Remove the dead HTS_FAST_CACHE==0 code paths

HTS_FAST_CACHE has been hard-set to 1 since the coucal hashtable became
the cache index; the ==0 arms no longer even compile (they reference an
undeclared variable in cache_readex). Drop the knob, the dead arms, and
the cache_back 'use' field they read, which was never assigned.

No behavior change: the kept code is exactly what the preprocessor
selected, and the removed cache.use cleanup was a never-taken branch.

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: |
+        run: make check
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
 
       - 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
-          make check -j"$jobs"
 
       - 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" \
+          ./configure CPPFLAGS="-I${ssl}/include" LDFLAGS="-L${ssl}/lib"
-            LDFLAGS="-L${ssl}/lib -L${brewp}/lib"
-          grep -q "define HTS_USEBROTLI 1" config.h
-          grep -q "define HTS_USEZSTD 1" config.h
 
       - 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: |
+        run: make check
-          jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
 
       - 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 \
+            autoconf-archive zlib1g-dev:i386 libssl-dev:i386
-            libbrotli-dev:i386 libzstd-dev:i386
 
       - name: Configure
         run: |
@@ -223,9 +171,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: |
+        run: make check
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
 
       - 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: |
+        run: make check
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -328,8 +272,7 @@ 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 TESTS="$tests"
-          make check -j"$jobs" TESTS="$tests"
 
       - name: Print the test log on failure
         if: failure()
@@ -354,7 +297,7 @@ 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 (fuzzers, static)
         run: |
@@ -404,9 +347,7 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: |
+        run: make check
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -434,7 +375,7 @@ 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 +419,7 @@ 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 +495,6 @@ 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

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

.github/workflows/windows-build.yml

@@ -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

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"$(nproc)" && make check
+  automake, libtool), then `bash configure && make && make check`. Or run
-  -j"$(nproc)"`. Always pass `-j` to `make check`: the suite runs under
+  `sh build.sh` to do bootstrap + configure + make in one shot.
-  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.
 
 ## 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

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
+# 3:3:0: 3.49.11 only adds enum values, macros and inline helpers to the
-# deletes dead comments; no struct layout or exported signature broke vs 3.49.11,
+# installed headers (no struct layout or exported signature changed vs
-# so it stays soname .so.3; bump revision.
+# 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], ["$HTS_LIBHTSJAVA_NAME"],
+  [Versioned libhtsjava runtime name, derived from VERSION_INFO])
+
 ### Default CFLAGS
 DEFAULT_CFLAGS="-Wall -Wformat -Wformat-security \
 -Wmultichar -Wwrite-strings -Wcast-qual -Wcast-align \
@@ -109,8 +119,8 @@ case "$CFLAGS" in
 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
+# libhttrack (libhtsjava, the libtest callbacks), but only with a GNU-style
-# ld rejects these flags and links libSystem unconditionally.
+# 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 +183,6 @@ 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],

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
+ The engine includes contributions from Yann Philippot (src/htsjava.c,
- Young); no OpenSSL/SSLeay code is bundled here.
+ 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

@@ -1,8 +1,7 @@
 # libFuzzer harnesses; built only with --enable-fuzzers (requires clang).
 if FUZZERS
 noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
-	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx \
+	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx
-	fuzz-htsparse
 endif
 
 AM_CPPFLAGS = \
@@ -26,7 +25,6 @@ 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 \
@@ -39,12 +37,9 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/filters/filter.bin corpus/filters/filter-size.bin \
 	corpus/filters/regress-empty-subject-unique.bin \
 	corpus/filters/redos-star-classes.bin \
-	corpus/filters/regress-classdepth-timeout.bin \
 	corpus/url/http-url.txt corpus/url/relative-path.txt \
 	corpus/url/regress-file-empty-path.txt corpus/url/regress-long-path-abort.txt \
 	corpus/header/full-response.txt corpus/header/redirect.txt \
 	corpus/cachendx/new-format.txt corpus/cachendx/old-format.txt \
 	corpus/cachendx/regress-overadvance.bin \
-	corpus/cachendx/regress-truncated-entry.bin \
+	corpus/cachendx/regress-truncated-entry.bin
-	corpus/htsparse/basic.html corpus/htsparse/script-inscript.html \
-	corpus/htsparse/meta-usemap.html corpus/htsparse/malformed.html

fuzz/corpus/htsparse/basic.html

@@ -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/meta/meta-content-first.html

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

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/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;
-}

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
+A: <em>Java applets may not work in some cases, for example if HTTrack failed to detect all included classes
-the resources they load. Java applets often need to be online anyway, since remote files are fetched directly
+or files called within the class file. Sometimes, Java applets need to be online, because remote files are
-at runtime.<br>
+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
+<p align=justify> A: Java applets may not work in some cases, for
-HTTrack does not parse compiled class files to find the resources they
+example if HTTrack failed to detect all included classes or files called
-load.  Java applets often need to be online anyway, since remote files
+within the class file.  Sometimes, Java applets need to be online,
-are fetched directly at runtime.
+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
+<p>*parse Java Classes (j0 don t parse, bitmask: |1 parse
-default, |4 don t parse .js |8 don t be aggressive)
+default, |2 don t parse .class |4 don t parse .js |8 don t
-(--parse-java[=N])</p></td></tr>
+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
+<p>disable a specific external mime module (-%w htsswf -%w
-httrack-plugin) (--disable-module &lt;param&gt;)</p></td></tr>
+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)
+j *parse Java Classes (j0 don't parse)
-This option defines whether the engine has to parse scripts or not to catch included files
+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

@@ -126,6 +126,7 @@ Note: the <i>Initialization</i>, <i>Main functions</i>, <i>Options handling</i>
 <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>
 

html/server/option10.html

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

html/server/option5.html

@@ -148,14 +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>
+  <li>Parse java files</li>
-  <br><small>Must the engine parse scripts to seek included filenames?
+  <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).

lang/Ukrainian.txt

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

lang/Uzbek.txt

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

m4/check_codecs.m4

@@ -1,66 +0,0 @@
-dnl @synopsis CHECK_BROTLI()
-dnl @synopsis CHECK_ZSTD()
-dnl
-dnl Look for libbrotlidec and libzstd, the decoders for the "br" and "zstd"
-dnl HTTP content codings. Both are optional: a missing library only drops the
-dnl coding from Accept-Encoding. --with-brotli=DIR / --with-zstd=DIR point at a
-dnl prefix; --without-brotli / --without-zstd disable the coding; the default
-dnl is to use the library when it is found.
-dnl
-dnl Define HTS_USEBROTLI / HTS_USEZSTD to 1 or 0, and substitute BROTLI_LIBS /
-dnl ZSTD_LIBS.
-
-dnl CHECK_CODEC(name, NAME, header, library, symbol, companion-libs)
-AC_DEFUN([CHECK_CODEC], [
-AC_ARG_WITH([$1],
-	[AS_HELP_STRING([--with-$1@<:@=DIR@:>@],[Enable the $1 content coding @<:@default=auto@:>@])],
-	[codec_want=$withval], [codec_want=auto])
-$2_LIBS=""
-codec_have=no
-if test "$codec_want" != "no"; then
-	codec_old_cppflags="$CPPFLAGS"
-	codec_old_ldflags="$LDFLAGS"
-	codec_dir=no
-	if test "$codec_want" != "yes" -a "$codec_want" != "auto"; then
-		codec_dir=yes
-		# An explicit prefix is authoritative: if the header is not under
-		# it, error rather than silently pick a system copy.
-		if test ! -f "$codec_want/include/$3"; then
-			AC_MSG_ERROR([$1 requested at $codec_want but $codec_want/include/$3 is missing])
-		fi
-		CPPFLAGS="$CPPFLAGS -I$codec_want/include"
-		LDFLAGS="$LDFLAGS -L$codec_want/lib"
-	fi
-	AC_CHECK_HEADER([$3], [codec_h=yes], [codec_h=no])
-	AC_CHECK_LIB([$4], [$5], [codec_lib=yes], [codec_lib=no], [$6])
-	CPPFLAGS="$codec_old_cppflags"
-	LDFLAGS="$codec_old_ldflags"
-	if test "$codec_h" = "yes" -a "$codec_lib" = "yes"; then
-		codec_have=yes
-		$2_LIBS="-l$4 $6"
-		if test "$codec_dir" = "yes"; then
-			$2_LIBS="-L$codec_want/lib -l$4 $6"
-			# The rest of configure still needs the header path.
-			CPPFLAGS="$CPPFLAGS -I$codec_want/include"
-		fi
-	elif test "$codec_want" != "auto"; then
-		AC_MSG_ERROR([$1 requested but lib$4/$3 not found])
-	fi
-fi
-AC_MSG_CHECKING([whether to enable the $1 content coding])
-AC_MSG_RESULT([$codec_have])
-if test "$codec_have" = "yes"; then
-	AC_DEFINE([HTS_USE$2], [1], [Define to 1 to decode the $1 content coding])
-else
-	AC_DEFINE([HTS_USE$2], [0], [Define to 1 to decode the $1 content coding])
-fi
-AC_SUBST([$2_LIBS])
-AC_SUBST([$2_ENABLED], [$codec_have])
-])
-
-dnl brotlidec needs brotlicommon (the static dictionary) for a fully-static link.
-AC_DEFUN([CHECK_BROTLI],
-	[CHECK_CODEC([brotli], [BROTLI], [brotli/decode.h], [brotlidec], [BrotliDecoderDecompressStream], [-lbrotlicommon])])
-
-AC_DEFUN([CHECK_ZSTD],
-	[CHECK_CODEC([zstd], [ZSTD], [zstd.h], [zstd], [ZSTD_decompressStream], [])])

man/httrack.1

@@ -3,7 +3,7 @@
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
 .\" SPDX-License-Identifier: GPL-3.0-or-later
-.TH httrack 1 "14 July 2026" "httrack website copier"
+.TH httrack 1 "07 July 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -135,7 +135,7 @@ continue an interrupted mirror using the cache (\-\-continue)
 mirror ALL links located in the first level pages (mirror links) (\-\-mirrorlinks)
 .SS Proxy options:
 .IP \-P
-proxy use (\-P [socks5://][user:pass@]proxy:port) (\-\-proxy <param>)
+proxy use (\-P proxy:port or \-P user:pass@proxy:port) (\-\-proxy <param>)
 .IP \-%f
 *use proxy for ftp (f0 don't use) (\-\-httpproxy\-ftp[=N])
 .IP \-%b
@@ -224,7 +224,7 @@ explain which filter rule accepts or rejects a URL, then exit (\-\-why <param>)
 .IP \-u
 check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (\-\-check\-type[=N])
 .IP \-j
-*parse scripts (j0 don't parse, bitmask: |1 parse default, |4 don't parse .js |8 don't be aggressive) (\-\-parse\-java[=N])
+*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])
 .IP \-sN
 follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always, 3=always (even strict rules)) (\-\-robots[=N])
 .IP \-%h
@@ -248,7 +248,7 @@ can also be used to force a specific file type: \-\-assume foo.cgi=text/html
 .IP \-@iN
 internet protocol (0=both ipv6+ipv4, 4=ipv4 only, 6=ipv6 only) (\-\-protocol[=N])
 .IP \-%w
-disable a specific external mime module (\-%w httrack\-plugin) (\-\-disable\-module <param>)
+disable a specific external mime module (\-%w htsswf \-%w htsjava) (\-\-disable\-module <param>)
 .SS Browser ID:
 .IP \-F
 user\-agent field sent in HTTP headers (\-F "user\-agent name") (\-\-user\-agent <param>)
@@ -514,6 +514,8 @@ that would have solved them.
 .SM
 \- Several scripts generating complex filenames may not find them (ex: img.src='image'+a+Mobj.dst+'.gif')
 .SM
+\- Some java classes may not find some files on them (class included)
+.SM
 \- Cgi\-bin links may not work properly in some cases (parameters needed). To avoid them: use filters like \-*cgi\-bin*
 .SH BUGS
 Please reports bugs to

src/Makefile.am

@@ -44,7 +44,7 @@ httrack_LDFLAGS = $(AM_LDFLAGS) $(LDFLAGS_PIE)
 proxytrack_LDFLAGS = $(AM_LDFLAGS) $(LDFLAGS_PIE)
 htsserver_LDFLAGS = $(AM_LDFLAGS) $(LDFLAGS_PIE)
 
-lib_LTLIBRARIES = libhttrack.la
+lib_LTLIBRARIES = libhttrack.la libhtsjava.la
 
 htsserver_SOURCES = htsserver.c htsserver.h htsweb.c htsweb.h
 proxytrack_SOURCES = proxy/main.c \
@@ -61,7 +61,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htshelp.c htslib.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
 	htsalias.c htsthread.c htsindex.c htsbauth.c \
-	htsmd5.c htscodec.c htsproxy.c htszlib.c htswrap.c htsconcat.c \
+	htsmd5.c htszlib.c htswrap.c htsconcat.c \
 	htsmodules.c htscharset.c punycode.c htsencoding.c htssniff.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
@@ -72,20 +72,25 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	htshelp.h htsindex.h htslib.h htsmd5.h \
 	htsmodules.h htsname.h htsnet.h htssniff.h \
 	htsopt.h htsrobots.h htsthread.h  \
-	htstools.h htswizard.h htswrap.h htscodec.h htsproxy.h htszlib.h  \
+	htstools.h htswizard.h htswrap.h htszlib.h  \
 	htsstrings.h htsarrays.h httrack-library.h \
 	htscharset.h punycode.h htsencoding.h \
 	htsentities.h htsentities.sh htsbasiccharsets.sh htscodepages.h \
 	md5.h coucal/murmurhash3.h \
 	minizip/crypt.h minizip/ioapi.h minizip/mztools.h minizip/unzip.h minizip/zip.h
-libhttrack_la_LIBADD = $(THREADS_LIBS) $(ZLIB_LIBS) $(BROTLI_LIBS) $(ZSTD_LIBS) $(OPENSSL_LIBS) $(DL_LIBS) $(SOCKET_LIBS) $(ICONV_LIBS)
+libhttrack_la_LIBADD = $(THREADS_LIBS) $(ZLIB_LIBS) $(OPENSSL_LIBS) $(DL_LIBS) $(SOCKET_LIBS) $(ICONV_LIBS)
 libhttrack_la_CFLAGS = $(AM_CFLAGS) -DLIBHTTRACK_EXPORTS -DZLIB_CONST
 libhttrack_la_LDFLAGS = $(AM_LDFLAGS) -version-info $(VERSION_INFO)
 
+libhtsjava_la_SOURCES = htsjava.c htsjava.h
+libhtsjava_la_LIBADD = $(THREADS_LIBS) $(DL_LIBS) libhttrack.la
+# This thin JNI wrapper reaches libc only through libhttrack, so the direct
+# libc edge is dropped from DT_NEEDED (library-not-linked-against-libc). Force
+# libc back as a dependency; configure gates the flag since only a GNU-style
+# linker accepts it (LIBC_FORCE_LINK is empty on e.g. macOS).
+libhtsjava_la_LDFLAGS = $(AM_LDFLAGS) -version-info $(VERSION_INFO) $(LIBC_FORCE_LINK)
+
 EXTRA_DIST = httrack.h webhttrack \
-		version.rc \
-		libhttrack.rc \
-		httrack.rc \
 		coucal/murmurhash3.h.diff \
 		coucal/murmurhash3.h.orig \
 		minizip/iowin32.c \
@@ -108,13 +113,13 @@ EXTRA_DIST = httrack.h webhttrack \
 		proxy/proxystrings.h \
 		proxy/proxytrack.h \
 		proxy/store.h \
+		proxy/proxytrack.vcproj \
 		coucal/LICENSE \
 		coucal/Makefile \
 		coucal/README.md \
 		coucal/sample.c \
 		coucal/tests.c \
-		vcpkg.json \
+		htsjava.vcproj \
-		httrack.vcxproj \
+		httrack.dsp httrack.dsw httrack.vcproj \
-		libhttrack.vcxproj \
+		libhttrack.dsp libhttrack.dsw libhttrack.vcproj \
-		proxytrack.vcxproj \
+		webhttrack.dsp webhttrack.dsw webhttrack.vcproj
-		webhttrack.vcxproj

src/htsback.c

@@ -44,8 +44,6 @@ Please visit our Website: http://www.httrack.com
 #include "htsback.h"
 
 #include "htsftp.h"
-#include "htscodec.h"
-#include "htsproxy.h"
 #if HTS_USEZLIB
 #include "htszlib.h"
 #else
@@ -70,15 +68,6 @@ static int slot_can_be_cached_on_disk(const lien_back * back);
 static int slot_can_be_cleaned(const lien_back * back);
 static int slot_can_be_finalized(httrackp * opt, const lien_back * back);
 
-/* Which hard quota, if any, is currently aborting the mirror. */
-typedef enum {
-  HTS_MIRROR_LIMIT_NONE = 0,
-  HTS_MIRROR_LIMIT_SIZE,
-  HTS_MIRROR_LIMIT_TIME,
-} hts_mirror_limit;
-
-static hts_mirror_limit back_mirror_limit(httrackp *opt);
-
 struct_back *back_new(httrackp *opt, int back_max) {
   int i;
   struct_back *sback = calloct(1, sizeof(struct_back));
@@ -140,9 +129,8 @@ int back_connect_fallback_due(int addr_index, int addr_count, int elapsed,
 
 /* Pending-connect result for a non-blocking socket reported ready by select():
    0 = connected, >0 = the connect errno (refused, unreachable, ...), -1 if the
-   probe itself failed. A failed connect is reported ready as well (writable on
+   probe itself failed. A failed connect is reported writable too, so this is
-   posix, exception set on winsock), so this is how success is told from failure
+   how success is told from failure without blocking. */
-   without blocking. */
 static int connect_socket_error(T_SOC soc) {
   int soerr = 0;
   socklen_t len = (socklen_t) sizeof(soerr);
@@ -536,13 +524,12 @@ int back_nsoc_overall(const struct_back * sback) {
 
 /* generate temporary file on lien_back */
 /* Note: utf-8 */
-static int create_back_tmpfile(httrackp *opt, lien_back *const back,
+static int create_back_tmpfile(httrackp * opt, lien_back *const back) {
-                               const char *ext) {
   // do not use tempnam() but a regular filename
   back->tmpfile_buffer[0] = '\0';
   if (back->url_sav != NULL && back->url_sav[0] != '\0') {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.%s",
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.z", 
-             back->url_sav, ext);
+             back->url_sav);
     back->tmpfile = back->tmpfile_buffer;
     if (structcheck(back->tmpfile) != 0) {
       hts_log_print(opt, LOG_WARNING, "can not create directory to %s", 
@@ -550,8 +537,9 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
       return -1;
     }
   } else {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s/tmp%d.%s",
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer),
-             StringBuff(opt->path_html_utf8), opt->state.tmpnameid++, ext);
+             "%s/tmp%d.z", StringBuff(opt->path_html_utf8),
+             opt->state.tmpnameid++);
     back->tmpfile = back->tmpfile_buffer;
   }
   /* OK */
@@ -559,39 +547,6 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
   return 0;
 }
 
-/* Move src onto dst; RENAME does not clobber an existing target on Windows. */
-static hts_boolean replace_file(const char *src, const char *dst) {
-  if (RENAME(src, dst) == 0)
-    return HTS_TRUE;
-  (void) UNLINK(dst);
-  return RENAME(src, dst) == 0 ? HTS_TRUE : HTS_FALSE;
-}
-
-/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
-   existing file moved the good copy to back->tmpfile before truncating url_sav.
-   commit keeps the new file and drops the backup; else restore it so an aborted
-   transfer leaves the previous copy intact. Skips the zlib .z temp. */
-static void back_finalize_backup(httrackp *opt, lien_back *const back,
-                                 const hts_boolean commit) {
-  if (back->tmpfile == NULL || back->r.compressed)
-    return;
-  if (commit) {
-    (void) UNLINK(back->tmpfile); /* new copy is good; drop the backup */
-  } else {
-    if (back->r.out != NULL) {
-      fclose(back->r.out);
-      back->r.out = NULL;
-    }
-    /* On failure keep the backup: an orphaned temp beats losing the good copy.
-     */
-    if (!replace_file(back->tmpfile, back->url_sav))
-      hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
-                    "could not restore %s; previous copy kept as %s",
-                    back->url_sav, back->tmpfile);
-  }
-  back->tmpfile = NULL;
-}
-
 // objet (lien) téléchargé ou transféré depuis le cache
 //
 // fermer les paramètres de transfert,
@@ -627,11 +582,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                       LLintP " got " LLintP "): %s%s", back[p].r.totalsize,
                       back[p].r.size, back[p].url_adr, back[p].url_fil);
       }
-      back_finalize_backup(opt, &back[p], HTS_FALSE);
-      /* Keep the surviving copy in new.lst, else the update purge drops the
-         file we refused to overwrite with the partial body (#562). */
-      if (fexist_utf8(back[p].url_sav))
-        filenote(&opt->state.strc, back[p].url_sav, NULL);
       return -1;
     }
 
@@ -641,7 +591,8 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
       if (!back[p].testmode) {  // not test mode
         const char *state = "unknown";
 
-        /* Undo the content coding */
+        /* décompression */
+#if HTS_USEZLIB
         if (back[p].r.compressed) {
           if (back[p].r.size > 0) {
             // stats
@@ -649,7 +600,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
             // en mémoire -> passage sur disque
             if (!back[p].r.is_write) {
               // do not use tempnam() but a regular filename
-              if (create_back_tmpfile(opt, &back[p], "z") == 0) {
+              if (create_back_tmpfile(opt, &back[p]) == 0) {
                 assertf(back[p].tmpfile != NULL);
                 /* note: tmpfile is utf-8 */
                 back[p].r.out = FOPEN(back[p].tmpfile, "wb");
@@ -687,67 +638,28 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
             // décompression
             if (back[p].tmpfile != NULL) {
               if (back[p].url_sav[0]) {
-                const hts_codec codec =
-                    hts_codec_parse(back[p].r.contentencoding);
-                /* Never decode over url_sav: a failed decode would destroy the
-                   copy an --update re-fetch is supposed to refresh (#557). */
-                char BIGSTK unpacked[HTS_URLMAXSIZE * 2 + 4]; // room for ".u"
                 LLint size;
 
-                snprintf(unpacked, sizeof(unpacked), "%s.u", back[p].url_sav);
+                file_notify(opt, back[p].url_adr, back[p].url_fil,
-                if ((size = hts_codec_unpack(codec, back[p].tmpfile,
+                            back[p].url_sav, 1, 1, back[p].r.notmodified);
-                                             unpacked)) >= 0) {
+                filecreateempty(&opt->state.strc, back[p].url_sav);     // filenote & co
+                if ((size = hts_zunpack(back[p].tmpfile, back[p].url_sav)) >= 0) {
                   back[p].r.size = back[p].r.totalsize = size;
+                  // fichier -> mémoire
                   if (!back[p].r.is_write) {
-                    // fichier -> mémoire ; le fichier est écrit plus tard
                     deleteaddr(&back[p].r);
-                    back[p].r.adr = readfile_utf8(unpacked);
+                    back[p].r.adr = readfile_utf8(back[p].url_sav);
                     if (!back[p].r.adr) {
                       back[p].r.statuscode = STATUSCODE_INVALID;
                       strcpybuff(back[p].r.msg,
                                  "Read error when decompressing");
                     }
-                    UNLINK(unpacked);
+                    UNLINK(back[p].url_sav);
-                  } else if (replace_file(unpacked, back[p].url_sav)) {
-                    /* The temp bypassed filecreate(), which is what chmods. */
-#ifndef _WIN32
-                    chmod(back[p].url_sav, HTS_ACCESS_FILE);
-#endif
-                    file_notify(opt, back[p].url_adr, back[p].url_fil,
-                                back[p].url_sav, 1, 1, back[p].r.notmodified);
-                    filenote(&opt->state.strc, back[p].url_sav, NULL);
-                  } else {
-                    back[p].r.statuscode = STATUSCODE_INVALID;
-                    strcpybuff(back[p].r.msg,
-                               "Write error when decompressing (can not rename "
-                               "the temporary file)");
-                    /* Keep the decoded body: the failed replace may have
-                       removed the previous copy, leaving this as the only one.
-                     */
-                    hts_log_print(
-                        opt, LOG_WARNING | LOG_ERRNO,
-                        "could not replace %s; decoded copy kept as %s",
-                        back[p].url_sav, unpacked);
                   }
                 } else {
                   back[p].r.statuscode = STATUSCODE_INVALID;
-                  snprintf(back[p].r.msg, sizeof(back[p].r.msg),
+                  strcpybuff(back[p].r.msg, "Error when decompressing");
-                           codec == HTS_CODEC_UNSUPPORTED
-                               ? "Unsupported Content-Encoding (%s)"
-                               : "Error when decompressing (%s)",
-                           back[p].r.contentencoding);
-                  /* Drop the undecoded body so the writer can't commit the
-                     coded bytes as the page; url_sav is left untouched. */
-                  if (!back[p].r.is_write)
-                    deleteaddr(&back[p].r);
-                  UNLINK(unpacked);
                 }
-                /* A failed decode keeps the previously-mirrored copy: note it,
-                   or the update purge (in old.lst, absent from new.lst) would
-                   delete what we just took care not to overwrite. */
-                if (back[p].r.statuscode == STATUSCODE_INVALID &&
-                    fexist_utf8(back[p].url_sav))
-                  filenote(&opt->state.strc, back[p].url_sav, NULL);
               }
               /* ensure that no remaining temporary file exists */
               unlink(back[p].tmpfile);
@@ -760,9 +672,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
             // unflag
           }
         }
-        /* Body fully received: keep the freshly written url_sav, drop the
+#endif
-           backup of the previous copy. */
-        back_finalize_backup(opt, &back[p], HTS_TRUE);
         /* Write mode to disk */
         if (back[p].r.is_write && back[p].r.adr != NULL) {
           freet(back[p].r.adr);
@@ -781,7 +691,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
         if (back[p].r.statuscode == HTTP_OK) {  // OK (ou 304 en backing)
           if (back[p].r.is_write) {     // Written file
             if (may_be_hypertext_mime(opt, back[p].r.contenttype, back[p].url_fil)) {   // to parse!
-              LLint sz;
+              off_t sz;
 
               sz = fsize_utf8(back[p].url_sav);
               if (sz > 0) {     // ok, exists!
@@ -858,7 +768,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
           else
             strcatbuff(flags, "-");
           if (back[p].r.compressed)
-            strcatbuff(flags, "Z"); // content coding
+            strcatbuff(flags, "Z");     // gzip
           else
             strcatbuff(flags, "-");
           /* Err I had to split these.. */
@@ -867,7 +777,9 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
           fprintf(cache->txt, LLintP, (LLint) back[p].r.totalsize);
           fprintf(cache->txt, "\t%s\t", flags);
         }
+#if HTS_USEZLIB
         back[p].r.compressed = 0;
+#endif
 
         if (back[p].r.statuscode == HTTP_OK) {
           if (back[p].r.size >= 0) {
@@ -989,9 +901,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
       }
     }
   }
-  /* Aborted, error, or not ready: url_sav (if written) is broken; restore the
-     previous copy from the backup. */
-  back_finalize_backup(opt, &back[p], HTS_FALSE);
   return -1;
 }
 
@@ -1958,7 +1867,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
       /* Not in cache ; maybe in temporary cache ? Warning: non-movable
          "url_sav" */
       else if (back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
-        const LLint file_size = fsize_utf8(itemback->url_sav);
+        const off_t file_size = fsize_utf8(itemback->url_sav);
 
         /* Found file on disk */
         if (file_size > 0) {
@@ -1993,7 +1902,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
       }
       /* Not in cache or temporary cache ; found on disk ? (hack) */
       else if (fexist_utf8(save)) {
-        const LLint sz = fsize_utf8(save);
+        const off_t sz = fsize_utf8(save);
 
         // Bon, là il est possible que le fichier ait été partiellement transféré
         // (s'il l'avait été en totalité il aurait été inscrit dans le cache ET existerait sur disque)
@@ -2117,17 +2026,6 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
                         "error: forbidden test with ftp link for back_add");
           return -1;            // erreur pas de test permis
         }
-        // the ftp client dials the origin itself: over socks that would bypass
-        // the proxy, so fail the link rather than leak the connection (#563)
-        if (back[p].r.req.proxy.active &&
-            hts_proxy_is_socks(back[p].r.req.proxy.name)) {
-          back[p].r.statuscode = STATUSCODE_NON_FATAL;
-          strcpybuff(back[p].r.msg,
-                     "ftp:// is not supported over a SOCKS proxy");
-          back[p].status = STATUS_READY;
-          back_set_finished(sback, p);
-          return 0;
-        }
         if (!(back[p].r.req.proxy.active && opt->ftp_proxy)) {  // connexion directe, gérée en thread
           FTPDownloadStruct *str =
             (FTPDownloadStruct *) malloc(sizeof(FTPDownloadStruct));
@@ -2152,9 +2050,13 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 
       if (!back_trylive(opt, cache, sback, p)) {
 #if HTS_XGETHOST
-        back[p].status = STATUS_WAIT_DNS; // host name resolution attempt
+#if HDEBUG
-        soc = INVALID_SOCKET;             // not opened yet
+        printf("back_solve..\n");
-        if (host_wait(opt, &back[p])) {   // ready (file, or cached dns)
+#endif
+        back[p].status = STATUS_WAIT_DNS;       // tentative de résolution du nom de host
+        soc = INVALID_SOCKET;   // pas encore ouverte
+        back_solve(opt, &back[p]);      // préparer
+        if (host_wait(opt, &back[p])) { // prêt, par ex fichier ou dispo dans dns
 #if HDEBUG
           printf("ok, dns cache ready..\n");
 #endif
@@ -2297,9 +2199,37 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 }
 
