Version 10 misc chores and small breaking changes

README.md

@@ -79,8 +79,9 @@ The table below shows the full list of supported languages (and corresponding cl
 | Basic                   | basic                  |         |
 | BNF                     | bnf                    |         |
 | Brainfuck               | brainfuck, bf          |         |
-| C#                      | cs, csharp             |         |
-| C++                     | cpp, c, cc, h, c++, h++, hpp |   |
+| C#                      | csharp, cs             |         |
+| C                       | h                      |         |
+| C++                     | cpp, hpp, cc, hh, c++, h++, cxx, hxx |   |
 | C/AL                    | cal                    |         |
 | Cache Object Script     | cos, cls               |         |
 | CMake                   | cmake, cmake.in        |         |
@@ -139,6 +140,7 @@ The table below shows the full list of supported languages (and corresponding cl
 | Java                    | java, jsp              |         |
 | JavaScript              | javascript, js, jsx    |         |
 | Kotlin                  | kotlin, kt             |         |
+| LaTeX                   | tex                    |         |
 | Leaf                    | leaf                   |         |
 | Lasso                   | lasso, ls, lassoscript |         |
 | Less                    | less                   |         |
@@ -162,7 +164,7 @@ The table below shows the full list of supported languages (and corresponding cl
 | N1QL                    | n1ql                   |         |
 | NSIS                    | nsis                   |         |
 | Nginx                   | nginx, nginxconf       |         |
-| Nimrod                  | nimrod, nim            |         |
+| Nim                     | nimrod                 |         |
 | Nix                     | nix                    |         |
 | OCaml                   | ocaml, ml              |         |
 | Objective C             | objectivec, mm, objc, obj-c |    |
@@ -219,7 +221,6 @@ The table below shows the full list of supported languages (and corresponding cl
 | Tcl                     | tcl, tk                |         |
 | Terraform (HCL)         | terraform, tf, hcl     | [highlightjs-terraform](https://github.com/highlightjs/highlightjs-terraform) |
 | Test Anything Protocol  | tap                    |         |
-| TeX                     | tex                    |         |
 | Thrift                  | thrift                 |         |
 | TP                      | tp                     |         |
 | Twig                    | twig, craftcms         |         |
@@ -301,8 +302,8 @@ onmessage = (event) => {
 
 ## Node.js
 
-You can use highlight.js with node to highlight content before sending it to the browser. 
-Make sure to use the `.value` property to get the formatted html. 
+You can use highlight.js with node to highlight content before sending it to the browser.
+Make sure to use the `.value` property to get the formatted html.
 For more info about the returned object refer to the api docs https://highlightjs.readthedocs.io/en/latest/api.html
 
 

VERSION_10_BREAKING.md

@@ -0,0 +1,30 @@
+## Version 10 Breaking Changes
+
+Incompatibilities:
+- chore(parser): compressed version 9.x language definitions no longer supported (rebuild them minified) [Josh Goebel][]
+
+Renamed Language Files:
+- chore(parser): rename `nimrod.js` to `nim.js` [Josh Goebel][]
+- chore(parser): rename `cs.js` to `csharp.js` [Josh Goebel][]
+- chore(parser): rename `tex.js` to `latex.js` [Josh Goebel][]
+- chore(parser): effectively rename `cpp.js` to `c-like.js` [Josh Goebel][]
+- chore(parser): create new `c.js` (C), depends on `c-like` now [Josh Goebel][]
+- chore(parser): create new `cpp.js` (C), depends on `c-like` now [Josh Goebel][]
+- This will allow us to clean up C/C++ in the future without another breaking change
+  by getting this require change out of the way early.
+  (https://github.com/highlightjs/highlight.js/issues/2146)
+
+Legacy Browser Issues:
+- **We're now using ES2015 features in the codebase.  Internet Explorer 11 is no longer supported.**
+- In general legacy browsers are no longer supported.
+- chore(parser): remove `load` listener in favor of only the newer `DOMContentLoaded` [Josh Goebel][]
+
+Removed styles:
+- chore(styles): darkula.css (use darcula.css instead) [Josh Goebel][]
+
+[Josh Goebel]: https://github.com/yyyc514
+
+---
+
+Also see:
+https://github.com/highlightjs/highlight.js/issues/2273

src/highlight.js

@@ -274,18 +274,6 @@ https://highlightjs.org/
     return [mode];
   }
 
-  function restoreLanguageApi(obj) {
-    if(API_REPLACES && !obj.langApiRestored) {
-      obj.langApiRestored = true;
-      for(var key in API_REPLACES) {
-        if (obj[key]) {
-          obj[API_REPLACES[key]] = obj[key];
-        }
-      }
-      (obj.contains || []).concat(obj.variants || []).forEach(restoreLanguageApi);
-    }
-  }
-
   function compileKeywords(rawKeywords, case_insensitive) {
       var compiled_keywords = {};
 
