Remove commented-out code across the engine

Sweep of ~650 lines of //-disabled statements, declarations, and calls
(plus three /*-wrapped dead blocks in htscoremain.c and htscore.c and
the MFC pApp remnant in htsserver.c). Prose comments stay, including
labels that describe live code; usage examples and config-knob docs
(HTS_TRACE_MALLOC, the htsweb.c DEBUG toggle) were kept. Insertions are
clang-format rewraps of live lines that became touched by the deletions.

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

.github/workflows/ci.yml

@@ -61,6 +61,50 @@ 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,
@@ -188,6 +232,52 @@ 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
+
   # 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

.gitignore

@@ -39,3 +39,6 @@ Makefile
 
 # Editor / autotools backup files.
 *~
+
+# Python bytecode (tests/local-server.py).
+__pycache__/

AGENTS.md

@@ -33,8 +33,9 @@ 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 -#N` debug
-  subcommand (`htscoremain.c`) driven by a `tests/NN_*.test`, over a slow crawl.
+- 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.
 
 ## Review your change adversarially (strongly suggested)
 Before pushing, and when reviewing others, don't skim for bugs:

CONTRIBUTING.md

@@ -39,6 +39,10 @@ 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.

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.9], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.11], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
 AC_COPYRIGHT([
 HTTrack Website Copier, Offline Browser for Windows and Unix
 Copyright (C) 1998-2015 Xavier Roche and other contributors
@@ -29,10 +29,11 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 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"
+# 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"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 
@@ -63,6 +64,16 @@ AC_SUBST(LT_CV_OBJDIR,$lt_cv_objdir)
 # Export version info
 AC_SUBST(VERSION_INFO)
 
+# Versioned plugin name for dlopen() in hts_create_opt(); soname major is
+# libtool's current - age, so this tracks VERSION_INFO bumps automatically.
+HTS_SONAME_MAJOR=$((${VERSION_INFO%%:*} - ${VERSION_INFO##*:}))
+case "$host_os" in
+darwin*) HTS_LIBHTSJAVA_NAME="libhtsjava.$HTS_SONAME_MAJOR.dylib" ;;
+*) HTS_LIBHTSJAVA_NAME="libhtsjava.so.$HTS_SONAME_MAJOR" ;;
+esac
+AC_DEFINE_UNQUOTED([HTS_LIBHTSJAVA_NAME], ["$HTS_LIBHTSJAVA_NAME"],
+  [Versioned libhtsjava runtime name, derived from VERSION_INFO])
+
 ### Default CFLAGS
 DEFAULT_CFLAGS="-Wall -Wformat -Wformat-security \
 -Wmultichar -Wwrite-strings -Wcast-qual -Wcast-align \

debian/changelog

@@ -1,3 +1,37 @@
+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

@@ -1,9 +1,8 @@
 Source: httrack
 Section: web
-Priority: optional
 Maintainer: Xavier Roche <roche@httrack.com>
-Standards-Version: 4.7.0
-Build-Depends: debhelper-compat (= 13), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
+Standards-Version: 4.7.4
+Build-Depends: debhelper-compat (= 14), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
 Rules-Requires-Root: no
 Homepage: http://www.httrack.com
 Vcs-Git: https://github.com/xroche/httrack.git
@@ -30,7 +29,7 @@ Description: Copy websites to your computer (Offline browser)
 Package: webhttrack
 Architecture: any
 Multi-Arch: foreign
-Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, firefox-esr | chromium | www-browser
+Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, chromium | firefox-esr | www-browser
 Replaces: webhttrack-common (<< 3.43.9-2)
 Breaks: webhttrack-common (<< 3.43.9-2)
 Suggests: httrack, httrack-doc

debian/source/lintian-overrides

@@ -1,4 +1,6 @@
-httrack source: changelog-should-mention-nmu
+# 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: source-nmu-has-incorrect-version-number
 
 # The bundled HTML pages are the genuine upstream documentation taken from

debian/upstream/metadata

@@ -0,0 +1,6 @@
+---
+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>

history.txt

@@ -4,7 +4,42 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
-3.49-9
+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
 + 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

@@ -0,0 +1,37 @@
+# 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.

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 "13 June 2026" "httrack website copier"
+.TH httrack 1 "27 June 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -24,6 +24,7 @@ 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 ]
@@ -43,11 +44,13 @@ 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\-u, \-\-check\-type[=N]\fR ]
 [ \fB\-j, \-\-parse\-java[=N]\fR ]
 [ \fB\-sN, \-\-robots[=N]\fR ]
@@ -153,6 +156,8 @@ 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:
@@ -198,6 +203,8 @@ 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
@@ -209,6 +216,8 @@ 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 \-u
 check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (\-\-check\-type[=N])
 .IP \-j
@@ -225,6 +234,8 @@ 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
@@ -313,12 +324,8 @@ 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 \-#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 \-#test
+list engine self\-tests (run one with \-#test=NAME [args])
 .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 \
+	htscache_selftest.c htsdns_selftest.c htsselftest.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 \
+	htsmodules.c htscharset.c punycode.c htsencoding.c htssniff.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
 	hts-indextmpl.h htsalias.h htsback.h htsbase.h htssafe.h \
-	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htscatchurl.h  \
+	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htsselftest.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 \
+	htsmodules.h htsname.h htsnet.h htssniff.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

@@ -60,6 +60,9 @@ 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"},
@@ -107,6 +110,12 @@ 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"},
+  {"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", ""},
@@ -123,6 +132,9 @@ 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"},
@@ -241,6 +253,7 @@ const char *hts_optalias[][4] = {
 
   {"", "", "", ""}
 };
+/* clang-format on */
 
 /* 
   Check for alias in command-line 
@@ -270,7 +283,6 @@ 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';
@@ -348,7 +360,6 @@ 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

@@ -43,21 +43,22 @@ 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"
@@ -569,9 +570,12 @@ 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,
-                      "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);
+                      "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);
       } else {
         hts_log_print(opt, LOG_INFO,
                       "incomplete file not yet stored in cache (expected "
@@ -591,7 +595,6 @@ 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
@@ -876,11 +879,12 @@ 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 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);
+            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);
           }
         }
 
@@ -920,7 +924,6 @@ 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;
@@ -1355,7 +1358,49 @@ 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;
@@ -1363,6 +1408,12 @@ 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")
@@ -1382,7 +1433,6 @@ 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);
       }
     }
@@ -1523,7 +1573,6 @@ 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;
 
@@ -1531,7 +1580,6 @@ 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, "");
@@ -1770,8 +1818,7 @@ 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
-            //file_notify(back[p].url_adr, back[p].url_fil, back[p].url_sav, 0, 0, back[p].r.notmodified);        // not modified
+            back[p].status = STATUS_READY; // OK prêt
             back_set_finished(sback, p);
 
             // finalize transfer
@@ -1786,7 +1833,6 @@ 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)
           }
@@ -1981,7 +2027,6 @@ 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;
@@ -2032,7 +2077,6 @@ 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
@@ -2098,9 +2142,9 @@ 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!)
-      //if ((back[p].statuscode!=HTTP_OK) || (soc<0)) { // ERREUR HTTP/autre
+      // 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 CNXDEBUG
       printf("Xfopen ok, poll..\n");
@@ -2118,7 +2162,6 @@ 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)
@@ -2139,8 +2182,6 @@ 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 {
@@ -2213,9 +2254,6 @@ 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);
-    //}
   }
 }
 
@@ -2234,12 +2272,13 @@ 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->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->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
+      ;
 }
 
 static int slot_can_be_finalized(httrackp * opt, const lien_back * back) {
@@ -2263,11 +2302,6 @@ 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)
@@ -2415,6 +2449,34 @@ 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;
@@ -2423,9 +2485,6 @@ 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);
@@ -2435,8 +2494,7 @@ 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=0;i<back_max;i++) {
+    for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
       unsigned int i = (i_mod + mod_random) % (back_max);
 
       // en cas de gestion du connect préemptif
@@ -2473,8 +2531,7 @@ 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
-        //printf("....socket in progress: %d\n",back[i].r.soc);
+#if BDEBUG == 1
 #endif
         // non local et non ftp
         if (!back[i].r.is_file) {
@@ -2560,8 +2617,7 @@ 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=0;i<back_max;i++) {
+    for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
       unsigned int i = (i_mod + mod_random) % (back_max);
 
       if (back[i].status > 0) {
@@ -2701,7 +2757,6 @@ 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,
@@ -2768,7 +2823,6 @@ 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)
@@ -2888,10 +2942,10 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
           // range size hack old location
 
 #if HTS_DIRECTDISK
-          // 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) {
+          // Shortcut: store the file directly on disk when possible,
+          // sparing memory
+          if (back[i].status &&
+              !back[i].locked) { // name still pending when locked
             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
@@ -3041,8 +3095,7 @@ 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!
-                //printf("chunk end at %d\n",back[i].r.size);
+              if (back[i].r.size == back[i].r.totalsize) { // fin chunk!
                 back[i].status = STATUS_CHUNK_CR;       /* fetch ending CRLF */
                 if (back[i].chunk_adr != NULL) {
                   freet(back[i].chunk_adr);
@@ -3105,11 +3158,9 @@ 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) && (back[i].status==STATUS_WAIT_HEADERS)) {    // tester totalsize
+            if (back[i].r.totalsize >= 0) { // 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
@@ -3118,14 +3169,13 @@ 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
                 }
               }
             }
@@ -3252,10 +3302,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                          back[i].r.size);
 #endif
                   /* End */
-                  //if (back[i].status==STATUS_CHUNK_CR) {
-                  back[i].status = STATUS_READY;        // fin  
+                  back[i].status = STATUS_READY; // fin
                   back_set_finished(sback, i);
-                  //}
 
                   // finalize transfer if not temporary
                   if (!IS_DELAYED_EXT(back[i].url_sav)) {
@@ -3722,7 +3770,6 @@ 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);
@@ -3732,38 +3779,32 @@ 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");
-
                     }
 
-/********** 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
+                  }
+                  // 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;
                     back_set_finished(sback, i);
-                    // 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
+                    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
 
                     // effacer buffer (requète)
                     if (!noFreebuff) {
@@ -3774,35 +3815,70 @@ 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) {
+                      if (sz >= 0 && range_ok) {
                         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), "ab");       // append
+                            back[i].r.out =
+                                FOPEN(fconv(catbuff, sizeof(catbuff),
+                                            back[i].url_sav),
+                                      "r+b"); // resume in place
                             if (back[i].r.out && opt->cache != 0) {
-                              back[i].r.is_write = 1;   // écrire
-                              back[i].r.size = sz;      // déja écrit
-                              back[i].r.statuscode = HTTP_OK;   // Forcer 'OK'
+                              back[i].r.is_write = 1;
+                              back[i].r.size = resume; // bytes already on disk
+                              back[i].r.statuscode = HTTP_OK; // force 'OK'
                               if (back[i].r.totalsize >= 0)
-                                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);
-                              }
+                                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");
+                                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);
@@ -3814,17 +3890,18 @@ 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 = sz + 1;
+                            LLint alloc_mem = resume + 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 = sz;
+                              back[i].r.size = resume;
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += sz;      // plus en fait
-                              if ((fread(back[i].r.adr, 1, sz, fp)) != sz) {
+                                back[i].r.totalsize += resume; // -> full size
+                              if ((fread(back[i].r.adr, 1, (size_t) resume,
+                                         fp)) != (size_t) resume) {
                                 back[i].status = STATUS_READY;  // terminé (voir plus loin)
                                 back_set_finished(sback, i);
                                 strcpybuff(back[i].r.msg,
@@ -3842,14 +3919,30 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                          "No memory for partial file");
                             }
                             fclose(fp);
-                          } else {      // Argh.. 
+                          } else {                              // open failed
                             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 {  // Non trouvé??
+                      } 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
                         back[i].status = STATUS_READY;  // terminé (voir plus loin)
                         back_set_finished(sback, i);
                         strcpybuff(back[i].r.msg, "Can not find partial file");
@@ -3864,7 +3957,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           deletehttp(&back[i].r);
                         }
                         back[i].r.soc = INVALID_SOCKET;
-                        //back[i].r.statuscode=206;  ????????
                         back[i].r.statuscode = STATUSCODE_NON_FATAL;
                         if (strnotempty(back[i].r.msg))
                           strcpybuff(back[i].r.msg,
@@ -3885,10 +3977,13 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                               && (back[i].r.adr = (char *) malloct(2))) {
                             back[i].r.adr[0] = 0;
                           }
-                          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
+                          /* 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
                           back[i].is_chunk = 0;
                           back[i].status = 1;   // start body
                         } else {
@@ -3930,7 +4025,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
                       }
                     }
-
                   }
 
                   /*} */
@@ -3950,14 +4044,11 @@ 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)
@@ -3970,18 +4061,16 @@ 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=0;i<back_max;i++) {
+      for (i_mod = 0; i_mod < (unsigned int) back_max; i_mod++) {
         unsigned int i = (i_mod + mod_random) % (back_max);
 
         if (back[i].status > 0) {       // réception/connexion/..
@@ -4009,7 +4098,6 @@ 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);
@@ -4085,6 +4173,11 @@ 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)) {
@@ -4101,13 +4194,19 @@ int back_checkmirror(httrackp * opt) {
      */
   }
   // Check max time
-  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);
+  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;
     }
   }
   return 1;                     /* Ok, go on */

src/htsback.h

@@ -113,6 +113,12 @@ 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,
@@ -136,6 +142,8 @@ 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

@@ -55,8 +55,6 @@ 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
 
@@ -129,6 +127,8 @@ 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,
@@ -146,7 +146,8 @@ typedef enum BackStatusCode {
   STATUSCODE_NON_FATAL = -5,
   STATUSCODE_SSL_HANDSHAKE = -6,
   STATUSCODE_TOO_BIG = -7,
-  STATUSCODE_TEST_OK = -10
+  STATUSCODE_TEST_OK = -10,
+  STATUSCODE_EXCLUDED = -11 /* aborted: MIME excluded by a -mime: filter */
 } 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 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
+    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
     rm -f CP932.TXT CP936.TXT CP949.TXT CP950.TXT
 fi
 

src/htsbauth.c

@@ -107,7 +107,6 @@ 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;
 }
@@ -208,8 +207,6 @@ 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.c

@@ -40,6 +40,7 @@ Please visit our Website: http://www.httrack.com
 #include "htscore.h"
 #include "htsbasenet.h"
 #include "htsmd5.h"
+#include <limits.h>
 #include <time.h>
 
 #include "htszlib.h"
@@ -220,6 +221,40 @@ struct cache_back_zip_entry {
 	} \
 } while(0)
 
+/* Consecutive entry write failures before the cache stream is declared dead. */
+#define CACHE_MAX_WRITE_FAILURES 8
+
+/* Cache write failed: a fatal errno or a failure streak aborts the mirror
+   (exit_xh); an isolated failure only drops the current entry. */
+static void cache_zip_write_failed(httrackp *opt, cache_back *cache,
+                                   const char *what, int zErr,
+                                   hts_boolean entry_open, const char *url_adr,
+                                   const char *url_fil) {
+  const int fatal_errno = zErr == ZIP_ERRNO && check_fatal_io_errno();
+
+  cache->zipWriteFailures++;
+  if (fatal_errno || cache->zipWriteFailures >= CACHE_MAX_WRITE_FAILURES) {
+    if (!cache->zipWriteFailed) {
+      cache->zipWriteFailed = HTS_TRUE;
+      if (fatal_errno) {
+        hts_log_print(opt, LOG_ERROR,
+                      "Mirror aborted: disk full or filesystem problems");
+      } else {
+        hts_log_print(opt, LOG_ERROR,
+                      "Mirror aborted: cache write failed (%s): %s", what,
+                      hts_get_zerror(zErr));
+      }
+    }
+    opt->state.exit_xh = -1; /* fatal: stop the mirror, exit non-zero */
+  } else {
+    if (entry_open)
+      zipCloseFileInZip((zipFile) cache->zipOutput); /* abandon, best-effort */
+    hts_log_print(opt, LOG_WARNING,
+                  "cache write failed (%s: %s), entry not cached: %s%s", what,
+                  hts_get_zerror(zErr), url_adr, url_fil);
+  }
+}
+
 /* Ajout d'un fichier en cache */
 void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
                const char *url_adr, const char *url_fil, const char *url_save,
@@ -230,12 +265,14 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
   char BIGSTK headers[8192];
   int headersSize = 0;
 
-  //int entryBodySize = 0;
-  //int entryFilenameSize = 0;
   zip_fileinfo fi;
   const char *url_save_suffix = url_save;
   int zErr;
 
+  /* already failed and aborting; don't touch the broken stream again */
+  if (cache->zipWriteFailed)
+    return;
+
   // robots.txt hack
   if (url_save == NULL) {
     dataincache = 0;            // testing links
@@ -263,10 +300,19 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
   if (r->size < 0)              // error
     return;
 
-  // data in cache
-  if (dataincache) {
-    assertf(((int) r->size) == r->size);
-    //entryBodySize = (int) r->size;
+  // data in cache: the body must fit the 32-bit zip write API
+  if (dataincache && (LLint) (int) r->size != r->size) {
+    if (r->is_write && url_save != NULL && strnotempty(url_save)) {
+      hts_log_print(opt, LOG_WARNING,
+                    "file too large for the cache, storing headers only: %s%s",
+                    url_adr, url_fil);
+      dataincache = 0;
+    } else {
+      hts_log_print(opt, LOG_WARNING,
+                    "entry too large for the cache, not cached: %s%s", url_adr,
+                    url_fil);
+      return;
+    }
   }
 
   /* Fields */
@@ -311,8 +357,6 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
   ZIP_FIELD_STRING(headers, headersSize, "X-Fil", url_fil);     // Original URI filename
   ZIP_FIELD_STRING(headers, headersSize, "X-Save", url_save_suffix);    // Original save filename
 
-  //entryFilenameSize = (int) ( strlen(url_adr) + strlen(url_fil));
-
   /* Filename */
   if (!link_has_authority(url_adr)) {
     strcpybuff(filename, "http://");
@@ -346,9 +390,9 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
                                    */
                                   headers, (uInt) strlen(headers), NULL, 0, NULL,       /* comment */
                                   Z_DEFLATED, Z_DEFAULT_COMPRESSION)) != Z_OK) {
-    int zip_zipOpenNewFileInZip_failed = 0;
-
-    assertf(zip_zipOpenNewFileInZip_failed);
+    cache_zip_write_failed(opt, cache, "opening a cache entry", zErr, HTS_FALSE,
+                           url_adr, url_fil);
+    return;
   }
 
   /* Write data in cache */
@@ -358,9 +402,9 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
         if ((zErr =
              zipWriteInFileInZip((zipFile) cache->zipOutput, r->adr,
                                  (int) r->size)) != Z_OK) {
-          int zip_zipWriteInFileInZip_failed = 0;
-
-          assertf(zip_zipWriteInFileInZip_failed);
+          cache_zip_write_failed(opt, cache, "writing to the cache", zErr,
+                                 HTS_TRUE, url_adr, url_fil);
+          return;
         }
       }
     } else {
@@ -381,9 +425,10 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
               if ((zErr =
                    zipWriteInFileInZip((zipFile) cache->zipOutput, buff,
                                        (int) nl)) != Z_OK) {
-                int zip_zipWriteInFileInZip_failed = 0;
-
-                assertf(zip_zipWriteInFileInZip_failed);
+                cache_zip_write_failed(opt, cache, "writing to the cache", zErr,
+                                       HTS_TRUE, url_adr, url_fil);
+                fclose(fp);
+                return;
               }
             }
           } while(nl > 0);
@@ -397,17 +442,19 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
 
   /* Close */
   if ((zErr = zipCloseFileInZip((zipFile) cache->zipOutput)) != Z_OK) {
-    int zip_zipCloseFileInZip_failed = 0;
-
-    assertf(zip_zipCloseFileInZip_failed);
+    cache_zip_write_failed(opt, cache, "closing a cache entry", zErr, HTS_FALSE,
+                           url_adr, url_fil);
+    return;
   }
 
   /* Flush */
   if ((zErr = zipFlush((zipFile) cache->zipOutput)) != 0) {
-    int zip_zipFlush_failed = 0;
-
-    assertf(zip_zipFlush_failed);
+    cache_zip_write_failed(opt, cache, "flushing the cache", zErr, HTS_FALSE,
+                           url_adr, url_fil);
+    return;
   }
+
+  cache->zipWriteFailures = 0; /* entry stored: reset the failure streak */
 }
 
 #else
@@ -576,15 +623,18 @@ htsblk cache_read_ro(httrackp * opt, cache_back * cache, const char *adr,
   return cache_readex(opt, cache, adr, fil, save, location, NULL, 1);
 }
 
-htsblk cache_read_including_broken(httrackp * opt, cache_back * cache,
-                                   const char *adr, const char *fil) {
-  htsblk r = cache_read(opt, cache, adr, fil, NULL, NULL);
+htsblk cache_read_including_broken(httrackp *opt, cache_back *cache,
+                                   const char *adr, const char *fil,
+                                   char *return_save) {
+  htsblk r = cache_readex(opt, cache, adr, fil, NULL, NULL, return_save, 0);
 
   if (r.statuscode == -1) {
     lien_back *itemback = NULL;
 
     if (back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
       r = itemback->r;
+      if (return_save != NULL)
+        strlcpybuff(return_save, itemback->url_sav, HTS_URLMAXSIZE * 2);
       /* cleanup */
       back_clear_entry(itemback);       /* delete entry content */
       freet(itemback);          /* delete item */
@@ -671,7 +721,6 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
         char BIGSTK headerBuff[8192 + 2];
         int readSizeHeader;
 
-        //int totalHeader = 0;
         int dataincache = 0;
 
         /* For BIG comments */
@@ -722,13 +771,10 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                                    HTS_URLMAXSIZE * 2);
               ZIP_READFIELD_STRING(line, value, "Content-Disposition", r.cdispo,
                                    sizeof(r.cdispo));
-              //ZIP_READFIELD_STRING(line, value, "X-Addr", ..);            // Original address
-              //ZIP_READFIELD_STRING(line, value, "X-Fil", ..);            // Original URI filename
               ZIP_READFIELD_STRING(line, value, "X-Save", previous_save_,
                                    sizeof(previous_save_));
             }
-          } while(offset < readSizeHeader && !lineEof);
-          //totalHeader = offset;
+          } while (offset < readSizeHeader && !lineEof);
 
           /* Previous entry */
           if (previous_save_[0] != '\0') {
@@ -745,6 +791,15 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
             strlcpybuff(return_save, previous_save, HTS_URLMAXSIZE * 2);
           }
 
+          /* A negative X-Size is corrupt; so is one >= INT_MAX when the data
+             is in the zip (the write path asserts int-sized). Headers-only
+             entries legitimately exceed INT_MAX (>2GB body on disk): keep
+             them, or every update would re-fetch the file. */
+          if (r.size < 0 || (dataincache && r.size >= INT_MAX)) {
+            r.statuscode = STATUSCODE_INVALID;
+            strcpybuff(r.msg, "Cache Read Error : Bad Size");
+          }
+
           /* Complete fields */
           r.totalsize = r.size;
           r.adr = NULL;
@@ -771,7 +826,8 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
             }                   // otherwise, the ZIP file is supposed to be consistent with data.
           }
           /* Read data ? */
-          else {                /* ne pas lire uniquement header */
+          else if (r.statuscode !=
+                   STATUSCODE_INVALID) { /* ne pas lire uniquement header */
             int ok = 0;
 
 #if HTS_DIRECTDISK
@@ -900,7 +956,6 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                   r.statuscode = STATUSCODE_INVALID;
                   strcpybuff(r.msg,
                              "Cache Write Error : Unable to Create File");
-                  //printf("%s\n",save);
                 }
               }
 
