to
- foreach ($definition->info[$token->name]->attr_transform_pre as $transform) { - $attr = $transform->transform($o = $attr, $config, $context); - if ($e) { - if ($attr != $o) { - $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); - } - } - } - - // create alias to this element's attribute definition array, see - // also $d_defs (global attribute definition array) - // DEFINITION CALL - $defs = $definition->info[$token->name]->attr; - - $attr_key = false; - $context->register('CurrentAttr', $attr_key); - - // iterate through all the attribute keypairs - // Watch out for name collisions: $key has previously been used - foreach ($attr as $attr_key => $value) { - - // call the definition - if (isset($defs[$attr_key])) { - // there is a local definition defined - if ($defs[$attr_key] === false) { - // We've explicitly been told not to allow this element. - // This is usually when there's a global definition - // that must be overridden. - // Theoretically speaking, we could have a - // AttrDef_DenyAll, but this is faster! - $result = false; - } else { - // validate according to the element's definition - $result = $defs[$attr_key]->validate( - $value, - $config, - $context - ); - } - } elseif (isset($d_defs[$attr_key])) { - // there is a global definition defined, validate according - // to the global definition - $result = $d_defs[$attr_key]->validate( - $value, - $config, - $context - ); - } else { - // system never heard of the attribute? DELETE! - $result = false; - } - - // put the results into effect - if ($result === false || $result === null) { - // this is a generic error message that should replaced - // with more specific ones when possible - if ($e) { - $e->send(E_ERROR, 'AttrValidator: Attribute removed'); - } - - // remove the attribute - unset($attr[$attr_key]); - } elseif (is_string($result)) { - // generally, if a substitution is happening, there - // was some sort of implicit correction going on. We'll - // delegate it to the attribute classes to say exactly what. - - // simple substitution - $attr[$attr_key] = $result; - } else { - // nothing happens - } - - // we'd also want slightly more complicated substitution - // involving an array as the return value, - // although we're not sure how colliding attributes would - // resolve (certain ones would be completely overriden, - // others would prepend themselves). - } - - $context->destroy('CurrentAttr'); - - // post transforms - - // global (error reporting untested) - foreach ($definition->info_attr_transform_post as $transform) { - $attr = $transform->transform($o = $attr, $config, $context); - if ($e) { - if ($attr != $o) { - $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); - } - } - } - - // local (error reporting untested) - foreach ($definition->info[$token->name]->attr_transform_post as $transform) { - $attr = $transform->transform($o = $attr, $config, $context); - if ($e) { - if ($attr != $o) { - $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); - } - } - } - - $token->attr = $attr; - - // destroy CurrentToken if we made it ourselves - if (!$current_token) { - $context->destroy('CurrentToken'); - } - - } - - -} - -// vim: et sw=4 sts=4 +getHTMLDefinition(); + $e =& $context->get('ErrorCollector', true); + + // initialize IDAccumulator if necessary + $ok =& $context->get('IDAccumulator', true); + if (!$ok) { + $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context); + $context->register('IDAccumulator', $id_accumulator); + } + + // initialize CurrentToken if necessary + $current_token =& $context->get('CurrentToken', true); + if (!$current_token) { + $context->register('CurrentToken', $token); + } + + if (!$token instanceof HTMLPurifier_Token_Start && + !$token instanceof HTMLPurifier_Token_Empty + ) { + return; + } + + // create alias to global definition array, see also $defs + // DEFINITION CALL + $d_defs = $definition->info_global_attr; + + // don't update token until the very end, to ensure an atomic update + $attr = $token->attr; + + // do global transformations (pre) + // nothing currently utilizes this + foreach ($definition->info_attr_transform_pre as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // do local transformations only applicable to this element (pre) + // ex.
to
+ foreach ($definition->info[$token->name]->attr_transform_pre as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // create alias to this element's attribute definition array, see + // also $d_defs (global attribute definition array) + // DEFINITION CALL + $defs = $definition->info[$token->name]->attr; + + $attr_key = false; + $context->register('CurrentAttr', $attr_key); + + // iterate through all the attribute keypairs + // Watch out for name collisions: $key has previously been used + foreach ($attr as $attr_key => $value) { + + // call the definition + if (isset($defs[$attr_key])) { + // there is a local definition defined + if ($defs[$attr_key] === false) { + // We've explicitly been told not to allow this element. + // This is usually when there's a global definition + // that must be overridden. + // Theoretically speaking, we could have a + // AttrDef_DenyAll, but this is faster! + $result = false; + } else { + // validate according to the element's definition + $result = $defs[$attr_key]->validate( + $value, + $config, + $context + ); + } + } elseif (isset($d_defs[$attr_key])) { + // there is a global definition defined, validate according + // to the global definition + $result = $d_defs[$attr_key]->validate( + $value, + $config, + $context + ); + } else { + // system never heard of the attribute? DELETE! + $result = false; + } + + // put the results into effect + if ($result === false || $result === null) { + // this is a generic error message that should replaced + // with more specific ones when possible + if ($e) { + $e->send(E_ERROR, 'AttrValidator: Attribute removed'); + } + + // remove the attribute + unset($attr[$attr_key]); + } elseif (is_string($result)) { + // generally, if a substitution is happening, there + // was some sort of implicit correction going on. We'll + // delegate it to the attribute classes to say exactly what. + + // simple substitution + $attr[$attr_key] = $result; + } else { + // nothing happens + } + + // we'd also want slightly more complicated substitution + // involving an array as the return value, + // although we're not sure how colliding attributes would + // resolve (certain ones would be completely overriden, + // others would prepend themselves). + } + + $context->destroy('CurrentAttr'); + + // post transforms + + // global (error reporting untested) + foreach ($definition->info_attr_transform_post as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + // local (error reporting untested) + foreach ($definition->info[$token->name]->attr_transform_post as $transform) { + $attr = $transform->transform($o = $attr, $config, $context); + if ($e) { + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } + } + } + + $token->attr = $attr; + + // destroy CurrentToken if we made it ourselves + if (!$current_token) { + $context->destroy('CurrentToken'); + } + + } + + +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Bootstrap.php b/lib/htmlpurifier/HTMLPurifier/Bootstrap.php index 707122bb296..0ab0e341e78 100644 --- a/lib/htmlpurifier/HTMLPurifier/Bootstrap.php +++ b/lib/htmlpurifier/HTMLPurifier/Bootstrap.php @@ -1,124 +1,124 @@ - -if (!defined('PHP_EOL')) { - switch (strtoupper(substr(PHP_OS, 0, 3))) { - case 'WIN': - define('PHP_EOL', "\r\n"); - break; - case 'DAR': - define('PHP_EOL', "\r"); - break; - default: - define('PHP_EOL', "\n"); - } -} - -/** - * Bootstrap class that contains meta-functionality for HTML Purifier such as - * the autoload function. - * - * @note - * This class may be used without any other files from HTML Purifier. - */ -class HTMLPurifier_Bootstrap -{ - - /** - * Autoload function for HTML Purifier - * @param string $class Class to load - * @return bool - */ - public static function autoload($class) - { - $file = HTMLPurifier_Bootstrap::getPath($class); - if (!$file) { - return false; - } - // Technically speaking, it should be ok and more efficient to - // just do 'require', but Antonio Parraga reports that with - // Zend extensions such as Zend debugger and APC, this invariant - // may be broken. Since we have efficient alternatives, pay - // the cost here and avoid the bug. - require_once HTMLPURIFIER_PREFIX . '/' . $file; - return true; - } - - /** - * Returns the path for a specific class. - * @param string $class Class path to get - * @return string - */ - public static function getPath($class) - { - if (strncmp('HTMLPurifier', $class, 12) !== 0) { - return false; - } - // Custom implementations - if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) { - $code = str_replace('_', '-', substr($class, 22)); - $file = 'HTMLPurifier/Language/classes/' . $code . '.php'; - } else { - $file = str_replace('_', '/', $class) . '.php'; - } - if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) { - return false; - } - return $file; - } - - /** - * "Pre-registers" our autoloader on the SPL stack. - */ - public static function registerAutoload() - { - $autoload = array('HTMLPurifier_Bootstrap', 'autoload'); - if (($funcs = spl_autoload_functions()) === false) { - spl_autoload_register($autoload); - } elseif (function_exists('spl_autoload_unregister')) { - if (version_compare(PHP_VERSION, '5.3.0', '>=')) { - // prepend flag exists, no need for shenanigans - spl_autoload_register($autoload, true, true); - } else { - $buggy = version_compare(PHP_VERSION, '5.2.11', '<'); - $compat = version_compare(PHP_VERSION, '5.1.2', '<=') && - version_compare(PHP_VERSION, '5.1.0', '>='); - foreach ($funcs as $func) { - if ($buggy && is_array($func)) { - // :TRICKY: There are some compatibility issues and some - // places where we need to error out - $reflector = new ReflectionMethod($func[0], $func[1]); - if (!$reflector->isStatic()) { - throw new Exception( - 'HTML Purifier autoloader registrar is not compatible - with non-static object methods due to PHP Bug #44144; - Please do not use HTMLPurifier.autoload.php (or any - file that includes this file); instead, place the code: - spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\')) - after your own autoloaders.' - ); - } - // Suprisingly, spl_autoload_register supports the - // Class::staticMethod callback format, although call_user_func doesn't - if ($compat) { - $func = implode('::', $func); - } - } - spl_autoload_unregister($func); - } - spl_autoload_register($autoload); - foreach ($funcs as $func) { - spl_autoload_register($func); - } - } - } - } -} - -// vim: et sw=4 sts=4 + +if (!defined('PHP_EOL')) { + switch (strtoupper(substr(PHP_OS, 0, 3))) { + case 'WIN': + define('PHP_EOL', "\r\n"); + break; + case 'DAR': + define('PHP_EOL', "\r"); + break; + default: + define('PHP_EOL', "\n"); + } +} + +/** + * Bootstrap class that contains meta-functionality for HTML Purifier such as + * the autoload function. + * + * @note + * This class may be used without any other files from HTML Purifier. + */ +class HTMLPurifier_Bootstrap +{ + + /** + * Autoload function for HTML Purifier + * @param string $class Class to load + * @return bool + */ + public static function autoload($class) + { + $file = HTMLPurifier_Bootstrap::getPath($class); + if (!$file) { + return false; + } + // Technically speaking, it should be ok and more efficient to + // just do 'require', but Antonio Parraga reports that with + // Zend extensions such as Zend debugger and APC, this invariant + // may be broken. Since we have efficient alternatives, pay + // the cost here and avoid the bug. + require_once HTMLPURIFIER_PREFIX . '/' . $file; + return true; + } + + /** + * Returns the path for a specific class. + * @param string $class Class path to get + * @return string + */ + public static function getPath($class) + { + if (strncmp('HTMLPurifier', $class, 12) !== 0) { + return false; + } + // Custom implementations + if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) { + $code = str_replace('_', '-', substr($class, 22)); + $file = 'HTMLPurifier/Language/classes/' . $code . '.php'; + } else { + $file = str_replace('_', '/', $class) . '.php'; + } + if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) { + return false; + } + return $file; + } + + /** + * "Pre-registers" our autoloader on the SPL stack. + */ + public static function registerAutoload() + { + $autoload = array('HTMLPurifier_Bootstrap', 'autoload'); + if (($funcs = spl_autoload_functions()) === false) { + spl_autoload_register($autoload); + } elseif (function_exists('spl_autoload_unregister')) { + if (version_compare(PHP_VERSION, '5.3.0', '>=')) { + // prepend flag exists, no need for shenanigans + spl_autoload_register($autoload, true, true); + } else { + $buggy = version_compare(PHP_VERSION, '5.2.11', '<'); + $compat = version_compare(PHP_VERSION, '5.1.2', '<=') && + version_compare(PHP_VERSION, '5.1.0', '>='); + foreach ($funcs as $func) { + if ($buggy && is_array($func)) { + // :TRICKY: There are some compatibility issues and some + // places where we need to error out + $reflector = new ReflectionMethod($func[0], $func[1]); + if (!$reflector->isStatic()) { + throw new Exception( + 'HTML Purifier autoloader registrar is not compatible + with non-static object methods due to PHP Bug #44144; + Please do not use HTMLPurifier.autoload.php (or any + file that includes this file); instead, place the code: + spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\')) + after your own autoloaders.' + ); + } + // Suprisingly, spl_autoload_register supports the + // Class::staticMethod callback format, although call_user_func doesn't + if ($compat) { + $func = implode('::', $func); + } + } + spl_autoload_unregister($func); + } + spl_autoload_register($autoload); + foreach ($funcs as $func) { + spl_autoload_register($func); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/CSSDefinition.php b/lib/htmlpurifier/HTMLPurifier/CSSDefinition.php index 47dfd1f6660..5e7490eb2d6 100644 --- a/lib/htmlpurifier/HTMLPurifier/CSSDefinition.php +++ b/lib/htmlpurifier/HTMLPurifier/CSSDefinition.php @@ -1,491 +1,491 @@ -info['text-align'] = new HTMLPurifier_AttrDef_Enum( - array('left', 'right', 'center', 'justify'), - false - ); - - $border_style = - $this->info['border-bottom-style'] = - $this->info['border-right-style'] = - $this->info['border-left-style'] = - $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum( - array( - 'none', - 'hidden', - 'dotted', - 'dashed', - 'solid', - 'double', - 'groove', - 'ridge', - 'inset', - 'outset' - ), - false - ); - - $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style); - - $this->info['clear'] = new HTMLPurifier_AttrDef_Enum( - array('none', 'left', 'right', 'both'), - false - ); - $this->info['float'] = new HTMLPurifier_AttrDef_Enum( - array('none', 'left', 'right'), - false - ); - $this->info['font-style'] = new HTMLPurifier_AttrDef_Enum( - array('normal', 'italic', 'oblique'), - false - ); - $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum( - array('normal', 'small-caps'), - false - ); - - $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('none')), - new HTMLPurifier_AttrDef_CSS_URI() - ) - ); - - $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum( - array('inside', 'outside'), - false - ); - $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum( - array( - 'disc', - 'circle', - 'square', - 'decimal', - 'lower-roman', - 'upper-roman', - 'lower-alpha', - 'upper-alpha', - 'none' - ), - false - ); - $this->info['list-style-image'] = $uri_or_none; - - $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config); - - $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum( - array('capitalize', 'uppercase', 'lowercase', 'none'), - false - ); - $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color(); - - $this->info['background-image'] = $uri_or_none; - $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum( - array('repeat', 'repeat-x', 'repeat-y', 'no-repeat') - ); - $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum( - array('scroll', 'fixed') - ); - $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition(); - - $border_color = - $this->info['border-top-color'] = - $this->info['border-bottom-color'] = - $this->info['border-left-color'] = - $this->info['border-right-color'] = - $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('transparent')), - new HTMLPurifier_AttrDef_CSS_Color() - ) - ); - - $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config); - - $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color); - - $border_width = - $this->info['border-top-width'] = - $this->info['border-bottom-width'] = - $this->info['border-left-width'] = - $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')), - new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative - ) - ); - - $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width); - - $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Length() - ) - ); - - $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Length() - ) - ); - - $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum( - array( - 'xx-small', - 'x-small', - 'small', - 'medium', - 'large', - 'x-large', - 'xx-large', - 'larger', - 'smaller' - ) - ), - new HTMLPurifier_AttrDef_CSS_Percentage(), - new HTMLPurifier_AttrDef_CSS_Length() - ) - ); - - $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true) - ) - ); - - $margin = - $this->info['margin-top'] = - $this->info['margin-bottom'] = - $this->info['margin-left'] = - $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage(), - new HTMLPurifier_AttrDef_Enum(array('auto')) - ) - ); - - $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin); - - // non-negative - $padding = - $this->info['padding-top'] = - $this->info['padding-bottom'] = - $this->info['padding-left'] = - $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true) - ) - ); - - $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding); - - $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage() - ) - ); - - $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true), - new HTMLPurifier_AttrDef_Enum(array('auto')) - ) - ); - $max = $config->get('CSS.MaxImgLength'); - - $this->info['min-width'] = - $this->info['max-width'] = - $this->info['min-height'] = - $this->info['max-height'] = - $this->info['width'] = - $this->info['height'] = - $max === null ? - $trusted_wh : - new HTMLPurifier_AttrDef_Switch( - 'img', - // For img tags: - new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length('0', $max), - new HTMLPurifier_AttrDef_Enum(array('auto')) - ) - ), - // For everyone else: - $trusted_wh - ); - - $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration(); - - $this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily(); - - // this could use specialized code - $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum( - array( - 'normal', - 'bold', - 'bolder', - 'lighter', - '100', - '200', - '300', - '400', - '500', - '600', - '700', - '800', - '900' - ), - false - ); - - // MUST be called after other font properties, as it references - // a CSSDefinition object - $this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config); - - // same here - $this->info['border'] = - $this->info['border-bottom'] = - $this->info['border-top'] = - $this->info['border-left'] = - $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config); - - $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum( - array('collapse', 'separate') - ); - - $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum( - array('top', 'bottom') - ); - - $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum( - array('auto', 'fixed') - ); - - $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Enum( - array( - 'baseline', - 'sub', - 'super', - 'top', - 'text-top', - 'middle', - 'bottom', - 'text-bottom' - ) - ), - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage() - ) - ); - - $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2); - - // These CSS properties don't work on many browsers, but we live - // in THE FUTURE! - $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum( - array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line') - ); - - if ($config->get('CSS.Proprietary')) { - $this->doSetupProprietary($config); - } - - if ($config->get('CSS.AllowTricky')) { - $this->doSetupTricky($config); - } - - if ($config->get('CSS.Trusted')) { - $this->doSetupTrusted($config); - } - - $allow_important = $config->get('CSS.AllowImportant'); - // wrap all attr-defs with decorator that handles !important - foreach ($this->info as $k => $v) { - $this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important); - } - - $this->setupConfigStuff($config); - } - - /** - * @param HTMLPurifier_Config $config - */ - protected function doSetupProprietary($config) - { - // Internet Explorer only scrollbar colors - $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - - // vendor specific prefixes of opacity - $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); - $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); - - // only opacity, for now - $this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter(); - - // more CSS3 - $this->info['page-break-after'] = - $this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum( - array( - 'auto', - 'always', - 'avoid', - 'left', - 'right' - ) - ); - $this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto', 'avoid')); - - $border_radius = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Percentage(true), // disallow negative - new HTMLPurifier_AttrDef_CSS_Length('0') // disallow negative - )); - - $this->info['border-top-left-radius'] = - $this->info['border-top-right-radius'] = - $this->info['border-bottom-right-radius'] = - $this->info['border-bottom-left-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 2); - // TODO: support SLASH syntax - $this->info['border-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 4); - - } - - /** - * @param HTMLPurifier_Config $config - */ - protected function doSetupTricky($config) - { - $this->info['display'] = new HTMLPurifier_AttrDef_Enum( - array( - 'inline', - 'block', - 'list-item', - 'run-in', - 'compact', - 'marker', - 'table', - 'inline-block', - 'inline-table', - 'table-row-group', - 'table-header-group', - 'table-footer-group', - 'table-row', - 'table-column-group', - 'table-column', - 'table-cell', - 'table-caption', - 'none' - ) - ); - $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum( - array('visible', 'hidden', 'collapse') - ); - $this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll')); - $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); - } - - /** - * @param HTMLPurifier_Config $config - */ - protected function doSetupTrusted($config) - { - $this->info['position'] = new HTMLPurifier_AttrDef_Enum( - array('static', 'relative', 'absolute', 'fixed') - ); - $this->info['top'] = - $this->info['left'] = - $this->info['right'] = - $this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage(), - new HTMLPurifier_AttrDef_Enum(array('auto')), - ) - ); - $this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite( - array( - new HTMLPurifier_AttrDef_Integer(), - new HTMLPurifier_AttrDef_Enum(array('auto')), - ) - ); - } - - /** - * Performs extra config-based processing. Based off of - * HTMLPurifier_HTMLDefinition. - * @param HTMLPurifier_Config $config - * @todo Refactor duplicate elements into common class (probably using - * composition, not inheritance). - */ - protected function setupConfigStuff($config) - { - // setup allowed elements - $support = "(for information on implementing this, see the " . - "support forums) "; - $allowed_properties = $config->get('CSS.AllowedProperties'); - if ($allowed_properties !== null) { - foreach ($this->info as $name => $d) { - if (!isset($allowed_properties[$name])) { - unset($this->info[$name]); - } - unset($allowed_properties[$name]); - } - // emit errors - foreach ($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]); - } - } - } - } -} - -// vim: et sw=4 sts=4 +info['text-align'] = new HTMLPurifier_AttrDef_Enum( + array('left', 'right', 'center', 'justify'), + false + ); + + $border_style = + $this->info['border-bottom-style'] = + $this->info['border-right-style'] = + $this->info['border-left-style'] = + $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum( + array( + 'none', + 'hidden', + 'dotted', + 'dashed', + 'solid', + 'double', + 'groove', + 'ridge', + 'inset', + 'outset' + ), + false + ); + + $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style); + + $this->info['clear'] = new HTMLPurifier_AttrDef_Enum( + array('none', 'left', 'right', 'both'), + false + ); + $this->info['float'] = new HTMLPurifier_AttrDef_Enum( + array('none', 'left', 'right'), + false + ); + $this->info['font-style'] = new HTMLPurifier_AttrDef_Enum( + array('normal', 'italic', 'oblique'), + false + ); + $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum( + array('normal', 'small-caps'), + false + ); + + $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('none')), + new HTMLPurifier_AttrDef_CSS_URI() + ) + ); + + $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum( + array('inside', 'outside'), + false + ); + $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum( + array( + 'disc', + 'circle', + 'square', + 'decimal', + 'lower-roman', + 'upper-roman', + 'lower-alpha', + 'upper-alpha', + 'none' + ), + false + ); + $this->info['list-style-image'] = $uri_or_none; + + $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config); + + $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum( + array('capitalize', 'uppercase', 'lowercase', 'none'), + false + ); + $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color(); + + $this->info['background-image'] = $uri_or_none; + $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum( + array('repeat', 'repeat-x', 'repeat-y', 'no-repeat') + ); + $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum( + array('scroll', 'fixed') + ); + $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition(); + + $border_color = + $this->info['border-top-color'] = + $this->info['border-bottom-color'] = + $this->info['border-left-color'] = + $this->info['border-right-color'] = + $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('transparent')), + new HTMLPurifier_AttrDef_CSS_Color() + ) + ); + + $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config); + + $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color); + + $border_width = + $this->info['border-top-width'] = + $this->info['border-bottom-width'] = + $this->info['border-left-width'] = + $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')), + new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative + ) + ); + + $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width); + + $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'xx-small', + 'x-small', + 'small', + 'medium', + 'large', + 'x-large', + 'xx-large', + 'larger', + 'smaller' + ) + ), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); + + $margin = + $this->info['margin-top'] = + $this->info['margin-bottom'] = + $this->info['margin-left'] = + $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ); + + $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin); + + // non-negative + $padding = + $this->info['padding-top'] = + $this->info['padding-bottom'] = + $this->info['padding-left'] = + $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); + + $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding); + + $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); + + $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ); + $max = $config->get('CSS.MaxImgLength'); + + $this->info['min-width'] = + $this->info['max-width'] = + $this->info['min-height'] = + $this->info['max-height'] = + $this->info['width'] = + $this->info['height'] = + $max === null ? + $trusted_wh : + new HTMLPurifier_AttrDef_Switch( + 'img', + // For img tags: + new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0', $max), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ), + // For everyone else: + $trusted_wh + ); + + $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration(); + + $this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily(); + + // this could use specialized code + $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum( + array( + 'normal', + 'bold', + 'bolder', + 'lighter', + '100', + '200', + '300', + '400', + '500', + '600', + '700', + '800', + '900' + ), + false + ); + + // MUST be called after other font properties, as it references + // a CSSDefinition object + $this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config); + + // same here + $this->info['border'] = + $this->info['border-bottom'] = + $this->info['border-top'] = + $this->info['border-left'] = + $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config); + + $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum( + array('collapse', 'separate') + ); + + $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum( + array('top', 'bottom') + ); + + $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum( + array('auto', 'fixed') + ); + + $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'baseline', + 'sub', + 'super', + 'top', + 'text-top', + 'middle', + 'bottom', + 'text-bottom' + ) + ), + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); + + $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2); + + // These CSS properties don't work on many browsers, but we live + // in THE FUTURE! + $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum( + array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line') + ); + + if ($config->get('CSS.Proprietary')) { + $this->doSetupProprietary($config); + } + + if ($config->get('CSS.AllowTricky')) { + $this->doSetupTricky($config); + } + + if ($config->get('CSS.Trusted')) { + $this->doSetupTrusted($config); + } + + $allow_important = $config->get('CSS.AllowImportant'); + // wrap all attr-defs with decorator that handles !important + foreach ($this->info as $k => $v) { + $this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important); + } + + $this->setupConfigStuff($config); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupProprietary($config) + { + // Internet Explorer only scrollbar colors + $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + + // vendor specific prefixes of opacity + $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + + // only opacity, for now + $this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter(); + + // more CSS3 + $this->info['page-break-after'] = + $this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum( + array( + 'auto', + 'always', + 'avoid', + 'left', + 'right' + ) + ); + $this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto', 'avoid')); + + $border_radius = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Percentage(true), // disallow negative + new HTMLPurifier_AttrDef_CSS_Length('0') // disallow negative + )); + + $this->info['border-top-left-radius'] = + $this->info['border-top-right-radius'] = + $this->info['border-bottom-right-radius'] = + $this->info['border-bottom-left-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 2); + // TODO: support SLASH syntax + $this->info['border-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 4); + + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTricky($config) + { + $this->info['display'] = new HTMLPurifier_AttrDef_Enum( + array( + 'inline', + 'block', + 'list-item', + 'run-in', + 'compact', + 'marker', + 'table', + 'inline-block', + 'inline-table', + 'table-row-group', + 'table-header-group', + 'table-footer-group', + 'table-row', + 'table-column-group', + 'table-column', + 'table-cell', + 'table-caption', + 'none' + ) + ); + $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum( + array('visible', 'hidden', 'collapse') + ); + $this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll')); + $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTrusted($config) + { + $this->info['position'] = new HTMLPurifier_AttrDef_Enum( + array('static', 'relative', 'absolute', 'fixed') + ); + $this->info['top'] = + $this->info['left'] = + $this->info['right'] = + $this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + $this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Integer(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + } + + /** + * Performs extra config-based processing. Based off of + * HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_Config $config + * @todo Refactor duplicate elements into common class (probably using + * composition, not inheritance). + */ + protected function setupConfigStuff($config) + { + // setup allowed elements + $support = "(for information on implementing this, see the " . + "support forums) "; + $allowed_properties = $config->get('CSS.AllowedProperties'); + if ($allowed_properties !== null) { + foreach ($this->info as $name => $d) { + if (!isset($allowed_properties[$name])) { + unset($this->info[$name]); + } + unset($allowed_properties[$name]); + } + // emit errors + foreach ($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]); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef.php b/lib/htmlpurifier/HTMLPurifier/ChildDef.php index 8eb17b82e15..5d64cd41a1a 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef.php @@ -1,52 +1,52 @@ -elements; - } - - /** - * Validates nodes according to definition and returns modification. - * - * @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node - * @param HTMLPurifier_Config $config HTMLPurifier_Config object - * @param HTMLPurifier_Context $context HTMLPurifier_Context object - * @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children - */ - abstract public function validateChildren($children, $config, $context); -} - -// vim: et sw=4 sts=4 +elements; + } + + /** + * Validates nodes according to definition and returns modification. + * + * @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node + * @param HTMLPurifier_Config $config HTMLPurifier_Config object + * @param HTMLPurifier_Context $context HTMLPurifier_Context object + * @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children + */ + abstract public function validateChildren($children, $config, $context); +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Chameleon.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Chameleon.php index 7439be26b64..f6b2f22e5ab 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Chameleon.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Chameleon.php @@ -1,67 +1,67 @@ -inline = new HTMLPurifier_ChildDef_Optional($inline); - $this->block = new HTMLPurifier_ChildDef_Optional($block); - $this->elements = $this->block->elements; - } - - /** - * @param HTMLPurifier_Node[] $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return bool - */ - public function validateChildren($children, $config, $context) - { - if ($context->get('IsInline') === false) { - return $this->block->validateChildren( - $children, - $config, - $context - ); - } else { - return $this->inline->validateChildren( - $children, - $config, - $context - ); - } - } -} - -// vim: et sw=4 sts=4 +inline = new HTMLPurifier_ChildDef_Optional($inline); + $this->block = new HTMLPurifier_ChildDef_Optional($block); + $this->elements = $this->block->elements; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + if ($context->get('IsInline') === false) { + return $this->block->validateChildren( + $children, + $config, + $context + ); + } else { + return $this->inline->validateChildren( + $children, + $config, + $context + ); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Custom.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Custom.php index 128132e96d8..1047cd8e8b9 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Custom.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Custom.php @@ -1,102 +1,102 @@ -dtd_regex = $dtd_regex; - $this->_compileRegex(); - } - - /** - * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex) - */ - protected function _compileRegex() - { - $raw = str_replace(' ', '', $this->dtd_regex); - if ($raw{0} != '(') { - $raw = "($raw)"; - } - $el = '[#a-zA-Z0-9_.-]+'; - $reg = $raw; - - // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M - // DOING! Seriously: if there's problems, please report them. - - // collect all elements into the $elements array - preg_match_all("/$el/", $reg, $matches); - foreach ($matches[0] as $match) { - $this->elements[$match] = true; - } - - // setup all elements as parentheticals with leading commas - $reg = preg_replace("/$el/", '(,\\0)', $reg); - - // remove commas when they were not solicited - $reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg); - - // remove all non-paranthetical commas: they are handled by first regex - $reg = preg_replace("/,\(/", '(', $reg); - - $this->_pcre_regex = $reg; - } - - /** - * @param HTMLPurifier_Node[] $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return bool - */ - public function validateChildren($children, $config, $context) - { - $list_of_children = ''; - $nesting = 0; // depth into the nest - foreach ($children as $node) { - if (!empty($node->is_whitespace)) { - continue; - } - $list_of_children .= $node->name . ','; - } - // add leading comma to deal with stray comma declarations - $list_of_children = ',' . rtrim($list_of_children, ','); - $okay = - preg_match( - '/^,?' . $this->_pcre_regex . '$/', - $list_of_children - ); - return (bool)$okay; - } -} - -// vim: et sw=4 sts=4 +dtd_regex = $dtd_regex; + $this->_compileRegex(); + } + + /** + * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex) + */ + protected function _compileRegex() + { + $raw = str_replace(' ', '', $this->dtd_regex); + if ($raw{0} != '(') { + $raw = "($raw)"; + } + $el = '[#a-zA-Z0-9_.-]+'; + $reg = $raw; + + // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M + // DOING! Seriously: if there's problems, please report them. + + // collect all elements into the $elements array + preg_match_all("/$el/", $reg, $matches); + foreach ($matches[0] as $match) { + $this->elements[$match] = true; + } + + // setup all elements as parentheticals with leading commas + $reg = preg_replace("/$el/", '(,\\0)', $reg); + + // remove commas when they were not solicited + $reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg); + + // remove all non-paranthetical commas: they are handled by first regex + $reg = preg_replace("/,\(/", '(', $reg); + + $this->_pcre_regex = $reg; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + $list_of_children = ''; + $nesting = 0; // depth into the nest + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + continue; + } + $list_of_children .= $node->name . ','; + } + // add leading comma to deal with stray comma declarations + $list_of_children = ',' . rtrim($list_of_children, ','); + $okay = + preg_match( + '/^,?' . $this->_pcre_regex . '$/', + $list_of_children + ); + return (bool)$okay; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Empty.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Empty.php index a8a6cbdd2c4..bbcde56e8fe 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Empty.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Empty.php @@ -1,38 +1,38 @@ - true, 'ul' => true, 'ol' => true); - - /** - * @param array $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return array - */ - public function validateChildren($children, $config, $context) - { - // Flag for subclasses - $this->whitespace = false; - - // if there are no tokens, delete parent node - if (empty($children)) { - return false; - } - - // if li is not allowed, delete parent node - if (!isset($config->getHTMLDefinition()->info['li'])) { - trigger_error("Cannot allow ul/ol without allowing li", E_USER_WARNING); - return false; - } - - // the new set of children - $result = array(); - - // a little sanity check to make sure it's not ALL whitespace - $all_whitespace = true; - - $current_li = null; - - foreach ($children as $node) { - if (!empty($node->is_whitespace)) { - $result[] = $node; - continue; - } - $all_whitespace = false; // phew, we're not talking about whitespace - - if ($node->name === 'li') { - // good - $current_li = $node; - $result[] = $node; - } else { - // we want to tuck this into the previous li - // Invariant: we expect the node to be ol/ul - // ToDo: Make this more robust in the case of not ol/ul - // by distinguishing between existing li and li created - // to handle non-list elements; non-list elements should - // not be appended to an existing li; only li created - // for non-list. This distinction is not currently made. - if ($current_li === null) { - $current_li = new HTMLPurifier_Node_Element('li'); - $result[] = $current_li; - } - $current_li->children[] = $node; - $current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo - } - } - if (empty($result)) { - return false; - } - if ($all_whitespace) { - return false; - } - return $result; - } -} - -// vim: et sw=4 sts=4 + true, 'ul' => true, 'ol' => true); + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // if li is not allowed, delete parent node + if (!isset($config->getHTMLDefinition()->info['li'])) { + trigger_error("Cannot allow ul/ol without allowing li", E_USER_WARNING); + return false; + } + + // the new set of children + $result = array(); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $current_li = null; + + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if ($node->name === 'li') { + // good + $current_li = $node; + $result[] = $node; + } else { + // we want to tuck this into the previous li + // Invariant: we expect the node to be ol/ul + // ToDo: Make this more robust in the case of not ol/ul + // by distinguishing between existing li and li created + // to handle non-list elements; non-list elements should + // not be appended to an existing li; only li created + // for non-list. This distinction is not currently made. + if ($current_li === null) { + $current_li = new HTMLPurifier_Node_Element('li'); + $result[] = $current_li; + } + $current_li->children[] = $node; + $current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo + } + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Optional.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Optional.php index b9468063b1a..1db864d907e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Optional.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Optional.php @@ -1,45 +1,45 @@ -whitespace) { - return $children; - } else { - return array(); - } - } - return $result; - } -} - -// vim: et sw=4 sts=4 +whitespace) { + return $children; + } else { + return array(); + } + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Required.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Required.php index 0d1c8f5f397..f6b8e8a2f07 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Required.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Required.php @@ -1,118 +1,118 @@ - $x) { - $elements[$i] = true; - if (empty($i)) { - unset($elements[$i]); - } // remove blank - } - } - $this->elements = $elements; - } - - /** - * @type bool - */ - public $allow_empty = false; - - /** - * @type string - */ - public $type = 'required'; - - /** - * @param array $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return array - */ - public function validateChildren($children, $config, $context) - { - // Flag for subclasses - $this->whitespace = false; - - // if there are no tokens, delete parent node - if (empty($children)) { - return false; - } - - // the new set of children - $result = array(); - - // whether or not parsed character data is allowed - // this controls whether or not we silently drop a tag - // or generate escaped HTML from it - $pcdata_allowed = isset($this->elements['#PCDATA']); - - // a little sanity check to make sure it's not ALL whitespace - $all_whitespace = true; - - $stack = array_reverse($children); - while (!empty($stack)) { - $node = array_pop($stack); - if (!empty($node->is_whitespace)) { - $result[] = $node; - continue; - } - $all_whitespace = false; // phew, we're not talking about whitespace - - if (!isset($this->elements[$node->name])) { - // special case text - // XXX One of these ought to be redundant or something - if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) { - $result[] = $node; - continue; - } - // spill the child contents in - // ToDo: Make configurable - if ($node instanceof HTMLPurifier_Node_Element) { - for ($i = count($node->children) - 1; $i >= 0; $i--) { - $stack[] = $node->children[$i]; - } - continue; - } - continue; - } - $result[] = $node; - } - if (empty($result)) { - return false; - } - if ($all_whitespace) { - $this->whitespace = true; - return false; - } - return $result; - } -} - -// vim: et sw=4 sts=4 + $x) { + $elements[$i] = true; + if (empty($i)) { + unset($elements[$i]); + } // remove blank + } + } + $this->elements = $elements; + } + + /** + * @type bool + */ + public $allow_empty = false; + + /** + * @type string + */ + public $type = 'required'; + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // the new set of children + $result = array(); + + // whether or not parsed character data is allowed + // this controls whether or not we silently drop a tag + // or generate escaped HTML from it + $pcdata_allowed = isset($this->elements['#PCDATA']); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $stack = array_reverse($children); + while (!empty($stack)) { + $node = array_pop($stack); + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if (!isset($this->elements[$node->name])) { + // special case text + // XXX One of these ought to be redundant or something + if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) { + $result[] = $node; + continue; + } + // spill the child contents in + // ToDo: Make configurable + if ($node instanceof HTMLPurifier_Node_Element) { + for ($i = count($node->children) - 1; $i >= 0; $i--) { + $stack[] = $node->children[$i]; + } + continue; + } + continue; + } + $result[] = $node; + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + $this->whitespace = true; + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/StrictBlockquote.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/StrictBlockquote.php index 3270a46e1bf..38bf9533eb5 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/StrictBlockquote.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/StrictBlockquote.php @@ -1,110 +1,110 @@ -init($config); - return $this->fake_elements; - } - - /** - * @param array $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return array - */ - public function validateChildren($children, $config, $context) - { - $this->init($config); - - // trick the parent class into thinking it allows more - $this->elements = $this->fake_elements; - $result = parent::validateChildren($children, $config, $context); - $this->elements = $this->real_elements; - - if ($result === false) { - return array(); - } - if ($result === true) { - $result = $children; - } - - $def = $config->getHTMLDefinition(); - $block_wrap_name = $def->info_block_wrapper; - $block_wrap = false; - $ret = array(); - - foreach ($result as $node) { - if ($block_wrap === false) { - if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) || - ($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) { - $block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper); - $ret[] = $block_wrap; - } - } else { - if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) { - $block_wrap = false; - - } - } - if ($block_wrap) { - $block_wrap->children[] = $node; - } else { - $ret[] = $node; - } - } - return $ret; - } - - /** - * @param HTMLPurifier_Config $config - */ - private function init($config) - { - if (!$this->init) { - $def = $config->getHTMLDefinition(); - // allow all inline elements - $this->real_elements = $this->elements; - $this->fake_elements = $def->info_content_sets['Flow']; - $this->fake_elements['#PCDATA'] = true; - $this->init = true; - } - } -} - -// vim: et sw=4 sts=4 +init($config); + return $this->fake_elements; + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + $this->init($config); + + // trick the parent class into thinking it allows more + $this->elements = $this->fake_elements; + $result = parent::validateChildren($children, $config, $context); + $this->elements = $this->real_elements; + + if ($result === false) { + return array(); + } + if ($result === true) { + $result = $children; + } + + $def = $config->getHTMLDefinition(); + $block_wrap_name = $def->info_block_wrapper; + $block_wrap = false; + $ret = array(); + + foreach ($result as $node) { + if ($block_wrap === false) { + if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) || + ($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) { + $block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper); + $ret[] = $block_wrap; + } + } else { + if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) { + $block_wrap = false; + + } + } + if ($block_wrap) { + $block_wrap->children[] = $node; + } else { + $ret[] = $node; + } + } + return $ret; + } + + /** + * @param HTMLPurifier_Config $config + */ + private function init($config) + { + if (!$this->init) { + $def = $config->getHTMLDefinition(); + // allow all inline elements + $this->real_elements = $this->elements; + $this->fake_elements = $def->info_content_sets['Flow']; + $this->fake_elements['#PCDATA'] = true; + $this->init = true; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ChildDef/Table.php b/lib/htmlpurifier/HTMLPurifier/ChildDef/Table.php index cb6b3e6cdc2..9b12c928039 100644 --- a/lib/htmlpurifier/HTMLPurifier/ChildDef/Table.php +++ b/lib/htmlpurifier/HTMLPurifier/ChildDef/Table.php @@ -1,224 +1,224 @@ - true, - 'tbody' => true, - 'thead' => true, - 'tfoot' => true, - 'caption' => true, - 'colgroup' => true, - 'col' => true - ); - - public function __construct() - { - } - - /** - * @param array $children - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return array - */ - public function validateChildren($children, $config, $context) - { - if (empty($children)) { - return false; - } - - // only one of these elements is allowed in a table - $caption = false; - $thead = false; - $tfoot = false; - - // whitespace - $initial_ws = array(); - $after_caption_ws = array(); - $after_thead_ws = array(); - $after_tfoot_ws = array(); - - // as many of these as you want - $cols = array(); - $content = array(); - - $tbody_mode = false; // if true, then we need to wrap any stray - //
- This directive turns on auto-paragraphing, where double newlines are - converted in to paragraphs whenever possible. Auto-paragraphing: -
--
-
- Always applies to inline elements or text in the root node, -
- Applies to inline elements or text with double newlines in nodes - that allow paragraph tags, -
- Applies to double newlines in paragraph tags -
- p tags must be allowed for this directive to take effect.
