Release 4.2.0.

Signed-off-by: Edward Z. Yang <ezyang@mit.edu>

.gitignore

@@ -18,3 +18,5 @@ docs/doxygen*
 *.phpt.php
 *.phpt.skip.php
 *.htmlt.ini
+*.patch
+/*.php

Doxyfile

@@ -31,7 +31,7 @@ PROJECT_NAME           = HTMLPurifier
 # This could be handy for archiving the generated documentation or
 # if some version control system is used.
 
-PROJECT_NUMBER         = 4.1.0
+PROJECT_NUMBER         = 4.2.0
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
 # base path where the generated documentation will be put.

FOCUS

@@ -1,4 +1,4 @@
-9 - Major security fixes
+4 - Minor feature enhancements
 
 [ Appendix A: Release focus IDs ]
 0 - N/A

NEWS

@@ -9,6 +9,41 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+4.2.0, released 2010-09-15
+! Added %Core.RemoveProcessingInstructions, which lets you remove
+  <? ... ?> statements.
+! Added %URI.DisableResources functionality; the directive originally
+  did nothing.  Thanks David Rothstein for reporting.
+! Add documentation about configuration directive types.
+! Add %CSS.ForbiddenProperties configuration directive.
+! Add %HTML.FlashAllowFullScreen to permit embedded Flash objects
+  to utilize full-screen mode.
+! Add optional support for the <code>file</code> URI scheme, enable
+  by explicitly setting %URI.AllowedSchemes.
+! Add %Core.NormalizeNewlines options to allow turning off newline
+  normalization.
+- Fix improper handling of Internet Explorer conditional comments
+  by parser.  Thanks zmonteca for reporting.
+- Fix missing attributes bug when running on Mac Snow Leopard and APC.
+  Thanks sidepodcast for the fix.
+- Warn if an element is allowed, but an attribute it requires is
+  not allowed.
+
+4.1.1, released 2010-05-31
+- Fix undefined index warnings in maintenance scripts.
+- Fix bug in DirectLex for parsing elements with a single attribute
+  with entities.
+- Rewrite CSS output logic for font-family and url().  Thanks Mario
+  Heiderich <mario.heiderich@googlemail.com> for reporting and Takeshi
+  Terada <t-terada@violet.plala.or.jp> for suggesting the fix.
+- Emit an error for CollectErrors if a body is extracted
+- Fix bug where in background-position for center keyword handling.
+- Fix infinite loop when a wrapper element is inserted in a context
+  where it's not allowed.  Thanks Lars <lars@renoz.dk> for reporting.
+- Remove +x bit and shebang from index.php; only supported mode is to
+  explicitly call it with php.
+- Make test script less chatty when log_errors is on.
+
 4.1.0, released 2010-04-26
 ! Support proprietary height attribute on table element
 ! Support YouTube slideshows that contain /cp/ in their URL.

TODO

@@ -20,11 +20,14 @@ Things to do as soon as possible:
    debugging
  - Allowed/Allowed* have strange interactions when both set
  - Transform lone embeds into object tags
+ - Deprecated config options that emit warnings when you set them (with'
+   a way of muting the warning if you really want to)
+ - Make HTML.Trusted work with Output.FlashCompat
 
 FUTURE VERSIONS
 ---------------
 
-4.2 release [OMG CONFIG PONIES]
+4.3 release [OMG CONFIG PONIES]
  ! Fix Printer. It's from the old days when we didn't have decent XML classes
  ! Factor demo.php into a set of Printer classes, and then create a stub
    file for users here (inside the actual HTML Purifier library)

VERSION

@@ -1 +1 @@
-4.1.0
+4.2.0

WHATSNEW

@@ -1,6 +1,8 @@
-HTML Purifier 4.1 is a major security release that fixes an XSS
-vulnerability exploitable on Internet Explorer.  It also contains
-a number of new features, including dramatically more flexible Flash
-support, including %Output.FlashCompat to replace %HTML.SafeEmbed,
-optional support for the data: URI scheme and better HTML parsing
-capabilities.
+HTML Purifier 4.2.0 is a minor release that implements a number of
+feature requests accumulated over half a year.  New configuration
+options include %Core.RemoveProcessingInstructions,
+%CSS.ForbiddenProperties, %HTML.FlashAllowFullScreen and
+%Core.NormalizeNewlines.  Additionally,%URI.DisableResources is
+now functional and file: is an optionally supported URI scheme.
+There are also some minor bugfixes, usability improvements and
+documentation updates.

configdoc/styles/plain.xsl

@@ -40,12 +40,26 @@
                             </xsl:apply-templates>
                         </ul>
                     </div>
+                    <div id="typesContainer">
+                        <h2>Types</h2>
+                        <xsl:apply-templates select="$typeLookup" mode="types" />
+                    </div>
                     <xsl:apply-templates />
                 </div>
             </body>
         </html>
     </xsl:template>
 
+    <xsl:template match="type" mode="types">
+        <div class="type-block">
+            <xsl:attribute name="id">type-<xsl:value-of select="@id" /></xsl:attribute>
+            <h3><code><xsl:value-of select="@id" /></code>: <xsl:value-of select="@name" /></h3>
+            <div class="type-description">
+                <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
+            </div>
+        </div>
+    </xsl:template>
+
     <xsl:template match="title" mode="toc" />
     <xsl:template match="namespace" mode="toc">
         <xsl:param name="overflowNumber" />
@@ -192,10 +206,13 @@
             <td>
                 <xsl:variable name="type" select="text()" />
                 <xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
-                <xsl:value-of select="$typeLookup/type[@id=$type]/text()" />
-                <xsl:if test="@allow-null='yes'">
-                    (or null)
-                </xsl:if>
+                <a>
+                    <xsl:attribute name="href">#type-<xsl:value-of select="$type" /></xsl:attribute>
+                    <xsl:value-of select="$typeLookup/type[@id=$type]/@name" />
+                    <xsl:if test="@allow-null='yes'">
+                        (or null)
+                    </xsl:if>
+                </a>
             </td>
         </tr>
     </xsl:template>

