From 55c4ac1bfe565f1ca7f537fdd8b7a201be28e581 Mon Sep 17 00:00:00 2001 From: xue <> Date: Thu, 10 Nov 2005 12:47:19 +0000 Subject: Initial import of prado framework --- tests/UnitTests/simpletest/parser.php | 750 ++++++++++++++++++++++++++++++++++ 1 file changed, 750 insertions(+) create mode 100644 tests/UnitTests/simpletest/parser.php (limited to 'tests/UnitTests/simpletest/parser.php') diff --git a/tests/UnitTests/simpletest/parser.php b/tests/UnitTests/simpletest/parser.php new file mode 100644 index 00000000..cb9a3e75 --- /dev/null +++ b/tests/UnitTests/simpletest/parser.php @@ -0,0 +1,750 @@ +_case = $case; + $this->_patterns = array(); + $this->_labels = array(); + $this->_regex = null; + } + + /** + * Adds a pattern with an optional label. + * @param string $pattern Perl style regex, but ( and ) + * lose the usual meaning. + * @param string $label Label of regex to be returned + * on a match. + * @access public + */ + function addPattern($pattern, $label = true) { + $count = count($this->_patterns); + $this->_patterns[$count] = $pattern; + $this->_labels[$count] = $label; + $this->_regex = null; + } + + /** + * Attempts to match all patterns at once against + * a string. + * @param string $subject String to match against. + * @param string $match First matched portion of + * subject. + * @return boolean True on success. + * @access public + */ + function match($subject, $match) { + if (count($this->_patterns) == 0) { + return false; + } + if (! preg_match($this->_getCompoundedRegex(), $subject, $matches)) { + $match = ''; + return false; + } + $match = $matches[0]; + for ($i = 1; $i < count($matches); $i++) { + if ($matches[$i]) { + return $this->_labels[$i - 1]; + } + } + return true; + } + + /** + * Compounds the patterns into a single + * regular expression separated with the + * "or" operator. Caches the regex. + * Will automatically escape (, ) and / tokens. + * @param array $patterns List of patterns in order. + * @access private + */ + function _getCompoundedRegex() { + if ($this->_regex == null) { + for ($i = 0, $count = count($this->_patterns); $i < $count; $i++) { + $this->_patterns[$i] = '(' . str_replace( + array('/', '(', ')'), + array('\/', '\(', '\)'), + $this->_patterns[$i]) . ')'; + } + $this->_regex = "/" . implode("|", $this->_patterns) . "/" . $this->_getPerlMatchingFlags(); + } + return $this->_regex; + } + + /** + * Accessor for perl regex mode flags to use. + * @return string Perl regex flags. + * @access private + */ + function _getPerlMatchingFlags() { + return ($this->_case ? "msS" : "msSi"); + } + } + + /** + * States for a stack machine. + * @package SimpleTest + * @subpackage WebTester + */ + class SimpleStateStack { + protected $_stack; + + /** + * Constructor. Starts in named state. + * @param string $start Starting state name. + * @access public + */ + function SimpleStateStack($start) { + $this->_stack = array($start); + } + + /** + * Accessor for current state. + * @return string State. + * @access public + */ + function getCurrent() { + return $this->_stack[count($this->_stack) - 1]; + } + + /** + * Adds a state to the stack and sets it + * to be the current state. + * @param string $state New state. + * @access public + */ + function enter($state) { + array_push($this->_stack, $state); + } + + /** + * Leaves the current state and reverts + * to the previous one. + * @return boolean False if we drop off + * the bottom of the list. + * @access public + */ + function leave() { + if (count($this->_stack) == 1) { + return false; + } + array_pop($this->_stack); + return true; + } + } + + /** + * Accepts text and breaks it into tokens. + * Some optimisation to make the sure the + * content is only scanned by the PHP regex + * parser once. Lexer modes must not start + * with leading underscores. + * @package SimpleTest + * @subpackage WebTester + */ + class SimpleLexer { + protected $_regexes; + protected $_parser; + protected $_mode; + protected $_mode_handlers; + protected $_case; + + /** + * Sets up the lexer in case insensitive matching + * by default. + * @param SimpleSaxParser $parser Handling strategy by + * reference. + * @param string $start Starting handler. + * @param boolean $case True for case sensitive. + * @access public + */ + function SimpleLexer($parser, $start = "accept", $case = false) { + $this->_case = $case; + $this->_regexes = array(); + $this->_parser = $parser; + $this->_mode = new SimpleStateStack($start); + $this->_mode_handlers = array($start => $start); + } + + /** + * Adds a token search pattern for a particular + * parsing mode. The pattern does not change the + * current mode. + * @param string $pattern Perl style regex, but ( and ) + * lose the usual meaning. + * @param string $mode Should only apply this + * pattern when dealing with + * this type of input. + * @access public + */ + function addPattern($pattern, $mode = "accept") { + if (! isset($this->_regexes[$mode])) { + $this->_regexes[$mode] = new ParallelRegex($this->_case); + } + $this->_regexes[$mode]->addPattern($pattern); + if (! isset($this->_mode_handlers[$mode])) { + $this->_mode_handlers[$mode] = $mode; + } + } + + /** + * Adds a pattern that will enter a new parsing + * mode. Useful for entering parenthesis, strings, + * tags, etc. + * @param string $pattern Perl style regex, but ( and ) + * lose the usual meaning. + * @param string $mode