Add unit test for handling PDFs with toUnicode cMaps that omit leadin…

…g zeros in hex encoded utf16
mozilla · Jul 4, 2024 · 69de633 · 69de633
1 parent bb81286
commit 69de633
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 0 deletions.
diff --git a/test/pdfs/issue18099_reduced.pdf b/test/pdfs/issue18099_reduced.pdf
diff --git a/test/unit/api_spec.js b/test/unit/api_spec.js
@@ -3418,6 +3418,18 @@ Caron Broadcasting, Inc., an Ohio corporation (“Lessee”).`)
 
       await loadingTask.destroy();
     });
+    it("gets text content, correctly handling documents with toUnicode cmaps that omit leading zeros on hex-encoded UTF-16", async function () {
+      const loadingTask = getDocument(
+        buildGetDocumentParams("issue18099_reduced.pdf")
+      );
+      const pdfDoc = await loadingTask.promise;
+      const pdfPage = await pdfDoc.getPage(1);
+      const { items } = await pdfPage.getTextContent({
+        disableNormalization: true,
+      });
+      const text = mergeText(items);
+      expect(text).toEqual("Hello world!");
+    });
 
     it("gets text content, and check that out-of-page text is not present (bug 1755201)", async function () {
       if (isNodeJS) {