 #if HTS_XGETHOST
-// Resolution is synchronous inside the connect path; no pre-resolve step, so
+// attendre que le host (ou celui du proxy) ait été résolu
-// the host is always immediately ready.
+// si c'est un fichier, la résolution est immédiate
-int host_wait(httrackp *opt, lien_back *back) { return 1; }
+// idem pour ftp://
+void back_solve(httrackp * opt, lien_back * back) {
+  assertf(opt != NULL);
+  assertf(back != NULL);
+  if ((!strfield(back->url_adr, "file://"))
+      && !strfield(back->url_adr, "ftp://")
+    ) {
+    const char *a;
+
+    if (!(back->r.req.proxy.active))
+      a = back->url_adr;
+    else
+      a = back->r.req.proxy.name;
+    assertf(a != NULL);
+    a = jump_protocol_const(a);
+    if (check_hostname_dns(a)) {
+      hts_log_print(opt, LOG_DEBUG, "resolved: %s", a);
+    } else {
+      hts_log_print(opt, LOG_DEBUG, "failed to resolve: %s", a);
+    }
+  }
+}
+
+// détermine si le host a pu être résolu
+int host_wait(httrackp * opt, lien_back * back) {
+  // Always synchronous. No more background DNS resolution
+  // (does not really improve performances)
+  return 1;
+}
 #endif
 
 // élimine les fichiers non html en backing (anticipation)
@@ -2486,15 +2416,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
   back_clean(opt, cache, sback);
 #endif
 
-  /* Time/size limit exceeded past grace: abort in-flight transfers so no wait
+  /* Time limit exceeded past grace: abort in-flight transfers so no wait loop
-     loop starves (#481, #77). FTP slots stay, their thread owns the socket. */
+     starves (#481). FTP slots stay, their thread owns the socket. */
   if (!back_checkmirror(opt)) {
-    const hts_mirror_limit limit = back_mirror_limit(opt);
-    const char *const reason =
-        (limit == HTS_MIRROR_LIMIT_SIZE) ? "size limit" : "time limit";
-    const char *const slotmsg = (limit == HTS_MIRROR_LIMIT_SIZE)
-                                    ? "Mirror Size Limit"
-                                    : "Mirror Time Out";
     int aborted = 0;
     unsigned int i;
 
@@ -2508,15 +2432,15 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
         if (back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))
           back_delayed_discard(opt, &back[i]);
         back[i].r.statuscode = STATUSCODE_TIMEOUT;
-        strcpybuff(back[i].r.msg, slotmsg);
+        strcpybuff(back[i].r.msg, "Mirror Time Out");
         back[i].status = STATUS_READY;
         back_set_finished(sback, i);
         aborted++;
       }
     }
     if (aborted > 0)
-      hts_log_print(opt, LOG_WARNING, "%s reached, %d transfer(s) aborted",
+      hts_log_print(opt, LOG_WARNING,
-                    reason, aborted);
+                    "time limit reached, %d transfer(s) aborted", aborted);
     return;
   }
 
@@ -2663,9 +2587,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
     for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
       unsigned int i = (i_mod + mod_random) % (back_max);
 
-      // winsock flags a failed connect in the exception set only: leave a
+      if (back[i].status > 0) {
-      // connecting slot to the connect handler, which can still fall back
-      if (back[i].status > 0 && back[i].status != STATUS_CONNECTING) {
         if (!back[i].r.is_file) {       // not file..
           if (back[i].r.soc != INVALID_SOCKET) {        // hey, you never know..
             int err = FD_ISSET(back[i].r.soc, &fds_e);
@@ -2679,7 +2601,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
               }
               back[i].r.soc = INVALID_SOCKET;
               back[i].r.statuscode = STATUSCODE_CONNERROR;
-              strcpybuff(back[i].r.msg, "Receive Error");
+              if (back[i].status == STATUS_CONNECTING)
+                strcpybuff(back[i].r.msg, "Connect Error");
+              else
+                strcpybuff(back[i].r.msg, "Receive Error");
               if (back[i].status == STATUS_ALIVE) {     /* Keep-alive socket */
                 back_delete(opt, cache, sback, i);
               } else {
@@ -2712,11 +2637,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
             gestion_timeout = 1;
 
         // connecté?
-        dispo = back[i].r.soc != INVALID_SOCKET &&
+        dispo = FD_ISSET(back[i].r.soc, &fds_c);
-                (FD_ISSET(back[i].r.soc, &fds_c) ||
-                 FD_ISSET(back[i].r.soc, &fds_e));
         if (dispo) { // socket ready: connect() finished (ok or failed)
-          // probe SO_ERROR and, on failure, fall back to the next address
+          // a refused/failed connect is reported writable too; probe SO_ERROR
+          // and, on failure, fall back to the next address (or fail the slot)
           if (connect_socket_error(back[i].r.soc) != 0) {
             if (!back_connect_next(opt, sback, i)) {
               deletehttp(&back[i].r);
@@ -2730,40 +2654,13 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
           }
           busy_state = 1;
 
-          // socks5: tunnel to the origin before anything is written, for http
-          // as well as https. Skip on a reused keep-alive socket (already
-          // tunneled) and on the post-TLS re-entry (ssl_con set) (#563).
-          if (back[i].r.req.proxy.active &&
-              hts_proxy_is_socks(back[i].r.req.proxy.name) &&
-              !back[i].r.keep_alive
-#if HTS_USEOPENSSL
-              && back[i].r.ssl_con == NULL
-#endif
-          ) {
-            const int timeout = back[i].timeout > 0 ? back[i].timeout : 30;
-
-            if (!socks5_handshake(opt, &back[i].r, back[i].url_adr, timeout)) {
-              if (!strnotempty(back[i].r.msg))
-                strcpybuff(back[i].r.msg, "SOCKS5 handshake failed");
-              deletehttp(&back[i].r);
-              back[i].r.soc = INVALID_SOCKET;
-              back[i].r.statuscode = STATUSCODE_NON_FATAL;
-              back[i].status = STATUS_READY;
-              back_set_finished(sback, i);
-              continue;
-            }
-          }
-
 #if HTS_USEOPENSSL
           /* SSL mode */
           if (back[i].r.ssl) {
             int tunnel_ok = 1;
 
-            // https via an http proxy: CONNECT-tunnel before TLS (#85); socks
+            // https via proxy: CONNECT-tunnel before TLS (#85)
-            // already carries the origin connection
+            if (back[i].r.req.proxy.active && back[i].r.ssl_con == NULL) {
-            if (back[i].r.req.proxy.active &&
-                !hts_proxy_is_socks(back[i].r.req.proxy.name) &&
-                back[i].r.ssl_con == NULL) {
               const int timeout = back[i].timeout > 0 ? back[i].timeout : 30;
 
               tunnel_ok =
@@ -3028,15 +2925,12 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                             int last_errno = 0;
 
                             back[i].r.is_write = 1;     // écrire
-                            /* a .gz/.br/.zst saved under its own coding stays
-                               packed on disk */
                             if (back[i].r.compressed &&
-                                !hts_codec_is_archive_ext(
+                                /* .gz are *NOT* depacked!! */
-                                    hts_codec_parse(back[i].r.contentencoding),
+                                strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "gz") == 0
-                                    get_ext(catbuff, sizeof(catbuff),
+                                && strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "tgz") == 0
-                                            back[i].url_sav))) {
+                              ) {
-                              if (create_back_tmpfile(opt, &back[i], "z") ==
+                              if (create_back_tmpfile(opt, &back[i]) == 0) {
-                                  0) {
                                 assertf(back[i].tmpfile != NULL);
                                 /* note: tmpfile is utf-8 */
                                 if ((back[i].r.out =
@@ -3049,20 +2943,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                           back[i].url_sav, 1, 1,
                                           back[i].r.notmodified);
                               back[i].r.compressed = 0;
-                              /* Re-fetch over an existing file (#77 follow-up):
-                                 move the good copy aside before truncating it
-                                 so an aborted transfer can restore it. url_sav
-                                 is still written normally (file list intact).
-                               */
-                              back[i].tmpfile = NULL;
-                              if (fexist_utf8(back[i].url_sav)) {
-                                if (create_back_tmpfile(opt, &back[i], "bak") !=
-                                        0 ||
-                                    RENAME(back[i].url_sav, back[i].tmpfile) !=
-                                        0) {
-                                  back[i].tmpfile = NULL;
-                                }
-                              }
                               if ((back[i].r.out =
                                    filecreate(&opt->state.strc,
                                               back[i].url_sav)) == NULL) {
@@ -3601,11 +3481,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     continue;
                   }
 
-                  // The server really sent 304 here; the *-hacks below force
-                  // NOT_MODIFIED only after confirming the file is complete.
-                  const hts_boolean server_sent_304 =
-                      (back[i].r.statuscode == HTTP_NOT_MODIFIED);
-
                   /*
                      Solve "false" 416 problems
                    */
@@ -3634,20 +3509,22 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                   if (back[i].r.statuscode == 406) {    // 'Not Acceptable'
                     back[i].r.statuscode = HTTP_OK;
                   }
-                  // On update, keep the good copy on error (mask as 304); skip
+                  // 'do not erase already downloaded file'
-                  // resume paths so a stale-partial 416 still re-fetches.
+                  // on an updated file
-                  if (HTTP_IS_ERROR(back[i].r.statuscode) &&
+                  // with an error : consider a 304 error
-                      back[i].is_update && !back[i].testmode &&
+                  if (!opt->delete_old) {
-                      back[i].range_req_size == 0 && back[i].url_sav[0] &&
+                    if (HTTP_IS_ERROR(back[i].r.statuscode) && back[i].is_update
-                      fexist_utf8(back[i].url_sav)) {
+                        && !back[i].testmode) {
-                    hts_log_print(opt, LOG_DEBUG,
+                      if (back[i].url_sav[0] && fexist_utf8(back[i].url_sav)) {
-                                  "Error %d (%s) ignored on update, keeping "
+                        hts_log_print(opt, LOG_DEBUG,
-                                  "existing copy: %s%s",
+                                      "Error ignored %d (%s) because of 'no purge' option for %s%s",
-                                  back[i].r.statuscode, back[i].r.msg,
+                                      back[i].r.statuscode, back[i].r.msg,
-                                  back[i].url_adr, back[i].url_fil);
+                                      back[i].url_adr, back[i].url_fil);
-                    back[i].r.statuscode = HTTP_NOT_MODIFIED;
+                        back[i].r.statuscode = HTTP_NOT_MODIFIED;
-                    deletehttp(&back[i].r);
+                        deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
+                        back[i].r.soc = INVALID_SOCKET;
+                      }
+                    }
                   }
                   // Various hacks to limit re-transfers when updating a mirror
                   // Force update if same size detected
@@ -3700,7 +3577,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                       if (back[i].r.statuscode == HTTP_OK && !back[i].testmode) {       // 'OK'
                         if (!is_hypertext_mime(opt, back[i].r.contenttype, back[i].url_fil)) {  // not HTML
                           if (strnotempty(back[i].url_sav)) {   // target found
-                            LLint size = fsize_utf8(back[i].url_sav);
+                            int size = fsize_utf8(back[i].url_sav);     // target size
 
                             if (size >= 0) {
                               if (back[i].r.totalsize == size) {        // same size!
@@ -3795,21 +3672,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     }
                   }
 
-                  // Out-of-protocol 304 to a Range resume: the file is still
-                  // partial, so drop it and refetch instead of trusting it.
-                  if (server_sent_304 && back[i].range_req_size > 0) {
-                    url_savename_refname_remove(opt, back[i].url_adr,
-                                                back[i].url_fil);
-                    UNLINK(back[i].url_sav);
-                    deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
-                    back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                    strcpybuff(back[i].r.msg,
-                               "Bogus 304 on resume, restarting");
-                    back[i].status = STATUS_READY;
-                    back_set_finished(sback, i);
-                  }
-
                   /* sinon, continuer */
                   /* if (back[i].r.soc!=INVALID_SOCKET) {   // ok récupérer body? */
                   // head: terminé
@@ -3919,7 +3781,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     // traiter 206 (partial content)
                     // xxc SI CHUNK VERIFIER QUE CA MARCHE??
                     if (back[i].r.statuscode == 206) {  // on nous envoie un morceau (la fin) coz une partie sur disque!
-                      LLint sz = fsize_utf8(back[i].url_sav);
+                      off_t sz = fsize_utf8(back[i].url_sav);
                       /* RFC 7233: resume at the server's Content-Range start,
                          not the offset we requested; a server may resume
                          earlier and appending the overlap duplicates bytes
@@ -3928,7 +3790,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                       const hts_boolean range_ok =
                           back[i].r.crange > 0 && resume >= 0 &&
                           resume <= (LLint) sz &&
-                          back[i].r.crange_end == back[i].r.crange - 1 &&
+                          back[i].r.crange_end + 1 == back[i].r.crange &&
                           (back[i].r.totalsize < 0 ||
                            back[i].r.totalsize ==
                                back[i].r.crange_end - resume + 1);
@@ -3957,9 +3819,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                               // drop bytes past the resume point; a silent
                               // failure could leave a stale tail, so on error
                               // drop the partial and refetch the whole file
-                              /* not (off_t): 32-bit on MSVC, wrapping a resume
+                              if (HTS_FTRUNCATE(back[i].r.out,
-                                 past 2GB */
+                                                (off_t) resume) != 0) {
-                              if (HTS_FTRUNCATE(back[i].r.out, resume) != 0) {
                                 fclose(back[i].r.out);
                                 back[i].r.out = NULL;
                                 url_savename_refname_remove(
@@ -3971,9 +3832,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                            "Can not truncate partial file, "
                                            "restarting");
                               } else {
-                                /* not (off_t): 32-bit on MSVC, truncating a
+                                fseeko(back[i].r.out, (off_t) resume, SEEK_SET);
-                                   resume past 2GB */
-                                fseeko(back[i].r.out, resume, SEEK_SET);
                                 /* create a temporary reference file in case of
                                  * broken mirror */
                                 if (back_serialize_ref(opt, &back[i]) != 0) {
@@ -4000,20 +3859,11 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           if (fp) {
                             LLint alloc_mem = resume + 1;
 
-                            // Bound the in-memory buffer to a 32-bit size (real
+                            if (back[i].r.totalsize >= 0)
-                            // in-RAM resources are far smaller); a hostile
-                            // Content-Length that would overflow the add or the
-                            // (size_t) cast is dropped and refetched instead.
-                            if (back[i].r.totalsize > INT32_MAX - alloc_mem) {
-                              url_savename_refname_remove(opt, back[i].url_adr,
-                                                          back[i].url_fil);
-                              UNLINK(back[i].url_sav);
-                              alloc_mem = -1;
-                            } else if (back[i].r.totalsize >= 0)
                               alloc_mem += back[i].r.totalsize; // AJOUTER RESTANT!
-                            if (alloc_mem >= 0 && deleteaddr(&back[i].r) &&
+                            if (deleteaddr(&back[i].r)
-                                (back[i].r.adr =
+                                && (back[i].r.adr =
-                                     (char *) malloct((size_t) alloc_mem))) {
+                                    (char *) malloct((size_t) alloc_mem))) {
                               back[i].r.size = resume;
                               if (back[i].r.totalsize >= 0)
                                 back[i].r.totalsize += resume; // -> full size
@@ -4295,46 +4145,38 @@ static int back_maxtime_grace(const int maxtime) {
   return maximum(5, minimum(30, maxtime / 10));
 }
 
-/* Bytes the smooth stop may overrun before in-flight transfers are aborted.
+int back_checkmirror(httrackp * opt) {
-   No floor (unlike the time grace): a size overrun should abort promptly. */
+  // Check max size
-static LLint back_maxsize_grace(const LLint maxsite) { return maxsite / 10; }
+  if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
-
+    if (!opt->state.stop) {     /* not yet stopped */
-/* Which cap has overrun its grace and must hard-stop the mirror (#77, #481).
+      hts_log_print(opt, LOG_ERROR,
-   -M measures received volume (HTS_TOTAL_RECV), not saved 200-only stat_bytes
+                    "More than " LLintP
-   which undercounts redirect/error-heavy crawls (#520). */
+                    " bytes have been transferred.. giving up",
-static hts_mirror_limit back_mirror_limit(httrackp *opt) {
+                    (LLint) opt->maxsite);
-  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
+      /* cancel mirror smoothly */
-      HTS_STAT.HTS_TOTAL_RECV - opt->maxsite >=
+      hts_request_stop(opt, 0);
-          back_maxsize_grace(opt->maxsite))
+    }
-    return HTS_MIRROR_LIMIT_SIZE;
+    return 1;                   /* don'k break mirror too sharply for size limits, but stop requested */
+    /*return 0;
+     */
+  }
+  // Check max time
   if (opt->maxtime > 0) {
     const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;
 
-    if (elapsed >= opt->maxtime &&
+    if (elapsed >= opt->maxtime) {
-        elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
+      if (!opt->state.stop) { /* not yet stopped */
-      return HTS_MIRROR_LIMIT_TIME;
+        hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
+                      opt->maxtime);
+        /* cancel mirror smoothly */
+        hts_request_stop(opt, 0);
+      }
+      /* smooth stop starved past the grace period: stop waiting (#481) */
+      if (elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
+        return 0;
+    }
   }
-  return HTS_MIRROR_LIMIT_NONE;
+  return 1;                     /* Ok, go on */
-}
-
-int back_checkmirror(httrackp *opt) {
-  /* request a smooth stop the first time each cap is reached */
-  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
-      !opt->state.stop) {
-    hts_log_print(opt, LOG_ERROR,
-                  "More than " LLintP
-                  " bytes have been transferred.. giving up",
-                  (LLint) opt->maxsite);
-    hts_request_stop(opt, 0);
-  }
-  if (opt->maxtime > 0 && !opt->state.stop &&
-      (time_local() - HTS_STAT.stat_timestart) >= opt->maxtime) {
-    hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
-                  opt->maxtime);
-    hts_request_stop(opt, 0);
-  }
-  /* hard stop once a cap overruns its grace (callers must stop waiting) */
-  return back_mirror_limit(opt) == HTS_MIRROR_LIMIT_NONE;
 }
 
 // octets transférés + add

src/htsback.h

@@ -138,11 +138,12 @@ LLint back_transferred(LLint add, struct_back * sback);
 
 // hostback
 #if HTS_XGETHOST
+void back_solve(httrackp * opt, lien_back * sback);
 int host_wait(httrackp * opt, lien_back * sback);
 #endif
 int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize);
-/* Enforce -M/-E quotas: smooth-stops when reached; returns 0 once the -M cap
+/* Enforce -M/-E quotas: requests a smooth stop when reached; returns 0 once
-   or -E deadline overruns its grace period (callers must stop waiting). */
+   the -E deadline overran its grace period (callers must stop waiting). */
 int back_checkmirror(httrackp * opt);
 
 #endif

src/htscache.c

@@ -356,7 +356,7 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
       FILE *fp;
 
       // On recopie le fichier->.
-      LLint file_size = fsize_utf8(fconv(catbuff, sizeof(catbuff), url_save));
+      off_t file_size = fsize_utf8(fconv(catbuff, sizeof(catbuff), url_save));
 
       if (file_size >= 0) {
         fp = FOPEN(fconv(catbuff, sizeof(catbuff), url_save), "rb");
@@ -1241,27 +1241,23 @@ char *readfile(const char *fil) {
 char *readfile2(const char *fil, LLint * size) {
   char *adr = NULL;
   char catbuff[CATBUFF_SIZE];
-  const LLint len = fsize(fil);
+  INTsys len = 0;
 
-  /* a size too large for size_t (32-bit Windows/i386) must fail closed: it
+  len = fsize(fil);
-     would wrap malloct() short while fread() still read the untruncated len */
+  if (len >= 0) {               // exists
-  const size_t buflen = len >= 0 ? llint_to_size_t(len) : (size_t) -1;
-
-  if (buflen != (size_t) -1) { // exists, and is addressable
     FILE *fp;
 
     fp = fopen(fconv(catbuff, sizeof(catbuff), fil), "rb");
     if (fp != NULL) {           // n'existe pas (!)
-      adr = (char *) malloct(buflen + 1);
+      adr = (char *) malloct(len + 1);
       if (size != NULL)
         *size = len;
       if (adr != NULL) {
-        if (buflen > 0 &&
+        if (len > 0 && fread(adr, 1, len, fp) != len) { // fichier endommagé ?
-            fread(adr, 1, buflen, fp) != buflen) { // fichier endommagé ?
           freet(adr);
           adr = NULL;
         } else
-          *(adr + buflen) = '\0';
+          *(adr + len) = '\0';
       }
       fclose(fp);
     }
@@ -1273,21 +1269,19 @@ char *readfile2(const char *fil, LLint * size) {
 char *readfile_utf8(const char *fil) {
   char *adr = NULL;
   char catbuff[CATBUFF_SIZE];
-  const LLint len = fsize_utf8(fil);
+  const off_t len = fsize_utf8(fil);
-  const size_t buflen = len >= 0 ? llint_to_size_t(len) : (size_t) -1;
 
-  if (buflen != (size_t) -1) { // exists, and is addressable (see readfile2)
+  if (len >= 0) {               // exists
     FILE *const fp = FOPEN(fconv(catbuff, sizeof(catbuff), fil), "rb");
 
     if (fp != NULL) {           // n'existe pas (!)
-      adr = (char *) malloct(buflen + 1);
+      adr = (char *) malloct(len + 1);
       if (adr != NULL) {
-        if (buflen > 0 &&
+        if (len > 0 && fread(adr, 1, len, fp) != len) { // fichier endommagé ?
-            fread(adr, 1, buflen, fp) != buflen) { // fichier endommagé ?
           freet(adr);
           adr = NULL;
         } else {
-          adr[buflen] = '\0';
+          adr[len] = '\0';
         }
       }
       fclose(fp);

src/htscache_selftest.c

@@ -232,10 +232,11 @@ static int disk_fallback_selftest(httrackp *opt) {
   static const char body[] = "BINARY-on-disk-body-0123456789-no-trailing-nul";
   const size_t body_len = sizeof(body) - 1;
 
-  /* a DOS-ified X-Save loses the path_html_utf8 prefix the reader matches on,
+  /* X-Save must start with path_html_utf8 so the reader resolves it verbatim
-     and gets re-rooted as a pre-3.40 relative path; fconv() only on access */
+     (otherwise it re-roots it as a pre-3.40 relative path); then the body we
-  concat(save, sizeof(save), StringBuff(opt->path_html_utf8),
+     create at fconv(save) is exactly where cache_readex looks for it. */
-         "example.com/blob.bin");
+  fconcat(save, sizeof(save), StringBuff(opt->path_html_utf8),
+          "example.com/blob.bin");
 
   /* write only the header (X-In-Cache: 0); the body stays on disk */
   selftest_open_for_write(&cache, opt);
@@ -938,9 +939,9 @@ static void reconcile_put(httrackp *opt, const char *name, size_t size) {
 }
 
 /* Expect `name` to weigh `size` bytes, or be absent when size == -1. */
-static int reconcile_expect(httrackp *opt, const char *name, LLint size,
+static int reconcile_expect(httrackp *opt, const char *name, off_t size,
                             const char *what) {
-  const LLint got = fsize(reconcile_st_path(opt, name));
+  const off_t got = fsize(reconcile_st_path(opt, name));
 
   if (got != size) {
     fprintf(stderr, "cache-reconcile: %s: %s is %d bytes, expected %d\n", what,
@@ -954,7 +955,7 @@ int cache_reconcile_selftest(httrackp *opt, const char *dir) {
   int failures = 0;
 
   /* around the interrupted-run thresholds (new < 32768, old > 65536) */
-  static const LLint TINY = 1024, MID = 40000, SOLID = 131072;
+  static const off_t TINY = 1024, MID = 40000, SOLID = 131072;
 
   golden_setup(opt, dir);
 #ifdef _WIN32
@@ -1252,9 +1253,8 @@ static void corrupt_build_disk(httrackp *opt) {
   memset(corrupt_body_a, 'a', sizeof(corrupt_body_a) - 1);
   remove(reconcile_st_path(opt, "hts-cache/new.zip"));
   remove(reconcile_st_path(opt, "hts-cache/old.zip"));
-  /* X-Save stored verbatim: see disk_fallback_selftest */
+  fconcat(save, sizeof(save), StringBuff(opt->path_html_utf8),
-  concat(save, sizeof(save), StringBuff(opt->path_html_utf8),
+          CORRUPT_ADR "/victim.bin");
-         CORRUPT_ADR "/victim.bin");
   selftest_open_for_write(&cache, opt);
   store_entry(opt, &cache, CORRUPT_ADR, "/canary.html", "canary.html", 200,
               "OK", "text/html", "utf-8", "", "", "", "", corrupt_body_a,

src/htscharset.c

@@ -31,9 +31,6 @@ Please visit our Website: http://www.httrack.com
 /* ------------------------------------------------------------ */
 
 #include "htscharset.h"
-#ifdef _WIN32
-#include <shellapi.h>
-#endif
 #include "htsbase.h"
 #include "punycode.h"
 #include "htssafe.h"
@@ -87,7 +84,7 @@ static int hts_equalsAlphanum(const char *a, const char *b) {
 
 /* Copy the memory region [s .. s + size - 1 ] as a \0-terminated string. */
 static char *hts_stringMemCopy(const char *s, size_t size) {
-  char *dest = malloct(size + 1);
+  char *dest = malloc(size + 1);
 
   if (dest != NULL) {
     memcpy(dest, s, size);
@@ -385,44 +382,10 @@ char *hts_convertStringFromUTF8(const char *s, size_t size, const char *charset)
   return hts_convertStringCPFromUTF8(s, size, cp);
 }
 
-HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size) {
+char *hts_convertStringSystemToUTF8(const char *s, size_t size) {
   return hts_convertStringCPToUTF8(s, size, GetACP());
 }
 
-HTSEXT_API void hts_argv_utf8(int *pargc, char ***pargv) {
-  int wargc = 0;
-  LPWSTR *const wargv = CommandLineToArgvW(GetCommandLineW(), &wargc);
-  char **argv;
-  int i;
-
-  // On any failure keep the CRT's ANSI argv: lossy, but never half-converted.
-  if (wargv == NULL)
-    return;
-  if (wargc <= 0 ||
-      (argv = calloct((size_t) wargc + 1, sizeof(char *))) == NULL) {
-    LocalFree(wargv);
-    return;
-  }
-  for (i = 0; i < wargc; i++) {
-    const int wsize = (int) wcslen(wargv[i]);
-
-    // hts_convertUCS2StringToUTF8() returns NULL on an empty string
-    argv[i] =
-        wsize != 0 ? hts_convertUCS2StringToUTF8(wargv[i], wsize) : strdupt("");
-    if (argv[i] == NULL) {
-      while (i-- != 0)
-        freet(argv[i]);
-      freet(argv);
-      LocalFree(wargv);
-      return;
-    }
-  }
-  argv[wargc] = NULL; // callers may rely on argv[argc] == NULL
-  LocalFree(wargv);
-  *pargc = wargc;
-  *pargv = argv; // never freed: argv lives for the process
-}
-
 #else
 
 #include <errno.h>
@@ -586,6 +549,42 @@ char *hts_convertStringFromUTF8(const char *s, size_t size, const char *charset)
 
 #endif
 
+HTS_STATIC char *hts_getCharsetFromContentType(const char *mime) {
+  /* text/html; charset=utf-8 */
+  const char *const charset = "charset";
+  char *pos = strstr(mime, charset);
+
+  if (pos != NULL) {
+    /* Skip spaces */
+    int eq = 0;
+
+    for(pos += strlen(charset);
+        *pos == ' ' || *pos == '=' || *pos == '"' || *pos == '\''; pos++) {
+      if (*pos == '=') {
+        eq = 1;
+      }
+    }
+    if (eq == 1) {
+      int len;
+
+      for(len = 0;
+          pos[len] == ' ' || pos[len] == ';' || pos[len] == '"' || *pos == '\'';
+          pos++) ;
+      if (len != 0) {
+        char *const s = malloc(len + 1);
+        int i;
+
+        for(i = 0; i < len; i++) {
+          s[i] = pos[i];
+        }
+        s[len] = '\0';
+        return s;
+      }
+    }
+  }
+  return NULL;
+}
+
 #ifdef _WIN32
 #define strcasecmp(a,b) stricmp(a,b)
 #define strncasecmp(a,b,n) strnicmp(a,b,n)
@@ -645,106 +644,58 @@ int hts_isCharsetUTF8(const char *charset) {
          || strcasecmp(charset, "utf8") == 0 );
 }
 
-/* Extract X from a "text/html; charset=X" content= attribute value. */
-static char *charset_from_content(const char *s, size_t len) {
-  size_t i;
-
-  for (i = 0; i + 7 < len; i++) {
-    if ((i == 0 || is_space(s[i - 1]) || s[i - 1] == ';') &&
-        strncasecmp(&s[i], "charset", 7) == 0 && is_space_or_equal(s[i + 7])) {
-      size_t j, val;
-
-      for (j = i + 7; j < len && is_space_or_equal_or_quote(s[j]); j++)
-        ;
-      for (val = j; j < len && s[j] != '"' && s[j] != '\'' && s[j] != ';' &&
-                    !is_space(s[j]);
-           j++)
-        ;
-      if (j != val) {
-        return hts_stringMemCopy(&s[val], j - val);
-      }
-    }
-  }
-  return NULL;
-}
-
 char *hts_getCharsetFromMeta(const char *html, size_t size) {
-  size_t i;
+  int i;
 
-  /* HTML5 <meta charset=X> or legacy
+  /* <META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=utf-8" > */
-     <meta http-equiv="Content-Type" content="text/html; charset=X">,
+  for(i = 0; i < size; i++) {
-     attributes in any order; first resolvable tag wins. */
+    if (html[i] == '<' && strncasecmp(&html[i + 1], "meta", 4) == 0
-  for (i = 0; i + 6 < size; i++) {
+        && is_space(html[i + 5])) {
-    size_t j;
+      /* Skip spaces */
-    const char *equiv = NULL, *content = NULL;
+      for(i += 5; is_space(html[i]); i++) ;
-    size_t equiv_len = 0, content_len = 0;
+      if (strncasecmp(&html[i], "HTTP-EQUIV", 10) == 0
+          && is_space_or_equal(html[i + 10])) {
+        for(i += 10; is_space_or_equal_or_quote(html[i]); i++) ;
+        if (strncasecmp(&html[i], "CONTENT-TYPE", 12) == 0) {
+          for(i += 12; is_space_or_equal_or_quote(html[i]); i++) ;
+          if (strncasecmp(&html[i], "CONTENT", 7) == 0
+              && is_space_or_equal(html[i + 7])) {
+            for(i += 7; is_space_or_equal_or_quote(html[i]); i++) ;
+            /* Skip content-type */
+            for(;
+                i < size && html[i] != ';' && html[i] != '"' && html[i] != '\'';
+                i++) ;
+            /* Expect charset attribute here */
+            if (html[i] == ';') {
+              for(i++; is_space(html[i]); i++) ;
+              /* Look for charset */
+              if (strncasecmp(&html[i], "charset", 7) == 0
+                  && is_space_or_equal(html[i + 7])) {
+                int len;
 
