Merge pull request #18390 from alexcat3/fix-issue-18099

Handle toUnicode cMaps that omit leading zeros in hex encoded UTF-16 (issue 18099)

src/core/evaluator.js

@@ -3852,6 +3852,11 @@ class PartialEvaluator {
             map[charCode] = String.fromCodePoint(token);
             return;
           }
+          // Add back omitted leading zeros on odd length tokens
+          // (fixes issue #18099)
+          if (token.length % 2 !== 0) {
+            token = "\u0000" + token;
+          }
           const str = [];
           for (let k = 0; k < token.length; k += 2) {
             const w1 = (token.charCodeAt(k) << 8) | token.charCodeAt(k + 1);

test/pdfs/.gitignore

@@ -653,3 +653,4 @@
 !bug1539074.1.pdf
 !issue18305.pdf
 !issue18360.pdf
+!issue18099_reduced.pdf

test/unit/api_spec.js

@@ -3419,6 +3419,21 @@ 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!");
+
+      await loadingTask.destroy();
+    });
+
     it("gets text content, and check that out-of-page text is not present (bug 1755201)", async function () {
       if (isNodeJS) {
         pending("Linked test-cases are not supported in Node.js.");