why_url) to httrackp and otherwise only
-# deletes dead comments; no struct layout or exported signature broke vs 3.49.11,
-# so it stays soname .so.3; bump revision.
+# 3:3:0: 3.49.11 only adds enum values, macros and inline helpers to the
+# installed headers (no struct layout or exported signature changed vs
+# 3.49.10), so it stays soname .so.3; bump revision.
 # (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
-VERSION_INFO="3:4:0"
+VERSION_INFO="3:3:0"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 
@@ -64,6 +64,16 @@ AC_SUBST(LT_CV_OBJDIR,$lt_cv_objdir)
 # Export version info
 AC_SUBST(VERSION_INFO)
 
+# Versioned plugin name for dlopen() in hts_create_opt(); soname major is
+# libtool's current - age, so this tracks VERSION_INFO bumps automatically.
+HTS_SONAME_MAJOR=$((${VERSION_INFO%%:*} - ${VERSION_INFO##*:}))
+case "$host_os" in
+darwin*) HTS_LIBHTSJAVA_NAME="libhtsjava.$HTS_SONAME_MAJOR.dylib" ;;
+*) HTS_LIBHTSJAVA_NAME="libhtsjava.so.$HTS_SONAME_MAJOR" ;;
+esac
+AC_DEFINE_UNQUOTED([HTS_LIBHTSJAVA_NAME], ["$HTS_LIBHTSJAVA_NAME"],
+  [Versioned libhtsjava runtime name, derived from VERSION_INFO])
+
 ### Default CFLAGS
 DEFAULT_CFLAGS="-Wall -Wformat -Wformat-security \
 -Wmultichar -Wwrite-strings -Wcast-qual -Wcast-align \
@@ -92,8 +102,7 @@ AX_CHECK_COMPILE_FLAG([-Wignored-qualifiers], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -
 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="$DEFAULT_CFLAGS -fstack-protector"])])
+AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$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="$DEFAULT_LDFLAGS -Wl,--discard-all"])
@@ -101,16 +110,9 @@ AX_CHECK_LINK_FLAG([-Wl,--no-undefined], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,
 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"])
 
-# Fortify libc calls (=3, else =2) unless the toolchain predefines it; skip
-# sanitizer builds, whose interceptors want the unfortified calls.
-case "$CFLAGS" in
-*-fsanitize=*) ;;
-*) AX_ADD_FORTIFY_SOURCE ;;
-esac
-
 # Force libc back into DT_NEEDED for libraries that reach it only through
-# libhttrack (the libtest callbacks), but only with a GNU-style linker; Apple
-# ld rejects these flags and links libSystem unconditionally.
+# libhttrack (libhtsjava, the libtest callbacks), but only with a GNU-style
+# linker; Apple ld rejects these flags and links libSystem unconditionally.
 AX_CHECK_LINK_FLAG([-Wl,--push-state,--no-as-needed,-lc,--pop-state],
 	[LIBC_FORCE_LINK="-Wl,--push-state,--no-as-needed,-lc,--pop-state"])
 AC_SUBST([LIBC_FORCE_LINK])
@@ -173,10 +175,6 @@ AC_CHECK_HEADERS([execinfo.h])
 ### zlib
 CHECK_ZLIB()
 
-### brotli and zstd content codings (optional)
-CHECK_BROTLI()
-CHECK_ZSTD()
-
 ### OpenSSL is explicitly enabled/disabled ?
 AC_MSG_CHECKING(whether to enable https support)
 AC_ARG_ENABLE([https],
@@ -312,37 +310,6 @@ AC_ARG_ENABLE([online-unit-tests],
 	])
 AC_SUBST(ONLINE_UNIT_TESTS,$online_unit_tests)
 
-## libFuzzer harnesses (fuzz/); requires clang
-AC_MSG_CHECKING(whether to build fuzzers)
-AC_ARG_ENABLE([fuzzers],
-	[AS_HELP_STRING([--enable-fuzzers],[Build libFuzzer harnesses in fuzz/ (requires clang) @<:@default=no@:>@])],
-	[
-	case "${enableval}" in
-	no|yes)
-		fuzzers=$enableval
-		AC_MSG_RESULT($enableval)
-		;;
-	*)
-		AC_MSG_ERROR(bad value for fuzzers, expected yes/no)
-		;;
-	esac
-	],
-	[
-	fuzzers=no
-	AC_MSG_RESULT(no)
-	])
-if test x"$fuzzers" = x"yes"; then
-	# Instrument the whole build for coverage; harnesses link -fsanitize=fuzzer.
-	AX_CHECK_COMPILE_FLAG([-fsanitize=fuzzer-no-link],
-		[DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fsanitize=fuzzer-no-link"],
-		[AC_MSG_ERROR([--enable-fuzzers requires libFuzzer support (clang)])])
-	# clang's static sanitizer runtimes clash with -Wl,--no-undefined on the .so.
-	if test x"$enable_shared" != x"no"; then
-		AC_MSG_ERROR([--enable-fuzzers requires --disable-shared])
-	fi
-fi
-AM_CONDITIONAL([FUZZERS], [test x"$fuzzers" = x"yes"])
-
 # Final output
 AC_CONFIG_FILES([
 Makefile
@@ -354,6 +321,5 @@ lang/Makefile
 html/Makefile
 libtest/Makefile
 tests/Makefile
-fuzz/Makefile
 ])
 AC_OUTPUT

debian/changelog

@@ -1,13 +1,3 @@
-httrack (3.49.12-1) unstable; urgency=medium
-
-  * New upstream release: security and crawl-correctness fixes (remote stack
-    overflow in Content-Type/-Encoding parsing, fuzzer-found parser over-reads,
-    world-readable cookies.txt, filter-pattern denial of service) plus a new
-    --why filter diagnostic; full list in history.txt.
-  * Build with _FORTIFY_SOURCE and -fstack-protector-strong.
-
- -- Xavier Roche <xavier@debian.org>  Fri, 10 Jul 2026 21:11:09 +0200
-
 httrack (3.49.11-1) unstable; urgency=medium
 
   * New upstream release: crawl correctness and security fixes (network-facing

debian/control

@@ -2,7 +2,7 @@ Source: httrack
 Section: web
 Maintainer: Xavier Roche <roche@httrack.com>
 Standards-Version: 4.7.4
-Build-Depends: debhelper-compat (= 14), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev, libbrotli-dev, libzstd-dev
+Build-Depends: debhelper-compat (= 14), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
 Rules-Requires-Root: no
 Homepage: http://www.httrack.com
 Vcs-Git: https://github.com/xroche/httrack.git

debian/copyright

@@ -7,8 +7,9 @@ Files: *
 Copyright: 1998-2026 Xavier Roche and other contributors
 License: GPL-3+
 Comment:
- htsbasenet.h links against the system OpenSSL library (originally by Eric
- Young); no OpenSSL/SSLeay code is bundled here.
+ The engine includes contributions from Yann Philippot (src/htsjava.c,
+ src/htsjava.h). htsbasenet.h links against the system OpenSSL library
+ (originally by Eric Young); no OpenSSL/SSLeay code is bundled here.
 
 Files: src/minizip/*
 Copyright: 1998-2010 Gilles Vollant

debian/libhttrack-dev.files

@@ -1,4 +1,5 @@
 usr/include/httrack
 usr/lib/*/libhttrack.{so}
+usr/lib/*/libhtsjava.{so}
 usr/share/httrack/libtest
 usr/lib/*/httrack/libtest

debian/libhttrack3.files

@@ -1,2 +1,3 @@
 usr/lib/*/libhttrack.so.3*
+usr/lib/*/libhtsjava.so.3*
 usr/share/httrack/templates

fuzz/Makefile.am

@@ -1,49 +0,0 @@
-# libFuzzer harnesses; built only with --enable-fuzzers (requires clang).
-if FUZZERS
-noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
-	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx \
-	fuzz-htsparse
-endif
-
-AM_CPPFLAGS = \
-	@DEFAULT_CFLAGS@ \
-	@THREADS_CFLAGS@ \
-	@V6_FLAG@ \
-	@LFS_FLAG@ \
-	-I$(top_srcdir)/src \
-	-I$(top_srcdir)/src/coucal
-
-# Static-link libhttrack.la: the internal symbols are hidden in the .so.
-AM_LDFLAGS = @DEFAULT_LDFLAGS@ -fsanitize=fuzzer -static-libtool-libs
-LDADD = $(top_builddir)/src/libhttrack.la $(THREADS_LIBS)
-
-fuzz_charset_SOURCES = fuzz-charset.c fuzz.h
-fuzz_meta_SOURCES = fuzz-meta.c fuzz.h
-fuzz_idna_SOURCES = fuzz-idna.c fuzz.h
-fuzz_entities_SOURCES = fuzz-entities.c fuzz.h
-fuzz_unescape_SOURCES = fuzz-unescape.c fuzz.h
-fuzz_filters_SOURCES = fuzz-filters.c fuzz.h
-fuzz_url_SOURCES = fuzz-url.c fuzz.h
-fuzz_header_SOURCES = fuzz-header.c fuzz.h
-fuzz_cachendx_SOURCES = fuzz-cachendx.c fuzz.h
-fuzz_htsparse_SOURCES = fuzz-htsparse.c fuzz.h
-
-# List corpus files explicitly: automake does not expand EXTRA_DIST globs.
-EXTRA_DIST = README.md run-fuzzers.sh \
-	corpus/charset/utf8.txt corpus/charset/latin1.txt corpus/charset/sjis.txt \
-	corpus/meta/meta-charset.html corpus/meta/meta-http-equiv.html \
-	corpus/idna/idna.txt corpus/idna/unicode.txt \
-	corpus/idna/regress-multilabel-leak.txt \
-	corpus/entities/entities.txt \
-	corpus/unescape/percent.txt \
-	corpus/filters/filter.bin corpus/filters/filter-size.bin \
-	corpus/filters/regress-empty-subject-unique.bin \
-	corpus/filters/redos-star-classes.bin \
-	corpus/url/http-url.txt corpus/url/relative-path.txt \
-	corpus/url/regress-file-empty-path.txt corpus/url/regress-long-path-abort.txt \
-	corpus/header/full-response.txt corpus/header/redirect.txt \
-	corpus/cachendx/new-format.txt corpus/cachendx/old-format.txt \
-	corpus/cachendx/regress-overadvance.bin \
-	corpus/cachendx/regress-truncated-entry.bin \
-	corpus/htsparse/basic.html corpus/htsparse/script-inscript.html \
-	corpus/htsparse/meta-usemap.html corpus/htsparse/malformed.html

