Bound htsback backing-info and fast-cache copies

Continue the htssafe.h pointer-destination migration in htsback.c.

back_infostr() wrote into a bare char* through the unchecked strcatbuff()
path. Thread the destination capacity through and use strlcatbuff(), and
fix a latent bug while here: the size/totalsize trailer was sprintf'd
straight into the destination, wiping the URL the function had just
assembled, instead of being built in the scratch buffer and appended.
The fixed-size sprintf() calls become snprintf().

Enlarge back_info()'s status buffer to HTS_URLMAXSIZE*4+1024 so it can
hold both url_adr and url_fil (each HTS_URLMAXSIZE*2) plus framing. The
old HTS_URLMAXSIZE*2+1024 buffer was too small for two full-length URL
fields, so the now-bounded appends would abort on a long URL.

In back_add()'s fast-header cache path, copy the cached location into its
backing array (location_buffer) rather than through the r.location alias,
so the bounded macro sees the real capacity.

Add a back_infostr()/back_info() self-test under -#7: it formats 2000
in-memory slots across every status-code arm with exact-match assertions
(no sockets needed), plus a near-maximal URL driven through back_info()
to guard the buffer sizing. It fails on the clobber bug and on an
undersized status buffer.

htsback.c is now free of pointer-destination buff() warnings.

Signed-off-by: Xavier Roche <roche@httrack.com>

.clang-format

@@ -0,0 +1,27 @@
+# clang-format 19 config for the HTTrack C engine.
+#
+# IMPORTANT: this is applied to TOUCHED LINES ONLY (via git-clang-format / the
+# CI format check). The engine was originally formatted by GNU indent / by hand
+# and does NOT round-trip through clang-format, so a whole-tree reformat is
+# intentionally never done. Format the lines you change; leave the rest.
+#
+# Reverse-engineered from src/*.c: 2-space indent, no tabs, 80 columns, pointers
+# bound to the name (char *x), attached braces, un-indented case labels, and a
+# space after C-style casts ((int) x). Most of that is LLVM's defaults; the
+# lines below are the deliberate deviations.
+
+BasedOnStyle: LLVM
+
+# Engine specifics / deviations from LLVM:
+SpaceAfterCStyleCast: true   # "(int) x", overwhelmingly dominant (542 vs 7)
+SortIncludes: false          # C include order can be significant; never reorder
+IncludeBlocks: Preserve      # do not merge/reflow include groups
+
+# Stated explicitly for robustness against base-style drift (these match LLVM):
+IndentWidth: 2
+UseTab: Never
+ColumnLimit: 80
+PointerAlignment: Right
+IndentCaseLabels: false
+SpaceBeforeParens: ControlStatements
+AllowShortIfStatementsOnASingleLine: Never

.githooks/README.md

@@ -0,0 +1,35 @@
+# Git hooks
+
+Versioned hooks for this repo. Enable them once per clone:
+
+```sh
+git config core.hooksPath .githooks
+```
+
+## pre-commit: auto-format changed C lines
+
+Runs `git-clang-format` (clang-format 19, using the repo `.clang-format`) on the
+**staged lines only** and re-stages the result, so every commit is
+clang-format-clean and the CI `format` check passes. It never reformats the
+whole tree, only the lines you changed.
+
+- Disable for a single commit: `HTTRACK_NO_AUTOFORMAT=1 git commit ...`
+- If clang-format 19 isn't installed, the hook skips silently (CI still
+  enforces). Install it with your distro's `clang-format-19`, or from
+  apt.llvm.org.
+- If a file has *both* staged and unstaged changes, the hook does not
+  auto-mutate it (that would commit the unstaged part); it instead reports
+  whether its staged lines need formatting and asks you to stage/stash the rest.
+
+### noexec working trees
+
+Git executes the hook directly, so if your working tree is on a `noexec` mount
+git cannot run `.githooks/pre-commit`. Point `core.hooksPath` at a copy on an
+exec filesystem instead:
+
+```sh
+mkdir -p ~/.httrack-hooks && cp .githooks/pre-commit ~/.httrack-hooks/
+chmod +x ~/.httrack-hooks/pre-commit
+git config core.hooksPath ~/.httrack-hooks
+```
+</content>

.githooks/pre-commit

@@ -0,0 +1,71 @@
+#!/usr/bin/env bash
+#
+# Auto-format the staged C lines with clang-format (touched lines only), then
+# re-stage them, so commits stay clang-format-clean and CI's format check passes.
+#
+# Enable once per clone:  git config core.hooksPath .githooks
+# Skip for one commit:    HTTRACK_NO_AUTOFORMAT=1 git commit ...
+#
+# Matches the CI gate (.clang-format, clang-format 19). It only ever touches the
+# lines a commit changes; it never reformats the whole tree.
+
+set -euo pipefail
+
+[ "${HTTRACK_NO_AUTOFORMAT:-}" = "1" ] && exit 0
+
+# Staged C/H files (added/copied/modified/renamed).
+mapfile -t files < <(git diff --cached --name-only --diff-filter=ACMR -- '*.c' '*.h')
+[ "${#files[@]}" -eq 0 ] && exit 0
+
+# Locate clang-format 19 and the git driver; if absent, skip (CI is the backstop).
+cf=""
+for c in clang-format-19 clang-format; do
+    if command -v "$c" >/dev/null 2>&1; then
+        case "$("$c" --version)" in *"version 19."*)
+            cf="$c"
+            break
+            ;;
+        esac
+    fi
+done
+gcf=""
+for g in git-clang-format-19 git-clang-format; do
+    command -v "$g" >/dev/null 2>&1 && {
+        gcf="$g"
+        break
+    }
+done
+if [ -z "$cf" ] || [ -z "$gcf" ]; then
+    echo "pre-commit: clang-format 19 not found; skipping auto-format (CI still checks)." >&2
+    exit 0
+fi
+
+# Files that are staged AND also have unstaged changes: re-staging them would
+# pull in the unstaged work, so don't auto-mutate. Check instead and let the
+# author resolve it.
+partial=()
+for f in "${files[@]}"; do
+    if ! git diff --quiet -- "$f"; then partial+=("$f"); fi
+done
+
+if [ "${#partial[@]}" -ne 0 ]; then
+    d="$("$gcf" --binary "$cf" --style=file --staged --diff --extensions c,h || true)"
+    case "$d" in
+    "" | "no modified files to format" | *"did not modify any files"*)
+        exit 0
+        ;; # staged lines already clean
+    *)
+        echo "pre-commit: these files have both staged and unstaged changes, so" >&2
+        echo "auto-format was skipped to avoid committing unstaged work:" >&2
+        printf '  %s\n' "${partial[@]}" >&2
+        echo "Their staged lines need formatting. Stage the rest (or stash it)," >&2
+        echo "or run: $gcf --binary $cf --staged" >&2
+        exit 1
+        ;;
+    esac
+fi
+
+# Clean-staged files: format the staged lines in the working tree, then re-stage.
+"$gcf" --binary "$cf" --style=file --staged --extensions c,h >/dev/null || true
+git add -- "${files[@]}"
+exit 0

.github/workflows/ci.yml

@@ -61,6 +61,37 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
+  dco:
+    name: DCO sign-off
+    # Only checkable on a PR, where we have the base..head commit range.
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Every commit must be signed off
+        env:
+          BASE: ${{ github.event.pull_request.base.sha }}
+          HEAD: ${{ github.event.pull_request.head.sha }}
+        run: |
+          set -euo pipefail
+          fail=0
+          # --no-merges: merge commits are GitHub-generated and carry no sign-off.
+          for sha in $(git rev-list --no-merges "$BASE..$HEAD"); do
+            if [ -z "$(git log -1 --format='%(trailers:key=Signed-off-by)' "$sha")" ]; then
+              echo "Missing Signed-off-by: $(git log -1 --format='%h %s' "$sha")"
+              fail=1
+            fi
+          done
+          if [ "$fail" -ne 0 ]; then
+            echo
+            echo "Sign commits with 'git commit -s'; fix a branch with 'git rebase --signoff $BASE'."
+            echo "See CONTRIBUTING.md (Developer Certificate of Origin)."
+            exit 1
+          fi
+
   lint:
     name: lint (shellcheck, shfmt)
     runs-on: ubuntu-24.04
@@ -81,7 +112,65 @@ jobs:
 
       # Lint the scripts we maintain; the legacy scripts are a separate cleanup.
       - name: shellcheck
-        run: shellcheck man/makeman.sh tools/mkdeb.sh tests/*.test tests/check-network.sh
+        run: shellcheck man/makeman.sh tools/mkdeb.sh .githooks/pre-commit tests/*.test tests/check-network.sh
 
       - name: shfmt
-        run: shfmt -d -i 4 man/makeman.sh tools/mkdeb.sh
+        run: shfmt -d -i 4 man/makeman.sh tools/mkdeb.sh .githooks/pre-commit
+
+  # Check clang-format on CHANGED LINES ONLY. The engine predates clang-format
+  # (it was shaped by an old Visual Studio formatter) and does not round-trip,
+  # so we never reformat the whole tree -- only the lines a PR touches.
+  format:
+    name: format (clang-format-19, changed lines)
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Install clang-format 19 (pinned, from apt.llvm.org)
+        run: |
+          set -euo pipefail
+          # ubuntu-24.04's native clang-format is 18; pin 19 to match local dev.
+          wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key \
+            | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc >/dev/null
+          echo "deb http://apt.llvm.org/noble/ llvm-toolchain-noble-19 main" \
+            | sudo tee /etc/apt/sources.list.d/llvm-19.list >/dev/null
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends clang-format-19
+          # git-clang-format driver, pinned to an immutable release tag (not a
+          # moving branch) since we curl and then execute it.
+          sudo curl -fsSL -o /usr/local/bin/git-clang-format \
+            https://raw.githubusercontent.com/llvm/llvm-project/llvmorg-19.1.7/clang/tools/clang-format/git-clang-format
+          sudo chmod 0755 /usr/local/bin/git-clang-format
+          clang-format-19 --version
+
+      - name: Check formatting of changed lines
+        run: |
+          set -euo pipefail
+          git fetch --no-tags origin \
+            "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
+          base="origin/${{ github.base_ref }}"
+          set +e
+          diff="$(git clang-format --binary clang-format-19 --style=file \
+                    --diff --extensions c,h "$base")"
+          rc=$?
+          set -e
+          # Classify by output first: a non-empty diff means "not clean",
+          # regardless of the driver's exit convention (the release-tag driver
+          # exits 0 and signals via stdout; some packaged drivers exit 1 on a
+          # diff). A nonzero exit with clean output is a real checker error.
+          case "$diff" in
+            "" | "no modified files to format" | *"did not modify any files"*)
+              if [ "$rc" -ne 0 ]; then
+                echo "::error::git clang-format failed (exit $rc): checker error."
+                exit 1
+              fi
+              echo "Formatting OK: changed C lines are clang-format-clean." ;;
+            *)
+              echo "$diff"
+              echo "::error::Changed C lines are not clang-format-clean."
+              echo "Fix locally with: git clang-format --binary clang-format-19 $base"
+              exit 1 ;;
+          esac

CODE_OF_CONDUCT.md

@@ -0,0 +1,83 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at <roche@httrack.com>. All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.1, available at [https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at [https://www.contributor-covenant.org/faq][FAQ]. Translations are available at [https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

CONTRIBUTING.md

@@ -0,0 +1,39 @@
+# Contributing to HTTrack
+
+HTTrack is small and old. Keep changes easy to review and safe to merge.
+
+## Pull requests
+
+- One change per PR. Small diffs merge fast.
+- PRs are squash-merged: the title and description become the commit message, so
+  explain *why*.
+- Add or update tests for engine changes (`tests/`), and keep CI green.
+
+## Style
+
+- C, matching nearby code. **Format only the lines you change** (`git
+  clang-format` against the repo `.clang-format`). Never reformat untouched code.
+- Comment the *why*, in English.
+- HTTrack parses hostile input off the network. Check bounds, avoid unchecked
+  copies, and never let an attacker-controlled length drive arithmetic unchecked.
+
+## Sign your work
+
+Every commit needs a `Signed-off-by` line, the
+[DCO](https://developercertificate.org/): `git commit -s`. CI rejects unsigned
+commits; fix a branch with `git rebase --signoff master`.
+
+## AI assistants
+
+Welcome, and nothing to disclose. Two rules:
+
+- **Own every line** as if you wrote it. Can't explain it in review? Not ready.
+- **Don't push your work onto reviewers.** A raw generated patch a maintainer has
+  to vet from scratch will be closed.
+
+The sign-off covers AI-assisted code too.
+
+## Bugs
+
+Open an issue with the version, OS, command used, and expected vs actual result.
+For security issues see [SECURITY.md](SECURITY.md), not a public issue.

README.md

@@ -23,7 +23,7 @@ http://www.httrack.com/
 
 ## Compile trunk release
 ```sh
-git clone https://github.com/xroche/httrack.git --recurse
+git clone https://github.com/xroche/httrack.git --recurse-submodules
 cd httrack
 ./configure --prefix=$HOME/usr && make -j8 && make install
 ```

SECURITY.md

@@ -0,0 +1,23 @@
+# Security Policy
+
+## Reporting
+
+Report privately, not in a public issue or PR: use GitHub
+[private advisories](https://github.com/xroche/httrack/security/advisories/new)
+or email <roche@httrack.com> (alternate: `xroche at gmail dot com`).
+
+Include the HTTrack version and platform, a concrete reproduction (command line,
+a sample page or server response, or a small proof of concept), and what an
+attacker gains. We'll acknowledge it and keep you posted. Please allow time for a
+release before disclosing publicly.
+
+## Supported versions
+
+Fixes land on `master` and ship in the next release; older releases aren't
+maintained. Confirm against current `master` when you can.
+
+## AI-assisted findings
+
+Scanners and LLMs are fine, but only send reports you have verified yourself. A
+confirmed, reproducible issue is worth our time; a plausible one that doesn't
+reproduce is not, and will be closed. If a report is AI-assisted, say so.

configure.ac

@@ -50,6 +50,9 @@ LT_INIT
 AC_PROG_LN_S
 LT_INIT
 
+# bash, used to run the test scripts (see tests/Makefile.am TEST_LOG_COMPILER)
+AC_PATH_PROGS([BASH], [bash], [/bin/bash])
+
 # Export LD_LIBRARY_PATH name or equivalent.
 AC_SUBST(SHLIBPATH_VAR,$shlibpath_var)
 

html/Makefile.am

@@ -13,22 +13,26 @@ WebIcon32x32dir = $(datadir)/icons/hicolor/32x32/apps
 WebIcon48x48dir = $(datadir)/icons/hicolor/48x48/apps
 VFolderEntrydir = $(prefix)/share/applications
 
+# Wildcards are globbed against $(srcdir): a bare "*.html" is resolved against
+# the build dir and stays unexpanded (breaking "make") in an out-of-tree build.
+# Explicit filenames (e.g. ../history.txt, div/search.sh) resolve via VPATH and
+# need no prefix.
 HelpHtmlroot_DATA = ../httrack-doc.html ../history.txt
-HelpHtml_DATA = *.html
+HelpHtml_DATA = $(srcdir)/*.html
 HelpHtmldiv_DATA = div/search.sh
-HelpHtmlimg_DATA  = img/*
-HelpHtmlimages_DATA = images/*
+HelpHtmlimg_DATA  = $(srcdir)/img/*
+HelpHtmlimages_DATA = $(srcdir)/images/*
 HelpHtmlTxt_DATA = ../greetings.txt ../history.txt ../license.txt
-WebHtml_DATA = server/*.html server/*.js server/*.css
-WebHtmlimages_DATA = server/images/*
+WebHtml_DATA = $(srcdir)/server/*.html $(srcdir)/server/*.js $(srcdir)/server/*.css
+WebHtmlimages_DATA = $(srcdir)/server/images/*
 # note: converted & normalized by
 # ico2xpm favicon.ico -o httrack.xpm
 # mogrify -format xpm -map /usr/share/doc/menu/examples/cmap.xpm httrack.xpm
-WebPixmap_DATA = server/div/*.xpm
-WebIcon16x16_DATA = server/div/16x16/*.png
-WebIcon32x32_DATA = server/div/32x32/*.png
-WebIcon48x48_DATA = server/div/48x48/*.png
-VFolderEntry_DATA = server/div/*.desktop
+WebPixmap_DATA = $(srcdir)/server/div/*.xpm
+WebIcon16x16_DATA = $(srcdir)/server/div/16x16/*.png
+WebIcon32x32_DATA = $(srcdir)/server/div/32x32/*.png
+WebIcon48x48_DATA = $(srcdir)/server/div/48x48/*.png
+VFolderEntry_DATA = $(srcdir)/server/div/*.desktop
 
 EXTRA_DIST = $(HelpHtml_DATA) $(HelpHtmlimg_DATA) $(HelpHtmlimages_DATA) \
 	$(HelpHtmldiv_DATA) $(WebHtml_DATA) $(WebHtmlimages_DATA) \

html/cmddoc.html

@@ -118,11 +118,11 @@ The command-line version
       <br>
       <br>
     <li>Add the URLs, separated by a blank space</li>
-      <br><small><tt>httrack www.someweb.com/foo/</tt></small>
+      <br><small><tt>httrack www.example.com/foo/</tt></small>
       <br>
       <br>
     <li>If you need, add some options (see the <a href="options.html">option list</a>)</li>
-      <br><small><tt>httrack www.someweb.com/foo/ -O "/webs" -N4 -P proxy.myhost.com:3128</tt></small>
+      <br><small><tt>httrack www.example.com/foo/ -O "/webs" -N4 -P proxy.myhost.com:3128</tt></small>
       <br>
       <br>
     <li>Launch the command line, and wait until the mirror is finishing</li>

html/faq.html

@@ -303,43 +303,43 @@ Okay, let me explain how to precisely control the capture process.<br>
 Let's take an example:<br>
 <br>
 Imagine you want to capture the following site:<br>
-<tt>www.someweb.com/gallery/flowers/</tt><br>
+<tt>www.example.com/gallery/flowers/</tt><br>
 <br>
-HTTrack, by default, will capture all links encountered in <tt>www.someweb.com/gallery/flowers/</tt> or in lower directories, like
-<tt>www.someweb.com/gallery/flowers/roses/</tt>.<br>
+HTTrack, by default, will capture all links encountered in <tt>www.example.com/gallery/flowers/</tt> or in lower directories, like
+<tt>www.example.com/gallery/flowers/roses/</tt>.<br>
 It will not follow links to other websites, because this behaviour might cause to capture the Web entirely!<br>
-It will not follow links located in higher directories, too (for example, <tt>www.someweb.com/gallery/flowers/</tt> itself) because this 
+It will not follow links located in higher directories, too (for example, <tt>www.example.com/gallery/flowers/</tt> itself) because this 
 might cause to capture too much data.<br>
 <br>
 This is the <b><u>default behaviour</b></u> of HTTrack, BUT, of course, if you want, you can tell HTTrack to capture other directorie(s), website(s)!..
 <br>
-In our example, we might want also to capture all links in <tt>www.someweb.com/gallery/trees/</tt>, and in <tt>www.someweb.com/photos/</tt><br>
+In our example, we might want also to capture all links in <tt>www.example.com/gallery/trees/</tt>, and in <tt>www.example.com/photos/</tt><br>
 <br>
 This can easily done by using filters: go to the Option panel, select the 'Scan rules' tab, and enter this line:
 (you can leave a blank space between each rules, instead of entering a carriage return)<br>
-<tt>+www.someweb.com/gallery/trees/*<br>
-+www.someweb.com/photos/*</tt><br>
+<tt>+www.example.com/gallery/trees/*<br>
++www.example.com/photos/*</tt><br>
 <br>
-This means "accept all links begining with <tt>www.someweb.com/gallery/trees/</tt> and <tt>www.someweb.com/photos/</tt>" 
+This means "accept all links begining with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
 - the <tt>+</tt> means "accept" and the final <tt>*</tt> means "any character will match after the previous ones".
 Remember the <tt>*.doc</tt> or <tt>*.zip</tt> encountered when you want to select all files from a certain type on your computer: 
 it is almost the same here, except the begining "+"<br>
 <br>
-Now, we might want to exclude all links in <tt>www.someweb.com/gallery/trees/hugetrees/</tt>, because with the previous filter,
+Now, we might want to exclude all links in <tt>www.example.com/gallery/trees/hugetrees/</tt>, because with the previous filter,
 we accepted too many files. Here again, you can add a filter rule to refuse these links. Modify the previous filters to:<br>
-<tt>+www.someweb.com/gallery/trees/*<br>
-+www.someweb.com/photos/*<br>
--www.someweb.com/gallery/trees/hugetrees/*</tt><br>
+<tt>+www.example.com/gallery/trees/*<br>
++www.example.com/photos/*<br>
+-www.example.com/gallery/trees/hugetrees/*</tt><br>
 <br>
 You have noticed the <tt>-</tt> in the begining of the third rule: this means "refuse links matching the rule" 
-; and the rule is "any files begining with <tt>www.someweb.com/gallery/trees/hugetrees/</tt><br>
+; and the rule is "any files begining with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
 