- We do not use br tags for paragraphing, as that is
- semantically incorrect.
-
- To prevent auto-paragraphing as a content-producer, refrain from using
- double-newlines except to specify a new paragraph or in contexts where
- it has special meaning (whitespace usually has no meaning except in
- tags like pre, so this should not be difficult.) To prevent
- the paragraphing of inline text adjacent to block elements, wrap them
- in div tags (the behavior is slightly different outside of
- the root node.)
-
+ This directive turns on auto-paragraphing, where double newlines are + converted in to paragraphs whenever possible. Auto-paragraphing: +
+-
+
- Always applies to inline elements or text in the root node, +
- Applies to inline elements or text with double newlines in nodes + that allow paragraph tags, +
- Applies to double newlines in paragraph tags +
+ p tags must be allowed for this directive to take effect.
+ We do not use br tags for paragraphing, as that is
+ semantically incorrect.
+
+ To prevent auto-paragraphing as a content-producer, refrain from using
+ double-newlines except to specify a new paragraph or in contexts where
+ it has special meaning (whitespace usually has no meaning except in
+ tags like pre, so this should not be difficult.) To prevent
+ the paragraphing of inline text adjacent to block elements, wrap them
+ in div tags (the behavior is slightly different outside of
+ the root node.)
+
- This directive can be used to add custom auto-format injectors. - Specify an array of injector names (class name minus the prefix) - or concrete implementations. Injector class must exist. -
---# vim: et sw=4 sts=4 +AutoFormat.Custom +TYPE: list +VERSION: 2.0.1 +DEFAULT: array() +--DESCRIPTION-- + ++ This directive can be used to add custom auto-format injectors. + Specify an array of injector names (class name minus the prefix) + or concrete implementations. Injector class must exist. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt index 663064a3447..c955de7f625 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt @@ -1,11 +1,11 @@ -AutoFormat.DisplayLinkURI -TYPE: bool -VERSION: 3.2.0 -DEFAULT: false ---DESCRIPTION-- -- This directive turns on the in-text display of URIs in <a> tags, and disables - those links. For example, example becomes - example (http://example.com). -
---# vim: et sw=4 sts=4 +AutoFormat.DisplayLinkURI +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- ++ This directive turns on the in-text display of URIs in <a> tags, and disables + those links. For example, example becomes + example (http://example.com). +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt index 3a48ba960e9..328b2b2bfe0 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt @@ -1,12 +1,12 @@ -AutoFormat.Linkify -TYPE: bool -VERSION: 2.0.1 -DEFAULT: false ---DESCRIPTION-- - -
- This directive turns on linkification, auto-linking http, ftp and
- https URLs. a tags with the href attribute
- must be allowed.
-
+ This directive turns on linkification, auto-linking http, ftp and
+ https URLs. a tags with the href attribute
+ must be allowed.
+
- Location of configuration documentation to link to, let %s substitute - into the configuration's namespace and directive names sans the percent - sign. -
---# vim: et sw=4 sts=4 +AutoFormat.PurifierLinkify.DocURL +TYPE: string +VERSION: 2.0.1 +DEFAULT: '#%s' +ALIASES: AutoFormatParam.PurifierLinkifyDocURL +--DESCRIPTION-- ++ Location of configuration documentation to link to, let %s substitute + into the configuration's namespace and directive names sans the percent + sign. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt index 7996488be0d..f3ab259a1b3 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt @@ -1,12 +1,12 @@ -AutoFormat.PurifierLinkify -TYPE: bool -VERSION: 2.0.1 -DEFAULT: false ---DESCRIPTION-- - -
- Internal auto-formatter that converts configuration directives in
- syntax %Namespace.Directive to links. a tags
- with the href attribute must be allowed.
-
+ Internal auto-formatter that converts configuration directives in
+ syntax %Namespace.Directive to links. a tags
+ with the href attribute must be allowed.
+
- Given that an element has no contents, it will be removed by default, unless
- this predicate dictates otherwise. The predicate can either be an associative
- map from tag name to list of attributes that must be present for the element
- to be considered preserved: thus, the default always preserves colgroup,
- th and td, and also iframe if it
- has a src.
-
+ Given that an element has no contents, it will be removed by default, unless
+ this predicate dictates otherwise. The predicate can either be an associative
+ map from tag name to list of attributes that must be present for the element
+ to be considered preserved: thus, the default always preserves colgroup,
+ th and td, and also iframe if it
+ has a src.
+
- When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp - are enabled, this directive defines what HTML elements should not be - removede if they have only a non-breaking space in them. -
---# vim: et sw=4 sts=4 +AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions +TYPE: lookup +VERSION: 4.0.0 +DEFAULT: array('td' => true, 'th' => true) +--DESCRIPTION-- ++ When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp + are enabled, this directive defines what HTML elements should not be + removede if they have only a non-breaking space in them. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt index ca17eb1dc48..5f355d6622e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt @@ -1,15 +1,15 @@ -AutoFormat.RemoveEmpty.RemoveNbsp -TYPE: bool -VERSION: 4.0.0 -DEFAULT: false ---DESCRIPTION-- -- When enabled, HTML Purifier will treat any elements that contain only - non-breaking spaces as well as regular whitespace as empty, and remove - them when %AutoForamt.RemoveEmpty is enabled. -
-- See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements - that don't have this behavior applied to them. -
---# vim: et sw=4 sts=4 +AutoFormat.RemoveEmpty.RemoveNbsp +TYPE: bool +VERSION: 4.0.0 +DEFAULT: false +--DESCRIPTION-- ++ When enabled, HTML Purifier will treat any elements that contain only + non-breaking spaces as well as regular whitespace as empty, and remove + them when %AutoForamt.RemoveEmpty is enabled. +
++ See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements + that don't have this behavior applied to them. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt index 34657ba47b1..6b5a7a5c9a3 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt @@ -1,46 +1,46 @@ -AutoFormat.RemoveEmpty -TYPE: bool -VERSION: 3.2.0 -DEFAULT: false ---DESCRIPTION-- -- When enabled, HTML Purifier will attempt to remove empty elements that - contribute no semantic information to the document. The following types - of nodes will be removed: -
--
- Tags with no attributes and no content, and that are not empty
- elements (remove
<a></a>but not -<br />), and -
- -
- Tags with no content, except for:
-
-
- The
colgroupelement, or
- -
- Elements with the
idornameattribute, - when those attributes are permitted on those elements. -
-
- - The
- Please be very careful when using this functionality; while it may not - seem that empty elements contain useful information, they can alter the - layout of a document given appropriate styling. This directive is most - useful when you are processing machine-generated HTML, please avoid using - it on regular user HTML. -
-- Elements that contain only whitespace will be treated as empty. Non-breaking - spaces, however, do not count as whitespace. See - %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior. -
-- This algorithm is not perfect; you may still notice some empty tags, - particularly if a node had elements, but those elements were later removed - because they were not permitted in that context, or tags that, after - being auto-closed by another tag, where empty. This is for safety reasons - to prevent clever code from breaking validation. The general rule of thumb: - if a tag looked empty on the way in, it will get removed; if HTML Purifier - made it empty, it will stay. -
---# vim: et sw=4 sts=4 +AutoFormat.RemoveEmpty +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- ++ When enabled, HTML Purifier will attempt to remove empty elements that + contribute no semantic information to the document. The following types + of nodes will be removed: +
+-
+ Tags with no attributes and no content, and that are not empty
+ elements (remove
<a></a>but not +<br />), and +
+ -
+ Tags with no content, except for:
-
+
- The
colgroupelement, or
+ -
+ Elements with the
idornameattribute, + when those attributes are permitted on those elements. +
+
+ - The
+ Please be very careful when using this functionality; while it may not + seem that empty elements contain useful information, they can alter the + layout of a document given appropriate styling. This directive is most + useful when you are processing machine-generated HTML, please avoid using + it on regular user HTML. +
++ Elements that contain only whitespace will be treated as empty. Non-breaking + spaces, however, do not count as whitespace. See + %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior. +
++ This algorithm is not perfect; you may still notice some empty tags, + particularly if a node had elements, but those elements were later removed + because they were not permitted in that context, or tags that, after + being auto-closed by another tag, where empty. This is for safety reasons + to prevent clever code from breaking validation. The general rule of thumb: + if a tag looked empty on the way in, it will get removed; if HTML Purifier + made it empty, it will stay. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt index dde990ab260..a448770e50e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt @@ -1,11 +1,11 @@ -AutoFormat.RemoveSpansWithoutAttributes -TYPE: bool -VERSION: 4.0.1 -DEFAULT: false ---DESCRIPTION-- -
- This directive causes span tags without any attributes
- to be removed. It will also remove spans that had all attributes
- removed during processing.
-
+ This directive causes span tags without any attributes
+ to be removed. It will also remove spans that had all attributes
+ removed during processing.
+
- By default, HTML Purifier removes duplicate CSS properties,
- like color:red; color:blue. If this is set to
- true, duplicate properties are allowed.
-
+ By default, HTML Purifier removes duplicate CSS properties,
+ like color:red; color:blue. If this is set to
+ true, duplicate properties are allowed.
+
display:none; is considered a tricky property that
-will only be allowed if this directive is set to true.
---# vim: et sw=4 sts=4
+CSS.AllowTricky
+TYPE: bool
+DEFAULT: false
+VERSION: 3.1.0
+--DESCRIPTION--
+This parameter determines whether or not to allow "tricky" CSS properties and
+values. Tricky CSS properties/values can drastically modify page layout or
+be used for deceptive practices but do not directly constitute a security risk.
+For example, display:none; is considered a tricky property that
+will only be allowed if this directive is set to true.
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt
index 3fd4654065d..7c2b54763e1 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt
@@ -1,12 +1,12 @@
-CSS.AllowedFonts
-TYPE: lookup/null
-VERSION: 4.3.0
-DEFAULT: NULL
---DESCRIPTION--
-
- Allows you to manually specify a set of allowed fonts. If
- NULL, all fonts are allowed. This directive
- affects generic names (serif, sans-serif, monospace, cursive,
- fantasy) as well as specific font families.
-
+ Allows you to manually specify a set of allowed fonts. If
+ NULL, all fonts are allowed. This directive
+ affects generic names (serif, sans-serif, monospace, cursive,
+ fantasy) as well as specific font families.
+
- If HTML Purifier's style attributes 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 an attribute that HTML Purifier never - supported in the first place. -
-- Warning: If another directive conflicts with the - elements here, that directive will win and override. -
---# vim: et sw=4 sts=4 +CSS.AllowedProperties +TYPE: lookup/null +VERSION: 3.1.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ If HTML Purifier's style attributes 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 an attribute that HTML Purifier never + supported in the first place. +
++ Warning: If another directive conflicts with the + elements here, that directive will win and override. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt index 5cb7dda3bae..96b410829e2 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt @@ -1,11 +1,11 @@ -CSS.DefinitionRev -TYPE: int -VERSION: 2.0.0 -DEFAULT: 1 ---DESCRIPTION-- - -- Revision identifier for your custom definition. See - %HTML.DefinitionRev for details. -
---# vim: et sw=4 sts=4 +CSS.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + ++ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt index f1f5c5f12b4..923e8e995cb 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt @@ -1,13 +1,13 @@ -CSS.ForbiddenProperties -TYPE: lookup -VERSION: 4.2.0 -DEFAULT: array() ---DESCRIPTION-- -- 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. -
---# vim: et sw=4 sts=4 +CSS.ForbiddenProperties +TYPE: lookup +VERSION: 4.2.0 +DEFAULT: array() +--DESCRIPTION-- ++ 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. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt index 7a3291470cc..3808581e2b7 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt @@ -1,16 +1,16 @@ -CSS.MaxImgLength -TYPE: string/null -DEFAULT: '1200px' -VERSION: 3.1.1 ---DESCRIPTION-- -
- This parameter sets the maximum allowed length on img tags,
- effectively the width and height properties.
- Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
- in place to prevent imagecrash attacks, disable with null at your own risk.
- This directive is similar to %HTML.MaxImgLength, and both should be
- concurrently edited, although there are
- subtle differences in the input format (the CSS max is a number with
- a unit).
-
+ This parameter sets the maximum allowed length on img tags,
+ effectively the width and height properties.
+ Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %HTML.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the CSS max is a number with
+ a unit).
+
- Whether or not to allow safe, proprietary CSS values. -
---# vim: et sw=4 sts=4 +CSS.Proprietary +TYPE: bool +VERSION: 3.0.0 +DEFAULT: false +--DESCRIPTION-- + ++ Whether or not to allow safe, proprietary CSS values. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt index e733a61e8a7..917ec42ba46 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt @@ -1,9 +1,9 @@ -CSS.Trusted -TYPE: bool -VERSION: 4.2.1 -DEFAULT: false ---DESCRIPTION-- -Indicates whether or not the user's CSS input is trusted or not. If the -input is trusted, a more expansive set of allowed properties. See -also %HTML.Trusted. ---# vim: et sw=4 sts=4 +CSS.Trusted +TYPE: bool +VERSION: 4.2.1 +DEFAULT: false +--DESCRIPTION-- +Indicates whether or not the user's CSS input is trusted or not. If the +input is trusted, a more expansive set of allowed properties. See +also %HTML.Trusted. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt index c486724c88a..afc6a87a643 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt @@ -1,14 +1,14 @@ -Cache.DefinitionImpl -TYPE: string/null -VERSION: 2.0.0 -DEFAULT: 'Serializer' ---DESCRIPTION-- - -This directive defines which method to use when caching definitions, -the complex data-type that makes HTML Purifier tick. Set to null -to disable caching (not recommended, as you will see a definite -performance degradation). - ---ALIASES-- -Core.DefinitionCache ---# vim: et sw=4 sts=4 +Cache.DefinitionImpl +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: 'Serializer' +--DESCRIPTION-- + +This directive defines which method to use when caching definitions, +the complex data-type that makes HTML Purifier tick. Set to null +to disable caching (not recommended, as you will see a definite +performance degradation). + +--ALIASES-- +Core.DefinitionCache +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt index 54036507d6c..668f248af4e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt @@ -1,13 +1,13 @@ -Cache.SerializerPath -TYPE: string/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -- Absolute path with no trailing slash to store serialized definitions in. - Default is within the - HTML Purifier library inside DefinitionCache/Serializer. This - path must be writable by the webserver. -
---# vim: et sw=4 sts=4 +Cache.SerializerPath +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ Absolute path with no trailing slash to store serialized definitions in. + Default is within the + HTML Purifier library inside DefinitionCache/Serializer. This + path must be writable by the webserver. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt index 2e0cc81044f..f6059e67201 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt @@ -1,16 +1,16 @@ -Cache.SerializerPermissions -TYPE: int/null -VERSION: 4.3.0 -DEFAULT: 0755 ---DESCRIPTION-- - -- Directory permissions of the files and directories created inside - the DefinitionCache/Serializer or other custom serializer path. -
-
- In HTML Purifier 4.8.0, this also supports NULL,
- which means that no chmod'ing or directory creation shall
- occur.
-
+ Directory permissions of the files and directories created inside + the DefinitionCache/Serializer or other custom serializer path. +
+
+ In HTML Purifier 4.8.0, this also supports NULL,
+ which means that no chmod'ing or directory creation shall
+ occur.
+
- This directive enables aggressive pre-filter fixes HTML Purifier can - perform in order to ensure that open angled-brackets do not get killed - during parsing stage. Enabling this will result in two preg_replace_callback - calls and at least two preg_replace calls for every HTML document parsed; - if your users make very well-formed HTML, you can set this directive false. - This has no effect when DirectLex is used. -
-- Notice: This directive's default turned from false to true - in HTML Purifier 3.2.0. -
---# vim: et sw=4 sts=4 +Core.AggressivelyFixLt +TYPE: bool +VERSION: 2.1.0 +DEFAULT: true +--DESCRIPTION-- ++ This directive enables aggressive pre-filter fixes HTML Purifier can + perform in order to ensure that open angled-brackets do not get killed + during parsing stage. Enabling this will result in two preg_replace_callback + calls and at least two preg_replace calls for every HTML document parsed; + if your users make very well-formed HTML, you can set this directive false. + This has no effect when DirectLex is used. +
++ Notice: This directive's default turned from false to true + in HTML Purifier 3.2.0. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt index b2b6ab14968..fb140b69dbd 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txt @@ -1,16 +1,16 @@ -Core.AggressivelyRemoveScript -TYPE: bool -VERSION: 4.9.0 -DEFAULT: true ---DESCRIPTION-- -- This directive enables aggressive pre-filter removal of - script tags. This is not necessary for security, - but it can help work around a bug in libxml where embedded - HTML elements inside script sections cause the parser to - choke. To revert to pre-4.9.0 behavior, set this to false. - This directive has no effect if %Core.Trusted is true, - %Core.RemoveScriptContents is false, or %Core.HiddenElements - does not contain script. -
---# vim: et sw=4 sts=4 +Core.AggressivelyRemoveScript +TYPE: bool +VERSION: 4.9.0 +DEFAULT: true +--DESCRIPTION-- ++ This directive enables aggressive pre-filter removal of + script tags. This is not necessary for security, + but it can help work around a bug in libxml where embedded + HTML elements inside script sections cause the parser to + choke. To revert to pre-4.9.0 behavior, set this to false. + This directive has no effect if %Core.Trusted is true, + %Core.RemoveScriptContents is false, or %Core.HiddenElements + does not contain script. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt index 2c910cc7de8..405d36f1741 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt @@ -1,16 +1,16 @@ -Core.AllowHostnameUnderscore -TYPE: bool -VERSION: 4.6.0 -DEFAULT: false ---DESCRIPTION-- -- By RFC 1123, underscores are not permitted in host names. - (This is in contrast to the specification for DNS, RFC - 2181, which allows underscores.) - However, most browsers do the right thing when faced with - an underscore in the host name, and so some poorly written - websites are written with the expectation this should work. - Setting this parameter to true relaxes our allowed character - check so that underscores are permitted. -
---# vim: et sw=4 sts=4 +Core.AllowHostnameUnderscore +TYPE: bool +VERSION: 4.6.0 +DEFAULT: false +--DESCRIPTION-- ++ By RFC 1123, underscores are not permitted in host names. + (This is in contrast to the specification for DNS, RFC + 2181, which allows underscores.) + However, most browsers do the right thing when faced with + an underscore in the host name, and so some poorly written + websites are written with the expectation this should work. + Setting this parameter to true relaxes our allowed character + check so that underscores are permitted. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt index d7317911fa3..c6ea06990fc 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt @@ -1,12 +1,12 @@ -Core.CollectErrors -TYPE: bool -VERSION: 2.0.0 -DEFAULT: false ---DESCRIPTION-- - -Whether or not to collect errors found while filtering the document. This -is a useful way to give feedback to your users. Warning: -Currently this feature is very patchy and experimental, with lots of -possible error messages not yet implemented. It will not cause any -problems, but it may not help your users either. ---# vim: et sw=4 sts=4 +Core.CollectErrors +TYPE: bool +VERSION: 2.0.0 +DEFAULT: false +--DESCRIPTION-- + +Whether or not to collect errors found while filtering the document. This +is a useful way to give feedback to your users. Warning: +Currently this feature is very patchy and experimental, with lots of +possible error messages not yet implemented. It will not cause any +problems, but it may not help your users either. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt index c572c14ec17..f7823982534 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt @@ -1,29 +1,29 @@ -Core.ColorKeywords -TYPE: hash -VERSION: 2.0.0 ---DEFAULT-- -array ( - 'maroon' => '#800000', - 'red' => '#FF0000', - 'orange' => '#FFA500', - 'yellow' => '#FFFF00', - 'olive' => '#808000', - 'purple' => '#800080', - 'fuchsia' => '#FF00FF', - 'white' => '#FFFFFF', - 'lime' => '#00FF00', - 'green' => '#008000', - 'navy' => '#000080', - 'blue' => '#0000FF', - 'aqua' => '#00FFFF', - 'teal' => '#008080', - 'black' => '#000000', - 'silver' => '#C0C0C0', - 'gray' => '#808080', -) ---DESCRIPTION-- - -Lookup array of color names to six digit hexadecimal number corresponding -to color, with preceding hash mark. Used when parsing colors. The lookup -is done in a case-insensitive manner. ---# vim: et sw=4 sts=4 +Core.ColorKeywords +TYPE: hash +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'maroon' => '#800000', + 'red' => '#FF0000', + 'orange' => '#FFA500', + 'yellow' => '#FFFF00', + 'olive' => '#808000', + 'purple' => '#800080', + 'fuchsia' => '#FF00FF', + 'white' => '#FFFFFF', + 'lime' => '#00FF00', + 'green' => '#008000', + 'navy' => '#000080', + 'blue' => '#0000FF', + 'aqua' => '#00FFFF', + 'teal' => '#008080', + 'black' => '#000000', + 'silver' => '#C0C0C0', + 'gray' => '#808080', +) +--DESCRIPTION-- + +Lookup array of color names to six digit hexadecimal number corresponding +to color, with preceding hash mark. Used when parsing colors. The lookup +is done in a case-insensitive manner. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt index 64b114fce2b..656d3783a80 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt @@ -1,14 +1,14 @@ -Core.ConvertDocumentToFragment -TYPE: bool -DEFAULT: true ---DESCRIPTION-- - -This parameter determines whether or not the filter should convert -input that is a full document with html and body tags to a fragment -of just the contents of a body tag. This parameter is simply something -HTML Purifier can do during an edge-case: for most inputs, this -processing is not necessary. - ---ALIASES-- -Core.AcceptFullDocuments ---# vim: et sw=4 sts=4 +Core.ConvertDocumentToFragment +TYPE: bool +DEFAULT: true +--DESCRIPTION-- + +This parameter determines whether or not the filter should convert +input that is a full document with html and body tags to a fragment +of just the contents of a body tag. This parameter is simply something +HTML Purifier can do during an edge-case: for most inputs, this +processing is not necessary. + +--ALIASES-- +Core.AcceptFullDocuments +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt index 36f16e07eae..2f54e462a15 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt @@ -1,17 +1,17 @@ -Core.DirectLexLineNumberSyncInterval -TYPE: int -VERSION: 2.0.0 -DEFAULT: 0 ---DESCRIPTION-- - -- Specifies the number of tokens the DirectLex line number tracking - implementations should process before attempting to resyncronize the - current line count by manually counting all previous new-lines. When - at 0, this functionality is disabled. Lower values will decrease - performance, and this is only strictly necessary if the counting - algorithm is buggy (in which case you should report it as a bug). - This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is - not being used. -
---# vim: et sw=4 sts=4 +Core.DirectLexLineNumberSyncInterval +TYPE: int +VERSION: 2.0.0 +DEFAULT: 0 +--DESCRIPTION-- + ++ Specifies the number of tokens the DirectLex line number tracking + implementations should process before attempting to resyncronize the + current line count by manually counting all previous new-lines. When + at 0, this functionality is disabled. Lower values will decrease + performance, and this is only strictly necessary if the counting + algorithm is buggy (in which case you should report it as a bug). + This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is + not being used. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt index 1cd4c2c9640..3c63c923c8c 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt @@ -1,14 +1,14 @@ -Core.DisableExcludes -TYPE: bool -DEFAULT: false -VERSION: 4.5.0 ---DESCRIPTION-- -
- This directive disables SGML-style exclusions, e.g. the exclusion of
- <object> in any descendant of a
- <pre> tag. Disabling excludes will allow some
- invalid documents to pass through HTML Purifier, but HTML Purifier
- will also be less likely to accidentally remove large documents during
- processing.
-
+ This directive disables SGML-style exclusions, e.g. the exclusion of
+ <object> in any descendant of a
+ <pre> tag. Disabling excludes will allow some
+ invalid documents to pass through HTML Purifier, but HTML Purifier
+ will also be less likely to accidentally remove large documents during
+ processing.
+
Warning: this configuration option is no longer does anything as of 4.6.0.
- -When true, a child is found that is not allowed in the context of the -parent element will be transformed into text as if it were ASCII. When -false, that element and all internal tags will be dropped, though text will -be preserved. There is no option for dropping the element but preserving -child nodes.
---# vim: et sw=4 sts=4 +Core.EscapeInvalidChildren +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +Warning: this configuration option is no longer does anything as of 4.6.0.
+ +When true, a child is found that is not allowed in the context of the +parent element will be transformed into text as if it were ASCII. When +false, that element and all internal tags will be dropped, though text will +be preserved. There is no option for dropping the element but preserving +child nodes.
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt index a7a5b249bb7..299775fab2e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt @@ -1,7 +1,7 @@ -Core.EscapeInvalidTags -TYPE: bool -DEFAULT: false ---DESCRIPTION-- -When true, invalid tags will be written back to the document as plain text. -Otherwise, they are silently dropped. ---# vim: et sw=4 sts=4 +Core.EscapeInvalidTags +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When true, invalid tags will be written back to the document as plain text. +Otherwise, they are silently dropped. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt index abb499948ac..f50db2f92a7 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt @@ -1,13 +1,13 @@ -Core.EscapeNonASCIICharacters -TYPE: bool -VERSION: 1.4.0 -DEFAULT: false ---DESCRIPTION-- -This directive overcomes a deficiency in %Core.Encoding by blindly -converting all non-ASCII characters into decimal numeric entities before -converting it to its native encoding. This means that even characters that -can be expressed in the non-UTF-8 encoding will be entity-ized, which can -be a real downer for encodings like Big5. It also assumes that the ASCII -repetoire is available, although this is the case for almost all encodings. -Anyway, use UTF-8! ---# vim: et sw=4 sts=4 +Core.EscapeNonASCIICharacters +TYPE: bool +VERSION: 1.4.0 +DEFAULT: false +--DESCRIPTION-- +This directive overcomes a deficiency in %Core.Encoding by blindly +converting all non-ASCII characters into decimal numeric entities before +converting it to its native encoding. This means that even characters that +can be expressed in the non-UTF-8 encoding will be entity-ized, which can +be a real downer for encodings like Big5. It also assumes that the ASCII +repetoire is available, although this is the case for almost all encodings. +Anyway, use UTF-8! +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt index 915391edb73..c337e47fca2 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt @@ -1,19 +1,19 @@ -Core.HiddenElements -TYPE: lookup ---DEFAULT-- -array ( - 'script' => true, - 'style' => true, -) ---DESCRIPTION-- - -
- This directive is a lookup array of elements which should have their
- contents removed when they are not allowed by the HTML definition.
- For example, the contents of a script tag are not
- normally shown in a document, so if script tags are to be removed,
- their contents should be removed to. This is opposed to a b
- tag, which defines some presentational changes but does not hide its
- contents.
-
+ This directive is a lookup array of elements which should have their
+ contents removed when they are not allowed by the HTML definition.
+ For example, the contents of a script tag are not
+ normally shown in a document, so if script tags are to be removed,
+ their contents should be removed to. This is opposed to a b
+ tag, which defines some presentational changes but does not hide its
+ contents.
+
- Prior to HTML Purifier 4.9.0, entities were decoded by performing - a global search replace for all entities whose decoded versions - did not have special meanings under HTML, and replaced them with - their decoded versions. We would match all entities, even if they did - not have a trailing semicolon, but only if there weren't any trailing - alphanumeric characters. -
-| Original | Text | Attribute |
|---|---|---|
| ¥ | ¥ | ¥ |
| ¥ | ¥ | ¥ |
| ¥a | ¥a | ¥a |
| ¥= | ¥= | ¥= |
- In HTML Purifier 4.9.0, we changed the behavior of entity parsing - to match entities that had missing trailing semicolons in less - cases, to more closely match HTML5 parsing behavior: -
-| Original | Text | Attribute |
|---|---|---|
| ¥ | ¥ | ¥ |
| ¥ | ¥ | ¥ |
| ¥a | ¥a | ¥a |
| ¥= | ¥= | ¥= |
- This flag reverts back to pre-HTML Purifier 4.9.0 behavior. -
---# vim: et sw=4 sts=4 +Core.LegacyEntityDecoder +TYPE: bool +VERSION: 4.9.0 +DEFAULT: false +--DESCRIPTION-- ++ Prior to HTML Purifier 4.9.0, entities were decoded by performing + a global search replace for all entities whose decoded versions + did not have special meanings under HTML, and replaced them with + their decoded versions. We would match all entities, even if they did + not have a trailing semicolon, but only if there weren't any trailing + alphanumeric characters. +
+| Original | Text | Attribute |
|---|---|---|
| ¥ | ¥ | ¥ |
| ¥ | ¥ | ¥ |
| ¥a | ¥a | ¥a |
| ¥= | ¥= | ¥= |
+ In HTML Purifier 4.9.0, we changed the behavior of entity parsing + to match entities that had missing trailing semicolons in less + cases, to more closely match HTML5 parsing behavior: +
+| Original | Text | Attribute |
|---|---|---|
| ¥ | ¥ | ¥ |
| ¥ | ¥ | ¥ |
| ¥a | ¥a | ¥a |
| ¥= | ¥= | ¥= |
+ This flag reverts back to pre-HTML Purifier 4.9.0 behavior. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt index 8983e2cca9b..e11c0152c2d 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt @@ -1,34 +1,34 @@ -Core.LexerImpl -TYPE: mixed/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -- This parameter determines what lexer implementation can be used. The - valid values are: -
--
-
- null -
- - Recommended, the lexer implementation will be auto-detected based on - your PHP-version and configuration. - -
- string lexer identifier -
- - This is a slim way of manually overridding the implementation. - Currently recognized values are: DOMLex (the default PHP5 -implementation) - and DirectLex (the default PHP4 implementation). Only use this if - you know what you are doing: usually, the auto-detection will - manage things for cases you aren't even aware of. - -
- object lexer instance -
-
- Super-advanced: you can specify your own, custom, implementation that
- implements the interface defined by
HTMLPurifier_Lexer. - I may remove this option simply because I don't expect anyone - to use it. -
-
+ This parameter determines what lexer implementation can be used. The + valid values are: +
+-
+
- null +
- + Recommended, the lexer implementation will be auto-detected based on + your PHP-version and configuration. + +
- string lexer identifier +
- + This is a slim way of manually overridding the implementation. + Currently recognized values are: DOMLex (the default PHP5 +implementation) + and DirectLex (the default PHP4 implementation). Only use this if + you know what you are doing: usually, the auto-detection will + manage things for cases you aren't even aware of. + +
- object lexer instance +
-
+ Super-advanced: you can specify your own, custom, implementation that
+ implements the interface defined by
HTMLPurifier_Lexer. + I may remove this option simply because I don't expect anyone + to use it. +
+
- If true, HTML Purifier will add line number information to all tokens. - This is useful when error reporting is turned on, but can result in - significant performance degradation and should not be used when - unnecessary. This directive must be used with the DirectLex lexer, - as the DOMLex lexer does not (yet) support this functionality. - If the value is null, an appropriate value will be selected based - on other configuration. -
---# vim: et sw=4 sts=4 +Core.MaintainLineNumbers +TYPE: bool/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ If true, HTML Purifier will add line number information to all tokens. + This is useful when error reporting is turned on, but can result in + significant performance degradation and should not be used when + unnecessary. This directive must be used with the DirectLex lexer, + as the DOMLex lexer does not (yet) support this functionality. + If the value is null, an appropriate value will be selected based + on other configuration. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt index d77f5360d7c..94a88600de7 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt @@ -1,11 +1,11 @@ -Core.NormalizeNewlines -TYPE: bool -VERSION: 4.2.0 -DEFAULT: true ---DESCRIPTION-- -
- Whether or not to normalize newlines to the operating
- system default. When false, HTML Purifier
- will attempt to preserve mixed newline files.
-
+ Whether or not to normalize newlines to the operating
+ system default. When false, HTML Purifier
+ will attempt to preserve mixed newline files.
+
- This directive enables pre-emptive URI checking in img
- tags, as the attribute validation strategy is not authorized to
- remove elements from the document. Revert to pre-1.3.0 behavior by setting to false.
-
+ This directive enables pre-emptive URI checking in img
+ tags, as the attribute validation strategy is not authorized to
+ remove elements from the document. Revert to pre-1.3.0 behavior by setting to false.
+
<? ...
-?>, 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
+Core.RemoveProcessingInstructions
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+Instead of escaping processing instructions in the form <? ...