@@ -935,7 +990,10 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                     strcpybuff(r.msg,
                                "Previous cache file not found (empty filename)");
                   }
-                } else {        /* Read in memory from disk */
+                } else if (r.size >= INT_MAX) { /* too big to read in memory */
+                  r.statuscode = STATUSCODE_INVALID;
+                  strcpybuff(r.msg, "Cache Read Error : Bad Size");
+                } else { /* Read in memory from disk */
                   FILE *const fp = FOPEN(fconv(catbuff, sizeof(catbuff), previous_save), "rb");
 
                   if (fp != NULL) {
@@ -975,7 +1033,6 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                     strcpybuff(r.msg, "Cache Read Error : Read Data");
                   } else
                     *(r.adr + r.size) = '\0';
-                  //printf(">%s status %d\n",back[p].r.contenttype,back[p].r.statuscode);
                 } else {        // erreur
                   r.statuscode = STATUSCODE_INVALID;
                   strcpybuff(r.msg, "Cache Memory Error");
@@ -1154,17 +1211,14 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
         // sécurité
         r.adr = NULL;
         r.out = NULL;
-        ////r.location=NULL;  non, fixée lors des 301 ou 302
         r.fp = NULL;
 
         if ((r.statuscode >= 0) && (r.statuscode <= 999)
             && (r.notmodified >= 0) && (r.notmodified <= 9)) {  // petite vérif intégrité
-          if ((save) && (!header_only)) {       /* ne pas lire uniquement header */
-            //int to_file=0;
+          if ((save) && (!header_only)) { /* ne pas lire uniquement header */
 
             r.adr = NULL;
             r.soc = INVALID_SOCKET;
-            // // r.location=NULL;
 
 #if HTS_DIRECTDISK
             // Court-circuit:
@@ -1173,12 +1227,11 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
               int ok = 0;
 
               r.is_write = 1;   // écrire
-              if (fexist_utf8(fconv(catbuff, sizeof(catbuff), save))) {  // un fichier existe déja
-                //if (fsize_utf8(fconv(save))==r.size) {  // même taille -- NON tant pis (taille mal declaree)
+              if (fexist_utf8(fconv(catbuff, sizeof(catbuff),
+                                    save))) { // un fichier existe déja
                 ok = 1;         // plus rien à faire
                 filenote(&opt->state.strc, save, NULL); // noter comme connu
                 file_notify(opt, adr, fil, save, 0, 0, 0);
-                //}
               }
 
               if ((pos < 0) && (!ok)) { // Pas de donnée en cache et fichier introuvable : erreur!
@@ -1229,7 +1282,6 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
                   r.statuscode = STATUSCODE_INVALID;
                   strcpybuff(r.msg,
                              "Cache Write Error : Unable to Create File");
-                  //printf("%s\n",save);
                 }
               }
 
@@ -1277,14 +1329,13 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
                     strcpybuff(r.msg, "Cache Read Error : Read Data");
                   } else
                     *(r.adr + r.size) = '\0';
-                  //printf(">%s status %d\n",back[p].r.contenttype,back[p].r.statuscode);
                 } else {        // erreur
                   r.statuscode = STATUSCODE_INVALID;
                   strcpybuff(r.msg, "Cache Memory Error");
                 }
               }
             }
-          }                     // si save==null, ne rien charger (juste en tête)
+          } // si save==null, ne rien charger (juste en tête)
         } else {
 #if DEBUGCA
           printf("Cache Read Error : Bad Data");
@@ -1397,6 +1448,86 @@ static int hts_rename(httrackp * opt, const char *a, const char *b) {
   return rename(a, b);
 }
 
+/* Pathname of a file inside the mirror dir (rotating concat buffer). */
+static char *reconcile_path(httrackp *opt, const char *name) {
+  return fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                 StringBuff(opt->path_log), name);
+}
+
+/* Interrupted-run heuristic: prefer the old generation when the new cache
+   stalled below NEW_TINY while the old one grew past OLD_SOLID (historical
+   arbitrary thresholds). */
+#define CACHE_RECONCILE_NEW_TINY 32768
+#define CACHE_RECONCILE_OLD_SOLID 65536
+
+/* Replace the new-generation file by the old one, when the old one exists. */
+static void reconcile_promote(httrackp *opt, const char *oldname,
+                              const char *newname) {
+  if (fexist(reconcile_path(opt, oldname))) {
+    remove(reconcile_path(opt, newname));
+    rename(reconcile_path(opt, oldname), reconcile_path(opt, newname));
+  }
+}
+
+void hts_cache_reconcile(httrackp *opt, hts_cache_reconcile_mode mode) {
+  switch (mode) {
+  case CACHE_RECONCILE_PROMOTE:
+    /* Previous run rotated new.* to old.* then died before writing: promote
+       the old generation back, whichever format it uses. */
+    if (!fexist(reconcile_path(opt, "hts-cache/new.zip")))
+      reconcile_promote(opt, "hts-cache/old.zip", "hts-cache/new.zip");
+    if ((!fexist(reconcile_path(opt, "hts-cache/new.dat")) ||
+         !fexist(reconcile_path(opt, "hts-cache/new.ndx"))) &&
+        fexist(reconcile_path(opt, "hts-cache/old.dat")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.ndx"))) {
+      reconcile_promote(opt, "hts-cache/old.dat", "hts-cache/new.dat");
+      reconcile_promote(opt, "hts-cache/old.ndx", "hts-cache/new.ndx");
+    }
+    break;
+  case CACHE_RECONCILE_INTERRUPTED:
+    /* Aborted run: keep the larger generation when the new cache is
+       suspiciously small next to the old one. The new file must exist: fsize()
+       is -1 for a missing file, which would spuriously pass the "< TINY" test
+       and overwrite a solid old generation that PROMOTE/ROLLBACK should keep.
+     */
+    if (!opt->cache || !fexist(reconcile_path(opt, "hts-in_progress.lock")))
+      break;
+    if (fexist(reconcile_path(opt, "hts-cache/new.zip")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.zip")) &&
+        fsize(reconcile_path(opt, "hts-cache/new.zip")) <
+            CACHE_RECONCILE_NEW_TINY &&
+        fsize(reconcile_path(opt, "hts-cache/old.zip")) >
+            CACHE_RECONCILE_OLD_SOLID &&
+        fsize(reconcile_path(opt, "hts-cache/old.zip")) >
+            fsize(reconcile_path(opt, "hts-cache/new.zip")))
+      reconcile_promote(opt, "hts-cache/old.zip", "hts-cache/new.zip");
+    if (fexist(reconcile_path(opt, "hts-cache/new.dat")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.dat")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.ndx")) &&
+        fsize(reconcile_path(opt, "hts-cache/new.dat")) <
+            CACHE_RECONCILE_NEW_TINY &&
+        fsize(reconcile_path(opt, "hts-cache/old.dat")) >
+            CACHE_RECONCILE_OLD_SOLID &&
+        fsize(reconcile_path(opt, "hts-cache/old.dat")) >
+            fsize(reconcile_path(opt, "hts-cache/new.dat"))) {
+      reconcile_promote(opt, "hts-cache/old.dat", "hts-cache/new.dat");
+      reconcile_promote(opt, "hts-cache/old.ndx", "hts-cache/new.ndx");
+    }
+    break;
+  case CACHE_RECONCILE_ROLLBACK:
+    /* Nothing transferred: restore the previous generation and sidecars. */
+    reconcile_promote(opt, "hts-cache/old.zip", "hts-cache/new.zip");
+    if (fexist(reconcile_path(opt, "hts-cache/old.dat")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.ndx"))) {
+      reconcile_promote(opt, "hts-cache/old.dat", "hts-cache/new.dat");
+      reconcile_promote(opt, "hts-cache/old.ndx", "hts-cache/new.ndx");
+    }
+    reconcile_promote(opt, "hts-cache/old.lst", "hts-cache/new.lst");
+    reconcile_promote(opt, "hts-cache/old.txt", "hts-cache/new.txt");
+    break;
+  }
+}
+
 // renvoyer uniquement en tête, ou NULL si erreur
 // return NULL upon error, and set -1 to r.statuscode
 htsblk *cache_header(httrackp * opt, cache_back * cache, const char *adr,
@@ -1427,25 +1558,10 @@ void cache_init(cache_back * cache, httrackp * opt) {
       mkdir(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache"),
             HTS_PROTECT_FOLDER);
 #endif
-      if ((fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/new.zip")))) {       // il existe déja un cache précédent.. renommer
-        /* Previous cache from the previous cache version */
-#if 0
-        /* No.. reuse with old httrack releases! */
-        if (fexist
-            (fconcat
-             (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
-              "hts-cache/old.dat")))
-          remove(fconcat
-                 (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
-                  "hts-cache/old.dat"));
-        if (fexist
-            (fconcat
-             (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
-              "hts-cache/old.ndx")))
-          remove(fconcat
-                 (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
-                  "hts-cache/old.ndx"));
-#endif
+      if ((fexist(fconcat(
+              OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+              StringBuff(opt->path_log),
+              "hts-cache/new.zip")))) { // a previous cache exists.. rename it
         /* Previous cache version */
         if ((fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/new.dat"))) && (fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/new.ndx")))) {     // il existe déja un cache précédent.. renommer
           rename(fconcat
@@ -1486,7 +1602,13 @@ void cache_init(cache_back * cache, httrackp * opt) {
         } else {
           hts_log_print(opt, LOG_DEBUG, "Cache: successfully renamed");
         }
-      } else if ((fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/new.dat"))) && (fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/new.ndx")))) {        // il existe déja un cache précédent.. renommer
+      } else if ((fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                                 StringBuff(opt->path_log),
+                                 "hts-cache/new.dat"))) &&
+                 (fexist(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                                 StringBuff(opt->path_log),
+                                 "hts-cache/new.ndx")))) { // a previous cache
+                                                           // exists.. rename it
 #if DEBUGCA
         printf("work with former cache\n");
 #endif
@@ -1515,7 +1637,7 @@ void cache_init(cache_back * cache, httrackp * opt) {
                 "hts-cache/new.ndx"), fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
                                               StringBuff(opt->path_log),
                                               "hts-cache/old.ndx"));
-      } else {                  // un des deux (ou les deux) fichiers cache absents: effacer l'autre éventuel
+      } else { // one or both cache files missing: remove the remaining one
 #if DEBUGCA
         printf("new cache\n");
 #endif
@@ -1884,12 +2006,6 @@ void cache_init(cache_back * cache, httrackp * opt) {
                    "hts-cache/new.lst"), "wb");
           strcpybuff(opt->state.strc.path, StringBuff(opt->path_html));
           opt->state.strc.lst = cache->lst;
-          //{
-          //filecreate_params tmp;
-          //strcpybuff(tmp.path,StringBuff(opt->path_html));    // chemin
-          //tmp.lst=cache->lst;                 // fichier lst
-          //filenote("",&tmp);        // initialiser filecreate
-          //}
 
           // supprimer old.txt
           if (fexist
@@ -1978,12 +2094,6 @@ void cache_init(cache_back * cache, httrackp * opt) {
                    "hts-cache/new.lst"), "wb");
           strcpybuff(opt->state.strc.path, StringBuff(opt->path_html));
           opt->state.strc.lst = cache->lst;
-          //{
-          //  filecreate_params tmp;
-          //  strcpybuff(tmp.path,StringBuff(opt->path_html));    // chemin
-          //  tmp.lst=cache->lst;                 // fichier lst
-          //  filenote("",&tmp);        // initialiser filecreate
-          //}
 
           // supprimer old.txt
           if (fexist
@@ -2015,8 +2125,6 @@ void cache_init(cache_back * cache, httrackp * opt) {
                     "statuscode\tstatus ('servermsg')\tMIME\tEtag|Date\tURL\tlocalfile\t(from URL)"
                     LF);
           }
-          // test
-          // cache_writedata(cache->ndx,cache->dat,"//[TEST]//","test1","TEST PIPO",9);
         }                       // cache->ndx!=NULL
       }                         //cache->zipOutput != NULL
 

src/htscache.h

@@ -66,8 +66,11 @@ 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);
-htsblk cache_read_including_broken(httrackp * opt, cache_back * cache,
-                                   const char *adr, const char *fil);
+/* 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_readex(httrackp * opt, cache_back * cache, const char *adr,
                     const char *fil, const char *save, char *location,
                     char *return_save, int readonly);
@@ -75,6 +78,17 @@ 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,

src/htscache_selftest.c

@@ -47,6 +47,8 @@ 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>
 
@@ -316,6 +318,328 @@ 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;
@@ -585,3 +909,494 @@ 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: a pure-legacy old generation is promoted too (was dead when no
+     zip cache existed) */
+  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", SOLID, "promote-dat");
+  failures += reconcile_expect(opt, "hts-cache/new.ndx", TINY, "promote-dat");
+  failures += reconcile_expect(opt, "hts-cache/old.dat", -1, "promote-dat");
+
+  /* PROMOTE: a half-written legacy new pair is replaced by the old pair */
+  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", TINY);
+  hts_cache_reconcile(opt, CACHE_RECONCILE_PROMOTE);
+  failures +=
+      reconcile_expect(opt, "hts-cache/new.dat", SOLID, "promote-dat-partial");
+  failures +=
+      reconcile_expect(opt, "hts-cache/new.ndx", TINY, "promote-dat-partial");
+
+  /* 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 legacy pair follows the same size rule (was dead code) */
+  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", SOLID, "interrupted-dat");
+  failures +=
+      reconcile_expect(opt, "hts-cache/new.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: full legacy generation incl. sidecars (historical behavior) */
+  reconcile_wipe(opt);
+  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);
+  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", SOLID, "rollback-dat");
+  failures += reconcile_expect(opt, "hts-cache/new.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;
+}
+
+/* --- 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

@@ -52,6 +52,19 @@ 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);
+
+/* 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, 31337, 0, -1 };
+  int try_to_listen_to[] = {8080, 3128, 80, 81, 82, 8081, 3129, 0, -1};
   int i = 0;
 
   do {
@@ -175,7 +175,9 @@ HTSEXT_API hts_boolean catch_url(T_SOC soc, char *url, char *method,
       //
       socinput(soc, line, 1000);
       if (strnotempty(line)) {
-        if (sscanf(line, "%s %s %s", method, url, protocol) == 3) {
+        /* widths bound the caller buffers: method[32], url[HTS_URLMAXSIZE*2],
+           protocol[256] */
+        if (sscanf(line, "%31s %2047s %255s", method, url, protocol) == 3) {
           lien_adrfil af;
 
           // méthode en majuscule
@@ -195,7 +197,6 @@ 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);
@@ -205,8 +206,8 @@ 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
-            //strcatbuff(data,"\r\n");
+            // CR/LF final de l'en tête inutile car déja placé via la ligne vide
+            // juste au dessus
             if (blkretour.totalsize > 0) {
               int len = (int) min(blkretour.totalsize, 32000);
               int pos = (int) strlen(data);

src/htscharset.c

@@ -841,71 +841,6 @@ 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

src/htsconfig.h

@@ -54,10 +54,6 @@ 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
@@ -80,10 +76,6 @@ 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
 
@@ -97,27 +89,10 @@ 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

@@ -214,6 +214,9 @@ 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
@@ -232,8 +235,12 @@ struct hash_struct {
   coucal adrfil;
   /* former address+path -> link index (renamed/moved entries) */
   coucal former_adrfil;
-  /* scratch buffers reused across lookups (not reentrant) */
-  int normalized;
+  /* 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;
   char normfil[HTS_URLMAXSIZE * 2];
   char normfil2[HTS_URLMAXSIZE * 2];
   char catbuff[CATBUFF_SIZE];
@@ -356,12 +363,42 @@ 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
@@ -375,10 +412,6 @@ 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. */
 
@@ -396,6 +429,19 @@ 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,
@@ -417,11 +463,6 @@ 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);
@@ -444,4 +485,8 @@ 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

@@ -69,11 +69,15 @@ 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
-   (dllexport on Windows, nothing elsewhere). */
+/* 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. */
 #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

@@ -30,12 +30,14 @@ 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 unsigned int hash, const size_t len);
-*/
+/* static int decode_entity(const uint64_t hash, const size_t len);
+ */
 #include "htsentities.h"
 
 /* hexadecimal conversion */
@@ -50,30 +52,31 @@ static int get_hex_value(char c) {
     return -1;
 }
 
-/* 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)
+/* 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)
 
 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;
-  unsigned int hash;
+  uint64_t hash;
 
   assertf(max != 0);
-  for(i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0,
-        uc = -1, hex = 0, hash = 0 ; src[i] != '\0' ; i++) {
+  for (i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0, uc = -1, hex = 0,
+      hash = HASH_INIT;
+       src[i] != '\0'; i++) {
     /* start of entity */
     if (src[i] == '&') {
       ampStart = i;
       ampStartDest = j;
-      hash = 0;
+      hash = HASH_INIT;
       uc = -1;
     }
     /* inside a potential entity */
@@ -174,14 +177,11 @@ int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t ma
       }
       /* alphanumerical entity */
       else {
-        /* 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')
-             )
-            ) {
+        /* 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'))) {
           /* 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
         }
       }
     }
-    
-    /* copy */
-    if (j + 1 > max) {
+
+    /* reserve one byte for the trailing NUL written after the loop */
+    if (j + 1 >= max) {
       /* overflow */
       return -1;
     }
@@ -300,6 +300,11 @@ 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;
 
@@ -314,8 +319,8 @@ int hts_unescapeUrlSpecial(const char *src, char *dest, const size_t max,
       }
     }
 
-    /* Check for overflow */
-    if (j + 1 > max) {
+    /* reserve one byte for the trailing NUL written after the loop */
+    if (j + 1 >= max) {
       return -1;
     }
 

src/htsentities.sh

@@ -1,75 +1,92 @@
 #!/bin/bash
 #
+# Regenerate htsentities.h from the WHATWG named character references.
 
-src=html40.txt
-url=http://www.w3.org/TR/1998/REC-html40-19980424/html40.txt
+set -euo pipefail
+
+src=entities.json
+url=https://html.spec.whatwg.org/entities.json
 dest=htsentities.h
 
-(
-    cat <<EOF
-/*
-  -- ${dest} --
-  FILE GENERATED BY $0, DO NOT MODIFY
+# 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"
+}
 
-  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.
+if [ ! -f "$src" ]; then
+    curl -fsS "$url" -o "$src"
+fi
 
-  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 $0 script.
-*/
+# Keep ';'-terminated single-codepoint names; the ~93 multi-codepoint refs can't
+# fit decode_entity's single-codepoint return and are skipped (left verbatim).
+pairs=$(jq -r '
+    to_entries
+    | map(select((.key | endswith(";")) and (.value.codepoints | length == 1)))
+    | sort_by(.key)
+    | .[] | "\(.key | ltrimstr("&") | rtrimstr(";"))\t\(.value.codepoints[0])"' "$src")
 
-static int decode_entity(const unsigned int hash, const size_t len) {
+# 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) {
   switch(hash) {
-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 ${code};"
-                echo -e "    }"
-                echo -e "    break;"
-
-                # next
-                read -r A
-            done
-        )
-    cat <<EOF
-  }
+${cases}  }
   /* unknown */
   return -1;
 }
 EOF
-) >${dest}
+
+echo "wrote $dest ($(grep -c '^  case ' "$dest") entities)" >&2

src/htsfilters.c

@@ -76,7 +76,8 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
     }
     if (size)
       sz = *size;
-    if (strjoker(nom, filters[i] + filteroffs, &sz, size_flag)) {       // reconnu
+    /* size unknown (scan time): no size pointer => size tests stay neutral */
+    if (strjoker(nom, filters[i] + filteroffs, size ? &sz : NULL, size_flag)) {
       if (size)
         if (sz != *size)
           sizelimit = sz;
@@ -101,9 +102,8 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
 // 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) {
-  //int err=0;
+HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
+                                LLint *size, int *size_flag) {
   if (strnotempty(joker) == 0) {        // fin de chaine joker
     if (strnotempty(chaine) == 0)       // fin aussi pour la chaine: ok
       return chaine;
@@ -192,7 +192,12 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
           int len = (int) strlen(joker);
 
           while((joker[i] != RIGHT) && (joker[i]) && (i < len)) {
-            if ((joker[i] == '<') || (joker[i] == '>')) {       // *[<10]
+            // '\' 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]
               int lsize = 0;
               int lverdict;
 
@@ -220,7 +225,9 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
                 while(isdigit((unsigned char) joker[i]))
                   i++;
               }
-            } else if (joker[i + 1] == '-') {   // 2 car, ex: *[A-Z]
+            } 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)
               if ((int) (unsigned char) joker[i + 2] >
                   (int) (unsigned char) joker[i]) {
                 int j;
@@ -228,14 +235,9 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
                 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: *[ ]
-              if (joker[i + 2] == '\\' && joker[i + 3] != 0) {  // escaped char, such as *[\[] or *[\]]
-                i++;
-              }
+            } else { // 1 car, ex: *[ ]
               pass[(int) (unsigned char) joker[i]] = 1;
               i++;
             }
@@ -257,7 +259,6 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
       for(i = 0; i < 256; i++)
         pass[i] = 1;            // tout autoriser
       jmp = 1;
-      ////if (joker[2]==LEFT) jmp=3;        // permet de recher *<crochet ouvrant>
     }
 
     {

src/htsftp.c

@@ -54,15 +54,9 @@ 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
 
@@ -128,6 +122,33 @@ 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;
@@ -173,43 +194,14 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
   while(*real_adr == '/')
     real_adr++;                 // sauter /
   if ((adr = jump_identification(real_adr)) != real_adr) {      // user
-    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';
-    }
+    ftp_split_userpass(real_adr, adr, user, sizeof(user), pass, sizeof(pass));
   }
   // 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];
@@ -233,7 +225,6 @@ 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;
     }
   }
@@ -267,7 +258,6 @@ 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;
     }
@@ -280,20 +270,17 @@ 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
@@ -335,64 +322,22 @@ 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));
-            // back->status=STATUS_FTP_READY;    // fini
+            snprintf(back->r.msg, sizeof(back->r.msg), "Bad password: %s",
+                     linejmp(line));
             back->r.statuscode = STATUSCODE_INVALID;
           }
         } else {
-          snprintf(back->r.msg, sizeof(back->r.msg), "Bad user name: %s", linejmp(line));
-          // back->status=STATUS_FTP_READY;    // fini
+          snprintf(back->r.msg, sizeof(back->r.msg), "Bad user name: %s",
+                   linejmp(line));
           back->r.statuscode = STATUSCODE_INVALID;
         }
       } else {
-        snprintf(back->r.msg, sizeof(back->r.msg), "Connection refused: %s", linejmp(line));
-        // back->status=STATUS_FTP_READY;    // fini
+        snprintf(back->r.msg, sizeof(back->r.msg), "Connection refused: %s",
+                 linejmp(line));
         back->r.statuscode = STATUSCODE_INVALID;
       }
 
