Add support for JSON5 as extension of json.js. (#4259)

Author: kshetline

CHANGES.md

@@ -16,6 +16,7 @@ Core Grammars:
 - fix(ex) adds support for `?'` char literal and missing `defguardp` keyword [Kevin Bloch][]
 - fix(diff) fix unified diff hunk header regex to allow unpaired numbers [Chris Wilson][]
 - enh(php) support single line and hash comments in attributes, constructor and functions [Antoine Musso][]
+- enh(json) add json5 support [Kerry Shetline][]
 
 Documentation:
 
@@ -34,7 +35,7 @@ CONTRIBUTORS
 [Adam Lui]: https://github.com/adamlui
 [Sebastiaan Speck]: https://github.com/sebastiaanspeck
 [Filip Hoffmann]: https://github.com/folospior
-
+[Kerry Shetline]: https://github.com/kshetline
 
 ## Version 11.11.1
 

SUPPORTED_LANGUAGES.md

@@ -112,6 +112,8 @@ The table below shows the full list of languages (and corresponding classes/alia
 | Inform7                 | inform7, i7            |         |
 | Ini, TOML               | ini, toml              |         |
 | Iptables                | iptables               | [highlightjs-iptables](https://github.com/highlightjs/highlightjs-iptables) |
+| JSON                    | json, jsonc, json5     |         |
+| JSONata                 | jsonata                | [highlightjs-jsonata](https://github.com/DevDimov/highlightjs-jsonata) |
 | IRPF90                  | irpf90                 |         |
 | Java                    | java, jsp              |         |
 | JavaScript              | javascript, js, jsx    |         |

src/languages/javascript.js

@@ -457,7 +457,7 @@ export default function(hljs) {
     keywords: KEYWORDS,
     // this will be extended by TypeScript
     exports: { PARAMS_CONTAINS, CLASS_REFERENCE },
-    illegal: /#(?![$_A-z])/,
+    illegal: /#(?![$_A-Za-z])/,
     contains: [
       hljs.SHEBANG({
         label: "shebang",

src/languages/json.js

@@ -1,15 +1,16 @@
 /*
 Language: JSON
 Description: JSON (JavaScript Object Notation) is a lightweight data-interchange format.
-Author: Ivan Sagalaev <[email protected]>
-Website: http://www.json.org
+Websites: http://www.json.org, https://www.json5.org
 Category: common, protocols, web
 */
 
+import { EXTENDED_NUMBER_MODE } from "./lib/ecmascript";
+
 export default function(hljs) {
   const ATTRIBUTE = {
     className: 'attr',
-    begin: /"(\\.|[^\\"\r\n])*"(?=\s*:)/,
+    begin: /(("(\\.|[^\\"\r\n])*")|('(\\.|[^\\'\r\n])*'))(?=\s*:)/,
     relevance: 1.01
   };
   const PUNCTUATION = {
@@ -34,16 +35,17 @@ export default function(hljs) {
 
   return {
     name: 'JSON',
-    aliases: ['jsonc'],
+    aliases: ['jsonc', 'json5'],
     keywords:{
       literal: LITERALS,
     },
     contains: [
       ATTRIBUTE,
       PUNCTUATION,
+      hljs.APOS_STRING_MODE,
       hljs.QUOTE_STRING_MODE,
       LITERALS_MODE,
-      hljs.C_NUMBER_MODE,
+      EXTENDED_NUMBER_MODE,
       hljs.C_LINE_COMMENT_MODE,
       hljs.C_BLOCK_COMMENT_MODE
     ],

src/languages/lib/ecmascript.js

@@ -1,4 +1,12 @@
 export const IDENT_RE = '[A-Za-z$_][0-9A-Za-z$_]*';
+export const EXTENDED_NUMBER_RE = '([-+]?)(\\b0[xX][a-fA-F0-9]+|(\\b\\d+(\\.\\d*)?|\\.\\d+)([eE][-+]?\\d+)?)|NaN|[-+]?Infinity'; // 0x..., 0..., decimal, float
+
+export const EXTENDED_NUMBER_MODE = {
+  scope: 'number',
+  match: EXTENDED_NUMBER_RE,
+  relevance: 0
+};
+
 const KEYWORDS = [
   "as", // for exports
   "in",