configdoc/types.xml

@@ -1,16 +1,68 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <types>
-  <type id="string">String</type>
-  <type id="istring">Case-insensitive string</type>
-  <type id="text">Text</type>
-  <type id="itext">Case-insensitive text</type>
-  <type id="int">Integer</type>
-  <type id="float">Float</type>
-  <type id="bool">Boolean</type>
-  <type id="lookup">Lookup array</type>
-  <type id="list">Array list</type>
-  <type id="hash">Associative array</type>
-  <type id="mixed">Mixed</type>
+  <type id="string" name="String"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+    href="http://docs.php.net/manual/en/language.types.string.php">sequence
+    of characters</a>.
+  </div></type>
+  <type id="istring" name="Case-insensitive string"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters.  Internally, upper-case
+    ASCII characters will be converted to lower-case.
+  </div></type>
+  <type id="text" name="Text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of characters that may contain newlines.  Text tends to
+    indicate human-oriented text, as opposed to a machine format.
+  </div></type>
+  <type id="itext" name="Case-insensitive text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters that may contain newlines.
+  </div></type>
+  <type id="int" name="Integer"><div xmlns="http://www.w3.org/1999/xhtml">
+    An <a
+      href="http://docs.php.net/manual/en/language.types.integer.php">
+      integer</a>.  You are alternatively permitted to pass a string of
+    digits instead, which will be cast to an integer using
+    <code>(int)</code>.
+  </div></type>
+  <type id="float" name="Float"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a href="http://docs.php.net/manual/en/language.types.float.php">
+      floating point number</a>.  You are alternatively permitted to
+    pass a numeric string (as defined by <code>is_numeric()</code>),
+    which will be cast to a float using <code>(float)</code>.
+  </div></type>
+  <type id="bool" name="Boolean"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+      href="http://docs.php.net/manual/en/language.types.boolean.php">boolean</a>.
+    You are alternatively permitted to pass an integer <code>0</code> or
+    <code>1</code> (other integers are not permitted) or a string
+    <code>"on"</code>, <code>"true"</code> or <code>"1"</code> for
+    <code>true</code>, and <code>"off"</code>, <code>"false"</code> or
+    <code>"0"</code> for <code>false</code>.
+  </div></type>
+  <type id="lookup" name="Lookup array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array whose values are <code>true</code>, e.g. <code>array('key'
+      => true, 'key2' => true)</code>.  You are alternatively permitted
+    to pass an array list of the keys <code>array('key', 'key2')</code>
+    or a comma-separated string of keys <code>"key, key2"</code>.  If
+    you pass an array list of values, ensure that your values are
+    strictly numerically indexed: <code>array('key1', 2 =>
+      'key2')</code> will not do what you expect and emits a warning.
+  </div></type>
+  <type id="list" name="Array list"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which has consecutive integer indexes, e.g.
+    <code>array('val1', 'val2')</code>.  You are alternatively permitted
+    to pass a comma-separated string of keys <code>"val1, val2"</code>.
+    If your array is not in this form, <code>array_values</code> is run
+    on the array and a warning is emitted.
+  </div></type>
+  <type id="hash" name="Associative array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which is a mapping of keys to values, e.g.
+    <code>array('key1' => 'val1', 'key2' => 'val2')</code>.  You are
+    alternatively permitted to pass a comma-separated string of
+    key-colon-value strings, e.g. <code>"key1: val1, key2: val2"</code>.
+  </div></type>
+  <type id="mixed" name="Mixed"><div xmlns="http://www.w3.org/1999/xhtml">
+    An arbitrary PHP value of any type.
+  </div></type>
 </types>
 
 <!-- vim: et sw=4 sts=4

configdoc/usage.xml

@@ -6,6 +6,7 @@
   </file>
   <file name="HTMLPurifier/Lexer.php">
    <line>81</line>
+   <line>284</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
    <line>53</line>
@@ -41,6 +42,11 @@
    <line>275</line>
   </file>
  </directive>
+ <directive id="CSS.ForbiddenProperties">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>289</line>
+  </file>
+ </directive>
  <directive id="Cache.DefinitionImpl">
   <file name="HTMLPurifier/DefinitionCacheFactory.php">
    <line>49</line>
@@ -103,10 +109,18 @@
    <line>87</line>
   </file>
  </directive>
- <directive id="Output.Newline">
+ <directive id="Core.NormalizeNewlines">
   <file name="HTMLPurifier/Generator.php">
    <line>101</line>
   </file>
+  <file name="HTMLPurifier/Lexer.php">
+   <line>266</line>
+  </file>
+ </directive>
+ <directive id="Output.Newline">
+  <file name="HTMLPurifier/Generator.php">
+   <line>102</line>
+  </file>
  </directive>
  <directive id="HTML.BlockWrapper">
   <file name="HTMLPurifier/HTMLDefinition.php">
@@ -135,12 +149,12 @@
  </directive>
  <directive id="HTML.ForbiddenElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>337</line>
+   <line>342</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>338</line>
+   <line>343</line>
   </file>
  </directive>
  <directive id="HTML.Trusted">
@@ -148,7 +162,7 @@
    <line>202</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>258</line>
+   <line>271</line>
   </file>
   <file name="HTMLPurifier/HTMLModule/Image.php">
    <line>27</line>
@@ -210,7 +224,12 @@
  </directive>
  <directive id="Core.ConvertDocumentToFragment">
   <file name="HTMLPurifier/Lexer.php">
-   <line>267</line>
+   <line>282</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveProcessingInstructions">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>303</line>
   </file>
  </directive>
  <directive id="URI.">
@@ -336,6 +355,11 @@
    <line>13</line>
   </file>
  </directive>
+ <directive id="HTML.FlashAllowFullScreen">
+  <file name="HTMLPurifier/AttrTransform/SafeParam.php">
+   <line>37</line>
+  </file>
+ </directive>
  <directive id="Core.EscapeInvalidChildren">
   <file name="HTMLPurifier/ChildDef/Required.php">
    <line>62</line>

library/HTMLPurifier.includes.php

@@ -7,7 +7,7 @@
  * primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
  * FILE, changes will be overwritten the next time the script is run.
  *
- * @version 4.1.0
+ * @version 4.2.0
  *
  * @warning
  *      You must *not* include any other HTML Purifier files before this file,
@@ -196,10 +196,12 @@ require 'HTMLPurifier/Token/Start.php';
 require 'HTMLPurifier/Token/Text.php';
 require 'HTMLPurifier/URIFilter/DisableExternal.php';
 require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
+require 'HTMLPurifier/URIFilter/DisableResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
 require 'HTMLPurifier/URIFilter/Munge.php';
 require 'HTMLPurifier/URIScheme/data.php';
+require 'HTMLPurifier/URIScheme/file.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier.php

@@ -19,7 +19,7 @@
  */
 
 /*
-    HTML Purifier 4.1.0 - Standards Compliant HTML Filtering
+    HTML Purifier 4.2.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006-2008 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -55,10 +55,10 @@ class HTMLPurifier
 {
 
     /** Version of HTML Purifier */
-    public $version = '4.1.0';
+    public $version = '4.2.0';
 
     /** Constant with version of HTML Purifier */
-    const VERSION = '4.1.0';
+    const VERSION = '4.2.0';
 
     /** Global configuration object */
     public $config;

library/HTMLPurifier.safe-includes.php

@@ -190,10 +190,12 @@ require_once $__dir . '/HTMLPurifier/Token/Start.php';
 require_once $__dir . '/HTMLPurifier/Token/Text.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/DisableResources.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/data.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/file.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier/AttrDef.php

@@ -82,6 +82,42 @@ abstract class HTMLPurifier_AttrDef
         return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
     }
 
+    /**
+     * Parses a possibly escaped CSS string and returns the "pure" 
+     * version of it.
+     */
+    protected function expandCSSEscape($string) {
+        // flexibly parse it
+        $ret = '';
+        for ($i = 0, $c = strlen($string); $i < $c; $i++) {
+            if ($string[$i] === '\\') {
+                $i++;
+                if ($i >= $c) {
+                    $ret .= '\\';
+                    break;
+                }
+                if (ctype_xdigit($string[$i])) {
+                    $code = $string[$i];
+                    for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                        if (!ctype_xdigit($string[$i])) break;
+                        $code .= $string[$i];
+                    }
+                    // We have to be extremely careful when adding
+                    // new characters, to make sure we're not breaking
+                    // the encoding.
+                    $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                    if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+                    $ret .= $char;
+                    if ($i < $c && trim($string[$i]) !== '') $i--;
+                    continue;
+                }
+                if ($string[$i] === "\n") continue;
+            }
+            $ret .= $string[$i];
+        }
+        return $ret;
+    }
+
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -59,7 +59,8 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
         $keywords = array();
         $keywords['h'] = false; // left, right
         $keywords['v'] = false; // top, bottom
-        $keywords['c'] = false; // center
+        $keywords['ch'] = false; // center (first word)
+        $keywords['cv'] = false; // center (second word)
         $measures = array();
 