fuzz/README.md

@@ -1,15 +0,0 @@
-# Fuzzing httrack
-
-libFuzzer harnesses for the pure hostile-input parsers (charset/UTF-8/IDNA codecs, entity and percent decoders, wildcard filters, URL splitter). Off by default; needs clang.
-
-```sh
-./bootstrap
-mkdir /var/tmp/bld-fuzz && cd /var/tmp/bld-fuzz
-CC=clang CFLAGS="-fsanitize=address,undefined -fno-sanitize-recover=all -g -O1" \
-  LDFLAGS="-fsanitize=address,undefined" \
-  bash /path/to/httrack/configure --enable-fuzzers --disable-shared
-make
-bash /path/to/httrack/fuzz/run-fuzzers.sh fuzz 60   # 60s per target
-```
-
-Run one target by hand: `fuzz/fuzz-url -max_total_time=300 corpusdir fuzz/corpus/url`. Seed corpora live in `corpus/<target>/`; a crash reproducer is replayed with `fuzz/fuzz-url crash-file`.

fuzz/corpus/cachendx/new-format.txt

@@ -1,7 +0,0 @@
-8
-CACHE-1.1
-28
-Mon, 01 Jan 2024 00:00:00 GMT
-www.example.com
-/index.html
-123

fuzz/corpus/cachendx/old-format.txt

@@ -1,5 +0,0 @@
-3
-1.0
-www.example.com
-/page
-5

fuzz/corpus/cachendx/regress-overadvance.bin

@@ -1,2 +0,0 @@
-32768
-CACHE-1.1

fuzz/corpus/cachendx/regress-truncated-entry.bin

@@ -1,5 +0,0 @@
-8
-CACHE-1.1
-1
-x
-www.example.com

fuzz/corpus/charset/latin1.txt

@@ -1 +0,0 @@
-
café naďve ¤

fuzz/corpus/charset/sjis.txt

@@ -1 +0,0 @@
-コンピュータ

fuzz/corpus/entities/entities.txt

@@ -1 +0,0 @@
-&<>A☃é&notarealentity;�

fuzz/corpus/filters/regress-empty-subject-unique.bin

@@ -1 +0,0 @@
-**((

fuzz/corpus/header/full-response.txt

@@ -1,10 +0,0 @@
-HTTP/1.1 200 OK
-Content-Type: text/html; charset=utf-8
-Content-Length: 1234
-Content-Encoding: gzip
-Last-Modified: Mon, 01 Jan 2024 00:00:00 GMT
-Etag: "abc"
-Location: http://example.com/x
-Set-Cookie: ID=42; path=/; domain=.example.com
-Content-Range: bytes 0-99/100
-Transfer-Encoding: chunked

fuzz/corpus/header/redirect.txt

@@ -1,3 +0,0 @@
-HTTP/1.0 301 Moved
-Location: /elsewhere
-Content-Disposition: attachment; filename="a.pdf"

fuzz/corpus/htsparse/basic.html

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

fuzz/corpus/htsparse/malformed.html

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

fuzz/corpus/htsparse/meta-usemap.html

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

fuzz/corpus/htsparse/script-inscript.html

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

fuzz/corpus/idna/idna.txt

@@ -1 +0,0 @@
-xn--bcher-kva.example.com

fuzz/corpus/idna/regress-multilabel-leak.txt

@@ -1 +0,0 @@
-büchev.例å­bücheple

fuzz/corpus/idna/unicode.txt

@@ -1 +0,0 @@
-bücher.例子.example

fuzz/corpus/meta/meta-charset.html

@@ -1 +0,0 @@
-<html><head><meta charset="utf-8"></head><body>x</body></html>

fuzz/corpus/meta/meta-content-first.html

@@ -1 +0,0 @@
-<meta content="text/html; charset=gb2312" http-equiv="content-type">

fuzz/corpus/meta/meta-http-equiv.html

@@ -1 +0,0 @@
-<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">

fuzz/corpus/meta/meta-truncated.html

@@ -1 +0,0 @@
-<meta charset='utf-8

fuzz/corpus/meta/meta-unquoted.html

@@ -1 +0,0 @@
-<meta   charset = utf-8 />

fuzz/corpus/unescape/percent.txt

@@ -1 +0,0 @@
-%41%zz%%20%c3%a9+%2e%2e%2f

fuzz/corpus/url/http-url.txt

@@ -1 +0,0 @@
-http://user:pass@www.example.com:8080/a/b/../c/./d.html?q=1#frag

fuzz/corpus/url/regress-file-empty-path.txt

@@ -1 +0,0 @@
-file://

fuzz/corpus/url/regress-long-path-abort.txt

@@ -1 +0,0 @@
-ftpumŠ[/../e0O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/.../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W//O/../f9O_i../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/.../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W//O/../f9O_i<5F>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._f9O_i../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/.../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W//O/../f9O_i<5F>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/i<>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_im<69>W/.¿ù../O/../9O_imÙ<6D>Š<EFBFBD>W/../_/../../e0O/../f9O_./f9O_i<5F>W/../O/../90O/./e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_imÙ<6D>Š<EFBFBD>W/../O/.._i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9O_i/../O/../f9O_i<5F>W/../O/../90O/../itpumÙ/ftpumŠ[/../e0O/../itpumÙ<6D>Š[/../O/../f9O_i<5F>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/../f9OmÙ<6D>Š<EFBFBD>W/../O/../9O_imÙ<6D>Š<EFBFBD>W/../O/..O_imÙ<6D>Š<EFBFBD>W/../O/../../e0O/9O_imÙ<6D>Š<EFBFBD>W/../O/../

fuzz/corpus/url/relative-path.txt

@@ -1 +0,0 @@
-ftp://ftp.example.com/pub/../file.txt

fuzz/fuzz-cachendx.c

@@ -1,65 +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 cache-index (.ndx) parser: a corrupt or truncated index must not
-   walk the length-prefixed cache_brstr/cache_binput scan past the buffer.
-   Mirrors the -#C cache-listing scan (htscoremain.c). */
-#include "fuzz.h"
-#include "htscache.h"
-#include "htslib.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  const char *const end = buf + size;
-  char firstline[256];
-  char *a = buf;
-
-  /* header: two length-prefixed fields (version, last-modified) */
-  a += cache_brstr(a, firstline, sizeof(firstline));
-  a += cache_brstr(a, firstline, sizeof(firstline));
-
-  /* body: newline-delimited host/file/position triples; the length-prefixed
-     scan must stay inside the buffer */
-  while (a != NULL && a < end) {
-    char BIGSTK line[HTS_URLMAXSIZE * 2];
-    char linepos[256];
-    int pos;
-
-    a = strchr(a + 1, '\n');
-    if (a == NULL)
-      break;
-    a++;
-    a += cache_binput(a, end, line, HTS_URLMAXSIZE);
-    a += cache_binput(a, end, line + strlen(line), HTS_URLMAXSIZE);
-    a += cache_binput(a, end, linepos, 200);
-    sscanf(linepos, "%d", &pos);
-    (void) pos;
-  }
-
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-charset.c

@@ -1,84 +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
-*/
-
-/* Fuzz the charset codecs: hts_convertStringToUTF8/FromUTF8 and the
-   UTF-8/UCS4 primitives (htscharset.c). First input byte picks the charset. */
-#include "fuzz.h"
-#include "htscharset.h"
-
-static const char *const charsets[] = {
-    "utf-8",    "iso-8859-1", "iso-8859-2", "iso-8859-15", "windows-1252",
-    "us-ascii", "shift_jis",  "euc-jp",     "iso-2022-jp", "gb2312",
-    "big5",     "euc-kr",     "koi8-r",     "utf-16",      "unknown-charset",
-};
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  const char *charset;
-  char *s;
-
-  if (size == 0)
-    return 0;
-  charset = charsets[data[0] % (sizeof(charsets) / sizeof(charsets[0]))];
-  data++, size--;
-  s = fuzz_strdup(data, size);
-
-  {
-    char *utf8 = hts_convertStringToUTF8(s, size, charset);
-    freet(utf8);
-  }
-  {
-    char *enc = hts_convertStringFromUTF8(s, size, charset);
-    freet(enc);
-  }
-  {
-    size_t nChars = 0;
-    hts_UCS4 *ucs = hts_convertUTF8StringToUCS4(s, size, &nChars);
-
-    if (ucs != NULL) {
-      char *back = hts_convertUCS4StringToUTF8(ucs, nChars);
-      freet(back);
-      freet(ucs);
-    }
-  }
-  {
-    size_t i = 0;
-
-    while (i < size) {
-      hts_UCS4 uc = 0;
-      const size_t nr = hts_readUTF8(s + i, size - i, &uc);
-      char out[8];
-
-      if (nr == 0)
-        break;
-      hts_writeUTF8(uc, out, sizeof(out));
-      i += nr;
-    }
-  }
-
-  freet(s);
-  return 0;
-}

