Follow <source>/<track> as embedded near-links (#451 )

src/srcset are already extracted from any element via hts_detect[], so <source>/<track> URLs were captured. But hts_detect_embed only listed <img src>, so at the recursion-depth boundary under --near these media were treated as plain links and dropped, unlike <img>. Add a separate HTML5 media table (keeping the legacy one clang-format-stable) and chain the embed lookup through both. 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 00:03:39 +02:00
2 changed files with 47 additions and 9 deletions
--- a/src/htswizard.c
+++ b/src/htswizard.c
@@ -80,6 +80,10 @@ htspair_t hts_detect_embed[] = {
  {NULL, NULL}
 };

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

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

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

--- a/tests/01_engine-parse.test
+++ b/tests/01_engine-parse.test
@@ -323,4 +323,33 @@ 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