Add HTTRACK_DEBUG_RESOLVE and a deterministic connect-fallback test

Exercising the connect fallback needs a host that resolves to a dead address
first and a live one next, deterministically and offline. A true SYN
black-hole can't be simulated without root, but a refused address can.

HTTRACK_DEBUG_RESOLVE="host:ip[,ip...]" pins a host's resolution to a fixed
address list (curl --resolve style), reusing the PR1 resolver seam: an
addrinfo backend that synthesizes the listed addresses for the named host and
delegates other hosts to libc (copying into its own allocations so one
freeaddrinfo frees both). It is a debug/test hook, inert unless the env var is
set, and IPv6-build-only like the rest of the resolver list.

The new local crawl test binds the server to 127.0.0.1 and resolves a host to
127.0.0.2 (refused) then 127.0.0.1: the mirror only succeeds via the fallback.
A V6_SUPPORT substitution (mirroring HTTPS_SUPPORT) lets it skip on non-IPv6
builds.

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

.github/workflows/ci.yml

@@ -61,50 +61,6 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
-  # Reproduce the Debian buildds: they build in a minimal chroot with no
-  # python3, so the local-server tests must SKIP (exit 77), not fail. GitHub
-  # runners ship python3, so every other job hides this path; here we remove it
-  # before `make check`. This is the guard that would have caught the 3.49.10-1
-  # FTBFS (28_local-pause failed instead of skipping when python3 was absent).
-  buildd-no-python3:
-    name: build (no python3, Debian buildd)
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev
-
-      - name: Configure
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure
-
-      - name: Build
-        run: make -j"$(nproc)"
-
-      - name: Test without python3
-        run: |
-          set -euo pipefail
-          # Hide every python3* so `command -v python3` fails like it does in the
-          # buildd chroot; masking with /bin/false would still resolve.
-          sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
-            -exec mv {} {}.hidden \;
-          ! command -v python3
-          make check
-
-      - name: Print the test log on failure
-        if: failure()
-        run: cat tests/test-suite.log 2>/dev/null || true
-
   # Portability: build and test on macOS (Darwin/clang) on a native runner --
   # no VM. The tree has no __APPLE__ branches, so Darwin exercises the
   # generic-Unix path on a second libc and kernel. brew's openssl@3 is keg-only,
@@ -232,91 +188,6 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
-  # MemorySanitizer catches reads of uninitialized memory (#143's stack-garbage
-  # size filter) that ASan/UBSan miss. It flags any byte an uninstrumented lib
-  # wrote, so the job stays in our own code: offline self-tests only, no openssl
-  # (--disable-https), no zlib cache tests, static (the runtime is not in .so's).
-  msan:
-    name: msan (MemorySanitizer, clang)
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential clang autoconf automake libtool autoconf-archive \
-            zlib1g-dev
-
-      - name: Configure (MSan, static, no https)
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure CC=clang \
-            CFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-sanitize-recover=all -g -O1 -fno-omit-frame-pointer" \
-            LDFLAGS="-fsanitize=memory" \
-            --disable-https --disable-shared --enable-static
-
-      - name: Build
-        run: make -j"$(nproc)"
-
-      - name: Test (offline self-tests under MSan)
-        env:
-          MSAN_OPTIONS: abort_on_error=1:halt_on_error=1
-        run: |
-          set -euo pipefail
-          # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
-          # skipped here (uninstrumented libz floods MSan with false positives).
-          tests="$(cd tests && ls 01_engine-*.test | tr '\n' ' ')"
-          make check TESTS="$tests"
-
-      - name: Print the test log on failure
-        if: failure()
-        run: cat tests/test-suite.log 2>/dev/null || true
-
-  # libFuzzer smoke: build the fuzz/ harnesses over the pure hostile-input
-  # parsers and replay each seed corpus under ASan+UBSan+LeakSanitizer. Replay
-  # (not open-ended mutation) keeps CI deterministic -- it can't hit strjoker's
-  # catastrophic backtracking -- and pins the regression seeds for the bugs the
-  # fuzzers found. Deep discovery is a maintainer / OSS-Fuzz activity.
-  fuzz:
-    name: fuzz (libFuzzer corpus replay, clang)
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential clang autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev
-
-      - name: Configure (fuzzers, static)
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure CC=clang \
-            CFLAGS="-fsanitize=address,undefined -fno-sanitize-recover=all -g -O1 -fno-omit-frame-pointer" \
-            LDFLAGS="-fsanitize=address,undefined" \
-            --enable-fuzzers --disable-shared
-
-      - name: Build
-        run: make -j"$(nproc)"
-
-      - name: Replay corpora
-        env:
-          ASAN_OPTIONS: detect_leaks=1:abort_on_error=1:halt_on_error=1
-          UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
-        run: bash fuzz/run-fuzzers.sh fuzz check
-
   # Optional-dependency build: compile and test with HTTPS/OpenSSL disabled --
   # the configuration users on minimal systems build, and one libssl is not even
   # installed here so configure cannot silently re-enable it. The matrix above
@@ -361,42 +232,30 @@ jobs:
   deb:
     name: deb package (lintian)
     runs-on: ubuntu-24.04
-    # Build and gate inside Debian sid, the upload target. A Debian dpkg-deb
-    # produces archive-legal xz members (an Ubuntu host defaults to zstd, which
-    # the archive's lintian rejects), and sid's lintian carries the same
-    # data-driven checks (embedded-lib fingerprints and the like) the buildds and
-    # UDD apply -- so issues surface here instead of after upload.
-    container: debian:sid
     steps:
-      - name: Install packaging toolchain
-        run: |
-          set -euo pipefail
-          apt-get update
-          apt-get install -y --no-install-recommends \
-            ca-certificates git \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev \
-            debhelper devscripts lintian fakeroot
-
       - uses: actions/checkout@v6
         with:
           submodules: recursive
 
+      - name: Install packaging toolchain
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev \
+            debhelper devscripts lintian fakeroot
+
       # --unsigned: CI has no GPG key (also skips the release sig/checksums).
-      # mkdeb builds every package then runs the lintian gate (--fail-on=error,
-      # warning); debuild runs the packaged test pass.
+      # debuild builds every package, then lintian gates on errors.
       #
       # DEB_BUILD_OPTIONS trims work CI does not need (release builds via
       # mkdeb.sh are untouched): noautodbgsym drops the -dbgsym packages whose
       # LTO payloads are slow to compress and that CI never ships; parallel uses
-      # every core.
-      - name: Build and lint Debian packages
+      # every core. We let debuild run its test pass -- the only one now that
+      # mkdeb no longer runs its own -- so CI exercises the packaged tests.
+      - name: Build Debian packages
         run: |
-          set -euo pipefail
-          # The workspace volume is owned by the host runner uid, but the
-          # container runs as root, so mkdeb's git calls (superproject and the
-          # coucal submodule) trip "dubious ownership"; mark them all safe.
-          git config --global --add safe.directory "*"
           export DEB_BUILD_OPTIONS="noautodbgsym parallel=$(nproc)"
           bash tools/mkdeb.sh --unsigned --no-release-artifacts
 

.github/workflows/codeql.yml

@@ -1,57 +0,0 @@
-# CodeQL static analysis (C). The security-extended suite covers the classes
-# this codebase actually fights: overflows, tainted-size allocs, format bugs.
-name: CodeQL
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-  schedule:
-    # Weekly re-scan of master so new/updated queries land without a push.
-    - cron: "17 4 * * 1"
-
-permissions:
-  contents: read
-
-concurrency:
-  group: codeql-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  analyze:
-    name: analyze (c-cpp)
-    runs-on: ubuntu-24.04
-    permissions:
-      contents: read
-      # Upload findings to the repo's code-scanning dashboard.
-      security-events: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev
-
-      - uses: github/codeql-action/init@v4
-        with:
-          languages: c-cpp
-          build-mode: manual
-          queries: security-extended
-
-      # Manual build: CodeQL traces the compiler, so build exactly what ships.
-      - name: Build
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure
-          make -j"$(nproc)"
-
-      - uses: github/codeql-action/analyze@v4
-        with:
-          category: "/language:c-cpp"

.gitignore

@@ -34,12 +34,8 @@ Makefile
 *.so.*
 *.a
 
-# make dist output; dist/ holds httrack-gh-release staging artifacts.
+# make dist output.
 /httrack-*.tar.gz
-/dist/
 
 # Editor / autotools backup files.
 *~
-
-# Python bytecode (tests/local-server.py).
-__pycache__/

AGENTS.md

@@ -33,9 +33,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 - Be terse. Comment the why, in English; translate French comments you touch.
 - Strip AI tells from prose (em-dash overuse, rule-of-three, filler, vague
   attributions). Ref: Wikipedia "Signs of AI writing". Claude Code: `/humanizer`.
-- Behavior change → add a test. Fast path: a hidden `httrack -#test=NAME` engine
-  self-test (registry in `htsselftest.c`; `-#test` lists them) driven by a
-  `tests/NN_*.test`, over a slow crawl.
+- Behavior change → add a test. Fast path: a hidden `httrack -#N` debug
+  subcommand (`htscoremain.c`) driven by a `tests/NN_*.test`, over a slow crawl.
 
 ## Review your change adversarially (strongly suggested)
 Before pushing, and when reviewing others, don't skim for bugs:

CONTRIBUTING.md

@@ -39,10 +39,6 @@ Welcome, and nothing to disclose. Two rules:
 
 The sign-off covers AI-assisted code too.
 
-## Translations
-
-Interface strings live in [`lang/`](lang/). See [lang/README.md](lang/README.md) for the file format and how to add or update a language.
-
 ## Bugs
 
 Open an issue with the version, OS, command used, and expected vs actual result.

Makefile.am

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

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.11], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.9], [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 +29,10 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 3:3:0: 3.49.11 only adds enum values, macros and inline helpers to the
-# installed headers (no struct layout or exported signature changed vs
-# 3.49.10), so it stays soname .so.3; bump revision.
-# (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
-VERSION_INFO="3:3:0"
+# 3:1:0: 3.49.9 changed code but not the exported interface vs 3.49.8 (same 164
+# symbols, no struct-layout change), so bump revision only. (3:0:0 was the htsblk
+# mime-buffer widening, an ABI break that moved the soname .so.2 -> .so.3.)
+VERSION_INFO="3:1:0"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 
@@ -64,16 +63,6 @@ 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], ["$HTS_LIBHTSJAVA_NAME"],
-  [Versioned libhtsjava runtime name, derived from VERSION_INFO])
-
 ### Default CFLAGS
 DEFAULT_CFLAGS="-Wall -Wformat -Wformat-security \
 -Wmultichar -Wwrite-strings -Wcast-qual -Wcast-align \
@@ -102,8 +91,7 @@ AX_CHECK_COMPILE_FLAG([-Wignored-qualifiers], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -
 AX_CHECK_COMPILE_FLAG([-Werror=attribute-warning], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=attribute-warning"])
 AX_CHECK_COMPILE_FLAG([-Werror=user-defined-warnings], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -Werror=user-defined-warnings"])
 AX_CHECK_COMPILE_FLAG([-fstrict-aliasing -Wstrict-aliasing], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstrict-aliasing -Wstrict-aliasing"])
-AX_CHECK_COMPILE_FLAG([-fstack-protector-strong], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector-strong"],
-	[AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector"])])
+AX_CHECK_COMPILE_FLAG([-fstack-protector], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-protector"])
 AX_CHECK_COMPILE_FLAG([-fstack-clash-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fstack-clash-protection"])
 AX_CHECK_COMPILE_FLAG([-fcf-protection], [DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fcf-protection"])
 AX_CHECK_LINK_FLAG([-Wl,--discard-all], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,--discard-all"])
@@ -111,13 +99,6 @@ AX_CHECK_LINK_FLAG([-Wl,--no-undefined], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,
 AX_CHECK_LINK_FLAG([-Wl,-z,relro,-z,now], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,-z,relro,-z,now"])
 AX_CHECK_LINK_FLAG([-Wl,-z,noexecstack], [DEFAULT_LDFLAGS="$DEFAULT_LDFLAGS -Wl,-z,noexecstack"])
 
-# Fortify libc calls (=3, else =2) unless the toolchain predefines it; skip
-# sanitizer builds, whose interceptors want the unfortified calls.
-case "$CFLAGS" in
-*-fsanitize=*) ;;
-*) AX_ADD_FORTIFY_SOURCE ;;
-esac
-
 # Force libc back into DT_NEEDED for libraries that reach it only through
 # libhttrack (libhtsjava, the libtest callbacks), but only with a GNU-style
 # linker; Apple ld rejects these flags and links libSystem unconditionally.
@@ -318,37 +299,6 @@ AC_ARG_ENABLE([online-unit-tests],
 	])
 AC_SUBST(ONLINE_UNIT_TESTS,$online_unit_tests)
 
-## libFuzzer harnesses (fuzz/); requires clang
-AC_MSG_CHECKING(whether to build fuzzers)
-AC_ARG_ENABLE([fuzzers],
-	[AS_HELP_STRING([--enable-fuzzers],[Build libFuzzer harnesses in fuzz/ (requires clang) @<:@default=no@:>@])],
-	[
-	case "${enableval}" in
-	no|yes)
-		fuzzers=$enableval
-		AC_MSG_RESULT($enableval)
-		;;
-	*)
-		AC_MSG_ERROR(bad value for fuzzers, expected yes/no)
-		;;
-	esac
-	],
-	[
-	fuzzers=no
-	AC_MSG_RESULT(no)
-	])
-if test x"$fuzzers" = x"yes"; then
-	# Instrument the whole build for coverage; harnesses link -fsanitize=fuzzer.
-	AX_CHECK_COMPILE_FLAG([-fsanitize=fuzzer-no-link],
-		[DEFAULT_CFLAGS="$DEFAULT_CFLAGS -fsanitize=fuzzer-no-link"],
-		[AC_MSG_ERROR([--enable-fuzzers requires libFuzzer support (clang)])])
-	# clang's static sanitizer runtimes clash with -Wl,--no-undefined on the .so.
-	if test x"$enable_shared" != x"no"; then
-		AC_MSG_ERROR([--enable-fuzzers requires --disable-shared])
-	fi
-fi
-AM_CONDITIONAL([FUZZERS], [test x"$fuzzers" = x"yes"])
-
 # Final output
 AC_CONFIG_FILES([
 Makefile
@@ -360,6 +310,5 @@ lang/Makefile
 html/Makefile
 libtest/Makefile
 tests/Makefile
-fuzz/Makefile
 ])
 AC_OUTPUT

debian/changelog

@@ -1,37 +1,3 @@
-httrack (3.49.11-1) unstable; urgency=medium
-
-  * New upstream release: crawl correctness and security fixes (network-facing
-    buffer overflows, file-type detection, redirect handling) and modernized
-    web defaults; full list in history.txt.
-  * Add DEP-12 upstream metadata (#466).
-  * Bump debhelper compat to 14 (#466).
-  * Drop the redundant Priority field and update the NMU lintian override to
-    the current tag names (#466).
-
- -- Xavier Roche <xavier@debian.org>  Sun, 05 Jul 2026 00:03:18 +0200
-
-httrack (3.49.10-2) unstable; urgency=medium
-
-  * Fix FTBFS: tests/28_local-pause failed instead of skipping when python3 is
-    absent (the local-server tests need python3, which the buildds lack). Add
-    patches/skip-local-pause-test-without-python3.patch to guard the test on
-    python3 up front, like its siblings, so it skips cleanly.
-
- -- Xavier Roche <xavier@debian.org>  Sun, 28 Jun 2026 20:18:46 +0200
-
-httrack (3.49.10-1) unstable; urgency=medium
-
-  * New upstream release: new download-pacing and URL-handling options plus a
-    batch of crawl and robustness fixes (full list in history.txt).
-  * Rewrite debian/copyright in machine-readable DEP-5 format, crediting the
-    bundled minizip, md5 and coucal sources (#415).
-  * Lead the webhttrack browser dependency with chromium so httrack is not
-    dragged into the firefox-esr autoremoval cascade (#436).
-  * Override the embedded-library lint for the bundled minizip (#419).
-  * Bump Standards-Version to 4.7.4 (no changes required).
-
- -- Xavier Roche <xavier@debian.org>  Sun, 28 Jun 2026 14:01:53 +0200
-
 httrack (3.49.9-1) unstable; urgency=medium
 
   * New upstream release: Content-Type and file-type detection fixes (trust a

debian/control

@@ -1,8 +1,9 @@
 Source: httrack
 Section: web
+Priority: optional
 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
+Standards-Version: 4.7.0
+Build-Depends: debhelper-compat (= 13), 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
@@ -29,7 +30,7 @@ Description: Copy websites to your computer (Offline browser)
 Package: webhttrack
 Architecture: any
 Multi-Arch: foreign
-Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, chromium | firefox-esr | www-browser
+Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, firefox-esr | chromium | www-browser
 Replaces: webhttrack-common (<< 3.43.9-2)
 Breaks: webhttrack-common (<< 3.43.9-2)
 Suggests: httrack, httrack-doc

debian/libhttrack3.lintian-overrides

@@ -1,8 +1,3 @@
 # The shared libraries ship without a versioned symbols control file (ABI is
 # tracked via the SONAME plus a >= upstream-version dependency, see debian/rules).
 libhttrack3: no-symbols-control-file usr/lib/*
-
-# Bundled, locally patched minizip (src/minizip): it adds a zipFlush() API the
-# system libminizip lacks (htscache.c flushes the cache .zip so an interrupted
-# crawl leaves a valid archive), plus Android/old-zlib portability fixes.
-libhttrack3: embedded-library *libminizip*

debian/proxytrack.lintian-overrides

@@ -1,3 +0,0 @@
-# Statically linked against httrack's bundled, patched minizip (see src/minizip
-# and libhttrack3's override): the zipFlush() API is absent from the system one.
-proxytrack: embedded-library *libminizip*

debian/source/lintian-overrides

@@ -1,6 +1,4 @@
-# Maintainer uploads sign the changelog as xavier@debian.org while the control
-# Maintainer is roche@httrack.com; lintian reads the address mismatch as an NMU.
-httrack source: no-nmu-in-changelog
+httrack source: changelog-should-mention-nmu
 httrack source: source-nmu-has-incorrect-version-number
 
 # The bundled HTML pages are the genuine upstream documentation taken from

debian/upstream/metadata

@@ -1,6 +0,0 @@
----
-Repository: https://github.com/xroche/httrack.git
-Repository-Browse: https://github.com/xroche/httrack
-Bug-Database: https://github.com/xroche/httrack/issues
-Bug-Submit: https://github.com/xroche/httrack/issues/new
-Contact: Xavier Roche <roche@httrack.com>

fuzz/Makefile.am

@@ -1,44 +0,0 @@
-# libFuzzer harnesses; built only with --enable-fuzzers (requires clang).
-if FUZZERS
-noinst_PROGRAMS = fuzz-charset fuzz-meta fuzz-idna fuzz-entities \
-	fuzz-unescape fuzz-filters fuzz-url fuzz-header fuzz-cachendx
-endif
-
-AM_CPPFLAGS = \
-	@DEFAULT_CFLAGS@ \
-	@THREADS_CFLAGS@ \
-	@V6_FLAG@ \
-	@LFS_FLAG@ \
-	-I$(top_srcdir)/src \
-	-I$(top_srcdir)/src/coucal
-
-# Static-link libhttrack.la: the internal symbols are hidden in the .so.
-AM_LDFLAGS = @DEFAULT_LDFLAGS@ -fsanitize=fuzzer -static-libtool-libs
-LDADD = $(top_builddir)/src/libhttrack.la $(THREADS_LIBS)
-
-fuzz_charset_SOURCES = fuzz-charset.c fuzz.h
-fuzz_meta_SOURCES = fuzz-meta.c fuzz.h
-fuzz_idna_SOURCES = fuzz-idna.c fuzz.h
-fuzz_entities_SOURCES = fuzz-entities.c fuzz.h
-fuzz_unescape_SOURCES = fuzz-unescape.c fuzz.h
-fuzz_filters_SOURCES = fuzz-filters.c fuzz.h
-fuzz_url_SOURCES = fuzz-url.c fuzz.h
-fuzz_header_SOURCES = fuzz-header.c fuzz.h
-fuzz_cachendx_SOURCES = fuzz-cachendx.c fuzz.h
-
-# List corpus files explicitly: automake does not expand EXTRA_DIST globs.
-EXTRA_DIST = README.md run-fuzzers.sh \
-	corpus/charset/utf8.txt corpus/charset/latin1.txt corpus/charset/sjis.txt \
-	corpus/meta/meta-charset.html corpus/meta/meta-http-equiv.html \
-	corpus/idna/idna.txt corpus/idna/unicode.txt \
-	corpus/idna/regress-multilabel-leak.txt \
-	corpus/entities/entities.txt \
-	corpus/unescape/percent.txt \
-	corpus/filters/filter.bin corpus/filters/filter-size.bin \
-	corpus/filters/regress-empty-subject-unique.bin \
-	corpus/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

fuzz/README.md

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

fuzz/corpus/cachendx/new-format.txt

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

fuzz/corpus/cachendx/old-format.txt

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

fuzz/corpus/cachendx/regress-overadvance.bin

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

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

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

fuzz/corpus/charset/latin1.txt

@@ -1 +0,0 @@
-
café naďve ¤

fuzz/corpus/charset/sjis.txt

@@ -1 +0,0 @@
-コンピュータ

fuzz/corpus/entities/entities.txt

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

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

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

fuzz/corpus/header/full-response.txt

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

fuzz/corpus/header/redirect.txt

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

fuzz/corpus/idna/idna.txt

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

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

@@ -1 +0,0 @@
-büchev.例å­bücheple

fuzz/corpus/idna/unicode.txt

@@ -1 +0,0 @@
-bücher.例子.example

fuzz/corpus/meta/meta-charset.html

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

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

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

fuzz/corpus/unescape/percent.txt

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

fuzz/corpus/url/http-url.txt

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

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

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

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

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

fuzz/corpus/url/relative-path.txt

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

fuzz/fuzz-cachendx.c

@@ -1,65 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the cache-index (.ndx) parser: a corrupt or truncated index must not
-   walk the length-prefixed cache_brstr/cache_binput scan past the buffer.
-   Mirrors the -#C cache-listing scan (htscoremain.c). */
-#include "fuzz.h"
-#include "htscache.h"
-#include "htslib.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  const char *const end = buf + size;
-  char firstline[256];
-  char *a = buf;
-
-  /* header: two length-prefixed fields (version, last-modified) */
-  a += cache_brstr(a, firstline, sizeof(firstline));
-  a += cache_brstr(a, firstline, sizeof(firstline));
-
-  /* body: newline-delimited host/file/position triples; the length-prefixed
-     scan must stay inside the buffer */
-  while (a != NULL && a < end) {
-    char BIGSTK line[HTS_URLMAXSIZE * 2];
-    char linepos[256];
-    int pos;
-
-    a = strchr(a + 1, '\n');
-    if (a == NULL)
-      break;
-    a++;
-    a += cache_binput(a, end, line, HTS_URLMAXSIZE);
-    a += cache_binput(a, end, line + strlen(line), HTS_URLMAXSIZE);
-    a += cache_binput(a, end, linepos, 200);
-    sscanf(linepos, "%d", &pos);
-    (void) pos;
-  }
-
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-charset.c

@@ -1,84 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the charset codecs: hts_convertStringToUTF8/FromUTF8 and the
-   UTF-8/UCS4 primitives (htscharset.c). First input byte picks the charset. */
-#include "fuzz.h"
-#include "htscharset.h"
-
-static const char *const charsets[] = {
-    "utf-8",    "iso-8859-1", "iso-8859-2", "iso-8859-15", "windows-1252",
-    "us-ascii", "shift_jis",  "euc-jp",     "iso-2022-jp", "gb2312",
-    "big5",     "euc-kr",     "koi8-r",     "utf-16",      "unknown-charset",
-};
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  const char *charset;
-  char *s;
-
-  if (size == 0)
-    return 0;
-  charset = charsets[data[0] % (sizeof(charsets) / sizeof(charsets[0]))];
-  data++, size--;
-  s = fuzz_strdup(data, size);
-
-  {
-    char *utf8 = hts_convertStringToUTF8(s, size, charset);
-    freet(utf8);
-  }
-  {
-    char *enc = hts_convertStringFromUTF8(s, size, charset);
-    freet(enc);
-  }
-  {
-    size_t nChars = 0;
-    hts_UCS4 *ucs = hts_convertUTF8StringToUCS4(s, size, &nChars);
-
-    if (ucs != NULL) {
-      char *back = hts_convertUCS4StringToUTF8(ucs, nChars);
-      freet(back);
-      freet(ucs);
-    }
-  }
-  {
-    size_t i = 0;
-
-    while (i < size) {
-      hts_UCS4 uc = 0;
-      const size_t nr = hts_readUTF8(s + i, size - i, &uc);
-      char out[8];
-
-      if (nr == 0)
-        break;
-      hts_writeUTF8(uc, out, sizeof(out));
-      i += nr;
-    }
-  }
-
-  freet(s);
-  return 0;
-}

fuzz/fuzz-entities.c

@@ -1,51 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the HTML entity decoder (htsencoding.c). First input byte picks the
-   destination size, so truncation bounds get exercised too. */
-#include "fuzz.h"
-#include "htsencoding.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static const size_t dsizes[] = {1, 2, 8, 64, 4096};
-  size_t dsize;
-  char *src, *dest;
-
-  if (size == 0)
-    return 0;
-  dsize = dsizes[data[0] % (sizeof(dsizes) / sizeof(dsizes[0]))];
-  data++, size--;
-  src = fuzz_strdup(data, size);
-  dest = malloct(dsize);
-
-  (void) hts_unescapeEntities(src, dest, dsize);
-  (void) hts_unescapeEntitiesWithCharset(src, dest, dsize, "iso-8859-1");
-
-  freet(dest);
-  freet(src);
-  return 0;
-}

fuzz/fuzz-filters.c

@@ -1,65 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the wildcard filter matcher (htsfilters.c; #148 bracket-range OOB was
-   here). Input splits on the first NUL: pattern, then subject string. */
-#include "fuzz.h"
-#include "htsfilters.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  const char *joker = buf;
-  const uint8_t *sep = memchr(data, '\0', size);
-  /* subject in its own allocation so ASan bounds it apart from the pattern */
-  char *nom = sep != NULL ? fuzz_strdup(sep + 1, (data + size) - (sep + 1))
-                          : fuzz_strdup(data + size, 0);
-
-  (void) strjoker(nom, joker, NULL, NULL);
-  {
-    LLint sz = (LLint) size;
-    int size_flag = 0;
-
-    (void) strjoker(nom, joker, &sz, &size_flag);
-  }
-  (void) strjokerfind(nom, joker);
-  {
-    char *filter = malloct(strlen(joker) + 2);
-    char *filters[1];
-    LLint sz = (LLint) size;
-    int size_flag = 0, depth = 0;
-
-    filter[0] = '-';
-    memcpy(filter + 1, joker, strlen(joker) + 1);
-    filters[0] = filter;
-    (void) fa_strjoker(0, filters, 1, nom, &sz, &size_flag, &depth);
-    freet(filter);
-  }
-
-  freet(nom);
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-header.c