-    if (html[i] != '<' || strncasecmp(&html[i + 1], "meta", 4) != 0 ||
+                for(i += 7; is_space_or_equal(html[i]) || html[i] == '\'';
-        !is_space(html[i + 5])) {
+                    i++) ;
-      continue;
+                /* Charset */
-    }
+                for(len = 0;
-    /* Attribute scan, strictly bounded by size. */
+                    i + len < size && html[i + len] != '"'
-    for (j = i + 6; j < size && html[j] != '>';) {
+                    && html[i + len] != '\'' && html[i + len] != ' '; len++) ;
-      size_t name, name_len, val = 0, val_len = 0;
+                /* No error ? */
+                if (len != 0 && i < size) {
+                  char *const s = malloc(len + 1);
+                  int j;
 
-      if (is_space(html[j]) || html[j] == '/') {
+                  for(j = 0; j < len; j++) {
-        j++;
+                    s[j] = html[i + j];
-        continue;
+                  }
-      }
+                  s[len] = '\0';
-      for (name = j; j < size && html[j] != '=' && html[j] != '>' &&
+                  return s;
-                     html[j] != '/' && !is_space(html[j]);
+                }
-           j++)
+              }
-        ;
+            }
-      name_len = j - name;
-      for (; j < size && is_space(html[j]); j++)
-        ;
-      if (j < size && html[j] == '=') {
-        for (j++; j < size && is_space(html[j]); j++)
-          ;
-        if (j < size && (html[j] == '"' || html[j] == '\'')) {
-          const char quote = html[j++];
-
-          for (val = j; j < size && html[j] != quote; j++)
-            ;
-          if (j >= size) /* unterminated quote: drop the tag */
-            break;
-          val_len = j++ - val;
-        } else {
-          /* unquoted: ends at whitespace or '>' only (HTML5 prescan); '/'
-             belongs to the value except as the tail of a self-close */
-          for (val = j; j < size && !is_space(html[j]) && html[j] != '>'; j++)
-            ;
-          val_len = j - val;
-          if (val_len != 0 && j < size && html[j] == '>' &&
-              html[val + val_len - 1] == '/') {
-            val_len--;
           }
         }
       }
-      /* first occurrence of each attribute wins, as in browsers */
-      if (val_len != 0) {
-        if (name_len == 7 && strncasecmp(&html[name], "charset", 7) == 0) {
-          return hts_stringMemCopy(&html[val], val_len);
-        } else if (equiv == NULL && name_len == 10 &&
-                   strncasecmp(&html[name], "http-equiv", 10) == 0) {
-          equiv = &html[val];
-          equiv_len = val_len;
-        } else if (content == NULL && name_len == 7 &&
-                   strncasecmp(&html[name], "content", 7) == 0) {
-          content = &html[val];
-          content_len = val_len;
-        }
-      }
     }
-    if (equiv_len == 12 && strncasecmp(equiv, "content-type", 12) == 0 &&
-        content != NULL) {
-      char *const s = charset_from_content(content, content_len);
-
-      if (s != NULL) {
-        return s;
-      }
-    }
-    i = j;
   }
   return NULL;
 }
@@ -1189,45 +1140,17 @@ int hts_isStringUTF8(const char *s, size_t size) {
   const unsigned char *const data = (const unsigned char*) s;
   size_t i;
 
-  /* Strict RFC 3629: reject overlongs, surrogates, > U+10FFFF, 5/6-byte. */
   for(i = 0 ; i < size ; ) {
-    const unsigned char c = data[i];
+    /* Reader: can read bytes up to j */
-    size_t len, k;
+#define RD ( i < size ? data[i++] : -1 )
-    hts_UCS4 uc, min;
 
-    if (c < 0x80) {
+    /* Writer: a malformed sequence means the string is not UTF-8 (return 0) */
-      i++;
+#define WR(C) if ((C) == -1) { return 0; }
-      continue;
-    } else if (c >= 0xc2 && c <= 0xdf) {
-      len = 2;
-      min = 0x80;
-      uc = c & 0x1f;
-    } else if (c >= 0xe0 && c <= 0xef) {
-      len = 3;
-      min = 0x800;
-      uc = c & 0x0f;
-    } else if (c >= 0xf0 && c <= 0xf4) {
-      len = 4;
-      min = 0x10000;
-      uc = c & 0x07;
-    } else { /* continuation byte, overlong C0/C1, or F5..FF lead */
-      return 0;
-    }
-    if (size - i < len) {
-      return 0;
-    }
-    for (k = 1; k < len; k++) {
-      const unsigned char cc = data[i + k];
 
-      if ((cc & 0xc0) != 0x80) {
+    /* Read Unicode character. */
-        return 0;
+    READ_UNICODE(RD, WR);
-      }
+#undef RD
-      uc = (uc << 6) | (cc & 0x3f);
+#undef WR
-    }
-    if (uc < min || uc > 0x10FFFF || (uc >= 0xD800 && uc <= 0xDFFF)) {
-      return 0;
-    }
-    i += len;
   }
 
   return 1;

src/htscharset.h

@@ -34,7 +34,6 @@ Please visit our Website: http://www.httrack.com
 #define HTS_CHARSET_DEFH
 
 /** Standard includes. **/
-#include "htsglobal.h"
 #include <stdlib.h>
 #include <string.h>
 #ifdef _WIN32
@@ -77,8 +76,7 @@ extern char *hts_convertStringIDNAToUTF8(const char *s, size_t size);
 extern int hts_isStringIDNA(const char *s, size_t size);
 
 /**
- * Extract the <meta> charset from the HTML buffer "html" (HTML5 charset= or
+ * Extract the charset from the HTML buffer "html"
- * legacy http-equiv form). Returns a malloc'ed string, or NULL if none.
  **/
 extern char *hts_getCharsetFromMeta(const char *html, size_t size);
 
@@ -88,8 +86,7 @@ extern char *hts_getCharsetFromMeta(const char *html, size_t size);
 extern int hts_isStringAscii(const char *s, size_t size);
 
 /**
- * Is the given string valid UTF-8 ? Strict RFC 3629: overlong forms,
+ * Is the given string an UTF-8 string ?
- * surrogates, codepoints above U+10FFFF and 5/6-byte sequences are rejected.
  **/
 extern int hts_isStringUTF8(const char *s, size_t size);
 
@@ -175,16 +172,7 @@ extern char *hts_convertUCS2StringToUTF8(LPWSTR woutput, int wsize);
  * Convert current system codepage to UTF-8.
  * This function is WIN32 specific.
  **/
-HTSEXT_API char *hts_convertStringSystemToUTF8(const char *s, size_t size);
+extern char *hts_convertStringSystemToUTF8(const char *s, size_t size);
-
-/**
- * Replace the CRT's ANSI argv by a UTF-8 one decoded from the real UTF-16
- * command line: every char* is UTF-8 on Windows (FOPEN, STAT, ... convert at
- * the syscall boundary). Keeps the CRT's argv on failure; the new array is
- * writable, NULL-terminated, and lives for the process.
- * This function is WIN32 specific.
- **/
-HTSEXT_API void hts_argv_utf8(int *pargc, char ***pargv);
 #endif
 
 #endif

src/htscodec.c

@@ -1,366 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* ------------------------------------------------------------ */
-/* File: HTTP content codings (gzip/deflate, brotli, zstd)      */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-/* Internal engine bytecode */
-#define HTS_INTERNAL_BYTECODE
-
-#include "htsbase.h"
-#include "htscore.h"
-#include "htscodec.h"
-#include "htszlib.h"
-
-#if HTS_USEBROTLI
-#include <brotli/decode.h>
-#endif
-
-#if HTS_USEZSTD
-#include <zstd.h>
-/* 8 MB, the window an HTTP zstd decoder must honor (RFC 9659); libzstd
-   defaults to 128 MB. */
-#define HTS_ZSTD_WINDOWLOG_MAX 23
-#endif
-
-/* Decoded-size budget, bounding a bomb: brotli and zstd reach a million to one.
-   Deflate cannot pass 1032x, so it only meets this at the 2 GiB ceiling. */
-#define HTS_CODEC_MAX_RATIO 4096
-#define HTS_CODEC_MIN_MAXOUT (1024 * 1024)
-
-LLint hts_codec_maxout(LLint in_size) {
-  LLint maxout;
-
-  if (in_size <= 0 || in_size > INT_MAX / HTS_CODEC_MAX_RATIO)
-    maxout = INT_MAX;
-  else
-    maxout = in_size * HTS_CODEC_MAX_RATIO;
-  if (maxout < HTS_CODEC_MIN_MAXOUT)
-    maxout = HTS_CODEC_MIN_MAXOUT;
-  return maxout;
-}
-
-hts_codec hts_codec_parse(const char *encoding) {
-  if (encoding == NULL || encoding[0] == '\0' ||
-      strfield2(encoding, "identity"))
-    return HTS_CODEC_IDENTITY;
-  if (strfield2(encoding, "gzip") || strfield2(encoding, "x-gzip") ||
-      strfield2(encoding, "deflate") || strfield2(encoding, "x-deflate"))
-    return HTS_USEZLIB ? HTS_CODEC_DEFLATE : HTS_CODEC_UNSUPPORTED;
-  if (strfield2(encoding, "br"))
-    return HTS_USEBROTLI ? HTS_CODEC_BROTLI : HTS_CODEC_UNSUPPORTED;
-  if (strfield2(encoding, "zstd"))
-    return HTS_USEZSTD ? HTS_CODEC_ZSTD : HTS_CODEC_UNSUPPORTED;
-  if (strfield2(encoding, "compress") || strfield2(encoding, "x-compress"))
-    return HTS_CODEC_UNSUPPORTED; /* LZW: never advertised, no decoder here */
-  /* Not a coding at all: broken servers put charsets and the like here, and
-     the plain body they sent must survive it. */
-  return HTS_CODEC_IDENTITY;
-}
-
-#if HTS_USEBROTLI
-#define HTS_AE_BROTLI ", br"
-#else
-#define HTS_AE_BROTLI ""
-#endif
-#if HTS_USEZSTD
-#define HTS_AE_ZSTD ", zstd"
-#else
-#define HTS_AE_ZSTD ""
-#endif
-
-const char *hts_acceptencoding(hts_boolean compressible, hts_boolean secure) {
-  if (!compressible)
-    return "identity";
-#if HTS_USEZLIB
-  /* br and zstd over TLS only, as browsers do: a cleartext intermediary that
-     rewrites a coding it can not read would corrupt the mirror. */
-  if (secure)
-    return "gzip, deflate" HTS_AE_BROTLI HTS_AE_ZSTD ", identity;q=0.9";
-  return "gzip, deflate, identity;q=0.9";
-#else
-  (void) secure;
-  return "identity";
-#endif
-}
-
-hts_boolean hts_codec_is_archive_ext(hts_codec codec, const char *ext) {
-  if (ext == NULL || ext[0] == '\0')
-    return HTS_FALSE;
-  switch (codec) {
-  case HTS_CODEC_DEFLATE:
-    return strfield2(ext, "gz") || strfield2(ext, "tgz") ? HTS_TRUE : HTS_FALSE;
-  case HTS_CODEC_BROTLI:
-    return strfield2(ext, "br") ? HTS_TRUE : HTS_FALSE;
-  case HTS_CODEC_ZSTD:
-    return strfield2(ext, "zst") || strfield2(ext, "tzst") ? HTS_TRUE
-                                                           : HTS_FALSE;
-  default:
-    return HTS_FALSE;
-  }
-}
-
-#if HTS_USEBROTLI || HTS_USEZSTD
-/* Append produced bytes to out under the decoded-size budget, advancing *total.
-   HTS_FALSE on a short write or once the budget is exceeded (a bomb); the
-   over-budget bytes are never written. */
-static hts_boolean codec_sink(FILE *out, const void *buf, size_t produced,
-                              LLint *total, LLint maxout) {
-  if (produced == 0)
-    return HTS_TRUE;
-  *total += (LLint) produced;
-  if (*total > maxout)
-    return HTS_FALSE;
-  return fwrite(buf, 1, produced, out) == produced ? HTS_TRUE : HTS_FALSE;
-}
-#endif
-
-#if HTS_USEBROTLI
-static int codec_unpack_brotli(FILE *in, FILE *out, LLint maxout) {
-  BrotliDecoderState *const state =
-      BrotliDecoderCreateInstance(NULL, NULL, NULL);
-  hts_boolean ok = HTS_TRUE, done = HTS_FALSE;
-  LLint total = 0;
-
-  if (state == NULL)
-    return -1;
-  while (ok && !done) {
-    unsigned char BIGSTK inbuf[8192];
-    size_t avail_in = fread(inbuf, 1, sizeof(inbuf), in);
-    const uint8_t *next_in = inbuf;
-
-    if (avail_in == 0)
-      break; /* EOF; a stream still hungry for input is truncated */
-    for (;;) {
-      unsigned char BIGSTK outbuf[8192];
-      uint8_t *next_out = outbuf;
-      size_t avail_out = sizeof(outbuf);
-      size_t produced;
-      BrotliDecoderResult res;
-
-      res = BrotliDecoderDecompressStream(state, &avail_in, &next_in,
-                                          &avail_out, &next_out, NULL);
-      produced = sizeof(outbuf) - avail_out;
-      if (!codec_sink(out, outbuf, produced, &total, maxout)) {
-        ok = HTS_FALSE;
-        break;
-      }
-      if (res == BROTLI_DECODER_RESULT_ERROR) {
-        ok = HTS_FALSE;
-        break;
-      }
-      if (res == BROTLI_DECODER_RESULT_SUCCESS) {
-        done = HTS_TRUE;
-        break;
-      }
-      if (res == BROTLI_DECODER_RESULT_NEEDS_MORE_INPUT)
-        break;
-    }
-    if (ferror(in))
-      ok = HTS_FALSE;
-  }
-  BrotliDecoderDestroyInstance(state);
-  return (ok && done && !ferror(in)) ? (int) total : -1;
-}
-
-static size_t codec_head_brotli(const void *in, size_t in_len, void *out,
-                                size_t out_len) {
-  BrotliDecoderState *const state =
-      BrotliDecoderCreateInstance(NULL, NULL, NULL);
-  const uint8_t *next_in = (const uint8_t *) in;
-  uint8_t *next_out = (uint8_t *) out;
-  size_t avail_in = in_len, avail_out = out_len;
-  BrotliDecoderResult res;
-
-  if (state == NULL)
-    return 0;
-  res = BrotliDecoderDecompressStream(state, &avail_in, &next_in, &avail_out,
-                                      &next_out, NULL);
-  BrotliDecoderDestroyInstance(state);
-  return (res != BROTLI_DECODER_RESULT_ERROR) ? out_len - avail_out : 0;
-}
-#endif
-
-#if HTS_USEZSTD
-static int codec_unpack_zstd(FILE *in, FILE *out, LLint maxout) {
-  ZSTD_DStream *const zds = ZSTD_createDStream();
-  hts_boolean ok = HTS_TRUE, eof = HTS_FALSE;
-  size_t zret = 1; /* 0 once a frame is fully flushed */
-  LLint total = 0;
-
-  if (zds == NULL)
-    return -1;
-  if (ZSTD_isError(ZSTD_DCtx_setParameter(zds, ZSTD_d_windowLogMax,
-                                          HTS_ZSTD_WINDOWLOG_MAX))) {
-    ZSTD_freeDStream(zds);
-    return -1;
-  }
-  while (ok && !eof) {
-    unsigned char BIGSTK inbuf[8192];
-    ZSTD_inBuffer input;
-
-    input.src = inbuf;
-    input.size = fread(inbuf, 1, sizeof(inbuf), in);
-    input.pos = 0;
-    if (input.size == 0) {
-      eof = HTS_TRUE;
-      break;
-    }
-    while (input.pos < input.size) {
-      unsigned char BIGSTK outbuf[8192];
-      ZSTD_outBuffer output;
-
-      output.dst = outbuf;
-      output.size = sizeof(outbuf);
-      output.pos = 0;
-      zret = ZSTD_decompressStream(zds, &output, &input);
-      if (ZSTD_isError(zret)) {
-        ok = HTS_FALSE;
-        break;
-      }
-      if (!codec_sink(out, outbuf, output.pos, &total, maxout)) {
-        ok = HTS_FALSE;
-        break;
-      }
-    }
-    if (ferror(in))
-      ok = HTS_FALSE;
-  }
-  ZSTD_freeDStream(zds);
-  /* zret != 0 at EOF: the last frame never completed */
-  return (ok && zret == 0 && !ferror(in)) ? (int) total : -1;
-}
-
-static size_t codec_head_zstd(const void *in, size_t in_len, void *out,
-                              size_t out_len) {
-  ZSTD_DStream *const zds = ZSTD_createDStream();
-  ZSTD_inBuffer input;
-  ZSTD_outBuffer output;
-  size_t zret;
-
-  if (zds == NULL)
-    return 0;
-  if (ZSTD_isError(ZSTD_DCtx_setParameter(zds, ZSTD_d_windowLogMax,
-                                          HTS_ZSTD_WINDOWLOG_MAX))) {
-    ZSTD_freeDStream(zds);
-    return 0;
-  }
-  input.src = in;
-  input.size = in_len;
-  input.pos = 0;
-  output.dst = out;
-  output.size = out_len;
-  output.pos = 0;
-  zret = ZSTD_decompressStream(zds, &output, &input);
-  ZSTD_freeDStream(zds);
-  return ZSTD_isError(zret) ? 0 : output.pos;
-}
-#endif
-
-LLint hts_codec_coded_size(FILE *in) {
-  long size;
-
-  if (fseek(in, 0, SEEK_END) != 0)
-    return -1;
-  size = ftell(in);
-  if (size < 0 || fseek(in, 0, SEEK_SET) != 0)
-    return -1;
-  return (LLint) size;
-}
-
-int hts_codec_unpack(hts_codec codec, const char *filename,
-                     const char *newfile) {
-  if (filename == NULL || newfile == NULL || !filename[0] || !newfile[0])
-    return -1;
-  switch (codec) {
-  case HTS_CODEC_DEFLATE:
-#if HTS_USEZLIB
-    return hts_zunpack(filename, newfile);
-#else
-    return -1;
-#endif
-  case HTS_CODEC_BROTLI:
-  case HTS_CODEC_ZSTD:
-    break;
-  default: /* IDENTITY never reaches the unpacker; UNSUPPORTED must fail */
-    return -1;
-  }
-#if HTS_USEBROTLI || HTS_USEZSTD
-  {
-    char catbuff[CATBUFF_SIZE];
-    FILE *out, *in = FOPEN(fconv(catbuff, sizeof(catbuff), filename), "rb");
-    LLint maxout;
-    int ret = -1;
-
-    if (in == NULL)
-      return -1;
-    maxout = hts_codec_maxout(hts_codec_coded_size(in));
-    out = FOPEN(fconv(catbuff, sizeof(catbuff), newfile), "wb");
-    if (out == NULL) {
-      fclose(in);
-      return -1;
-    }
-#if HTS_USEBROTLI
-    if (codec == HTS_CODEC_BROTLI)
-      ret = codec_unpack_brotli(in, out, maxout);
-#endif
-#if HTS_USEZSTD
-    if (codec == HTS_CODEC_ZSTD)
-      ret = codec_unpack_zstd(in, out, maxout);
-#endif
-    fclose(out);
-    fclose(in);
-    return ret;
-  }
-#else
-  return -1;
-#endif
-}
-
-size_t hts_codec_head(hts_codec codec, const void *in, size_t in_len, void *out,
-                      size_t out_len) {
-  if (in == NULL || in_len == 0 || out == NULL || out_len == 0)
-    return 0;
-  switch (codec) {
-#if HTS_USEZLIB
-  case HTS_CODEC_DEFLATE:
-    return hts_zhead(in, in_len, out, out_len);
-#endif
-#if HTS_USEBROTLI
-  case HTS_CODEC_BROTLI:
-    return codec_head_brotli(in, in_len, out, out_len);
-#endif
-#if HTS_USEZSTD
-  case HTS_CODEC_ZSTD:
-    return codec_head_zstd(in, in_len, out, out_len);
-#endif
-  default:
-    return 0;
-  }
-}

src/htscodec.h

@@ -1,79 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* ------------------------------------------------------------ */
-/* File: HTTP content codings (gzip/deflate, brotli, zstd)      */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-#ifndef HTS_DEFCODEC
-#define HTS_DEFCODEC
-
-#include "htsglobal.h"
-
-/* Content codings we may meet in a Content-Encoding header. */
-typedef enum {
-  HTS_CODEC_IDENTITY = 0, /**< no coding, or a token we treat as none */
-  HTS_CODEC_DEFLATE,      /**< gzip, x-gzip, deflate, x-deflate */
-  HTS_CODEC_BROTLI,       /**< br */
-  HTS_CODEC_ZSTD,         /**< zstd */
-  HTS_CODEC_UNSUPPORTED   /**< a real coding we can not decode */
-} hts_codec;
-
-#ifdef HTS_INTERNAL_BYTECODE
-
-/* Codec for a Content-Encoding token. A known coding we can not decode is
-   UNSUPPORTED; an unrecognized token is IDENTITY (servers do emit junk). */
-extern hts_codec hts_codec_parse(const char *encoding);
-
-/* Accept-Encoding value to advertise; secure (TLS) also offers br and zstd. */
-extern const char *hts_acceptencoding(hts_boolean compressible,
-                                      hts_boolean secure);
-
-/* HTS_TRUE if ext is the codec's own archive extension: a foo.gz served as
-   Content-Encoding: gzip stays packed on disk. */
-extern hts_boolean hts_codec_is_archive_ext(hts_codec codec, const char *ext);
-
-/* Decode filename into newfile. Returns the decoded size, or -1 on a truncated
-   or corrupt stream, an unsupported coding, a bomb over the budget, or I/O. */
-extern int hts_codec_unpack(hts_codec codec, const char *filename,
-                            const char *newfile);
-
-/* Decode up to out_len leading bytes of a coded body for the MIME sniffer;
-   0 when nothing could be decoded. */
-extern size_t hts_codec_head(hts_codec codec, const void *in, size_t in_len,
-                             void *out, size_t out_len);
-
-/* Ceiling on the decoded size of a body of in_size coded bytes. */
-extern LLint hts_codec_maxout(LLint in_size);
-
-/* Coded size of an open stream, left rewound; -1 if unknown. */
-extern LLint hts_codec_coded_size(FILE *in);
-
-#endif
-
-#endif

src/htscore.c

@@ -855,7 +855,7 @@ int httpmirror(char *url1, httrackp * opt) {
       char *filelist_buff = NULL;
       size_t filelist_sz = 0;
       const char *filelist_err = NULL; /* failure reason, NULL on success */
-      const LLint fs = fsize(StringBuff(opt->filelist));
+      const off_t fs = fsize(StringBuff(opt->filelist));
 
       if (fs < 0) {
         /* fsize() hides the cause; redo stat() for a precise errno (#49) */
@@ -863,7 +863,7 @@ int httpmirror(char *url1, httrackp * opt) {
         filelist_err = stat(StringBuff(opt->filelist), &st) != 0
                            ? strerror(errno)
                            : "not a regular file";
-      } else if ((filelist_sz = llint_to_size_t(fs)) == (size_t) -1) {
+      } else if ((filelist_sz = off_t_to_size_t(fs)) == (size_t) -1) {
         filelist_err = "file too large";
         filelist_sz = 0;
       } else {
@@ -1905,10 +1905,7 @@ int httpmirror(char *url1, httrackp * opt) {
           }
 
           // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!          
-          // An empty body must not overwrite the file when the transfer failed
+          if (r.adr != NULL || r.size == 0) {
-          // (statuscode <= 0, e.g. an -M hard-stop): it would truncate a good
-          // copy to 0 (#77 follow-up).
-          if (r.adr != NULL || (r.size == 0 && r.statuscode > 0)) {
             file_notify(opt, urladr(), urlfil(), savename(), 1, 1, r.notmodified);
             if (filesave(opt, r.adr, (int) r.size, savename(), urladr(), urlfil()) !=
                 0) {
@@ -1929,6 +1926,7 @@ int httpmirror(char *url1, httrackp * opt) {
                */
             }
           }
+
         }
 
         /* Parsing of other media types (java, ram..) */
@@ -2089,9 +2087,10 @@ int httpmirror(char *url1, httrackp * opt) {
               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
                "hts-cache/old.lst"), "rb");
       if (old_lst) {
-        const size_t sz = llint_to_size_t(
+        const size_t sz =
-            fsize(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+          off_t_to_size_t(fsize(fconcat
-                          StringBuff(opt->path_log), "hts-cache/new.lst")));
+                (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                 "hts-cache/new.lst")));
         new_lst =
           fopen(fconcat
                 (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
@@ -3874,6 +3873,7 @@ void voidf(void) {
   a = "|                      HTTrack Website Copier   |" CRLF;
   a = "|Code:         Windows Interface Xavier Roche   |" CRLF;
   a = "|                    HTS/HTTrack Xavier Roche   |" CRLF;
+  a = "|                .class Parser Yann Philippot   |" CRLF;
   a = "|                                               |" CRLF;
   a = "|Tested on:                 Windows95,98,NT,2K  |" CRLF;
   a = "|                           Linux PC            |" CRLF;

src/htscoremain.c

@@ -1452,7 +1452,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
                   HTS_PANIC_PRINTF
                     ("Option %w needs to be followed by a blank space, and a module name");
-                  printf("Example: -%%w httrack-plugin\n");
+                  printf("Example: -%%w htsswf\n");
                   htsmain_free();
                   return -1;
                 } else {
@@ -1509,7 +1509,7 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                   htsmain_free();
                   return -1;
                 } else {
-                  LLint fz;
+                  off_t fz;
 
                   na++;
                   fz = fsize(argv[na]);
@@ -2253,12 +2253,21 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
               htsmain_free();
               return -1;
             } else {
-              char BIGSTK pname[HTS_URLMAXSIZE * 2];
+              char *a;
 
               na++;
               opt->proxy.active = 1;
-              hts_parse_proxy(argv[na], pname, sizeof(pname), &opt->proxy.port);
+              // Rechercher MAIS en partant de la fin à cause de user:pass@proxy:port
-              StringCopy(opt->proxy.name, pname);
+              a = argv[na] + strlen(argv[na]) - 1;
+              while((a > argv[na]) && (*a != ':') && (*a != '@'))
+                a--;
+              if (*a == ':') {  // un port est présent, <proxy>:port
+                sscanf(a + 1, "%d", &opt->proxy.port);
+                StringCopyN(opt->proxy.name, argv[na], (int) (a - argv[na]));
+              } else {          // <proxy>
+                opt->proxy.port = 8080;
+                StringCopy(opt->proxy.name, argv[na]);
+              }
             }
             break;
           case 'F':            // user-agent field
@@ -2584,11 +2593,21 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 hts_get_version_info(opt), t, url);
         fprintf(opt->log, "(");
         for(i = 0; i < argc; i++) {
-          const char *arg = argv[i]; // already UTF-8 on every platform
+#ifdef _WIN32
+          char *carg =
+            hts_convertStringSystemToUTF8(argv[i], (int) strlen(argv[i]));
+          char *arg = carg != NULL ? carg : argv[i];
+#else
+          const char *arg = argv[i];
+#endif
           if (strchr(arg, ' ') == NULL || strchr(arg, '\"') != NULL)
             fprintf(opt->log, "%s ", arg);
           else                  // entre "" (si espace(s) et pas déja de ")
             fprintf(opt->log, "\"%s\" ", arg);
+#ifdef _WIN32
+          if (carg != NULL)
+            free(carg);
+#endif
         }
         fprintf(opt->log, ")" LF);
         fprintf(opt->log, LF);

src/htsdefines.h

@@ -70,7 +70,7 @@ typedef struct t_hts_callbackarg t_hts_callbackarg;
 #endif
 
 /* Marks a symbol an external wrapper module exports back to the engine.
-   Must override -fvisibility=hidden on ELF, or dlopen()ed plugins
+   Must override -fvisibility=hidden on ELF, or dlopen()ed plugins (htsjava)
    hide their own hts_plug()/hts_unplug() entry points. */
 #ifndef EXTERNAL_FUNCTION
 #ifdef _WIN32

src/htsdns_selftest.c

@@ -133,10 +133,9 @@ static struct addrinfo *mock_mkai(const mock_addr *a) {
   return ai;
 }
 
-static int HTS_RESOLVER_CALL mock_getaddrinfo(const char *node,
+static int mock_getaddrinfo(const char *node, const char *service,
-                                              const char *service,
+                            const struct addrinfo *hints,
-                                              const struct addrinfo *hints,
+                            struct addrinfo **res) {
-                                              struct addrinfo **res) {
   mock_host *const h = mock_find(node);
   const int want = (hints != NULL) ? hints->ai_family : PF_UNSPEC;
   struct addrinfo *head = NULL, *tail = NULL;
@@ -165,7 +164,7 @@ static int HTS_RESOLVER_CALL mock_getaddrinfo(const char *node,
   return 0;
 }
 
-static void HTS_RESOLVER_CALL mock_freeaddrinfo(struct addrinfo *res) {
+static void mock_freeaddrinfo(struct addrinfo *res) {
   while (res != NULL) {
     struct addrinfo *const next = res->ai_next;
 
@@ -298,26 +297,6 @@ int dns_selftests(httrackp *opt) {
     IPV6_resolver = 0;
   }
 
