🗃️ Update codebase 🗃️

rootfs/root/docker/setup/06-post.sh

rootfs/root/docker/setup/06-post.sh

@@ -26,141 +26,26 @@ set -o pipefail
 exitCode=0
 LIST_INDEX_FILE="/usr/share/httpd/default/list.html"
 RAW_URL="https://raw.githubusercontent.com/alecmuffett/real-world-onion-sites/refs/heads/master/README.md"
-
 # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
 # Predefined actions
-md2html() {
+__build_onions_html() {
-	# Emit a lightweight container; you can remove the outer <div> if you don’t want it.
+	# temp file (POSIX-safe mktemp use)
-	emit_open() {
+	tmp_md="$(mktemp 2>/dev/null || printf '/tmp/rwos.%s' "$$")" || {
-		cat <<'EOF'
+		printf '%s\n' "mktemp failed" >&2
-<div class="wrap md-body">
+		return 1
-EOF
-	}
-	emit_close() {
-		cat <<'EOF'
-</div>
-EOF
 	}
+	trap 'rm -f "$tmp_md"' 0 1 2 3 15
 
-	# AWK Markdown -> HTML (body only). Designed to handle the README’s structure.
+	# 1) Fetch README (UTF-8)
-	awk_prog='
+	if ! curl -fsSL "$RAW_URL" >"$tmp_md"; then
-BEGIN{
+		printf '%s\n' "curl failed to fetch README" >&2
-  in_code=0; in_ul=0; in_ol=0; in_blockquote=0; in_table=0; table_open=0;
+		return 2
-  last_nonblank="";
+	fi
-  FS="";
-}
-function htmlesc(s){ gsub(/&/,"&amp;",s); gsub(/</,"&lt;",s); gsub(/>/,"&gt;",s); return s }
 