@@ -1,70 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the HTTP response-header parser (htslib.c): treatfirstline on the
-   status line, treathead on each following header. Both consume raw bytes
-   off the wire and copy fields into fixed htsblk buffers; treathead also
-   mutates its line in place and drives cookie parsing. */
-#include "fuzz.h"
-#include "htslib.h"
-#include "htsbauth.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *buf = fuzz_strdup(data, size);
-  htsblk r;
-  t_cookie *cookie = calloct(1, sizeof(*cookie));
-  char *line = malloct(size + 1);
-  char *p = buf;
-  int first = 1;
-
-  memset(&r, 0, sizeof(r));
-  cookie->max_len = (int) sizeof(cookie->data);
-  r.location = malloct(HTS_URLMAXSIZE * 2);
-  r.location[0] = '\0';
-
-  /* feed one header line at a time, as the receive loop does */
-  while (p != NULL && *p != '\0') {
-    char *nl = strchr(p, '\n');
-    size_t n = (nl != NULL) ? (size_t) (nl - p) : strlen(p);
-
-    memcpy(line, p, n);
-    line[n] = '\0';
-    if (first) {
-      treatfirstline(&r, line);
-      first = 0;
-    } else {
-      treathead(cookie, "www.example.com", "/", &r, line);
-    }
-    p = (nl != NULL) ? nl + 1 : NULL;
-  }
-
-  freet(r.location);
-  freet(line);
-  freet(cookie);
-  freet(buf);
-  return 0;
-}

fuzz/fuzz-idna.c

@@ -1,47 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the IDNA/punycode codec (htscharset.c, CVE-prone lineage). */
-#include "fuzz.h"
-#include "htscharset.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *s = fuzz_strdup(data, size);
-
-  {
-    char *idna = hts_convertStringUTF8ToIDNA(s, size);
-    freet(idna);
-  }
-  {
-    char *utf8 = hts_convertStringIDNAToUTF8(s, size);
-    freet(utf8);
-  }
-  (void) hts_isStringIDNA(s, size);
-
-  freet(s);
-  return 0;
-}

fuzz/fuzz-meta.c

@@ -1,40 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz hts_getCharsetFromMeta (htscharset.c): scans raw attacker HTML for a
-   <meta> charset declaration. */
-#include "fuzz.h"
-#include "htscharset.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *html = fuzz_strdup(data, size);
-  char *charset = hts_getCharsetFromMeta(html, size);
-
-  freet(charset);
-  freet(html);
-  return 0;
-}

fuzz/fuzz-unescape.c

@@ -1,53 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the URL percent-decoders (htslib.c). First input byte picks the
-   output buffer size, so the bounded-copy contract is exercised. */
-#include "fuzz.h"
-#include "httrack-library.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  static const size_t bsizes[] = {1, 2, 16, 256, 8192};
-  size_t bsize;
-  char *s, *catbuff;
-
-  if (size == 0)
-    return 0;
-  bsize = bsizes[data[0] % (sizeof(bsizes) / sizeof(bsizes[0]))];
-  data++, size--;
-  s = fuzz_strdup(data, size);
-  catbuff = malloct(bsize);
-
-  (void) unescape_http(catbuff, bsize, s);
-  (void) unescape_http_unharm(catbuff, bsize, s, 0);
-  (void) unescape_http_unharm(catbuff, bsize, s, 1);
-  unescape_amp(s);
-
-  freet(catbuff);
-  freet(s);
-  return 0;
-}

fuzz/fuzz-url.c

@@ -1,49 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Fuzz the URL splitter and path normalizer (htslib.c): ident_url_absolute
-   is the first parser to touch a raw URL; fil_simplifie collapses ./ and ../
-   in place. */
-#include "fuzz.h"
-#include "htscore.h"
-#include "htslib.h"
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
-  char *s = fuzz_strdup(data, size);
-  lien_adrfil *af = calloct(1, sizeof(*af));
-  /* fil_simplifie rewrites in place and may grow an empty path to "./" */
-  char *path = malloct(size + 3);
-
-  (void) ident_url_absolute(s, af);
-  memcpy(path, s, size + 1);
-  fil_simplifie(path);
-
-  freet(path);
-  freet(af);
-  freet(s);
-  return 0;
-}

fuzz/fuzz.h

@@ -1,51 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* Shared helpers for the libFuzzer harnesses. */
-#ifndef FUZZ_H
-#define FUZZ_H
-
-#define HTS_INTERNAL_BYTECODE
-
-#include <stddef.h>
-#include <stdint.h>
-#include <string.h>
-
-#include "htsbase.h"
-
-/* Heap NUL-terminated copy of the fuzzer input, so ASan bounds every read. */
-static char *fuzz_strdup(const uint8_t *data, size_t size) {
-  char *s = malloct(size + 1);
-
-  memcpy(s, data, size);
-  s[size] = '\0';
-  return s;
-}
-
-int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
-
-#endif

fuzz/run-fuzzers.sh

@@ -1,41 +0,0 @@
-#!/bin/bash
-# Drive every built harness against its seed corpus.
-#   run-fuzzers.sh <build-fuzz-dir> check       deterministic replay (CI smoke)
-#   run-fuzzers.sh <build-fuzz-dir> [seconds]   timed mutation run (discovery)
-# Replay is crash/leak-only and never mutates, so it can't hit strjoker's
-# catastrophic backtracking; the timed mode can, hence the per-unit -timeout.
-set -euo pipefail
-
-srcdir=$(cd "$(dirname "$0")" && pwd)
-bld=${1:?usage: run-fuzzers.sh <build-fuzz-dir> [check|seconds]}
-mode=${2:-20}
-
-status=0
-for f in "$bld"/fuzz-*; do
-    if [ ! -f "$f" ] || [ ! -r "$f" ]; then continue; fi
-    case "$f" in *.o | *.c | *.dSYM) continue ;; esac
-    name=$(basename "$f")
-    corpus="$srcdir/corpus/${name#fuzz-}"
-    if [ "$mode" = "check" ]; then
-        echo "=== $name (replay) ==="
-        [ -d "$corpus" ] || continue
-        if ! "$f" -runs=0 -timeout=25 -rss_limit_mb=2048 "$corpus"; then
-            echo "*** $name FAILED on its corpus" >&2
-            status=1
-        fi
-        continue
-    fi
-    work=$(mktemp -d)
-    args=("$work")
-    [ -d "$corpus" ] && args+=("$corpus")
-    echo "=== $name (${mode}s) ==="
-    if ! "$f" -max_total_time="$mode" -timeout=25 -rss_limit_mb=2048 \
-        -artifact_prefix="$work/" -print_final_stats=1 "${args[@]}"; then
-        echo "*** $name FAILED; artifacts:" >&2
-        ls -l "$work" >&2
-        status=1
-    else
-        rm -rf "$work"
-    fi
-done
-exit $status

history.txt

@@ -4,42 +4,7 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
-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)
-+ New: follow <source> and <track> media elements as embedded links (#451)
-+ New: added modern web MIME types to the type/extension table (#448)
-+ Fixed: enforce the -E time limit during a slow transfer instead of only between files (#481)
-+ Fixed: sniff the leading bytes of a download so a misdeclared Content-Type no longer renames a correct URL extension
-+ Fixed: fast transfers could be saved under their temporary .delayed placeholder name (#5, #107)
-+ Fixed: follow a redirect that maps to the same saved file instead of writing a self-pointing stub (#159)
-+ Fixed: several network-facing buffer overflows in the FTP, Java and HTML parsers
-+ Fixed: the htsjava plugin could not be loaded (hidden entry points, stale library name)
-+ Fixed: HTML-escape truncation and a cache-buffer leak in the parser
-+ Changed: modernized the default User-Agent to an honest HTTrack identifier (#449)
-+ Changed: decode the full WHATWG set of HTML named character references (#443)
-+ Changed: refreshed stale HTTP status, proxy-port and TLS-floor constants (#453)
-+ Changed: multiple internal hardening, build, test and CI improvements
-
-3.49-10
-+ New: --cookies-file to preload a Netscape cookies.txt before crawling (#215)
-+ New: --pause to space out file downloads by a random delay (#185)
-+ New: --strip-query to drop selected query keys from the dedup naming (#112)
-+ Changed: split the -%u URL hacks into independent --keep-www-prefix, --keep-double-slashes and --keep-query-order toggles (#271)
-+ Fixed: follow a redirect Location after dropping its #fragment, instead of requesting the fragment and polluting the saved name (#204)
-+ Fixed: escaped brackets inside a *[...] filter character class (#148)
-+ Fixed: honor the server's Content-Range when resuming a partial download, instead of appending overlapping bytes (#198)
-+ Fixed: abort the download as soon as the response type is excluded by -mime:, instead of fetching then discarding the body (#58)
-+ Fixed: keep size-based filter rules neutral until the file size is known (#143)
-+ Fixed: stop the mirror with a clean fatal error on a cache write failure, instead of crashing (#174, #219)
-+ Fixed: stop the 412/416 partial re-get loop on --continue and --update (#206)
-+ Fixed: keep an unrecognized URL tail instead of mangling it to .html (#115)
-+ Fixed: honor --tolerant (-%B) on a broken Content-Length, and fix an out-of-bounds read it exposed (#32, #41)
-+ Fixed: fall back to the next resolved address when a connection fails or stalls, instead of hanging on a dead IPv6 address
-+ Fixed: report why a -%L URL list could not be loaded (#49)
-+ Changed: multiple internal hardening, build and CI improvements
-
-.49-9
+3.49-9
 + Fixed: file-type detection from the Content-Type header: trust a declared type over a binary URL extension, honor --assume under the delayed type check, and keep a known extension against a bogus or empty Content-Type (#267, #29, #56)
 + Fixed: an uninitialized-buffer read when the Content-Type is empty (#411)
 + Fixed: restored C++ source-compatibility of the installed headers so reverse dependencies (httraqt) build again (#413)

html/filters.html

@@ -247,7 +247,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
         <td>the \ character</td>
       </tr>
       <tr>
-        <td nowrap><tt>*[\[,\]]</tt></td>
+        <td nowrap><tt>*[\[\]]</tt></td>
         <td>the [ or ] character</td>
       </tr>
       <tr>

lang/English.txt

@@ -295,7 +295,7 @@ Max Depth
 Maximum external depth:
 Maximum external depth:
 Filters (refuse/accept links) :
-Filters (refuse/accept links):
+Filters (refuse/accept links) :
 Paths
 Paths
 Save prefs

lang/README.md

@@ -1,37 +0,0 @@
-# Translating HTTrack
-
-Interface strings live here, one `.txt` file per language. `English.txt` is the reference: every other file maps each English string to its translation.
-
-## File format
-
-Plain text, entries in consecutive pairs of lines:
-
-```
-<English string>
-<translation>
-```
-
-The first line of a pair is the lookup key and must stay identical to the one in `English.txt`; translate only the second line. Missing entries fall back to the English text at runtime, so a partial translation works.
-
-Preserve any `\r\n`, `\t` and `printf` placeholders (`%s`, `%d`, ...) in the translation.
-
-A few `LANGUAGE_*` entries at the top describe the file itself:
-
-| Key | Meaning |
-| --- | --- |
-| `LANGUAGE_NAME` | Name shown in the language picker, in its own language (`Deutsch`, not `German`) |
-| `LANGUAGE_ISO` | ISO 639 code, with region if needed (`de`, `pt_BR`) |
-| `LANGUAGE_CHARSET` | Encoding the file is saved in (`ISO-8859-1`, `windows-1251`, `UTF-8`, ...) |
-| `LANGUAGE_AUTHOR` | Your name and contact |
-| `LANGUAGE_WINDOWSID` | Windows locale name used by WinHTTrack (`German (Standard)`) |
-
-Save the file in exactly its declared `LANGUAGE_CHARSET`; an editor that rewrites it as UTF-8 will corrupt the non-ASCII bytes.
-
-## Adding or updating a language
-
-1. Copy `English.txt` to `<Language>.txt`, or edit the existing file.
-2. Translate each second line; leave the English keys untouched.
-3. Fill in the `LANGUAGE_*` header for a new file.
-4. Open a pull request, or attach the file to a GitHub issue.
-
-When new strings land in `English.txt` they show up untranslated (as English) until a translator fills them in.

m4/ax_add_fortify_source.m4

@@ -1,119 +0,0 @@
-# ===========================================================================
-#  https://www.gnu.org/software/autoconf-archive/ax_add_fortify_source.html
-# ===========================================================================
-#
-# SYNOPSIS
-#
-#   AX_ADD_FORTIFY_SOURCE
-#
-# DESCRIPTION
-#
-#   Check whether -D_FORTIFY_SOURCE=2 can be added to CPPFLAGS without macro
-#   redefinition warnings, other cpp warnings or linker. Some distributions
-#   (such as Ubuntu or Gentoo Linux) enable _FORTIFY_SOURCE globally in
-#   their compilers, leading to unnecessary warnings in the form of
-#
-#     <command-line>:0:0: error: "_FORTIFY_SOURCE" redefined [-Werror]
-#     <built-in>: note: this is the location of the previous definition
-#
-#   which is a problem if -Werror is enabled. This macro checks whether
-#   _FORTIFY_SOURCE is already defined, and if not, adds -D_FORTIFY_SOURCE=2
-#   to CPPFLAGS.
-#
-#   Newer mingw-w64 msys2 package comes with a bug in
-#   headers-git-7.0.0.5546.d200317d-1. It broke -D_FORTIFY_SOURCE support,
-#   and would need -lssp or -fstack-protector.  See
-#   https://github.com/msys2/MINGW-packages/issues/5803. Try to actually
-#   link it.
-#
-# LICENSE
-#
-#   Copyright (c) 2017 David Seifert <soap@gentoo.org>
-#   Copyright (c) 2019, 2023 Reini Urban <rurban@cpan.org>
-#
-#   Copying and distribution of this file, with or without modification, are
-#   permitted in any medium without royalty provided the copyright notice
-#   and this notice are preserved.  This file is offered as-is, without any
-#   warranty.
-
-#serial 10
-
-AC_DEFUN([AX_ADD_FORTIFY_SOURCE],[
-    ac_save_cflags=$CFLAGS
-    ac_cwerror_flag=yes
-    AX_CHECK_COMPILE_FLAG([-Werror],[CFLAGS="$CFLAGS -Werror"])
-    ax_add_fortify_3_failed=
-    AC_MSG_CHECKING([whether to add -D_FORTIFY_SOURCE=3 to CPPFLAGS])
-    AC_LINK_IFELSE([
-        AC_LANG_PROGRAM([],
-            [[
-                #ifndef _FORTIFY_SOURCE
-                    return 0;
-                #else
-                    _FORTIFY_SOURCE_already_defined;
-                #endif
-            ]]
-        )],
-        AC_LINK_IFELSE([
-            AC_LANG_SOURCE([[
-                #define _FORTIFY_SOURCE 3
-                #include <string.h>
-                int main(void) {
-                    char *s = " ";
-                    strcpy(s, "x");
-                    return strlen(s)-1;
-                }
-              ]]
-            )],
-            [
-              AC_MSG_RESULT([yes])
-              CFLAGS=$ac_save_cflags
-              CPPFLAGS="$CPPFLAGS -D_FORTIFY_SOURCE=3"
-            ], [
-              AC_MSG_RESULT([no])
-              ax_add_fortify_3_failed=1
-            ],
-        ),
-        [
-          AC_MSG_RESULT([no])
-          ax_add_fortify_3_failed=1
-        ])
-    if test -n "$ax_add_fortify_3_failed"
-    then
-    AC_MSG_CHECKING([whether to add -D_FORTIFY_SOURCE=2 to CPPFLAGS])
-    AC_LINK_IFELSE([
-        AC_LANG_PROGRAM([],
-            [[
-                #ifndef _FORTIFY_SOURCE
-                    return 0;
-                #else
-                    _FORTIFY_SOURCE_already_defined;
-                #endif
-            ]]
-        )],
-        AC_LINK_IFELSE([
-            AC_LANG_SOURCE([[
-                #define _FORTIFY_SOURCE 2
-                #include <string.h>
-                int main(void) {
-                    char *s = " ";
-                    strcpy(s, "x");
-                    return strlen(s)-1;
-                }
-              ]]
-            )],
-            [
-              AC_MSG_RESULT([yes])
-              CFLAGS=$ac_save_cflags
-              CPPFLAGS="$CPPFLAGS -D_FORTIFY_SOURCE=2"
-            ], [
-              AC_MSG_RESULT([no])
-              CFLAGS=$ac_save_cflags
-            ],
-        ),
-        [
-          AC_MSG_RESULT([no])
-          CFLAGS=$ac_save_cflags
-        ])
-    fi
-])

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 "07 July 2026" "httrack website copier"
+.TH httrack 1 "13 June 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -24,7 +24,6 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-EN, \-\-max\-time[=N]\fR ]
 [ \fB\-AN, \-\-max\-rate[=N]\fR ]
 [ \fB\-%cN, \-\-connection\-per\-second[=N]\fR ]
-[ \fB\-%G, \-\-pause\fR ]
 [ \fB\-GN, \-\-max\-pause[=N]\fR ]
 [ \fB\-cN, \-\-sockets[=N]\fR ]
 [ \fB\-TN, \-\-timeout[=N]\fR ]
@@ -44,14 +43,11 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-x, \-\-replace\-external\fR ]
 [ \fB\-%x, \-\-disable\-passwords\fR ]
 [ \fB\-%q, \-\-include\-query\-string\fR ]
-[ \fB\-%g, \-\-strip\-query\fR ]
 [ \fB\-o, \-\-generate\-errors\fR ]
 [ \fB\-X, \-\-purge\-old[=N]\fR ]
 [ \fB\-%p, \-\-preserve\fR ]
 [ \fB\-%T, \-\-utf8\-conversion\fR ]
 [ \fB\-bN, \-\-cookies[=N]\fR ]
-[ \fB\-%K, \-\-cookies\-file\fR ]
-[ \fB\-%Y, \-\-why\fR ]
 [ \fB\-u, \-\-check\-type[=N]\fR ]
 [ \fB\-j, \-\-parse\-java[=N]\fR ]
 [ \fB\-sN, \-\-robots[=N]\fR ]
@@ -157,8 +153,6 @@ maximum mirror time in seconds (60=1 minute, 3600=1 hour) (\-\-max\-time[=N])
 maximum transfer rate in bytes/seconds (1000=1KB/s max) (\-\-max\-rate[=N])
 .IP \-%cN
 maximum number of connections/seconds (*%c10) (\-\-connection\-per\-second[=N])
-.IP \-%G
-random pause of MIN[:MAX] seconds between files (e.g. %G5:10) (\-\-pause <param>)
 .IP \-GN
 pause transfer if N bytes reached, and wait until lock file is deleted (\-\-max\-pause[=N])
 .SS Flow control:
@@ -204,8 +198,6 @@ replace external html links by error pages (\-\-replace\-external)
 do not include any password for external password protected websites (%x0 include) (\-\-disable\-passwords)
 .IP \-%q
 *include query string for local files (useless, for information purpose only) (%q0 don't include) (\-\-include\-query\-string)
-.IP \-%g
-strip query keys for dedup ([host/pattern=]key1,key2,...) (\-\-strip\-query <param>)
 .IP \-o
 *generate output html file in case of error (404..) (o0 don't generate) (\-\-generate\-errors)
 .IP \-X
@@ -217,10 +209,6 @@ links conversion to UTF\-8 (\-\-utf8\-conversion)
 .SS Spider options:
 .IP \-bN
 accept cookies in cookies.txt (0=do not accept,* 1=accept) (\-\-cookies[=N])
-.IP \-%K
-load extra cookies from a Netscape cookies.txt (\-\-cookies\-file <param>)
-.IP \-%Y
-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
@@ -237,8 +225,6 @@ tolerant requests (accept bogus responses on some servers, but not standard!) (\
 update hacks: various hacks to limit re\-transfers when updating (identical size, bogus response..) (\-\-updatehack)
 .IP \-%u
 url hacks: various hacks to limit duplicate URLs (strip //, www.foo.com==foo.com..) (\-\-urlhack)
-.br
-opt out of one url\-hack part: \-\-keep\-www\-prefix (www.foo.com<>foo.com), \-\-keep\-double\-slashes (//), \-\-keep\-query\-order (?b&a)
 .IP \-%A
 assume that a type (cgi,asp..) is always linked with a mime type (\-%A php3,cgi=text/html;dat,bin=application/x\-zip) (\-\-assume <param>)
 .br
@@ -327,8 +313,12 @@ debug HTTP headers in logfile (\-\-debug\-headers)
 .SS Guru options: (do NOT use if possible)
 .IP \-#X
 *use optimized engine (limited memory boundary checks) (\-\-fast\-engine)
-.IP \-#test
-list engine self\-tests (run one with \-#test=NAME [args])
+.IP \-#0
+filter test (\-#0 '*.gif' 'www.bar.com/foo.gif') (\-\-debug\-testfilters <param>)
+.IP \-#1
+simplify test (\-#1 ./foo/bar/../foobar)
+.IP \-#2
+type test (\-#2 /foo/bar.php)
 .IP \-#C
 cache list (\-#C '*.com/spider*.gif' (\-\-debug\-cache <param>)
 .IP \-#R

src/Makefile.am

@@ -56,21 +56,21 @@ whttrackrundir = $(bindir)
 whttrackrun_SCRIPTS = webhttrack
 
 libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
-	htscache_selftest.c htsdns_selftest.c htsselftest.c \
+	htscache_selftest.c htsdns_selftest.c \
 	htscatchurl.c htsfilters.c htsftp.c htshash.c coucal/coucal.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 htszlib.c htswrap.c htsconcat.c \
-	htsmodules.c htscharset.c punycode.c htsencoding.c htssniff.c \
+	htsmodules.c htscharset.c punycode.c htsencoding.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
 	hts-indextmpl.h htsalias.h htsback.h htsbase.h htssafe.h \
-	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htsselftest.h htscatchurl.h  \
+	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htscatchurl.h  \
 	htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
 	htsfilters.h htsftp.h htsglobal.h htshash.h coucal/coucal.h \
 	htshelp.h htsindex.h htslib.h htsmd5.h \
-	htsmodules.h htsname.h htsnet.h htssniff.h \
+	htsmodules.h htsname.h htsnet.h \
 	htsopt.h htsrobots.h htsthread.h  \
 	htstools.h htswizard.h htswrap.h htszlib.h  \
 	htsstrings.h htsarrays.h httrack-library.h \

src/htsalias.c

@@ -60,9 +60,6 @@ Please visit our Website: http://www.httrack.com
   param1 : this option must be alone, and needs one distinct parameter (-P <path>)
   param0 : this option must be alone, but the parameter should be put together (+*.gif)
 */
-/* clang-format off: hand-aligned table; clang-format reflows the whole
-   initializer (2->4 space) on any edit, churning every untouched row. */
-/* clang-format off */
 const char *hts_optalias[][4] = {
   /*   {"","","",""}, */
   {"path", "-O", "param1", "output path"},
@@ -110,14 +107,6 @@ const char *hts_optalias[][4] = {
   {"disable-passwords", "-%x", "single", ""}, {"disable-password", "-%x",
                                                "single", ""},
   {"include-query-string", "-%q", "single", ""},
-  {"strip-query", "-%g", "param1",
-   "strip [host/pattern=]key1,key2,... from URLs"},
-  {"cookies-file", "-%K", "param1",
-   "load extra cookies from a Netscape cookies.txt"},
-  {"why", "-%Y", "param1",
-   "explain which filter rule accepts or rejects a URL, then exit"},
-  {"pause", "-%G", "param1",
-   "random pause of MIN[:MAX] seconds between files"},
   {"generate-errors", "-o", "single", ""},
   {"do-not-generate-errors", "-o0", "single", ""},
   {"purge-old", "-X", "param", ""},
@@ -134,9 +123,6 @@ const char *hts_optalias[][4] = {
   {"tolerant", "-%B", "single", ""},
   {"updatehack", "-%s", "single", ""}, {"sizehack", "-%s", "single", ""},
   {"urlhack", "-%u", "single", ""},
-  {"keep-www-prefix", "-%j", "single", ""},
-  {"keep-double-slashes", "-%o", "single", ""},
-  {"keep-query-order", "-%y", "single", ""},
   {"user-agent", "-F", "param1", "user-agent identity"},
   {"referer", "-%R", "param1", "default referer URL"},
   {"from", "-%E", "param1", "from email address"},
@@ -255,7 +241,6 @@ const char *hts_optalias[][4] = {
 
   {"", "", "", ""}
 };
-/* clang-format on */
 
 /* 
   Check for alias in command-line 
@@ -285,6 +270,7 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
       char *position;
       int need_param = 1;
 
+      //int return_param=0;
       int pos;
 
       command[0] = param[0] = addcommand[0] = '\0';
@@ -362,6 +348,7 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
               strlcatbuff(return_argv[0], "0", return_argv_size);
             else if (strcmp(param, "on") == 0) {
               // on is the default
+              // strcatbuff(return_argv[0],"1");
             } else
               strlcatbuff(return_argv[0], param, return_argv_size);
           }

src/htsback.c

@@ -43,22 +43,21 @@ Please visit our Website: http://www.httrack.com
 
 #include "htsback.h"
 
+//#ifdef _WIN32
 #include "htsftp.h"
 #if HTS_USEZLIB
 #include "htszlib.h"
 #else
 #error HTS_USEZLIB not defined
 #endif
+//#endif
 
 #ifdef _WIN32
 #ifndef __cplusplus
 // DOS
 #include <process.h>            /* _beginthread, _endthread */
 #endif
-#include <io.h> /* _chsize_s */
-#define HTS_FTRUNCATE(fp, sz) _chsize_s(_fileno(fp), (sz))
 #else
-#define HTS_FTRUNCATE(fp, sz) ftruncate(fileno(fp), (sz))
 #endif
 
 #define VT_CLREOL       "\33[K"
@@ -570,12 +569,9 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
         && back[p].r.size != back[p].r.totalsize && !opt->tolerant) {
       if (back[p].status == STATUS_READY) {
         hts_log_print(opt, LOG_WARNING,
-                      "incomplete transfer (expected " LLintP
-                      " bytes, got " LLintP
-                      "): file not cached, will be retried on the next update"
-                      " (use -%%B to cache anyway): %s%s",
-                      back[p].r.totalsize, back[p].r.size, back[p].url_adr,
-                      back[p].url_fil);
+                      "file not stored in cache due to bogus state (broken size, expected "
+                      LLintP " got " LLintP "): %s%s", back[p].r.totalsize,
+                      back[p].r.size, back[p].url_adr, back[p].url_fil);
       } else {
         hts_log_print(opt, LOG_INFO,
                       "incomplete file not yet stored in cache (expected "
@@ -595,6 +591,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
 #if HTS_USEZLIB
         if (back[p].r.compressed) {
           if (back[p].r.size > 0) {
+            //if ( (back[p].r.adr) && (back[p].r.size>0) ) {
             // stats
             back[p].compressed_size = back[p].r.size;
             // en mémoire -> passage sur disque
@@ -879,12 +876,11 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                          back[p].url_fil, NULL);
           } else {
             /* Partial file, but marked as "ok" ? */
-            hts_log_print(
-                opt, LOG_WARNING,
-                "file with unresolved type not cached (%s (%d), size " LLintP
-                "): %s%s",
-                back[p].r.msg, back[p].r.statuscode, (LLint) back[p].r.size,
-                back[p].url_adr, back[p].url_fil);
+            hts_log_print(opt, LOG_WARNING,
+                          "file not stored in cache due to bogus state (incomplete type with %s (%d), size "
+                          LLintP "): %s%s", back[p].r.msg, back[p].r.statuscode,
+                          (LLint) back[p].r.size, back[p].url_adr,
+                          back[p].url_fil);
           }
         }
 
@@ -924,6 +920,7 @@ int back_letlive(httrackp * opt, cache_back * cache, struct_back * sback,
     /* clear everything but connection: switch, close, and reswitch */
     back_connxfr(src, &tmp);
     back_delete(opt, cache, sback, p);
+    //deletehttp(src);
     back_connxfr(&tmp, src);
     src->req.flush_garbage = 1; /* ignore CRLF garbage */
     return 1;
@@ -1358,49 +1355,7 @@ int back_flush_output(httrackp * opt, cache_back * cache, struct_back * sback,
   return 0;
 }
 
-/* Move a still-writing .delayed placeholder to its final name (#483). */
-hts_boolean back_delayed_rename(httrackp *opt, lien_back *back,
-                                const char *newname) {
-  hts_boolean renamed;
-
-  if (!back->r.is_write || back->tmpfile != NULL ||
-      !IS_DELAYED_EXT(back->url_sav) || strcmp(back->url_sav, newname) == 0)
-    return HTS_TRUE; /* nothing bound to the placeholder name */
-  if (back->r.out != NULL) {
-    fclose(back->r.out);
-    back->r.out = NULL;
-  }
-  renamed = RENAME(back->url_sav, newname) == 0 ? HTS_TRUE : HTS_FALSE;
-  if (renamed && (back->status == STATUS_READY ||
-                  (back->r.out = FOPEN(newname, "ab")) != NULL)) {
-    filenote(&opt->state.strc, newname, NULL);
-    hts_log_print(opt, LOG_DEBUG, "moved placeholder %s to %s", back->url_sav,
-                  newname);
-    return HTS_TRUE;
-  }
-  /* partial lost: drop only what we own (Windows rename won't overwrite) */
-  hts_log_print(opt, LOG_WARNING | LOG_ERRNO, "unable to move %s to %s",
-                back->url_sav, newname);
-  back->r.statuscode = STATUSCODE_INVALID;
-  strcpybuff(back->r.msg, "Write error on disk");
-  back->r.is_write = 0;
-  (void) UNLINK(renamed ? newname : back->url_sav);
-  return HTS_FALSE;
-}
-
 // effacer entrée
-/* Discard a cancelled mid-write .delayed placeholder (unusable across runs). */
-void back_delayed_discard(httrackp *opt, lien_back *back) {
-  if (back->r.out != NULL) {
-    fclose(back->r.out);
-    back->r.out = NULL;
-  }
-  back->r.is_write = 0;
-  if (opt != NULL)
-    url_savename_refname_remove(opt, back->url_adr, back->url_fil);
-  (void) UNLINK(back->url_sav);
-}
-
 int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
                 const int p) {
   lien_back *const back = sback->lnk;
@@ -1408,12 +1363,6 @@ int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
 
   assertf(p >= 0 && p < back_max);
   if (p >= 0 && p < sback->count) {     // on sait jamais..
-    /* mid-write cancel: drop a .delayed placeholder; real-named partials
-       survive for resume (--continue) */
-    if (back[p].r.is_write && IS_DELAYED_EXT(back[p].url_sav) &&
-        (back[p].status != STATUS_READY || back[p].r.statuscode <= 0)) {
-      back_delayed_discard(opt, &back[p]);
-    }
     // Vérificateur d'intégrité
 #if DEBUG_CHECKINT
     _CHECKINT(&back[p], "Appel back_delete")
@@ -1433,6 +1382,7 @@ int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
                       back[p].url_adr, back[p].url_fil, back[p].url_sav);
       }
       if (cache != NULL) {
+        //hts_log_print(opt, LOG_TRACE, "finalizing from back_delete");
         back_finalize(opt, cache, sback, p);
       }
     }
@@ -1573,6 +1523,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
     if (back[p].r.soc != INVALID_SOCKET) {      /* we never know */
       deletehttp(&back[p].r);
     }
+    //memset(&(back[p].r), 0, sizeof(htsblk)); 
     hts_init_htsblk(&back[p].r);
     back[p].r.location = back[p].location_buffer;
 
@@ -1580,6 +1531,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
     strcpybuff(back[p].url_adr, adr);
     strcpybuff(back[p].url_fil, fil);
     strcpybuff(back[p].url_sav, save);
+    //back[p].links_index = links_index;
     // copier referer si besoin
     strcpybuff(back[p].referer_adr, "");
     strcpybuff(back[p].referer_fil, "");
@@ -1818,7 +1770,8 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
                             back[p].url_adr, back[p].url_fil);
             }
             back[p].r.notmodified = 1;  // fichier non modifié
-            back[p].status = STATUS_READY; // OK prêt
+            back[p].status = STATUS_READY;      // OK prêt
+            //file_notify(back[p].url_adr, back[p].url_fil, back[p].url_sav, 0, 0, back[p].r.notmodified);        // not modified
             back_set_finished(sback, p);
 
