Merge branch 'skip'

docs/reference.rst

@@ -296,3 +296,29 @@ The value of the attribute controls which language or languages will be used for
 * language name: explicit highlighting with the specified language
 * empty array: auto detection with all the languages available
 * array of language names: auto detection constrained to the specified set
+
+skip
+^^^^
+
+**type**: boolean
+
+Skips any markup processing for the mode ensuring that it remains a part of its
+parent buffer along with the starting and the ending lexemes. This works in
+conjunction with the parent's :ref:`subLanguage` when it requires complex
+parsing.
+
+Consider parsing PHP inside HTML::
+
+  <p><? echo 'PHP'; /* ?> */ ?></p>
+
+The ``?>`` inside the comment should **not** end the PHP part, so we have to
+handle pairs of ``/* .. */`` to correctly find the ending ``?>``::
+
+  {
+    begin: /<\?/, end: /\?>/,
+    subLanguage: 'php',
+    contains: [{begin: '/\\*', end: '\\*/', skip: true}]
+  }
+
+Without ``skip: true`` every comment would cause the parser to drop out back
+into the HTML mode.

src/highlight.js

@@ -373,57 +373,64 @@ https://highlightjs.org/
     }
 
     function processBuffer() {
-      return top.subLanguage !== undefined ? processSubLanguage() : processKeywords();
+      result += (top.subLanguage !== undefined ? processSubLanguage() : processKeywords());
+      mode_buffer = '';
     }
 
     function startNewMode(mode, lexeme) {
-      var markup = mode.className? buildSpan(mode.className, '', true): '';
-      if (mode.returnBegin) {
-        result += markup;
-        mode_buffer = '';
-      } else if (mode.excludeBegin) {
-        result += escape(lexeme) + markup;
-        mode_buffer = '';
-      } else {
-        result += markup;
-        mode_buffer = lexeme;
-      }
+      result += mode.className? buildSpan(mode.className, '', true): '';
       top = Object.create(mode, {parent: {value: top}});
     }
 
     function processLexeme(buffer, lexeme) {
 
       mode_buffer += buffer;
+
       if (lexeme === undefined) {
-        result += processBuffer();
+        processBuffer();
         return 0;
       }
 
       var new_mode = subMode(lexeme, top);
       if (new_mode) {
-        result += processBuffer();
+        if (new_mode.skip) {
+          mode_buffer += lexeme;
+        } else {
+          if (new_mode.excludeBegin) {
+            mode_buffer += lexeme;
+          }
+          processBuffer();
+          if (!new_mode.returnBegin && !new_mode.excludeBegin) {
+            mode_buffer = lexeme;
+          }
+        }
         startNewMode(new_mode, lexeme);
         return new_mode.returnBegin ? 0 : lexeme.length;
       }
 
       var end_mode = endOfMode(top, lexeme);
       if (end_mode) {
         var origin = top;
-        if (!(origin.returnEnd || origin.excludeEnd)) {
+        if (origin.skip) {
           mode_buffer += lexeme;
+        } else {
+          if (!(origin.returnEnd || origin.excludeEnd)) {
+            mode_buffer += lexeme;
+          }
+          processBuffer();
+          if (origin.excludeEnd) {
+            mode_buffer = lexeme;
+          }
         }
-        result += processBuffer();
         do {
           if (top.className) {
             result += '</span>';
           }
-          relevance += top.relevance;
+          if (!top.skip) {
+            relevance += top.relevance;
+          }
           top = top.parent;
         } while (top != end_mode.parent);
-        if (origin.excludeEnd) {
-          result += escape(lexeme);
-        }
-        mode_buffer = '';
         if (end_mode.starts) {
           startNewMode(end_mode.starts, '');
         }

src/languages/javascript.js

@@ -68,9 +68,12 @@ function(hljs) {
           hljs.C_BLOCK_COMMENT_MODE,
           hljs.REGEXP_MODE,
           { // E4X / JSX
-            begin: /</, end: />\s*[);\]]/,
-            relevance: 0,
-            subLanguage: 'xml'
+            begin: /</, end: /(\/\w+|\w+\/)>/,
+            subLanguage: 'xml',
+            contains: [
+              {begin: /<\w+\/>/, skip: true},
+              {begin: /<\w+/, end: /(\/\w+|\w+\/)>/, skip: true, contains: ['self']}
+            ]
           }
         ],
         relevance: 0

