Improve generic navigation pattern recognition

php-transformer/src/HtmlToBlocks/HtmlTransformer.php

@@ -4080,18 +4080,14 @@ private function hasSidebarAndContentChildren(DOMElement $element): bool
      */
     private function navigationSectionBlockFromElement(DOMElement $element): ?array
     {
-        if ( ! $this->hasNavigationContainerSignal($element) ) {
-            return null;
-        }
-
         $heading = null;
         $anchors = array();
         foreach ( $element->childNodes as $child ) {
             if ( XML_TEXT_NODE === $child->nodeType && '' === trim($child->textContent ?? '') ) {
                 continue;
             }
 
-            if ( $child instanceof DOMElement && preg_match('/^h[1-6]$/i', $child->tagName) ) {
+            if ( $child instanceof DOMElement && $this->isNavigationSectionHeading($child) ) {
                 if ( $heading instanceof DOMElement ) {
                     return null;
                 }
@@ -4111,6 +4107,10 @@ private function navigationSectionBlockFromElement(DOMElement $element): ?array
             return null;
         }
 
+        if ( ! $this->hasNavigationContainerSignal($element) && ! $this->hasSoftNavigationSectionHeadingSignal($heading) ) {
+            return null;
+        }
+
         $sectionFallbacks = array();
         $blocks = array( $this->convertElement($heading, $sectionFallbacks, true) );
         $links = array();
@@ -4126,6 +4126,25 @@ private function navigationSectionBlockFromElement(DOMElement $element): ?array
         return $this->createBlock('core/group', $this->presentationAttributes($element), array_values(array_filter($blocks)), $element);
     }
 
+    private function isNavigationSectionHeading(DOMElement $element): bool
+    {
+        if ( preg_match('/^h[1-6]$/i', $element->tagName) ) {
+            return true;
+        }
+
+        if ( ! in_array(strtolower($element->tagName), array( 'div', 'p', 'span' ), true) || '' === trim($element->textContent ?? '') ) {
+            return false;
+        }
+
+        $name = strtolower(trim($this->attr($element, 'class') . ' ' . $this->attr($element, 'id') . ' ' . $this->attr($element, 'role') . ' ' . $this->attr($element, 'aria-label')));
+        return (bool) preg_match('/(?:^|[\s_-])(?:heading|label|title)(?:$|[\s_-])/', $name);
+    }
+
+    private function hasSoftNavigationSectionHeadingSignal(DOMElement $element): bool
+    {
+        return ! preg_match('/^h[1-6]$/i', $element->tagName) && $this->isNavigationSectionHeading($element);
+    }
+
     private function hasNavigationContainerSignal(DOMElement $element): bool
     {
         if ( 'navigation' === strtolower($this->attr($element, 'role')) ) {

php-transformer/src/HtmlToBlocks/Patterns/NavigationPattern.php

@@ -171,6 +171,8 @@ private function navigationLinkBlock(DOMElement $anchor, callable $presentationA
 
     private function navigationLabel(string $html): string
     {
+        $html = preg_replace('/<svg\b[^>]*>.*?<\/svg>/is', '', $html) ?? $html;
+        $html = preg_replace('/<span\b[^>]*>\s*<\/span>/i', '', $html) ?? $html;
         $html = preg_replace('/<([a-z][a-z0-9]*)\b[^>]*\baria-hidden\s*=\s*(["\'])?true\2[^>]*>\s*<\/\1>/i', '', $html) ?? $html;
         $html = preg_replace('/<\/?(?:' . self::BLOCK_LEVEL_LABEL_TAGS . ')\b[^>]*>/i', '', $html) ?? $html;
         return trim($html);

