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

test/katex-spec.js

@@ -2864,7 +2864,8 @@ describe("Unicode accents", function() {
             "\\tilde n" +
             "\\grave o\\acute o\\hat o\\tilde o\\ddot o" +
             "\\grave u\\acute u\\hat u\\ddot u" +
-            "\\acute y\\ddot y");
+            "\\acute y\\ddot y",
+            {unicodeTextInMathMode: true});
     });
 
     it("should parse Latin-1 letters in text mode", function() {
@@ -2894,18 +2895,21 @@ describe("Unicode accents", function() {
     });
 
     it("should parse combining characters", function() {
-        expect("A\u0301C\u0301").toParseLike("Á\\acute C");
+        expect("A\u0301C\u0301").toParseLike("Á\\acute C",
+            {unicodeTextInMathMode: true});
         expect("\\text{A\u0301C\u0301}").toParseLike("\\text{Á\\'C}");
     });
 
     it("should parse multi-accented characters", function() {
-        expect("ấā́ắ\\text{ấā́ắ}").toParse();
+        expect("ấā́ắ\\text{ấā́ắ}").toParse({unicodeTextInMathMode: true});
         // Doesn't parse quite the same as
         // "\\text{\\'{\\^a}\\'{\\=a}\\'{\\u a}}" because of the ordgroups.
     });
 
     it("should parse accented i's and j's", function() {
-        expect("íȷ́").toParseLike("\\acute ı\\acute ȷ");
+        expect("íȷ́").toParseLike("\\acute ı\\acute ȷ",
+            {unicodeTextInMathMode: true});
+        expect("ấā́ắ\\text{ấā́ắ}").toParse({unicodeTextInMathMode: true});
     });
 });
 
@@ -3009,6 +3013,29 @@ describe("Symbols", function() {
     });
 });
 
+describe("unicodeTextInMathMode setting", function() {
+    it("should allow unicode text when true", () => {
+        expect("é").toParse({unicodeTextInMathMode: true});
+        expect("試").toParse({unicodeTextInMathMode: true});
+    });
+
+    it("should forbid unicode text when false", () => {
+        expect("é").toNotParse({unicodeTextInMathMode: false});
+        expect("試").toNotParse({unicodeTextInMathMode: false});
+    });
+
+    it("should forbid unicode text when default", () => {
+        expect("é").toNotParse();
+        expect("試").toNotParse();
+    });
+
+    it("should always allow unicode text in text mode", () => {
+        expect("\\text{é試}").toParse({unicodeTextInMathMode: false});
+        expect("\\text{é試}").toParse({unicodeTextInMathMode: true});
+        expect("\\text{é試}").toParse();
+    });
+});
+
 describe("Internal __* interface", function() {
     const latex = "\\sum_{k = 0}^{\\infty} x^k";
     const rendered = katex.renderToString(latex);

test/mathml-spec.js

@@ -95,6 +95,7 @@ describe("A MathML builder", function() {
     });
 
     it('accents turn into <mover accent="true"> in MathML', function() {
-        expect(getMathML("über fiancée")).toMatchSnapshot();
+        expect(getMathML("über fiancée", {unicodeTextInMathMode: true}))
+            .toMatchSnapshot();
     });
 });

test/unicode-spec.js

@@ -72,9 +72,16 @@ describe("unicode", function() {
             'ÆÇÐØÞßæçðøþ}').toParse();
     });
 
+    it("should not parse Latin-1 outside \\text{} without setting", function() {
+        const chars = 'ÀÁÂÃÄÅÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝàáâãäåèéêëìíîïñòóôõöùúûüýÿÇÐÞçþ';
+        for (const ch of chars) {
+            expect(ch).toNotParse();
+        }
+    });
+
     it("should parse Latin-1 outside \\text{}", function() {
         expect('ÀÁÂÃÄÅÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝàáâãäåèéêëìíîïñòóôõöùúûüýÿ' +
-            'ÇÐÞçðþ').toParse();
+            'ÇÐÞçðþ').toParse({unicodeTextInMathMode: true});
     });
 
     it("should parse all lower case Greek letters", function() {