+?>, 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
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt
index a4cd966df89..efbe994c28c 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt
@@ -1,12 +1,12 @@
-Core.RemoveScriptContents
-TYPE: bool/null
-DEFAULT: NULL
-VERSION: 2.0.0
-DEPRECATED-VERSION: 2.1.0
-DEPRECATED-USE: Core.HiddenElements
---DESCRIPTION--
-- This directive enables HTML Purifier to remove not only script tags - but all of their contents. -
---# vim: et sw=4 sts=4 +Core.RemoveScriptContents +TYPE: bool/null +DEFAULT: NULL +VERSION: 2.0.0 +DEPRECATED-VERSION: 2.1.0 +DEPRECATED-USE: Core.HiddenElements +--DESCRIPTION-- ++ This directive enables HTML Purifier to remove not only script tags + but all of their contents. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt index 3db50ef204b..861ae66c3a9 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt @@ -1,11 +1,11 @@ -Filter.Custom -TYPE: list -VERSION: 3.1.0 -DEFAULT: array() ---DESCRIPTION-- -
- This directive can be used to add custom filters; it is nearly the
- equivalent of the now deprecated HTMLPurifier->addFilter()
- method. Specify an array of concrete implementations.
-
+ This directive can be used to add custom filters; it is nearly the
+ equivalent of the now deprecated HTMLPurifier->addFilter()
+ method. Specify an array of concrete implementations.
+
- Whether or not to escape the dangerous characters <, > and & - as \3C, \3E and \26, respectively. This is can be safely set to false - if the contents of StyleBlocks will be placed in an external stylesheet, - where there is no risk of it being interpreted as HTML. -
---# vim: et sw=4 sts=4 +Filter.ExtractStyleBlocks.Escaping +TYPE: bool +VERSION: 3.0.0 +DEFAULT: true +ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping +--DESCRIPTION-- + ++ Whether or not to escape the dangerous characters <, > and & + as \3C, \3E and \26, respectively. This is can be safely set to false + if the contents of StyleBlocks will be placed in an external stylesheet, + where there is no risk of it being interpreted as HTML. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt index 7f95f54d125..baa81ae062f 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt @@ -1,29 +1,29 @@ -Filter.ExtractStyleBlocks.Scope -TYPE: string/null -VERSION: 3.0.0 -DEFAULT: NULL -ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope ---DESCRIPTION-- - -
- If you would like users to be able to define external stylesheets, but
- only allow them to specify CSS declarations for a specific node and
- prevent them from fiddling with other elements, use this directive.
- It accepts any valid CSS selector, and will prepend this to any
- CSS declaration extracted from the document. For example, if this
- directive is set to #user-content and a user uses the
- selector a:hover, the final selector will be
- #user-content a:hover.
-
- The comma shorthand may be used; consider the above example, with
- #user-content, #user-content2, the final selector will
- be #user-content a:hover, #user-content2 a:hover.
-
- Warning: It is possible for users to bypass this measure - using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML - Purifier, and I am working to get it fixed. Until then, HTML Purifier - performs a basic check to prevent this. -
---# vim: et sw=4 sts=4 +Filter.ExtractStyleBlocks.Scope +TYPE: string/null +VERSION: 3.0.0 +DEFAULT: NULL +ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope +--DESCRIPTION-- + +
+ If you would like users to be able to define external stylesheets, but
+ only allow them to specify CSS declarations for a specific node and
+ prevent them from fiddling with other elements, use this directive.
+ It accepts any valid CSS selector, and will prepend this to any
+ CSS declaration extracted from the document. For example, if this
+ directive is set to #user-content and a user uses the
+ selector a:hover, the final selector will be
+ #user-content a:hover.
+
+ The comma shorthand may be used; consider the above example, with
+ #user-content, #user-content2, the final selector will
+ be #user-content a:hover, #user-content2 a:hover.
+
+ Warning: It is possible for users to bypass this measure + using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML + Purifier, and I am working to get it fixed. Until then, HTML Purifier + performs a basic check to prevent this. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt index 6c231b2d7f7..3b7018917e7 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt @@ -1,16 +1,16 @@ -Filter.ExtractStyleBlocks.TidyImpl -TYPE: mixed/null -VERSION: 3.1.0 -DEFAULT: NULL -ALIASES: FilterParam.ExtractStyleBlocksTidyImpl ---DESCRIPTION-- -
- If left NULL, HTML Purifier will attempt to instantiate a csstidy
- class to use for internal cleaning. This will usually be good enough.
-
- However, for trusted user input, you can set this to false to
- disable cleaning. In addition, you can supply your own concrete implementation
- of Tidy's interface to use, although I don't know why you'd want to do that.
-
+ If left NULL, HTML Purifier will attempt to instantiate a csstidy
+ class to use for internal cleaning. This will usually be good enough.
+
+ However, for trusted user input, you can set this to false to
+ disable cleaning. In addition, you can supply your own concrete implementation
+ of Tidy's interface to use, although I don't know why you'd want to do that.
+
- This directive turns on the style block extraction filter, which removes
- style blocks from input HTML, cleans them up with CSSTidy,
- and places them in the StyleBlocks context variable, for further
- use by you, usually to be placed in an external stylesheet, or a
- style block in the head of your document.
-
- Sample usage: -
-'; -?> - - - --Filter.ExtractStyleBlocks -body {color:#F00;} Some text'; - - $config = HTMLPurifier_Config::createDefault(); - $config->set('Filter', 'ExtractStyleBlocks', true); - $purifier = new HTMLPurifier($config); - - $html = $purifier->purify($dirty); - - // This implementation writes the stylesheets to the styles/ directory. - // You can also echo the styles inside the document, but it's a bit - // more difficult to make sure they get interpreted properly by - // browsers; try the usual CSS armoring techniques. - $styles = $purifier->context->get('StyleBlocks'); - $dir = 'styles/'; - if (!is_dir($dir)) mkdir($dir); - $hash = sha1($_GET['html']); - foreach ($styles as $i => $style) { - file_put_contents($name = $dir . $hash . "_$i"); - echo ''; - } -?> - - -- -- - -]]>
- Warning: It is possible for a user to mount an - imagecrash attack using this CSS. Counter-measures are difficult; - it is not simply enough to limit the range of CSS lengths (using - relative lengths with many nesting levels allows for large values - to be attained without actually specifying them in the stylesheet), - and the flexible nature of selectors makes it difficult to selectively - disable lengths on image tags (HTML Purifier, however, does disable - CSS width and height in inline styling). There are probably two effective - counter measures: an explicit width and height set to auto in all - images in your document (unlikely) or the disabling of width and - height (somewhat reasonable). Whether or not these measures should be - used is left to the reader. -
---# vim: et sw=4 sts=4 +Filter.ExtractStyleBlocks +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +EXTERNAL: CSSTidy +--DESCRIPTION-- +
+ This directive turns on the style block extraction filter, which removes
+ style blocks from input HTML, cleans them up with CSSTidy,
+ and places them in the StyleBlocks context variable, for further
+ use by you, usually to be placed in an external stylesheet, or a
+ style block in the head of your document.
+
+ Sample usage: +
+'; +?> + + + ++Filter.ExtractStyleBlocks +body {color:#F00;} Some text'; + + $config = HTMLPurifier_Config::createDefault(); + $config->set('Filter', 'ExtractStyleBlocks', true); + $purifier = new HTMLPurifier($config); + + $html = $purifier->purify($dirty); + + // This implementation writes the stylesheets to the styles/ directory. + // You can also echo the styles inside the document, but it's a bit + // more difficult to make sure they get interpreted properly by + // browsers; try the usual CSS armoring techniques. + $styles = $purifier->context->get('StyleBlocks'); + $dir = 'styles/'; + if (!is_dir($dir)) mkdir($dir); + $hash = sha1($_GET['html']); + foreach ($styles as $i => $style) { + file_put_contents($name = $dir . $hash . "_$i"); + echo ''; + } +?> + + ++ ++ + +]]>
+ Warning: It is possible for a user to mount an + imagecrash attack using this CSS. Counter-measures are difficult; + it is not simply enough to limit the range of CSS lengths (using + relative lengths with many nesting levels allows for large values + to be attained without actually specifying them in the stylesheet), + and the flexible nature of selectors makes it difficult to selectively + disable lengths on image tags (HTML Purifier, however, does disable + CSS width and height in inline styling). There are probably two effective + counter measures: an explicit width and height set to auto in all + images in your document (unlikely) or the disabling of width and + height (somewhat reasonable). Whether or not these measures should be + used is left to the reader. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt index 321eaa2d803..88221866856 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt @@ -1,16 +1,16 @@ -Filter.YouTube -TYPE: bool -VERSION: 3.1.0 -DEFAULT: false ---DESCRIPTION-- -- Warning: Deprecated in favor of %HTML.SafeObject and - %Output.FlashCompat (turn both on to allow YouTube videos and other - Flash content). -
-- This directive enables YouTube video embedding in HTML Purifier. Check - this document - on embedding videos for more information on what this filter does. -
---# vim: et sw=4 sts=4 +Filter.YouTube +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- ++ Warning: Deprecated in favor of %HTML.SafeObject and + %Output.FlashCompat (turn both on to allow YouTube videos and other + Flash content). +
++ This directive enables YouTube video embedding in HTML Purifier. Check + this document + on embedding videos for more information on what this filter does. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt index 0b2c106da5e..afd48a0d47d 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -1,25 +1,25 @@ -HTML.Allowed -TYPE: itext/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -
- This is a preferred convenience directive that combines
- %HTML.AllowedElements and %HTML.AllowedAttributes.
- Specify elements and attributes that are allowed using:
- element1[attr1|attr2],element2.... For example,
- if you would like to only allow paragraphs and links, specify
- a[href],p. You can specify attributes that apply
- to all elements using an asterisk, e.g. *[lang].
- You can also use newlines instead of commas to separate elements.
-
- Warning:
- All of the constraints on the component directives are still enforced.
- The syntax is a subset of TinyMCE's valid_elements
- whitelist: directly copy-pasting it here will probably result in
- broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes
- are set, this directive has no effect.
-
+ This is a preferred convenience directive that combines
+ %HTML.AllowedElements and %HTML.AllowedAttributes.
+ Specify elements and attributes that are allowed using:
+ element1[attr1|attr2],element2.... For example,
+ if you would like to only allow paragraphs and links, specify
+ a[href],p. You can specify attributes that apply
+ to all elements using an asterisk, e.g. *[lang].
+ You can also use newlines instead of commas to separate elements.
+
+ Warning:
+ All of the constraints on the component directives are still enforced.
+ The syntax is a subset of TinyMCE's valid_elements
+ whitelist: directly copy-pasting it here will probably result in
+ broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes
+ are set, this directive has no effect.
+
- If HTML Purifier's attribute set is unsatisfactory, overload it! - The syntax is "tag.attr" or "*.attr" for the global attributes - (style, id, class, dir, lang, xml:lang). -
-- Warning: If another directive conflicts with the - elements here, that directive will win and override. For - example, %HTML.EnableAttrID will take precedence over *.id in this - directive. You must set that directive to true before you can use - IDs at all. -
---# vim: et sw=4 sts=4 +HTML.AllowedAttributes +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ If HTML Purifier's attribute set is unsatisfactory, overload it! + The syntax is "tag.attr" or "*.attr" for the global attributes + (style, id, class, dir, lang, xml:lang). +
++ Warning: If another directive conflicts with the + elements here, that directive will win and override. For + example, %HTML.EnableAttrID will take precedence over *.id in this + directive. You must set that directive to true before you can use + IDs at all. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt index 140e21423e5..8440bc39df4 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt @@ -1,10 +1,10 @@ -HTML.AllowedComments -TYPE: lookup -VERSION: 4.4.0 -DEFAULT: array() ---DESCRIPTION-- -A whitelist which indicates what explicit comment bodies should be -allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp -(these directives are union'ed together, so a comment is considered -valid if any directive deems it valid.) ---# vim: et sw=4 sts=4 +HTML.AllowedComments +TYPE: lookup +VERSION: 4.4.0 +DEFAULT: array() +--DESCRIPTION-- +A whitelist which indicates what explicit comment bodies should be +allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp +(these directives are union'ed together, so a comment is considered +valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt index f22e977d438..b1e65beb16b 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt @@ -1,15 +1,15 @@ -HTML.AllowedCommentsRegexp -TYPE: string/null -VERSION: 4.4.0 -DEFAULT: NULL ---DESCRIPTION-- -A regexp, which if it matches the body of a comment, indicates that -it should be allowed. Trailing and leading spaces are removed prior -to running this regular expression. -Warning: Make sure you specify -correct anchor metacharacters^regex$, otherwise you may accept
-comments that you did not mean to! In particular, the regex /foo|bar/
-is probably not sufficiently strict, since it also allows foobar.
-See also %HTML.AllowedComments (these directives are union'ed together,
-so a comment is considered valid if any directive deems it valid.)
---# vim: et sw=4 sts=4
+HTML.AllowedCommentsRegexp
+TYPE: string/null
+VERSION: 4.4.0
+DEFAULT: NULL
+--DESCRIPTION--
+A regexp, which if it matches the body of a comment, indicates that
+it should be allowed. Trailing and leading spaces are removed prior
+to running this regular expression.
+Warning: Make sure you specify
+correct anchor metacharacters ^regex$, otherwise you may accept
+comments that you did not mean to! In particular, the regex /foo|bar/
+is probably not sufficiently strict, since it also allows foobar.
+See also %HTML.AllowedComments (these directives are union'ed together,
+so a comment is considered valid if any directive deems it valid.)
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
index 1d3fa7907dc..ca3c13ddbf1 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
@@ -1,23 +1,23 @@
-HTML.AllowedElements
-TYPE: lookup/null
-VERSION: 1.3.0
-DEFAULT: NULL
---DESCRIPTION--
-- 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. -
-- 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 - advanced customization features. -
-- Warning: If another directive conflicts with the - elements here, that directive will win and override. -
---# vim: et sw=4 sts=4 +HTML.AllowedElements +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- ++ 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. +
++ 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 + advanced customization features. +
++ Warning: If another directive conflicts with the + elements here, that directive will win and override. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt index 5a59a55c083..e373791a58a 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt @@ -1,20 +1,20 @@ -HTML.AllowedModules -TYPE: lookup/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -- A doctype comes with a set of usual modules to use. Without having - to mucking about with the doctypes, you can quickly activate or - disable these modules by specifying which modules you wish to allow - with this directive. This is most useful for unit testing specific - modules, although end users may find it useful for their own ends. -
-- If you specify a module that does not exist, the manager will silently - fail to use it, so be careful! User-defined modules are not affected - by this directive. Modules defined in %HTML.CoreModules are not - affected by this directive. -
---# vim: et sw=4 sts=4 +HTML.AllowedModules +TYPE: lookup/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ A doctype comes with a set of usual modules to use. Without having + to mucking about with the doctypes, you can quickly activate or + disable these modules by specifying which modules you wish to allow + with this directive. This is most useful for unit testing specific + modules, although end users may find it useful for their own ends. +
++ If you specify a module that does not exist, the manager will silently + fail to use it, so be careful! User-defined modules are not affected + by this directive. Modules defined in %HTML.CoreModules are not + affected by this directive. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt index 151fb7b8264..75d680ee1eb 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt @@ -1,11 +1,11 @@ -HTML.Attr.Name.UseCDATA -TYPE: bool -DEFAULT: false -VERSION: 4.0.0 ---DESCRIPTION-- -The W3C specification DTD defines the name attribute to be CDATA, not ID, due -to limitations of DTD. In certain documents, this relaxed behavior is desired, -whether it is to specify duplicate names, or to specify names that would be -illegal IDs (for example, names that begin with a digit.) Set this configuration -directive to true to use the relaxed parsing rules. ---# vim: et sw=4 sts=4 +HTML.Attr.Name.UseCDATA +TYPE: bool +DEFAULT: false +VERSION: 4.0.0 +--DESCRIPTION-- +The W3C specification DTD defines the name attribute to be CDATA, not ID, due +to limitations of DTD. In certain documents, this relaxed behavior is desired, +whether it is to specify duplicate names, or to specify names that would be +illegal IDs (for example, names that begin with a digit.) Set this configuration +directive to true to use the relaxed parsing rules. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt index 45ae469ec98..f32b802c6d5 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt @@ -1,18 +1,18 @@ -HTML.BlockWrapper -TYPE: string -VERSION: 1.3.0 -DEFAULT: 'p' ---DESCRIPTION-- - -- String name of element to wrap inline elements that are inside a block - context. This only occurs in the children of blockquote in strict mode. -
-
- Example: by default value,
- <blockquote>Foo</blockquote> would become
- <blockquote><p>Foo</p></blockquote>.
- The <p> tags can be replaced with whatever you desire,
- as long as it is a block level element.
-
+ String name of element to wrap inline elements that are inside a block + context. This only occurs in the children of blockquote in strict mode. +
+
+ Example: by default value,
+ <blockquote>Foo</blockquote> would become
+ <blockquote><p>Foo</p></blockquote>.
+ The <p> tags can be replaced with whatever you desire,
+ as long as it is a block level element.
+
- Certain modularized doctypes (XHTML, namely), have certain modules - that must be included for the doctype to be an conforming document - type: put those modules here. By default, XHTML's core modules - are used. You can set this to a blank array to disable core module - protection, but this is not recommended. -
---# vim: et sw=4 sts=4 +HTML.CoreModules +TYPE: lookup +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'Structure' => true, + 'Text' => true, + 'Hypertext' => true, + 'List' => true, + 'NonXMLCommonAttributes' => true, + 'XMLCommonAttributes' => true, + 'CommonAttributes' => true, +) +--DESCRIPTION-- + ++ Certain modularized doctypes (XHTML, namely), have certain modules + that must be included for the doctype to be an conforming document + type: put those modules here. By default, XHTML's core modules + are used. You can set this to a blank array to disable core module + protection, but this is not recommended. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt index 6ed70b599f4..187c0a0d5e1 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt @@ -1,9 +1,9 @@ -HTML.CustomDoctype -TYPE: string/null -VERSION: 2.0.1 -DEFAULT: NULL ---DESCRIPTION-- - -A custom doctype for power-users who defined their own document -type. This directive only applies when %HTML.Doctype is blank. ---# vim: et sw=4 sts=4 +HTML.CustomDoctype +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +A custom doctype for power-users who defined their own document +type. This directive only applies when %HTML.Doctype is blank. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt index 103db754a28..f5433e3f1fb 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt @@ -1,33 +1,33 @@ -HTML.DefinitionID -TYPE: string/null -DEFAULT: NULL -VERSION: 2.0.0 ---DESCRIPTION-- - -- Unique identifier for a custom-built HTML definition. If you edit - the raw version of the HTMLDefinition, introducing changes that the - configuration object does not reflect, you must specify this variable. - If you change your custom edits, you should change this directive, or - clear your cache. Example: -
-
-$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', '1');
-$def = $config->getHTMLDefinition();
-$def->addAttribute('a', 'tabindex', 'Number');
-
-- In the above example, the configuration is still at the defaults, but - using the advanced API, an extra attribute has been added. The - configuration object normally has no way of knowing that this change - has taken place, so it needs an extra directive: %HTML.DefinitionID. - If someone else attempts to use the default configuration, these two - pieces of code will not clobber each other in the cache, since one has - an extra directive attached to it. -
-- You must specify a value to this directive to use the - advanced API features. -
---# vim: et sw=4 sts=4 +HTML.DefinitionID +TYPE: string/null +DEFAULT: NULL +VERSION: 2.0.0 +--DESCRIPTION-- + ++ Unique identifier for a custom-built HTML definition. If you edit + the raw version of the HTMLDefinition, introducing changes that the + configuration object does not reflect, you must specify this variable. + If you change your custom edits, you should change this directive, or + clear your cache. Example: +
+
+$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', '1');
+$def = $config->getHTMLDefinition();
+$def->addAttribute('a', 'tabindex', 'Number');
+
++ In the above example, the configuration is still at the defaults, but + using the advanced API, an extra attribute has been added. The + configuration object normally has no way of knowing that this change + has taken place, so it needs an extra directive: %HTML.DefinitionID. + If someone else attempts to use the default configuration, these two + pieces of code will not clobber each other in the cache, since one has + an extra directive attached to it. +
++ You must specify a value to this directive to use the + advanced API features. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt index 229ae0267a6..0bb5a718d5f 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt @@ -1,16 +1,16 @@ -HTML.DefinitionRev -TYPE: int -VERSION: 2.0.0 -DEFAULT: 1 ---DESCRIPTION-- - -- Revision identifier for your custom definition specified in - %HTML.DefinitionID. This serves the same purpose: uniquely identifying - your custom definition, but this one does so in a chronological - context: revision 3 is more up-to-date then revision 2. Thus, when - this gets incremented, the cache handling is smart enough to clean - up any older revisions of your definition as well as flush the - cache. -
---# vim: et sw=4 sts=4 +HTML.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + ++ Revision identifier for your custom definition specified in + %HTML.DefinitionID. This serves the same purpose: uniquely identifying + your custom definition, but this one does so in a chronological + context: revision 3 is more up-to-date then revision 2. Thus, when + this gets incremented, the cache handling is smart enough to clean + up any older revisions of your definition as well as flush the + cache. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt index 9dab497f2f3..a6969b99571 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt @@ -1,11 +1,11 @@ -HTML.Doctype -TYPE: string/null -DEFAULT: NULL ---DESCRIPTION-- -Doctype to use during filtering. Technically speaking this is not actually -a doctype (as it does not identify a corresponding DTD), but we are using -this name for sake of simplicity. When non-blank, this will override any -older directives like %HTML.XHTML or %HTML.Strict. ---ALLOWED-- -'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1' ---# vim: et sw=4 sts=4 +HTML.Doctype +TYPE: string/null +DEFAULT: NULL +--DESCRIPTION-- +Doctype to use during filtering. Technically speaking this is not actually +a doctype (as it does not identify a corresponding DTD), but we are using +this name for sake of simplicity. When non-blank, this will override any +older directives like %HTML.XHTML or %HTML.Strict. +--ALLOWED-- +'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1' +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt index 7878dc0bf64..08d641f954a 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt @@ -1,11 +1,11 @@ -HTML.FlashAllowFullScreen -TYPE: bool -VERSION: 4.2.0 -DEFAULT: false ---DESCRIPTION-- -
- Whether or not to permit embedded Flash content from
- %HTML.SafeObject to expand to the full screen. Corresponds to
- the allowFullScreen parameter.
-
+ Whether or not to permit embedded Flash content from
+ %HTML.SafeObject to expand to the full screen. Corresponds to
+ the allowFullScreen parameter.
+
- While this directive is similar to %HTML.AllowedAttributes, for
- forwards-compatibility with XML, this attribute has a different syntax. Instead of
- tag.attr, use tag@attr. To disallow href
- attributes in a tags, set this directive to
- a@href. You can also disallow an attribute globally with
- attr or *@attr (either syntax is fine; the latter
- is provided for consistency with %HTML.AllowedAttributes).
-
- Warning: This directive complements %HTML.ForbiddenElements, - accordingly, check - out that directive for a discussion of why you - should think twice before using this directive. -
---# vim: et sw=4 sts=4 +HTML.ForbiddenAttributes +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +
+ While this directive is similar to %HTML.AllowedAttributes, for
+ forwards-compatibility with XML, this attribute has a different syntax. Instead of
+ tag.attr, use tag@attr. To disallow href
+ attributes in a tags, set this directive to
+ a@href. You can also disallow an attribute globally with
+ attr or *@attr (either syntax is fine; the latter
+ is provided for consistency with %HTML.AllowedAttributes).
+
+ Warning: This directive complements %HTML.ForbiddenElements, + accordingly, check + out that directive for a discussion of why you + should think twice before using this directive. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt index 93a53e14fb4..40466c463d2 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt @@ -1,20 +1,20 @@ -HTML.ForbiddenElements -TYPE: lookup -VERSION: 3.1.0 -DEFAULT: array() ---DESCRIPTION-- -- This was, perhaps, the most requested feature ever in HTML - Purifier. Please don't abuse it! This is the logical inverse of - %HTML.AllowedElements, and it will override that directive, or any - other directive. -
-
- If possible, %HTML.Allowed is recommended over this directive, because it
- can sometimes be difficult to tell whether or not you've forbidden all of
- the behavior you would like to disallow. If you forbid img
- with the expectation of preventing images on your site, you'll be in for
- a nasty surprise when people start using the background-image
- CSS property.
-
+ This was, perhaps, the most requested feature ever in HTML + Purifier. Please don't abuse it! This is the logical inverse of + %HTML.AllowedElements, and it will override that directive, or any + other directive. +
+
+ If possible, %HTML.Allowed is recommended over this directive, because it
+ can sometimes be difficult to tell whether or not you've forbidden all of
+ the behavior you would like to disallow. If you forbid img
+ with the expectation of preventing images on your site, you'll be in for
+ a nasty surprise when people start using the background-image
+ CSS property.
+
- This directive controls the maximum number of pixels in the width and
- height attributes in img tags. This is
- in place to prevent imagecrash attacks, disable with null at your own risk.
- This directive is similar to %CSS.MaxImgLength, and both should be
- concurrently edited, although there are
- subtle differences in the input format (the HTML max is an integer).
-
+ This directive controls the maximum number of pixels in the width and
+ height attributes in img tags. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %CSS.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the HTML max is an integer).
+
- String name of element that HTML fragment passed to library will be - inserted in. An interesting variation would be using span as the - parent element, meaning that only inline tags would be allowed. -
---# vim: et sw=4 sts=4 +HTML.Parent +TYPE: string +VERSION: 1.3.0 +DEFAULT: 'div' +--DESCRIPTION-- + ++ String name of element that HTML fragment passed to library will be + inserted in. An interesting variation would be using span as the + parent element, meaning that only inline tags would be allowed. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt index dfb720496da..b3c45e19094 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt @@ -1,12 +1,12 @@ -HTML.Proprietary -TYPE: bool -VERSION: 3.1.0 -DEFAULT: false ---DESCRIPTION-- -
- Whether or not to allow proprietary elements and attributes in your
- documents, as per HTMLPurifier_HTMLModule_Proprietary.
- Warning: This can cause your documents to stop
- validating!
-
+ Whether or not to allow proprietary elements and attributes in your
+ documents, as per HTMLPurifier_HTMLModule_Proprietary.
+ Warning: This can cause your documents to stop
+ validating!
+
- Whether or not to permit embed tags in documents, with a number of extra - security features added to prevent script execution. This is similar to - what websites like MySpace do to embed tags. Embed is a proprietary - element and will cause your website to stop validating; you should - see if you can use %Output.FlashCompat with %HTML.SafeObject instead - first.
---# vim: et sw=4 sts=4 +HTML.SafeEmbed +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- ++ Whether or not to permit embed tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to embed tags. Embed is a proprietary + element and will cause your website to stop validating; you should + see if you can use %Output.FlashCompat with %HTML.SafeObject instead + first.
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt index 5eb6ec2b5a0..295a8cf6608 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt @@ -1,13 +1,13 @@ -HTML.SafeIframe -TYPE: bool -VERSION: 4.4.0 -DEFAULT: false ---DESCRIPTION-- -- Whether or not to permit iframe tags in untrusted documents. This - directive must be accompanied by a whitelist of permitted iframes, - such as %URI.SafeIframeRegexp, otherwise it will fatally error. - This directive has no effect on strict doctypes, as iframes are not - valid. -
---# vim: et sw=4 sts=4 +HTML.SafeIframe +TYPE: bool +VERSION: 4.4.0 +DEFAULT: false +--DESCRIPTION-- ++ Whether or not to permit iframe tags in untrusted documents. This + directive must be accompanied by a whitelist of permitted iframes, + such as %URI.SafeIframeRegexp, otherwise it will fatally error. + This directive has no effect on strict doctypes, as iframes are not + valid. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt index ceb342e22b7..07f6e536e37 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt @@ -1,13 +1,13 @@ -HTML.SafeObject -TYPE: bool -VERSION: 3.1.1 -DEFAULT: false ---DESCRIPTION-- -- Whether or not to permit object tags in documents, with a number of extra - security features added to prevent script execution. This is similar to - what websites like MySpace do to object tags. You should also enable - %Output.FlashCompat in order to generate Internet Explorer - compatibility code for your object tags. -
---# vim: et sw=4 sts=4 +HTML.SafeObject +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- ++ Whether or not to permit object tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to object tags. You should also enable + %Output.FlashCompat in order to generate Internet Explorer + compatibility code for your object tags. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt index 5ebc7a19d54..641b4a8d6b4 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt @@ -1,10 +1,10 @@ -HTML.SafeScripting -TYPE: lookup -VERSION: 4.5.0 -DEFAULT: array() ---DESCRIPTION-- -- Whether or not to permit script tags to external scripts in documents. - Inline scripting is not allowed, and the script must match an explicit whitelist. -
---# vim: et sw=4 sts=4 +HTML.SafeScripting +TYPE: lookup +VERSION: 4.5.0 +DEFAULT: array() +--DESCRIPTION-- ++ Whether or not to permit script tags to external scripts in documents. + Inline scripting is not allowed, and the script must match an explicit whitelist. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt index a8b1de56bef..d99663a5ee5 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt @@ -1,9 +1,9 @@ -HTML.Strict -TYPE: bool -VERSION: 1.3.0 -DEFAULT: false -DEPRECATED-VERSION: 1.7.0 -DEPRECATED-USE: HTML.Doctype ---DESCRIPTION-- -Determines whether or not to use Transitional (loose) or Strict rulesets. ---# vim: et sw=4 sts=4 +HTML.Strict +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +DEPRECATED-VERSION: 1.7.0 +DEPRECATED-USE: HTML.Doctype +--DESCRIPTION-- +Determines whether or not to use Transitional (loose) or Strict rulesets. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt index 587a16778b2..d65f0d041a9 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt @@ -1,8 +1,8 @@ -HTML.TargetBlank -TYPE: bool -VERSION: 4.4.0 -DEFAULT: FALSE ---DESCRIPTION-- -If enabled,target=blank attributes are added to all outgoing links.
-(This includes links from an HTTPS version of a page to an HTTP version.)
---# vim: et sw=4 sts=4
+HTML.TargetBlank
+TYPE: bool
+VERSION: 4.4.0
+DEFAULT: FALSE
+--DESCRIPTION--
+If enabled, target=blank attributes are added to all outgoing links.
+(This includes links from an HTTPS version of a page to an HTTP version.)
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt
index dd514c0def2..05cb3424f89 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txt
@@ -1,10 +1,10 @@
---# vim: et sw=4 sts=4
-HTML.TargetNoopener
-TYPE: bool
-VERSION: 4.8.0
-DEFAULT: TRUE
---DESCRIPTION--
-If enabled, noopener rel attributes are added to links which have
-a target attribute associated with them. This prevents malicious
-destinations from overwriting the original window.
---# vim: et sw=4 sts=4
+--# vim: et sw=4 sts=4
+HTML.TargetNoopener
+TYPE: bool
+VERSION: 4.8.0
+DEFAULT: TRUE
+--DESCRIPTION--
+If enabled, noopener rel attributes are added to links which have
+a target attribute associated with them. This prevents malicious
+destinations from overwriting the original window.
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt
index cb5a0b0e5e1..993a81704ee 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txt
@@ -1,9 +1,9 @@
-HTML.TargetNoreferrer
-TYPE: bool
-VERSION: 4.8.0
-DEFAULT: TRUE
---DESCRIPTION--
-If enabled, noreferrer rel attributes are added to links which have
-a target attribute associated with them. This prevents malicious
-destinations from overwriting the original window.
---# vim: et sw=4 sts=4
+HTML.TargetNoreferrer
+TYPE: bool
+VERSION: 4.8.0
+DEFAULT: TRUE
+--DESCRIPTION--
+If enabled, noreferrer rel attributes are added to links which have
+a target attribute associated with them. This prevents malicious
+destinations from overwriting the original window.
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt
index b4c271b7fac..602453f6ee6 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt
@@ -1,8 +1,8 @@
-HTML.TidyAdd
-TYPE: lookup
-VERSION: 2.0.0
-DEFAULT: array()
---DESCRIPTION--
-
-Fixes to add to the default set of Tidy fixes as per your level.
---# vim: et sw=4 sts=4
+HTML.TidyAdd
+TYPE: lookup
+VERSION: 2.0.0
+DEFAULT: array()
+--DESCRIPTION--
+
+Fixes to add to the default set of Tidy fixes as per your level.
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt
index 4186ccd0d19..bf943e8f011 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt
@@ -1,24 +1,24 @@
-HTML.TidyLevel
-TYPE: string
-VERSION: 2.0.0
-DEFAULT: 'medium'
---DESCRIPTION--
-
-General level of cleanliness the Tidy module should enforce. -There are four allowed values:
--
-
- none -
- No extra tidying should be done -
- light -
- Only fix elements that would be discarded otherwise due to - lack of support in doctype -
- medium -
- Enforce best practices -
- heavy -
- Transform all deprecated elements and attributes to standards - compliant equivalents -
General level of cleanliness the Tidy module should enforce. +There are four allowed values:
+-
+
- none +
- No extra tidying should be done +
- light +
- Only fix elements that would be discarded otherwise due to + lack of support in doctype +
- medium +
- Enforce best practices +
- heavy +
- Transform all deprecated elements and attributes to standards + compliant equivalents +
- If true, HTML Purifier will protect against Internet Explorer's
- mishandling of the innerHTML attribute by appending
- a space to any attribute that does not contain angled brackets, spaces
- or quotes, but contains a backtick. This slightly changes the
- semantics of any given attribute, so if this is unacceptable and
- you do not use innerHTML on any of your pages, you can
- turn this directive off.
-
+ If true, HTML Purifier will protect against Internet Explorer's
+ mishandling of the innerHTML attribute by appending
+ a space to any attribute that does not contain angled brackets, spaces
+ or quotes, but contains a backtick. This slightly changes the
+ semantics of any given attribute, so if this is unacceptable and
+ you do not use innerHTML on any of your pages, you can
+ turn this directive off.
+
- If true, HTML Purifier will generate Internet Explorer compatibility - code for all object code. This is highly recommended if you enable - %HTML.SafeObject. -
---# vim: et sw=4 sts=4 +Output.FlashCompat +TYPE: bool +VERSION: 4.1.0 +DEFAULT: false +--DESCRIPTION-- ++ If true, HTML Purifier will generate Internet Explorer compatibility + code for all object code. This is highly recommended if you enable + %HTML.SafeObject. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt index 79f8ad82cfc..4bb90252318 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt @@ -1,13 +1,13 @@ -Output.Newline -TYPE: string/null -VERSION: 2.0.1 -DEFAULT: NULL ---DESCRIPTION-- - -- Newline string to format final output with. If left null, HTML Purifier - will auto-detect the default newline type of the system and use that; - you can manually override it here. Remember, \r\n is Windows, \r - is Mac, and \n is Unix. -
---# vim: et sw=4 sts=4 +Output.Newline +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + ++ Newline string to format final output with. If left null, HTML Purifier + will auto-detect the default newline type of the system and use that; + you can manually override it here. Remember, \r\n is Windows, \r + is Mac, and \n is Unix. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt index 232b02362a4..32231065179 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt @@ -1,14 +1,14 @@ -Output.SortAttr -TYPE: bool -VERSION: 3.2.0 -DEFAULT: false ---DESCRIPTION-- -
- If true, HTML Purifier will sort attributes by name before writing them back
- to the document, converting a tag like: <el b="" a="" c="" />
- to <el a="" b="" c="" />. This is a workaround for
- a bug in FCKeditor which causes it to swap attributes order, adding noise
- to text diffs. If you're not seeing this bug, chances are, you don't need
- this directive.
-
+ If true, HTML Purifier will sort attributes by name before writing them back
+ to the document, converting a tag like: <el b="" a="" c="" />
+ to <el a="" b="" c="" />. This is a workaround for
+ a bug in FCKeditor which causes it to swap attributes order, adding noise
+ to text diffs. If you're not seeing this bug, chances are, you don't need
+ this directive.
+
- 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. Tidy is a non-default - extension, and this directive will silently fail if Tidy is not - available. -
-- If you are looking to make the overall look of your page's source - better, I recommend running Tidy on the entire page rather than just - user-content (after all, the indentation relative to the containing - blocks will be incorrect). -
---ALIASES-- -Core.TidyFormat ---# vim: et sw=4 sts=4 +Output.TidyFormat +TYPE: bool +VERSION: 1.1.1 +DEFAULT: false +--DESCRIPTION-- ++ 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. Tidy is a non-default + extension, and this directive will silently fail if Tidy is not + available. +
++ If you are looking to make the overall look of your page's source + better, I recommend running Tidy on the entire page rather than just + user-content (after all, the indentation relative to the containing + blocks will be incorrect). +
+--ALIASES-- +Core.TidyFormat +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt index 071bc0295df..d1820cdbd5d 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt @@ -1,7 +1,7 @@ -Test.ForceNoIconv -TYPE: bool -DEFAULT: false ---DESCRIPTION-- -When set to true, HTMLPurifier_Encoder will act as if iconv does not exist -and use only pure PHP implementations. ---# vim: et sw=4 sts=4 +Test.ForceNoIconv +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When set to true, HTMLPurifier_Encoder will act as if iconv does not exist +and use only pure PHP implementations. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt index eb97307e200..0b0533a77f4 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt @@ -1,18 +1,18 @@ -URI.AllowedSchemes -TYPE: lookup ---DEFAULT-- -array ( - 'http' => true, - 'https' => true, - 'mailto' => true, - 'ftp' => true, - 'nntp' => true, - 'news' => true, - 'tel' => true, -) ---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 thedata and file
-URI schemes, but they are not enabled by default.