@@ -459,8 +404,8 @@ 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));
-            // back->status=STATUS_FTP_READY;    // fini
+            snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s",
+                     linejmp(line));
             back->r.statuscode = STATUSCODE_INVALID;
           }                     // sinon on est prêts
         } else {
@@ -491,13 +436,13 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
                 }
               }
             } else {
-              snprintf(back->r.msg, sizeof(back->r.msg), "EPSV incorrect: %s", linejmp(line));
-              // back->status=STATUS_FTP_READY;    // fini
+              snprintf(back->r.msg, sizeof(back->r.msg), "EPSV incorrect: %s",
+                       linejmp(line));
               back->r.statuscode = STATUSCODE_INVALID;
             }
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "PASV/EPSV error: %s", linejmp(line));
-            // back->status=STATUS_FTP_READY;    // fini
+            snprintf(back->r.msg, sizeof(back->r.msg), "PASV/EPSV error: %s",
+                     linejmp(line));
             back->r.statuscode = STATUSCODE_INVALID;
           }                     // sinon on est prêts
         }
@@ -603,9 +548,8 @@ 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));
-                  // back->status=STATUS_FTP_READY;    // fini
+                  snprintf(back->r.msg, sizeof(back->r.msg),
+                           "RETR command error: %s", linejmp(line));
                   back->r.statuscode = STATUSCODE_INVALID;
                 }               // sinon on est prêts
               } else {
@@ -616,23 +560,20 @@ 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));
-          // back->status=STATUS_FTP_READY;    // fini
+          snprintf(back->r.msg, sizeof(back->r.msg), "PASV incorrect: %s",
+                   linejmp(line));
           back->r.statuscode = STATUSCODE_INVALID;
         }                       // sinon on est prêts
 #else
@@ -653,17 +594,16 @@ 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));
-              // back->status=STATUS_FTP_READY;    // fini
+              snprintf(back->r.msg, sizeof(back->r.msg),
+                       "RETR command error: %s", linejmp(line));
               back->r.statuscode = STATUSCODE_INVALID;
             }
           } else {
-            snprintf(back->r.msg, sizeof(back->r.msg), "PORT command error: %s", linejmp(line));
-            // back->status=STATUS_FTP_READY;    // fini
+            snprintf(back->r.msg, sizeof(back->r.msg), "PORT command error: %s",
+                     linejmp(line));
             back->r.statuscode = STATUSCODE_INVALID;
           }
 #ifdef _WIN32
@@ -673,7 +613,6 @@ 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
@@ -697,21 +636,18 @@ 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);
-                // back->status=STATUS_FTP_READY;    // fini
+                snprintf(back->r.msg, sizeof(back->r.msg), "Time out (%d)",
+                         timeout);
                 back->r.statuscode = STATUSCODE_INVALID;
                 len = 0;        // fin
                 break;
@@ -733,17 +669,14 @@ 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
-                  // back->status=STATUS_FTP_READY;    // fini
+                } else { // Erreur ou terminé
                   back->r.statuscode = 0;
                   if (back->r.totalsize > 0
                       && back->r.size != back->r.totalsize) {
@@ -752,7 +685,6 @@ 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) {
@@ -761,7 +693,6 @@ 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
@@ -777,16 +708,14 @@ 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));
-                // back->status=STATUS_FTP_READY;    // fini
+                snprintf(back->r.msg, sizeof(back->r.msg), "RETR incorrect: %s",
+                         linejmp(line));
                 back->r.statuscode = STATUSCODE_INVALID;
               }
             } else {
               strcpybuff(back->r.msg, "FTP read error");
-              // back->status=STATUS_FTP_READY;    // fini
               back->r.statuscode = STATUSCODE_INVALID;
             }
           }
@@ -812,7 +741,6 @@ int run_launch_ftp(FTPDownloadStruct * pStruct) {
     back->r.statuscode = HTTP_OK;
     strcpybuff(back->r.msg, "OK");
   }
-  // back->status=STATUS_FTP_READY;    // fini
   return 0;
 }
 
@@ -979,13 +907,11 @@ 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))
-        data[i++] = b;
+      if ((b != 10) && (b != 13) && (i < (int) sizeof(data) - 1))
+        data[i++] = b; // truncate hostile over-long reply lines
       break;
     default:
       if (ptrline)
@@ -1108,7 +1034,6 @@ 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

@@ -70,6 +70,11 @@ 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 "3.49-9"
-#define HTTRACK_VERSIONID "3.49.9"
+#define HTTRACK_VERSION "3.49-11"
+#define HTTRACK_VERSIONID "3.49.11"
 #define HTTRACK_AFF_VERSION "3.x"
 #define HTTRACK_LIB_VERSION "2.0"
 
@@ -229,6 +229,10 @@ 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->normalized  ? jump_normalized_const(adr)
-                        : jump_identification_const(adr) )
-    : NULL;
+  const char *const adr_norm =
+      adr != NULL ? (hash->norm_host ? jump_normalized_const(adr)
+                                     : jump_identification_const(adr))
+                  : NULL;
 
   // copy address
   assertf(adr_norm != NULL);
@@ -117,10 +117,18 @@ static coucal_hashkeys key_adrfil_hashes_generic(void *arg,
 
   // copy link
   assertf(fil != NULL);
-  if (hash->normalized) {
-    fil_normalized(fil, &hash->normfil[strlen(hash->normfil)]);
-  } else {
-    strcpy(&hash->normfil[strlen(hash->normfil)], fil);
+  {
+    /* 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);
+    }
   }
 
   // hash
@@ -132,8 +140,7 @@ 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;
-  const int normalized = hash->normalized;
+  hash_struct *const hash = (hash_struct *) arg;
   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;
@@ -150,10 +157,10 @@ static int key_adrfil_equals_generic(void *arg,
   assertf(b_fil != NULL);
 
   // skip scheme and authentication to the domain (possibly without www.)
-  ja = normalized
-    ? jump_normalized_const(a_adr) : jump_identification_const(a_adr);
-  jb = normalized
-    ? jump_normalized_const(b_adr) : jump_identification_const(b_adr);
+  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);
   assertf(ja != NULL);
   assertf(jb != NULL);
   if (strcasecmp(ja, jb) != 0) {
@@ -161,12 +168,23 @@ static int key_adrfil_equals_generic(void *arg,
   }
 
   // now compare pathes
-  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;
+  {
+    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;
+    }
   }
 }
 
@@ -222,11 +240,17 @@ 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, int normalized) {
+void hash_init(httrackp *opt, hash_struct *hash, hts_boolean normalized) {
   hash->sav = coucal_new(0);
   hash->adrfil = coucal_new(0);
   hash->former_adrfil = coucal_new(0);
-  hash->normalized = normalized;
+  /* 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;
 
   hts_set_hash_handler(hash->sav, opt);
   hts_set_hash_handler(hash->adrfil, opt);
@@ -282,6 +306,26 @@ 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

@@ -51,8 +51,12 @@ typedef enum hash_struct_type {
 } hash_struct_type;
 
 // tables de hachage
-void hash_init(httrackp *opt, hash_struct *hash, int normalized);
+void hash_init(httrackp *opt, hash_struct *hash, hts_boolean 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

@@ -152,16 +152,6 @@ 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;
 
@@ -227,8 +217,6 @@ 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) :");
@@ -349,8 +337,6 @@ void help_wizard(httrackp * opt) {
       }
       hts_main(argc, argv);
     }
-    //} else {
-    //  help("httrack",1);
   }
 
   /* Free buffers */
@@ -455,23 +441,6 @@ 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) {
@@ -521,6 +490,7 @@ 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("");
@@ -563,6 +533,7 @@ 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)");
@@ -571,6 +542,7 @@ 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
     ("  u  check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)");
   infomsg
@@ -587,6 +559,9 @@ 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 "
@@ -646,9 +621,7 @@ 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(" #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(" #test  list engine self-tests (run one with -#test=NAME [args])");
   infomsg(" #C  cache list (-#C '*.com/spider*.gif'");
   infomsg(" #R  cache repair (damaged cache)");
   infomsg(" #d  debug parser");
@@ -804,7 +777,4 @@ 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

@@ -45,7 +45,6 @@ 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

@@ -142,8 +142,6 @@ 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;
 
@@ -178,8 +176,6 @@ 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;
 
@@ -275,8 +271,6 @@ 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];
@@ -286,7 +280,6 @@ 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" */
@@ -300,11 +293,9 @@ 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);
     }
   }
 
@@ -330,7 +321,6 @@ 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) {
@@ -398,8 +388,6 @@ 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) >=
@@ -416,8 +404,6 @@ 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

@@ -63,6 +63,9 @@ 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;
 
@@ -172,15 +175,14 @@ 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) {
-        //fprintf(stderr, "Cannot open input file.\n");
+      if ((fpout = FOPEN(fconv(catbuff, sizeof(catbuff), file), "r+b")) ==
+          NULL) {
         sprintf(str->err_msg, "Unable to open file %s", file);
         return 0;               // une erreur..
       }
 #if JAVADEBUG
       printf("fread\n");
 #endif
-      //if (fread(&header,1,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 ")",
@@ -204,7 +206,16 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
         return 0;
       }
 
-      tab = (RESP_STRUCT *) calloc(header.count, sizeof(RESP_STRUCT));
+      /* A constant-pool entry is >= 1 byte on disk; reject a count exceeding
+         the file size (hostile .class ~68 MB alloc DoS). */
+      if (!hts_count_fits(header.count, (LLint) fsize(file))) {
+        fclose(fpout);
+        sprintf(str->err_msg,
+                "Invalid constant pool count %u (file len " LLintP ")",
+                (unsigned) header.count, (LLint) fsize(file));
+        return 0;
+      }
+      tab = (RESP_STRUCT *) calloct(header.count, sizeof(RESP_STRUCT));
       if (!tab) {
         sprintf(str->err_msg, "Unable to alloc %d bytes",
                 (int) sizeof(RESP_STRUCT));
@@ -230,7 +241,7 @@ 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");
-            free(tab);
+            freet(tab);
             if (fpout) {
               fclose(fpout);
               fpout = NULL;
@@ -245,12 +256,10 @@ 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);
 
@@ -288,7 +297,7 @@ static int hts_parse_java(t_hts_callbackarg * carg, httrackp * opt,
 #if JAVADEBUG
       printf("end\n");
 #endif
-      free(tab);
+      freet(tab);
       if (fpout) {
         fclose(fpout);
         fpout = NULL;
@@ -395,11 +404,9 @@ 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);
 
@@ -407,17 +414,13 @@ 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--;
@@ -433,7 +436,6 @@ 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;
@@ -496,7 +498,6 @@ 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

@@ -33,15 +33,19 @@ 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 {
-  unsigned long int magic;
-  unsigned short int minor;
-  unsigned short int major;
-  unsigned short int count;
+  uint32_t magic;
+  uint16_t minor;
+  uint16_t major;
+  uint16_t count;
 };
 
 #ifndef HTS_DEF_FWSTRUCT_RESP_STRUCT

src/htslib.c

@@ -563,58 +563,62 @@ const char *hts_mime[][2] = {
   {"", ""}
 };
 
+/* Modern web formats (post-2010), kept in their own table: appending to the
+   legacy hts_mime[] above makes clang-format reflow its whole initializer.
+   Scanned after hts_mime[], so it never shadows a legacy mapping. */
+static const char *hts_mime_modern[][2] = {
+    {"image/webp", "webp"},
+    {"image/avif", "avif"},
+    {"image/heic", "heic"},
+    {"font/woff", "woff"},
+    {"font/woff2", "woff2"},
+    {"font/ttf", "ttf"},
+    {"font/otf", "otf"},
+    {"application/json", "json"},
+    {"application/ld+json", "jsonld"},
+    {"application/manifest+json", "webmanifest"},
+    {"application/wasm", "wasm"},
+    {"text/javascript", "js"},
+    {"text/javascript", "mjs"},
+    {"text/markdown", "md"},
+    {"video/mp4", "mp4"},
+    {"video/webm", "webm"},
+    {"video/ogg", "ogv"},
+    {"video/mp2t", "ts"},
+    {"audio/mp4", "m4a"},
+    {"audio/aac", "aac"},
+    {"audio/ogg", "oga"},
+    {"audio/opus", "opus"},
+    {"audio/flac", "flac"},
+    {"audio/webm", "weba"},
+    {"application/x-7z-compressed", "7z"},
+    {"application/x-rar-compressed", "rar"},
+    {"application/zstd", "zst"},
+    {"", ""}};
+
 // Reserved (RFC2396)
 #define CIS(c,ch) ( ((unsigned char)(c)) == (ch) )
-#define CHAR_RESERVED(c)  ( CIS(c,';') \
-                         || CIS(c,'/') \
-                         || CIS(c,'?') \
-                         || CIS(c,':') \
-                         || CIS(c,'@') \
-                         || CIS(c,'&') \
-                         || CIS(c,'=') \
-                         || CIS(c,'+') \
-                         || CIS(c,'$') \
-                         || CIS(c,',') )
-//#define CHAR_RESERVED(c)  ( strchr(";/?:@&=+$,",(unsigned char)(c)) != 0 )
+#define CHAR_RESERVED(c)                                                       \
+  (CIS(c, ';') || CIS(c, '/') || CIS(c, '?') || CIS(c, ':') || CIS(c, '@') ||  \
+   CIS(c, '&') || CIS(c, '=') || CIS(c, '+') || CIS(c, '$') || CIS(c, ','))
 // Delimiters (RFC2396)
-#define CHAR_DELIM(c)     ( CIS(c,'<') \
-                         || CIS(c,'>') \
-                         || CIS(c,'#') \
-                         || CIS(c,'%') \
-                         || CIS(c,'\"') )
-//#define CHAR_DELIM(c)     ( strchr("<>#%\"",(unsigned char)(c)) != 0 )
+#define CHAR_DELIM(c)                                                          \
+  (CIS(c, '<') || CIS(c, '>') || CIS(c, '#') || CIS(c, '%') || CIS(c, '\"'))
 // Unwise (RFC2396)
-#define CHAR_UNWISE(c)    ( CIS(c,'{') \
-                         || CIS(c,'}') \
-                         || CIS(c,'|') \
-                         || CIS(c,'\\') \
-                         || CIS(c,'^') \
-                         || CIS(c,'[') \
-                         || CIS(c,']') \
-                         || CIS(c,'`') )
-//#define CHAR_UNWISE(c)    ( strchr("{}|\\^[]`",(unsigned char)(c)) != 0 )
+#define CHAR_UNWISE(c)                                                         \
+  (CIS(c, '{') || CIS(c, '}') || CIS(c, '|') || CIS(c, '\\') || CIS(c, '^') || \
+   CIS(c, '[') || CIS(c, ']') || CIS(c, '`'))
 // Special (escape chars) (RFC2396 + >127 )
 #define CHAR_LOW(c)       ( ((unsigned char)(c) <= 31) )
 #define CHAR_HIG(c)       ( ((unsigned char)(c) >= 127) )
 #define CHAR_SPECIAL(c)   ( CHAR_LOW(c) || CHAR_HIG(c) )
 // We try to avoid them and encode them instead
-#define CHAR_XXAVOID(c)   ( CIS(c,' ') \
-                         || CIS(c,'*') \
-                         || CIS(c,'\'') \
-                         || CIS(c,'\"') \
-                         || CIS(c,'&') \
-                         || CIS(c,'!') )
-//#define CHAR_XXAVOID(c)   ( strchr(" *'\"!",(unsigned char)(c)) != 0 )
-#define CHAR_MARK(c)      ( CIS(c,'-') \
-                         || CIS(c,'_') \
-                         || CIS(c,'.') \
-                         || CIS(c,'!') \
-                         || CIS(c,'~') \
-                         || CIS(c,'*') \
-                         || CIS(c,'\'') \
-                         || CIS(c,'(') \
-                         || CIS(c,')') )
-//#define CHAR_MARK(c)      ( strchr("-_.!~*'()",(unsigned char)(c)) != 0 )
+#define CHAR_XXAVOID(c)                                                        \
+  (CIS(c, ' ') || CIS(c, '*') || CIS(c, '\'') || CIS(c, '\"') ||               \
+   CIS(c, '&') || CIS(c, '!'))
+#define CHAR_MARK(c)                                                           \
+  (CIS(c, '-') || CIS(c, '_') || CIS(c, '.') || CIS(c, '!') || CIS(c, '~') ||  \
+   CIS(c, '*') || CIS(c, '\'') || CIS(c, '(') || CIS(c, ')'))
 
 // conversion éventuelle / vers antislash
 #ifdef _WIN32
@@ -808,15 +812,12 @@ int http_proxy_tunnel(httrackp *opt, htsblk *retour, const char *adr,
 // treat: traiter header?
 // waitconnect: attendre le connect()
 // note: dans retour, on met les params du proxy
-T_SOC http_xfopen(httrackp * opt, int mode, int treat, int waitconnect,
-                  const char *xsend, const char *adr, const char *fil, htsblk * retour) {
-  //htsblk retour;
-  //int bufl=TAILLE_BUFFER;    // 8Ko de buffer
+T_SOC http_xfopen(httrackp *opt, int mode, int treat, int waitconnect,
+                  const char *xsend, const char *adr, const char *fil,
+                  htsblk *retour) {
   T_SOC soc = INVALID_SOCKET;
   char BIGSTK tempo_fil[HTS_URLMAXSIZE * 2];
 
-  //char *p,*q;
-
   // retour prédéfini: erreur
   if (retour) {
     retour->adr = NULL;
@@ -901,7 +902,6 @@ T_SOC http_xfopen(httrackp * opt, int mode, int treat, int waitconnect,
         strcpybuff(retour->msg, "Unable to open local file");
       else {
         // Note: On passe par un FILE* (plus propre)
-        //soc=open(fil,O_RDONLY,0);    // en lecture seule!
         retour->fp = FOPEN(fconv(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), 
           unescape_http(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), fil)), "rb");      // ouvrir
         if (retour->fp == NULL)
@@ -978,17 +978,10 @@ T_SOC http_xfopen(httrackp * opt, int mode, int treat, int waitconnect,
 
         } while(strnotempty(rcvd));
 
-        //rcvsize=-1;    // forCER CHARGEMENT INCONNU
-
-        //if (retour)
-        //  retour->totalsize=rcvsize;
-
-      } else {                  // si GET, on recevra l'en tête APRES
-        //rcvsize=-1;    // on ne connait pas la taille de l'en-tête
+      } else { // si GET, on recevra l'en tête APRES
         if (retour)
           retour->totalsize = -1;
       }
-
     }
 
   }
@@ -1085,19 +1078,12 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
   char BIGSTK buffer_head_request[16384];
   buff_struct bstr = { buffer_head_request, sizeof(buffer_head_request), 0 };
 
-  //int use_11=0;     // HTTP 1.1 utilisé
   int direct_url = 0;           // ne pas analyser l'url (exemple: ftp://)
   const char *search_tag = NULL;
 
   // Initialize buffer
   buffer_head_request[0] = '\0';
 
-  // header Date
-  //strcatbuff(buff,"Date: ");
-  //time_gmt_rfc822(buff);    // obtenir l'heure au format rfc822
-  //sendc("\n");
-  //strcatbuff(buff,buff);
-
   // possibilité non documentée: >post: et >postfile:
   // si présence d'un tag >post: alors executer un POST
   // exemple: http://www.example.com/test.cgi?foo>post:posteddata=10&foo=5
@@ -1116,7 +1102,8 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
           char BIGSTK protocol[256], url[HTS_URLMAXSIZE * 2], method[256];
 
           linput(fp, line, 1000);
-          if (sscanf(line, "%s %s %s", method, url, protocol) == 3) {
+          /* widths bound method[256], url[HTS_URLMAXSIZE*2], protocol[256] */
+          if (sscanf(line, "%255s %2047s %255s", method, url, protocol) == 3) {
             size_t ret;
             // selon que l'on a ou pas un proxy
             if (retour->req.proxy.active) {
@@ -1190,11 +1177,9 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
     }
 
     // protocole
-    if (!retour->req.http11) {  // forcer HTTP/1.0
-      //use_11=0;
+    if (!retour->req.http11) { // forcer HTTP/1.0
       print_buffer(&bstr, " HTTP/1.0\x0d\x0a");
-    } else {                    // Requète 1.1
-      //use_11=1;
+    } else { // Requète 1.1
       print_buffer(&bstr, " HTTP/1.1\x0d\x0a");
     }
 
@@ -1293,16 +1278,12 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
 
       // Compression accepted ?
       if (retour->req.http11) {
+        hts_boolean compressible = HTS_FALSE;
 #if HTS_USEZLIB
-        if ((!retour->req.range_used)
-            && (!retour->req.nocompression))
-          print_buffer(&bstr, "Accept-Encoding: " "gzip" /* gzip if the preffered encoding */
-                     ", " "identity;q=0.9" H_CRLF);
-        else
-          print_buffer(&bstr, "Accept-Encoding: identity" H_CRLF);       /* no compression */
-#else
-        print_buffer(&bstr, "Accept-Encoding: identity" H_CRLF); /* no compression */
+        compressible = (!retour->req.range_used && !retour->req.nocompression);
 #endif
+        print_buffer(&bstr, "Accept-Encoding: %s" H_CRLF,
+                     hts_acceptencoding(compressible));
       }
 
       /* Authentification */
@@ -1334,9 +1315,7 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
           print_buffer(&bstr, "Authorization: Basic %s"H_CRLF, autorisation);
         }
       }
-
     }
-    //strcatbuff(buff,"Accept-Charset: iso-8859-1,*,utf-8\n");
 
     // Custom header(s)
     if (strnotempty(retour->req.headers)) {
@@ -1490,14 +1469,11 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
         a += strlen("filename=");
         while(is_space(*a))
           a++;
-        //a=strchr(a,'"');
         if (a) {
           char *c = NULL;
 
-          //a++;      /* jump " */
           while((c = strchr(a, '/')))   /* skip all / (see RFC2616) */
             a = c + 1;
-          //b=strchr(a+1,'"');
           b = a + strlen(a) - 1;
           while(is_space(*b))
             b--;
@@ -1514,16 +1490,14 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
   } else if ((p = strfield(rcvd, "Last-Modified:")) != 0) {
     while(is_realspace(*(rcvd + p)))
       p++;                      // sauter espaces
-    if ((int) strlen(rcvd + p) < 64) {  // pas trop long?
-      //struct tm* tm_time=convert_time_rfc822(rcvd+p);
+    if ((int) strlen(rcvd + p) < 64) { // pas trop long?
       strcpybuff(retour->lastmodified, rcvd + p);
     }
   } else if ((p = strfield(rcvd, "Date:")) != 0) {
     if (strnotempty(retour->lastmodified) == 0) {       /* pas encore de last-modified */
       while(is_realspace(*(rcvd + p)))
         p++;                    // sauter espaces
-      if ((int) strlen(rcvd + p) < 64) {        // pas trop long?
-        //struct tm* tm_time=convert_time_rfc822(rcvd+p);
+      if ((int) strlen(rcvd + p) < 64) { // pas trop long?
         strcpybuff(retour->lastmodified, rcvd + p);
       }
     }
@@ -1536,14 +1510,11 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
       else                      // erreur.. ignorer
         retour->etag[0] = '\0';
     }
-  }
-  // else if ((p=strfield(rcvd,"Transfer-Encoding: chunked"))!=0) {  // chunk!
-  else if ((p = strfield(rcvd, "Transfer-Encoding:")) != 0) {   // chunk!
+  } else if ((p = strfield(rcvd, "Transfer-Encoding:")) != 0) { // chunk!
     while(is_realspace(*(rcvd + p)))
       p++;                      // sauter espaces
     if (strfield(rcvd + p, "chunked")) {
-      retour->is_chunk = 1;     // chunked
-      //retour->http11=2;     // chunked
+      retour->is_chunk = 1; // chunked
 #if HDEBUG
       printf("ok, Transfer-Encoding: détecté\n");
 #endif
@@ -1720,7 +1691,8 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
           retour->location[0] = '\0';
       }
     }
-  } else if (((p = strfield(rcvd, "Set-Cookie:")) != 0) && (cookie)) {  // ohh un cookie
+  } else if (((p = strfield(rcvd, "Set-Cookie:")) != 0) &&
+             (cookie)) {        // ohh un cookie
     char *a = rcvd + p;         // pointeur
     char domain[256];           // domaine cookie (.netscape.com)
     char path[256];             // chemin (/)
@@ -1764,10 +1736,8 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
             a++;                // sauter espaces
           value_st = a;
           while((*a != ';') && (*a))
-            a++;                // prochain ;
-          //while( ((*a!='"') || (*(a-1)=='\\')) && (*a)) a++;    // prochain " (et pas \")
+            a++; // prochain ;
           value_end = a;
-          //if (*a==';') {  // finit par un ;
           // vérifier débordements
           if ((((int) (token_end - token_st)) < 200)
               && (((int) (value_end - value_st)) < 8000)
@@ -1918,6 +1888,10 @@ HTSEXT_API const char *infostatuscode_const(int statuscode) {
     return "Requested Range Not Satisfiable";
   case 417:
     return "Expectation Failed";
+  case 429:
+    return "Too Many Requests";
+  case 451:
+    return "Unavailable For Legal Reasons";
   case 500:
     return "Internal Server Error";
   case 501:
@@ -2105,8 +2079,6 @@ LLint http_xfread1(htsblk * r, int bufl) {
             nl = READ_ERROR;
           }
         }
-        //if ((nl < 0) || ((r->totalsize>0) && (r->size >= r->totalsize)))
-        //  nl=-1;  // break
 