 Voila! With these three rules, you have precisely defined what you wanted to capture.<br>
 <br>
 A more complex example?<br>
 <br>
-Imagine that you want to accept all jpg files (files with .jpg type) that have "blue" in the name and located in www.someweb.com<br>
-<tt>+www.someweb.com/*blue*.jpg</tt><br>
+Imagine that you want to accept all jpg files (files with .jpg type) that have "blue" in the name and located in www.example.com<br>
+<tt>+www.example.com/*blue*.jpg</tt><br>
 <br>
 More detailed information can be found <a href="filters.html">here</a>!<br>
 <br>
@@ -440,7 +440,7 @@ This will cause a performance loss, but will increase the compatibility with som
 
 <a NAME="QT1">Q: <strong>Only the first page is caught. What's wrong?</a></strong></br>
 A: <em>First, check the <tt>hts-log.txt</tt> file (and/or <tt>hts-err.txt</tt> error log file) - this can give you precious information.<br>
-The problem can be a website that redirects you to another site (for example, <tt>www.someweb.com</tt> to <tt>public.someweb.com</tt>) : 
+The problem can be a website that redirects you to another site (for example, <tt>www.example.com</tt> to <tt>public.example.com</tt>) : 
 in this case, use filters to accept this site<br>
 This can be, also, a problem in the HTTrack options (link depth too low, for example)</em>
 
@@ -485,10 +485,10 @@ You may also want to capture files that are forbidden by default by the <a href=
 In these cases, HTTrack does not capture these links automatically, you have to tell it to do so. 
 <br><br>
 <ul><li>Either use the <a href="filters.html">filters</a>.<br>
-Example: You are downloading <tt>http://www.someweb.com/foo/</tt> and can not get .jpg images located
-in <tt>http://www.someweb.com/bar/</tt> (for example, http://www.someweb.com/bar/blue.jpg)<br>
-Then, add the filter rule <tt>+www.someweb.com/bar/*.jpg</tt> to accept all .jpg files from this location<br>
-You can, also, accept all files from the /bar folder with <tt>+www.someweb.com/bar/*</tt>, or only html files with <tt>+www.someweb.com/bar/*.html</tt> and so on..<br><br>
+Example: You are downloading <tt>http://www.example.com/foo/</tt> and can not get .jpg images located
+in <tt>http://www.example.com/bar/</tt> (for example, http://www.example.com/bar/blue.jpg)<br>
+Then, add the filter rule <tt>+www.example.com/bar/*.jpg</tt> to accept all .jpg files from this location<br>
+You can, also, accept all files from the /bar folder with <tt>+www.example.com/bar/*</tt>, or only html files with <tt>+www.example.com/bar/*.html</tt> and so on..<br><br>
 </li><li>
 If the problems are related to robots.txt rules, that do not let you access some folders (check in the logs if you are not sure),
 you may want to disable the default robots.txt rules in the options. (but only disable this option with great care, 
@@ -509,8 +509,8 @@ and rescan the website as described before. HTTrack will be obliged to recatch t
 <a NAME="Q1bb">Q: <strong>FTP links are not caught! What's happening?</strong><br>
 A: <em>FTP files might be seen as external links, especially if they are located in outside domain. You have either to accept all external links (See the links options, -n option) or
 only specific files (see <a href="filters.html">filters</a> section). <br>
-Example: You are downloading <tt>http://www.someweb.com/foo/</tt> and can not get ftp://ftp.someweb.com files<br>
-Then, add the filter rule <tt>+ftp.someweb.com/*</tt> to accept all files from this (ftp) location<br>
+Example: You are downloading <tt>http://www.example.com/foo/</tt> and can not get ftp://ftp.example.com files<br>
+Then, add the filter rule <tt>+ftp.example.com/*</tt> to accept all files from this (ftp) location<br>
 </em>
 <br>
 
@@ -551,10 +551,10 @@ Note: In some rare cases, duplicate data files can be found when the website red
 
 <a NAME="Q1b2">Q: <strong>I'm downloading too many files! What can I do?</strong><br>
 A: <em>This is often the case when you use too large a filter, for example <tt>+*.html</tt>, which asks the
-engine to catch all .html pages (even ones on other sites!). In this case, try to use more specific filters, like <tt>+www.someweb.com/specificfolder/*.html</tt><br>
-If you still have too many files, use filters to avoid somes files. For example, if you have too many files from www.someweb.com/big/, 
-use <tt>-www.someweb.com/big/*</tt> to avoid all files from this folder. Remember that the default behaviour of the engine, when
-mirroring http://www.someweb.com/big/index.html, is to catch everything in http://www.someweb.com/big/. Filters are your friends,
+engine to catch all .html pages (even ones on other sites!). In this case, try to use more specific filters, like <tt>+www.example.com/specificfolder/*.html</tt><br>
+If you still have too many files, use filters to avoid somes files. For example, if you have too many files from www.example.com/big/, 
+use <tt>-www.example.com/big/*</tt> to avoid all files from this folder. Remember that the default behaviour of the engine, when
+mirroring http://www.example.com/big/index.html, is to catch everything in http://www.example.com/big/. Filters are your friends,
 use them!
 </em>
 <br>
@@ -562,7 +562,7 @@ use them!
 
 <a NAME="Q1b22">Q: <strong>The engine turns crazy, getting thousands of files! What's going on?</strong><br>
 A: <em>This can happen if a loop occurs in some bogus website. For example, a page that refers to itself, with a timestamp
-in the query string (e.g. <tt>http://www.someweb.com/foo.asp?ts=2000/10/10,09:45:17:147</tt>). 
+in the query string (e.g. <tt>http://www.example.com/foo.asp?ts=2000/10/10,09:45:17:147</tt>). 
 These are really annoying, as it is VERY difficult to detect the loop (the timestamp might be a page number).
 To limit the problem: set a recurse level (for example to 6), or avoid the bogus pages (use the filters)
 </em>
@@ -571,7 +571,7 @@ To limit the problem: set a recurse level (for example to 6), or avoid the bogus
 
 <a NAME="Q1b3">Q: <strong>File are sometimes renamed (the type is changed)! Why?</strong><br>
 A: <em>By default, HTTrack tries to know the type of remote files. This is useful when links like
-<tt>http://www.someweb.com/foo.cgi?id=1</tt> can be either HTML pages, images or anything else. 
+<tt>http://www.example.com/foo.cgi?id=1</tt> can be either HTML pages, images or anything else. 
 Locally, foo.cgi will not be recognized as an html page, or as an image, by your browser. HTTrack has to rename the file
 as foo.html or foo.gif so that it can be viewed.<br>
 </em>
@@ -730,8 +730,8 @@ but this is a smart bug..
 the domain, too. How to retrieve them?</strong><br>
 A: <em>If you just want to retrieve files that can be reached through links, just activate
 the 'get file near links' option. But if you want to retrieve html pages too, you can both
-use wildcards or explicit addresses ; e.g. add <tt>www.someweb.com/*</tt> to accept all
-files and pages from www.someweb.com.<br>
+use wildcards or explicit addresses ; e.g. add <tt>www.example.com/*</tt> to accept all
+files and pages from www.example.com.<br>
 <br>
 </em></a><a NAME="Q6">Q: <strong>I have forgotten some URLs of files during a long
 mirror.. Should I redo all?</strong><br>
@@ -744,7 +744,7 @@ A: <em>You can use different methods. You can use the 'get files near a link' op
 files are in a foreign domain. You can use, too, a filter adress: adding <tt>+*.zip</tt>
 in the URL list (or in the filter list) will accept all ZIP files, even if these files are
 outside the address. <br>
-Example : <tt>httrack www.someweb.com/someaddress.html +*.zip</tt> will allow
+Example : <tt>httrack www.example.com/someaddress.html +*.zip</tt> will allow
 you to retrieve all zip files that are linked on the site.</em><br>
 <br>
 </a><a NAME="Q8">Q: <strong>There are ZIP files in a page, but I don't want to transfer
@@ -771,7 +771,7 @@ them on filters!</strong><br>
 A: <em>By default, HTTrack retrieves all types of files on authorized links. To avoid
 that, define filters like </a><a NAME="Q7"><tt>-* +&lt;website&gt;/*.html
 +&lt;website&gt;/*.htm +&lt;website&gt;/ +*.&lt;type wanted&gt;</tt></a><a NAME="Q10"><br>
-Example: <tt>httrack www.someweb.com/index.html -* +www.someweb.com/*.htm* +www.someweb.com/*.gif +www.someweb.com/*.jpg</tt><br>
+Example: <tt>httrack www.example.com/index.html -* +www.example.com/*.htm* +www.example.com/*.gif +www.example.com/*.jpg</tt><br>
 <br>
 </em><a NAME="Q10">Q: <strong>When I use filters, I get too many files!</strong><br>
 A: <em>You might use too large a filter, for example <tt>*.html</tt> will get ALL html
@@ -779,13 +779,13 @@ files identified. If you want to get all files on an address, use <tt>www.&lt;ad
 If you want to get ONLY files defined by your filters, use something like <tt>-* +www.foo.com/*</tt>, because 
 <tt>+www.foo.com/*</tt> will only accept selected links without forbidding other ones!<br>
 There are lots of possibilities using filters.<br>
-Example:<tt>httrack www.someweb.com +*.someweb.com/*.htm*</tt><br>
+Example:<tt>httrack www.example.com +*.example.com/*.htm*</tt><br>
 <br>
 </em></a><a NAME="Q11">Q: <strong>When I use filters, I can't access another domain, but I
 have filtered it!</strong><br>
-A: <em>You may have done a mistake declaring filters, for example <tt>+www.someweb.com/*
--*someweb* </tt></em>will not work, because -*someweb* has an upper priority (because it has
-been declared after +www.someweb.com)<br>
+A: <em>You may have done a mistake declaring filters, for example <tt>+www.example.com/*
+-*example* </tt></em>will not work, because -*example* has an upper priority (because it has
+been declared after +www.example.com)<br>
 <br>
 </a><a NAME="Q12">Q: <strong>Must I add a&nbsp; '+' or '-' in the filter list when I want
 to use filters?</strong><br>
@@ -800,7 +800,7 @@ filter list) and accept only html files and the file(s) you want to retrieve (BU
 forget to add <tt>+&lt;website&gt;*.html</tt> in the filter list, or pages will not be
 scanned! Add the name of files you want with a <tt>*/</tt> before ; i.e. if you want to
 retrieve file.zip, add <tt>*/file.zip</tt>)<br>
-Example:<tt>httrack www.someweb.com +www.someweb.com/*.htm* +thefileiwant.zip</tt><br>
+Example:<tt>httrack www.example.com +www.example.com/*.htm* +thefileiwant.zip</tt><br>
 <br>
 </em>
 
@@ -828,7 +828,7 @@ A: <em>Yes. See the URL capture abilities (--catchurl for command-line release,
 A: <em>Yes. See the shell system command option (-V option for command-line release)</em>
 
 <br><br><a NAME="QM6">Q: <strong>Can I use username/password authentication on a site?</strong></a><br>
-A: <em>Yes. Use user:password@your_url (example: <tt>http://foo:bar@www.someweb.com/private/mybox.html</tt>)</em>
+A: <em>Yes. Use user:password@your_url (example: <tt>http://foo:bar@www.example.com/private/mybox.html</tt>)</em>
 
 <br><br><a NAME="QM7">Q: <strong>Can I use username/password authentication for a proxy?</strong></a><br>
 A: <em>Yes. Use user:password@your_proxy_name as your proxy name (example: <tt>smith:foo@proxy.mycorp.com</tt>)</em>

html/fcguide.html

@@ -181,17 +181,17 @@ used for some time.
 
 <p align=justify> The rest of this manual is dedicated to detailing what
 you find in the help message and providing examples - lots and lots of
-examples...  Here is what you get (page by page - use <enter> to move to
+examples...  Here is what you get (page by page - use &lt;enter&gt; to move to
 the next page in the real program) if you type 'httrack --help':
 
 <pre>
 >httrack --help
  HTTrack version 3.03BETAo4 (compiled Jul  1 2001)
-	usage: ./httrack <URLs [-option] [+<FILTERs>] [-<FILTERs>]
+	usage: ./httrack &lt;URLs&gt; [-option] [+&lt;FILTERs&gt;] [-&lt;FILTERs&gt;]
 	with options listed below: (* is the default value)
 
 General options:
-  O  path for mirror/logfiles+cache (-O path_mirror[,path_cache_and_logfiles]) (--path <param>)
+  O  path for mirror/logfiles+cache (-O path_mirror[,path_cache_and_logfiles]) (--path &lt;param&gt;)
  %O  top path if no path defined (-O path_mirror[,path_cache_and_logfiles])
 
 Action options:
@@ -202,7 +202,7 @@ Action options:
   Y   mirror ALL links located in the first level pages (mirror links) (--mirrorlinks)
 
 Proxy options:
-  P  proxy use (-P proxy:port or -P user:pass@proxy:port) (--proxy <param>)
+  P  proxy use (-P proxy:port or -P user:pass@proxy:port) (--proxy &lt;param&gt;)
  %f *use proxy for ftp (f0 don't use) (--httpproxy-ftp[=N])
 
 Limits options:
@@ -227,7 +227,7 @@ Links options:
  %P *extended parsing, attempt to parse all links, even in unknown tags or Javascript (%P0 don't use) (--extended-parsing[=N])
   n  get non-html files 'near' an html file (ex: an image located outside) (--near)
   t  test all URLs (even forbidden ones) (--test)
- %L <file add all URL located in this text file (one URL per line) (--list <param>)
+ %L &lt;file&gt; add all URL located in this text file (one URL per line) (--list &lt;param&gt;)
 
 Build options:
   NN structure type (0 *original structure, 1+: see below) (--structure[=N])
@@ -248,12 +248,12 @@ Spider options:
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (--http-10)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!) (--tolerant)
  %s  update hacks: various hacks to limit re-transfers when updating (identical size, bogus response..) (--updatehack)
- %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume <param>)
+ %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume &lt;param&gt;)
 
 Browser ID:
-  F  user-agent field (-F "user-agent name") (--user-agent <param>)
- %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]" (--footer <param>)
- %l  preferred language (-%l "fr, en, jp, *" (--language <param>)
+  F  user-agent field (-F "user-agent name") (--user-agent &lt;param&gt;)
+ %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]" (--footer &lt;param&gt;)
+ %l  preferred language (-%l "fr, en, jp, *" (--language &lt;param&gt;)
 
 Log, index, cache
   C  create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before) (--cache[=N])
@@ -303,8 +303,8 @@ Guru options: (do NOT use)
  #!  Execute a shell command (-#! "echo hello")
 
 Command-line specific options:
-  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd <param>)
- %U run the engine with another id when called as root (-%U smith) (--user <param>)
+  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd &lt;param&gt;)
+ %U run the engine with another id when called as root (-%U smith) (--user &lt;param&gt;)
 
 Details: Option N
   N0 Site-structure (default)
@@ -332,7 +332,7 @@ Details: User-defined option N
   %N Name of file, including file type (ex: image.gif)
   %t File type (ex: gif)
   %p Path [without ending /] (ex: /someimages)
-  %h Host name (ex: www.someweb.com) (--http-10)
+  %h Host name (ex: www.example.com) (--http-10)
   %M URL MD5 (128 bits, 32 ascii bytes)
   %Q query string MD5 (128 bits, 32 ascii bytes)
   %q small query string MD5 (16 bits, 4 ascii bytes) (--include-query-string)
@@ -340,14 +340,14 @@ Details: User-defined option N
   %[param] param variable in query string
 
 Shortcuts:
---mirror      <URLs *make a mirror of site(s) (default)
---get         <URLs  get the files indicated, do not seek other URLs (-qg)
---list   <text file  add all URL located in this text file (-%L)
---mirrorlinks <URLs  mirror all links in 1st level pages (-Y)
---testlinks   <URLs  test links in pages (-r1p0C0I0t)
---spider      <URLs  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
---testsite    <URLs  identical to --spider
---skeleton    <URLs  make a mirror, but gets only html files (-p1)
+--mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
+--get         &lt;URLs&gt;  get the files indicated, do not seek other URLs (-qg)
+--list   &lt;text file&gt;  add all URL located in this text file (-%L)
+--mirrorlinks &lt;URLs&gt;  mirror all links in 1st level pages (-Y)
+--testlinks   &lt;URLs&gt;  test links in pages (-r1p0C0I0t)
+--spider      &lt;URLs&gt;  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
+--testsite    &lt;URLs&gt;  identical to --spider
+--skeleton    &lt;URLs&gt;  make a mirror, but gets only html files (-p1)
 --update              update a mirror, without confirmation (-iC2)
 --continue            continue a mirror, without confirmation (-iC1)
 
@@ -356,17 +356,17 @@ Shortcuts:
 
 --http10              force http/1.0 requests (-%h)
 
-example: httrack www.someweb.com/bob/
-means:   mirror site www.someweb.com/bob/ and only this site
+example: httrack www.example.com/bob/
+means:   mirror site www.example.com/bob/ and only this site
 
-example: httrack www.someweb.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg
+example: httrack www.example.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg
 means:   mirror the two sites together (with shared links) and accept any .jpg files on .com sites
 
-example: httrack www.someweb.com/bob/bobby.html +* -r6
+example: httrack www.example.com/bob/bobby.html +* -r6
 means get all files starting from bobby.html, with 6 link-depth, and possibility of going everywhere on the web
 
-example: httrack www.someweb.com/bob/bobby.html --spider -P proxy.myhost.com:8080
-runs the spider on www.someweb.com/bob/bobby.html using a proxy
+example: httrack www.example.com/bob/bobby.html --spider -P proxy.myhost.com:8080
+runs the spider on www.example.com/bob/bobby.html using a proxy
 
 example: httrack --update
 updates a mirror in the current folder
@@ -387,13 +387,13 @@ with examples... I will be here a while...
 <hr>
 <h2> Syntax </h2>
 
-<pre><b><i>httrack <URLs> [-option] [+<FILTERs>] [-<FILTERs>] </i></b></pre>
+<pre><b><i>httrack &lt;URLs&gt; [-option] [+&lt;FILTERs&gt;] [-&lt;FILTERs&gt;] </i></b></pre>
 
 <p align=justify> The syntax of httrack is quite simple.  You specify
-the URLs you wish to start the process from (<URLS>), any options you
+the URLs you wish to start the process from (&lt;URLS&gt;), any options you
 might want to add ([-option], any filters specifying places you should
-([+<FILTERs>]) and should not ([-<FILTERs>]) go, and end the command
-line by pressing <enter>.  Httrack then goes off and does your bidding.
+([+&lt;FILTERs&gt;]) and should not ([-&lt;FILTERs&gt;]) go, and end the command
+line by pressing &lt;enter&gt;.  Httrack then goes off and does your bidding.
 For example:
 
 <pre><b><i>
@@ -425,7 +425,7 @@ site. Specifically, the defauls are:
   pN priority mode: (* p3)  *3 save all files
   D  *can only go down into subdirs
   a  *stay on the same address
-  --mirror      <URLs> *make a mirror of site(s) (default)
+  --mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
 </pre>
 
 <p align=justify> Here's what all of that means:
@@ -542,7 +542,7 @@ subdirectories of the starting directory to be investigated.
 search started are to be collected.  Other sites they point to are not
 to be imaged. 
 
-<pre><b><i>  --mirror      <URLs> *make a mirror of site(s) (default) </i></b></pre>
+<pre><b><i>  --mirror      &lt;URLs&gt; *make a mirror of site(s) (default) </i></b></pre>
 
 <p align=justify> This indicates that the program should try to make a
 copy of the site as well as it can. 
@@ -921,7 +921,7 @@ Links options:
  %P *extended parsing, attempt to parse all links, even in unknown tags or Javascript (%P0 don't use)
   n   get non-html files 'near' an html file (ex: an image located outside)
   t   test all URLs (even forbidden ones)
- %L <file> add all URL located in this text file (one URL per line)
+ %L &lt;file&gt; add all URL located in this text file (one URL per line)
 </i></b></pre>
 
 <p align=justify> The links options allow you to control what links are
@@ -1183,7 +1183,7 @@ Spider options:
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!)
  %s  update hacks: various hacks to limit re-transfers when updating
- %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume <param>)
+ %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> By default, cookies are universally accepted and
@@ -1387,7 +1387,7 @@ web servers leave footprints in the browser.
 Browser ID:
   F  user-agent field (-F "user-agent name")
  %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]"
- %l  preferred language (-%l "fr, en, jp, *" (--language <param>)
+ %l  preferred language (-%l "fr, en, jp, *" (--language &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> The user-agent field is used by browsers to determine
@@ -1799,7 +1799,7 @@ based authentication)
 
 <pre><b><i>
 Command-line specific options:
-  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd <param>)
+  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> This option is very nice for a wide array of actions
@@ -1811,7 +1811,7 @@ httrack http://www.shoesizes.com/bob/ -O /tmp/shoesizes -V "/bin/echo \$0"
 </i></b></pre>
 
 <pre>
- %U run the engine with another id when called as root (-%U smith) (--user <param>)
+ %U run the engine with another id when called as root (-%U smith) (--user &lt;param&gt;)
 </pre>
 
 <p align=justify> Change the UID of the owner when running as r00t
@@ -1856,14 +1856,14 @@ of other options that are commonly used.
 