@@ -321,7 +309,7 @@ https://highlightjs.org/
   }
 
   function commonKeyword(word) {
-    return COMMON_KEYWORDS.indexOf(word.toLowerCase()) != -1;
+    return COMMON_KEYWORDS.includes(word.toLowerCase());
   }
 
   function compileLanguage(language) {
@@ -500,7 +488,7 @@ https://highlightjs.org/
     }
 
     // self is not valid at the top-level
-    if (language.contains && language.contains.indexOf('self') != -1) {
+    if (language.contains && language.contains.includes('self')) {
       if (!SAFE_MODE) {
         throw new Error("ERR: contains `self` is not supported at the top-level of a language.  See documentation.")
       } else {
@@ -777,7 +765,7 @@ https://highlightjs.org/
         top: top
       };
     } catch (err) {
-      if (err.message && err.message.indexOf('Illegal') !== -1) {
+      if (err.message && err.message.includes('Illegal')) {
         return {
           illegal: true,
           relevance: 0,
@@ -935,7 +923,6 @@ https://highlightjs.org/
   */
   function initHighlightingOnLoad() {
     window.addEventListener('DOMContentLoaded', initHighlighting, false);
-    window.addEventListener('load', initHighlighting, false);
   }
 
   var PLAINTEXT_LANGUAGE = { disableAutodetect: true };
@@ -954,7 +941,6 @@ https://highlightjs.org/
       lang = PLAINTEXT_LANGUAGE;
     }
     languages[name] = lang;
-    restoreLanguageApi(lang);
     lang.rawDefinition = language.bind(null,hljs);
 