         // libérer bloc tempo
         freet(buff);
@@ -2194,9 +2166,6 @@ htsblk http_test(httrackp * opt, const char *adr, const char *fil, char *loc) {
   T_SOC soc;
   htsblk retour;
 
-  //int rcvsize=-1;
-  //char* rcv=NULL;    // adresse de retour
-  //int bufl=TAILLE_BUFFER;    // 8Ko de buffer
   TStamp tl;
   int timeout = 30;             // timeout pour un check (arbitraire) // **
 
@@ -2205,11 +2174,8 @@ htsblk http_test(httrackp * opt, const char *adr, const char *fil, char *loc) {
 
   loc[0] = '\0';
   hts_init_htsblk(&retour);
-  //memset(&retour, 0, sizeof(htsblk));    // effacer
   retour.location = loc;        // si non nul, contiendra l'adresse véritable en cas de moved xx
 
-  //soc=http_fopen(adr,fil,&retour,NULL);  // ouvrir, + header
-
   // on ouvre en head, et on traite l'en tête
   soc = http_xfopen(opt, 1, 0, 1, NULL, adr, fil, &retour);     // ouvrir HEAD, + envoi header
 
@@ -2585,7 +2551,6 @@ int ident_url_absolute(const char *url, lien_adrfil *adrfil) {
 
     // chemin www... trop long!!
     if ((((int) (q - p))) > HTS_URLMAXSIZE) {
-      //strcpybuff(retour.msg,"Path too long");
       return -1;                // erreur
     }
     // recopier adrfil->adresse www..
@@ -2771,7 +2736,6 @@ void deletesoc_r(htsblk * r) {
 #if HTS_USEOPENSSL
   if (r->ssl_con) {
     SSL_shutdown(r->ssl_con);
-    // SSL_CTX_set_quiet_shutdown(r->ssl_con->ctx, 1);
     SSL_free(r->ssl_con);
     r->ssl_con = NULL;
   }
@@ -3160,7 +3124,6 @@ int finput(T_SOC fd, char *s, int max) {
   int j = 0;
 
   do {
-    //c=fgetc(fp);
     if (read((int) fd, &c, 1) <= 0) {
       c = 0;
     }
@@ -3176,7 +3139,7 @@ int finput(T_SOC fd, char *s, int max) {
         break;
       }
     }
-  } while((c != 0) && (j < max - 1));
+  } while ((c != 0) && (j < max - 1));
   s[j] = '\0';
   return j;
 }
@@ -3610,7 +3573,10 @@ static int sortNormFnc(const void *a_, const void *b_) {
   return strcmp(*a + 1, *b + 1);
 }
 
-HTSEXT_API char *fil_normalized(const char *source, char *dest) {
+/* Path normalizer core: optionally collapse redundant '//' (DO_SLASH) and/or
+   sort query arguments (DO_QUERY) so equivalent URLs dedupe. */
+static char *fil_normalized_ex(const char *source, char *dest, int do_slash,
+                               int do_query) {
   char lastc = 0;
   int gotquery = 0;
   int ampargs = 0;
@@ -3620,8 +3586,8 @@ HTSEXT_API char *fil_normalized(const char *source, char *dest) {
   for(i = j = 0; source[i] != '\0'; i++) {
     if (!gotquery && source[i] == '?')
       gotquery = ampargs = 1;
-    if ((!gotquery && lastc == '/' && source[i] == '/') // foo//bar -> foo/bar
-      ) {
+    if (do_slash && !gotquery && lastc == '/' && source[i] == '/') {
+      // foo//bar -> foo/bar
     } else {
       if (gotquery && source[i] == '&') {
         ampargs++;
@@ -3633,7 +3599,7 @@ HTSEXT_API char *fil_normalized(const char *source, char *dest) {
   dest[j++] = '\0';
 
   /* Sort arguments (&foo=1&bar=2 == &bar=2&foo=1) */
-  if (ampargs > 1) {
+  if (do_query && ampargs > 1) {
     char **amps = malloct(ampargs * sizeof(char *));
     char *copyBuff = NULL;
     size_t qLen = 0;
@@ -3681,6 +3647,153 @@ HTSEXT_API char *fil_normalized(const char *source, char *dest) {
   return dest;
 }
 
+HTSEXT_API char *fil_normalized(const char *source, char *dest) {
+  return fil_normalized_ex(source, dest, 1, 1);
+}
+
+/* Is query key ARG[0..keylen) in the comma-separated STRIP list? "*" = all;
+   case-sensitive, space-trimmed tokens. */
+static int hts_query_key_stripped(const char *arg, size_t keylen,
+                                  const char *strip) {
+  const char *p = strip;
+
+  while (*p != '\0') {
+    const char *start = p;
+    size_t toklen;
+
+    while (*p != '\0' && *p != ',')
+      p++;
+    toklen = (size_t) (p - start);
+    while (toklen > 0 && *start == ' ') {
+      start++;
+      toklen--;
+    }
+    while (toklen > 0 && start[toklen - 1] == ' ')
+      toklen--;
+    if (toklen == 1 && start[0] == '*')
+      return 1;
+    if (toklen == keylen && strncmp(start, arg, keylen) == 0)
+      return 1;
+    if (*p == ',')
+      p++;
+  }
+  return 0;
+}
+
+/* see htscore.h */
+char *fil_normalized_filtered_ex(const char *source, char *dest,
+                                 const char *strip, int do_slash,
+                                 int do_query) {
+  const char *query;
+  char BIGSTK tmp[HTS_URLMAXSIZE * 2];
+  htsbuff cb;
+  int wrote = 0;
+
+  /* No strip list, or no query: plain normalization. */
+  if (strip == NULL || *strip == '\0' ||
+      (query = strchr(source, '?')) == NULL) {
+    return fil_normalized_ex(source, dest, do_slash, do_query);
+  }
+
+  /* Copy the path, re-emit kept query args, let fil_normalized() sort. Walk
+     every field incl. empty/trailing ("a&","?&&") so the result is a fixpoint
+     (the read re-normalizes it; a dropped empty arg would miss dedup). */
+  cb = htsbuff_ptr(tmp, sizeof(tmp));
+  htsbuff_catn(&cb, source, (size_t) (query - source));
+  for (query++;;) {
+    const char *const arg = query;
+    const char *eq = NULL;
+    size_t keylen, arglen;
+
+    while (*query != '\0' && *query != '&') {
+      if (eq == NULL && *query == '=')
+        eq = query;
+      query++;
+    }
+    arglen = (size_t) (query - arg);
+    keylen = eq != NULL ? (size_t) (eq - arg) : arglen;
+    if (!hts_query_key_stripped(arg, keylen, strip)) {
+      htsbuff_catc(&cb, wrote ? '&' : '?');
+      htsbuff_catn(&cb, arg, arglen);
+      wrote = 1;
+    }
+    if (*query == '\0')
+      break;
+    query++;
+  }
+  return fil_normalized_ex(tmp, dest, do_slash, do_query);
+}
+
+/* see htscore.h */
+char *fil_normalized_filtered(const char *source, char *dest,
+                              const char *strip) {
+  return fil_normalized_filtered_ex(source, dest, strip, 1, 1);
+}
+
+/* see htscore.h */
+const char *hts_query_strip_keys(const char *rules, const char *adr,
+                                 const char *fil, char *dest, size_t destsize) {
+  const char *p, *q;
+  const char *result = NULL;
+  char BIGSTK url[HTS_URLMAXSIZE * 2];
+
+  if (rules == NULL || *rules == '\0' || destsize == 0)
+    return NULL;
+
+  /* Match string = normalized host/path, query removed. jump_normalized_const
+     collapses www+scheme/auth so read and write (double-normalized) agree;
+     query excluded keeps the decision on host/path only. */
+  url[0] = '\0';
+  strcatbuff(url, jump_normalized_const(adr));
+  if (fil[0] != '/')
+    strcatbuff(url, "/");
+  q = strchr(fil, '?');
+  if (q != NULL)
+    strncatbuff(url, fil, (int) (q - fil));
+  else
+    strcatbuff(url, fil);
+
+  /* Walk the '\n' entries; last match wins (like the +/- filter eval). Each is
+     "pattern=keys"; no '=' is the bare form, pattern "*". */
+  for (p = rules; *p != '\0';) {
+    const char *const line = p;
+    const char *eol, *eq, *keys;
+    char BIGSTK pat[HTS_URLMAXSIZE * 2];
+
+    while (*p != '\0' && *p != '\n')
+      p++;
+    eol = p;
+    if (*p == '\n')
+      p++;
+    if (eol == line)
+      continue;
+    eq = memchr(line, '=', (size_t) (eol - line));
+    if (eq != NULL) {
+      size_t patlen = (size_t) (eq - line);
+
+      if (patlen >= sizeof(pat))
+        patlen = sizeof(pat) - 1;
+      memcpy(pat, line, patlen);
+      pat[patlen] = '\0';
+      keys = eq + 1;
+    } else {
+      pat[0] = '*';
+      pat[1] = '\0';
+      keys = line;
+    }
+    if (strjoker(url, pat, NULL, NULL) != NULL) {
+      size_t klen = (size_t) (eol - keys);
+
+      if (klen >= destsize)
+        klen = destsize - 1;
+      memcpy(dest, keys, klen);
+      dest[klen] = '\0';
+      result = dest;
+    }
+  }
+  return result;
+}
+
 #define endwith(a) ( (len >= (sizeof(a)-1)) ? ( strncmp(dest, a+len-(sizeof(a)-1), sizeof(a)-1) == 0 ) : 0 );
 HTSEXT_API char *adr_normalized_sized(const char *source, char *dest,
                                       size_t destsize) {
@@ -3948,25 +4061,33 @@ DECLARE_APPEND_ESCAPE_VERSION(escape_uri)
 
 #undef DECLARE_APPEND_ESCAPE_VERSION
 
-// Same as above, but in-place
-#undef DECLARE_INPLACE_ESCAPE_VERSION
-#define DECLARE_INPLACE_ESCAPE_VERSION(NAME) \
-HTSEXT_API size_t inplace_ ##NAME(char *const dest, const size_t size) { \
-  char buffer[256]; \
-  const size_t len = strnlen(dest, size); \
-  const int in_buffer = len + 1 < sizeof(buffer); \
-  char *src = in_buffer ? buffer : malloct(len + 1); \
-  size_t ret; \
-  assertf(src != NULL); \
-  assertf(len < size); \
-  memcpy(src, dest, len + 1); \
-  ret = NAME(src, dest, size); \
-  if (!in_buffer) { \
-    freet(src); \
-  } \
-  return ret; \
+// In-place escaping: copy dest aside, then escape that copy back into dest.
+typedef size_t (*escape_fn_t)(const char *src, char *dest, size_t size);
+
+static size_t inplace_escape(char *const dest, const size_t size,
+                             escape_fn_t escape) {
+  char buffer[256];
+  const size_t len = strnlen(dest, size);
+  const int in_buffer = len + 1 < sizeof(buffer);
+  char *src = in_buffer ? buffer : malloct(len + 1);
+  size_t ret;
+  assertf(src != NULL);
+  assertf(len < size);
+  memcpy(src, dest, len + 1);
+  ret = escape(src, dest, size);
+  if (!in_buffer) {
+    freet(src);
+  }
+  return ret;
 }
 
+// Thin exported wrappers binding inplace_escape() to each escaper (ABI).
+#undef DECLARE_INPLACE_ESCAPE_VERSION
+#define DECLARE_INPLACE_ESCAPE_VERSION(NAME)                                   \
+  HTSEXT_API size_t inplace_##NAME(char *const dest, const size_t size) {      \
+    return inplace_escape(dest, size, NAME);                                   \
+  }
+
 DECLARE_INPLACE_ESCAPE_VERSION(escape_in_url)
 DECLARE_INPLACE_ESCAPE_VERSION(escape_spc_url)
 DECLARE_INPLACE_ESCAPE_VERSION(escape_uri_utf)
@@ -4158,6 +4279,20 @@ void guess_httptype(httrackp * opt, char *s, const char *fil) {
   (void) get_httptype_sized(opt, s, HTS_MIMETYPE_SIZE, fil, 1);
 }
 
+// first match in a NUL-terminated {mime,ext} table. key selects the lookup
+// column (0=mime, 1=ext); returns the other column, or NULL if no row matches
+// (a "*" partner means the row carries no value).
+static const char *hts_mime_lookup(const char *(*table)[2], int key,
+                                   const char *needle) {
+  int j;
+
+  for (j = 0; strnotempty(table[j][1]); j++) {
+    if (strfield2(table[j][key], needle) && table[j][!key][0] != '*')
+      return table[j][!key];
+  }
+  return NULL;
+}
+
 // write the mime type for fil into s (capacity ssize)
 // flag: 1 to always return a type (the "application/..." / octet-stream
 // fallback) returns 1 if a type was written to s, 0 otherwise
@@ -4177,20 +4312,19 @@ HTSEXT_API hts_boolean get_httptype_sized(httrackp *opt, char *s, size_t ssize,
     /* Check html -> text/html */
     const char *a = fil + strlen(fil) - 1;
 
-    while((*a != '.') && (*a != '/') && (a > fil))
+    /* a < fil when fil is empty: bound before dereferencing */
+    while ((a > fil) && (*a != '.') && (*a != '/'))
       a--;
-    if (*a == '.' && strlen(a) < 32) {
-      int j = 0;
+    if (a >= fil && *a == '.' && strlen(a) < 32) {
+      const char *mime;
 
       a++;
-      while(strnotempty(hts_mime[j][1])) {
-        if (strfield2(hts_mime[j][1], a)) {
-          if (hts_mime[j][0][0] != '*') { // a match exists
-            strlcpybuff(s, hts_mime[j][0], ssize);
-            return 1;
-          }
-        }
-        j++;
+      mime = hts_mime_lookup(hts_mime, 1, a);
+      if (mime == NULL)
+        mime = hts_mime_lookup(hts_mime_modern, 1, a);
+      if (mime != NULL) {
+        strlcpybuff(s, mime, ssize);
+        return 1;
       }
 
       if (flag) {
@@ -4214,6 +4348,11 @@ HTSEXT_API void get_httptype(httrackp *opt, char *s, const char *fil,
   (void) get_httptype_sized(opt, s, HTS_MIMETYPE_SIZE, fil, flag);
 }
 
+/* Advertised Accept-Encoding; gzip and deflate both decode via hts_zunpack */
+const char *hts_acceptencoding(hts_boolean compressible) {
+  return compressible ? "gzip, deflate, identity;q=0.9" : "identity";
+}
+
 // get type of fil (php)
 // s: buffer (text/html) or NULL
 // return: 1 if known by user
@@ -4325,18 +4464,16 @@ int get_userhttptype(httrackp * opt, char *s, const char *fil) {
 // returns 1 if an extension was found (and written to s), 0 otherwise
 int give_mimext(char *s, size_t ssize, const char *st) {
   int ok = 0;
-  int j = 0;
+  const char *ext;
 
   st = hts_effective_mime(st); /* no declared type: derive an html ext */
   s[0] = '\0';
-  while((!ok) && (strnotempty(hts_mime[j][1]))) {
-    if (strfield2(hts_mime[j][0], st)) {
-      if (hts_mime[j][1][0] != '*') { // a match exists
-        strlcpybuff(s, hts_mime[j][1], ssize);
-        ok = 1;
-      }
-    }
-    j++;
+  ext = hts_mime_lookup(hts_mime, 0, st);
+  if (ext == NULL)
+    ext = hts_mime_lookup(hts_mime_modern, 0, st);
+  if (ext != NULL) {
+    strlcpybuff(s, ext, ssize);
+    ok = 1;
   }
   // wrap "x" mimetypes, such as:
   // application/x-mp3
@@ -4661,7 +4798,6 @@ LLint check_downloadable_bytes(int rate) {
 
     time_now = mtime_local();
     elapsed_useconds = time_now - HTS_STAT.istat_timestart[id_timer];
-    // NO totally stupid - elapsed_useconds+=1000;      // for the next second, too
     bytes_transferred_during_period =
       (HTS_STAT.HTS_TOTAL_RECV - HTS_STAT.istat_bytes[id_timer]);
 
@@ -4674,32 +4810,6 @@ LLint check_downloadable_bytes(int rate) {
     return TAILLE_BUFFER;
 }
 
-//
-// 0 : OK
-// 1 : slow down
-#if 0
-int HTS_TOTAL_RECV_CHECK(int var) {
-  if (HTS_STAT.HTS_TOTAL_RECV_STATE)
-    return 1;
-  /*
-     {
-     if (HTS_STAT.HTS_TOTAL_RECV_STATE==3) { 
-     var = min(var,32); 
-     Sleep(250); 
-     } else if (HTS_STAT.HTS_TOTAL_RECV_STATE==2) { 
-     var = min(var,256); 
-     Sleep(100); 
-     } else { 
-     var/=2; 
-     if (var<=0) var=1; 
-     Sleep(50); 
-     } 
-     }
-   */
-  return 0;
-}
-#endif
-
 // Lecture dans buff de size octets au maximum en utilisant la socket r (structure htsblk)
 // returns: 
 // >0 : data received
@@ -4708,7 +4818,6 @@ int HTS_TOTAL_RECV_CHECK(int var) {
 int hts_read(htsblk * r, char *buff, int size) {
   int retour;
 
-  //  return read(soc,buff,size);
   if (r->is_file) {
 #if HTS_WIDE_DEBUG
     DEBUG_W("read(%p, %d, %d)\n" _(void *)buff _(int) size _(int) r->fp);
@@ -4726,7 +4835,6 @@ int hts_read(htsblk * r, char *buff, int size) {
     if (r->soc == INVALID_SOCKET)
       printf("!!WIDE_DEBUG ERROR, soc==INVALID hts_read\n");
 #endif
-    //HTS_TOTAL_RECV_CHECK(size);         // Diminuer au besoin si trop de données reçues
 #if HTS_USEOPENSSL
     if (r->ssl) {
       retour = SSL_read(r->ssl_con, buff, size);
@@ -5161,18 +5269,13 @@ SOCaddr* hts_dns_resolve(httrackp * opt, const char *_iadr, SOCaddr *const addr)
 
 // --- Tracage des mallocs() ---
 #ifdef HTS_TRACE_MALLOC
-//#define htsLocker(A, N) htsLocker(A, N)
 #define htsLocker(A, N) do {} while(0)
 static mlink trmalloc = { NULL, 0, 0, NULL };
 
 static int trmalloc_id = 0;
 static htsmutex *mallocMutex = NULL;
-static void hts_meminit(void) {
-  //if (mallocMutex == NULL) {
-  //  mallocMutex = calloc(sizeof(*mallocMutex), 1);
-  //  htsLocker(mallocMutex, -999);
-  //}
-}
+
+static void hts_meminit(void) {}
 void *hts_malloc(size_t len) {
   void *adr;
 
@@ -5256,7 +5359,6 @@ void hts_free(void *adr) {
               htsboundary);
       lnk->next = lnk->next->next;
       free((void *) blk_free);
-      //blk_free->id=-1;
       free((char *) adr - bsize);
       htsLocker(mallocMutex, 0);
       return;
@@ -5325,7 +5427,6 @@ mlink *hts_find(char *adr) {
 
     if (depl < 0)
       depl = -depl;
-    //assertf(depl < 512000);   /* near the stack frame.. doesn't look like malloc but stack variable */
     return NULL;
   }
 }
@@ -5381,8 +5482,7 @@ int ftp_available(void) {
 }
 #else
 int ftp_available(void) {
-  return 1;                     // ok!
-  //return 0;   // SOUS UNIX, PROBLEMESs
+  return 1; // ok!
 }
 #endif
 
@@ -5596,13 +5696,19 @@ HTSEXT_API int hts_init(void) {
       assertf("OpenSSL version seems vulnerable to heartbleed bug (CVE-2014-0160)" == NULL);
     }
 
-    // OpenSSL_add_all_algorithms();
     openssl_ctx = SSL_CTX_new(method);
     if (!openssl_ctx) {
       fprintf(stderr, "fatal: unable to initialize TLS: SSL_CTX_new()\n");
       abortLog("unable to initialize TLS: SSL_CTX_new()");
       assertf("unable to initialize TLS" == NULL);
     }
+    /* Pin a TLS floor (no SSLv3/TLS1.0/1.1); no cert verify, by design. */
+#if OPENSSL_VERSION_NUMBER >= 0x10100000L
+    SSL_CTX_set_min_proto_version(openssl_ctx, TLS1_2_VERSION);
+#else
+    SSL_CTX_set_options(openssl_ctx, SSL_OP_NO_SSLv2 | SSL_OP_NO_SSLv3 |
+                                         SSL_OP_NO_TLSv1 | SSL_OP_NO_TLSv1_1);
+#endif
   }
 #endif
 
@@ -5808,9 +5914,11 @@ HTSEXT_API httrackp *hts_create_opt(void) {
     "htsswf", "htsjava", "httrack-plugin", NULL
   };
 #else
-  static const char *defaultModules[] = {
-    "libhtsswf.so.1", "libhtsjava.so.2", "httrack-plugin", NULL
-  };
+#ifndef HTS_LIBHTSJAVA_NAME
+#define HTS_LIBHTSJAVA_NAME "libhtsjava.so" /* non-autoconf fallback */
+#endif
+  static const char *defaultModules[] = {"libhtsswf.so.1", HTS_LIBHTSJAVA_NAME,
+                                         "httrack-plugin", NULL};
 #endif
   httrackp *opt = malloc(sizeof(httrackp));
 
@@ -5854,8 +5962,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->shell = HTS_FALSE;
   opt->proxy.active = 0;        // pas de proxy
   opt->user_agent_send = HTS_TRUE;
-  StringCopy(opt->user_agent,
-             "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)");
+  StringCopy(opt->user_agent, HTS_DEFAULT_USER_AGENT);
   StringCopy(opt->referer, "");
   StringCopy(opt->from, "");
   opt->savename_83 = HTS_SAVENAME_83_LONG; // long names by default
@@ -5889,7 +5996,14 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->verbosedisplay = HTS_VERBOSE_NONE; // no text animation
   opt->sizehack = HTS_FALSE;
   opt->urlhack = HTS_TRUE;
+  opt->no_www_dedup = HTS_FALSE;
+  opt->no_slash_dedup = HTS_FALSE;
+  opt->no_query_dedup = HTS_FALSE;
   StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
+  StringCopy(opt->strip_query, "");
+  StringCopy(opt->cookies_file, "");
+  opt->pause_min_ms = 0;
+  opt->pause_max_ms = 0;
   opt->ftp_proxy = HTS_TRUE;
   opt->convert_utf8 = HTS_TRUE;
   StringCopy(opt->filelist, "");
@@ -5903,7 +6017,6 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->log = stdout;
   opt->errlog = stderr;
   opt->flush = HTS_TRUE;
-  // opt->aff_progress=0;
   opt->keyboard = HTS_FALSE;
   //
   StringCopy(opt->path_html, "");
@@ -5913,8 +6026,8 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   //
   opt->maxlink = 100000;        // 100,000 liens max par défaut
   opt->maxfilter = 200;         // 200 filtres max par défaut
-  opt->maxcache = 1048576 * 32; // a peu près 32Mo en cache max -- OPTION NON PARAMETRABLE POUR L'INSTANT --
-  //opt->maxcache_anticipate=256;  // maximum de liens à anticiper
+  opt->maxcache = 1048576 * 32; // a peu près 32Mo en cache max -- OPTION NON
+                                // PARAMETRABLE POUR L'INSTANT --
   opt->maxtime = -1;            // temps max en secondes
   opt->maxrate = 100000;        // taux maxi
   opt->maxconn = 5.0;           // nombre connexions/s
@@ -6034,6 +6147,8 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->urllist);
     StringFree(opt->footer);
     StringFree(opt->mod_blacklist);
+    StringFree(opt->strip_query);
+    StringFree(opt->cookies_file);
 