 <pre><b><i>
 Shortcuts:
---mirror      <URLs> *make a mirror of site(s) (default)
---get         <URLs>  get the files indicated, do not seek other URLs (-qg)
---list   <text file>  add all URL located in this text file (-%L)
---mirrorlinks <URLs>  mirror all links in 1st level pages (-Y)
---testlinks   <URLs>  test links in pages (-r1p0C0I0t)
---spider      <URLs>  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
---testsite    <URLs>  identical to --spider
---skeleton    <URLs>  make a mirror, but gets only html files (-p1)
+--mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
+--get         &lt;URLs&gt;  get the files indicated, do not seek other URLs (-qg)
+--list   &lt;text file&gt;  add all URL located in this text file (-%L)
+--mirrorlinks &lt;URLs&gt;  mirror all links in 1st level pages (-Y)
+--testlinks   &lt;URLs&gt;  test links in pages (-r1p0C0I0t)
+--spider      &lt;URLs&gt;  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
+--testsite    &lt;URLs&gt;  identical to --spider
+--skeleton    &lt;URLs&gt;  make a mirror, but gets only html files (-p1)
 --update              update a mirror, without confirmation (-iC2)
 --continue            continue a mirror, without confirmation (-iC1)
 --catchurl            create a temporary proxy to capture an URL or a form post URL
@@ -2019,15 +2019,15 @@ are in reverse priority order.  Here's an example:
         <td>no characters must be present after</a></td>
       </tr>
 	<tr>
-		<td> <b> <filter>*[&lt NN]</b></td>
+		<td> <b> &lt;filter&gt;*[&lt NN]</b></td>
 		<td> size less than NN Kbytes</td>
 	</tr>
 	<tr>
-		<td> <b> <filter>*[&gt PP]</b></td>
+		<td> <b> &lt;filter&gt;*[&gt PP]</b></td>
 		<td> size more than PP Kbytes</td>
 	</tr>
 	<tr>
-		<td> <b> <filter>*[&lt NN &gt PP]</b></td>
+		<td> <b> &lt;filter&gt;*[&lt NN &gt PP]</b></td>
 		<td> size less than NN Kbytes and more than PP Kbytes</td>
 	</tr>
     </table>
@@ -2054,8 +2054,8 @@ generated automatically using the interface)
         <td>This will accept all zip files in .com addresses</td>
       </tr>
       <tr>
-        <td><b>-*someweb*/*.tar*</b></td>
-        <td>This will refuse all tar (or tar.gz etc.) files in hosts containing someweb</td>
+        <td><b>-*example*/*.tar*</b></td>
+        <td>This will refuse all tar (or tar.gz etc.) files in hosts containing example</td>
       </tr>
       <tr>
         <td><b>+*/*somepage*</b></td>

html/filters.html

@@ -109,8 +109,8 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
 
     <i>You have to know that once you have defined
     starts links, the default mode is to mirror these links - i.e. if one of your start page is
-    www.someweb.com/test/index.html, all links starting with www.someweb.com/test/ will be
-    accepted. But links directly in www.someweb.com/.. will not be accepted, however, because
+    www.example.com/test/index.html, all links starting with www.example.com/test/ will be
+    accepted. But links directly in www.example.com/.. will not be accepted, however, because
     they are in a higher strcuture. This prevent HTTrack from mirroring the whole site. (All
     files in structure levels equal or lower than the primary links will be retrieved.)<br>
     </i>
@@ -278,8 +278,8 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
         <td>This will refuse/accept all zip files in .com addresses</td>
       </tr>
       <tr>
-        <td nowrap><tt>*someweb*/*.tar*</tt></td>
-        <td>This will refuse/accept all tar (or tar.gz etc.) files in hosts containing someweb</td>
+        <td nowrap><tt>*example*/*.tar*</tt></td>
+        <td>This will refuse/accept all tar (or tar.gz etc.) files in hosts containing example</td>
       </tr>
       <tr>
         <td nowrap><tt>*/*somepage*</tt></td>
@@ -289,13 +289,13 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
         <td nowrap><tt>*.html</tt></td>
         <td>This will refuse/accept all html files. <br>
         Warning! With this filter you will accept ALL html files, even those in other addresses.
-        (causing a global (!) web mirror..) Use www.someweb.com/*.html to accept all html files from
+        (causing a global (!) web mirror..) Use www.example.com/*.html to accept all html files from
         a web.</td>
       </tr>
       <tr>
         <td nowrap><tt>*.html*[]</tt></td>
         <td>Identical to <tt>*.html</tt>, but the link must not have any supplemental characters
-        at the end (links with parameters, like <tt>www.someweb.com/index.html?page=10</tt>, will be
+        at the end (links with parameters, like <tt>www.example.com/index.html?page=10</tt>, will be
         refused)</td>
       </tr>
     </table>

html/httrack.man.html

@@ -123,12 +123,12 @@ mirrored site, and resume interrupted downloads.</p>
 
 
 <p style="margin-left:11%; margin-top: 1em"><b>httrack
-www.someweb.com/bob/</b></p>
+www.example.com/bob/</b></p>
 
 <p style="margin-left:22%;">mirror site
-www.someweb.com/bob/ and only this site</p>
+www.example.com/bob/ and only this site</p>
 
-<p style="margin-left:11%;"><b>httrack www.someweb.com/bob/
+<p style="margin-left:11%;"><b>httrack www.example.com/bob/
 www.anothertest.com/mike/ +*.com/*.jpg <br>
 -mime:application/*</b></p>
 
@@ -137,18 +137,18 @@ www.anothertest.com/mike/ +*.com/*.jpg <br>
 sites</p>
 
 <p style="margin-left:11%;"><b>httrack
-www.someweb.com/bob/bobby.html +* -r6</b></p>
+www.example.com/bob/bobby.html +* -r6</b></p>
 
 <p style="margin-left:22%;">means get all files starting
 from bobby.html, with 6 link-depth, and possibility of going
 everywhere on the web</p>
 
 <p style="margin-left:11%;"><b>httrack
-www.someweb.com/bob/bobby.html --spider -P <br>
+www.example.com/bob/bobby.html --spider -P <br>
 proxy.myhost.com:8080</b></p>
 
 <p style="margin-left:22%;">runs the spider on
-www.someweb.com/bob/bobby.html using a proxy</p>
+www.example.com/bob/bobby.html using a proxy</p>
 
 <p style="margin-left:11%;"><b>httrack --update</b></p>
 
@@ -1877,7 +1877,7 @@ User-defined option N</b> <br>
 %N Name of file, including file type (ex: image.gif) <br>
 %t File type (ex: gif) <br>
 %p Path [without ending /] (ex: /someimages) <br>
-%h Host name (ex: www.someweb.com) <br>
+%h Host name (ex: www.example.com) <br>
 %M URL MD5 (128 bits, 32 ascii bytes) <br>
 %Q query string MD5 (128 bits, 32 ascii bytes) <br>
 %k full query string <br>

html/options.html

@@ -131,16 +131,16 @@ This is the default primary scanning option, the engine does not go out of domai
 
 d   stay on the same principal domain
 This option lets the engine go on all sites that exist on the same principal domain.
-Example: a link located at www.someweb.com that goes to members.someweb.com will be followed.
+Example: a link located at www.example.com that goes to members.example.com will be followed.
 
 l   stay on the same location (.com, etc.)
 This option lets the engine go on all sites that exist on the same location.
-Example: a link located at www.someweb.com that goes to www.anyotherweb.com will be followed.
+Example: a link located at www.example.com that goes to www.anyotherweb.com will be followed.
 Warning: this is a potentially dangerous option, limit the recurse depth with r option.
 
 e   go everywhere on the web
 This option lets the engine go on any sites.
-Example: a link located at www.someweb.com that goes to www.anyotherweb.org will be followed.
+Example: a link located at www.example.com that goes to www.anyotherweb.org will be followed.
 Warning: this is a potentially dangerous option, limit the recurse depth with r option.
 
 n   get non-html files 'near' an html file (ex: an image located outside)

html/step9_opt8.html

@@ -117,7 +117,7 @@ h4 { margin: 0;  font-weight: bold;  font-size: 1.18em; }
   <li>HTML Footer</li>
   <br><small>Enter here the optionnal text that will be included as a comment in each HTML file to make archiving easier
   <br>The string entered is generally an HTML comment (<tt>&lt;!-- HTML comment --&gt;</tt>) with optionnal %s, which will be transformed into a specific string information:
-  <br>%s #1 : host name (for example, www.someweb.com)
+  <br>%s #1 : host name (for example, www.example.com)
   <br>%s #2 : file name (for example, /index.html)
   <br>%s #3 : date of the mirror
   <br><b>Example</b>: <tt>&lt;!-- Page mirrored from %s, file %s. Archive date: %s --&gt;</tt>

lang/Makefile.am

@@ -1,6 +1,8 @@
 
 langdir = $(datadir)/httrack/lang
-lang_DATA = *.txt
+# Glob against $(srcdir): a bare "*.txt" is resolved against the build dir and
+# stays unexpanded (breaking "make") in an out-of-tree build.
+lang_DATA = $(srcdir)/*.txt
 langrootdir = $(datadir)/httrack
 langroot_DATA = ../lang.def ../lang.indexes
 

lang/Ukrainian.txt

@@ -7,7 +7,7 @@ uk
 LANGUAGE_AUTHOR
 Andrij Shevchuk (http://programy.com.ua, http://vic-info.com.ua) \r\n
 LANGUAGE_CHARSET
-ISO-8859-5
+windows-1251
 LANGUAGE_WINDOWSID
 Ukrainian
 OK

libtest/Makefile.am

@@ -1,6 +1,8 @@
 
 exemplesdir = $(datadir)/httrack/libtest
-exemples_DATA = *.c *.h *.txt
+# Glob against $(srcdir), not the build dir: a bare "*.c" is resolved relative to
+# the build dir and stays unexpanded (breaking "make") in an out-of-tree build.
+exemples_DATA = $(srcdir)/*.c $(srcdir)/*.h $(srcdir)/*.txt
 EXTRA_DIST = $(exemples_DATA) libtest.mak libtest.vcproj
 
 AM_CPPFLAGS = \
@@ -12,7 +14,9 @@ AM_CPPFLAGS = \
 	-DSYSCONFDIR=\""$(sysconfdir)"\" \
 	-DDATADIR=\""$(datadir)"\" \
 	-DLIBDIR=\""$(libdir)"\"
-AM_CPPFLAGS += -I../src
+# Use $(top_srcdir)/src, not ../src: the latter is relative to the build dir and
+# misses the source headers (e.g. httrack-library.h) in an out-of-tree build.
+AM_CPPFLAGS += -I$(top_srcdir)/src
 
 # The callback examples reference libc only through libhttrack, so the direct
 # libc edge gets dropped from DT_NEEDED (library-not-linked-against-libc).

m4/Makefile.am

@@ -1 +1,3 @@
-EXTRA_DIST = *.m4
+# Glob against $(srcdir) so "make dist" works out-of-tree (a bare "*.m4" is
+# resolved against the build dir, where there are no sources).
+EXTRA_DIST = $(srcdir)/*.m4

man/Makefile.am

@@ -13,3 +13,9 @@ regen-man: makeman.sh $(top_builddir)/src/httrack$(EXEEXT)
 	README='$(top_srcdir)/README' $(SHELL) $(srcdir)/makeman.sh \
 		'$(top_builddir)/src/httrack$(EXEEXT)' > $(srcdir)/httrack.1
 .PHONY: regen-man
+
+# Render html/httrack.man.html from httrack.1. Needs the groff html device
+# (Debian: full "groff" package, not "groff-base"). Run by hand: make -C man regen-man-html
+regen-man-html: httrack.1
+	groff -t -man -Thtml $(srcdir)/httrack.1 > $(top_srcdir)/html/httrack.man.html
+.PHONY: regen-man-html

man/Makefile.in

@@ -551,6 +551,12 @@ regen-man: makeman.sh $(top_builddir)/src/httrack$(EXEEXT)
 		'$(top_builddir)/src/httrack$(EXEEXT)' > $(srcdir)/httrack.1
 .PHONY: regen-man
 
+# Render html/httrack.man.html from httrack.1. Needs the groff html device
+# (Debian: full "groff" package, not "groff-base"). Run by hand: make -C man regen-man-html
+regen-man-html: httrack.1
+	groff -t -man -Thtml $(srcdir)/httrack.1 > $(top_srcdir)/html/httrack.man.html
+.PHONY: regen-man-html
+
 # Tell versions [3.59,3.63) of GNU make to not export all variables.
 # Otherwise a system limit (for SysV at least) may be exceeded.
 .NOEXPORT:

man/htsserver.1

@@ -1,6 +1,7 @@
 .\" Process this file with
 .\" groff -man -Tascii htsserver.1
 .\"
+.\" SPDX-License-Identifier: GPL-3.0-or-later
 .TH htsserver 1 "Mar 2003" "httrack website copier"
 .SH NAME
 htsserver \- offline browser server : copy websites to a local directory
@@ -35,7 +36,7 @@ Please reports bugs to
 .B <bugs@httrack.com>.
 Include a complete, self-contained example that will allow the bug to be reproduced, and say which version of (web)httrack you are using. Do not forget to detail options used, OS version, and any other information you deem necessary.
 .SH COPYRIGHT
-Copyright (C) 1998-2013 Xavier Roche and other contributors
+Copyright (C) 1998-2026 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

man/httrack.1

@@ -2,7 +2,8 @@
 .\" groff -man -Tascii httrack.1
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
-.TH httrack 1 "07 June 2026" "httrack website copier"
+.\" SPDX-License-Identifier: GPL-3.0-or-later
+.TH httrack 1 "13 June 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -98,15 +99,15 @@ httrack \- offline browser : copy websites to a local directory
 allows you to download a World Wide Web site from the Internet to a local directory, building recursively all directories, getting HTML, images, and other files from the server to your computer. HTTrack arranges the original site's relative link-structure. Simply open a page of the "mirrored" website in your browser, and you can browse the site from link to link, as if you were viewing it online. HTTrack can also update an existing mirrored site, and resume interrupted downloads.
 .SH EXAMPLES
 .TP
-.B httrack www.someweb.com/bob/
-mirror site www.someweb.com/bob/ and only this site
+.B httrack www.example.com/bob/
+mirror site www.example.com/bob/ and only this site
 .TP
-.B httrack www.someweb.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg \-mime:application/*
+.B httrack www.example.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg \-mime:application/*
 mirror the two sites together (with shared links) and accept any .jpg files on .com sites
 .TP
-.B httrack www.someweb.com/bob/bobby.html +* \-r6
+.B httrack www.example.com/bob/bobby.html +* \-r6
 .TP
-.B httrack www.someweb.com/bob/bobby.html \-\-spider \-P proxy.myhost.com:8080
+.B httrack www.example.com/bob/bobby.html \-\-spider \-P proxy.myhost.com:8080
 .TP
 .B httrack \-\-update
 .TP
@@ -411,7 +412,7 @@ File type (ex: gif)
 .IP \-%p
 Path [without ending /] (ex: /someimages)
 .IP \-%h
-Host name (ex: www.someweb.com)
+Host name (ex: www.example.com)
 .IP \-%M
 URL MD5 (128 bits, 32 ascii bytes)
 .IP \-%Q

man/makeman.sh

@@ -110,6 +110,7 @@ cat <<'EOF'
 .\" groff -man -Tascii httrack.1
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
+.\" SPDX-License-Identifier: GPL-3.0-or-later
 EOF
 printf '.TH httrack 1 "%s" "httrack website copier"\n' "$date_str"
 cat <<'EOF'

man/proxytrack.1

@@ -1,6 +1,7 @@
 .\" Process this file with
 .\" groff -man -Tascii proxytrack.1
 .\"
+.\" SPDX-License-Identifier: GPL-3.0-or-later
 .TH proxytrack 1 "Mar 2003" "httrack website copier"
 .SH NAME
 proxytrack \- proxy to serve content archived by httrack website copier
@@ -25,7 +26,7 @@ Please reports bugs to
 .B <bugs@httrack.com>.
 Include a complete, self-contained example that will allow the bug to be reproduced, and say which version of (web)httrack you are using. Do not forget to detail options used, OS version, and any other information you deem necessary.
 .SH COPYRIGHT
-Copyright (C) 1998-2013 Xavier Roche and other contributors
+Copyright (C) 1998-2026 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

man/webhttrack.1

@@ -1,6 +1,7 @@
 .\" Process this file with
 .\" groff -man -Tascii webhttrack.1
 .\"
+.\" SPDX-License-Identifier: GPL-3.0-or-later
 .TH webhttrack 1 "Mar 2003" "httrack website copier"
 .SH NAME
 webhttrack \- offline browser : copy websites to a local directory
@@ -36,7 +37,7 @@ Please reports bugs to
 .B <bugs@httrack.com>.
 Include a complete, self-contained example that will allow the bug to be reproduced, and say which version of (web)httrack you are using. Do not forget to detail options used, OS version, and any other information you deem necessary.
 .SH COPYRIGHT
-Copyright (C) 1998-2013 Xavier Roche and other contributors
+Copyright (C) 1998-2026 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

src/Makefile.am

@@ -56,6 +56,7 @@ whttrackrundir = $(bindir)
 whttrackrun_SCRIPTS = webhttrack
 
 libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
+	htscache_selftest.c \
 	htscatchurl.c htsfilters.c htsftp.c htshash.c coucal/coucal.c \
 	htshelp.c htslib.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
@@ -65,7 +66,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.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 htscatchurl.h  \
+	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htscatchurl.h  \
 	htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
 	htsfilters.h htsftp.h htsglobal.h htshash.h coucal/coucal.h \
 	htshelp.h htsindex.h htslib.h htsmd5.h \

src/hts-indextmpl.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsalias.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -266,13 +268,18 @@ const char *hts_optalias[][4] = {
   return value: number of arguments treated (0 if error)
 */
 int optalias_check(int argc, const char *const *argv, int n_arg,
-                   int *return_argc, char **return_argv, char *return_error) {
+                   int *return_argc, char **return_argv,
+                   size_t return_argv_size, char *return_error,
+                   size_t return_error_size) {
   return_error[0] = '\0';
   *return_argc = 1;
   if (argv[n_arg][0] == '-')
     if (argv[n_arg][1] == '-') {
-      char command[1000];
-      char param[1000];
+      /* sized to HTS_CDLMAXSIZE: a long-form option value (--user-agent,
+         --headers, ...) is copied into param, and the value is bounded by the
+         general per-argument check in htscoremain.c (HTS_CDLMAXSIZE) */
+      char command[HTS_CDLMAXSIZE];
+      char param[HTS_CDLMAXSIZE];
       char addcommand[256];
 
       /* */
@@ -320,9 +327,10 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
           /* Copy parameters? */
           if (need_param == 2) {
             if ((n_arg + 1 >= argc) || (argv[n_arg + 1][0] == '-')) {   /* no supplemental parameter */
-              sprintf(return_error,
-                      "Syntax error:\n\tOption %s needs to be followed by a parameter: %s <param>\n\t%s\n",
-                      command, command, _NOT_NULL(optalias_help(command)));
+              snprintf(return_error, return_error_size,
+                       "Syntax error:\n\tOption %s needs to be followed by a "
+                       "parameter: %s <param>\n\t%s\n",
+                       command, command, _NOT_NULL(optalias_help(command)));
               return 0;
             }
             strcpybuff(param, argv[n_arg + 1]);
@@ -335,35 +343,36 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
 
         /* Must be alone (-P /tmp) */
         if (strcmp(hts_optalias[pos][2], "param1") == 0) {
-          strcpybuff(return_argv[0], command);
-          strcpybuff(return_argv[1], param);
+          strlcpybuff(return_argv[0], command, return_argv_size);
+          strlcpybuff(return_argv[1], param, return_argv_size);
           *return_argc = 2;     /* 2 parameters returned */
         }
         /* Alone with parameter (+*.gif) */
         else if (strcmp(hts_optalias[pos][2], "param0") == 0) {
           /* Command */
-          strcpybuff(return_argv[0], command);
-          strcatbuff(return_argv[0], param);
+          strlcpybuff(return_argv[0], command, return_argv_size);
+          strlcatbuff(return_argv[0], param, return_argv_size);
         }
         /* Together (-c8) */
         else {
           /* Command */
-          strcpybuff(return_argv[0], command);
+          strlcpybuff(return_argv[0], command, return_argv_size);
           /* Parameters accepted */
           if (strncmp(hts_optalias[pos][2], "param", 5) == 0) {
             /* --cache=off or --index=on */
             if (strcmp(param, "off") == 0)
-              strcatbuff(return_argv[0], "0");
+              strlcatbuff(return_argv[0], "0", return_argv_size);
             else if (strcmp(param, "on") == 0) {
               // on is the default
               // strcatbuff(return_argv[0],"1");
             } else
-              strcatbuff(return_argv[0], param);
+              strlcatbuff(return_argv[0], param, return_argv_size);
           }
           *return_argc = 1;     /* 1 parameter returned */
         }
       } else {
-        sprintf(return_error, "Unknown option: %s\n", command);
+        snprintf(return_error, return_error_size, "Unknown option: %s\n",
+                 command);
         return 0;
       }
       return need_param;
@@ -377,15 +386,16 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
       if ((strcmp(hts_optalias[pos][2], "param1") == 0)
           || (strcmp(hts_optalias[pos][2], "param0") == 0)) {
         if ((n_arg + 1 >= argc) || (argv[n_arg + 1][0] == '-')) {       /* no supplemental parameter */
-          sprintf(return_error,
-                  "Syntax error:\n\tOption %s needs to be followed by a parameter: %s <param>\n\t%s\n",
-                  argv[n_arg], argv[n_arg],
-                  _NOT_NULL(optalias_help(argv[n_arg])));
+          snprintf(return_error, return_error_size,
+                   "Syntax error:\n\tOption %s needs to be followed by a "
+                   "parameter: %s <param>\n\t%s\n",
+                   argv[n_arg], argv[n_arg],
+                   _NOT_NULL(optalias_help(argv[n_arg])));
           return 0;
         }
         /* Copy parameters */
-        strcpybuff(return_argv[0], argv[n_arg]);
-        strcpybuff(return_argv[1], argv[n_arg + 1]);
+        strlcpybuff(return_argv[0], argv[n_arg], return_argv_size);
+        strlcpybuff(return_argv[1], argv[n_arg + 1], return_argv_size);
         /* And return */
         *return_argc = 2;       /* 2 parameters returned */
         return 2;               /* 2 parameters used */
@@ -394,7 +404,7 @@ int optalias_check(int argc, const char *const *argv, int n_arg,
   }
 