-  /* "host:port" resolves as the bare host: the cache/connect path strips
-     ":port" before both the backend and the cache key (#181). */
-  mock_reset_calls();
-  {
-    SOCaddr a;
-    char ip[64];
-    const char *err = NULL;
-
-    /* cache miss: the backend is hit with the stripped host, not "host:port" */
-    CHECK(hts_dns_resolve2(opt, "v6only.test:8080", &a, &err) != NULL);
-    CHECK(mock_find("v6only.test")->calls == 1);
-    /* the bare host shares that one cache entry (stripped key) */
-    CHECK(hts_dns_resolve2(opt, "v6only.test", &a, &err) != NULL);
-    CHECK(mock_find("v6only.test")->calls == 1);
-    /* a port variant of an already-cached host also hits, right address */
-    CHECK(hts_dns_resolve2(opt, "v4only.test:1234", &a, &err) != NULL);
-    SOCaddr_inetntoa(ip, sizeof(ip), a);
-    CHECK(strcmp(ip, "1.2.3.4") == 0);
-  }
-
   /* newhttp_addr() must connect to the addr_index-th address, not always the
      first: this is what back_connect_next relies on to reach the fallback. */
   {

src/htsfilters.c

@@ -121,80 +121,54 @@ int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
   return use1 ? jok1 : jok2;
 }
 
-/* Real filters/URLs fit HTS_URLMAXSIZE*2; past it a hostile pattern recurses
-   O(len) deep or runs O(n^2*stars). Cap length, recursion depth and steps
-   (work): the length cap alone still allows ~2000 frames, ~900KB of stack,
-   which overflows the 1MB a Windows thread gets (#574). */
-#define STRJOKER_MAXLEN (HTS_URLMAXSIZE * 2)
-#define STRJOKER_MAXDEPTH 256u
-#define STRJOKER_MAXSTEPS 2000000u
-
 /* Failure memo for the recursive matcher: one bit per (chaine, joker) offset
    pair keeps star-heavy patterns polynomial instead of exponential (#501). */
 typedef struct strjoker_memo {
   const char *chaine0, *joker0; /* offsets are relative to these bases */
   size_t stride;                /* strlen(joker0) + 1 */
   unsigned char *failed;        /* failed-pair bitmap; NULL: no memo */
-  size_t *nsteps; /* shared work counter; NULL: unbounded (oracle) */
-  size_t maxdepth; /* deepest recursion reached */
-  hts_boolean cut; /* a branch hit the depth cap: its failures are not final */
 } strjoker_memo;
 
-static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
+static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
-                                 const char *joker, LLint *size, int *size_flag,
+                                 const char *joker, LLint *size,
-                                 size_t depth);
+                                 int *size_flag);
 
 /* A pair that failed once fails forever (*size is only written on the success
    path), so record NULL results and cut the re-exploration. */
-static const char *strjoker_rec(strjoker_memo *memo, const char *chaine,
+static const char *strjoker_rec(const strjoker_memo *memo, const char *chaine,
-                                const char *joker, LLint *size, int *size_flag,
+                                const char *joker, LLint *size,
-                                size_t depth) {
+                                int *size_flag) {
   size_t bit = 0;
   const char *adr;
 
-  if (depth > memo->maxdepth)
-    memo->maxdepth = depth;
-  /* Charge the budget before the depth cap: cut disables the memo, so uncounted
-     deep calls would let the sub-cap search explode (OSS-Fuzz 535114376). */
-  if (memo->nsteps != NULL && ++*memo->nsteps > STRJOKER_MAXSTEPS)
-    return NULL; /* work budget spent: fail the match safely */
-  if (depth >= STRJOKER_MAXDEPTH) {
-    memo->cut = HTS_TRUE;
-    return NULL; /* nesting beyond any real filter: fail the branch safely */
-  }
   if (memo->failed) {
     bit = (size_t) (chaine - memo->chaine0) * memo->stride +
           (size_t) (joker - memo->joker0);
     if (memo->failed[bit >> 3] & (unsigned char) (1u << (bit & 7)))
       return NULL;
   }
-  adr = strjoker_impl(memo, chaine, joker, size, size_flag, depth + 1);
+  adr = strjoker_impl(memo, chaine, joker, size, size_flag);
-  /* a cut branch may fail here yet match when reached at a shallower depth */
+  if (adr == NULL && memo->failed)
-  if (adr == NULL && memo->failed && !memo->cut)
     memo->failed[bit >> 3] |= (unsigned char) (1u << (bit & 7));
   return adr;
 }
 
-/* Match chaine against joker with a shared work budget *nsteps (a strjokerfind
+// wildcard comparator: match chaine against joker (pattern), case-insensitive
-   sweep passes one counter, bounding the whole scan). */
+// returns the address of the first matched letter past any leading joker
-static const char *strjoker_bounded(const char *chaine, const char *joker,
+// (ie. *[..]toto.. returns the address of toto within chaine), NULL on mismatch
-                                    LLint *size, int *size_flag, size_t *nsteps,
+HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
-                                    size_t *maxdepth) {
+                                LLint *size, int *size_flag) {
-  strjoker_memo memo = {chaine, joker, 0, NULL, nsteps, 0, HTS_FALSE};
+  strjoker_memo memo = {chaine, joker, 0, NULL};
   unsigned char stackbits[2048];
   hts_boolean onheap = HTS_FALSE;
   const char *adr;
 
-  if (maxdepth != NULL)
-    *maxdepth = 0;
   if (chaine != NULL && joker != NULL) {
-    const size_t l1 = strlen(chaine), l2 = strlen(joker);
+    const size_t n1 = strlen(chaine) + 1;
 
-    if (l1 > STRJOKER_MAXLEN || l2 > STRJOKER_MAXLEN)
+    memo.stride = strlen(joker) + 1;
-      return NULL; /* beyond any real filter/URL: bound depth+work */
+    if (n1 <= (SIZE_MAX - 7) / memo.stride) { // overflow-safe bitmap size
-    memo.stride = l2 + 1;
+      const size_t bytes = (n1 * memo.stride + 7) / 8;
-    if (l1 + 1 <= (SIZE_MAX - 7) / memo.stride) { // overflow-safe bitmap size
-      const size_t bytes = ((l1 + 1) * memo.stride + 7) / 8;
 
       if (bytes <= sizeof(stackbits)) {
         memset(stackbits, 0, bytes);
@@ -205,54 +179,23 @@ static const char *strjoker_bounded(const char *chaine, const char *joker,
       }
     }
   }
-  adr = strjoker_rec(&memo, chaine, joker, size, size_flag, 0);
+  adr = strjoker_rec(&memo, chaine, joker, size, size_flag);
   if (onheap)
     freet(memo.failed);
-  if (maxdepth != NULL)
-    *maxdepth = memo.maxdepth;
   return adr;
 }
 
-// wildcard comparator: match chaine against joker (pattern), case-insensitive
-// returns the address of the first matched letter past any leading joker
-// (ie. *[..]toto.. returns the address of toto within chaine), NULL on mismatch
-HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
-                                LLint *size, int *size_flag) {
-  size_t nsteps = 0;
-
-  return strjoker_bounded(chaine, joker, size, size_flag, &nsteps, NULL);
-}
-
 /* Test-only oracle: the same matcher without the failure memo. */
 const char *strjoker_nomemo(const char *chaine, const char *joker, LLint *size,
                             int *size_flag) {
-  strjoker_memo memo = {chaine, joker, 0, NULL, NULL, 0, HTS_FALSE};
+  const strjoker_memo memo = {chaine, joker, 0, NULL};
 
-  return strjoker_rec(&memo, chaine, joker, size, size_flag, 0);
+  return strjoker_rec(&memo, chaine, joker, size, size_flag);
 }
 
-/* Test-only: strjoker() reporting the work and depth spent and their caps, so a
+static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
-   self-test can prove both bound a hostile pattern. */
+                                 const char *joker, LLint *size,
-const char *strjoker_bounds(const char *chaine, const char *joker,
+                                 int *size_flag) {
-                            size_t *nsteps_out, size_t *maxsteps_out,
-                            size_t *depth_out, size_t *maxdepth_out) {
-  size_t nsteps = 0, depth = 0;
-  const char *r = strjoker_bounded(chaine, joker, NULL, NULL, &nsteps, &depth);
-
-  if (nsteps_out != NULL)
-    *nsteps_out = nsteps;
-  if (maxsteps_out != NULL)
-    *maxsteps_out = STRJOKER_MAXSTEPS;
-  if (depth_out != NULL)
-    *depth_out = depth;
-  if (maxdepth_out != NULL)
-    *maxdepth_out = STRJOKER_MAXDEPTH;
-  return r;
-}
-
-static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
-                                 const char *joker, LLint *size, int *size_flag,
-                                 size_t depth) {
   if (strnotempty(joker) == 0) {        // fin de chaine joker
     if (strnotempty(chaine) == 0)       // fin aussi pour la chaine: ok
       return chaine;
@@ -426,8 +369,7 @@ static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
 
       // tester sans le joker (pas ()+ mais ()*)
       if (!unique) {
-        if ((adr = strjoker_rec(memo, chaine, joker + jmp, size, size_flag,
+        if ((adr = strjoker_rec(memo, chaine, joker + jmp, size, size_flag))) {
-                                depth))) {
           return adr;
         }
       }
@@ -440,7 +382,7 @@ static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
       while(i < (int) max) {
         if (pass[(int) (unsigned char) chaine[i]]) {    // caractère autorisé
           if ((adr = strjoker_rec(memo, chaine + i + 1, joker + jmp, size,
-                                  size_flag, depth))) {
+                                  size_flag))) {
             return adr;
           }
           i++;
@@ -451,7 +393,7 @@ static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
       // tester chaîne vide
       if (i != max + 2)         // avant c'est ok
         if ((adr = strjoker_rec(memo, chaine + max, joker + jmp, size,
-                                size_flag, depth)))
+                                size_flag)))
           return adr;
 
       return NULL;              // perdu
@@ -473,8 +415,7 @@ static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
       // comparaison ok?
       if (ok) {
         // continuer la comparaison.
-        if (strjoker_rec(memo, chaine + jmp, joker + jmp, size, size_flag,
+        if (strjoker_rec(memo, chaine + jmp, joker + jmp, size, size_flag))
-                         depth))
           return chaine;        // retourner 1e lettre
       }
 
@@ -490,18 +431,12 @@ static const char *strjoker_impl(strjoker_memo *memo, const char *chaine,
 // d'un strcpy sur une variable ayant un nom en lettres et copiant une chaine de chiffres
 // ATTENTION!! Eviter les jokers en début, où gare au temps machine!
 const char *strjokerfind(const char *chaine, const char *joker) {
-  size_t nsteps = 0; /* one budget for the whole scan */
   const char *adr;
 
-  if (chaine != NULL && strlen(chaine) > STRJOKER_MAXLEN)
-    return NULL;
   while(*chaine) {
-    if ((adr = strjoker_bounded(chaine, joker, NULL, NULL, &nsteps,
+    if ((adr = strjoker(chaine, joker, NULL, NULL))) {  // ok trouvé
-                                NULL))) { // ok trouvé
       return adr;
     }
-    if (nsteps > STRJOKER_MAXSTEPS) // scan budget spent: no match
-      return NULL;
     chaine++;
   }
   return NULL;

src/htsfilters.h

@@ -52,12 +52,6 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
    oracle for the memoized matcher. */
 const char *strjoker_nomemo(const char *chaine, const char *joker, LLint *size,
                             int *size_flag);
-/* strjoker() reporting the work-budget steps and the recursion depth it spent,
-   with their caps; test-only, lets a self-test assert both bound a hostile
-   pattern (depth bounds the stack: an uncapped one overflows Windows' 1MB). */
-const char *strjoker_bounds(const char *chaine, const char *joker,
-                            size_t *nsteps_out, size_t *maxsteps_out,
-                            size_t *depth_out, size_t *maxdepth_out);
 const char *strjokerfind(const char *chaine, const char *joker);
 #endif
 

src/htsglobal.h

@@ -43,8 +43,8 @@ Please visit our Website: http://www.httrack.com
    configure.ac, decoupled from these). VERSION is the display form, VERSIONID
    the dotted numeric form, AFF_VERSION the short form shown in footers,
    LIB_VERSION the data/cache format generation. */
-#define HTTRACK_VERSION "3.49-12"
+#define HTTRACK_VERSION "3.49-11"
-#define HTTRACK_VERSIONID "3.49.12"
+#define HTTRACK_VERSIONID "3.49.11"
 #define HTTRACK_AFF_VERSION "3.x"
 #define HTTRACK_LIB_VERSION "2.0"
 
@@ -56,10 +56,6 @@ Please visit our Website: http://www.httrack.com
 // Platform detection (sizes, feature macros)
 #include "htsconfig.h"
 
-// Fixed-width integer types + PRI* format macros for the LLint/TStamp typedefs
-#include <stdint.h>
-#include <inttypes.h>
-
 // WIN32 types
 #ifdef _WIN32
 #ifndef SIZEOF_LONG
@@ -115,6 +111,29 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DO_NOT_USE_UID
 #endif
 
+#ifndef HTS_LONGLONG
+#ifdef SIZEOF_LONG_LONG
+#if SIZEOF_LONG_LONG == 8
+#define HTS_LONGLONG 1
+#endif
+#endif
+
+#ifndef HTS_LONGLONG
+#ifdef __sun
+#define HTS_LONGLONG 0
+#endif
+#ifdef __osf__
+#define HTS_LONGLONG 0
+#endif
+#ifdef __linux
+#define HTS_LONGLONG 1
+#endif
+#ifdef _WIN32
+#define HTS_LONGLONG 1
+#endif
+#endif
+#endif
+
 #ifdef DLLIB
 #define HTS_DLOPEN 1
 #else
@@ -140,15 +159,6 @@ Please visit our Website: http://www.httrack.com
 #define HTS_USEZLIB 1
 #endif
 
-// brotli and zstd content codings; off unless the build opted in (configure,
-// or the Visual Studio projects, which link the vcpkg libraries)
-#ifndef HTS_USEBROTLI
-#define HTS_USEBROTLI 0
-#endif
-#ifndef HTS_USEZSTD
-#define HTS_USEZSTD 0
-#endif
-
 #ifndef HTS_INET6
 #define HTS_INET6 0
 #endif
@@ -316,21 +326,70 @@ typedef int hts_tristate;
 #define HTS_DEPRECATED(msg)
 #endif
 
-/* LLint/TStamp: signed exact-width 64-bit; -1 is a sentinel engine-wide. */
+#ifndef HTS_LONGLONG
-typedef int64_t LLint;
+#ifdef HTS_NO_64_BIT
-typedef int64_t TStamp;
+#define HTS_LONGLONG 0
-/* Full printf conversion, '%' included (PRId64 has none): "X: " LLintP. */
+#else
-#define LLintP "%" PRId64
+#define HTS_LONGLONG 1
+#endif
+#endif
 
-/* Integer type for file offsets/sizes passed to the C library; INTsysP is its
+/* Wide integer types, chosen per platform.
-   printf conversion. FIXME: LFS_FLAG is a configure make variable, never a C
+   LLint:  signed 64-bit counter for byte counts and large sizes (falls back to
-   macro, so this test is dead and INTsys stays int on POSIX despite large-file
+           plain int where 64-bit is unavailable).
-   support (the real macro is HTS_LFS). Widening it there is an installed-header
+   TStamp: timestamp/duration in the same width (a double in the no-64-bit
-   type change, so it is left alone here. */
+           fallback).
-#if defined(LFS_FLAG) || defined(_MSC_VER)
+   LLintP: the printf conversion for an LLint. */
+#if HTS_LONGLONG
+#ifdef LLINT_FORMAT
+typedef LLINT_TYPE LLint;
+
+typedef LLINT_TYPE TStamp;
+
+#define LLintP LLINT_FORMAT
+#else
+
+#ifdef _WIN32
+typedef __int64 LLint;
+
+typedef __int64 TStamp;
+
+#define LLintP "%I64d"
+#elif (defined(_LP64) || defined(__x86_64__) || defined(__powerpc64__) ||      \
+       defined(__64BIT__))
+
+typedef long int LLint;
+
+typedef long int TStamp;
+
+#define LLintP "%ld"
+#else
+typedef long long int LLint;
+
+typedef long long int TStamp;
+
+#define LLintP "%lld"
+#endif
+
+#endif /* HTS_LONGLONG */
+
+#else
+typedef int LLint;
+
+#define LLintP "%d"
+typedef double TStamp;
+#endif
+
+/* Integer type for file offsets/sizes passed to the C library. Widens to
+   LLint (with HTS_FSEEKO for fseeko/ftello) under large-file support, plain
+   int otherwise; INTsysP is its printf conversion. */
+#ifdef LFS_FLAG
 typedef LLint INTsys;
 
 #define INTsysP LLintP
+#ifdef __linux
+#define HTS_FSEEKO
+#endif
 #else
 typedef int INTsys;
 

src/htshelp.c

@@ -477,7 +477,7 @@ void help(const char *app, int more) {
     ("  Y   mirror ALL links located in the first level pages (mirror links)");
   infomsg("");
   infomsg("Proxy options:");
-  infomsg("  P  proxy use (-P [socks5://][user:pass@]proxy:port)");
+  infomsg("  P  proxy use (-P proxy:port or -P user:pass@proxy:port)");
   infomsg(" %f *use proxy for ftp (f0 don't use)");
   infomsg(" %b  use this local hostname to make/send requests (-%b hostname)");
   infomsg("");
@@ -546,8 +546,8 @@ void help(const char *app, int more) {
   infomsg(" %Y  explain which filter rule accepts or rejects a URL, then exit");
   infomsg
     ("  u  check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)");
-  infomsg("  j *parse scripts (j0 don't parse, bitmask: |1 parse default, |4 "
+  infomsg
-          "don't parse .js |8 don't be aggressive)");
+    ("  j *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)");
   infomsg
     ("  sN follow robots.txt and meta robots tags (0=never,1=sometimes,* 2=always, 3=always (even strict rules))");
   infomsg
@@ -571,7 +571,8 @@ void help(const char *app, int more) {
     ("     can also be used to force a specific file type: --assume foo.cgi=text/html");
   infomsg
     (" @iN internet protocol (0=both ipv6+ipv4, 4=ipv4 only, 6=ipv6 only)");
-  infomsg(" %w  disable a specific external mime module (-%w httrack-plugin)");
+  infomsg
+    (" %w  disable a specific external mime module (-%w htsswf -%w htsjava)");
   infomsg("");
   infomsg("Browser ID:");
   infomsg

src/htsindex.c

@@ -318,7 +318,7 @@ void index_finish(const char *indexpath, int mode) {
   char catbuff[CATBUFF_SIZE];
   char **tab;
   char *blk;
-  LLint size = fpsize(fp_tmpproject);
+  off_t size = fpsize(fp_tmpproject);
 
   if (size > 0) {
     if (fp_tmpproject) {

src/htsjava.c

@@ -0,0 +1,517 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: Java classes parser                                    */
+/* Author: Yann Philippot                                       */
+/* ------------------------------------------------------------ */
+
+/* Version: Oct/2000 */
+/* Fixed: problems with class structure (10/2000) */
+
+// htsjava.c - Parseur de classes java
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#if ( defined(_WIN32) ||defined(HAVE_SYS_TYPES_H) )
+#include <sys/types.h>
+#endif
+#ifdef HAVE_UNISTD_H
+#include <unistd.h>
+#endif
+
+/* Standard httrack module includes */
+#include "httrack-library.h"
+#include "htsopt.h"
+#include "htsdefines.h"
+
+/* Module structures */
+#include "htsmodules.h"
+
+/* We link to libhttrack, we can use its functions */
+#include "httrack-library.h"
+
+/* This file */
+#include "htsjava.h"
+
+/* calloct/freet wrappers */
+#include "htssafe.h"
+
+static int reverse_endian(void) {
+  int endian = 1;
+
+  return (*((char *) &endian) == 1);
+}
+
+/* big/little endian swap */
+#define hts_swap16(A) ( (((A) & 0xFF)<<8) | (((A) & 0xFF00)>>8) )
+#define hts_swap32(A) ( (( (hts_swap16(A)) & 0xFFFF)<<16) | (( (hts_swap16(A>>16)) & 0xFFFF)) )
+
+/* Static definitions */
+static RESP_STRUCT readtable(htsmoduleStruct * str, FILE * fp, RESP_STRUCT,
+                             int *);
+static unsigned short int readshort(FILE * fp);
+static int tris(httrackp * opt, char *);
+static char *printname(char[1024], char[1024]);
+
+// ** HTS_xx sinon pas pris par VC++
+#define HTS_CLASS  7
+#define HTS_FIELDREF  9
+#define HTS_METHODREF  10
+#define HTS_STRING  8
+#define HTS_INTEGER  3
+#define HTS_FLOAT  4
+#define HTS_LONG  5
+#define HTS_DOUBLE  6
+#define HTS_INTERFACE  11
+#define HTS_NAMEANDTYPE  12
+#define HTS_ASCIZ  1
+#define HTS_UNICODE  2
+
+#define JAVADEBUG 0
+
+static const char *libName = "htsjava";
+
+#ifdef _WIN32
+#define strcasecmp(a,b) stricmp(a,b)
+#define strncasecmp(a,b,n) strnicmp(a,b,n)
+#endif
+
+static int detect_mime(htsmoduleStruct * str) {
+  const char *savename = str->filename;
+
+  if (savename) {
+    int len = (int) strlen(savename);
+
+    if (len > 6 && strcasecmp(savename + len - 6, ".class") == 0) {
+      return 1;
+    }
+  }
+  return 0;
+}
+
+static int hts_detect_java(t_hts_callbackarg * carg, httrackp * opt,
+                           htsmoduleStruct * str) {
+  /* Call parent functions if multiple callbacks are chained. */
+  if (CALLBACKARG_PREV_FUN(carg, detect) != NULL) {
+    if (CALLBACKARG_PREV_FUN(carg, detect)
+        (CALLBACKARG_PREV_CARG(carg), opt, str)) {
+      return 1;                 /* Found before us, let them have the priority */
+    }
+  }
+
+  /* Check MIME */
+  if (detect_mime(str)) {
+    str->wrapper_name = libName;        /* Our ID */
+    return 1;                   /* Known format, we take it */
+  }
+
+  return 0;                     /* Unknown format */
+}
+
+static off_t fsize(const char *s) {
+  STRUCT_STAT st;
+
+  if (STAT(s, &st) == 0 && S_ISREG(st.st_mode)) {
+    return st.st_size;
+  } else {
+    return -1;
+  }
+}
+
+static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
+                          htsmoduleStruct * str) {
+  /* The wrapper_name memebr has changed: not for us anymore */
+  if (str->wrapper_name == NULL || strcmp(str->wrapper_name, libName) != 0) {
+    /* Call parent functions if multiple callbacks are chained. */
+    if (CALLBACKARG_PREV_FUN(carg, parse) != NULL) {
+      return CALLBACKARG_PREV_FUN(carg, parse) (CALLBACKARG_PREV_CARG(carg),
+                                                opt, str);
+    }
+    strcpy(str->err_msg,
+           "unexpected error: bad wrapper_name and no previous wrapper");
+    return 0;                   /* Unexpected error */
+  } else {
+    if (detect_mime(str)) {
+
+      /* (Legacy code) */
+      char catbuff[CATBUFF_SIZE];
+      FILE *fpout;
+      JAVA_HEADER header;
+      RESP_STRUCT *tab;
+      const char *file = str->filename;
+
+      str->relativeToHtmlLink = 1;
+
+#if JAVADEBUG
+      printf("fopen\n");
+#endif
+      if ((fpout = FOPEN(fconv(catbuff, sizeof(catbuff), file), "r+b")) ==
+          NULL) {
+        sprintf(str->err_msg, "Unable to open file %s", file);
+        return 0;               // une erreur..
+      }
+#if JAVADEBUG
+      printf("fread\n");
+#endif
+      if (fread(&header, 1, 10, fpout) != 10) { // pas complet..
+        fclose(fpout);
+        sprintf(str->err_msg, "File header too small (file len = " LLintP ")",
+                (LLint) fsize(file));
+        return 0;
+      }
+#if JAVADEBUG
+      printf("header\n");
+#endif
+      // tester en tête
+      if (reverse_endian()) {
+        header.magic = hts_swap32(header.magic);
+        header.count = hts_swap16(header.count);
+      }
+      if (header.magic != 0xCAFEBABE) {
+        sprintf(str->err_msg, "non java file");
+        if (fpout) {
+          fclose(fpout);
+          fpout = NULL;
+        }
+        return 0;
+      }
+
+      /* A constant-pool entry is >= 1 byte on disk; reject a count exceeding
+         the file size (hostile .class ~68 MB alloc DoS). */
+      if (!hts_count_fits(header.count, (LLint) fsize(file))) {
+        fclose(fpout);
+        sprintf(str->err_msg,
+                "Invalid constant pool count %u (file len " LLintP ")",
+                (unsigned) header.count, (LLint) fsize(file));
+        return 0;
+      }
+      tab = (RESP_STRUCT *) calloct(header.count, sizeof(RESP_STRUCT));
+      if (!tab) {
+        sprintf(str->err_msg, "Unable to alloc %d bytes",
+                (int) sizeof(RESP_STRUCT));
+        if (fpout) {
+          fclose(fpout);
+          fpout = NULL;
+        }
+        return 0;               // erreur..
+      }
+#if JAVADEBUG
+      printf("calchead\n");
+#endif
+      {
+        int i;
+
+        for(i = 1; i < header.count; i++) {
+          int err = 0;          // ++    
+
+          tab[i] = readtable(str, fpout, tab[i], &err);
+          if (!err) {
+            if ((tab[i].type == HTS_LONG) || (tab[i].type == HTS_DOUBLE))
+              i++;              //2 element si double ou float
+          } else {              // ++ une erreur est survenue!
+            if (strnotempty(str->err_msg) == 0)
+              strcpy(str->err_msg, "Internal readtable error");
+            freet(tab);
+            if (fpout) {
+              fclose(fpout);
+              fpout = NULL;
+            }
+            return 0;
+          }
+        }
+
+      }
+
+#if JAVADEBUG
+      printf("addfiles\n");
+#endif
+      {
+        unsigned int Class;
+        unsigned int SClass;
+        int i;
+
+        Class = readshort(fpout);
+        SClass = readshort(fpout);
+
+        for(i = 1; i < header.count; i++) {
+
+          if (tab[i].type == HTS_CLASS) {
+
+            if ((tab[i].index1 < header.count) && (tab[i].index1 >= 0)) {
+
+              if ((tab[i].index1 != SClass) && (tab[i].index1 != Class)
+                  && (tab[tab[i].index1].name[0] != '[')) {
+
+                if (!strstr(tab[tab[i].index1].name, "java/")) {
+                  char BIGSTK tempo[1024];
+
+                  tempo[0] = '\0';
+
+                  snprintf(tempo, sizeof(tempo), "%s.class", tab[tab[i].index1].name);
+#if JAVADEBUG
+                  printf("add %s\n", tempo);
+#endif
+                  if (tab[tab[i].index1].file_position >= 0)
+                    str->addLink(str, tempo);   /* tab[tab[i].index1].file_position */
+                }
+
+              }
+            } else {
+              i = header.count; // exit 
+            }
+          }
+
+        }
+      }
+
+#if JAVADEBUG
+      printf("end\n");
+#endif
+      freet(tab);
+      if (fpout) {
+        fclose(fpout);
+        fpout = NULL;
+      }
+      return 1;
+
+    } else {
+      strcpy(str->err_msg, "bad MIME type");
+    }
+  }
+  return 0;                     /* Error */
+}
+
+/*
+module entry point 
+*/
+EXTERNAL_FUNCTION int hts_plug(httrackp * opt, const char *argv);
+EXTERNAL_FUNCTION int hts_plug(httrackp * opt, const char *argv) {
+  /* Plug callback functions */
+  CHAIN_FUNCTION(opt, detect, hts_detect_java, NULL);
+  CHAIN_FUNCTION(opt, parse, hts_parse_java, NULL);
+
+  return 1;                     /* success */
+}
+
+// error: !=0 si erreur fatale
+static RESP_STRUCT readtable(htsmoduleStruct * str, FILE * fp,
+                             RESP_STRUCT trans, int *error) {
+  char rname[1024];
+  unsigned short int length;
+  int j;
+
+  *error = 0;                   // pas d'erreur
+  trans.file_position = -1;
+  trans.type = (int) (unsigned char) fgetc(fp);
+  switch (trans.type) {
+  case HTS_CLASS:
+    strcpy(trans.name, "Class");
+    trans.index1 = readshort(fp);
+    break;
+
+  case HTS_FIELDREF:
+    strcpy(trans.name, "Field Reference");
+    trans.index1 = readshort(fp);
+    readshort(fp);
+    break;
+
+  case HTS_METHODREF:
+    strcpy(trans.name, "Method Reference");
+    trans.index1 = readshort(fp);
+    readshort(fp);
+    break;
+
+  case HTS_INTERFACE:
+    strcpy(trans.name, "Interface Method Reference");
+    trans.index1 = readshort(fp);
+    readshort(fp);
+    break;
+  case HTS_NAMEANDTYPE:
+    strcpy(trans.name, "Name and Type");
+    trans.index1 = readshort(fp);
+    readshort(fp);
+    break;
+
+  case HTS_STRING:             // CONSTANT_String
+    strcpy(trans.name, "String");
+    trans.index1 = readshort(fp);
+    break;
+
+  case HTS_INTEGER:
+    strcpy(trans.name, "Integer");
+    for(j = 0; j < 4; j++)
+      fgetc(fp);
+    break;
+
+  case HTS_FLOAT:
+    strcpy(trans.name, "Float");
+    for(j = 0; j < 4; j++)
+      fgetc(fp);
+    break;
+
+  case HTS_LONG:
+    strcpy(trans.name, "Long");
+    for(j = 0; j < 8; j++)
+      fgetc(fp);
+    break;
+  case HTS_DOUBLE:
+    strcpy(trans.name, "Double");
+    for(j = 0; j < 8; j++)
+      fgetc(fp);
+    break;
+
+  case HTS_ASCIZ:
+  case HTS_UNICODE:
+
+    if (trans.type == HTS_ASCIZ)
+      strcpy(trans.name, "HTS_ASCIZ");
+    else
+      strcpy(trans.name, "HTS_UNICODE");
+
+    {
+      char BIGSTK buffer[1024];
+      char *p;
+
+      p = &buffer[0];
+
+      trans.file_position = ftell(fp);
+      length = readshort(fp);
+      if (length < HTS_URLMAXSIZE) {
+        while(length > 0) {
+          *p++ = fgetc(fp);
+
+          length--;
+        }
+        *p = '\0';
+
+        if (tris(str->opt, buffer) == 1)
+          str->addLink(str, buffer);    /* trans.file_position */
+        else if (tris(str->opt, buffer) == 2)
+          str->addLink(str, printname(rname, buffer));
+
+        strcpy(trans.name, buffer);
+      } else { // gros pb
+        while((length > 0) && (!feof(fp))) {
+          fgetc(fp);
+          length--;
+        }
+        if (!feof(fp)) {
+          trans.type = -1;
+        } else {
+          sprintf(str->err_msg, "Internal structure error (ASCII)");
+          *error = 1;
+        }
+        return (trans);
+      }
+    }
+    break;
+  default:
+    // on arrête tout 
+    sprintf(str->err_msg, "Internal structure unknown (type %d)", trans.type);
+    *error = 1;
+    return (trans);
+    break;
+  }
+  return (trans);
+}
+
+static unsigned short int readshort(FILE * fp) {
+  unsigned short int valint;
+
+  if (fread(&valint, sizeof(valint), 1, fp) == 1) {
+    if (reverse_endian())
+      return hts_swap16(valint);
+    else
+      return valint;
+  } else {
+    return 0;
+  }
+
+}
+
+static int tris(httrackp * opt, char *buffer) {
+  char catbuff[CATBUFF_SIZE];
+
+  //
+  // Java
+  if ((buffer[0] == '[') && buffer[1] == 'L' && (!strstr(buffer, "java/")))
+    return 2;
+  if (strstr(buffer, ".gif") || strstr(buffer, ".jpg")
+      || strstr(buffer, ".jpeg") || strstr(buffer, ".au"))
+    return 1;
+  // Ajouts R.X: test type
+  // Autres fichiers
+  {
+    char type[256];
+
+    if (get_httptype_sized(opt, type, sizeof(type), buffer,
+                           0)) // recognized type
+      return 1;
+    // ajout RX 05/2001
+    else if (is_dyntype(get_ext(catbuff, sizeof(catbuff), buffer)))      // asp,cgi...
+      return 1;
+  }
+  return 0;
+}
+
+static char *printname(char rname[1024], char name[1024]) {
+  char *p;
+  char *p1;
+  size_t j;
+
+  rname[0] = '\0';
+  //
+
+  p = &name[0];
+
+  if (*p != '[') {
+    return rname;  // ""
+  }
+  p += 2;
+  p1 = rname;
+  for(j = 0; name[j] != '\0'; j++, p++) {
+    if (*p == '/')
+      *p1 = '.';
+    if (*p == ';') {
+      *p1 = '\0';
+      strcat(rname, ".class");
+      return rname;
+    } else
+      *p1 = *p;
+    p1++;
+  }
+  p1 -= 3;
+  *p1 = '\0';
+  return rname;
+
+}