         $i = 0;
@@ -79,6 +80,13 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
             $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
             if (isset($lookup[$lbit])) {
                 $status = $lookup[$lbit];
+                if ($status == 'c') {
+                    if ($i == 0) {
+                        $status = 'ch';
+                    } else {
+                        $status = 'cv';
+                    }
+                }
                 $keywords[$status] = $lbit;
                 $i++;
             }
@@ -101,20 +109,19 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 
         if (!$i) return false; // no valid values were caught
 
-
         $ret = array();
 
         // first keyword
         if     ($keywords['h'])     $ret[] = $keywords['h'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c']) {
-            $ret[] = $keywords['c'];
-            $keywords['c'] = false; // prevent re-use: center = center center
+        elseif ($keywords['ch']) {
+            $ret[] = $keywords['ch'];
+            $keywords['cv'] = false; // prevent re-use: center = center center
         }
+        elseif (count($measures))   $ret[] = array_shift($measures);
 
         if     ($keywords['v'])     $ret[] = $keywords['v'];
+        elseif ($keywords['cv'])    $ret[] = $keywords['cv'];
         elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c'])     $ret[] = $keywords['c'];
 
         if (empty($ret)) return false;
         return implode(' ', $ret);

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -34,37 +34,10 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 $quote = $font[0];
                 if ($font[$length - 1] !== $quote) continue;
                 $font = substr($font, 1, $length - 2);
-
-                $new_font = '';
-                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
-                    if ($font[$i] === '\\') {
-                        $i++;
-                        if ($i >= $c) {
-                            $new_font .= '\\';
-                            break;
-                        }
-                        if (ctype_xdigit($font[$i])) {
-                            $code = $font[$i];
-                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
-                                if (!ctype_xdigit($font[$i])) break;
-                                $code .= $font[$i];
-                            }
-                            // We have to be extremely careful when adding
-                            // new characters, to make sure we're not breaking
-                            // the encoding.
-                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
-                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
-                            $new_font .= $char;
-                            if ($i < $c && trim($font[$i]) !== '') $i--;
-                            continue;
-                        }
-                        if ($font[$i] === "\n") continue;
-                    }
-                    $new_font .= $font[$i];
-                }
-
-                $font = $new_font;
             }
+
+            $font = $this->expandCSSEscape($font);
+
             // $font is a pure representation of the font name
 
             if (ctype_alnum($font) && $font !== '') {
@@ -73,12 +46,21 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 continue;
             }
 
-            // complicated font, requires quoting
+            // bugger out on whitespace.  form feed (0C) really
+            // shouldn't show up regardless
+            $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
 
-            // armor single quotes and new lines
-            $font = str_replace("\\", "\\\\", $font);
-            $font = str_replace("'", "\\'", $font);
-            $final .= "'$font', ";
+            // These ugly transforms don't pose a security
+            // risk (as \\ and \" might).  We could try to be clever and
+            // use single-quote wrapping when there is a double quote
+            // present, but I have choosen not to implement that.
+            // (warning: this code relies on the selection of quotation
+            // mark below)
+            $font = str_replace('\\', '\\5C ', $font);
+            $font = str_replace('"',  '\\22 ', $font);
+
+            // complicated font, requires quoting
+            $final .= "\"$font\", "; // note that this will later get turned into &quot;
         }
         $final = rtrim($final, ', ');
         if ($final === '') return false;

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -34,20 +34,16 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
             $uri = substr($uri, 1, $new_length - 1);
         }
 
-        $keys   = array(  '(',   ')',   ',',   ' ',   '"',   "'");
-        $values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
-        $uri = str_replace($values, $keys, $uri);
+        $uri = $this->expandCSSEscape($uri);
 
         $result = parent::validate($uri, $config, $context);
 
         if ($result === false) return false;
 
-        // escape necessary characters according to CSS spec
-        // except for the comma, none of these should appear in the
-        // URI at all
-        $result = str_replace($keys, $values, $result);
+        // extra sanity check; should have been done by URI
+        $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
 
-        return "url('$result')";
+        return "url(\"$result\")";
 
     }
 

library/HTMLPurifier/AttrTransform/SafeParam.php

@@ -33,6 +33,13 @@ class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform
             case 'allowNetworking':
                 $attr['value'] = 'internal';
                 break;
+            case 'allowFullScreen':
+                if ($config->get('HTML.FlashAllowFullScreen')) {
+                    $attr['value'] = ($attr['value'] == 'true') ? 'true' : 'false';
+                } else {
+                    $attr['value'] = 'false';
+                }
+                break;
             case 'wmode':
                 $attr['value'] = 'window';
                 break;

library/HTMLPurifier/CSSDefinition.php

@@ -272,20 +272,29 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         // setup allowed elements
         $support = "(for information on implementing this, see the ".
                    "support forums) ";
-        $allowed_attributes = $config->get('CSS.AllowedProperties');
-        if ($allowed_attributes !== null) {
+        $allowed_properties = $config->get('CSS.AllowedProperties');
+        if ($allowed_properties !== null) {
             foreach ($this->info as $name => $d) {
-                if(!isset($allowed_attributes[$name])) unset($this->info[$name]);
-                unset($allowed_attributes[$name]);
+                if(!isset($allowed_properties[$name])) unset($this->info[$name]);
+                unset($allowed_properties[$name]);
             }
             // emit errors
-            foreach ($allowed_attributes as $name => $d) {
+            foreach ($allowed_properties as $name => $d) {
                 // :TODO: Is this htmlspecialchars() call really necessary?
                 $name = htmlspecialchars($name);
                 trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING);
             }
         }
 
+        $forbidden_properties = $config->get('CSS.ForbiddenProperties');
+        if ($forbidden_properties !== null) {
+            foreach ($this->info as $name => $d) {
+                if (isset($forbidden_properties[$name])) {
+                    unset($this->info[$name]);
+                }
+            }
+        }
+
     }
 }
 

library/HTMLPurifier/Config.php

@@ -20,7 +20,7 @@ class HTMLPurifier_Config
     /**
      * HTML Purifier's version
      */
-    public $version = '4.1.0';
+    public $version = '4.2.0';
 
     /**
      * Bool indicator whether or not to automatically finalize

library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt

@@ -0,0 +1,13 @@
+CSS.ForbiddenProperties
+TYPE: lookup
+VERSION: 4.2.0
+DEFAULT: array()
+--DESCRIPTION--
+<p>
+    This is the logical inverse of %CSS.AllowedProperties, and it will
+    override that directive or any other directive.  If possible,
+    %CSS.AllowedProperties is recommended over this directive,
+    because it can sometimes be difficult to tell whether or not you've
+    forbidden all of the CSS properties you truly would like to disallow.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt

@@ -0,0 +1,11 @@
+Core.NormalizeNewlines
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: true
+--DESCRIPTION--
+<p>
+    Whether or not to normalize newlines to the operating
+    system default.  When <code>false</code>, HTML Purifier
+    will attempt to preserve mixed newline files.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt

@@ -0,0 +1,11 @@
+Core.RemoveProcessingInstructions
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+Instead of escaping processing instructions in the form <code>&lt;? ...
+?&gt;</code>, remove it out-right.  This may be useful if the HTML
+you are validating contains XML processing instruction gunk, however,
+it can also be user-unfriendly for people attempting to post PHP
+snippets.
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt

@@ -3,6 +3,11 @@ TYPE: bool
 VERSION: 3.1.0
 DEFAULT: false
 --DESCRIPTION--
+<p>
+  <strong>Warning:</strong> Deprecated in favor of %HTML.SafeObject and
+  %Output.FlashCompat (turn both on to allow YouTube videos and other
+  Flash content).
+</p>
 <p>
   This directive enables YouTube video embedding in HTML Purifier. Check
   <a href="http://htmlpurifier.org/docs/enduser-youtube.html">this document

library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt

@@ -5,11 +5,14 @@ DEFAULT: NULL
 --DESCRIPTION--
 
 <p>
-    This is a convenience directive that rolls the functionality of
-    %HTML.AllowedElements and %HTML.AllowedAttributes into one directive.
+    This is a preferred convenience directive that combines
+    %HTML.AllowedElements and %HTML.AllowedAttributes.
     Specify elements and attributes that are allowed using:
-    <code>element1[attr1|attr2],element2...</code>. You can also use
-    newlines instead of commas to separate elements.
+    <code>element1[attr1|attr2],element2...</code>.  For example,
+    if you would like to only allow paragraphs and links, specify
+    <code>a[href],p</code>.  You can specify attributes that apply
+    to all elements using an asterisk, e.g. <code>*[lang]</code>.
+    You can also use newlines instead of commas to separate elements.
 </p>
 <p>
     <strong>Warning</strong>:

library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt

@@ -4,12 +4,17 @@ VERSION: 1.3.0
 DEFAULT: NULL
 --DESCRIPTION--
 <p>
-    If HTML Purifier's tag set is unsatisfactory for your needs, you
-    can overload it with your own list of tags to allow.  Note that this
-    method is subtractive: it does its job by taking away from HTML Purifier
-    usual feature set, so you cannot add a tag that HTML Purifier never
-    supported in the first place (like embed, form or head).  If you
-    change this, you probably also want to change %HTML.AllowedAttributes.
+    If HTML Purifier's tag set is unsatisfactory for your needs, you can
+    overload it with your own list of tags to allow.  If you change
+    this, you probably also want to change %HTML.AllowedAttributes; see
+    also %HTML.Allowed which lets you set allowed elements and
+    attributes at the same time.
+</p>
+<p>
+    If you attempt to allow an element that HTML Purifier does not know
+    about, HTML Purifier will raise an error.  You will need to manually
+    tell HTML Purifier about this element by using the
+    <a href="http://htmlpurifier.org/docs/enduser-customize.html">advanced customization features.</a>
 </p>
 <p>
     <strong>Warning:</strong> If another directive conflicts with the

library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt

@@ -0,0 +1,11 @@
+HTML.FlashAllowFullScreen
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+    Whether or not to permit embedded Flash content from
+    %HTML.SafeObject to expand to the full screen.  Corresponds to
+    the <code>allowFullScreen</code> parameter.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt

@@ -12,6 +12,6 @@ array (
 --DESCRIPTION--
 Whitelist that defines the schemes that a URI is allowed to have.  This
 prevents XSS attacks from using pseudo-schemes like javascript or mocha.
-There is also support for the <code>data</code> URI scheme, but it is not
-enabled by default.
+There is also support for the <code>data</code> and <code>file</code>
+URI schemes, but they are not enabled by default.
 --# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt

@@ -1,12 +1,15 @@
 URI.DisableResources
 TYPE: bool
-VERSION: 1.3.0
+VERSION: 4.2.0
 DEFAULT: false
 --DESCRIPTION--
-
 <p>
     Disables embedding resources, essentially meaning no pictures. You can
     still link to them though. See %URI.DisableExternalResources for why
     this might be a good idea.
 </p>
+<p>
+    <em>Note:</em> While this directive has been available since 1.3.0,
+    it didn't actually start doing anything until 4.2.0.
+</p>
 --# vim: et sw=4 sts=4

library/HTMLPurifier/Generator.php

@@ -98,9 +98,11 @@ class HTMLPurifier_Generator
         }
 
         // Normalize newlines to system defined value
-        $nl = $this->config->get('Output.Newline');
-        if ($nl === null) $nl = PHP_EOL;
-        if ($nl !== "\n") $html = str_replace("\n", $nl, $html);
+        if ($this->config->get('Core.NormalizeNewlines')) {
+            $nl = $this->config->get('Output.Newline');
+            if ($nl === null) $nl = PHP_EOL;
+            if ($nl !== "\n") $html = str_replace("\n", $nl, $html);
+        }
         return $html;
     }
 
@@ -215,7 +217,10 @@ class HTMLPurifier_Generator
      *               permissible for non-attribute output.
      * @return String escaped data.
      */
-    public function escape($string, $quote = ENT_COMPAT) {
+    public function escape($string, $quote = null) {
+        // Workaround for APC bug on Mac Leopard reported by sidepodcast
+        // http://htmlpurifier.org/phorum/read.php?3,4823,4846
+        if ($quote === null) $quote = ENT_COMPAT;
         return htmlspecialchars($string, $quote, 'UTF-8');
     }
 

library/HTMLPurifier/HTMLDefinition.php

@@ -300,7 +300,12 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
                             unset($allowed_attributes_mutable[$key]);
                         }
                     }
-                    if ($delete) unset($this->info[$tag]->attr[$attr]);
+                    if ($delete) {
+                        if ($this->info[$tag]->attr[$attr]->required) {
+                            trigger_error("Required attribute '$attr' in element '$tag' was not allowed, which means '$tag' will not be allowed either", E_USER_WARNING);
+                        }
+                        unset($this->info[$tag]->attr[$attr]);
+                    }
                 }
             }
             // emit errors

library/HTMLPurifier/Injector/SafeObject.php

@@ -22,6 +22,7 @@ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector
         'movie' => true,
         'flashvars' => true,
         'src' => true,
+        'allowFullScreen' => true, // if omitted, assume to be 'false'
     );
 
     public function prepare($config, $context) {

library/HTMLPurifier/Language/messages/en.php

@@ -23,6 +23,7 @@ $messages = array(
 'Lexer: Missing gt'            => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped',
 'Lexer: Missing attribute key' => 'Attribute declaration has no key',
 'Lexer: Missing end quote'     => 'Attribute declaration has no end quote',
+'Lexer: Extracted body'        => 'Removed document metadata tags',
 
 'Strategy_RemoveForeignElements: Tag transform'              => '<$1> element transformed into $CurrentToken.Serialized',
 'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1',

library/HTMLPurifier/Lexer.php

@@ -230,6 +230,17 @@ class HTMLPurifier_Lexer
         );
     }
 
+    /**
+     * Special Internet Explorer conditional comments should be removed.
+     */
+    protected static function removeIEConditional($string) {
+        return preg_replace(
+            '#<!--\[if [^>]+\]>.*<!\[endif\]-->#si', // probably should generalize for all strings
+            '',
+            $string
+        );
+    }
+
     /**
      * Callback function for escapeCDATA() that does the work.
      *
@@ -252,20 +263,32 @@ class HTMLPurifier_Lexer
     public function normalize($html, $config, $context) {
 
         // normalize newlines to \n
-        $html = str_replace("\r\n", "\n", $html);
-        $html = str_replace("\r", "\n", $html);
+        if ($config->get('Core.NormalizeNewlines')) {
+            $html = str_replace("\r\n", "\n", $html);
+            $html = str_replace("\r", "\n", $html);
+        }
 
         if ($config->get('HTML.Trusted')) {
             // escape convoluted CDATA
             $html = $this->escapeCommentedCDATA($html);
         }
 
+        $html = $this->removeIEConditional($html);
+
         // escape CDATA
         $html = $this->escapeCDATA($html);
 