   /* Copy and return other unknown option */
-  strcpybuff(return_argv[0], argv[n_arg]);
+  strlcpybuff(return_argv[0], argv[n_arg], return_argv_size);
   return 1;
 }
 
@@ -521,9 +531,10 @@ int optinclude_file(const char *name, int *argc, char **argv, char *x_argvblk,
             strcatbuff(_tmp_argv[0], a);
             strcpybuff(_tmp_argv[1], b);
 
-            result =
-              optalias_check(2, (const char *const *) tmp_argv, 0, &return_argc,
-                             (tmp_argv + 2), return_error);
+            result = optalias_check(2, (const char *const *) tmp_argv, 0,
+                                    &return_argc, (tmp_argv + 2),
+                                    sizeof(_tmp_argv[0]), return_error,
+                                    sizeof(return_error));
             if (!result) {
               printf("%s\n", return_error);
             } else {

src/htsalias.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -38,7 +40,9 @@ Please visit our Website: http://www.httrack.com
 #ifdef HTS_INTERNAL_BYTECODE
 extern const char *hts_optalias[][4];
 int optalias_check(int argc, const char *const *argv, int n_arg,
-                   int *return_argc, char **return_argv, char *return_error);
+                   int *return_argc, char **return_argv,
+                   size_t return_argv_size, char *return_error,
+                   size_t return_error_size);
 int optalias_find(const char *token);
 const char *optalias_help(const char *token);
 int optreal_find(const char *token);

src/htsarrays.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 2014 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

src/htsback.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -1516,9 +1518,11 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 
           if (sscanf(text, "%d", &code) == 1) { // got code
             back[p].r.statuscode = code;
-            back[p].status = STATUS_READY;      // terminé
+            back[p].status = STATUS_READY;      // done
             if (lf != NULL && *lf != '\0') {    // got location ?
-              strcpybuff(back[p].r.location, lf + 1);
+              // r.location aliases location_buffer (set above); write the array
+              // so the bounded macro picks up its capacity.
+              strcpybuff(back[p].location_buffer, lf + 1);
             }
             return 0;
           }
@@ -3996,26 +4000,30 @@ LLint back_transferred(LLint nb, struct_back * sback) {
   return nb;
 }
 
-// infos backing
-// j: 1 afficher sockets 2 afficher autres 3 tout afficher
+// backing info
+// j: 1=show sockets 2=show others 3=show all
 void back_info(struct_back * sback, int i, int j, FILE * fp) {
   lien_back *const back = sback->lnk;
   const int back_max = sback->count;
 
   assertf(i >= 0 && i < back_max);
   if (back[i].status >= 0) {
-    char BIGSTK s[HTS_URLMAXSIZE * 2 + 1024];
+    // Holds the status tag plus the full URL: url_adr and url_fil are each
+    // HTS_URLMAXSIZE*2, so reserve room for both (*4) plus framing/trailer.
+    // Undersizing would make back_infostr's bounded appends abort on a long
+    // URL.
+    char BIGSTK s[HTS_URLMAXSIZE * 4 + 1024];
 
     s[0] = '\0';
-    back_infostr(sback, i, j, s);
+    back_infostr(sback, i, j, s, sizeof(s));
     strcatbuff(s, LF);
     fprintf(fp, "%s", s);
   }
 }
 
-// infos backing
-// j: 1 afficher sockets 2 afficher autres 3 tout afficher
-void back_infostr(struct_back * sback, int i, int j, char *s) {
+// backing info
+// j: 1=show sockets 2=show others 3=show all
+void back_infostr(struct_back *sback, int i, int j, char *s, size_t size) {
   lien_back *const back = sback->lnk;
   const int back_max = sback->count;
 
@@ -4025,16 +4033,16 @@ void back_infostr(struct_back * sback, int i, int j, char *s) {
 
     if (j & 1) {
       if (back[i].status == STATUS_CONNECTING) {
-        strcatbuff(s, "CONNECT ");
+        strlcatbuff(s, "CONNECT ", size);
       } else if (back[i].status == STATUS_WAIT_HEADERS) {
-        strcatbuff(s, "INFOS ");
+        strlcatbuff(s, "INFOS ", size);
         aff = 1;
       } else if (back[i].status == STATUS_CHUNK_WAIT
                  || back[i].status == STATUS_CHUNK_CR) {
-        strcatbuff(s, "INFOSC");        // infos chunk
+        strlcatbuff(s, "INFOSC", size); // chunk info
         aff = 1;
       } else if (back[i].status > 0) {
-        strcatbuff(s, "RECEIVE ");
+        strlcatbuff(s, "RECEIVE ", size);
         aff = 1;
       }
     }
@@ -4042,44 +4050,44 @@ void back_infostr(struct_back * sback, int i, int j, char *s) {
       if (back[i].status == STATUS_READY) {
         switch (back[i].r.statuscode) {
         case 200:
-          strcatbuff(s, "READY ");
+          strlcatbuff(s, "READY ", size);
           aff = 1;
           break;
         case -1:
-          strcatbuff(s, "ERROR ");
+          strlcatbuff(s, "ERROR ", size);
           aff = 1;
           break;
         case -2:
-          strcatbuff(s, "TIMEOUT ");
+          strlcatbuff(s, "TIMEOUT ", size);
           aff = 1;
           break;
         case -3:
-          strcatbuff(s, "TOOSLOW ");
+          strlcatbuff(s, "TOOSLOW ", size);
           aff = 1;
           break;
         case 400:
-          strcatbuff(s, "BADREQUEST ");
+          strlcatbuff(s, "BADREQUEST ", size);
           aff = 1;
           break;
         case 401:
         case 403:
-          strcatbuff(s, "FORBIDDEN ");
+          strlcatbuff(s, "FORBIDDEN ", size);
           aff = 1;
           break;
         case 404:
-          strcatbuff(s, "NOT FOUND ");
+          strlcatbuff(s, "NOT FOUND ", size);
           aff = 1;
           break;
         case 500:
-          strcatbuff(s, "SERVERROR ");
+          strlcatbuff(s, "SERVERROR ", size);
           aff = 1;
           break;
         default:
           {
             char s2[256];
 
-            sprintf(s2, "ERROR(%d)", back[i].r.statuscode);
-            strcatbuff(s, s2);
+            snprintf(s2, sizeof(s2), "ERROR(%d)", back[i].r.statuscode);
+            strlcatbuff(s, s2, size);
           }
           aff = 1;
         }
@@ -4090,16 +4098,18 @@ void back_infostr(struct_back * sback, int i, int j, char *s) {
       {
         char BIGSTK s2[HTS_URLMAXSIZE * 2 + 1024];
 
-        sprintf(s2, "\"%s", back[i].url_adr);
-        strcatbuff(s, s2);
+        snprintf(s2, sizeof(s2), "\"%s", back[i].url_adr);
+        strlcatbuff(s, s2, size);
 
         if (back[i].url_fil[0] != '/')
-          strcatbuff(s, "/");
-        sprintf(s2, "%s\" ", back[i].url_fil);
-        strcatbuff(s, s2);
-        sprintf(s, LLintP " " LLintP " ", (LLint) back[i].r.size,
-                (LLint) back[i].r.totalsize);
-        strcatbuff(s, s2);
+          strlcatbuff(s, "/", size);
+        snprintf(s2, sizeof(s2), "%s\" ", back[i].url_fil);
+        strlcatbuff(s, s2, size);
+        // size/totalsize trailer: build in s2, then append (the old code wrote
+        // straight into s here, clobbering the URL it had just assembled).
+        snprintf(s2, sizeof(s2), LLintP " " LLintP " ", (LLint) back[i].r.size,
+                 (LLint) back[i].r.totalsize);
+        strlcatbuff(s, s2, size);
       }
     }
   }

src/htsback.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -127,7 +129,7 @@ int back_trylive(httrackp * opt, cache_back * cache, struct_back * sback,
 int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                   const int p);
 void back_info(struct_back * sback, int i, int j, FILE * fp);
-void back_infostr(struct_back * sback, int i, int j, char *s);
+void back_infostr(struct_back *sback, int i, int j, char *s, size_t size);
 LLint back_transferred(LLint add, struct_back * sback);
 
 // hostback

src/htsbase.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsbasenet.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsbauth.c

@@ -1,6 +1,8 @@
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -102,7 +104,8 @@ int cookie_add(t_cookie * cookie, const char *cook_name, const char *cook_value,
   strcatbuff(cook, "\n");
   if (!((strlen(cookie->data) + strlen(cook)) < cookie->max_len))
     return -1;                  // impossible d'ajouter
-  cookie_insert(insert, cook);
+  cookie_insert(insert, cookie->max_len - (size_t) (insert - cookie->data),
+                cook);
 #if DEBUG_COOK
   printf("add_new cookie: name=\"%s\" value=\"%s\" domain=\"%s\" path=\"%s\"\n",
          cook_name, cook_value, domain, path);
@@ -118,7 +121,7 @@ int cookie_del(t_cookie * cookie, const char *cook_name, const char *domain, con
   b = cookie_find(cookie->data, cook_name, domain, path);
   if (b) {
     a = cookie_nextfield(b);
-    cookie_delete(b, a - b);
+    cookie_delete(b, cookie->max_len - (size_t) (b - cookie->data), a - b);
 #if DEBUG_COOK
     printf("deleted old cookie: %s %s %s\n", cook_name, domain, path);
 #endif
@@ -336,41 +339,44 @@ int cookie_save(t_cookie * cookie, const char *name) {
   return -1;
 }
 
-// insertion chaine ins avant s
-void cookie_insert(char *s, const char *ins) {
+// Insert string ins before s. s_size is the capacity of the buffer at s.
+void cookie_insert(char *s, size_t s_size, const char *ins) {
   char *buff;
 
-  if (strnotempty(s) == 0) {    // rien à faire, juste concat
-    strcatbuff(s, ins);
+  if (strnotempty(s) == 0) { // nothing there yet: just concatenate
+    strlcatbuff(s, ins, s_size);
   } else {
     buff = (char *) malloct(strlen(s) + 1);
     if (buff) {
-      strcpybuff(buff, s);      // copie temporaire
-      strcpybuff(s, ins);       // insérer
-      strcatbuff(s, buff);      // copier
+      strlcpybuff(buff, s, strlen(s) + 1); // temporary copy of s
+      strlcpybuff(s, ins, s_size);         // write ins
+      strlcatbuff(s, buff, s_size);        // then the saved content
       freet(buff);
     }
   }
 }
 
-// destruction chaine dans s position pos
-void cookie_delete(char *s, size_t pos) {
+// Delete the substring of s at position pos. s_size is the capacity at s.
+void cookie_delete(char *s, size_t s_size, size_t pos) {
   char *buff;
 
-  if (strnotempty(s + pos) == 0) {      // rien à faire, effacer
+  if (strnotempty(s + pos) == 0) { // nothing after pos: truncate
     s[0] = '\0';
   } else {
     buff = (char *) malloct(strlen(s + pos) + 1);
     if (buff) {
-      strcpybuff(buff, s + pos);        // copie temporaire
-      strcpybuff(s, buff);      // copier
+      strlcpybuff(buff, s + pos, strlen(s + pos) + 1); // temporary copy
+      strlcpybuff(s, buff, s_size);                    // overwrite from start
       freet(buff);
     }
   }
 }
 
-// renvoie champ param de la chaine cookie_base
-// ex: cookie_get("ceci est<tab>un<tab>exemple",1) renvoi "un"
+// Return field <param> (0-based, tab-separated) of the cookie line cookie_base,
+// into buffer. ex: cookie_get("ceci est<tab>un<tab>exemple", 1) returns "un".
+// buffer must hold at least COOKIE_FIELD_BUFFER_SIZE bytes (all callers use
+// char[8192]).
+#define COOKIE_FIELD_BUFFER_SIZE 8192
 const char *cookie_get(char *buffer, const char *cookie_base, int param) {
   const char *limit;
 
@@ -394,11 +400,11 @@ const char *cookie_get(char *buffer, const char *cookie_base, int param) {
     if (cookie_base) {
       if (cookie_base < limit) {
         const char *a = cookie_base;
+        htsbuff b = htsbuff_ptr(buffer, COOKIE_FIELD_BUFFER_SIZE);
 
         while((*a) && (*a != '\t') && (*a != '\n'))
           a++;
-        buffer[0] = '\0';
-        strncatbuff(buffer, cookie_base, (int) (a - cookie_base));
+        htsbuff_catn(&b, cookie_base, (size_t) (a - cookie_base));
         return buffer;
       } else
         return "";
@@ -458,11 +464,13 @@ char *bauth_check(t_cookie * cookie, const char *adr, const char *fil) {
   return NULL;
 }
 
+/* Build the auth prefix (host + path, query stripped) into prefix.
+   Callers pass a buffer of HTS_URLMAXSIZE * 2 bytes. */
 char *bauth_prefix(char *prefix, const char *adr, const char *fil) {
   char *a;
 
-  strcpybuff(prefix, jump_identification_const(adr));
-  strcatbuff(prefix, fil);
+  strlcpybuff(prefix, jump_identification_const(adr), HTS_URLMAXSIZE * 2);
+  strlcatbuff(prefix, fil, HTS_URLMAXSIZE * 2);
   a = strchr(prefix, '?');
   if (a)
     *a = '\0';

src/htsbauth.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -67,8 +69,8 @@ int cookie_add(t_cookie * cookie, const  char *cook_name, const  char *cook_valu
 int cookie_del(t_cookie * cookie, const char *cook_name, const char *domain, const char *path);
 int cookie_load(t_cookie * cookie, const char *path, const char *name);
 int cookie_save(t_cookie * cookie, const char *name);
-void cookie_insert(char *s, const char *ins);
-void cookie_delete(char *s, size_t pos);
+void cookie_insert(char *s, size_t s_size, const char *ins);
+void cookie_delete(char *s, size_t s_size, size_t pos);
 const char *cookie_get(char *buffer, const char *cookie_base, int param);
 char *cookie_find(char *s, const char *cook_name, const char *domain, const char *path);
 char *cookie_nextfield(char *a);

src/htscache.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -196,12 +198,13 @@ struct cache_back_zip_entry {
   int compressionMethod;
 };
 
-#define ZIP_READFIELD_STRING(line, value, refline, refvalue) do { \
-  if (line[0] != '\0' && strfield2(line, refline)) { \
-    strcpybuff(refvalue, value); \
-    line[0] = '\0'; \
-	} \
-} while(0)
+#define ZIP_READFIELD_STRING(line, value, refline, refvalue, refvalue_size)    \
+  do {                                                                         \
+    if (line[0] != '\0' && strfield2(line, refline)) {                         \
+      strlcpybuff(refvalue, value, refvalue_size);                             \
+      line[0] = '\0';                                                          \
+    }                                                                          \
+  } while (0)
 #define ZIP_READFIELD_INT(line, value, refline, refvalue) do { \
   if (line[0] != '\0' && strfield2(line, refline)) { \
     int intval = 0; \
@@ -643,7 +646,7 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
   } else {
     r.location = location_default;
   }
-  strcpybuff(r.location, "");
+  r.location[0] = '\0';
   strcpybuff(buff, adr);
   strcatbuff(buff, fil);
   hash_pos_return = coucal_read(cache->hashtable, buff, &hash_pos);
@@ -706,17 +709,25 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
                 value++;
               ZIP_READFIELD_INT(line, value, "X-In-Cache", dataincache);
               ZIP_READFIELD_INT(line, value, "X-Statuscode", r.statuscode);
-              ZIP_READFIELD_STRING(line, value, "X-StatusMessage", r.msg);      // msg
+              ZIP_READFIELD_STRING(line, value, "X-StatusMessage", r.msg,
+                                   sizeof(r.msg));
               ZIP_READFIELD_LLINT(line, value, "X-Size", r.size);       // size
-              ZIP_READFIELD_STRING(line, value, "Content-Type", r.contenttype); // contenttype
-              ZIP_READFIELD_STRING(line, value, "X-Charset", r.charset);        // contenttype
-              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, "Content-Type", r.contenttype,
+                                   sizeof(r.contenttype));
+              ZIP_READFIELD_STRING(line, value, "X-Charset", r.charset,
+                                   sizeof(r.charset));
+              ZIP_READFIELD_STRING(line, value, "Last-Modified", r.lastmodified,
+                                   sizeof(r.lastmodified));
+              ZIP_READFIELD_STRING(line, value, "Etag", r.etag, sizeof(r.etag));
+              // r.location is a char* pointing into a HTS_URLMAXSIZE*2 buffer
+              ZIP_READFIELD_STRING(line, value, "Location", r.location,
+                                   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_);      // Original save filename
+              ZIP_READFIELD_STRING(line, value, "X-Save", previous_save_,
+                                   sizeof(previous_save_));
             }
           } while(offset < readSizeHeader && !lineEof);
           //totalHeader = offset;
@@ -733,7 +744,7 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
             }
           }
           if (return_save != NULL) {
-            strcpybuff(return_save, previous_save);
+            strlcpybuff(return_save, previous_save, HTS_URLMAXSIZE * 2);
           }
 
           /* Complete fields */
@@ -1025,7 +1036,7 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
   } else {
     r.location = location_default;
   }
-  strcpybuff(r.location, "");
+  r.location[0] = '\0';
 #if HTS_FAST_CACHE
   strcpybuff(buff, adr);
   strcatbuff(buff, fil);
@@ -1096,30 +1107,34 @@ static htsblk cache_readex_old(httrackp * opt, cache_back * cache,
         //
         cache_rint(cache->olddat, &r.statuscode);
         cache_rLLint(cache->olddat, &r.size);
-        cache_rstr(cache->olddat, r.msg);
-        cache_rstr(cache->olddat, r.contenttype);
+        cache_rstr(cache->olddat, r.msg, sizeof(r.msg));
+        cache_rstr(cache->olddat, r.contenttype, sizeof(r.contenttype));
         if (cache->version >= 3)
-          cache_rstr(cache->olddat, r.charset);
-        cache_rstr(cache->olddat, r.lastmodified);
-        cache_rstr(cache->olddat, r.etag);
-        cache_rstr(cache->olddat, r.location);
+          cache_rstr(cache->olddat, r.charset, sizeof(r.charset));
+        cache_rstr(cache->olddat, r.lastmodified, sizeof(r.lastmodified));
+        cache_rstr(cache->olddat, r.etag, sizeof(r.etag));
+        // r.location points into a HTS_URLMAXSIZE*2 buffer
+        cache_rstr(cache->olddat, r.location, HTS_URLMAXSIZE * 2);
         if (cache->version >= 2)
-          cache_rstr(cache->olddat, r.cdispo);
+          cache_rstr(cache->olddat, r.cdispo, sizeof(r.cdispo));
         if (cache->version >= 4) {
-          cache_rstr(cache->olddat, previous_save);     // adr
-          cache_rstr(cache->olddat, previous_save);     // fil
+          cache_rstr(cache->olddat, previous_save,
+                     sizeof(previous_save)); // adr
+          cache_rstr(cache->olddat, previous_save,
+                     sizeof(previous_save)); // fil
           previous_save[0] = '\0';
-          cache_rstr(cache->olddat, previous_save);     // save
+          cache_rstr(cache->olddat, previous_save,
+                     sizeof(previous_save)); // save
           if (return_save != NULL) {
-            strcpybuff(return_save, previous_save);
+            strlcpybuff(return_save, previous_save, HTS_URLMAXSIZE * 2);
           }
         }
         if (cache->version >= 5) {
           r.headers = cache_rstr_addr(cache->olddat);
         }
         //
-        cache_rstr(cache->olddat, check);
-        if (strcmp(check, "HTS") == 0) {        /* intégrité OK */
+        cache_rstr(cache->olddat, check, sizeof(check));
+        if (strcmp(check, "HTS") == 0) { /* integrity OK */
           ok = 1;
         }
         cache_rLLint(cache->olddat, &size_read);        /* lire size pour être sûr de la taille déclarée (réécrire) */
@@ -1758,12 +1773,12 @@ void cache_init(cache_back * cache, httrackp * opt) {
           char firstline[256];
           char *a = cache->use;
 