     StringFree(opt->path_html);
     StringFree(opt->path_html_utf8);
@@ -6065,11 +6180,9 @@ const hts_stat_struct* hts_get_stats(httrackp * opt) {
 }
 
 // defaut wrappers
-static void __cdecl htsdefault_init(t_hts_callbackarg * carg) {
-}
-static void __cdecl htsdefault_uninit(t_hts_callbackarg * carg) {
-  // hts_freevar();
-}
+static void __cdecl htsdefault_init(t_hts_callbackarg *carg) {}
+
+static void __cdecl htsdefault_uninit(t_hts_callbackarg *carg) {}
 static int __cdecl htsdefault_start(t_hts_callbackarg * carg, httrackp * opt) {
   return 1;
 }

src/htslib.h

@@ -171,7 +171,6 @@ 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);
@@ -190,7 +189,6 @@ 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
@@ -285,6 +283,9 @@ 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

@@ -55,12 +55,6 @@ 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] = "";
@@ -112,18 +106,6 @@ 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

@@ -41,6 +41,10 @@ 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 \
@@ -70,31 +74,6 @@ 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;
@@ -138,37 +117,191 @@ static void cleanEndingSpaceOrDot(char *s) {
   }
 }
 
-/* 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];
+/* 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 0; /* type kept verbatim (keep-list / bogus-multiple) */
+    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, sizeof(urlmime), file, 0))
-    return 1; /* URL ext implies no known type: trust the wire type */
+  if (!get_httptype_sized(opt, urlmime, urlmime_size, file, 0))
+    return WIRE_WINS; /* URL ext implies no known 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. */
+    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) {
+  char urlmime[256];
+
+  switch (wire_ext_verdict(opt, wiremime, file, urlmime, sizeof(urlmime))) {
+  case WIRE_KEEPS_EXT:
+    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;
 }
 
-// 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 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).
 int url_savename(lien_adrfilsave *const afs,
                  lien_adrfil *const former,
                  const char *referer_adr, const char *referer_fil, 
@@ -198,6 +331,13 @@ 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
 
@@ -230,9 +370,13 @@ int url_savename(lien_adrfilsave *const afs,
   // www-42.foo.com -> foo.com
   // foo.com/bar//foobar -> foo.com/bar/foobar
   if (opt->urlhack) {
-    // copy of adr (without protocol), used for lookups (see urlhack)
-    normadr = adr_normalized_sized(adr, normadr_, sizeof(normadr_));
-    normfil = fil_normalized(fil_complete, normfil_);
+    // 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);
   } else {
     if (link_has_authority(adr_complete)) {     // https or other protocols : in "http/" subfolder
       char *pos = strchr(adr_complete, ':');
@@ -245,6 +389,11 @@ 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://
@@ -389,45 +538,30 @@ 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 ||
-            (ishtest = ishtml(opt, fil)) <
-                0) { // unsure whether it's html or a file
+            ishtml(opt, fil) < 0) { // unsure whether it's html or a file
           // lire dans le cache
-          htsblk r = cache_read_including_broken(opt, cache, adr, fil); // test uniquement
+          char BIGSTK previous_save[HTS_URLMAXSIZE * 2];
+          htsblk r;
 
-          if (r.statuscode != -1) {     // pas d'erreur de lecture cache
-            char s[32];
+          previous_save[0] = '\0';
+          r = cache_read_including_broken(opt, cache, adr, fil,
+                                          previous_save); // test uniquement
 
-            s[0] = '\0';
+          if (r.statuscode != -1) { // cache entry read OK
             hts_log_print(opt, LOG_DEBUG, "Testing link type (from cache) %s%s",
                           adr_complete, fil_complete);
             if (!HTTP_IS_REDIRECT(r.statuscode)) {
-              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);
-                }
-              }
+              const sniff_src src = {sback, NULL, adr, fil, previous_save};
+
+              ext_chg = resolve_extension(opt, &src, r.cdispo, r.contenttype,
+                                          fil, ext, sizeof(ext));
             }
-#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,
@@ -451,22 +585,13 @@ 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. We basically take the same logic as later.
-            // FIXME: we should cleanup and factorize this unholy mess
+            // Check if the file is ready in backing.
             if (headers != NULL && headers->status >= 0 && !is_redirect) {
-              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);
-                }
-              }
+              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));
             }
             else if (mime_type != NULL) {
               ext[0] = '\0';
@@ -484,13 +609,6 @@ 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;
                 }
@@ -509,11 +627,10 @@ int url_savename(lien_adrfilsave *const afs,
             int has_been_moved = 0;
             lien_adrfil current;
 
-            /* 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 
+            /* Wait for an available test slot, honoring the connection limits
              */
-            URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
+            if (!hts_wait_available_socket(sback, opt, cache, ptr))
+              return -1;
 
             /* Rock'in */
             current.adr[0] = current.fil[0] = '\0';
@@ -543,24 +660,11 @@ int url_savename(lien_adrfilsave *const afs,
                   if (ptr >= 0) {
                     back_fillmax(sback, opt, cache, ptr, numero_passe);
                   }
-                  // 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)) {
+                  if (!hts_loop_tick(sback, opt, b, ptr)) {
                     return -1;
-                  } else if (opt->state._hts_cancel || !back_checkmirror(opt)) {        // cancel 2 ou 1 (cancel parsing)
+                  } else if (opt->state._hts_cancel ||
+                             !back_checkmirror(
+                                 opt)) { // cancel level 2 or 1 (cancel parsing)
                     back_delete(opt, cache, sback, b);  // cancel test
                     stop_looping = 1;
                   }
@@ -625,8 +729,9 @@ int url_savename(lien_adrfilsave *const afs,
                                                 "Loop with HEAD request (during prefetch) at %s%s",
                                                 current.adr, current.fil);
                                 }
-                                // Ajouter
-                                URLSAVENAME_WAIT_FOR_AVAILABLE_SOCKET();
+                                if (!hts_wait_available_socket(sback, opt,
+                                                               cache, ptr))
+                                  return -1;
                                 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",
@@ -680,30 +785,10 @@ int url_savename(lien_adrfilsave *const afs,
                     // libérer emplacement backing
                   }
 
-                  {             // 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
-                  }
+                  // 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));
                 }
                 // FIN Si non déplacé, forcer type?
 
@@ -1247,8 +1332,7 @@ int url_savename(lien_adrfilsave *const afs,
 
     while((a > afs->save) && (*a != '.') && (*a != '/'))
       a--;
-    if (*a != '.') {            // agh pas de point
-      //strcatbuff(save,".none");                 // a éviter
+    if (*a != '.') {                         // agh pas de point
       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);
@@ -1386,17 +1470,6 @@ 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,
@@ -1544,10 +1617,6 @@ 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 */
@@ -1613,17 +1682,13 @@ 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;
 }

src/htsname.h

@@ -100,6 +100,8 @@ 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,

src/htsopt.h

@@ -105,7 +105,6 @@ 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 */
@@ -440,7 +439,6 @@ 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
@@ -492,7 +490,6 @@ 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 */
@@ -529,6 +526,16 @@ 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 */
 };
 
 /* Running statistics for a mirror. */
@@ -539,8 +546,6 @@ 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) */
@@ -672,7 +677,6 @@ 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 */
 };
@@ -717,9 +721,6 @@ 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

@@ -66,7 +66,6 @@ struct htsmoduleStructExtended {
   char ***filters_;
   robots_wizard *robots_;
   hash_struct *hash_;
-  //int *lien_max_;
 
   /* Base & codebase */
   char *base;
@@ -116,6 +115,19 @@ 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..
 */
@@ -162,27 +174,4 @@ 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

@@ -44,28 +44,84 @@ 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[250];
+        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;
 
-        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 (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;
               }
             }
-          } while((strnotempty(line)) && (ptr < (int) strlen(robots->token)));
+          }
         }
+        if (matched && !best_allow)
+          return -1; // forbidden
       } else {
         return -1;
       }
@@ -74,6 +130,93 @@ 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

@@ -39,17 +39,27 @@ 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[4096];
+  char token[HTS_ROBOTS_TOKEN_SIZE];
   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

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

src/htsselftest.h

@@ -0,0 +1,52 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 2026 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: htsselftest.h                                          */
+/*       named dispatch for the hidden engine self-tests        */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#ifndef HTSSELFTEST_DEFH
+#define HTSSELFTEST_DEFH
+
+#ifdef HTS_INTERNAL_BYTECODE
+
+#ifndef HTS_DEF_FWSTRUCT_httrackp
+#define HTS_DEF_FWSTRUCT_httrackp
+typedef struct httrackp httrackp;
+#endif
+
+/* Run engine self-test `name` over the positional args argv[0..argc-1], or list
+   the available tests when name is NULL, empty, or "list". Prints the result;
+   returns the process exit code (0 == success). The caller owns option cleanup.
+   Reached through the hidden `httrack -#test[=NAME ...]` subcommand. */
+int hts_selftest(httrackp *opt, const char *name, int argc, char **argv);
+
+#endif
+
+#endif

src/htsserver.c

@@ -265,7 +265,6 @@ T_SOC smallserver_init(int *port, char *adr) {
       SOCaddr_initport(server, *port);
       if (bind(soc, &SOCaddr_sockaddr(server), SOCaddr_size(server)) == 0) {
         if (listen(soc, 10) >= 0) {
-          // SOCaddr_inetntoa(adr, 128, server2);
           strcpy(adr, h_loc);
         } else {
 #ifdef _WIN32
@@ -358,12 +357,12 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
       {NULL, 0}
     };
     initStrElt initStr[] = {
-      {"user", "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)"},
-      {"footer",
-       "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x [XR&CO'2014], %s -->"},
-      {"url2", "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
-      {NULL, NULL}
-    };
+        {"user", HTS_DEFAULT_USER_AGENT},
+        {"footer", "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x "
+                   "[XR&CO'2014], %s -->"},
+        {"url2",
+         "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
+        {NULL, NULL}};
     int i = 0;
 
     for(i = 0; initInt[i].name; i++) {
@@ -439,7 +438,6 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
         meth = 10;
       } else {
 #ifdef _DEBUG
-        // assert(FALSE);
 #endif
       }
       if (meth) {
@@ -1360,7 +1358,6 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
 
             StringCat(headers, error_hdr);
             StringCat(output, error);
-            //assert(file == NULL);
           }
         }
       } else {
@@ -1388,12 +1385,10 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
                   != StringLength(output)))
         ) {
 #ifdef _DEBUG
-        //assert(FALSE);
 #endif
       }
     } else {
 #ifdef _DEBUG
-      // assert(FALSE);
 #endif
     }
 
@@ -1540,8 +1535,7 @@ static int htslang_load(char *limit_to, size_t limit_size, const char *path) {
             } while(strnotempty(test));
           }
 
-          if (!strnotempty(test)) {     // éviter doublons
-            // conv_printf(key,key);
+          if (!strnotempty(test)) { // éviter doublons
             const size_t len = strlen(intkey);
             char *const buff = (char *) malloc(len + 1);
 
@@ -1632,8 +1626,6 @@ static int htslang_load(char *limit_to, size_t limit_size, const char *path) {
                     intkey = "";
                 } else {
                   if (loops > 0) {
-                    //err_msg += intkey;
-                    //err_msg += " ";
                   }
                 }
               }
@@ -1740,13 +1732,7 @@ static void LANG_DELETE(void) {
 }
 
 // sélection de la langue
-static void LANG_INIT(const char *path) {
-  //CWinApp* pApp = AfxGetApp();
-  //if (pApp) {
-  /* pApp->GetProfileInt("Language","IntId",0); */
-  LANG_T(path, 0 /*pApp->GetProfileInt("Language","IntId",0) */ );
-  //}
-}
+static void LANG_INIT(const char *path) { LANG_T(path, 0); }
 
 static int LANG_T(const char *path, int l) {
   if (l >= 0) {

src/htssniff.c

@@ -0,0 +1,352 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 1998-2017 Xavier Roche and other contributors
+
+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/>.
+
+Important notes:
+
+- We hereby ask people using this source NOT to use it in purpose of grabbing
+emails addresses, or collecting any other private information on persons.
+This would disgrace our work, and spoil the many hours we spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: MIME magic-byte consistency checks                     */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#include "htssniff.h"
+
+#include <string.h>
+
+#include "htslib.h"
+
+/* One magic rule: `len` bytes at `off` confirm `mime`. */
+typedef struct sniff_magic {
+  const char *mime;
+  unsigned short off;
+  unsigned char len;
+  const char *bytes;
+} sniff_magic;
+
+/* Direction is mime -> magic (verify a claim, never classify); types with
+   no reliable magic (plain text, css, js..) are deliberately absent. Patterns
+   follow the WHATWG MIME Sniffing Standard tables where it defines them
+   (https://mimesniff.spec.whatwg.org/); the rest covers httrack's wider MIME
+   set. Spec-only types absent from our MIME tables (EOT, font/collection)
+   are omitted as unreachable. */
+static const sniff_magic sniff_table[] = {
+    /* images */
+    {"image/jpeg", 0, 3, "\xff\xd8\xff"},
+    {"image/pipeg", 0, 3, "\xff\xd8\xff"},
+    {"image/pjpeg", 0, 3, "\xff\xd8\xff"},
+    {"image/png", 0, 8, "\x89PNG\r\n\x1a\n"},
+    {"image/gif", 0, 6, "GIF87a"},
+    {"image/gif", 0, 6, "GIF89a"},
+    {"image/bmp", 0, 2, "BM"},
+    {"image/tiff", 0, 4, "II*\0"},
+    {"image/tiff", 0, 4, "MM\0*"},
+    {"image/x-icon", 0, 4, "\0\0\1\0"},
+    {"image/x-icon", 0, 4, "\0\0\2\0"}, /* Windows cursor, per the spec */
+    {"image/x-portable-bitmap", 0, 2, "P1"},
+    {"image/x-portable-bitmap", 0, 2, "P4"},
+    {"image/x-portable-pixmap", 0, 2, "P3"},
+    {"image/x-portable-pixmap", 0, 2, "P6"},
+    {"image/x-xpixmap", 0, 9, "/* XPM */"},
+    {"image/x-xbitmap", 0, 7, "#define"},
+    {"image/x-rgb", 0, 2, "\x01\xda"},
+    {"image/x-cmu-raster", 0, 4, "\xf1\x00\x40\xbb"},
+    /* audio */
+    {"audio/mpeg", 0, 3, "ID3"},
+    {"audio/basic", 0, 4, ".snd"},
+    {"audio/mid", 0, 8, "MThd\0\0\0\6"},
+    {"audio/midi", 0, 8, "MThd\0\0\0\6"},
+    {"audio/x-pn-realaudio", 0, 4, ".ra\xfd"},
+    {"audio/x-pn-realaudio", 0, 4, ".RMF"},
+    {"audio/x-pn-realaudio-plugin", 0, 4, ".ra\xfd"},
+    {"audio/x-pn-realaudio-plugin", 0, 4, ".RMF"},
+    {"audio/flac", 0, 4, "fLaC"},
+    {"audio/aac", 0, 4, "ADIF"},
+    /* video */
+    {"video/mpeg", 0, 4, "\x00\x00\x01\xba"},
+    {"video/mpeg", 0, 4, "\x00\x00\x01\xb3"},
+    {"video/x-sgi-movie", 0, 4, "MOVI"},
+    /* archives / compression */
+    {"application/x-gzip", 0, 3, "\x1f\x8b\x08"},
+    {"multipart/x-gzip", 0, 3, "\x1f\x8b\x08"},
+    {"application/x-compressed", 0, 3, "\x1f\x8b\x08"},
+    {"application/x-compress", 0, 2, "\x1f\x9d"},
+    {"application/x-bzip2", 0, 3, "BZh"},
+    {"application/x-7z-compressed", 0, 6, "7z\xbc\xaf\x27\x1c"},
+    /* 6-byte prefix common to RAR4 (spec) and RAR5 */
+    {"application/x-rar-compressed", 0, 6, "Rar!\x1a\x07"},
+    {"application/zstd", 0, 4, "\x28\xb5\x2f\xfd"},
+    {"application/arj", 0, 2, "\x60\xea"},
+    {"application/x-cpio", 0, 6, "070701"},
+    {"application/x-cpio", 0, 6, "070707"},
+    {"application/x-cpio", 0, 2, "\xc7\x71"},
+    {"application/x-sv4cpio", 0, 6, "070701"},
+    {"application/x-sv4crc", 0, 6, "070702"},
+    {"application/x-stuffit", 0, 8, "StuffIt "},
+    {"application/x-stuffit", 0, 4, "SIT!"},
+    {"application/mac-binhex40", 0, 10, "(This file"},
+    /* documents */
+    {"application/pdf", 0, 5, "%PDF-"},
+    {"application/postscript", 0, 2, "%!"},
+    {"application/rtf", 0, 5, "{\\rtf"},
+    {"application/x-dvi", 0, 2, "\xf7\x02"},
+    {"application/x-hdf", 0, 4, "\x0e\x03\x13\x01"},
+    {"application/x-hdf", 0, 8, "\x89HDF\r\n\x1a\n"},
+    {"application/x-netcdf", 0, 4, "CDF\x01"},
+    {"application/x-netcdf", 0, 4, "CDF\x02"},
+    {"application/x-msaccess", 0, 19, "\0\1\0\0Standard Jet DB"},
+    /* fonts */
+    {"font/woff", 0, 4, "wOFF"},
+    {"font/woff2", 0, 4, "wOF2"},
+    {"font/ttf", 0, 4, "\0\1\0\0"},
+    {"font/ttf", 0, 4, "true"},
+    {"font/otf", 0, 4, "OTTO"},
+    /* misc */
+    {"application/x-shockwave-flash", 0, 3, "FWS"},
+    {"application/x-shockwave-flash", 0, 3, "CWS"},
+    {"application/x-shockwave-flash", 0, 3, "ZWS"},
+    {"application/futuresplash", 0, 3, "FWS"},
+    {"application/x-director", 0, 4, "RIFX"},
+    {"application/x-director", 0, 4, "XFIR"},
+    {"application/x-java-vm", 0, 4, "\xca\xfe\xba\xbe"},
+    {"application/wasm", 0, 4, "\0asm"},
+    {"application/x-msmetafile", 0, 4, "\xd7\xcd\xc6\x9a"},
+    {"application/x-msmetafile", 0, 4, "\x01\x00\x09\x00"},
+    {"application/x-x509-ca-cert", 0, 2, "\x30\x82"},
+    {"application/x-pkcs12", 0, 2, "\x30\x82"},
+    {"application/x-pkcs7-mime", 0, 2, "\x30\x82"},
+    {"application/x-pkcs7-signature", 0, 2, "\x30\x82"},
+    {"application/x-pkcs7-certificates", 0, 2, "\x30\x82"},
+    {"x-world/x-vrml", 0, 5, "#VRML"},
+    {"application/x-bittorrent", 0, 11, "d8:announce"},
+    {"drawing/x-dwf", 0, 4, "(DWF"},
+    {"application/acad", 0, 4, "AC10"},
+    {NULL, 0, 0, NULL}};
+
+/* MIME families sharing a container magic */
+static const char *const zip_mimes[] = {
+    "application/zip", "application/x-zip-compressed", "multipart/x-zip", NULL};
+static const char *const zip_mime_prefixes[] = {
+    "application/vnd.openxmlformats-officedocument.",
+    "application/vnd.oasis.opendocument.", NULL};
+static const char *const ole_mimes[] = {"application/msword",
+                                        "application/excel",
+                                        "application/vnd.ms-excel",
+                                        "application/powerpoint",
+                                        "application/vnd.ms-powerpoint",
+                                        "application/vnd.ms-project",
+                                        "application/vnd.ms-works",
+                                        "application/x-msmoney",
+                                        "application/x-mspublisher",
+                                        NULL};
+static const char *const tar_mimes[] = {
+    "application/x-tar", "application/x-ustar", "application/x-gtar", NULL};
+static const char *const ogg_mimes[] = {"application/ogg", "audio/ogg",
+                                        "video/ogg", "audio/opus", NULL};
+static const char *const ebml_mimes[] = {"video/webm", "audio/webm", NULL};
+/* ISO-BMFF, any 'ftyp' brand: containers overlap too much to split */
+static const char *const bmff_mimes[] = {"video/mp4", "audio/mp4",
+                                         "video/quicktime", NULL};
+static const char *const avif_mimes[] = {"image/avif", NULL};
+static const char *const heic_mimes[] = {"image/heic", NULL};
+static const char *const asf_mimes[] = {"video/x-ms-asf", "video/x-ms-wmv",
+                                        "video/x-la-asf", NULL};
+static const char *const xml_mimes[] = {"application/xml", "text/xml",
+                                        "image/svg+xml", "image/svg-xml", NULL};
+static const char *const svg_mimes[] = {"image/svg+xml", "image/svg-xml", NULL};
+static const char *const html_mimes[] = {"text/html", NULL};
+static const char *const pem_mimes[] = {
+    "application/x-x509-ca-cert", "application/x-pkcs7-certificates",
+    "application/x-pkcs7-mime", "application/x-pkcs7-signature", NULL};
+
+static hts_boolean mime_in(const char *const *list, const char *mime) {
+  size_t i;
+
+  for (i = 0; list[i] != NULL; i++)
+    if (strfield2(list[i], mime))
+      return HTS_TRUE;
+  return HTS_FALSE;
+}
+
+static hts_boolean mime_in_prefix(const char *const *list, const char *mime) {
+  size_t i;
+
+  for (i = 0; list[i] != NULL; i++)
+    if (strfield(mime, list[i]))
+      return HTS_TRUE;
+  return HTS_FALSE;
+}
+
+static hts_boolean has_bytes(const unsigned char *d, size_t n, size_t off,
+                             const char *bytes, size_t len) {
+  /* overflow-safe: untrusted n alone on one side */
+  return n >= off && len <= n - off && memcmp(d + off, bytes, len) == 0
+             ? HTS_TRUE
+             : HTS_FALSE;
+}
+
+static unsigned char ascii_lower(unsigned char c) {
+  return c >= 'A' && c <= 'Z' ? (unsigned char) (c + 32) : c;
+}
+
+/* Case-insensitive text prefix after an optional UTF-8 BOM and whitespace. */
+static hts_boolean has_text_prefix(const unsigned char *d, size_t n,
+                                   const char *prefix) {
+  const size_t len = strlen(prefix);
+  size_t i, k;
+
+  i = n >= 3 && memcmp(d, "\xef\xbb\xbf", 3) == 0 ? 3 : 0;
+  while (i < n && (d[i] == ' ' || d[i] == '\t' || d[i] == '\r' || d[i] == '\n'))
+    i++;
+  if (len > n - i) /* i <= n from the loop above */
+    return HTS_FALSE;
+  for (k = 0; k < len; k++)
+    if (ascii_lower(d[i + k]) != ascii_lower((unsigned char) prefix[k]))
+      return HTS_FALSE;
+  return HTS_TRUE;
+}
+
+typedef enum sniff_op {
+  SNIFF_QUERY_KNOWN, /* is any rule defined for this MIME? */
+  SNIFF_QUERY_MATCH  /* do the bytes confirm this MIME? */
+} sniff_op;
+
+/* Single walk for both queries so the rule set can't drift apart. */
+static hts_boolean sniff_eval(sniff_op op, const unsigned char *d, size_t n,
+                              const char *mime) {
+  size_t i;
+
+/* KNOWN short-circuits; MATCH tests the magic */
+#define SNIFF_RULE(cond)                                                       \
+  do {                                                                         \
+    if (op == SNIFF_QUERY_KNOWN)                                               \
+      return HTS_TRUE;                                                         \
+    if (cond)                                                                  \
+      return HTS_TRUE;                                                         \
+  } while (0)
+
+  for (i = 0; sniff_table[i].mime != NULL; i++) {
+    if (strfield2(sniff_table[i].mime, mime)) {
+      SNIFF_RULE(has_bytes(d, n, sniff_table[i].off, sniff_table[i].bytes,
+                           sniff_table[i].len));
+    }
+  }
+  if (mime_in(zip_mimes, mime) || mime_in_prefix(zip_mime_prefixes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "PK\3\4", 4) ||
+               has_bytes(d, n, 0, "PK\5\6", 4));
+  }
+  if (mime_in(ole_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1", 8));
+  }
+  if (mime_in(tar_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 257, "ustar", 5));
+  }
+  if (mime_in(ogg_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "OggS\0", 5));
+  }
+  if (mime_in(ebml_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "\x1a\x45\xdf\xa3", 4));
+  }
+  if (mime_in(bmff_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 4, "ftyp", 4));
+  }
+  if (mime_in(avif_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 4, "ftypavif", 8) ||
+               has_bytes(d, n, 4, "ftypavis", 8));
+  }
+  if (mime_in(heic_mimes, mime)) {
+    SNIFF_RULE(
+        has_bytes(d, n, 4, "ftyphei", 7) || has_bytes(d, n, 4, "ftyphev", 7) ||
+        has_bytes(d, n, 4, "ftypmif1", 8) || has_bytes(d, n, 4, "ftypmsf1", 8));
+  }
+  if (mime_in(asf_mimes, mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "\x30\x26\xb2\x75\x8e\x66\xcf\x11", 8));
+  }
+  if (strfield2("audio/x-wav", mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "RIFF", 4) && has_bytes(d, n, 8, "WAVE", 4));
+  }
+  if (strfield2("video/x-msvideo", mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "RIFF", 4) && has_bytes(d, n, 8, "AVI ", 4));
+  }
+  if (strfield2("image/webp", mime)) {
+    SNIFF_RULE(has_bytes(d, n, 0, "RIFF", 4) &&
+               has_bytes(d, n, 8, "WEBPVP", 6));
+  }
+  if (strfield2("image/x-portable-anymap", mime)) {
+    SNIFF_RULE(n >= 2 && d[0] == 'P' && d[1] >= '1' && d[1] <= '6');
+  }
+  if (strfield2("audio/x-aiff", mime)) {
+    SNIFF_RULE(
+        has_bytes(d, n, 0, "FORM", 4) &&
+        (has_bytes(d, n, 8, "AIFF", 4) || has_bytes(d, n, 8, "AIFC", 4)));
+  }
+  if (strfield2("audio/mpeg", mime)) {
+    /* MPEG audio frame sync (11 bits), valid layer and bitrate fields */
+    SNIFF_RULE(n >= 2 && d[0] == 0xff && (d[1] & 0xe0) == 0xe0 &&
+               (d[1] & 0x06) != 0);
+  }
+  if (strfield2("audio/aac", mime)) {
+    /* ADTS sync */
+    SNIFF_RULE(n >= 2 && d[0] == 0xff && (d[1] & 0xf6) == 0xf0);
+  }
+  if (strfield2("video/mp2t", mime)) {
+    SNIFF_RULE(n >= 1 && d[0] == 0x47 && (n <= 188 || d[188] == 0x47));
+  }
+  if (mime_in(xml_mimes, mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "<?xml"));
+  }
+  if (mime_in(svg_mimes, mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "<svg") ||
+               has_text_prefix(d, n, "<!DOCTYPE svg"));
+  }
+  if (mime_in(html_mimes, mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "<!DOCTYPE") ||
+               has_text_prefix(d, n, "<html") ||
+               has_text_prefix(d, n, "<head"));
+  }
+  if (mime_in(pem_mimes, mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "-----BEGIN"));
+  }
+  if (strfield2("audio/x-mpegurl", mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "#EXTM3U"));
+  }
+  if (strfield2("text/x-vcard", mime)) {
+    SNIFF_RULE(has_text_prefix(d, n, "BEGIN:VCARD"));
+  }
+#undef SNIFF_RULE
+  return HTS_FALSE;
+}
+
+hts_boolean hts_sniff_mime_known(const char *mime) {
+  if (mime == NULL || *mime == '\0')
+    return HTS_FALSE;
+  return sniff_eval(SNIFF_QUERY_KNOWN, NULL, 0, mime);
+}
+
+hts_boolean hts_sniff_mime_consistent(const void *data, size_t size,
+                                      const char *mime) {
+  if (data == NULL || size == 0 || mime == NULL || *mime == '\0')
+    return HTS_FALSE;
+  return sniff_eval(SNIFF_QUERY_MATCH, (const unsigned char *) data, size,
+                    mime);
+}