src/htsjava.h

@@ -0,0 +1,70 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: Java classes parser .h                                 */
+/* Author: Yann Philippot                                       */
+/* ------------------------------------------------------------ */
+
+#ifndef HTSJAVA_DEFH
+#define HTSJAVA_DEFH
+
+#include <stdint.h>
+
+#ifndef HTS_DEF_FWSTRUCT_JAVA_HEADER
+#define HTS_DEF_FWSTRUCT_JAVA_HEADER
+typedef struct JAVA_HEADER JAVA_HEADER;
+#endif
+/* 10-byte on-disk .class header image, fread() directly: fields need exact
+   widths (LP64's 8-byte 'unsigned long' magic never matched 0xCAFEBABE). */
+struct JAVA_HEADER {
+  uint32_t magic;
+  uint16_t minor;
+  uint16_t major;
+  uint16_t count;
+};
+
+#ifndef HTS_DEF_FWSTRUCT_RESP_STRUCT
+#define HTS_DEF_FWSTRUCT_RESP_STRUCT
+typedef struct RESP_STRUCT RESP_STRUCT;
+#endif
+struct RESP_STRUCT {
+  int file_position;
+  //
+  unsigned int index1;
+  unsigned int type;
+  char name[1024];
+};
+
+/* Library internal definictions */
+#ifdef HTS_INTERNAL_BYTECODE
+
+EXTERNAL_FUNCTION int hts_plug_java(httrackp * opt, const char *argv);
+
+#endif
+
+#endif

src/htsjava.vcproj

@@ -0,0 +1,373 @@
+<?xml version="1.0" encoding="Windows-1252"?>
+<VisualStudioProject
+	ProjectType="Visual C++"
+	Version="9,00"
+	Name="htsjava"
+	ProjectGUID="{2F353408-2C6C-4D31-9AC0-08BDC064DF64}"
+	RootNamespace="htsjava"
+	Keyword="Win32Proj"
+	TargetFrameworkVersion="131072"
+	>
+	<Platforms>
+		<Platform
+			Name="Win32"
+		/>
+		<Platform
+			Name="x64"
+		/>
+	</Platforms>
+	<ToolFiles>
+	</ToolFiles>
+	<Configurations>
+		<Configuration
+			Name="Debug|Win32"
+			OutputDirectory="C:\temp\htsjava\Debug"
+			IntermediateDirectory="C:\temp\htsjava\Debug"
+			ConfigurationType="2"
+			InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
+			CharacterSet="2"
+			>
+			<Tool
+				Name="VCPreBuildEventTool"
+			/>
+			<Tool
+				Name="VCCustomBuildTool"
+			/>
+			<Tool
+				Name="VCXMLDataGeneratorTool"
+			/>
+			<Tool
+				Name="VCWebServiceProxyGeneratorTool"
+			/>
+			<Tool
+				Name="VCMIDLTool"
+			/>
+			<Tool
+				Name="VCCLCompilerTool"
+				Optimization="0"
+				AdditionalIncludeDirectories="C:\Dev\openssl-1.0.1j\include"
+				PreprocessorDefinitions="_CRT_SECURE_NO_WARNINGS;_CRT_NONSTDC_NO_DEPRECATE"
+				MinimalRebuild="true"
+				BasicRuntimeChecks="3"
+				RuntimeLibrary="1"
+				UsePrecompiledHeader="0"
+				WarningLevel="3"
+				Detect64BitPortabilityProblems="true"
+				DebugInformationFormat="4"
+			/>
+			<Tool
+				Name="VCManagedResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCPreLinkEventTool"
+			/>
+			<Tool
+				Name="VCLinkerTool"
+				OutputFile="C:\temp\httrack\htsjava.dll"
+				LinkIncremental="2"
+				GenerateDebugInformation="true"
+				ProgramDatabaseFile="$(OutDir)/htsjava.pdb"
+				SubSystem="2"
+				RandomizedBaseAddress="1"
+				DataExecutionPrevention="0"
+				ImportLibrary="$(OutDir)/htsjava.lib"
+				TargetMachine="1"
+			/>
+			<Tool
+				Name="VCALinkTool"
+			/>
+			<Tool
+				Name="VCManifestTool"
+			/>
+			<Tool
+				Name="VCXDCMakeTool"
+			/>
+			<Tool
+				Name="VCBscMakeTool"
+			/>
+			<Tool
+				Name="VCFxCopTool"
+			/>
+			<Tool
+				Name="VCAppVerifierTool"
+			/>
+			<Tool
+				Name="VCPostBuildEventTool"
+			/>
+		</Configuration>
+		<Configuration
+			Name="Debug|x64"
+			OutputDirectory="$(SolutionDir)$(PlatformName)\$(ConfigurationName)"
+			IntermediateDirectory="$(PlatformName)\$(ConfigurationName)"
+			ConfigurationType="2"
+			InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
+			CharacterSet="2"
+			>
+			<Tool
+				Name="VCPreBuildEventTool"
+			/>
+			<Tool
+				Name="VCCustomBuildTool"
+			/>
+			<Tool
+				Name="VCXMLDataGeneratorTool"
+			/>
+			<Tool
+				Name="VCWebServiceProxyGeneratorTool"
+			/>
+			<Tool
+				Name="VCMIDLTool"
+				TargetEnvironment="3"
+			/>
+			<Tool
+				Name="VCCLCompilerTool"
+				Optimization="0"
+				AdditionalIncludeDirectories="C:\Dev\openssl-1.0.1j\include"
+				PreprocessorDefinitions="_CRT_SECURE_NO_WARNINGS;_CRT_NONSTDC_NO_DEPRECATE"
+				MinimalRebuild="true"
+				BasicRuntimeChecks="3"
+				RuntimeLibrary="1"
+				UsePrecompiledHeader="0"
+				WarningLevel="3"
+				Detect64BitPortabilityProblems="true"
+				DebugInformationFormat="3"
+			/>
+			<Tool
+				Name="VCManagedResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCPreLinkEventTool"
+			/>
+			<Tool
+				Name="VCLinkerTool"
+				OutputFile="C:\temp\httrack64\htsjava.dll"
+				LinkIncremental="2"
+				GenerateDebugInformation="true"
+				ProgramDatabaseFile="$(OutDir)/htsjava.pdb"
+				SubSystem="2"
+				RandomizedBaseAddress="1"
+				DataExecutionPrevention="0"
+				ImportLibrary="$(OutDir)/htsjava.lib"
+				TargetMachine="17"
+			/>
+			<Tool
+				Name="VCALinkTool"
+			/>
+			<Tool
+				Name="VCManifestTool"
+			/>
+			<Tool
+				Name="VCXDCMakeTool"
+			/>
+			<Tool
+				Name="VCBscMakeTool"
+			/>
+			<Tool
+				Name="VCFxCopTool"
+			/>
+			<Tool
+				Name="VCAppVerifierTool"
+			/>
+			<Tool
+				Name="VCPostBuildEventTool"
+			/>
+		</Configuration>
+		<Configuration
+			Name="Release|Win32"
+			OutputDirectory="C:\temp\htsjava\Release"
+			IntermediateDirectory="C:\temp\htsjava\Release"
+			ConfigurationType="2"
+			InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
+			CharacterSet="2"
+			>
+			<Tool
+				Name="VCPreBuildEventTool"
+			/>
+			<Tool
+				Name="VCCustomBuildTool"
+			/>
+			<Tool
+				Name="VCXMLDataGeneratorTool"
+			/>
+			<Tool
+				Name="VCWebServiceProxyGeneratorTool"
+			/>
+			<Tool
+				Name="VCMIDLTool"
+			/>
+			<Tool
+				Name="VCCLCompilerTool"
+				AdditionalIncludeDirectories="C:\Dev\openssl-1.0.1j\include"
+				PreprocessorDefinitions="_CRT_SECURE_NO_WARNINGS;_CRT_NONSTDC_NO_DEPRECATE"
+				RuntimeLibrary="0"
+				UsePrecompiledHeader="0"
+				WarningLevel="3"
+				Detect64BitPortabilityProblems="true"
+				DebugInformationFormat="0"
+			/>
+			<Tool
+				Name="VCManagedResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCPreLinkEventTool"
+			/>
+			<Tool
+				Name="VCLinkerTool"
+				OutputFile="O:\HTTrack\httrack\htsjava.dll"
+				LinkIncremental="1"
+				GenerateDebugInformation="true"
+				ProgramDatabaseFile="O:\HTTrack\httrack\htsjava.pdb"
+				SubSystem="2"
+				OptimizeReferences="2"
+				EnableCOMDATFolding="2"
+				RandomizedBaseAddress="1"
+				DataExecutionPrevention="0"
+				ImportLibrary="$(OutDir)/htsjava.lib"
+				TargetMachine="1"
+			/>
+			<Tool
+				Name="VCALinkTool"
+			/>
+			<Tool
+				Name="VCManifestTool"
+			/>
+			<Tool
+				Name="VCXDCMakeTool"
+			/>
+			<Tool
+				Name="VCBscMakeTool"
+			/>
+			<Tool
+				Name="VCFxCopTool"
+			/>
+			<Tool
+				Name="VCAppVerifierTool"
+			/>
+			<Tool
+				Name="VCPostBuildEventTool"
+				CommandLine="&quot;C:\Program Files\Microsoft SDKs\Windows\v6.0A\Bin\signtool.exe&quot; sign /f &quot;Z:\Mes Documents\certificats\httrack-com\httrack-signing-certificate.pfx&quot; /t http://timestamp.verisign.com/scripts/timstamp.dll $(TargetPath)&#x0D;&#x0A;"
+			/>
+		</Configuration>
+		<Configuration
+			Name="Release|x64"
+			OutputDirectory="$(SolutionDir)$(PlatformName)\$(ConfigurationName)"
+			IntermediateDirectory="$(PlatformName)\$(ConfigurationName)"
+			ConfigurationType="2"
+			InheritedPropertySheets="$(VCInstallDir)VCProjectDefaults\UpgradeFromVC71.vsprops"
+			CharacterSet="2"
+			>
+			<Tool
+				Name="VCPreBuildEventTool"
+			/>
+			<Tool
+				Name="VCCustomBuildTool"
+			/>
+			<Tool
+				Name="VCXMLDataGeneratorTool"
+			/>
+			<Tool
+				Name="VCWebServiceProxyGeneratorTool"
+			/>
+			<Tool
+				Name="VCMIDLTool"
+				TargetEnvironment="3"
+			/>
+			<Tool
+				Name="VCCLCompilerTool"
+				AdditionalIncludeDirectories="C:\Dev\openssl-1.0.1j\include"
+				PreprocessorDefinitions="_CRT_SECURE_NO_WARNINGS;_CRT_NONSTDC_NO_DEPRECATE"
+				RuntimeLibrary="0"
+				UsePrecompiledHeader="0"
+				WarningLevel="3"
+				Detect64BitPortabilityProblems="true"
+				DebugInformationFormat="0"
+			/>
+			<Tool
+				Name="VCManagedResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCResourceCompilerTool"
+			/>
+			<Tool
+				Name="VCPreLinkEventTool"
+			/>
+			<Tool
+				Name="VCLinkerTool"
+				OutputFile="O:\HTTrack\httrack\x64\htsjava.dll"
+				LinkIncremental="1"
+				GenerateDebugInformation="true"
+				ProgramDatabaseFile="O:\HTTrack\httrack\x64\htsjava.pdb"
+				SubSystem="2"
+				OptimizeReferences="2"
+				EnableCOMDATFolding="2"
+				RandomizedBaseAddress="1"
+				DataExecutionPrevention="0"
+				ImportLibrary="$(OutDir)/htsjava.lib"
+				TargetMachine="17"
+			/>
+			<Tool
+				Name="VCALinkTool"
+			/>
+			<Tool
+				Name="VCManifestTool"
+			/>
+			<Tool
+				Name="VCXDCMakeTool"
+			/>
+			<Tool
+				Name="VCBscMakeTool"
+			/>
+			<Tool
+				Name="VCFxCopTool"
+			/>
+			<Tool
+				Name="VCAppVerifierTool"
+			/>
+			<Tool
+				Name="VCPostBuildEventTool"
+				CommandLine="&quot;C:\Program Files\Microsoft SDKs\Windows\v6.0A\Bin\signtool.exe&quot; sign /f &quot;Z:\Mes Documents\certificats\httrack-com\httrack-signing-certificate.pfx&quot; /t http://timestamp.verisign.com/scripts/timstamp.dll $(TargetPath)&#x0D;&#x0A;"
+			/>
+		</Configuration>
+	</Configurations>
+	<References>
+	</References>
+	<Files>
+		<Filter
+			Name="Source Files"
+			Filter="cpp;c;cxx;def;odl;idl;hpj;bat;asm;asmx"
+			UniqueIdentifier="{4FC737F1-C7A5-4376-A066-2A32D752A2FF}"
+			>
+			<File
+				RelativePath="htsjava.c"
+				>
+			</File>
+		</Filter>
+		<Filter
+			Name="Header Files"
+			Filter="h;hpp;hxx;hm;inl;inc;xsd"
+			UniqueIdentifier="{93995380-89BD-4b04-88EB-625FBE52EBFB}"
+			>
+			<File
+				RelativePath="htsjava.h"
+				>
+			</File>
+		</Filter>
+		<Filter
+			Name="Resource Files"
+			Filter="rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx"
+			UniqueIdentifier="{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}"
+			>
+		</Filter>
+	</Files>
+	<Globals>
+	</Globals>
+</VisualStudioProject>

src/htslib.c

@@ -48,7 +48,6 @@ Please visit our Website: http://www.httrack.com
 #include "htsmodules.h"
 #include "htscharset.h"
 #include "htsencoding.h"
-#include "htscodec.h"
 
 #ifdef _WIN32
 #include <direct.h>
@@ -649,6 +648,165 @@ T_SOC http_fopen(httrackp * opt, const char *adr, const char *fil, htsblk * reto
   return http_xfopen(opt, 0, 1, 1, NULL, adr, fil, retour);
 }
 
+// Read a CRLF line from a non-blocking socket (waits up to timeout per recv).
+// Returns the line length (0 = empty), or -1 on timeout/EOF/error.
+static int proxy_getline(T_SOC soc, char *s, int max, int timeout) {
+  int j = 0;
+
+  for (;;) {
+    unsigned char ch;
+    int n;
+
+    if (!check_readinput_t(soc, timeout))
+      return -1; // timed out waiting for data
+    n = (int) recv(soc, &ch, 1, 0);
+    if (n == 1) {
+      if (ch == 13) // CR
+        continue;
+      if (ch == 10) // LF: end of line
+        break;
+      if (j >= max - 1)
+        return -1; // line too long: bound the read against a hostile proxy
+      s[j++] = (char) ch;
+    } else if (n == 0) {
+      return -1; // connection closed
+    } else {
+#ifdef _WIN32
+      if (WSAGetLastError() == WSAEWOULDBLOCK)
+        continue;
+#else
+      if (errno == EINTR || errno == EAGAIN || errno == EWOULDBLOCK)
+        continue;
+#endif
+      return -1;
+    }
+  }
+  s[j] = '\0';
+  return j;
+}
+
+int http_proxy_tunnel(httrackp *opt, htsblk *retour, const char *adr,
+                      int timeout) {
+  const T_SOC soc = retour->soc;
+  const char *const host = jump_identification_const(adr); // host[:port]
+  const char *const portsep = jump_toport_const(adr);      // ":port" or NULL
+  char BIGSTK authority[HTS_URLMAXSIZE * 2];
+  char BIGSTK req[HTS_URLMAXSIZE * 4 + 1100];
+  char line[1024];
+  int code;
+
+  if (soc == INVALID_SOCKET)
+    return 0;
+
+  // CONNECT needs an explicit host:port; default the https port
+  authority[0] = '\0';
+  if (portsep != NULL)
+    strlcatbuff(authority, host, sizeof(authority)); // already host:port
+  else
+    snprintf(authority, sizeof(authority), "%s:%d", host, 443);
+
+  // backstop: never let a stray CR/LF in the host smuggle a second line into
+  // the CONNECT request (the host is already sanitized upstream)
+  {
+    const char *c;
+
+    for (c = authority; *c != '\0'; c++) {
+      if ((unsigned char) *c < ' ') {
+        strcpybuff(retour->msg, "proxy CONNECT: invalid host");
+        return 0;
+      }
+    }
+  }
+
+  snprintf(req, sizeof(req), "CONNECT %s HTTP/1.0" H_CRLF "Host: %s" H_CRLF,
+           authority, authority);
+
+  // creds go on the CONNECT, not the tunneled origin request
+  if (link_has_authorization(retour->req.proxy.name)) {
+    const char *a = jump_identification_const(retour->req.proxy.name);
+    const char *astart = jump_protocol_const(retour->req.proxy.name);
+    char autorisation[1100];
+    char user_pass[256];
+
+    autorisation[0] = user_pass[0] = '\0';
+    strncatbuff(user_pass, astart, (int) (a - astart) - 1);
+    strcpybuff(user_pass, unescape_http(OPT_GET_BUFF(opt),
+                                        OPT_GET_BUFF_SIZE(opt), user_pass));
+    code64((unsigned char *) user_pass, (int) strlen(user_pass),
+           (unsigned char *) autorisation, 0);
+    strlcatbuff(req, "Proxy-Authorization: Basic ", sizeof(req));
+    strlcatbuff(req, autorisation, sizeof(req));
+    strlcatbuff(req, H_CRLF, sizeof(req));
+  }
+  strlcatbuff(req, H_CRLF, sizeof(req)); // end of request headers
+
+  // raw send: ssl is set, so sendc() would route to TLS
+  {
+    const char *p = req;
+    size_t remain = strlen(req);
+    int stalls = 0;
+
+    while (remain > 0) {
+      const int n = (int) send(soc, p, (int) remain, 0);
+
+      if (n > 0) {
+        p += n;
+        remain -= (size_t) n;
+        stalls = 0;
+      } else {
+#ifdef _WIN32
+        const int wouldblock = (WSAGetLastError() == WSAEWOULDBLOCK);
+#else
+        const int wouldblock =
+            (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR);
+#endif
+        // don't spin forever on a fatal error or an unwritable socket
+        if (!wouldblock || !check_writeinput_t(soc, timeout) ||
+            ++stalls > 100) {
+          strcpybuff(retour->msg, "proxy CONNECT: write error");
+          return 0;
+        }
+      }
+    }
+  }
+
+  // proxy status line: "HTTP/1.x <code> ..."
+  if (proxy_getline(soc, line, sizeof(line), timeout) < 0) {
+    strcpybuff(retour->msg, "proxy CONNECT: no response");
+    return 0;
+  }
+  if (sscanf(line, "HTTP/%*d.%*d %d", &code) < 1)
+    code = 0;
+  if (code < 200 || code >= 300) {
+    snprintf(retour->msg, sizeof(retour->msg), "proxy CONNECT refused: %s",
+             strnotempty(line) ? line : "(no status)");
+    return 0;
+  }
+
+  // drain headers to the blank line; cap the count so a flooding proxy can't
+  // stall the crawl
+  {
+    int headers = 0;
+
+    for (;;) {
+      const int n = proxy_getline(soc, line, sizeof(line), timeout);
+
+      if (n < 0) {
+        strcpybuff(retour->msg, "proxy CONNECT: truncated response");
+        return 0;
+      }
+      if (n == 0)
+        break; // blank line: tunnel ready
+      if (++headers > 64) {
+        strcpybuff(retour->msg, "proxy CONNECT: too many response headers");
+        return 0;
+      }
+    }
+  }
+
+  return 1;
+}
+
 // ouverture d'une liaison http, envoi d'une requète
 // mode: 0 GET  1 HEAD  [2 POST]
 // treat: traiter header?
@@ -901,10 +1059,10 @@ static int append_cookie_header(buff_struct *bstr, t_cookie *cookie,
   return cook;
 }
 
-/* Build the request Cookie line for domain/path into dst (always
+/* Self-test entry for append_cookie_header(): build the request Cookie line
-   NUL-terminated). Returns the number of cookies emitted. */
+   into dst (always NUL-terminated). Returns the number of cookies emitted. */
-int http_cookie_header(t_cookie *cookie, const char *domain, const char *path,
+int http_cookie_header_selftest(t_cookie *cookie, const char *domain,
-                       char *dst, size_t dst_size) {
+                                const char *path, char *dst, size_t dst_size) {
   buff_struct bstr = {dst, dst_size, 0};
 
   assertf(dst != NULL && dst_size > 0);
@@ -947,9 +1105,8 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
           /* widths bound method[256], url[HTS_URLMAXSIZE*2], protocol[256] */
           if (sscanf(line, "%255s %2047s %255s", method, url, protocol) == 3) {
             size_t ret;
-            // absolute-URI for an http proxy; a socks tunnel takes origin-form
+            // selon que l'on a ou pas un proxy
-            if (retour->req.proxy.active &&
+            if (retour->req.proxy.active) {
-                !hts_proxy_is_socks(retour->req.proxy.name)) {
               print_buffer(&bstr,
                       "%s http://%s%s %s\r\n", method, adr, url,
                       protocol);
@@ -985,10 +1142,8 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
         print_buffer(&bstr, "HEAD ");
     }
 
-    // an http proxy needs an absolute URI; a socks tunnel does not
+    // si on gère un proxy, il faut une Absolute URI: on ajoute avant http://www.adr.dom
-    if (retour->req.proxy.active &&
+    if (retour->req.proxy.active && (strncmp(adr, "https://", 8) != 0)) {
-        !hts_proxy_is_socks(retour->req.proxy.name) &&
-        (strncmp(adr, "https://", 8) != 0)) {
       if (!link_has_authority(adr)) {   // default http
 #if HDEBUG
         printf("Proxy Use: for %s%s proxy %d port %d\n", adr, fil,
@@ -1032,11 +1187,8 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
     if (xsend)
       print_buffer(&bstr, "%s", xsend);  // éventuelles autres lignes
 
-    // for https, auth rides the CONNECT (the tunneled GET would leak it); for
+    // for https, auth rides the CONNECT (the tunneled GET would leak it)
-    // socks, the handshake
+    if (retour->req.proxy.active && strncmp(adr, "https://", 8) != 0) {
-    if (retour->req.proxy.active &&
-        !hts_proxy_is_socks(retour->req.proxy.name) &&
-        strncmp(adr, "https://", 8) != 0) {
       if (link_has_authorization(retour->req.proxy.name)) {     // et hop, authentification proxy!
         const char *a = jump_identification_const(retour->req.proxy.name);
         const char *astart = jump_protocol_const(retour->req.proxy.name);
@@ -1127,16 +1279,11 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
       // Compression accepted ?
       if (retour->req.http11) {
         hts_boolean compressible = HTS_FALSE;
-        hts_boolean secure = HTS_FALSE;
-
 #if HTS_USEZLIB
         compressible = (!retour->req.range_used && !retour->req.nocompression);
-#endif
-#if HTS_USEOPENSSL
-        secure = retour->ssl ? HTS_TRUE : HTS_FALSE;
 #endif
         print_buffer(&bstr, "Accept-Encoding: %s" H_CRLF,
-                     hts_acceptencoding(compressible, secure));
+                     hts_acceptencoding(compressible));
       }
 
       /* Authentification */
@@ -1439,7 +1586,7 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
         a = strchr(rcvd + p, '/');
         if (a != NULL) {
           a++;
-          if (sscanf(a, LLintP, &retour->crange) == 1 && retour->crange >= 0) {
+          if (sscanf(a, LLintP, &retour->crange) == 1) {
             retour->crange_start = 0;
             retour->crange_end = retour->crange - 1;
           } else {
@@ -1447,12 +1594,6 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
           }
         }
       }
-      // A valid Content-Range has no negative field; reject hostile values so
-      // the crange +/- 1 arithmetic downstream cannot sign-overflow (UB).
-      if (retour->crange_start < 0 || retour->crange_end < 0 ||
-          retour->crange < 0) {
-        retour->crange_start = retour->crange_end = retour->crange = 0;
-      }
     }
   } else if ((p = strfield(rcvd, "Connection:")) != 0) {
     char *a = rcvd + p;
@@ -1521,10 +1662,22 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
         strcpybuff(retour->contentencoding, tempo);
       else
         retour->contentencoding[0] = '\0';
-      /* A coding to undo (or one we can not undo, which must fail the fetch
+#if HTS_USEZLIB
-         rather than save the coded bytes as the page) */
+      /* Check known encodings */
-      if (hts_codec_parse(retour->contentencoding) != HTS_CODEC_IDENTITY)
+      if (retour->contentencoding[0]) {
-        retour->compressed = 1;
+        if ((strfield2(retour->contentencoding, "gzip"))
+            || (strfield2(retour->contentencoding, "x-gzip"))
+            /*
+               || (strfield2(retour->contentencoding, "compress"))
+               || (strfield2(retour->contentencoding, "x-compress"))
+             */
+            || (strfield2(retour->contentencoding, "deflate"))
+            || (strfield2(retour->contentencoding, "x-deflate"))
+          ) {
+          retour->compressed = 1;
+        }
+      }
+#endif
     }
   } else if ((p = strfield(rcvd, "Location:")) != 0) {
     if (retour) {
@@ -1549,9 +1702,6 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
 #if DEBUG_COOK
     printf("set-cookie detected\n");
 #endif
-    /* Over-long host overflows the fail-safe domain[] copy (abort); drop it. */
-    if (adr && strlen(jump_identification_const(adr)) >= sizeof(domain))
-      return;
     while(*a) {
       char *token_st, *token_end;
       char *value_st, *value_end;
@@ -1848,15 +1998,6 @@ LLint http_xfread1(htsblk * r, int bufl) {
 
   if (bufl > 0) {
     if (!r->is_write) {         // stocker en mémoire
-      // In-memory content must fit a 32-bit index (allocs below add 1, reads
-      // use int offsets): reject a hostile Content-Length or endless stream.
-      const LLint inmem_want =
-          (r->totalsize >= 0) ? r->totalsize : (r->size + bufl);
-      if (inmem_want >= INT32_MAX) {
-        r->statuscode = STATUSCODE_INVALID;
-        strcpybuff(r->msg, "In-memory content too large");
-        return READ_ERROR;
-      }
       if (r->totalsize >= 0) {  // totalsize déterminé ET ALLOUE
         if (r->adr == NULL) {
           r->adr = (char *) malloct((size_t) r->totalsize + 1);
@@ -2419,11 +2560,6 @@ int ident_url_absolute(const char *url, lien_adrfil *adrfil) {
     // recopier adrfil->adresse www..
     strncatbuff(adrfil->adr, p, ((int) (q - p)));
     // *( adrfil->adr+( ((int) q) - ((int) p) ) )=0;  // faut arrêter la fumette!
-
-    // fil[] holds the path plus a possible leading '/' the top strlen() misses.
-    if (strlen(q) >= sizeof(adrfil->fil) - (q[0] != '/' ? 1 : 0))
-      return -1;
-
     // recopier chemin /pub/..
     if (q[0] != '/')            // page par défaut (/)
       strcatbuff(adrfil->fil, "/");
@@ -2902,11 +3038,12 @@ HTSEXT_API char *int2char(strc_int2bytes2 * strc, int n) {
 /* See http://physics.nist.gov/cuu/Units/binary.html */
 #define ToLLint(a) ((LLint)(a))
 #define ToLLintKiB (ToLLint(1024))
-#define ToLLintMiB (ToLLintKiB * ToLLintKiB)
+#define ToLLintMiB (ToLLintKiB*ToLLintKiB)
-#define ToLLintGiB (ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#ifdef HTS_LONGLONG
-#define ToLLintTiB (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#define ToLLintGiB (ToLLintKiB*ToLLintKiB*ToLLintKiB)
-#define ToLLintPiB                                                             \
+#define ToLLintTiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
-  (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#define ToLLintPiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
+#endif
 HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
   if (n < ToLLintKiB) {
     sprintf(strc->buff1, "%d", (int) (LLint) n);
@@ -2915,7 +3052,9 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
     sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / ToLLintKiB)),
             (int) ((LLint) ((n % ToLLintKiB) * 100) / ToLLintKiB));
     strcpybuff(strc->buff2, "KiB");
-  } else if (n < ToLLintGiB) {
+  }
+#ifdef HTS_LONGLONG
+  else if (n < ToLLintGiB) {
     sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
             (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
     strcpybuff(strc->buff2, "MiB");
@@ -2932,6 +3071,13 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
             (int) ((LLint) (((n % (ToLLintPiB)) * 100) / (ToLLintPiB))));
     strcpybuff(strc->buff2, "PiB");
   }
+#else
+  else {
+    sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
+            (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
+    strcpybuff(strc->buff2, "MiB");
+  }
+#endif
   strc->buffadr[0] = strc->buff1;
   strc->buffadr[1] = strc->buff2;
   return strc->buffadr;
@@ -3713,10 +3859,6 @@ const char *jump_protocol_const(const char *source) {
     source += p;
   else if ((p = strfield(source, "file:")))
     source += p;
-  else if ((p = strfield(source, "socks5h:")))
-    source += p;
-  else if ((p = strfield(source, "socks5:")))
-    source += p;
   // net_path
   if (strncmp(source, "//", 2) == 0)
     source += 2;
@@ -3725,48 +3867,6 @@ const char *jump_protocol_const(const char *source) {
 