             // finalize transfer
@@ -1833,6 +1786,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
           } else {              // erreur
             // effacer r
             hts_init_htsblk(&back[p].r);
+            //memset(&(back[p].r), 0, sizeof(htsblk)); 
             back[p].r.location = back[p].location_buffer;
             // et continuer (chercher le fichier)
           }
@@ -2027,6 +1981,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
       // ouvrir liaison, envoyer requète
       // ne pas traiter ou recevoir l'en tête immédiatement
       hts_init_htsblk(&back[p].r);
+      // memset(&(back[p].r), 0, sizeof(htsblk));
       back[p].r.location = back[p].location_buffer;
       // fresh connect: address list not yet probed, start at the first
       sback->connect_fallback[p].addr_index = 0;
@@ -2077,6 +2032,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 #if HTS_USEOPENSSL
       else if (strfield(back[p].url_adr, "https://")) {     // let's rock
         back[p].r.ssl = 1;
+        // back[p].r.ssl_soc = NULL;
         back[p].r.ssl_con = NULL;
       }
 #endif
@@ -2142,9 +2098,9 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
         back[p].rateout = -1;   // pas de gestion (default)
       }
 
-      // Note: on charge les code-page erreurs (erreur 404, etc) dans le cas où
-      // cela est rattrapable (exemple: 301,302 moved xxx -> refresh sur la
-      // page!)
+      // Note: on charge les code-page erreurs (erreur 404, etc) dans le cas où cela est
+      // rattrapable (exemple: 301,302 moved xxx -> refresh sur la page!)
+      //if ((back[p].statuscode!=HTTP_OK) || (soc<0)) { // ERREUR HTTP/autre
 
 #if CNXDEBUG
       printf("Xfopen ok, poll..\n");
@@ -2162,6 +2118,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
       if (soc == INVALID_SOCKET) {      // erreur socket
         back[p].status = STATUS_READY;  // FINI
         back_set_finished(sback, p);
+        //if (back[p].soc!=INVALID_SOCKET) deletehttp(back[p].soc);
         back[p].r.soc = INVALID_SOCKET;
       } else {
         if (!back[p].r.is_file)
@@ -2182,6 +2139,8 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 
     // note: si il y a erreur (404,etc) status=2 (terminé/échec) mais
     // le lien est considéré comme traité
+    //if (back[p].soc<0)  // erreur
+    //  return -1;
 
     return 0;
   } else {
@@ -2254,6 +2213,9 @@ void back_solve(httrackp * opt, lien_back * back) {
     } else {
       hts_log_print(opt, LOG_DEBUG, "failed to resolve: %s", a);
     }
+    //if (hts_dnstest(opt, a, 1) == 2) { // non encore testé!..
+    //  hts_log_print(opt, LOG_DEBUG, "resolving in background: %s", a);
+    //}
   }
 }
 
@@ -2272,13 +2234,12 @@ int host_wait(httrackp * opt, lien_back * back) {
 
 static int slot_can_be_cleaned(const lien_back * back) {
   return (back->status == STATUS_READY) // ready
-         /* Check autoclean */
-         && (!back->locked)   // not held by hts_wait_delayed (name pending)
-         && (!back->testmode) // not test mode
-         && (strnotempty(back->url_sav))     // filename exists
-         && (HTTP_IS_OK(back->r.statuscode)) // HTTP "OK"
-         && (back->r.size >= 0)              // size>=0
-      ;
+    /* Check autoclean */
+    && (!back->testmode)        // not test mode
+    && (strnotempty(back->url_sav))     // filename exists
+    && (HTTP_IS_OK(back->r.statuscode)) // HTTP "OK"
+    && (back->r.size >= 0)      // size>=0
+    ;
 }
 
 static int slot_can_be_finalized(httrackp * opt, const lien_back * back) {
@@ -2302,6 +2263,11 @@ void back_clean(httrackp * opt, cache_back * cache, struct_back * sback) {
         (void) back_flush_output(opt, cache, sback, i); // flush output buffers
         usercommand(opt, 0, NULL, back[i].url_sav, back[i].url_adr,
                     back[i].url_fil);
+        //if (back[i].links_index >= 0) {
+        //  assertf(back[i].links_index < opt->hash->max_lien);
+        //  opt->hash->liens[back[i].links_index]->pass2 = -1;
+        //  // *back[i].pass2_ptr=-1;  // Done!
+        //}
         /* MANDATORY if we don't want back_fill() to endlessly put the same file on download! */
         {
           int index = hash_read(opt->hash, back[i].url_sav, NULL, HASH_STRUCT_FILENAME );       // lecture type 0 (sav)
@@ -2449,34 +2415,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
   back_clean(opt, cache, sback);
 #endif
 
-  /* Time limit exceeded past grace: abort in-flight transfers so no wait loop
-     starves (#481). FTP slots stay, their thread owns the socket. */
-  if (!back_checkmirror(opt)) {
-    int aborted = 0;
-    unsigned int i;
-
-    for (i = 0; i < (unsigned int) back_max; i++) {
-      if (back[i].status > 0 && back[i].status < STATUS_FTP_TRANSFER) {
-        if (back[i].r.soc != INVALID_SOCKET) {
-          deletehttp(&back[i].r);
-        }
-        back[i].r.soc = INVALID_SOCKET;
-        /* drop a .delayed placeholder; real partials survive for resume */
-        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, "Mirror Time Out");
-        back[i].status = STATUS_READY;
-        back_set_finished(sback, i);
-        aborted++;
-      }
-    }
-    if (aborted > 0)
-      hts_log_print(opt, LOG_WARNING,
-                    "time limit reached, %d transfer(s) aborted", aborted);
-    return;
-  }
-
   // recevoir tant qu'il y a des données (avec un maximum de max_loop boucles)
   do_wait = 0;
   gestion_timeout = 0;
@@ -2485,6 +2423,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
     busy_state = busy_recv = 0;
 
+#if 0
+    check_rate(stat_timestart, opt->maxrate);   // vérifier taux de transfert
+#endif
     // inscrire les sockets actuelles, et rechercher l'ID la plus élevée
     FD_ZERO(&fds);
     FD_ZERO(&fds_c);
@@ -2494,7 +2435,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
     nfds = INVALID_SOCKET;
 
     max_c = 1;
-    for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+    for(i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+      // for(i=0;i<back_max;i++) {
       unsigned int i = (i_mod + mod_random) % (back_max);
 
       // en cas de gestion du connect préemptif
@@ -2531,7 +2473,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
         // poll pour la lecture sur les sockets
       if ((back[i].status > 0) && (back[i].status < 100)) {     // en réception http
 
-#if BDEBUG == 1
+#if BDEBUG==1
+        //printf("....socket in progress: %d\n",back[i].r.soc);
 #endif
         // non local et non ftp
         if (!back[i].r.is_file) {
@@ -2617,7 +2560,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
       busy_recv = 0;
 
     // recevoir les données arrivées
-    for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+    for(i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+      // for(i=0;i<back_max;i++) {
       unsigned int i = (i_mod + mod_random) % (back_max);
 
       if (back[i].status > 0) {
@@ -2757,6 +2701,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
               back[i].rateout_time = back[i].ka_time_start;
             }
             // envoyer header
+            //if (strcmp(back[i].url_sav,BACK_ADD_TEST)!=0)    // vrai get
             HTS_STAT.stat_nrequests++;
             if (!back[i].head_request)
               http_sendhead(opt, opt->cookie, 0, back[i].send_too,
@@ -2823,6 +2768,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 #if HTS_XGETHOST
       else if (back[i].status == STATUS_WAIT_DNS) {     // attendre gethostbyname
 #if DEBUGDNS
+        //printf("status 101 for %s\n",back[i].url_adr);
 #endif
 
         if (!gestion_timeout)
@@ -2942,10 +2888,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
           // range size hack old location
 
 #if HTS_DIRECTDISK
-          // Shortcut: store the file directly on disk when possible,
-          // sparing memory
-          if (back[i].status &&
-              !back[i].locked) { // name still pending when locked
+          // Court-circuit:
+          // Peut-on stocker le fichier directement sur disque?
+          // Ahh que ca serait vachement mieux et que ahh que la mémoire vous dit merci!
+          if (back[i].status) {
             if (back[i].r.is_write == 0) {      // mode mémoire
               if (back[i].r.adr == NULL) {      // rien n'a été écrit
                 if (!back[i].testmode) {        // pas mode test
@@ -3095,7 +3041,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
           // Si réception chunk, tester si on est pas à la fin!
           if (back[i].status == 1) {
             if (back[i].is_chunk) {     // attendre prochain chunk
-              if (back[i].r.size == back[i].r.totalsize) { // fin chunk!
+              if (back[i].r.size == back[i].r.totalsize) {      // fin chunk!
+                //printf("chunk end at %d\n",back[i].r.size);
                 back[i].status = STATUS_CHUNK_CR;       /* fetch ending CRLF */
                 if (back[i].chunk_adr != NULL) {
                   freet(back[i].chunk_adr);
@@ -3158,9 +3105,11 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
               back_finalize(opt, cache, sback, i);
             }
 
-            if (back[i].r.totalsize >= 0) { // tester totalsize
+            if (back[i].r.totalsize >= 0) {     // tester totalsize
+              //if ((back[i].r.totalsize>=0) && (back[i].status==STATUS_WAIT_HEADERS)) {    // tester totalsize
               if (back[i].r.totalsize != back[i].r.size) {      // pas la même!
                 if (!opt->tolerant) {
+                  //#if HTS_CL_IS_FATAL
                   deleteaddr(&back[i].r);
                   if (back[i].r.size < back[i].r.totalsize)
                     back[i].r.statuscode = STATUSCODE_CONNERROR;        // recatch
@@ -3169,13 +3118,14 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           " expected)", (LLint) back[i].r.size,
                           (LLint) back[i].r.totalsize);
                 } else {
+                  //#else
                   // Un warning suffira..
                   hts_log_print(opt, LOG_WARNING,
                                 "Incorrect length (" LLintP "!=" LLintP
-                                " expected) for %s%s",
-                                (LLint) back[i].r.size,
+                                " expected) for %s%s", (LLint) back[i].r.size,
                                 (LLint) back[i].r.totalsize, back[i].url_adr,
                                 back[i].url_fil);
+                  //#endif
                 }
               }
             }
@@ -3302,8 +3252,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                          back[i].r.size);
 #endif
                   /* End */
-                  back[i].status = STATUS_READY; // fin
+                  //if (back[i].status==STATUS_CHUNK_CR) {
+                  back[i].status = STATUS_READY;        // fin  
                   back_set_finished(sback, i);
+                  //}
 
                   // finalize transfer if not temporary
                   if (!IS_DELAYED_EXT(back[i].url_sav)) {
@@ -3770,6 +3722,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                     back[i].url_adr, back[i].url_fil);
 
                       // finalize
+                      //file_notify(back[i].url_adr, back[i].url_fil, back[i].url_sav, 0, 0, back[i].r.notmodified);        // not modified
                       if (back[i].r.statuscode > 0) {
                         hts_log_print(opt, LOG_TRACE, "finalizing after cache load");
                         back_finalize(opt, cache, sback, i);
@@ -3779,32 +3732,38 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                              back[i].url_adr, back[i].url_fil);
 #endif
 
+                      //printf(">%s status %d\n",back[p].r.contenttype,back[p].r.statuscode);
                     } else {    // erreur
                       back[i].status = STATUS_READY;    // terminé
                       back_set_finished(sback, i);
+                      //printf("erreur cache\n");
+
                     }
 
-                  }
-                  // MIME type excluded by a -mime: filter: abort, don't fetch
-                  // the body (#58)
-                  else if (HTTP_IS_OK(back[i].r.statuscode) &&
-                           !back[i].testmode &&
-                           strnotempty(back[i].r.contenttype) &&
-                           hts_acceptmime(opt, 0, back[i].url_adr,
-                                          back[i].url_fil,
-                                          back[i].r.contenttype) == 1) {
-                    deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
-                    back[i].status = STATUS_READY;
+/********** NO - must complete the body! ********** */
+#if 0
+                  } else if (HTTP_IS_REDIRECT(back[i].r.statuscode)
+                             || (back[i].r.statuscode == 412)
+                             || (back[i].r.statuscode == 416)
+                    ) {         // Ne pas prendre le html, erreurs connues et gérées
+#if HTS_DEBUG_CLOSESOCK
+                    DEBUG_W
+                      ("back_wait(301,302,303,307,412,416..): deletehttp\n");
+#endif
+                    // Couper connexion
+                    /*KA deletehttp(&back[i].r); back[i].r.soc=INVALID_SOCKET; */
+                    back_maydeletehttp(opt, cache, sback, i);
+
+                    back[i].status = STATUS_READY;      // terminé
                     back_set_finished(sback, i);
-                    back[i].r.statuscode = STATUSCODE_EXCLUDED;
-                    strcpybuff(back[i].r.msg, "Excluded by MIME type filter");
-                    hts_log_print(
-                        opt, LOG_NOTICE,
-                        "File excluded by MIME type filter (%s): %s%s",
-                        back[i].r.contenttype, back[i].url_adr,
-                        back[i].url_fil);
-                  } else { // il faut aller le chercher
+                    // finalize
+                    if (back[i].r.statuscode > 0) {
+                      hts_log_print(opt, LOG_TRACE, "finalizing redirect & 4xx");
+                      back_finalize(opt, cache, sback, i);
+                    }
+#endif
+/********** **************************** ********** */
+                  } else {      // il faut aller le chercher
 
                     // effacer buffer (requète)
                     if (!noFreebuff) {
@@ -3815,70 +3774,35 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     // 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!
                       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
-                         (#198). */
-                      const LLint resume = back[i].r.crange_start;
-                      const hts_boolean range_ok =
-                          back[i].r.crange > 0 && resume >= 0 &&
-                          resume <= (LLint) sz &&
-                          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);
 
 #if HDEBUG
                       printf("partial content: " LLintP " on disk..\n",
                              (LLint) sz);
 #endif
-                      if (sz >= 0 && range_ok) {
+                      if (sz >= 0) {
                         if (!is_hypertext_mime(opt, back[i].r.contenttype, back[i].url_sav)) {  // pas HTML
                           if (opt->getmode & HTS_GETMODE_NONHTML) {
                             filenote(&opt->state.strc, back[i].url_sav, NULL);  // noter fichier comme connu
                             file_notify(opt, back[i].url_adr, back[i].url_fil,
                                         back[i].url_sav, 0, 1,
                                         back[i].r.notmodified);
-                            back[i].r.out =
-                                FOPEN(fconv(catbuff, sizeof(catbuff),
-                                            back[i].url_sav),
-                                      "r+b"); // resume in place
+                            back[i].r.out = FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "ab");       // append
                             if (back[i].r.out && opt->cache != 0) {
-                              back[i].r.is_write = 1;
-                              back[i].r.size = resume; // bytes already on disk
-                              back[i].r.statuscode = HTTP_OK; // force 'OK'
+                              back[i].r.is_write = 1;   // écrire
+                              back[i].r.size = sz;      // déja écrit
+                              back[i].r.statuscode = HTTP_OK;   // Forcer 'OK'
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += resume; // -> full size
-                              // 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
-                              if (HTS_FTRUNCATE(back[i].r.out,
-                                                (off_t) resume) != 0) {
-                                fclose(back[i].r.out);
-                                back[i].r.out = NULL;
-                                url_savename_refname_remove(
-                                    opt, back[i].url_adr, back[i].url_fil);
-                                UNLINK(back[i].url_sav);
-                                back[i].status = STATUS_READY;
-                                back_set_finished(sback, i);
-                                strcpybuff(back[i].r.msg,
-                                           "Can not truncate partial file, "
-                                           "restarting");
-                              } else {
-                                fseeko(back[i].r.out, (off_t) resume, SEEK_SET);
-                                /* create a temporary reference file in case of
-                                 * broken mirror */
-                                if (back_serialize_ref(opt, &back[i]) != 0) {
-                                  hts_log_print(opt, LOG_WARNING,
-                                                "Could not create temporary "
-                                                "reference file for %s%s",
-                                                back[i].url_adr,
-                                                back[i].url_fil);
-                                }
-#if HDEBUG
-                                printf("continue interrupted file\n");
-#endif
+                                back[i].r.totalsize += sz;      // plus en fait
+                              fseek(back[i].r.out, 0, SEEK_END);        // à la fin
+                              /* create a temporary reference file in case of broken mirror */
+                              if (back_serialize_ref(opt, &back[i]) != 0) {
+                                hts_log_print(opt, LOG_WARNING,
+                                              "Could not create temporary reference file for %s%s",
+                                              back[i].url_adr, back[i].url_fil);
                               }
+#if HDEBUG
+                              printf("continue interrupted file\n");
+#endif
                             } else {    // On est dans la m**
                               back[i].status = STATUS_READY;    // terminé (voir plus loin)
                               back_set_finished(sback, i);
@@ -3890,18 +3814,17 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           FILE *fp =
                             FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "rb");
                           if (fp) {
-                            LLint alloc_mem = resume + 1;
+                            LLint alloc_mem = sz + 1;
 
                             if (back[i].r.totalsize >= 0)
                               alloc_mem += back[i].r.totalsize; // AJOUTER RESTANT!
                             if (deleteaddr(&back[i].r)
                                 && (back[i].r.adr =
                                     (char *) malloct((size_t) alloc_mem))) {
-                              back[i].r.size = resume;
+                              back[i].r.size = sz;
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += resume; // -> full size
-                              if ((fread(back[i].r.adr, 1, (size_t) resume,
-                                         fp)) != (size_t) resume) {
+                                back[i].r.totalsize += sz;      // plus en fait
+                              if ((fread(back[i].r.adr, 1, sz, fp)) != sz) {
                                 back[i].status = STATUS_READY;  // terminé (voir plus loin)
                                 back_set_finished(sback, i);
                                 strcpybuff(back[i].r.msg,
@@ -3919,30 +3842,14 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                          "No memory for partial file");
                             }
                             fclose(fp);
-                          } else {                              // open failed
+                          } else {      // Argh.. 
                             back[i].status = STATUS_READY;      // terminé (voir plus loin)
                             back_set_finished(sback, i);
                             strcpybuff(back[i].r.msg,
                                        "Can not open partial file");
                           }
                         }
-                      } else if (sz >=
-                                 0) { // unusable range -> restart whole file
-                        hts_log_print(opt, LOG_WARNING,
-                                      "Unusable partial-content range for %s%s "
-                                      "(have " LLintP " bytes, got " LLintP
-                                      "-" LLintP "/" LLintP "), restarting",
-                                      back[i].url_adr, back[i].url_fil,
-                                      (LLint) sz, back[i].r.crange_start,
-                                      back[i].r.crange_end, back[i].r.crange);
-                        url_savename_refname_remove(opt, back[i].url_adr,
-                                                    back[i].url_fil);
-                        UNLINK(back[i].url_sav);
-                        back[i].status = STATUS_READY;
-                        back_set_finished(sback, i);
-                        strcpybuff(back[i].r.msg,
-                                   "Unusable partial content, restarting");
-                      } else {                          // partial not found
+                      } else {  // Non trouvé??
                         back[i].status = STATUS_READY;  // terminé (voir plus loin)
                         back_set_finished(sback, i);
                         strcpybuff(back[i].r.msg, "Can not find partial file");
@@ -3957,6 +3864,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           deletehttp(&back[i].r);
                         }
                         back[i].r.soc = INVALID_SOCKET;
+                        //back[i].r.statuscode=206;  ????????
                         back[i].r.statuscode = STATUSCODE_NON_FATAL;
                         if (strnotempty(back[i].r.msg))
                           strcpybuff(back[i].r.msg,
@@ -3977,13 +3885,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                               && (back[i].r.adr = (char *) malloct(2))) {
                             back[i].r.adr[0] = 0;
                           }
-                          /* locked = name pending; the waiter finalizes after
-                             patching url_sav (else: cached as .delayed, #5) */
-                          if (!back[i].locked) {
-                            hts_log_print(opt, LOG_TRACE, "finalizing empty");
-                            back_finalize(opt, cache, sback, i);
-                          }
-                        } else if (!back[i].r.is_chunk) { // pas de chunk
+                          hts_log_print(opt, LOG_TRACE, "finalizing empty");
+                          back_finalize(opt, cache, sback, i);
+                        } else if (!back[i].r.is_chunk) {       // pas de chunk
+                          //if (back[i].r.http11!=2) {    // pas de chunk
                           back[i].is_chunk = 0;
                           back[i].status = 1;   // start body
                         } else {
@@ -4025,6 +3930,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
                       }
                     }
+
                   }
 
                   /*} */
@@ -4044,11 +3950,14 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
         if (back[i].status < 0) {
           if (!back[i].testmode) {      // pas en test
             UNLINK(back[i].url_sav);    // éliminer fichier (endommagé)
+            //printf("&& %s\n",back[i].url_sav);
           }
         }
 #endif
 
         /* funny log for commandline users */
+        //if (!opt->quiet) {  
+        // petite animation
         if (opt->verbosedisplay == HTS_VERBOSE_SIMPLE) {
           if (back[i].status == STATUS_READY) {
             if (back[i].r.statuscode == HTTP_OK)
@@ -4061,16 +3970,18 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
             fflush(stdout);
           }
         }
+        //}
 
       }                         // status>0
-    } // for
+    }                           // for
 
     // vérifier timeouts
     if (gestion_timeout) {
       TStamp act;
 
       act = time_local();       // temps en secondes
-      for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+      for(i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
+        // for(i=0;i<back_max;i++) {
         unsigned int i = (i_mod + mod_random) % (back_max);
 
         if (back[i].status > 0) {       // réception/connexion/..
@@ -4098,6 +4009,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                 continue;
               }
             }
+            //printf("time check %d\n",((int) (act-back[i].timeout_refresh))-back[i].timeout);
             if (((int) (act - back[i].timeout_refresh)) >= back[i].timeout) {
               hts_log_print(opt, LOG_DEBUG, "connection timed out for %s%s", back[i].url_adr,
                 back[i].url_fil);
@@ -4173,11 +4085,6 @@ int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize)
   return 1;
 }
 
-/* Grace left to the smooth stop before in-flight transfers are aborted. */
-static int back_maxtime_grace(const int maxtime) {
-  return maximum(5, minimum(30, maxtime / 10));
-}
-
 int back_checkmirror(httrackp * opt) {
   // Check max size
   if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
@@ -4194,19 +4101,13 @@ int back_checkmirror(httrackp * opt) {
      */
   }
   // Check max time
-  if (opt->maxtime > 0) {
-    const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;
-
-    if (elapsed >= opt->maxtime) {
-      if (!opt->state.stop) { /* not yet stopped */
-        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;
+  if ((opt->maxtime > 0)
+      && ((time_local() - HTS_STAT.stat_timestart) >= opt->maxtime)) {
+    if (!opt->state.stop) {     /* not yet stopped */
+      hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
+                    opt->maxtime);
+      /* cancel mirror smoothly */
+      hts_request_stop(opt, 0);
     }
   }
   return 1;                     /* Ok, go on */

src/htsback.h

@@ -113,12 +113,6 @@ void back_set_locked(struct_back * sback, const int p);
 void back_set_unlocked(struct_back * sback, const int p);
 int back_delete(httrackp * opt, cache_back * cache, struct_back * sback,
                 const int p);
-/* Discard back's on-disk .delayed placeholder and its refname. */
-void back_delayed_discard(httrackp *opt, lien_back *back);
-/* Move back's .delayed placeholder (and open stream) to newname;
-   HTS_FALSE = file lost, slot flagged in error. */
-hts_boolean back_delayed_rename(httrackp *opt, lien_back *back,
-                                const char *newname);
 void back_index_unlock(struct_back * sback, const int p);
 int back_clear_entry(lien_back * back);
 int back_flush_output(httrackp * opt, cache_back * cache, struct_back * sback,
@@ -142,8 +136,6 @@ 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: requests a smooth stop when reached; returns 0 once
-   the -E deadline overran its grace period (callers must stop waiting). */
 int back_checkmirror(httrackp * opt);
 
 #endif

src/htsbasenet.h

@@ -55,6 +55,8 @@ Please visit our Website: http://www.httrack.com
 // inline function in Wspiapi.h.
 #include <ws2tcpip.h>
 #include <Wspiapi.h>
+// #include <winsock2.h>
+// #include <tpipv6.h>
 
 #endif
 
@@ -127,8 +129,6 @@ typedef enum HTTPStatusCode {
   HTTP_UNSUPPORTED_MEDIA_TYPE = 415,
   HTTP_REQUESTED_RANGE_NOT_SATISFIABLE = 416,
   HTTP_EXPECTATION_FAILED = 417,
-  HTTP_TOO_MANY_REQUESTS = 429,
-  HTTP_UNAVAILABLE_FOR_LEGAL_REASONS = 451,
   HTTP_INTERNAL_SERVER_ERROR = 500,
   HTTP_NOT_IMPLEMENTED = 501,
   HTTP_BAD_GATEWAY = 502,
@@ -146,8 +146,7 @@ typedef enum BackStatusCode {
   STATUSCODE_NON_FATAL = -5,
   STATUSCODE_SSL_HANDSHAKE = -6,
   STATUSCODE_TOO_BIG = -7,
-  STATUSCODE_TEST_OK = -10,
-  STATUSCODE_EXCLUDED = -11 /* aborted: MIME excluded by a -mime: filter */
+  STATUSCODE_TEST_OK = -10
 } BackStatusCode;
 
 /** HTTrack status ('status' member of of 'lien_back') **/

src/htsbasiccharsets.sh

@@ -3,12 +3,12 @@
 
 # Change this to download files
 if false; then
-    echo "mget https://www.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
-    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
-    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
-    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
-    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
-    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
+    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
     rm -f CP932.TXT CP936.TXT CP949.TXT CP950.TXT
 fi
 

src/htsbauth.c

@@ -107,6 +107,7 @@ int cookie_add(t_cookie * cookie, const char *cook_name, const char *cook_value,
 #if DEBUG_COOK
   printf("add_new cookie: name=\"%s\" value=\"%s\" domain=\"%s\" path=\"%s\"\n",
          cook_name, cook_value, domain, path);
+  //printf(">>>cook: %s<<<\n",cookie->data);
 #endif
   return 0;
 }
@@ -207,6 +208,8 @@ int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
   char catbuff[CATBUFF_SIZE];
   char buffer[8192];
 
+  //  cookie->data[0]='\0';
+
   // Fusionner d'abord les éventuels cookies IE
 #ifdef _WIN32
   {

src/htscache.h

@@ -66,11 +66,8 @@ htsblk cache_read(httrackp * opt, cache_back * cache, const char *adr,
                   const char *fil, const char *save, char *location);
 htsblk cache_read_ro(httrackp * opt, cache_back * cache, const char *adr,
                      const char *fil, const char *save, char *location);
-/* Like cache_read, but also yields entries whose transfer broke; return_save
-   (optional, HTS_URLMAXSIZE*2) receives the entry's recorded save name. */
-htsblk cache_read_including_broken(httrackp *opt, cache_back *cache,
-                                   const char *adr, const char *fil,
-                                   char *return_save);
+htsblk cache_read_including_broken(httrackp * opt, cache_back * cache,
+                                   const char *adr, const char *fil);
 htsblk cache_readex(httrackp * opt, cache_back * cache, const char *adr,
                     const char *fil, const char *save, char *location,
                     char *return_save, int readonly);
@@ -78,22 +75,14 @@ htsblk *cache_header(httrackp * opt, cache_back * cache, const char *adr,
                      const char *fil, htsblk * r);
 void cache_init(cache_back * cache, httrackp * opt);
 
-/* Which hts-cache/ generation (new.* vs old.*) is authoritative. */
-typedef enum {
-  CACHE_RECONCILE_PROMOTE,     /* no new cache: promote the old generation */
-  CACHE_RECONCILE_INTERRUPTED, /* aborted run: keep the larger generation */
-  CACHE_RECONCILE_ROLLBACK     /* nothing transferred: restore the old one */
-} hts_cache_reconcile_mode;
-
-/* Reconcile the on-disk cache generations according to mode; a no-op when
-   the involved files are absent. */
-void hts_cache_reconcile(httrackp *opt, hts_cache_reconcile_mode mode);
+int cache_writedata(FILE * cache_ndx, FILE * cache_dat, const char *str1,
+                    const char *str2, char *outbuff, int len);
+int cache_readdata(cache_back * cache, const char *str1, const char *str2,
+                   char **inbuff, int *len);
 
 void cache_rstr(FILE *fp, char *s, size_t s_size);
 char *cache_rstr_addr(FILE * fp);
 int cache_brstr(char *adr, char *s, size_t s_size);
-/* binput over a NUL-terminated buffer, bounded: no read starts at/past end. */
-int cache_binput(char *adr, const char *end, char *s, int max);
 int cache_brint(char *adr, int *i);
 void cache_rint(FILE * fp, int *i);
 void cache_rLLint(FILE * fp, LLint * i);

src/htscache_selftest.c

@@ -47,8 +47,6 @@ Please visit our Website: http://www.httrack.com
 #include "htslib.h"
 #include "htszlib.h"
 
-#include <errno.h>
-#include <limits.h>
 #include <stdio.h>
 #include <string.h>
 
@@ -78,6 +76,14 @@ static void selftest_open_for_read(cache_back *cache, httrackp *opt) {
 }
 
 static void selftest_close(cache_back *cache) {
+  if (cache->dat != NULL) {
+    fclose(cache->dat);
+    cache->dat = NULL;
+  }
+  if (cache->ndx != NULL) {
+    fclose(cache->ndx);
+    cache->ndx = NULL;
+  }
   if (cache->zipOutput != NULL) {
     zipClose(cache->zipOutput,
              "Created by HTTrack Website Copier (cache self-test)");
@@ -310,328 +316,6 @@ static int disk_fallback_selftest(httrackp *opt) {
   return fail;
 }
 
