unicodeTextInMathMode setting (#1117)

* unicodeTextInMathMode setting

* When `unicodeTextInMathMode` is `true`, accented letters from
  `unicodeSymbols.js`, and CJK and other supported languages,
  get added support in math mode (as requested in #895).
* When `unicodeTextInMathMode` is `false, all of these stop working in
  math mode, and are only supported in text mode (matching XeTeX behavior).
  Note that this is a backwards incompatibility with some 0.9.0 alpha/betas.

* Fix handling of Unicode characters ð, Å, å

* Fix double handling of ð (math maps to \eth, not special Unicode character)
* Remove Åå special math handling, thanks to #1125

* Forbid extraLatin when unicodeTextInMathMode is false

src/Parser.js

@@ -4,7 +4,7 @@
 import functions from "./functions";
 import environments from "./environments";
 import MacroExpander from "./MacroExpander";
-import symbols from "./symbols";
+import symbols, { extraLatin } from "./symbols";
 import { validUnit } from "./units";
 import { supportedCodepoint } from "./unicodeScripts";
 import unicodeAccents from "./unicodeAccents";
@@ -968,9 +968,12 @@ export default class Parser {
             return newDollar(nucleus);
         }
         // At this point, we should have a symbol, possibly with accents.
-        // First expand any accented base symbol according to unicodeSymbols.
+        // First expand any accented base symbol according to unicodeSymbols,
+        // unless we're in math mode and unicodeTextInMathMode is false
+        // (XeTeX-compatible mode).
         if (unicodeSymbols.hasOwnProperty(text[0]) &&
-            !symbols[this.mode][text[0]]) {
+            !symbols[this.mode][text[0]] &&
+            (this.settings.unicodeTextInMathMode || this.mode === "text")) {
             text = unicodeSymbols[text[0]] + text.substr(1);
         }
         // Strip off any combining characters
@@ -986,10 +989,15 @@ export default class Parser {
         // Recognize base symbol
         let symbol = null;
         if (symbols[this.mode][text]) {
+            if (this.mode === 'math' && extraLatin.indexOf(text) >= 0 &&
+                !this.settings.unicodeTextInMathMode) {
+                throw new ParseError(`Unicode text character ${text} used in ` +
+                    `math mode without unicodeTextInMathMode setting`, nucleus);
+            }
             symbol = new ParseNode(symbols[this.mode][text].group,
                             text, this.mode, nucleus);
-        } else if (this.mode === "text" &&
-                   supportedCodepoint(text.charCodeAt(0))) {
+        } else if (supportedCodepoint(text.charCodeAt(0)) &&
+            (this.mode === "text" || this.settings.unicodeTextInMathMode)) {
             symbol = new ParseNode("textord", text, this.mode, nucleus);
         } else {
             return null;  // EOF, ^, _, {, }, etc.

src/Settings.js

@@ -14,6 +14,7 @@ export type SettingsOptions = {
     errorColor?: string;
     macros?: MacroMap;
     colorIsTextColor?: boolean;
+    unicodeTextInMathMode?: boolean;
     maxSize?: number;
 };
 
@@ -33,6 +34,7 @@ class Settings {
     errorColor: string;
     macros: MacroMap;
     colorIsTextColor: boolean;
+    unicodeTextInMathMode: boolean;
     maxSize: number;
 
     constructor(options: SettingsOptions) {
@@ -43,6 +45,8 @@ class Settings {
         this.errorColor = utils.deflt(options.errorColor, "#cc0000");
         this.macros = options.macros || {};
         this.colorIsTextColor = utils.deflt(options.colorIsTextColor, false);
+        this.unicodeTextInMathMode =
+            utils.deflt(options.unicodeTextInMathMode, false);
         this.maxSize = Math.max(0, utils.deflt(options.maxSize, Infinity));
     }
 }

src/symbols.js

@@ -739,7 +739,7 @@ for (let i = 0; i < letters.length; i++) {
 // but they are not actually in the font, nor are they supported by the
 // Unicode accent mechanism, so they fall back to Times font and look ugly.
 // TODO(edemaine): Fix this.
-const extraLatin = "ÇÐÞçþ";
+export const extraLatin = "ÇÐÞçþ";
 for (let i = 0; i < extraLatin.length; i++) {
     const ch = extraLatin.charAt(i);
     defineSymbol(math, main, mathord, ch, ch);