diff --git a/library/HTMLPurifier.php b/library/HTMLPurifier.php
index c758b439..3bd32887 100644
--- a/library/HTMLPurifier.php
+++ b/library/HTMLPurifier.php
@@ -91,7 +91,6 @@ class HTMLPurifier
$this->lexer = HTMLPurifier_Lexer::create();
$this->strategy = new HTMLPurifier_Strategy_Core();
$this->generator = new HTMLPurifier_Generator();
- $this->encoder = new HTMLPurifier_Encoder();
}
@@ -110,7 +109,7 @@ class HTMLPurifier
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
$context = new HTMLPurifier_Context();
- $html = $this->encoder->convertToUTF8($html, $config, $context);
+ $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
// purified HTML
$html =
@@ -127,7 +126,7 @@ class HTMLPurifier
$config, $context
);
- $html = $this->encoder->convertFromUTF8($html, $config, $context);
+ $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
$this->context =& $context;
return $html;
}
diff --git a/library/HTMLPurifier/Encoder.php b/library/HTMLPurifier/Encoder.php
index d9cc655c..b818e199 100644
--- a/library/HTMLPurifier/Encoder.php
+++ b/library/HTMLPurifier/Encoder.php
@@ -38,10 +38,18 @@ HTMLPurifier_ConfigSchema::define(
/**
* A UTF-8 specific character encoder that handles cleaning and transforming.
+ * @note All functions in this class should be static.
*/
class HTMLPurifier_Encoder
{
+ /**
+ * Constructor throws fatal error if you attempt to instantiate class
+ */
+ function HTMLPurifier_Encoder() {
+ trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
+ }
+
/**
* Cleans a UTF-8 string for well-formedness and SGML validity
*
@@ -290,6 +298,7 @@ class HTMLPurifier_Encoder
/**
* Converts a string to UTF-8 based on configuration.
+ * @static
*/
function convertToUTF8($str, $config, &$context) {
static $iconv = null;
@@ -305,6 +314,7 @@ class HTMLPurifier_Encoder
/**
* Converts a string from UTF-8 based on configuration.
+ * @static
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
diff --git a/library/HTMLPurifier/Lexer.php b/library/HTMLPurifier/Lexer.php
index 122bbb5d..29e92b66 100644
--- a/library/HTMLPurifier/Lexer.php
+++ b/library/HTMLPurifier/Lexer.php
@@ -56,7 +56,6 @@ class HTMLPurifier_Lexer
{
function HTMLPurifier_Lexer() {
- $this->_encoder = new HTMLPurifier_Encoder();
$this->_entity_parser = new HTMLPurifier_EntityParser();
}
@@ -114,8 +113,6 @@ class HTMLPurifier_Lexer
return $string;
}
- var $_encoder;
-
/**
* Lexes an HTML string into tokens.
*
@@ -216,7 +213,7 @@ class HTMLPurifier_Lexer
// clean into wellformed UTF-8 string for an SGML context: this has
// to be done after entity expansion because the entities sometimes
// represent non-SGML characters (horror, horror!)
- $html = $this->_encoder->cleanUTF8($html);
+ $html = HTMLPurifier_Encoder::cleanUTF8($html);
return $html;
}
diff --git a/tests/HTMLPurifier/EncoderTest.php b/tests/HTMLPurifier/EncoderTest.php
index 2e0eae8d..b8437fb2 100644
--- a/tests/HTMLPurifier/EncoderTest.php
+++ b/tests/HTMLPurifier/EncoderTest.php
@@ -8,14 +8,13 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
var $Encoder;
function setUp() {
- $this->Encoder = new HTMLPurifier_Encoder();
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
}
function assertCleanUTF8($string, $expect = null) {
if ($expect === null) $expect = $string;
- $this->assertIdentical($this->Encoder->cleanUTF8($string), $expect, 'iconv: %s');
- $this->assertIdentical($this->Encoder->cleanUTF8($string, true), $expect, 'PHP: %s');
+ $this->assertIdentical(HTMLPurifier_Encoder::cleanUTF8($string), $expect, 'iconv: %s');
+ $this->assertIdentical(HTMLPurifier_Encoder::cleanUTF8($string, true), $expect, 'PHP: %s');
}
function test_cleanUTF8() {
@@ -35,7 +34,7 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
// UTF-8 means that we don't touch it
$this->assertIdentical(
- $this->Encoder->convertToUTF8("\xF6", $config, $context),
+ HTMLPurifier_Encoder::convertToUTF8("\xF6", $config, $context),
"\xF6" // this is invalid
);
$this->assertNoErrors();
@@ -44,14 +43,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
// Now it gets converted
$this->assertIdentical(
- $this->Encoder->convertToUTF8("\xF6", $config, $context),
+ HTMLPurifier_Encoder::convertToUTF8("\xF6", $config, $context),
"\xC3\xB6"
);
$config->set('Test', 'ForceNoIconv', true);
$this->assertIdentical(
- $this->Encoder->convertToUTF8("\xF6", $config, $context),
+ HTMLPurifier_Encoder::convertToUTF8("\xF6", $config, $context),
"\xC3\xB6"
);
@@ -63,7 +62,7 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
// UTF-8 means that we don't touch it
$this->assertIdentical(
- $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+ HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $config, $context),
"\xC3\xB6"
);
@@ -71,14 +70,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
// Now it gets converted
$this->assertIdentical(
- $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+ HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $config, $context),
"\xF6"
);
$config->set('Test', 'ForceNoIconv', true);
$this->assertIdentical(
- $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+ HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $config, $context),
"\xF6"
);