-typedef struct {
-  size_t budget;  /**< bytes allowed through before writes start failing */
-  int fail_errno; /**< errno set on the failing write (ENOSPC, EIO, ...) */
-  int writes;     /**< zwrite call count, to detect re-entry into the stream */
-  int fail_once;  /**< recover (unlimited budget) after the first failure */
-} writefail_inject;
-
-/* zwrite that copies until the budget runs out, then fails with inj->fail_errno
-   (the #174/#219 condition). Counts calls so the test can prove a flagged cache
-   never re-enters the stream. */
-static uLong selftest_failing_zwrite(voidpf opaque, voidpf stream,
-                                     const void *buf, uLong size) {
-  writefail_inject *inj = (writefail_inject *) opaque;
-
-  inj->writes++;
-  if (inj->budget >= (size_t) size) {
-    inj->budget -= (size_t) size;
-    return (uLong) fwrite(buf, 1, (size_t) size, (FILE *) stream);
-  }
-  if (inj->fail_once)
-    inj->budget = (size_t) -1; /* the backend recovers after this failure */
-  errno = inj->fail_errno;
-  return 0; /* short write -> the minizip op returns an error */
-}
-
-/* Open a ZIP whose writes fail past inj->budget, so cache_add() hits an error.
- */
-static zipFile selftest_open_failing_zip(const char *path,
-                                         writefail_inject *inj) {
-  zlib_filefunc_def ff;
-
-  fill_fopen_filefunc(&ff); /* real fopen/read/seek/close; ignores opaque */
-  ff.zwrite_file = selftest_failing_zwrite;
-  ff.opaque = inj;
-  return zipOpen2(path, APPEND_STATUS_CREATE, NULL, &ff);
-}
-
-/* Store one octet-stream body into `cache` (all-in-cache, body in the ZIP). */
-static void writefail_store(httrackp *opt, cache_back *cache, const char *fil,
-                            const char *body, size_t body_len) {
-  htsblk r;
-  char locbuf[4];
-  char *bodycopy = malloct(body_len);
-
-  hts_init_htsblk(&r);
-  r.statuscode = 200;
-  r.size = (LLint) body_len;
-  strcpybuff(r.msg, "OK");
-  strcpybuff(r.contenttype, "application/octet-stream");
-  locbuf[0] = '\0';
-  r.location = locbuf;
-  r.is_write = 0;
-  memcpy(bodycopy, body, body_len);
-  r.adr = bodycopy;
-  cache_add(opt, cache, &r, "example.com", fil, "example.com/blob.bin", 1,
-            NULL);
-  freet(bodycopy);
-}
-
-/* Store an entry claiming a >2GB body; the degrade path never reads data. */
-static void writefail_store_oversized(httrackp *opt, cache_back *cache,
-                                      const char *fil, int is_write) {
-  htsblk r;
-  char locbuf[4];
-
-  hts_init_htsblk(&r);
-  r.statuscode = 200;
-  r.size = (LLint) INT_MAX + 1;
-  strcpybuff(r.msg, "OK");
-  strcpybuff(r.contenttype, "application/octet-stream");
-  locbuf[0] = '\0';
-  r.location = locbuf;
-  r.is_write = (short int) is_write;
-  cache_add(opt, cache, &r, "example.com", fil, "example.com/big.bin", 1, NULL);
-}
-
-/* Read back `entryname`: extra field (cached headers) and body. Returns the
-   body length, or -1 if the entry is absent or unreadable. */
-static int writefail_read_entry(const char *path, const char *entryname,
-                                char *extra, size_t extralen, char *body,
-                                size_t bodylen) {
-  unzFile z = unzOpen(path);
-  int n = -1;
-
-  if (z == NULL)
-    return -1;
-  if (unzLocateFile(z, entryname, 1) == UNZ_OK &&
-      unzOpenCurrentFile(z) == UNZ_OK) {
-    const int elen = unzGetLocalExtrafield(z, extra, (unsigned) (extralen - 1));
-
-    if (elen >= 0) {
-      extra[elen] = '\0';
-      n = unzReadCurrentFile(z, body, (unsigned) bodylen);
-    }
-    unzCloseCurrentFile(z);
-  }
-  unzClose(z);
-  return n;
-}
-
-/* Cache write-failure policy (#174/#219): fatal errno or a failure streak
-   stops the mirror (exit_xh=-1, no crash); isolated/oversized drops the entry.
- */
-int cache_write_failure_selftest(httrackp *opt, const char *dir) {
-  int fail = 0;
-  char path[HTS_URLMAXSIZE];
-  /* incompressible + big, so deflate flushes (and fails) mid-write, before
-   * close */
-  static const size_t body_len = 256 * 1024;
-  char *body = malloct(body_len);
-  int phase;
-
-  gen_body(body, body_len, 1 /* incompressible */);
-  fconcat(path, sizeof(path), dir, "/wfail.zip");
-
-  /* phase 0: fatal errno (ENOSPC) aborts at once; phase 1: persistent EIO
-     drops entries until the streak caps out, then aborts. */
-  for (phase = 0; phase < 2; phase++) {
-    cache_back cache;
-    writefail_inject inj;
-    int writes_after_fail;
-
-    inj.budget = (phase == 0) ? 4096 : 0;
-    inj.fail_errno = (phase == 0) ? ENOSPC : EIO;
-    inj.writes = 0;
-    inj.fail_once = 0;
-    memset(&cache, 0, sizeof(cache));
-    cache.type = 1;
-    cache.log = stderr;
-    cache.errlog = stderr;
-    cache.hashtable = coucal_new(0);
-    cache.zipOutput = selftest_open_failing_zip(path, &inj);
-    if (cache.zipOutput == NULL) {
-      fprintf(stderr, "cache-writefail: could not open injected ZIP\n");
-      fail++;
-      continue;
-    }
-
-    opt->state.exit_xh = 0; /* clear; the failing write must set it to -1 */
-    if (phase == 0) {
-      writefail_store(opt, &cache, "/blob.bin", body, body_len);
-    } else {
-      /* the abort must land exactly on the 8th consecutive failure */
-      int i;
-
-      for (i = 0; i < 7; i++) {
-        char fil[32];
-
-        snprintf(fil, sizeof(fil), "/b%d.bin", i);
-        writefail_store(opt, &cache, fil, body, 16);
-      }
-      if (cache.zipWriteFailed) {
-        fprintf(stderr, "cache-writefail: phase 1: aborted before the "
-                        "8th consecutive failure\n");
-        fail++;
-      }
-      writefail_store(opt, &cache, "/b7.bin", body, 16);
-    }
-    if (!cache.zipWriteFailed) {
-      fprintf(stderr, "cache-writefail: phase %d: write error not caught\n",
-              phase);
-      fail++;
-    }
-    if (opt->state.exit_xh != -1) {
-      fprintf(stderr,
-              "cache-writefail: phase %d: mirror not aborted (exit_xh=%d)\n",
-              phase, opt->state.exit_xh);
-      fail++;
-    }
-
-    /* a flagged cache must no-op a sibling write: no further backend write */
-    writes_after_fail = inj.writes;
-    writefail_store(opt, &cache, "/blob2.bin", body, 16);
-    if (inj.writes != writes_after_fail) {
-      fprintf(stderr,
-              "cache-writefail: phase %d: sibling write re-entered the broken "
-              "stream (%d extra backend writes)\n",
-              phase, inj.writes - writes_after_fail);
-      fail++;
-    }
-
-    if (cache.zipOutput != NULL) {
-      zipClose(cache.zipOutput,
-               NULL); /* best-effort; may fail on the backend */
-      cache.zipOutput = NULL;
-    }
-  }
-
-  /* failures with successes in between reset the streak: never aborts */
-  {
-    cache_back cache;
-    writefail_inject inj;
-    int i;
-
-    inj.budget = (size_t) -1;
-    inj.fail_errno = EIO;
-    inj.writes = 0;
-    inj.fail_once = 0;
-    memset(&cache, 0, sizeof(cache));
-    cache.type = 1;
-    cache.log = stderr;
-    cache.errlog = stderr;
-    cache.hashtable = coucal_new(0);
-    cache.zipOutput = selftest_open_failing_zip(path, &inj);
-    opt->state.exit_xh = 0;
-
-    for (i = 0; i < 10; i++) {
-      char fil[32];
-
-      inj.budget = 0; /* this store fails */
-      snprintf(fil, sizeof(fil), "/s%d.bin", i);
-      writefail_store(opt, &cache, fil, body, 16);
-      inj.budget = (size_t) -1; /* this one succeeds and resets the streak */
-      snprintf(fil, sizeof(fil), "/ok%d.bin", i);
-      writefail_store(opt, &cache, fil, body, 16);
-    }
-    if (cache.zipWriteFailed || opt->state.exit_xh != 0) {
-      fprintf(stderr,
-              "cache-writefail: scattered: non-consecutive failures aborted "
-              "the mirror (flagged=%d, exit_xh=%d)\n",
-              (int) cache.zipWriteFailed, opt->state.exit_xh);
-      fail++;
-    }
-    zipClose(cache.zipOutput, NULL);
-    cache.zipOutput = NULL;
-  }
-
-  /* isolated failure: only that entry drops; a later sibling round-trips */
-  {
-    cache_back cache;
-    writefail_inject inj;
-    char extra[8192];
-    char rbody[64];
-    int n;
-
-    inj.budget = 4096;
-    inj.fail_errno = EIO;
-    inj.writes = 0;
-    inj.fail_once = 1;
-    memset(&cache, 0, sizeof(cache));
-    cache.type = 1;
-    cache.log = stderr;
-    cache.errlog = stderr;
-    cache.hashtable = coucal_new(0);
-    cache.zipOutput = selftest_open_failing_zip(path, &inj);
-    opt->state.exit_xh = 0;
-
-    writefail_store(opt, &cache, "/blob.bin", body, body_len);
-    if (cache.zipWriteFailed || opt->state.exit_xh != 0) {
-      fprintf(stderr,
-              "cache-writefail: skip: isolated failure aborted the mirror "
-              "(flagged=%d, exit_xh=%d)\n",
-              (int) cache.zipWriteFailed, opt->state.exit_xh);
-      fail++;
-    }
-    writefail_store(opt, &cache, "/blob2.bin", body, 16);
-    zipClose(cache.zipOutput, NULL);
-    cache.zipOutput = NULL;
-    n = writefail_read_entry(path, "http://example.com/blob2.bin", extra,
-                             sizeof(extra), rbody, sizeof(rbody));
-    if (n != 16 || memcmp(rbody, body, 16) != 0) {
-      fprintf(stderr,
-              "cache-writefail: skip: sibling entry lost after a skipped "
-              "entry (%d)\n",
-              n);
-      fail++;
-    }
-  }
-
-  /* >2GB bodies: in-memory drops the entry, on-disk degrades to headers-only */
-  {
-    cache_back cache;
-    writefail_inject inj;
-    char extra[8192];
-    char rbody[64];
-    int n;
-
-    inj.budget = (size_t) -1; /* no injected failure */
-    inj.fail_errno = 0;
-    inj.writes = 0;
-    inj.fail_once = 0;
-    memset(&cache, 0, sizeof(cache));
-    cache.type = 1;
-    cache.log = stderr;
-    cache.errlog = stderr;
-    cache.hashtable = coucal_new(0);
-    cache.zipOutput = selftest_open_failing_zip(path, &inj);
-    opt->state.exit_xh = 0;
-
-    writefail_store_oversized(opt, &cache, "/bigmem.bin", 0 /* in-memory */);
-    writefail_store_oversized(opt, &cache, "/bigdisk.bin", 1 /* on-disk */);
-    zipClose(cache.zipOutput, NULL);
-    cache.zipOutput = NULL;
-
-    if (cache.zipWriteFailed || opt->state.exit_xh != 0) {
-      fprintf(stderr,
-              "cache-writefail: oversize: mirror aborted (flagged=%d, "
-              "exit_xh=%d)\n",
-              (int) cache.zipWriteFailed, opt->state.exit_xh);
-      fail++;
-    }
-    if (writefail_read_entry(path, "http://example.com/bigmem.bin", extra,
-                             sizeof(extra), rbody, sizeof(rbody)) >= 0) {
-      fprintf(stderr,
-              "cache-writefail: oversize: in-memory entry was stored\n");
-      fail++;
-    }
-    n = writefail_read_entry(path, "http://example.com/bigdisk.bin", extra,
-                             sizeof(extra), rbody, sizeof(rbody));
-    if (n != 0 || strstr(extra, "X-In-Cache: 0") == NULL) {
-      fprintf(stderr,
-              "cache-writefail: oversize: on-disk entry not stored "
-              "headers-only (%d)\n",
-              n);
-      fail++;
-    }
-  }
-
-  freet(body);
-  return fail;
-}
-
 int cache_selftests(httrackp *opt, const char *dir) {
   int failures = 0;
   cache_back cache;
@@ -901,583 +585,3 @@ int cache_golden_selftest(httrackp *opt, const char *dir, int regen) {
 
   return failures;
 }
-
-/* --- hts_cache_reconcile() policies -------------------------------------- */
-
-/* All reconcile inputs/outputs, wiped between cases. */
-static const char *const reconcile_files[] = {
-    "hts-cache/new.zip", "hts-cache/old.zip",   "hts-cache/new.dat",
-    "hts-cache/old.dat", "hts-cache/new.ndx",   "hts-cache/old.ndx",
-    "hts-cache/new.lst", "hts-cache/old.lst",   "hts-cache/new.txt",
-    "hts-cache/old.txt", "hts-in_progress.lock"};
-
-static char *reconcile_st_path(httrackp *opt, const char *name) {
-  return fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                 StringBuff(opt->path_log), name);
-}
-
-static void reconcile_wipe(httrackp *opt) {
-  size_t i;
-
-  for (i = 0; i < sizeof(reconcile_files) / sizeof(reconcile_files[0]); i++)
-    remove(reconcile_st_path(opt, reconcile_files[i]));
-}
-
-/* Create a filler file of exactly `size` bytes. */
-static void reconcile_put(httrackp *opt, const char *name, size_t size) {
-  FILE *const fp = fopen(reconcile_st_path(opt, name), "wb");
-  static const char filler[1024] = {'x'};
-
-  assertf(fp != NULL);
-  while (size > 0) {
-    const size_t n = size > sizeof(filler) ? sizeof(filler) : size;
-
-    assertf(fwrite(filler, 1, n, fp) == n);
-    size -= n;
-  }
-  fclose(fp);
-}
-
-/* Expect `name` to weigh `size` bytes, or be absent when size == -1. */
-static int reconcile_expect(httrackp *opt, const char *name, off_t size,
-                            const char *what) {
-  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,
-            name, (int) got, (int) size);
-    return 1;
-  }
-  return 0;
-}
-
-int cache_reconcile_selftest(httrackp *opt, const char *dir) {
-  int failures = 0;
-
-  /* around the interrupted-run thresholds (new < 32768, old > 65536) */
-  static const off_t TINY = 1024, MID = 40000, SOLID = 131072;
-
-  golden_setup(opt, dir);
-#ifdef _WIN32
-  mkdir(reconcile_st_path(opt, "hts-cache"));
-#else
-  mkdir(reconcile_st_path(opt, "hts-cache"), HTS_PROTECT_FOLDER);
-#endif
-
-  /* PROMOTE: a zip old generation replaces a missing new one */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_PROMOTE);
-  failures += reconcile_expect(opt, "hts-cache/new.zip", SOLID, "promote-zip");
-  failures += reconcile_expect(opt, "hts-cache/old.zip", -1, "promote-zip");
-
-  /* PROMOTE: an existing new.zip is left alone */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_PROMOTE);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", TINY, "promote-zip-noop");
-  failures +=
-      reconcile_expect(opt, "hts-cache/old.zip", SOLID, "promote-zip-noop");
-
-  /* PROMOTE: the removed pre-3.31 legacy pair is left alone */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/old.dat", SOLID);
-  reconcile_put(opt, "hts-cache/old.ndx", TINY);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_PROMOTE);
-  failures += reconcile_expect(opt, "hts-cache/new.dat", -1, "promote-dat");
-  failures += reconcile_expect(opt, "hts-cache/new.ndx", -1, "promote-dat");
-  failures += reconcile_expect(opt, "hts-cache/old.dat", SOLID, "promote-dat");
-  failures += reconcile_expect(opt, "hts-cache/old.ndx", TINY, "promote-dat");
-
-  /* INTERRUPTED: no lock file, no action */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", TINY, "interrupted-nolock");
-
-  /* INTERRUPTED: an absent new.zip must NOT promote old.zip (fsize(-1) would
-     spuriously pass "< TINY"); leave the solid old generation for ROLLBACK */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-in_progress.lock", 0);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", -1, "interrupted-nonew");
-  failures +=
-      reconcile_expect(opt, "hts-cache/old.zip", SOLID, "interrupted-nonew");
-
-  /* INTERRUPTED: stalled tiny new.zip loses to a solid old.zip (was dead for
-     zip caches: the arm was gated on a legacy new.dat) */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-in_progress.lock", 0);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", SOLID, "interrupted-zip");
-  failures += reconcile_expect(opt, "hts-cache/old.zip", -1, "interrupted-zip");
-
-  /* INTERRUPTED: old below the confidence threshold, keep new */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-in_progress.lock", 0);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  reconcile_put(opt, "hts-cache/old.zip", MID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", TINY, "interrupted-smallold");
-
-  /* INTERRUPTED: new big enough to trust, keep it */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-in_progress.lock", 0);
-  reconcile_put(opt, "hts-cache/new.zip", MID);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.zip", MID, "interrupted-bignew");
-
-  /* INTERRUPTED: the removed pre-3.31 legacy pair is left alone */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-in_progress.lock", 0);
-  reconcile_put(opt, "hts-cache/new.dat", TINY);
-  reconcile_put(opt, "hts-cache/new.ndx", TINY);
-  reconcile_put(opt, "hts-cache/old.dat", SOLID);
-  reconcile_put(opt, "hts-cache/old.ndx", MID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_INTERRUPTED);
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.dat", TINY, "interrupted-dat");
-  failures +=
-      reconcile_expect(opt, "hts-cache/new.ndx", TINY, "interrupted-dat");
-  failures +=
-      reconcile_expect(opt, "hts-cache/old.dat", SOLID, "interrupted-dat");
-  failures +=
-      reconcile_expect(opt, "hts-cache/old.ndx", MID, "interrupted-dat");
-
-  /* ROLLBACK: the old zip generation is restored (a zip cache used to lose
-     its only good generation here) */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  reconcile_put(opt, "hts-cache/old.zip", SOLID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_ROLLBACK);
-  failures += reconcile_expect(opt, "hts-cache/new.zip", SOLID, "rollback-zip");
-  failures += reconcile_expect(opt, "hts-cache/old.zip", -1, "rollback-zip");
-
-  /* ROLLBACK: sidecars are restored regardless of format */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.lst", TINY);
-  reconcile_put(opt, "hts-cache/old.lst", MID);
-  reconcile_put(opt, "hts-cache/old.txt", MID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_ROLLBACK);
-  failures += reconcile_expect(opt, "hts-cache/new.lst", MID, "rollback-lst");
-  failures += reconcile_expect(opt, "hts-cache/new.txt", MID, "rollback-txt");
-
-  /* ROLLBACK: sidecars restored, the removed pre-3.31 pair left alone */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.dat", TINY);
-  reconcile_put(opt, "hts-cache/old.dat", SOLID);
-  reconcile_put(opt, "hts-cache/old.ndx", MID);
-  reconcile_put(opt, "hts-cache/old.lst", MID);
-  reconcile_put(opt, "hts-cache/old.txt", MID);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_ROLLBACK);
-  failures += reconcile_expect(opt, "hts-cache/new.dat", TINY, "rollback-dat");
-  failures += reconcile_expect(opt, "hts-cache/new.ndx", -1, "rollback-dat");
-  failures += reconcile_expect(opt, "hts-cache/old.dat", SOLID, "rollback-dat");
-  failures += reconcile_expect(opt, "hts-cache/old.ndx", MID, "rollback-dat");
-  failures += reconcile_expect(opt, "hts-cache/new.lst", MID, "rollback-dat");
-  failures += reconcile_expect(opt, "hts-cache/new.txt", MID, "rollback-dat");
-
-  /* ROLLBACK: nothing to restore, the new generation stays */
-  reconcile_wipe(opt);
-  reconcile_put(opt, "hts-cache/new.zip", TINY);
-  hts_cache_reconcile(opt, CACHE_RECONCILE_ROLLBACK);
-  failures += reconcile_expect(opt, "hts-cache/new.zip", TINY, "rollback-noop");
-
-  reconcile_wipe(opt);
-  return failures;
-}
-
-/* The pre-3.31 .dat/.ndx import was removed: cache_init must refuse the
-   legacy pair, leave the files in place, and not flag an update run. */
-int cache_legacy_refused_selftest(httrackp *opt, const char *dir) {
-  int failures = 0;
-  int variant;
-
-  selftest_tag = "cache-legacy";
-  golden_setup(opt, dir);
-#ifdef _WIN32
-  mkdir(reconcile_st_path(opt, "hts-cache"));
-#else
-  mkdir(reconcile_st_path(opt, "hts-cache"), HTS_PROTECT_FOLDER);
-#endif
-
-  /* variant 0: old.dat/old.ndx (--update layout); 1: new.dat/new.ndx (ro) */
-  for (variant = 0; variant < 2; variant++) {
-    cache_back cache;
-    const char *const dat =
-        variant == 0 ? "hts-cache/old.dat" : "hts-cache/new.dat";
-    const char *const ndx =
-        variant == 0 ? "hts-cache/old.ndx" : "hts-cache/new.ndx";
-
-    reconcile_wipe(opt);
-    reconcile_put(opt, dat, 4096);
-    reconcile_put(opt, ndx, 4096);
-    opt->is_update = 0;
-    selftest_open(&cache, opt, /*ro*/ variant == 1);
-    if (cache_readable(&cache)) {
-      printf("cache-legacy: variant %d imported a removed format\n", variant);
-      failures++;
-    }
-    if (coucal_nitems(cache.hashtable) != 0) { /* no phantom index entries */
-      printf("cache-legacy: variant %d imported index entries\n", variant);
-      failures++;
-    }
-    if (opt->is_update) {
-      printf("cache-legacy: variant %d flagged an update\n", variant);
-      failures++;
-    }
-    if (fsize(reconcile_st_path(opt, dat)) != 4096 ||
-        fsize(reconcile_st_path(opt, ndx)) != 4096) {
-      printf("cache-legacy: variant %d touched the legacy files\n", variant);
-      failures++;
-    }
-    if (cache.lst != NULL) {
-      fclose(cache.lst);
-      cache.lst = NULL;
-    }
-    if (cache.txt != NULL) {
-      fclose(cache.txt);
-      cache.txt = NULL;
-    }
-    selftest_close(&cache);
-  }
-
-  /* a healthy zip must win over stray legacy files, with no refusal */
-  {
-    cache_back cache;
-    const char *const body = "<html>zip wins</html>";
-
-    reconcile_wipe(opt);
-    selftest_open_for_write(&cache, opt);
-    store_entry(opt, &cache, "example.com", "/", "example.com/index.html", 200,
-                "OK", "text/html", "utf-8", "", "", "", "", body, strlen(body));
-    selftest_close(&cache);
-    reconcile_put(opt, "hts-cache/old.ndx", 4096);
-    reconcile_put(opt, "hts-cache/old.dat", 4096);
-    selftest_open_for_read(&cache, opt);
-    if (!cache_readable(&cache)) {
-      printf("cache-legacy: stray legacy files shadowed the zip cache\n");
-      failures++;
-    }
-    failures +=
-        check_entry(opt, &cache, "example.com", "/", 200, "OK", "text/html",
-                    "utf-8", "", "", "", "", body, strlen(body));
-    if (fsize(reconcile_st_path(opt, "hts-cache/old.ndx")) != 4096 ||
-        fsize(reconcile_st_path(opt, "hts-cache/old.dat")) != 4096) {
-      printf("cache-legacy: zip-wins pass touched the legacy files\n");
-      failures++;
-    }
-    if (cache.lst != NULL) {
-      fclose(cache.lst);
-      cache.lst = NULL;
-    }
-    if (cache.txt != NULL) {
-      fclose(cache.txt);
-      cache.txt = NULL;
-    }
-    selftest_close(&cache);
-  }
-
-  reconcile_wipe(opt);
-  return failures;
-}
-
-/* --- read-side corruption injection --------------------------------------- */
-
-/* canary read back intact after each corruption; victim gets the byte surgery
- */
-#define CORRUPT_ADR "corrupt.example.com"
-static char corrupt_body_a[33 + 1];
-static char corrupt_body_b[44 + 1];
-
-/* Write a fresh two-entry cache: /canary.html then /victim.html. */
-static void corrupt_build(httrackp *opt) {
-  cache_back cache;
-
-  memset(corrupt_body_a, 'a', sizeof(corrupt_body_a) - 1);
-  memset(corrupt_body_b, 'b', sizeof(corrupt_body_b) - 1);
-  remove(reconcile_st_path(opt, "hts-cache/new.zip"));
-  remove(reconcile_st_path(opt, "hts-cache/old.zip"));
-  selftest_open_for_write(&cache, opt);
-  store_entry(opt, &cache, CORRUPT_ADR, "/canary.html", "canary.html", 200,
-              "OK", "text/html", "utf-8", "", "", "", "", corrupt_body_a,
-              strlen(corrupt_body_a));
-  store_entry(opt, &cache, CORRUPT_ADR, "/victim.html", "victim.html", 200,
-              "OK", "text/html", "utf-8", "", "", "", "", corrupt_body_b,
-              strlen(corrupt_body_b));
-  selftest_close(&cache);
-}
-
-/* Like corrupt_build, but the victim carries a 20-char Etag whose header line
-   is later overwritten with a forged oversized X-Size (same byte length). */
-static void corrupt_build_etag(httrackp *opt) {
-  cache_back cache;
-
-  memset(corrupt_body_a, 'a', sizeof(corrupt_body_a) - 1);
-  memset(corrupt_body_b, 'b', sizeof(corrupt_body_b) - 1);
-  remove(reconcile_st_path(opt, "hts-cache/new.zip"));
-  remove(reconcile_st_path(opt, "hts-cache/old.zip"));
-  selftest_open_for_write(&cache, opt);
-  store_entry(opt, &cache, CORRUPT_ADR, "/canary.html", "canary.html", 200,
-              "OK", "text/html", "utf-8", "", "", "", "", corrupt_body_a,
-              strlen(corrupt_body_a));
-  store_entry(opt, &cache, CORRUPT_ADR, "/victim.html", "victim.html", 200,
-              "OK", "text/html", "utf-8", "", "AAAAAAAAAAAAAAAAAAAA", "", "",
-              corrupt_body_b, strlen(corrupt_body_b));
-  selftest_close(&cache);
-}
-
-/* Like corrupt_build_etag, but the victim is headers-only (X-In-Cache: 0,
-   body on disk): the shape every non-html file is stored with. */
-static void corrupt_build_disk(httrackp *opt) {
-  cache_back cache;
-  htsblk w;
-  char locw[4];
-  char BIGSTK save[HTS_URLMAXSIZE * 2];
-  char BIGSTK catbuff[HTS_URLMAXSIZE * 2];
-  char *path;
-  FILE *fp;
-
-  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"));
-  fconcat(save, sizeof(save), StringBuff(opt->path_html_utf8),
-          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,
-              strlen(corrupt_body_a));
-  hts_init_htsblk(&w);
-  w.statuscode = 200;
-  w.size = (LLint) sizeof(corrupt_body_b) - 1;
-  strcpybuff(w.msg, "OK");
-  strcpybuff(w.contenttype, "application/octet-stream");
-  strcpybuff(w.etag, "AAAAAAAAAAAAAAAAAAAA");
-  locw[0] = '\0';
-  w.location = locw;
-  w.is_write = 0;
-  cache_add(opt, &cache, &w, CORRUPT_ADR, "/victim.bin", save,
-            0 /* all_in_cache */, NULL);
-  selftest_close(&cache);
-  /* the reader only checks this file exists; it never reads it here */
-  path = fconv(catbuff, sizeof(catbuff), save);
-  (void) structcheck(path);
-  fp = FOPEN(path, "wb");
-  assertf(fp != NULL);
-  fclose(fp);
-}
-
-/* Patch the nth of total occurrences of pat (same-length rep) in new.zip. */
-static void corrupt_patch(httrackp *opt, const char *pat, size_t patlen,
-                          const char *rep, size_t nth, size_t total) {
-  LLint fsz = 0;
-  char *data = readfile2(reconcile_st_path(opt, "hts-cache/new.zip"), &fsz);
-  const size_t n = (size_t) fsz;
-  size_t k, hits = 0, at = 0;
-  FILE *fp;
-
-  assertf(data != NULL);
-  for (k = 0; k + patlen <= n; k++) {
-    if (memcmp(data + k, pat, patlen) == 0) {
-      hits++;
-      if (hits == nth)
-        at = k;
-    }
-  }
-  assertf(hits == total);
-  memcpy(data + at, rep, patlen);
-  fp = fopen(reconcile_st_path(opt, "hts-cache/new.zip"), "wb");
-  assertf(fp != NULL);
-  assertf(fwrite(data, 1, n, fp) == n);
-  fclose(fp);
-  freet(data);
-}
-
-/* Garbage the first bytes of the victim's deflated data (2nd local header). */
-static void corrupt_victim_body(httrackp *opt) {
-  LLint fsz = 0;
-  char *data = readfile2(reconcile_st_path(opt, "hts-cache/new.zip"), &fsz);
-  const size_t n = (size_t) fsz;
-  size_t k, hits = 0, off = 0;
-  FILE *fp;
-
-  assertf(data != NULL);
-  for (k = 0; k + 4 <= n; k++) {
-    if (memcmp(data + k, "PK\x03\x04", 4) == 0 && ++hits == 2) {
-      const size_t namelen =
-          (unsigned char) data[k + 26] | ((unsigned char) data[k + 27] << 8);
-      const size_t extralen =
-          (unsigned char) data[k + 28] | ((unsigned char) data[k + 29] << 8);
-
-      off = k + 30 + namelen + extralen;
-    }
-  }
-  assertf(hits == 2);
-  assertf(off != 0 && off + 4 <= n);
-  memset(data + off, 0xFF, 4);
-  fp = fopen(reconcile_st_path(opt, "hts-cache/new.zip"), "wb");
-  assertf(fp != NULL);
-  assertf(fwrite(data, 1, n, fp) == n);
-  fclose(fp);
-  freet(data);
-}
-
-/* Read the corrupt /victim.html and, in the SAME read session, the intact
-   /canary.html: the victim must be rejected (wantmsg pins which path) and the
-   canary must still decode byte-exact, proving one bad entry never taints a
-   sibling read. */
-static int corrupt_expect_victim_fil(httrackp *opt, const char *fil,
-                                     const char *wantmsg, const char *what) {
-  cache_back cache;
-  htsblk v, c;
-  char BIGSTK lv[HTS_URLMAXSIZE * 2];
-  char BIGSTK lc[HTS_URLMAXSIZE * 2];
-  int fail = 0;
-
-  selftest_open_for_read(&cache, opt);
-  lv[0] = lc[0] = '\0';
-  v = cache_readex(opt, &cache, CORRUPT_ADR, fil, "", lv, NULL, 1);
-  if (v.statuscode != STATUSCODE_INVALID) {
-    fprintf(stderr, "%s: %s: victim: statuscode is %d, expected %d\n",
-            selftest_tag, what, v.statuscode, STATUSCODE_INVALID);
-    fail++;
-  }
-  if (wantmsg != NULL && strcmp(v.msg, wantmsg) != 0) {
-    fprintf(stderr, "%s: %s: victim: msg is '%s', expected '%s'\n",
-            selftest_tag, what, v.msg, wantmsg);
-    fail++;
-  }
-  c = cache_readex(opt, &cache, CORRUPT_ADR, "/canary.html", "", lc, NULL, 1);
-  if (c.statuscode != 200 || c.adr == NULL ||
-      c.size != (LLint) strlen(corrupt_body_a) ||
-      memcmp(c.adr, corrupt_body_a, strlen(corrupt_body_a)) != 0) {
-    fprintf(stderr, "%s: %s: canary tainted (status %d)\n", selftest_tag, what,
-            c.statuscode);
-    fail++;
-  }
-  if (v.adr != NULL)
-    freet(v.adr);
-  if (c.adr != NULL)
-    freet(c.adr);
-  selftest_close(&cache);
-  return fail;
-}
-
-static int corrupt_expect_victim(httrackp *opt, const char *wantmsg,
-                                 const char *what) {
-  return corrupt_expect_victim_fil(opt, "/victim.html", wantmsg, what);
-}
-
-/* Headers-only probe of the disk victim: must parse OK with the size kept. */
-static int corrupt_expect_disk_header(httrackp *opt, LLint wantsize,
-                                      const char *what) {
-  cache_back cache;
-  htsblk v;
-  char BIGSTK lv[HTS_URLMAXSIZE * 2];
-  int fail = 0;
-
-  selftest_open_for_read(&cache, opt);
-  lv[0] = '\0';
-  v = cache_readex(opt, &cache, CORRUPT_ADR, "/victim.bin", NULL, lv, NULL, 1);
-  if (v.statuscode != 200 || v.size != wantsize) {
-    fprintf(stderr,
-            "%s: %s: statuscode %d size " LLintP ", expected 200/" LLintP "\n",
-            selftest_tag, what, v.statuscode, (LLint) v.size, wantsize);
-    fail++;
-  }
-  if (v.adr != NULL)
-    freet(v.adr);
-  selftest_close(&cache);
-  return fail;
-}
-
-/* One zip corruption case: build, patch, then check victim+canary in-session.
- */
-static int corrupt_case_zip(httrackp *opt, const char *pat, const char *rep,
-                            size_t nth, size_t total, const char *wantmsg,
-                            const char *what) {
-  corrupt_build(opt);
-  corrupt_patch(opt, pat, strlen(pat), rep, nth, total);
-  return corrupt_expect_victim(opt, wantmsg, what);
-}
-
-int cache_corruption_selftest(httrackp *opt, const char *dir) {
-  int failures = 0;
-
-  selftest_tag = "cache-corrupt";
-  golden_setup(opt, dir);
-
-  failures +=
-      corrupt_case_zip(opt, "X-Size: 44", "X-Size: 99", 1, 1,
-                       "Cache Read Error : Read Data", "oversized X-Size");
-  failures +=
-      corrupt_case_zip(opt, "X-Size: 44", "X-Size: -4", 1, 1,
-                       "Cache Read Error : Bad Size", "negative X-Size");
-  /* both entries carry the line; the victim's is the second */
-  failures += corrupt_case_zip(opt, "X-In-Cache: 1", "X-In-Cache: 0", 2, 2,
-                               "Previous cache file not found (empty filename)",
-                               "blanked X-In-Cache");
-  /* smashed local file header: the entry is dropped at index load */
-  failures +=
-      corrupt_case_zip(opt, "PK\x03\x04", "XK\x03\x04", 2, 2,
-                       "File Cache Entry Not Found", "smashed local header");
-
-  corrupt_build(opt);
-  corrupt_victim_body(opt);
-  failures += corrupt_expect_victim(opt, "Cache Read Error : Read Data",
-                                    "garbled deflate stream");
-
-  /* An X-Size above INT_MAX is positive as int64 (slips a bare sign check) but
-     truncates negative in the (int) cast the malloc uses: a wraparound alloc.
-     cache_add asserts size fits an int, so such a value only reaches the reader
-     from a corrupt/foreign cache; inject it by overwriting the victim's long
-     Etag line with a same-length forged X-Size line (the parser keeps the last
-     X-Size it sees), keeping the zip byte-length and offsets intact. */
-  corrupt_build_etag(opt);
-  corrupt_patch(opt, "Etag: AAAAAAAAAAAAAAAAAAAA", 26,
-                "X-Size: 2147483648AAAAAAAA", 1, 1);
-  failures += corrupt_expect_victim(opt, "Cache Read Error : Bad Size",
-                                    "X-Size above INT_MAX");
-
-  /* A headers-only entry (X-In-Cache: 0) may carry an X-Size >= INT_MAX: that
-     is how every >2GB non-html file is stored. It must survive a header probe
-     (or every update re-fetches the file); an in-memory read still rejects. */
-  corrupt_build_disk(opt);
-  corrupt_patch(opt, "Etag: AAAAAAAAAAAAAAAAAAAA", 26,
-                "X-Size: 2147483648AAAAAAAA", 1, 1);
-  failures += corrupt_expect_disk_header(opt, (LLint) 2147483648LL,
-                                         "headers-only X-Size above INT_MAX");
-  failures += corrupt_expect_victim_fil(opt, "/victim.bin",
-                                        "Cache Read Error : Bad Size",
-                                        "in-memory X-Size above INT_MAX");
-
-  /* exactly INT_MAX pins the >= boundary: (int) r.size + 1 would overflow */
-  corrupt_build_disk(opt);
-  corrupt_patch(opt, "Etag: AAAAAAAAAAAAAAAAAAAA", 26,
-                "X-Size: 2147483647AAAAAAAA", 1, 1);
-  failures += corrupt_expect_victim_fil(opt, "/victim.bin",
-                                        "Cache Read Error : Bad Size",
-                                        "in-memory X-Size at INT_MAX");
-
-  /* the negative check must stay global, headers-only included */
-  corrupt_build_disk(opt);
-  corrupt_patch(opt, "Etag: AAAAAAAAAAAAAAAAAAAA", 26,
-                "X-Size: -2147483648AAAAAAA", 1, 1);
-  failures += corrupt_expect_victim_fil(opt, "/victim.bin",
-                                        "Cache Read Error : Bad Size",
-                                        "headers-only negative X-Size");
-
-  return failures;
-}