 DECLARE_NON_CONST_VERSION(jump_protocol)
 
-hts_boolean hts_proxy_is_socks(const char *name) {
-  if (name == NULL)
-    return HTS_FALSE;
-  return (strfield(name, "socks5h:") || strfield(name, "socks5:")) ? HTS_TRUE
-                                                                   : HTS_FALSE;
-}
-
-// default proxy port for a -P argument, keyed on the scheme
-static int proxy_default_port(const char *arg) {
-  return hts_proxy_is_socks(arg) ? 1080 : 8080;
-}
-
-void hts_parse_proxy(const char *arg, char *name, size_t name_size, int *port) {
-  const char *authority = strstr(arg, "://");
-  const char *a;
-  size_t namelen;
-
-  if (name_size == 0)
-    return;
-  // scan back to the port ':' (or userinfo '@'), but never past the authority,
-  // so a scheme's own colon is not read as a port separator; inspect a[-1] from
-  // one-past-end so no pointer below the string is ever formed
-  authority = (authority != NULL) ? authority + 3 : arg;
-  a = arg + strlen(arg);
-  while (a > authority && a[-1] != ':' && a[-1] != '@')
-    a--;
-  if (a > authority && a[-1] == ':') {
-    int p = -1;
-
-    sscanf(a, "%d", &p);
-    *port = (p > 0) ? p : proxy_default_port(arg);
-    namelen = (size_t) (a - 1 - arg);
-  } else {
-    *port = proxy_default_port(arg);
-    namelen = strlen(arg);
-  }
-  if (namelen >= name_size) // arg is user-controlled: truncate, don't overflow
-    namelen = name_size - 1;
-  memcpy(name, arg, namelen);
-  name[namelen] = '\0';
-}
-
 // codage base 64 a vers b
 void code64(unsigned char *a, int size_a, unsigned char *b, int crlf) {
   int i1 = 0, i2 = 0, i3 = 0, i4 = 0;
@@ -4252,6 +4352,11 @@ HTSEXT_API void get_httptype(httrackp *opt, char *s, const char *fil,
   (void) get_httptype_sized(opt, s, HTS_MIMETYPE_SIZE, fil, flag);
 }
 
+/* Advertised Accept-Encoding; gzip and deflate both decode via hts_zunpack */
+const char *hts_acceptencoding(hts_boolean compressible) {
+  return compressible ? "gzip, deflate, identity;q=0.9" : "identity";
+}
+
 // get type of fil (php)
 // s: buffer (text/html) or NULL
 // return: 1 if known by user
@@ -4591,31 +4696,26 @@ int fexist_utf8(const char *s) {
   return 0;
 }
 
-/* File size, -1 if absent */
+/* Taille d'un fichier, -1 si n'existe pas */
 /* Note: NOT utf-8 */
-LLint fsize(const char *s) {
+off_t fsize(const char *s) {
-  STRUCT_STAT st;
+  struct stat st;
 
-  if (!strnotempty(s)) // empty name: error
+  if (!strnotempty(s))          // nom vide: erreur
     return -1;
-  /* _stat64, not stat(): the latter is 32-bit on MSVC */
-#ifdef _WIN32
-  if (_stat64(s, &st) == 0 && S_ISREG(st.st_mode)) {
-#else
   if (stat(s, &st) == 0 && S_ISREG(st.st_mode)) {
-#endif
     return st.st_size;
   } else {
     return -1;
   }
 }
 
-/* File size, -1 if absent */
+/* Taille d'un fichier, -1 si n'existe pas */
 /* Note: utf-8 */
-LLint fsize_utf8(const char *s) {
+off_t fsize_utf8(const char *s) {
   STRUCT_STAT st;
 
-  if (!strnotempty(s)) // empty name: error
+  if (!strnotempty(s))          // nom vide: erreur
     return -1;
   if (STAT(s, &st) == 0 && S_ISREG(st.st_mode)) {
     return st.st_size;
@@ -4624,17 +4724,24 @@ LLint fsize_utf8(const char *s) {
   }
 }
 
-/* fseeko/ftello, never fseek/ftell: ftell returns long, which cannot carry an
+off_t fpsize(FILE * fp) {
-   offset past 2GB on a 32-bit platform and fails with EOVERFLOW there. */
+  off_t oldpos, size;
-LLint fpsize(FILE *fp) {
-  LLint oldpos, size;
 
   if (!fp)
     return -1;
+#ifdef HTS_FSEEKO
   oldpos = ftello(fp);
-  fseeko(fp, 0, SEEK_END);
+#else
+  oldpos = ftell(fp);
+#endif
+  fseek(fp, 0, SEEK_END);
+#ifdef HTS_FSEEKO
   size = ftello(fp);
   fseeko(fp, oldpos, SEEK_SET);
+#else
+  size = ftell(fp);
+  fseek(fp, oldpos, SEEK_SET);
+#endif
   return size;
 }
 
@@ -4898,7 +5005,7 @@ static struct addrinfo *resolver_make_ai(const char *ip, int want_family) {
   return ai;
 }
 
-static void HTS_RESOLVER_CALL override_freeaddrinfo(struct addrinfo *res) {
+static void override_freeaddrinfo(struct addrinfo *res) {
   while (res != NULL) {
     struct addrinfo *const next = res->ai_next;
 
@@ -4908,10 +5015,9 @@ static void HTS_RESOLVER_CALL override_freeaddrinfo(struct addrinfo *res) {
   }
 }
 
-static int HTS_RESOLVER_CALL override_getaddrinfo(const char *node,
+static int override_getaddrinfo(const char *node, const char *service,
-                                                  const char *service,
+                                const struct addrinfo *hints,
-                                                  const struct addrinfo *hints,
+                                struct addrinfo **res) {
-                                                  struct addrinfo **res) {
   const char *const spec = getenv("HTTRACK_DEBUG_RESOLVE");
   const int want = (hints != NULL) ? hints->ai_family : PF_UNSPEC;
   const char *colon;
@@ -5807,7 +5913,17 @@ int multipleStringMatch(const char *s, const char *match) {
 }
 
 HTSEXT_API httrackp *hts_create_opt(void) {
-  static const char *defaultModules[] = {"httrack-plugin", NULL};
+#if ( defined(_WIN32) || defined(__ANDROID__) )
+  static const char *defaultModules[] = {
+    "htsswf", "htsjava", "httrack-plugin", NULL
+  };
+#else
+#ifndef HTS_LIBHTSJAVA_NAME
+#define HTS_LIBHTSJAVA_NAME "libhtsjava.so" /* non-autoconf fallback */
+#endif
+  static const char *defaultModules[] = {"libhtsswf.so.1", HTS_LIBHTSJAVA_NAME,
+                                         "httrack-plugin", NULL};
+#endif
   httrackp *opt = malloc(sizeof(httrackp));
 
   /* default options */
@@ -6030,8 +6146,6 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->referer);
     StringFree(opt->from);
     StringFree(opt->lang_iso);
-    StringFree(opt->accept);
-    StringFree(opt->headers);
     StringFree(opt->sys_com);
     StringFree(opt->mimedefs);
     StringFree(opt->filelist);
@@ -6400,13 +6514,13 @@ int hts_stat_utf8(const char *path, STRUCT_STAT * buf) {
   LPWSTR wpath = hts_convertUTF8StringToUCS2(path, (int) strlen(path), NULL);
 
   if (wpath != NULL) {
-    const int result = _wstat64(wpath, buf);
+    const int result = _wstat(wpath, buf);
 
     free(wpath);
     return result;
   } else {
     // Fallback on conversion error.
-    return _stat64(path, buf);
+    return _stat(path, buf);
   }
 }
 

src/htslib.h

@@ -184,10 +184,10 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode, const char *xsend
                   const char *referer_adr, const char *referer_fil,
                   htsblk * retour);
 /* Build the request "Cookie:" header line for stored cookies matching
-   domain/path into dst (NUL-terminated), wrapping the logic http_sendhead()
+   domain/path into dst (NUL-terminated). Exposed for the -#Q self-test;
-   uses. Returns cookies emitted. */
+   wraps the same logic http_sendhead() uses. Returns cookies emitted. */
-int http_cookie_header(t_cookie *cookie, const char *domain, const char *path,
+int http_cookie_header_selftest(t_cookie *cookie, const char *domain,
-                       char *dst, size_t dst_size);
+                                const char *path, char *dst, size_t dst_size);
 
 T_SOC newhttp(httrackp * opt, const char *iadr, htsblk * retour, int port,
               int waitconnect);
@@ -207,9 +207,15 @@ int check_readinput(htsblk * r);
 int check_readinput_t(T_SOC soc, int timeout);
 int check_writeinput_t(T_SOC soc, int timeout);
 
-/* TRUE if this -P proxy name (which keeps its scheme) is a SOCKS5 proxy. */
+/* Open an HTTP CONNECT tunnel through the active proxy for an https request:
-hts_boolean hts_proxy_is_socks(const char *name);
+   `retour->soc` must already be TCP-connected to the proxy, and `adr` is the
-
+   origin authority (url_adr, e.g. "https://host:port"). Sends the CONNECT
+   request (with Proxy-Authorization when the proxy carries credentials) and
+   reads the proxy's status line, so the caller's TLS handshake then runs
+   end-to-end with the origin. Blocks up to `timeout` seconds. Returns 1 on a
+   2xx tunnel, 0 on failure (retour->msg/statuscode set). */
+int http_proxy_tunnel(httrackp *opt, htsblk *retour, const char *adr,
+                      int timeout);
 void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * retour,
                char *rcvd);
 void treatfirstline(htsblk * retour, const char *rcvd);
@@ -277,18 +283,15 @@ int ishttperror(int err);
 int get_userhttptype(httrackp * opt, char *s, const char *fil);
 int give_mimext(char *s, size_t ssize, const char *st);
 
+/* Advertised Accept-Encoding value (no header name/CRLF); see htslib.c. */
+const char *hts_acceptencoding(hts_boolean compressible);
+
 int may_bogus_multiple(httrackp * opt, const char *mime, const char *filename);
 int may_unknown2(httrackp * opt, const char *mime, const char *filename);
 
 const char *strrchr_limit(const char *s, char c, const char *limit);
 char *jump_protocol(char *source);
 const char *jump_protocol_const(const char *source);
-
-/* Split a -P proxy argument "[scheme://][user:pass@]host[:port]" into the proxy
-   host string (scheme and any user:pass kept, for later stripping and auth),
-   written NUL-terminated into name[name_size] (truncated to fit), and the port
-   in *port. The port defaults by scheme: 1080 for socks5/socks5h, else 8080. */
-void hts_parse_proxy(const char *arg, char *name, size_t name_size, int *port);
 void code64(unsigned char *a, int size_a, unsigned char *b, int crlf);
 
 #define copychar(catbuff,a) concat(catbuff,(a),NULL)
@@ -310,11 +313,10 @@ void cut_path(char *fullpath, char *path, size_t path_size, char *pname,
 int fexist(const char *s);
 int fexist_utf8(const char *s);
 
-/* File size in bytes, -1 if absent or not a regular file. LLint, not off_t:
+/*LLint fsize(const char* s);    */
-   the latter is a 32-bit long on MSVC, truncating any file of 2GB or more. */
+off_t fpsize(FILE * fp);
-LLint fpsize(FILE *fp);
+off_t fsize(const char *s);
-LLint fsize(const char *s);
+off_t fsize_utf8(const char *s);
-LLint fsize_utf8(const char *s);
 
 // Threads
 typedef void *(*beginthread_type) (void *);
@@ -394,8 +396,7 @@ void *hts_get_callback(t_hts_htmlcheck_callbacks * callbacks,
      HTSEXT_API FILE *hts_fopen_utf8(const char *path, const char *mode);
 
 #define STAT hts_stat_utf8
-     /* _stat64: _stat's st_size is a 32-bit long, even in x64 builds */
+     typedef struct _stat STRUCT_STAT;
-     typedef struct _stat64 STRUCT_STAT;
      HTSEXT_API int hts_stat_utf8(const char *path, STRUCT_STAT * buf);
 
 #define UNLINK hts_unlink_utf8
@@ -492,14 +493,6 @@ HTS_STATIC int strcmpnocase(const char *a, const char *b) {
 #define snprintf _snprintf
 #endif
 
-/* MSVC ships these POSIX functions under other names. Kept out of the installed
-   headers: they would rewrite the same identifiers in a consumer's own code. */
-#ifdef _MSC_VER
-#define fseeko _fseeki64
-#define ftello _ftelli64
-#define timegm _mkgmtime
-#endif
-
 #define strfield2(f,s) ( (strlen(f)!=strlen(s)) ? 0 : (strfield(f,s)) )
 
 // is this MIME an hypertext MIME (text/html), html/js-style or other script/text type?
@@ -593,9 +586,9 @@ HTS_STATIC int compare_mime(httrackp * opt, const char *mime, const char *file,
 #endif
 
 // returns (size_t) -1 upon error
-static HTS_UNUSED size_t llint_to_size_t(LLint o) {
+static HTS_UNUSED size_t off_t_to_size_t(off_t o) {
   const size_t so = (size_t) o;
-  if ((LLint) so == o) {
+  if ((off_t) so == o) {
     return so;
   } else {
     return (size_t) -1;

src/htsname.c

@@ -42,7 +42,6 @@ Please visit our Website: http://www.httrack.com
 #include "htscharset.h"
 #include "htsencoding.h"
 #include "htssniff.h"
-#include "htscodec.h"
 #if HTS_USEZLIB
 #include "htszlib.h"
 #endif
@@ -152,6 +151,29 @@ typedef struct sniff_src {
   const char *prev_save; /* previous run's save name (cache X-Save) */
 } sniff_src;
 
+#if HTS_USEZLIB
+/* Inflate the head of a gzip/zlib stream; 0 when undecodable. */
+static size_t sniff_inflate_head(const void *in, size_t in_len, void *out,
+                                 size_t out_len) {
+  z_stream zs;
+  size_t n = 0;
+  int err;
+
+  memset(&zs, 0, sizeof(zs));
+  if (inflateInit2(&zs, 47) != Z_OK) /* 47: gzip or zlib, autodetected */
+    return 0;
+  zs.next_in = (const Bytef *) in;
+  zs.avail_in = (uInt) in_len;
+  zs.next_out = (Bytef *) out;
+  zs.avail_out = (uInt) out_len;
+  err = inflate(&zs, Z_SYNC_FLUSH);
+  if (err == Z_OK || err == Z_STREAM_END || err == Z_BUF_ERROR)
+    n = out_len - zs.avail_out;
+  inflateEnd(&zs);
+  return n;
+}
+#endif
+
 static size_t sniff_read_head(const char *path, void *buf, size_t len) {
   char catbuff[CATBUFF_SIZE];
   FILE *const fp = FOPEN(fconv(catbuff, sizeof(catbuff), path), "rb");
@@ -183,12 +205,16 @@ static size_t sniff_slot_head(const lien_back *slot, void *buf, size_t len) {
       n = sniff_read_head(slot->tmpfile, buf, len);
   }
   if (n > 0 && r->compressed) {
+#if HTS_USEZLIB
     unsigned char raw[HTS_SNIFF_LEN];
 
     if (n > sizeof(raw))
       n = sizeof(raw);
     memcpy(raw, buf, n);
-    n = hts_codec_head(hts_codec_parse(r->contentencoding), raw, n, buf, len);
+    n = sniff_inflate_head(raw, n, buf, len);
+#else
+    n = 0;
+#endif
   }
   return n;
 }

src/htsnet.h

@@ -309,19 +309,10 @@ typedef socklen_t SOClen;
     self-test can script DNS answers (families, multiplicity, errors)
     in-process. The free function must match its getaddrinfo (a fake allocates
     its own chain), hence the pair. */
-/* Winsock's resolver is __stdcall; a plain pointer only compiles on x64, where
-   there is one convention. Backend implementations must carry this too. */
-#ifdef _WIN32
-#define HTS_RESOLVER_CALL WSAAPI
-#else
-#define HTS_RESOLVER_CALL
-#endif
-
 typedef struct hts_resolver_backend {
-  int(HTS_RESOLVER_CALL *getaddrinfo)(const char *node, const char *service,
+  int (*getaddrinfo)(const char *node, const char *service,
-                                      const struct addrinfo *hints,
+                     const struct addrinfo *hints, struct addrinfo **res);
-                                      struct addrinfo **res);
+  void (*freeaddrinfo)(struct addrinfo *res);
-  void(HTS_RESOLVER_CALL *freeaddrinfo)(struct addrinfo *res);
 } hts_resolver_backend;
 
 /** Install a resolver backend for the process; NULL restores the libc default.

src/htsopt.h

@@ -328,8 +328,8 @@ typedef enum hts_wizard {
 
 typedef enum hts_robots {
   HTS_ROBOTS_NEVER = 0,        /**< ignore robots rules */
-  HTS_ROBOTS_SOMETIMES = 1,    /**< partial obedience, set by -s */
+  HTS_ROBOTS_SOMETIMES = 1,    /**< partial obedience (default) */
-  HTS_ROBOTS_ALWAYS = 2,       /**< obey robots rules (default) */
+  HTS_ROBOTS_ALWAYS = 2,       /**< obey robots rules */
   HTS_ROBOTS_ALWAYS_STRICT = 3 /**< obey even strict rules */
 } hts_robots;
 #endif

src/htsparse.c

@@ -2007,7 +2007,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 
                 /* Unescape/escape %20 and other   */
                 {
-                  // NULL when UTF-8 conversion is off (-%T0)
+                  // Note: always true (iso-8859-1 as default)
                   const char *const charset = str->page_charset_;
                   const int hasCharset = charset != NULL 
                     && *charset != '\0';
@@ -2031,11 +2031,10 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                   // Force to encode non-printable chars (should never happend)
                   escape_remove_control(lien);
                   
-                  // charset conversion for the URI filename (not the query
+                  // charset conversion for the URI filename, 
-                  // string), unless the bytes already are valid UTF-8:
+                  // and not already UTF-8
-                  // converting those would double-encode them (#180)
+                  // (note: not for the query string!)
-                  if (hasCharset && !hts_isCharsetUTF8(charset) &&
+                  if (hasCharset && !hts_isCharsetUTF8(charset)) {
-                      !hts_isStringUTF8(lien, strlen(lien))) {
                     char *const s = hts_convertStringToUTF8(lien, strlen(lien), charset);
                     if (s != NULL) {
                       hts_log_print(opt, LOG_DEBUG,
@@ -4311,8 +4310,6 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
       *forbidden_url == 0 && IS_DELAYED_EXT(afs->save) && !opt->state.stop) {
     int loops;
     int continue_loop;
-    char BIGSTK
-        cookie_before[16384]; /* #15: this URL's Cookie header, pre-request */
 
     hts_log_print(opt, LOG_DEBUG, "Waiting for type to be known: %s%s", afs->af.adr,
                   afs->af.fil);
@@ -4321,12 +4318,6 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
     for(loops = 0, continue_loop = 1;
         IS_DELAYED_EXT(afs->save) && continue_loop && loops < 7; loops++) {
       continue_loop = 0;
-      /* #15: snapshot the Cookie header THIS url would send, so only its own
-         self-redirect Set-Cookie trips the retry, not a concurrent slot's. */
-      cookie_before[0] = '\0';
-      if (opt->accept_cookie && opt->cookie != NULL)
-        http_cookie_header(opt->cookie, jump_identification_const(afs->af.adr),
-                           afs->af.fil, cookie_before, sizeof(cookie_before));
 
       /* Wait for an available slot */
       if (!hts_wait_available_socket(sback, opt, cache, ptr))
@@ -4524,17 +4515,6 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
           /* Moved! */
           else if (HTTP_IS_REDIRECT(back[b].r.statuscode)) {
             char BIGSTK mov_url[HTS_URLMAXSIZE * 2];
-            char BIGSTK cookie_after[16384];
-            hts_boolean cookies_changed;
-
-            /* #15: cookie-wall signal: this URL's own Cookie header changed
-               across its self-redirect (a Set-Cookie it just set). */
-            cookie_after[0] = '\0';
-            if (opt->accept_cookie && opt->cookie != NULL)
-              http_cookie_header(
-                  opt->cookie, jump_identification_const(afs->af.adr),
-                  afs->af.fil, cookie_after, sizeof(cookie_after));
-            cookies_changed = strcmp(cookie_before, cookie_after) != 0;
 
             mov_url[0] = '\0';
             strcpybuff(mov_url, back[b].r.location);    // copier URL
@@ -4604,24 +4584,11 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
                   url_savename(afs, former, heap(ptr)->adr, heap(ptr)->fil, 
                                opt, sback, cache, hash, ptr, numero_passe,
                                &delayed_back);
-                } else if (cookies_changed) {
-                  // #15: cookie-wall self-redirect; evict the cached
-                  // fast-header so the re-issue refetches with the cookie.
-                  if (cache->cached_tests != NULL)
-                    coucal_remove(cache->cached_tests,
-                                  concat(OPT_GET_BUFF(opt),
-                                         OPT_GET_BUFF_SIZE(opt), afs->af.adr,
-                                         afs->af.fil));
-                  afs->save[0] = '\0';
-                  url_savename(afs, former, heap(ptr)->adr, heap(ptr)->fil, opt,
-                               sback, cache, hash, ptr, numero_passe,
-                               &delayed_back);
-                  continue_loop = 1;
                 } else {
                   hts_log_print(opt, LOG_WARNING,
                                 "Unable to test %s%s (loop to same filename)",
                                 afs->af.adr, afs->af.fil);
-                } // loop to same location
+                }               // loop to same location
               }                 // ident_url_relatif()
             }                   // location
           }                     // redirect