src/htssniff.h

@@ -0,0 +1,50 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 1998-2017 Xavier Roche and other contributors
+
+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/>.
+
+Important notes:
+
+- We hereby ask people using this source NOT to use it in purpose of grabbing
+emails addresses, or collecting any other private information on persons.
+This would disgrace our work, and spoil the many hours we spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: MIME magic-byte consistency checks                     */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#ifndef HTSSNIFF_DEFH
+#define HTSSNIFF_DEFH
+
+#include <stddef.h>
+#include "htsglobal.h"
+
+/* Leading-body window read to arbitrate a wire/extension MIME conflict. */
+#define HTS_SNIFF_LEN 512
+
+/* Can a magic rule ever confirm this MIME? (whether sniffing is worth it) */
+hts_boolean hts_sniff_mime_known(const char *mime);
+
+/* TRUE when the leading body bytes are consistent with the claimed MIME;
+   FALSE on unknown MIME, unknown magic, or too-short data (fail-safe). */
+hts_boolean hts_sniff_mime_consistent(const void *data, size_t size,
+                                      const char *mime);
+
+#endif

src/htsstrings.h

@@ -121,9 +121,6 @@ struct String {
 /** Byte at POS (read/write). No bounds check; POS must be < StringLength. **/
 #define StringSubRW(BLK, POS) (StringBuffRW(BLK)[POS])
 
-/** Subcharacter (read/write) **/
-#define StringSubRW(BLK, POS) (StringBuffRW(BLK)[POS])
-
 /** Byte POS positions from the end (read). POS==1 is the last byte. **/
 #define StringRight(BLK, POS) (StringBuff(BLK)[StringLength(BLK) - POS])
 
@@ -191,8 +188,9 @@ HTS_STATIC char *StringBuffN_(String *blk, int size) {
     asserts SIZE fits the existing content; does not (re)allocate. **/
 #define StringSetLength(BLK, SIZE)                                             \
   do {                                                                         \
-    if (SIZE >= 0) {                                                           \
-      (BLK).length_ = SIZE;                                                    \
+    const int len__ = (SIZE); /* signed: negative means strlen(buffer_) */     \
+    if (len__ >= 0) {                                                          \
+      (BLK).length_ = len__;                                                   \
     } else {                                                                   \
       (BLK).length_ = strlen((BLK).buffer_);                                   \
     }                                                                          \
@@ -308,10 +306,11 @@ HTS_STATIC void StringAttach(String *blk, char **str) {
 #define StringCatN(BLK, STR, SIZE)                                             \
   do {                                                                         \
     const char *str__ = (STR);                                                 \
+    const size_t usize__ = (SIZE);                                             \
     if (str__ != NULL) {                                                       \
       size_t size__ = strlen(str__);                                           \
-      if (size__ > (SIZE)) {                                                   \
-        size__ = (SIZE);                                                       \
+      if (size__ > usize__) {                                                  \
+        size__ = usize__;                                                      \
       }                                                                        \
       StringMemcat(BLK, str__, size__);                                        \
     }                                                                          \

src/htstools.c

@@ -68,16 +68,6 @@ struct find_handle_struct {
   char path[2048];
 };
 #endif
-//#ifndef HTS_DEF_FWSTRUCT_topindex_chain
-//#define HTS_DEF_FWSTRUCT_topindex_chain
-//typedef struct topindex_chain topindex_chain;
-//#endif
-//struct topindex_chain {
-//  int level;                    /* sort level */
-//  char *category;               /* category */
-//  char name[2048];              /* path */
-//  struct topindex_chain *next;  /* next element */
-//};
 
 /* Tools */
 
@@ -293,7 +283,6 @@ int lienrelatif(char *s, size_t ssize, const char *link, const char *curr_fil) {
   char BIGSTK newcurr_fil[HTS_URLMAXSIZE * 2], newlink[HTS_URLMAXSIZE * 2];
   char *curr;
 
-  //int n=0;
   char *a;
   int slash = 0;
 
@@ -338,7 +327,6 @@ int lienrelatif(char *s, size_t ssize, const char *link, const char *curr_fil) {
     if (*curr == '/')
       curr++;
     l = link;
-    //c=curr;
     // couper ce qui est commun
     while((streql(*link, *curr)) && (*link != 0)) {
       link++;
@@ -350,8 +338,6 @@ int lienrelatif(char *s, size_t ssize, const char *link, const char *curr_fil) {
       link--;
       curr--;
     }
-    //if (*link=='/') link++;
-    //if (*curr=='/') curr++;
   }
 
   // calculer la profondeur du répertoire courant et remonter
@@ -362,7 +348,6 @@ int lienrelatif(char *s, size_t ssize, const char *link, const char *curr_fil) {
   while(*a)
     if (*(a++) == '/')
       strlcatbuff(s, "../", ssize);
-  //if (strlen(s)==0) strcatbuff(s,"/");
 
   if (slash)
     strlcatbuff(s, "/", ssize); // keep it absolute!

src/htsweb.c

@@ -639,8 +639,7 @@ int __cdecl htsshow_loop(t_hts_callbackarg * carg, httrackp * opt, lien_back * b
           for(_i = 0 + k; (_i < max(back_max * k, 1)) && (index < NStatsBuffer); _i++) {        // no lien
             int i = (back_index + _i) % back_max;       // commencer par le "premier" (l'actuel)
 
-            if (back[i].status >= 0) {  // signifie "lien actif"
-              // int ok=0;  // OPTI
+            if (back[i].status >= 0) { // signifie "lien actif"
               ok = 0;
               switch (j) {
               case 0:          // prioritaire

src/htswizard.c

@@ -80,6 +80,10 @@ htspair_t hts_detect_embed[] = {
   {NULL, NULL}
 };
 
+/* HTML5 media siblings of <img src>: same near-link treatment (#451) */
+static const htspair_t hts_detect_embed_html5[] = {
+    {"source", "src"}, {"source", "srcset"}, {"track", "src"}, {NULL, NULL}};
+
 /* Internal */
 static int hts_acceptlink_(httrackp * opt, int ptr, const char *adr,
                            const char *fil, const char *tag,
@@ -136,6 +140,17 @@ static int cmp_token(const char *tag, const char *cmp) {
           && !isalnum((unsigned char) tag[p]));
 }
 
+/* TRUE if (tag, attribute) matches an embedded-asset pair in the table */
+static hts_boolean is_embed_pair(const htspair_t *table, const char *tag,
+                                 const char *attribute) {
+  int i;
+  for (i = 0; table[i].tag != NULL; i++) {
+    if (cmp_token(tag, table[i].tag) && cmp_token(attribute, table[i].attr))
+      return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
 static int hts_acceptlink_(httrackp * opt, int ptr,
                            const char *adr, const char *fil, const char *tag,
                            const char *attribute, int *set_prio_to,
@@ -163,15 +178,9 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
   /* Built-in known tags (<img src=..>, ..) */
   if (forbidden_url != 0 && opt->nearlink && tag != NULL && attribute != NULL) {
-    int i;
-
-    for(i = 0; hts_detect_embed[i].tag != NULL; i++) {
-      if (cmp_token(tag, hts_detect_embed[i].tag)
-          && cmp_token(attribute, hts_detect_embed[i].attr)
-        ) {
-        embedded_triggered = 1;
-        break;
-      }
+    if (is_embed_pair(hts_detect_embed, tag, attribute) ||
+        is_embed_pair(hts_detect_embed_html5, tag, attribute)) {
+      embedded_triggered = 1;
     }
   }
 
@@ -179,12 +188,10 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
   /* Doit-on traiter les non html? */
   if ((opt->getmode & HTS_GETMODE_NONHTML) == 0) { // non on ne doit pas
-    if (!ishtml(opt, fil)) {    // non il ne faut pas
-      //adr[0]='\0';    // ne pas traiter ce lien, pas traiter
+    if (!ishtml(opt, fil)) {                       // non il ne faut pas
       forbidden_url = 1;        // interdire récupération du lien
       hts_log_print(opt, LOG_DEBUG, "non-html file ignored at %s : %s", adr,
                     fil);
-
     }
   }
 
@@ -343,7 +350,6 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
   } else {                      // adresse différente, sortir?
 
-    //if (!opt->wizard) {    // mode non wizard
     // doit-on traiter ce lien?.. vérifier droits de sortie
     switch ((opt->travel & HTS_TRAVEL_SCOPE_MASK)) {
     case HTS_TRAVEL_SAME_ADDRESS:
@@ -371,7 +377,6 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
       if ((i > 0) && (j > 0)) {
         if (!strfield2(adr + i, urladr() + j)) { // !=
           if (!opt->wizard) {                    // mode non wizard
-            // printf("refused: %s\n",adr);
             forbidden_url = 1; // pas même domaine
             hts_log_print(opt, LOG_DEBUG, "foreign domain link canceled: %s%s",
                           adr, fil);
@@ -399,7 +404,6 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
       if ((i > 0) && (j > 0)) {
         if (!strfield2(adr + i, urladr() + j)) { // !-
           if (!opt->wizard) {                    // mode non wizard
-            // printf("refused: %s\n",adr);
             forbidden_url = 1; // pas même .xx
             hts_log_print(opt, LOG_DEBUG,
                           "foreign location link canceled: %s%s", adr, fil);
@@ -430,7 +434,6 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
   // récupérer les liens à côtés d'un lien (nearlink) (nvelle pos)
   if (forbidden_url != 0 && opt->nearlink) {
     if (!ishtml(opt, fil)) {    // non html
-      //printf("ok %s%s\n",ad,fil);
       forbidden_url = 0;        // autoriser
       may_set_prio_to = 1 + 1;  // set prio to 1 (parse but skip urls) if near is the winner
       hts_log_print(opt, LOG_DEBUG, "near link authorized: %s%s", adr, fil);
@@ -878,7 +881,6 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
         }
       }
     }
-    //adr[0]='\0';  // cancel
   }
   // -------------------- FINAL PHASE --------------------
   // Test if the "Near" test won

src/htszlib.c

@@ -47,48 +47,89 @@ Please visit our Website: http://www.httrack.com
 */
 
 /*
-  Unpack file into a new file
+  Unpack file into a new file (gzip, zlib RFC1950 or raw deflate RFC1951).
   Return value: size of the new file, or -1 if an error occurred
 */
 /* Note: utf-8 */
 int hts_zunpack(char *filename, char *newfile) {
   int ret = -1;
 
-  if (filename != NULL && newfile != NULL) {
-    if (filename[0] && newfile[0]) {
-      char catbuff[CATBUFF_SIZE];
-      FILE *const in = FOPEN(fconv(catbuff, sizeof(catbuff), filename), "rb");
-      const int fd = in != NULL ? fileno(in) : -1;
-      const int dup_fd = fd != -1 ? dup(fd) : -1;
-      // Note: we must dup to be able to flose cleanly.
-      const gzFile gz = dup_fd != -1 ? gzdopen(dup_fd, "rb") : NULL;
+  if (filename != NULL && newfile != NULL && filename[0] && newfile[0]) {
+    char catbuff[CATBUFF_SIZE];
+    FILE *const in = FOPEN(fconv(catbuff, sizeof(catbuff), filename), "rb");
 
-      if (gz) {
-        FILE *const fpout = FOPEN(fconv(catbuff, sizeof(catbuff), newfile), "wb");
-        int size = 0;
+    if (in != NULL) {
+      unsigned char BIGSTK inbuf[8192];
+      size_t navail = fread(inbuf, 1, sizeof(inbuf), in);
+      /* gzip/zlib headers -> +32 windowBits; else raw deflate (RFC1951) */
+      const hts_boolean wrapped =
+          (navail >= 2 &&
+           ((inbuf[0] == 0x1f && inbuf[1] == 0x8b) ||
+            ((inbuf[0] & 0x0f) == Z_DEFLATED &&
+             (((unsigned) inbuf[0] << 8 | inbuf[1]) % 31) == 0)));
+      int attempt;
 
-        if (fpout) {
-          int nr;
+      /* deflate is ambiguous; on failure retry with the other windowBits */
+      for (attempt = 0; attempt < 2 && ret < 0; attempt++) {
+        const int windowBits =
+            (attempt == 0 ? wrapped : !wrapped) ? (32 + MAX_WBITS) : -MAX_WBITS;
+        FILE *fpout;
+        z_stream strm;
 
-          do {
-            char BIGSTK buff[1024];
-
-            nr = gzread(gz, buff, sizeof(buff));
-            if (nr > 0) {
-              size += nr;
-              if (fwrite(buff, 1, nr, fpout) != nr)
-                nr = size = -1;
-            }
-          } while(nr > 0);
+        if (attempt > 0) {
+          /* rewind input; reopening fpout "wb" discards the partial output */
+          if (fseek(in, 0, SEEK_SET) != 0)
+            break;
+          navail = fread(inbuf, 1, sizeof(inbuf), in);
+        }
+        fpout = FOPEN(fconv(catbuff, sizeof(catbuff), newfile), "wb");
+        if (fpout == NULL)
+          break;
+        memset(&strm, 0, sizeof(strm));
+        if (inflateInit2(&strm, windowBits) != Z_OK) {
           fclose(fpout);
-        } else
-          size = -1;
-        gzclose(gz);
-        ret = (int) size;
-      }
-      if (in != NULL) {
-        fclose(in);
+          break;
+        }
+        {
+          hts_boolean ok = HTS_TRUE;
+          int size = 0;
+          int zerr = Z_OK;
+
+          /* chunked inflate; first chunk in inbuf, single member */
+          do {
+            strm.next_in = inbuf;
+            strm.avail_in = (uInt) navail;
+            do {
+              unsigned char BIGSTK outbuf[8192];
+              size_t produced;
+
+              strm.next_out = outbuf;
+              strm.avail_out = sizeof(outbuf);
+              zerr = inflate(&strm, Z_NO_FLUSH);
+              if (zerr == Z_NEED_DICT || zerr == Z_DATA_ERROR ||
+                  zerr == Z_MEM_ERROR || zerr == Z_STREAM_ERROR) {
+                ok = HTS_FALSE;
+                break;
+              }
+              produced = sizeof(outbuf) - strm.avail_out;
+              if (produced > 0 &&
+                  fwrite(outbuf, 1, produced, fpout) != produced) {
+                ok = HTS_FALSE;
+                break;
+              }
+              size += (int) produced;
+            } while (strm.avail_out == 0);
+            if (!ok || zerr == Z_STREAM_END)
+              break;
+            navail = fread(inbuf, 1, sizeof(inbuf), in);
+          } while (navail > 0);
+          if (ok && zerr == Z_STREAM_END)
+            ret = size;
+        }
+        inflateEnd(&strm);
+        fclose(fpout);
       }
+      fclose(in);
     }
   }
   return ret;

src/htszlib.h

@@ -36,7 +36,6 @@ Please visit our Website: http://www.httrack.com
 
 /* ZLib */
 #include "zlib.h"
-//#include "zutil.h"
 
 /* MiniZip */
 #include "minizip/zip.h"

src/httrack.c

@@ -54,7 +54,6 @@ static int linput(FILE * fp, char *s, int max);
 #include "htswrap.h"
 
 /* specific definitions */
-//#include "htsbase.h"
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -454,8 +453,7 @@ static int __cdecl htsshow_loop(t_hts_callbackarg * carg, httrackp * opt, lien_b
           for(_i = 0 + k; (_i < max(back_max * k, 1)) && (index < NStatsBuffer); _i++) {        // no lien
             int i = (back_index + _i) % back_max;       // commencer par le "premier" (l'actuel)
 
-            if (back[i].status >= 0) {  // signifie "lien actif"
-              // int ok=0;  // OPTI
+            if (back[i].status >= 0) { // signifie "lien actif"
               ok = 0;
               switch (j) {
               case 0:          // prioritaire
@@ -773,28 +771,7 @@ static void sig_finish(int code) {      // finir et quitter
   fprintf(stderr, "\nExit requested to engine (signal %d)\n", code);
 }
 
-#ifdef _WIN32
-#if 0
-static void sig_ask(int code) { // demander
-  char s[256];
-
-  signal(code, sig_term);       // quitter si encore
-  printf("\nQuit program/Interrupt/Cancel? (Q/I/C) ");
-  fflush(stdout);
-  scanf("%s", s);
-  if ((s[0] == 'y') || (s[0] == 'Y') || (s[0] == 'o') || (s[0] == 'O')
-      || (s[0] == 'q') || (s[0] == 'Q'))
-    exit(0);                    // quitter
-  else if ((s[0] == 'i') || (s[0] == 'I')) {
-    if (global_opt != NULL) {
-      // ask for stop
-      global_opt->state.stop = 1;
-    }
-  }
-  signal(code, sig_ask);        // remettre signal
-}
-#endif
-#else
+#ifndef _WIN32
 static void sig_doback(int blind);
 static void sig_back(int code) {        // ignorer et mettre en backing 
   if (global_opt != NULL && !global_opt->background_on_suspend) {
@@ -809,36 +786,6 @@ static void sig_back(int code) {        // ignorer et mettre en backing
   }
 }
 
-#if 0
-static void sig_ask(int code) { // demander
-  char s[256];
-
-  signal(code, sig_term);       // quitter si encore
-  printf
-    ("\nQuit program/Interrupt/Background/bLind background/Cancel? (Q/I/B/L/C) ");
-  fflush(stdout);
-  scanf("%s", s);
-  if ((s[0] == 'y') || (s[0] == 'Y') || (s[0] == 'o') || (s[0] == 'O')
-      || (s[0] == 'q') || (s[0] == 'Q'))
-    exit(0);                    // quitter
-  else if ((s[0] == 'b') || (s[0] == 'B') || (s[0] == 'a') || (s[0] == 'A'))
-    sig_doback(0);              // arrière plan
-  else if ((s[0] == 'l') || (s[0] == 'L'))
-    sig_doback(1);              // arrière plan
-  else if ((s[0] == 'i') || (s[0] == 'I')) {
-    if (global_opt != NULL) {
-      // ask for stop
-      printf("finishing pending transfers.. please wait\n");
-      global_opt->state.stop = 1;
-    }
-    signal(code, sig_ask);      // remettre signal
-  } else {
-    printf("cancel..\n");
-    signal(code, sig_ask);      // remettre signal
-  }
-}
-#endif
-
 static void sig_brpipe(int code) {      // treat if necessary
   signal(code, sig_brpipe);
 }
@@ -951,23 +898,12 @@ static void sig_leave(int code) {
 
 static void signal_handlers(void) {
 #ifdef _WIN32
-#if 0                           /* BUG366763 */
-  signal(SIGINT, sig_ask);      // ^C
-#else
   signal(SIGINT, sig_leave);    // ^C
-#endif
   signal(SIGTERM, sig_finish);  // kill <process>
 #else
-#if 0                           /* BUG366763 */
-  signal(SIGHUP, sig_back);     // close window
-#endif
   signal(SIGTSTP, sig_back);    // ^Z
   signal(SIGTERM, sig_finish);  // kill <process>
-#if 0                           /* BUG366763 */
-  signal(SIGINT, sig_ask);      // ^C
-#else
   signal(SIGINT, sig_leave);    // ^C
-#endif
   signal(SIGPIPE, sig_brpipe);  // broken pipe (write into non-opened socket)
   signal(SIGCHLD, sig_ignore);  // child change status
 #endif

src/proxy/proxytrack.c

@@ -250,13 +250,6 @@ static int gethost(const char *hostname, SOCaddr * server) {
     struct addrinfo hints;
 
     memset(&hints, 0, sizeof(hints));
-#if 0
-    if (IPV6_resolver == 1)     // V4 only (for bogus V6 entries)
-      hints.ai_family = PF_INET;
-    else if (IPV6_resolver == 2)        // V6 only (for testing V6 only)
-      hints.ai_family = PF_INET6;
-    else
-#endif
     hints.ai_family = PF_UNSPEC;
     hints.ai_socktype = SOCK_STREAM;
     hints.ai_protocol = IPPROTO_TCP;
@@ -340,12 +333,7 @@ int proxytrack_main(char *proxyAddr, int proxyPort, char *icpAddr, int icpPort,
   T_SOC socICP = smallserver_init(proxyAddr, icpPort, SOCK_DGRAM);
 
   if (soc != INVALID_SOCKET && socICP != INVALID_SOCKET) {
-    //char url[HTS_URLMAXSIZE * 2];
-    //char method[32];
-    //char data[32768];
 