src/htscache_selftest.h

@@ -52,23 +52,6 @@ int cache_selftests(httrackp *opt, const char *dir);
    committed file, never by the test). Returns the failed-check count. */
 int cache_golden_selftest(httrackp *opt, const char *dir, int regen);
 
-/* Cache write-failure policy (#174/#219): abort on fatal errno or a streak,
-   drop just the entry otherwise. Returns the failed-check count. */
-int cache_write_failure_selftest(httrackp *opt, const char *dir);
-
-/* Exercise the hts_cache_reconcile() generation policies on file fixtures
-   under <dir>. Returns the failed-check count. */
-int cache_reconcile_selftest(httrackp *opt, const char *dir);
-
-/* Verify cache_init refuses a pre-3.31 .dat/.ndx cache without touching it.
-   Returns the number of failed checks (0 = pass). */
-int cache_legacy_refused_selftest(httrackp *opt, const char *dir);
-
-/* Inject read-side corruption (zip byte surgery: bad size, header, deflate)
-   under <dir> and assert every case degrades to STATUSCODE_INVALID without
-   tainting a sibling entry. */
-int cache_corruption_selftest(httrackp *opt, const char *dir);
-
 #endif
 
 #endif

src/htscatchurl.c

@@ -64,7 +64,7 @@ Please visit our Website: http://www.httrack.com
 // catch_url_init(&port,&return_host);
 HTSEXT_API T_SOC catch_url_init_std(int *port_prox, char *adr_prox) {
   T_SOC soc;
-  int try_to_listen_to[] = {8080, 3128, 80, 81, 82, 8081, 3129, 0, -1};
+  int try_to_listen_to[] = { 8080, 3128, 80, 81, 82, 8081, 3129, 31337, 0, -1 };
   int i = 0;
 
   do {
@@ -175,9 +175,7 @@ HTSEXT_API hts_boolean catch_url(T_SOC soc, char *url, char *method,
       //
       socinput(soc, line, 1000);
       if (strnotempty(line)) {
-        /* widths bound the caller buffers: method[32], url[HTS_URLMAXSIZE*2],
-           protocol[256] */
-        if (sscanf(line, "%31s %2047s %255s", method, url, protocol) == 3) {
+        if (sscanf(line, "%s %s %s", method, url, protocol) == 3) {
           lien_adrfil af;
 
           // méthode en majuscule
@@ -197,6 +195,7 @@ HTSEXT_API hts_boolean catch_url(T_SOC soc, char *url, char *method,
             htsblk blkretour;
 
             hts_init_htsblk(&blkretour);
+            //memset(&blkretour, 0, sizeof(htsblk));    // effacer
             blkretour.location = loc;   // si non nul, contiendra l'adresse véritable en cas de moved xx
             // Lire en têtes restants
             sprintf(data, "%s %s %s\r\n", method, af.fil, protocol);
@@ -206,8 +205,8 @@ HTSEXT_API hts_boolean catch_url(T_SOC soc, char *url, char *method,
               strlcatbuff(data, line, CATCH_URL_DATA_SIZE);
               strlcatbuff(data, "\r\n", CATCH_URL_DATA_SIZE);
             }
-            // CR/LF final de l'en tête inutile car déja placé via la ligne vide
-            // juste au dessus
+            // CR/LF final de l'en tête inutile car déja placé via la ligne vide juste au dessus
+            //strcatbuff(data,"\r\n");
             if (blkretour.totalsize > 0) {
               int len = (int) min(blkretour.totalsize, 32000);
               int pos = (int) strlen(data);

src/htscharset.c

@@ -841,6 +841,71 @@ static unsigned int nlz8(unsigned char x) {
     }                                           \
   } while(0)
 
+/* Sample. */
+#if 0
+
+int main(int argc, char **argv) {
+  int i;
+  int hex = 0;
+  
+#define READ_INT(DEST)                                  \
+  ( ( !hex && sscanf(argv[i], "%d", &(DEST)) == 1)      \
+    || (hex && sscanf(argv[i], "%x", &(DEST)) == 1 ) )
+  
+  for(i = 1 ; i < argc ; i++) {
+    unsigned int uc, from, to;
+    
+    if (strcmp(argv[i], "--hex") == 0) {
+      hex = 1;
+    }
+    else if (strcmp(argv[i], "--decimal") == 0) {
+      hex = 0;
+    }
+    else if (strcmp(argv[i], "--decode") == 0) {
+#define RD fgetc_unlocked(stdin)
+#define WR(C) do {                              \
+        if (C != -1) {                          \
+          printf("%04x\n", C);                  \
+        } else if (!feof(stdin)) {              \
+          fprintf(stderr, "read error\n");      \
+          exit(EXIT_FAILURE);                   \
+        }                                       \
+      } while(0)
+      while(!feof(stdin)) {
+        READ_UNICODE(RD, WR);
+      }
+#undef RD
+#undef WR
+    }
+    else if (strcmp(argv[i], "-range") == 0
+             && i + 2 < argc
+             && (++i, 1)
+             && READ_INT(from)
+             && (++i, 1)
+             && READ_INT(to)
+             ) {
+      unsigned int i;
+      for(i = from ; i < to ; i++) {
+#define EM(C) fputc_unlocked(C, stdout)
+        EMIT_UNICODE(i, EM);
+#undef EM
+      }
+    }
+    else if (READ_INT(uc)) {
+#define EM(C) fputc_unlocked(C, stdout)
+      EMIT_UNICODE(uc, EM);
+#undef EM
+    }
+    else {
+      return EXIT_FAILURE;
+    }
+  }
+  
+  return EXIT_SUCCESS;
+}
+
+#endif
+
 /* IDNA helpers. */
 #undef ADD_BYTE
 #undef INCREASE_CAPA
@@ -910,19 +975,19 @@ char *hts_convertStringUTF8ToIDNA(const char *s, size_t size) {
                 /* Reader: can read bytes up to j */
 #define RD ( utfSeq < j ? segData[utfSeq++] : -1 )
 
-                /* Writer: a malformed sequence abandons the encode (NULL) */
-#define WR(C)                                                                  \
-  do {                                                                         \
-    if ((C) != -1) {                                                           \
-      /* copy character */                                                     \
-      assertf(segOutputSize < segSize);                                        \
-      segInt[segOutputSize++] = (C);                                           \
-    } else {                                                                   \
-      freet(segInt);                                                           \
-      FREE_BUFFER();                                                           \
-      return NULL;                                                             \
-    }                                                                          \
-  } while (0)
+                /* Writer: upon error, return FFFD (replacement character) */
+#define WR(C) do { \
+  if ((C) != -1) { \
+    /* copy character */ \
+    assertf(segOutputSize < segSize); \
+    segInt[segOutputSize++] = (C); \
+  } \
+  /* In case of error, abort. */ \
+  else { \
+    FREE_BUFFER(); \
+    return NULL; \
+  } \
+} while(0)
 
                 /* Read/Write Unicode character. */
                 READ_UNICODE(RD, WR);
@@ -1144,7 +1209,7 @@ int hts_isStringUTF8(const char *s, size_t size) {
     /* Reader: can read bytes up to j */
 #define RD ( i < size ? data[i++] : -1 )
 
-    /* Writer: a malformed sequence means the string is not UTF-8 (return 0) */
+    /* Writer: upon error, return FFFD (replacement character) */
 #define WR(C) if ((C) == -1) { return 0; }
 
     /* Read Unicode character. */

src/htsconfig.h

@@ -54,6 +54,10 @@ Please visit our Website: http://www.httrack.com
 // extension par défaut pour fichiers n'en ayant pas
 #define DEFAULT_EXT ".html"
 #define DEFAULT_EXT_SHORT ".htm"
+// #define DEFAULT_BIN_EXT   ".bin"
+// #define DEFAULT_BIN_EXT_SHORT ".bin"
+// #define DEFAULT_EXT       ".txt"
+// #define DEFAULT_EXT_SHORT ".txt"
 
 // éviter les /nul, /con..
 #define HTS_OVERRIDE_DOS_FOLDERS 1
@@ -76,6 +80,10 @@ Please visit our Website: http://www.httrack.com
 // always direct-to-disk (0/1)
 #define HTS_DIRECTDISK_ALWAYS 1
 
+// gérer une table de hachage?
+// REMOVED
+// #define HTS_HASH 1
+
 // fast cache (build hash table)
 #define HTS_FAST_CACHE 1
 
@@ -89,10 +97,27 @@ Please visit our Website: http://www.httrack.com
 // always transform a '//' into a sigle '/'
 #define HTS_STRIP_DOUBLE_SLASH 0
 
+// case-sensitive pour les dossiers et fichiers (0/1)
+// [normalement 1, mais pose des problèmes (url malformée par exemple) et n'est
+// pas très utile..
+// ..et pas bcp respecté]
+// REMOVED
+// #define HTS_CASSE 0
+
+// Un fichier ayant une taille différente du content-length doit il être annulé?
+// SEE opt.tolerant and opt.http10
+// #define HTS_CL_IS_FATAL 0
+
 // une erreur supprime le fichier sur disque
 // (non fixé pour cause de retry)
 #define HTS_REMOVE_BAD_FILES 0
 
+// en cas de Range: xx- donnant un Content-length: xx
+// alors skipper le fichier, considéré comme transmis
+// #define HTS_SKIP_FULL_RANGE 1
+
+// nombre max de filtres que l'utilisateur peut fixer
+// #define HTS_FILTERSMAX 10000
 #define HTS_FILTERSINC 1000
 
 // connect non bloquant? (poll sur write)

src/htscore.h

@@ -193,7 +193,7 @@ struct cache_back {
   /* */
   int type;
   int ro;                   /**< read-only: no new cache is written */
-
+  FILE *dat, *ndx, *olddat; /**< new data, new index, old data files */
   char *use;                /**< in-memory list of cached adr+fil keys */
   FILE *lst;                /**< file list, used for purge */
   FILE *txt;                /**< human-readable file list (info) */
@@ -214,9 +214,6 @@ struct cache_back {
   cache_back_zip_entry *zipEntries;
   int zipEntriesOffs;
   int zipEntriesCapa;
-  hts_boolean
-      zipWriteFailed; /**< a cache write failed; stop touching the stream */
-  int zipWriteFailures; /**< consecutive entry write failures; reset on store */
 };
 
 #ifndef HTS_DEF_FWSTRUCT_hash_struct
@@ -235,12 +232,8 @@ struct hash_struct {
   coucal adrfil;
   /* former address+path -> link index (renamed/moved entries) */
   coucal former_adrfil;
-  /* effective urlhack sub-flags: www.==host / // collapse / query-arg sort */
-  hts_boolean norm_host;
-  hts_boolean norm_slash;
-  hts_boolean norm_query;
-  /* query-strip keys (not owned); set from opt->strip_query at hash_init */
-  const char *strip_query;
+  /* scratch buffers reused across lookups (not reentrant) */
+  int normalized;
   char normfil[HTS_URLMAXSIZE * 2];
   char normfil2[HTS_URLMAXSIZE * 2];
   char catbuff[CATBUFF_SIZE];
@@ -288,12 +281,12 @@ struct filecreate_params {
 
 /* True if a new cache is being written (plain or zip backend). */
 HTS_STATIC int cache_writable(cache_back * cache) {
-  return (cache != NULL && cache->zipOutput != NULL);
+  return (cache != NULL && (cache->dat != NULL || cache->zipOutput != NULL));
 }
 
 /* True if an old cache is available to read (plain or zip backend). */
 HTS_STATIC int cache_readable(cache_back * cache) {
-  return (cache != NULL && cache->zipInput != NULL);
+  return (cache != NULL && (cache->olddat != NULL || cache->zipInput != NULL));
 }
 
 #endif
@@ -363,42 +356,12 @@ void usercommand(httrackp * opt, int exe, const char *cmd, const char *file,
 
 void usercommand_exe(const char *cmd, const char *file);
 
-// Finish the makeindex index.html (footer + refresh meta), run usercommand.
-// Updates *makeindex_done/*makeindex_fp in place; adr/fil are the mode strings.
-void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
-                          FILE **makeindex_fp, int makeindex_links,
-                          const char *makeindex_firstlink,
-                          const char *template_footer, const char *adr,
-                          const char *fil);
-
-// Flush ht_buff[0..ht_len] to save on disk (skip if MD5 unchanged); *fp
-// closed+NULLed on write. Precondition: ht_len>0.
-void hts_finish_html_file(httrackp *opt, cache_back *cache, htsblk *r,
-                          FILE **fp, const char *ht_buff, size_t ht_len,
-                          const char *adr, const char *fil, const char *save);
-
 int filters_init(char ***ptrfilters, int maxfilter, int filterinc);
 
 int fspc(httrackp * opt, FILE * fp, const char *type);
 
 char *next_token(char *p, int flag);
 
-/* Like fil_normalized(), but first drops query keys in STRIP (comma-separated,
-   "*" = all); STRIP NULL/empty behaves exactly like fil_normalized(). */
-char *fil_normalized_filtered(const char *source, char *dest,
-                              const char *strip);
-
-/* As fil_normalized_filtered(), but DO_SLASH/DO_QUERY gate the // collapse and
-   the query-argument sort independently (the urlhack sub-flags). */
-char *fil_normalized_filtered_ex(const char *source, char *dest,
-                                 const char *strip, int do_slash, int do_query);
-
-/* For URL ADR/FIL, return (in DEST) the comma keylist to strip from the
-   '\n'-separated "[pattern=]keys" RULES (patterns matched on host/path via
-   strjoker, last wins); NULL if none match. Feeds fil_normalized_filtered(). */
-const char *hts_query_strip_keys(const char *rules, const char *adr,
-                                 const char *fil, char *dest, size_t destsize);
-
 /* Read a whole file into a freshly malloc'd, NUL-terminated buffer; the caller
    owns it and must release it with freet(). Return NULL on missing/unreadable
    file (readfile_or substitutes defaultdata instead). The byte content is NOT
@@ -412,6 +375,10 @@ char *readfile_utf8(const char *fil);
 
 char *readfile_or(const char *fil, const char *defaultdata);
 
+#if 0
+void check_rate(TStamp stat_timestart, int maxrate);
+#endif
+
 /* Backing (download-slot) scheduler. Operate on the back[] ring (struct_back).
    Not thread-safe; call from the single crawl loop. */
 
@@ -429,19 +396,6 @@ int back_pluggable_sockets(struct_back * sback, httrackp * opt);
 
 int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt);
 
-/* One engine-loop tick: refresh the transfer stats and run the loop callback
-   for slot b (-1 = none). HTS_FALSE = the callback requested an abort. */
-hts_boolean hts_loop_tick(struct_back *sback, httrackp *opt, int b, int ptr);
-
-/* Wait until a test socket can be plugged, pumping transfers, stats and the
-   loop callback; gives up past the -E deadline. HTS_FALSE = callback abort. */
-hts_boolean hts_wait_available_socket(struct_back *sback, httrackp *opt,
-                                      cache_back *cache, int ptr);
-
-/* Randomized inter-file pause target in [min_ms,max_ms] (#185), derived from a
-   timestamp seed so it is stable within one gap and rerolls per launch. */
-int hts_pause_target_ms(TStamp seed, int min_ms, int max_ms);
-
 /* Schedule more links from the heap into free slots. Returns the number queued,
    or <=0 if none could be added (no free slot / paused / stopped). */
 int back_fill(struct_back * sback, httrackp * opt, cache_back * cache,
@@ -463,6 +417,11 @@ int ask_continue(httrackp * opt);
 /* Number of decimal digits in n. */
 int nombre_digit(int n);
 
+// Java
+#if 0
+int hts_add_file(char *file, int file_position);
+#endif
+
 // Polling
 #if HTS_POLL
 int check_flot(T_SOC s);
@@ -485,8 +444,4 @@ void voidf(void);
 /* HTML marker comment marking where the top index is spliced. */
 #define HTS_TOPINDEX "TOP_INDEX_HTTRACK"
 
-/* Worst-case byte expansion HT_ADD_HTMLESCAPED* must reserve per escaper. */
-#define HTS_HTMLESCAPE_MAXEXP 5      /* escape_for_html_print: '&'->"&amp;" */
-#define HTS_HTMLESCAPE_FULL_MAXEXP 6 /* _full: high byte->"&#xHH;" */
-
 #endif

src/htsdefines.h

@@ -69,15 +69,11 @@ typedef struct t_hts_callbackarg t_hts_callbackarg;
 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 (htsjava)
-   hide their own hts_plug()/hts_unplug() entry points. */
+/* Marks a symbol an external wrapper module exports back to the engine
+   (dllexport on Windows, nothing elsewhere). */
 #ifndef EXTERNAL_FUNCTION
 #ifdef _WIN32
 #define EXTERNAL_FUNCTION __declspec(dllexport)
-#elif ((defined(__GNUC__) && (__GNUC__ >= 4)) ||                               \
-       (defined(HAVE_VISIBILITY) && HAVE_VISIBILITY))
-#define EXTERNAL_FUNCTION __attribute__((visibility("default")))
 #else
 #define EXTERNAL_FUNCTION
 #endif

src/htsencoding.c

@@ -30,14 +30,12 @@ Please visit our Website: http://www.httrack.com
 /* Author: Xavier Roche                                         */
 /* ------------------------------------------------------------ */
 
-#include <stdint.h>
-
 #include "htscharset.h"
 #include "htsencoding.h"
 #include "htssafe.h"
 
-/* static int decode_entity(const uint64_t hash, const size_t len);
- */
+/* static int decode_entity(const unsigned int hash, const size_t len);
+*/
 #include "htsentities.h"
 
 /* hexadecimal conversion */
@@ -52,31 +50,30 @@ static int get_hex_value(char c) {
     return -1;
 }
 
-/* 64-bit FNV-1a; must match htsentities.sh, which keys the entity table on it.
- */
-#define HASH_INIT 0xcbf29ce484222325ULL
-#define HASH_PRIME 0x100000001b3ULL
-#define HASH_ADD(HASH, C)                                                      \
-  do {                                                                         \
-    (HASH) ^= (unsigned char) (C);                                             \
-    (HASH) *= HASH_PRIME;                                                      \
-  } while (0)
+/* Numerical Recipes,
+   see <http://en.wikipedia.org/wiki/Linear_congruential_generator> */
+#define HASH_PRIME ( 1664525 )
+#define HASH_CONST ( 1013904223 )
+#define HASH_ADD(HASH, C) do {                  \
+    (HASH) *= HASH_PRIME;                       \
+    (HASH) += HASH_CONST;                       \
+    (HASH) += (C);                              \
+  } while(0)
 
 int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t max, const char *charset) {
   size_t i, j, ampStart, ampStartDest;
   int uc;
   int hex;
-  uint64_t hash;
+  unsigned int hash;
 
   assertf(max != 0);
-  for (i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0, uc = -1, hex = 0,
-      hash = HASH_INIT;
-       src[i] != '\0'; i++) {
+  for(i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0,
+        uc = -1, hex = 0, hash = 0 ; src[i] != '\0' ; i++) {
     /* start of entity */
     if (src[i] == '&') {
       ampStart = i;
       ampStartDest = j;
-      hash = HASH_INIT;
+      hash = 0;
       uc = -1;
     }
     /* inside a potential entity */
@@ -177,11 +174,14 @@ int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t ma
       }
       /* alphanumerical entity */
       else {
-        /* alphanum, capped at the longest name
-         * '&CounterClockwiseContourIntegral;' (31) */
-        if (i <= ampStart + 31 && ((src[i] >= '0' && src[i] <= '9') ||
-                                   (src[i] >= 'A' && src[i] <= 'Z') ||
-                                   (src[i] >= 'a' && src[i] <= 'z'))) {
+        /* alphanum and not too far ('&thetasym;' is the longest) */
+        if (i <= ampStart + 10 &&
+            (
+             (src[i] >= '0' && src[i] <= '9')
+             || (src[i] >= 'A' && src[i] <= 'Z')
+             || (src[i] >= 'a' && src[i] <= 'z')
+             )
+            ) {
           /* compute hash */
           HASH_ADD(hash, (unsigned char) src[i]);
         } else {
@@ -190,9 +190,9 @@ int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t ma
         }
       }
     }
-
-    /* reserve one byte for the trailing NUL written after the loop */
-    if (j + 1 >= max) {
+    
+    /* copy */
+    if (j + 1 > max) {
       /* overflow */
       return -1;
     }
@@ -300,11 +300,6 @@ int hts_unescapeUrlSpecial(const char *src, char *dest, const size_t max,
 
           /* Was the character read successfully ? */
           if (nRead == utfBufferSize) {
-            /* the 'continue' below skips the NUL-reserve guard: re-check */
-            if (utfBufferJ + utfBufferSize >= max) {
-              return -1;
-            }
-
             /* Rollback write position to sequence start write position */
             j = utfBufferJ;
 
@@ -319,8 +314,8 @@ int hts_unescapeUrlSpecial(const char *src, char *dest, const size_t max,
       }
     }
 
-    /* reserve one byte for the trailing NUL written after the loop */
-    if (j + 1 >= max) {
+    /* Check for overflow */
+    if (j + 1 > max) {
       return -1;
     }
 

src/htsentities.sh

@@ -1,92 +1,75 @@
 #!/bin/bash
 #
-# Regenerate htsentities.h from the WHATWG named character references.
 
-set -euo pipefail
-
-src=entities.json
-url=https://html.spec.whatwg.org/entities.json
+src=html40.txt
+url=http://www.w3.org/TR/1998/REC-html40-19980424/html40.txt
 dest=htsentities.h
 
-# 64-bit FNV-1a of $1, printed as a C constant. Must match the hash in
-# htsencoding.c. The offset basis is stored as its wrapped (signed) bit pattern;
-# bash arithmetic is 64-bit two's complement, so the result is bit-exact.
-fnv1a() {
-    local s=$1 i c h=$((0xcbf29ce484222325))
-    for ((i = 0; i < ${#s}; i++)); do
-        printf -v c '%d' "'${s:i:1}"
-        h=$(((h ^ (c & 0xff)) * 0x100000001b3))
-    done
-    printf '0x%016xULL' "$h"
-}
+(
+    cat <<EOF
+/*
+  -- ${dest} --
+  FILE GENERATED BY $0, DO NOT MODIFY
 
-if [ ! -f "$src" ]; then
-    curl -fsS "$url" -o "$src"
-fi
+  We compute the LCG hash
+  (see <http://en.wikipedia.org/wiki/Linear_congruential_generator>)
+  for each entity. We should in theory check using strncmp() that we
+  actually have the correct entity, but this is actually statistically
+  not needed.
 