fuzz/fuzz-entities.c

@@ -1,51 +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
-*/
-
-/* Fuzz the HTML entity decoder (htsencoding.c). First input byte picks the
-   destination size, so truncation bounds get exercised too. */
-#include "fuzz.h"
-#include "htsencoding.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static const size_t dsizes[] = {1, 2, 8, 64, 4096};
-  size_t dsize;
-  char *src, *dest;
-
-  if (size == 0)
-    return 0;
-  dsize = dsizes[data[0] % (sizeof(dsizes) / sizeof(dsizes[0]))];
-  data++, size--;
-  src = fuzz_strdup(data, size);
-  dest = malloct(dsize);
-
-  (void) hts_unescapeEntities(src, dest, dsize);
-  (void) hts_unescapeEntitiesWithCharset(src, dest, dsize, "iso-8859-1");
-
-  freet(dest);
-  freet(src);
-  return 0;
-}

fuzz/fuzz-filters.c

@@ -1,65 +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
-*/
-
-/* Fuzz the wildcard filter matcher (htsfilters.c; #148 bracket-range OOB was
-   here). Input splits on the first NUL: pattern, then subject string. */
-#include "fuzz.h"
-#include "htsfilters.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  const char *joker = buf;
-  const uint8_t *sep = memchr(data, '\0', size);
-  /* subject in its own allocation so ASan bounds it apart from the pattern */
-  char *nom = sep != NULL ? fuzz_strdup(sep + 1, (data + size) - (sep + 1))
-                          : fuzz_strdup(data + size, 0);
-
-  (void) strjoker(nom, joker, NULL, NULL);
-  {
-    LLint sz = (LLint) size;
-    int size_flag = 0;
-
-    (void) strjoker(nom, joker, &sz, &size_flag);
-  }
-  (void) strjokerfind(nom, joker);
-  {
-    char *filter = malloct(strlen(joker) + 2);
-    char *filters[1];
-    LLint sz = (LLint) size;
-    int size_flag = 0, depth = 0;
-
-    filter[0] = '-';
-    memcpy(filter + 1, joker, strlen(joker) + 1);
-    filters[0] = filter;
-    (void) fa_strjoker(0, filters, 1, nom, &sz, &size_flag, &depth);
-    freet(filter);
-  }
-
-  freet(nom);
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-header.c

@@ -1,74 +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 HTTP response-header parser (htslib.c): treatfirstline on the
-   status line, treathead on each following header. Both consume raw bytes
-   off the wire and copy fields into fixed htsblk buffers; treathead also
-   mutates its line in place and drives cookie parsing. */
-#include "fuzz.h"
-#include "htslib.h"
-#include "htsbauth.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  htsblk r;
-  t_cookie *cookie = calloct(1, sizeof(*cookie));
-  char *line = malloct(size + 1);
-  char *p = buf;
-  int first = 1;
-
-  memset(&r, 0, sizeof(r));
-  cookie->max_len = (int) sizeof(cookie->data);
-  r.location = malloct(HTS_URLMAXSIZE * 2);
-  r.location[0] = '\0';
-
-  /* feed one header line at a time, as the receive loop does */
-  while (p != NULL && *p != '\0') {
-    char *nl = strchr(p, '\n');
-    size_t n = (nl != NULL) ? (size_t) (nl - p) : strlen(p);
-    size_t i, len = 0;
-
-    /* binput drops every '\r' on the wire; mirror it */
-    for (i = 0; i < n; i++)
-      if (p[i] != '\r')
-        line[len++] = p[i];
-    line[len] = '\0';
-    if (first) {
-      treatfirstline(&r, line);
-      first = 0;
-    } else {
-      treathead(cookie, "www.example.com", "/", &r, line);
-    }
-    p = (nl != NULL) ? nl + 1 : NULL;
-  }
-
-  freet(r.location);
-  freet(line);
-  freet(cookie);
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-htsparse.c

@@ -1,175 +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/>.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the real htsparse() over a mocked engine: the minimal crawl state
-   httpmirror() builds, then a page walked through the parser and discarded. The
-   str/stre wiring below mirrors htsparse()'s call site in htscore.c; update it
-   in lockstep if those structs gain a field the parser reads. */
-#include "fuzz.h"
-
-#include "httrack-library.h"
-#include "htscore.h"
-#include "htsback.h"
-#include "htshash.h"
-#include "htsrobots.h"
-#include "htsparse.h"
-#include "htsmodules.h"
-#include "coucal.h"
-
-/* htsparse ignores str.addLink on the internal parse; stub it. */
-static int fuzz_addlink(htsmoduleStruct *str, char *link) {
-  (void) str;
-  (void) link;
-  return 0;
-}
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static int inited = 0;
-
-  httrackp *opt;
-  cache_back cache;
-  hash_struct hash;
-  robots_wizard robots;
-  struct_back *sback;
-  char **filters = NULL;
-  int filptr = 0;
-
-  htsblk r;
-  htsmoduleStruct str;
-  htsmoduleStructExtended stre;
-  int ptr, error = 0, store_errpage = 0;
-  int makeindex_done = 0, makeindex_links = 0;
-  FILE *makeindex_fp = NULL;
-  char makeindex_firstlink[HTS_URLMAXSIZE * 2] = "";
-  LLint stat_fragment = 0, makestat_total = 0;
-  int makestat_lnk = 0;
-  char base[HTS_URLMAXSIZE * 2] = "";
-  char codebase[HTS_URLMAXSIZE * 2] = "";
-  char err_msg[1024] = "";
-
-  if (!inited) {
-    hts_init();
-    inited = 1;
-  }
-
-  opt = hts_create_opt();
-  opt->log = opt->errlog = NULL;
-  opt->robots = 0;
-
-  memset(&cache, 0, sizeof(cache));
-  cache.type = 0; /* no on-disk cache */
-  cache.hashtable = coucal_new(0);
-  cache.cached_tests = coucal_new(0);
-  coucal_value_is_malloc(cache.cached_tests, 1);
-
-  memset(&robots, 0, sizeof(robots));
-  strcpybuff(robots.adr, "!");
-  opt->robotsptr = &robots;
-
-  opt->maxfilter = maximum(opt->maxfilter, 128);
-  filters_init(&filters, opt->maxfilter, 0);
-  opt->filters.filters = &filters;
-  opt->filters.filptr = &filptr;
-
-  opt->hash = &hash;
-  hts_record_init(opt);
-  hash_init(opt, &hash, opt->urlhack);
-  hash.liens = (const lien_url *const *const *) &opt->liens;
-
-  sback = back_new(opt, opt->maxsoc * 32 + 1024);
-
-  /* ptr=1 (index 1 is the parsed page) selects full HTML parsing + the
-     rewriter; urladr()/urlfil()/savename() alias heap(ptr), save=/dev/null. */
-  hts_record_link(opt, "example.com", "/", "/dev/null", "", "", NULL);
-  hts_record_link(opt, "example.com", "/index.html", "/dev/null", "", "", NULL);
-  ptr = 1;
-
-  /* NUL-terminated in a size+1 alloc: htsparse one-past-reads onto the NUL. */
-  hts_init_htsblk(&r);
-  r.statuscode = 200;
-  r.size = (LLint) size;
-  r.adr = malloct(size + 1);
-  if (size)
-    memcpy(r.adr, data, size);
-  r.adr[size] = '\0';
-  strcpybuff(r.contenttype, "text/html");
-
-  memset(&str, 0, sizeof(str));
-  memset(&stre, 0, sizeof(stre));
-  str.err_msg = err_msg;
-  str.filename = heap(ptr)->sav;
-  str.mime = r.contenttype;
-  str.url_host = heap(ptr)->adr;
-  str.url_file = heap(ptr)->fil;
-  str.size = (int) r.size;
-  str.addLink = fuzz_addlink;
-  str.opt = opt;
-  str.sback = sback;
-  str.cache = &cache;
-  str.hashptr = &hash;
-  str.numero_passe = 0;
-  str.ptr_ = &ptr;
-  str.page_charset_ = NULL;
-
-  stre.r_ = &r;
-  stre.error_ = &error;
-  stre.exit_xh_ = &opt->state.exit_xh;
-  stre.store_errpage_ = &store_errpage;
-  stre.base = base;
-  stre.codebase = codebase;
-  stre.filters_ = &filters;
-  stre.filptr_ = &filptr;
-  stre.robots_ = &robots;
-  stre.hash_ = &hash;
-  stre.makeindex_done_ = &makeindex_done;
-  stre.makeindex_fp_ = &makeindex_fp;
-  stre.makeindex_links_ = &makeindex_links;
-  stre.makeindex_firstlink_ = makeindex_firstlink;
-  stre.template_header_ = "";
-  stre.template_body_ = "";
-  stre.template_footer_ = "";
-  stre.stat_fragment_ = &stat_fragment;
-  stre.makestat_time = 0;
-  stre.makestat_fp = NULL;
-  stre.makestat_total_ = &makestat_total;
-  stre.makestat_lnk_ = &makestat_lnk;
-  stre.maketrack_fp = NULL;
-
-  (void) htsparse(&str, &stre);
-
-  freet(r.adr);
-  back_delete_all(opt, &cache, sback);
-  back_free(&sback);
-  hash_free(&hash);
-  coucal_delete(&cache.hashtable);
-  coucal_delete(&cache.cached_tests);
-  checkrobots_free(&robots);
-  if (filters != NULL) {
-    if (filters[0] != NULL)
-      freet(filters[0]);
-    freet(filters);
-  }
-  hts_record_free(opt);
-  hts_free_opt(opt);
-  return 0;
-}

