fix(ruby) symbols, string interpolation, class names with underscores

CHANGES.md

@@ -1,3 +1,10 @@
+## Version 11.11.2
+
+Core Grammars:
+
+- fix(ruby) symbols, string interpolation, class names with underscores
+
+
 ## Version 11.11.1
 
 - Fixes regression with Rust grammar.

src/languages/ruby.js

@@ -11,13 +11,7 @@ export default function(hljs) {
   const regex = hljs.regex;
   const RUBY_METHOD_RE = '([a-zA-Z_]\\w*[!?=]?|[-+~]@|<<|>>|=~|===?|<=>|[<>]=?|\\*\\*|[-/+%^&*~`|]|\\[\\]=?)';
   // TODO: move concepts like CAMEL_CASE into `modes.js`
-  const CLASS_NAME_RE = regex.either(
-    /\b([A-Z]+[a-z0-9]+)+/,
-    // ends in caps
-    /\b([A-Z]+[a-z0-9]+)+[A-Z]+/,
-  )
-  ;
-  const CLASS_NAME_WITH_NAMESPACE_RE = regex.concat(CLASS_NAME_RE, /(::\w+)*/)
+  const CLASS_NAME_RE = /\b([A-Z]+[a-z0-9_]*)+[A-Z]*/;
   // very popular ruby built-ins that one might even assume
   // are actual keywords (despite that not being the case)
   const PSEUDO_KWS = [
@@ -120,19 +114,15 @@ export default function(hljs) {
     className: 'subst',
     begin: /#\{/,
     end: /\}/,
-    keywords: RUBY_KEYWORDS
+    keywords: RUBY_KEYWORDS,
   };
-  const STRING = {
+  const STRING_INTERPOLABLE = {
     className: 'string',
     contains: [
       hljs.BACKSLASH_ESCAPE,
       SUBST
     ],
     variants: [
-      {
-        begin: /'/,
-        end: /'/
-      },
       {
         begin: /"/,
         end: /"/
@@ -142,45 +132,37 @@ export default function(hljs) {
         end: /`/
       },
       {
-        begin: /%[qQwWx]?\(/,
-        end: /\)/
+        begin: /%[QWx]?\(/,
+        end: /\)/,
       },
       {
-        begin: /%[qQwWx]?\[/,
-        end: /\]/
+        begin: /%[QWx]?\[/,
+        end: /\]/,
       },
       {
-        begin: /%[qQwWx]?\{/,
-        end: /\}/
+        begin: /%[QWx]?\{/,
+        end: /\}/,
       },
       {
-        begin: /%[qQwWx]?</,
-        end: />/
+        begin: /%[QWx]?</,
+        end: />/,
       },
       {
-        begin: /%[qQwWx]?\//,
-        end: /\//
+        begin: /%[QWx]?\//,
+        end: /\//,
       },
       {
-        begin: /%[qQwWx]?%/,
-        end: /%/
+        begin: /%[QWx]?%/,
+        end: /%/,
       },
       {
-        begin: /%[qQwWx]?-/,
-        end: /-/
+        begin: /%[QWx]?-/,
+        end: /-/,
       },
       {
-        begin: /%[qQwWx]?\|/,
-        end: /\|/
+        begin: /%[QWx]?\|/,
+        end: /\|/,
       },
-      // in the following expressions, \B in the beginning suppresses recognition of ?-sequences
-      // where ? is the last character of a preceding identifier, as in: `func?4`
-      { begin: /\B\?(\\\d{1,3})/ },
-      { begin: /\B\?(\\x[A-Fa-f0-9]{1,2})/ },
-      { begin: /\B\?(\\u\{?[A-Fa-f0-9]{1,6}\}?)/ },
-      { begin: /\B\?(\\M-\\C-|\\M-\\c|\\c\\M-|\\M-|\\C-\\M-)[\x20-\x7e]/ },
-      { begin: /\B\?\\(c|C-)[\x20-\x7e]/ },
-      { begin: /\B\?\\?\S/ },
       // heredocs
       {
         // this guard makes sure that we have an entire heredoc and not a false
@@ -202,6 +184,55 @@ export default function(hljs) {
       }
     ]
   };
+  const STRING_NONINTERPOLABLE = {
+    className: 'string',
+    variants: [
+      {
+        begin: /'/,
+        end: /'/
+      },
+      {
+        begin: /%[qw]?\(/,
+        end: /\)/,
+      },
+      {
+        begin: /%[qw]?\[/,
+        end: /\]/,
+      },
+      {
+        begin: /%[qw]?\{/,
+        end: /\}/,
+      },
+      {
+        begin: /%[qw]?</,
+        end: />/,
+      },
+      {
+        begin: /%[qw]?\//,
+        end: /\//,
+      },
+      {
+        begin: /%[qw]?%/,
+        end: /%/,
+      },
+      {
+        begin: /%[qw]?-/,
+        end: /-/,
+      },
+      {
+        begin: /%[qw]?\|/,
+        end: /\|/,
+      },
+      // in the following expressions, \B in the beginning suppresses recognition of ?-sequences
+      // where ? is the last character of a preceding identifier, as in: `func?4`
+      { begin: /\B\?(\\\d{1,3})/ },
+      { begin: /\B\?(\\x[A-Fa-f0-9]{1,2})/ },
+      { begin: /\B\?(\\u\{?[A-Fa-f0-9]{1,6}\}?)/ },
+      { begin: /\B\?(\\M-\\C-|\\M-\\c|\\c\\M-|\\M-|\\C-\\M-)[\x20-\x7e]/ },
+      { begin: /\B\?\\(c|C-)[\x20-\x7e]/ },
+      { begin: /\B\?\\?\S/ }
+    ]
+  };
 