-          a += cache_brstr(a, firstline);
-          if (strncmp(firstline, "CACHE-", 6) == 0) {   // Nouvelle version du cache
-            if (strncmp(firstline, "CACHE-1.", 8) == 0) {       // Version 1.1x
+          a += cache_brstr(a, firstline, sizeof(firstline));
+          if (strncmp(firstline, "CACHE-", 6) == 0) {     // new cache format
+            if (strncmp(firstline, "CACHE-1.", 8) == 0) { // version 1.1x
               cache->version = (int) (firstline[8] - '0');      // cache 1.x
               if (cache->version <= 5) {
-                a += cache_brstr(a, firstline);
+                a += cache_brstr(a, firstline, sizeof(firstline));
                 strcpybuff(cache->lastmodified, firstline);
               } else {
                 hts_log_print(opt, LOG_ERROR,
@@ -1774,7 +1789,7 @@ void cache_init(cache_back * cache, httrackp * opt) {
                 freet(cache->use);
                 cache->use = NULL;
               }
-            } else {            // non supporté
+            } else { // non supporté
               hts_log_print(opt, LOG_ERROR,
                             "Cache: %s not supported, ignoring current cache",
                             firstline);
@@ -1784,7 +1799,7 @@ void cache_init(cache_back * cache, httrackp * opt) {
               cache->use = NULL;
             }
             /* */
-          } else {              // Vieille version du cache
+          } else { // Vieille version du cache
             /* */
             hts_log_print(opt, LOG_WARNING,
                           "Cache: importing old cache format");
@@ -2088,7 +2103,7 @@ char *readfile_or(const char *fil, const char *defaultdata) {
     char *adr = malloct(strlen(defaultdata) + 1);
 
     if (adr) {
-      strcpybuff(adr, defaultdata);
+      strlcpybuff(adr, defaultdata, strlen(defaultdata) + 1);
       return adr;
     }
   }
@@ -2109,7 +2124,7 @@ int cache_wstr(FILE * fp, const char *s) {
     return -1;
   return 0;
 }
-void cache_rstr(FILE * fp, char *s) {
+void cache_rstr(FILE *fp, char *s, size_t s_size) {
   INTsys i;
   char buff[256 + 4];
 
@@ -2118,13 +2133,26 @@ void cache_rstr(FILE * fp, char *s) {
   if (i < 0 || i > 32768)       /* error, something nasty happened */
     i = 0;
   if (i > 0) {
-    if ((int) fread(s, 1, i, fp) != i) {
+    /* Store at most s_size-1 bytes into s, but consume all i bytes from the
+       stream so the next field stays aligned (the field may be longer than the
+       destination in a tampered/old cache). */
+    const size_t want = (size_t) i;
+    const size_t store = want < s_size ? want : s_size - 1;
+
+    if (fread(s, 1, store, fp) != store) {
       int fread_cache_failed = 0;
 
       assertf(fread_cache_failed);
     }
+    if (want > store && fseek(fp, (long) (want - store), SEEK_CUR) != 0) {
+      int fseek_cache_failed = 0;
+
+      assertf(fseek_cache_failed);
+    }
+    s[store] = '\0';
+  } else {
+    s[0] = '\0';
   }
-  *(s + i) = '\0';
 }
 char *cache_rstr_addr(FILE * fp) {
   INTsys i;
@@ -2148,7 +2176,7 @@ char *cache_rstr_addr(FILE * fp) {
   }
   return addr;
 }
-int cache_brstr(char *adr, char *s) {
+int cache_brstr(char *adr, char *s, size_t s_size) {
   int i;
   int off;
   char buff[256 + 4];
@@ -2156,23 +2184,17 @@ int cache_brstr(char *adr, char *s) {
   off = binput(adr, buff, 256);
   adr += off;
   sscanf(buff, "%d", &i);
-  if (i > 0)
-    strncpy(s, adr, i);
-  *(s + i) = '\0';
-  off += i;
-  return off;
-}
-int cache_quickbrstr(char *adr, char *s) {
-  int i;
-  int off;
-  char buff[256 + 4];
+  if (i < 0 || i > 32768) /* guard a corrupt length */
+    i = 0;
+  if (i > 0) {
+    /* copy at most s_size-1 bytes; advance past the full field regardless */
+    const size_t store = (size_t) i < s_size ? (size_t) i : s_size - 1;
 
-  off = binput(adr, buff, 256);
-  adr += off;
-  sscanf(buff, "%d", &i);
-  if (i > 0)
-    strncpy(s, adr, i);
-  *(s + i) = '\0';
+    strncpy(s, adr, store);
+    s[store] = '\0';
+  } else {
+    s[0] = '\0';
+  }
   off += i;
   return off;
 }
@@ -2180,7 +2202,7 @@ int cache_quickbrstr(char *adr, char *s) {
 /* idem, mais en int */
 int cache_brint(char *adr, int *i) {
   char s[256];
-  int r = cache_brstr(adr, s);
+  int r = cache_brstr(adr, s, sizeof(s));
 
   if (r != -1)
     sscanf(s, "%d", i);
@@ -2189,7 +2211,7 @@ int cache_brint(char *adr, int *i) {
 void cache_rint(FILE * fp, int *i) {
   char s[256];
 
-  cache_rstr(fp, s);
+  cache_rstr(fp, s, sizeof(s));
   sscanf(s, "%d", i);
 }
 int cache_wint(FILE * fp, int i) {
@@ -2201,7 +2223,7 @@ int cache_wint(FILE * fp, int i) {
 void cache_rLLint(FILE * fp, LLint * i) {
   char s[256];
 
-  cache_rstr(fp, s);
+  cache_rstr(fp, s, sizeof(s));
   sscanf(s, LLintP, i);
 }
 int cache_wLLint(FILE * fp, LLint i) {

src/htscache.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -80,10 +82,9 @@ int cache_writedata(FILE * cache_ndx, FILE * cache_dat, const char *str1,
 int cache_readdata(cache_back * cache, const char *str1, const char *str2,
                    char **inbuff, int *len);
 
-void cache_rstr(FILE * fp, char *s);
+void cache_rstr(FILE *fp, char *s, size_t s_size);
 char *cache_rstr_addr(FILE * fp);
-int cache_brstr(char *adr, char *s);
-int cache_quickbrstr(char *adr, char *s);
+int cache_brstr(char *adr, char *s, size_t s_size);
 int cache_brint(char *adr, int *i);
 void cache_rint(FILE * fp, int *i);
 void cache_rLLint(FILE * fp, LLint * i);

src/htscache_selftest.c

@@ -0,0 +1,376 @@
+/* ------------------------------------------------------------ */
+/*
+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/>.
+
+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: htscache_selftest.c subroutines:                       */
+/*       in-process self-test for the (ZIP) cache subsystem      */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+/* Drives the public cache API (cache_init / cache_add / cache_readex)
+   through a create -> read -> update cycle on a real on-disk ZIP cache,
+   asserting every header field and the (binary-safe) body round-trips.
+   Besides a few hand-crafted edge cases it stores a few thousand entries
+   (index/lookup scale) and a handful of large compressible/incompressible
+   bodies (zlib deflate/inflate). Reached via `httrack -#A <dir>`. */
+
+#define HTS_INTERNAL_BYTECODE
+
+#include "htscache_selftest.h"
+
+#include "htscache.h"
+#include "htscore.h"
+#include "htslib.h"
+#include "htszlib.h"
+
+#include <stdio.h>
+#include <string.h>
+
+#define SELFTEST_VOLUME 3000 /* number of small entries in the scale pass */
+
+/* Open a cache session. A write session (ro=0) rotates new.zip -> old.zip and
+   opens a fresh new.zip; a read session (ro=1) opens new.zip in place. */
+static void selftest_open(cache_back *cache, httrackp *opt, int ro) {
+  memset(cache, 0, sizeof(*cache));
+  cache->type = 1;
+  cache->log = stderr;
+  cache->errlog = stderr;
+  cache->hashtable = coucal_new(0);
+  cache->ro = ro;
+  cache_init(cache, opt);
+}
+
+static void selftest_open_for_write(cache_back *cache, httrackp *opt) {
+  selftest_open(cache, opt, 0);
+}
+
+static void selftest_open_for_read(cache_back *cache, httrackp *opt) {
+  selftest_open(cache, opt, 1);
+}
+
+static void selftest_close(cache_back *cache) {
+  if (cache->dat != NULL) {
+    fclose(cache->dat);
+    cache->dat = NULL;
+  }
+  if (cache->ndx != NULL) {
+    fclose(cache->ndx);
+    cache->ndx = NULL;
+  }
+  if (cache->zipOutput != NULL) {
+    zipClose(cache->zipOutput,
+             "Created by HTTrack Website Copier (cache self-test)");
+    cache->zipOutput = NULL;
+  }
+  if (cache->zipInput != NULL) {
+    unzClose(cache->zipInput);
+    cache->zipInput = NULL;
+  }
+  /* hashtable is intentionally not coucal_delete()d: it would dump a stats
+     summary to stderr on every call, and this is a one-shot CLI subcommand
+     that exits right after (same choice as the other -# cache subcommands) */
+}
+
+/* Store one entry. The body is copied into a private buffer (any size), so
+   callers may pass const data and cache_add never sees a cast-away qualifier;
+   it consumes everything synchronously, so the copy is freed on return. */
+static void store_entry(httrackp *opt, cache_back *cache, const char *adr,
+                        const char *fil, const char *save, int statuscode,
+                        const char *msg, const char *contenttype,
+                        const char *charset, const char *lastmodified,
+                        const char *etag, const char *location,
+                        const char *body, size_t body_len) {
+  htsblk r;
+  char locbuf[HTS_URLMAXSIZE * 2];
+  char *bodycopy = NULL;
+
+  hts_init_htsblk(&r);
+  r.statuscode = statuscode;
+  r.size = (LLint) body_len;
+  strcpybuff(r.msg, msg);
+  strcpybuff(r.contenttype, contenttype);
+  strcpybuff(r.charset, charset);
+  strcpybuff(r.lastmodified, lastmodified);
+  strcpybuff(r.etag, etag);
+  strcpybuff(locbuf, location);
+  r.location = locbuf;
+  r.is_write = 0;
+  /* an empty body must be a NULL pointer: cache_add rejects a non-NULL
+     pointer with size 0 */
+  if (body_len != 0) {
+    bodycopy = malloct(body_len);
+    memcpy(bodycopy, body, body_len);
+    r.adr = bodycopy;
+  }
+  /* all_in_cache=1: keep the body in the ZIP whatever the content-type,
+     so the read path never depends on a file on disk */
+  cache_add(opt, cache, &r, adr, fil, save, 1, NULL);
+  if (bodycopy != NULL) {
+    freet(bodycopy);
+  }
+}
+
+/* Read one entry back and check every field. Returns the number of
+   mismatches (0 == success). */
+static int check_entry(httrackp *opt, cache_back *cache, const char *adr,
+                       const char *fil, int statuscode, const char *msg,
+                       const char *contenttype, const char *charset,
+                       const char *lastmodified, const char *etag,
+                       const char *location, const char *body,
+                       size_t body_len) {
+  int fail = 0;
+  char *locbuf = malloct(HTS_URLMAXSIZE * 2);
+  htsblk r;
+
+  locbuf[0] = '\0';
+  /* readonly=1: pure read, no rename/disk-write decision logic */
+  r = cache_readex(opt, cache, adr, fil, "", locbuf, NULL, 1);
+
+#define CHECK_STR(field, want)                                                 \
+  do {                                                                         \
+    if (strcmp((field), (want)) != 0) {                                        \
+      fprintf(stderr,                                                          \
+              "cache-selftest: %s%s: " #field " is '%s', expected '%s'\n",     \
+              adr, fil, (field), (want));                                      \
+      fail++;                                                                  \
+    }                                                                          \
+  } while (0)
+
+  if (r.statuscode != statuscode) {
+    fprintf(stderr, "cache-selftest: %s%s: statuscode is %d, expected %d\n",
+            adr, fil, r.statuscode, statuscode);
+    fail++;
+  }
+  CHECK_STR(r.msg, msg);
+  CHECK_STR(r.contenttype, contenttype);
+  CHECK_STR(r.charset, charset);
+  CHECK_STR(r.lastmodified, lastmodified);
+  CHECK_STR(r.etag, etag);
+  CHECK_STR(locbuf, location);
+
+  if (r.size != (LLint) body_len) {
+    fprintf(stderr, "cache-selftest: %s%s: size is " LLintP ", expected %d\n",
+            adr, fil, (LLint) r.size, (int) body_len);
+    fail++;
+  } else if (body_len != 0 &&
+             (r.adr == NULL || memcmp(r.adr, body, body_len) != 0)) {
+    fprintf(stderr, "cache-selftest: %s%s: body mismatch\n", adr, fil);
+    fail++;
+  }
+
+#undef CHECK_STR
+
+  if (r.adr != NULL) {
+    freet(r.adr);
+  }
+  freet(locbuf);
+  return fail;
+}
+
+/* Fill a body of the requested size. kind 0 is highly compressible (a short
+   repeating pattern), kind 1 is incompressible (a deterministic PRNG), kind 2
+   alternates the two -- together they exercise both deflate outcomes. */
+static void gen_body(char *buf, size_t len, int kind) {
+  unsigned int seed = 0x9e3779b1u ^ (unsigned int) len;
+  size_t j;
+
+  for (j = 0; j < len; j++) {
+    if (kind == 0 || (kind == 2 && (j & 1) == 0)) {
+      buf[j] = (char) ('A' + (j % 26));
+    } else {
+      seed = seed * 1103515245u + 12345u;
+      buf[j] = (char) (seed >> 16);
+    }
+  }
+}
+
+int cache_selftests(httrackp *opt, const char *dir) {
+  int failures = 0;
+  cache_back cache;
+  int i;
+
+  /* near-limit field values. The etag stresses htsblk.etag[256]; the location
+     stresses a long redirect URL. Each cached header line is read back through
+     a HTS_URLMAXSIZE-sized parse buffer ("<field>: <value>\r\n"), so the
+     round-trippable value is shorter than HTS_URLMAXSIZE: 1000 stays safely
+     under that real limit. */
+  static char etag_long[251];
+  static char location_long[1001];
+
+  /* a body with embedded NUL and high bytes, to prove binary safety */
+  static const char binary_body[] = {
+      'P',  'N',  'G', '\0', '\r', '\n',        (char) 0xFF, (char) 0x80,
+      '\0', '\0', 'e', 'n',  'd',  (char) 0xCA, (char) 0xFE, '\n'};
+
+  /* large bodies for the compression pass; kept alive across the write and
+     read passes so the read can compare against them */
+  static const size_t large_size[] = {200000, 200000, 50000};
+  const int large_count = (int) (sizeof(large_size) / sizeof(large_size[0]));
+  char *large_body[3];
+
+  /* edge-case bodies, named so store and read assert the exact same bytes */
+  const char *const body_index = "<html><body>hello</body></html>";
+  const char *const body_api = "{\"k\":\"v\"}";
+  const char *const body_updated = "<html><body>UPDATED CONTENT</body></html>";
+  const char *const body_404 = "<html><body>404 Not Found</body></html>";
+
+  memset(etag_long, 'E', sizeof(etag_long) - 1);
+  etag_long[sizeof(etag_long) - 1] = '\0';
+  memset(location_long, 'L', sizeof(location_long) - 1);
+  location_long[sizeof(location_long) - 1] = '\0';
+
+  for (i = 0; i < large_count; i++) {
+    large_body[i] = malloct(large_size[i]);
+    gen_body(large_body[i], large_size[i], i);
+  }
+
+  /* set up an isolated cache directory */
+  {
+    char base[HTS_URLMAXSIZE];
+
+    strcpybuff(base, dir);
+    if (base[0] != '\0' && base[strlen(base) - 1] != '/') {
+      strcatbuff(base, "/");
+    }
+    StringCopy(opt->path_log, base);
+  }
+  opt->cache = 1;
+
+  /* pass 1: create everything in a single write session */
+  selftest_open_for_write(&cache, opt);
+
+  /* edge cases: normal HTML page */
+  store_entry(opt, &cache, "example.com", "/", "example.com/index.html", 200,
+              "OK", "text/html", "utf-8", "Mon, 01 Jan 2024 00:00:00 GMT",
+              "etag-normal", "", body_index, strlen(body_index));
+  /* redirect: empty body, empty optional fields, near-limit location */
+  store_entry(opt, &cache, "example.com", "/moved", "example.com/moved.html",
+              301, "Moved Permanently", "text/html", "", "", "", location_long,
+              NULL, 0);
+  /* non-HTML content-type kept in cache via all_in_cache, near-limit etag */
+  store_entry(opt, &cache, "example.com", "/api", "example.com/api.json", 200,
+              "OK", "application/json", "utf-8",
+              "Tue, 02 Jan 2024 12:00:00 GMT", etag_long, "", body_api,
+              strlen(body_api));
+  /* binary body */
+  store_entry(opt, &cache, "example.com", "/logo", "example.com/logo.png", 200,
+              "OK", "image/png", "", "", "etag-bin", "", binary_body,
+              sizeof(binary_body));
+  /* error status with a body and a location (non-2xx codes are cached too) */
+  store_entry(opt, &cache, "example.com", "/gone", "example.com/gone.html", 404,
+              "Not Found", "text/html", "utf-8", "", "etag-404",
+              "https://example.com/where-it-went", body_404, strlen(body_404));
+
+  /* scale: a few thousand small entries */
+  for (i = 0; i < SELFTEST_VOLUME; i++) {
+    char fil[64], save[128], body[64];
+
+    sprintf(fil, "/v/%05d", i);
+    sprintf(save, "example.com/v/%05d.html", i);
+    sprintf(body, "<html>volume entry %d</html>", i);
+    store_entry(opt, &cache, "example.com", fil, save, 200, "OK", "text/html",
+                "utf-8", "", "", "", body, strlen(body));
+  }
+
+  /* compression: a few large bodies */
+  for (i = 0; i < large_count; i++) {
+    char fil[64], save[128];
+
+    sprintf(fil, "/big/%d.bin", i);
+    sprintf(save, "example.com/big/%d.bin", i);
+    store_entry(opt, &cache, "example.com", fil, save, 200, "OK",
+                "application/octet-stream", "", "", "", "", large_body[i],
+                large_size[i]);
+  }
+
+  selftest_close(&cache);
+
+  /* pass 2: read back and verify everything round-tripped */
+  selftest_open_for_read(&cache, opt);
+
+  failures += check_entry(opt, &cache, "example.com", "/", 200, "OK",
+                          "text/html", "utf-8", "Mon, 01 Jan 2024 00:00:00 GMT",
+                          "etag-normal", "", body_index, strlen(body_index));
+  failures += check_entry(opt, &cache, "example.com", "/moved", 301,
+                          "Moved Permanently", "text/html", "", "", "",
+                          location_long, NULL, 0);
+  failures +=
+      check_entry(opt, &cache, "example.com", "/api", 200, "OK",
+                  "application/json", "utf-8", "Tue, 02 Jan 2024 12:00:00 GMT",
+                  etag_long, "", body_api, strlen(body_api));
+  failures +=
+      check_entry(opt, &cache, "example.com", "/logo", 200, "OK", "image/png",
+                  "", "", "etag-bin", "", binary_body, sizeof(binary_body));
+  failures += check_entry(opt, &cache, "example.com", "/gone", 404, "Not Found",
+                          "text/html", "utf-8", "", "etag-404",
+                          "https://example.com/where-it-went", body_404,
+                          strlen(body_404));
+
+  for (i = 0; i < SELFTEST_VOLUME; i++) {
+    char fil[64], body[64];
+
+    sprintf(fil, "/v/%05d", i);
+    sprintf(body, "<html>volume entry %d</html>", i);
+    failures +=
+        check_entry(opt, &cache, "example.com", fil, 200, "OK", "text/html",
+                    "utf-8", "", "", "", body, strlen(body));
+  }
+
+  for (i = 0; i < large_count; i++) {
+    char fil[64];
+
+    sprintf(fil, "/big/%d.bin", i);
+    failures += check_entry(opt, &cache, "example.com", fil, 200, "OK",
+                            "application/octet-stream", "", "", "", "",
+                            large_body[i], large_size[i]);
+  }
+
+  selftest_close(&cache);
+
+  /* pass 3: update one edge entry with new body and headers */
+  selftest_open_for_write(&cache, opt);
+  store_entry(opt, &cache, "example.com", "/", "example.com/index.html", 200,
+              "OK", "text/html", "iso-8859-1", "Wed, 03 Jan 2024 09:30:00 GMT",
+              "etag-updated", "", body_updated, strlen(body_updated));
+  selftest_close(&cache);
+
+  /* pass 4: re-read and confirm the updated value, not the old one */
+  selftest_open_for_read(&cache, opt);
+  failures +=
+      check_entry(opt, &cache, "example.com", "/", 200, "OK", "text/html",
+                  "iso-8859-1", "Wed, 03 Jan 2024 09:30:00 GMT", "etag-updated",
+                  "", body_updated, strlen(body_updated));
+  selftest_close(&cache);
+
+  for (i = 0; i < large_count; i++) {
+    freet(large_body[i]);
+  }
+
+  return failures;
+}

src/htscache_selftest.h

@@ -0,0 +1,51 @@
+/* ------------------------------------------------------------ */
+/*
+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/>.
+
+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: htscache_selftest.h                                    */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#ifndef HTSCACHE_SELFTEST_DEFH
+#define HTSCACHE_SELFTEST_DEFH
+
+#ifdef HTS_INTERNAL_BYTECODE
+
+#ifndef HTS_DEF_FWSTRUCT_httrackp
+#define HTS_DEF_FWSTRUCT_httrackp
+typedef struct httrackp httrackp;
+#endif
+
+/* Run the cache create/read/update self-test against a working directory.
+   Returns the number of failed checks (0 == success). */
+int cache_selftests(httrackp *opt, const char *dir);
+
+#endif
+
+#endif

src/htscatchurl.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -201,8 +203,8 @@ HTSEXT_API int catch_url(T_SOC soc, char *url, char *method, char *data) {
             while(strnotempty(line)) {
               socinput(soc, line, 1000);
               treathead(NULL, NULL, NULL, &blkretour, line);    // traiter
-              strcatbuff(data, line);
-              strcatbuff(data, "\r\n");
+              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");

src/htscatchurl.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -40,6 +42,9 @@ Please visit our Website: http://www.httrack.com
 /* Library internal definictions */
 #ifdef HTS_INTERNAL_BYTECODE
 
