Start using Iterator.prototype.join in the code-base

This is an upcoming JavaScript feature, which helps avoid creating intermediate Arrays in some cases; see https://github.com/tc39/proposal-iterator-join

Firefox implemented this in [bug 2004803](https://bugzilla.mozilla.org/show_bug.cgi?id=2004803), and it was enabled by default in [bug 2047995](https://bugzilla.mozilla.org/show_bug.cgi?id=2047995).

This patch changes two Objects to Maps, in the XFA-parsing respectively the find-implementation, to make use of the new feature.

src/core/document.js

@@ -1280,13 +1280,13 @@ class PDFDocument {
     if (!streams) {
       return null;
     }
-    const data = Object.create(null);
+    const data = new Map();
     for (const [key, stream] of streams) {
       if (!stream) {
         continue;
       }
       try {
-        data[key] = stringToUTF8String(stream.getString());
+        data.set(key, stringToUTF8String(stream.getString()));
       } catch {
         warn("XFA - Invalid utf-8 string.");
         return null;

src/core/xfa/factory.js

@@ -132,10 +132,7 @@ class XFAFactory {
   }
 
   static _createDocument(data) {
-    if (!data["/xdp:xdp"]) {
+    return !data.get("/xdp:xdp") ? data.get("xdp:xdp") : data.values().join("");
-      return data["xdp:xdp"];
-    }
-    return Object.values(data).join("");
   }
 
   static getRichTextAsHtml(rc) {

src/shared/util.js

@@ -1159,6 +1159,14 @@ if (
   };
 }
 
+// TODO: Remove this once `Iterator.prototype.join` is generally available.
+if (typeof Iterator.prototype.join !== "function") {
+  // eslint-disable-next-line no-extend-native
+  Iterator.prototype.join = function (separator) {
+    return [...this].join(separator);
+  };
+}
+
 export {
   _isValidExplicitDest,
   AbortException,

test/unit/xfa_tohtml_spec.js

@@ -82,7 +82,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
       factory.setFonts([]);
 
       expect(await factory.getNumPages()).toEqual(2);
@@ -168,7 +168,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -202,7 +202,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -256,7 +256,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
       factory.setFonts([]);
 
       expect(await factory.getNumPages()).toEqual(1);
@@ -330,7 +330,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -372,7 +372,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -414,7 +414,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -457,7 +457,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
       `;
-      const factory = new XFAFactory({ "xdp:xdp": xml });
+      const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
       expect(await factory.getNumPages()).toEqual(1);
 
@@ -511,7 +511,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
     `;
-    const factory = new XFAFactory({ "xdp:xdp": xml });
+    const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
     expect(await factory.getNumPages()).toEqual(1);
 
@@ -555,7 +555,9 @@ describe("XFAFactory", function () {
     let factory, pages, a;
 
     // A valid, and complete, URL.
-    factory = new XFAFactory({ "xdp:xdp": getXml("https://www.example.com/") });
+    factory = new XFAFactory(
+      new Map([["xdp:xdp", getXml("https://www.example.com/")]])
+    );
     expect(await factory.getNumPages()).toEqual(1);
     pages = await factory.getPages();
     a = searchHtmlNode(pages, "name", "a");
@@ -563,7 +565,9 @@ describe("XFAFactory", function () {
     expect(a.attributes.href).toEqual("https://www.example.com/");
 
     // A valid, but incomplete, URL.
-    factory = new XFAFactory({ "xdp:xdp": getXml("www.example.com/") });
+    factory = new XFAFactory(
+      new Map([["xdp:xdp", getXml("www.example.com/")]])
+    );
     expect(await factory.getNumPages()).toEqual(1);
     pages = await factory.getPages();
     a = searchHtmlNode(pages, "name", "a");
@@ -571,7 +575,9 @@ describe("XFAFactory", function () {
     expect(a.attributes.href).toEqual("http://www.example.com/");
 
