From 24663d65ed9eeb30ac5c678ae55d2e55e6616267 Mon Sep 17 00:00:00 2001
From: "Edward Z. Yang" <edwardzyang@thewritingpot.com>
Date: Sun, 24 Sep 2006 21:23:54 +0000
Subject: [PATCH] [1.1.1] To make up for DOMLex's tendency to drop tags, we've
 added a configuration option to let Tidy cleanup the HTML afterwards. Good
 for hand-editors. Also, Tidy is a smart solution for pretty-printed HTML, so
 we're marking the related TODO wontfix.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@454 48356398-32a2-884e-a903-53898d9a118a
---
 TODO                                 |  2 +-
 docs/examples/demo.php               |  6 ++++-
 library/HTMLPurifier/Generator.php   | 37 ++++++++++++++++++++++++++++
 tests/HTMLPurifier/GeneratorTest.php | 22 +++++++++++++++++
 4 files changed, 65 insertions(+), 2 deletions(-)

diff --git a/TODO b/TODO
index aad4c467..79c32c89 100644
--- a/TODO
+++ b/TODO
@@ -43,9 +43,9 @@ Unknown release (on a scratch-an-itch basis)
  - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
  - Automatically add non-breaking spaces to empty table cells when
    empty-cells:show is applied to have compatibility with Internet Explorer
- - Pretty-printing HTML (adds dependency of Generator to HTMLDefinition)
  - Non-lossy dumb alternate character encoding transformations, achieved by
    numerically encoding all non-ASCII characters
 
 Wontfix
  - Non-lossy smart alternate character encoding transformations
+ - Pretty-printing HTML, users can use Tidy on the output on entire page
diff --git a/docs/examples/demo.php b/docs/examples/demo.php
index 07630078..35a47986 100644
--- a/docs/examples/demo.php
+++ b/docs/examples/demo.php
@@ -21,7 +21,9 @@ if (!empty($_POST['html'])) {
     
     $html = get_magic_quotes_gpc() ? stripslashes($_POST['html']) : $_POST['html'];
     
-    $purifier = new HTMLPurifier();
+    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Core', 'TidyFormat', !empty($_POST['tidy']));
+    $purifier = new HTMLPurifier($config);
     $pure_html = $purifier->purify($html);
     
 ?>
@@ -65,6 +67,8 @@ if (isset($html)) {
             HTMLPurifier_Encoder::cleanUTF8($html), ENT_COMPAT, 'UTF-8');
 }
         ?></textarea>
+        <div>Nicely format output with Tidy? <input type="checkbox" value="1"
+        name="tidy"<?php if (!empty($_POST['tidy'])) echo ' checked="checked"'; ?> /></div>
         <div>
             <input type="submit" value="Submit" name="submit" class="button" />
         </div>
diff --git a/library/HTMLPurifier/Generator.php b/library/HTMLPurifier/Generator.php
index 613ea965..7adfa81a 100644
--- a/library/HTMLPurifier/Generator.php
+++ b/library/HTMLPurifier/Generator.php
@@ -23,6 +23,19 @@ HTMLPurifier_ConfigSchema::define(
     'This directive was available since 1.1.'
 );
 
+// extension constraints could be factored into ConfigSchema
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'TidyFormat', false, 'bool',
+    'Determines whether or not to run Tidy on the final output for pretty '.
+    'formatting reasons, such as indentation and wrap.  This can greatly '.
+    'improve readability for editors who are hand-editing the HTML, but is '.
+    'by no means necessary as HTML Purifier has already fixed all major '.
+    'errors the HTML may have had and could potentially result in data loss '.
+    'due to bugs in Tidy. Tidy is a non-default extension, and this directive '.
+    'will silently fail if Tidy is not available. This '.
+    'directive was available since 1.1.1.'
+);
+
 /**
  * Generates HTML from tokens.
  */
@@ -56,6 +69,30 @@ class HTMLPurifier_Generator
         foreach ($tokens as $token) {
             $html .= $this->generateFromToken($token);
         }
+        if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
+            
+            $tidy_options = array(
+               'indent'=> true,
+               'output-xhtml' => $this->_xhtml,
+               'show-body-only' => true,
+               'indent-spaces' => 2,
+               'wrap' => 68,
+            );
+            if (version_compare(PHP_VERSION, '5', '<')) {
+                tidy_set_encoding('utf8');
+                foreach ($tidy_options as $key => $value) {
+                    tidy_setopt($key, $value);
+                }
+                tidy_parse_string($html);
+                tidy_clean_repair();
+                $html = tidy_get_output();
+            } else {
+                $tidy = new Tidy;
+                $tidy->parseString($html, $tidy_options, 'utf8');
+                $tidy->cleanRepair();
+                $html = (string) $tidy;
+            }
+        }
         return $html;
     }
     
diff --git a/tests/HTMLPurifier/GeneratorTest.php b/tests/HTMLPurifier/GeneratorTest.php
index 6b85a9ca..a6ca4043 100644
--- a/tests/HTMLPurifier/GeneratorTest.php
+++ b/tests/HTMLPurifier/GeneratorTest.php
@@ -123,6 +123,9 @@ class HTMLPurifier_GeneratorTest extends UnitTestCase
     var $config;
     function assertGeneration($tokens, $expect) {
         $result = $this->gen->generateFromTokens($tokens, $this->config);
+        // normalized newlines, this probably should be put somewhere else
+        $result = str_replace("\r\n", "\n", $result);
+        $result = str_replace("\r", "\n", $result);
         $this->assertEqual($expect, $result);
     }
     
@@ -148,6 +151,25 @@ class HTMLPurifier_GeneratorTest extends UnitTestCase
         
     }
     
+    function test_generateFromTokens_TidyFormat() {
+        // abort test if tidy isn't loaded
+        if (!extension_loaded('tidy')) return;
+        
+        $this->config = HTMLPurifier_Config::createDefault();
+        $this->config->set('Core', 'TidyFormat', true);
+        
+        // nice wrapping please
+        $this->assertGeneration(
+            array(
+                new HTMLPurifier_Token_Start('div'),
+                new HTMLPurifier_Token_Text('Text'),
+                new HTMLPurifier_Token_End('div')
+            ),
+            "<div>\n  Text\n</div>\n"
+        );
+        
+    }
+    
 }
 
 ?>
\ No newline at end of file