     if (lang.aliases) {

src/languages/c-like.js

@@ -0,0 +1,236 @@
+/*
+Language: C-like foundation grammar for C/C++ grammars
+Author: Ivan Sagalaev <maniac@softwaremaniacs.org>
+Contributors: Evgeny Stepanischev <imbolk@gmail.com>, Zaven Muradyan <megalivoithos@gmail.com>, Roel Deckers <admin@codingcat.nl>, Sam Wu <samsam2310@gmail.com>, Jordi Petit <jordi.petit@gmail.com>, Pieter Vantorre <pietervantorre@gmail.com>, Google Inc. (David Benjamin) <davidben@google.com>
+Category: common, system
+*/
+
+/* In the future the intention is to split out the C/C++ grammars distinctly
+since they are separate languages.  They will likely share a common foundation
+though, and this file sets the groundwork for that - so that we get the breaking
+change in v10 and don't have to change the requirements again later.
+
+See: https://github.com/highlightjs/highlight.js/issues/2146
+*/
+
+function(hljs) {
+  function optional(s) {
+    return '(?:' + s + ')?';
+  }
+  var DECLTYPE_AUTO_RE = 'decltype\\(auto\\)'
+  var NAMESPACE_RE = '[a-zA-Z_]\\w*::'
+  var TEMPLATE_ARGUMENT_RE = '<.*?>';
+  var FUNCTION_TYPE_RE = '(' +
+    DECLTYPE_AUTO_RE + '|' +
+    optional(NAMESPACE_RE) +'[a-zA-Z_]\\w*' + optional(TEMPLATE_ARGUMENT_RE) +
+  ')';
+  var CPP_PRIMITIVE_TYPES = {
+    className: 'keyword',
+    begin: '\\b[a-z\\d_]*_t\\b'
+  };
+
+  // https://en.cppreference.com/w/cpp/language/escape
+  // \\ \x \xFF \u2837 \u00323747 \374
+  var CHARACTER_ESCAPES = '\\\\(x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4,8}|[0-7]{3}|\\S)'
+  var STRINGS = {
+    className: 'string',
+    variants: [
+      {
+        begin: '(u8?|U|L)?"', end: '"',
+        illegal: '\\n',
+        contains: [hljs.BACKSLASH_ESCAPE]
+      },
+      {
+        begin: '(u8?|U|L)?\'(' + CHARACTER_ESCAPES + "|.)", end: '\'',
+        illegal: '.'
+      },
+      { begin: /(?:u8?|U|L)?R"([^()\\ ]{0,16})\((?:.|\n)*?\)\1"/ }
+    ]
+  };
+
+  var NUMBERS = {
+    className: 'number',
+    variants: [
+      { begin: '\\b(0b[01\']+)' },
+      { begin: '(-?)\\b([\\d\']+(\\.[\\d\']*)?|\\.[\\d\']+)(u|U|l|L|ul|UL|f|F|b|B)' },
+      { begin: '(-?)(\\b0[xX][a-fA-F0-9\']+|(\\b[\\d\']+(\\.[\\d\']*)?|\\.[\\d\']+)([eE][-+]?[\\d\']+)?)' }
+    ],
+    relevance: 0
+  };
+
+  var PREPROCESSOR =       {
+    className: 'meta',
+    begin: /#\s*[a-z]+\b/, end: /$/,
+    keywords: {
+      'meta-keyword':
+        'if else elif endif define undef warning error line ' +
+        'pragma _Pragma ifdef ifndef include'
+    },
+    contains: [
+      {
+        begin: /\\\n/, relevance: 0
+      },
+      hljs.inherit(STRINGS, {className: 'meta-string'}),
+      {
+        className: 'meta-string',
+        begin: /<.*?>/, end: /$/,
+        illegal: '\\n',
+      },
+      hljs.C_LINE_COMMENT_MODE,
+      hljs.C_BLOCK_COMMENT_MODE
+    ]
+  };
+
+  var TITLE_MODE = {
+    className: 'title',
+    begin: optional(NAMESPACE_RE) + hljs.IDENT_RE,
+    relevance: 0
+  };
+
+  var FUNCTION_TITLE = optional(NAMESPACE_RE) + hljs.IDENT_RE + '\\s*\\(';
+
+  var CPP_KEYWORDS = {
+    keyword: 'int float while private char char8_t char16_t char32_t catch import module export virtual operator sizeof ' +
+      'dynamic_cast|10 typedef const_cast|10 const for static_cast|10 union namespace ' +
+      'unsigned long volatile static protected bool template mutable if public friend ' +
+      'do goto auto void enum else break extern using asm case typeid wchar_t' +
+      'short reinterpret_cast|10 default double register explicit signed typename try this ' +
+      'switch continue inline delete alignas alignof constexpr consteval constinit decltype ' +
+      'concept co_await co_return co_yield requires ' +
+      'noexcept static_assert thread_local restrict final override ' +
+      'atomic_bool atomic_char atomic_schar ' +
+      'atomic_uchar atomic_short atomic_ushort atomic_int atomic_uint atomic_long atomic_ulong atomic_llong ' +
+      'atomic_ullong new throw return ' +
+      'and and_eq bitand bitor compl not not_eq or or_eq xor xor_eq',
+    built_in: 'std string wstring cin cout cerr clog stdin stdout stderr stringstream istringstream ostringstream ' +
+      'auto_ptr deque list queue stack vector map set bitset multiset multimap unordered_set ' +
+      'unordered_map unordered_multiset unordered_multimap array shared_ptr abort terminate abs acos ' +
+      'asin atan2 atan calloc ceil cosh cos exit exp fabs floor fmod fprintf fputs free frexp ' +
