[api-minor] Add a parameter to PDFPageProxy_getTextContent that enables replacing of all whitespace with standard spaces in the textLayer (issue 6612)

This patch goes a bit further than issue 6612 requires, and replaces all kinds of whitespace with standard spaces.

When testing this locally, it actually seemed to slightly improve two existing test-cases (`tracemonkey-text` and `taro-text`).

Fixes 6612.

test/driver.js

@@ -334,10 +334,12 @@ var Driver = (function DriverClosure() {
               textLayerContext.clearRect(0, 0,
                 textLayerCanvas.width, textLayerCanvas.height);
               // The text builder will draw its content on the test canvas
-              initPromise = page.getTextContent().then(function(textContent) {
-                return rasterizeTextLayer(textLayerContext, viewport,
-                                          textContent);
-              });
+              initPromise =
+                page.getTextContent({ normalizeWhitespace: true }).then(
+                  function(textContent) {
+                    return rasterizeTextLayer(textLayerContext, viewport,
+                                              textContent);
+                });
             } else {
               textLayerCanvas = null;
               initPromise = Promise.resolve();

test/pdfs/.gitignore

@@ -49,6 +49,7 @@
 !issue5280.pdf
 !issue5677.pdf
 !issue5954.pdf
+!issue6612.pdf
 !alphatrans.pdf
 !devicen.pdf
 !cmykjpeg.pdf

test/test_manifest.json

@@ -1271,6 +1271,13 @@
        "link": false,
        "type": "eq"
     },
+    {  "id": "issue6612-text",
+       "file": "pdfs/issue6612.pdf",
+       "md5": "657f33236496916597cd70ef1222509a",
+       "rounds": 1,
+       "link": false,
+       "type": "text"
+    },
     {  "id": "zerowidthline",
       "file": "pdfs/zerowidthline.pdf",
       "md5": "295d26e61a85635433f8e4b768953f60",

test/unit/api_spec.js

@@ -482,11 +482,21 @@ describe('api', function() {
       });
     });
     it('gets text content', function () {
-      var promise = page.getTextContent();
-      waitsForPromiseResolved(promise, function (data) {
-        expect(!!data.items).toEqual(true);
-        expect(data.items.length).toEqual(7);
-        expect(!!data.styles).toEqual(true);
+      var defaultPromise = page.getTextContent();
+      var normalizeWhitespacePromise = page.getTextContent({
+        normalizeWhitespace: true });
+
+      var promises = [
+        defaultPromise,
+        normalizeWhitespacePromise
+      ];
+      waitsForPromiseResolved(Promise.all(promises), function (data) {
+        expect(!!data[0].items).toEqual(true);
+        expect(data[0].items.length).toEqual(7);
+        expect(!!data[0].styles).toEqual(true);
+
+        // A simple check that ensures the two `textContent` object match.
+        expect(JSON.stringify(data[0])).toEqual(JSON.stringify(data[1]));
       });
     });
     it('gets operator list', function() {