fuzz/fuzz-idna.c

@@ -1,47 +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
-*/
-
-/* Fuzz the IDNA/punycode codec (htscharset.c, CVE-prone lineage). */
-#include "fuzz.h"
-#include "htscharset.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *s = fuzz_strdup(data, size);
-
-  {
-    char *idna = hts_convertStringUTF8ToIDNA(s, size);
-    freet(idna);
-  }
-  {
-    char *utf8 = hts_convertStringIDNAToUTF8(s, size);
-    freet(utf8);
-  }
-  (void) hts_isStringIDNA(s, size);
-
-  freet(s);
-  return 0;
-}

fuzz/fuzz-meta.c

@@ -1,40 +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
-*/
-
-/* Fuzz hts_getCharsetFromMeta (htscharset.c): scans raw attacker HTML for a
-   <meta> charset declaration. */
-#include "fuzz.h"
-#include "htscharset.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *html = fuzz_strdup(data, size);
-  char *charset = hts_getCharsetFromMeta(html, size);
-
-  freet(charset);
-  freet(html);
-  return 0;
-}

fuzz/fuzz-unescape.c

@@ -1,53 +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
-*/
-
-/* Fuzz the URL percent-decoders (htslib.c). First input byte picks the
-   output buffer size, so the bounded-copy contract is exercised. */
-#include "fuzz.h"
-#include "httrack-library.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static const size_t bsizes[] = {1, 2, 16, 256, 8192};
-  size_t bsize;
-  char *s, *catbuff;
-
-  if (size == 0)
-    return 0;
-  bsize = bsizes[data[0] % (sizeof(bsizes) / sizeof(bsizes[0]))];
-  data++, size--;
-  s = fuzz_strdup(data, size);
-  catbuff = malloct(bsize);
-
-  (void) unescape_http(catbuff, bsize, s);
-  (void) unescape_http_unharm(catbuff, bsize, s, 0);
-  (void) unescape_http_unharm(catbuff, bsize, s, 1);
-  unescape_amp(s);
-
-  freet(catbuff);
-  freet(s);
-  return 0;
-}

fuzz/fuzz-url.c

@@ -1,49 +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
-*/
-
-/* Fuzz the URL splitter and path normalizer (htslib.c): ident_url_absolute
-   is the first parser to touch a raw URL; fil_simplifie collapses ./ and ../
-   in place. */
-#include "fuzz.h"
-#include "htscore.h"
-#include "htslib.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *s = fuzz_strdup(data, size);
-  lien_adrfil *af = calloct(1, sizeof(*af));
-  /* fil_simplifie rewrites in place and may grow an empty path to "./" */
-  char *path = malloct(size + 3);
-
-  (void) ident_url_absolute(s, af);
-  memcpy(path, s, size + 1);
-  fil_simplifie(path);
-
-  freet(path);
-  freet(af);
-  freet(s);
-  return 0;
-}

fuzz/run-fuzzers.sh

@@ -1,41 +0,0 @@
-#!/bin/bash
-# Drive every built harness against its seed corpus.
-#   run-fuzzers.sh <build-fuzz-dir> check       deterministic replay (CI smoke)
-#   run-fuzzers.sh <build-fuzz-dir> [seconds]   timed mutation run (discovery)
-# Replay is crash/leak-only and never mutates; the per-unit -timeout guards
-# both modes against pathological slowdowns (e.g. pre-#501 strjoker).
-set -euo pipefail
-
-srcdir=$(cd "$(dirname "$0")" && pwd)
-bld=${1:?usage: run-fuzzers.sh <build-fuzz-dir> [check|seconds]}
-mode=${2:-20}
-
-status=0
-for f in "$bld"/fuzz-*; do
-    if [ ! -f "$f" ] || [ ! -r "$f" ]; then continue; fi
-    case "$f" in *.o | *.c | *.dSYM) continue ;; esac
-    name=$(basename "$f")
-    corpus="$srcdir/corpus/${name#fuzz-}"
-    if [ "$mode" = "check" ]; then
-        echo "=== $name (replay) ==="
-        [ -d "$corpus" ] || continue
-        if ! "$f" -runs=0 -timeout=25 -rss_limit_mb=2048 "$corpus"; then
-            echo "*** $name FAILED on its corpus" >&2
-            status=1
-        fi
-        continue
-    fi
-    work=$(mktemp -d)
-    args=("$work")
-    [ -d "$corpus" ] && args+=("$corpus")
-    echo "=== $name (${mode}s) ==="
-    if ! "$f" -max_total_time="$mode" -timeout=25 -rss_limit_mb=2048 \
-        -artifact_prefix="$work/" -print_final_stats=1 "${args[@]}"; then
-        echo "*** $name FAILED; artifacts:" >&2
-        ls -l "$work" >&2
-        status=1
-    else
-        rm -rf "$work"
-    fi
-done
-exit $status

history.txt

@@ -4,23 +4,6 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
-3.49-12
-+ New: --why explains which filter rule accepts or rejects a given URL, then exits (#505)
-+ Fixed: links carrying raw UTF-8 bytes were fetched double-encoded and 404'd (#516)
-+ Fixed: an uncompressed body mislabeled as gzip no longer loses the page (#515)
-+ Fixed: remote stack overflow and uninitialized read in Content-Type/-Encoding parsing (#506)
-+ Fixed: several over-reads and a leak in the filter, URL and IDNA parsers (#499)
-+ Fixed: bound the cache-index (.ndx) parser to its buffer (#507)
-+ Fixed: catastrophic backtracking on '*'-heavy filter patterns (#513)
-+ Fixed: cookies.txt was created world-readable (#511)
-+ Fixed: a single corrupt cache entry no longer aborts the whole mirror (#494)
-+ Fixed: cache-reconcile policy was broken for zip caches (#491, #493, #495)
-+ Fixed: cancelling a crawl mid type-check no longer orphans .delayed placeholders (#496)
-+ Fixed: detect URLs after the first inline script and in mid-tag attributes (#497)
-+ Changed: build with _FORTIFY_SOURCE and -fstack-protector-strong (#504)
-+ Changed: removed the pre-3.31 (.dat/.ndx) cache import (#512)
-+ Changed: multiple internal hardening and build improvements (libFuzzer harnesses, CodeQL, dead-code removal)
-
 3.49-11
 + New: parse robots.txt Allow rules and path wildcards per RFC 9309 (#452)
 + New: advertise deflate in Accept-Encoding and decode deflate responses (#450)

html/faq.html

@@ -609,9 +609,10 @@ most mirrors do work. We still are working to improve the mirror quality of HTTr
 <br>
 
 </a><a NAME="Q2b">Q: <strong>Some Java applets do not work properly!</strong><br>
-A: <em>Java applets may not work in some cases, because HTTrack does not parse compiled class files to find
-the resources they load. Java applets often need to be online anyway, since remote files are fetched directly
-at runtime.<br>
+A: <em>Java applets may not work in some cases, for example if HTTrack failed to detect all included classes
+or files called within the class file. Sometimes, Java applets need to be online, because remote files are
+directly caught. Finally, the site structure can be incompatible with the class (always try to keep the original site structure
+when you want to get Java classes)<br>
 If there is no way to make some classes work properly, you can exclude them with the filters. 
 They will be available, but only online.
 </em>

html/fcguide.html

@@ -243,7 +243,7 @@ Build options:
 Spider options:
   bN accept cookies in cookies.txt (0=do not accept,* 1=accept) (--cookies[=N])
   u  check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (--check-type[=N])
-  j *parse scripts (j0 don't parse) (--parse-java[=N])
+  j *parse Java Classes (j0 don't parse) (--parse-java[=N])
   sN follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always) (--robots[=N])
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (--http-10)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!) (--tolerant)
@@ -417,7 +417,7 @@ site. Specifically, the defauls are:
   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)
-  j *parse scripts (j0 don't parse)
+  j *parse Java Classes (j0 don't parse)
   sN  follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always)
   C  create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before)
   f *log file mode
@@ -497,9 +497,9 @@ about your browser retaining them.
 <p align=justify> This causes different document types to be analyzed
 differently.
 
-<pre><b><i>  j *parse scripts (j0 don't parse) </i></b></pre>
+<pre><b><i>  j *parse Java Classes (j0 don't parse) </i></b></pre>
 
-<p align=justify> This causes scripts to be parsed looking for
+<p align=justify> This causes Java class files to be parsed looking for
 URLs.
 
 <pre><b><i>  sN  follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always) </i></b></pre>
@@ -1178,7 +1178,7 @@ accepted and sent back in order to allow access.
 Spider options:
  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)
- j   *parse scripts (j0 don't parse)
+ j   *parse Java Classes (j0 don't parse)
  sN  follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always)
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!)
@@ -2451,10 +2451,12 @@ work.  We still are working to improve the mirror quality of HTTrack.
 
