Try to improve text-selection for Type3 fonts that utilize a non-default /FontMatrix (bug 1513120)

For Type3 fonts text-selection is often not that great, and there's a couple of heuristics used to try and improve things. This patch simple extends those heuristics a bit, and fixes a pre-existing "naive" array comparison, but this all feels a bit brittle to say the least.

The existing Type3 test-coverage isn't that great in general, and in particular Type3 `text` tests are few and far between, hence why this patch adds *two* different new `text` tests.

src/core/evaluator.js

@@ -15,8 +15,8 @@
 
 import {
   AbortException, assert, CMapCompressionType, createPromiseCapability,
-  FONT_IDENTITY_MATRIX, FormatError, IDENTITY_MATRIX, info, isNum, isString,
-  NativeImageDecoding, OPS, stringToPDFString, TextRenderingMode,
+  FONT_IDENTITY_MATRIX, FormatError, IDENTITY_MATRIX, info, isArrayEqual, isNum,
+  isString, NativeImageDecoding, OPS, stringToPDFString, TextRenderingMode,
   UNSUPPORTED_FEATURES, Util, warn
 } from '../shared/util';
 import { CMapFactory, IdentityCMap } from './cmap';
@@ -1264,13 +1264,11 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
                    0, textState.fontSize,
                    0, textState.textRise];
 
-        if (font.isType3Font &&
-            textState.fontMatrix !== FONT_IDENTITY_MATRIX &&
-            textState.fontSize === 1) {
-          var glyphHeight = font.bbox[3] - font.bbox[1];
+        if (font.isType3Font && textState.fontSize <= 1 &&
+            !isArrayEqual(textState.fontMatrix, FONT_IDENTITY_MATRIX)) {
+          const glyphHeight = font.bbox[3] - font.bbox[1];
           if (glyphHeight > 0) {
-            glyphHeight = glyphHeight * textState.fontMatrix[3];
-            tsm[3] *= glyphHeight;
+            tsm[3] *= (glyphHeight * textState.fontMatrix[3]);
           }
         }
 

src/shared/util.js

@@ -824,6 +824,15 @@ function isArrayBuffer(v) {
   return typeof v === 'object' && v !== null && v.byteLength !== undefined;
 }
 
+function isArrayEqual(arr1, arr2) {
+  if (arr1.length !== arr2.length) {
+    return false;
+  }
+  return arr1.every(function(element, index) {
+    return element === arr2[index];
+  });
+}
+
 // Checks if ch is one of the following characters: SPACE, TAB, CR or LF.
 function isSpace(ch) {
   return (ch === 0x20 || ch === 0x09 || ch === 0x0D || ch === 0x0A);
@@ -927,6 +936,7 @@ export {
   getVerbosityLevel,
   info,
   isArrayBuffer,
+  isArrayEqual,
   isBool,
   isEmptyObj,
   isNum,

test/pdfs/.gitignore

@@ -93,6 +93,7 @@
 !bug1146106.pdf
 !bug1245391_reduced.pdf
 !bug1252420.pdf
+!bug1513120_reduced.pdf
 !issue9949.pdf
 !bug1308536.pdf
 !bug1337429.pdf

test/test_manifest.json

@@ -1016,6 +1016,20 @@
        "link": false,
        "type": "eq"
     },
+    {  "id": "bug1245391-text",
+       "file": "pdfs/bug1245391_reduced.pdf",
+       "md5": "6c946045ee0f2f663f269717c0f1614a",
+       "rounds": 1,
+       "link": false,
+       "type": "text"
+    },
+    {  "id": "bug1513120-text",
+       "file": "pdfs/bug1513120_reduced.pdf",
+       "md5": "e88ad8b5bb385296f475ca51ce0d216d",
+       "rounds": 1,
+       "link": false,
+       "type": "text"
+    },
     {  "id": "bug1250079",
        "file": "pdfs/bug1250079.pdf",
        "md5": "a1dd21a70ae7097d96273e85a80b26ef",