         // extract body from document if applicable
         if ($config->get('Core.ConvertDocumentToFragment')) {
-            $html = $this->extractBody($html);
+            $e = false;
+            if ($config->get('Core.CollectErrors')) {
+                $e =& $context->get('ErrorCollector');
+            }
+            $new_html = $this->extractBody($html);
+            if ($e && $new_html != $html) {
+                $e->send(E_WARNING, 'Lexer: Extracted body');
+            }
+            $html = $new_html;
         }
 
         // expand entities that aren't the big five
@@ -276,6 +299,11 @@ class HTMLPurifier_Lexer
         // represent non-SGML characters (horror, horror!)
         $html = HTMLPurifier_Encoder::cleanUTF8($html);
 
+        // if processing instructions are to removed, remove them now
+        if ($config->get('Core.RemoveProcessingInstructions')) {
+            $html = preg_replace('#<\?.+?\?>#s', '', $html);
+        }
+
         return $html;
     }
 

library/HTMLPurifier/Lexer/DirectLex.php

@@ -384,7 +384,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 }
             }
             if ($value === false) $value = '';
-            return array($key => $value);
+            return array($key => $this->parseData($value));
         }
 
         // setup loop environment

library/HTMLPurifier/Lexer/PH5P.php

@@ -125,8 +125,6 @@ class HTML5 {
     const EOF      = 5;
 
     public function __construct($data) {
-        $data = str_replace("\r\n", "\n", $data);
-        $data = str_replace("\r", null, $data);
 
         $this->data = $data;
         $this->char = -1;

library/HTMLPurifier/Strategy/MakeWellFormed.php

@@ -165,6 +165,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             $token = $tokens[$t];
 
             //echo '<br>'; printTokens($tokens, $t); printTokens($this->stack);
+            //flush();
 
             // quick-check: if it's not a tag, no need to process
             if (empty($token->is_tag)) {
@@ -221,11 +222,14 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                     }
 
                     if ($autoclose && $definition->info[$token->name]->wrap) {
-                        // check if this is actually a wrap (mmm wraps!)
+                        // Check if an element can be wrapped by another 
+                        // element to make it valid in a context (for 
+                        // example, <ul><ul> needs a <li> in between)
                         $wrapname = $definition->info[$token->name]->wrap;
                         $wrapdef = $definition->info[$wrapname];
                         $elements = $wrapdef->child->getAllowedElements($config);
-                        if (isset($elements[$token->name])) {
+                        $parent_elements = $definition->info[$parent->name]->child->getAllowedElements($config);
+                        if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) {
                             $newtoken = new HTMLPurifier_Token_Start($wrapname);
                             $this->insertBefore($newtoken);
                             $reprocess = true;

library/HTMLPurifier/URIFilter/DisableResources.php

@@ -0,0 +1,11 @@
+<?php
+
+class HTMLPurifier_URIFilter_DisableResources extends HTMLPurifier_URIFilter
+{
+    public $name = 'DisableResources';
+    public function filter(&$uri, $config, $context) {
+        return !$context->get('EmbeddedURI', true);
+    }
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/URIScheme/file.php

@@ -0,0 +1,26 @@
+<?php
+
+/**
+ * Validates file as defined by RFC 1630 and RFC 1738.
+ */
+class HTMLPurifier_URIScheme_file extends HTMLPurifier_URIScheme {
+
+    // Generally file:// URLs are not accessible from most
+    // machines, so placing them as an img src is incorrect.
+    public $browsable = false;
+
+    public function validate(&$uri, $config, $context) {
+        parent::validate($uri, $config, $context);
+        // Authentication method is not supported
+        $uri->userinfo = null;
+        // file:// makes no provisions for accessing the resource
+        $uri->port     = null;
+        // While it seems to work on Firefox, the querystring has
+        // no possible effect and is thus stripped.
+        $uri->query    = null;
+        return true;
+    }
+
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/VarParser/Flexible.php

@@ -62,7 +62,7 @@ class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser
                         foreach ($var as $keypair) {
                             $c = explode(':', $keypair, 2);
                             if (!isset($c[1])) continue;
-                            $nvar[$c[0]] = $c[1];
+                            $nvar[trim($c[0])] = trim($c[1]);
                         }
                         $var = $nvar;
                     }
@@ -79,8 +79,15 @@ class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser
                         return $new;
                     } else break;
                 }
+                if ($type === self::ALIST) {
+                    trigger_error("Array list did not have consecutive integer indexes", E_USER_WARNING);
+                    return array_values($var);
+                }
                 if ($type === self::LOOKUP) {
                     foreach ($var as $key => $value) {
+                        if ($value !== true) {
+                            trigger_error("Lookup array has non-true value at key '$key'; maybe your input array was not indexed numerically", E_USER_WARNING);
+                        }
                         $var[$key] = true;
                     }
                 }

maintenance/flush.php

@@ -18,8 +18,7 @@ function e($cmd) {
     if ($status) exit($status);
 }
 
-$php = $_SERVER['argv'][1];
-if (!$php) $php = 'php';
+$php = empty($_SERVER['argv'][1]) ? 'php' : $_SERVER['argv'][1];
 
 e($php . ' generate-includes.php');
 e($php . ' generate-schema-cache.php');

maintenance/generate-includes.php

@@ -80,8 +80,9 @@ function get_dependency_lookup($file) {
         if (strncmp('class', $line, 5) === 0) {
             // The implementation here is fragile and will break if we attempt
             // to use interfaces. Beware!
-            list(, $parent) = explode(' extends ', trim($line, ' {'."\n\r"), 2);
-            if (empty($parent)) break;
+            $arr = explode(' extends ', trim($line, ' {'."\n\r"), 2);
+            if (count($arr) < 2) break;
+            $parent = $arr[1];
             $dep_file = HTMLPurifier_Bootstrap::getPath($parent);
             if (!$dep_file) break;
             $deps[$dep_file] = true;

tests/HTMLPurifier/AttrDef/CSS/BackgroundPositionTest.php

@@ -28,13 +28,13 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPositionTest extends HTMLPurifier_AttrD
 
         // reordered due to internal impl details
         $this->assertDef('top left', 'left top');
-        $this->assertDef('top center', 'center top');
+        $this->assertDef('top center', 'top');
         $this->assertDef('top right', 'right top');
-        $this->assertDef('center left', 'left center');
-        $this->assertDef('center center', 'center'); // two centers collide
-        $this->assertDef('center right', 'right center');
+        $this->assertDef('center left', 'left');
+        $this->assertDef('center center', 'center');
+        $this->assertDef('center right', 'right');
         $this->assertDef('bottom left', 'left bottom');
-        $this->assertDef('bottom center', 'center bottom');
+        $this->assertDef('bottom center', 'bottom');
         $this->assertDef('bottom right', 'right bottom');
 
         // more cases from the defined syntax

tests/HTMLPurifier/AttrDef/CSS/BackgroundTest.php

@@ -8,12 +8,12 @@ class HTMLPurifier_AttrDef_CSS_BackgroundTest extends HTMLPurifier_AttrDefHarnes
         $config = HTMLPurifier_Config::createDefault();
         $this->def = new HTMLPurifier_AttrDef_CSS_Background($config);
 
-        $valid = '#333 url(\'chess.png\') repeat fixed 50% top';
+        $valid = '#333 url("chess.png") repeat fixed 50% top';
         $this->assertDef($valid);
-        $this->assertDef('url("chess.png") #333 50% top repeat fixed', $valid);
+        $this->assertDef('url(\'chess.png\') #333 50% top repeat fixed', $valid);
         $this->assertDef(
             'rgb(34, 56, 33) url(chess.png) repeat fixed top',
-            'rgb(34,56,33) url(\'chess.png\') repeat fixed top'
+            'rgb(34,56,33) url("chess.png") repeat fixed top'
         );
 