---# vim: et sw=4 sts=4
+URI.AllowedSchemes
+TYPE: lookup
+--DEFAULT--
+array (
+ 'http' => true,
+ 'https' => true,
+ 'mailto' => true,
+ 'ftp' => true,
+ 'nntp' => true,
+ 'news' => true,
+ 'tel' => true,
+)
+--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 data and file
+URI schemes, but they are not enabled by default.
+--# vim: et sw=4 sts=4
diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt
index 876f0680cf2..ba4730808fb 100644
--- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt
+++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt
@@ -1,17 +1,17 @@
-URI.Base
-TYPE: string/null
-VERSION: 2.1.0
-DEFAULT: NULL
---DESCRIPTION--
-
-- The base URI is the URI of the document this purified HTML will be - inserted into. This information is important if HTML Purifier needs - to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute - is on. You may use a non-absolute URI for this value, but behavior - may vary (%URI.MakeAbsolute deals nicely with both absolute and - relative paths, but forwards-compatibility is not guaranteed). - Warning: If set, the scheme on this URI - overrides the one specified by %URI.DefaultScheme. -
---# vim: et sw=4 sts=4 +URI.Base +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ The base URI is the URI of the document this purified HTML will be + inserted into. This information is important if HTML Purifier needs + to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute + is on. You may use a non-absolute URI for this value, but behavior + may vary (%URI.MakeAbsolute deals nicely with both absolute and + relative paths, but forwards-compatibility is not guaranteed). + Warning: If set, the scheme on this URI + overrides the one specified by %URI.DefaultScheme. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt index 834bc08c0ba..981e443251e 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt @@ -1,15 +1,15 @@ -URI.DefaultScheme -TYPE: string/null -DEFAULT: 'http' ---DESCRIPTION-- - -- Defines through what scheme the output will be served, in order to - select the proper object validator when no scheme information is present. -
- -- Starting with HTML Purifier 4.9.0, the default scheme can be null, in - which case we reject all URIs which do not have explicit schemes. -
---# vim: et sw=4 sts=4 +URI.DefaultScheme +TYPE: string/null +DEFAULT: 'http' +--DESCRIPTION-- + ++ Defines through what scheme the output will be served, in order to + select the proper object validator when no scheme information is present. +
+ ++ Starting with HTML Purifier 4.9.0, the default scheme can be null, in + which case we reject all URIs which do not have explicit schemes. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt index f05312ba862..523204c08a9 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt @@ -1,11 +1,11 @@ -URI.DefinitionID -TYPE: string/null -VERSION: 2.1.0 -DEFAULT: NULL ---DESCRIPTION-- - -- Unique identifier for a custom-built URI definition. If you want - to add custom URIFilters, you must specify this value. -
---# vim: et sw=4 sts=4 +URI.DefinitionID +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ Unique identifier for a custom-built URI definition. If you want + to add custom URIFilters, you must specify this value. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt index 80cfea93f72..a9c07b1a392 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt @@ -1,11 +1,11 @@ -URI.DefinitionRev -TYPE: int -VERSION: 2.1.0 -DEFAULT: 1 ---DESCRIPTION-- - -- Revision identifier for your custom definition. See - %HTML.DefinitionRev for details. -
---# vim: et sw=4 sts=4 +URI.DefinitionRev +TYPE: int +VERSION: 2.1.0 +DEFAULT: 1 +--DESCRIPTION-- + ++ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt index 71ce025a2dc..b19ca1d5b80 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt @@ -1,14 +1,14 @@ -URI.Disable -TYPE: bool -VERSION: 1.3.0 -DEFAULT: false ---DESCRIPTION-- - -- Disables all URIs in all forms. Not sure why you'd want to do that - (after all, the Internet's founded on the notion of a hyperlink). -
- ---ALIASES-- -Attr.DisableURI ---# vim: et sw=4 sts=4 +URI.Disable +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- + ++ Disables all URIs in all forms. Not sure why you'd want to do that + (after all, the Internet's founded on the notion of a hyperlink). +
+ +--ALIASES-- +Attr.DisableURI +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt index 13c122c8cec..9132ea4f5f6 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt @@ -1,11 +1,11 @@ -URI.DisableExternal -TYPE: bool -VERSION: 1.2.0 -DEFAULT: false ---DESCRIPTION-- -Disables links to external websites. This is a highly effective anti-spam -and anti-pagerank-leech measure, but comes at a hefty price: nolinks or -images outside of your domain will be allowed. Non-linkified URIs will -still be preserved. If you want to be able to link to subdomains or use -absolute URIs, specify %URI.Host for your website. ---# vim: et sw=4 sts=4 +URI.DisableExternal +TYPE: bool +VERSION: 1.2.0 +DEFAULT: false +--DESCRIPTION-- +Disables links to external websites. This is a highly effective anti-spam +and anti-pagerank-leech measure, but comes at a hefty price: nolinks or +images outside of your domain will be allowed. Non-linkified URIs will +still be preserved. If you want to be able to link to subdomains or use +absolute URIs, specify %URI.Host for your website. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt index abcc1efd613..d74bc1e3da6 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt @@ -1,13 +1,13 @@ -URI.DisableExternalResources -TYPE: bool -VERSION: 1.3.0 -DEFAULT: false ---DESCRIPTION-- -Disables the embedding of external resources, preventing users from -embedding things like images from other hosts. This prevents access -tracking (good for email viewers), bandwidth leeching, cross-site request -forging, goatse.cx posting, and other nasties, but also results in a loss -of end-user functionality (they can't directly post a pic they posted from -Flickr anymore). Use it if you don't have a robust user-content moderation -team. ---# vim: et sw=4 sts=4 +URI.DisableExternalResources +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- +Disables the embedding of external resources, preventing users from +embedding things like images from other hosts. This prevents access +tracking (good for email viewers), bandwidth leeching, cross-site request +forging, goatse.cx posting, and other nasties, but also results in a loss +of end-user functionality (they can't directly post a pic they posted from +Flickr anymore). Use it if you don't have a robust user-content moderation +team. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt index f891de49965..6c106144a00 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt @@ -1,15 +1,15 @@ -URI.DisableResources -TYPE: bool -VERSION: 4.2.0 -DEFAULT: false ---DESCRIPTION-- -- 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. -
-- Note: While this directive has been available since 1.3.0, - it didn't actually start doing anything until 4.2.0. -
---# vim: et sw=4 sts=4 +URI.DisableResources +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- ++ 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. +
++ Note: While this directive has been available since 1.3.0, + it didn't actually start doing anything until 4.2.0. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt index ee83b121dec..ba0e6bce194 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt @@ -1,19 +1,19 @@ -URI.Host -TYPE: string/null -VERSION: 1.2.0 -DEFAULT: NULL ---DESCRIPTION-- - -- Defines the domain name of the server, so we can determine whether or - an absolute URI is from your website or not. Not strictly necessary, - as users should be using relative URIs to reference resources on your - website. It will, however, let you use absolute URIs to link to - subdomains of the domain you post here: i.e. example.com will allow - sub.example.com. However, higher up domains will still be excluded: - if you set %URI.Host to sub.example.com, example.com will be blocked. - Note: This directive overrides %URI.Base because - a given page may be on a sub-domain, but you wish HTML Purifier to be - more relaxed and allow some of the parent domains too. -
---# vim: et sw=4 sts=4 +URI.Host +TYPE: string/null +VERSION: 1.2.0 +DEFAULT: NULL +--DESCRIPTION-- + ++ Defines the domain name of the server, so we can determine whether or + an absolute URI is from your website or not. Not strictly necessary, + as users should be using relative URIs to reference resources on your + website. It will, however, let you use absolute URIs to link to + subdomains of the domain you post here: i.e. example.com will allow + sub.example.com. However, higher up domains will still be excluded: + if you set %URI.Host to sub.example.com, example.com will be blocked. + Note: This directive overrides %URI.Base because + a given page may be on a sub-domain, but you wish HTML Purifier to be + more relaxed and allow some of the parent domains too. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt index 0b6df7625dc..825fef27694 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt @@ -1,9 +1,9 @@ -URI.HostBlacklist -TYPE: list -VERSION: 1.3.0 -DEFAULT: array() ---DESCRIPTION-- -List of strings that are forbidden in the host of any URI. Use it to kill -domain names of spam, etc. Note that it will catch anything in the domain, -so moo.com will catch moo.com.example.com. ---# vim: et sw=4 sts=4 +URI.HostBlacklist +TYPE: list +VERSION: 1.3.0 +DEFAULT: array() +--DESCRIPTION-- +List of strings that are forbidden in the host of any URI. Use it to kill +domain names of spam, etc. Note that it will catch anything in the domain, +so moo.com will catch moo.com.example.com. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt index 4214900a592..eb58c7f1a45 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt @@ -1,13 +1,13 @@ -URI.MakeAbsolute -TYPE: bool -VERSION: 2.1.0 -DEFAULT: false ---DESCRIPTION-- - -- Converts all URIs into absolute forms. This is useful when the HTML - being filtered assumes a specific base path, but will actually be - viewed in a different context (and setting an alternate base URI is - not possible). %URI.Base must be set for this directive to work. -
---# vim: et sw=4 sts=4 +URI.MakeAbsolute +TYPE: bool +VERSION: 2.1.0 +DEFAULT: false +--DESCRIPTION-- + ++ Converts all URIs into absolute forms. This is useful when the HTML + being filtered assumes a specific base path, but will actually be + viewed in a different context (and setting an alternate base URI is + not possible). %URI.Base must be set for this directive to work. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt index 58c81dcc441..bedd610d669 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt @@ -1,83 +1,83 @@ -URI.Munge -TYPE: string/null -VERSION: 1.3.0 -DEFAULT: NULL ---DESCRIPTION-- - -
- Munges all browsable (usually http, https and ftp)
- absolute URIs into another URI, usually a URI redirection service.
- This directive accepts a URI, formatted with a %s where
- the url-encoded original URI should be inserted (sample:
- http://www.google.com/url?q=%s).
-
- Uses for this directive: -
--
-
- - Prevent PageRank leaks, while being fairly transparent - to users (you may also want to add some client side JavaScript to - override the text in the statusbar). Notice: - Many security experts believe that this form of protection does not deter spam-bots. - -
- - Redirect users to a splash page telling them they are leaving your - website. While this is poor usability practice, it is often mandated - in corporate environments. - -
- Prior to HTML Purifier 3.1.1, this directive also enabled the munging
- of browsable external resources, which could break things if your redirection
- script was a splash page or used meta tags. To revert to
- previous behavior, please use %URI.MungeResources.
-
- You may want to also use %URI.MungeSecretKey along with this directive - in order to enforce what URIs your redirector script allows. Open - redirector scripts can be a security risk and negatively affect the - reputation of your domain name. -
-- Starting with HTML Purifier 3.1.1, there is also these substitutions: -
-| Key | -Description | -Example <a href=""> |
-
|---|---|---|
| %r | -1 - The URI embeds a resource (blank) - The URI is merely a link |
- - |
| %n | -The name of the tag this URI came from | -a | -
| %m | -The name of the attribute this URI came from | -href | -
| %p | -The name of the CSS property this URI came from, or blank if irrelevant | -- |
- Admittedly, these letters are somewhat arbitrary; the only stipulation - was that they couldn't be a through f. r is for resource (I would have preferred - e, but you take what you can get), n is for name, m - was picked because it came after n (and I couldn't use a), p is for - property. -
---# vim: et sw=4 sts=4 +URI.Munge +TYPE: string/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +
+ Munges all browsable (usually http, https and ftp)
+ absolute URIs into another URI, usually a URI redirection service.
+ This directive accepts a URI, formatted with a %s where
+ the url-encoded original URI should be inserted (sample:
+ http://www.google.com/url?q=%s).
+
+ Uses for this directive: +
+-
+
- + Prevent PageRank leaks, while being fairly transparent + to users (you may also want to add some client side JavaScript to + override the text in the statusbar). Notice: + Many security experts believe that this form of protection does not deter spam-bots. + +
- + Redirect users to a splash page telling them they are leaving your + website. While this is poor usability practice, it is often mandated + in corporate environments. + +
+ Prior to HTML Purifier 3.1.1, this directive also enabled the munging
+ of browsable external resources, which could break things if your redirection
+ script was a splash page or used meta tags. To revert to
+ previous behavior, please use %URI.MungeResources.
+
+ You may want to also use %URI.MungeSecretKey along with this directive + in order to enforce what URIs your redirector script allows. Open + redirector scripts can be a security risk and negatively affect the + reputation of your domain name. +
++ Starting with HTML Purifier 3.1.1, there is also these substitutions: +
+| Key | +Description | +Example <a href=""> |
+
|---|---|---|
| %r | +1 - The URI embeds a resource (blank) - The URI is merely a link |
+ + |
| %n | +The name of the tag this URI came from | +a | +
| %m | +The name of the attribute this URI came from | +href | +
| %p | +The name of the CSS property this URI came from, or blank if irrelevant | ++ |
+ Admittedly, these letters are somewhat arbitrary; the only stipulation + was that they couldn't be a through f. r is for resource (I would have preferred + e, but you take what you can get), n is for name, m + was picked because it came after n (and I couldn't use a), p is for + property. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt index 6fce0fdc373..ed4b5b0d023 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt @@ -1,17 +1,17 @@ -URI.MungeResources -TYPE: bool -VERSION: 3.1.1 -DEFAULT: false ---DESCRIPTION-- -
- If true, any URI munging directives like %URI.Munge
- will also apply to embedded resources, such as <img src="">.
- Be careful enabling this directive if you have a redirector script
- that does not use the Location HTTP header; all of your images
- and other embedded resources will break.
-
- Warning: It is strongly advised you use this in conjunction - %URI.MungeSecretKey to mitigate the security risk of an open redirector. -
---# vim: et sw=4 sts=4 +URI.MungeResources +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +
+ If true, any URI munging directives like %URI.Munge
+ will also apply to embedded resources, such as <img src="">.
+ Be careful enabling this directive if you have a redirector script
+ that does not use the Location HTTP header; all of your images
+ and other embedded resources will break.
+
+ Warning: It is strongly advised you use this in conjunction + %URI.MungeSecretKey to mitigate the security risk of an open redirector. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt index 1e17c1d461c..123b6e26b80 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt @@ -1,30 +1,30 @@ -URI.MungeSecretKey -TYPE: string/null -VERSION: 3.1.1 -DEFAULT: NULL ---DESCRIPTION-- -- This directive enables secure checksum generation along with %URI.Munge. - It should be set to a secure key that is not shared with anyone else. - The checksum can be placed in the URI using %t. Use of this checksum - affords an additional level of protection by allowing a redirector - to check if a URI has passed through HTML Purifier with this line: -
- -$checksum === hash_hmac("sha256", $url, $secret_key)
-
-- If the output is TRUE, the redirector script should accept the URI. -
- -- Please note that it would still be possible for an attacker to procure - secure hashes en-mass by abusing your website's Preview feature or the - like, but this service affords an additional level of protection - that should be combined with website blacklisting. -
- -- Remember this has no effect if %URI.Munge is not on. -
---# vim: et sw=4 sts=4 +URI.MungeSecretKey +TYPE: string/null +VERSION: 3.1.1 +DEFAULT: NULL +--DESCRIPTION-- ++ This directive enables secure checksum generation along with %URI.Munge. + It should be set to a secure key that is not shared with anyone else. + The checksum can be placed in the URI using %t. Use of this checksum + affords an additional level of protection by allowing a redirector + to check if a URI has passed through HTML Purifier with this line: +
+ +$checksum === hash_hmac("sha256", $url, $secret_key)
+
++ If the output is TRUE, the redirector script should accept the URI. +
+ ++ Please note that it would still be possible for an attacker to procure + secure hashes en-mass by abusing your website's Preview feature or the + like, but this service affords an additional level of protection + that should be combined with website blacklisting. +
+ ++ Remember this has no effect if %URI.Munge is not on. +
+--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt index 23331a4e790..8b387dea31f 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt @@ -1,9 +1,9 @@ -URI.OverrideAllowedSchemes -TYPE: bool -DEFAULT: true ---DESCRIPTION-- -If this is set to true (which it is by default), you can override -%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the -registry. If false, you will also have to update that directive in order -to add more schemes. ---# vim: et sw=4 sts=4 +URI.OverrideAllowedSchemes +TYPE: bool +DEFAULT: true +--DESCRIPTION-- +If this is set to true (which it is by default), you can override +%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the +registry. If false, you will also have to update that directive in order +to add more schemes. +--# vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt index 79084832be3..7e1f227f793 100644 --- a/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt +++ b/lib/htmlpurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt @@ -1,22 +1,22 @@ -URI.SafeIframeRegexp -TYPE: string/null -VERSION: 4.4.0 -DEFAULT: NULL ---DESCRIPTION-- -- A PCRE regular expression that will be matched against an iframe URI. This is - a relatively inflexible scheme, but works well enough for the most common - use-case of iframes: embedded video. This directive only has an effect if - %HTML.SafeIframe is enabled. Here are some example values: -
--
-
%^http://www.youtube.com/embed/%- Allow YouTube videos
- %^http://player.vimeo.com/video/%- Allow Vimeo videos
- %^http://(www.youtube.com/embed/|player.vimeo.com/video/)%- Allow both
-
- Note that this directive does not give you enough granularity to, say, disable
- all autoplay videos. Pipe up on the HTML Purifier forums if this
- is a capability you want.
-
+ A PCRE regular expression that will be matched against an iframe URI. This is + a relatively inflexible scheme, but works well enough for the most common + use-case of iframes: embedded video. This directive only has an effect if + %HTML.SafeIframe is enabled. Here are some example values: +
+-
+
%^http://www.youtube.com/embed/%- Allow YouTube videos
+ %^http://player.vimeo.com/video/%- Allow Vimeo videos
+ %^http://(www.youtube.com/embed/|player.vimeo.com/video/)%- Allow both
+
+ Note that this directive does not give you enough granularity to, say, disable
+ all autoplay videos. Pipe up on the HTML Purifier forums if this
+ is a capability you want.
+
' . $this->locale->getMessage('ErrorCollector: No errors') . '
'; - } else { - return '- ' . implode('
- ', $ret) . '
';
- // W3C uses an icon to indicate the severity of the error.
- $error = $this->locale->getErrorName($severity);
- $string .= "$error ";
- if (!is_null($line) && !is_null($col)) {
- $string .= "Line $line, Column $col: ";
- } else {
- $string .= 'End of Document: ';
- }
- $string .= '' . $this->generator->escape($msg) . ' ';
- $string .= '
';
- // Here, have a marker for the character on the column appropriate.
- // Be sure to clip extremely long lines.
- //$string .= ''; - //$string .= ''; - //$string .= ''; - $ret[] = $string; - } - foreach ($current->children as $array) { - $context[] = $current; - $stack = array_merge($stack, array_reverse($array, true)); - for ($i = count($array); $i > 0; $i--) { - $context_stack[] = $context; - } - } - } - } -} - -// vim: et sw=4 sts=4 +locale =& $context->get('Locale'); + $this->context = $context; + $this->_current =& $this->_stacks[0]; + $this->errors =& $this->_stacks[0]; + } + + /** + * Sends an error message to the collector for later use + * @param int $severity Error severity, PHP error style (don't use E_USER_) + * @param string $msg Error message text + */ + public function send($severity, $msg) + { + $args = array(); + if (func_num_args() > 2) { + $args = func_get_args(); + array_shift($args); + unset($args[0]); + } + + $token = $this->context->get('CurrentToken', true); + $line = $token ? $token->line : $this->context->get('CurrentLine', true); + $col = $token ? $token->col : $this->context->get('CurrentCol', true); + $attr = $this->context->get('CurrentAttr', true); + + // perform special substitutions, also add custom parameters + $subst = array(); + if (!is_null($token)) { + $args['CurrentToken'] = $token; + } + if (!is_null($attr)) { + $subst['$CurrentAttr.Name'] = $attr; + if (isset($token->attr[$attr])) { + $subst['$CurrentAttr.Value'] = $token->attr[$attr]; + } + } + + if (empty($args)) { + $msg = $this->locale->getMessage($msg); + } else { + $msg = $this->locale->formatMessage($msg, $args); + } + + if (!empty($subst)) { + $msg = strtr($msg, $subst); + } + + // (numerically indexed) + $error = array( + self::LINENO => $line, + self::SEVERITY => $severity, + self::MESSAGE => $msg, + self::CHILDREN => array() + ); + $this->_current[] = $error; + + // NEW CODE BELOW ... + // Top-level errors are either: + // TOKEN type, if $value is set appropriately, or + // "syntax" type, if $value is null + $new_struct = new HTMLPurifier_ErrorStruct(); + $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN; + if ($token) { + $new_struct->value = clone $token; + } + if (is_int($line) && is_int($col)) { + if (isset($this->lines[$line][$col])) { + $struct = $this->lines[$line][$col]; + } else { + $struct = $this->lines[$line][$col] = $new_struct; + } + // These ksorts may present a performance problem + ksort($this->lines[$line], SORT_NUMERIC); + } else { + if (isset($this->lines[-1])) { + $struct = $this->lines[-1]; + } else { + $struct = $this->lines[-1] = $new_struct; + } + } + ksort($this->lines, SORT_NUMERIC); + + // Now, check if we need to operate on a lower structure + if (!empty($attr)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr); + if (!$struct->value) { + $struct->value = array($attr, 'PUT VALUE HERE'); + } + } + if (!empty($cssprop)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop); + if (!$struct->value) { + // if we tokenize CSS this might be a little more difficult to do + $struct->value = array($cssprop, 'PUT VALUE HERE'); + } + } + + // Ok, structs are all setup, now time to register the error + $struct->addError($severity, $msg); + } + + /** + * Retrieves raw error data for custom formatter to use + */ + public function getRaw() + { + return $this->errors; + } + + /** + * Default HTML formatting implementation for error messages + * @param HTMLPurifier_Config $config Configuration, vital for HTML output nature + * @param array $errors Errors array to display; used for recursion. + * @return string + */ + public function getHTMLFormatted($config, $errors = null) + { + $ret = array(); + + $this->generator = new HTMLPurifier_Generator($config, $this->context); + if ($errors === null) { + $errors = $this->errors; + } + + // 'At line' message needs to be removed + + // generation code for new structure goes here. It needs to be recursive. + foreach ($this->lines as $line => $col_array) { + if ($line == -1) { + continue; + } + foreach ($col_array as $col => $struct) { + $this->_renderStruct($ret, $struct, $line, $col); + } + } + if (isset($this->lines[-1])) { + $this->_renderStruct($ret, $this->lines[-1]); + } + + if (empty($errors)) { + return '
' . $this->locale->getMessage('ErrorCollector: No errors') . '
'; + } else { + return '- ' . implode('
- ', $ret) . '
';
+ // W3C uses an icon to indicate the severity of the error.
+ $error = $this->locale->getErrorName($severity);
+ $string .= "$error ";
+ if (!is_null($line) && !is_null($col)) {
+ $string .= "Line $line, Column $col: ";
+ } else {
+ $string .= 'End of Document: ';
+ }
+ $string .= '' . $this->generator->escape($msg) . ' ';
+ $string .= '
';
+ // Here, have a marker for the character on the column appropriate.
+ // Be sure to clip extremely long lines.
+ //$string .= ''; + //$string .= ''; + //$string .= ''; + $ret[] = $string; + } + foreach ($current->children as $array) { + $context[] = $current; + $stack = array_merge($stack, array_reverse($array, true)); + for ($i = count($array); $i > 0; $i--) { + $context_stack[] = $context; + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/ErrorStruct.php b/lib/htmlpurifier/HTMLPurifier/ErrorStruct.php index cf869d32124..a6c0da29e80 100644 --- a/lib/htmlpurifier/HTMLPurifier/ErrorStruct.php +++ b/lib/htmlpurifier/HTMLPurifier/ErrorStruct.php @@ -1,74 +1,74 @@ -children[$type][$id])) { - $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); - $this->children[$type][$id]->type = $type; - } - return $this->children[$type][$id]; - } - - /** - * @param int $severity - * @param string $message - */ - public function addError($severity, $message) - { - $this->errors[] = array($severity, $message); - } -} - -// vim: et sw=4 sts=4 +children[$type][$id])) { + $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); + $this->children[$type][$id]->type = $type; + } + return $this->children[$type][$id]; + } + + /** + * @param int $severity + * @param string $message + */ + public function addError($severity, $message) + { + $this->errors[] = array($severity, $message); + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Exception.php b/lib/htmlpurifier/HTMLPurifier/Exception.php index be85b4c560e..defe157e75d 100644 --- a/lib/htmlpurifier/HTMLPurifier/Exception.php +++ b/lib/htmlpurifier/HTMLPurifier/Exception.php @@ -1,12 +1,12 @@ -preFilter, - * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter, - * 1->postFilter. - * - * @note Methods are not declared abstract as it is perfectly legitimate - * for an implementation not to want anything to happen on a step - */ - -class HTMLPurifier_Filter -{ - - /** - * Name of the filter for identification purposes. - * @type string - */ - public $name; - - /** - * Pre-processor function, handles HTML before HTML Purifier - * @param string $html - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return string - */ - public function preFilter($html, $config, $context) - { - return $html; - } - - /** - * Post-processor function, handles HTML after HTML Purifier - * @param string $html - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return string - */ - public function postFilter($html, $config, $context) - { - return $html; - } -} - -// vim: et sw=4 sts=4 +preFilter, + * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter, + * 1->postFilter. + * + * @note Methods are not declared abstract as it is perfectly legitimate + * for an implementation not to want anything to happen on a step + */ + +class HTMLPurifier_Filter +{ + + /** + * Name of the filter for identification purposes. + * @type string + */ + public $name; + + /** + * Pre-processor function, handles HTML before HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function preFilter($html, $config, $context) + { + return $html; + } + + /** + * Post-processor function, handles HTML after HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + return $html; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php b/lib/htmlpurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php index 66f70b0fc00..5af24c2020e 100644 --- a/lib/htmlpurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php +++ b/lib/htmlpurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php @@ -1,341 +1,341 @@ - blocks from input HTML, cleans them up - * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') - * so they can be used elsewhere in the document. - * - * @note - * See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for - * sample usage. - * - * @note - * This filter can also be used on stylesheets not included in the - * document--something purists would probably prefer. Just directly - * call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS() - */ -class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter -{ - /** - * @type string - */ - public $name = 'ExtractStyleBlocks'; - - /** - * @type array - */ - private $_styleMatches = array(); - - /** - * @type csstidy - */ - private $_tidy; - - /** - * @type HTMLPurifier_AttrDef_HTML_ID - */ - private $_id_attrdef; - - /** - * @type HTMLPurifier_AttrDef_CSS_Ident - */ - private $_class_attrdef; - - /** - * @type HTMLPurifier_AttrDef_Enum - */ - private $_enum_attrdef; - - public function __construct() - { - $this->_tidy = new csstidy(); - $this->_tidy->set_cfg('lowercase_s', false); - $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); - $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); - $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( - array( - 'first-child', - 'link', - 'visited', - 'active', - 'hover', - 'focus' - ) - ); - } - - /** - * Save the contents of CSS blocks to style matches - * @param array $matches preg_replace style $matches array - */ - protected function styleCallback($matches) - { - $this->_styleMatches[] = $matches[1]; - } - - /** - * Removes inline - // we must not grab foo in a font-family prop). - if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { - $css = str_replace( - array('<', '>', '&'), - array('\3C ', '\3E ', '\26 '), - $css - ); - } - return $css; - } -} - -// vim: et sw=4 sts=4 + blocks from input HTML, cleans them up + * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') + * so they can be used elsewhere in the document. + * + * @note + * See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for + * sample usage. + * + * @note + * This filter can also be used on stylesheets not included in the + * document--something purists would probably prefer. Just directly + * call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS() + */ +class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter +{ + /** + * @type string + */ + public $name = 'ExtractStyleBlocks'; + + /** + * @type array + */ + private $_styleMatches = array(); + + /** + * @type csstidy + */ + private $_tidy; + + /** + * @type HTMLPurifier_AttrDef_HTML_ID + */ + private $_id_attrdef; + + /** + * @type HTMLPurifier_AttrDef_CSS_Ident + */ + private $_class_attrdef; + + /** + * @type HTMLPurifier_AttrDef_Enum + */ + private $_enum_attrdef; + + public function __construct() + { + $this->_tidy = new csstidy(); + $this->_tidy->set_cfg('lowercase_s', false); + $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); + $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); + $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( + array( + 'first-child', + 'link', + 'visited', + 'active', + 'hover', + 'focus' + ) + ); + } + + /** + * Save the contents of CSS blocks to style matches + * @param array $matches preg_replace style $matches array + */ + protected function styleCallback($matches) + { + $this->_styleMatches[] = $matches[1]; + } + + /** + * Removes inline + // we must not grab foo in a font-family prop). + if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { + $css = str_replace( + array('<', '>', '&'), + array('\3C ', '\3E ', '\26 '), + $css + ); + } + return $css; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Filter/YouTube.php b/lib/htmlpurifier/HTMLPurifier/Filter/YouTube.php index 276d8362fa0..b90ddf75171 100644 --- a/lib/htmlpurifier/HTMLPurifier/Filter/YouTube.php +++ b/lib/htmlpurifier/HTMLPurifier/Filter/YouTube.php @@ -1,65 +1,65 @@ -]+>.+?' . - '(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?#s'; - $pre_replace = ''; - return preg_replace($pre_regex, $pre_replace, $html); - } - - /** - * @param string $html - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return string - */ - public function postFilter($html, $config, $context) - { - $post_regex = '##'; - return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); - } - - /** - * @param $url - * @return string - */ - protected function armorUrl($url) - { - return str_replace('--', '--', $url); - } - - /** - * @param array $matches - * @return string - */ - protected function postFilterCallback($matches) - { - $url = $this->armorUrl($matches[1]); - return ''; - } -} - -// vim: et sw=4 sts=4 +]+>.+?' . + '(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?#s'; + $pre_replace = ''; + return preg_replace($pre_regex, $pre_replace, $html); + } + + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + $post_regex = '##'; + return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); + } + + /** + * @param $url + * @return string + */ + protected function armorUrl($url) + { + return str_replace('--', '--', $url); + } + + /** + * @param array $matches + * @return string + */ + protected function postFilterCallback($matches) + { + $url = $this->armorUrl($matches[1]); + return ''; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Generator.php b/lib/htmlpurifier/HTMLPurifier/Generator.php index eb56e2dfa2e..addc23e9e4d 100644 --- a/lib/htmlpurifier/HTMLPurifier/Generator.php +++ b/lib/htmlpurifier/HTMLPurifier/Generator.php @@ -1,286 +1,286 @@ - tags. - * @type bool - */ - private $_scriptFix = false; - - /** - * Cache of HTMLDefinition during HTML output to determine whether or - * not attributes should be minimized. - * @type HTMLPurifier_HTMLDefinition - */ - private $_def; - - /** - * Cache of %Output.SortAttr. - * @type bool - */ - private $_sortAttr; - - /** - * Cache of %Output.FlashCompat. - * @type bool - */ - private $_flashCompat; - - /** - * Cache of %Output.FixInnerHTML. - * @type bool - */ - private $_innerHTMLFix; - - /** - * Stack for keeping track of object information when outputting IE - * compatibility code. - * @type array - */ - private $_flashStack = array(); - - /** - * Configuration for the generator - * @type HTMLPurifier_Config - */ - protected $config; - - /** - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - */ - public function __construct($config, $context) - { - $this->config = $config; - $this->_scriptFix = $config->get('Output.CommentScriptContents'); - $this->_innerHTMLFix = $config->get('Output.FixInnerHTML'); - $this->_sortAttr = $config->get('Output.SortAttr'); - $this->_flashCompat = $config->get('Output.FlashCompat'); - $this->_def = $config->getHTMLDefinition(); - $this->_xhtml = $this->_def->doctype->xml; - } - - /** - * Generates HTML from an array of tokens. - * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token - * @return string Generated HTML - */ - public function generateFromTokens($tokens) - { - if (!$tokens) { - return ''; - } - - // Basic algorithm - $html = ''; - for ($i = 0, $size = count($tokens); $i < $size; $i++) { - if ($this->_scriptFix && $tokens[$i]->name === 'script' - && $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) { - // script special case - // the contents of the script block must be ONE token - // for this to work. - $html .= $this->generateFromToken($tokens[$i++]); - $html .= $this->generateScriptFromToken($tokens[$i++]); - } - $html .= $this->generateFromToken($tokens[$i]); - } - - // Tidy cleanup - if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) { - $tidy = new Tidy; - $tidy->parseString( - $html, - array( - 'indent'=> true, - 'output-xhtml' => $this->_xhtml, - 'show-body-only' => true, - 'indent-spaces' => 2, - 'wrap' => 68, - ), - 'utf8' - ); - $tidy->cleanRepair(); - $html = (string) $tidy; // explicit cast necessary - } - - // Normalize newlines to system defined value - if ($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; - } - - /** - * Generates HTML from a single token. - * @param HTMLPurifier_Token $token HTMLPurifier_Token object. - * @return string Generated HTML - */ - public function generateFromToken($token) - { - if (!$token instanceof HTMLPurifier_Token) { - trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING); - return ''; - - } elseif ($token instanceof HTMLPurifier_Token_Start) { - $attr = $this->generateAttributes($token->attr, $token->name); - if ($this->_flashCompat) { - if ($token->name == "object") { - $flash = new stdClass(); - $flash->attr = $token->attr; - $flash->param = array(); - $this->_flashStack[] = $flash; - } - } - return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>'; - - } elseif ($token instanceof HTMLPurifier_Token_End) { - $_extra = ''; - if ($this->_flashCompat) { - if ($token->name == "object" && !empty($this->_flashStack)) { - // doesn't do anything for now - } - } - return $_extra . 'name . '>'; - - } elseif ($token instanceof HTMLPurifier_Token_Empty) { - if ($this->_flashCompat && $token->name == "param" && !empty($this->_flashStack)) { - $this->_flashStack[count($this->_flashStack)-1]->param[$token->attr['name']] = $token->attr['value']; - } - $attr = $this->generateAttributes($token->attr, $token->name); - return '<' . $token->name . ($attr ? ' ' : '') . $attr . - ( $this->_xhtml ? ' /': '' ) //
v.
- . '>'; - - } elseif ($token instanceof HTMLPurifier_Token_Text) { - return $this->escape($token->data, ENT_NOQUOTES); - - } elseif ($token instanceof HTMLPurifier_Token_Comment) { - return ''; - } else { - return ''; - - } - } - - /** - * Special case processor for the contents of script tags - * @param HTMLPurifier_Token $token HTMLPurifier_Token object. - * @return string - * @warning This runs into problems if there's already a literal - * --> somewhere inside the script contents. - */ - public function generateScriptFromToken($token) - { - if (!$token instanceof HTMLPurifier_Token_Text) { - return $this->generateFromToken($token); - } - // Thanks
v.
+ . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Text) { + return $this->escape($token->data, ENT_NOQUOTES); + + } elseif ($token instanceof HTMLPurifier_Token_Comment) { + return ''; + } else { + return ''; + + } + } + + /** + * Special case processor for the contents of script tags + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string + * @warning This runs into problems if there's already a literal + * --> somewhere inside the script contents. + */ + public function generateScriptFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token_Text) { + return $this->generateFromToken($token); + } + // Thanks
tags? - if ($this->allowsElement('p')) { - if (empty($this->currentNesting) || strpos($text, "\n\n") !== false) { - // Note that we have differing behavior when dealing with text - // in the anonymous root node, or a node inside the document. - // If the text as a double-newline, the treatment is the same; - // if it doesn't, see the next if-block if you're in the document. - - $i = $nesting = null; - if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) { - // State 1.1: ... ^ (whitespace, then document end) - // ---- - // This is a degenerate case - } else { - if (!$token->is_whitespace || $this->_isInline($current)) { - // State 1.2: PAR1 - // ---- - - // State 1.3: PAR1\n\nPAR2 - // ------------ - - // State 1.4:
PAR1\n\nPAR2 (see State 2)
- // ------------
- $token = array($this->_pStart());
- $this->_splitText($text, $token);
- } else {
- // State 1.5: \n
- // -- - } - } - } else { - // State 2:
- // -- - } - } - } else { - // State 2:
PAR1... (similar to 1.4)
- // ----
-
- // We're in an element that allows paragraph tags, but we're not
- // sure if we're going to need them.