src/htsproxy.c

@@ -1,539 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* ------------------------------------------------------------ */
-/* File: Proxy tunneling (HTTP CONNECT, SOCKS5)                 */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-/* Internal engine bytecode */
-#define HTS_INTERNAL_BYTECODE
-
-#include "htscore.h"
-
-#include "htslib.h"
-#include "htsproxy.h"
-
-#include <string.h>
-
-// Read a CRLF line from a non-blocking socket (waits up to timeout per recv).
-// Returns the line length (0 = empty), or -1 on timeout/EOF/error.
-static int proxy_getline(T_SOC soc, char *s, int max, int timeout) {
-  int j = 0;
-
-  for (;;) {
-    unsigned char ch;
-    int n;
-
-    if (!check_readinput_t(soc, timeout))
-      return -1; // timed out waiting for data
-    n = (int) recv(soc, &ch, 1, 0);
-    if (n == 1) {
-      if (ch == 13) // CR
-        continue;
-      if (ch == 10) // LF: end of line
-        break;
-      if (j >= max - 1)
-        return -1; // line too long: bound the read against a hostile proxy
-      s[j++] = (char) ch;
-    } else if (n == 0) {
-      return -1; // connection closed
-    } else {
-#ifdef _WIN32
-      if (WSAGetLastError() == WSAEWOULDBLOCK)
-        continue;
-#else
-      if (errno == EINTR || errno == EAGAIN || errno == EWOULDBLOCK)
-        continue;
-#endif
-      return -1;
-    }
-  }
-  s[j] = '\0';
-  return j;
-}
-
-int http_proxy_tunnel(httrackp *opt, htsblk *retour, const char *adr,
-                      int timeout) {
-  const T_SOC soc = retour->soc;
-  const char *const host = jump_identification_const(adr); // host[:port]
-  const char *const portsep = jump_toport_const(adr);      // ":port" or NULL
-  char BIGSTK authority[HTS_URLMAXSIZE * 2];
-  char BIGSTK req[HTS_URLMAXSIZE * 4 + 1100];
-  char line[1024];
-  int code;
-
-  if (soc == INVALID_SOCKET)
-    return 0;
-
-  // CONNECT needs an explicit host:port; default the https port
-  authority[0] = '\0';
-  if (portsep != NULL)
-    strlcatbuff(authority, host, sizeof(authority)); // already host:port
-  else
-    snprintf(authority, sizeof(authority), "%s:%d", host, 443);
-
-  // backstop: never let a stray CR/LF in the host smuggle a second line into
-  // the CONNECT request (the host is already sanitized upstream)
-  {
-    const char *c;
-
-    for (c = authority; *c != '\0'; c++) {
-      if ((unsigned char) *c < ' ') {
-        strcpybuff(retour->msg, "proxy CONNECT: invalid host");
-        return 0;
-      }
-    }
-  }
-
-  snprintf(req, sizeof(req), "CONNECT %s HTTP/1.0" H_CRLF "Host: %s" H_CRLF,
-           authority, authority);
-
-  // creds go on the CONNECT, not the tunneled origin request
-  if (link_has_authorization(retour->req.proxy.name)) {
-    const char *a = jump_identification_const(retour->req.proxy.name);
-    const char *astart = jump_protocol_const(retour->req.proxy.name);
-    char autorisation[1100];
-    char user_pass[256];
-
-    autorisation[0] = user_pass[0] = '\0';
-    strncatbuff(user_pass, astart, (int) (a - astart) - 1);
-    strcpybuff(user_pass, unescape_http(OPT_GET_BUFF(opt),
-                                        OPT_GET_BUFF_SIZE(opt), user_pass));
-    code64((unsigned char *) user_pass, (int) strlen(user_pass),
-           (unsigned char *) autorisation, 0);
-    strlcatbuff(req, "Proxy-Authorization: Basic ", sizeof(req));
-    strlcatbuff(req, autorisation, sizeof(req));
-    strlcatbuff(req, H_CRLF, sizeof(req));
-  }
-  strlcatbuff(req, H_CRLF, sizeof(req)); // end of request headers
-
-  // raw send: ssl is set, so sendc() would route to TLS
-  {
-    const char *p = req;
-    size_t remain = strlen(req);
-    int stalls = 0;
-
-    while (remain > 0) {
-      const int n = (int) send(soc, p, (int) remain, 0);
-
-      if (n > 0) {
-        p += n;
-        remain -= (size_t) n;
-        stalls = 0;
-      } else {
-#ifdef _WIN32
-        const int wouldblock = (WSAGetLastError() == WSAEWOULDBLOCK);
-#else
-        const int wouldblock =
-            (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR);
-#endif
-        // don't spin forever on a fatal error or an unwritable socket
-        if (!wouldblock || !check_writeinput_t(soc, timeout) ||
-            ++stalls > 100) {
-          strcpybuff(retour->msg, "proxy CONNECT: write error");
-          return 0;
-        }
-      }
-    }
-  }
-
-  // proxy status line: "HTTP/1.x <code> ..."
-  if (proxy_getline(soc, line, sizeof(line), timeout) < 0) {
-    strcpybuff(retour->msg, "proxy CONNECT: no response");
-    return 0;
-  }
-  if (sscanf(line, "HTTP/%*d.%*d %d", &code) < 1)
-    code = 0;
-  if (code < 200 || code >= 300) {
-    snprintf(retour->msg, sizeof(retour->msg), "proxy CONNECT refused: %s",
-             strnotempty(line) ? line : "(no status)");
-    return 0;
-  }
-
-  // drain headers to the blank line; cap the count so a flooding proxy can't
-  // stall the crawl
-  {
-    int headers = 0;
-
-    for (;;) {
-      const int n = proxy_getline(soc, line, sizeof(line), timeout);
-
-      if (n < 0) {
-        strcpybuff(retour->msg, "proxy CONNECT: truncated response");
-        return 0;
-      }
-      if (n == 0)
-        break; // blank line: tunnel ready
-      if (++headers > 64) {
-        strcpybuff(retour->msg, "proxy CONNECT: too many response headers");
-        return 0;
-      }
-    }
-  }
-
-  return 1;
-}
-
-/* SOCKS5 client (RFC 1928, RFC 1929 auth), hostname mode only: the proxy
-   resolves the origin name (remote DNS, curl's socks5h). The stream is the
-   proxy socket, or a scripted buffer under -#test=socks5. */
-
-#define SOCKS5_VERSION 0x05
-#define SOCKS5_AUTH_VERSION 0x01
-#define SOCKS5_METHOD_NONE 0x00
-#define SOCKS5_METHOD_USERPASS 0x02
-#define SOCKS5_METHOD_NOACCEPTABLE 0xFF
-#define SOCKS5_CMD_CONNECT 0x01
-#define SOCKS5_ATYP_IPV4 0x01
-#define SOCKS5_ATYP_DOMAIN 0x03
-#define SOCKS5_ATYP_IPV6 0x04
-#define SOCKS5_MAXFIELD 255 /* one length byte: host, user and password */
-
-typedef struct socks5_stream {
-  T_SOC soc; /* INVALID_SOCKET when scripted (self-test) */
-  int timeout;
-  socks5_test_io *io;
-} socks5_stream;
-
-static int socks5_fail(char *msg, size_t msgsize, const char *text) {
-  if (msgsize != 0)
-    strlcpybuff(msg, text, msgsize);
-  return 0;
-}
-
-/* Read exactly n bytes, or fail: SOCKS frames are not self-delimiting, so a
-   short read would desync the stream shared with the origin traffic. */
-static int socks5_read_n(socks5_stream *st, unsigned char *buf, size_t n) {
-  size_t got = 0;
-  int stalls = 0;
-
-  if (st->soc == INVALID_SOCKET) { /* scripted */
-    socks5_test_io *const io = st->io;
-
-    if (n > io->reply_len - io->consumed)
-      return 0;
-    memcpy(buf, io->reply + io->consumed, n);
-    io->consumed += n;
-    return 1;
-  }
-  while (got < n) {
-    const int r = (int) recv(st->soc, (char *) buf + got, (int) (n - got), 0);
-
-    if (r > 0) {
-      got += (size_t) r;
-      stalls = 0;
-    } else if (r == 0) {
-      return 0; // proxy closed mid-frame
-    } else {
-#ifdef _WIN32
-      const int wouldblock = (WSAGetLastError() == WSAEWOULDBLOCK);
-#else
-      const int wouldblock =
-          (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR);
-#endif
-      if (!wouldblock || !check_readinput_t(st->soc, st->timeout) ||
-          ++stalls > 100)
-        return 0;
-    }
-  }
-  return 1;
-}
-
-static int socks5_write_all(socks5_stream *st, const unsigned char *buf,
-                            size_t len) {
-  size_t remain = len;
-  int stalls = 0;
-
-  if (st->soc == INVALID_SOCKET) { /* scripted */
-    socks5_test_io *const io = st->io;
-
-    if (len > sizeof(io->sent) - io->sent_len)
-      return 0;
-    memcpy(io->sent + io->sent_len, buf, len);
-    io->sent_len += len;
-    return 1;
-  }
-  while (remain > 0) {
-    // raw send: the socket is still plain here, sendc() would route to TLS
-    const int n = (int) send(st->soc, (const char *) buf, (int) remain, 0);
-
-    if (n > 0) {
-      buf += n;
-      remain -= (size_t) n;
-      stalls = 0;
-    } else {
-#ifdef _WIN32
-      const int wouldblock = (WSAGetLastError() == WSAEWOULDBLOCK);
-#else
-      const int wouldblock =
-          (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR);
-#endif
-      if (!wouldblock || !check_writeinput_t(st->soc, st->timeout) ||
-          ++stalls > 100)
-        return 0;
-    }
-  }
-  return 1;
-}
-
-static const char *socks5_rep_message(unsigned char rep) {
-  switch (rep) {
-  case 0x01:
-    return "general failure";
-  case 0x02:
-    return "connection not allowed by ruleset";
-  case 0x03:
-    return "network unreachable";
-  case 0x04:
-    return "host unreachable";
-  case 0x05:
-    return "connection refused";
-  case 0x06:
-    return "TTL expired";
-  case 0x07:
-    return "command not supported";
-  case 0x08:
-    return "address type not supported";
-  default:
-    return "unknown error";
-  }
-}
-
-/* The reply's BND.ADDR is variable-length: consume exactly what ATYP says, or
-   the leftover bytes prepend to the first origin (or TLS) read. */
-static int socks5_read_reply(socks5_stream *st, char *msg, size_t msgsize) {
-  unsigned char head[4];
-  unsigned char addr[SOCKS5_MAXFIELD + 2];
-  size_t addrlen;
-
-  if (!socks5_read_n(st, head, sizeof(head)))
-    return socks5_fail(msg, msgsize, "SOCKS5: no reply from proxy");
-  if (head[0] != SOCKS5_VERSION)
-    return socks5_fail(msg, msgsize, "SOCKS5: bad version in reply");
-  if (head[1] != 0x00) {
-    snprintf(msg, msgsize, "SOCKS5 connect failed: %s",
-             socks5_rep_message(head[1]));
-    return 0;
-  }
-  switch (head[3]) {
-  case SOCKS5_ATYP_IPV4:
-    addrlen = 4;
-    break;
-  case SOCKS5_ATYP_IPV6:
-    addrlen = 16;
-    break;
-  case SOCKS5_ATYP_DOMAIN: {
-    unsigned char len;
-
-    if (!socks5_read_n(st, &len, 1))
-      return socks5_fail(msg, msgsize, "SOCKS5: truncated reply");
-    addrlen = len; // <= 255, always fits addr[]
-    break;
-  }
-  default: // unknown length: the stream cannot be resynchronized
-    return socks5_fail(msg, msgsize, "SOCKS5: unknown address type in reply");
-  }
-  if (addrlen != 0 && !socks5_read_n(st, addr, addrlen))
-    return socks5_fail(msg, msgsize, "SOCKS5: truncated reply address");
-  if (!socks5_read_n(st, addr, 2)) // BND.PORT, unused
-    return socks5_fail(msg, msgsize, "SOCKS5: truncated reply port");
-  return 1;
-}
-
-static int socks5_negotiate(socks5_stream *st, const char *host, size_t hostlen,
-                            int port, const char *user, size_t userlen,
-                            const char *pass, size_t passlen, int want_auth,
-                            char *msg, size_t msgsize) {
-  unsigned char frame[3 + SOCKS5_MAXFIELD + SOCKS5_MAXFIELD];
-  unsigned char rep[2];
-
-  /* greeting */
-  frame[0] = SOCKS5_VERSION;
-  frame[1] = (unsigned char) (want_auth ? 2 : 1);
-  frame[2] = SOCKS5_METHOD_NONE;
-  frame[3] = SOCKS5_METHOD_USERPASS;
-  if (!socks5_write_all(st, frame, (size_t) 2 + frame[1]))
-    return socks5_fail(msg, msgsize, "SOCKS5: write error");
-  if (!socks5_read_n(st, rep, sizeof(rep)))
-    return socks5_fail(msg, msgsize, "SOCKS5: no method reply from proxy");
-  if (rep[0] != SOCKS5_VERSION)
-    return socks5_fail(msg, msgsize, "SOCKS5: bad version in method reply");
-  switch (rep[1]) {
-  case SOCKS5_METHOD_NONE:
-    break;
-  case SOCKS5_METHOD_USERPASS:
-    if (!want_auth)
-      return socks5_fail(msg, msgsize,
-                         "SOCKS5: proxy requires authentication, none given");
-    /* RFC 1929 sub-negotiation; its version byte is 0x01, not 0x05 */
-    frame[0] = SOCKS5_AUTH_VERSION;
-    frame[1] = (unsigned char) userlen;
-    memcpy(frame + 2, user, userlen);
-    frame[2 + userlen] = (unsigned char) passlen;
-    memcpy(frame + 3 + userlen, pass, passlen);
-    if (!socks5_write_all(st, frame, 3 + userlen + passlen))
-      return socks5_fail(msg, msgsize, "SOCKS5: write error");
-    if (!socks5_read_n(st, rep, sizeof(rep)))
-      return socks5_fail(msg, msgsize, "SOCKS5: no authentication reply");
-    if (rep[1] != 0x00)
-      return socks5_fail(msg, msgsize, "SOCKS5: authentication failed");
-    break;
-  case SOCKS5_METHOD_NOACCEPTABLE:
-    return socks5_fail(
-        msg, msgsize,
-        "SOCKS5: proxy accepts no authentication method we offer");
-  default:
-    return socks5_fail(msg, msgsize,
-                       "SOCKS5: proxy selected an unknown method");
-  }
-
-  /* CONNECT to the origin, by name */
-  frame[0] = SOCKS5_VERSION;
-  frame[1] = SOCKS5_CMD_CONNECT;
-  frame[2] = 0x00; // RSV
-  frame[3] = SOCKS5_ATYP_DOMAIN;
-  frame[4] = (unsigned char) hostlen;
-  memcpy(frame + 5, host, hostlen);
-  frame[5 + hostlen] = (unsigned char) (port >> 8);
-  frame[6 + hostlen] = (unsigned char) (port & 0xFF);
-  if (!socks5_write_all(st, frame, 7 + hostlen))
-    return socks5_fail(msg, msgsize, "SOCKS5: write error");
-
-  return socks5_read_reply(st, msg, msgsize);
-}
-
-/* Decode the proxy userinfo into the two RFC 1929 fields. Split on the first
-   colon of the still-escaped string, so a %3A stays inside the username. */
-static int socks5_credentials(httrackp *opt, const char *proxy_name, char *user,
-                              size_t user_size, size_t *userlen, char *pass,
-                              size_t pass_size, size_t *passlen, char *msg,
-                              size_t msgsize) {
-  const char *const a = jump_identification_const(proxy_name); // past the '@'
-  const char *const astart = jump_protocol_const(proxy_name);
-  char userinfo[1024];
-  char *colon;
-
-  if (a <= astart || (size_t) (a - astart) - 1 >= sizeof(userinfo))
-    return socks5_fail(msg, msgsize, "SOCKS5: credentials too long");
-  userinfo[0] = '\0';
-  strncatbuff(userinfo, astart, (int) (a - astart) - 1);
-  colon = strchr(userinfo, ':');
-  if (colon != NULL)
-    *colon++ = '\0';
-  strlcpybuff(
-      user, unescape_http(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), userinfo),
-      user_size);
-  strlcpybuff(pass,
-              colon != NULL ? unescape_http(OPT_GET_BUFF(opt),
-                                            OPT_GET_BUFF_SIZE(opt), colon)
-                            : "",
-              pass_size);
-  *userlen = strlen(user);
-  *passlen = strlen(pass);
-  // reject, never truncate: a clipped secret would authenticate as another one
-  if (*userlen > SOCKS5_MAXFIELD || *passlen > SOCKS5_MAXFIELD)
-    return socks5_fail(msg, msgsize, "SOCKS5: credentials too long");
-  if (*userlen == 0)
-    return socks5_fail(msg, msgsize, "SOCKS5: empty proxy username");
-  return 1;
-}
-
-static int socks5_handshake_stream(httrackp *opt, socks5_stream *st,
-                                   const char *adr, const char *proxy_name,
-                                   int ssl, char *msg, size_t msgsize) {
-  const char *const host = jump_identification_const(adr);
-  const char *const portsep = jump_toport_const(adr);
-  const size_t hostlen =
-      portsep != NULL ? (size_t) (portsep - host) : strlen(host);
-  // sized for the whole userinfo: decoding shrinks, so an over-long credential
-  // lands intact and is rejected below rather than silently clipped
-  char user[1024];
-  char pass[1024];
-  size_t userlen = 0, passlen = 0;
-  int want_auth = 0;
-  int port = ssl ? 443 : 80;
-  size_t i;
-
-  if (hostlen == 0 || hostlen > SOCKS5_MAXFIELD)
-    return socks5_fail(msg, msgsize, "SOCKS5: invalid origin host");
-  if (host[0] == '[') // ATYP=domain cannot carry an IPv6 literal
-    return socks5_fail(msg, msgsize,
-                       "SOCKS5: IPv6 literal origin is not supported");
-  for (i = 0; i < hostlen; i++) {
-    if ((unsigned char) host[i] < ' ')
-      return socks5_fail(msg, msgsize, "SOCKS5: invalid origin host");
-  }
-  if (portsep != NULL) {
-    int p = -1;
-
-    sscanf(portsep + 1, "%d", &p);
-    if (p <= 0 || p > 65535)
-      return socks5_fail(msg, msgsize, "SOCKS5: invalid origin port");
-    port = p;
-  }
-  if (link_has_authorization(proxy_name)) {
-    if (!socks5_credentials(opt, proxy_name, user, sizeof(user), &userlen, pass,
-                            sizeof(pass), &passlen, msg, msgsize))
-      return 0;
-    want_auth = 1;
-  }
-  return socks5_negotiate(st, host, hostlen, port, user, userlen, pass, passlen,
-                          want_auth, msg, msgsize);
-}
-
-int socks5_handshake(httrackp *opt, htsblk *retour, const char *adr,
-                     int timeout) {
-  socks5_stream st;
-#if HTS_USEOPENSSL
-  const int ssl = retour->ssl;
-#else
-  const int ssl = 0;
-#endif
-
-  if (retour->soc == INVALID_SOCKET)
-    return 0;
-  st.soc = retour->soc;
-  st.timeout = timeout;
-  st.io = NULL;
-  return socks5_handshake_stream(opt, &st, adr, retour->req.proxy.name, ssl,
-                                 retour->msg, sizeof(retour->msg));
-}
-
-int socks5_handshake_scripted(httrackp *opt, const char *adr,
-                              const char *proxy_name, socks5_test_io *io) {
-  socks5_stream st;
-
-  st.soc = INVALID_SOCKET;
-  st.timeout = 0;
-  st.io = io;
-  io->consumed = 0;
-  io->sent_len = 0;
-  io->msg[0] = '\0';
-  return socks5_handshake_stream(opt, &st, adr, proxy_name, 0, io->msg,
-                                 sizeof(io->msg));
-}

src/htsproxy.h

@@ -1,82 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* ------------------------------------------------------------ */
-/* File: Proxy tunneling (HTTP CONNECT, SOCKS5) .h              */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-#ifndef HTS_DEFPROXY
-#define HTS_DEFPROXY
-
-#include "htsglobal.h"
-
-/* Forward definitions */
-#ifndef HTS_DEF_FWSTRUCT_httrackp
-#define HTS_DEF_FWSTRUCT_httrackp
-typedef struct httrackp httrackp;
-#endif
-#ifndef HTS_DEF_FWSTRUCT_htsblk
-#define HTS_DEF_FWSTRUCT_htsblk
-typedef struct htsblk htsblk;
-#endif
-
-/* Open an HTTP CONNECT tunnel through the active proxy for an https request:
-   `retour->soc` must already be TCP-connected to the proxy, and `adr` is the
-   origin authority (url_adr, e.g. "https://host:port"). Sends the CONNECT
-   request (with Proxy-Authorization when the proxy carries credentials) and
-   reads the proxy's status line, so the caller's TLS handshake then runs
-   end-to-end with the origin. Blocks up to `timeout` seconds. Returns 1 on a
-   2xx tunnel, 0 on failure (retour->msg/statuscode set). */
-int http_proxy_tunnel(httrackp *opt, htsblk *retour, const char *adr,
-                      int timeout);
-
-/* SOCKS5 (RFC 1928, RFC 1929 auth) handshake on the raw proxy socket, before
-   any TLS: `retour->soc` must be TCP-connected to the proxy and `adr` is the
-   origin (url_adr). The origin name is sent verbatim (ATYP=domain), so the
-   proxy resolves it; a bracketed IPv6 literal origin is rejected. Blocks up to
-   `timeout` seconds. Returns 1 with the stream positioned on the first origin
-   byte, 0 on failure (retour->msg set). */
-int socks5_handshake(httrackp *opt, htsblk *retour, const char *adr,
-                     int timeout);
-
-/* Self-test hook (-#test=socks5): run the handshake against `reply`, a scripted
-   server byte stream, instead of a socket. `sent` captures the client frames,
-   `consumed` the reply bytes eaten (the frame-desync guard). */
-typedef struct socks5_test_io {
-  const unsigned char *reply;
-  size_t reply_len;
-  size_t consumed;
-  unsigned char sent[1024];
-  size_t sent_len;
-  char msg[256];
-} socks5_test_io;
-
-int socks5_handshake_scripted(httrackp *opt, const char *adr,
-                              const char *proxy_name, socks5_test_io *io);
-
-#endif

src/htssafe.h

@@ -456,6 +456,13 @@ static HTS_INLINE HTS_UNUSED const char *htsbuff_str(const htsbuff *b) {
   return b->buf;
 }
 
+/** True if 'count' records of >= 1 byte each fit in 'available' bytes; guards
+    an attacker-controlled count driving a large allocation. */
+static HTS_INLINE HTS_UNUSED hts_boolean hts_count_fits(size_t count,
+                                                        LLint available) {
+  return (available >= 0 && (LLint) count <= available) ? HTS_TRUE : HTS_FALSE;
+}
+
 /* Thin aliases over the libc allocator/memcpy (historical "t" suffix); no
    added bounds checking. freet() also NULLs the freed pointer and tolerates
    NULL. memcpybuff() despite the name is a raw memcpy: the caller owns the

src/htsselftest.c

@@ -54,18 +54,12 @@ Please visit our Website: http://www.httrack.com
 #include "htsftp.h"
 #include "htsmd5.h"
 #include "htssniff.h"
-#include "htscodec.h"
-#include "htsproxy.h"
 #if HTS_USEZLIB
 #include "htszlib.h"
 #endif
-#if HTS_USEZSTD
-#include <zstd.h>
-#endif
 #include "coucal/coucal.h"
 
 #include <ctype.h>
-#include <errno.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -73,9 +67,6 @@ Please visit our Website: http://www.httrack.com
 #ifndef _WIN32
 #include <sys/socket.h>
 #include <unistd.h>
-#else
-#include <io.h>       /* _get_osfhandle, for the sparse-file hint */
-#include <winioctl.h> /* FSCTL_SET_SPARSE */
 #endif
 
 /* very minimalistic internal tests */
@@ -749,71 +740,6 @@ static int st_filterdual(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* Length/work caps stop a hostile pattern stack-overflowing or hanging the
-   process (OSS-Fuzz 5060751291908096 / 5745936014573568). */
-static int st_filterbounds(httrackp *opt, int argc, char **argv) {
-  const size_t big = 100000; /* well past the length cap */
-  const size_t stars = 1023; /* pattern len 2047, under the length cap */
-  const size_t subjlen = 2048;
-  char *subj = malloct(big + 1);
-  char *pat = malloct(2 * stars + 2);
-  size_t steps = 0, maxsteps = 0, depth = 0, maxdepth = 0, i;
-
-  (void) opt;
-  (void) argc;
-  (void) argv;
-  memset(subj, 'a', big);
-  subj[big] = '\0';
-  /* '*' matches anything, but an over-length subject trips the length cap */
-  assertf(strjoker(subj, "*", NULL, NULL) == NULL);
-  assertf(strjokerfind(subj, "*") == NULL);
-  /* Star-heavy dead-end at the length cap: unbounded it runs ~1.26e9 memo-steps
-     (~6s). */
-  for (i = 0; i < stars; i++) {
-    pat[2 * i] = '*';
-    pat[2 * i + 1] = 'a';
-  }
-  pat[2 * stars] = 'b'; /* never matches an all-'a' subject */
-  pat[2 * stars + 1] = '\0';
-  subj[subjlen] = '\0';
-  /* Budget must fire and hold: steps > cap (deleting the budget zeroes the
-     counter that is the enforcement), steps < 10*cap (unbudgeted ~1.26e9). */
-  assertf(strjoker_bounds(subj, pat, &steps, &maxsteps, &depth, &maxdepth) ==
-          NULL);
-  assertf(steps > maxsteps && steps < 10 * maxsteps);
-  /* Depth caps the stack: uncapped this recurses 2046 frames, ~900KB (#574). */
-  assertf(depth == maxdepth);
-  assertf(strjokerfind(subj, pat) == NULL);
-  /* Pin the cap from below: 32 segments must still match, so a cap set so low
-     it would break real multi-segment filters (which use far fewer) fails. */
-  for (i = 0; i < 32; i++) {
-    pat[2 * i] = '*';
-    pat[2 * i + 1] = 'a';
-  }
-  pat[64] = '\0';
-  memset(subj, 'a', 32);
-  subj[32] = '\0';
-  assertf(strjoker(subj, pat, NULL, NULL) != NULL);
-  /* Same pin for the class-branch shape users actually write (*[..]), against a
-     long subject: it must match with room to spare under the work cap. */
-  {
-    const char *seg = "*[A-Z,a-z,0-9]";
-    const size_t seglen = strlen(seg), nseg = 16;
-
-    for (i = 0; i < (int) nseg; i++)
-      memcpy(pat + i * seglen, seg, seglen);
-    pat[nseg * seglen] = '\0';
-    memset(subj, 'a', 512);
-    subj[512] = '\0';
-    assertf(strjoker_bounds(subj, pat, &steps, &maxsteps, NULL, NULL) != NULL);
-    assertf(steps < maxsteps);
-  }
-  freet(pat);
-  freet(subj);
-  printf("filterbounds: OK\n");
-  return 0;
-}
-
 static int st_simplify(httrackp *opt, int argc, char **argv) {
   (void) opt;
   if (argc < 1) {
@@ -844,11 +770,7 @@ static int st_mime(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-static size_t st_decode_body(const char *arg, char *buf, size_t size);
-
 static int st_charset(httrackp *opt, int argc, char **argv) {
-  char buf[512];
-  size_t len;
   char *s;
 
   (void) opt;
@@ -856,8 +778,7 @@ static int st_charset(httrackp *opt, int argc, char **argv) {
     fprintf(stderr, "charset: needs a charset and a string\n");
     return 1;
   }
-  len = st_decode_body(argv[1], buf, sizeof(buf));
+  s = hts_convertStringToUTF8(argv[1], strlen(argv[1]), argv[0]);
-  s = hts_convertStringToUTF8(buf, len, argv[0]);
   if (s != NULL) {
     printf("%s\n", s);
     freet(s);
@@ -867,37 +788,7 @@ static int st_charset(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-static int st_metacharset(httrackp *opt, int argc, char **argv) {
-  char *s;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "metacharset: needs an html string\n");
-    return 1;
-  }
-  s = hts_getCharsetFromMeta(argv[0], strlen(argv[0]));
-  printf("%s\n", s != NULL ? s : "(none)");
-  freet(s);
-  return 0;
-}
-
-static int st_isutf8(httrackp *opt, int argc, char **argv) {
-  char buf[512];
-  size_t len;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "isutf8: needs a string\n");
-    return 1;
-  }
-  len = st_decode_body(argv[0], buf, sizeof(buf));
-  printf("%d\n", hts_isStringUTF8(buf, len) ? 1 : 0);
-  return 0;
-}
-
 static int st_idna_encode(httrackp *opt, int argc, char **argv) {
-  char buf[512];
-  size_t len;
   char *s;
 
   (void) opt;
@@ -905,8 +796,7 @@ static int st_idna_encode(httrackp *opt, int argc, char **argv) {
     fprintf(stderr, "idna-encode: needs a hostname\n");
     return 1;
   }
-  len = st_decode_body(argv[0], buf, sizeof(buf));
+  s = hts_convertStringUTF8ToIDNA(argv[0], strlen(argv[0]));
-  s = hts_convertStringUTF8ToIDNA(buf, len);
   if (s != NULL) {
     printf("%s\n", s);
     freet(s);
@@ -1068,7 +958,7 @@ static int st_hashtable(httrackp *opt, int argc, char **argv) {
 
   /* produce random patterns, or read from a file */
   if (sscanf(snum, "%lu", &count) != 1) {
-    const LLint size = fsize(snum);
+    const off_t size = fsize(snum);
     FILE *fp = fopen(snum, "rb");
     if (fp != NULL) {
       buff = malloct(size);
@@ -1168,10 +1058,7 @@ static int st_strsafe(httrackp *opt, int argc, char **argv) {
        comes from argv so its length is opaque to the compiler (no static
        -Wstringop-overflow, genuine runtime check). "overflow-buff" exercises
        htsbuff. */
-    /* Not sizeof(char*): on ILP32 a char[4] equals the pointer size, and the
+    char small[4];
-       MSVC array-vs-pointer heuristic (sizeof(A) != sizeof(char*)) then reads
-       it as a pointer and silently skips the bound. */
-    char small[6];
     const char *const src = (argc >= 2) ? argv[1] : "overflowing";
 
     if (strcmp(argv[0], "overflow-buff") == 0) {
@@ -1355,186 +1242,6 @@ static int st_identurl(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-static int st_proxyurl(httrackp *opt, int argc, char **argv) {
-  char BIGSTK name[HTS_URLMAXSIZE * 2];
-  int port = -1;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "proxyurl: needs a proxy argument\n");
-    return 1;
-  }
-  hts_parse_proxy(argv[0], name, sizeof(name), &port);
-  // host= is what the connect actually resolves (scheme + user:pass stripped)
-  printf("name=%s port=%d host=%s\n", name, port,
-         jump_identification_const(name));
-  return 0;
-}
-
-/* Scripted SOCKS5 server: no-auth method reply, then a success CONNECT reply
-   carrying the given ATYP address, then a sentinel origin byte the handshake
-   must leave unread (an off-by-one in the reply framing eats it). */
-static size_t socks5_reply(unsigned char *buf, unsigned char atyp,
-                           const unsigned char *addr, size_t addrlen) {
-  size_t n = 0;
-
-  buf[n++] = 0x05;
-  buf[n++] = 0x00; /* method: no authentication */
-  buf[n++] = 0x05;
-  buf[n++] = 0x00; /* REP: succeeded */
-  buf[n++] = 0x00;
-  buf[n++] = atyp;
-  memcpy(buf + n, addr, addrlen);
-  n += addrlen;
-  buf[n++] = 0x1f;
-  buf[n++] = 0x90; /* BND.PORT */
-  buf[n++] = 0xAA; /* sentinel */
-  return n;
-}
-
-#define SOCKS5_SENTINEL_LEFT(io, len) ((io).consumed == (len) - 1)
-
-static int st_socks5(httrackp *opt, int argc, char **argv) {
-  static const unsigned char v4[4] = {127, 0, 0, 1};
-  static const unsigned char v6[16] = {0};
-  static const unsigned char domain[6] = {5, 'p', 'r', 'o', 'x', 'y'};
-  const char *const proxy = "socks5://127.0.0.1";
-  unsigned char script[64];
-  socks5_test_io io;
-  size_t len;
-
-  (void) argc;
-  (void) argv;
-
-  /* each reply address type is drained exactly, sentinel untouched */
-  len = socks5_reply(script, 0x01, v4, sizeof(v4));
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 1);
-  assertf(SOCKS5_SENTINEL_LEFT(io, len));
-  /* the greeting offers no-auth only, and the origin goes out by name, port 80
-   */
-  assertf(io.sent_len == 3 + 7 + 11);
-  assertf(memcmp(io.sent, "\x05\x01\x00", 3) == 0);
-  assertf(memcmp(io.sent + 3, "\x05\x01\x00\x03\x0borigin.test\x00\x50", 18) ==
-          0);
-
-  len = socks5_reply(script, 0x04, v6, sizeof(v6));
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 1);
-  assertf(SOCKS5_SENTINEL_LEFT(io, len));
-
-  len = socks5_reply(script, 0x03, domain, sizeof(domain));
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 1);
-  assertf(SOCKS5_SENTINEL_LEFT(io, len));
-
-  /* an unknown address type has no known length: fail, never guess */
-  len = socks5_reply(script, 0x02, v4, sizeof(v4));
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 0);
-
-  /* truncated frames (here: no BND.PORT) fail instead of over-reading */
-  len = socks5_reply(script, 0x01, v4, sizeof(v4)) - 3;
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 0);
-
-  /* explicit origin port is encoded big-endian (8443 = 0x20fb) */
-  len = socks5_reply(script, 0x01, v4, sizeof(v4));
-  io.reply = script;
-  io.reply_len = len;
-  assertf(socks5_handshake_scripted(opt, "origin.test:8443", proxy, &io) == 1);
-  assertf(memcmp(io.sent + io.sent_len - 2, "\x20\xfb", 2) == 0);
-
-  /* credentials: split on the first colon of the escaped userinfo, so %3a stays
-     inside the username and a colon in the password is not a delimiter */
-  {
-    static const unsigned char auth_script[] = {
-        0x05, 0x02,             /* method: user/pass */
-        0x01, 0x00,             /* auth: success */
-        0x05, 0x00, 0x00, 0x01, /* REP: succeeded, ATYP ipv4 */
-        127,  0,    0,    1,    0x1f, 0x90, 0xAA};
-
-    io.reply = auth_script;
-    io.reply_len = sizeof(auth_script);
-    assertf(socks5_handshake_scripted(opt, "origin.test",
-                                      "socks5://us%3aer:p:ass@127.0.0.1",
-                                      &io) == 1);
-    assertf(SOCKS5_SENTINEL_LEFT(io, sizeof(auth_script)));
-    assertf(memcmp(io.sent, "\x05\x02\x00\x02", 4) == 0);
-    assertf(memcmp(io.sent + 4, "\x01\x05us:er\x05p:ass", 13) == 0);
-  }
-
-  /* a proxy demanding auth we cannot provide, and one refusing every method */
-  io.reply = (const unsigned char *) "\x05\x02";
-  io.reply_len = 2;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 0);
-  io.reply = (const unsigned char *) "\x05\xff";
-  io.reply_len = 2;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 0);
-
-  /* a refused CONNECT is an error, not a tunnel */
-  io.reply = (const unsigned char
-                  *) "\x05\x00\x05\x05\x00\x01\x7f\x00\x00\x01\x1f\x90";
-  io.reply_len = 12;
-  assertf(socks5_handshake_scripted(opt, "origin.test", proxy, &io) == 0);
-
-  /* over-long host or credentials are rejected before anything is sent */
-  {
-    char host[512];
-    char name[1024];
-    size_t i;
-
-    host[0] = '\0';
-    for (i = 0; i < 256; i++)
-      strcatbuff(host, "a");
-    io.reply = script;
-    io.reply_len = len;
-    assertf(socks5_handshake_scripted(opt, host, proxy, &io) == 0);
-    assertf(io.sent_len == 0);
-
-    strcpybuff(name, "socks5://user:");
-    for (i = 0; i < 256; i++)
-      strcatbuff(name, "p");
-    strcatbuff(name, "@127.0.0.1");
-    io.reply = script;
-    io.reply_len = len;
-    assertf(socks5_handshake_scripted(opt, "origin.test", name, &io) == 0);
-    assertf(io.sent_len == 0);
-  }
-
-  printf("socks5 self-test OK\n");
-  return 0;
-}
-
-/* Regression for the one-byte fil[] overflow: a 2047-byte hostless "?"-URL used
-   to abort in strncat_safe_ when the missing leading '/' pushed fil to 2048. */
-static int st_identabs(httrackp *opt, int argc, char **argv) {
-  lien_adrfil af;
-  const size_t len =
-      sizeof(af.fil) - 1; /* 2047: max URL the top guard admits */
-  char *url = malloct(len + 1);
-
-  (void) opt;
-  (void) argc;
-  (void) argv;
-  url[0] = '?';
-  memset(url + 1, 'a', len - 1);
-  url[len] = '\0';
-  assertf(ident_url_absolute(url, &af) == -1);
-  freet(url);
-  /* valid URLs still parse, so the guard is not over-rejecting */
-  assertf(ident_url_absolute("http://www.example.com/a/b/c.html?x=1", &af) ==
-          0);
-  assertf(ident_url_absolute("www.foo.com?bar=1", &af) == 0);
-  printf("identabs self-test OK\n");
-  return 0;
-}
-
 /* Extra args are key=value: adr= cdispo= statuscode= status= strip= urlhack=
    no-www= no-slash= no-query= n83= type=, plus repeatable prior=adr|fil|sav
    registering an already-crawled link (dedup/collision paths). */
@@ -1579,84 +1286,7 @@ static int st_headerlong(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* http_xfread1 must refuse an in-memory buffer whose size would exceed a 32-bit
+/* Decode a body argument ("hex:FFD8.." or literal text) into buf. */
-   index (hostile Content-Length or endless stream) rather than allocate it.
-   The guard returns before any socket read, so no real connection is needed. */
-static int st_xfread_limit(httrackp *opt, int argc, char **argv) {
-  htsblk r;
-
-  (void) opt;
-  (void) argc;
-  (void) argv;
-
-  // Content-Length just over 2 GiB.
-  memset(&r, 0, sizeof(r));
-  r.soc = INVALID_SOCKET;
-  r.totalsize = (LLint) INT32_MAX + 1;
-  printf("bylen: refused=%d adr=%s msg=%s\n",
-         http_xfread1(&r, 8192) == READ_ERROR, r.adr != NULL ? "alloc" : "null",
-         r.msg);
-  if (r.adr != NULL)
-    freet(r.adr);
-
-  // Unknown length, buffer already at the limit: the next read would exceed it.
-  memset(&r, 0, sizeof(r));
-  r.soc = INVALID_SOCKET;
-  r.totalsize = -1;
-  r.size = (LLint) INT32_MAX;
-  printf("bygrow: refused=%d adr=%s msg=%s\n",
-         http_xfread1(&r, 8192) == READ_ERROR, r.adr != NULL ? "alloc" : "null",
-         r.msg);
-  if (r.adr != NULL)
-    freet(r.adr);
-
-  // Exactly at the 2 GiB index (size + bufl == INT32_MAX): must also be
-  // refused, since the reallocs below add 1 (a `> INT32_MAX` check would let
-  // this through and overflow the int realloc size).
-  memset(&r, 0, sizeof(r));
-  r.soc = INVALID_SOCKET;
-  r.totalsize = -1;
-  r.size = (LLint) INT32_MAX - 8192;
-  http_xfread1(&r, 8192);
-  printf("boundary: msg=%s\n", r.msg);
-
-  // A legitimate small size must NOT be refused by the guard (the read then
-  // fails on the invalid socket, but the size-too-large msg must not be set).
-  memset(&r, 0, sizeof(r));
-  r.soc = INVALID_SOCKET;
-  r.totalsize = 1000;
-  http_xfread1(&r, 8192);
-  printf("accept: msg=%s\n", r.msg);
-  if (r.adr != NULL)
-    freet(r.adr);
-  return 0;
-}
-
-/* Parse a Content-Range header and print the sanitized triple. A hostile value
-   (negative or INT64 extreme) must clamp to 0 without signed-overflow UB. */
-static int st_crange(httrackp *opt, int argc, char **argv) {
-  int i;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "crange: needs at least one raw Content-Range line\n");
-    return 1;
-  }
-  for (i = 0; i < argc; i++) {
-    htsblk r;
-    char BIGSTK line[HTS_URLMAXSIZE * 2];
-
-    memset(&r, 0, sizeof(r));
-    strcpybuff(line, argv[i]);
-    treathead(NULL, "www.example.com", "/", &r, line);
-    printf("crange_start=" LLintP " crange_end=" LLintP " crange=" LLintP "\n",
-           (LLint) r.crange_start, (LLint) r.crange_end, (LLint) r.crange);
-  }
-  return 0;
-}
-
-/* Decode an argument ("hex:FFD8.." or literal text) into buf. Raw non-UTF-8
-   bytes cannot survive a Windows command line, so hostile inputs go as hex. */
 static size_t st_decode_body(const char *arg, char *buf, size_t size) {
   size_t n = 0;
 