 <p align=justify><b>Q: Some Java applets do not work properly! </b>
 
-<p align=justify> A: Java applets may not work in some cases, because
-HTTrack does not parse compiled class files to find the resources they
-load.  Java applets often need to be online anyway, since remote files
-are fetched directly at runtime.
+<p align=justify> A: Java applets may not work in some cases, for
+example if HTTrack failed to detect all included classes or files called
+within the class file.  Sometimes, Java applets need to be online,
+because remote files are directly caught.  Finally, the site structure
+can be incompatible with the class (always try to keep the original site
+structure when you want to get Java classes)
 
 <p align=justify> If there is no way to make some classes work properly,
 you can exclude them with the filters.  They will be available, but only

html/httrack.man.html

@@ -764,9 +764,9 @@ check, * u1 check but /, u2 check always)
 <td width="78%">
 
 
-<p>*parse scripts (j0 don t parse, bitmask: |1 parse
-default, |4 don t parse .js |8 don t be aggressive)
-(--parse-java[=N])</p></td></tr>
+<p>*parse Java Classes (j0 don t parse, bitmask: |1 parse
+default, |2 don t parse .class |4 don t parse .js |8 don t
+be aggressive) (--parse-java[=N])</p></td></tr>
 <tr valign="top" align="left">
 <td width="11%"></td>
 <td width="6%">
@@ -889,8 +889,8 @@ only) (--protocol[=N])</p></td></tr>
 <td width="78%">
 
 
-<p>disable a specific external mime module (-%w
-httrack-plugin) (--disable-module &lt;param&gt;)</p></td></tr>
+<p>disable a specific external mime module (-%w htsswf -%w
+htsjava) (--disable-module &lt;param&gt;)</p></td></tr>
 </table>
 
 <p style="margin-left:11%; margin-top: 1em"><b>Browser
@@ -2175,6 +2175,10 @@ Several scripts generating complex filenames may not find
 them (ex:
 img.src=&rsquo;image&rsquo;+a+Mobj.dst+&rsquo;.gif&rsquo;)</small></p>
 
+<p style="margin-left:11%; margin-top: 1em"><small>- Some
+java classes may not find some files on them (class
+included)</small></p>
+
 <p style="margin-left:11%; margin-top: 1em"><small>-
 Cgi-bin links may not work properly in some cases
 (parameters needed). To avoid them: use filters like

html/options.html

@@ -288,8 +288,8 @@ This option define whether the engine has to abandon a host if a timeout/"too sl
 &P extended parsing, attempt to parse all links (even in unknown tags or Javascript)
 This option activates the extended parsing, that attempt to find links in unknown Html code/javascript
 
-j *parse scripts (j0 don't parse)
-This option defines whether the engine has to parse scripts or not to catch included files
+j *parse Java Classes (j0 don't parse)
+This option define whether the engine has to parse java files or not to catch included files
 
 I *make an index (I0 don't make)
 This option define whether the engine has to generate an index.html on the top directory

html/plug.html

@@ -103,219 +103,220 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
 
 <br>
 
-You can write external functions to be plugged in the httrack library very easily. 
-We'll see there some examples.
+You can write external functions to be plugged in the httrack library very easily. 
+We'll see there some examples.
 