-    //url[0] = method[0] = data[0] = '\0';
-    //
     printf("HTTP Proxy installed on %s:%d/\n", proxyAddr, proxyPort);
     printf("ICP Proxy installed on %s:%d/\n", icpAddr, icpPort);
 #ifndef _WIN32
@@ -497,6 +485,12 @@ static const char *GetHttpMessage(int statuscode) {
   case 417:
     return "Expectation Failed";
     break;
+  case 429:
+    return "Too Many Requests";
+    break;
+  case 451:
+    return "Unavailable For Legal Reasons";
+    break;
   case 500:
     return "Internal Server Error";
     break;
@@ -944,7 +938,6 @@ static void proxytrack_process_HTTP(PT_Indexes indexes, T_SOC soc_c) {
     char *command;
     char *proto;
     char *surl;
-    //int directHit = 0;
     int headRequest = 0;
     int listRequest = 0;
 
@@ -1086,10 +1079,8 @@ static void proxytrack_process_HTTP(PT_Indexes indexes, T_SOC soc_c) {
 
       /* Post-process request */
       if (link_has_authority(surl)) {
-        if (strncasecmp
-            (surl, "http://proxytrack/",
-             sizeof("http://proxytrack/") - 1) == 0) {
-          //directHit = 1;        /* Another direct hit hack */
+        if (strncasecmp(surl, "http://proxytrack/",
+                        sizeof("http://proxytrack/") - 1) == 0) {
         }
         StringCopy(url, surl);
       } else {
@@ -1110,7 +1101,6 @@ static void proxytrack_process_HTTP(PT_Indexes indexes, T_SOC soc_c) {
               toHit += 7;
             }
             /* Direct hit */
-            //directHit = 1;
             StringCopy(url, "");
             if (!link_has_authority(toHit))
               StringCat(url, "http://");
@@ -1121,7 +1111,6 @@ static void proxytrack_process_HTTP(PT_Indexes indexes, T_SOC soc_c) {
             const char *toHit = surl + sizeof("/proxytrack/") - 1;
 
             /* Direct hit */
-            //directHit = 1;
             StringCopy(url, "");
             if (!link_has_authority(toHit))
               StringCat(url, "http://");
@@ -1605,10 +1594,7 @@ static int proxytrack_start_ICP(PT_Indexes indexes, T_SOC soc) {
         unsigned char Opcode = buffer[0];
         unsigned char Version = buffer[1];
         unsigned short Message_Length = READ_NET16(&buffer[2]);
-        unsigned int Request_Number = READ_NET32(&buffer[4]);   /* Session ID */
-        //unsigned int Options = READ_NET32(&buffer[8]);
-        //unsigned int Option_Data = READ_NET32(&buffer[12]);     /* ICP_FLAG_SRC_RTT */
-        //unsigned int Sender_Host_Address = READ_NET32(&buffer[16]);     /* ignored */
+        unsigned int Request_Number = READ_NET32(&buffer[4]); /* Session ID */
         unsigned char *Payload = &buffer[20];
 
         buffer[bufferSize] = '\0';      /* Ensure payload is NULL terminated */

src/proxy/store.c

@@ -1035,7 +1035,6 @@ static PT_Element PT_ReadCache__New_u(PT_Index index_, const char *url,
       if (unzOpenCurrentFile(index->zFile) == Z_OK) {
         char headerBuff[8192 + 2];
         int readSizeHeader;
-        //int totalHeader = 0;
         int dataincache = 0;
 
         /* For BIG comments */
@@ -1074,9 +1073,8 @@ static PT_Element PT_ReadCache__New_u(PT_Index index_, const char *url,
               ZIP_READFIELD_STRING(line, value, "Last-Modified", r->lastmodified);      // last-modified
               ZIP_READFIELD_STRING(line, value, "Etag", r->etag);       // Etag
               ZIP_READFIELD_STRING(line, value, "Location", r->location);       // 'location' pour moved
-              ZIP_READFIELD_STRING(line, value, "Content-Disposition", r->cdispo);      // Content-disposition
-              //ZIP_READFIELD_STRING(line, value, "X-Addr", ..);            // Original address
-              //ZIP_READFIELD_STRING(line, value, "X-Fil", ..);            // Original URI filename
+              ZIP_READFIELD_STRING(line, value, "Content-Disposition",
+                                   r->cdispo); // Content-disposition
               ZIP_READFIELD_STRING(line, value, "X-Save", previous_save_);      // Original save filename
               if (line[0] != '\0') {
                 int len = r->headers ? ((int) strlen(r->headers)) : 0;
@@ -1090,8 +1088,7 @@ static PT_Element PT_ReadCache__New_u(PT_Index index_, const char *url,
                 strcat(r->headers, "\r\n");
               }
             }
-          } while(offset < readSizeHeader && !lineEof);
-          //totalHeader = offset;
+          } while (offset < readSizeHeader && !lineEof);
 
           /* Previous entry */
           if (previous_save_[0] != '\0') {
@@ -1202,7 +1199,6 @@ static PT_Element PT_ReadCache__New_u(PT_Index index_, const char *url,
                       strcpy(r->msg, "Cache Read Error : Read Data");
                     } else
                       *(r->adr + r->size) = '\0';
-                    //printf(">%s status %d\n",back[p].r->contenttype,back[p].r->statuscode);
                   } else {      // erreur
                     r->statuscode = STATUSCODE_INVALID;
                     strcpy(r->msg, "Cache Memory Error");
@@ -1484,14 +1480,12 @@ static int PT_LoadCache__Old(PT_Index index_, const char *filename) {
               a += cache_brstr(a, firstline);
               strcpy(cache->lastmodified, firstline);
             } else {
-              // fprintf(opt->errlog,"Cache: version 1.%d not supported, ignoring current cache"LF,cache->version);
               fclose(cache->dat);
               cache->dat = NULL;
               free(use);
               use = NULL;
             }
-          } else {              // non supporté
-            // fspc(opt->errlog,"error"); fprintf(opt->errlog,"Cache: %s not supported, ignoring current cache"LF,firstline);
+          } else { // non supporté
             fclose(cache->dat);
             cache->dat = NULL;
             free(use);
@@ -1500,7 +1494,6 @@ static int PT_LoadCache__Old(PT_Index index_, const char *filename) {
           /* */
         } else {                // Vieille version du cache
           /* */
-          // hts_log_print(opt, LOG_WARNING, "Cache: importing old cache format");
           cache->version = 0;   // cache 1.0
           strcpy(cache->lastmodified, firstline);
         }

tests/01_engine-charset.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # charset -> UTF-8 conversion (hts_convertStringToUTF8).
-# -#3 <charset> <string> prints the string re-decoded from <charset> as UTF-8.
+# -#test=charset <charset> <string> prints the string re-decoded from <charset> as UTF-8.
 conv() {
-    test "$(httrack -O /dev/null -#3 "$1" "$2")" == "$3" || exit 1
+    test "$(httrack -O /dev/null -#test=charset "$1" "$2")" == "$3" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#3 "$1" "$2" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#test=charset "$1" "$2" >/dev/null 2>&1 || exit 1
 }
 
 # the source bytes below are UTF-8 (this file is UTF-8); "café" is 0x63 61 66 C3 A9.
@@ -31,7 +31,7 @@ conv 'us-ascii' 'hello' 'hello'
 # unknown charset: ASCII passes through unchanged, but non-ASCII input cannot be
 # decoded and yields empty output (an error is printed to stderr).
 conv 'no-such-charset-xyz' 'abc' 'abc'
-test "$(httrack -O /dev/null -#3 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
+test "$(httrack -O /dev/null -#test=charset 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
 
 # malformed UTF-8 (lone continuation byte, truncated lead byte) must not crash
 runs 'utf-8' $'\x80'

tests/01_engine-cmdline.test

@@ -90,4 +90,16 @@ refused "dangling-quote argument not refused cleanly"
 run_only "$tmp/q-lone" '"'
 refused "lone-quote argument not refused cleanly"
 
+# --pause (#185): valid MIN[:MAX] accepted; malformed, reversed, over-range and
+# non-finite values refused cleanly. NaN defeats naive `<`/`>` checks (it
+# compares false to everything), so it must not slip through to the int cast.
+run "$tmp/pause-ok" --pause 0.2:0.4
+accepted "$tmp/pause-ok" "#185: valid --pause range rejected"
+run "$tmp/pause-fix" --pause 0.2
+accepted "$tmp/pause-fix" "#185: valid fixed --pause rejected"
+for bad in nan nan:5 5:nan inf 10:5 99999; do
+    run "$tmp/pause-bad" --pause "$bad"
+    refused "#185: invalid --pause '$bad' not refused cleanly"
+done
+
 exit 0

tests/01_engine-cookies.test

@@ -1,14 +1,15 @@
 #!/bin/bash
 #
 # Issue #151 guard: the request Cookie header must be bare RFC 6265 name=value
-# pairs, no $Version/$Path attributes. Driven by the 'httrack -#Q' selftest.
+# pairs, no $Version/$Path attributes. Driven by the 'httrack -#test=cookies' selftest.
 
 set -eu
 
-# A trailing token is required; a bare '-#Q' falls through to the usage screen.
-out=$(httrack -#Q run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=cookies run)
 
-# Exact-match the success line so a fall-through to usage can't pass the test.
+# Exact-match the success line so a renamed/removed test (it prints the registry
+# to stderr) can't pass.
 test "$out" = "cookie-header: OK" || {
     echo "expected 'cookie-header: OK', got: $out" >&2
     exit 1

tests/01_engine-copyopt.test

@@ -2,15 +2,16 @@
 #
 # Regression guard for the unsigned-enum sentinel trap: copy_htsopt's
 # `if (from->X > -1)` guard is always false for unsigned hts_boolean fields, so
-# they silently stop being copied. Driven by the in-process 'httrack -#9' test.
+# they silently stop being copied. Driven by the in-process 'httrack -#test=copyopt' test.
 # Keep POSIX-portable (harness runs it via $(BASH), a plain /bin/sh on macOS).
 
 set -eu
 
-# A trailing token is required; a bare '-#9' falls through to the usage screen.
-out=$(httrack -#9 run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=copyopt run)
 
-# Exact-match the success line so a fall-through to usage can't pass the test.
+# Exact-match the success line so a renamed/removed test (it prints the registry
+# to stderr) can't pass.
 test "$out" = "copy-htsopt: OK" || {
     echo "expected 'copy-htsopt: OK', got: $out" >&2
     exit 1

tests/01_engine-dns.test

@@ -5,9 +5,8 @@ set -euo pipefail
 
 # DNS resolver/cache self-test: a mock getaddrinfo (no network) checks address
 # family, single-address selection, the -@i4/-@i6 family filter, and cache reuse.
-# The trailing token is required, like the other -# selftests, so a bare command
-# line isn't treated as "no arguments" and routed to the usage screen.
-out=$(httrack -#D run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=dns run)
 
 test "$out" = "dns-selftest: OK" || {
     echo "expected 'dns-selftest: OK', got: $out" >&2

tests/01_engine-entities.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # HTML entity unescaping (hts_unescapeEntitiesWithCharset).
-# -#6 <string> prints the string with entities decoded (UTF-8 output).
+# -#test=entities <string> prints the string with entities decoded (UTF-8 output).
 ent() {
-    test "$(httrack -O /dev/null -#6 "$1")" == "$2" || exit 1
+    test "$(httrack -O /dev/null -#test=entities "$1")" == "$2" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#6 "$1" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#test=entities "$1" >/dev/null 2>&1 || exit 1
 }
 
 # named entities
@@ -18,6 +18,21 @@ ent '&amp;' '&'
 ent '&lt;&gt;' '<>'
 ent '&eacute;' 'é'
 
+# HTML5 names from the WHATWG set
+ent '&hellip;' '…'
+ent '&bigcup;' '⋃'
+# longest name (31 chars) exercises the name-length cap
+ent '&CounterClockwiseContourIntegral;' '∳'
+# astral codepoint -> 4-byte UTF-8
+ent '&Aopf;' '𝔸'
+# multi-codepoint refs are skipped at generation, so left verbatim
+ent '&fjlig;' '&fjlig;'
+
+# common HTML4 names still decode (regression guard against accidental drops)
+ent '&copy;&reg;&trade;' '©®™'
+ent '&mdash;&ndash;' '—–'
+ent '&alpha;&beta;' 'αβ'
+
 # numeric: decimal and hex
 ent '&#65;&#66;' 'AB'
 ent '&#x41;' 'A'

tests/01_engine-escape-room.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# HT_ADD_HTMLESCAPED* must reserve the escaper's worst case (6 for _full).
+httrack -O /dev/null -#test=escape-room run | grep -q "escape-room self-test OK"

tests/01_engine-filelist.test

@@ -0,0 +1,65 @@
+#!/bin/bash
+#
+# -%L URL-list loading (#49): a readable list is honored; an unusable one fails
+# with the reason (errno / not-a-regular-file), not a bare "Could not include
+# URL list". Offline: file:// fixture, no server. Asserts on httrack's own
+# strings and the message shape, so it is locale-independent.
+
+set -euo pipefail
+
+tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_filelist.XXXXXX") || exit 1
+trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+
+echo '<html><body>hi</body></html>' >"$tmp/index.html"
+
+# run httrack with the given -%L target; structured log lands in $out/hts-log.txt
+run() {
+    local out="$1" list="$2"
+    rm -rf "$out"
+    mkdir -p "$out"
+    httrack -O "$out" --quiet -n "-%L" "$list" >"$out/.stdout" 2>&1 || true
+    LOG="$out/hts-log.txt"
+}
+
+fail() {
+    echo "FAIL: $1"
+    cat "$LOG"
+    exit 1
+}
+loghas() {
+    grep -Eq "$1" "$LOG" || fail "expected /$1/ in $LOG"
+}
+lognot() {
+    if grep -Eq "$1" "$LOG"; then fail "unexpected /$1/ in $LOG"; fi
+}
+
+# readable list: its one URL is loaded and counted (count must be non-zero)
+printf 'file://%s/index.html\n' "$tmp" >"$tmp/urls.txt"
+run "$tmp/ok" "$tmp/urls.txt"
+loghas '[1-9][0-9]* links added from'
+
+# missing file: quoted name + a non-empty reason, never the old reasonless
+# "Could not include URL list: <name>". The reason is the stat() errno, not the
+# directory fallback literal (guards against dropping the errno lookup).
+run "$tmp/miss" "$tmp/nope.txt"
+loghas 'Could not include URL list "[^"]+": .+'
+lognot 'Could not include URL list: '
+lognot 'not a regular file'
+
+# a directory is rejected with our own reason (locale-independent)
+mkdir -p "$tmp/adir"
+run "$tmp/dir" "$tmp/adir"
+loghas 'Could not include URL list "[^"]+": not a regular file'
+
+# unreadable regular file: the fopen() errno arm fires, distinct from the
+# directory branch. Root bypasses mode 000, so skip it there.
+if test "$(id -u)" -ne 0; then
+    : >"$tmp/noperm.txt"
+    chmod 000 "$tmp/noperm.txt"
+    run "$tmp/perm" "$tmp/noperm.txt"
+    chmod 644 "$tmp/noperm.txt"
+    loghas 'Could not include URL list "[^"]+": .+'
+    lognot 'not a regular file'
+fi
+
+exit 0

tests/01_engine-filter.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # wildcard filter engine (strjoker), the core of +/- include/exclude rules.
-# -#0 <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
+# -#test=filter <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
 
 match() {
-    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does match $1" || exit 1
+    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does match $1" || exit 1
 }
 nomatch() {
-    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does NOT match $1" || exit 1
+    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does NOT match $1" || exit 1
 }
 
 # bare star matches everything
@@ -50,24 +50,75 @@ match '*foo*bar' 'foozbar'
 # '?' is the query-string marker, not a single-char wildcard
 nomatch 'a?c' 'abc'
 
-# backslash escapes a metacharacter inside a class so it is matched literally.
-# Quirk: the decoder also adds the backslash itself to the set, so '\X' matches
-# both X and '\'. These assertions pin that behavior.
+# Inside a class, backslash escapes the next char as a literal member (#148):
+# '\X' matches X only (not '\'), and an escaped ']' is a member, not the terminator.
 match '*[\*]' '*'
-match '*[\*]' "\\"
-nomatch '*[\*]' 'a'
+nomatch '*[\*]' "\\"
 match '*[\\]' "\\"
-nomatch '*[\\]' 'a'
+nomatch '*[\\]' '*'
 match '*[\[]' '['
-match '*[\[]' "\\"
-nomatch '*[\[]' 'a'
+nomatch '*[\[]' "\\"
+match '*[\]]' ']'
+nomatch '*[\]]' "\\"
 
-# A literal ']' cannot be a class member: the class parser stops at the first
-# ']', escaped or not. So '*[\[\]]' does NOT mean "the [ or ] character" as the
-# filter guide claims (GitHub #148); it parses as the class {'[','\'} followed
-# by a trailing literal ']'. These assertions document the current (buggy)
-# behavior so any future matcher fix is a deliberate, visible change.
-nomatch '*[\[\]]' '[' # not matched, despite the docs
-match '*[\[\]]' ']'   # only via the empty class-match + trailing ']'
-match '*[\[\]]' '[]'  # one of {'[','\'} then the trailing ']'
-nomatch '*[\[\]]' '[]x'
+# '*[\[\]]' is "the [ or ] character", as the filter guide documents.
+match '*[\[\]]' '['
+match '*[\[\]]' ']'
+nomatch '*[\[\]]' 'a'
+match '*[\[,\]]' '[' # comma between members is optional
+match '*[\[,\]]' ']'
+match '*[a,\[]' 'a' # an escaped member no longer eats the preceding one
+match '*[a,\[]' '['
+
+# Escape is decoded before the range/separator/size checks, so '\-' '\,' '\<'
+# are literal members, not operators.
+match '*[a\-z]' 'a'
+match '*[a\-z]' 'z'
+nomatch '*[a\-z]' 'b' # not the a..z range
+match '*[\,]' ','
+nomatch '*[\,]' "\\" # the escape must not leak '\' into the class
+match '*[\<]' '<'
+nomatch '*[\<]' "\\"
+match '*[\[,\],a]' '['
+match '*[\[,\],a]' ']'
+match '*[\[,\],a]' 'a'
+
+# A truncated range '*[a-' is the literal members {a,-}; the parser must not
+# read past the end decoding it (was a 1-byte heap over-read in the range arm).
+match '*[a-' 'a'
+nomatch '*[a-' 'b'
+
+# *(...) matches exactly one char from the class; *[...] matches a run.
+match '*(a,b)' 'a'
+nomatch '*(a,b)' 'aa'
+nomatch '*(a,b)' 'c'
+
+# documented composite filters (filters.html)
+match 'www.*[path].com/*[path].zip' 'www.foo.com/a/b.zip'
+nomatch 'www.*[path].com/*[path].zip' 'www.foo.com/a/b.tar'
+match '*.html*[]' 'page.html'
+nomatch '*.html*[]' 'page.html?x=1' # *[] forbids the trailing query
+
+# Size-based rules (-#test=filtersize <size> <string> <filter...>): a negative size
+# means the size is still unknown (scan time). A size exclusion must stay neutral
+# then, so the file is fetched and only cancelled once its size is known (#143).
+fsize() {
+    local want="$1"
+    shift
+    test "$(httrack -O /dev/null -#test=filtersize "$@")" == "$want" || exit 1
+}
+fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # scan time: keep
+fsize 'verdict=forbidden size_flag=1' 5 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'  # <10KB: cancel
+fsize 'verdict=allowed size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # >=10KB: keep
+fsize 'verdict=forbidden size_flag=0' -1 foo.txt -* '+*.jpg' '-*.jpg*[<10]' # not a jpg
+# the '>' operator is just as neutral at scan time, and fires once size is known
+fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[>10]'   # scan time: keep
+fsize 'verdict=forbidden size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[>10]' # >10KB: cancel
+
+# [name]/[file]/[path] never span '?' mid-string; a trailing query is still
+# tolerated by the global '?' rule (same as plain *.aspx), not the class (#144).
+nomatch '*[path]/end' 'a?b/end'
+nomatch '*[file]end' 'foo?xend'
+nomatch '*[name]X' 'abc?X'
+match '*[file]' 'foo?x=1' # trailing query: tolerated, as for *.aspx
+match '*.aspx' 'page.aspx?y=2'

tests/01_engine-ftp-line.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# get_ftp_line bounds a hostile CRLF-less FTP reply into its 1024-byte buffer.
+httrack -O /dev/null -#test=ftp-line run | grep -q "ftp-line self-test OK"

tests/01_engine-ftp-userpass.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# ftp_split_userpass bounds an over-long user:pass@ from a hostile ftp:// URL.
+httrack -O /dev/null -#test=ftp-userpass run | grep -q "ftp-userpass self-test OK"

tests/01_engine-hashtable.test

@@ -3,5 +3,7 @@
 
 set -euo pipefail
 
-# httrack internal hashtable autotest on 100K keys
-httrack -#7 100000
+# httrack internal hashtable autotest on 100K keys. Assert the success line (on
+# stderr) so a misrouted registry entry can't pass on exit code alone.
+out=$(httrack -#test=hashtable 100000 2>&1)
+printf '%s\n' "$out" | grep -q "all hashtable tests were successful!" || exit 1

tests/01_engine-header.test

@@ -0,0 +1,29 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# Response header-line parsing (treathead via -#test=header <raw-line> ...).
+# Isolates the wire layer from url_savename, which strips traversal on its own.
+
+hdr() {
+    local want="$1"
+    shift
+    out="$(httrack -O /dev/null -#test=header "$@" | grep '^contenttype=')"
+    test "$out" == "$want" || {
+        echo "FAIL: $* -> '$out' (want '$want')"
+        exit 1
+    }
+}
+
+hdr 'contenttype=application/pdf cdispo=' 'Content-Type: application/pdf'
+
+# filename= is honored quoted or bare.
+hdr 'contenttype= cdispo=report.pdf' \
+    'Content-Disposition: attachment; filename="report.pdf"'
+hdr 'contenttype= cdispo=report.pdf' \
+    'Content-Disposition: attachment; filename=report.pdf'
+
+# Path components in the filename are dropped on the wire (RFC 2616).
+hdr 'contenttype= cdispo=evil.pdf' \
+    'Content-Disposition: attachment; filename="../../evil.pdf"'

tests/01_engine-idna.test

@@ -3,13 +3,13 @@
 
 set -euo pipefail
 
-# IDNA / punycode encode (-#4) and decode (-#5). This code has a CVE history,
+# IDNA / punycode encode (-#test=idna-encode) and decode (-#test=idna-decode). This code has a CVE history,
 # so the edge cases below cover passthrough, round-trips, and malformed input.
 