php-transformer/tests/fixtures/parity/html-footer-labeled-link-clusters.json

@@ -0,0 +1,41 @@
+{
+  "schema": "blocks-engine/php-transformer/parity-fixture/v1",
+  "name": "html-footer-labeled-link-clusters",
+  "description": "Converts footer and mobile navigation link clusters introduced by labeled span headings into grouped navigation blocks.",
+  "source_reference": {
+    "repo": "php-transformer",
+    "path": "tests/fixtures/parity/html-footer-labeled-link-clusters.json",
+    "notes": "Generic fixture based on SSI footer CTA/navigation columns and mobile drawer sections."
+  },
+  "legacy_comparison": {
+    "skip": true,
+    "reason": "This upstream primitive fixture has no downstream legacy comparison."
+  },
+  "operation": "html_transformer.transform",
+  "input": {
+    "content": "<footer class=\"site-footer\" role=\"contentinfo\"><div class=\"footer-top\"><div><span class=\"footer-nav__heading\">Shop</span><a href=\"shop-all.html\" class=\"footer-nav__link\">Shop All</a><a href=\"bundles.html\" class=\"footer-nav__link\">Bundles</a><a href=\"by-outing.html\" class=\"footer-nav__link\">By Outing</a></div><div class=\"mobile-nav__section\"><span class=\"mobile-nav__label\">Support</span><a href=\"help.html\" class=\"mobile-nav__link\">Help Center</a><a href=\"returns.html\" class=\"mobile-nav__link\">Returns</a></div></div></footer>"
+  },
+  "expected_blocks": [
+    { "path": "blocks.0", "name": "core/group", "attrs": { "className": "site-footer" } },
+    { "path": "blocks.0.innerBlocks.0", "name": "core/group", "attrs": { "className": "footer-top" } },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0", "name": "core/group" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0.innerBlocks.0", "name": "core/paragraph" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0.innerBlocks.1", "name": "core/navigation" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0.innerBlocks.1.innerBlocks.0", "name": "core/navigation-link", "attrs": { "label": "Shop All", "url": "shop-all.html", "kind": "custom" } },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1", "name": "core/group", "attrs": { "className": "mobile-nav__section" } },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1.innerBlocks.0", "name": "core/paragraph" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1.innerBlocks.1", "name": "core/navigation" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1.innerBlocks.1.innerBlocks.0", "name": "core/navigation-link", "attrs": { "label": "Help Center", "url": "help.html", "kind": "custom" } }
+  ],
+  "expected_fallbacks": [],
+  "expect": [
+    { "path": "status", "assert": "equals", "value": "success" },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks", "assert": "count", "count": 2 },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0.innerBlocks.1.innerBlocks", "assert": "count", "count": 3 },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1.innerBlocks.1.innerBlocks", "assert": "count", "count": 2 },
+    { "path": "fallbacks", "assert": "count", "count": 0 },
+    { "path": "serialized_blocks", "assert": "contains", "value": "<!-- wp:navigation" },
+    { "path": "serialized_blocks", "assert": "not_contains", "value": "<!-- wp:html" },
+    { "path": "coverage.0.fallback_count", "assert": "equals", "value": 0 }
+  ]
+}

php-transformer/tests/fixtures/parity/html-nav-decorative-labels.json

@@ -0,0 +1,37 @@
+{
+  "schema": "blocks-engine/php-transformer/parity-fixture/v1",
+  "name": "html-nav-decorative-labels",
+  "description": "Strips decorative SVG and empty icon spans from navigation labels while preserving the link URLs and submenu structure.",
+  "source_reference": {
+    "repo": "php-transformer",
+    "path": "tests/fixtures/parity/html-nav-decorative-labels.json",
+    "notes": "Generic fixture based on static-site desktop dropdown navigation with chevrons and icon dots in anchors."
+  },
+  "legacy_comparison": {
+    "skip": true,
+    "reason": "This upstream primitive fixture has no downstream legacy comparison."
+  },
+  "operation": "html_transformer.transform",
+  "input": {
+    "content": "<nav class=\"main-nav\" aria-label=\"Main navigation\"><div class=\"nav-item\"><a href=\"by-outing.html\" class=\"nav-link\">By Outing <svg class=\"nav-chevron\" viewBox=\"0 0 10 6\"><path d=\"M1 1l4 4 4-4\"></path></svg></a><div class=\"dropdown\"><a href=\"by-outing.html#day-hike\" class=\"dropdown__link\"><span class=\"dropdown__dot\"></span>Day Hike</a><a href=\"by-outing.html#camp\" class=\"dropdown__link\"><span class=\"dropdown__dot\"></span>Weekend Camp</a></div></div><div class=\"nav-item\"><a href=\"bundles.html\" class=\"nav-link\">Bundles</a></div></nav>"
+  },
+  "expected_blocks": [
+    { "path": "blocks.0", "name": "core/navigation", "attrs": { "className": "main-nav" } },
+    { "path": "blocks.0.innerBlocks.0", "name": "core/navigation-submenu", "attrs": { "label": "By Outing", "url": "by-outing.html", "kind": "custom" } },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.0", "name": "core/navigation-link", "attrs": { "label": "Day Hike", "url": "by-outing.html#day-hike", "kind": "custom" } },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks.1", "name": "core/navigation-link", "attrs": { "label": "Weekend Camp", "url": "by-outing.html#camp", "kind": "custom" } },
+    { "path": "blocks.0.innerBlocks.1", "name": "core/navigation-link", "attrs": { "label": "Bundles", "url": "bundles.html", "kind": "custom" } }
+  ],
+  "expected_fallbacks": [],
+  "expect": [
+    { "path": "status", "assert": "equals", "value": "success" },
+    { "path": "blocks.0.innerBlocks", "assert": "count", "count": 2 },
+    { "path": "blocks.0.innerBlocks.0.innerBlocks", "assert": "count", "count": 2 },
+    { "path": "fallbacks", "assert": "count", "count": 0 },
+    { "path": "serialized_blocks", "assert": "contains", "value": "\"label\":\"By Outing\"" },
+    { "path": "serialized_blocks", "assert": "contains", "value": "\"label\":\"Day Hike\"" },
+    { "path": "serialized_blocks", "assert": "not_contains", "value": "nav-chevron" },
+    { "path": "serialized_blocks", "assert": "not_contains", "value": "dropdown__dot" },
+    { "path": "coverage.0.fallback_count", "assert": "equals", "value": 0 }
+  ]
+}