   // Ruby syntax is underdocumented, but this grammar seems to be accurate
   // as of version 2.7.2 (confirmed with (irb and `Ripper.sexp(...)`)
@@ -246,7 +277,7 @@ export default function(hljs) {
   const INCLUDE_EXTEND = {
     match: [
       /(include|extend)\s+/,
-      CLASS_NAME_WITH_NAMESPACE_RE
+      CLASS_NAME_RE
     ],
     scope: {
       2: "title.class"
@@ -259,15 +290,15 @@ export default function(hljs) {
       {
         match: [
           /class\s+/,
-          CLASS_NAME_WITH_NAMESPACE_RE,
+          CLASS_NAME_RE,
           /\s+<\s+/,
-          CLASS_NAME_WITH_NAMESPACE_RE
+          CLASS_NAME_RE
         ]
       },
       {
         match: [
           /\b(class|module)\s+/,
-          CLASS_NAME_WITH_NAMESPACE_RE
+          CLASS_NAME_RE
         ]
       }
     ],
@@ -301,7 +332,7 @@ export default function(hljs) {
   const OBJECT_CREATION = {
     relevance: 0,
     match: [
-      CLASS_NAME_WITH_NAMESPACE_RE,
+      CLASS_NAME_RE,
       /\.new[. (]/
     ],
     scope: {
@@ -317,7 +348,8 @@ export default function(hljs) {
   };
 
   const RUBY_DEFAULT_CONTAINS = [
-    STRING,
+    STRING_INTERPOLABLE,
+    STRING_NONINTERPOLABLE,
     CLASS_DEFINITION,
     INCLUDE_EXTEND,
     OBJECT_CREATION,
@@ -326,20 +358,28 @@ export default function(hljs) {
     METHOD_DEFINITION,
     {
       // swallow namespace qualifiers before symbols
-      begin: hljs.IDENT_RE + '::' },
+      begin: '::'
+    },
     {
       className: 'symbol',
-      begin: hljs.UNDERSCORE_IDENT_RE + '(!|\\?)?:',
+      begin: hljs.UNDERSCORE_IDENT_RE + '(!|\\?)?:(?!:)',
       relevance: 0
     },
     {
       className: 'symbol',
       begin: ':(?!\\s)',
       contains: [
-        STRING,
-        { begin: RUBY_METHOD_RE }
+        { begin: /'/, end: /'/ },
+        {
+          begin: /"/, end: /"/,
+          contains: [
+            hljs.BACKSLASH_ESCAPE,
+            SUBST
+          ]
+         },
+        { begin: hljs.UNDERSCORE_IDENT_RE }
       ],
-      relevance: 0
+      relevance: 1
     },
     NUMBER,
     {

test/markup/ruby/classes.expect.txt

@@ -0,0 +1,13 @@
+<span class="hljs-title class_">Class</span>
+<span class="hljs-title class_">ClassName</span>
+<span class="hljs-title class_">Class_Name</span>
+<span class="hljs-title class_">ClassNAME</span>
+<span class="hljs-title class_">ClassName</span>::<span class="hljs-title class_">With</span>::<span class="hljs-title class_">Namespace</span>
+<span class="hljs-title class_">ClassName</span>::<span class="hljs-title class_">With</span>.method
+::<span class="hljs-title class_">TopLevel</span>::<span class="hljs-title class_">Class</span>
+
+<span class="hljs-keyword">class</span> <span class="hljs-title class_">Class</span>::<span class="hljs-title class_">Name</span> &lt; <span class="hljs-title class_">With</span>::<span class="hljs-title class_">Inheritance</span>
+<span class="hljs-keyword">end</span>
+
+<span class="hljs-keyword">class</span> <span class="hljs-title class_">A</span>::<span class="hljs-title class_">B</span> &lt; <span class="hljs-title class_">C</span>::<span class="hljs-title class_">D</span>
+<span class="hljs-keyword">end</span>