src/languages/php-html.js

@@ -0,0 +1,18 @@
+/*
+Language: PHP in HTML
+Requires: php.js, xml.js
+Category: common
+*/
+
+function(hljs) {
+  return {
+    subLanguage: 'xml',
+    contains: [
+      {
+        begin: /<\?(php)?/, end: /\?>/,
+        subLanguage: 'php',
+        contains: [{begin: '/\\*', end: '\\*/', skip: true}]
+      }
+    ]
+  }
+}

src/languages/php.js

@@ -40,8 +40,8 @@ function(hljs) {
       'trait goto instanceof insteadof __DIR__ __NAMESPACE__ ' +
       'yield finally',
     contains: [
-      hljs.C_LINE_COMMENT_MODE,
       hljs.HASH_COMMENT_MODE,
+      hljs.COMMENT('//', '$', {contains: [PREPROCESSOR]}),
       hljs.COMMENT(
         '/\\*',
         '\\*/',
@@ -50,8 +50,7 @@ function(hljs) {
             {
               className: 'doctag',
               begin: '@[A-Za-z]+'
-            },
-            PREPROCESSOR
+            }
           ]
         }
       ),

src/languages/xml.js

@@ -5,16 +5,11 @@ Category: common
 
 function(hljs) {
   var XML_IDENT_RE = '[A-Za-z0-9\\._:-]+';
-  var PHP = {
-    begin: /<\?(php)?(?!\w)/, end: /\?>/,
-    subLanguage: 'php'
-  };
   var TAG_INTERNALS = {
     endsWithParent: true,
     illegal: /</,
     relevance: 0,
     contains: [
-      PHP,
       {
         className: 'attr',
         begin: XML_IDENT_RE,
@@ -26,7 +21,6 @@ function(hljs) {
         contains: [
           {
             className: 'string',
-            contains: [PHP],
             variants: [
               {begin: /"/, end: /"/},
               {begin: /'/, end: /'/},
@@ -85,11 +79,12 @@ function(hljs) {
           subLanguage: ['actionscript', 'javascript', 'handlebars', 'xml']
         }
       },
-      PHP,
       {
         className: 'meta',
-        begin: /<\?\w+/, end: /\?>/,
-        relevance: 10
+        variants: [
+          {begin: /<\?xml/, end: /\?>/, relevance: 10},
+          {begin: /<\?\w+/, end: /\?>/}
+        ]
       },
       {
         className: 'tag',

test/detect/php-html/default.txt

@@ -0,0 +1,3 @@
+<p>HTML</p>
+<?php echo 'PHP' ?>
+<hr>

test/fixtures/expect/sublanguages.txt

@@ -1,5 +1,5 @@
-<span class="php"><span class="hljs-meta">&lt;?</span> <span class="hljs-keyword">echo</span> <span class="hljs-string">'php'</span>; <span class="hljs-comment">/* <span class="hljs-meta">?&gt;</span></span></span>
+<span class="xml"></span><span class="php"><span class="hljs-meta">&lt;?</span> <span class="hljs-keyword">echo</span> <span class="hljs-string">'php'</span>; <span class="hljs-comment">/* ?&gt; */</span> <span class="hljs-meta">?&gt;</span></span><span class="xml">
 <span class="hljs-tag">&lt;<span class="hljs-name">body</span>&gt;</span>
-<span class="hljs-tag">&lt;<span class="hljs-name">script</span>&gt;</span><span class="actionscript"><span class="hljs-function"><span class="hljs-keyword">function</span> <span class="hljs-title">tf</span> <span class="hljs-params">(x)</span> </span>{ <span class="hljs-keyword">return</span> <span class="hljs-keyword">typeof</span> x; }</span><span class="hljs-tag">&lt;/<span class="hljs-name">script</span>&gt;</span>
+<span class="hljs-tag">&lt;<span class="hljs-name">script</span>&gt;</span><span class="javascript"><span class="hljs-built_in">document</span>.write(<span class="hljs-string">'Legacy code'</span>);</span><span class="hljs-tag">&lt;/<span class="hljs-name">script</span>&gt;</span>
 <span class="hljs-tag">&lt;/<span class="hljs-name">body</span>&gt;</span>
-<span class="php"><span class="hljs-comment"><span class="hljs-meta">&lt;?</span> end of comment */</span> <span class="hljs-meta">?&gt;</span></span>
+</span>

test/fixtures/index.html

@@ -97,11 +97,10 @@
 </div>
 
 <!-- sub-languages -->
-<pre><code id="sublanguages" class="xml">&lt;? echo 'php'; /* ?&gt;
+<pre><code id="sublanguages" class="php-html">&lt;? echo 'php'; /* ?&gt; */ ?&gt;
 &lt;body&gt;
-&lt;script&gt;function tf (x) { return typeof x; }&lt;/script&gt;
+&lt;script&gt;document.write('Legacy code');&lt;/script&gt;
 &lt;/body&gt;
-&lt;? end of comment */ ?&gt;
 </code></pre>
 