 <br><br>
-
-The <tt>httrack</tt> commandline tool allows (since the 3.30 release) to plug external functions to various callbacks defined in httrack.
-The 3.41 release introduces a cleaned up verion of callbacks, with two major changes:
-<ul>
-<li>Cleaned up function prototypes, with two arguments always passed (the caller carg structure, and the httrackp* object), convenient to pass an user-defined pointer (see <tt>CALLBACKARG_USERDEF(carg)</tt>)</li>
-<li>The httrackp* option structure can be directly accessed to plug callbacks (no need to give the callback name and function name in the commandline!)</li>
-<li>The callback plug is made through the CHAIN_FUNCTION() helper, allowing to chain multiple callbacks of the same type (the callbacks MUST preserve the chain by calling ancestors)</li>
-</ul>
-
-<br>
-References: 
-<ul>
-<li>the <tt>httrack-library.h</tt> prototype file
-<br />
+
+The <tt>httrack</tt> commandline tool allows (since the 3.30 release) to plug external functions to various callbacks defined in httrack.
+The 3.41 release introduces a cleaned up verion of callbacks, with two major changes:
+<ul>
+<li>Cleaned up function prototypes, with two arguments always passed (the caller carg structure, and the httrackp* object), convenient to pass an user-defined pointer (see <tt>CALLBACKARG_USERDEF(carg)</tt>)</li>
+<li>The httrackp* option structure can be directly accessed to plug callbacks (no need to give the callback name and function name in the commandline!)</li>
+<li>The callback plug is made through the CHAIN_FUNCTION() helper, allowing to chain multiple callbacks of the same type (the callbacks MUST preserve the chain by calling ancestors)</li>
+</ul>
+
+<br>
+References: 
+<ul>
+<li>the <tt>httrack-library.h</tt> prototype file
+<br />
 Note: the <i>Initialization</i>, <i>Main functions</i>, <i>Options handling</i> and <i>Wrapper functions</i> sections are generally the only ones to be considered.
 </li>
-<li>the <tt>htsdefines.h</tt> prototype file, which describes callback function prototypes</li>
-<li>the <tt>htsopt.h</tt> prototype file, which describes the full httrackp* structure</li>
-<li>the <tt>callbacks-example*.c</tt> files given in the httrack archive</li>
-<li>the example given at the end of this document</li>
-</ul>
-
-<br />
-Below the list of functions to be defined in the module (plugin).<br />
-<br />
-
-<table width="100%">
-<tr><td><b><i>module function name</i></b></td><td><b>function description</b></td><td><b>function signature</b></td></tr>
-<tr><td background="img/fade.gif"><i>hts_plug</i></td><td background="img/fade.gif">
-The module entry point. The opt structure can be used to plug callbacks, using the CHAIN_FUNCTION() macro helper. The argv optional argument is the one passed in the commandline as --wrapper parameter.<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)<br />
-
-<br />
-Wrappers can be plugged inside hts_plug() using:<br />
-<tt>
-CHAIN_FUNCTION(opt, &lt;callback name&gt;, &lt;our callback function name&gt;, &lt;our callback function optional custom pointer argument&gt;);
-</tt>
-<br />
-
-<br />
-Example:
-<br />
-<tt>
-CHAIN_FUNCTION(opt, check_html, process, userdef);
-</tt>
-<br />
-
-</td><td background="img/fade.gif"><tt>extern int hts_plug(httrackp *opt, const char* argv);</tt></td></tr>
-
-<!-- -->
-
-<tr><td background="img/fade.gif"><i>hts_unplug</i></td><td background="img/fade.gif">
-The module exit point. To free allocated resources without using global variables, use the uninit callback (see below)</td><td background="img/fade.gif"><tt>extern int hts_unplug(httrackp *opt);</tt></td></tr>
-
-</table>
-
-
-<br />
-Note that all callbacks (except init and uninit) take as first two argument:
-<ul>
-<li>the t_hts_callbackarg structure<br />
-this structure holds the callback chain (parent callbacks defined before the current callback) pointers, and the user-defined pointer ; see <tt>CALLBACKARG_USERDEF(carg)</tt>)
-</li>
-<li>the httrackp structure<br />
-this structure, holding all current httrack options and mirror state, can be read or mofidied
-</li>
-</ul>
-
-<br />
-Below the list of callbacks, and associated external wrappers.
-
-<table width="100%">
-<tr><td><b><i>callback name</i></b></td><td><b>callback description</b></td><td><b>callback function signature</b></td></tr>
-
-<tr><td background="img/fade.gif"><i>init</i></td><td background="img/fade.gif">Note: the use the "start" callback is advised. Called during initialization.<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>uninit</i></td><td background="img/fade.gif">Note: the use os the "end" callback is advised.<br />Called during un-initialization<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>start</i></td><td background="img/fade.gif">Called when the mirror starts. The <tt>opt</tt> structure passed lists all options defined for this mirror. You may modify the <tt>opt</tt> structure to fit your needs.<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)</td><td background="img/fade.gif"><tt>int mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>end</i></td><td background="img/fade.gif">Called when the mirror ends<br>return value: 1 upon success, 0 upon error (the mirror will then be considered aborted)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>chopt</i></td><td background="img/fade.gif">Called when options are to be changed. The <tt>opt</tt> structure passed lists all options, updated to take account of recent changes<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>preprocess</i></td><td background="img/fade.gif">Called when a document (which is an html document) is to be parsed (original, not yet modified document). The <tt>html</tt> address points to the document data address (char**), and the <tt>length</tt> address points to the lenth of this document. Both pointer values (address and size) can be modified to change the document. It is up to the callback function to reallocate the given pointer (using the hts_realloc()/hts_free() library functions), which will be free()'ed by the engine. Hence, return of static buffers is strictly forbidden, and the use of hts_strdup() in such cases is advised. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the new pointers can be applied (default value)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char** html, int* len, const char* url_address, const char* url_file);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>postprocess</i></td><td background="img/fade.gif">Called when a document (which is an html document) is parsed and transformed (links rewritten). The <tt>html</tt> address points to the document data address (char**), and the <tt>length</tt> address points to the lenth of this document. Both pointer values (address and size) can be modified to change the document. It is up to the callback function to reallocate the given pointer (using the hts_realloc()/hts_free() library functions), which will be free()'ed by the engine. Hence, return of static buffers is strictly forbidden, and the use of hts_strdup() in such cases is advised. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the new pointers can be applied (default value)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char** html, int* len, const char* url_address, const char* url_file);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>check_html</i></td><td background="img/fade.gif">Called when a document (which may not be an html document) is to be parsed. The <tt>html</tt> address points to the document data, of lenth <tt>len</tt>. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the parsing can be processed, 0 if the file must be skipped without being parsed</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* html, int len, const char* url_address, const char* url_file);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>query</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question. The <tt>question</tt> string contains the question for the (human) user<br>return value: the string answer ("" for default reply)</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>query2</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>query3</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>loop</i></td><td background="img/fade.gif">Called periodically (informational, to display statistics)<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, lien_back* back, int back_max, int back_index, int lien_tot, int lien_ntot, int stat_time, hts_stat_struct* stats);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>check_link</i></td><td background="img/fade.gif">Called when a link has to be tested. The <tt>adr</tt> and <tt>fil</tt> are the address and URI of the link being tested. The passed <tt>status</tt> value has the following meaning: 0 if the link is to be accepted by default, 1 if the link is to be refused by default, and -1 if no decision has yet been taken by the engine<br>return value: same meaning as the passed <tt>status</tt> value ; you may generally return -1 to let the engine take the decision by itself</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr, const char* fil, int status);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>check_mime</i></td><td background="img/fade.gif">Called when a link download has begun, and needs to be tested against its MIME type. The <tt>adr</tt> and <tt>fil</tt> are the address and URI of the link being tested, and the <tt>mime</tt> string contains the link type being processed. The passed <tt>status</tt> value has the following meaning: 0 if the link is to be accepted by default, 1 if the link is to be refused by default, and -1 if no decision has yet been taken by the engine<br>return value: same meaning as the passed <tt>status</tt> value ; you may generally return -1 to let the engine take the decision by itself</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr, const char* fil, const char* mime, int status);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>pause</i></td><td background="img/fade.gif">Called when the engine must pause. When the <tt>lockfile</tt> passed is deleted, the function can return<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* lockfile);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>filesave</i></td><td background="img/fade.gif">Called when a file is to be saved on disk<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* file);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>filesave2</i></td><td background="img/fade.gif">Called when a file is to be saved or checked on disk<br>The hostname, filename and local filename are given. Two additional flags tells if the local file is new (is_new), if the local file is to be modified (is_modified), and if the file was not updated remotely (not_updated).<br>(!is_new && !is_modified): the file is up-to-date, and will not be modified<br>(is_new && is_modified): a new file will be written (or an updated file is being written)<br>(!is_new && is_modified): a file is being updated (append)<br>(is_new && !is_modified): an empty file will be written ("do not recatch locally erased files")<br>not_updated: the file was not re-downloaded because it was up-to-date (no data transferred again)<br><br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* hostname, const char* filename, const char* localfile, int is_new, int is_modified, int not_updated);</tt></td></tr>
-
-<tr><td background="img/fade.gif"><i>linkdetected</i></td><td background="img/fade.gif">Called when a link has been detected<br>return value: 1 if the link can be analyzed, 0 if the link must not even be considered</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* link);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>linkdetected2</i></td><td background="img/fade.gif">Called when a link has been detected<br>return value: 1 if the link can be analyzed, 0 if the link must not even be considered</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* link, const const char* tag_start);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>xfrstatus</i></td><td background="img/fade.gif">Called when a file has been processed (downloaded, updated, or error)<br>return value: must return 1</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, lien_back* back);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>savename</i></td><td background="img/fade.gif">Called when a local filename has to be processed. The <tt>adr_complete</tt> and <tt>fil_complete</tt> are the address and URI of the file being saved ; the <tt>referer_adr</tt> and <tt>referer_fil</tt> are the address and URI of the referer link. The <tt>save</tt> string contains the local filename being used. You may modifiy the <tt>save</tt> string to fit your needs, up to 1024 bytes (note: filename collisions, if any, will be handled by the engine by renaming the file into file-2.ext, file-3.ext ..).<br>return value: must return 1</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr_complete, const char* fil_complete, const char* referer_adr, const char* referer_fil, char* save);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>sendhead</i></td><td background="img/fade.gif">Called when HTTP headers are to be sent to the remote server. The <tt>buff</tt> buffer contains text headers, <tt>adr</tt> and <tt>fil</tt> the URL, and <tt>referer_adr</tt> and <tt>referer_fil</tt> the referer URL. The <tt>outgoing</tt> structure contains all information related to the current slot.<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* buff, const char* adr, const char* fil, const char* referer_adr, const char* referer_fil, htsblk* outgoing);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>receivehead</i></td><td background="img/fade.gif">Called when HTTP headers are recevived from the remote server. The <tt>buff</tt> buffer contains text headers, <tt>adr</tt> and <tt>fil</tt> the URL, and <tt>referer_adr</tt> and <tt>referer_fil</tt> the referer URL. The <tt>incoming</tt> structure contains all information related to the current slot.<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* buff, const char* adr, const char* fil, const char* referer_adr, const char* referer_fil, htsblk* incoming);</tt></td></tr>
-
-<tr><td background="img/fade.gif"><i>detect</i></td><td background="img/fade.gif">Called when an unknown document is to be parsed. The <tt>str</tt> structure contains all information related to the document.<br>return value: 1 if the type is known and can be parsed, 0 if the document type is unknown</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, htsmoduleStruct* str);</tt></td></tr>
-<tr><td background="img/fade.gif"><i>parse</i></td><td background="img/fade.gif">The <tt>str</tt> structure contains all information related to the document.<br>return value: 1 if the document was successfully parsed, 0 if an error occurred</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, htsmoduleStruct* str);</tt></td></tr>
-
-
-</table>
+<li>the <tt>htsdefines.h</tt> prototype file, which describes callback function prototypes</li>
+<li>the <tt>htsopt.h</tt> prototype file, which describes the full httrackp* structure</li>
+<li>the <tt>callbacks-example*.c</tt> files given in the httrack archive</li>
+<li>the <tt>htsjava.c</tt> source file (the java class plugin ; overrides 'detect' and 'parse')</li>
+<li>the example given at the end of this document</li>
+</ul>
+
+<br />
+Below the list of functions to be defined in the module (plugin).<br />
+<br />
+
+<table width="100%">
+<tr><td><b><i>module function name</i></b></td><td><b>function description</b></td><td><b>function signature</b></td></tr>
+<tr><td background="img/fade.gif"><i>hts_plug</i></td><td background="img/fade.gif">
+The module entry point. The opt structure can be used to plug callbacks, using the CHAIN_FUNCTION() macro helper. The argv optional argument is the one passed in the commandline as --wrapper parameter.<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)<br />
+
+<br />
+Wrappers can be plugged inside hts_plug() using:<br />
+<tt>
+CHAIN_FUNCTION(opt, &lt;callback name&gt;, &lt;our callback function name&gt;, &lt;our callback function optional custom pointer argument&gt;);
+</tt>
+<br />
+
+<br />
+Example:
+<br />
+<tt>
+CHAIN_FUNCTION(opt, check_html, process, userdef);
+</tt>
+<br />
+
+</td><td background="img/fade.gif"><tt>extern int hts_plug(httrackp *opt, const char* argv);</tt></td></tr>
+
+<!-- -->
+
+<tr><td background="img/fade.gif"><i>hts_unplug</i></td><td background="img/fade.gif">
+The module exit point. To free allocated resources without using global variables, use the uninit callback (see below)</td><td background="img/fade.gif"><tt>extern int hts_unplug(httrackp *opt);</tt></td></tr>
+
+</table>
+
+
+<br />
+Note that all callbacks (except init and uninit) take as first two argument:
+<ul>
+<li>the t_hts_callbackarg structure<br />
+this structure holds the callback chain (parent callbacks defined before the current callback) pointers, and the user-defined pointer ; see <tt>CALLBACKARG_USERDEF(carg)</tt>)
+</li>
+<li>the httrackp structure<br />
+this structure, holding all current httrack options and mirror state, can be read or mofidied
+</li>
+</ul>
+
+<br />
+Below the list of callbacks, and associated external wrappers.
+
+<table width="100%">
+<tr><td><b><i>callback name</i></b></td><td><b>callback description</b></td><td><b>callback function signature</b></td></tr>
+
+<tr><td background="img/fade.gif"><i>init</i></td><td background="img/fade.gif">Note: the use the "start" callback is advised. Called during initialization.<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>uninit</i></td><td background="img/fade.gif">Note: the use os the "end" callback is advised.<br />Called during un-initialization<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>start</i></td><td background="img/fade.gif">Called when the mirror starts. The <tt>opt</tt> structure passed lists all options defined for this mirror. You may modify the <tt>opt</tt> structure to fit your needs.<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)</td><td background="img/fade.gif"><tt>int mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>end</i></td><td background="img/fade.gif">Called when the mirror ends<br>return value: 1 upon success, 0 upon error (the mirror will then be considered aborted)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>chopt</i></td><td background="img/fade.gif">Called when options are to be changed. The <tt>opt</tt> structure passed lists all options, updated to take account of recent changes<br>return value: 1 upon success, 0 upon error (the mirror will then be aborted)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>preprocess</i></td><td background="img/fade.gif">Called when a document (which is an html document) is to be parsed (original, not yet modified document). The <tt>html</tt> address points to the document data address (char**), and the <tt>length</tt> address points to the lenth of this document. Both pointer values (address and size) can be modified to change the document. It is up to the callback function to reallocate the given pointer (using the hts_realloc()/hts_free() library functions), which will be free()'ed by the engine. Hence, return of static buffers is strictly forbidden, and the use of hts_strdup() in such cases is advised. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the new pointers can be applied (default value)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char** html, int* len, const char* url_address, const char* url_file);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>postprocess</i></td><td background="img/fade.gif">Called when a document (which is an html document) is parsed and transformed (links rewritten). The <tt>html</tt> address points to the document data address (char**), and the <tt>length</tt> address points to the lenth of this document. Both pointer values (address and size) can be modified to change the document. It is up to the callback function to reallocate the given pointer (using the hts_realloc()/hts_free() library functions), which will be free()'ed by the engine. Hence, return of static buffers is strictly forbidden, and the use of hts_strdup() in such cases is advised. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the new pointers can be applied (default value)</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char** html, int* len, const char* url_address, const char* url_file);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>check_html</i></td><td background="img/fade.gif">Called when a document (which may not be an html document) is to be parsed. The <tt>html</tt> address points to the document data, of lenth <tt>len</tt>. The <tt>url_address</tt> and <tt>url_file</tt> are the address and URI of the file being processed<br>return value: 1 if the parsing can be processed, 0 if the file must be skipped without being parsed</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* html, int len, const char* url_address, const char* url_file);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>query</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question. The <tt>question</tt> string contains the question for the (human) user<br>return value: the string answer ("" for default reply)</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>query2</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>query3</i></td><td background="img/fade.gif">Called when the wizard needs to ask a question</td><td background="img/fade.gif"><tt>const char* mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* question);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>loop</i></td><td background="img/fade.gif">Called periodically (informational, to display statistics)<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, lien_back* back, int back_max, int back_index, int lien_tot, int lien_ntot, int stat_time, hts_stat_struct* stats);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>check_link</i></td><td background="img/fade.gif">Called when a link has to be tested. The <tt>adr</tt> and <tt>fil</tt> are the address and URI of the link being tested. The passed <tt>status</tt> value has the following meaning: 0 if the link is to be accepted by default, 1 if the link is to be refused by default, and -1 if no decision has yet been taken by the engine<br>return value: same meaning as the passed <tt>status</tt> value ; you may generally return -1 to let the engine take the decision by itself</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr, const char* fil, int status);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>check_mime</i></td><td background="img/fade.gif">Called when a link download has begun, and needs to be tested against its MIME type. The <tt>adr</tt> and <tt>fil</tt> are the address and URI of the link being tested, and the <tt>mime</tt> string contains the link type being processed. The passed <tt>status</tt> value has the following meaning: 0 if the link is to be accepted by default, 1 if the link is to be refused by default, and -1 if no decision has yet been taken by the engine<br>return value: same meaning as the passed <tt>status</tt> value ; you may generally return -1 to let the engine take the decision by itself</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr, const char* fil, const char* mime, int status);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>pause</i></td><td background="img/fade.gif">Called when the engine must pause. When the <tt>lockfile</tt> passed is deleted, the function can return<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* lockfile);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>filesave</i></td><td background="img/fade.gif">Called when a file is to be saved on disk<br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* file);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>filesave2</i></td><td background="img/fade.gif">Called when a file is to be saved or checked on disk<br>The hostname, filename and local filename are given. Two additional flags tells if the local file is new (is_new), if the local file is to be modified (is_modified), and if the file was not updated remotely (not_updated).<br>(!is_new && !is_modified): the file is up-to-date, and will not be modified<br>(is_new && is_modified): a new file will be written (or an updated file is being written)<br>(!is_new && is_modified): a file is being updated (append)<br>(is_new && !is_modified): an empty file will be written ("do not recatch locally erased files")<br>not_updated: the file was not re-downloaded because it was up-to-date (no data transferred again)<br><br>return value: none</td><td background="img/fade.gif"><tt>void  mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* hostname, const char* filename, const char* localfile, int is_new, int is_modified, int not_updated);</tt></td></tr>
+
+<tr><td background="img/fade.gif"><i>linkdetected</i></td><td background="img/fade.gif">Called when a link has been detected<br>return value: 1 if the link can be analyzed, 0 if the link must not even be considered</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* link);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>linkdetected2</i></td><td background="img/fade.gif">Called when a link has been detected<br>return value: 1 if the link can be analyzed, 0 if the link must not even be considered</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* link, const const char* tag_start);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>xfrstatus</i></td><td background="img/fade.gif">Called when a file has been processed (downloaded, updated, or error)<br>return value: must return 1</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, lien_back* back);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>savename</i></td><td background="img/fade.gif">Called when a local filename has to be processed. The <tt>adr_complete</tt> and <tt>fil_complete</tt> are the address and URI of the file being saved ; the <tt>referer_adr</tt> and <tt>referer_fil</tt> are the address and URI of the referer link. The <tt>save</tt> string contains the local filename being used. You may modifiy the <tt>save</tt> string to fit your needs, up to 1024 bytes (note: filename collisions, if any, will be handled by the engine by renaming the file into file-2.ext, file-3.ext ..).<br>return value: must return 1</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, const char* adr_complete, const char* fil_complete, const char* referer_adr, const char* referer_fil, char* save);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>sendhead</i></td><td background="img/fade.gif">Called when HTTP headers are to be sent to the remote server. The <tt>buff</tt> buffer contains text headers, <tt>adr</tt> and <tt>fil</tt> the URL, and <tt>referer_adr</tt> and <tt>referer_fil</tt> the referer URL. The <tt>outgoing</tt> structure contains all information related to the current slot.<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* buff, const char* adr, const char* fil, const char* referer_adr, const char* referer_fil, htsblk* outgoing);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>receivehead</i></td><td background="img/fade.gif">Called when HTTP headers are recevived from the remote server. The <tt>buff</tt> buffer contains text headers, <tt>adr</tt> and <tt>fil</tt> the URL, and <tt>referer_adr</tt> and <tt>referer_fil</tt> the referer URL. The <tt>incoming</tt> structure contains all information related to the current slot.<br>return value: 1 if the mirror can continue, 0 if the mirror must be aborted</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, char* buff, const char* adr, const char* fil, const char* referer_adr, const char* referer_fil, htsblk* incoming);</tt></td></tr>
+
+<tr><td background="img/fade.gif"><i>detect</i></td><td background="img/fade.gif">Called when an unknown document is to be parsed. The <tt>str</tt> structure contains all information related to the document.<br>return value: 1 if the type is known and can be parsed, 0 if the document type is unknown</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, htsmoduleStruct* str);</tt></td></tr>
+<tr><td background="img/fade.gif"><i>parse</i></td><td background="img/fade.gif">The <tt>str</tt> structure contains all information related to the document.<br>return value: 1 if the document was successfully parsed, 0 if an error occurred</td><td background="img/fade.gif"><tt>int   mycallback(t_hts_callbackarg *carg, httrackp* opt, htsmoduleStruct* str);</tt></td></tr>
+
+
+</table>
 
