Localize the hardcoded step3/step4 wizard headings in webhttrack

The "Select URLs" and "Start" section headings on the webhttrack server
wizard were literal English, bypassing the ${LANG_...} substitution, so
they stayed English in all 30 locales. Reuse existing, already-translated
keys: step3 -> ${LANG_G44} ("Web Addresses: (URL)"), step4 -> ${LANG_J9}
("Start"). No lang/*.txt changes needed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/ci.yml

@@ -618,3 +618,31 @@ jobs:
               echo "Fix locally with: git clang-format --binary clang-format-19 $base"
               exit 1 ;;
           esac
+
+  man-page-sync:
+    name: man page / html in sync
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      # html/httrack.man.html is groff-rendered from man/httrack.1 and committed.
+      # Rendering needs the full groff html device, so CI can't regenerate it;
+      # instead require the two to move together: a PR that touches httrack.1
+      # must also touch the html, catching the "regenerated roff, forgot html".
+      - name: httrack.1 changes must include html/httrack.man.html
+        run: |
+          set -euo pipefail
+          git fetch --no-tags origin \
+            "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
+          base="origin/${{ github.base_ref }}"
+          changed="$(git diff --name-only "$base"...HEAD)"
+          has() { printf '%s\n' "$changed" | grep -qx "$1"; }
+          if has man/httrack.1 && ! has html/httrack.man.html; then
+            echo "::error::man/httrack.1 changed but html/httrack.man.html did not."
+            echo "Regenerate it with: make -C man regen-man-html (needs the full groff package)."
+            exit 1
+          fi
+          echo "man/html sync OK."

html/cmdguide.html

@@ -219,6 +219,23 @@ that a <tt>403 Forbidden</tt> is a server refusal, not a robots rule: robots
 options will not help there. That is an
 <a href="#identity">identity</a> problem.</p>
 
+<h4>Filter wildcards</h4>
+<p>Inside a filter pattern, <tt>*</tt> matches any run of characters; a few
+bracket forms match narrower sets. The full table, with size and mime rules, is on
+<a href="filters.html">the filters page</a>.</p>
+<table class="tblRegular tableWidth" border="0">
+  <tr class="tblHeaderColor"><td><b>Wildcard</b></td><td><b>Matches</b></td><td><b>Example</b></td></tr>
+  <tr><td><tt>*</tt></td><td>any run of characters</td><td><tt>+*.pdf</tt> &mdash; any URL ending <tt>.pdf</tt></td></tr>
+  <tr><td><tt>*[file]</tt>, <tt>*[name]</tt></td><td>one path segment (any char but <tt>/</tt> and <tt>?</tt>)</td><td><tt>example.com/*[file]/</tt> &mdash; a directory-index page</td></tr>
+  <tr><td><tt>*[path]</tt></td><td>a path, slashes allowed (any char but <tt>?</tt>)</td><td><tt>example.com/*[path].zip</tt></td></tr>
+  <tr><td><tt>*[param]</tt></td><td>an optional query string</td><td><tt>page.html*[param]</tt> matches with or without <tt>?...</tt></td></tr>
+  <tr><td><tt>*[a,b,c]</tt></td><td>any one character in the set</td><td><tt>*[a,b,c].txt</tt></td></tr>
+  <tr><td><tt>*[a-z]</tt></td><td>any one character in the range</td><td><tt>img*[0-9].gif</tt></td></tr>
+  <tr><td><tt>*[\x]</tt></td><td>the literal character x (escapes <tt>* [ ] \</tt>)</td><td><tt>*[\*]</tt> matches a real <tt>*</tt></td></tr>
+  <tr><td><tt>*[&lt;NN]</tt>, <tt>*[&gt;NN]</tt></td><td>file size in KB below / above NN</td><td><tt>-*.gif*[&lt;5]</tt> skips GIFs under 5&nbsp;KB</td></tr>
+  <tr><td><tt>*[]</tt></td><td>end anchor: nothing may follow</td><td><tt>*.html*[]</tt> rejects <tt>i.html?p=1</tt></td></tr>
+</table>
+
 <h3 id="limits">4. Limits and politeness</h3>
 
 <p>HTTrack ships cautious on purpose: it is easy to hammer a small site by

html/server/step3.html

@@ -95,7 +95,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>Select URLs</em></h2>
+	<h2 align="center"><em>${LANG_G44}</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}

html/server/step4.html

@@ -77,7 +77,7 @@ ${do:end-if}
 
 <table border="0" width="100%">
 <tr><td width="90%">
-	<h2 align="center"><em>Start</em></h2>
+	<h2 align="center"><em>${LANG_J9}</em></h2>
 </td>
 ${/* show help only if available */}
 ${do:if-file-exists:html/index.html}

man/Makefile.am

@@ -16,6 +16,11 @@ regen-man: makeman.sh $(top_builddir)/src/httrack$(EXEEXT)
 
 # 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
+# Strip groff's version-stamp and creation-date comments so the committed file
+# doesn't churn across groff versions or rebuilds; the ci man-page-sync guard
+# only requires this file to change whenever httrack.1 does.
 regen-man-html: httrack.1
-	groff -t -man -Thtml $(srcdir)/httrack.1 > $(top_srcdir)/html/httrack.man.html
+	groff -t -man -Thtml $(srcdir)/httrack.1 \
+		| sed -e 's/groff version [0-9][0-9.]*/groff/' -e '/^<!-- CreationDate:/d' \
+		> $(top_srcdir)/html/httrack.man.html
 .PHONY: regen-man-html