@uniweb/semantic-parser 1.1.10 → 1.1.11

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@uniweb/semantic-parser",
-  "version": "1.1.10",
+  "version": "1.1.11",
   "description": "Semantic parser for ProseMirror/TipTap content structures",
   "type": "module",
   "main": "./src/index.js",

package/src/processors/groups.js

@@ -5,7 +5,7 @@
  */
 function flattenGroup(group) {
     if (!group) return null;
-    return {
+    const flat = {
         title: group.header.title || '',
         pretitle: group.header.pretitle || '',
         subtitle: group.header.subtitle || '',
@@ -21,6 +21,11 @@ function flattenGroup(group) {
         quotes: group.body.quotes || [],
         headings: group.body.headings || [],
     };
+    // Only attach rare collections when present so we don't pay the cost
+    // on every page (math is <1% of content in practice; authors who need
+    // ordering should use content.sequence anyway).
+    if (group.body.math && group.body.math.length) flat.math = group.body.math;
+    return flat;
 }
 
 /**
@@ -240,6 +245,9 @@ function processGroupContent(elements) {
         data: {},
         quotes: [],
         headings: [],
+        // `math` is lazily added in the math_display case when encountered —
+        // avoids allocating an empty array on every group (math is rare; most
+        // consumers that care about ordering should use content.sequence).
     };
 
     const metadata = {
@@ -370,6 +378,23 @@ function processGroupContent(elements) {
                     });
                     break;
 
+                case "math_display":
+                    // Block-level math from $$...$$ on its own line or ```math
+                    // fence. The mathml string is pre-compiled at parse time;
+                    // foundations render it by setting dangerouslySetInnerHTML
+                    // on the mathml field. The optional id enables numbered
+                    // cross-references (see @uniweb/scholar/math).
+                    // For ordered rendering alongside paragraphs, prefer
+                    // `content.sequence` — this flat collection is convenience
+                    // sugar when order doesn't matter. Allocate lazily so
+                    // pages without math pay nothing.
+                    (body.math ||= []).push({
+                        id: element.id || null,
+                        latex: element.latex || '',
+                        mathml: element.mathml || '',
+                    });
+                    break;
+
                 case "inset":
                     body.insets.push({ refId: element.refId });
                     break;

package/src/processors/sequence.js

@@ -167,16 +167,33 @@ function createSequenceElement(node, options = {}) {
                 type: "inset",
                 refId: attrs.refId,
             };
+
+        case "math_display":
+            // Block-level math. The mathml string is pre-compiled at parse
+            // time (content-reader) and renders natively via kit's HTML
+            // renderers. Foundations can read el.mathml from content.sequence.
+            // The optional id enables numbered cross-references via
+            // @uniweb/scholar/math's <EquationRef>.
+            return {
+                type: "math_display",
+                id: node.attrs?.id || null,
+                latex: node.attrs?.latex || "",
+                mathml: node.attrs?.mathml || "",
+                attrs,
+            };
         case "ImageBlock":
             return {
                 type: "image",
                 attrs: parseImgBlock(attrs),
             };
         case "image":
-            // Standard ProseMirror image node - wrap attrs like ImageBlock
+            // Standard ProseMirror image node - resolve attrs the same way as
+            // ImageBlock so info.identifier lands as a CDN URL. CLI-deployed
+            // content uses this node type; without parseImgBlock the url
+            // wouldn't be populated and components render an empty slot.
             return {
                 type: "image",
-                attrs: attrs || {},
+                attrs: parseImgBlock(attrs || {}),
             };
         case "Video":
             return {
@@ -381,6 +398,12 @@ function getTextContent(content, options = {}) {
                 }
 
                 return prev + styledText;
+            } else if (type === "math_inline") {
+                // Pre-compiled MathML string rides straight into the
+                // paragraph's HTML and reaches kit's Text via
+                // dangerouslySetInnerHTML. The HTML5 parser handles <math>
+                // as MathML natively — zero runtime math library needed.
+                return prev + (curr.attrs?.mathml || "");
             } else if (type === "hardBreak") {
                 return prev + "<br>";
             } else {