     }

tests/HTMLPurifier/AttrDef/CSS/FontFamilyTest.php

@@ -8,29 +8,29 @@ class HTMLPurifier_AttrDef_CSS_FontFamilyTest extends HTMLPurifier_AttrDefHarnes
         $this->def = new HTMLPurifier_AttrDef_CSS_FontFamily();
 
         $this->assertDef('Gill, Helvetica, sans-serif');
-        $this->assertDef('\'Times New Roman\', serif');
-        $this->assertDef('"Times New Roman"', "'Times New Roman'");
+        $this->assertDef('"Times New Roman", serif');
+        $this->assertDef('\'Times New Roman\'', '"Times New Roman"');
         $this->assertDef('01234');
         $this->assertDef(',', false);
-        $this->assertDef('Times New Roman, serif', '\'Times New Roman\', serif');
-        $this->assertDef($d = "'John\\'s Font'");
+        $this->assertDef('Times New Roman, serif', '"Times New Roman", serif');
+        $this->assertDef($d = '"John\'s Font"');
         $this->assertDef("John's Font", $d);
-        $this->assertDef($d = "'\xE5\xAE\x8B\xE4\xBD\x93'");
+        $this->assertDef($d = "\"\xE5\xAE\x8B\xE4\xBD\x93\"");
         $this->assertDef("\xE5\xAE\x8B\xE4\xBD\x93", $d);
-        $this->assertDef("'\\','f'", "'\\\\', f");
-        $this->assertDef("'\\01'", "''");
-        $this->assertDef("'\\20'", "' '");
-        $this->assertDef("\\0020", "'\\\\0020'");
+        $this->assertDef("'\\','f'", "\"\\5C \", f");
+        $this->assertDef("'\\01'", "\"\"");
+        $this->assertDef("'\\20'", "\" \"");
+        $this->assertDef("\\0020", "\" \"");
         $this->assertDef("'\\000045'", "E");
         $this->assertDef("','", false);
-        $this->assertDef("',' foobar','", "' foobar'");
-        $this->assertDef("'\\27'", "'\''");
-        $this->assertDef('"\\22"', "'\"'");
-        $this->assertDef('"\\""', "'\"'");
-        $this->assertDef('"\'"', "'\\''");
+        $this->assertDef("',' foobar','", "\" foobar\"");
+        $this->assertDef("'\\27'", "\"'\"");
+        $this->assertDef('"\\22"', "\"\\22 \"");
+        $this->assertDef('"\\""', "\"\\22 \"");
+        $this->assertDef('"\'"', "\"'\"");
         $this->assertDef("'\\000045a'", "Ea");
         $this->assertDef("'\\00045 a'", "Ea");
-        $this->assertDef("'\\00045  a'", "'E a'");
+        $this->assertDef("'\\00045  a'", "\"E a\"");
         $this->assertDef("'\\\nf'", "f");
     }
 

tests/HTMLPurifier/AttrDef/CSS/FontTest.php

@@ -11,10 +11,10 @@ class HTMLPurifier_AttrDef_CSS_FontTest extends HTMLPurifier_AttrDefHarness
         // hodgepodge of usage cases from W3C spec, but " -> '
         $this->assertDef('12px/14px sans-serif');
         $this->assertDef('80% sans-serif');
-        $this->assertDef('x-large/110% \'New Century Schoolbook\', serif');
+        $this->assertDef('x-large/110% "New Century Schoolbook", serif');
         $this->assertDef('bold italic large Palatino, serif');
         $this->assertDef('normal small-caps 120%/120% fantasy');
-        $this->assertDef('300 italic 1.3em/1.7em \'FB Armada\', sans-serif');
+        $this->assertDef('300 italic 1.3em/1.7em "FB Armada", sans-serif');
         $this->assertDef('600 9px Charcoal');
         $this->assertDef('600 9px/ 12px Charcoal', '600 9px/12px Charcoal');
 

tests/HTMLPurifier/AttrDef/CSS/ListStyleTest.php

@@ -13,14 +13,14 @@ class HTMLPurifier_AttrDef_CSS_ListStyleTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('circle outside');
         $this->assertDef('inside');
         $this->assertDef('none');
-        $this->assertDef('url(\'foo.gif\')');
-        $this->assertDef('circle url(\'foo.gif\') inside');
+        $this->assertDef('url("foo.gif")');
+        $this->assertDef('circle url("foo.gif") inside');
 
         // invalid values
         $this->assertDef('outside inside', 'outside');
 
         // ordering
-        $this->assertDef('url(foo.gif) none', 'none url(\'foo.gif\')');
+        $this->assertDef('url(foo.gif) none', 'none url("foo.gif")');
         $this->assertDef('circle lower-alpha', 'circle');
         // the spec is ambiguous about what happens in these
         // cases, so we're going off the W3C CSS validator

tests/HTMLPurifier/AttrDef/CSS/URITest.php

@@ -12,20 +12,16 @@ class HTMLPurifier_AttrDef_CSS_URITest extends HTMLPurifier_AttrDefHarness
         // we could be nice but we won't be
         $this->assertDef('http://www.example.com/', false);
 
-        // no quotes are used, since that's the most widely supported
-        // syntax
         $this->assertDef('url(', false);
-        $this->assertDef('url(\'\')', true);
-        $result = "url('http://www.example.com/')";
+        $this->assertDef('url("")', true);
+        $result = 'url("http://www.example.com/")';
         $this->assertDef('url(http://www.example.com/)', $result);
         $this->assertDef('url("http://www.example.com/")', $result);
         $this->assertDef("url('http://www.example.com/')", $result);
         $this->assertDef(
             '  url(  "http://www.example.com/" )   ', $result);
-
-        // escaping
         $this->assertDef("url(http://www.example.com/foo,bar\))",
-            "url('http://www.example.com/foo\,bar\)')");
+            'url("http://www.example.com/foo,bar)")');
     }
 
 }

tests/HTMLPurifier/AttrDef/CSSTest.php

@@ -25,7 +25,7 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('text-transform:capitalize;');
         $this->assertDef('background-color:rgb(0,0,255);');
         $this->assertDef('background-color:transparent;');
-        $this->assertDef('background:#333 url(\'chess.png\') repeat fixed 50% top;');
+        $this->assertDef('background:#333 url("chess.png") repeat fixed 50% top;');
         $this->assertDef('color:#F00;');
         $this->assertDef('border-top-color:#F00;');
         $this->assertDef('border-color:#F00 #FF0;');
@@ -62,7 +62,7 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('width:-50px;', false);
         $this->assertDef('text-decoration:underline;');
         $this->assertDef('font-family:sans-serif;');
-        $this->assertDef('font-family:Gill, \'Times New Roman\', sans-serif;');
+        $this->assertDef('font-family:Gill, "Times New Roman", sans-serif;');
         $this->assertDef('font:12px serif;');
         $this->assertDef('border:1px solid #000;');
         $this->assertDef('border-bottom:2em double #FF00FA;');
@@ -73,9 +73,9 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('vertical-align:12px;');
         $this->assertDef('vertical-align:50%;');
         $this->assertDef('table-layout:fixed;');
-        $this->assertDef('list-style-image:url(\'nice.jpg\');');
-        $this->assertDef('list-style:disc url(\'nice.jpg\') inside;');
-        $this->assertDef('background-image:url(\'foo.jpg\');');
+        $this->assertDef('list-style-image:url("nice.jpg");');
+        $this->assertDef('list-style:disc url("nice.jpg") inside;');
+        $this->assertDef('background-image:url("foo.jpg");');
         $this->assertDef('background-image:none;');
         $this->assertDef('background-repeat:repeat-y;');
         $this->assertDef('background-attachment:fixed;');
@@ -144,6 +144,12 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('overflow:scroll;');
     }
 