+// Capacity contract for the catch_url() 'data' buffer (32 Kb).
+#define CATCH_URL_DATA_SIZE 32768
+
 // Fonctions
 void socinput(T_SOC soc, char *s, int max);
 

src/htscharset.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htscharset.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsconcat.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2013 Xavier Roche and other contributors
+Copyright (C) 2014 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

src/htsconfig.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htscore.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -3993,5 +3995,5 @@ void voidf(void) {
   (void) a;
 }
 
-// HTTrack Website Copier Copyright (C) 1998-2017 Xavier Roche and other contributors
+// HTTrack Website Copier Copyright (C) 1998 Xavier Roche and other contributors
 //

src/htscore.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htscoremain.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -40,11 +42,13 @@ Please visit our Website: http://www.httrack.com
 #include "htscore.h"
 #include "htsdefines.h"
 #include "htsalias.h"
+#include "htsbauth.h"
 #include "htswrap.h"
 #include "htsmodules.h"
 #include "htszlib.h"
 #include "htscharset.h"
 #include "htsencoding.h"
+#include "htscache_selftest.h"
 #include "htsmd5.h"
 
 #include <ctype.h>
@@ -138,6 +142,193 @@ static void basic_selftests(void) {
   fil_normalized(source, buffer);
   // MD5 selftests
   md5selftest();
+  // cookie_get field extraction (tab-separated, 0-based)
+  {
+    char cbuf[8192];
+
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 0), "a") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 1), "b") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 2), "c") == 0);
+    // multi-char fields catch length/boundary bugs that 1-char fields hide
+    assertf(strcmp(cookie_get(cbuf, "host\tx\t/path/to", 0), "host") == 0);
+    assertf(strcmp(cookie_get(cbuf, "host\tx\t/path/to", 2), "/path/to") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\t\tc", 1), "") == 0);  // empty field
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 9), "") == 0); // beyond last
+  }
+  // back_infostr() status-line formatting (no sockets: pure formatting over
+  // in-memory slots). Stresses a few thousand entries across every status-code
+  // arm. Regression for a clobber bug where the size/totalsize trailer was
+  // written straight into the destination, wiping the URL it had just built.
+  {
+    static const struct {
+      int code;
+      const char *tag;
+    } cases[] = {
+        {200, "READY "},     {-1, "ERROR "},       {-2, "TIMEOUT "},
+        {-3, "TOOSLOW "},    {400, "BADREQUEST "}, {403, "FORBIDDEN "},
+        {404, "NOT FOUND "}, {500, "SERVERROR "},  {999, "ERROR(999)"},
+    };
+    const int ncases = (int) (sizeof(cases) / sizeof(cases[0]));
+    const int n = 2000;
+    lien_back *slots = calloct(n, sizeof(lien_back));
+    char line[HTS_URLMAXSIZE * 4 + 1024];
+    char expect[HTS_URLMAXSIZE * 4 + 1024];
+    struct_back sb;
+    int idx;
+
+    sb.lnk = slots;
+    sb.count = n;
+    sb.ready = NULL;
+    sb.ready_size_bytes = 0;
+    for (idx = 0; idx < n; idx++) {
+      lien_back *const slot = &slots[idx];
+
+      slot->r.location = slot->location_buffer;
+      slot->status = STATUS_READY;
+      slot->r.statuscode = cases[idx % ncases].code;
+      slot->r.size = idx;
+      slot->r.totalsize = idx + 1;
+      snprintf(slot->url_adr, sizeof(slot->url_adr), "http://h%d.example", idx);
+      snprintf(slot->url_fil, sizeof(slot->url_fil), "/p/%d.html", idx);
+    }
+    for (idx = 0; idx < n; idx++) {
+      line[0] = '\0';
+      back_infostr(&sb, idx, 3, line, sizeof(line));
+      // Exact match (not substring): pins tag/URL/trailer order and rejects a
+      // partial clobber, duplication, or truncation that a presence check would
+      // let through. The expected format is stated here independently.
+      snprintf(expect, sizeof(expect),
+               "%s\"http://h%d.example/p/%d.html\" " LLintP " " LLintP " ",
+               cases[idx % ncases].tag, idx, idx, (LLint) idx,
+               (LLint) (idx + 1));
+      assertf(strcmp(line, expect) == 0);
+    }
+    // Near-maximal URL, driven through back_info() (which owns the status
+    // buffer internally and prints to a FILE*). url_adr + url_fil together
+    // overrun the old HTS_URLMAXSIZE*2+1024 buffer, so the bounded appends
+    // would abort unless that buffer is sized to hold both fields. Regression
+    // for that sizing -- exercising back_infostr() directly would miss it,
+    // since the caller's buffer is what matters.
+    {
+      lien_back *const slot = &slots[0];
+      const size_t adrlen = sizeof(slot->url_adr) - 8;
+      const size_t fillen = sizeof(slot->url_fil) - 8;
+      FILE *const fp = tmpfile();
+      size_t got;
+
+      assertf(fp != NULL);
+      slot->status = STATUS_READY;
+      slot->r.statuscode = 200;
+      slot->r.size = 1;
+      slot->r.totalsize = 2;
+      memset(slot->url_adr, 'a', adrlen);
+      slot->url_adr[adrlen] = '\0';
+      slot->url_fil[0] = '/';
+      memset(slot->url_fil + 1, 'b', fillen - 1);
+      slot->url_fil[fillen] = '\0';
+      back_info(&sb, 0, 3, fp);
+      rewind(fp);
+      got = fread(line, 1, sizeof(line) - 1, fp);
+      line[got] = '\0';
+      fclose(fp);
+      snprintf(expect, sizeof(expect),
+               "READY \"%s%s\" " LLintP " " LLintP " " LF, slot->url_adr,
+               slot->url_fil, (LLint) 1, (LLint) 2);
+      assertf(strcmp(line, expect) == 0);
+    }
+    freet(slots);
+  }
+}
+
+/* Self-tests for the htssafe.h bounded string ops (driven by httrack -#8).
+   Returns 0 if every bounded operation behaved correctly, 1 otherwise.
+   The abort-on-overflow guarantee is checked separately by the -#8 "overflow"
+   sub-mode (it aborts the process by design). */
+static int string_safety_selftests(void) {
+  char buf[8];
+
+  /* strcpybuff into a sized array: exact copy */
+  strcpybuff(buf, "abc");
+  if (strcmp(buf, "abc") != 0)
+    return 1;
+
+  /* strcatbuff append within capacity */
+  strcatbuff(buf, "de");
+  if (strcmp(buf, "abcde") != 0)
+    return 1;
+
+  /* strncatbuff appends at most N source chars */
+  strcpybuff(buf, "ab");
+  strncatbuff(buf, "cdef", 2);
+  if (strcmp(buf, "abcd") != 0)
+    return 1;
+
+  /* strlcpybuff: explicit-capacity copy into a pointer destination, the form
+     the migration moves toward */
+  {
+    char storage[8];
+    char *const p = storage;
+
+    strlcpybuff(p, "hello", sizeof(storage));
+    if (strcmp(p, "hello") != 0)
+      return 1;
+  }
+
+  /* strcpybuff into a pointer destination: routes through the unchecked
+     strcpybuff_ptr_ fallback (the path the -#8 warning flags). The warning is
+     intentional here; we only verify the fallback still copies correctly. */
+#if defined(__GNUC__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wattribute-warning"
+#endif
+  {
+    char storage[8];
+    char *const p = storage;
+
+    strcpybuff(p, "ptr");
+    if (strcmp(p, "ptr") != 0)
+      return 1;
+  }
+#if defined(__GNUC__)
+#pragma GCC diagnostic pop
+#endif
+
+  /* htsbuff: bounded builder over a fixed array (append, truncating append,
+     reset, and length tracking) */
+  {
+    char dst[8];
+    htsbuff b = htsbuff_array(dst);
+
+    htsbuff_cat(&b, "ab");
+    htsbuff_cat(&b, "cd");
+    if (strcmp(htsbuff_str(&b), "abcd") != 0 || b.len != 4)
+      return 1;
+
+    htsbuff_catn(&b, "efghij", 2);      /* append at most 2 */
+    if (strcmp(htsbuff_str(&b), "abcdef") != 0)
+      return 1;
+
+    htsbuff_cpy(&b, "xyz");             /* reset */
+    if (strcmp(htsbuff_str(&b), "xyz") != 0 || b.len != 3)
+      return 1;
+
+    htsbuff_catc(&b, '!'); /* single character */
+    if (strcmp(htsbuff_str(&b), "xyz!") != 0 || b.len != 4)
+      return 1;
+  }
+
+  /* boundary: filling to exactly cap-1 must succeed (one more aborts, which the
+     -#8 overflow-buff mode checks) */
+  {
+    char d2[4];
+    htsbuff c = htsbuff_array(d2);
+
+    htsbuff_cat(&c, "abc");
+    if (strcmp(htsbuff_str(&c), "abc") != 0 || c.len != 3)
+      return 1;
+  }
+
+  return 0;
 }
 
 static int hts_main_internal(int argc, char **argv, httrackp * opt);
@@ -294,10 +485,10 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
       /* Vérifier argv[] non vide */
       if (strnotempty(argv[na])) {
 
-        /* Vérifier Commande (alias) */
-        result =
-          optalias_check(argc, (const char *const *) argv, na, &tmp_argc,
-                         (char **) tmp_argv, tmp_error);
+        /* Resolve an option alias, if any */
+        result = optalias_check(argc, (const char *const *) argv, na, &tmp_argc,
+                                (char **) tmp_argv, sizeof(_tmp_argv[0]),
+                                tmp_error, sizeof(tmp_error));
         if (!result) {
           HTS_PANIC_PRINTF(tmp_error);
           htsmain_free();
@@ -1787,10 +1978,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                     HTS_PANIC_PRINTF("Empty string given");
                     htsmain_free();
                     return -1;
-                  } else if (strlen(argv[na]) >= 256) {
-                    HTS_PANIC_PRINTF("Header line string too long");
-                    htsmain_free();
-                    return -1;
                   }
                   StringCat(opt->headers, argv[na]);
                   StringCat(opt->headers, "\r\n");  /* separator */
@@ -2012,6 +2199,19 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
           case '#':{           // non documenté
               com++;
               switch (*com) {
+              case 'A': // cache self-test: httrack -#A <dir>
+                if (na + 1 < argc) {
+                  const int err = cache_selftests(opt, argv[na + 1]);
+
+                  printf("cache-selftest: %s\n", err ? "FAIL" : "OK");
+                  htsmain_free();
+                  return err;
+                } else {
+                  fprintf(stderr, "Option #A requires a directory argument\n");
+                  htsmain_free();
+                  return 1;
+                }
+                break;
               case 'C':        // list cache files : httrack -#C '*spid*.gif' will attempt to find the matching file
                 {
                   int hasFilter = 0;
@@ -2054,8 +2254,8 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                       char firstline[256];
                       char *a = cacheNdx;
 
-                      a += cache_brstr(a, firstline);
-                      a += cache_brstr(a, firstline);
+                      a += cache_brstr(a, firstline, sizeof(firstline));
+                      a += cache_brstr(a, firstline, sizeof(firstline));
                       while(a != NULL) {
                         a = strchr(a + 1, '\n');        /* start of line */
                         if (a) {
@@ -2441,6 +2641,35 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 htsmain_free();
                 return 0;
                 break;
+              case '8':        /* string-safety selftest: httrack -#8 [overflow <bigstr>] */
+                if (na + 1 < argc
+                    && strncmp(argv[na + 1], "overflow", 8) == 0) {
+                  /* Deliberately exceed a sized buffer: the bounded op must
+                     abort. The source comes from argv so its length is opaque
+                     to the compiler (no static -Wstringop-overflow, genuine
+                     runtime check). "overflow-buff" exercises htsbuff. */
+                  char small[4];
+                  const char *const src =
+                    (na + 2 < argc) ? argv[na + 2] : "overflowing";
+
+                  if (strcmp(argv[na + 1], "overflow-buff") == 0) {
+                    htsbuff b = htsbuff_array(small);
+
+                    htsbuff_cat(&b, src);
+                  } else {
+                    strcpybuff(small, src);
+                  }
+                  printf("strsafe: NOT aborted\n");     /* must be unreachable */
+                  htsmain_free();
+                  return 1;
+                } else {
+                  const int err = string_safety_selftests();
+
+                  printf("strsafe: %s\n", err ? "FAIL" : "OK");
+                  htsmain_free();
+                  return err;
+                }
+                break;
               case '7':  // hashtable selftest: httrack -#7 nb_entries
                 basic_selftests();
                 if (++na < argc) {
@@ -2691,11 +2920,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
               return -1;
             } else {
               na++;
-              if (strlen(argv[na]) >= 126) {
-                HTS_PANIC_PRINTF("User-agent length too long");
-                htsmain_free();
-                return -1;
-              }
               StringCopy(opt->user_agent, argv[na]);
               if (StringNotEmpty(opt->user_agent))
                 opt->user_agent_send = 1;

src/htscoremain.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsdefines.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsencoding.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 2013 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

src/htsencoding.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 2013 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

src/htsfilters.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsfilters.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsftp.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsftp.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsglobal.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -202,7 +204,7 @@ Please visit our Website: http://www.httrack.com
 /* Taille max ligne de commande (>=HTS_URLMAXSIZE*2) */
 #define HTS_CDLMAXSIZE 1024
 
-/* Copyright (C) 1998-2017 Xavier Roche and other contributors */
+/* Copyright (C) 1998 Xavier Roche and other contributors */
 #define HTTRACK_AFF_AUTHORS "[XR&CO'2014]"
 #define HTS_DEFAULT_FOOTER "<!-- Mirrored from %s%s by HTTrack Website Copier/" HTTRACK_AFF_VERSION " " HTTRACK_AFF_AUTHORS ", %s -->"
 #define HTTRACK_WEB "http://www.httrack.com"

src/htshash.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htshash.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htshelp.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -182,7 +184,8 @@ void help_wizard(httrackp * opt) {
   printf("\n");
   printf("Welcome to HTTrack Website Copier (Offline Browser) " HTTRACK_VERSION
          "%s\n", hts_get_version_info(opt));
-  printf("Copyright (C) 1998-2017 Xavier Roche and other contributors\n");
+  printf("Copyright (C) 1998-%s Xavier Roche and other contributors\n",
+         &__DATE__[7]);
 #ifdef _WIN32
   printf("Note: You are running the commandline version,\n");
   printf("run 'WinHTTrack.exe' to get the GUI version.\n");
@@ -409,7 +412,7 @@ void help_catchurl(const char *dest_path) {
   if (soc != INVALID_SOCKET) {
     char BIGSTK url[HTS_URLMAXSIZE * 2];
     char method[32];
-    char BIGSTK data[32768];
+    char BIGSTK data[CATCH_URL_DATA_SIZE];
 
     url[0] = method[0] = data[0] = '\0';
     //
@@ -712,7 +715,7 @@ void help(const char *app, int more) {
   infomsg("  '%N' Name of file, including file type (ex: image.gif)");
   infomsg("  '%t' File type (ex: gif)");
   infomsg("  '%p' Path [without ending /] (ex: /someimages)");
-  infomsg("  '%h' Host name (ex: www.someweb.com)");
+  infomsg("  '%h' Host name (ex: www.example.com)");
   infomsg("  '%M' URL MD5 (128 bits, 32 ascii bytes)");
   infomsg("  '%Q' query string MD5 (128 bits, 32 ascii bytes)");
   infomsg("  '%k' full query string");
@@ -767,21 +770,21 @@ void help(const char *app, int more) {
   infomsg("Details: Option %W: External callbacks prototypes");
   infomsg("see htsdefines.h");
   infomsg("");
-  infomsg("example: httrack www.someweb.com/bob/");
-  infomsg("means:   mirror site www.someweb.com/bob/ and only this site");
+  infomsg("example: httrack www.example.com/bob/");
+  infomsg("means:   mirror site www.example.com/bob/ and only this site");
   infomsg("");
   infomsg
-    ("example: httrack www.someweb.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg -mime:application/*");
+    ("example: httrack www.example.com/bob/ www.anothertest.com/mike/ +*.com/*.jpg -mime:application/*");
   infomsg
     ("means:   mirror the two sites together (with shared links) and accept any .jpg files on .com sites");
   infomsg("");
-  infomsg("example: httrack www.someweb.com/bob/bobby.html +* -r6");
+  infomsg("example: httrack www.example.com/bob/bobby.html +* -r6");
   infomsg
     ("means get all files starting from bobby.html, with 6 link-depth, and possibility of going everywhere on the web");
   infomsg("");
   infomsg
-    ("example: httrack www.someweb.com/bob/bobby.html --spider -P proxy.myhost.com:8080");
-  infomsg("runs the spider on www.someweb.com/bob/bobby.html using a proxy");
+    ("example: httrack www.example.com/bob/bobby.html --spider -P proxy.myhost.com:8080");
+  infomsg("runs the spider on www.example.com/bob/bobby.html using a proxy");
   infomsg("");
   infomsg("example: httrack --update");
   infomsg("updates a mirror in the current folder");
@@ -795,7 +798,10 @@ void help(const char *app, int more) {
   snprintf(info, sizeof(info), "HTTrack version " HTTRACK_VERSION "%s",
           hts_is_available());
   infomsg(info);
-  infomsg("Copyright (C) 1998-2017 Xavier Roche and other contributors");
+  snprintf(info, sizeof(info),
+           "Copyright (C) 1998-%s Xavier Roche and other contributors",
+           &__DATE__[7]);
+  infomsg(info);
 #ifdef HTS_PLATFORM_NAME
   infomsg("[compiled: " HTS_PLATFORM_NAME "]");
 #endif

src/htshelp.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsindex.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsindex.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsjava.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsjava.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htslib.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -121,6 +123,7 @@ const char *hts_detect[] = {
   "lowsrc",
   "profile",                    // element META
   "src",
+  "srcset",                     // HTML5 responsive images (<img>, <source>)
   "swurl",
   "url",
   "usemap",
@@ -877,7 +880,7 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
                   const char *xsend, const char *adr, const char *fil,
                   const char *referer_adr, const char *referer_fil,
                   htsblk * retour) {
-  char BIGSTK buffer_head_request[8192];
+  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
@@ -895,9 +898,9 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode,
 
   // possibilité non documentée: >post: et >postfile:
   // si présence d'un tag >post: alors executer un POST
-  // exemple: http://www.someweb.com/test.cgi?foo>post:posteddata=10&foo=5
+  // exemple: http://www.example.com/test.cgi?foo>post:posteddata=10&foo=5
   // si présence d'un tag >postfile: alors envoyer en tête brut contenu dans le fichier en question
-  // exemple: http://www.someweb.com/test.cgi?foo>postfile:post0.txt
+  // exemple: http://www.example.com/test.cgi?foo>postfile:post0.txt
   search_tag = strstr(fil, POSTTOK ":");
   if (!search_tag) {
     search_tag = strstr(fil, POSTTOK "file:");
@@ -1659,138 +1662,107 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
   }
 }
 