-# Keep ';'-terminated single-codepoint names; the ~93 multi-codepoint refs can't
-# fit decode_entity's single-codepoint return and are skipped (left verbatim).
-pairs=$(jq -r '
-    to_entries
-    | map(select((.key | endswith(";")) and (.value.codepoints | length == 1)))
-    | sort_by(.key)
-    | .[] | "\(.key | ltrimstr("&") | rtrimstr(";"))\t\(.value.codepoints[0])"' "$src")
+  We may want to do better, but we expect the hash function to be uniform, and
+  let the compiler be smart enough to optimize the switch (for example by
+  checking in log2() intervals)
+  
+  This code has been generated using the evil $0 script.
+*/
 
-# Skipped multi-codepoint names, kept to prove none aliases an emitted hash.
-skipped=$(jq -r '
-    to_entries
-    | map(select((.key | endswith(";")) and (.value.codepoints | length > 1)))
-    | .[] | .key | ltrimstr("&") | rtrimstr(";")' "$src")
-
-cases=""
-emit_hashes=""
-while IFS=$'\t' read -r name cp; do
-    hash=$(fnv1a "$name")
-    cases+="    /* $name */"$'\n'
-    cases+="  case $hash:"$'\n'
-    cases+="    if (len == ${#name}) {"$'\n'
-    cases+="      return $cp;"$'\n'
-    cases+="    }"$'\n'
-    cases+="    break;"$'\n'
-    emit_hashes+="$hash"$'\n'
-done <<<"$pairs"
-
-skip_hashes=""
-while IFS= read -r name; do
-    [ -n "$name" ] && skip_hashes+="$(fnv1a "$name")"$'\n'
-done <<<"$skipped"
-
-# The switch keys on the hash alone, so the dispatch is correct only while every
-# emitted name hashes uniquely; prove it here, no runtime name compare needed.
-dups=$(printf '%s' "$emit_hashes" | sort | uniq -d || true)
-if [ -n "$dups" ]; then
-    echo "FATAL: two entity names share a hash (duplicate switch case); change the hash:" >&2
-    echo "$dups" >&2
-    exit 1
-fi
-# A skipped name colliding with an emitted hash would mis-decode instead of
-# staying verbatim; forbid that too.
-aliased=$(comm -12 <(printf '%s' "$emit_hashes" | sort -u) <(printf '%s' "$skip_hashes" | sort -u) || true)
-if [ -n "$aliased" ]; then
-    echo "FATAL: a skipped multi-codepoint name aliases an emitted hash:" >&2
-    echo "$aliased" >&2
-    exit 1
-fi
-
-cat >"$dest" <<EOF
-/* GENERATED by $0 from the WHATWG named character references
-   (${url}). DO NOT EDIT.
-   Dispatch keys on a 64-bit FNV-1a hash of the entity name; the generator
-   aborts on any hash collision, so no runtime name compare is needed. */
-
-#include <stdint.h>
-
-static int decode_entity(const uint64_t hash, const size_t len) {
+static int decode_entity(const unsigned int hash, const size_t len) {
   switch(hash) {
-${cases}  }
+EOF
+    (
+        if test -f ${src}; then
+            cat ${src}
+        else
+            GET "${url}"
+        fi
+    ) |
+        grep -E '^<!ENTITY [a-zA-Z0-9_]' |
+        sed \
+            -e 's/<!ENTITY //' -e "s/[[:space:]][[:space:]]*/ /g" \
+            -e 's/-->$//' \
+            -e 's/\([^ ]*\) CDATA "&#\([^\"]*\);" -- \(.*\)/\1 \2 \3/' |
+        (
+            read -r A
+            while test -n "$A"; do
+                ent="${A%% *}"
+                code=$(echo "$A" | cut -f2 -d' ')
+                # compute hash
+                hash=0
+                i=0
+                a=1664525
+                c=1013904223
+                m="$((1 << 32))"
+                while test "$i" -lt ${#ent}; do
+                    d="$(echo -n "${ent:${i}:1}" | hexdump -v -e '/1 "%d"')"
+                    hash="$((((hash * a) % (m) + d + c) % (m)))"
+                    i=$((i + 1))
+                done
+                echo -e "    /* $A */"
+                echo -e "  case ${hash}u:"
+                echo -e "    if (len == ${#ent} /* && strncmp(ent, \"${ent}\") == 0 */) {"
+                echo -e "      return ${code};"
+                echo -e "    }"
+                echo -e "    break;"
+
+                # next
+                read -r A
+            done
+        )
+    cat <<EOF
+  }
   /* unknown */
   return -1;
 }
 EOF
-
-echo "wrote $dest ($(grep -c '^  case ' "$dest") entities)" >&2
+) >${dest}

src/htsfilters.c

@@ -76,8 +76,7 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
     }
     if (size)
       sz = *size;
-    /* size unknown (scan time): no size pointer => size tests stay neutral */
-    if (strjoker(nom, filters[i] + filteroffs, size ? &sz : NULL, size_flag)) {
+    if (strjoker(nom, filters[i] + filteroffs, &sz, size_flag)) {       // reconnu
       if (size)
         if (sz != *size)
           sizelimit = sz;
@@ -94,32 +93,6 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
   return verdict;
 }
 
-int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
-                     const char *nom2, LLint *size, int *size_flag,
-                     int *depth) {
-  int depth1 = 0, depth2 = 0;
-  int flag1 = 0, flag2 = 0;
-  LLint sz1 = 0, sz2 = 0;
-  int jok1, jok2, use1;
-
-  if (size) {
-    sz1 = *size;
-    sz2 = *size;
-  }
-  jok1 = fa_strjoker(type, filters, nfil, nom1, size ? &sz1 : NULL,
-                     size_flag ? &flag1 : NULL, &depth1);
-  jok2 = fa_strjoker(type, filters, nfil, nom2, size ? &sz2 : NULL,
-                     size_flag ? &flag2 : NULL, &depth2);
-  use1 = jok2 == 0 || (jok1 != 0 && depth1 >= depth2);
-  if (size)
-    *size = use1 ? sz1 : sz2;
-  if (size_flag)
-    *size_flag = use1 ? flag1 : flag2;
-  if (depth)
-    *depth = use1 ? depth1 : depth2;
-  return use1 ? jok1 : jok2;
-}
-
 // supercomparateur joker (tm)
 // compare a et b (b=avec joker dedans), case insensitive [voir CI]
 // renvoi l'adresse de la première lettre de la chaine
@@ -128,8 +101,9 @@ int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
 // cet algo est 'un peu' récursif mais ne consomme pas trop de tm
 // * = toute lettre
 // --?-- : spécifique à HTTrack et aux ?
-HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
-                                LLint *size, int *size_flag) {
+HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * size,
+                          int *size_flag) {
+  //int err=0;
   if (strnotempty(joker) == 0) {        // fin de chaine joker
     if (strnotempty(chaine) == 0)       // fin aussi pour la chaine: ok
       return chaine;
@@ -218,12 +192,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
           int len = (int) strlen(joker);
 
           while((joker[i] != RIGHT) && (joker[i]) && (i < len)) {
-            // '\' escapes the next char as a literal member, e.g. *[\[\]]
-            if (joker[i] == '\\' && joker[i + 1] != '\0') {
-              i++;
-              pass[(int) (unsigned char) joker[i]] = 1;
-              i++;
-            } else if ((joker[i] == '<') || (joker[i] == '>')) { // *[<10]
+            if ((joker[i] == '<') || (joker[i] == '>')) {       // *[<10]
               int lsize = 0;
               int lverdict;
 
@@ -251,9 +220,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
                 while(isdigit((unsigned char) joker[i]))
                   i++;
               }
-            } else if (joker[i + 1] == '-' && joker[i + 2] != '\0') {
-              // range *[A-Z]; the '\0' guard rejects a truncated *[a- (else
-              // i+=3 overshoots the NUL)
+            } else if (joker[i + 1] == '-') {   // 2 car, ex: *[A-Z]
               if ((int) (unsigned char) joker[i + 2] >
                   (int) (unsigned char) joker[i]) {
                 int j;
@@ -261,9 +228,14 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
                 for(j = (int) (unsigned char) joker[i];
                     j <= (int) (unsigned char) joker[i + 2]; j++)
                   pass[j] = 1;
+
               }
+              // else err=1;
               i += 3;
-            } else { // 1 car, ex: *[ ]
+            } else {            // 1 car, ex: *[ ]
+              if (joker[i + 2] == '\\' && joker[i + 3] != 0) {  // escaped char, such as *[\[] or *[\]]
+                i++;
+              }
               pass[(int) (unsigned char) joker[i]] = 1;
               i++;
             }
@@ -285,6 +257,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
       for(i = 0; i < 256; i++)
         pass[i] = 1;            // tout autoriser
       jmp = 1;
+      ////if (joker[2]==LEFT) jmp=3;        // permet de recher *<crochet ouvrant>
     }
 
     {
@@ -312,7 +285,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
       if (!unique)
         max = (int) strlen(chaine);
       else                      /* *(a) only match a (not aaaaa) */
-        max = strnotempty(chaine) ? 1 : 0; /* empty chaine: no char to eat */
+        max = 1;
       while(i < (int) max) {
         if (pass[(int) (unsigned char) chaine[i]]) {    // caractère autorisé
           if ((adr = strjoker(chaine + i + 1, joker + jmp, size, size_flag))) {

src/htsfilters.h

@@ -41,11 +41,6 @@ Please visit our Website: http://www.httrack.com
 
 int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * size,
                 int *size_flag, int *depth);
-/* fa_strjoker() on both URL forms the engine builds (nom1 full, nom2 without
-   scheme); the match latest in the list wins, a "don't know" verdict defers.
-   Returns the merged verdict; the out-params carry the winner's values. */
-int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
-                     const char *nom2, LLint *size, int *size_flag, int *depth);
 HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * size,
                           int *size_flag);
 const char *strjokerfind(const char *chaine, const char *joker);

src/htsftp.c

@@ -54,9 +54,15 @@ Please visit our Website: http://www.httrack.com
 #endif
 
 // ftp mode passif
+// #if HTS_INET6==0
 #define FTP_PASV 1
+// #else
+// no passive mode for v6
+// #define FTP_PASV 0
+// #endif
 
 #define FTP_DEBUG 0
+//#define FORK_DEBUG 0
 
 #if USE_BEGINTHREAD
 
@@ -122,33 +128,6 @@ void launch_ftp(FTPDownloadStruct * params) {
   return 0; \
   }
 
-/* Bounded split of a hostile-URL "user[:pass]@" prefix (see htsftp.h). */
-void ftp_split_userpass(const char *src, const char *end, char *user,
-                        size_t user_size, char *pass, size_t pass_size) {
-  size_t n = 0;
-
-  assertf(user_size > 0 && pass_size > 0); /* the size-1 math underflows on 0 */
-
-  while (src[n] != '\0' && src[n] != ':') {
-    if (n < user_size - 1)
-      user[n] = src[n];
-    n++;
-  }
-  user[n < user_size ? n : user_size - 1] = '\0';
-  pass[0] = '\0';
-  if (src[n] == ':') { // password follows the colon
-    const size_t base = n + 1;
-    size_t k = 0;
-
-    while (&src[base + k + 1] < end && src[base + k] != '\0') {
-      if (k < pass_size - 1)
-        pass[k] = src[base + k];
-      k++;
-    }
-    pass[k < pass_size ? k : pass_size - 1] = '\0';
-  }
-}
-
 // la véritable fonction une fois lancées les routines thread/fork
 int run_launch_ftp(FTPDownloadStruct * pStruct) {
   lien_back *back = pStruct->pBack;
@@ -194,14 +173,43 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
   while(*real_adr == '/')
     real_adr++;                 // sauter /
   if ((adr = jump_identification(real_adr)) != real_adr) {      // user
-    ftp_split_userpass(real_adr, adr, user, sizeof(user), pass, sizeof(pass));
+    int i = -1;
+
+    pass[0] = '\0';
+    do {
+      i++;
+      user[i] = real_adr[i];
+    } while((real_adr[i] != ':') && (real_adr[i]));
+    user[i] = '\0';
+    if (real_adr[i] == ':') {   // pass
+      int j = -1;
+
+      i++;                      // oui on saute aussi le :
+      do {
+        j++;
+        pass[j] = real_adr[i + j];
+      } while(((&real_adr[i + j + 1]) < adr) && (real_adr[i + j]));
+      pass[j] = '\0';
+    }
   }
   // Calculer RETR <nom>
   {
     char *a;
 
+#if 0
+    a = back->url_fil + strlen(back->url_fil) - 1;
+    while((a > back->url_fil) && (*a != '/'))
+      a--;
+    if (*a != '/') {
+      a = NULL;
+    }
+#else
     a = back->url_fil;
+#endif
     if (a != NULL && *a != '\0') {
+#if 0
+      a++;                      // sauter /
+#endif
       ftp_filename = a;
       if (strnotempty(a)) {
         char catbuff[CATBUFF_SIZE];
@@ -225,6 +233,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
       }
     } else {
       strcpybuff(back->r.msg, "Unexpected PORT error");
+      // back->status=STATUS_FTP_READY;    // fini
       back->r.statuscode = STATUSCODE_INVALID;
     }
   }
@@ -258,6 +267,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
     if (hts_dns_resolve2(opt, _adr, &server, &error) == NULL) {
       snprintf(back->r.msg, sizeof(back->r.msg),
                "Unable to get server's address: %s", error);
+      // back->status=STATUS_FTP_READY;    // fini
       back->r.statuscode = STATUSCODE_NON_FATAL;
       _HALT_FTP return 0;
     }
@@ -270,17 +280,20 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
     soc_ctl = (T_SOC) socket(SOCaddr_sinfamily(server), SOCK_STREAM, 0);
     if (soc_ctl == INVALID_SOCKET) {
       strcpybuff(back->r.msg, "Unable to create a socket");
+      // back->status=STATUS_FTP_READY;    // fini
       back->r.statuscode = STATUSCODE_INVALID;
       _HALT_FTP return 0;
     }
 
     SOCaddr_initport(server, port);
+    // server.sin_port = htons((unsigned short int) port);
 
     // connexion (bloquante, on est en thread)
     strcpybuff(back->info, "connect");
 
     if (connect(soc_ctl, &SOCaddr_sockaddr(server), SOCaddr_size(server)) != 0) {
       strcpybuff(back->r.msg, "Unable to connect to the server");
+      // back->status=STATUS_FTP_READY;    // fini
       back->r.statuscode = STATUSCODE_INVALID;
       _HALT_FTP return 0;
 #ifdef _WIN32
@@ -322,22 +335,64 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
               // ok
             } else {
               strcpybuff(back->r.msg, "TYPE I error");
+              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }
+#if 0
+            // --CWD--
+            char *a;
+
+            a = back->url_fil + strlen(back->url_fil) - 1;
+            while((a > back->url_fil) && (*a != '/'))
+              a--;
+            if (*a == '/') {    // ok repéré
+              char BIGSTK target[1024];
+
+              target[0] = '\0';
+              strncatbuff(target, back->url_fil, (int) (a - back->url_fil));
+              if (strnotempty(target) == 0)
+                strcatbuff(target, "/");
+              strcpybuff(back->info, "cwd");
+              snprintf(line, sizeof(line), "CWD %s", target);
+              send_line(soc_ctl, line);
+              get_ftp_line(soc_ctl, line, sizeof(line), timeout);
+              _CHECK_HALT_FTP;
+              if (line[0] == '2') {
+                send_line(soc_ctl, "TYPE I");
+                get_ftp_line(soc_ctl, line, sizeof(line), timeout);
+                _CHECK_HALT_FTP;
+                if (line[0] == '2') {
+                  // ok..
+                } else {
+                  strcpybuff(back->r.msg, "TYPE I error");
+                  // back->status=STATUS_FTP_READY;    // fini
+                  back->r.statuscode = STATUSCODE_INVALID;
+                }
+              } else {
+                snprintf(back->r.msg, sizeof(back->r.msg), "CWD error: %s", linejmp(line));
+                // back->status=STATUS_FTP_READY;    // fini
+                back->r.statuscode = STATUSCODE_INVALID;
+              }                 // sinon on est prêts
+            } else {
+              strcpybuff(back->r.msg, "Unexpected ftp error");
+              // back->status=STATUS_FTP_READY;    // fini
+              back->r.statuscode = STATUSCODE_INVALID;
+            }
+#endif
 
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "Bad password: %s",
-                     linejmp(line));
+            snprintf(back->r.msg, sizeof(back->r.msg), "Bad password: %s", linejmp(line));
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }
         } else {
-          snprintf(back->r.msg, sizeof(back->r.msg), "Bad user name: %s",
-                   linejmp(line));
+          snprintf(back->r.msg, sizeof(back->r.msg), "Bad user name: %s", linejmp(line));
+          // back->status=STATUS_FTP_READY;    // fini
           back->r.statuscode = STATUSCODE_INVALID;
         }
       } else {
-        snprintf(back->r.msg, sizeof(back->r.msg), "Connection refused: %s",
-                 linejmp(line));
+        snprintf(back->r.msg, sizeof(back->r.msg), "Connection refused: %s", linejmp(line));
+        // back->status=STATUS_FTP_READY;    // fini
         back->r.statuscode = STATUSCODE_INVALID;
       }
 
@@ -404,8 +459,8 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
             }
             // -- fin analyse de l'adresse IP et du port --
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s",
-                     linejmp(line));
+            snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s", linejmp(line));
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }                     // sinon on est prêts
         } else {
@@ -436,13 +491,13 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                 }
               }
             } else {
-              snprintf(back->r.msg, sizeof(back->r.msg), "EPSV incorrect: %s",
-                       linejmp(line));
+              snprintf(back->r.msg, sizeof(back->r.msg), "EPSV incorrect: %s", linejmp(line));
+              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "PASV/EPSV error: %s",
-                     linejmp(line));
+            snprintf(back->r.msg, sizeof(back->r.msg), "PASV/EPSV error: %s", linejmp(line));
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }                     // sinon on est prêts
         }
@@ -548,8 +603,9 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                   deletesoc(soc_dat);
                   soc_dat = INVALID_SOCKET;
                   //
-                  snprintf(back->r.msg, sizeof(back->r.msg),
-                           "RETR command error: %s", linejmp(line));
+                  snprintf(back->r.msg, sizeof(back->r.msg), "RETR command error: %s",
+                          linejmp(line));
+                  // back->status=STATUS_FTP_READY;    // fini
                   back->r.statuscode = STATUSCODE_INVALID;
                 }               // sinon on est prêts
               } else {
@@ -560,20 +616,23 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                 soc_dat = INVALID_SOCKET;
                 //
                 strcpybuff(back->r.msg, "Unable to connect");
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = STATUSCODE_INVALID;
               }                 // sinon on est prêts
             } else {
               strcpybuff(back->r.msg, "Unable to create a socket");
+              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }                   // sinon on est prêts
           } else {
             snprintf(back->r.msg, sizeof(back->r.msg),
                      "Unable to resolve IP %s: %s", adr_ip, error);
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }                     // sinon on est prêts
         } else {
-          snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s",
-                   linejmp(line));
+          snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s", linejmp(line));
+          // back->status=STATUS_FTP_READY;    // fini
           back->r.statuscode = STATUSCODE_INVALID;
         }                       // sinon on est prêts
 #else
@@ -594,16 +653,17 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
               //T_SOC soc_dat;
               if ((soc_dat = accept(soc_servdat, NULL, NULL)) == INVALID_SOCKET) {
                 strcpybuff(back->r.msg, "Unable to accept connection");
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = STATUSCODE_INVALID;
               }
             } else {
-              snprintf(back->r.msg, sizeof(back->r.msg),
-                       "RETR command error: %s", linejmp(line));
+              snprintf(back->r.msg, sizeof(back->r.msg), "RETR command error: %s", linejmp(line));
+              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "PORT command error: %s",
-                     linejmp(line));
+            snprintf(back->r.msg, sizeof(back->r.msg), "PORT command error: %s", linejmp(line));
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }
 #ifdef _WIN32
@@ -613,6 +673,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
 #endif
         } else {
           strcpybuff(back->r.msg, "Unable to listen to a port");
+          // back->status=STATUS_FTP_READY;    // fini
           back->r.statuscode = STATUSCODE_INVALID;
         }
 #endif
@@ -636,18 +697,21 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
             int len = 1;
             int read_len = 1024;
 
+            //HTS_TOTAL_RECV_CHECK(read_len);         // Diminuer au besoin si trop de données reçues
+
             while((len > 0) && (!stop_ftp(back))) {
               // attendre les données
               len = 1;          // pas d'erreur pour le moment
               switch (wait_socket_receive(soc_dat, timeout)) {
               case -1:
                 strcpybuff(back->r.msg, "FTP read error");
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = STATUSCODE_INVALID;
                 len = 0;        // fin
                 break;
               case 0:
-                snprintf(back->r.msg, sizeof(back->r.msg), "Time out (%d)",
-                         timeout);
+                snprintf(back->r.msg, sizeof(back->r.msg), "Time out (%d)", timeout);
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = STATUSCODE_INVALID;
                 len = 0;        // fin
                 break;
@@ -669,14 +733,17 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                          }
                        */
                       strcpybuff(back->r.msg, "Write error");
+                      // back->status=STATUS_FTP_READY;    // fini
                       back->r.statuscode = STATUSCODE_INVALID;
                       len = 0;  // error
                     }
                   } else {
                     strcpybuff(back->r.msg, "Unexpected write error");
+                    // back->status=STATUS_FTP_READY;    // fini
                     back->r.statuscode = STATUSCODE_INVALID;
                   }
-                } else { // Erreur ou terminé
+                } else {        // Erreur ou terminé
+                  // back->status=STATUS_FTP_READY;    // fini
                   back->r.statuscode = 0;
                   if (back->r.totalsize > 0
                       && back->r.size != back->r.totalsize) {
@@ -685,6 +752,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                   }
                 }
                 read_len = 1024;
+                //HTS_TOTAL_RECV_CHECK(read_len);         // Diminuer au besoin si trop de données reçues
               }
             }
             if (back->r.fp) {
@@ -693,6 +761,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
             }
           } else {
             strcpybuff(back->r.msg, "Unable to write file");
+            // back->status=STATUS_FTP_READY;    // fini
             back->r.statuscode = STATUSCODE_INVALID;
           }
 #ifdef _WIN32
@@ -708,14 +777,16 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
               get_ftp_line(soc_ctl, line, sizeof(line), timeout);
               if (line[0] == '2') {     // OK
                 strcpybuff(back->r.msg, "OK");
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = HTTP_OK;
               } else {
-                snprintf(back->r.msg, sizeof(back->r.msg), "RETR incorrect: %s",
-                         linejmp(line));
+                snprintf(back->r.msg, sizeof(back->r.msg), "RETR incorrect: %s", linejmp(line));
+                // back->status=STATUS_FTP_READY;    // fini
                 back->r.statuscode = STATUSCODE_INVALID;
               }
             } else {
               strcpybuff(back->r.msg, "FTP read error");
+              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }
           }
@@ -741,6 +812,7 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
     back->r.statuscode = HTTP_OK;
     strcpybuff(back->r.msg, "OK");
   }
+  // back->status=STATUS_FTP_READY;    // fini
   return 0;
 }
 
@@ -907,11 +979,13 @@ int get_ftp_line(T_SOC soc, char *ptrline, size_t line_size, int timeout) {
       break;
     }
 
+    //HTS_TOTAL_RECV_CHECK(dummy);     // Diminuer au besoin si trop de données reçues
     switch (recv(soc, &b, 1, 0)) {
+      //case 0: break;    // pas encore --> erreur (on attend)!
     case 1:
       HTS_STAT.HTS_TOTAL_RECV += 1;     // compter flux entrant
-      if ((b != 10) && (b != 13) && (i < (int) sizeof(data) - 1))
-        data[i++] = b; // truncate hostile over-long reply lines
+      if ((b != 10) && (b != 13))
+        data[i++] = b;
       break;
     default:
       if (ptrline)
@@ -1034,6 +1108,7 @@ int wait_socket_receive(T_SOC soc, int timeout) {
 int stop_ftp(lien_back * back) {
   if (back->stop_ftp) {
     strcpybuff(back->r.msg, "Cancelled by User");
+    // back->status=STATUS_FTP_READY;    // fini
     back->r.statuscode = STATUSCODE_INVALID;
     return 1;
   }

src/htsftp.h

@@ -70,11 +70,6 @@ int back_launch_ftp(FTPDownloadStruct * params);
 int run_launch_ftp(FTPDownloadStruct * params);
 int send_line(T_SOC soc, const char *data);
 int get_ftp_line(T_SOC soc, char *line, size_t line_size, int timeout);
-/* Split a "user[:pass]@" prefix (end = jump_identification result) into
-   bounded, NUL-terminated user/pass buffers, truncating to fit.
-   Both sizes must be nonzero. */
-void ftp_split_userpass(const char *src, const char *end, char *user,
-                        size_t user_size, char *pass, size_t pass_size);
 T_SOC get_datasocket(char *to_send, size_t to_send_size);
 int stop_ftp(lien_back * back);
 char *linejmp(char *line);

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 "3.49-11"
-#define HTTRACK_VERSIONID "3.49.11"
+#define HTTRACK_VERSION "3.49-9"
+#define HTTRACK_VERSIONID "3.49.9"
 #define HTTRACK_AFF_VERSION "3.x"
 #define HTTRACK_LIB_VERSION "2.0"
 
@@ -229,10 +229,6 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DEFAULT_FOOTER                                                     \
   "<!-- Mirrored from %s%s by HTTrack Website Copier/" HTTRACK_AFF_VERSION     \
   " " HTTRACK_AFF_AUTHORS ", %s -->"
-/* Honest crawler User-Agent; no fake OS/browser to go stale. */
-#define HTS_DEFAULT_USER_AGENT                                                 \
-  "Mozilla/5.0 (compatible; HTTrack/" HTTRACK_AFF_VERSION                      \
-  "; +https://www.httrack.com/)"
 #define HTTRACK_WEB "http://www.httrack.com"
 #define HTS_UPDATE_WEBSITE                                                     \
   "http://www.httrack.com/"                                                    \

src/htshash.c

@@ -106,10 +106,10 @@ static coucal_hashkeys key_adrfil_hashes_generic(void *arg,
   const lien_url*const lien = (const lien_url*) value;
   const char *const adr = !former ? lien->adr : lien->former_adr;
   const char *const fil = !former ? lien->fil : lien->former_fil;
-  const char *const adr_norm =
-      adr != NULL ? (hash->norm_host ? jump_normalized_const(adr)
-                                     : jump_identification_const(adr))
-                  : NULL;
+  const char *const adr_norm = adr != NULL ? 
+    ( hash->normalized  ? jump_normalized_const(adr)
+                        : jump_identification_const(adr) )
+    : NULL;
 
   // copy address
   assertf(adr_norm != NULL);
@@ -117,18 +117,10 @@ static coucal_hashkeys key_adrfil_hashes_generic(void *arg,
 
   // copy link
   assertf(fil != NULL);
-  {
-    /* resolve the per-URL strip keys; strip applies even when urlhack is off */
-    char BIGSTK keybuf[HTS_URLMAXSIZE];
-    const char *const keys = hts_query_strip_keys(hash->strip_query, adr, fil,
-                                                  keybuf, sizeof(keybuf));
-
-    if (hash->norm_slash || hash->norm_query || keys != NULL) {
-      fil_normalized_filtered_ex(fil, &hash->normfil[strlen(hash->normfil)],
-                                 keys, hash->norm_slash, hash->norm_query);
-    } else {
-      strcpy(&hash->normfil[strlen(hash->normfil)], fil);
-    }
+  if (hash->normalized) {
+    fil_normalized(fil, &hash->normfil[strlen(hash->normfil)]);
+  } else {
+    strcpy(&hash->normfil[strlen(hash->normfil)], fil);
   }
 
   // hash
@@ -140,7 +132,8 @@ static int key_adrfil_equals_generic(void *arg,
                                      coucal_key_const a_,
                                      coucal_key_const b_, 
                                      const int former) {
-  hash_struct *const hash = (hash_struct *) arg;
+  hash_struct *const hash = (hash_struct*) arg;
+  const int normalized = hash->normalized;
   const lien_url*const a = (const lien_url*) a_;
   const lien_url*const b = (const lien_url*) b_;
   const char *const a_adr = !former ? a->adr : a->former_adr;
@@ -157,10 +150,10 @@ static int key_adrfil_equals_generic(void *arg,
   assertf(b_fil != NULL);
 
   // skip scheme and authentication to the domain (possibly without www.)
-  ja = hash->norm_host ? jump_normalized_const(a_adr)
-                       : jump_identification_const(a_adr);
-  jb = hash->norm_host ? jump_normalized_const(b_adr)
-                       : jump_identification_const(b_adr);
+  ja = normalized
+    ? jump_normalized_const(a_adr) : jump_identification_const(a_adr);
+  jb = normalized
+    ? jump_normalized_const(b_adr) : jump_identification_const(b_adr);
   assertf(ja != NULL);
   assertf(jb != NULL);
   if (strcasecmp(ja, jb) != 0) {
@@ -168,23 +161,12 @@ static int key_adrfil_equals_generic(void *arg,
   }
 
   // now compare pathes
-  {
-    char BIGSTK ka[HTS_URLMAXSIZE], kb[HTS_URLMAXSIZE];
-    const char *const keysa =
-        hts_query_strip_keys(hash->strip_query, a_adr, a_fil, ka, sizeof(ka));
-    const char *const keysb =
-        hts_query_strip_keys(hash->strip_query, b_adr, b_fil, kb, sizeof(kb));
-
-    if (hash->norm_slash || hash->norm_query || keysa != NULL ||
-        keysb != NULL) {
-      fil_normalized_filtered_ex(a_fil, hash->normfil, keysa, hash->norm_slash,
-                                 hash->norm_query);
-      fil_normalized_filtered_ex(b_fil, hash->normfil2, keysb, hash->norm_slash,
-                                 hash->norm_query);
-      return strcmp(hash->normfil, hash->normfil2) == 0;
-    } else {
-      return strcmp(a_fil, b_fil) == 0;
-    }
+  if (normalized) {
+    fil_normalized(a_fil, hash->normfil);
+    fil_normalized(b_fil, hash->normfil2);
+    return strcmp(hash->normfil, hash->normfil2) == 0;
+  } else {
+    return strcmp(a_fil, b_fil) == 0;
   }
 }
 
@@ -240,17 +222,11 @@ static int key_former_adrfil_equals(void *arg,
   return key_adrfil_equals_generic(arg, a, b, 1);
 }
 