- if ($this->_pLookAhead()) {
- // State 2.1:
PAR1PAR1\n\nPAR2
- // ----
- // Note: This will always be the first child, since any
- // previous inline element would have triggered this very
- // same routine, and found the double newline. One possible
- // exception would be a comment.
- $token = array($this->_pStart(), $token);
- } else {
- // State 2.2.1:
PAR1
- // ----
-
- // State 2.2.2:
PAR1PAR1
- // ----
- }
- }
- // Is the current parent a tag? - } elseif (!empty($this->currentNesting) && - $this->currentNesting[count($this->currentNesting) - 1]->name == 'p') { - // State 3.1: ...
PAR1 - // ---- - - // State 3.2: ...
PAR1\n\nPAR2 - // ------------ - $token = array(); - $this->_splitText($text, $token); - // Abort! - } else { - // State 4.1: ...PAR1 - // ---- - - // State 4.2: ...PAR1\n\nPAR2 - // ------------ - } - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleElement(&$token) - { - // We don't have to check if we're already in a
tag for block - // tokens, because the tag would have been autoclosed by MakeWellFormed. - if ($this->allowsElement('p')) { - if (!empty($this->currentNesting)) { - if ($this->_isInline($token)) { - // State 1:
...
- // ---
- // Check if this token is adjacent to the parent token
- // (seek backwards until token isn't whitespace)
- $i = null;
- $this->backward($i, $prev);
-
- if (!$prev instanceof HTMLPurifier_Token_Start) {
- // Token wasn't adjacent
- if ($prev instanceof HTMLPurifier_Token_Text &&
- substr($prev->data, -2) === "\n\n"
- ) {
- // State 1.1.4:
- // --- - // State 1.1.3:
PAR1
\n\n - // --- - // Quite frankly, this should be handled by splitText - $token = array($this->_pStart(), $token); - } else { - // State 1.1.1:PAR1
- // --- - // State 1.1.2:- // --- - // State 1.1.3:
PAR
- // ---
- }
- } else {
- // State 1.2.1:
- // ---
- // Lookahead to see if
is needed. - if ($this->_pLookAhead()) { - // State 1.3.1:
PAR1\n\nPAR2
- // ---
- $token = array($this->_pStart(), $token);
- } else {
- // State 1.3.2:
PAR1
- // ---
-
- // State 1.3.3: PAR1\n\n
- // ---
- }
- }
- } else {
- // State 2.3: ...
- // -----
- }
- } else {
- if ($this->_isInline($token)) {
- // State 3.1:
- // ---
- // This is where the {p} tag is inserted, not reflected in
- // inputTokens yet, however.
- $token = array($this->_pStart(), $token);
- } else {
- // State 3.2:
- // -----
- }
-
- $i = null;
- if ($this->backward($i, $prev)) {
- if (!$prev instanceof HTMLPurifier_Token_Text) {
- // State 3.1.1: ...{p}
- // ---
- // State 3.2.1: ...
- // -----
- if (!is_array($token)) {
- $token = array($token);
- }
- array_unshift($token, new HTMLPurifier_Token_Text("\n\n"));
- } else {
- // State 3.1.2: ...\n\n{p}
- // ---
- // State 3.2.2: ...\n\n
- // -----
- // Note: PAR cannot occur because PAR would have been
- // wrapped in
tags. - } - } - } - } else { - // State 2.2:
-
- // ----
- // State 2.4:
- // --- - } - } - - /** - * Splits up a text in paragraph tokens and appends them - * to the result stream that will replace the original - * @param string $data String text data that will be processed - * into paragraphs - * @param HTMLPurifier_Token[] $result Reference to array of tokens that the - * tags will be appended onto - */ - private function _splitText($data, &$result) - { - $raw_paragraphs = explode("\n\n", $data); - $paragraphs = array(); // without empty paragraphs - $needs_start = false; - $needs_end = false; - - $c = count($raw_paragraphs); - if ($c == 1) { - // There were no double-newlines, abort quickly. In theory this - // should never happen. - $result[] = new HTMLPurifier_Token_Text($data); - return; - } - for ($i = 0; $i < $c; $i++) { - $par = $raw_paragraphs[$i]; - if (trim($par) !== '') { - $paragraphs[] = $par; - } else { - if ($i == 0) { - // Double newline at the front - if (empty($result)) { - // The empty result indicates that the AutoParagraph - // injector did not add any start paragraph tokens. - // This means that we have been in a paragraph for - // a while, and the newline means we should start a new one. - $result[] = new HTMLPurifier_Token_End('p'); - $result[] = new HTMLPurifier_Token_Text("\n\n"); - // However, the start token should only be added if - // there is more processing to be done (i.e. there are - // real paragraphs in here). If there are none, the - // next start paragraph tag will be handled by the - // next call to the injector - $needs_start = true; - } else { - // We just started a new paragraph! - // Reinstate a double-newline for presentation's sake, since - // it was in the source code. - array_unshift($result, new HTMLPurifier_Token_Text("\n\n")); - } - } elseif ($i + 1 == $c) { - // Double newline at the end - // There should be a trailing
when we're finally done. - $needs_end = true; - } - } - } - - // Check if this was just a giant blob of whitespace. Move this earlier, - // perhaps? - if (empty($paragraphs)) { - return; - } - - // Add the start tag indicated by \n\n at the beginning of $data - if ($needs_start) { - $result[] = $this->_pStart(); - } - - // Append the paragraphs onto the result - foreach ($paragraphs as $par) { - $result[] = new HTMLPurifier_Token_Text($par); - $result[] = new HTMLPurifier_Token_End('p'); - $result[] = new HTMLPurifier_Token_Text("\n\n"); - $result[] = $this->_pStart(); - } - - // Remove trailing start token; Injector will handle this later if - // it was indeed needed. This prevents from needing to do a lookahead, - // at the cost of a lookbehind later. - array_pop($result); - - // If there is no need for an end tag, remove all of it and let - // MakeWellFormed close it later. - if (!$needs_end) { - array_pop($result); // removes \n\n - array_pop($result); // removes - } - } - - /** - * Returns true if passed token is inline (and, ergo, allowed in - * paragraph tags) - * @param HTMLPurifier_Token $token - * @return bool - */ - private function _isInline($token) - { - return isset($this->htmlDefinition->info['p']->child->elements[$token->name]); - } - - /** - * Looks ahead in the token list and determines whether or not we need - * to insert atag. - * @return bool - */ - private function _pLookAhead() - { - if ($this->currentToken instanceof HTMLPurifier_Token_Start) { - $nesting = 1; - } else { - $nesting = 0; - } - $ok = false; - $i = null; - while ($this->forwardUntilEndToken($i, $current, $nesting)) { - $result = $this->_checkNeedsP($current); - if ($result !== null) { - $ok = $result; - break; - } - } - return $ok; - } - - /** - * Determines if a particular token requires an earlier inline token - * to get a paragraph. This should be used with _forwardUntilEndToken - * @param HTMLPurifier_Token $current - * @return bool - */ - private function _checkNeedsP($current) - { - if ($current instanceof HTMLPurifier_Token_Start) { - if (!$this->_isInline($current)) { - //
PAR1- // ---- - // Terminate early, since we hit a block element - return false; - } - } elseif ($current instanceof HTMLPurifier_Token_Text) { - if (strpos($current->data, "\n\n") !== false) { - //PAR1PAR1\n\nPAR2 - // ---- - return true; - } else { - //PAR1PAR1... - // ---- - } - } - return null; - } -} - -// vim: et sw=4 sts=4 +armor['MakeWellFormed_TagClosedError'] = true; + return $par; + } + + /** + * @param HTMLPurifier_Token_Text $token + */ + public function handleText(&$token) + { + $text = $token->data; + // Does the current parent allowtags? + if ($this->allowsElement('p')) { + if (empty($this->currentNesting) || strpos($text, "\n\n") !== false) { + // Note that we have differing behavior when dealing with text + // in the anonymous root node, or a node inside the document. + // If the text as a double-newline, the treatment is the same; + // if it doesn't, see the next if-block if you're in the document. + + $i = $nesting = null; + if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) { + // State 1.1: ... ^ (whitespace, then document end) + // ---- + // This is a degenerate case + } else { + if (!$token->is_whitespace || $this->_isInline($current)) { + // State 1.2: PAR1 + // ---- + + // State 1.3: PAR1\n\nPAR2 + // ------------ + + // State 1.4:
PAR1\n\nPAR2 (see State 2) + // ------------ + $token = array($this->_pStart()); + $this->_splitText($text, $token); + } else { + // State 1.5: \n
+ // -- + } + } + } else { + // State 2:PAR1... (similar to 1.4) + // ---- + + // We're in an element that allows paragraph tags, but we're not + // sure if we're going to need them. + if ($this->_pLookAhead()) { + // State 2.1:PAR1PAR1\n\nPAR2 + // ---- + // Note: This will always be the first child, since any + // previous inline element would have triggered this very + // same routine, and found the double newline. One possible + // exception would be a comment. + $token = array($this->_pStart(), $token); + } else { + // State 2.2.1:PAR1+ // ---- + + // State 2.2.2:PAR1PAR1+ // ---- + } + } + // Is the current parent atag? + } elseif (!empty($this->currentNesting) && + $this->currentNesting[count($this->currentNesting) - 1]->name == 'p') { + // State 3.1: ...
PAR1 + // ---- + + // State 3.2: ...
PAR1\n\nPAR2 + // ------------ + $token = array(); + $this->_splitText($text, $token); + // Abort! + } else { + // State 4.1: ...PAR1 + // ---- + + // State 4.2: ...PAR1\n\nPAR2 + // ------------ + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + // We don't have to check if we're already in a
tag for block + // tokens, because the tag would have been autoclosed by MakeWellFormed. + if ($this->allowsElement('p')) { + if (!empty($this->currentNesting)) { + if ($this->_isInline($token)) { + // State 1:
... + // --- + // Check if this token is adjacent to the parent token + // (seek backwards until token isn't whitespace) + $i = null; + $this->backward($i, $prev); + + if (!$prev instanceof HTMLPurifier_Token_Start) { + // Token wasn't adjacent + if ($prev instanceof HTMLPurifier_Token_Text && + substr($prev->data, -2) === "\n\n" + ) { + // State 1.1.4:PAR1
\n\n + // --- + // Quite frankly, this should be handled by splitText + $token = array($this->_pStart(), $token); + } else { + // State 1.1.1:PAR1
+ // --- + // State 1.1.2:
+ // --- + // State 1.1.3:PAR + // --- + } + } else { + // State 1.2.1:+ // --- + // Lookahead to see ifis needed. + if ($this->_pLookAhead()) { + // State 1.3.1:
PAR1\n\nPAR2 + // --- + $token = array($this->_pStart(), $token); + } else { + // State 1.3.2:PAR1+ // --- + + // State 1.3.3:PAR1\n\n+ // --- + } + } + } else { + // State 2.3: ...+ // ----- + } + } else { + if ($this->_isInline($token)) { + // State 3.1: + // --- + // This is where the {p} tag is inserted, not reflected in + // inputTokens yet, however. + $token = array($this->_pStart(), $token); + } else { + // State 3.2:+ // ----- + } + + $i = null; + if ($this->backward($i, $prev)) { + if (!$prev instanceof HTMLPurifier_Token_Text) { + // State 3.1.1: ...{p} + // --- + // State 3.2.1: ...+ // ----- + if (!is_array($token)) { + $token = array($token); + } + array_unshift($token, new HTMLPurifier_Token_Text("\n\n")); + } else { + // State 3.1.2: ...\n\n{p} + // --- + // State 3.2.2: ...\n\n+ // ----- + // Note: PARcannot occur because PAR would have been + // wrapped in tags. + } + } + } + } else { + // State 2.2:
-
+ // ----
+ // State 2.4:
+ // --- + } + } + + /** + * Splits up a text in paragraph tokens and appends them + * to the result stream that will replace the original + * @param string $data String text data that will be processed + * into paragraphs + * @param HTMLPurifier_Token[] $result Reference to array of tokens that the + * tags will be appended onto + */ + private function _splitText($data, &$result) + { + $raw_paragraphs = explode("\n\n", $data); + $paragraphs = array(); // without empty paragraphs + $needs_start = false; + $needs_end = false; + + $c = count($raw_paragraphs); + if ($c == 1) { + // There were no double-newlines, abort quickly. In theory this + // should never happen. + $result[] = new HTMLPurifier_Token_Text($data); + return; + } + for ($i = 0; $i < $c; $i++) { + $par = $raw_paragraphs[$i]; + if (trim($par) !== '') { + $paragraphs[] = $par; + } else { + if ($i == 0) { + // Double newline at the front + if (empty($result)) { + // The empty result indicates that the AutoParagraph + // injector did not add any start paragraph tokens. + // This means that we have been in a paragraph for + // a while, and the newline means we should start a new one. + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + // However, the start token should only be added if + // there is more processing to be done (i.e. there are + // real paragraphs in here). If there are none, the + // next start paragraph tag will be handled by the + // next call to the injector + $needs_start = true; + } else { + // We just started a new paragraph! + // Reinstate a double-newline for presentation's sake, since + // it was in the source code. + array_unshift($result, new HTMLPurifier_Token_Text("\n\n")); + } + } elseif ($i + 1 == $c) { + // Double newline at the end + // There should be a trailing
when we're finally done. + $needs_end = true; + } + } + } + + // Check if this was just a giant blob of whitespace. Move this earlier, + // perhaps? + if (empty($paragraphs)) { + return; + } + + // Add the start tag indicated by \n\n at the beginning of $data + if ($needs_start) { + $result[] = $this->_pStart(); + } + + // Append the paragraphs onto the result + foreach ($paragraphs as $par) { + $result[] = new HTMLPurifier_Token_Text($par); + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + $result[] = $this->_pStart(); + } + + // Remove trailing start token; Injector will handle this later if + // it was indeed needed. This prevents from needing to do a lookahead, + // at the cost of a lookbehind later. + array_pop($result); + + // If there is no need for an end tag, remove all of it and let + // MakeWellFormed close it later. + if (!$needs_end) { + array_pop($result); // removes \n\n + array_pop($result); // removes + } + } + + /** + * Returns true if passed token is inline (and, ergo, allowed in + * paragraph tags) + * @param HTMLPurifier_Token $token + * @return bool + */ + private function _isInline($token) + { + return isset($this->htmlDefinition->info['p']->child->elements[$token->name]); + } + + /** + * Looks ahead in the token list and determines whether or not we need + * to insert atag. + * @return bool + */ + private function _pLookAhead() + { + if ($this->currentToken instanceof HTMLPurifier_Token_Start) { + $nesting = 1; + } else { + $nesting = 0; + } + $ok = false; + $i = null; + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + $result = $this->_checkNeedsP($current); + if ($result !== null) { + $ok = $result; + break; + } + } + return $ok; + } + + /** + * Determines if a particular token requires an earlier inline token + * to get a paragraph. This should be used with _forwardUntilEndToken + * @param HTMLPurifier_Token $current + * @return bool + */ + private function _checkNeedsP($current) + { + if ($current instanceof HTMLPurifier_Token_Start) { + if (!$this->_isInline($current)) { + //
PAR1+ // ---- + // Terminate early, since we hit a block element + return false; + } + } elseif ($current instanceof HTMLPurifier_Token_Text) { + if (strpos($current->data, "\n\n") !== false) { + //PAR1PAR1\n\nPAR2 + // ---- + return true; + } else { + //PAR1PAR1... + // ---- + } + } + return null; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/DisplayLinkURI.php b/lib/htmlpurifier/HTMLPurifier/Injector/DisplayLinkURI.php index c19b1bc2718..9f9044829de 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/DisplayLinkURI.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/DisplayLinkURI.php @@ -1,40 +1,40 @@ -start->attr['href'])) { - $url = $token->start->attr['href']; - unset($token->start->attr['href']); - $token = array($token, new HTMLPurifier_Token_Text(" ($url)")); - } else { - // nothing to display - } - } -} - -// vim: et sw=4 sts=4 +start->attr['href'])) { + $url = $token->start->attr['href']; + unset($token->start->attr['href']); + $token = array($token, new HTMLPurifier_Token_Text(" ($url)")); + } else { + // nothing to display + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/Linkify.php b/lib/htmlpurifier/HTMLPurifier/Injector/Linkify.php index 74f83eaa7d1..531dde4acf1 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/Linkify.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/Linkify.php @@ -1,64 +1,64 @@ - array('href')); - - /** - * @param HTMLPurifier_Token $token - */ - public function handleText(&$token) - { - if (!$this->allowsElement('a')) { - return; - } - - if (strpos($token->data, '://') === false) { - // our really quick heuristic failed, abort - // this may not work so well if we want to match things like - // "google.com", but then again, most people don't - return; - } - - // there is/are URL(s). Let's split the string. - // We use this regex: - // https://gist.github.com/gruber/249502 - // but with @cscott's backtracking fix and also - // the Unicode characters un-Unicodified. - $bits = preg_split( - '/\\b((?:[a-z][\\w\\-]+:(?:\\/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}\\/)(?:[^\\s()<>]|\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\))+(?:\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:\'".,<>?\x{00ab}\x{00bb}\x{201c}\x{201d}\x{2018}\x{2019}]))/iu', - $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); - - - $token = array(); - - // $i = index - // $c = count - // $l = is link - for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { - if (!$l) { - if ($bits[$i] === '') { - continue; - } - $token[] = new HTMLPurifier_Token_Text($bits[$i]); - } else { - $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); - $token[] = new HTMLPurifier_Token_Text($bits[$i]); - $token[] = new HTMLPurifier_Token_End('a'); - } - } - } -} - -// vim: et sw=4 sts=4 + array('href')); + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + + if (strpos($token->data, '://') === false) { + // our really quick heuristic failed, abort + // this may not work so well if we want to match things like + // "google.com", but then again, most people don't + return; + } + + // there is/are URL(s). Let's split the string. + // We use this regex: + // https://gist.github.com/gruber/249502 + // but with @cscott's backtracking fix and also + // the Unicode characters un-Unicodified. + $bits = preg_split( + '/\\b((?:[a-z][\\w\\-]+:(?:\\/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}\\/)(?:[^\\s()<>]|\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\))+(?:\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:\'".,<>?\x{00ab}\x{00bb}\x{201c}\x{201d}\x{2018}\x{2019}]))/iu', + $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + + + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/PurifierLinkify.php b/lib/htmlpurifier/HTMLPurifier/Injector/PurifierLinkify.php index cb9046f3346..d7dd7d972ae 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/PurifierLinkify.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/PurifierLinkify.php @@ -1,71 +1,71 @@ - array('href')); - - /** - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return string - */ - public function prepare($config, $context) - { - $this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL'); - return parent::prepare($config, $context); - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleText(&$token) - { - if (!$this->allowsElement('a')) { - return; - } - if (strpos($token->data, '%') === false) { - return; - } - - $bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); - $token = array(); - - // $i = index - // $c = count - // $l = is link - for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { - if (!$l) { - if ($bits[$i] === '') { - continue; - } - $token[] = new HTMLPurifier_Token_Text($bits[$i]); - } else { - $token[] = new HTMLPurifier_Token_Start( - 'a', - array('href' => str_replace('%s', $bits[$i], $this->docURL)) - ); - $token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]); - $token[] = new HTMLPurifier_Token_End('a'); - } - } - } -} - -// vim: et sw=4 sts=4 + array('href')); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function prepare($config, $context) + { + $this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL'); + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + if (strpos($token->data, '%') === false) { + return; + } + + $bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start( + 'a', + array('href' => str_replace('%s', $bits[$i], $this->docURL)) + ); + $token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/RemoveEmpty.php b/lib/htmlpurifier/HTMLPurifier/Injector/RemoveEmpty.php index 0ebc477c68e..aae2dca1a76 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/RemoveEmpty.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/RemoveEmpty.php @@ -1,112 +1,112 @@ -config = $config; - $this->context = $context; - $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp'); - $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions'); - $this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate'); - foreach ($this->exclude as $key => $attrs) { - if (!is_array($attrs)) { - // HACK, see HTMLPurifier/Printer/ConfigForm.php - $this->exclude[$key] = explode(';', $attrs); - } - } - $this->attrValidator = new HTMLPurifier_AttrValidator(); - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleElement(&$token) - { - if (!$token instanceof HTMLPurifier_Token_Start) { - return; - } - $next = false; - $deleted = 1; // the current tag - for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) { - $next = $this->inputZipper->back[$i]; - if ($next instanceof HTMLPurifier_Token_Text) { - if ($next->is_whitespace) { - continue; - } - if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) { - $plain = str_replace("\xC2\xA0", "", $next->data); - $isWsOrNbsp = $plain === '' || ctype_space($plain); - if ($isWsOrNbsp) { - continue; - } - } - } - break; - } - if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) { - $this->attrValidator->validateToken($token, $this->config, $this->context); - $token->armor['ValidateAttributes'] = true; - if (isset($this->exclude[$token->name])) { - $r = true; - foreach ($this->exclude[$token->name] as $elem) { - if (!isset($token->attr[$elem])) $r = false; - } - if ($r) return; - } - if (isset($token->attr['id']) || isset($token->attr['name'])) { - return; - } - $token = $deleted + 1; - for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) { - $prev = $this->inputZipper->front[$b]; - if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) { - continue; - } - break; - } - // This is safe because we removed the token that triggered this. - $this->rewindOffset($b+$deleted); - return; - } - } -} - -// vim: et sw=4 sts=4 +config = $config; + $this->context = $context; + $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp'); + $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions'); + $this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate'); + foreach ($this->exclude as $key => $attrs) { + if (!is_array($attrs)) { + // HACK, see HTMLPurifier/Printer/ConfigForm.php + $this->exclude[$key] = explode(';', $attrs); + } + } + $this->attrValidator = new HTMLPurifier_AttrValidator(); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if (!$token instanceof HTMLPurifier_Token_Start) { + return; + } + $next = false; + $deleted = 1; // the current tag + for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) { + $next = $this->inputZipper->back[$i]; + if ($next instanceof HTMLPurifier_Token_Text) { + if ($next->is_whitespace) { + continue; + } + if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) { + $plain = str_replace("\xC2\xA0", "", $next->data); + $isWsOrNbsp = $plain === '' || ctype_space($plain); + if ($isWsOrNbsp) { + continue; + } + } + } + break; + } + if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) { + $this->attrValidator->validateToken($token, $this->config, $this->context); + $token->armor['ValidateAttributes'] = true; + if (isset($this->exclude[$token->name])) { + $r = true; + foreach ($this->exclude[$token->name] as $elem) { + if (!isset($token->attr[$elem])) $r = false; + } + if ($r) return; + } + if (isset($token->attr['id']) || isset($token->attr['name'])) { + return; + } + $token = $deleted + 1; + for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) { + $prev = $this->inputZipper->front[$b]; + if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) { + continue; + } + break; + } + // This is safe because we removed the token that triggered this. + $this->rewindOffset($b+$deleted); + return; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php b/lib/htmlpurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php index 9ee7aa84d71..270b7f828c0 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php @@ -1,84 +1,84 @@ -attrValidator = new HTMLPurifier_AttrValidator(); - $this->config = $config; - $this->context = $context; - return parent::prepare($config, $context); - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleElement(&$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; - } - - $nesting = 0; - while ($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; - } - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleEnd(&$token) - { - if ($token->markForDeletion) { - $token = false; - } - } -} - -// vim: et sw=4 sts=4 +attrValidator = new HTMLPurifier_AttrValidator(); + $this->config = $config; + $this->context = $context; + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$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; + } + + $nesting = 0; + while ($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; + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleEnd(&$token) + { + if ($token->markForDeletion) { + $token = false; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Injector/SafeObject.php b/lib/htmlpurifier/HTMLPurifier/Injector/SafeObject.php index 317f7864dd4..0b051101d3d 100644 --- a/lib/htmlpurifier/HTMLPurifier/Injector/SafeObject.php +++ b/lib/htmlpurifier/HTMLPurifier/Injector/SafeObject.php @@ -1,124 +1,124 @@ - 'never', - 'allowNetworking' => 'internal', - ); - - /** - * These are all lower-case keys. - * @type array - */ - protected $allowedParam = array( - 'wmode' => true, - 'movie' => true, - 'flashvars' => true, - 'src' => true, - 'allowfullscreen' => true, // if omitted, assume to be 'false' - ); - - /** - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return void - */ - public function prepare($config, $context) - { - parent::prepare($config, $context); - } - - /** - * @param HTMLPurifier_Token $token - */ - public function handleElement(&$token) - { - if ($token->name == 'object') { - $this->objectStack[] = $token; - $this->paramStack[] = array(); - $new = array($token); - foreach ($this->addParam as $name => $value) { - $new[] = new HTMLPurifier_Token_Empty('param', array('name' => $name, 'value' => $value)); - } - $token = $new; - } elseif ($token->name == 'param') { - $nest = count($this->currentNesting) - 1; - if ($nest >= 0 && $this->currentNesting[$nest]->name === 'object') { - $i = count($this->objectStack) - 1; - if (!isset($token->attr['name'])) { - $token = false; - return; - } - $n = $token->attr['name']; - // We need this fix because YouTube doesn't supply a data - // attribute, which we need if a type is specified. This is - // *very* Flash specific. - if (!isset($this->objectStack[$i]->attr['data']) && - ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src') - ) { - $this->objectStack[$i]->attr['data'] = $token->attr['value']; - } - // Check if the parameter is the correct value but has not - // already been added - if (!isset($this->paramStack[$i][$n]) && - isset($this->addParam[$n]) && - $token->attr['name'] === $this->addParam[$n]) { - // keep token, and add to param stack - $this->paramStack[$i][$n] = true; - } elseif (isset($this->allowedParam[strtolower($n)])) { - // keep token, don't do anything to it - // (could possibly check for duplicates here) - // Note: In principle, parameters should be case sensitive. - // But it seems they are not really; so accept any case. - } else { - $token = false; - } - } else { - // not directly inside an object, DENY! - $token = false; - } - } - } - - public function handleEnd(&$token) - { - // This is the WRONG way of handling the object and param stacks; - // we should be inserting them directly on the relevant object tokens - // so that the global stack handling handles it. - if ($token->name == 'object') { - array_pop($this->objectStack); - array_pop($this->paramStack); - } - } -} - -// vim: et sw=4 sts=4 + 'never', + 'allowNetworking' => 'internal', + ); + + /** + * These are all lower-case keys. + * @type array + */ + protected $allowedParam = array( + 'wmode' => true, + 'movie' => true, + 'flashvars' => true, + 'src' => true, + 'allowfullscreen' => true, // if omitted, assume to be 'false' + ); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return void + */ + public function prepare($config, $context) + { + parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if ($token->name == 'object') { + $this->objectStack[] = $token; + $this->paramStack[] = array(); + $new = array($token); + foreach ($this->addParam as $name => $value) { + $new[] = new HTMLPurifier_Token_Empty('param', array('name' => $name, 'value' => $value)); + } + $token = $new; + } elseif ($token->name == 'param') { + $nest = count($this->currentNesting) - 1; + if ($nest >= 0 && $this->currentNesting[$nest]->name === 'object') { + $i = count($this->objectStack) - 1; + if (!isset($token->attr['name'])) { + $token = false; + return; + } + $n = $token->attr['name']; + // We need this fix because YouTube doesn't supply a data + // attribute, which we need if a type is specified. This is + // *very* Flash specific. + if (!isset($this->objectStack[$i]->attr['data']) && + ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src') + ) { + $this->objectStack[$i]->attr['data'] = $token->attr['value']; + } + // Check if the parameter is the correct value but has not + // already been added + if (!isset($this->paramStack[$i][$n]) && + isset($this->addParam[$n]) && + $token->attr['name'] === $this->addParam[$n]) { + // keep token, and add to param stack + $this->paramStack[$i][$n] = true; + } elseif (isset($this->allowedParam[strtolower($n)])) { + // keep token, don't do anything to it + // (could possibly check for duplicates here) + // Note: In principle, parameters should be case sensitive. + // But it seems they are not really; so accept any case. + } else { + $token = false; + } + } else { + // not directly inside an object, DENY! + $token = false; + } + } + } + + public function handleEnd(&$token) + { + // This is the WRONG way of handling the object and param stacks; + // we should be inserting them directly on the relevant object tokens + // so that the global stack handling handles it. + if ($token->name == 'object') { + array_pop($this->objectStack); + array_pop($this->paramStack); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Language.php b/lib/htmlpurifier/HTMLPurifier/Language.php index 65277dd43ca..35a13f785d0 100644 --- a/lib/htmlpurifier/HTMLPurifier/Language.php +++ b/lib/htmlpurifier/HTMLPurifier/Language.php @@ -1,204 +1,204 @@ -config = $config; - $this->context = $context; - } - - /** - * Loads language object with necessary info from factory cache - * @note This is a lazy loader - */ - public function load() - { - if ($this->_loaded) { - return; - } - $factory = HTMLPurifier_LanguageFactory::instance(); - $factory->loadLanguage($this->code); - foreach ($factory->keys as $key) { - $this->$key = $factory->cache[$this->code][$key]; - } - $this->_loaded = true; - } - - /** - * Retrieves a localised message. - * @param string $key string identifier of message - * @return string localised message - */ - public function getMessage($key) - { - if (!$this->_loaded) { - $this->load(); - } - if (!isset($this->messages[$key])) { - return "[$key]"; - } - return $this->messages[$key]; - } - - /** - * Retrieves a localised error name. - * @param int $int error number, corresponding to PHP's error reporting - * @return string localised message - */ - public function getErrorName($int) - { - if (!$this->_loaded) { - $this->load(); - } - if (!isset($this->errorNames[$int])) { - return "[Error: $int]"; - } - return $this->errorNames[$int]; - } - - /** - * Converts an array list into a string readable representation - * @param array $array - * @return string - */ - public function listify($array) - { - $sep = $this->getMessage('Item separator'); - $sep_last = $this->getMessage('Item separator last'); - $ret = ''; - for ($i = 0, $c = count($array); $i < $c; $i++) { - if ($i == 0) { - } elseif ($i + 1 < $c) { - $ret .= $sep; - } else { - $ret .= $sep_last; - } - $ret .= $array[$i]; - } - return $ret; - } - - /** - * Formats a localised message with passed parameters - * @param string $key string identifier of message - * @param array $args Parameters to substitute in - * @return string localised message - * @todo Implement conditionals? Right now, some messages make - * reference to line numbers, but those aren't always available - */ - public function formatMessage($key, $args = array()) - { - if (!$this->_loaded) { - $this->load(); - } - if (!isset($this->messages[$key])) { - return "[$key]"; - } - $raw = $this->messages[$key]; - $subst = array(); - $generator = false; - foreach ($args as $i => $value) { - if (is_object($value)) { - if ($value instanceof HTMLPurifier_Token) { - // factor this out some time - if (!$generator) { - $generator = $this->context->get('Generator'); - } - if (isset($value->name)) { - $subst['$'.$i.'.Name'] = $value->name; - } - if (isset($value->data)) { - $subst['$'.$i.'.Data'] = $value->data; - } - $subst['$'.$i.'.Compact'] = - $subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value); - // a more complex algorithm for compact representation - // could be introduced for all types of tokens. This - // may need to be factored out into a dedicated class - if (!empty($value->attr)) { - $stripped_token = clone $value; - $stripped_token->attr = array(); - $subst['$'.$i.'.Compact'] = $generator->generateFromToken($stripped_token); - } - $subst['$'.$i.'.Line'] = $value->line ? $value->line : 'unknown'; - } - continue; - } elseif (is_array($value)) { - $keys = array_keys($value); - if (array_keys($keys) === $keys) { - // list - $subst['$'.$i] = $this->listify($value); - } else { - // associative array - // no $i implementation yet, sorry - $subst['$'.$i.'.Keys'] = $this->listify($keys); - $subst['$'.$i.'.Values'] = $this->listify(array_values($value)); - } - continue; - } - $subst['$' . $i] = $value; - } - return strtr($raw, $subst); - } -} - -// vim: et sw=4 sts=4 +config = $config; + $this->context = $context; + } + + /** + * Loads language object with necessary info from factory cache + * @note This is a lazy loader + */ + public function load() + { + if ($this->_loaded) { + return; + } + $factory = HTMLPurifier_LanguageFactory::instance(); + $factory->loadLanguage($this->code); + foreach ($factory->keys as $key) { + $this->$key = $factory->cache[$this->code][$key]; + } + $this->_loaded = true; + } + + /** + * Retrieves a localised message. + * @param string $key string identifier of message + * @return string localised message + */ + public function getMessage($key) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + return $this->messages[$key]; + } + + /** + * Retrieves a localised error name. + * @param int $int error number, corresponding to PHP's error reporting + * @return string localised message + */ + public function getErrorName($int) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->errorNames[$int])) { + return "[Error: $int]"; + } + return $this->errorNames[$int]; + } + + /** + * Converts an array list into a string readable representation + * @param array $array + * @return string + */ + public function listify($array) + { + $sep = $this->getMessage('Item separator'); + $sep_last = $this->getMessage('Item separator last'); + $ret = ''; + for ($i = 0, $c = count($array); $i < $c; $i++) { + if ($i == 0) { + } elseif ($i + 1 < $c) { + $ret .= $sep; + } else { + $ret .= $sep_last; + } + $ret .= $array[$i]; + } + return $ret; + } + + /** + * Formats a localised message with passed parameters + * @param string $key string identifier of message + * @param array $args Parameters to substitute in + * @return string localised message + * @todo Implement conditionals? Right now, some messages make + * reference to line numbers, but those aren't always available + */ + public function formatMessage($key, $args = array()) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + $raw = $this->messages[$key]; + $subst = array(); + $generator = false; + foreach ($args as $i => $value) { + if (is_object($value)) { + if ($value instanceof HTMLPurifier_Token) { + // factor this out some time + if (!$generator) { + $generator = $this->context->get('Generator'); + } + if (isset($value->name)) { + $subst['$'.$i.'.Name'] = $value->name; + } + if (isset($value->data)) { + $subst['$'.$i.'.Data'] = $value->data; + } + $subst['$'.$i.'.Compact'] = + $subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value); + // a more complex algorithm for compact representation + // could be introduced for all types of tokens. This + // may need to be factored out into a dedicated class + if (!empty($value->attr)) { + $stripped_token = clone $value; + $stripped_token->attr = array(); + $subst['$'.$i.'.Compact'] = $generator->generateFromToken($stripped_token); + } + $subst['$'.$i.'.Line'] = $value->line ? $value->line : 'unknown'; + } + continue; + } elseif (is_array($value)) { + $keys = array_keys($value); + if (array_keys($keys) === $keys) { + // list + $subst['$'.$i] = $this->listify($value); + } else { + // associative array + // no $i implementation yet, sorry + $subst['$'.$i.'.Keys'] = $this->listify($keys); + $subst['$'.$i.'.Values'] = $this->listify(array_values($value)); + } + continue; + } + $subst['$' . $i] = $value; + } + return strtr($raw, $subst); + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Language/classes/en-x-test.php b/lib/htmlpurifier/HTMLPurifier/Language/classes/en-x-test.php index 8828f5cdede..a6f8d163437 100644 --- a/lib/htmlpurifier/HTMLPurifier/Language/classes/en-x-test.php +++ b/lib/htmlpurifier/HTMLPurifier/Language/classes/en-x-test.php @@ -1,9 +1,9 @@ - 'HTML Purifier X' -); - -// vim: et sw=4 sts=4 + 'HTML Purifier X' +); + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Language/messages/en-x-testmini.php b/lib/htmlpurifier/HTMLPurifier/Language/messages/en-x-testmini.php index 806c83fbf75..ed8560fd586 100644 --- a/lib/htmlpurifier/HTMLPurifier/Language/messages/en-x-testmini.php +++ b/lib/htmlpurifier/HTMLPurifier/Language/messages/en-x-testmini.php @@ -1,12 +1,12 @@ - 'HTML Purifier XNone' -); - -// vim: et sw=4 sts=4 + 'HTML Purifier XNone' +); + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Language/messages/en.php b/lib/htmlpurifier/HTMLPurifier/Language/messages/en.php index c7f197e1e1b..1fa30bdfedd 100644 --- a/lib/htmlpurifier/HTMLPurifier/Language/messages/en.php +++ b/lib/htmlpurifier/HTMLPurifier/Language/messages/en.php @@ -1,55 +1,55 @@ - 'HTML Purifier', -// for unit testing purposes - 'LanguageFactoryTest: Pizza' => 'Pizza', - 'LanguageTest: List' => '$1', - 'LanguageTest: Hash' => '$1.Keys; $1.Values', - 'Item separator' => ', ', - 'Item separator last' => ' and ', // non-Harvard style - - 'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', - 'ErrorCollector: At line' => ' at line $line', - 'ErrorCollector: Incidental errors' => 'Incidental errors', - 'Lexer: Unclosed comment' => 'Unclosed comment', - 'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', - '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', - 'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', - 'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', - 'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', - 'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', - 'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', - 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', - 'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', - 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', - 'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', - 'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', - 'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', - 'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', - 'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', - 'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', - 'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', - 'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', - 'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', - 'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', - 'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', - 'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', - 'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', -); - -$errorNames = array( - E_ERROR => 'Error', - E_WARNING => 'Warning', - E_NOTICE => 'Notice' -); - -// vim: et sw=4 sts=4 + 'HTML Purifier', +// for unit testing purposes + 'LanguageFactoryTest: Pizza' => 'Pizza', + 'LanguageTest: List' => '$1', + 'LanguageTest: Hash' => '$1.Keys; $1.Values', + 'Item separator' => ', ', + 'Item separator last' => ' and ', // non-Harvard style + + 'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', + 'ErrorCollector: At line' => ' at line $line', + 'ErrorCollector: Incidental errors' => 'Incidental errors', + 'Lexer: Unclosed comment' => 'Unclosed comment', + 'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', + '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', + 'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', + 'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', + 'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', + 'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', + 'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', + 'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', + 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', + 'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', + 'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', + 'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', + 'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', + 'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', + 'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', + 'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', +); + +$errorNames = array( + E_ERROR => 'Error', + E_WARNING => 'Warning', + E_NOTICE => 'Notice' +); + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/LanguageFactory.php b/lib/htmlpurifier/HTMLPurifier/LanguageFactory.php index 4e35272d873..e3e7a3b8d72 100644 --- a/lib/htmlpurifier/HTMLPurifier/LanguageFactory.php +++ b/lib/htmlpurifier/HTMLPurifier/LanguageFactory.php @@ -1,209 +1,209 @@ -cache[$language_code][$key] = $value - * @type array - */ - public $cache; - - /** - * Valid keys in the HTMLPurifier_Language object. Designates which - * variables to slurp out of a message file. - * @type array - */ - public $keys = array('fallback', 'messages', 'errorNames'); - - /** - * Instance to validate language codes. - * @type HTMLPurifier_AttrDef_Lang - * - */ - protected $validator; - - /** - * Cached copy of dirname(__FILE__), directory of current file without - * trailing slash. - * @type string - */ - protected $dir; - - /** - * Keys whose contents are a hash map and can be merged. - * @type array - */ - protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true); - - /** - * Keys whose contents are a list and can be merged. - * @value array lookup - */ - protected $mergeable_keys_list = array(); - - /** - * Retrieve sole instance of the factory. - * @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with, - * or bool true to reset to default factory. - * @return HTMLPurifier_LanguageFactory - */ - public static function instance($prototype = null) - { - static $instance = null; - if ($prototype !