 <br><br>
-Note: the optional libhttrack-plugin module (libhttrack-plugin.dll or libhttrack-plugin.so), if found in the library environment, is loaded automatically, and its <tt>hts_plug()</tt> function being called.<br />
-
-
-<br />
-An example is generally more efficient than anything else, so let's write our first module, aimed to stupidely print all parsed html files:
-<table width="100%" border="2">
-<tr><td>
-<pre>
-/* system includes */
-#include &lt;stdio.h&gt;
-#include &lt;stdlib.h&gt;
-#include &lt;string.h&gt;
-
-/* standard httrack module includes */
-#include "httrack-library.h"
-#include "htsopt.h"
-#include "htsdefines.h"
-
-/* local function called as "check_html" callback */
-static int process_file(t_hts_callbackarg /*the carg structure, holding various information*/*carg, /*the option settings*/httrackp *opt, 
-                        /*other parameters are callback-specific*/
-                        char* html, int len, const char* url_address, const char* url_file) {
-  void *ourDummyArg = (void*) CALLBACKARG_USERDEF(carg);    /*optional user-defined arg*/
-
-  /* call parent functions if multiple callbacks are chained. you can skip this part, if you don't want previous callbacks to be called. */
-  if (CALLBACKARG_PREV_FUN(carg, check_html) != NULL) {
-    if (!CALLBACKARG_PREV_FUN(carg, check_html)(CALLBACKARG_PREV_CARG(carg), opt,
-                                                html, len, url_address, url_file)) {
-        return 0;  /* abort */
-      }
-  }
-
-  printf("file %s%s content: %s\n", url_address, url_file, html);
-  return 1;  /* success */
-}
-
-/* local function called as "end" callback */
-static int end_of_mirror(t_hts_callbackarg /*the carg structure, holding various information*/*carg, /*the option settings*/httrackp *opt) {
-  void *ourDummyArg = (void*) CALLBACKARG_USERDEF(carg);    /*optional user-defined arg*/
-
-  /* processing */
-  fprintf(stderr, "That's all, folks!\n");
-
-  /* call parent functions if multiple callbacks are chained. you can skip this part, if you don't want previous callbacks to be called. */
-  if (CALLBACKARG_PREV_FUN(carg, end) != NULL) {
-    /* status is ok on our side, return other callabck's status */
-    return CALLBACKARG_PREV_FUN(carg, end)(CALLBACKARG_PREV_CARG(carg), opt);
-  }
-
-  return 1;  /* success */
-}
-
-/*
-module entry point
-the function name and prototype MUST match this prototype
-*/
-EXTERNAL_FUNCTION int hts_plug(httrackp *opt, const char* argv) {
-  /* optional argument passed in the commandline we won't be using here */
-  const char *arg = strchr(argv, ',');
-  if (arg != NULL)
-    arg++;
-
-  /* plug callback functions */
-  CHAIN_FUNCTION(opt, check_html, process_file, /*optional user-defined arg*/NULL);
-  CHAIN_FUNCTION(opt, end, end_of_mirror, /*optional user-defined arg*/NULL);
-
-  return 1;  /* success */
-}
-
-/*
-module exit point
-the function name and prototype MUST match this prototype
-*/
-EXTERNAL_FUNCTION int hts_unplug(httrackp *opt) {
-  fprintf(stder, "Module unplugged");
-
-  return 1;  /* success */
-}
-</pre>
-</td></tr></table>
-
-<br />
-Compile this file ; for example:
-<br />
-<tt>
-gcc -O -g3 -shared -o mylibrary.so myexample.c
-</tt>
-<br />
-and plug the module using the commandline ; for example:
-<br />
-<tt>
-httrack --wrapper mylibrary http://www.example.com
-</tt>
-<br />
-or, if some parameters are desired:
-<br />
-<tt>
-httrack --wrapper mylibrary,myparameter-string http://www.example.com
-</tt>
-<br />
-(the "myparameter-string" string will be available in the 'arg' parameter passed to the hts_plug entry point)
-<br />
-
+Note: the optional libhttrack-plugin module (libhttrack-plugin.dll or libhttrack-plugin.so), if found in the library environment, is loaded automatically, and its <tt>hts_plug()</tt> function being called.<br />
+
 
