Implement auto-formatter that removes empty span tags.

Signed-off-by: Paul Stone <patches@pdjs.co.uk>
Signed-off-by: Edward Z. Yang <ezyang@mit.edu>

library/HTMLPurifier.includes.php

@@ -176,6 +176,7 @@ require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
 require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';

library/HTMLPurifier.safe-includes.php

@@ -170,6 +170,7 @@ require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt

@@ -0,0 +1,11 @@
+AutoFormat.RemoveSpansWithoutAttributes
+TYPE: bool
+VERSION: 4.0.1
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  This directive causes <code>span</code> tags without any attributes
+  to be removed. It will also remove spans that had all attributes
+  removed during processing.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php

@@ -0,0 +1,60 @@
+<?php
+
+/**
+ * Injector that removes spans with no attributes
+ */
+class HTMLPurifier_Injector_RemoveSpansWithoutAttributes extends HTMLPurifier_Injector
+{
+    public $name = 'RemoveSpansWithoutAttributes';
+    public $needed = array('span');
+
+    private $attrValidator;
+
+    /**
+     * Used by AttrValidator
+     */
+    private $config;
+    private $context;
+
+    public function prepare($config, $context) {
+        $this->attrValidator = new HTMLPurifier_AttrValidator();
+        $this->config = $config;
+        $this->context = $context;
+        return parent::prepare($config, $context);
+    }
+
+    public function handleElement(&$token) {
+        if ($token->name !== 'span' || !$token instanceof HTMLPurifier_Token_Start) {
+            return;
+        }
+
+        // We need to validate the attributes now since this doesn't normally
+        // happen until after MakeWellFormed. If all the attributes are removed
+        // the span needs to be removed too.
+        $this->attrValidator->validateToken($token, $this->config, $this->context);
+        $token->armor['ValidateAttributes'] = true;
+
+        if (!empty($token->attr)) {
+            return;
+        }
+
+        $nesting = 0;
+        $spanContentTokens = array();
+        while ($this->forwardUntilEndToken(&$i, &$current, &$nesting)) {}
+
+        if ($current instanceof HTMLPurifier_Token_End && $current->name === 'span') {
+            // Mark closing span tag for deletion
+            $current->markForDeletion = true;
+            // Delete open span tag
+            $token = false;
+        }
+    }
+
+    public function handleEnd(&$token) {
+        if ($token->markForDeletion) {
+            $token = false;
+        }
+    }
+}
+
+// vim: et sw=4 sts=4

tests/HTMLPurifier/Injector/RemoveSpansWithoutAttributesTest.php

@@ -0,0 +1,99 @@
+<?php
+
+class HTMLPurifier_Injector_RemoveSpansWithoutAttributesTest extends HTMLPurifier_InjectorHarness
+{
+    function setup() {
+        parent::setup();
+        $this->config->set('HTML.Allowed', 'span[class],div,p,strong,em');
+        $this->config->set('AutoFormat.RemoveSpansWithoutAttributes', true);
+    }
+
+    function testSingleSpan() {
+        $this->assertResult(
+            '<span>foo</span>',
+            'foo'
+        );
+    }
+
+    function testSingleSpanWithAttributes() {
+        $this->assertResult(
+            '<span class="bar">foo</span>',
+            '<span class="bar">foo</span>'
+        );
+    }
+
+    function testSingleNestedSpan() {
+        $this->assertResult(
+            '<p><span>foo</span></p>',
+            '<p>foo</p>'
+        );
+    }
+
+    function testSingleNestedSpanWithAttributes() {
+        $this->assertResult(
+            '<p><span class="bar">foo</span></p>',
+            '<p><span class="bar">foo</span></p>'
+        );
+    }
+
+
+    function testSpanWithChildren() {
+        $this->assertResult(
+            '<span>foo <strong>bar</strong> <em>baz</em></span>',
+            'foo <strong>bar</strong> <em>baz</em>'
+        );
+    }
+
+    function testSpanWithSiblings() {
+        $this->assertResult(
+            '<p>before <span>inside</span> <strong>after</strong></p>',
+            '<p>before inside <strong>after</strong></p>'
+        );
+    }
+
+    function testNestedSpanWithSiblingsAndChildren() {
+        $this->assertResult(
+            '<p>a <span>b <em>c</em> d</span> e</p>',
+            '<p>a b <em>c</em> d e</p>'
+        );
+    }
+
+    function testNestedSpansWithoutAttributes() {
+        $this->assertResult(
+            '<span>one<span>two<span>three</span></span></span>',
+            'onetwothree'
+        );
+    }
+
+    function testDeeplyNestedSpan() {
+        $this->assertResult(
+            '<div><div><div><span class="a">a <span>b</span> c</span></div></div></div>',
+            '<div><div><div><span class="a">a b c</span></div></div></div>'
+        );
+    }
+
+    function testSpanWithInvalidAttributes() {
+        $this->assertResult(
+            '<p><span snorkel buzzer="emu">foo</span></p>',
+            '<p>foo</p>'
+        );
+    }
+
+    function testNestedAlternateSpans() {
+        $this->assertResult(
+'<span>a <span class="x">b <span>c <span class="y">d <span>e <span class="z">f
+</span></span></span></span></span></span>',
+'a <span class="x">b c <span class="y">d e <span class="z">f
+</span></span></span>'
+        );
+    }
+
+    function testSpanWithSomeInvalidAttributes() {
+        $this->assertResult(
+            '<p><span buzzer="emu" class="bar">foo</span></p>',
+            '<p><span class="bar">foo</span></p>'
+        );
+    }
+}
+
+// vim: et sw=4 sts=4