-enc() { test "$(httrack -O /dev/null -#4 "$1")" == "$2" || exit 1; }
-dec() { test "$(httrack -O /dev/null -#5 "$1")" == "$2" || exit 1; }
+enc() { test "$(httrack -O /dev/null -#test=idna-encode "$1")" == "$2" || exit 1; }
+dec() { test "$(httrack -O /dev/null -#test=idna-decode "$1")" == "$2" || exit 1; }
 # crash probe: malformed ACE input must exit cleanly, not abort.
-runs() { httrack -O /dev/null -#5 "$1" >/dev/null 2>&1 || exit 1; }
+runs() { httrack -O /dev/null -#test=idna-decode "$1" >/dev/null 2>&1 || exit 1; }
 
 # encode
 enc 'www.café.com' 'www.xn--caf-dma.com'

tests/01_engine-inplace-escape.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# inplace_escape_*() must match escape_*() on a copy: guards the shared helper.
+httrack -O /dev/null -#test=inplace-escape run | grep -q "inplace-escape self-test OK"

tests/01_engine-java.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# .class constant-pool count is capped to the file size (calloc DoS).
+httrack -O /dev/null -#test=java run | grep -q "java constant-pool cap self-test OK"

tests/01_engine-makeindex.test

@@ -0,0 +1,12 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# hts_finish_makeindex writes the footer and gates the refresh meta on a single
+# first link (guards the macro->function extraction).
+dir=$(mktemp -d)
+trap 'rm -rf "$dir"' EXIT
+
+httrack -O /dev/null -#test=makeindex "$dir" run |
+    grep -q "makeindex self-test OK"

tests/01_engine-mime.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # MIME type guessing from extension (get_httptype / give_mimext).
-# -#2 <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
+# -#test=mime <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
 
 mime() {
-    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is '$2'" || exit 1
+    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is '$2'" || exit 1
 }
 unknown() {
-    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
+    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
 }
 
 mime '/a/b.html' 'text/html'

tests/01_engine-parse.test

@@ -106,8 +106,6 @@ grep -Eq 'srcset="j\.gif 2x"' "$saved" ||
 # inline style attribute, with the URL unquoted, double-quoted and single-quoted
 # (the quote style is preserved on rewrite). No-detect attributes (title, alt,
 # ...) are left untouched. Asserted by rewrite (deterministic), not download.
-# data-* (#201/#203) is omitted: its detection is currently nondeterministic and
-# can't be locked yet.
 site2="$tmp/attrs"
 mkdir -p "$site2"
 for f in xl ibg ibgs cex cexd cexs tt; do gif "$site2/$f.gif"; done
@@ -323,4 +321,93 @@ grep -Fq 'href="ahref%20(4).gif"' "$saved9" ||
 ! grep -Eq '(src|href)="[^"]*%28' "$saved9" ||
     ! echo "FAIL #163: gate over-fired onto a non-url() attribute link" || exit 1
 
+# HTML5 <source>/<track> follow as embedded near-links past the -r2 depth boundary (#451).
+# img.gif positive control; plain.gif (bare <a href>) negative control proves the gate is selective.
+site10="$tmp/html5media"
+mkdir -p "$site10"
+for f in img ss plain; do gif "$site10/$f.gif"; done
+printf 'x' >"$site10/v.webm"
+printf 'x' >"$site10/subs.vtt"
+cat >"$site10/index.html" <<EOF
+<html><body><a href="leaf.html">leaf</a></body></html>
+EOF
+cat >"$site10/leaf.html" <<EOF
+<html><body>
+<img src="img.gif">
+<picture><source srcset="ss.gif 2x"></picture>
+<video><source src="v.webm"></video>
+<video><track src="subs.vtt"></video>
+<a href="plain.gif">plain link past the boundary</a>
+</body></html>
+EOF
+out10="$tmp/html5media-out"
+rm -rf "$out10"
+mkdir -p "$out10"
+httrack "file://$site10/index.html" -O "$out10" --quiet --near -r2 >"$out10/.log" 2>&1 || true
+found "img.gif" "$out10"
+found "ss.gif" "$out10"
+found "v.webm" "$out10"
+found "subs.vtt" "$out10"
+notfound "plain.gif" "$out10"
+
+# Unknown-attr (data-*) URLs (#201/#203): the script automaton state must reset at
+# </script>, or detection dies for the rest of the page after the first script.
+site11="$tmp/dataattr"
+mkdir -p "$site11"
+for f in pre post mid spdata handler handler2 jsdecoy jsdecoy2 nodecoy \
+    spalt glalt spxml jtail1 jtail2 textdecoy tagdecoy phantom; do gif "$site11/$f.gif"; done
+cat >"$site11/index.html" <<EOF
+<html><body>
+<img data-pre="file://$site11/pre.gif">
+<script>var x = 1;</script>
+<img data-post="file://$site11/post.gif">
+<img data-mid="file://$site11/mid.gif" alt="mid-tag attr, no delimiter after">
+<img data-sp = "file://$site11/spdata.gif" q=1>
+<img alt="nodecoy.gif" src="pre.gif">
+<img alt = "spalt.gif" id=x>
+<img src="pre.gif"alt="glalt.gif" id=x>
+<p xmlns:bar = "spxml.gif" id=x></p>
+<div data-json='["jtail1.gif","jtail2.gif"]' q=1></div>
+<p>t = "textdecoy.gif" q</p>
+<img ="tagdecoy.gif" q>
+<a onclick='q = 1; "h1'>x</a>
+<img data-h1="file://$site11/handler.gif">
+<a onclick='w = 1; "h2>x</a>
+<img data-h2="file://$site11/handler2.gif">
+<script>var s; s = 1; "jsdecoy.gif";</script>
+<script>var s2 = "jsdecoy2.gif" x;</script>
+<script>var f = "</script>
+<img alt="y" "phantom.gif">
+</body></html>
+EOF
+out11="$tmp/dataattr-out"
+crawl "$site11/index.html" "$out11"
+saved11=$(savedhtml "$out11")
+test -n "$saved11" || ! echo "FAIL: saved dataattr page not found" || exit 1
+grep -Fq 'data-pre="pre.gif"' "$saved11" ||
+    ! echo "FAIL #201: data-* URL before any script not detected/rewritten" || exit 1
+grep -Fq 'data-post="post.gif"' "$saved11" ||
+    ! echo "FAIL #201: data-* URL after a script not detected (state leak)" || exit 1
+grep -Fq 'data-mid="mid.gif"' "$saved11" ||
+    ! echo "FAIL #201: mid-tag data-* URL not detected" || exit 1
+grep -Fq 'data-sp = "spdata.gif"' "$saved11" ||
+    ! echo "FAIL #201: spaced-= data-* URL not detected" || exit 1
+found "handler.gif" "$out11"  # automaton reset at the handler-terminator exit
+found "handler2.gif" "$out11" # ... and at the '>' exit of an unterminated handler
+# a JS string not preceded by =/(/, is still ignored after the reset
+notfound "jsdecoy.gif" "$out11"
+# in-script, the strict follower gate still applies (intag is 1 in script bodies)
+notfound "jsdecoy2.gif" "$out11"
+# no-detect attrs stay exempt, incl. spaced-'=' and glued-attr forms
+notfound "nodecoy.gif" "$out11"
+notfound "spalt.gif" "$out11"
+notfound "glalt.gif" "$out11"
+notfound "spxml.gif" "$out11"
+# not '='-preceded: comma-list tails and out-of-tag text tokens stay ignored
+notfound "jtail2.gif" "$out11"
+notfound "textdecoy.gif" "$out11"
+notfound "tagdecoy.gif" "$out11" # a '=' glued to the tag name is not an attr
+# a </script> inside a JS string must not cause phantom fetches later
+notfound "phantom.gif" "$out11"
+
 exit 0

tests/01_engine-pause.test

@@ -0,0 +1,15 @@
+#!/bin/bash
+#
+# --pause (#185): the inter-file pause target must stay in [min,max] and spread
+# across it (a per-call rand() would collapse it toward min). Driven by the
+# in-process 'httrack -#test=pause' test. POSIX-portable ($(BASH) is /bin/sh on macOS).
+
+set -eu
+
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=pause run)
+
+test "$out" = "pause: OK" || {
+    echo "expected 'pause: OK', got: $out" >&2
+    exit 1
+}

tests/01_engine-reconcile.test

@@ -0,0 +1,17 @@
+#!/bin/bash
+#
+# Cache generation reconcile policies (httrack -#test=reconcile <dir>):
+# promote a stranded old generation, keep the larger one after an aborted
+# run, and restore the old one when an update transferred nothing.
+
+set -eu
+
+dir=$(mktemp -d)
+trap 'rm -rf "$dir"' EXIT
+
+out=$(httrack -#test=reconcile "$dir")
+
+test "$out" = "cache-reconcile: OK" || {
+    echo "expected 'cache-reconcile: OK', got: $out" >&2
+    exit 1
+}

tests/01_engine-redirect.test

@@ -0,0 +1,9 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# #159: a redirect to a same-file alias (http<->https, user@host, ..) must be
+# followed through, not turned into a self-pointing "moved" stub. The decision
+# helper is exercised by the engine self-test.
+httrack -O /dev/null -#test=redirect-samefile run | grep -q "redirect-samefile self-test OK"

tests/01_engine-relative.test

@@ -8,7 +8,7 @@ set -euo pipefail
 # relative path from <curr>'s directory to <link>
 rel() {
     local got
-    got=$(httrack -O /dev/null -#l "$1" "$2")
+    got=$(httrack -O /dev/null -#test=relative "$1" "$2")
     test "$got" == "relative=$3" ||
         {
             echo "FAIL rel($1, $2): got '$got' want 'relative=$3'"
@@ -19,7 +19,7 @@ rel() {
 # resolve <link> against origin <adr>/<fil> -> adr=.. fil=..
 ident() {
     local got
-    got=$(httrack -O /dev/null -#i "$1" "$2" "$3")
+    got=$(httrack -O /dev/null -#test=resolve "$1" "$2" "$3")
     test "$got" == "$4" ||
         {
             echo "FAIL ident($1, $2, $3): got '$got' want '$4'"

tests/01_engine-robots.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# robots.txt RFC 9309 Allow/Disallow precedence (#452): longest match wins.
+httrack -O /dev/null -#test=robots run | grep -q "robots self-test OK"

tests/01_engine-savename.test

@@ -3,13 +3,38 @@
 
 set -euo pipefail
 
-# Local save-name extension resolution (url_savename via -#N <fil> <content-type>).
-# Asserts on the basename of "savename: <path>".
+# Local save-name resolution (url_savename via -#test=savename <fil> <content-type> [key=value ...]).
+# name() asserts on the basename, full() on the whole path; prior= registers an
+# already-crawled link whose sav is rooted under the -O path (/dev/null here).
+
+# resolve httrack before cd: make check puts a RELATIVE ../src on PATH
+httrack_bin=$(cd "$(dirname "$(command -v httrack)")" && pwd)/httrack
+
+# scratch dir: body= and cached= write temp files (st-savename-body.tmp, hts-cache/)
+scratch=$(mktemp -d)
+trap 'rm -rf "$scratch"' EXIT
+cd "$scratch"
+
+run() {
+    "$httrack_bin" -O /dev/null -#test=savename "$@" | sed -n 's/^savename: //p'
+}
 
 name() {
-    out="$(httrack -O /dev/null -#N "$1" "$2" | sed -n 's/^savename: //p')"
-    test "${out##*/}" == "$3" || {
-        echo "FAIL: '$1' '$2' -> '$out' (want '$3')"
+    local fil="$1" ctype="$2" want="$3"
+    shift 3
+    out="$(run "$fil" "$ctype" "$@")"
+    test "${out##*/}" == "$want" || {
+        echo "FAIL: '$fil' '$ctype' $* -> '$out' (want '$want')"
+        exit 1
+    }
+}
+
+full() {
+    local fil="$1" ctype="$2" want="$3"
+    shift 3
+    out="$(run "$fil" "$ctype" "$@")"
+    test "$out" == "$want" || {
+        echo "FAIL: '$fil' '$ctype' $* -> '$out' (want '$want')"
         exit 1
     }
 }
@@ -39,3 +64,95 @@ name '/types/data.json' 'application/json' 'data.json'
 
 # Agreeing type must not rewrite the extension's casing (no strip-and-reappend).
 name '/x.JPG' 'image/jpeg' 'x.JPG'
+
+# A Content-Disposition filename replaces the URL name outright.
+name '/x.php' 'application/pdf' 'report.pdf' cdispo=report.pdf
+name '/download' 'text/html' 'setup.exe' cdispo=setup.exe
+
+# Reserved characters in a hostile Content-Disposition name are sanitized.
+name '/x.php' 'application/pdf' 'set_up.exe' 'cdispo=set:up.exe'
+
+# The md5-of-query suffix lands inside a Content-Disposition name too.
+name '/x.php?id=1' 'application/pdf' 'report681a.pdf' cdispo=report.pdf
+
+# Still-downloading path (status=-1): mime drives the ext, cdispo is ignored
+# there (the deliberately unfolded 4th resolve_extension variant).
+name '/x.pdf' 'text/html' 'x.html' status=-1
+name '/x.html' 'text/html' 'x.html' status=-1
+name '/x.php' 'application/pdf' 'x.pdf' status=-1 cdispo=report.pdf
+
+# Contested type (wire disagrees with a specific ext): magic bytes proving the
+# extension right keep it, anything else trusts the wire as before.
+name '/photo.jpg' 'image/png' 'photo.jpg' body=hex:FFD8FFE000104A46
+name '/photo.jpg' 'image/png' 'photo.png' body=hex:89504E470D0A1A0A
+name '/photo.jpg' 'image/png' 'photo.png'
+name '/doc.pdf' 'text/html' 'doc.pdf' body=hex:255044462D312E34
+name '/doc.pdf' 'text/html' 'doc.html' 'body=<html><body>soft 404</body></html>'
+name '/style.css' 'image/png' 'style.png' 'body=body { }' # no rule for css: wire wins
+
+# A redirect answer resolves nothing: delayed placeholder name.
+name '/x.php' 'text/html' 'x.0.delayed' statuscode=301
+
+# Root and query-only URLs get index + the md5-of-query suffix.
+name '/' 'text/html' 'index.html'
+name '/?a=1' 'text/html' 'index3872.html'
+
+# Same URL crawled before: reuse its sav verbatim (case preserved).
+full '/X.PHP' 'text/html' 'www.example.com/CASE.HTML' \
+    'prior=www.example.com|/X.PHP|www.example.com/CASE.HTML'
+
+# Another URL owns the name: collision suffix -2, then -3, case-insensitively.
+name '/x.php' 'text/html' 'x-2.html' \
+    'prior=www.example.com|/other.html|/dev/null/www.example.com/x.html'
+name '/x.php' 'text/html' 'x-3.html' \
+    'prior=www.example.com|/o1.html|/dev/null/www.example.com/x.html' \
+    'prior=www.example.com|/o2.html|/dev/null/www.example.com/x-2.html'
+name '/INDEX.HTML' 'text/html' 'INDEX-2.HTML' \
+    'prior=www.example.com|/index.html|/dev/null/www.example.com/index.html'
+
+# Same basename in another directory is NOT a collision.
+name '/x.php' 'text/html' 'x.html' \
+    'prior=www.example.com|/sub/x.html|/dev/null/www.example.com/sub/x.html'
+
+# 8-3 modes: DOS truncates every component to 8+3, ISO9660 level 2 to 31.
+full '/directory-long/verylongfilename.html' 'text/html' \
+    '/dev/null/EXAMPLE/DIRECTOR/VERYLONG.HTM' n83=1
+full '/directory-long/verylongfilename.html' 'text/html' \
+    '/dev/null/EXAMPLE_C/DIRECTORY_LONG/VERYLONGFILENAME.HTM' n83=2
+name '/verylongfilename.php' 'text/html' 'VERYLO-2.HTM' n83=1 \
+    'prior=www.example.com|/other.html|/dev/null/EXAMPLE/VERYLONG.HTM'
+
+# urlhack dedup (#271): // collapse and www-strip map to the prior link's sav;
+# the per-feature negatives opt out and take a fresh name.
+full '/a//b.php' 'text/html' '/dev/null/www.example.com/a/PRIOR.html' \
+    'prior=www.example.com|/a/b.php|/dev/null/www.example.com/a/PRIOR.html'
+full '/a//b.php' 'text/html' '/dev/null/www.example.com/a/b.html' no-slash=1 \
+    'prior=www.example.com|/a/b.php|/dev/null/www.example.com/a/PRIOR.html'
+full '/w.php' 'text/html' '/dev/null/www.example.com/W-PRIOR.html' adr=example.com \
+    'prior=www.example.com|/w.php|/dev/null/www.example.com/W-PRIOR.html'
+full '/w.php' 'text/html' '/dev/null/example.com/w.html' adr=example.com no-www=1 \
+    'prior=www.example.com|/w.php|/dev/null/www.example.com/W-PRIOR.html'
+
+# Distinct URLs must stay distinct under urlhack (no over-normalization).
+full '/a//b.php' 'text/html' '/dev/null/www.example.com/a/b.html' \
+    'prior=www.example.com|/a/c.php|/dev/null/www.example.com/a/C-PRIOR.html'
+
+# --strip-query (#112): stripped key dedups onto the prior sav; without the
+# option the same URLs stay distinct.
+full '/page.php?id=3&sid=42' 'text/html' '/dev/null/www.example.com/PAGE-PRIOR.html' \
+    strip=sid 'prior=www.example.com|/page.php?id=3|/dev/null/www.example.com/PAGE-PRIOR.html'
+full '/page.php?id=3&sid=42' 'text/html' '/dev/null/www.example.com/page475b.html' \
+    'prior=www.example.com|/page.php?id=3|/dev/null/www.example.com/PAGE-PRIOR.html'
+
+# A kept key that differs must still block the dedup (no over-stripping).
+full '/page.php?id=3&sid=42' 'text/html' '/dev/null/www.example.com/page475b.html' \
+    strip=sid 'prior=www.example.com|/page.php?id=4|/dev/null/www.example.com/PAGE-PRIOR.html'
+
+# Hostile fils stay rooted under the mirror: ../ (raw or %2e-encoded) drops out,
+# control characters become spaces, oversized names cap at 210 chars (the cap
+# can chop the extension off entirely).
+full '/../../etc/passwd' 'text/html' '/dev/null/www.example.com///etc/passwd.html'
+full '/%2e%2e/%2e%2e/etc/passwd' 'text/html' '/dev/null/www.example.com///etc/passwd.html'
+full '/x.php' 'application/pdf' '/dev/null/www.example.com///evil.exe' 'cdispo=../../evil.exe'
+name $'/evil\rname\t.php' 'text/html' 'evil name .html'
+name "/$(printf 'a%.0s' {1..300}).php" 'text/html' "$(printf 'a%.0s' {1..210})"

tests/01_engine-selftest-dispatch.test

@@ -0,0 +1,17 @@
+#!/bin/bash
+#
+# The -#test dispatch itself: a bare -#test lists the registry, and an unknown
+# name errors (non-zero, diagnostic) instead of silently passing.
+
+set -eu
+
+# Bare -#test lists known tests (printed to stderr).
+list=$(httrack -#test 2>&1)
+printf '%s\n' "$list" | grep -q "filter" || exit 1
+printf '%s\n' "$list" | grep -q "cache-writefail" || exit 1
+
+# Unknown name: non-zero exit + diagnostic, and no test result line.
+rc=0
+err=$(httrack -#test=bogus 2>&1) || rc=$?
+test "$rc" -ne 0 || exit 1
+printf '%s\n' "$err" | grep -q "Unknown self-test" || exit 1

tests/01_engine-simplify.test

@@ -5,7 +5,7 @@ set -euo pipefail
 
 # path simplify engine (fil_simplifie): collapses ./ and ../ segments.
 simp() {
-    test "$(httrack -O /dev/null -#1 "$1")" == "simplified=$2" || exit 1
+    test "$(httrack -O /dev/null -#test=simplify "$1")" == "simplified=$2" || exit 1
 }
 
 simp './foo/bar/' 'foo/bar/'

tests/01_engine-sniff.test

@@ -0,0 +1,87 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# MIME magic consistency (-#test=sniff <content-type> <hex:..|text>), the
+# tie-break behind htsname's wire-vs-extension naming.
+
+chk() {
+    local mime="$1" body="$2" want="$3"
+    out="$(httrack -#test=sniff "$mime" "$body" | sed -n 's/^sniff: //p')"
+    test "$out" == "$want" || {
+        echo "FAIL: '$mime' '$body' -> '$out' (want '$want')"
+        exit 1
+    }
+}
+
+yes='known=1 consistent=1'
+no='known=1 consistent=0'
+unk='known=0 consistent=0'
+
+# images
+chk image/jpeg hex:FFD8FFE000104A46 "$yes"
+chk image/png hex:89504E470D0A1A0A "$yes"
+chk image/png hex:FFD8FFE000104A46 "$no" # jpeg bytes are not a png
+chk image/gif 'GIF89a' "$yes"
+chk image/bmp 'BMxxxx' "$yes"
+chk image/tiff hex:49492A00 "$yes"
+chk image/tiff hex:4D4D002A "$yes" # both endians
+chk image/x-icon hex:00000100 "$yes"
+chk image/x-icon hex:00000200 "$yes" # Windows cursor, spec maps to x-icon
+chk image/webp 'RIFFxxxxWEBPVP' "$yes"
+chk image/webp 'RIFFxxxxWAVE' "$no" # riff subtype discriminates
+chk image/avif hex:0000001C6674797061766966 "$yes"
+chk image/avif hex:0000001C6674797068656963 "$no" # heic brand is not avif
+chk image/heic hex:0000001C6674797068656963 "$yes"
+chk image/svg+xml '<svg xmlns="x">' "$yes"
+chk image/svg+xml $'\xef\xbb\xbf  <?xml version="1.0"?>' "$yes" # BOM+ws skip
+
+# audio / video
+chk audio/mpeg 'ID3xxx' "$yes"
+chk audio/mpeg hex:FFFB9000 "$yes" # bare frame sync
+chk audio/aac hex:FFF15080 "$yes"
+chk audio/flac 'fLaC' "$yes"
+chk audio/ogg hex:4F67675300 "$yes"
+chk audio/x-wav 'RIFFxxxxWAVE' "$yes"
+chk video/x-msvideo 'RIFFxxxxAVI ' "$yes"
+chk video/x-msvideo 'RIFFxxxxWAVE' "$no"
+chk video/mp4 hex:000000186674797069736F6D "$yes"
+chk video/webm hex:1A45DFA3 "$yes"
+chk video/mpeg hex:000001BA "$yes"
+chk video/x-ms-wmv hex:3026B2758E66CF11 "$yes"
+
+# archives; zip magic covers the office-container families
+chk application/zip hex:504B0304 "$yes"
+chk application/vnd.openxmlformats-officedocument.wordprocessingml.document hex:504B0304 "$yes"
+chk application/vnd.oasis.opendocument.text hex:504B0304 "$yes"
+chk application/msword hex:D0CF11E0A1B11AE1 "$yes"
+chk application/msword hex:504B0304 "$no" # legacy .doc is OLE, not zip
+chk application/x-gzip hex:1F8B08 "$yes"
+chk application/x-bzip2 'BZh9' "$yes"
+chk application/x-7z-compressed hex:377ABCAF271C "$yes"
+chk application/x-rar-compressed hex:526172211A07 "$yes"
+chk application/zstd hex:28B52FFD "$yes"
+chk application/x-tar "hex:$(printf '00%.0s' {1..257})7573746172" "$yes" # ustar at 257
+chk application/x-tar hex:7573746172 "$no"
+
+# documents, fonts, misc
+chk application/pdf '%PDF-1.7' "$yes"
+chk application/pdf '<html><body>soft 404</body></html>' "$no"
+chk application/postscript '%!PS-Adobe' "$yes"
+chk application/rtf '{\rtf1' "$yes"
+chk font/woff2 'wOF2' "$yes"
+chk font/otf 'OTTO' "$yes"
+chk font/ttf hex:0001000000 "$yes"
+chk application/x-shockwave-flash 'CWSx' "$yes"
+chk application/x-java-vm hex:CAFEBABE "$yes"
+chk application/wasm hex:0061736D "$yes"
+chk text/html $'  \r\n<!DOCTYPE html><html>' "$yes"
+chk text/html '<html lang="en">' "$yes"
+chk text/html 'plain text, no markup' "$no"
+chk text/xml '<?xml version="1.0"?>' "$yes"
+
+# no magic rule at all: never confirmed, never blocks the wire type
+chk text/css 'body { }' "$unk"
+chk text/plain 'hello' "$unk"
+chk application/x-javascript 'var x;' "$unk"

tests/01_engine-status.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# HTTP status -> reason phrase, including the modern 429/451 (#453).
+httrack -O /dev/null -#test=status run | grep -q "status self-test OK"