+<br />
+An example is generally more efficient than anything else, so let's write our first module, aimed to stupidely print all parsed html files:
+<table width="100%" border="2">
+<tr><td>
+<pre>
+/* system includes */
+#include &lt;stdio.h&gt;
+#include &lt;stdlib.h&gt;
+#include &lt;string.h&gt;
+
+/* standard httrack module includes */
+#include "httrack-library.h"
+#include "htsopt.h"
+#include "htsdefines.h"
+
+/* local function called as "check_html" callback */
+static int process_file(t_hts_callbackarg /*the carg structure, holding various information*/*carg, /*the option settings*/httrackp *opt, 
+                        /*other parameters are callback-specific*/
+                        char* html, int len, const char* url_address, const char* url_file) {
+  void *ourDummyArg = (void*) CALLBACKARG_USERDEF(carg);    /*optional user-defined arg*/
+
+  /* call parent functions if multiple callbacks are chained. you can skip this part, if you don't want previous callbacks to be called. */
+  if (CALLBACKARG_PREV_FUN(carg, check_html) != NULL) {
+    if (!CALLBACKARG_PREV_FUN(carg, check_html)(CALLBACKARG_PREV_CARG(carg), opt,
+                                                html, len, url_address, url_file)) {
+        return 0;  /* abort */
+      }
+  }
+
+  printf("file %s%s content: %s\n", url_address, url_file, html);
+  return 1;  /* success */
+}
+
+/* local function called as "end" callback */
+static int end_of_mirror(t_hts_callbackarg /*the carg structure, holding various information*/*carg, /*the option settings*/httrackp *opt) {
+  void *ourDummyArg = (void*) CALLBACKARG_USERDEF(carg);    /*optional user-defined arg*/
+
+  /* processing */
+  fprintf(stderr, "That's all, folks!\n");
+
+  /* call parent functions if multiple callbacks are chained. you can skip this part, if you don't want previous callbacks to be called. */
+  if (CALLBACKARG_PREV_FUN(carg, end) != NULL) {
+    /* status is ok on our side, return other callabck's status */
+    return CALLBACKARG_PREV_FUN(carg, end)(CALLBACKARG_PREV_CARG(carg), opt);
+  }
+
+  return 1;  /* success */
+}
+
+/*
+module entry point
+the function name and prototype MUST match this prototype
+*/
+EXTERNAL_FUNCTION int hts_plug(httrackp *opt, const char* argv) {
+  /* optional argument passed in the commandline we won't be using here */
+  const char *arg = strchr(argv, ',');
+  if (arg != NULL)
+    arg++;
+
+  /* plug callback functions */
+  CHAIN_FUNCTION(opt, check_html, process_file, /*optional user-defined arg*/NULL);
+  CHAIN_FUNCTION(opt, end, end_of_mirror, /*optional user-defined arg*/NULL);
+
+  return 1;  /* success */
+}
+
+/*
+module exit point
+the function name and prototype MUST match this prototype
+*/
+EXTERNAL_FUNCTION int hts_unplug(httrackp *opt) {
+  fprintf(stder, "Module unplugged");
+
+  return 1;  /* success */
+}
+</pre>
+</td></tr></table>
+
+<br />
+Compile this file ; for example:
+<br />
+<tt>
+gcc -O -g3 -shared -o mylibrary.so myexample.c
+</tt>
+<br />
+and plug the module using the commandline ; for example:
+<br />
+<tt>
+httrack --wrapper mylibrary http://www.example.com
+</tt>
+<br />
+or, if some parameters are desired:
+<br />
+<tt>
+httrack --wrapper mylibrary,myparameter-string http://www.example.com
+</tt>
+<br />
+(the "myparameter-string" string will be available in the 'arg' parameter passed to the hts_plug entry point)
+<br />
+
+
 <br><br>
 
 <!-- ==================== Start epilogue ==================== -->

html/server/option10.html

@@ -98,16 +98,7 @@ ${do:end-if}
 <input type="hidden" name="redirect" value="">
 <input type="hidden" name="closeme" value="">
 
-${LANG_PROXYTYPE}
-<select name="proxytype"
-			onMouseOver="info('${html:LANG_PROXYTYPETIP}'); return true" onMouseOut="info('&nbsp;'); return true"
->
-<option value=""${ztest:proxytype: selected:}>HTTP</option>
-<option value="1"${test:proxytype:: selected}>SOCKS5</option>
-</select>
-<br><br>
-
-${LANG_IOPT10}:
+${LANG_IOPT10}: 
 <input name="prox" value="${prox}" size="32"
 			onMouseOver="info('${html:LANG_G14}'); return true" onMouseOut="info('&nbsp;'); return true"
 >:

html/server/option5.html

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

html/server/option8.html

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

html/server/step2.html

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

html/server/step4.html

@@ -178,12 +178,6 @@ ${do:end-if}
 	${test:parsejava:--parse-java=0:}
 	${test:updhack:--updatehack}
 	${test:urlhack:--urlhack=0:--urlhack}
-	${test:keepwww:--keep-www-prefix}
-	${test:keepslashes:--keep-double-slashes}
-	${test:keepqueryorder:--keep-query-order}
-	${test:cookiesfile:--cookies-file "}${html:cookiesfile}${test:cookiesfile:"}
-	${test:pausefiles:--pause "}${pausefiles}${test:pausefiles:"}
-	${test:stripquery:--strip-query "}${html:stripquery}${test:stripquery:"}
 	${test:toler:--tolerant}
 	${test:http10:--http-10}
 	${test:cache2:--store-all-in-cache}
@@ -192,7 +186,7 @@ ${do:end-if}
 	${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}${test:proxytype:socks5\3A//}${do:end-if}${do:output-mode:html}${prox}${test:prox:\3A}${portprox}${test:prox:"}
+	${test:prox:--proxy "}${prox}${test:prox:\3A}${portprox}${test:prox:"}
 	${test:ftpprox:--httpproxy-ftp=0:--httpproxy-ftp}
 </textarea>
 
@@ -225,21 +219,15 @@ NoPwdInPages=${ztest:hidepwd:0:1}
 NoQueryStrings=${ztest:hidequery:0:1}
 NoPurgeOldFiles=${ztest:nopurge:0:1}
 Cookies=${ztest:cookies:0:1}
-CookiesFile=${cookiesfile}
 CheckType=${ztest:checktype:0:1:2}
 ParseJava=${ztest:parsejava:0:1}
 HTTP10=${ztest:http10:0:1}
 TolerantRequests=${ztest:toler:0:1}
 UpdateHack=${ztest:updhack:0:1}
 URLHack=${ztest:urlhack:0:1}
-KeepWww=${ztest:keepwww:0:1}
-KeepSlashes=${ztest:keepslashes:0:1}
-KeepQueryOrder=${ztest:keepqueryorder:0:1}
-StripQuery=${stripquery}
 StoreAllInCache=${ztest:cache2:0:1}
 LogType=${logtype}
 UseHTTPProxyForFTP=${ztest:ftpprox:0:1}
-ProxyType=${proxytype}
 Build=${build}
 PrimaryScan=${filter}
 Travel=${travel}
@@ -250,7 +238,6 @@ MaxHtml=${maxhtml}
 MaxOther=${othermax}
 MaxAll=${sizemax}
 MaxWait=${pausebytes}
-PauseFiles=${pausefiles}
 Sockets=${connexion}
 Retry=${retry}
 MaxTime=${maxtime}

html/step9_opt6.html

@@ -118,8 +118,8 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
   <br>Avoid "never", because the local mirror could be bogus
   </small><br><br>
 <!-- -->
-  <li>Parse scripts</li>
-  <br><small>Must the engine parse scripts to seek included filenames?
+  <li>Parse java files</li>
+  <br><small>Must the engine parse .java files (java classes) to seek included filenames?
   <br>It is checked by default
   </small><br><br>
 <!-- -->

lang.def

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

lang/Bulgarian.txt

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

lang/Castellano.txt

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

lang/Cesky.txt

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

lang/Chinese-BIG5.txt

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

lang/Chinese-Simplified.txt

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

lang/Croatian.txt

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

lang/Dansk.txt

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

lang/Deutsch.txt

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

lang/Eesti.txt

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

lang/English.txt

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

lang/Finnish.txt

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

lang/Francais.txt

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

lang/Greek.txt

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

lang/Italiano.txt

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

lang/Japanese.txt

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

lang/Macedonian.txt

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

lang/Magyar.txt

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

lang/Nederlands.txt

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

lang/Norsk.txt

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

lang/Polski.txt

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

lang/Portugues-Brasil.txt

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

lang/Portugues.txt

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

lang/Romanian.txt

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

lang/Russian.txt

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

lang/Slovak.txt

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

lang/Slovenian.txt

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

lang/Svenska.txt

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

lang/Turkish.txt

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