== null) { - $instance = $prototype; - } elseif ($instance === null || $prototype == true) { - $instance = new HTMLPurifier_LanguageFactory(); - $instance->setup(); - } - return $instance; - } - - /** - * Sets up the singleton, much like a constructor - * @note Prevents people from getting this outside of the singleton - */ - public function setup() - { - $this->validator = new HTMLPurifier_AttrDef_Lang(); - $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier'; - } - - /** - * Creates a language object, handles class fallbacks - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @param bool|string $code Code to override configuration with. Private parameter. - * @return HTMLPurifier_Language - */ - public function create($config, $context, $code = false) - { - // validate language code - if ($code === false) { - $code = $this->validator->validate( - $config->get('Core.Language'), - $config, - $context - ); - } else { - $code = $this->validator->validate($code, $config, $context); - } - if ($code === false) { - $code = 'en'; // malformed code becomes English - } - - $pcode = str_replace('-', '_', $code); // make valid PHP classname - static $depth = 0; // recursion protection - - if ($code == 'en') { - $lang = new HTMLPurifier_Language($config, $context); - } else { - $class = 'HTMLPurifier_Language_' . $pcode; - $file = $this->dir . '/Language/classes/' . $code . '.php'; - if (file_exists($file) || class_exists($class, false)) { - $lang = new $class($config, $context); - } else { - // Go fallback - $raw_fallback = $this->getFallbackFor($code); - $fallback = $raw_fallback ? $raw_fallback : 'en'; - $depth++; - $lang = $this->create($config, $context, $fallback); - if (!$raw_fallback) { - $lang->error = true; - } - $depth--; - } - } - $lang->code = $code; - return $lang; - } - - /** - * Returns the fallback language for language - * @note Loads the original language into cache - * @param string $code language code - * @return string|bool - */ - public function getFallbackFor($code) - { - $this->loadLanguage($code); - return $this->cache[$code]['fallback']; - } - - /** - * Loads language into the cache, handles message file and fallbacks - * @param string $code language code - */ - public function loadLanguage($code) - { - static $languages_seen = array(); // recursion guard - - // abort if we've already loaded it - if (isset($this->cache[$code])) { - return; - } - - // generate filename - $filename = $this->dir . '/Language/messages/' . $code . '.php'; - - // default fallback : may be overwritten by the ensuing include - $fallback = ($code != 'en') ? 'en' : false; - - // load primary localisation - if (!file_exists($filename)) { - // skip the include: will rely solely on fallback - $filename = $this->dir . '/Language/messages/en.php'; - $cache = array(); - } else { - include $filename; - $cache = compact($this->keys); - } - - // load fallback localisation - if (!empty($fallback)) { - - // infinite recursion guard - if (isset($languages_seen[$code])) { - trigger_error( - 'Circular fallback reference in language ' . - $code, - E_USER_ERROR - ); - $fallback = 'en'; - } - $language_seen[$code] = true; - - // load the fallback recursively - $this->loadLanguage($fallback); - $fallback_cache = $this->cache[$fallback]; - - // merge fallback with current language - foreach ($this->keys as $key) { - if (isset($cache[$key]) && isset($fallback_cache[$key])) { - if (isset($this->mergeable_keys_map[$key])) { - $cache[$key] = $cache[$key] + $fallback_cache[$key]; - } elseif (isset($this->mergeable_keys_list[$key])) { - $cache[$key] = array_merge($fallback_cache[$key], $cache[$key]); - } - } else { - $cache[$key] = $fallback_cache[$key]; - } - } - } - - // save to cache for later retrieval - $this->cache[$code] = $cache; - return; - } -} - -// vim: et sw=4 sts=4 +cache[$language_code][$key] = $value + * @type array + */ + public $cache; + + /** + * Valid keys in the HTMLPurifier_Language object. Designates which + * variables to slurp out of a message file. + * @type array + */ + public $keys = array('fallback', 'messages', 'errorNames'); + + /** + * Instance to validate language codes. + * @type HTMLPurifier_AttrDef_Lang + * + */ + protected $validator; + + /** + * Cached copy of dirname(__FILE__), directory of current file without + * trailing slash. + * @type string + */ + protected $dir; + + /** + * Keys whose contents are a hash map and can be merged. + * @type array + */ + protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true); + + /** + * Keys whose contents are a list and can be merged. + * @value array lookup + */ + protected $mergeable_keys_list = array(); + + /** + * Retrieve sole instance of the factory. + * @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with, + * or bool true to reset to default factory. + * @return HTMLPurifier_LanguageFactory + */ + public static function instance($prototype = null) + { + static $instance = null; + if ($prototype !== null) { + $instance = $prototype; + } elseif ($instance === null || $prototype == true) { + $instance = new HTMLPurifier_LanguageFactory(); + $instance->setup(); + } + return $instance; + } + + /** + * Sets up the singleton, much like a constructor + * @note Prevents people from getting this outside of the singleton + */ + public function setup() + { + $this->validator = new HTMLPurifier_AttrDef_Lang(); + $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier'; + } + + /** + * Creates a language object, handles class fallbacks + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @param bool|string $code Code to override configuration with. Private parameter. + * @return HTMLPurifier_Language + */ + public function create($config, $context, $code = false) + { + // validate language code + if ($code === false) { + $code = $this->validator->validate( + $config->get('Core.Language'), + $config, + $context + ); + } else { + $code = $this->validator->validate($code, $config, $context); + } + if ($code === false) { + $code = 'en'; // malformed code becomes English + } + + $pcode = str_replace('-', '_', $code); // make valid PHP classname + static $depth = 0; // recursion protection + + if ($code == 'en') { + $lang = new HTMLPurifier_Language($config, $context); + } else { + $class = 'HTMLPurifier_Language_' . $pcode; + $file = $this->dir . '/Language/classes/' . $code . '.php'; + if (file_exists($file) || class_exists($class, false)) { + $lang = new $class($config, $context); + } else { + // Go fallback + $raw_fallback = $this->getFallbackFor($code); + $fallback = $raw_fallback ? $raw_fallback : 'en'; + $depth++; + $lang = $this->create($config, $context, $fallback); + if (!$raw_fallback) { + $lang->error = true; + } + $depth--; + } + } + $lang->code = $code; + return $lang; + } + + /** + * Returns the fallback language for language + * @note Loads the original language into cache + * @param string $code language code + * @return string|bool + */ + public function getFallbackFor($code) + { + $this->loadLanguage($code); + return $this->cache[$code]['fallback']; + } + + /** + * Loads language into the cache, handles message file and fallbacks + * @param string $code language code + */ + public function loadLanguage($code) + { + static $languages_seen = array(); // recursion guard + + // abort if we've already loaded it + if (isset($this->cache[$code])) { + return; + } + + // generate filename + $filename = $this->dir . '/Language/messages/' . $code . '.php'; + + // default fallback : may be overwritten by the ensuing include + $fallback = ($code != 'en') ? 'en' : false; + + // load primary localisation + if (!file_exists($filename)) { + // skip the include: will rely solely on fallback + $filename = $this->dir . '/Language/messages/en.php'; + $cache = array(); + } else { + include $filename; + $cache = compact($this->keys); + } + + // load fallback localisation + if (!empty($fallback)) { + + // infinite recursion guard + if (isset($languages_seen[$code])) { + trigger_error( + 'Circular fallback reference in language ' . + $code, + E_USER_ERROR + ); + $fallback = 'en'; + } + $language_seen[$code] = true; + + // load the fallback recursively + $this->loadLanguage($fallback); + $fallback_cache = $this->cache[$fallback]; + + // merge fallback with current language + foreach ($this->keys as $key) { + if (isset($cache[$key]) && isset($fallback_cache[$key])) { + if (isset($this->mergeable_keys_map[$key])) { + $cache[$key] = $cache[$key] + $fallback_cache[$key]; + } elseif (isset($this->mergeable_keys_list[$key])) { + $cache[$key] = array_merge($fallback_cache[$key], $cache[$key]); + } + } else { + $cache[$key] = $fallback_cache[$key]; + } + } + } + + // save to cache for later retrieval + $this->cache[$code] = $cache; + return; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Length.php b/lib/htmlpurifier/HTMLPurifier/Length.php index bbfbe6624d6..9cc1bc750b6 100644 --- a/lib/htmlpurifier/HTMLPurifier/Length.php +++ b/lib/htmlpurifier/HTMLPurifier/Length.php @@ -1,160 +1,162 @@ - true, 'ex' => true, 'px' => true, 'in' => true, - 'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true - ); - - /** - * @param string $n Magnitude - * @param bool|string $u Unit - */ - public function __construct($n = '0', $u = false) - { - $this->n = (string) $n; - $this->unit = $u !== false ? (string) $u : false; - } - - /** - * @param string $s Unit string, like '2em' or '3.4in' - * @return HTMLPurifier_Length - * @warning Does not perform validation. - */ - public static function make($s) - { - if ($s instanceof HTMLPurifier_Length) { - return $s; - } - $n_length = strspn($s, '1234567890.+-'); - $n = substr($s, 0, $n_length); - $unit = substr($s, $n_length); - if ($unit === '') { - $unit = false; - } - return new HTMLPurifier_Length($n, $unit); - } - - /** - * Validates the number and unit. - * @return bool - */ - protected function validate() - { - // Special case: - if ($this->n === '+0' || $this->n === '-0') { - $this->n = '0'; - } - if ($this->n === '0' && $this->unit === false) { - return true; - } - if (!ctype_lower($this->unit)) { - $this->unit = strtolower($this->unit); - } - if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) { - return false; - } - // Hack: - $def = new HTMLPurifier_AttrDef_CSS_Number(); - $result = $def->validate($this->n, false, false); - if ($result === false) { - return false; - } - $this->n = $result; - return true; - } - - /** - * Returns string representation of number. - * @return string - */ - public function toString() - { - if (!$this->isValid()) { - return false; - } - return $this->n . $this->unit; - } - - /** - * Retrieves string numeric magnitude. - * @return string - */ - public function getN() - { - return $this->n; - } - - /** - * Retrieves string unit. - * @return string - */ - public function getUnit() - { - return $this->unit; - } - - /** - * Returns true if this length unit is valid. - * @return bool - */ - public function isValid() - { - if ($this->isValid === null) { - $this->isValid = $this->validate(); - } - return $this->isValid; - } - - /** - * Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal. - * @param HTMLPurifier_Length $l - * @return int - * @warning If both values are too large or small, this calculation will - * not work properly - */ - public function compareTo($l) - { - if ($l === false) { - return false; - } - if ($l->unit !== $this->unit) { - $converter = new HTMLPurifier_UnitConverter(); - $l = $converter->convert($l, $this->unit); - if ($l === false) { - return false; - } - } - return $this->n - $l->n; - } -} - -// vim: et sw=4 sts=4 + true, 'ex' => true, 'px' => true, 'in' => true, + 'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true, + 'ch' => true, 'rem' => true, 'vw' => true, 'vh' => true, + 'vmin' => true, 'vmax' => true + ); + + /** + * @param string $n Magnitude + * @param bool|string $u Unit + */ + public function __construct($n = '0', $u = false) + { + $this->n = (string) $n; + $this->unit = $u !== false ? (string) $u : false; + } + + /** + * @param string $s Unit string, like '2em' or '3.4in' + * @return HTMLPurifier_Length + * @warning Does not perform validation. + */ + public static function make($s) + { + if ($s instanceof HTMLPurifier_Length) { + return $s; + } + $n_length = strspn($s, '1234567890.+-'); + $n = substr($s, 0, $n_length); + $unit = substr($s, $n_length); + if ($unit === '') { + $unit = false; + } + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Validates the number and unit. + * @return bool + */ + protected function validate() + { + // Special case: + if ($this->n === '+0' || $this->n === '-0') { + $this->n = '0'; + } + if ($this->n === '0' && $this->unit === false) { + return true; + } + if (!ctype_lower($this->unit)) { + $this->unit = strtolower($this->unit); + } + if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) { + return false; + } + // Hack: + $def = new HTMLPurifier_AttrDef_CSS_Number(); + $result = $def->validate($this->n, false, false); + if ($result === false) { + return false; + } + $this->n = $result; + return true; + } + + /** + * Returns string representation of number. + * @return string + */ + public function toString() + { + if (!$this->isValid()) { + return false; + } + return $this->n . $this->unit; + } + + /** + * Retrieves string numeric magnitude. + * @return string + */ + public function getN() + { + return $this->n; + } + + /** + * Retrieves string unit. + * @return string + */ + public function getUnit() + { + return $this->unit; + } + + /** + * Returns true if this length unit is valid. + * @return bool + */ + public function isValid() + { + if ($this->isValid === null) { + $this->isValid = $this->validate(); + } + return $this->isValid; + } + + /** + * Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal. + * @param HTMLPurifier_Length $l + * @return int + * @warning If both values are too large or small, this calculation will + * not work properly + */ + public function compareTo($l) + { + if ($l === false) { + return false; + } + if ($l->unit !== $this->unit) { + $converter = new HTMLPurifier_UnitConverter(); + $l = $converter->convert($l, $this->unit); + if ($l === false) { + return false; + } + } + return $this->n - $l->n; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Lexer.php b/lib/htmlpurifier/HTMLPurifier/Lexer.php index e9da3ed5e94..1f48ab58cf2 100644 --- a/lib/htmlpurifier/HTMLPurifier/Lexer.php +++ b/lib/htmlpurifier/HTMLPurifier/Lexer.php @@ -1,382 +1,382 @@ -get('Core.LexerImpl'); - } - - $needs_tracking = - $config->get('Core.MaintainLineNumbers') || - $config->get('Core.CollectErrors'); - - $inst = null; - if (is_object($lexer)) { - $inst = $lexer; - } else { - if (is_null($lexer)) { - do { - // auto-detection algorithm - if ($needs_tracking) { - $lexer = 'DirectLex'; - break; - } - - if (class_exists('DOMDocument', false) && - method_exists('DOMDocument', 'loadHTML') && - !extension_loaded('domxml') - ) { - // check for DOM support, because while it's part of the - // core, it can be disabled compile time. Also, the PECL - // domxml extension overrides the default DOM, and is evil - // and nasty and we shan't bother to support it - $lexer = 'DOMLex'; - } else { - $lexer = 'DirectLex'; - } - } while (0); - } // do..while so we can break - - // instantiate recognized string names - switch ($lexer) { - case 'DOMLex': - $inst = new HTMLPurifier_Lexer_DOMLex(); - break; - case 'DirectLex': - $inst = new HTMLPurifier_Lexer_DirectLex(); - break; - case 'PH5P': - $inst = new HTMLPurifier_Lexer_PH5P(); - break; - default: - throw new HTMLPurifier_Exception( - "Cannot instantiate unrecognized Lexer type " . - htmlspecialchars($lexer) - ); - } - } - - if (!$inst) { - throw new HTMLPurifier_Exception('No lexer was instantiated'); - } - - // once PHP DOM implements native line numbers, or we - // hack out something using XSLT, remove this stipulation - if ($needs_tracking && !$inst->tracksLineNumbers) { - throw new HTMLPurifier_Exception( - 'Cannot use lexer that does not support line numbers with ' . - 'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)' - ); - } - - return $inst; - - } - - // -- CONVENIENCE MEMBERS --------------------------------------------- - - public function __construct() - { - $this->_entity_parser = new HTMLPurifier_EntityParser(); - } - - /** - * Most common entity to raw value conversion table for special entities. - * @type array - */ - protected $_special_entity2str = - array( - '"' => '"', - '&' => '&', - '<' => '<', - '>' => '>', - ''' => "'", - ''' => "'", - ''' => "'" - ); - - public function parseText($string, $config) { - return $this->parseData($string, false, $config); - } - - public function parseAttr($string, $config) { - return $this->parseData($string, true, $config); - } - - /** - * Parses special entities into the proper characters. - * - * This string will translate escaped versions of the special characters - * into the correct ones. - * - * @param string $string String character data to be parsed. - * @return string Parsed character data. - */ - public function parseData($string, $is_attr, $config) - { - // following functions require at least one character - if ($string === '') { - return ''; - } - - // subtracts amps that cannot possibly be escaped - $num_amp = substr_count($string, '&') - substr_count($string, '& ') - - ($string[strlen($string) - 1] === '&' ? 1 : 0); - - if (!$num_amp) { - return $string; - } // abort if no entities - $num_esc_amp = substr_count($string, '&'); - $string = strtr($string, $this->_special_entity2str); - - // code duplication for sake of optimization, see above - $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') - - ($string[strlen($string) - 1] === '&' ? 1 : 0); - - if ($num_amp_2 <= $num_esc_amp) { - return $string; - } - - // hmm... now we have some uncommon entities. Use the callback. - if ($config->get('Core.LegacyEntityDecoder')) { - $string = $this->_entity_parser->substituteSpecialEntities($string); - } else { - if ($is_attr) { - $string = $this->_entity_parser->substituteAttrEntities($string); - } else { - $string = $this->_entity_parser->substituteTextEntities($string); - } - } - return $string; - } - - /** - * Lexes an HTML string into tokens. - * @param $string String HTML. - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return HTMLPurifier_Token[] array representation of HTML. - */ - public function tokenizeHTML($string, $config, $context) - { - trigger_error('Call to abstract class', E_USER_ERROR); - } - - /** - * Translates CDATA sections into regular sections (through escaping). - * @param string $string HTML string to process. - * @return string HTML with CDATA sections escaped. - */ - protected static function escapeCDATA($string) - { - return preg_replace_callback( - '//s', - array('HTMLPurifier_Lexer', 'CDATACallback'), - $string - ); - } - - /** - * Special CDATA case that is especially convoluted for #i', '', $html); - } - - return $html; - } - - /** - * Takes a string of HTML (fragment or document) and returns the content - * @todo Consider making protected - */ - public function extractBody($html) - { - $matches = array(); - $result = preg_match('|(.*?)- $tokens = array(); - $this->tokenizeDOM($div, $tokens, $config); - // If the div has a sibling, that means we tripped across - // a prematuretag. So remove the div we parsed, - // and then tokenize the rest of body. We can't tokenize - // the sibling directly as we'll lose the tags in that case. - if ($div->nextSibling) { - $body->removeChild($div); - $this->tokenizeDOM($body, $tokens, $config); - } - return $tokens; - } - - /** - * Iterative function that tokenizes a node, putting it into an accumulator. - * To iterate is human, to recurse divine - L. Peter Deutsch - * @param DOMNode $node DOMNode to be tokenized. - * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. - * @return HTMLPurifier_Token of node appended to previously passed tokens. - */ - protected function tokenizeDOM($node, &$tokens, $config) - { - $level = 0; - $nodes = array($level => new HTMLPurifier_Queue(array($node))); - $closingNodes = array(); - do { - while (!$nodes[$level]->isEmpty()) { - $node = $nodes[$level]->shift(); // FIFO - $collect = $level > 0 ? true : false; - $needEndingTag = $this->createStartNode($node, $tokens, $collect, $config); - if ($needEndingTag) { - $closingNodes[$level][] = $node; - } - if ($node->childNodes && $node->childNodes->length) { - $level++; - $nodes[$level] = new HTMLPurifier_Queue(); - foreach ($node->childNodes as $childNode) { - $nodes[$level]->push($childNode); - } - } - } - $level--; - if ($level && isset($closingNodes[$level])) { - while ($node = array_pop($closingNodes[$level])) { - $this->createEndNode($node, $tokens); - } - } - } while ($level > 0); - } - - /** - * @param DOMNode $node DOMNode to be tokenized. - * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. - * @param bool $collect Says whether or start and close are collected, set to - * false at first recursion because it's the implicit DIV - * tag you're dealing with. - * @return bool if the token needs an endtoken - * @todo data and tagName properties don't seem to exist in DOMNode? - */ - protected function createStartNode($node, &$tokens, $collect, $config) - { - // intercept non element nodes. WE MUST catch all of them, - // but we're not getting the character reference nodes because - // those should have been preprocessed - if ($node->nodeType === XML_TEXT_NODE) { - $tokens[] = $this->factory->createText($node->data); - return false; - } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { - // undo libxml's special treatment of )#si', - array($this, 'scriptCallback'), - $html - ); - } - - $html = $this->normalize($html, $config, $context); - - $cursor = 0; // our location in the text - $inside_tag = false; // whether or not we're parsing the inside of a tag - $array = array(); // result array - - // This is also treated to mean maintain *column* numbers too - $maintain_line_numbers = $config->get('Core.MaintainLineNumbers'); - - if ($maintain_line_numbers === null) { - // automatically determine line numbering by checking - // if error collection is on - $maintain_line_numbers = $config->get('Core.CollectErrors'); - } - - if ($maintain_line_numbers) { - $current_line = 1; - $current_col = 0; - $length = strlen($html); - } else { - $current_line = false; - $current_col = false; - $length = false; - } - $context->register('CurrentLine', $current_line); - $context->register('CurrentCol', $current_col); - $nl = "\n"; - // how often to manually recalculate. This will ALWAYS be right, - // but it's pretty wasteful. Set to 0 to turn off - $synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval'); - - $e = false; - if ($config->get('Core.CollectErrors')) { - $e =& $context->get('ErrorCollector'); - } - - // for testing synchronization - $loops = 0; - - while (++$loops) { - // $cursor is either at the start of a token, or inside of - // a tag (i.e. there was a < immediately before it), as indicated - // by $inside_tag - - if ($maintain_line_numbers) { - // $rcursor, however, is always at the start of a token. - $rcursor = $cursor - (int)$inside_tag; - - // Column number is cheap, so we calculate it every round. - // We're interested at the *end* of the newline string, so - // we need to add strlen($nl) == 1 to $nl_pos before subtracting it - // from our "rcursor" position. - $nl_pos = strrpos($html, $nl, $rcursor - $length); - $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1); - - // recalculate lines - if ($synchronize_interval && // synchronization is on - $cursor > 0 && // cursor is further than zero - $loops % $synchronize_interval === 0) { // time to synchronize! - $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor); - } - } - - $position_next_lt = strpos($html, '<', $cursor); - $position_next_gt = strpos($html, '>', $cursor); - - // triggers on "asdf" but not "asdf " - // special case to set up context - if ($position_next_lt === $cursor) { - $inside_tag = true; - $cursor++; - } - - if (!$inside_tag && $position_next_lt !== false) { - // We are not inside tag and there still is another tag to parse - $token = new - HTMLPurifier_Token_Text( - $this->parseText( - substr( - $html, - $cursor, - $position_next_lt - $cursor - ), $config - ) - ); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor); - } - $array[] = $token; - $cursor = $position_next_lt + 1; - $inside_tag = true; - continue; - } elseif (!$inside_tag) { - // We are not inside tag but there are no more tags - // If we're already at the end, break - if ($cursor === strlen($html)) { - break; - } - // Create Text of rest of string - $token = new - HTMLPurifier_Token_Text( - $this->parseText( - substr( - $html, - $cursor - ), $config - ) - ); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - } - $array[] = $token; - break; - } elseif ($inside_tag && $position_next_gt !== false) { - // We are in tag and it is well formed - // Grab the internals of the tag - $strlen_segment = $position_next_gt - $cursor; - - if ($strlen_segment < 1) { - // there's nothing to process! - $token = new HTMLPurifier_Token_Text('<'); - $cursor++; - continue; - } - - $segment = substr($html, $cursor, $strlen_segment); - - if ($segment === false) { - // somehow, we attempted to access beyond the end of - // the string, defense-in-depth, reported by Nate Abele - break; - } - - // Check if it's a comment - if (substr($segment, 0, 3) === '!--') { - // re-determine segment length, looking for --> - $position_comment_end = strpos($html, '-->', $cursor); - if ($position_comment_end === false) { - // uh oh, we have a comment that extends to - // infinity. Can't be helped: set comment - // end position to end of string - if ($e) { - $e->send(E_WARNING, 'Lexer: Unclosed comment'); - } - $position_comment_end = strlen($html); - $end = true; - } else { - $end = false; - } - $strlen_segment = $position_comment_end - $cursor; - $segment = substr($html, $cursor, $strlen_segment); - $token = new - HTMLPurifier_Token_Comment( - substr( - $segment, - 3, - $strlen_segment - 3 - ) - ); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment); - } - $array[] = $token; - $cursor = $end ? $position_comment_end : $position_comment_end + 3; - $inside_tag = false; - continue; - } - - // Check if it's an end tag - $is_end_tag = (strpos($segment, '/') === 0); - if ($is_end_tag) { - $type = substr($segment, 1); - $token = new HTMLPurifier_Token_End($type); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); - } - $array[] = $token; - $inside_tag = false; - $cursor = $position_next_gt + 1; - continue; - } - - // Check leading character is alnum, if not, we may - // have accidently grabbed an emoticon. Translate into - // text and go our merry way - if (!ctype_alpha($segment[0])) { - // XML: $segment[0] !== '_' && $segment[0] !== ':' - if ($e) { - $e->send(E_NOTICE, 'Lexer: Unescaped lt'); - } - $token = new HTMLPurifier_Token_Text('<'); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); - } - $array[] = $token; - $inside_tag = false; - continue; - } - - // Check if it is explicitly self closing, if so, remove - // trailing slash. Remember, we could have a tag like
, so - // any later token processing scripts must convert improperly - // classified EmptyTags from StartTags. - $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1); - if ($is_self_closing) { - $strlen_segment--; - $segment = substr($segment, 0, $strlen_segment); - } - - // Check if there are any attributes - $position_first_space = strcspn($segment, $this->_whitespace); - - if ($position_first_space >= $strlen_segment) { - if ($is_self_closing) { - $token = new HTMLPurifier_Token_Empty($segment); - } else { - $token = new HTMLPurifier_Token_Start($segment); - } - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); - } - $array[] = $token; - $inside_tag = false; - $cursor = $position_next_gt + 1; - continue; - } - - // Grab out all the data - $type = substr($segment, 0, $position_first_space); - $attribute_string = - trim( - substr( - $segment, - $position_first_space - ) - ); - if ($attribute_string) { - $attr = $this->parseAttributeString( - $attribute_string, - $config, - $context - ); - } else { - $attr = array(); - } - - if ($is_self_closing) { - $token = new HTMLPurifier_Token_Empty($type, $attr); - } else { - $token = new HTMLPurifier_Token_Start($type, $attr); - } - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); - } - $array[] = $token; - $cursor = $position_next_gt + 1; - $inside_tag = false; - continue; - } else { - // inside tag, but there's no ending > sign - if ($e) { - $e->send(E_WARNING, 'Lexer: Missing gt'); - } - $token = new - HTMLPurifier_Token_Text( - '<' . - $this->parseText( - substr($html, $cursor), $config - ) - ); - if ($maintain_line_numbers) { - $token->rawPosition($current_line, $current_col); - } - // no cursor scroll? Hmm... - $array[] = $token; - break; - } - break; - } - - $context->destroy('CurrentLine'); - $context->destroy('CurrentCol'); - return $array; - } - - /** - * PHP 5.0.x compatible substr_count that implements offset and length - * @param string $haystack - * @param string $needle - * @param int $offset - * @param int $length - * @return int - */ - protected function substrCount($haystack, $needle, $offset, $length) - { - static $oldVersion; - if ($oldVersion === null) { - $oldVersion = version_compare(PHP_VERSION, '5.1', '<'); - } - if ($oldVersion) { - $haystack = substr($haystack, $offset, $length); - return substr_count($haystack, $needle); - } else { - return substr_count($haystack, $needle, $offset, $length); - } - } - - /** - * Takes the inside of an HTML tag and makes an assoc array of attributes. - * - * @param string $string Inside of tag excluding name. - * @param HTMLPurifier_Config $config - * @param HTMLPurifier_Context $context - * @return array Assoc array of attributes. - */ - public function parseAttributeString($string, $config, $context) - { - $string = (string)$string; // quick typecast - - if ($string == '') { - return array(); - } // no attributes - - $e = false; - if ($config->get('Core.CollectErrors')) { - $e =& $context->get('ErrorCollector'); - } - - // let's see if we can abort as quickly as possible - // one equal sign, no spaces => one attribute - $num_equal = substr_count($string, '='); - $has_space = strpos($string, ' '); - if ($num_equal === 0 && !$has_space) { - // bool attribute - return array($string => $string); - } elseif ($num_equal === 1 && !$has_space) { - // only one attribute - list($key, $quoted_value) = explode('=', $string); - $quoted_value = trim($quoted_value); - if (!$key) { - if ($e) { - $e->send(E_ERROR, 'Lexer: Missing attribute key'); - } - return array(); - } - if (!$quoted_value) { - return array($key => ''); - } - $first_char = @$quoted_value[0]; - $last_char = @$quoted_value[strlen($quoted_value) - 1]; - - $same_quote = ($first_char == $last_char); - $open_quote = ($first_char == '"' || $first_char == "'"); - - if ($same_quote && $open_quote) { - // well behaved - $value = substr($quoted_value, 1, strlen($quoted_value) - 2); - } else { - // not well behaved - if ($open_quote) { - if ($e) { - $e->send(E_ERROR, 'Lexer: Missing end quote'); - } - $value = substr($quoted_value, 1); - } else { - $value = $quoted_value; - } - } - if ($value === false) { - $value = ''; - } - return array($key => $this->parseAttr($value, $config)); - } - - // setup loop environment - $array = array(); // return assoc array of attributes - $cursor = 0; // current position in string (moves forward) - $size = strlen($string); // size of the string (stays the same) - - // if we have unquoted attributes, the parser expects a terminating - // space, so let's guarantee that there's always a terminating space. - $string .= ' '; - - $old_cursor = -1; - while ($cursor < $size) { - if ($old_cursor >= $cursor) { - throw new Exception("Infinite loop detected"); - } - $old_cursor = $cursor; - - $cursor += ($value = strspn($string, $this->_whitespace, $cursor)); - // grab the key - - $key_begin = $cursor; //we're currently at the start of the key - - // scroll past all characters that are the key (not whitespace or =) - $cursor += strcspn($string, $this->_whitespace . '=', $cursor); - - $key_end = $cursor; // now at the end of the key - - $key = substr($string, $key_begin, $key_end - $key_begin); - - if (!$key) { - if ($e) { - $e->send(E_ERROR, 'Lexer: Missing attribute key'); - } - $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop - continue; // empty key - } - - // scroll past all whitespace - $cursor += strspn($string, $this->_whitespace, $cursor); - - if ($cursor >= $size) { - $array[$key] = $key; - break; - } - - // if the next character is an equal sign, we've got a regular - // pair, otherwise, it's a bool attribute - $first_char = @$string[$cursor]; - - if ($first_char == '=') { - // key="value" - - $cursor++; - $cursor += strspn($string, $this->_whitespace, $cursor); - - if ($cursor === false) { - $array[$key] = ''; - break; - } - - // we might be in front of a quote right now - - $char = @$string[$cursor]; - - if ($char == '"' || $char == "'") { - // it's quoted, end bound is $char - $cursor++; - $value_begin = $cursor; - $cursor = strpos($string, $char, $cursor); - $value_end = $cursor; - } else { - // it's not quoted, end bound is whitespace - $value_begin = $cursor; - $cursor += strcspn($string, $this->_whitespace, $cursor); - $value_end = $cursor; - } - - // we reached a premature end - if ($cursor === false) { - $cursor = $size; - $value_end = $cursor; - } - - $value = substr($string, $value_begin, $value_end - $value_begin); - if ($value === false) { - $value = ''; - } - $array[$key] = $this->parseAttr($value, $config); - $cursor++; - } else { - // boolattr - if ($key !== '') { - $array[$key] = $key; - } else { - // purely theoretical - if ($e) { - $e->send(E_ERROR, 'Lexer: Missing attribute key'); - } - } - } - } - return $array; - } -} - -// vim: et sw=4 sts=4 +get('HTML.Trusted')) { + $html = preg_replace_callback( + '#(
, so + // any later token processing scripts must convert improperly + // classified EmptyTags from StartTags. + $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1); + if ($is_self_closing) { + $strlen_segment--; + $segment = substr($segment, 0, $strlen_segment); + } + + // Check if there are any attributes + $position_first_space = strcspn($segment, $this->_whitespace); + + if ($position_first_space >= $strlen_segment) { + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($segment); + } else { + $token = new HTMLPurifier_Token_Start($segment); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + $cursor = $position_next_gt + 1; + continue; + } + + // Grab out all the data + $type = substr($segment, 0, $position_first_space); + $attribute_string = + trim( + substr( + $segment, + $position_first_space + ) + ); + if ($attribute_string) { + $attr = $this->parseAttributeString( + $attribute_string, + $config, + $context + ); + } else { + $attr = array(); + } + + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($type, $attr); + } else { + $token = new HTMLPurifier_Token_Start($type, $attr); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $cursor = $position_next_gt + 1; + $inside_tag = false; + continue; + } else { + // inside tag, but there's no ending > sign + if ($e) { + $e->send(E_WARNING, 'Lexer: Missing gt'); + } + $token = new + HTMLPurifier_Token_Text( + '<' . + $this->parseText( + substr($html, $cursor), $config + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } + // no cursor scroll? Hmm... + $array[] = $token; + break; + } + break; + } + + $context->destroy('CurrentLine'); + $context->destroy('CurrentCol'); + return $array; + } + + /** + * PHP 5.0.x compatible substr_count that implements offset and length + * @param string $haystack + * @param string $needle + * @param int $offset + * @param int $length + * @return int + */ + protected function substrCount($haystack, $needle, $offset, $length) + { + static $oldVersion; + if ($oldVersion === null) { + $oldVersion = version_compare(PHP_VERSION, '5.1', '<'); + } + if ($oldVersion) { + $haystack = substr($haystack, $offset, $length); + return substr_count($haystack, $needle); + } else { + return substr_count($haystack, $needle, $offset, $length); + } + } + + /** + * Takes the inside of an HTML tag and makes an assoc array of attributes. + * + * @param string $string Inside of tag excluding name. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array Assoc array of attributes. + */ + public function parseAttributeString($string, $config, $context) + { + $string = (string)$string; // quick typecast + + if ($string == '') { + return array(); + } // no attributes + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + // let's see if we can abort as quickly as possible + // one equal sign, no spaces => one attribute + $num_equal = substr_count($string, '='); + $has_space = strpos($string, ' '); + if ($num_equal === 0 && !$has_space) { + // bool attribute + return array($string => $string); + } elseif ($num_equal === 1 && !$has_space) { + // only one attribute + list($key, $quoted_value) = explode('=', $string); + $quoted_value = trim($quoted_value); + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + return array(); + } + if (!$quoted_value) { + return array($key => ''); + } + $first_char = @$quoted_value[0]; + $last_char = @$quoted_value[strlen($quoted_value) - 1]; + + $same_quote = ($first_char == $last_char); + $open_quote = ($first_char == '"' || $first_char == "'"); + + if ($same_quote && $open_quote) { + // well behaved + $value = substr($quoted_value, 1, strlen($quoted_value) - 2); + } else { + // not well behaved + if ($open_quote) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing end quote'); + } + $value = substr($quoted_value, 1); + } else { + $value = $quoted_value; + } + } + if ($value === false) { + $value = ''; + } + return array($key => $this->parseAttr($value, $config)); + } + + // setup loop environment + $array = array(); // return assoc array of attributes + $cursor = 0; // current position in string (moves forward) + $size = strlen($string); // size of the string (stays the same) + + // if we have unquoted attributes, the parser expects a terminating + // space, so let's guarantee that there's always a terminating space. + $string .= ' '; + + $old_cursor = -1; + while ($cursor < $size) { + if ($old_cursor >= $cursor) { + throw new Exception("Infinite loop detected"); + } + $old_cursor = $cursor; + + $cursor += ($value = strspn($string, $this->_whitespace, $cursor)); + // grab the key + + $key_begin = $cursor; //we're currently at the start of the key + + // scroll past all characters that are the key (not whitespace or =) + $cursor += strcspn($string, $this->_whitespace . '=', $cursor); + + $key_end = $cursor; // now at the end of the key + + $key = substr($string, $key_begin, $key_end - $key_begin); + + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop + continue; // empty key + } + + // scroll past all whitespace + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor >= $size) { + $array[$key] = $key; + break; + } + + // if the next character is an equal sign, we've got a regular + // pair, otherwise, it's a bool attribute + $first_char = @$string[$cursor]; + + if ($first_char == '=') { + // key="value" + + $cursor++; + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor === false) { + $array[$key] = ''; + break; + } + + // we might be in front of a quote right now + + $char = @$string[$cursor]; + + if ($char == '"' || $char == "'") { + // it's quoted, end bound is $char + $cursor++; + $value_begin = $cursor; + $cursor = strpos($string, $char, $cursor); + $value_end = $cursor; + } else { + // it's not quoted, end bound is whitespace + $value_begin = $cursor; + $cursor += strcspn($string, $this->_whitespace, $cursor); + $value_end = $cursor; + } + + // we reached a premature end + if ($cursor === false) { + $cursor = $size; + $value_end = $cursor; + } + + $value = substr($string, $value_begin, $value_end - $value_begin); + if ($value === false) { + $value = ''; + } + $array[$key] = $this->parseAttr($value, $config); + $cursor++; + } else { + // boolattr + if ($key !== '') { + $array[$key] = $key; + } else { + // purely theoretical + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + } + } + } + return $array; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/Lexer/PH5P.php b/lib/htmlpurifier/HTMLPurifier/Lexer/PH5P.php index 0b452d17fcd..6b281a5428e 100644 --- a/lib/htmlpurifier/HTMLPurifier/Lexer/PH5P.php +++ b/lib/htmlpurifier/HTMLPurifier/Lexer/PH5P.php @@ -1,4788 +1,4788 @@ -normalize($html, $config, $context); - $new_html = $this->wrapHTML($new_html, $config, $context, false /* no div */); - try { - $parser = new HTML5($new_html); - $doc = $parser->save(); - } catch (DOMException $e) { - // Uh oh, it failed. Punt to DirectLex. - $lexer = new HTMLPurifier_Lexer_DirectLex(); - $context->register('PH5PError', $e); // save the error, so we can detect it - return $lexer->tokenizeHTML($html, $config, $context); // use original HTML - } - $tokens = array(); - $this->tokenizeDOM( - $doc->getElementsByTagName('html')->item(0)-> // - getElementsByTagName('body')->item(0) // - , - $tokens, $config - ); - return $tokens; - } -} - -/* - -Copyright 2007 Jeroen van der Meer