@@ -1696,94 +1326,6 @@ static int st_sniff(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* fsize()/fsize_utf8()/fpsize() must report a size past 4GB: 32-bit wraps both
-   ways there (MSVC's off_t and struct _stat st_size are long, 32-bit even on
-   x64), and a size under 4GB would survive an *unsigned* 32-bit truncation. */
-static int st_fsize(httrackp *opt, int argc, char **argv) {
-  const LLint expected = 5 * 1024 * 1024 * 1024LL;
-  char BIGSTK path[HTS_URLMAXSIZE * 2];
-  char BIGSTK absent[HTS_URLMAXSIZE * 2];
-  /* both variants: only fsize() feeds the >2GB readers (file://, --list) */
-  const int width = (int) sizeof(fsize(""));
-  const int width_utf8 = (int) sizeof(fsize_utf8(""));
-  FILE *fp;
-  LLint got, got_utf8, gotp, gone;
-  int rc = 0;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "fsize: needs a directory\n");
-    return 1;
-  }
-  concat(path, sizeof(path), argv[0], "/sparse-5g.bin");
-  concat(absent, sizeof(absent), argv[0], "/no-such-file.bin");
-
-  /* sparse: seek past 4GB and write the last byte */
-  fp = FOPEN(path, "wb");
-  if (fp == NULL) {
-    fprintf(stderr, "fsize: cannot create '%s': %s\n", path, strerror(errno));
-    return 1;
-  }
-#ifdef _WIN32
-  {
-    /* NTFS allocates the hole unless asked not to; POSIX gives it for free.
-       Best-effort: a non-sparse file still measures the same, just costs 5GB.
-     */
-    HANDLE h = (HANDLE) _get_osfhandle(_fileno(fp));
-    DWORD ret;
-
-    if (h != INVALID_HANDLE_VALUE)
-      (void) DeviceIoControl(h, FSCTL_SET_SPARSE, NULL, 0, NULL, 0, &ret, NULL);
-  }
-#endif
-  if (fseeko(fp, expected - 1, SEEK_SET) != 0 || fputc(0, fp) == EOF ||
-      fclose(fp) != 0) {
-    fprintf(stderr, "fsize: cannot extend '%s' to " LLintP ": %s\n", path,
-            expected, strerror(errno));
-    UNLINK(path);
-    return 1;
-  }
-
-  got = fsize(path);
-  got_utf8 = fsize_utf8(path);
-  fp = FOPEN(path, "rb");
-  if (fp == NULL) {
-    fprintf(stderr, "fsize: cannot reopen '%s': %s\n", path, strerror(errno));
-    gotp = -1;
-  } else {
-    gotp = fpsize(fp);
-    fclose(fp);
-  }
-  UNLINK(path);
-  gone = fsize(absent); /* contract: -1, not 0, when absent */
-
-  printf("fsize: width=%d,%d size=" LLintP "," LLintP " psize=" LLintP
-         " absent=" LLintP "\n",
-         width, width_utf8, got, got_utf8, gotp, gone);
-  if (width != 8 || width_utf8 != 8) {
-    fprintf(stderr, "fsize: return types are %d/%d bytes, expected 8\n", width,
-            width_utf8);
-    rc = 1;
-  }
-  if (got != expected || got_utf8 != expected) {
-    fprintf(stderr,
-            "fsize: fsize/fsize_utf8 are " LLintP "/" LLintP
-            ", expected " LLintP "\n",
-            got, got_utf8, expected);
-    rc = 1;
-  }
-  if (gotp != expected) {
-    fprintf(stderr, "fsize: fpsize is " LLintP ", expected " LLintP "\n", gotp,
-            expected);
-    rc = 1;
-  }
-  if (gone != -1) {
-    fprintf(stderr, "fsize: absent file is " LLintP ", expected -1\n", gone);
-    rc = 1;
-  }
-  return rc;
-}
-
 static int st_savename(httrackp *opt, int argc, char **argv) {
   lien_adrfilsave afs;
   cache_back cache;
@@ -2113,30 +1655,9 @@ static int st_cookies(httrackp *opt, int argc, char **argv) {
     return 1;
   }
 
-  http_cookie_header(&cookie, dom, "/", hdr, sizeof(hdr));
+  http_cookie_header_selftest(&cookie, dom, "/", hdr, sizeof(hdr));
   if (strcmp(hdr, expected) != 0)
     err = 1;
-
-  /* A hostile over-long request host must not overflow domain[256] in
-     treathead's default-domain copy (that would abort the mirror). */
-  {
-    static t_cookie ck2;
-    htsblk r;
-    char host[600];
-
-    memset(&r, 0, sizeof(r));
-    memset(host, 'a', sizeof(host) - 1);
-    host[sizeof(host) - 1] = '\0';
-    ck2.max_len = (int) sizeof(ck2.data);
-    ck2.data[0] = '\0';
-    treathead(&ck2, host, "/", &r, "Set-Cookie: SID=1; path=/");
-    if (strnotempty(ck2.data)) // oversize-host cookie was not dropped
-      err = 1;
-    /* control: a normal host still yields a cookie through treathead */
-    treathead(&ck2, dom, "/", &r, "Set-Cookie: SID=1; path=/");
-    if (strstr(ck2.data, "SID") == NULL) // guard wrongly dropped a valid cookie
-      err = 1;
-  }
   if (strstr(hdr, "$Version") != NULL || strstr(hdr, "$Path") != NULL)
     err = 1;
   if (strstr(hdr, "junk") != NULL) // wrong-domain cookie leaked
@@ -2601,20 +2122,6 @@ static int ae_write_collision(const char *path, const unsigned char *src,
   freet(buf);
   return ok ? 0 : 1;
 }
-#endif
-
-/* Write src[0..len) to path as-is; 0 on success. */
-static int ae_write_raw(const char *path, const unsigned char *src,
-                        size_t len) {
-  FILE *const f = FOPEN(path, "wb");
-  int ok;
-
-  if (f == NULL)
-    return 1;
-  ok = fwrite(src, 1, len, f) == len;
-  fclose(f);
-  return ok ? 0 : 1;
-}
 
 /* Compare path's bytes to expect[0..len); 0 if equal. Streams (large files). */
 static int ae_check_decoded(const char *path, const unsigned char *expect,
@@ -2635,22 +2142,17 @@ static int ae_check_decoded(const char *path, const unsigned char *expect,
   fclose(f);
   return (off == len) ? 0 : 1;
 }
+#endif
 
 /* Accept-Encoding (#450): advertise gzip+deflate; both decode (hts_zunpack) */
 static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
-  const char *off = hts_acceptencoding(HTS_FALSE, HTS_TRUE);
+  const char *off = hts_acceptencoding(HTS_FALSE);
-  const char *on = hts_acceptencoding(HTS_TRUE, HTS_FALSE);
+  const char *on = hts_acceptencoding(HTS_TRUE);
-  const char *tls = hts_acceptencoding(HTS_TRUE, HTS_TRUE);
 
   (void) opt;
   assertf(strcmp(off, "identity") == 0);
   assertf(strstr(on, "gzip") != NULL);
   assertf(strstr(on, "deflate") != NULL); /* fails on the old gzip-only list */
-  /* br and zstd ride on TLS only, so a cleartext proxy can not be handed a
-     coding it may try to rewrite */
-  assertf(strstr(on, "br") == NULL && strstr(on, "zstd") == NULL);
-  assertf((strstr(tls, ", br") != NULL) == (HTS_USEBROTLI != 0));
-  assertf((strstr(tls, "zstd") != NULL) == (HTS_USEZSTD != 0));
 #if HTS_USEZLIB
   if (argc >= 1) {
     static const int windowBits[] = {16 + MAX_WBITS, MAX_WBITS, -MAX_WBITS};
@@ -2688,46 +2190,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
     assertf(ae_write_collision(inpath, body, 64) == 0);
     assertf(hts_zunpack(inpath, outpath) == 64);
     assertf(ae_check_decoded(outpath, body, 64) == 0);
-    /* Identity fallback (#47): a plain body mislabeled as compressed is kept
-       verbatim, small and multi-chunk (> one 8 KiB fread). */
-    assertf(ae_write_raw(inpath, small, slen) == 0);
-    assertf(hts_zunpack(inpath, outpath) == (int) slen);
-    assertf(ae_check_decoded(outpath, small, slen) == 0);
-    {
-      const size_t ilen = 16 * 1024;
-      unsigned char *idbody = malloct(ilen);
-
-      assertf(idbody != NULL);
-      for (i = 0; i < ilen; i++)
-        idbody[i] = small[i % slen];
-      assertf(ae_write_raw(inpath, idbody, ilen) == 0);
-      assertf(hts_zunpack(inpath, outpath) == (int) ilen);
-      assertf(ae_check_decoded(outpath, idbody, ilen) == 0);
-      freet(idbody);
-    }
-    /* Truncated gzip (CRC+ISIZE cut), zlib (ADLER32 cut) and raw deflate
-       must all still fail, not fall back to a verbatim copy. */
-    {
-      static const struct {
-        int wb;
-        size_t cut;
-      } tr[] = {{16 + MAX_WBITS, 8}, {MAX_WBITS, 4}, {-MAX_WBITS, 5}};
-
-      for (i = 0; i < sizeof(tr) / sizeof(tr[0]); i++) {
-        unsigned char z[512];
-        size_t zlen;
-        FILE *f;
-
-        assertf(ae_write_packed(inpath, tr[i].wb, small, slen) == 0);
-        f = FOPEN(inpath, "rb");
-        assertf(f != NULL);
-        zlen = fread(z, 1, sizeof(z), f);
-        fclose(f);
-        assertf(zlen > tr[i].cut && zlen < sizeof(z));
-        assertf(ae_write_raw(inpath, z, zlen - tr[i].cut) == 0);
-        assertf(hts_zunpack(inpath, outpath) < 0);
-      }
-    }
     freet(body);
   }
 #else
@@ -2738,115 +2200,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-#if HTS_USEBROTLI
-/* No brotli encoder is linked, so the coded bytes are canned: brotli quality 9
-   over cc_text, and over 4 MiB of 'A' (14 bytes, ~300000x). */
-static const unsigned char cc_br_text[] = {
-    0x1b, 0x43, 0x00, 0x00, 0x44, 0xdd, 0x96, 0xea, 0xe8, 0x22, 0xdd, 0x90,
-    0xa4, 0x1b, 0x8a, 0xf7, 0x47, 0x0e, 0xc2, 0xc5, 0x3d, 0x09, 0x1b, 0x70,
-    0xe0, 0x1e, 0x60, 0xa0, 0x8b, 0xcc, 0xbe, 0xcb, 0xb0, 0x31, 0x76, 0x9e,
-    0xcf, 0x6e, 0x41, 0xb5, 0xe8, 0x2e, 0x56, 0x78, 0x08, 0x1b, 0xfa, 0x08,
-    0x8a, 0x50, 0x83, 0x4e, 0x62, 0x7f, 0xbf, 0x05, 0xf2, 0x22, 0x8f, 0xdf,
-    0x28, 0xdc, 0x9f, 0xa9, 0x90, 0x50, 0x37, 0x62, 0x56, 0x4f, 0xa8};
-static const unsigned char cc_br_bomb[] = {0x9b, 0xff, 0xff, 0x3f, 0x00,
-                                           0x24, 0x82, 0xe2, 0xb1, 0x40,
-                                           0x72, 0xef, 0x7f, 0x00};
-#endif
-
-static const unsigned char cc_text[] =
-    "content codings: HTTrack decodes gzip, brotli and zstd bodies alike.";
-
-/* Content codings: br and zstd decode, junk tokens stay identity, a coding we
-   can not undo fails the fetch, and a bomb never lands on disk. */
-static int st_contentcodings(httrackp *opt, int argc, char **argv) {
-  const size_t tlen = sizeof(cc_text) - 1;
-  char inpath[HTS_URLMAXSIZE], outpath[HTS_URLMAXSIZE];
-
-  (void) opt;
-  assertf(hts_codec_parse("gzip") == HTS_CODEC_DEFLATE);
-  assertf(hts_codec_parse("x-deflate") == HTS_CODEC_DEFLATE);
-  assertf(hts_codec_parse("") == HTS_CODEC_IDENTITY);
-  assertf(hts_codec_parse("identity") == HTS_CODEC_IDENTITY);
-  /* servers do label plain bodies with junk; the page must survive that */
-  assertf(hts_codec_parse("utf-8") == HTS_CODEC_IDENTITY);
-  /* a real coding with no decoder here: fail, never save the coded bytes */
-  assertf(hts_codec_parse("compress") == HTS_CODEC_UNSUPPORTED);
-  assertf(hts_codec_parse("br") ==
-          (HTS_USEBROTLI ? HTS_CODEC_BROTLI : HTS_CODEC_UNSUPPORTED));
-  assertf(hts_codec_parse("zstd") ==
-          (HTS_USEZSTD ? HTS_CODEC_ZSTD : HTS_CODEC_UNSUPPORTED));
-  assertf(hts_codec_is_archive_ext(HTS_CODEC_DEFLATE, "tgz"));
-  assertf(!hts_codec_is_archive_ext(HTS_CODEC_DEFLATE, "html"));
-  assertf(hts_codec_is_archive_ext(HTS_CODEC_BROTLI, "br"));
-  assertf(hts_codec_is_archive_ext(HTS_CODEC_ZSTD, "zst"));
-  /* decoded-size budget: 4096x, floor 1 MiB, ceiling INT_MAX */
-  assertf(hts_codec_maxout(1) == 1024 * 1024);
-  assertf(hts_codec_maxout(1024) == 4096 * 1024);
-  assertf(hts_codec_maxout(1024 * 1024) == INT_MAX);
-
-  if (argc >= 1) {
-    snprintf(inpath, sizeof(inpath), "%s/cc-in", argv[0]);
-    snprintf(outpath, sizeof(outpath), "%s/cc-out", argv[0]);
-#if HTS_USEBROTLI
-    {
-      unsigned char head[16];
-
-      assertf(ae_write_raw(inpath, cc_br_text, sizeof(cc_br_text)) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_BROTLI, inpath, outpath) ==
-              (int) tlen);
-      assertf(ae_check_decoded(outpath, cc_text, tlen) == 0);
-      assertf(hts_codec_head(HTS_CODEC_BROTLI, cc_br_text, sizeof(cc_br_text),
-                             head, sizeof(head)) == sizeof(head));
-      assertf(memcmp(head, cc_text, sizeof(head)) == 0);
-      /* truncated: must fail, not fall back to a verbatim copy */
-      assertf(ae_write_raw(inpath, cc_br_text, sizeof(cc_br_text) - 4) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_BROTLI, inpath, outpath) < 0);
-      /* cc_br_bomb is a valid stream that expands to 4 MiB; the budget, not a
-         corrupt frame, is what must reject it. */
-      assertf((LLint) (4 * 1024 * 1024) >
-              hts_codec_maxout((LLint) sizeof(cc_br_bomb)));
-      assertf(ae_write_raw(inpath, cc_br_bomb, sizeof(cc_br_bomb)) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_BROTLI, inpath, outpath) < 0);
-    }
-#endif
-#if HTS_USEZSTD
-    {
-      const size_t bomblen = 4 * 1024 * 1024;
-      const size_t bound = ZSTD_compressBound(bomblen);
-      unsigned char *bomb = malloct(bomblen);
-      unsigned char *zbuf = malloct(bound);
-      unsigned char head[16];
-      size_t zlen;
-
-      assertf(bomb != NULL && zbuf != NULL);
-      zlen = ZSTD_compress(zbuf, bound, cc_text, tlen, 6);
-      assertf(!ZSTD_isError(zlen));
-      assertf(ae_write_raw(inpath, zbuf, zlen) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_ZSTD, inpath, outpath) == (int) tlen);
-      assertf(ae_check_decoded(outpath, cc_text, tlen) == 0);
-      assertf(hts_codec_head(HTS_CODEC_ZSTD, zbuf, zlen, head, sizeof(head)) ==
-              sizeof(head));
-      assertf(memcmp(head, cc_text, sizeof(head)) == 0);
-      assertf(ae_write_raw(inpath, zbuf, zlen - 4) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_ZSTD, inpath, outpath) < 0);
-      memset(bomb, 'A', bomblen);
-      zlen = ZSTD_compress(zbuf, bound, bomb, bomblen, 6);
-      assertf(!ZSTD_isError(zlen));
-      /* the fixture must really be past the budget, whatever the ratio is */
-      assertf((LLint) bomblen > hts_codec_maxout((LLint) zlen));
-      assertf(ae_write_raw(inpath, zbuf, zlen) == 0);
-      assertf(hts_codec_unpack(HTS_CODEC_ZSTD, inpath, outpath) < 0);
-      freet(bomb);
-      freet(zbuf);
-    }
-#endif
-    /* a coding we can not undo yields no file at all */
-    assertf(hts_codec_unpack(HTS_CODEC_UNSUPPORTED, inpath, outpath) < 0);
-  }
-  printf("contentcodings self-test OK\n");
-  return 0;
-}
-
 /* Each call parses `txt` under a fresh host, then checkrobots() for `path`. */
 static int rb_decide(robots_wizard *r, const char *txt, const char *path) {
   static int n = 0;
@@ -2930,43 +2283,11 @@ static int st_robots(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* Connected stream pair over loopback; Windows has no socketpair(). */
-static int st_socketpair(T_SOC sv[2]) {
-  struct sockaddr_in sa;
-  socklen_t len = sizeof(sa);
-  T_SOC srv, cli, acc;
-
-  memset(&sa, 0, sizeof(sa));
-  sa.sin_family = AF_INET;
-  sa.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-  if ((srv = (T_SOC) socket(AF_INET, SOCK_STREAM, 0)) == INVALID_SOCKET)
-    return -1;
-  if (bind(srv, (struct sockaddr *) &sa, sizeof(sa)) != 0 ||
-      listen(srv, 1) != 0 ||
-      getsockname(srv, (struct sockaddr *) &sa, &len) != 0) {
-    deletesoc(srv);
-    return -1;
-  }
-  if ((cli = (T_SOC) socket(AF_INET, SOCK_STREAM, 0)) == INVALID_SOCKET) {
-    deletesoc(srv);
-    return -1;
-  }
-  if (connect(cli, (struct sockaddr *) &sa, sizeof(sa)) != 0 ||
-      (acc = (T_SOC) accept(srv, NULL, NULL)) == INVALID_SOCKET) {
-    deletesoc(cli);
-    deletesoc(srv);
-    return -1;
-  }
-  deletesoc(srv);
-  sv[0] = acc;
-  sv[1] = cli;
-  return 0;
-}
-
 /* get_ftp_line must bound a hostile, CRLF-less reply into its internal
    1024-byte buffer; ASan turns the pre-fix overflow into an abort here. */
+#ifndef _WIN32
 static int st_ftpline(httrackp *opt, int argc, char **argv) {
-  T_SOC sv[2];
+  int sv[2];
   char line[2048];
   char flood[4096];
 
@@ -2974,19 +2295,19 @@ static int st_ftpline(httrackp *opt, int argc, char **argv) {
   (void) argc;
   (void) argv;
   memset(flood, 'x', sizeof(flood));
-  assertf(st_socketpair(sv) == 0);
+  assertf(socketpair(AF_UNIX, SOCK_STREAM, 0, sv) == 0);
-  // the 4102-byte reply fits the loopback send buffer, so no reader is needed
+  assertf(write(sv[1], "220 ", 4) == 4); // valid 3-digit code
-  assertf(send(sv[1], "220 ", 4, 0) == 4); // valid 3-digit code
+  assertf(write(sv[1], flood, sizeof(flood)) == (ssize_t) sizeof(flood));
-  assertf(send(sv[1], flood, (int) sizeof(flood), 0) == (int) sizeof(flood));
+  assertf(write(sv[1], "\r\n", 2) == 2); // end the line so we return
-  assertf(send(sv[1], "\r\n", 2, 0) == 2); // end the line so we return
+  close(sv[1]);
-  deletesoc(sv[1]);
   line[0] = '\0';
   get_ftp_line(sv[0], line, sizeof(line), 5);
-  deletesoc(sv[0]);
+  close(sv[0]);
   printf("ftp-line self-test OK (bounded %d-byte reply)\n",
          (int) sizeof(flood));
   return 0;
 }
+#endif
 
 /* ftp_split_userpass: well-formed split, plus a hostile over-long userinfo
    that pre-fix overran user[256]/pass[256]. */
@@ -3027,6 +2348,21 @@ static int st_ftpuser(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* hts_count_fits caps the .class constant-pool entry count to the file size,
+   rejecting the ~68 MB-per-file calloc DoS. */
+static int st_java(httrackp *opt, int argc, char **argv) {
+  (void) opt;
+  (void) argc;
+  (void) argv;
+  assertf(hts_count_fits(10, 1000) == HTS_TRUE);
+  assertf(hts_count_fits(0, 10) == HTS_TRUE);
+  assertf(hts_count_fits(65535, 10) == HTS_FALSE);
+  assertf(hts_count_fits(1, 0) == HTS_FALSE);
+  assertf(hts_count_fits(1, -1) == HTS_FALSE);
+  printf("java constant-pool cap self-test OK\n");
+  return 0;
+}
+
 /* ------------------------------------------------------------ */
 /* Registry: name -> handler, with a usage hint and a one-line description. */
 /* ------------------------------------------------------------ */
@@ -3048,8 +2384,6 @@ static const struct selftest_entry {
      "memoized vs unmemoized matcher differential", st_filtermemo},
     {"filterdual", "<string1> <string2> <filter>...",
      "merged two-form filter verdict (fa_strjoker_dual)", st_filterdual},
-    {"filterbounds", "", "matcher length/work caps reject hostile patterns",
-     st_filterbounds},
     {"simplify", "<path>", "collapse ./ and ../ in a path", st_simplify},
     {"stripquery", "", "--strip-query pattern/key stripping self-test",
      st_stripquery},
@@ -3058,11 +2392,8 @@ static const struct selftest_entry {
     {"redirect-samefile", "", "same-file redirect detection self-test (#159)",
      st_redirect_samefile},
     {"mime", "<filename>", "MIME type for a filename", st_mime},
-    {"charset", "<charset> <hex:..|string>",
+    {"charset", "<charset> <string>",
      "convert a string to UTF-8 from a charset", st_charset},
-    {"metacharset", "<html>", "extract the <meta> charset from an HTML page",
-     st_metacharset},
-    {"isutf8", "<hex:..|string>", "is the string valid UTF-8 (1/0)", st_isutf8},
     {"idna-encode", "<host>", "encode a hostname to IDNA/punycode",
      st_idna_encode},
     {"idna-decode", "<host>", "decode an IDNA/punycode hostname",
@@ -3080,26 +2411,15 @@ static const struct selftest_entry {
     {"resolve", "<link> <adr> <fil>", "resolve a link against an origin",
      st_resolve},
     {"identurl", "<url>", "split an absolute URL into (adr, fil)", st_identurl},
-    {"proxyurl", "<proxy-arg>", "parse a -P proxy URL into host/port",
-     st_proxyurl},
-    {"socks5", "", "SOCKS5 handshake framing and credential self-test",
-     st_socks5},
-    {"identabs", "", "ident_url_absolute one-byte fil[] overflow self-test",
-     st_identabs},
     {"header", "<raw-header-line> ...", "response header-line parsing",
      st_header},
     {"headerlong", "[header-name:]",
      "over-long header value must not overflow the parse scratch",
      st_headerlong},
-    {"crange", "<raw-content-range-line> ...",
-     "Content-Range parse integer safety", st_crange},
-    {"xfread-limit", "", "in-memory receive buffer size bound",
-     st_xfread_limit},
     {"savename", "<fil> <content-type> [key=value ...]",
      "local save-name for a URL", st_savename},
     {"sniff", "<content-type> <hex:..|text>", "MIME magic consistency",
      st_sniff},
-    {"fsize", "<dir>", "file size past the 2GB signed-32-bit wrap", st_fsize},
     {"cache", "<dir>", "cache read/write round-trip self-test", st_cache},
     {"cacheindex", "", "cache-index (.ndx) parse must stay in bounds",
      st_cacheindex},
@@ -3125,14 +2445,14 @@ static const struct selftest_entry {
     {"status", "", "HTTP status code -> reason phrase self-test", st_status},
     {"acceptencoding", "[dir]",
      "Accept-Encoding advertises gzip+deflate, both decode", st_acceptencoding},
-    {"contentcodings", "[dir]",
-     "brotli and zstd bodies decode; bombs and unknown codings are refused",
-     st_contentcodings},
     {"robots", "", "robots.txt RFC 9309 Allow/Disallow precedence self-test",
      st_robots},
+#ifndef _WIN32
     {"ftp-line", "", "get_ftp_line bounds a hostile FTP reply line",
      st_ftpline},
+#endif
     {"ftp-userpass", "", "ftp_split_userpass bounds URL userinfo", st_ftpuser},
+    {"java", "", "java .class constant-pool count cap self-test", st_java},
 };
 
 static void list_selftests(void) {