# $params: String between element name and >
# $brace: Ending '>' or '/>'
# $rest: Everything until the next element of $bits
- if ( preg_match( '!^(/?)(\\w+)([^>]*?)(/{0,1}>)([^<]*)$!', $x, $regs ) ) {
+ if ( preg_match( '!^(/?)([^\\s/>]+)([^>]*?)(/{0,1}>)([^<]*)$!', $x, $regs ) ) {
list( /* $qbar */, $slash, $t, $params, $brace, $rest ) = $regs;
} else {
$slash = $t = $params = $brace = $rest = null;
</p>
!! end
+# <strike> is HTML4, <s> is HTML4/5.
+!! test
+<s> or <strike> for strikethrough
+!! input
+<strike>strike</strike>
+
+<s>s</s>
+!! result
+<p><strike>strike</strike>
+</p><p><s>s</s>
+</p>
+!! end
+
+!! test
+Non-word characters don't terminate tag names (bug 17663, 40670, 52022)
+!! input
+<b→> doesn't work! </b>
+
+<bä> doesn't work! </b>
+
+<boo> works fine </b>
+
+<s.foo>foo</s>
+
+<s.foo>s.foo</s.foo>
+
+<sub-ID#1>
+!! result
+<p><b→> doesn't work! </b>
+</p><p><bä> doesn't work! </b>
+</p><p><boo> works fine </b>
+</p><p><s.foo>foo</s>
+</p><p><s.foo>s.foo</s.foo>
+</p><p><sub-ID#1>
+</p>
+!! end
+
###
### Special characters
###
!! end
-# This fails in the PHP parser (see bug 40670,
-# https://bugzilla.wikimedia.org/show_bug.cgi?id=40670), so disabled for it.
+# This was a bug in the PHP parser (see bug 17663 and its dups,
+# https://bugzilla.wikimedia.org/show_bug.cgi?id=17663)
!! test
Tag names followed by punctuation should not be recognized as tags
-!! options
-parsoid
!! input
<s.ome> text
!! result