 <div id="build-classname">

test/markup/javascript/jsx.expect.txt

@@ -1,21 +1,5 @@
-<span class="hljs-keyword">var</span> X = React.createClass({
-  render: <span class="hljs-function"><span class="hljs-keyword">function</span>(<span class="hljs-params"></span>) </span>{
-    <span class="hljs-keyword">var</span> c = <span class="hljs-keyword">this</span>.map(c =&gt; <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">Comment</span> <span class="hljs-attr">comment</span>=<span class="hljs-string">{c}</span> <span class="hljs-attr">key</span>=<span class="hljs-string">{c.id}</span> /&gt;</span>)</span>;
-    <span class="hljs-keyword">return</span> (
-      <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">div</span> <span class="hljs-attr">className</span>=<span class="hljs-string">'comments'</span>&gt;</span>
-        {c}
-      <span class="hljs-tag">&lt;/<span class="hljs-name">div</span>&gt;</span>
-    )</span>;
-  },
-  foo: <span class="hljs-function"><span class="hljs-keyword">function</span>(<span class="hljs-params"></span>) </span>{}
-});
-
-<span class="hljs-keyword">var</span> Comment = React.createClass({
-  render: <span class="hljs-function"><span class="hljs-keyword">function</span>(<span class="hljs-params"></span>) </span>{
-    <span class="hljs-keyword">var</span> comment = <span class="hljs-keyword">this</span>.props.comment;
-    <span class="hljs-keyword">return</span> (
-        <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">li</span>&gt;</span>{comment}<span class="hljs-tag">&lt;/<span class="hljs-name">li</span>&gt;</span>
-    )</span>;
-  }
-  foo: <span class="hljs-function"><span class="hljs-keyword">function</span>(<span class="hljs-params"></span>) </span>{}
-});
+<span class="hljs-keyword">var</span> jsx = <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">node</span>/&gt;</span></span>;
+<span class="hljs-keyword">var</span> jsx = <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">node</span>&gt;</span><span class="hljs-tag">&lt;<span class="hljs-name">child</span>/&gt;</span><span class="hljs-tag">&lt;/<span class="hljs-name">node</span>&gt;</span></span>;
+<span class="hljs-keyword">var</span> jsx = <span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">node</span>&gt;</span>...<span class="hljs-tag">&lt;<span class="hljs-name">child</span>&gt;</span>...<span class="hljs-tag">&lt;/<span class="hljs-name">child</span>&gt;</span><span class="hljs-tag">&lt;/<span class="hljs-name">node</span>&gt;</span></span>;
+<span class="hljs-keyword">var</span> x = <span class="hljs-number">5</span>;
+<span class="hljs-keyword">return</span> (<span class="xml"><span class="hljs-tag">&lt;<span class="hljs-name">node</span> <span class="hljs-attr">attr</span>=<span class="hljs-string">"value"</span>&gt;</span><span class="hljs-tag">&lt;/<span class="hljs-name">node</span>&gt;</span></span>);

test/markup/javascript/jsx.txt

@@ -1,21 +1,5 @@
-var X = React.createClass({
-  render: function() {
-    var c = this.map(c => <Comment comment={c} key={c.id} />);
-    return (
-      <div className='comments'>
-        {c}
-      </div>
-    );
-  },
-  foo: function() {}
-});
-
-var Comment = React.createClass({
-  render: function() {
-    var comment = this.props.comment;
-    return (
-        <li>{comment}</li>
-    );
-  }
-  foo: function() {}
-});
+var jsx = <node/>;
+var jsx = <node><child/></node>;
+var jsx = <node>...<child>...</child></node>;
+var x = 5;
+return (<node attr="value"></node>);

test/utility.js

@@ -17,7 +17,7 @@ exports.numberToString = _.method('toString');
 
 exports.expectedFile = function(filename, encoding, actual) {
   return readFile(filename, encoding)
-    .then(expected => actual.should.equal(expected));
+    .then(expected => actual.trim().should.equal(expected.trim()));
 };
 
 exports.setupFile = function(filename, encoding, that, testHTML) {