-// transforme le message statuscode en chaîne
-HTSEXT_API void infostatuscode(char *msg, int statuscode) {
+// HTTP status code -> reason phrase (per RFC), or NULL if unknown.
+HTSEXT_API const char *infostatuscode_const(int statuscode) {
+  // O(1) dispatch (the compiler builds a jump table); the phrases are static.
   switch (statuscode) {
-    // Erreurs HTTP, selon RFC
   case 100:
-    strcpybuff(msg, "Continue");
-    break;
+    return "Continue";
   case 101:
-    strcpybuff(msg, "Switching Protocols");
-    break;
+    return "Switching Protocols";
   case 200:
-    strcpybuff(msg, "OK");
-    break;
+    return "OK";
   case 201:
-    strcpybuff(msg, "Created");
-    break;
+    return "Created";
   case 202:
-    strcpybuff(msg, "Accepted");
-    break;
+    return "Accepted";
   case 203:
-    strcpybuff(msg, "Non-Authoritative Information");
-    break;
+    return "Non-Authoritative Information";
   case 204:
-    strcpybuff(msg, "No Content");
-    break;
+    return "No Content";
   case 205:
-    strcpybuff(msg, "Reset Content");
-    break;
+    return "Reset Content";
   case 206:
-    strcpybuff(msg, "Partial Content");
-    break;
+    return "Partial Content";
   case 300:
-    strcpybuff(msg, "Multiple Choices");
-    break;
+    return "Multiple Choices";
   case 301:
-    strcpybuff(msg, "Moved Permanently");
-    break;
+    return "Moved Permanently";
   case 302:
-    strcpybuff(msg, "Moved Temporarily");
-    break;
+    return "Moved Temporarily";
   case 303:
-    strcpybuff(msg, "See Other");
-    break;
+    return "See Other";
   case 304:
-    strcpybuff(msg, "Not Modified");
-    break;
+    return "Not Modified";
   case 305:
-    strcpybuff(msg, "Use Proxy");
-    break;
+    return "Use Proxy";
   case 306:
-    strcpybuff(msg, "Undefined 306 error");
-    break;
+    return "Undefined 306 error";
   case 307:
-    strcpybuff(msg, "Temporary Redirect");
-    break;
+    return "Temporary Redirect";
   case 400:
-    strcpybuff(msg, "Bad Request");
-    break;
+    return "Bad Request";
   case 401:
-    strcpybuff(msg, "Unauthorized");
-    break;
+    return "Unauthorized";
   case 402:
-    strcpybuff(msg, "Payment Required");
-    break;
+    return "Payment Required";
   case 403:
-    strcpybuff(msg, "Forbidden");
-    break;
+    return "Forbidden";
   case 404:
-    strcpybuff(msg, "Not Found");
-    break;
+    return "Not Found";
   case 405:
-    strcpybuff(msg, "Method Not Allowed");
-    break;
+    return "Method Not Allowed";
   case 406:
-    strcpybuff(msg, "Not Acceptable");
-    break;
+    return "Not Acceptable";
   case 407:
-    strcpybuff(msg, "Proxy Authentication Required");
-    break;
+    return "Proxy Authentication Required";
   case 408:
-    strcpybuff(msg, "Request Time-out");
-    break;
+    return "Request Time-out";
   case 409:
-    strcpybuff(msg, "Conflict");
-    break;
+    return "Conflict";
   case 410:
-    strcpybuff(msg, "Gone");
-    break;
+    return "Gone";
   case 411:
-    strcpybuff(msg, "Length Required");
-    break;
+    return "Length Required";
   case 412:
-    strcpybuff(msg, "Precondition Failed");
-    break;
+    return "Precondition Failed";
   case 413:
-    strcpybuff(msg, "Request Entity Too Large");
-    break;
+    return "Request Entity Too Large";
   case 414:
-    strcpybuff(msg, "Request-URI Too Large");
-    break;
+    return "Request-URI Too Large";
   case 415:
-    strcpybuff(msg, "Unsupported Media Type");
-    break;
+    return "Unsupported Media Type";
   case 416:
-    strcpybuff(msg, "Requested Range Not Satisfiable");
-    break;
+    return "Requested Range Not Satisfiable";
   case 417:
-    strcpybuff(msg, "Expectation Failed");
-    break;
+    return "Expectation Failed";
   case 500:
-    strcpybuff(msg, "Internal Server Error");
-    break;
+    return "Internal Server Error";
   case 501:
-    strcpybuff(msg, "Not Implemented");
-    break;
+    return "Not Implemented";
   case 502:
-    strcpybuff(msg, "Bad Gateway");
-    break;
+    return "Bad Gateway";
   case 503:
-    strcpybuff(msg, "Service Unavailable");
-    break;
+    return "Service Unavailable";
   case 504:
-    strcpybuff(msg, "Gateway Time-out");
-    break;
+    return "Gateway Time-out";
   case 505:
-    strcpybuff(msg, "HTTP Version Not Supported");
-    break;
-    //
+    return "HTTP Version Not Supported";
   default:
-    if (strnotempty(msg) == 0)
-      strcpybuff(msg, "Unknown error");
-    break;
+    return NULL;
+  }
+}
+
+// Write the status code's reason phrase into msg. For an unknown code, keep any
+// caller-provided message, otherwise fall back to a default. Callers provide a
+// buffer of at least 64 bytes (the longest reason phrase is 31).
+HTSEXT_API void infostatuscode(char *msg, int statuscode) {
+  const char *const text = infostatuscode_const(statuscode);
+
+  if (text != NULL) {
+    strlcpybuff(msg, text, 64);
+  } else if (strnotempty(msg) == 0) {
+    strlcpybuff(msg, "Unknown error", 64);
   }
 }
 

src/htslib.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsmd5.c

@@ -1,7 +1,9 @@
 
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsmd5.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsmodules.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsmodules.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsname.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -767,7 +769,7 @@ int url_savename(lien_adrfilsave *const afs,
   // ajouter nom du site éventuellement en premier
   if (opt->savename_type == -1) {       // utiliser savename_userdef! (%h%p/%n%q.%t)
     const char *a = StringBuff(opt->savename_userdef);
-    char *b = afs->save;
+    htsbuff sb = htsbuff_array(afs->save);
 
     /*char *nom_pos=NULL,*dot_pos=NULL;  // Position nom et point */
     char tok;
@@ -787,17 +789,16 @@ int url_savename(lien_adrfilsave *const afs,
        }
      */
 
-    // Construire nom
-    while((*a) && (((int) (b - afs->save)) < HTS_URLMAXSIZE)) {      // parser, et pas trop long..
+    // build the name
+    while ((*a) && (sb.len < HTS_URLMAXSIZE)) { // parse, but not too long
       if (*a == '%') {
         int short_ver = 0;
 
         a++;
-        if (*a == 's') {
+        if (*a == 's') { // '%s...' selects the short (8.3) form
           short_ver = 1;
           a++;
         }
-        *b = '\0';
         switch (tok = *a++) {
         case '[':              // %[param:prefix_if_not_empty:suffix_if_not_empty:empty_replacement:notfound_replacement]
           if (strchr(a, ']')) {
@@ -834,8 +835,7 @@ int url_savename(lien_adrfilsave *const afs,
               }
               if (cp) {
                 c = cp + strlen(name[0]);       /* jumps "param=" */
-                strcpybuff(b, name[1]); /* prefix */
-                b += strlen(b);
+                htsbuff_cat(&sb, name[1]);      /* prefix */
                 if (*c != '\0' && *c != '&') {
                   char *d = name[0];
 
@@ -846,110 +846,90 @@ int url_savename(lien_adrfilsave *const afs,
                   *d = '\0';
                   d = unescape_http(catbuff, sizeof(catbuff), name[0]);
                   if (d && *d) {
-                    strcpybuff(b, d);   /* value */
-                    b += strlen(b);
+                    htsbuff_cat(&sb, d); /* value */
                   } else {
-                    strcpybuff(b, name[3]);     /* empty replacement if any */
-                    b += strlen(b);
+                    htsbuff_cat(&sb, name[3]); /* empty replacement if any */
                   }
                 } else {
-                  strcpybuff(b, name[3]);       /* empty replacement if any */
-                  b += strlen(b);
+                  htsbuff_cat(&sb, name[3]); /* empty replacement if any */
                 }
-                strcpybuff(b, name[2]); /* suffix */
-                b += strlen(b);
+                htsbuff_cat(&sb, name[2]); /* suffix */
               } else {
-                strcpybuff(b, name[4]); /* not found replacement if any */
-                b += strlen(b);
+                htsbuff_cat(&sb, name[4]); /* not found replacement if any */
               }
             } else {
-              strcpybuff(b, name[4]);   /* not found replacement if any */
-              b += strlen(b);
+              htsbuff_cat(&sb, name[4]); /* not found replacement if any */
             }
           }
           break;
         case '%':
-          *b++ = '%';
+          htsbuff_catc(&sb, '%');
           break;
-        case 'n':              // nom sans ext
-          *b = '\0';
+        case 'n': // name without extension
           if (dot_pos) {
-            if (!short_ver)     // Noms longs
-              strncatbuff(b, nom_pos, (int) (dot_pos - nom_pos));
+            if (!short_ver)
+              htsbuff_catn(&sb, nom_pos, (int) (dot_pos - nom_pos));
             else
-              strncatbuff(b, nom_pos, min((int) (dot_pos - nom_pos), 8));
+              htsbuff_catn(&sb, nom_pos, min((int) (dot_pos - nom_pos), 8));
           } else {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, nom_pos);
+            if (!short_ver)
+              htsbuff_cat(&sb, nom_pos);
             else
-              strncatbuff(b, nom_pos, 8);
+              htsbuff_catn(&sb, nom_pos, 8);
           }
-          b += strlen(b);       // pointer à la fin
           break;
-        case 'N':              // nom avec ext
-          // RECOPIE NOM + EXT
-          *b = '\0';
+        case 'N': // name with extension
           if (dot_pos) {
-            if (!short_ver)     // Noms longs
-              strncatbuff(b, nom_pos, (int) (dot_pos - nom_pos));
+            if (!short_ver)
+              htsbuff_catn(&sb, nom_pos, (int) (dot_pos - nom_pos));
             else
-              strncatbuff(b, nom_pos, min((int) (dot_pos - nom_pos), 8));
+              htsbuff_catn(&sb, nom_pos, min((int) (dot_pos - nom_pos), 8));
           } else {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, nom_pos);
+            if (!short_ver)
+              htsbuff_cat(&sb, nom_pos);
             else
-              strncatbuff(b, nom_pos, 8);
+              htsbuff_catn(&sb, nom_pos, 8);
           }
-          b += strlen(b);       // pointer à la fin
-          *b = '.';
-          ++b;
-          // RECOPIE NOM + EXT
-          *b = '\0';
+          htsbuff_catc(&sb, '.');
           if (dot_pos) {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, dot_pos + 1);
+            if (!short_ver)
+              htsbuff_cat(&sb, dot_pos + 1);
             else
-              strncatbuff(b, dot_pos + 1, 3);
+              htsbuff_catn(&sb, dot_pos + 1, 3);
           } else {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, DEFAULT_EXT + 1);   // pas de..
+            if (!short_ver)
+              htsbuff_cat(&sb, DEFAULT_EXT + 1); // skip the leading dot
             else
-              strcpybuff(b, DEFAULT_EXT_SHORT + 1);     // pas de..
+              htsbuff_cat(&sb, DEFAULT_EXT_SHORT + 1); // skip the leading dot
           }
-          b += strlen(b);       // pointer à la fin
-          //
           break;
-        case 't':              // ext
-          *b = '\0';
+        case 't': // extension
           if (dot_pos) {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, dot_pos + 1);
+            if (!short_ver)
+              htsbuff_cat(&sb, dot_pos + 1);
             else
-              strncatbuff(b, dot_pos + 1, 3);
+              htsbuff_catn(&sb, dot_pos + 1, 3);
           } else {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, DEFAULT_EXT + 1);   // pas de..
+            if (!short_ver)
+              htsbuff_cat(&sb, DEFAULT_EXT + 1); // skip the leading dot
             else
-              strcpybuff(b, DEFAULT_EXT_SHORT + 1);     // pas de..
+              htsbuff_cat(&sb, DEFAULT_EXT_SHORT + 1); // skip the leading dot
           }
-          b += strlen(b);       // pointer à la fin
           break;
-        case 'p':              // path sans dernier /
-          *b = '\0';
-          if (nom_pos != fil + 1) {     // pas: /index.html (chemin nul)
-            if (!short_ver) {   // Noms longs
-              strncatbuff(b, fil, (int) (nom_pos - fil) - 1);
+        case 'p': // path without trailing /
+          if (nom_pos !=
+              fil + 1) { // skip when the path is empty (e.g. /index.html)
+            if (!short_ver) {
+              htsbuff_catn(&sb, fil, (int) (nom_pos - fil) - 1);
             } else {
               char BIGSTK pth[HTS_URLMAXSIZE * 2], n83[HTS_URLMAXSIZE * 2];
 
               pth[0] = n83[0] = '\0';
-              //
               strncatbuff(pth, fil, (int) (nom_pos - fil) - 1);
               long_to_83(opt->savename_83, n83, pth);
-              strcpybuff(b, n83);
+              htsbuff_cat(&sb, n83);
             }
           }
-          b += strlen(b);       // pointer à la fin
           break;
         case 'h':              // host (IDNA decoded if suitable)
           // IDNA / RFC 3492 (Punycode) handling for HTTP(s)
@@ -957,62 +937,50 @@ int url_savename(lien_adrfilsave *const afs,
             DECLARE_ADR(final_adr);
 
             /* Copy address */
-            *b = '\0';
             if (!short_ver)
-              strcpybuff(b, final_adr);
+              htsbuff_cat(&sb, final_adr);
             else
-              strcpybuff(b, final_adr);
+              htsbuff_cat(&sb, final_adr);
 
             /* release */
             RELEASE_ADR();
           }
-          b += strlen(b);       // pointer à la fin
           break;
-        case 'H':              // host, raw (old mode)
-          *b = '\0';
+        case 'H': // host, raw (old mode)
           if (protocol == PROTOCOL_FILE) {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, "localhost");
+            if (!short_ver)
+              htsbuff_cat(&sb, "localhost");
             else
-              strcpybuff(b, "local");
+              htsbuff_cat(&sb, "local");
           } else {
-            if (!short_ver)     // Noms longs
-              strcpybuff(b, print_adr);
+            if (!short_ver)
+              htsbuff_cat(&sb, print_adr);
             else
-              strncatbuff(b, print_adr, 8);
+              htsbuff_catn(&sb, print_adr, 8);
           }
-          b += strlen(b);       // pointer à la fin
           break;
-        case 'M':              /* host/address?query MD5 (128-bits) */
-          *b = '\0';
-          {
-            char digest[32 + 2];
-            char BIGSTK buff[HTS_URLMAXSIZE * 2];
+        case 'M': /* host/address?query MD5 (128-bits) */
+        {
+          char digest[32 + 2];
+          char BIGSTK buff[HTS_URLMAXSIZE * 2];
 
-            digest[0] = buff[0] = '\0';
-            strcpybuff(buff, adr);
-            strcatbuff(buff, fil_complete);
-            domd5mem(buff, strlen(buff), digest, 1);
-            strcpybuff(b, digest);
-          }
-          b += strlen(b);       // pointer à la fin
-          break;
+          digest[0] = buff[0] = '\0';
+          strcpybuff(buff, adr);
+          strcatbuff(buff, fil_complete);
+          domd5mem(buff, strlen(buff), digest, 1);
+          htsbuff_cat(&sb, digest);
+        } break;
         case 'Q':
-        case 'q':              /* query MD5 (128-bits/16-bits) 
-                                   GENERATED ONLY IF query string exists! */
-          {
-            char md5[32 + 2];
+        case 'q': /* query MD5 (128-bits/16-bits)
+                      GENERATED ONLY IF query string exists! */
+        {
+          char md5[32 + 2];
 
-            *b = '\0';
-            strncatbuff(b, url_md5(md5, fil_complete), (tok == 'Q') ? 32 : 4);
-            b += strlen(b);     // pointer à la fin
-          }
-          break;
+          htsbuff_catn(&sb, url_md5(md5, fil_complete), (tok == 'Q') ? 32 : 4);
+        } break;
         case 'r':
         case 'R':              // protocol
-          *b = '\0';
-          strcatbuff(b, protocol_str[protocol]);
-          b += strlen(b);       // pointer à la fin
+          htsbuff_cat(&sb, protocol_str[protocol]);
           break;
 
           /* Patch by Juan Fco Rodriguez to get the full query string */
@@ -1021,19 +989,17 @@ int url_savename(lien_adrfilsave *const afs,
             char *d = strchr(fil_complete, '?');
 
             if (d != NULL) {
-              strcatbuff(b, d);
-              b += strlen(b);
+              htsbuff_cat(&sb, d);
             }
           }
           break;
 
         }
       } else
-        *b++ = *a++;
+        htsbuff_catc(&sb, *a++);
     }
-    *b++ = '\0';
     //
-    // Types prédéfinis
+    // predefined types
     //
 
   }

src/htsname.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsnet.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsopt.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsparse.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -274,6 +276,28 @@ Please visit our Website: http://www.httrack.com
   } \
 } while(0)
 
+/* Percent-encode the angle brackets of a string so it is safe to embed inside
+   an HTML comment (the default footer) or any other HTML context. A URL holding
+   "-->" would otherwise close the footer comment and inject markup (issue #165).
+   Raw '<' and '>' are not valid URL characters, so encoding them is harmless. */
+static const char *html_inline_safe(const char *src, char *dst, size_t size) {
+  size_t i, j;
+
+  for(i = 0, j = 0; src[i] != '\0' && j + 4 < size; i++) {
+    const char c = src[i];
+
+    if (c == '<' || c == '>') {
+      dst[j++] = '%';
+      dst[j++] = '3';
+      dst[j++] = (c == '<') ? 'C' : 'E';
+    } else {
+      dst[j++] = c;
+    }
+  }
+  dst[j] = '\0';
+  return dst;
+}
+
 /* Main parser */
 int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
   char catbuff[CATBUFF_SIZE];
@@ -510,6 +534,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
         int valid_p = 0;        // force to take p even if == 0
         int ending_p = '\0';    // ending quote?
         int archivetag_p = 0;   // avoid multiple-archives with commas
+        int srcset_p = 0;       // srcset="url1 480w, url2 2x": list of URLs
         int unquoted_script = 0;
         INSCRIPT inscript_state_pos_prev = inscript_state_pos;
 
@@ -719,13 +744,16 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 if (StringNotEmpty(opt->footer)) {
                   char BIGSTK tempo[1024 + HTS_URLMAXSIZE * 2];
                   char gmttime[256];
+                  char BIGSTK safe_adr[HTS_URLMAXSIZE * 3 + 4];
+                  char BIGSTK safe_fil[HTS_URLMAXSIZE * 3 + 4];
 
                   tempo[0] = '\0';
                   time_gmt_rfc822(gmttime);
                   strcatbuff(tempo, eol);
                   hts_template_format_str(tempo + strlen(tempo), sizeof(tempo) - strlen(tempo),
                           StringBuff(opt->footer),
-                          jump_identification_const(urladr()), urlfil(), gmttime,
+                          html_inline_safe(jump_identification_const(urladr()), safe_adr, sizeof(safe_adr)),
+                          html_inline_safe(urlfil(), safe_fil, sizeof(safe_fil)), gmttime,
                           HTTRACK_VERSIONID, /* EOF */ NULL);
                   strcatbuff(tempo, eol);
                   //fwrite(tempo,1,strlen(tempo),fp);
@@ -1025,6 +1053,12 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                           if (strcmp(hts_detect[i], "archive") == 0) {
                             archivetag_p = 1;
                           }
+                          /* srcset: a comma-list of candidate URLs, each split
+                             out and rewritten below (#235, #236) */
+                          else if (strcmp(hts_detect[i], "srcset") == 0
+                                   || strcmp(hts_detect[i], "data-srcset") == 0) {
+                            srcset_p = 1;
+                          }
                         }
                         i++;
                       }
@@ -1790,6 +1824,14 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 html++;          // sauter # pour usemap etc
               }
             }
+ srcset_next:
+            /* srcset: skip leading whitespace/commas before each candidate;
+               the skipped bytes flush verbatim below */
+            if (srcset_p) {
+              while(html < r->adr + r->size
+                    && (is_realspace(*html) || *html == ','))
+                INCREMENT_CURRENT_ADR(1);
+            }
             eadr = html;
 
             // ne pas flusher après code si on doit écrire le codebase avant!
@@ -1819,6 +1861,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                     if ((*eadr == quote && (!quoteinscript || *(eadr - 1) == '\\'))     // end quote
                         || (noquote && (*eadr == '\"' || *eadr == '\''))        // end at any quote
                         || (!noquote && quote == '\0' && is_realspace(*eadr))   // unquoted href
+                        || srcset_p     // whitespace ends a srcset candidate URL
                       )         // si pas d'attente de quote spéciale ou si quote atteinte
                       ok = 0;
                   } else if (ending_p && (*eadr == ending_p))
@@ -1847,6 +1890,16 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                       break;    // \" ou \' point d'arrêt
                     case '?':  /*quote_adr=adr; */
                       break;    // noter position query
+                    case ',':
+                      if (srcset_p) {
+                        /* split only on a trailing comma; one inside the URL
+                           (data: URI, CDN path) is kept, per the WHATWG algo */
+                        const char *const n = eadr + 1;
+
+                        if (n >= r->adr + r->size || is_space(*n) || *n == ',')
+                          ok = 0;
+                      }
+                      break;
                     }
                   }
                   //}
@@ -3225,6 +3278,28 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
             // adr=eadr-1;  // ** sauter
 