'; printZipper($zipper, $token);//printTokens($this->stack); - //flush(); - - // quick-check: if it's not a tag, no need to process - if (empty($token->is_tag)) { - if ($token instanceof HTMLPurifier_Token_Text) { - foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) { - // See Note [Injector skips] - continue; - } - if ($token->rewind !== null && $token->rewind !== $i) { - continue; - } - // XXX fuckup - $r = $token; - $injector->handleText($r); - $token = $this->processToken($r, $i); - $reprocess = true; - break; - } - } - // another possibility is a comment - continue; - } - - if (isset($definition->info[$token->name])) { - $type = $definition->info[$token->name]->child->type; - } else { - $type = false; // Type is unknown, treat accordingly - } - - // quick tag checks: anything that's *not* an end tag - $ok = false; - if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) { - // claims to be a start tag but is empty - $token = new HTMLPurifier_Token_Empty( - $token->name, - $token->attr, - $token->line, - $token->col, - $token->armor - ); - $ok = true; - } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) { - // claims to be empty but really is a start tag - // NB: this assignment is required - $old_token = $token; - $token = new HTMLPurifier_Token_End($token->name); - $token = $this->insertBefore( - new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor) - ); - // punt (since we had to modify the input stream in a non-trivial way) - $reprocess = true; - continue; - } elseif ($token instanceof HTMLPurifier_Token_Empty) { - // real empty token - $ok = true; - } elseif ($token instanceof HTMLPurifier_Token_Start) { - // start tag - - // ...unless they also have to close their parent - if (!empty($this->stack)) { - - // Performance note: you might think that it's rather - // inefficient, recalculating the autoclose information - // for every tag that a token closes (since when we - // do an autoclose, we push a new token into the - // stream and then /process/ that, before - // re-processing this token.) But this is - // necessary, because an injector can make an - // arbitrary transformations to the autoclosing - // tokens we introduce, so things may have changed - // in the meantime. Also, doing the inefficient thing is - // "easy" to reason about (for certain perverse definitions - // of "easy") - - $parent = array_pop($this->stack); - $this->stack[] = $parent; - - $parent_def = null; - $parent_elements = null; - $autoclose = false; - if (isset($definition->info[$parent->name])) { - $parent_def = $definition->info[$parent->name]; - $parent_elements = $parent_def->child->getAllowedElements($config); - $autoclose = !isset($parent_elements[$token->name]); - } - - if ($autoclose && $definition->info[$token->name]->wrap) { - // Check if an element can be wrapped by another - // element to make it valid in a context (for - // example,- in between) - $wrapname = $definition->info[$token->name]->wrap; - $wrapdef = $definition->info[$wrapname]; - $elements = $wrapdef->child->getAllowedElements($config); - if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) { - $newtoken = new HTMLPurifier_Token_Start($wrapname); - $token = $this->insertBefore($newtoken); - $reprocess = true; - continue; - } - } - - $carryover = false; - if ($autoclose && $parent_def->formatting) { - $carryover = true; - } - - if ($autoclose) { - // check if this autoclose is doomed to fail - // (this rechecks $parent, which his harmless) - $autoclose_ok = isset($global_parent_allowed_elements[$token->name]); - if (!$autoclose_ok) { - foreach ($this->stack as $ancestor) { - $elements = $definition->info[$ancestor->name]->child->getAllowedElements($config); - if (isset($elements[$token->name])) { - $autoclose_ok = true; - break; - } - if ($definition->info[$token->name]->wrap) { - $wrapname = $definition->info[$token->name]->wrap; - $wrapdef = $definition->info[$wrapname]; - $wrap_elements = $wrapdef->child->getAllowedElements($config); - if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) { - $autoclose_ok = true; - break; - } - } - } - } - if ($autoclose_ok) { - // errors need to be updated - $new_token = new HTMLPurifier_Token_End($parent->name); - $new_token->start = $parent; - // [TagClosedSuppress] - if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) { - if (!$carryover) { - $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent); - } else { - $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent); - } - } - if ($carryover) { - $element = clone $parent; - // [TagClosedAuto] - $element->armor['MakeWellFormed_TagClosedError'] = true; - $element->carryover = true; - $token = $this->processToken(array($new_token, $token, $element)); - } else { - $token = $this->insertBefore($new_token); - } - } else { - $token = $this->remove(); - } - $reprocess = true; - continue; - } - - } - $ok = true; - } - - if ($ok) { - foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) { - // See Note [Injector skips] - continue; - } - if ($token->rewind !== null && $token->rewind !== $i) { - continue; - } - $r = $token; - $injector->handleElement($r); - $token = $this->processToken($r, $i); - $reprocess = true; - break; - } - if (!$reprocess) { - // ah, nothing interesting happened; do normal processing - if ($token instanceof HTMLPurifier_Token_Start) { - $this->stack[] = $token; - } elseif ($token instanceof HTMLPurifier_Token_End) { - throw new HTMLPurifier_Exception( - 'Improper handling of end tag in start code; possible error in MakeWellFormed' - ); - } - } - continue; - } - - // sanity check: we should be dealing with a closing tag - if (!$token instanceof HTMLPurifier_Token_End) { - throw new HTMLPurifier_Exception('Unaccounted for tag token in input stream, bug in HTML Purifier'); - } - - // make sure that we have something open - if (empty($this->stack)) { - if ($escape_invalid_tags) { - if ($e) { - $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text'); - } - $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); - } else { - if ($e) { - $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); - } - $token = $this->remove(); - } - $reprocess = true; - continue; - } - - // first, check for the simplest case: everything closes neatly. - // Eventually, everything passes through here; if there are problems - // we modify the input stream accordingly and then punt, so that - // the tokens get processed again. - $current_parent = array_pop($this->stack); - if ($current_parent->name == $token->name) { - $token->start = $current_parent; - foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) { - // See Note [Injector skips] - continue; - } - if ($token->rewind !== null && $token->rewind !== $i) { - continue; - } - $r = $token; - $injector->handleEnd($r); - $token = $this->processToken($r, $i); - $this->stack[] = $current_parent; - $reprocess = true; - break; - } - continue; - } - - // okay, so we're trying to close the wrong tag - - // undo the pop previous pop - $this->stack[] = $current_parent; - - // scroll back the entire nest, trying to find our tag. - // (feature could be to specify how far you'd like to go) - $size = count($this->stack); - // -2 because -1 is the last element, but we already checked that - $skipped_tags = false; - for ($j = $size - 2; $j >= 0; $j--) { - if ($this->stack[$j]->name == $token->name) { - $skipped_tags = array_slice($this->stack, $j); - break; - } - } - - // we didn't find the tag, so remove - if ($skipped_tags === false) { - if ($escape_invalid_tags) { - if ($e) { - $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); - } - $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); - } else { - if ($e) { - $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); - } - $token = $this->remove(); - } - $reprocess = true; - continue; - } - - // do errors, in REVERSE $j order: a,b,c with
- needs a
'; printZipper($zipper, $token);//printTokens($this->stack); + //flush(); + + // quick-check: if it's not a tag, no need to process + if (empty($token->is_tag)) { + if ($token instanceof HTMLPurifier_Token_Text) { + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + // See Note [Injector skips] + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + // XXX fuckup + $r = $token; + $injector->handleText($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + } + // another possibility is a comment + continue; + } + + if (isset($definition->info[$token->name])) { + $type = $definition->info[$token->name]->child->type; + } else { + $type = false; // Type is unknown, treat accordingly + } + + // quick tag checks: anything that's *not* an end tag + $ok = false; + if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) { + // claims to be a start tag but is empty + $token = new HTMLPurifier_Token_Empty( + $token->name, + $token->attr, + $token->line, + $token->col, + $token->armor + ); + $ok = true; + } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) { + // claims to be empty but really is a start tag + // NB: this assignment is required + $old_token = $token; + $token = new HTMLPurifier_Token_End($token->name); + $token = $this->insertBefore( + new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor) + ); + // punt (since we had to modify the input stream in a non-trivial way) + $reprocess = true; + continue; + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + // real empty token + $ok = true; + } elseif ($token instanceof HTMLPurifier_Token_Start) { + // start tag + + // ...unless they also have to close their parent + if (!empty($this->stack)) { + + // Performance note: you might think that it's rather + // inefficient, recalculating the autoclose information + // for every tag that a token closes (since when we + // do an autoclose, we push a new token into the + // stream and then /process/ that, before + // re-processing this token.) But this is + // necessary, because an injector can make an + // arbitrary transformations to the autoclosing + // tokens we introduce, so things may have changed + // in the meantime. Also, doing the inefficient thing is + // "easy" to reason about (for certain perverse definitions + // of "easy") + + $parent = array_pop($this->stack); + $this->stack[] = $parent; + + $parent_def = null; + $parent_elements = null; + $autoclose = false; + if (isset($definition->info[$parent->name])) { + $parent_def = $definition->info[$parent->name]; + $parent_elements = $parent_def->child->getAllowedElements($config); + $autoclose = !isset($parent_elements[$token->name]); + } + + if ($autoclose && $definition->info[$token->name]->wrap) { + // Check if an element can be wrapped by another + // element to make it valid in a context (for + // example,- in between) + $wrapname = $definition->info[$token->name]->wrap; + $wrapdef = $definition->info[$wrapname]; + $elements = $wrapdef->child->getAllowedElements($config); + if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) { + $newtoken = new HTMLPurifier_Token_Start($wrapname); + $token = $this->insertBefore($newtoken); + $reprocess = true; + continue; + } + } + + $carryover = false; + if ($autoclose && $parent_def->formatting) { + $carryover = true; + } + + if ($autoclose) { + // check if this autoclose is doomed to fail + // (this rechecks $parent, which his harmless) + $autoclose_ok = isset($global_parent_allowed_elements[$token->name]); + if (!$autoclose_ok) { + foreach ($this->stack as $ancestor) { + $elements = $definition->info[$ancestor->name]->child->getAllowedElements($config); + if (isset($elements[$token->name])) { + $autoclose_ok = true; + break; + } + if ($definition->info[$token->name]->wrap) { + $wrapname = $definition->info[$token->name]->wrap; + $wrapdef = $definition->info[$wrapname]; + $wrap_elements = $wrapdef->child->getAllowedElements($config); + if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) { + $autoclose_ok = true; + break; + } + } + } + } + if ($autoclose_ok) { + // errors need to be updated + $new_token = new HTMLPurifier_Token_End($parent->name); + $new_token->start = $parent; + // [TagClosedSuppress] + if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) { + if (!$carryover) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent); + } else { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent); + } + } + if ($carryover) { + $element = clone $parent; + // [TagClosedAuto] + $element->armor['MakeWellFormed_TagClosedError'] = true; + $element->carryover = true; + $token = $this->processToken(array($new_token, $token, $element)); + } else { + $token = $this->insertBefore($new_token); + } + } else { + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + } + $ok = true; + } + + if ($ok) { + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + // See Note [Injector skips] + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleElement($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + if (!$reprocess) { + // ah, nothing interesting happened; do normal processing + if ($token instanceof HTMLPurifier_Token_Start) { + $this->stack[] = $token; + } elseif ($token instanceof HTMLPurifier_Token_End) { + throw new HTMLPurifier_Exception( + 'Improper handling of end tag in start code; possible error in MakeWellFormed' + ); + } + } + continue; + } + + // sanity check: we should be dealing with a closing tag + if (!$token instanceof HTMLPurifier_Token_End) { + throw new HTMLPurifier_Exception('Unaccounted for tag token in input stream, bug in HTML Purifier'); + } + + // make sure that we have something open + if (empty($this->stack)) { + if ($escape_invalid_tags) { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); + } + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + // first, check for the simplest case: everything closes neatly. + // Eventually, everything passes through here; if there are problems + // we modify the input stream accordingly and then punt, so that + // the tokens get processed again. + $current_parent = array_pop($this->stack); + if ($current_parent->name == $token->name) { + $token->start = $current_parent; + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + // See Note [Injector skips] + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleEnd($r); + $token = $this->processToken($r, $i); + $this->stack[] = $current_parent; + $reprocess = true; + break; + } + continue; + } + + // okay, so we're trying to close the wrong tag + + // undo the pop previous pop + $this->stack[] = $current_parent; + + // scroll back the entire nest, trying to find our tag. + // (feature could be to specify how far you'd like to go) + $size = count($this->stack); + // -2 because -1 is the last element, but we already checked that + $skipped_tags = false; + for ($j = $size - 2; $j >= 0; $j--) { + if ($this->stack[$j]->name == $token->name) { + $skipped_tags = array_slice($this->stack, $j); + break; + } + } + + // we didn't find the tag, so remove + if ($skipped_tags === false) { + if ($escape_invalid_tags) { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); + } + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + // do errors, in REVERSE $j order: a,b,c with
- needs a
n"; - //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n
\n"; - - $n = $this->round($n, $sigfigs); - if (strpos($n, '.') !== false) { - $n = rtrim($n, '0'); - } - $n = rtrim($n, '.'); - - return new HTMLPurifier_Length($n, $unit); - } - - /** - * Returns the number of significant figures in a string number. - * @param string $n Decimal number - * @return int number of sigfigs - */ - public function getSigFigs($n) - { - $n = ltrim($n, '0+-'); - $dp = strpos($n, '.'); // decimal position - if ($dp === false) { - $sigfigs = strlen(rtrim($n, '0')); - } else { - $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character - if ($dp !== 0) { - $sigfigs--; - } - } - return $sigfigs; - } - - /** - * Adds two numbers, using arbitrary precision when available. - * @param string $s1 - * @param string $s2 - * @param int $scale - * @return string - */ - private function add($s1, $s2, $scale) - { - if ($this->bcmath) { - return bcadd($s1, $s2, $scale); - } else { - return $this->scale((float)$s1 + (float)$s2, $scale); - } - } - - /** - * Multiples two numbers, using arbitrary precision when available. - * @param string $s1 - * @param string $s2 - * @param int $scale - * @return string - */ - private function mul($s1, $s2, $scale) - { - if ($this->bcmath) { - return bcmul($s1, $s2, $scale); - } else { - return $this->scale((float)$s1 * (float)$s2, $scale); - } - } - - /** - * Divides two numbers, using arbitrary precision when available. - * @param string $s1 - * @param string $s2 - * @param int $scale - * @return string - */ - private function div($s1, $s2, $scale) - { - if ($this->bcmath) { - return bcdiv($s1, $s2, $scale); - } else { - return $this->scale((float)$s1 / (float)$s2, $scale); - } - } - - /** - * Rounds a number according to the number of sigfigs it should have, - * using arbitrary precision when available. - * @param float $n - * @param int $sigfigs - * @return string - */ - private function round($n, $sigfigs) - { - $new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1 - $rp = $sigfigs - $new_log - 1; // Number of decimal places needed - $neg = $n < 0 ? '-' : ''; // Negative sign - if ($this->bcmath) { - if ($rp >= 0) { - $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); - $n = bcdiv($n, '1', $rp); - } else { - // This algorithm partially depends on the standardized - // form of numbers that comes out of bcmath. - $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); - $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); - } - return $n; - } else { - return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); - } - } - - /** - * Scales a float to $scale digits right of decimal point, like BCMath. - * @param float $r - * @param int $scale - * @return string - */ - private function scale($r, $scale) - { - if ($scale < 0) { - // The f sprintf type doesn't support negative numbers, so we - // need to cludge things manually. First get the string. - $r = sprintf('%.0f', (float)$r); - // Due to floating point precision loss, $r will more than likely - // look something like 4652999999999.9234. We grab one more digit - // than we need to precise from $r and then use that to round - // appropriately. - $precise = (string)round(substr($r, 0, strlen($r) + $scale), -1); - // Now we return it, truncating the zero that was rounded off. - return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); - } - return sprintf('%.' . $scale . 'f', (float)$r); - } -} - -// vim: et sw=4 sts=4 + array( + 'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary + 'pt' => 4, + 'pc' => 48, + 'in' => 288, + self::METRIC => array('pt', '0.352777778', 'mm'), + ), + self::METRIC => array( + 'mm' => 1, + 'cm' => 10, + self::ENGLISH => array('mm', '2.83464567', 'pt'), + ), + ); + + /** + * Minimum bcmath precision for output. + * @type int + */ + protected $outputPrecision; + + /** + * Bcmath precision for internal calculations. + * @type int + */ + protected $internalPrecision; + + /** + * Whether or not BCMath is available. + * @type bool + */ + private $bcmath; + + public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) + { + $this->outputPrecision = $output_precision; + $this->internalPrecision = $internal_precision; + $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); + } + + /** + * Converts a length object of one unit into another unit. + * @param HTMLPurifier_Length $length + * Instance of HTMLPurifier_Length to convert. You must validate() + * it before passing it here! + * @param string $to_unit + * Unit to convert to. + * @return HTMLPurifier_Length|bool + * @note + * About precision: This conversion function pays very special + * attention to the incoming precision of values and attempts + * to maintain a number of significant figure. Results are + * fairly accurate up to nine digits. Some caveats: + * - If a number is zero-padded as a result of this significant + * figure tracking, the zeroes will be eliminated. + * - If a number contains less than four sigfigs ($outputPrecision) + * and this causes some decimals to be excluded, those + * decimals will be added on. + */ + public function convert($length, $to_unit) + { + if (!$length->isValid()) { + return false; + } + + $n = $length->getN(); + $unit = $length->getUnit(); + + if ($n === '0' || $unit === false) { + return new HTMLPurifier_Length('0', false); + } + + $state = $dest_state = false; + foreach (self::$units as $k => $x) { + if (isset($x[$unit])) { + $state = $k; + } + if (isset($x[$to_unit])) { + $dest_state = $k; + } + } + if (!$state || !$dest_state) { + return false; + } + + // Some calculations about the initial precision of the number; + // this will be useful when we need to do final rounding. + $sigfigs = $this->getSigFigs($n); + if ($sigfigs < $this->outputPrecision) { + $sigfigs = $this->outputPrecision; + } + + // BCMath's internal precision deals only with decimals. Use + // our default if the initial number has no decimals, or increase + // it by how ever many decimals, thus, the number of guard digits + // will always be greater than or equal to internalPrecision. + $log = (int)floor(log(abs($n), 10)); + $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision + + for ($i = 0; $i < 2; $i++) { + + // Determine what unit IN THIS SYSTEM we need to convert to + if ($dest_state === $state) { + // Simple conversion + $dest_unit = $to_unit; + } else { + // Convert to the smallest unit, pending a system shift + $dest_unit = self::$units[$state][$dest_state][0]; + } + + // Do the conversion if necessary + if ($dest_unit !== $unit) { + $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp); + $n = $this->mul($n, $factor, $cp); + $unit = $dest_unit; + } + + // Output was zero, so bail out early. Shouldn't ever happen. + if ($n === '') { + $n = '0'; + $unit = $to_unit; + break; + } + + // It was a simple conversion, so bail out + if ($dest_state === $state) { + break; + } + + if ($i !== 0) { + // Conversion failed! Apparently, the system we forwarded + // to didn't have this unit. This should never happen! + return false; + } + + // Pre-condition: $i == 0 + + // Perform conversion to next system of units + $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp); + $unit = self::$units[$state][$dest_state][2]; + $state = $dest_state; + + // One more loop around to convert the unit in the new system. + + } + + // Post-condition: $unit == $to_unit + if ($unit !== $to_unit) { + return false; + } + + // Useful for debugging: + //echo "n"; + //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n
\n"; + + $n = $this->round($n, $sigfigs); + if (strpos($n, '.') !== false) { + $n = rtrim($n, '0'); + } + $n = rtrim($n, '.'); + + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Returns the number of significant figures in a string number. + * @param string $n Decimal number + * @return int number of sigfigs + */ + public function getSigFigs($n) + { + $n = ltrim($n, '0+-'); + $dp = strpos($n, '.'); // decimal position + if ($dp === false) { + $sigfigs = strlen(rtrim($n, '0')); + } else { + $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character + if ($dp !== 0) { + $sigfigs--; + } + } + return $sigfigs; + } + + /** + * Adds two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function add($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcadd($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 + (float)$s2, $scale); + } + } + + /** + * Multiples two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function mul($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcmul($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 * (float)$s2, $scale); + } + } + + /** + * Divides two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function div($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcdiv($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 / (float)$s2, $scale); + } + } + + /** + * Rounds a number according to the number of sigfigs it should have, + * using arbitrary precision when available. + * @param float $n + * @param int $sigfigs + * @return string + */ + private function round($n, $sigfigs) + { + $new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1 + $rp = $sigfigs - $new_log - 1; // Number of decimal places needed + $neg = $n < 0 ? '-' : ''; // Negative sign + if ($this->bcmath) { + if ($rp >= 0) { + $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); + $n = bcdiv($n, '1', $rp); + } else { + // This algorithm partially depends on the standardized + // form of numbers that comes out of bcmath. + $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); + $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); + } + return $n; + } else { + return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); + } + } + + /** + * Scales a float to $scale digits right of decimal point, like BCMath. + * @param float $r + * @param int $scale + * @return string + */ + private function scale($r, $scale) + { + if ($scale < 0) { + // The f sprintf type doesn't support negative numbers, so we + // need to cludge things manually. First get the string. + $r = sprintf('%.0f', (float)$r); + // Due to floating point precision loss, $r will more than likely + // look something like 4652999999999.9234. We grab one more digit + // than we need to precise from $r and then use that to round + // appropriately. + $precise = (string)round(substr($r, 0, strlen($r) + $scale), -1); + // Now we return it, truncating the zero that was rounded off. + return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); + } + return sprintf('%.' . $scale . 'f', (float)$r); + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/VarParser.php b/lib/htmlpurifier/HTMLPurifier/VarParser.php index 50cba6910db..4bf7771a1fb 100644 --- a/lib/htmlpurifier/HTMLPurifier/VarParser.php +++ b/lib/htmlpurifier/HTMLPurifier/VarParser.php @@ -1,198 +1,198 @@ - self::STRING, - 'istring' => self::ISTRING, - 'text' => self::TEXT, - 'itext' => self::ITEXT, - 'int' => self::INT, - 'float' => self::FLOAT, - 'bool' => self::BOOL, - 'lookup' => self::LOOKUP, - 'list' => self::ALIST, - 'hash' => self::HASH, - 'mixed' => self::MIXED - ); - - /** - * Lookup table of types that are string, and can have aliases or - * allowed value lists. - */ - public static $stringTypes = array( - self::STRING => true, - self::ISTRING => true, - self::TEXT => true, - self::ITEXT => true, - ); - - /** - * Validate a variable according to type. - * It may return NULL as a valid type if $allow_null is true. - * - * @param mixed $var Variable to validate - * @param int $type Type of variable, see HTMLPurifier_VarParser->types - * @param bool $allow_null Whether or not to permit null as a value - * @return string Validated and type-coerced variable - * @throws HTMLPurifier_VarParserException - */ - final public function parse($var, $type, $allow_null = false) - { - if (is_string($type)) { - if (!isset(HTMLPurifier_VarParser::$types[$type])) { - throw new HTMLPurifier_VarParserException("Invalid type '$type'"); - } else { - $type = HTMLPurifier_VarParser::$types[$type]; - } - } - $var = $this->parseImplementation($var, $type, $allow_null); - if ($allow_null && $var === null) { - return null; - } - // These are basic checks, to make sure nothing horribly wrong - // happened in our implementations. - switch ($type) { - case (self::STRING): - case (self::ISTRING): - case (self::TEXT): - case (self::ITEXT): - if (!is_string($var)) { - break; - } - if ($type == self::ISTRING || $type == self::ITEXT) { - $var = strtolower($var); - } - return $var; - case (self::INT): - if (!is_int($var)) { - break; - } - return $var; - case (self::FLOAT): - if (!is_float($var)) { - break; - } - return $var; - case (self::BOOL): - if (!is_bool($var)) { - break; - } - return $var; - case (self::LOOKUP): - case (self::ALIST): - case (self::HASH): - if (!is_array($var)) { - break; - } - if ($type === self::LOOKUP) { - foreach ($var as $k) { - if ($k !== true) { - $this->error('Lookup table contains value other than true'); - } - } - } elseif ($type === self::ALIST) { - $keys = array_keys($var); - if (array_keys($keys) !== $keys) { - $this->error('Indices for list are not uniform'); - } - } - return $var; - case (self::MIXED): - return $var; - default: - $this->errorInconsistent(get_class($this), $type); - } - $this->errorGeneric($var, $type); - } - - /** - * Actually implements the parsing. Base implementation does not - * do anything to $var. Subclasses should overload this! - * @param mixed $var - * @param int $type - * @param bool $allow_null - * @return string - */ - protected function parseImplementation($var, $type, $allow_null) - { - return $var; - } - - /** - * Throws an exception. - * @throws HTMLPurifier_VarParserException - */ - protected function error($msg) - { - throw new HTMLPurifier_VarParserException($msg); - } - - /** - * Throws an inconsistency exception. - * @note This should not ever be called. It would be called if we - * extend the allowed values of HTMLPurifier_VarParser without - * updating subclasses. - * @param string $class - * @param int $type - * @throws HTMLPurifier_Exception - */ - protected function errorInconsistent($class, $type) - { - throw new HTMLPurifier_Exception( - "Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) . - " not implemented" - ); - } - - /** - * Generic error for if a type didn't work. - * @param mixed $var - * @param int $type - */ - protected function errorGeneric($var, $type) - { - $vtype = gettype($var); - $this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype"); - } - - /** - * @param int $type - * @return string - */ - public static function getTypeName($type) - { - static $lookup; - if (!$lookup) { - // Lazy load the alternative lookup table - $lookup = array_flip(HTMLPurifier_VarParser::$types); - } - if (!isset($lookup[$type])) { - return 'unknown'; - } - return $lookup[$type]; - } -} - -// vim: et sw=4 sts=4 + self::STRING, + 'istring' => self::ISTRING, + 'text' => self::TEXT, + 'itext' => self::ITEXT, + 'int' => self::INT, + 'float' => self::FLOAT, + 'bool' => self::BOOL, + 'lookup' => self::LOOKUP, + 'list' => self::ALIST, + 'hash' => self::HASH, + 'mixed' => self::MIXED + ); + + /** + * Lookup table of types that are string, and can have aliases or + * allowed value lists. + */ + public static $stringTypes = array( + self::STRING => true, + self::ISTRING => true, + self::TEXT => true, + self::ITEXT => true, + ); + + /** + * Validate a variable according to type. + * It may return NULL as a valid type if $allow_null is true. + * + * @param mixed $var Variable to validate + * @param int $type Type of variable, see HTMLPurifier_VarParser->types + * @param bool $allow_null Whether or not to permit null as a value + * @return string Validated and type-coerced variable + * @throws HTMLPurifier_VarParserException + */ + final public function parse($var, $type, $allow_null = false) + { + if (is_string($type)) { + if (!isset(HTMLPurifier_VarParser::$types[$type])) { + throw new HTMLPurifier_VarParserException("Invalid type '$type'"); + } else { + $type = HTMLPurifier_VarParser::$types[$type]; + } + } + $var = $this->parseImplementation($var, $type, $allow_null); + if ($allow_null && $var === null) { + return null; + } + // These are basic checks, to make sure nothing horribly wrong + // happened in our implementations. + switch ($type) { + case (self::STRING): + case (self::ISTRING): + case (self::TEXT): + case (self::ITEXT): + if (!is_string($var)) { + break; + } + if ($type == self::ISTRING || $type == self::ITEXT) { + $var = strtolower($var); + } + return $var; + case (self::INT): + if (!is_int($var)) { + break; + } + return $var; + case (self::FLOAT): + if (!is_float($var)) { + break; + } + return $var; + case (self::BOOL): + if (!is_bool($var)) { + break; + } + return $var; + case (self::LOOKUP): + case (self::ALIST): + case (self::HASH): + if (!is_array($var)) { + break; + } + if ($type === self::LOOKUP) { + foreach ($var as $k) { + if ($k !== true) { + $this->error('Lookup table contains value other than true'); + } + } + } elseif ($type === self::ALIST) { + $keys = array_keys($var); + if (array_keys($keys) !== $keys) { + $this->error('Indices for list are not uniform'); + } + } + return $var; + case (self::MIXED): + return $var; + default: + $this->errorInconsistent(get_class($this), $type); + } + $this->errorGeneric($var, $type); + } + + /** + * Actually implements the parsing. Base implementation does not + * do anything to $var. Subclasses should overload this! + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return string + */ + protected function parseImplementation($var, $type, $allow_null) + { + return $var; + } + + /** + * Throws an exception. + * @throws HTMLPurifier_VarParserException + */ + protected function error($msg) + { + throw new HTMLPurifier_VarParserException($msg); + } + + /** + * Throws an inconsistency exception. + * @note This should not ever be called. It would be called if we + * extend the allowed values of HTMLPurifier_VarParser without + * updating subclasses. + * @param string $class + * @param int $type + * @throws HTMLPurifier_Exception + */ + protected function errorInconsistent($class, $type) + { + throw new HTMLPurifier_Exception( + "Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) . + " not implemented" + ); + } + + /** + * Generic error for if a type didn't work. + * @param mixed $var + * @param int $type + */ + protected function errorGeneric($var, $type) + { + $vtype = gettype($var); + $this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype"); + } + + /** + * @param int $type + * @return string + */ + public static function getTypeName($type) + { + static $lookup; + if (!$lookup) { + // Lazy load the alternative lookup table + $lookup = array_flip(HTMLPurifier_VarParser::$types); + } + if (!isset($lookup[$type])) { + return 'unknown'; + } + return $lookup[$type]; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/VarParser/Flexible.php b/lib/htmlpurifier/HTMLPurifier/VarParser/Flexible.php index b15016c5b24..b2ed860ac07 100644 --- a/lib/htmlpurifier/HTMLPurifier/VarParser/Flexible.php +++ b/lib/htmlpurifier/HTMLPurifier/VarParser/Flexible.php @@ -1,130 +1,130 @@ - $j) { - $var[$i] = trim($j); - } - if ($type === self::HASH) { - // key:value,key2:value2 - $nvar = array(); - foreach ($var as $keypair) { - $c = explode(':', $keypair, 2); - if (!isset($c[1])) { - continue; - } - $nvar[trim($c[0])] = trim($c[1]); - } - $var = $nvar; - } - } - if (!is_array($var)) { - break; - } - $keys = array_keys($var); - if ($keys === array_keys($keys)) { - if ($type == self::ALIST) { - return $var; - } elseif ($type == self::LOOKUP) { - $new = array(); - foreach ($var as $key) { - $new[$key] = true; - } - 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; - } - } - return $var; - default: - $this->errorInconsistent(__CLASS__, $type); - } - $this->errorGeneric($var, $type); - } -} - -// vim: et sw=4 sts=4 + $j) { + $var[$i] = trim($j); + } + if ($type === self::HASH) { + // key:value,key2:value2 + $nvar = array(); + foreach ($var as $keypair) { + $c = explode(':', $keypair, 2); + if (!isset($c[1])) { + continue; + } + $nvar[trim($c[0])] = trim($c[1]); + } + $var = $nvar; + } + } + if (!is_array($var)) { + break; + } + $keys = array_keys($var); + if ($keys === array_keys($keys)) { + if ($type == self::ALIST) { + return $var; + } elseif ($type == self::LOOKUP) { + $new = array(); + foreach ($var as $key) { + $new[$key] = true; + } + 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; + } + } + return $var; + default: + $this->errorInconsistent(__CLASS__, $type); + } + $this->errorGeneric($var, $type); + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/VarParser/Native.php b/lib/htmlpurifier/HTMLPurifier/VarParser/Native.php index f11c318efb6..c28055b5ed1 100644 --- a/lib/htmlpurifier/HTMLPurifier/VarParser/Native.php +++ b/lib/htmlpurifier/HTMLPurifier/VarParser/Native.php @@ -1,38 +1,38 @@ -evalExpression($var); - } - - /** - * @param string $expr - * @return mixed - * @throws HTMLPurifier_VarParserException - */ - protected function evalExpression($expr) - { - $var = null; - $result = eval("\$var = $expr;"); - if ($result === false) { - throw new HTMLPurifier_VarParserException("Fatal error in evaluated code"); - } - return $var; - } -} - -// vim: et sw=4 sts=4 +evalExpression($var); + } + + /** + * @param string $expr + * @return mixed + * @throws HTMLPurifier_VarParserException + */ + protected function evalExpression($expr) + { + $var = null; + $result = eval("\$var = $expr;"); + if ($result === false) { + throw new HTMLPurifier_VarParserException("Fatal error in evaluated code"); + } + return $var; + } +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/HTMLPurifier/VarParserException.php b/lib/htmlpurifier/HTMLPurifier/VarParserException.php index 5df3414959b..82e465d6a9c 100644 --- a/lib/htmlpurifier/HTMLPurifier/VarParserException.php +++ b/lib/htmlpurifier/HTMLPurifier/VarParserException.php @@ -1,11 +1,11 @@ -front = $front; - $this->back = $back; - } - - /** - * Creates a zipper from an array, with a hole in the - * 0-index position. - * @param Array to zipper-ify. - * @return Tuple of zipper and element of first position. - */ - static public function fromArray($array) { - $z = new self(array(), array_reverse($array)); - $t = $z->delete(); // delete the "dummy hole" - return array($z, $t); - } - - /** - * Convert zipper back into a normal array, optionally filling in - * the hole with a value. (Usually you should supply a $t, unless you - * are at the end of the array.) - */ - public function toArray($t = NULL) { - $a = $this->front; - if ($t !== NULL) $a[] = $t; - for ($i = count($this->back)-1; $i >= 0; $i--) { - $a[] = $this->back[$i]; - } - return $a; - } - - /** - * Move hole to the next element. - * @param $t Element to fill hole with - * @return Original contents of new hole. - */ - public function next($t) { - if ($t !== NULL) array_push($this->front, $t); - return empty($this->back) ? NULL : array_pop($this->back); - } - - /** - * Iterated hole advancement. - * @param $t Element to fill hole with - * @param $i How many forward to advance hole - * @return Original contents of new hole, i away - */ - public function advance($t, $n) { - for ($i = 0; $i < $n; $i++) { - $t = $this->next($t); - } - return $t; - } - - /** - * Move hole to the previous element - * @param $t Element to fill hole with - * @return Original contents of new hole. - */ - public function prev($t) { - if ($t !== NULL) array_push($this->back, $t); - return empty($this->front) ? NULL : array_pop($this->front); - } - - /** - * Delete contents of current hole, shifting hole to - * next element. - * @return Original contents of new hole. - */ - public function delete() { - return empty($this->back) ? NULL : array_pop($this->back); - } - - /** - * Returns true if we are at the end of the list. - * @return bool - */ - public function done() { - return empty($this->back); - } - - /** - * Insert element before hole. - * @param Element to insert - */ - public function insertBefore($t) { - if ($t !== NULL) array_push($this->front, $t); - } - - /** - * Insert element after hole. - * @param Element to insert - */ - public function insertAfter($t) { - if ($t !== NULL) array_push($this->back, $t); - } - - /** - * Splice in multiple elements at hole. Functional specification - * in terms of array_splice: - * - * $arr1 = $arr; - * $old1 = array_splice($arr1, $i, $delete, $replacement); - * - * list($z, $t) = HTMLPurifier_Zipper::fromArray($arr); - * $t = $z->advance($t, $i); - * list($old2, $t) = $z->splice($t, $delete, $replacement); - * $arr2 = $z->toArray($t); - * - * assert($old1 === $old2); - * assert($arr1 === $arr2); - * - * NB: the absolute index location after this operation is - * *unchanged!* - * - * @param Current contents of hole. - */ - public function splice($t, $delete, $replacement) { - // delete - $old = array(); - $r = $t; - for ($i = $delete; $i > 0; $i--) { - $old[] = $r; - $r = $this->delete(); - } - // insert - for ($i = count($replacement)-1; $i >= 0; $i--) { - $this->insertAfter($r); - $r = $replacement[$i]; - } - return array($old, $r); - } -} +front = $front; + $this->back = $back; + } + + /** + * Creates a zipper from an array, with a hole in the + * 0-index position. + * @param Array to zipper-ify. + * @return Tuple of zipper and element of first position. + */ + static public function fromArray($array) { + $z = new self(array(), array_reverse($array)); + $t = $z->delete(); // delete the "dummy hole" + return array($z, $t); + } + + /** + * Convert zipper back into a normal array, optionally filling in + * the hole with a value. (Usually you should supply a $t, unless you + * are at the end of the array.) + */ + public function toArray($t = NULL) { + $a = $this->front; + if ($t !== NULL) $a[] = $t; + for ($i = count($this->back)-1; $i >= 0; $i--) { + $a[] = $this->back[$i]; + } + return $a; + } + + /** + * Move hole to the next element. + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function next($t) { + if ($t !== NULL) array_push($this->front, $t); + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Iterated hole advancement. + * @param $t Element to fill hole with + * @param $i How many forward to advance hole + * @return Original contents of new hole, i away + */ + public function advance($t, $n) { + for ($i = 0; $i < $n; $i++) { + $t = $this->next($t); + } + return $t; + } + + /** + * Move hole to the previous element + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function prev($t) { + if ($t !== NULL) array_push($this->back, $t); + return empty($this->front) ? NULL : array_pop($this->front); + } + + /** + * Delete contents of current hole, shifting hole to + * next element. + * @return Original contents of new hole. + */ + public function delete() { + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Returns true if we are at the end of the list. + * @return bool + */ + public function done() { + return empty($this->back); + } + + /** + * Insert element before hole. + * @param Element to insert + */ + public function insertBefore($t) { + if ($t !== NULL) array_push($this->front, $t); + } + + /** + * Insert element after hole. + * @param Element to insert + */ + public function insertAfter($t) { + if ($t !== NULL) array_push($this->back, $t); + } + + /** + * Splice in multiple elements at hole. Functional specification + * in terms of array_splice: + * + * $arr1 = $arr; + * $old1 = array_splice($arr1, $i, $delete, $replacement); + * + * list($z, $t) = HTMLPurifier_Zipper::fromArray($arr); + * $t = $z->advance($t, $i); + * list($old2, $t) = $z->splice($t, $delete, $replacement); + * $arr2 = $z->toArray($t); + * + * assert($old1 === $old2); + * assert($arr1 === $arr2); + * + * NB: the absolute index location after this operation is + * *unchanged!