+      'fscanf future isalnum isalpha iscntrl isdigit isgraph islower isprint ispunct isspace isupper ' +
+      'isxdigit tolower toupper labs ldexp log10 log malloc realloc memchr memcmp memcpy memset modf pow ' +
+      'printf putchar puts scanf sinh sin snprintf sprintf sqrt sscanf strcat strchr strcmp ' +
+      'strcpy strcspn strlen strncat strncmp strncpy strpbrk strrchr strspn strstr tanh tan ' +
+      'vfprintf vprintf vsprintf endl initializer_list unique_ptr _Bool complex _Complex imaginary _Imaginary',
+    literal: 'true false nullptr NULL'
+  };
+
+  var EXPRESSION_CONTAINS = [
+    CPP_PRIMITIVE_TYPES,
+    hljs.C_LINE_COMMENT_MODE,
+    hljs.C_BLOCK_COMMENT_MODE,
+    NUMBERS,
+    STRINGS
+  ];
+
+  var EXPRESSION_CONTEXT = {
+    // This mode covers expression context where we can't expect a function
+    // definition and shouldn't highlight anything that looks like one:
+    // `return some()`, `else if()`, `(x*sum(1, 2))`
+    variants: [
+      {begin: /=/, end: /;/},
+      {begin: /\(/, end: /\)/},
+      {beginKeywords: 'new throw return else', end: /;/}
+    ],
+    keywords: CPP_KEYWORDS,
+    contains: EXPRESSION_CONTAINS.concat([
+      {
+        begin: /\(/, end: /\)/,
+        keywords: CPP_KEYWORDS,
+        contains: EXPRESSION_CONTAINS.concat(['self']),
+        relevance: 0
+      }
+    ]),
+    relevance: 0
+  };
+
+  var FUNCTION_DECLARATION = {
+    className: 'function',
+    begin: '(' + FUNCTION_TYPE_RE + '[\\*&\\s]+)+' + FUNCTION_TITLE,
+    returnBegin: true, end: /[{;=]/,
+    excludeEnd: true,
+    keywords: CPP_KEYWORDS,
+    illegal: /[^\w\s\*&:<>]/,
+    contains: [
+
+      { // to prevent it from being confused as the function title
+        begin: DECLTYPE_AUTO_RE,
+        keywords: CPP_KEYWORDS,
+        relevance: 0,
+      },
+      {
+        begin: FUNCTION_TITLE, returnBegin: true,
+        contains: [TITLE_MODE],
+        relevance: 0
+      },
+      {
+        className: 'params',
+        begin: /\(/, end: /\)/,
+        keywords: CPP_KEYWORDS,
+        relevance: 0,
+        contains: [
+          hljs.C_LINE_COMMENT_MODE,
+          hljs.C_BLOCK_COMMENT_MODE,
+          STRINGS,
+          NUMBERS,
+          CPP_PRIMITIVE_TYPES,
+          // Count matching parentheses.
+          {
+            begin: /\(/, end: /\)/,
+            keywords: CPP_KEYWORDS,
+            relevance: 0,
+            contains: [
+              'self',
+              hljs.C_LINE_COMMENT_MODE,
+              hljs.C_BLOCK_COMMENT_MODE,
+              STRINGS,
+              NUMBERS,
+              CPP_PRIMITIVE_TYPES
+            ]
+          }
+        ]
+      },
+      CPP_PRIMITIVE_TYPES,
+      hljs.C_LINE_COMMENT_MODE,
+      hljs.C_BLOCK_COMMENT_MODE,
+      PREPROCESSOR
+    ]
+  };
+
+  return {
+    aliases: ['c', 'cc', 'h', 'c++', 'h++', 'hpp', 'hh', 'hxx', 'cxx'],
+    keywords: CPP_KEYWORDS,
+    // the base c-like language will NEVER be auto-detected, rather the
+    // derivitives: c, c++, arduino turn auto-detect back on for themselves
+    disableAutodetect: true,
+    illegal: '</',
+    contains: [].concat(
+      EXPRESSION_CONTEXT,
+      FUNCTION_DECLARATION,
+      EXPRESSION_CONTAINS,
+      [
+      PREPROCESSOR,
+      {
+        begin: '\\b(deque|list|queue|stack|vector|map|set|bitset|multiset|multimap|unordered_map|unordered_set|unordered_multiset|unordered_multimap|array)\\s*<', end: '>',
+        keywords: CPP_KEYWORDS,
+        contains: ['self', CPP_PRIMITIVE_TYPES]
+      },
+      {
+        begin: hljs.IDENT_RE + '::',
+        keywords: CPP_KEYWORDS
+      },
+      {
+        className: 'class',
+        beginKeywords: 'class struct', end: /[{;:]/,
+        contains: [
+          {begin: /</, end: />/, contains: ['self']}, // skip generic stuff
+          hljs.TITLE_MODE
+        ]
+      }
+    ]),
+    exports: {
+      preprocessor: PREPROCESSOR,
+      strings: STRINGS,
+      keywords: CPP_KEYWORDS
+    }
+  };
+}

src/languages/c.js

@@ -0,0 +1,21 @@
+/*
+Language: C
+Category: common, system
+Website: https://en.wikipedia.org/wiki/C_(programming_language)
+Requires: c-like.js
+*/
+
+function(hljs) {
+
+  var lang = hljs.getLanguage('c-like').rawDefinition();
+  // Until C is actually different than C++ there is no reason to auto-detect C
+  // as it's own language since it would just fail auto-detect testing or
+  // simply match with C++.
+  //
+  // See further comments in c-like.js.
+
+  // lang.disableAutodetect = false;
+  lang.aliases = ['c', 'h'];
+  return lang;
+
+}