-function linkify(s){
+	# 2) Emit full HTML
-  # Images: ![alt](src)
+	{
-  s = gensub(/!\[([^[\]]+)\]\(([^) \t]+)\)/, "<img alt=\"\\1\" src=\"\\2\" />", "g", s)
+		# --- HEAD (your exact head) ---
-  # Links: [text](url)
+		cat <<'HTML_HEAD'
-  s = gensub(/\[([^[\]]+)\]\(([^) \t]+)\)/, "<a href=\"\\2\" rel=\"noopener noreferrer\">\\1<\\/a>", "g", s)
-  # Inline code
-  s = gensub(/`([^`]+)`/, "<code>\\1<\\/code>", "g", s)
-  # Bold / italic (simple)
-  s = gensub(/\*\*([^*]+)\*\*/, "<strong>\\1<\\/strong>", "g", s)
-  s = gensub(/\*([^*]+)\*/, "<em>\\1<\\/em>", "g", s)
-  # Autolink http(s)
-  s = gensub(/(https?:\/\/[A-Za-z0-9._~:\/?#\\[\\]@!$&'\''()*+,;=%-]+)/, "<a href=\"\\1\" rel=\"noopener noreferrer\">\\1<\\/a>", "g", s)
-  # Bare .onion (with optional path/query)
-  s = gensub(/([A-Za-z2-7]{16,56}\\.onion([A-Za-z0-9._~:\/?#\\[\\]@!$&'\''()*+,;=%-]*)?)/, "<a href=\"http:\\/\\/\\1\" rel=\"noopener noreferrer\">\\1<\\/a>", "g", s)
-  return s
-}
-
-function flush_p(){ if(pbuf!=""){ printf("<p>%s</p>\n", pbuf); pbuf="" } }
-function close_lists(){ if(in_ul){ print "</ul>"; in_ul=0 } if(in_ol){ print "</ol>"; in_ol=0 } }
-function close_blockquote(){ if(in_blockquote){ print "</blockquote>"; in_blockquote=0 } }
-
-function table_close_fn(){ if(table_open){ print "</tbody></table>"; table_open=0 } in_table=0 }
-function split_cells(line,  n,i){
-  sub(/^ *\|/,"",line); sub(/\| *$/,"",line);
-  n=split(line, C, /\|/);
-  for(i=1;i<=n;i++){ gsub(/^ +| +$/,"",C[i]) }
-  return n
-}
-
-{
-  raw=$0
-  if(raw ~ /[^[:space:]]/){ last_nonblank=raw }
-
-  # Fenced code
-  if(!in_code && raw ~ /^```/){ flush_p(); close_lists(); close_blockquote(); print "<pre><code>"; in_code=1; next }
-  if(in_code){
-    if(raw ~ /^```/){ print "</code></pre>"; in_code=0; next }
-    print htmlesc(raw); next
-  }
-
-  # Blank line
-  if(raw ~ /^[[:space:]]*$/){
-    if(in_table==0){ flush_p(); close_lists(); close_blockquote() }
-    next
-  }
-
-  # HR
-  if(raw ~ /^ *(-{3,}|\*{3,}|_{3,}) *$/){ flush_p(); close_lists(); close_blockquote(); print "<hr />"; next }
-
-  # Table separator row -> open table with the previous header line
-  if(raw ~ /^ *\|? *:?-{3,}:? *(?:\| *:?-{3,}:? *)+\|? *$/){
-    hdr=last_nonblank
-    split_cells(hdr); print "<table><thead><tr>";
-    for(i=1;i in C;i++){ printf("<th>%s</th>", linkify(htmlesc(C[i]))) }
-    print "</tr></thead><tbody>"; in_table=1; table_open=1; next
-  }
-  if(in_table && raw ~ /\|/){
-    split_cells(raw); printf("<tr>");
-    for(i=1;i in C;i++){ printf("<td>%s</td>", linkify(htmlesc(C[i]))) }
-    print "</tr>"; next
-  }
-  if(in_table){ table_close_fn() }
-
-  # Blockquotes
-  if(raw ~ /^ *> */){
-    flush_p(); close_lists();
-    if(!in_blockquote){ print "<blockquote>"; in_blockquote=1 }
-    gsub(/^ *> */,"",raw); print "<p>" linkify(htmlesc(raw)) "</p>"; next
-  } else if(in_blockquote){ close_blockquote() }
-
-  # Headings
-  if(raw ~ /^#{1,6} /){
-    flush_p(); close_lists(); close_blockquote();
-    m=match(raw,/^#{1,6}/); level=RLENGTH; text=substr(raw, level+2);
-    printf("<h%d>%s</h%d>\n", level, linkify(htmlesc(text)), level); next
-  }
-
-  # Lists
-  if(raw ~ /^ *([-*]) +/){
-    flush_p(); if(!in_ul){ print "<ul>"; in_ul=1 }
-    item=raw; sub(/^ *[-*] +/,"",item); print "<li>" linkify(htmlesc(item)) "</li>"; next
-  }
-  if(raw ~ /^ *[0-9]+\. +/){
-    flush_p(); if(!in_ol){ print "<ol>"; in_ol=1 }
-    item=raw; sub(/^ *[0-9]+\. +/,"",item); print "<li>" linkify(htmlesc(item)) "</li>"; next
-  }
-  if(in_ul && raw !~ /^ *([-*]) +/ && raw !~ /^[[:space:]]*$/){ close_lists() }
-  if(in_ol && raw !~ /^ *[0-9]+\. +/ && raw !~ /^[[:space:]]*$/){ close_lists() }
-
-  # Paragraph accumulation (soft-wrap)
-  line = linkify(htmlesc(raw))
-  if(pbuf==""){ pbuf=line } else { pbuf=pbuf " " line }
-}
-END{
-  if(in_code){ print "</code></pre>" }
-  if(in_table){ table_close_fn() }
-  if(in_blockquote){ close_blockquote() }
-  flush_p(); close_lists()
-}
-'
-
-	emit_open
-	curl -q -LSsf "$RAW_URL" | awk "$awk_prog" || return 1
-	emit_close
-}
-
-# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-# Main script
-echo "Creating the onion web sites list"
-cat >"$LIST_INDEX_FILE" <<'HTML'
 <!doctype html>
 <html lang="en">
 <head>
@@ -171,10 +56,76 @@ cat >"$LIST_INDEX_FILE" <<'HTML'
   <title>Welcome to your tor site</title>
 </head>
 <body>
-HTML
+<main>
-md2html >>"$LIST_INDEX_FILE"
+<pre>
-printf '<div><center>%s</center></div>\n' "Last uopdated on $(date +'%A, %B %d, %Y at %H:%M %Z')" >>"$LIST_INDEX_FILE"
+HTML_HEAD
-printf '\n</body>\n</html>\n' >>"$LIST_INDEX_FILE"
+
+		# --- Body content pipeline ---
+		# Step A: replace GitHub :shortcodes: with emoji
+		# Step B: HTML-escape (&, <, >) to preserve literal layout
+		# Step C: auto-link http(s) URLs (done after escaping so <a> survives)
+		awk '
+      BEGIN { OFS=""; RS="\n"; ORS="\n" }
+      {
+        gsub(":white_check_mark:", "✅")
+        gsub(":closed_lock_with_key:", "🔐")
+        gsub(":small_red_triangle:", "🔺")
+        gsub(":key:", "🔑")
+        gsub(":question:", "❓")
+        gsub(":sos:", "🆘")
+        gsub(":alarm_clock:", "⏰")
+        gsub(":timer_clock:", "⏲️")
+        gsub(":exclamation:", "❗")
+        gsub(":eight_spoked_asterisk:", "✳️")
+        gsub(":crystal_ball:", "🔮")
+        gsub(":lock:", "🔒")
+        gsub(":arrow_up:", "⬆️")
+        gsub(":wrench:", "🔧")
+        gsub(":new:", "🆕")
+        print
+      }
+    ' "$tmp_md" |
+			awk '
+        # HTML-escape in correct order
+        { gsub(/&/, "&amp;"); gsub(/</, "&lt;"); gsub(/>/, "&gt;"); print }
+      ' |
+			awk '
+        # Auto-link URLs using POSIX awk (ERE), no gensub needed.
+        # Allowed URL chars kept conservative; onion links are fine.
+        {
+          line = $0
+          re = "https?://[A-Za-z0-9._~:/?#@!$&()*+,;=%-]+"
+          out = ""
+          while (match(line, re)) {
+            pre = substr(line, 1, RSTART-1)
+            url = substr(line, RSTART, RLENGTH)
+            line = substr(line, RSTART+RLENGTH)
+            out = out pre "<a href=\"" url "\" rel=\"noopener noreferrer\">" url "</a>"
+          }
+          $0 = out line
+          print
+        }
+      '
+
+		# --- TAIL ---
+		cat <<'HTML_TAIL'
+</pre>
+<div><center>%s</center></div>\n' "Last uopdated on $(date +'%A, %B %d, %Y at %H:%M %Z')"
+</main>
+</body>
+</html>
+HTML_TAIL
+	} >"$LIST_INDEX_FILE" || {
+		printf '%s\n' "write failed: $LIST_INDEX_FILE" >&2
+		return 3
+	}
+
+	printf 'Wrote %s\n' "$LIST_INDEX_FILE" >&2
+}
+
+# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+# Main script
+__build_onions_html
 # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
 # Set the exit code
 #exitCode=$?