+    function testForbidden() {
+        $this->config->set('CSS.ForbiddenProperties', 'float');
+        $this->assertDef('float:left;', false);
+        $this->assertDef('text-align:right;');
+    }
+
 }
 
 // vim: et sw=4 sts=4

tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php

@@ -81,7 +81,7 @@ class HTMLPurifier_Filter_ExtractStyleBlocksTest extends HTMLPurifier_Harness
     function test_cleanCSS_angledBrackets() {
         $this->assertCleanCSS(
             ".class {\nfont-family:'</style>';\n}",
-            ".class {\nfont-family:'\\3C /style\\3E ';\n}"
+            ".class {\nfont-family:\"\\3C /style\\3E \";\n}"
         );
     }
 
@@ -99,14 +99,14 @@ class HTMLPurifier_Filter_ExtractStyleBlocksTest extends HTMLPurifier_Harness
 
     function test_cleanCSS_escapeCodes() {
         $this->assertCleanCSS(
-            ".class {\nfont-family:'\\3C /style\\3E ';\n}"
+            ".class {\nfont-family:\"\\3C /style\\3E \";\n}"
         );
     }
 
     function test_cleanCSS_noEscapeCodes() {
         $this->config->set('Filter.ExtractStyleBlocks.Escaping', false);
         $this->assertCleanCSS(
-            ".class {\nfont-family:'</style>';\n}"
+            ".class {\nfont-family:\"</style>\";\n}"
         );
     }
 

tests/HTMLPurifier/HTMLDefinitionTest.php

@@ -122,17 +122,20 @@ a[href|title]
     }
 
     function test_AllowedAttributes_global_preferredSyntax() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'style');
         $this->assertPurification_AllowedAttributes_global_style();
     }
 
     function test_AllowedAttributes_global_verboseSyntax() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', '*@style');
         $this->assertPurification_AllowedAttributes_global_style();
     }
 
     function test_AllowedAttributes_global_discouragedSyntax() {
         // Emit errors eventually
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', '*.style');
         $this->assertPurification_AllowedAttributes_global_style();
     }
@@ -144,16 +147,19 @@ a[href|title]
     }
 
     function test_AllowedAttributes_local_preferredSyntax() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p@style');
         $this->assertPurification_AllowedAttributes_local_p_style();
     }
 
     function test_AllowedAttributes_local_discouragedSyntax() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p.style');
         $this->assertPurification_AllowedAttributes_local_p_style();
     }
 
     function test_AllowedAttributes_multiple() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p@style,br@class,title');
         $this->assertPurification(
             '<p style="font-weight:bold;" class="foo" title="foo">Jelly</p><br style="clear:both;" class="foo" title="foo" />',
@@ -162,29 +168,34 @@ a[href|title]
     }
 
     function test_AllowedAttributes_local_invalidAttribute() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', array('p@style', 'p@<foo>'));
         $this->expectError(new PatternExpectation("/Attribute '&lt;foo&gt;' in element 'p' not supported/"));
         $this->assertPurification_AllowedAttributes_local_p_style();
     }
 
     function test_AllowedAttributes_global_invalidAttribute() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', array('style', '<foo>'));
         $this->expectError(new PatternExpectation("/Global attribute '&lt;foo&gt;' is not supported in any elements/"));
         $this->assertPurification_AllowedAttributes_global_style();
     }
 
     function test_AllowedAttributes_local_invalidAttributeDueToMissingElement() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p.style,foo.style');
         $this->expectError(new PatternExpectation("/Cannot allow attribute 'style' if element 'foo' is not allowed\/supported/"));
         $this->assertPurification_AllowedAttributes_local_p_style();
     }
 
     function test_AllowedAttributes_duplicate() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p.style,p@style');
         $this->assertPurification_AllowedAttributes_local_p_style();
     }
 
     function test_AllowedAttributes_multipleErrors() {
+        $this->config->set('HTML.AllowedElements', array('p', 'br'));
         $this->config->set('HTML.AllowedAttributes', 'p.style,foo.style,<foo>');
         $this->expectError(new PatternExpectation("/Cannot allow attribute 'style' if element 'foo' is not allowed\/supported/"));
         $this->expectError(new PatternExpectation("/Global attribute '&lt;foo&gt;' is not supported in any elements/"));
@@ -347,6 +358,12 @@ a[href|title]
         );
     }
 
+    function test_notAllowedRequiredAttributeError() {
+        $this->expectError("Required attribute 'src' in element 'img' was not allowed, which means 'img' will not be allowed either");
+        $this->config->set('HTML.Allowed', 'img[alt]');
+        $this->config->getHTMLDefinition();
+    }
+
 }
 
 // vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLModule/SafeObjectTest.php

@@ -6,8 +6,7 @@ class HTMLPurifier_HTMLModule_SafeObjectTest extends HTMLPurifier_HTMLModuleHarn
     function setUp() {
         parent::setUp();
         $this->config->set('HTML.DefinitionID', 'HTMLPurifier_HTMLModule_SafeObjectTest');
-        $def = $this->config->getHTMLDefinition(true);
-        $def->manager->addModule('SafeObject');
+        $this->config->set('HTML.SafeObject', true);
     }
 
     function testMinimal() {
@@ -38,6 +37,13 @@ class HTMLPurifier_HTMLModule_SafeObjectTest extends HTMLPurifier_HTMLModuleHarn
         );
     }
 
+    function testFullScreen() {
+        $this->config->set('HTML.FlashAllowFullScreen', true);
+        $this->assertResult(
+            '<b><object width="425" height="344" type="application/x-shockwave-flash" data="Foobar"><param name="allowScriptAccess" value="never" /><param name="allowNetworking" value="internal" /><param name="flashvars" value="foobarbaz=bally" /><param name="movie" value="http://www.youtube.com/v/RVtEQxH7PWA&amp;hl=en" /><param name="wmode" value="window" /><param name="allowFullScreen" value="true" /></object></b>'
+        );
+    }
+
 }
 
 // vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/double-youtube.htmlt

@@ -0,0 +1,6 @@
+--INI--
+HTML.SafeObject = true
+Output.FlashCompat = true
+--HTML--
+<object width="425" height="350" data="http://www.youtube.com/v/BdU--T8rLns" type="application/x-shockwave-flash"><param name="allowScriptAccess" value="never" /><param name="allowNetworking" value="internal" /><param name="movie" value="http://www.youtube.com/v/BdU--T8rLns" /><param name="wmode" value="window" /><!--[if IE]><embed width="425" height="350" src="http://www.youtube.com/v/BdU--T8rLns" allowScriptAccess="never" allowNetworking="internal" wmode="window" /><![endif]--></object>
+--# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/file-uri.htmlt

@@ -0,0 +1,5 @@
+--INI--
+URI.AllowedSchemes = file
+--HTML--
+<a href="file:///foo">foo</a>
+--# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/inline-list-loop.htmlt

@@ -0,0 +1,5 @@
+--HTML--
+<i><ul></ul></i>
+--EXPECT--
+<i></i><i></i>
+--# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/munge-extra.htmlt