-void hash_init(httrackp *opt, hash_struct *hash, hts_boolean normalized) {
+void hash_init(httrackp *opt, hash_struct * hash, int normalized) {
   hash->sav = coucal_new(0);
   hash->adrfil = coucal_new(0);
   hash->former_adrfil = coucal_new(0);
-  /* urlhack is the umbrella; per-feature negatives opt out of each part */
-  hash->norm_host = normalized && !opt->no_www_dedup;
-  hash->norm_slash = normalized && !opt->no_slash_dedup;
-  hash->norm_query = normalized && !opt->no_query_dedup;
-  /* snapshot the query-strip list (not owned; valid for the hash lifetime) */
-  hash->strip_query =
-      StringNotEmpty(opt->strip_query) ? StringBuff(opt->strip_query) : NULL;
+  hash->normalized = normalized;
 
   hts_set_hash_handler(hash->sav, opt);
   hts_set_hash_handler(hash->adrfil, opt);
@@ -306,26 +282,6 @@ void hash_free(hash_struct *hash) {
   }
 }
 
-/* Test helper: do the two URLs dedupe to the same key under opt's urlhack
-   flags? Exercises the live hash compare (norm_host/slash/query resolution). */
-hts_boolean hash_url_equals(httrackp *opt, const char *adra, const char *fila,
-                            const char *adrb, const char *filb) {
-  hash_struct hash;
-  lien_url la, lb;
-  hts_boolean eq;
-
-  memset(&la, 0, sizeof(la));
-  memset(&lb, 0, sizeof(lb));
-  la.adr = key_duphandler(NULL, adra);
-  la.fil = key_duphandler(NULL, fila);
-  lb.adr = key_duphandler(NULL, adrb);
-  lb.fil = key_duphandler(NULL, filb);
-  hash_init(opt, &hash, opt->urlhack);
-  eq = key_adrfil_equals(&hash, &la, &lb);
-  hash_free(&hash);
-  return eq;
-}
-
 // retour: position ou -1 si non trouvé
 int hash_read(const hash_struct * hash, const char *nom1, const char *nom2,
               hash_struct_type type) {

src/htshash.h

@@ -51,12 +51,8 @@ typedef enum hash_struct_type {
 } hash_struct_type;
 
 // tables de hachage
-void hash_init(httrackp *opt, hash_struct *hash, hts_boolean normalized);
+void hash_init(httrackp *opt, hash_struct *hash, int normalized);
 void hash_free(hash_struct *hash);
-/* Test helper: HTS_TRUE if the two URLs dedupe together under opt's urlhack
-   flags. */
-hts_boolean hash_url_equals(httrackp *opt, const char *adra, const char *fila,
-                            const char *adrb, const char *filb);
 int hash_read(const hash_struct * hash, const char *nom1, const char *nom2,
               hash_struct_type type);
 void hash_write(hash_struct * hash, size_t lpos);

src/htshelp.c

@@ -152,6 +152,16 @@ void help_wizard(httrackp * opt) {
 #define str (buffers->str)
 #define argv (buffers->argv)
 
+  //char *urls = (char *) malloct(HTS_URLMAXSIZE * 2);
+  //char *mainpath = (char *) malloct(256);
+  //char *projname = (char *) malloct(256);
+  //char *stropt = (char *) malloct(2048);        // options
+  //char *stropt2 = (char *) malloct(2048);       // options longues
+  //char *strwild = (char *) malloct(2048);       // wildcards
+  //char *cmd = (char *) malloct(4096);
+  //char *str = (char *) malloct(256);
+  //char **argv = (char **) malloct(256 * sizeof(char *));
+
   //
   char *a;
 
@@ -217,6 +227,8 @@ void help_wizard(httrackp * opt) {
   strcatbuff(stropt2, str);
   strcatbuff(stropt2, projname);
   strcatbuff(stropt2, "\" ");
+  // Créer si ce n'est fait un index.html 1er niveau
+  make_empty_index(str);
   //
   printf("\n");
   printf("Enter URLs (separated by commas or blank spaces) :");
@@ -337,6 +349,8 @@ void help_wizard(httrackp * opt) {
       }
       hts_main(argc, argv);
     }
+    //} else {
+    //  help("httrack",1);
   }
 
   /* Free buffers */
@@ -441,6 +455,23 @@ void help_catchurl(const char *dest_path) {
     printf("Unable to create a temporary proxy (no remaining port)\n");
 }
 
+// Créer un index.html vide
+void make_empty_index(const char *str) {
+#if 0
+  if (!fexist(fconcat(str, "index.html"))) {
+    FILE *fp = fopen(fconcat(str, "index.html"), "wb");
+
+    if (fp) {
+      fprintf(fp, "<!-- " HTS_TOPINDEX " -->" CRLF);
+      fprintf(fp,
+              "<HTML><BODY>Index is empty!<BR>(File used to index all HTTrack projects)</BODY></HTML>"
+              CRLF);
+      fclose(fp);
+    }
+  }
+#endif
+}
+
 // mini-aide  (h: help)
 //           y
 void help(const char *app, int more) {
@@ -490,7 +521,6 @@ void help(const char *app, int more) {
   infomsg("  EN maximum mirror time in seconds (60=1 minute, 3600=1 hour)");
   infomsg("  AN maximum transfer rate in bytes/seconds (1000=1KB/s max)");
   infomsg(" %cN maximum number of connections/seconds (*%c10)");
-  infomsg(" %G  random pause of MIN[:MAX] seconds between files (e.g. %G5:10)");
   infomsg
     ("  GN pause transfer if N bytes reached, and wait until lock file is deleted");
   infomsg("");
@@ -533,7 +563,6 @@ void help(const char *app, int more) {
     (" %x  do not include any password for external password protected websites (%x0 include)");
   infomsg
     (" %q *include query string for local files (useless, for information purpose only) (%q0 don't include)");
-  infomsg(" %g  strip query keys for dedup ([host/pattern=]key1,key2,...)");
   infomsg
     ("  o *generate output html file in case of error (404..) (o0 don't generate)");
   infomsg("  X *purge old files after update (X0 keep delete)");
@@ -542,8 +571,6 @@ void help(const char *app, int more) {
   infomsg("");
   infomsg("Spider options:");
   infomsg("  bN accept cookies in cookies.txt (0=do not accept,* 1=accept)");
-  infomsg(" %K  load extra cookies from a Netscape cookies.txt");
-  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
@@ -560,9 +587,6 @@ void help(const char *app, int more) {
     (" %s  update hacks: various hacks to limit re-transfers when updating (identical size, bogus response..)");
   infomsg
     (" %u  url hacks: various hacks to limit duplicate URLs (strip //, www.foo.com==foo.com..)");
-  infomsg("     opt out of one url-hack part: --keep-www-prefix "
-          "(www.foo.com<>foo.com), --keep-double-slashes (//), "
-          "--keep-query-order (?b&a)");
   infomsg
     (" %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3,cgi=text/html;dat,bin=application/x-zip)");
   infomsg("     shortcut: '--assume standard' is equivalent to -%A "
@@ -622,7 +646,9 @@ void help(const char *app, int more) {
   infomsg("");
   infomsg("Guru options: (do NOT use if possible)");
   infomsg(" #X *use optimized engine (limited memory boundary checks)");
-  infomsg(" #test  list engine self-tests (run one with -#test=NAME [args])");
+  infomsg(" #0  filter test (-#0 '*.gif' 'www.bar.com/foo.gif')");
+  infomsg(" #1  simplify test (-#1 ./foo/bar/../foobar)");
+  infomsg(" #2  type test (-#2 /foo/bar.php)");
   infomsg(" #C  cache list (-#C '*.com/spider*.gif'");
   infomsg(" #R  cache repair (damaged cache)");
   infomsg(" #d  debug parser");
@@ -778,4 +804,7 @@ void help(const char *app, int more) {
   infomsg("[compiled: " HTS_PLATFORM_NAME "]");
 #endif
   infomsg(NULL);
+
+//  infomsg("  R  *relative links (e.g ../link)\n");
+//  infomsg("  A   absolute links (e.g /www.adr/link)\n");
 }

src/htshelp.h

@@ -45,6 +45,7 @@ typedef struct httrackp httrackp;
 
 void infomsg(const char *msg);
 void help(const char *app, int more);
+void make_empty_index(const char *str);
 void help_wizard(httrackp * opt);
 int help_query(const char *list, int def);
 void help_catchurl(const char *dest_path);

src/htsindex.c

@@ -142,6 +142,8 @@ int index_keyword(const char *html_data, LLint size, const char *mime,
   char keyword[KEYW_LEN + 32];
   int i = 0;
 
+  //
+  //int WordIndexSize = 1024;
   coucal WordIndexHash = NULL;
   FILE *tmpfp = NULL;
 
@@ -176,6 +178,8 @@ int index_keyword(const char *html_data, LLint size, const char *mime,
              || (strfield2(mime, "text/css"))
     ) {
     inscript = 1;
+    //} else if (strfield2(mime, "text/vnd.wap.wml")) {   // humm won't work in many cases
+    //  inscript=0;
   } else
     return 0;
 
@@ -271,6 +275,8 @@ int index_keyword(const char *html_data, LLint size, const char *mime,
 
   // Process indexing for this page
   {
+    //FILE* fp=NULL;
+    //fp=fopen(concat(indexpath,"index.txt"),"ab");
     if (fp_tmpproject) {
       while(!feof(tmpfp)) {
         char line[KEYW_LEN + 32];
@@ -280,6 +286,7 @@ int index_keyword(const char *html_data, LLint size, const char *mime,
           intptr_t e = 0;
 
           if (coucal_read(WordIndexHash, line, &e)) {
+            //if (e) {
             char BIGSTK savelst[HTS_URLMAXSIZE * 2];
 
             e++;                /* 0 means "once" */
@@ -293,9 +300,11 @@ int index_keyword(const char *html_data, LLint size, const char *mime,
             fprintf(fp_tmpproject, "%s %d %s\n", line,
                     (int) (KEYW_SORT_MAXCOUNT - e), savelst);
             hts_primindex_size++;
+            //}
           }
         }
       }
+      //fclose(fp);
     }
   }
 
@@ -321,6 +330,7 @@ void index_finish(const char *indexpath, int mode) {
   off_t size = fpsize(fp_tmpproject);
 
   if (size > 0) {
+    //FILE* fp=fopen(concat(indexpath,"index.txt"),"rb");
     if (fp_tmpproject) {
       tab = (char **) malloct(sizeof(char *) * (hts_primindex_size + 2));
       if (tab) {
@@ -388,6 +398,8 @@ void index_finish(const char *indexpath, int mode) {
                       if (total_hit) {
                         if (mode == 1)  // TEXT
                           fprintf(fp, "\t=%d\r\n", total_hit);
+                        //else                // HTML
+                        //  fprintf(fp,"<br>(%d total hits)\r\n",total_hit);
                         if ((((total_hit * 1000) / hts_primindex_words) >=
                              KEYW_USELESS1K)
                             || (((total_line * 1000) / index) >=
@@ -404,6 +416,8 @@ void index_finish(const char *indexpath, int mode) {
                           if (mode == 1)        // TEXT
                             fprintf(fp, "\t(%d)\r\n",
                                     ((total_hit * 1000) / hts_primindex_words));
+                          //else                // HTML
+                          //  fprintf(fp,"(%d)\r\n",((total_hit*1000)/hts_primindex_words));
                         }
                       }
                       if (mode == 1)    // TEXT

src/htsjava.c

@@ -63,9 +63,6 @@ Please visit our Website: http://www.httrack.com
 /* This file */
 #include "htsjava.h"
 
-/* calloct/freet wrappers */
-#include "htssafe.h"
-
 static int reverse_endian(void) {
   int endian = 1;
 
@@ -175,14 +172,15 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
 #if JAVADEBUG
       printf("fopen\n");
 #endif
-      if ((fpout = FOPEN(fconv(catbuff, sizeof(catbuff), file), "r+b")) ==
-          NULL) {
+      if ((fpout = FOPEN(fconv(catbuff, sizeof(catbuff), file), "r+b")) == NULL) {
+        //fprintf(stderr, "Cannot open input file.\n");
         sprintf(str->err_msg, "Unable to open file %s", file);
         return 0;               // une erreur..
       }
 #if JAVADEBUG
       printf("fread\n");
 #endif
+      //if (fread(&header,1,sizeof(JAVA_HEADER),fpout) != sizeof(JAVA_HEADER)) {   // pas complet..
       if (fread(&header, 1, 10, fpout) != 10) { // pas complet..
         fclose(fpout);
         sprintf(str->err_msg, "File header too small (file len = " LLintP ")",
@@ -206,16 +204,7 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
         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));
+      tab = (RESP_STRUCT *) calloc(header.count, sizeof(RESP_STRUCT));
       if (!tab) {
         sprintf(str->err_msg, "Unable to alloc %d bytes",
                 (int) sizeof(RESP_STRUCT));
@@ -241,7 +230,7 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
           } else {              // ++ une erreur est survenue!
             if (strnotempty(str->err_msg) == 0)
               strcpy(str->err_msg, "Internal readtable error");
-            freet(tab);
+            free(tab);
             if (fpout) {
               fclose(fpout);
               fpout = NULL;
@@ -256,10 +245,12 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
       printf("addfiles\n");
 #endif
       {
+        //unsigned int acess;
         unsigned int Class;
         unsigned int SClass;
         int i;
 
+        //acess = readshort(fpout);
         Class = readshort(fpout);
         SClass = readshort(fpout);
 
@@ -297,7 +288,7 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
 #if JAVADEBUG
       printf("end\n");
 #endif
-      freet(tab);
+      free(tab);
       if (fpout) {
         fclose(fpout);
         fpout = NULL;
@@ -404,9 +395,11 @@ static RESP_STRUCT readtable(htsmoduleStruct * str, FILE * fp,
 
       p = &buffer[0];
 
+      //fflush(fp); 
       trans.file_position = ftell(fp);
       length = readshort(fp);
       if (length < HTS_URLMAXSIZE) {
+        // while ((length > 0) && (length<500)) {
         while(length > 0) {
           *p++ = fgetc(fp);
 
@@ -414,13 +407,17 @@ static RESP_STRUCT readtable(htsmoduleStruct * str, FILE * fp,
         }
         *p = '\0';
 
+        //#if JDEBUG
+        //      if(tris(buffer)==1) printf("%s\n ",buffer);
+        //      if(tris(buffer)==2)  printf("%s\n ",printname(buffer));
+        //#endif
         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
+      } else {                  // gros pb
         while((length > 0) && (!feof(fp))) {
           fgetc(fp);
           length--;
@@ -436,6 +433,7 @@ static RESP_STRUCT readtable(htsmoduleStruct * str, FILE * fp,
     }
     break;
   default:
+    // printf("Type inconnue\n");
     // on arrête tout 
     sprintf(str->err_msg, "Internal structure unknown (type %d)", trans.type);
     *error = 1;
@@ -498,6 +496,7 @@ static char *printname(char rname[1024], char name[1024]) {
     return rname;  // ""
   }
   p += 2;
+  //rname=(char*)calloct(strlen(name)+8,sizeof(char));
   p1 = rname;
   for(j = 0; name[j] != '\0'; j++, p++) {
     if (*p == '/')

src/htsjava.h

@@ -33,19 +33,15 @@ Please visit our Website: http://www.httrack.com
 #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;
+  unsigned long int magic;
+  unsigned short int minor;
+  unsigned short int major;
+  unsigned short int count;
 };
 
 #ifndef HTS_DEF_FWSTRUCT_RESP_STRUCT

src/htslib.h

@@ -147,8 +147,9 @@ struct OLD_htsblk {
 #define HTS_DEF_FWSTRUCT_t_dnscache
 typedef struct t_dnscache t_dnscache;
 #endif
-// One DNS cache record, stored as a coucal value keyed by hostname.
 struct t_dnscache {
+  struct t_dnscache *next;
+  const char *iadr;
   // resolved addresses, in resolver (RFC 6724) order; host_count==0 means the
   // name does not resolve (negative cache). host_count<=HTS_MAXADDRNUM.
   int host_count;
@@ -171,6 +172,7 @@ HTSEXT_API const char* hts_version(void);
 // fonctions unix/winsock
 int hts_read(htsblk * r, char *buff, int size);
 
+//int HTS_TOTAL_RECV_CHECK(int var);
 LLint check_downloadable_bytes(int rate);
 
 HTSEXT_API int hts_uninit_module(void);
@@ -189,6 +191,7 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode, const char *xsend
 int http_cookie_header_selftest(t_cookie *cookie, const char *domain,
                                 const char *path, char *dst, size_t dst_size);
 
+//int newhttp(char* iadr,char* err=NULL);
 T_SOC newhttp(httrackp * opt, const char *iadr, htsblk * retour, int port,
               int waitconnect);
 /* Like newhttp(), but connect to the addr_index-th resolved address of the host
@@ -242,9 +245,8 @@ HTSEXT_API int check_hostname_dns(const char *const hostname);
 int ftp_available(void);
 
 #if HTS_DNSCACHE
-/* Return opt's DNS cache hashtable (hostname -> t_dnscache record), creating it
-   on first use. Records are owned by the table and freed on coucal_delete. */
-coucal hts_cache(httrackp *opt);
+void hts_cache_free(t_dnscache *const cache);
+t_dnscache *hts_cache(httrackp * opt);
 #endif
 
 // outils divers
@@ -283,9 +285,6 @@ 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);
 

src/htsmodules.c

@@ -55,6 +55,12 @@ extern int fspc(httrackp * opt, FILE * fp, const char *type);
 
 /* >>> Put all modules variables here */
 
+#if 0
+t_gzopen gzopen = NULL;
+t_gzread gzread = NULL;
+t_gzclose gzclose = NULL;
+#endif
+
 int V6_is_available = HTS_INET6;
 
 static char WHAT_is_available[64] = "";
@@ -106,6 +112,18 @@ int hts_parse_externals(htsmoduleStruct * str) {
   return -1;
 }
 
+//static void addCallback(htscallbacks* chain, void* moduleHandle, htscallbacksfncptr exitFnc) {
+//  while(chain->next != NULL) {
+//    chain = chain->next;
+//  }
+//  chain->next = calloct(1, sizeof(htscallbacks));
+//  assertf(chain->next != NULL);
+//  chain = chain->next;
+//  memset(chain, 0, sizeof(*chain));
+//  chain->exitFnc = exitFnc;
+//  chain->moduleHandle = moduleHandle;
+//}
+
 void clearCallbacks(htscallbacks * chain_);
 void clearCallbacks(htscallbacks * chain_) {
   htscallbacks *chain;

src/htsname.c

@@ -41,10 +41,6 @@ Please visit our Website: http://www.httrack.com
 #include "htstools.h"
 #include "htscharset.h"
 #include "htsencoding.h"
-#include "htssniff.h"
-#if HTS_USEZLIB
-#include "htszlib.h"
-#endif
 #include <ctype.h>
 
 #define ADD_STANDARD_PATH \
@@ -74,6 +70,31 @@ static const char *hts_tbdev[] = {
   ""
 };
 
+#define URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET() do { \
+  int prev = opt->state._hts_in_html_parsing; \
+  while(back_pluggable_sockets_strict(sback, opt) <= 0) { \
+    opt->state. _hts_in_html_parsing = 6; \
+    /* Wait .. */ \
+    back_wait(sback,opt,cache,0); \
+    /* Transfer rate */ \
+    engine_stats(); \
+    /* Refresh various stats */ \
+    HTS_STAT.stat_nsocket=back_nsoc(sback); \
+    HTS_STAT.stat_errors=fspc(opt,NULL,"error"); \
+    HTS_STAT.stat_warnings=fspc(opt,NULL,"warning"); \
+    HTS_STAT.stat_infos=fspc(opt,NULL,"info"); \
+    HTS_STAT.nbk=backlinks_done(sback,opt->liens,opt->lien_tot,ptr); \
+    HTS_STAT.nb=back_transferred(HTS_STAT.stat_bytes,sback); \
+    /* Check */ \
+    { \
+      if (!RUN_CALLBACK7(opt, loop, sback->lnk, sback->count,-1,ptr,opt->lien_tot,(int) (time_local()-HTS_STAT.stat_timestart),&HTS_STAT)) { \
+        return -1; \
+      } \
+    } \
+  } \
+  opt->state._hts_in_html_parsing = prev; \
+} while(0)
+
 /* Strip all // */
 static void cleanDoubleSlash(char *s) {
   int i, j;
@@ -117,191 +138,37 @@ static void cleanEndingSpaceOrDot(char *s) {
   }
 }
 
-/* Wire Content-Type vs URL extension: a patchable wire type wins over an
-   unspecific ext, the HTS_UNKNOWN_MIME sentinel keeps a specific non-HTML ext
-   (#267 guard), a declared disagreement is CONTESTED (sniffed below). */
-typedef enum wire_verdict {
-  WIRE_KEEPS_EXT,
-  WIRE_WINS,
-  WIRE_CONTESTED
-} wire_verdict;
-
-static wire_verdict wire_ext_verdict(httrackp *opt, const char *wiremime,
-                                     const char *file, char *urlmime,
-                                     size_t urlmime_size) {
-  if (may_unknown2(opt, wiremime, file))
-    return WIRE_KEEPS_EXT; /* type kept verbatim (keep-list / bogus-multiple) */
-  urlmime[0] = '\0';
-  /* type implied by the URL extension, only when confidently known (flag 0) */
-  if (!get_httptype_sized(opt, urlmime, urlmime_size, file, 0))
-    return WIRE_WINS; /* URL ext implies no known type */
-  if (strfield2(wiremime, urlmime))
-    return WIRE_KEEPS_EXT; /* agreement (no .htm->.html churn) */
-  if (!is_hypertext_mime(opt, urlmime, file) &&
-      strfield2(wiremime, HTS_UNKNOWN_MIME))
-    return WIRE_KEEPS_EXT; /* no declared type */
-  return WIRE_CONTESTED;
-}
-
-/* Optional evidence for a contested wire-vs-ext verdict. */
-typedef struct sniff_src {
-  struct_back *sback;       /* live backing (looked up by adr/fil) */
-  const lien_back *headers; /* snapshot: r.adr, else the url_sav file */
-  const char *adr, *fil;
-  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");
-  size_t n = 0;
-
-  if (fp != NULL) {
-    n = fread(buf, 1, len, fp);
-    fclose(fp);
-  }
-  return n;
-}
-
-/* Body head of one slot: memory, else its flushed on-disk file (url_sav, or
-   tmpfile for a compressed stream); inflated so the sniff sees the final body.
- */
-static size_t sniff_slot_head(const lien_back *slot, void *buf, size_t len) {
-  const htsblk *const r = &slot->r;
-  size_t n = 0;
-
-  if (r->adr != NULL && r->size > 0) {
-    n = (size_t) r->size < len ? (size_t) r->size : len;
-    memcpy(buf, r->adr, n);
-  } else {
-    if (r->out != NULL)
-      fflush(r->out);
-    if (slot->url_sav[0] != '\0')
-      n = sniff_read_head(slot->url_sav, buf, len);
-    if (n == 0 && slot->tmpfile != NULL && slot->tmpfile[0] != '\0')
-      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 = sniff_inflate_head(raw, n, buf, len);
-#else
-    n = 0;
-#endif
-  }
-  return n;
-}
-
-/* Up to len leading body bytes; 0 when unavailable, and always in
-   non-delayed mode (its HEAD-probe first run couldn't sniff either). */
-static size_t sniff_body_head(httrackp *opt, const sniff_src *src, void *buf,
-                              size_t len) {
-  size_t n = 0;
-
-  if (src == NULL || opt->savename_delayed == HTS_SAVENAME_DELAYED_NONE)
-    return 0;
-  /* live backing slot: a snapshot (back_copy_static) loses r.adr/r.out */
-  if (src->sback != NULL && src->adr != NULL && src->fil != NULL) {
-    const int b = back_index(opt, src->sback, src->adr, src->fil, NULL);
-
-    if (b >= 0)
-      n = sniff_slot_head(&src->sback->lnk[b], buf, len);
-  }
-  if (n == 0 && src->headers != NULL)
-    n = sniff_slot_head(src->headers, buf, len);
-  return n;
-}
-
-/* Contested verdicts: magic proving the URL ext keeps it, else wire wins. */
-static int wire_patches_ext(httrackp *opt, const sniff_src *src,
-                            const char *wiremime, const char *file) {
+/* Should the wire Content-Type override the URL's own extension when naming the
+   saved file? True when the type is patchable (may_unknown2) and either the URL
+   extension implies no specific type or the server declared a disagreeing one.
+   A URL extension mapping to a specific non-HTML type is kept only when the
+   server declared NO type (the HTS_UNKNOWN_MIME sentinel; the #267 mangle
+   guard): a typeless .png stays .png, but a .pdf explicitly served as text/html
+   is named .html. The sentinel rides the cache, so updates stay consistent. */
+static int wire_patches_ext(httrackp *opt, const char *wiremime,
+                            const char *file) {
   char urlmime[256];
 
-  switch (wire_ext_verdict(opt, wiremime, file, urlmime, sizeof(urlmime))) {
-  case WIRE_KEEPS_EXT:
+  if (may_unknown2(opt, wiremime, file))
+    return 0; /* type kept verbatim (keep-list / bogus-multiple) */
+  urlmime[0] = '\0';
+  /* type implied by the URL extension, only when confidently known (flag 0) */
+  if (!get_httptype_sized(opt, urlmime, sizeof(urlmime), file, 0))
+    return 1; /* URL ext implies no known type: trust the wire type */
+  if (strfield2(wiremime, urlmime))
+    return 0; /* wire agrees with the ext: keep it (no .htm->.html churn) */
+  /* wire disagrees with a specific non-HTML URL ext. Keep the ext only when
+     the server declared no type (the sentinel); an explicitly declared type,
+     even text/html, is trusted, so a binary-looking URL that really serves
+     HTML (login/error interstitial, soft-404) is named .html. */
+  if (!is_hypertext_mime(opt, urlmime, file) &&
+      strfield2(wiremime, HTS_UNKNOWN_MIME))
     return 0;
-  case WIRE_WINS:
-    return 1;
-  case WIRE_CONTESTED:
-    break;
-  }
-  if (src != NULL) {
-    if (hts_sniff_mime_known(urlmime)) {
-      unsigned char head[HTS_SNIFF_LEN];
-      const size_t n = sniff_body_head(opt, src, head, sizeof(head));
-
-      if (n > 0)
-        return hts_sniff_mime_consistent(head, n, urlmime) ? 0 : 1;
-    }
-    /* no bytes: reproduce the previous run's verdict (cached X-Save name) */
-    if (src->prev_save != NULL && src->prev_save[0] != '\0') {
-      char prevmime[256];
-
-      prevmime[0] = '\0';
-      if (get_httptype_sized(opt, prevmime, sizeof(prevmime), src->prev_save,
-                             0) &&
-          strfield2(prevmime, urlmime))
-        return 0;
-    }
-  }
   return 1;
 }
 
-int hts_ext_sniff_wanted(httrackp *opt, const char *wiremime,
-                         const char *file) {
-  char urlmime[256];
-
-  return wiremime != NULL && strnotempty(wiremime) &&
-         wire_ext_verdict(opt, wiremime, file, urlmime, sizeof(urlmime)) ==
-             WIRE_CONTESTED &&
-         hts_sniff_mime_known(urlmime);
-}
-
-/* Wire-metadata name change: a Content-Disposition filename wins (returns 2),
-   else the declared type's ext when wire_patches_ext() allows (returns 1),
-   else 0. ext receives the new extension or replacement filename. */
-static int resolve_extension(httrackp *opt, const sniff_src *src,
-                             const char *cdispo, const char *contenttype,
-                             const char *fil, char *ext, size_t ext_size) {
-  if (strnotempty(cdispo)) {
-    strlcpybuff(ext, cdispo, ext_size);
-    return 2;
-  }
-  if (wire_patches_ext(opt, src, contenttype, fil) &&
-      give_mimext(ext, ext_size, contenttype))
-    return 1;
-  return 0;
-}
-
-// Build the local save name (save) from adr/fil; renames on collision
-// (e.g. INDEX.HTML vs index.html).
+// forme le nom du fichier à sauver (save) à partir de fil et adr
+// système intelligent, qui renomme en cas de besoin (exemple: deux INDEX.HTML et index.html)
 int url_savename(lien_adrfilsave *const afs,
                  lien_adrfil *const former,
                  const char *referer_adr, const char *referer_fil, 
@@ -331,13 +198,6 @@ int url_savename(lien_adrfilsave *const afs,
   // copy of fil, used for lookups (see urlhack)
   const char *normadr = adr;
   const char *normfil = fil_complete;
-  /* query keys to strip for this URL (NULL = none); decoupled from urlhack */
-  char BIGSTK stripkeys[HTS_URLMAXSIZE];
-  const char *const strip =
-      StringNotEmpty(opt->strip_query)
-          ? hts_query_strip_keys(StringBuff(opt->strip_query), adr,
-                                 fil_complete, stripkeys, sizeof(stripkeys))
-          : NULL;
   const char *const print_adr = jump_protocol_const(adr);
   const char *start_pos = NULL, *nom_pos = NULL, *dot_pos = NULL;     // Position nom et point
 
@@ -370,13 +230,9 @@ int url_savename(lien_adrfilsave *const afs,
   // www-42.foo.com -> foo.com
   // foo.com/bar//foobar -> foo.com/bar/foobar
   if (opt->urlhack) {
-    // dedup-lookup key; honor the per-feature negatives like htshash.c so
-    // distinct URLs keep distinct savenames (else keep normadr = adr)
-    if (!opt->no_www_dedup)
-      normadr = adr_normalized_sized(adr, normadr_, sizeof(normadr_));
-    normfil =
-        fil_normalized_filtered_ex(fil_complete, normfil_, strip,
-                                   !opt->no_slash_dedup, !opt->no_query_dedup);
+    // copy of adr (without protocol), used for lookups (see urlhack)
+    normadr = adr_normalized_sized(adr, normadr_, sizeof(normadr_));
+    normfil = fil_normalized(fil_complete, normfil_);
   } else {
     if (link_has_authority(adr_complete)) {     // https or other protocols : in "http/" subfolder
       char *pos = strchr(adr_complete, ':');
@@ -389,11 +245,6 @@ int url_savename(lien_adrfilsave *const afs,
         normadr = normadr_;
       }
     }
-    // strip still applies with urlhack off (host left untouched); no // or
-    // query-sort here, to match the hash key (norm_slash/norm_query are 0 when
-    // urlhack is off) so a URL is looked up under the key it was stored with
-    if (strip != NULL)
-      normfil = fil_normalized_filtered_ex(fil_complete, normfil_, strip, 0, 0);
   }
 
