Add support for bogus comments

wooorm · wooorm · commit dcd4ac853d81 · 2020-02-29T10:22:09.000+01:00
Closes GH-16.
diff --git a/lib/comment.js b/lib/comment.js
@@ -8,9 +8,18 @@ module.exports = serializeComment
 // See: <https://html.spec.whatwg.org/multipage/syntax.html#comments>
 var breakout = /^>|^->|<!--|-->|--!>|<!-$/g
 var subset = ['<', '>']
+var bogusSubset = ['>']
 
 function serializeComment(ctx, node) {
-  return '<!--' + node.value.replace(breakout, encode) + '-->'
+  var value = node.value
+
+  if (ctx.bogusComments) {
+    return (
+      '<?' + entities(value, xtend(ctx.entities, {subset: bogusSubset})) + '>'
+    )
+  }
+
+  return '<!--' + value.replace(breakout, encode) + '-->'
 
   function encode($0) {
     return entities($0, xtend(ctx.entities, {subset: subset}))
diff --git a/lib/index.js b/lib/index.js
@@ -57,6 +57,7 @@ function toHtml(node, options) {
       tight: settings.tightAttributes,
       upperDoctype: Boolean(settings.upperDoctype),
       tightDoctype: Boolean(settings.tightDoctype),
+      bogusComments: Boolean(settings.bogusComments),
       tightLists: settings.tightCommaSeparatedLists,
       tightClose: settings.tightSelfClosing,
       collapseEmpty: settings.collapseEmptyAttributes,
diff --git a/readme.md b/readme.md
@@ -152,6 +152,12 @@ Drop unneeded spaces in doctypes: `<!doctypehtml>` instead of `<!doctype html>`
 to save bytes (`boolean`, default: `false`).
 **Note**: creates invalid (but working) markup.
 
+###### `options.bogusComments`
+
+Use “bogus comments” instead of comments to save byes: `<?charlie>` instead of
+`<!--charlie-->` (`boolean`, default: `false`).
+**Note**: creates invalid (but working) markup.
+
 ###### `options.allowParseErrors`
 
 Do not encode characters which cause parse errors (even though they work), to
diff --git a/test/comment.js b/test/comment.js
@@ -17,6 +17,18 @@ test('`comment`', function(t) {
     'should not encode `comment`s'
   )
 
+  t.deepEqual(
+    to(u('comment', 'asd'), {bogusComments: true}),
+    '<?asd>',
+    '`bogusComments`: should serialize bogus comments'
+  )
+
+  t.deepEqual(
+    to(u('comment', 'a<s>d'), {bogusComments: true}),
+    '<?a<s&#x3E;d>',
+    '`bogusComments`: should prevent breaking out of bogus comments'
+  )
+
   // https://html.spec.whatwg.org/multipage/syntax.html#comments
   // Optionally, text, with the additional restriction that the text must not
   // start with the string `>`, nor start with the string `->`, nor contain the