@@ -7,5 +7,5 @@ URI.MungeResources = true
 <img src="http://example.com" style="background-image:url(http://example.com);" alt="example.com" />
 --EXPECT--
 <a href="/redirect?s=http%3A%2F%2Fexample.com&amp;t=c15354f3953dfec262c55b1403067e0d045a3059&amp;r=&amp;n=a&amp;m=href&amp;p=">Link</a>
-<img src="/redirect?s=http%3A%2F%2Fexample.com&amp;t=c15354f3953dfec262c55b1403067e0d045a3059&amp;r=1&amp;n=img&amp;m=src&amp;p=" style="background-image:url('/redirect?s=http%3A%2F%2Fexample.com&amp;t=c15354f3953dfec262c55b1403067e0d045a3059&amp;r=1&amp;n=img&amp;m=style&amp;p=background-image');" alt="example.com" />
+<img src="/redirect?s=http%3A%2F%2Fexample.com&amp;t=c15354f3953dfec262c55b1403067e0d045a3059&amp;r=1&amp;n=img&amp;m=src&amp;p=" style="background-image:url(&quot;/redirect?s=http%3A%2F%2Fexample.com&amp;t=c15354f3953dfec262c55b1403067e0d045a3059&amp;r=1&amp;n=img&amp;m=style&amp;p=background-image&quot;);" alt="example.com" />
 --# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/shift-jis-preserve-yen.htmlt

@@ -4,5 +4,5 @@ if (!function_exists('iconv')) return true;
 Core.Encoding = "Shift_JIS"
 Core.EscapeNonASCIICharacters = true
 --HTML--
-<b style="font-family:'&#165;';">111</b>
+<b style="font-family:&quot;&#165;&quot;;">111</b>
 --# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/shift-jis-remove-yen.htmlt

@@ -3,7 +3,7 @@ if (!function_exists('iconv')) return true;
 --INI--
 Core.Encoding = Shift_JIS
 --HTML--
-<b style="font-family:'&#165;';">111</b>
+<b style="font-family:&quot;&#165;&quot;;">111</b>
 --EXPECT--
-<b style="font-family:'';">111</b>
+<b style="font-family:&quot;&quot;;">111</b>
 --# vim: et sw=4 sts=4

tests/HTMLPurifier/HTMLT/tidy-background.htmlt

@@ -1,5 +1,5 @@
 --HTML--
 <table background="logo.png"><tr><td>asdf</td></tr></table>
 --EXPECT--
-<table style="background-image:url('logo.png');"><tr><td>asdf</td></tr></table>
+<table style="background-image:url(&quot;logo.png&quot;);"><tr><td>asdf</td></tr></table>
 --# vim: et sw=4 sts=4

tests/HTMLPurifier/Lexer/DirectLex_ErrorsTest.php

@@ -13,6 +13,11 @@ class HTMLPurifier_Lexer_DirectLex_ErrorsTest extends HTMLPurifier_ErrorsHarness
         $lexer->parseAttributeString($input, $this->config, $this->context);
     }
 
+    function testExtractBody() {
+        $this->expectErrorCollection(E_WARNING, 'Lexer: Extracted body');
+        $this->invoke('<body>foo</body>');
+    }
+
     function testUnclosedComment() {
         $this->expectErrorCollection(E_WARNING, 'Lexer: Unclosed comment');
         $this->expectContext('CurrentLine', 1);

tests/HTMLPurifier/LexerTest.php

@@ -262,6 +262,15 @@ class HTMLPurifier_LexerTest extends HTMLPurifier_Harness
         );
     }
 
+    function test_tokenizeHTML_singleAttribute() {
+        $this->assertTokenization(
+            '<br style="&amp;" />',
+            array(
+                new HTMLPurifier_Token_Empty('br', array('style' => '&'))
+            )
+        );
+    }
+
     function test_tokenizeHTML_emptyTag() {
         $this->assertTokenization(
             '<br />',
@@ -701,6 +710,39 @@ div {}
         );
     }
 
+    function test_tokenizeHTML_ignoreIECondComment() {
+        $this->assertTokenization(
+            '<!--[if IE]>foo<a>bar<!-- baz --><![endif]-->',
+            array()
+        );
+    }
+
+    function test_tokenizeHTML_removeProcessingInstruction() {
+        $this->config->set('Core.RemoveProcessingInstructions', true);
+        $this->assertTokenization(
+            '<?xml blah blah ?>',
+            array()
+        );
+    }
+
+   function test_tokenizeHTML_removeNewline() {
+        $this->config->set('Core.NormalizeNewlines', true);
+        $input = "plain\rtext\r\n";
+        $expect = array(
+            new HTMLPurifier_Token_Text("plain\ntext\n")
+        );
+   }
+
+   function test_tokenizeHTML_noRemoveNewline() {
+        $this->config->set('Core.NormalizeNewlines', false);
+        $input = "plain\rtext\r\n";
+        $expect = array(
+            new HTMLPurifier_Token_Text("plain\rtext\r\n")
+        );
+        $this->assertTokenization($input, $expect);
+     }
+
+
     /*
 
     function test_tokenizeHTML_() {

tests/HTMLPurifier/Strategy/MakeWellFormedTest.php

@@ -118,8 +118,8 @@ class HTMLPurifier_Strategy_MakeWellFormedTest extends HTMLPurifier_StrategyHarn
 
     function testNestedOl() {
         $this->assertResult(
-            '<ol><ol></ol></ol>',
-            '<ol><li><ol></ol></li></ol>'
+            '<ol><ol><li>foo</li></ol></ol>',
+            '<ol><li><ol><li>foo</li></ol></li></ol>'
         );
     }
 

tests/HTMLPurifier/URIFilter/DisableResourcesTest.php

@@ -0,0 +1,24 @@
+<?php
+
+class HTMLPurifier_URIFilter_DisableResourcesTest extends HTMLPurifier_URIFilterHarness
+{
+
+    function setUp() {
+        parent::setUp();
+        $this->filter = new HTMLPurifier_URIFilter_DisableResources();
+        $var = true;
+        $this->context->register('EmbeddedURI', $var);
+    }
+
+    function testRemoveResource() {
+        $this->assertFiltering('/foo/bar', false);
+    }
+
+    function testPreserveRegular() {
+        $this->context->destroy('EmbeddedURI'); // undo setUp
+        $this->assertFiltering('/foo/bar');
+    }
+
+}
+
+// vim: et sw=4 sts=4

tests/HTMLPurifier/URISchemeTest.php

@@ -165,6 +165,13 @@ class HTMLPurifier_URISchemeTest extends HTMLPurifier_URIHarness
         );
     }
 
+    function test_file_basic() {
+        $this->assertValidation(
+            'file://user@MYCOMPUTER:12/foo/bar?baz#frag',
+            'file://MYCOMPUTER/foo/bar#frag'
+        );
+    }
+
 }
 
 // vim: et sw=4 sts=4

tests/index.php

@@ -1,4 +1,3 @@
-#!/usr/bin/php
 <?php
 
 /** @file
@@ -24,6 +23,16 @@
  *          $test_files) do not have underscores in their names.
  */
 
+// HTML Purifier runs error free on E_STRICT, so if code reports
+// errors, we want to know about it.
+error_reporting(E_ALL | E_STRICT);
+
+// Because we always want to know about errors, and because SimpleTest
+// will notify us about them, logging the errors to stderr is
+// counterproductive and in fact the wrong thing when a test case 
+// exercises an error condition to detect for it.
+ini_set('log_errors', false);
+
 define('HTMLPurifierTest', 1);
 define('HTMLPURIFIER_SCHEMA_STRICT', true); // validate schemas
 chdir(dirname(__FILE__));