   // à afficher sans ftp://
@@ -538,30 +389,45 @@ int url_savename(lien_adrfilsave *const afs,
 
   // si option check_type activée
   if (is_html < 0 && opt->check_type && !ext_chg) {
+    int ishtest = 0;
+
     if (protocol != PROTOCOL_FILE
         && protocol != PROTOCOL_FTP
       ) {
       // tester type avec requète HEAD si on ne connait pas le type du fichier
       if (!((opt->check_type == 1) && (fil[strlen(fil) - 1] == '/')))   // slash doit être html?
         if (opt->savename_delayed == HTS_SAVENAME_DELAYED_HARD ||
-            ishtml(opt, fil) < 0) { // unsure whether it's html or a file
+            (ishtest = ishtml(opt, fil)) <
+                0) { // unsure whether it's html or a file
           // lire dans le cache
-          char BIGSTK previous_save[HTS_URLMAXSIZE * 2];
-          htsblk r;
+          htsblk r = cache_read_including_broken(opt, cache, adr, fil); // test uniquement
 
-          previous_save[0] = '\0';
-          r = cache_read_including_broken(opt, cache, adr, fil,
-                                          previous_save); // test uniquement
+          if (r.statuscode != -1) {     // pas d'erreur de lecture cache
+            char s[32];
 
-          if (r.statuscode != -1) { // cache entry read OK
+            s[0] = '\0';
             hts_log_print(opt, LOG_DEBUG, "Testing link type (from cache) %s%s",
                           adr_complete, fil_complete);
             if (!HTTP_IS_REDIRECT(r.statuscode)) {
-              const sniff_src src = {sback, NULL, adr, fil, previous_save};
-
-              ext_chg = resolve_extension(opt, &src, r.cdispo, r.contenttype,
-                                          fil, ext, sizeof(ext));
+              if (strnotempty(r.cdispo)) {        /* filename given */
+                ext_chg = 2;      /* change filename */
+                strcpybuff(ext, r.cdispo);
+              } else if (wire_patches_ext(opt, r.contenttype, fil)) {
+                if (give_mimext(s, sizeof(s),
+                                r.contenttype)) { // recognized extension
+                  ext_chg = 1;
+                  strcpybuff(ext, s);
+                }
+              }
             }
+#ifdef DEFAULT_BIN_EXT
+            // no extension and potentially bogus
+            else if (ishtest == -2) {
+              ext_chg = 1;
+              strcpybuff(ext, DEFAULT_BIN_EXT + 1);
+            }
+#endif
+            //
           } else if (opt->savename_delayed != HTS_SAVENAME_DELAYED_HARD &&
                      is_userknowntype(opt, fil)) { /* PATCH BY BRIAN SCHRÖDER.
                               Lookup mimetype not only by extension,
@@ -585,13 +451,22 @@ int url_savename(lien_adrfilsave *const afs,
           // fail later
           else if (opt->savename_delayed != HTS_SAVENAME_DELAYED_NONE &&
                    !opt->state.stop) {
-            // Check if the file is ready in backing.
+            // Check if the file is ready in backing. We basically take the same logic as later.
+            // FIXME: we should cleanup and factorize this unholy mess
             if (headers != NULL && headers->status >= 0 && !is_redirect) {
-              const sniff_src src = {sback, headers, adr, fil, NULL};
-
-              ext_chg = resolve_extension(opt, &src, headers->r.cdispo,
-                                          headers->r.contenttype,
-                                          headers->url_fil, ext, sizeof(ext));
+              if (strnotempty(headers->r.cdispo)) {        /* filename given */
+                ext_chg = 2;      /* change filename */
+                strcpybuff(ext, headers->r.cdispo);
+              } else if (wire_patches_ext(opt, headers->r.contenttype,
+                                          headers->url_fil)) {
+                char s[16];
+                if (give_mimext(
+                        s, sizeof(s),
+                        headers->r.contenttype)) { // recognized extension
+                  ext_chg = 1;
+                  strcpybuff(ext, s);
+                }
+              }
             }
             else if (mime_type != NULL) {
               ext[0] = '\0';
@@ -609,6 +484,13 @@ int url_savename(lien_adrfilsave *const afs,
                   if (!may_unknown2(opt, mime_type, fil)) {
                     ext_chg = 1;
                   }
+#ifdef DEFAULT_BIN_EXT
+                  // no extension and potentially bogus
+                  else if (ishtml(opt, fil) == -2) {
+                    ext_chg = 1;
+                    strcpybuff(ext, DEFAULT_BIN_EXT + 1);
+                  }
+#endif
                 } else {
                   ext_chg = 0;
                 }
@@ -627,10 +509,11 @@ int url_savename(lien_adrfilsave *const afs,
             int has_been_moved = 0;
             lien_adrfil current;
 
-            /* Wait for an available test slot, honoring the connection limits
+            /* Ensure we don't use too many sockets by using a "testing" one
+               If we have only 1 simultaneous connection authorized, wait for pending download
+               Wait for an available slot 
              */
-            if (!hts_wait_available_socket(sback, opt, cache, ptr))
-              return -1;
+            URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
 
             /* Rock'in */
             current.adr[0] = current.fil[0] = '\0';
@@ -660,11 +543,24 @@ int url_savename(lien_adrfilsave *const afs,
                   if (ptr >= 0) {
                     back_fillmax(sback, opt, cache, ptr, numero_passe);
                   }
-                  if (!hts_loop_tick(sback, opt, b, ptr)) {
+                  // on est obligé d'appeler le shell pour le refresh..
+                  // Transfer rate
+                  engine_stats();
+
+                  // Refresh various stats
+                  HTS_STAT.stat_nsocket = back_nsoc(sback);
+                  HTS_STAT.stat_errors = fspc(opt, NULL, "error");
+                  HTS_STAT.stat_warnings = fspc(opt, NULL, "warning");
+                  HTS_STAT.stat_infos = fspc(opt, NULL, "info");
+                  HTS_STAT.nbk = backlinks_done(sback, opt->liens, opt->lien_tot, ptr);
+                  HTS_STAT.nb = back_transferred(HTS_STAT.stat_bytes, sback);
+
+                  if (!RUN_CALLBACK7
+                      (opt, loop, sback->lnk, sback->count, b, ptr, opt->lien_tot,
+                       (int) (time_local() - HTS_STAT.stat_timestart),
+                       &HTS_STAT)) {
                     return -1;
-                  } else if (opt->state._hts_cancel ||
-                             !back_checkmirror(
-                                 opt)) { // cancel level 2 or 1 (cancel parsing)
+                  } else if (opt->state._hts_cancel || !back_checkmirror(opt)) {        // cancel 2 ou 1 (cancel parsing)
                     back_delete(opt, cache, sback, b);  // cancel test
                     stop_looping = 1;
                   }
@@ -729,9 +625,8 @@ int url_savename(lien_adrfilsave *const afs,
                                                 "Loop with HEAD request (during prefetch) at %s%s",
                                                 current.adr, current.fil);
                                 }
-                                if (!hts_wait_available_socket(sback, opt,
-                                                               cache, ptr))
-                                  return -1;
+                                // Ajouter
+                                URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
                                 if (back_add(sback, opt, cache, moved.adr, moved.fil, methode, referer_adr, referer_fil, 1) != -1) {        // OK
                                   hts_log_print(opt, LOG_DEBUG,
                                                 "(during prefetch) %s (%d) to link %s at %s%s",
@@ -785,10 +680,30 @@ int url_savename(lien_adrfilsave *const afs,
                     // libérer emplacement backing
                   }
 
-                  // no error: change the type?
-                  ext_chg = resolve_extension(
-                      opt, NULL, back[b].r.cdispo, back[b].r.contenttype,
-                      back[b].url_fil, ext, sizeof(ext));
+                  {             // pas d'erreur, changer type?
+                    char s[16];
+
+                    s[0] = '\0';
+                    if (strnotempty(back[b].r.cdispo)) {        /* filename given */
+                      ext_chg = 2;      /* change filename */
+                      strcpybuff(ext, back[b].r.cdispo);
+                    } else if (wire_patches_ext(opt, back[b].r.contenttype,
+                                                back[b].url_fil)) {
+                      if (give_mimext(
+                              s, sizeof(s),
+                              back[b].r.contenttype)) { // recognized extension
+                        ext_chg = 1;
+                        strcpybuff(ext, s);
+                      }
+                    }
+#ifdef DEFAULT_BIN_EXT
+                    // no extension and potentially bogus
+                    else if (ishtest == -2) {
+                      ext_chg = 1;
+                      strcpybuff(ext, DEFAULT_BIN_EXT + 1);
+                    }
+#endif
+                  }
                 }
                 // FIN Si non déplacé, forcer type?
 
@@ -845,9 +760,9 @@ int url_savename(lien_adrfilsave *const afs,
         strcatbuff(fil, DEFAULT_HTML);  // nommer page par défaut (à priori ici html depuis un proxy http)
     }
   }
-  // Change the extension? e.g. php3 saved as html, cgi as html or gif/xbm
-  // depending on the resolved type.
-  if (ext_chg && !opt->no_type_change) {
+  // Changer extension?
+  // par exemple, php3 sera sauvé en html, cgi en html ou gif, xbm etc.. selon les cas
+  if (ext_chg && !opt->no_type_change) {                // changer ext
     char *a = fil + strlen(fil) - 1;
 
     if ((opt->debug > 1) && (opt->log != NULL)) {
@@ -859,19 +774,11 @@ int url_savename(lien_adrfilsave *const afs,
                       adr_complete, fil_complete, ext);
     }
     if (ext_chg == 1) {
-      // Cut the old extension only when it is empty (a bare trailing dot), the
-      // new one, or a recognized one; an unknown trailing ".token" (e.g.
-      // /article-1.884291, #115) is part of the name, not an extension.
-      const char *const old_ext = get_ext(catbuff, sizeof(catbuff), fil);
-      const int known_ext = !*old_ext || strfield2(old_ext, ext) ||
-                            is_knowntype(opt, fil) || is_dyntype(old_ext) ||
-                            ishtml_ext(old_ext) != -1;
-
       while((a > fil) && (*a != '.') && (*a != '/'))
         a--;
-      if (*a == '.' && known_ext)
-        *a = '\0';          // cut
-      strcatbuff(fil, "."); // re-add the dot
+      if (*a == '.')
+        *a = '\0';              // couper
+      strcatbuff(fil, ".");     // recopier point
     } else {
       while((a > fil) && (*a != '/'))
         a--;
@@ -879,7 +786,7 @@ int url_savename(lien_adrfilsave *const afs,
         a++;
       *a = '\0';
     }
-    strcatbuff(fil, ext); // append ext/name
+    strcatbuff(fil, ext);       // copier ext/nom
   }
   // Rechercher premier / et dernier .
   {
@@ -1332,7 +1239,8 @@ int url_savename(lien_adrfilsave *const afs,
 
     while((a > afs->save) && (*a != '.') && (*a != '/'))
       a--;
-    if (*a != '.') {                         // agh pas de point
+    if (*a != '.') {            // agh pas de point
+      //strcatbuff(save,".none");                 // a éviter
       strcatbuff(afs->save, ".html");        // préférable!
       hts_log_print(opt, LOG_DEBUG, "Default HTML type set for %s%s => %s",
                     adr_complete, fil_complete, afs->save);
@@ -1470,6 +1378,17 @@ int url_savename(lien_adrfilsave *const afs,
   fil_simplifie(afs->save);
 
   /* convert name to UTF-8 ? Note: already done while parsing. */
+  //if (charset != NULL && charset[0] != '\0') {
+  //  char *const s = hts_convertStringToUTF8(save, (int) strlen(save), charset);
+
+  //  if (s != NULL) {
+  //    hts_log_print(opt, LOG_DEBUG,
+  //                  "engine: save-name: charset conversion from '%s' to '%s' using charset '%s'",
+  //                  save, s, charset);
+  //    strcpybuff(save, s);
+  //    free(s);
+  //  }
+  //}
 
   /* callback */
   RUN_CALLBACK5(opt, savename, adr_complete, fil_complete, referer_adr,
@@ -1617,6 +1536,10 @@ int url_savename(lien_adrfilsave *const afs,
         int sameAdr = (strfield2(heap(i)->adr, normadr) != 0);
         int sameFil;
 
+        // NO - URL hack is only for stripping // and www.
+        //if (opt->urlhack != 0)
+        //  sameFil = ( strfield2(heap(i)->fil, normfil) != 0);
+        //else
         sameFil = (strcmp(heap(i)->fil, normfil) == 0);
         if (sameAdr && sameFil) {       // ok c'est le même lien, adresse déja définie
           /* Take the existing name not to screw up with cAsE sEnSiTiViTy of Linux/Unix */
@@ -1682,13 +1605,17 @@ int url_savename(lien_adrfilsave *const afs,
 
           strcpybuff(afs->save, tempo);
 
+          //printf("switched: %s\n",save);
+
         }                       // if
       }
 #if DEBUG_SAVENAME
       printf("\nEnd search, %s\n", fil_complete);
 #endif
-    } while (!nom_ok);
+    } while(!nom_ok);
+
   }
+  //printf("'%s' %s %s\n",save,adr,fil);
 
   return 0;
 }
@@ -1794,10 +1721,10 @@ char *url_savename_refname_fullpath(httrackp * opt, const char *adr,
     StringBuff(opt->path_log), digest_filename);
 }
 
-/* remove refname if any; HTS_TRUE if it was removed */
-hts_boolean url_savename_refname_remove(httrackp *opt, const char *adr,
-                                        const char *fil) {
+/* remove refname if any */
+void url_savename_refname_remove(httrackp * opt, const char *adr,
+                                 const char *fil) {
   char *filename = url_savename_refname_fullpath(opt, adr, fil);
 
-  return UNLINK(filename) == 0 ? HTS_TRUE : HTS_FALSE;
+  (void) UNLINK(filename);
 }

src/htsname.h

@@ -100,15 +100,12 @@ void standard_name(char *b, size_t bsize, const char *dot_pos,
                    const char *nom_pos, const char *fil_complete,
                    int short_ver);
 void url_savename_addstr(char *d, const char *s);
-/* Contested wire-vs-ext verdict that a body sniff could settle (htssniff.h). */
-int hts_ext_sniff_wanted(httrackp *opt, const char *wiremime, const char *file);
 char *url_md5(char *digest_buffer, const char *fil_complete);
 void url_savename_refname(const char *adr, const char *fil, char *filename);
 char *url_savename_refname_fullpath(httrackp * opt, const char *adr,
                                     const char *fil);
-/* Remove the temp-ref for (adr,fil); HTS_TRUE if it was removed. */
-hts_boolean url_savename_refname_remove(httrackp *opt, const char *adr,
-                                        const char *fil);
+void url_savename_refname_remove(httrackp * opt, const char *adr,
+                                 const char *fil);
 #endif
 
 #endif

src/htsopt.h

@@ -105,6 +105,7 @@ typedef struct htsfilters htsfilters;
 struct htsfilters {
   char ***filters; /**< pointer to the +/-pattern filter array */
   int *filptr;     /**< pointer to the current filter count */
+  // int*    filter_max;
 };
 
 /* User callbacks chain */
@@ -240,7 +241,7 @@ struct htsoptstate {
   char *userhttptype;
   int verif_backblue_done; /**< backblue.gif/fade.gif already emitted */
   int verif_external_status;
-  coucal dns_cache; /**< DNS resolution cache: hostname -> t_dnscache record */
+  t_dnscache *dns_cache;  /**< DNS resolution cache */
   int dns_cache_nthreads; /**< number of in-flight DNS resolver threads */
   /* HTML parsing state */
   char _hts_errmsg[HTS_CDLMAXSIZE + 256]; /**< last engine error message */
@@ -439,6 +440,7 @@ struct httrackp {
   float maxconn;          /**< max connections per second */
   int waittime;           /**< scheduled start time (wall-clock seconds) */
   hts_cachemode cache;    /**< cache generation mode */
+  // int aff_progress;     // progress bar
   hts_boolean shell; /**< driven by a shell over stdin/stdout pipes */
   t_proxy proxy;     /**< proxy configuration */
   hts_savename_83
@@ -490,6 +492,7 @@ struct httrackp {
   hts_verbosedisplay verbosedisplay; /**< animated text progress display */
   String footer; /**< footer/info line injected into pages */
   int maxcache;  /**< in-memory cache backing limit (bytes) */
+  // int maxcache_anticipate; // maximum links to anticipate (upper bound)
   hts_boolean ftp_proxy;    /**< use the HTTP proxy for FTP too */
   String filelist;          /**< file listing URLs to include */
   String urllist;           /**< file listing filters to include */
@@ -526,18 +529,6 @@ struct httrackp {
   htslibhandles libHandles; /**< loaded external module handles */
   //
   htsoptstate state; /**< embedded live engine state */
-  String strip_query; /**< query keys to drop when deduping URLs (-strip-query);
-                           appended at the tail to keep field offsets stable */
-  hts_boolean
-      no_www_dedup; /**< with urlhack, keep www.host distinct from host */
-  hts_boolean no_slash_dedup; /**< with urlhack, keep redundant // in paths */
-  hts_boolean no_query_dedup; /**< with urlhack, keep query-argument order */
-  String cookies_file;        /**< extra Netscape cookies.txt to preload
-                                 (--cookies-file) */
-  int pause_min_ms; /**< inter-file pause lower bound, ms (0=off, #185) */
-  int pause_max_ms; /**< inter-file pause upper bound, ms */
-  String why_url;   /**< URL to diagnose (--why): print the deciding filter rule
-                         and exit without crawling */
 };
 
 /* Running statistics for a mirror. */
@@ -548,6 +539,8 @@ typedef struct hts_stat_struct hts_stat_struct;
 struct hts_stat_struct {
   LLint HTS_TOTAL_RECV; /**< total bytes received from the network */
   LLint stat_bytes;     /**< total bytes written to disk */
+  // int HTS_TOTAL_RECV_STATE;  // status: 0 ok 1: slow down a little 2: slow
+  // down 3: a lot
   TStamp stat_timestart; /**< mirror start time */
   //
   LLint total_packed;    /**< compressed bytes received (on the wire) */
@@ -679,6 +672,7 @@ struct lien_url {
   int depth;        /**< remaining allowed depth; >0 strong, 0 weak */
   int pass2;        /**< second-pass marker; -1 means handled in background */
   char link_import; /**< imported after a move; skip the usual up/down rules */
+  // int moved;          // pointer to moved
   int retry;    /**< remaining retries */
   int testmode; /**< test only: send just a HEAD */
 };
@@ -723,6 +717,9 @@ struct lien_back {
   LLint chunk_size; /**< size of the chunk being loaded */
   LLint chunk_blocksize; /**< data size declared by the chunk */
   LLint compressed_size; /**< compressed size (stats only) */
+  //
+  // int links_index;        // to access liens[links_index]
+  //
   char info[256]; /**< status text, e.g. for FTP */
   int stop_ftp;   /**< stop flag for FTP */
   int finalized;  /**< finalized (memory optimization) */

src/htsparse.h

@@ -66,6 +66,7 @@ struct htsmoduleStructExtended {
   char ***filters_;
   robots_wizard *robots_;
   hash_struct *hash_;
+  //int *lien_max_;
 
   /* Base & codebase */
   char *base;
@@ -115,19 +116,6 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre);
 int hts_mirror_check_moved(htsmoduleStruct * str,
                            htsmoduleStructExtended * stre);
 
-/*
-  Non-zero if a redirect (cur_adr,cur_fil)->(moved_adr,moved_fil) saves to the
-  same local file, so it must be followed rather than turned into a
-  self-pointing "moved" stub (#159). Mirrors the savename: scheme+userinfo
-  stripped, www kept (www dedup is the crawl layer's job), path
-  slash/query-normalized per the URL-hack flags. Not hash_url_equals: that keys
-  on the dedup hash, which folds www and never collapses http<->https.
-*/
-hts_boolean hts_redirect_same_savefile(httrackp *opt, const char *cur_adr,
-                                       const char *cur_fil,
-                                       const char *moved_adr,
-                                       const char *moved_fil);
-
 /*
   Process user intercations: pause, add link, delete link..
 */
@@ -174,4 +162,27 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
   /* Apply changes */ \
   * str->ptr_ = ptr
 
+#define WAIT_FOR_AVAILABLE_SOCKET() do { \
+  int prev = opt->state._hts_in_html_parsing; \
+  while(back_pluggable_sockets_strict(sback, opt) <= 0) { \
+    opt->state._hts_in_html_parsing = 6; \
+    /* Wait .. */ \
+    back_wait(sback,opt,cache,0); \
+    /* Transfer rate */ \
+    engine_stats(); \
+    /* Refresh various stats */ \
+    HTS_STAT.stat_nsocket=back_nsoc(sback); \
+    HTS_STAT.stat_errors=fspc(opt,NULL,"error"); \
+    HTS_STAT.stat_warnings=fspc(opt,NULL,"warning"); \
+    HTS_STAT.stat_infos=fspc(opt,NULL,"info"); \
+    HTS_STAT.nbk=backlinks_done(sback,opt->liens,opt->lien_tot,ptr); \
+    HTS_STAT.nb=back_transferred(HTS_STAT.stat_bytes,sback); \
+    /* Check */ \
+    if (!RUN_CALLBACK7(opt, loop, sback->lnk, sback->count, -1,ptr,opt->lien_tot,(int) (time_local()-HTS_STAT.stat_timestart),&HTS_STAT)) { \
+      return -1; \
+    } \
+  } \
+  opt->state._hts_in_html_parsing = prev; \
+} while(0)
+
 #endif

src/htsrobots.c

@@ -44,84 +44,28 @@ Please visit our Website: http://www.httrack.com
 
 // -- robots --
 
-/* RFC 9309 path-prefix match; '*' any run, '$' anchors end; linear. */
-static hts_boolean robots_pattern_match(const char *pattern, const char *path) {
-  size_t patlen = strlen(pattern);
-  hts_boolean anchored = HTS_FALSE;
-  const char *p, *pend, *s;
-  const char *star = NULL, *star_s = NULL;
-
-  if (patlen > 0 && pattern[patlen - 1] == '$') {
-    anchored = HTS_TRUE;
-    patlen--;
-  }
-  p = pattern;
-  pend = pattern + patlen;
-  s = path;
-  while (*s != '\0') {
-    if (p == pend) {
-      if (!anchored)
-        return HTS_TRUE;  // prefix matched
-      if (star != NULL) { // anchored: '*' must eat the rest
-        p = star + 1;
-        s = ++star_s;
-        continue;
-      }
-      return HTS_FALSE;
-    }
-    if (*p == '*') {
-      star = p++;
-      star_s = s;
-    } else if (*p == *s) {
-      p++;
-      s++;
-    } else if (star != NULL) {
-      p = star + 1;
-      s = ++star_s;
-    } else {
-      return HTS_FALSE;
-    }
-  }
-  while (p < pend && *p == '*')
-    p++;
-  return (p == pend) ? HTS_TRUE : HTS_FALSE;
-}
-
 // fil="" : vérifier si règle déja enregistrée
 int checkrobots(robots_wizard * robots, const char *adr, const char *fil) {
   while(robots) {
     if (strfield2(robots->adr, adr)) {
       if (fil[0]) {
-        /* RFC 9309: longest pattern wins, Allow beats Disallow on ties. */
         int ptr = 0;
-        char line[HTS_ROBOTS_TOKEN_SIZE];
-        size_t toklen = strlen(robots->token);
-        size_t best_len = 0;
-        hts_boolean matched = HTS_FALSE;
-        hts_boolean best_allow = HTS_FALSE;
+        char line[250];
 
-        while (ptr < (int) toklen) {
-          ptr += binput(robots->token + ptr, line, sizeof(line) - 1);
-          if (line[0] != 'A' && line[0] != 'D')
-            continue;
-          {
-            const hts_boolean is_allow =
-                (line[0] == 'A') ? HTS_TRUE : HTS_FALSE;
-            const char *pat = line + 1;
-
-            if (robots_pattern_match(pat, fil)) {
-              const size_t len = strlen(pat);
-
-              if (!matched || len > best_len || (len == best_len && is_allow)) {
-                matched = HTS_TRUE;
-                best_len = len;
-                best_allow = is_allow;
+        if (strnotempty(robots->token)) {
+          do {
+            ptr += binput(robots->token + ptr, line, 200);
+            if (line[0] == '/') {       // absolu
+              if (strfield(fil, line)) {        // commence avec ligne
+                return -1;      // interdit
+              }
+            } else {            // relatif
+              if (strstrcase(fil, line)) {
+                return -1;
               }
             }
-          }
+          } while((strnotempty(line)) && (ptr < (int) strlen(robots->token)));
         }
-        if (matched && !best_allow)
-          return -1; // forbidden
       } else {
         return -1;
       }
@@ -130,93 +74,6 @@ int checkrobots(robots_wizard * robots, const char *adr, const char *fil) {
   }
   return 0;
 }
-
-/* Append "<marker><pattern>\n" to the bounded rule blob if it fits. */
-static void robots_blob_add(char *blob, size_t blobsize, char marker,
-                            const char *pat) {
-  const size_t used = strlen(blob);
-  const size_t need = strlen(pat) + 2; // marker + '\n'
-
-  if (need < blobsize - used) { // overflow-safe: used <= blobsize-1
-    blob[used] = marker;
-    blob[used + 1] = '\0';
-    strlcatbuff(blob, pat, blobsize);
-    strlcatbuff(blob, "\n", blobsize);
-  }
-}
-
-void robots_parse(robots_wizard *robots, const char *adr, const char *body,
-                  size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow) {
-  size_t bptr = 0;
-  int record = 0;
-  char BIGSTK line[1024];
-  char BIGSTK blob[HTS_ROBOTS_TOKEN_SIZE];
-
-  blob[0] = '\0';
-  if (info != NULL && infosize > 0)
-    info[0] = '\0';
-#if DEBUG_ROBOTS
-  printf("robots.txt dump:\n%s\n", body);
-#endif
-  while (bptr < bodysize) {
-    char *comm;
-    int llen;
-
-    bptr += binput(body + bptr, line, sizeof(line) - 2);
-    comm = strchr(line, '#'); // strip comment
-    if (comm != NULL)
-      *comm = '\0';
-    llen = (int) strlen(line); // strip trailing spaces
-    while (llen > 0 && is_realspace(line[llen - 1])) {
-      line[llen - 1] = '\0';
-      llen--;
-    }
-    if (strfield(line, "user-agent:")) {
-      char *a = line + 11;
-
-      while (is_realspace(*a))
-        a++;
-      if (*a == '*') {
-        if (record != 2)
-          record = 1; // generic group applies to us
-      } else if (strfield(a, "httrack") || strfield(a, "winhttrack") ||
-                 strfield(a, "webhttrack")) {
-        blob[0] = '\0'; // explicit group: restart capture
-        if (info != NULL && infosize > 0)
-          info[0] = '\0';
-        record = 2; // locked to the httrack group
-      } else
-        record = 0;
-    } else if (record) {
-      hts_boolean is_allow = strfield(line, "allow:");
-      hts_boolean is_disallow = !is_allow && strfield(line, "disallow:");
-
-      if (is_allow || is_disallow) {
-        char *a = line + (is_allow ? 6 : 9);
-
-        while (is_realspace(*a))
-          a++;
-        if (strnotempty(a)) {
-          if (is_disallow && !keep_root_disallow && strcmp(a, "/") == 0) {
-            // dropped: site-wide disallow ignored by option
-          } else {
-            robots_blob_add(blob, sizeof(blob), is_allow ? 'A' : 'D', a);
-            if (is_disallow && info != NULL &&
-                strlen(a) + 2 < infosize - strlen(info)) {
-              if (strnotempty(info))
-                strlcatbuff(info, ", ", infosize);
-              strlcatbuff(info, a, infosize);
-            }
-          }
-        }
-      }
-    }
-  }
-  if (strnotempty(blob))
-    checkrobots_set(robots, adr, blob);
-}
-
 int checkrobots_set(robots_wizard * robots, const char *adr, const char *data) {
   if (((int) strlen(adr)) >= sizeof(robots->adr) - 2)
     return 0;

src/htsrobots.h

@@ -39,27 +39,17 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DEF_FWSTRUCT_robots_wizard
 typedef struct robots_wizard robots_wizard;
 #endif
-
-/* Per-host blob: one rule per line, first byte 'A'/'D' then path pattern. */
-#define HTS_ROBOTS_TOKEN_SIZE 4096
-
 struct robots_wizard {
   char adr[128];
-  char token[HTS_ROBOTS_TOKEN_SIZE];
+  char token[4096];
   struct robots_wizard *next;
 };
 
 /* Library internal definictions */
 #ifdef HTS_INTERNAL_BYTECODE
-/* -1 if `fil` disallowed for `adr` (RFC 9309); empty: -1 if rules exist. */
 int checkrobots(robots_wizard * robots, const char *adr, const char *fil);
 void checkrobots_free(robots_wizard * robots);
 int checkrobots_set(robots_wizard * robots, const char *adr, const char *data);
-/* Parse robots.txt `body` for `adr`, storing the HTTrack group's rules; `info`
-   gets a disallow summary, `keep_root_disallow` FALSE drops "Disallow: /". */
-void robots_parse(robots_wizard *robots, const char *adr, const char *body,
-                  size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow);
 #endif
 
 #endif

src/htssafe.h

@@ -456,13 +456,6 @@ 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