Merge pull request #20327 from edoardocavazza/collect-list-table-children

Collect all child nodes of lists and tables in StructTree

Author: calixteman

src/core/struct_tree.js

@@ -824,6 +824,23 @@ class StructTreePage {
 
     const element = new StructElementNode(this, dict);
     map.set(dict, element);
+    switch (element.role) {
+      case "L":
+      case "LBody":
+      case "LI":
+      case "Table":
+      case "THead":
+      case "TBody":
+      case "TFoot":
+      case "TR": {
+        // Always collect all child nodes of lists and tables, even empty ones
+        for (const kid of element.kids) {
+          if (kid.type === StructElementType.ELEMENT) {
+            this.addNode(kid.dict, map, level - 1);
+          }
+        }
+      }
+    }
 
     const parent = dict.get("P");
 

test/pdfs/.gitignore

@@ -620,6 +620,7 @@
 !autoprint.pdf
 !bug1811694.pdf
 !bug1811510.pdf
+!issue20324.pdf
 !bug1815476.pdf
 !issue16021.pdf
 !bug1770750.pdf

test/pdfs/issue20324.pdf

@@ -300,6 +300,34 @@ describe("struct tree", function () {
       },
       struct
     );
+  });
+
+  it("should collect all list and table items in StructTree", async function () {
+    const findNodes = (node, check) => {
+      const results = [];
+      if (check(node)) {
+        results.push(node);
+      }
+      if (node.children) {
+        for (const child of node.children) {
+          results.push(...findNodes(child, check));
+        }
+      }
+      return results;
+    };
+    const loadingTask = getDocument(buildGetDocumentParams("issue20324.pdf"));
+
+    const pdfDoc = await loadingTask.promise;
+    const page = await pdfDoc.getPage(1);
+    const tree = await page.getStructTree({
+      includeMarkedContent: true,
+    });
+    const cells = findNodes(tree, node => node.role === "TD");
+    expect(cells.length).toEqual(4);
+
+    const listItems = findNodes(tree, node => node.role === "LI");
+    expect(listItems.length).toEqual(4);
+
     await loadingTask.destroy();
   });
 });