     // A valid email-address.
-    factory = new XFAFactory({ "xdp:xdp": getXml("mailto:test@example.com") });
+    factory = new XFAFactory(
+      new Map([["xdp:xdp", getXml("mailto:test@example.com")]])
+    );
     expect(await factory.getNumPages()).toEqual(1);
     pages = await factory.getPages();
     a = searchHtmlNode(pages, "name", "a");
@@ -579,7 +585,7 @@ describe("XFAFactory", function () {
     expect(a.attributes.href).toEqual("mailto:test@example.com");
 
     // Not a valid URL.
-    factory = new XFAFactory({ "xdp:xdp": getXml("qwerty/") });
+    factory = new XFAFactory(new Map([["xdp:xdp", getXml("qwerty/")]]));
     expect(await factory.getNumPages()).toEqual(1);
     pages = await factory.getPages();
     a = searchHtmlNode(pages, "name", "a");
@@ -629,7 +635,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
     `;
-    const factory = new XFAFactory({ "xdp:xdp": xml });
+    const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
     expect(await factory.getNumPages()).toEqual(1);
 
@@ -675,7 +681,7 @@ describe("XFAFactory", function () {
   </xfa:datasets>
 </xdp:xdp>
     `;
-    const factory = new XFAFactory({ "xdp:xdp": xml });
+    const factory = new XFAFactory(new Map([["xdp:xdp", xml]]));
 
     expect(await factory.getNumPages()).toEqual(1);
 

web/pdf_find_controller.js

@@ -28,20 +28,20 @@ const FindState = {
   PENDING: 3,
 };
 
-const CHARACTERS_TO_NORMALIZE = {
+const CHARACTERS_TO_NORMALIZE = new Map([
-  "\u2010": "-", // Hyphen
+  ["\u2010", "-"], // Hyphen
-  "\u2018": "'", // Left single quotation mark
+  ["\u2018", "'"], // Left single quotation mark
-  "\u2019": "'", // Right single quotation mark
+  ["\u2019", "'"], // Right single quotation mark
-  "\u201A": "'", // Single low-9 quotation mark
+  ["\u201A", "'"], // Single low-9 quotation mark
-  "\u201B": "'", // Single high-reversed-9 quotation mark
+  ["\u201B", "'"], // Single high-reversed-9 quotation mark
-  "\u201C": '"', // Left double quotation mark
+  ["\u201C", '"'], // Left double quotation mark
-  "\u201D": '"', // Right double quotation mark
+  ["\u201D", '"'], // Right double quotation mark
-  "\u201E": '"', // Double low-9 quotation mark
+  ["\u201E", '"'], // Double low-9 quotation mark
-  "\u201F": '"', // Double high-reversed-9 quotation mark
+  ["\u201F", '"'], // Double high-reversed-9 quotation mark
-  "\u00BC": "1/4", // Vulgar fraction one quarter
+  ["\u00BC", "1/4"], // Vulgar fraction one quarter
-  "\u00BD": "1/2", // Vulgar fraction one half
+  ["\u00BD", "1/2"], // Vulgar fraction one half
-  "\u00BE": "3/4", // Vulgar fraction three quarters
+  ["\u00BE", "3/4"], // Vulgar fraction three quarters
-};
+]);
 
 // These diacritics aren't considered as combining diacritics
 // when searching in a document:
@@ -121,7 +121,7 @@ function normalize(text, options = {}) {
     normalizationRegex = withSyllablesRegExp;
   } else {
     // Compile the regular expression for text normalization once.
-    const replace = Object.keys(CHARACTERS_TO_NORMALIZE).join("");
+    const replace = CHARACTERS_TO_NORMALIZE.keys().join("");
     const toNormalizeWithNFKC = getNormalizeWithNFKC();
 
     // 3040-309F: Hiragana
@@ -206,7 +206,7 @@ function normalize(text, options = {}) {
       i -= shiftOrigin;
       if (p1) {
         // Maybe fractions or quotations mark...
-        const replacement = CHARACTERS_TO_NORMALIZE[p1];
+        const replacement = CHARACTERS_TO_NORMALIZE.get(p1);
         const jj = replacement.length;
         for (let j = 1; j < jj; j++) {
           positions.push(i - shift + j, shift - j);