test/detect/json5/default.txt

@@ -0,0 +1,16 @@
+[
+  {
+    "title": "apples",
+    "count": [12000, 20000],
+    "description": {"text": "...", "sensitive": false}
+  },
+  { // Like JSON, but can also include comments and unquoted identifiers.
+    title: "oranges",
+     // Hexadecimal allowed, + before numbers, leading/trailing decimal point, NaN, Infinity
+    'count': [17500, null, 0x1F2B, +5, -10, .6, 6., NaN, Infinity, +Infinity, -Infinity],
+    description: {'text': '...', 'sensitive': true} /* Single-quoted strings allowed */,
+    multi_line: "Strings can\
+escape\
+new lines"
+  }, // Trailing commas allowed
+]

test/markup/json5/default.expect.txt

@@ -0,0 +1,16 @@
+<span class="hljs-punctuation">[</span>
+  <span class="hljs-punctuation">{</span>
+    <span class="hljs-attr">&quot;title&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;apples&quot;</span><span class="hljs-punctuation">,</span>
+    <span class="hljs-attr">&quot;count&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-number">12000</span><span class="hljs-punctuation">,</span> <span class="hljs-number">20000</span><span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
+    <span class="hljs-attr">&quot;description&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span><span class="hljs-attr">&quot;text&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;...&quot;</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">&quot;sensitive&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-literal"><span class="hljs-keyword">false</span></span><span class="hljs-punctuation">}</span>
+  <span class="hljs-punctuation">}</span><span class="hljs-punctuation">,</span>
+  <span class="hljs-punctuation">{</span> <span class="hljs-comment">// Like JSON, but can also include comments and unquoted identifiers.</span>
+    title<span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;oranges&quot;</span><span class="hljs-punctuation">,</span>
+     <span class="hljs-comment">// Hexadecimal allowed, + before numbers, leading/trailing decimal point, NaN, Infinity</span>
+    <span class="hljs-attr">&#x27;count&#x27;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-number">17500</span><span class="hljs-punctuation">,</span> <span class="hljs-literal"><span class="hljs-keyword">null</span></span><span class="hljs-punctuation">,</span> <span class="hljs-number">0x1F2B</span><span class="hljs-punctuation">,</span> <span class="hljs-number">+5</span><span class="hljs-punctuation">,</span> <span class="hljs-number">-10</span><span class="hljs-punctuation">,</span> <span class="hljs-number">.6</span><span class="hljs-punctuation">,</span> <span class="hljs-number">6.</span><span class="hljs-punctuation">,</span> <span class="hljs-number">NaN</span><span class="hljs-punctuation">,</span> <span class="hljs-number">Infinity</span><span class="hljs-punctuation">,</span> <span class="hljs-number">+Infinity</span><span class="hljs-punctuation">,</span> <span class="hljs-number">-Infinity</span><span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
+    description<span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span><span class="hljs-attr">&#x27;text&#x27;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&#x27;...&#x27;</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">&#x27;sensitive&#x27;</span><span class="hljs-punctuation">:</span> <span class="hljs-literal"><span class="hljs-keyword">true</span></span><span class="hljs-punctuation">}</span> <span class="hljs-comment">/* Single-quoted strings allowed */</span><span class="hljs-punctuation">,</span>
+    multi_line<span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;Strings can\
+escape\
+new lines&quot;</span>
+  <span class="hljs-punctuation">}</span><span class="hljs-punctuation">,</span> <span class="hljs-comment">// Trailing commas allowed</span>
+<span class="hljs-punctuation">]</span>

test/markup/json5/default.txt

@@ -0,0 +1,16 @@
+[
+  {
+    "title": "apples",
+    "count": [12000, 20000],
+    "description": {"text": "...", "sensitive": false}
+  },
+  { // Like JSON, but can also include comments and unquoted identifiers.
+    title: "oranges",
+     // Hexadecimal allowed, + before numbers, leading/trailing decimal point, NaN, Infinity
+    'count': [17500, null, 0x1F2B, +5, -10, .6, 6., NaN, Infinity, +Infinity, -Infinity],
+    description: {'text': '...', 'sensitive': true} /* Single-quoted strings allowed */,
+    multi_line: "Strings can\
+escape\
+new lines"
+  }, // Trailing commas allowed
+]