Refresh minor legacy constants (#453 )

Three independent low-risk items under tracking issue #453: - HTTP status enum/reason map: add 429 (Too Many Requests) and 451 (Unavailable For Legal Reasons); appended to the HTTPStatusCode enum (installed header, tail-append only) and to infostatuscode_const(). - Drop the 1990s relic port 31337 from the local proxy bind fallback list. - Pin a TLS protocol floor (TLS1.2 via SSL_CTX_set_min_proto_version, with an SSL_OP_NO_* fallback for OpenSSL < 1.1.0) so obsolete SSLv3/TLS1.0/1.1 aren't negotiated. No cert verification added: that remains by design. Adds a -#test=status engine self-test (01_engine-status.test) asserting the reason phrases for 429/451. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Signed-off-by: Xavier Roche <roche@httrack.com>
2026-06-29 05:26:32 +03:00 · 2026-06-29 00:04:07 +02:00
2 changed files with 9 additions and 47 deletions
--- a/src/htswizard.c
+++ b/src/htswizard.c
@@ -80,10 +80,6 @@ htspair_t hts_detect_embed[] = {
  {NULL, NULL}
 };

-/* HTML5 media siblings of <img src>: same near-link treatment (#451) */
-static const htspair_t hts_detect_embed_html5[] = {
-    {"source", "src"}, {"source", "srcset"}, {"track", "src"}, {NULL, NULL}};
-
 /* Internal */
 static int hts_acceptlink_(httrackp * opt, int ptr, const char *adr,
                           const char *fil, const char *tag,
@@ -140,17 +136,6 @@ static int cmp_token(const char *tag, const char *cmp) {
          && !isalnum((unsigned char) tag[p]));
 }

-/* TRUE if (tag, attribute) matches an embedded-asset pair in the table */
-static hts_boolean is_embed_pair(const htspair_t *table, const char *tag,
-                                 const char *attribute) {
-  int i;
-  for (i = 0; table[i].tag != NULL; i++) {
-    if (cmp_token(tag, table[i].tag) && cmp_token(attribute, table[i].attr))
-      return HTS_TRUE;
-  }
-  return HTS_FALSE;
-}
-
 static int hts_acceptlink_(httrackp * opt, int ptr,
                           const char *adr, const char *fil, const char *tag,
                           const char *attribute, int *set_prio_to,
@@ -178,9 +163,15 @@ static int hts_acceptlink_(httrackp * opt, int ptr,

  /* Built-in known tags (<img src=..>, ..) */
  if (forbidden_url != 0 && opt->nearlink && tag != NULL && attribute != NULL) {
-    if (is_embed_pair(hts_detect_embed, tag, attribute) ||
-        is_embed_pair(hts_detect_embed_html5, tag, attribute)) {
-      embedded_triggered = 1;
+    int i;
+
+    for(i = 0; hts_detect_embed[i].tag != NULL; i++) {
+      if (cmp_token(tag, hts_detect_embed[i].tag)
+          && cmp_token(attribute, hts_detect_embed[i].attr)
+        ) {
+        embedded_triggered = 1;
+        break;
+      }
    }
  }

--- a/tests/01_engine-parse.test
+++ b/tests/01_engine-parse.test
@@ -323,33 +323,4 @@ grep -Fq 'href="ahref%20(4).gif"' "$saved9" ||
 ! grep -Eq '(src|href)="[^"]*%28' "$saved9" ||
    ! echo "FAIL #163: gate over-fired onto a non-url() attribute link" || exit 1

-# HTML5 <source>/<track> follow as embedded near-links past the -r2 depth boundary (#451).
-# img.gif positive control; plain.gif (bare <a href>) negative control proves the gate is selective.
-site10="$tmp/html5media"
-mkdir -p "$site10"
-for f in img ss plain; do gif "$site10/$f.gif"; done
-printf 'x' >"$site10/v.webm"
-printf 'x' >"$site10/subs.vtt"
-cat >"$site10/index.html" <<EOF
-<html><body><a href="leaf.html">leaf</a></body></html>
-EOF
-cat >"$site10/leaf.html" <<EOF
-<html><body>
-<img src="img.gif">
-<picture><source srcset="ss.gif 2x"></picture>
-<video><source src="v.webm"></video>
-<video><track src="subs.vtt"></video>
-<a href="plain.gif">plain link past the boundary</a>
-</body></html>
-EOF
-out10="$tmp/html5media-out"
-rm -rf "$out10"
-mkdir -p "$out10"
-httrack "file://$site10/index.html" -O "$out10" --quiet --near -r2 >"$out10/.log" 2>&1 || true
-found "img.gif" "$out10"
-found "ss.gif" "$out10"
-found "v.webm" "$out10"
-found "subs.vtt" "$out10"
-notfound "plain.gif" "$out10"
-
 exit 0