+            /* srcset candidate loop: skip the descriptor and comma, then
+               re-enter the capture for the next URL. Backward goto, not a loop:
+               the per-candidate body is this whole block. */
+            if (srcset_p && ok == 0) {
+              const char *const endp = r->adr + r->size;
+              const char *q = html;
+              while(q < endp && *q != '\0' && *q != ',' && *q != quote
+                    && *q != '<' && *q != '>' && (unsigned char) *q >= 32)
+                q++;            // skip the descriptor
+              if (q < endp && *q == ',') {
+                q++;
+                while(q < endp && (is_realspace(*q) || *q == ','))
+                  q++;          // skip whitespace and empty candidates
+                if (q < endp && *q != '\0' && *q != ',' && *q != quote
+                    && *q != '<' && *q != '>' && (unsigned char) *q >= 32) {
+                  INCREMENT_CURRENT_ADR(q - html);   // keep the automate in sync
+                  ok = 1;
+                  goto srcset_next;
+                }
+              }
+            }
+
             /* We skipped bytes and skip the " : reset state */
             /*if (inscript) {
                inscript_state_pos = INSCRIPT_START;

src/htsparse.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsrobots.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsrobots.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htssafe.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 2014 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
@@ -123,41 +125,111 @@ static HTS_UNUSED void htssafe_compile_time_check_(void) {
   (void) check_pointer;
 }
 
+/*
+ * Pointer-destination diagnostics for the buff() macros (GCC/Clang, C only).
+ *
+ * strcpybuff()/strcatbuff()/strncatbuff() bounds-check only when the
+ * destination is a sized char[] array (HTS_IS_CHAR_BUFFER). For a bare char*
+ * the capacity is unknown, so the macro silently falls back to plain
+ * strcpy()/strcat()/strncat() while still looking like a checked call.
+ *
+ * These stubs route that pointer case through __builtin_choose_expr() so the
+ * 'warning' attribute fires only at pointer-destination sites; array sites use
+ * the bounded *_safe_ helpers and stay quiet. The warning names the
+ * explicit-size replacement (strlcpybuff/strlcatbuff). Diagnostic only: no
+ * runtime or ABI change, built only on GCC/Clang in C mode. Other compilers
+ * (MSVC, ...) keep the previous behavior via the #else branches.
+ */
+#if (defined(__GNUC__) && !defined(__cplusplus))
+#if defined(__has_attribute)
+#if __has_attribute(warning)
+#define HTS_BUFF_PTR_ATTR(msg) __attribute__((unused, noinline, warning(msg)))
+#endif
+#endif
+#ifndef HTS_BUFF_PTR_ATTR
+/* 'warning' attribute unavailable: keep noinline so the migration can still
+   grep for these symbols, but no compile-time diagnostic is emitted. */
+#define HTS_BUFF_PTR_ATTR(msg) __attribute__((unused, noinline))
+#endif
+
+HTS_BUFF_PTR_ATTR("strcpybuff() destination is a pointer (capacity unknown): "
+                  "NOT bounds-checked; use strlcpybuff(dst, src, size)")
+static char *strcpybuff_ptr_(char *dest, const char *src) {
+  return strcpy(dest, src);
+}
+
+HTS_BUFF_PTR_ATTR("strcatbuff() destination is a pointer (capacity unknown): "
+                  "NOT bounds-checked; use strlcatbuff(dst, src, size)")
+static char *strcatbuff_ptr_(char *dest, const char *src) {
+  return strcat(dest, src);
+}
+
+HTS_BUFF_PTR_ATTR("strncatbuff() destination is a pointer (capacity unknown): "
+                  "NOT bounds-checked; use strlcatbuff(dst, src, size)")
+static char *strncatbuff_ptr_(char *dest, const char *src, size_t n) {
+  return strncat(dest, src, n);
+}
+#endif
+
 /**
  * Append at most N characters from "B" to "A".
  * If "A" is a char[] variable whose size is not sizeof(char*), then the size 
  * is assumed to be the capacity of this array.
  */
+#if (defined(__GNUC__) && !defined(__cplusplus))
+#define strncatbuff(A, B, N) __builtin_choose_expr( HTS_IS_CHAR_BUFFER(A), \
+  strncat_safe_(A, sizeof(A), B, \
+  HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), N, \
+  "overflow while appending '" #B "' to '"#A"'", __FILE__, __LINE__), \
+  strncatbuff_ptr_((A), (B), (N)) )
+#else
 #define strncatbuff(A, B, N) \
   ( HTS_IS_NOT_CHAR_BUFFER(A) \
   ? strncat(A, B, N) \
   : strncat_safe_(A, sizeof(A), B, \
   HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), N, \
   "overflow while appending '" #B "' to '"#A"'", __FILE__, __LINE__) )
+#endif
 
 /**
  * Append characters of "B" to "A".
  * If "A" is a char[] variable whose size is not sizeof(char*), then the size 
  * is assumed to be the capacity of this array.
  */
+#if (defined(__GNUC__) && !defined(__cplusplus))
+#define strcatbuff(A, B) __builtin_choose_expr( HTS_IS_CHAR_BUFFER(A), \
+  strncat_safe_(A, sizeof(A), B, \
+  HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), (size_t) -1, \
+  "overflow while appending '" #B "' to '"#A"'", __FILE__, __LINE__), \
+  strcatbuff_ptr_((A), (B)) )
+#else
 #define strcatbuff(A, B) \
   ( HTS_IS_NOT_CHAR_BUFFER(A) \
   ? strcat(A, B) \
   : strncat_safe_(A, sizeof(A), B, \
   HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), (size_t) -1, \
   "overflow while appending '" #B "' to '"#A"'", __FILE__, __LINE__) )
+#endif
 
 /**
  * Copy characters from "B" to "A".
  * If "A" is a char[] variable whose size is not sizeof(char*), then the size 
  * is assumed to be the capacity of this array.
  */
+#if (defined(__GNUC__) && !defined(__cplusplus))
+#define strcpybuff(A, B) __builtin_choose_expr( HTS_IS_CHAR_BUFFER(A), \
+  strcpy_safe_(A, sizeof(A), B, \
+  HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), \
+  "overflow while copying '" #B "' to '"#A"'", __FILE__, __LINE__), \
+  strcpybuff_ptr_((A), (B)) )
+#else
 #define strcpybuff(A, B) \
   ( HTS_IS_NOT_CHAR_BUFFER(A) \
   ? strcpy(A, B) \
   : strcpy_safe_(A, sizeof(A), B, \
   HTS_IS_NOT_CHAR_BUFFER(B) ? (size_t) -1 : sizeof(B), \
   "overflow while copying '" #B "' to '"#A"'", __FILE__, __LINE__) )
+#endif
 
 /**
  * Append characters of "B" to "A", "A" having a maximum capacity of "S".
@@ -217,6 +289,88 @@ static HTS_INLINE HTS_UNUSED char* strcpy_safe_(char *const dest, const size_t s
   return strncat_safe_(dest, sizeof_dest, source, sizeof_source, (size_t) -1, exp, file, line);
 }
 
+/**
+ * htsbuff: a non-owning bounded string builder over a fixed buffer.
+ *
+ * Companion to the strcpybuff()/strcatbuff() macros for the common case of a
+ * cursor walking a buffer of known capacity (building a name into a fixed
+ * array, assembling a status line, etc.). It tracks the write position, bounds
+ * every write against the real capacity, and aborts on overflow (same contract
+ * as the *_safe_ helpers), so the error-prone manual "p += strlen(p)" dance
+ * goes away.
+ *
+ * Build one from an in-scope array with htsbuff_array() (capacity via sizeof,
+ * so pass an array, not a pointer), or from a pointer of known capacity with
+ * htsbuff_ptr(). The buffer is kept NUL-terminated; htsbuff_str() returns it.
+ */
+typedef struct {
+  char *buf;        /* backing buffer (kept NUL-terminated) */
+  size_t cap;       /* total capacity of buf, including the NUL */
+  size_t len;       /* current length, excluding the NUL */
+} htsbuff;
+
+static HTS_INLINE HTS_UNUSED htsbuff htsbuff_ptr_(char *buf, size_t cap) {
+  htsbuff b;
+  b.buf = buf;
+  b.cap = cap;
+  b.len = 0;
+  assertf(cap != 0);
+  buf[0] = '\0';
+  return b;
+}
+
+/**
+ * Builder over the in-scope array ARR (capacity = sizeof(ARR)).
+ * On GCC/Clang this rejects a non-array (e.g. a char* pointer), whose sizeof
+ * would be the pointer size and silently wrong; use htsbuff_ptr() for pointers.
+ * On other compilers there is no such guard, so pass only true arrays there.
+ */
+#if (defined(__GNUC__) && !defined(__cplusplus))
+/* 0 for an array, a -1 array-size compile error for a pointer. */
+#define htsbuff_must_be_array_(A) \
+  (sizeof(char[1 - 2 * !!__builtin_types_compatible_p(typeof(A), typeof(&(A)[0]))]) - 1)
+#define htsbuff_array(ARR) htsbuff_ptr_((ARR), sizeof(ARR) + htsbuff_must_be_array_(ARR))
+#else
+#define htsbuff_array(ARR) htsbuff_ptr_((ARR), sizeof(ARR))
+#endif
+/** Builder over pointer P of known capacity N (N includes the NUL). */
+#define htsbuff_ptr(P, N)  htsbuff_ptr_((P), (N))
+
+/** Append at most n characters of s (stopping at its NUL). Aborts on overflow. */
+static HTS_INLINE HTS_UNUSED void htsbuff_catn(htsbuff *b, const char *s, size_t n) {
+  const size_t add = strnlen(s, n);
+  /* Overflow-safe: keep the (potentially huge) 'add' alone on one side. The
+     maintained invariant len < cap makes 'cap - len' >= 1 (no underflow), so
+     'add < cap - len' cannot wrap the way 'len + add < cap' could. */
+  assertf__(add < b->cap - b->len, "htsbuff append overflow", __FILE__, __LINE__);
+  memcpy(b->buf + b->len, s, add);
+  b->len += add;
+  b->buf[b->len] = '\0';
+}
+
+/** Append s. Aborts on overflow. */
+static HTS_INLINE HTS_UNUSED void htsbuff_cat(htsbuff *b, const char *s) {
+  htsbuff_catn(b, s, (size_t) -1);
+}
+
+/** Append a single character (including '\0' as data). Aborts on overflow. */
+static HTS_INLINE HTS_UNUSED void htsbuff_catc(htsbuff *b, char c) {
+  assertf__(1 < b->cap - b->len, "htsbuff append overflow", __FILE__, __LINE__);
+  b->buf[b->len++] = c;
+  b->buf[b->len] = '\0';
+}
+
+/** Reset content to s. Aborts on overflow. */
+static HTS_INLINE HTS_UNUSED void htsbuff_cpy(htsbuff *b, const char *s) {
+  b->len = 0;
+  htsbuff_catn(b, s, (size_t) -1);
+}
+
+/** Current NUL-terminated content. */
+static HTS_INLINE HTS_UNUSED const char *htsbuff_str(const htsbuff *b) {
+  return b->buf;
+}
+
 #define malloct(A)          malloc(A)
 #define calloct(A,B)        calloc((A), (B))
 #define freet(A)            do { if ((A) != NULL) { free(A); (A) = NULL; } } while(0)

src/htsserver.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsserver.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsstrings.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsthread.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -193,7 +195,23 @@ HTSEXT_API void hts_mutexfree(htsmutex * mutex) {
 HTSEXT_API void hts_mutexlock(htsmutex * mutex) {
   assertf(mutex != NULL);
   if (*mutex == HTSMUTEX_INIT) {        /* must be initialized */
-    hts_mutexinit(mutex);
+    /* Initialize exactly once, even when several threads race to lock the same
+       mutex for the first time. Build our own object, then publish it with a
+       single atomic compare-and-swap; the threads that lose the race free the
+       object they built (issue #297). No static guard is needed, which keeps
+       this safe on Windows 2000 (no statically-initializable lock there). */
+    htsmutex created = HTSMUTEX_INIT;
+
+    hts_mutexinit(&created);
+#ifdef _WIN32
+    if (InterlockedCompareExchangePointer((PVOID volatile *) mutex, created,
+                                          HTSMUTEX_INIT) != HTSMUTEX_INIT)
+#else
+    if (!__sync_bool_compare_and_swap(mutex, HTSMUTEX_INIT, created))
+#endif
+    {
+      hts_mutexfree(&created);
+    }
   }
   assertf(*mutex != NULL);
 #ifdef _WIN32

src/htsthread.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htstools.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htstools.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsweb.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htsweb.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htswizard.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -43,17 +45,23 @@ Please visit our Website: http://www.httrack.com
 /* END specific definitions */
 
 // libérer filters[0] pour insérer un élément dans filters[0]
-#define HT_INSERT_FILTERS0 do {\
-  int i;\
-  if (*opt->filters.filptr > 0) {\
-    for(i = (*opt->filters.filptr)-1 ; i>=0 ; i--) {\
-      strcpybuff((*opt->filters.filters)[i+1],(*opt->filters.filters)[i]);\
-    }\
-  }\
-  (*opt->filters.filters)[0][0]='\0';\
-  (*opt->filters.filptr)++;\
-  assertf((*opt->filters.filptr) < opt->maxfilter); \
-} while(0)
+/* Per-slot capacity of the filters array, matching the slot stride allocated by
+   filters_init() in htscore.c (HTS_URLMAXSIZE * 2). */
+#define HTS_FILTER_SLOT_SIZE (HTS_URLMAXSIZE * 2)
+
+#define HT_INSERT_FILTERS0                                                     \
+  do {                                                                         \
+    int i;                                                                     \
+    if (*opt->filters.filptr > 0) {                                            \
+      for (i = (*opt->filters.filptr) - 1; i >= 0; i--) {                      \
+        strlcpybuff((*opt->filters.filters)[i + 1],                            \
+                    (*opt->filters.filters)[i], HTS_FILTER_SLOT_SIZE);         \
+      }                                                                        \
+    }                                                                          \
+    (*opt->filters.filters)[0][0] = '\0';                                      \
+    (*opt->filters.filptr)++;                                                  \
+    assertf((*opt->filters.filptr) < opt->maxfilter);                          \
+  } while (0)
 
 typedef struct htspair_t {
   const char *tag;
@@ -707,17 +715,21 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
         forbidden_url = 1;
         opt->wizard = 2;        // sauter tout le reste
         break;
-      case 0:                  // interdire les mêmes liens: adr/fil
+      case 0: // forbid the same link: adr/fil
         forbidden_url = 1;
-        HT_INSERT_FILTERS0;     // insérer en 0
-        strcpybuff(_FILTERS[0], "-");
-        strcatbuff(_FILTERS[0], jump_identification_const(adr));
-        if (*fil != '/')
-          strcatbuff(_FILTERS[0], "/");
-        strcatbuff(_FILTERS[0], fil);
+        HT_INSERT_FILTERS0; // insert at slot 0
+        {
+          htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+          htsbuff_cpy(&f, "-");
+          htsbuff_cat(&f, jump_identification_const(adr));
+          if (*fil != '/')
+            htsbuff_cat(&f, "/");
+          htsbuff_cat(&f, fil);
+        }
         break;
 
-      case 1:                  // éliminer répertoire entier et sous rép: adr/path/ *
+      case 1: // forbid the whole directory and subdirs: adr/path/*
         forbidden_url = 1;
         {
           size_t i = strlen(fil) - 1;
@@ -725,27 +737,34 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
           while((fil[i] != '/') && (i > 0))
             i--;
           if (fil[i] == '/') {
-            HT_INSERT_FILTERS0; // insérer en 0
-            strcpybuff(_FILTERS[0], "-");
-            strcatbuff(_FILTERS[0], jump_identification_const(adr));
+            htsbuff f;
+
+            HT_INSERT_FILTERS0; // insert at slot 0
+            f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+            htsbuff_cpy(&f, "-");
+            htsbuff_cat(&f, jump_identification_const(adr));
             if (*fil != '/')
-              strcatbuff(_FILTERS[0], "/");
-            strncatbuff(_FILTERS[0], fil, i);
-            if (_FILTERS[0][strlen(_FILTERS[0]) - 1] != '/')
-              strcatbuff(_FILTERS[0], "/");
-            strcatbuff(_FILTERS[0], "*");
+              htsbuff_cat(&f, "/");
+            htsbuff_catn(&f, fil, i);
+            if (f.len > 0 && f.buf[f.len - 1] != '/')
+              htsbuff_cat(&f, "/");
+            htsbuff_cat(&f, "*");
           }
         }
 
         // ** ...
         break;
 
-      case 2:                  // adresse adr*
+      case 2: // the whole address: adr*
         forbidden_url = 1;
-        HT_INSERT_FILTERS0;     // insérer en 0                                
-        strcpybuff(_FILTERS[0], "-");
-        strcatbuff(_FILTERS[0], jump_identification_const(adr));
-        strcatbuff(_FILTERS[0], "*");
+        HT_INSERT_FILTERS0; // insert at slot 0
+        {
+          htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+          htsbuff_cpy(&f, "-");
+          htsbuff_cat(&f, jump_identification_const(adr));
+          htsbuff_cat(&f, "*");
+        }
         break;
 
       case 3:                  // ** A FAIRE
@@ -777,54 +796,70 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
         break;
 
-      case 5:                  // autoriser répertoire entier et fils
-        if ((opt->seeker & 2) == 0) {   // interdiction de monter
+      case 5: // allow the whole directory and its children
+        if ((opt->seeker & 2) == 0) { // not allowed to go up
           size_t i = strlen(fil) - 1;
 
           while((fil[i] != '/') && (i > 0))
             i--;
           if (fil[i] == '/') {
-            HT_INSERT_FILTERS0; // insérer en 0                                
-            strcpybuff(_FILTERS[0], "+");
-            strcatbuff(_FILTERS[0], jump_identification_const(adr));
-            if (*fil != '/')
-              strcatbuff(_FILTERS[0], "/");
-            strncatbuff(_FILTERS[0], fil, i + 1);
-            strcatbuff(_FILTERS[0], "*");
+            HT_INSERT_FILTERS0; // insert at slot 0
+            {
+              htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+              htsbuff_cpy(&f, "+");
+              htsbuff_cat(&f, jump_identification_const(adr));
+              if (*fil != '/')
+                htsbuff_cat(&f, "/");
+              htsbuff_catn(&f, fil, i + 1);
+              htsbuff_cat(&f, "*");
+            }
+          }
+        } else {              // then allow the domain
+          HT_INSERT_FILTERS0; // insert at slot 0
+          {
+            htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+            htsbuff_cpy(&f, "+");
+            htsbuff_cat(&f, jump_identification_const(adr));
+            htsbuff_cat(&f, "*");
           }
-        } else {                // autoriser domaine alors!!
-          HT_INSERT_FILTERS0;   // insérer en 0                                strcpybuff(filters[filptr],"+");
-          strcpybuff(_FILTERS[0], "+");
-          strcatbuff(_FILTERS[0], jump_identification_const(adr));
-          strcatbuff(_FILTERS[0], "*");
         }
         break;
 
       case 6:                  // same domain
-        HT_INSERT_FILTERS0;     // insérer en 0                                strcpybuff(filters[filptr],"+");
-        strcpybuff(_FILTERS[0], "+");
-        strcatbuff(_FILTERS[0], jump_identification_const(adr));
-        strcatbuff(_FILTERS[0], "*");
+        HT_INSERT_FILTERS0;    // insert at slot 0
+        {
+          htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+          htsbuff_cpy(&f, "+");
+          htsbuff_cat(&f, jump_identification_const(adr));
+          htsbuff_cat(&f, "*");
+        }
         break;
         //
-      case 7:                  // autoriser ce répertoire
-        {
-          size_t i = strlen(fil) - 1;
+      case 7: // allow this directory
+      {
+        size_t i = strlen(fil) - 1;
 
-          while((fil[i] != '/') && (i > 0))
-            i--;
-          if (fil[i] == '/') {
-            HT_INSERT_FILTERS0; // insérer en 0                                
-            strcpybuff(_FILTERS[0], "+");
-            strcatbuff(_FILTERS[0], jump_identification_const(adr));
+        while ((fil[i] != '/') && (i > 0))
+          i--;
+        if (fil[i] == '/') {
+          HT_INSERT_FILTERS0; // insert at slot 0
+          {
+            htsbuff f = htsbuff_ptr(_FILTERS[0], HTS_FILTER_SLOT_SIZE);
+
+            htsbuff_cpy(&f, "+");
+            htsbuff_cat(&f, jump_identification_const(adr));
             if (*fil != '/')
-              strcatbuff(_FILTERS[0], "/");
-            strncatbuff(_FILTERS[0], fil, i + 1);
-            strcatbuff(_FILTERS[0], "*[file]");
+              htsbuff_cat(&f, "/");
+            htsbuff_catn(&f, fil, i + 1);
+            htsbuff_cat(&f, "*[file]");
           }
         }
+      }
 
-        break;
+      break;
 
       case 50:                 // on fait rien
         break;

src/htswizard.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htswrap.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htswrap.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htszlib.c

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/htszlib.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

src/httrack-library.h

@@ -1,7 +1,9 @@
 /* ------------------------------------------------------------ */
 /*
 HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 1998-2017 Xavier Roche and other contributors
+Copyright (C) 1998 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -193,6 +195,7 @@ HTSEXT_API int structcheck(const char *path);
 HTSEXT_API int structcheck_utf8(const char *path);
 HTSEXT_API int dir_exists(const char *path);
 HTSEXT_API void infostatuscode(char *msg, int statuscode);
+HTSEXT_API const char *infostatuscode_const(int statuscode);
 HTSEXT_API TStamp mtime_local(void);
 HTSEXT_API void qsec2str(char *st, TStamp t);
 HTSEXT_API char *int2char(strc_int2bytes2 * strc, int n);