test/markup/ruby/classes.txt

@@ -0,0 +1,13 @@
+Class
+ClassName
+Class_Name
+ClassNAME
+ClassName::With::Namespace
+ClassName::With.method
+::TopLevel::Class
+
+class Class::Name < With::Inheritance
+end
+
+class A::B < C::D
+end

test/markup/ruby/strings.expect.txt

@@ -27,4 +27,28 @@ c = <span class="hljs-string">?\u{00AF09}</span>
 c = <span class="hljs-string">?\u{0AF09}</span>
 c = <span class="hljs-string">?\u{AF9}</span>
 c = <span class="hljs-string">?\u{F9}</span>
-c = <span class="hljs-string">?\u{F}</span>
+c = <span class="hljs-string">?\u{F}</span>
+
+<span class="hljs-comment"># Interpolable Strings</span>
+<span class="hljs-string">&quot;string&quot;</span>
+<span class="hljs-string">&quot;string <span class="hljs-subst">#{var}</span>&quot;</span>
+<span class="hljs-string">`string`</span>
+<span class="hljs-string">`string <span class="hljs-subst">#{var}</span>`</span>
+<span class="hljs-string">%W[foo bar]</span>
+<span class="hljs-string">%W[foo bar <span class="hljs-subst">#{var}</span>]</span>
+<span class="hljs-string">%Q[foo bar]</span>
+<span class="hljs-string">%Q[foo bar <span class="hljs-subst">#{var}</span>]</span>
+<span class="hljs-string">%x[foo]</span>
+<span class="hljs-string">%x[foo <span class="hljs-subst">#{var}</span>]</span>
+<span class="hljs-string">&lt;&lt;~DOC
+  Multiline heredoc
+  Text <span class="hljs-subst">#{var}</span>
+DOC</span>
+
+<span class="hljs-comment"># Non-interpolable Strings</span>
+<span class="hljs-string">&#x27;string&#x27;</span>
+<span class="hljs-string">&#x27;string #{var}&#x27;</span>
+<span class="hljs-string">%q[foo]</span>
+<span class="hljs-string">%q[foo #{var}]</span>
+<span class="hljs-string">%w[foo]</span>
+<span class="hljs-string">%w[foo #{var}]</span>

test/markup/ruby/strings.txt

@@ -27,4 +27,28 @@ c = ?\u{00AF09}
 c = ?\u{0AF09}
 c = ?\u{AF9}
 c = ?\u{F9}
-c = ?\u{F}
+c = ?\u{F}
+
+# Interpolable Strings
+"string"
+"string #{var}"
+`string`
+`string #{var}`
+%W[foo bar]
+%W[foo bar #{var}]
+%Q[foo bar]
+%Q[foo bar #{var}]
+%x[foo]
+%x[foo #{var}]
+<<~DOC
+  Multiline heredoc
+  Text #{var}
+DOC
+
+# Non-interpolable Strings
+'string'
+'string #{var}'
+%q[foo]
+%q[foo #{var}]
+%w[foo]
+%w[foo #{var}]

test/markup/ruby/symbols.expect.txt

@@ -0,0 +1,22 @@
+<span class="hljs-symbol">:symbol</span>
+<span class="hljs-symbol">:Symbol</span>
+<span class="hljs-symbol">:_leading</span>
+<span class="hljs-symbol">:trailing_</span>
+<span class="hljs-symbol">:contains_underscore</span>
+<span class="hljs-symbol">:symbol_CAPS</span>
+<span class="hljs-symbol">:&quot;string symbol&quot;</span>
+<span class="hljs-symbol">:&quot;interpolated <span class="hljs-subst">#{test}</span>&quot;</span>
+<span class="hljs-symbol">:&#x27;string symbol&#x27;</span>
+<span class="hljs-symbol">:&#x27;not interpolated #{test}&#x27;</span>
+method <span class="hljs-symbol">:symbol</span>
+method(<span class="hljs-symbol">:symbol</span>)
+method(&amp;<span class="hljs-symbol">:symbol</span>)
+assign=<span class="hljs-symbol">:symbol</span>
+assign = <span class="hljs-symbol">:symbol</span>
+<span class="hljs-symbol">:symbol</span>, others
+<span class="hljs-symbol">:</span>1notasymbol
+<span class="hljs-symbol">:</span><span class="hljs-string">%q[notasymbol]</span>
+
+::notsymbol
+
+<span class="hljs-symbol">hash_symbol:</span> value

test/markup/ruby/symbols.txt

@@ -0,0 +1,22 @@
+:symbol
+:Symbol
+:_leading
+:trailing_
+:contains_underscore
+:symbol_CAPS
+:"string symbol"
+:"interpolated #{test}"
+:'string symbol'
+:'not interpolated #{test}'
+method :symbol
+method(:symbol)
+method(&:symbol)
+assign=:symbol
+assign = :symbol
+:symbol, others
+:1notasymbol
+:%q[notasymbol]
+
+::notsymbol
+
+hash_symbol: value