* + * + * @param Current contents of hole. + */ + public function splice($t, $delete, $replacement) { + // delete + $old = array(); + $r = $t; + for ($i = $delete; $i > 0; $i--) { + $old[] = $r; + $r = $this->delete(); + } + // insert + for ($i = count($replacement)-1; $i >= 0; $i--) { + $this->insertAfter($r); + $r = $replacement[$i]; + } + return array($old, $r); + } +} diff --git a/lib/htmlpurifier/LICENSE b/lib/htmlpurifier/LICENSE index 8c88a20d455..21ee8faa5a8 100644 --- a/lib/htmlpurifier/LICENSE +++ b/lib/htmlpurifier/LICENSE @@ -1,504 +1,504 @@ - GNU LESSER GENERAL PUBLIC LICENSE - Version 2.1, February 1999 - - Copyright (C) 1991, 1999 Free Software Foundation, Inc. - 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - -[This is the first released version of the Lesser GPL. It also counts - as the successor of the GNU Library Public License, version 2, hence - the version number 2.1.] - - Preamble - - The licenses for most software are designed to take away your -freedom to share and change it. By contrast, the GNU General Public -Licenses are intended to guarantee your freedom to share and change -free software--to make sure the software is free for all its users. - - This license, the Lesser General Public License, applies to some -specially designated software packages--typically libraries--of the -Free Software Foundation and other authors who decide to use it. You -can use it too, but we suggest you first think carefully about whether -this license or the ordinary General Public License is the better -strategy to use in any particular case, based on the explanations below. - - When we speak of free software, we are referring to freedom of use, -not price. Our General Public Licenses are designed to make sure that -you have the freedom to distribute copies of free software (and charge -for this service if you wish); that you receive source code or can get -it if you want it; that you can change the software and use pieces of -it in new free programs; and that you are informed that you can do -these things. - - To protect your rights, we need to make restrictions that forbid -distributors to deny you these rights or to ask you to surrender these -rights. These restrictions translate to certain responsibilities for -you if you distribute copies of the library or if you modify it. - - For example, if you distribute copies of the library, whether gratis -or for a fee, you must give the recipients all the rights that we gave -you. You must make sure that they, too, receive or can get the source -code. If you link other code with the library, you must provide -complete object files to the recipients, so that they can relink them -with the library after making changes to the library and recompiling -it. And you must show them these terms so they know their rights. - - We protect your rights with a two-step method: (1) we copyright the -library, and (2) we offer you this license, which gives you legal -permission to copy, distribute and/or modify the library. - - To protect each distributor, we want to make it very clear that -there is no warranty for the free library. Also, if the library is -modified by someone else and passed on, the recipients should know -that what they have is not the original version, so that the original -author's reputation will not be affected by problems that might be -introduced by others. - - Finally, software patents pose a constant threat to the existence of -any free program. We wish to make sure that a company cannot -effectively restrict the users of a free program by obtaining a -restrictive license from a patent holder. Therefore, we insist that -any patent license obtained for a version of the library must be -consistent with the full freedom of use specified in this license. - - Most GNU software, including some libraries, is covered by the -ordinary GNU General Public License. This license, the GNU Lesser -General Public License, applies to certain designated libraries, and -is quite different from the ordinary General Public License. We use -this license for certain libraries in order to permit linking those -libraries into non-free programs. - - When a program is linked with a library, whether statically or using -a shared library, the combination of the two is legally speaking a -combined work, a derivative of the original library. The ordinary -General Public License therefore permits such linking only if the -entire combination fits its criteria of freedom. The Lesser General -Public License permits more lax criteria for linking other code with -the library. - - We call this license the "Lesser" General Public License because it -does Less to protect the user's freedom than the ordinary General -Public License. It also provides other free software developers Less -of an advantage over competing non-free programs. These disadvantages -are the reason we use the ordinary General Public License for many -libraries. However, the Lesser license provides advantages in certain -special circumstances. - - For example, on rare occasions, there may be a special need to -encourage the widest possible use of a certain library, so that it becomes -a de-facto standard. To achieve this, non-free programs must be -allowed to use the library. A more frequent case is that a free -library does the same job as widely used non-free libraries. In this -case, there is little to gain by limiting the free library to free -software only, so we use the Lesser General Public License. - - In other cases, permission to use a particular library in non-free -programs enables a greater number of people to use a large body of -free software. For example, permission to use the GNU C Library in -non-free programs enables many more people to use the whole GNU -operating system, as well as its variant, the GNU/Linux operating -system. - - Although the Lesser General Public License is Less protective of the -users' freedom, it does ensure that the user of a program that is -linked with the Library has the freedom and the wherewithal to run -that program using a modified version of the Library. - - The precise terms and conditions for copying, distribution and -modification follow. Pay close attention to the difference between a -"work based on the library" and a "work that uses the library". The -former contains code derived from the library, whereas the latter must -be combined with the library in order to run. - - GNU LESSER GENERAL PUBLIC LICENSE - TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION - - 0. This License Agreement applies to any software library or other -program which contains a notice placed by the copyright holder or -other authorized party saying it may be distributed under the terms of -this Lesser General Public License (also called "this License"). -Each licensee is addressed as "you". - - A "library" means a collection of software functions and/or data -prepared so as to be conveniently linked with application programs -(which use some of those functions and data) to form executables. - - The "Library", below, refers to any such software library or work -which has been distributed under these terms. A "work based on the -Library" means either the Library or any derivative work under -copyright law: that is to say, a work containing the Library or a -portion of it, either verbatim or with modifications and/or translated -straightforwardly into another language. (Hereinafter, translation is -included without limitation in the term "modification".) - - "Source code" for a work means the preferred form of the work for -making modifications to it. For a library, complete source code means -all the source code for all modules it contains, plus any associated -interface definition files, plus the scripts used to control compilation -and installation of the library. - - Activities other than copying, distribution and modification are not -covered by this License; they are outside its scope. The act of -running a program using the Library is not restricted, and output from -such a program is covered only if its contents constitute a work based -on the Library (independent of the use of the Library in a tool for -writing it). Whether that is true depends on what the Library does -and what the program that uses the Library does. - - 1. You may copy and distribute verbatim copies of the Library's -complete source code as you receive it, in any medium, provided that -you conspicuously and appropriately publish on each copy an -appropriate copyright notice and disclaimer of warranty; keep intact -all the notices that refer to this License and to the absence of any -warranty; and distribute a copy of this License along with the -Library. - - You may charge a fee for the physical act of transferring a copy, -and you may at your option offer warranty protection in exchange for a -fee. - - 2. You may modify your copy or copies of the Library or any portion -of it, thus forming a work based on the Library, and copy and -distribute such modifications or work under the terms of Section 1 -above, provided that you also meet all of these conditions: - - a) The modified work must itself be a software library. - - b) You must cause the files modified to carry prominent notices - stating that you changed the files and the date of any change. - - c) You must cause the whole of the work to be licensed at no - charge to all third parties under the terms of this License. - - d) If a facility in the modified Library refers to a function or a - table of data to be supplied by an application program that uses - the facility, other than as an argument passed when the facility - is invoked, then you must make a good faith effort to ensure that, - in the event an application does not supply such function or - table, the facility still operates, and performs whatever part of - its purpose remains meaningful. - - (For example, a function in a library to compute square roots has - a purpose that is entirely well-defined independent of the - application. Therefore, Subsection 2d requires that any - application-supplied function or table used by this function must - be optional: if the application does not supply it, the square - root function must still compute square roots.) - -These requirements apply to the modified work as a whole. If -identifiable sections of that work are not derived from the Library, -and can be reasonably considered independent and separate works in -themselves, then this License, and its terms, do not apply to those -sections when you distribute them as separate works. But when you -distribute the same sections as part of a whole which is a work based -on the Library, the distribution of the whole must be on the terms of -this License, whose permissions for other licensees extend to the -entire whole, and thus to each and every part regardless of who wrote -it. - -Thus, it is not the intent of this section to claim rights or contest -your rights to work written entirely by you; rather, the intent is to -exercise the right to control the distribution of derivative or -collective works based on the Library. - -In addition, mere aggregation of another work not based on the Library -with the Library (or with a work based on the Library) on a volume of -a storage or distribution medium does not bring the other work under -the scope of this License. - - 3. You may opt to apply the terms of the ordinary GNU General Public -License instead of this License to a given copy of the Library. To do -this, you must alter all the notices that refer to this License, so -that they refer to the ordinary GNU General Public License, version 2, -instead of to this License. (If a newer version than version 2 of the -ordinary GNU General Public License has appeared, then you can specify -that version instead if you wish.) Do not make any other change in -these notices. - - Once this change is made in a given copy, it is irreversible for -that copy, so the ordinary GNU General Public License applies to all -subsequent copies and derivative works made from that copy. - - This option is useful when you wish to copy part of the code of -the Library into a program that is not a library. - - 4. You may copy and distribute the Library (or a portion or -derivative of it, under Section 2) in object code or executable form -under the terms of Sections 1 and 2 above provided that you accompany -it with the complete corresponding machine-readable source code, which -must be distributed under the terms of Sections 1 and 2 above on a -medium customarily used for software interchange. - - If distribution of object code is made by offering access to copy -from a designated place, then offering equivalent access to copy the -source code from the same place satisfies the requirement to -distribute the source code, even though third parties are not -compelled to copy the source along with the object code. - - 5. A program that contains no derivative of any portion of the -Library, but is designed to work with the Library by being compiled or -linked with it, is called a "work that uses the Library". Such a -work, in isolation, is not a derivative work of the Library, and -therefore falls outside the scope of this License. - - However, linking a "work that uses the Library" with the Library -creates an executable that is a derivative of the Library (because it -contains portions of the Library), rather than a "work that uses the -library". The executable is therefore covered by this License. -Section 6 states terms for distribution of such executables. - - When a "work that uses the Library" uses material from a header file -that is part of the Library, the object code for the work may be a -derivative work of the Library even though the source code is not. -Whether this is true is especially significant if the work can be -linked without the Library, or if the work is itself a library. The -threshold for this to be true is not precisely defined by law. - - If such an object file uses only numerical parameters, data -structure layouts and accessors, and small macros and small inline -functions (ten lines or less in length), then the use of the object -file is unrestricted, regardless of whether it is legally a derivative -work. (Executables containing this object code plus portions of the -Library will still fall under Section 6.) - - Otherwise, if the work is a derivative of the Library, you may -distribute the object code for the work under the terms of Section 6. -Any executables containing that work also fall under Section 6, -whether or not they are linked directly with the Library itself. - - 6. As an exception to the Sections above, you may also combine or -link a "work that uses the Library" with the Library to produce a -work containing portions of the Library, and distribute that work -under terms of your choice, provided that the terms permit -modification of the work for the customer's own use and reverse -engineering for debugging such modifications. - - You must give prominent notice with each copy of the work that the -Library is used in it and that the Library and its use are covered by -this License. You must supply a copy of this License. If the work -during execution displays copyright notices, you must include the -copyright notice for the Library among them, as well as a reference -directing the user to the copy of this License. Also, you must do one -of these things: - - a) Accompany the work with the complete corresponding - machine-readable source code for the Library including whatever - changes were used in the work (which must be distributed under - Sections 1 and 2 above); and, if the work is an executable linked - with the Library, with the complete machine-readable "work that - uses the Library", as object code and/or source code, so that the - user can modify the Library and then relink to produce a modified - executable containing the modified Library. (It is understood - that the user who changes the contents of definitions files in the - Library will not necessarily be able to recompile the application - to use the modified definitions.) - - b) Use a suitable shared library mechanism for linking with the - Library. A suitable mechanism is one that (1) uses at run time a - copy of the library already present on the user's computer system, - rather than copying library functions into the executable, and (2) - will operate properly with a modified version of the library, if - the user installs one, as long as the modified version is - interface-compatible with the version that the work was made with. - - c) Accompany the work with a written offer, valid for at - least three years, to give the same user the materials - specified in Subsection 6a, above, for a charge no more - than the cost of performing this distribution. - - d) If distribution of the work is made by offering access to copy - from a designated place, offer equivalent access to copy the above - specified materials from the same place. - - e) Verify that the user has already received a copy of these - materials or that you have already sent this user a copy. - - For an executable, the required form of the "work that uses the -Library" must include any data and utility programs needed for -reproducing the executable from it. However, as a special exception, -the materials to be distributed need not include anything that is -normally distributed (in either source or binary form) with the major -components (compiler, kernel, and so on) of the operating system on -which the executable runs, unless that component itself accompanies -the executable. - - It may happen that this requirement contradicts the license -restrictions of other proprietary libraries that do not normally -accompany the operating system. Such a contradiction means you cannot -use both them and the Library together in an executable that you -distribute. - - 7. You may place library facilities that are a work based on the -Library side-by-side in a single library together with other library -facilities not covered by this License, and distribute such a combined -library, provided that the separate distribution of the work based on -the Library and of the other library facilities is otherwise -permitted, and provided that you do these two things: - - a) Accompany the combined library with a copy of the same work - based on the Library, uncombined with any other library - facilities. This must be distributed under the terms of the - Sections above. - - b) Give prominent notice with the combined library of the fact - that part of it is a work based on the Library, and explaining - where to find the accompanying uncombined form of the same work. - - 8. You may not copy, modify, sublicense, link with, or distribute -the Library except as expressly provided under this License. Any -attempt otherwise to copy, modify, sublicense, link with, or -distribute the Library is void, and will automatically terminate your -rights under this License. However, parties who have received copies, -or rights, from you under this License will not have their licenses -terminated so long as such parties remain in full compliance. - - 9. You are not required to accept this License, since you have not -signed it. However, nothing else grants you permission to modify or -distribute the Library or its derivative works. These actions are -prohibited by law if you do not accept this License. Therefore, by -modifying or distributing the Library (or any work based on the -Library), you indicate your acceptance of this License to do so, and -all its terms and conditions for copying, distributing or modifying -the Library or works based on it. - - 10. Each time you redistribute the Library (or any work based on the -Library), the recipient automatically receives a license from the -original licensor to copy, distribute, link with or modify the Library -subject to these terms and conditions. You may not impose any further -restrictions on the recipients' exercise of the rights granted herein. -You are not responsible for enforcing compliance by third parties with -this License. - - 11. If, as a consequence of a court judgment or allegation of patent -infringement or for any other reason (not limited to patent issues), -conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot -distribute so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you -may not distribute the Library at all. For example, if a patent -license would not permit royalty-free redistribution of the Library by -all those who receive copies directly or indirectly through you, then -the only way you could satisfy both it and this License would be to -refrain entirely from distribution of the Library. - -If any portion of this section is held invalid or unenforceable under any -particular circumstance, the balance of the section is intended to apply, -and the section as a whole is intended to apply in other circumstances. - -It is not the purpose of this section to induce you to infringe any -patents or other property right claims or to contest validity of any -such claims; this section has the sole purpose of protecting the -integrity of the free software distribution system which is -implemented by public license practices. Many people have made -generous contributions to the wide range of software distributed -through that system in reliance on consistent application of that -system; it is up to the author/donor to decide if he or she is willing -to distribute software through any other system and a licensee cannot -impose that choice. - -This section is intended to make thoroughly clear what is believed to -be a consequence of the rest of this License. - - 12. If the distribution and/or use of the Library is restricted in -certain countries either by patents or by copyrighted interfaces, the -original copyright holder who places the Library under this License may add -an explicit geographical distribution limitation excluding those countries, -so that distribution is permitted only in or among countries not thus -excluded. In such case, this License incorporates the limitation as if -written in the body of this License. - - 13. The Free Software Foundation may publish revised and/or new -versions of the Lesser General Public License from time to time. -Such new versions will be similar in spirit to the present version, -but may differ in detail to address new problems or concerns. - -Each version is given a distinguishing version number. If the Library -specifies a version number of this License which applies to it and -"any later version", you have the option of following the terms and -conditions either of that version or of any later version published by -the Free Software Foundation. If the Library does not specify a -license version number, you may choose any version ever published by -the Free Software Foundation. - - 14. If you wish to incorporate parts of the Library into other free -programs whose distribution conditions are incompatible with these, -write to the author to ask for permission. For software which is -copyrighted by the Free Software Foundation, write to the Free -Software Foundation; we sometimes make exceptions for this. Our -decision will be guided by the two goals of preserving the free status -of all derivatives of our free software and of promoting the sharing -and reuse of software generally. - - NO WARRANTY - - 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO -WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. -EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR -OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY -KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR -PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE -LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME -THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. - - 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN -WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY -AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU -FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR -CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE -LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING -RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A -FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF -SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH -DAMAGES. - - END OF TERMS AND CONDITIONS - - How to Apply These Terms to Your New Libraries - - If you develop a new library, and you want it to be of the greatest -possible use to the public, we recommend making it free software that -everyone can redistribute and change. You can do so by permitting -redistribution under these terms (or, alternatively, under the terms of the -ordinary General Public License). - - To apply these terms, attach the following notices to the library. It is -safest to attach them to the start of each source file to most effectively -convey the exclusion of warranty; and each file should have at least the -"copyright" line and a pointer to where the full notice is found. - -- Copyright (C) - - This library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - This library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with this library; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA - -Also add information on how to contact you by electronic and paper mail. - -You should also get your employer (if you work as a programmer) or your -school, if any, to sign a "copyright disclaimer" for the library, if -necessary. Here is a sample; alter the names: - - Yoyodyne, Inc., hereby disclaims all copyright interest in the - library `Frob' (a library for tweaking knobs) written by James Random Hacker. - - , 1 April 1990 - Ty Coon, President of Vice - -That's all there is to it! - - vim: et sw=4 sts=4 + GNU LESSER GENERAL PUBLIC LICENSE + Version 2.1, February 1999 + + Copyright (C) 1991, 1999 Free Software Foundation, Inc. + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + +[This is the first released version of the Lesser GPL. It also counts + as the successor of the GNU Library Public License, version 2, hence + the version number 2.1.] + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +Licenses are intended to guarantee your freedom to share and change +free software--to make sure the software is free for all its users. + + This license, the Lesser General Public License, applies to some +specially designated software packages--typically libraries--of the +Free Software Foundation and other authors who decide to use it. You +can use it too, but we suggest you first think carefully about whether +this license or the ordinary General Public License is the better +strategy to use in any particular case, based on the explanations below. + + When we speak of free software, we are referring to freedom of use, +not price. Our General Public Licenses are designed to make sure that +you have the freedom to distribute copies of free software (and charge +for this service if you wish); that you receive source code or can get +it if you want it; that you can change the software and use pieces of +it in new free programs; and that you are informed that you can do +these things. + + To protect your rights, we need to make restrictions that forbid +distributors to deny you these rights or to ask you to surrender these +rights. These restrictions translate to certain responsibilities for +you if you distribute copies of the library or if you modify it. + + For example, if you distribute copies of the library, whether gratis +or for a fee, you must give the recipients all the rights that we gave +you. You must make sure that they, too, receive or can get the source +code. If you link other code with the library, you must provide +complete object files to the recipients, so that they can relink them +with the library after making changes to the library and recompiling +it. And you must show them these terms so they know their rights. + + We protect your rights with a two-step method: (1) we copyright the +library, and (2) we offer you this license, which gives you legal +permission to copy, distribute and/or modify the library. + + To protect each distributor, we want to make it very clear that +there is no warranty for the free library. Also, if the library is +modified by someone else and passed on, the recipients should know +that what they have is not the original version, so that the original +author's reputation will not be affected by problems that might be +introduced by others. + + Finally, software patents pose a constant threat to the existence of +any free program. We wish to make sure that a company cannot +effectively restrict the users of a free program by obtaining a +restrictive license from a patent holder. Therefore, we insist that +any patent license obtained for a version of the library must be +consistent with the full freedom of use specified in this license. + + Most GNU software, including some libraries, is covered by the +ordinary GNU General Public License. This license, the GNU Lesser +General Public License, applies to certain designated libraries, and +is quite different from the ordinary General Public License. We use +this license for certain libraries in order to permit linking those +libraries into non-free programs. + + When a program is linked with a library, whether statically or using +a shared library, the combination of the two is legally speaking a +combined work, a derivative of the original library. The ordinary +General Public License therefore permits such linking only if the +entire combination fits its criteria of freedom. The Lesser General +Public License permits more lax criteria for linking other code with +the library. + + We call this license the "Lesser" General Public License because it +does Less to protect the user's freedom than the ordinary General +Public License. It also provides other free software developers Less +of an advantage over competing non-free programs. These disadvantages +are the reason we use the ordinary General Public License for many +libraries. However, the Lesser license provides advantages in certain +special circumstances. + + For example, on rare occasions, there may be a special need to +encourage the widest possible use of a certain library, so that it becomes +a de-facto standard. To achieve this, non-free programs must be +allowed to use the library. A more frequent case is that a free +library does the same job as widely used non-free libraries. In this +case, there is little to gain by limiting the free library to free +software only, so we use the Lesser General Public License. + + In other cases, permission to use a particular library in non-free +programs enables a greater number of people to use a large body of +free software. For example, permission to use the GNU C Library in +non-free programs enables many more people to use the whole GNU +operating system, as well as its variant, the GNU/Linux operating +system. + + Although the Lesser General Public License is Less protective of the +users' freedom, it does ensure that the user of a program that is +linked with the Library has the freedom and the wherewithal to run +that program using a modified version of the Library. + + The precise terms and conditions for copying, distribution and +modification follow. Pay close attention to the difference between a +"work based on the library" and a "work that uses the library". The +former contains code derived from the library, whereas the latter must +be combined with the library in order to run. + + GNU LESSER GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License Agreement applies to any software library or other +program which contains a notice placed by the copyright holder or +other authorized party saying it may be distributed under the terms of +this Lesser General Public License (also called "this License"). +Each licensee is addressed as "you". + + A "library" means a collection of software functions and/or data +prepared so as to be conveniently linked with application programs +(which use some of those functions and data) to form executables. + + The "Library", below, refers to any such software library or work +which has been distributed under these terms. A "work based on the +Library" means either the Library or any derivative work under +copyright law: that is to say, a work containing the Library or a +portion of it, either verbatim or with modifications and/or translated +straightforwardly into another language. (Hereinafter, translation is +included without limitation in the term "modification".) + + "Source code" for a work means the preferred form of the work for +making modifications to it. For a library, complete source code means +all the source code for all modules it contains, plus any associated +interface definition files, plus the scripts used to control compilation +and installation of the library. + + Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running a program using the Library is not restricted, and output from +such a program is covered only if its contents constitute a work based +on the Library (independent of the use of the Library in a tool for +writing it). Whether that is true depends on what the Library does +and what the program that uses the Library does. + + 1. You may copy and distribute verbatim copies of the Library's +complete source code as you receive it, in any medium, provided that +you conspicuously and appropriately publish on each copy an +appropriate copyright notice and disclaimer of warranty; keep intact +all the notices that refer to this License and to the absence of any +warranty; and distribute a copy of this License along with the +Library. + + You may charge a fee for the physical act of transferring a copy, +and you may at your option offer warranty protection in exchange for a +fee. + + 2. You may modify your copy or copies of the Library or any portion +of it, thus forming a work based on the Library, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) The modified work must itself be a software library. + + b) You must cause the files modified to carry prominent notices + stating that you changed the files and the date of any change. + + c) You must cause the whole of the work to be licensed at no + charge to all third parties under the terms of this License. + + d) If a facility in the modified Library refers to a function or a + table of data to be supplied by an application program that uses + the facility, other than as an argument passed when the facility + is invoked, then you must make a good faith effort to ensure that, + in the event an application does not supply such function or + table, the facility still operates, and performs whatever part of + its purpose remains meaningful. + + (For example, a function in a library to compute square roots has + a purpose that is entirely well-defined independent of the + application. Therefore, Subsection 2d requires that any + application-supplied function or table used by this function must + be optional: if the application does not supply it, the square + root function must still compute square roots.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Library, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Library, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote +it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Library. + +In addition, mere aggregation of another work not based on the Library +with the Library (or with a work based on the Library) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may opt to apply the terms of the ordinary GNU General Public +License instead of this License to a given copy of the Library. To do +this, you must alter all the notices that refer to this License, so +that they refer to the ordinary GNU General Public License, version 2, +instead of to this License. (If a newer version than version 2 of the +ordinary GNU General Public License has appeared, then you can specify +that version instead if you wish.) Do not make any other change in +these notices. + + Once this change is made in a given copy, it is irreversible for +that copy, so the ordinary GNU General Public License applies to all +subsequent copies and derivative works made from that copy. + + This option is useful when you wish to copy part of the code of +the Library into a program that is not a library. + + 4. You may copy and distribute the Library (or a portion or +derivative of it, under Section 2) in object code or executable form +under the terms of Sections 1 and 2 above provided that you accompany +it with the complete corresponding machine-readable source code, which +must be distributed under the terms of Sections 1 and 2 above on a +medium customarily used for software interchange. + + If distribution of object code is made by offering access to copy +from a designated place, then offering equivalent access to copy the +source code from the same place satisfies the requirement to +distribute the source code, even though third parties are not +compelled to copy the source along with the object code. + + 5. A program that contains no derivative of any portion of the +Library, but is designed to work with the Library by being compiled or +linked with it, is called a "work that uses the Library". Such a +work, in isolation, is not a derivative work of the Library, and +therefore falls outside the scope of this License. + + However, linking a "work that uses the Library" with the Library +creates an executable that is a derivative of the Library (because it +contains portions of the Library), rather than a "work that uses the +library". The executable is therefore covered by this License. +Section 6 states terms for distribution of such executables. + + When a "work that uses the Library" uses material from a header file +that is part of the Library, the object code for the work may be a +derivative work of the Library even though the source code is not. +Whether this is true is especially significant if the work can be +linked without the Library, or if the work is itself a library. The +threshold for this to be true is not precisely defined by law. + + If such an object file uses only numerical parameters, data +structure layouts and accessors, and small macros and small inline +functions (ten lines or less in length), then the use of the object +file is unrestricted, regardless of whether it is legally a derivative +work. (Executables containing this object code plus portions of the +Library will still fall under Section 6.) + + Otherwise, if the work is a derivative of the Library, you may +distribute the object code for the work under the terms of Section 6. +Any executables containing that work also fall under Section 6, +whether or not they are linked directly with the Library itself. + + 6. As an exception to the Sections above, you may also combine or +link a "work that uses the Library" with the Library to produce a +work containing portions of the Library, and distribute that work +under terms of your choice, provided that the terms permit +modification of the work for the customer's own use and reverse +engineering for debugging such modifications. + + You must give prominent notice with each copy of the work that the +Library is used in it and that the Library and its use are covered by +this License. You must supply a copy of this License. If the work +during execution displays copyright notices, you must include the +copyright notice for the Library among them, as well as a reference +directing the user to the copy of this License. Also, you must do one +of these things: + + a) Accompany the work with the complete corresponding + machine-readable source code for the Library including whatever + changes were used in the work (which must be distributed under + Sections 1 and 2 above); and, if the work is an executable linked + with the Library, with the complete machine-readable "work that + uses the Library", as object code and/or source code, so that the + user can modify the Library and then relink to produce a modified + executable containing the modified Library. (It is understood + that the user who changes the contents of definitions files in the + Library will not necessarily be able to recompile the application + to use the modified definitions.) + + b) Use a suitable shared library mechanism for linking with the + Library. A suitable mechanism is one that (1) uses at run time a + copy of the library already present on the user's computer system, + rather than copying library functions into the executable, and (2) + will operate properly with a modified version of the library, if + the user installs one, as long as the modified version is + interface-compatible with the version that the work was made with. + + c) Accompany the work with a written offer, valid for at + least three years, to give the same user the materials + specified in Subsection 6a, above, for a charge no more + than the cost of performing this distribution. + + d) If distribution of the work is made by offering access to copy + from a designated place, offer equivalent access to copy the above + specified materials from the same place. + + e) Verify that the user has already received a copy of these + materials or that you have already sent this user a copy. + + For an executable, the required form of the "work that uses the +Library" must include any data and utility programs needed for +reproducing the executable from it. However, as a special exception, +the materials to be distributed need not include anything that is +normally distributed (in either source or binary form) with the major +components (compiler, kernel, and so on) of the operating system on +which the executable runs, unless that component itself accompanies +the executable. + + It may happen that this requirement contradicts the license +restrictions of other proprietary libraries that do not normally +accompany the operating system. Such a contradiction means you cannot +use both them and the Library together in an executable that you +distribute. + + 7. You may place library facilities that are a work based on the +Library side-by-side in a single library together with other library +facilities not covered by this License, and distribute such a combined +library, provided that the separate distribution of the work based on +the Library and of the other library facilities is otherwise +permitted, and provided that you do these two things: + + a) Accompany the combined library with a copy of the same work + based on the Library, uncombined with any other library + facilities. This must be distributed under the terms of the + Sections above. + + b) Give prominent notice with the combined library of the fact + that part of it is a work based on the Library, and explaining + where to find the accompanying uncombined form of the same work. + + 8. You may not copy, modify, sublicense, link with, or distribute +the Library except as expressly provided under this License. Any +attempt otherwise to copy, modify, sublicense, link with, or +distribute the Library is void, and will automatically terminate your +rights under this License. However, parties who have received copies, +or rights, from you under this License will not have their licenses +terminated so long as such parties remain in full compliance. + + 9. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Library or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Library (or any work based on the +Library), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Library or works based on it. + + 10. Each time you redistribute the Library (or any work based on the +Library), the recipient automatically receives a license from the +original licensor to copy, distribute, link with or modify the Library +subject to these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties with +this License. + + 11. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Library at all. For example, if a patent +license would not permit royalty-free redistribution of the Library by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Library. + +If any portion of this section is held invalid or unenforceable under any +particular circumstance, the balance of the section is intended to apply, +and the section as a whole is intended to apply in other circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 12. If the distribution and/or use of the Library is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Library under this License may add +an explicit geographical distribution limitation excluding those countries, +so that distribution is permitted only in or among countries not thus +excluded. In such case, this License incorporates the limitation as if +written in the body of this License. + + 13. The Free Software Foundation may publish revised and/or new +versions of the Lesser General Public License from time to time. +Such new versions will be similar in spirit to the present version, +but may differ in detail to address new problems or concerns. + +Each version is given a distinguishing version number. If the Library +specifies a version number of this License which applies to it and +"any later version", you have the option of following the terms and +conditions either of that version or of any later version published by +the Free Software Foundation. If the Library does not specify a +license version number, you may choose any version ever published by +the Free Software Foundation. + + 14. If you wish to incorporate parts of the Library into other free +programs whose distribution conditions are incompatible with these, +write to the author to ask for permission. For software which is +copyrighted by the Free Software Foundation, write to the Free +Software Foundation; we sometimes make exceptions for this. Our +decision will be guided by the two goals of preserving the free status +of all derivatives of our free software and of promoting the sharing +and reuse of software generally. + + NO WARRANTY + + 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO +WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. +EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR +OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY +KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE +LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME +THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN +WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY +AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU +FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR +CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE +LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING +RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A +FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF +SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH +DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Libraries + + If you develop a new library, and you want it to be of the greatest +possible use to the public, we recommend making it free software that +everyone can redistribute and change. You can do so by permitting +redistribution under these terms (or, alternatively, under the terms of the +ordinary General Public License). + + To apply these terms, attach the following notices to the library. It is +safest to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least the +"copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with this library; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + +Also add information on how to contact you by electronic and paper mail. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the library, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the + library `Frob' (a library for tweaking knobs) written by James Random Hacker. + + , 1 April 1990 + Ty Coon, President of Vice + +That's all there is to it! + + vim: et sw=4 sts=4
-
+ // ----
+ // State 2.4: