Build a fallback ToUnicode map for simple fonts (issue 8229)

In some fonts, the included `ToUnicode` data is incomplete causing text-selection to not work properly. For simple fonts that contain encoding data, we can manually build a `ToUnicode` map to attempt to improve things.

Please note that since we're currently using the `ToUnicode` data during glyph mapping, in an attempt to avoid rendering regressions, I purposely didn't want to amend to original `ToUnicode` data for this text-selection edge-case.
Instead, I opted for the current solution, which will (hopefully) give slightly better text-extraction results in PDF file with incomplete `ToUnicode` data.

According to the PDF specification, see [section 9.10.2](http://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/PDF32000_2008.pdf#G8.1873172):

> A conforming reader can use these methods, in the priority given, to map a character code to a Unicode value.
> ...

Reading that paragraph literally, it doesn't seem too unreasonable to use *different* methods for different charcodes.

Fixes 8229.

src/core/evaluator.js

@@ -2021,6 +2021,14 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
 
       // Section 9.10.2 Mapping Character Codes to Unicode Values
       if (properties.hasIncludedToUnicodeMap) {
+        // Some fonts contain incomplete ToUnicode data, causing issues with
+        // text-extraction. For simple fonts, containing encoding information,
+        // use a fallback ToUnicode map to improve this (fixes issue8229.pdf).
+        if (!properties.composite && properties.hasEncoding) {
+          properties.fallbackToUnicode =
+            this._buildSimpleFontToUnicode(properties);
+        }
+
         return Promise.resolve(properties.toUnicode);
       }
 

src/core/fonts.js

@@ -211,9 +211,9 @@ var Glyph = (function GlyphClosure() {
 })();
 
 var ToUnicodeMap = (function ToUnicodeMapClosure() {
-  function ToUnicodeMap(cmap) {
+  function ToUnicodeMap(cmap = []) {
     // The elements of this._map can be integers or strings, depending on how
-    // |cmap| was created.
+    // `cmap` was created.
     this._map = cmap;
   }
 
@@ -516,6 +516,7 @@ var Font = (function FontClosure() {
     this.defaultEncoding = properties.defaultEncoding;
 
     this.toUnicode = properties.toUnicode;
+    this.fallbackToUnicode = properties.fallbackToUnicode || new ToUnicodeMap();
 
     this.toFontChar = [];
 
@@ -2766,7 +2767,8 @@ var Font = (function FontClosure() {
       width = isNum(width) ? width : this.defaultWidth;
       var vmetric = this.vmetrics && this.vmetrics[widthCode];
 
-      var unicode = this.toUnicode.get(charcode) || charcode;
+      let unicode = this.toUnicode.get(charcode) ||
+        this.fallbackToUnicode.get(charcode) || charcode;
       if (typeof unicode === 'number') {
         unicode = String.fromCharCode(unicode);
       }

test/pdfs/.gitignore

@@ -53,6 +53,7 @@
 !issue8061.pdf
 !issue8088.pdf
 !issue8125.pdf
+!issue8229.pdf
 !issue8372.pdf
 !issue8424.pdf
 !issue8480.pdf

test/test_manifest.json

@@ -1438,6 +1438,13 @@
        "link": false,
        "type": "text"
     },
+    {  "id": "issue8229",
+       "file": "pdfs/issue8229.pdf",
+       "md5": "a729f663782e87ebc1efad0755ebf6a5",
+       "rounds": 1,
+       "link": false,
+       "type": "text"
+    },
     {  "id": "ShowText-ShadingPattern",
        "file": "pdfs/ShowText-ShadingPattern.pdf",
        "md5": "fe683725db037ffe19d390969610a652",