Should only apply this + * pattern when dealing with + * this type of input. + * @param string $new_mode Change parsing to this new + * nested mode. + * @access public + */ + function addEntryPattern($pattern, $mode, $new_mode) { + if (! isset($this->_regexes[$mode])) { + $this->_regexes[$mode] = new ParallelRegex($this->_case); + } + $this->_regexes[$mode]->addPattern($pattern, $new_mode); + if (! isset($this->_mode_handlers[$new_mode])) { + $this->_mode_handlers[$new_mode] = $new_mode; + } + } + + /** + * Adds a pattern that will exit the current mode + * and re-enter the previous one. + * @param string $pattern Perl style regex, but ( and ) + * lose the usual meaning. + * @param string $mode Mode to leave. + * @access public + */ + function addExitPattern($pattern, $mode) { + if (! isset($this->_regexes[$mode])) { + $this->_regexes[$mode] = new ParallelRegex($this->_case); + } + $this->_regexes[$mode]->addPattern($pattern, "__exit"); + if (! isset($this->_mode_handlers[$mode])) { + $this->_mode_handlers[$mode] = $mode; + } + } + + /** + * Adds a pattern that has a special mode. Acts as an entry + * and exit pattern in one go, effectively calling a special + * parser handler for this token only. + * @param string $pattern Perl style regex, but ( and ) + * lose the usual meaning. + * @param string $mode Should only apply this + * pattern when dealing with + * this type of input. + * @param string $special Use this mode for this one token. + * @access public + */ + function addSpecialPattern($pattern, $mode, $special) { + if (! isset($this->_regexes[$mode])) { + $this->_regexes[$mode] = new ParallelRegex($this->_case); + } + $this->_regexes[$mode]->addPattern($pattern, "_$special"); + if (! isset($this->_mode_handlers[$special])) { + $this->_mode_handlers[$special] = $special; + } + } + + /** + * Adds a mapping from a mode to another handler. + * @param string $mode Mode to be remapped. + * @param string $handler New target handler. + * @access public + */ + function mapHandler($mode, $handler) { + $this->_mode_handlers[$mode] = $handler; + } + + /** + * Splits the page text into tokens. Will fail + * if the handlers report an error or if no + * content is consumed. If successful then each + * unparsed and parsed token invokes a call to the + * held listener. + * @param string $raw Raw HTML text. + * @return boolean True on success, else false. + * @access public + */ + function parse($raw) { + if (! isset($this->_parser)) { + return false; + } + $length = strlen($raw); + while (is_array($parsed = $this->_reduce($raw))) { + list($raw, $unmatched, $matched, $mode) = $parsed; + if (! $this->_dispatchTokens($unmatched, $matched, $mode)) { + return false; + } + if ($raw === '') { + return true; + } + if (strlen($raw) == $length) { + return false; + } + $length = strlen($raw); + } + if (! $parsed) { + return false; + } + return $this->_invokeParser($raw, LEXER_UNMATCHED); + } + + /** + * Sends the matched token and any leading unmatched + * text to the parser changing the lexer to a new + * mode if one is listed. + * @param string $unmatched Unmatched leading portion. + * @param string $matched Actual token match. + * @param string $mode Mode after match. A boolean + * false mode causes no change. + * @return boolean False if there was any error + * from the parser. + * @access private + */ + function _dispatchTokens($unmatched, $matched, $mode = false) { + if (! $this->_invokeParser($unmatched, LEXER_UNMATCHED)) { + return false; + } + if (is_bool($mode)) { + return $this->_invokeParser($matched, LEXER_MATCHED); + } + if ($this->_isModeEnd($mode)) { + if (! $this->_invokeParser($matched, LEXER_EXIT)) { + return false; + } + return $this->_mode->leave(); + } + if ($this->_isSpecialMode($mode)) { + $this->_mode->enter($this->_decodeSpecial($mode)); + if (! $this->_invokeParser($matched, LEXER_SPECIAL)) { + return false; + } + return $this->_mode->leave(); + } + $this->_mode->enter($mode); + return $this->_invokeParser($matched, LEXER_ENTER); + } + + /** + * Tests to see if the new mode is actually to leave + * the current mode and pop an item from the matching + * mode stack. + * @param string $mode Mode to test. + * @return boolean True if this is the exit mode. + * @access private + */ + function _isModeEnd($mode) { + return ($mode === "__exit"); + } + + /** + * Test to see if the mode is one where this mode + * is entered for this token only and automatically + * leaves immediately afterwoods. + * @param string $mode Mode to test. + * @return boolean True if this is the exit mode. + * @access private + */ + function _isSpecialMode($mode) { + return (strncmp($mode, "_", 1) == 0); + } + + /** + * Strips the magic underscore marking single token + * modes. + * @param string $mode Mode to decode. + * @return string Underlying mode name. + * @access private + */ + function _decodeSpecial($mode) { + return substr($mode, 1); + } + + /** + * Calls the parser method named after the current + * mode. Empty content will be ignored. The lexer + * has a parser handler for each mode in the lexer. + * @param string $content Text parsed. + * @param boolean $is_match Token is recognised rather + * than unparsed data. + * @access private + */ + function _invokeParser($content, $is_match) { + if (($content === '') || ($content === false)) { + return true; + } + $handler = $this->_mode_handlers[$this->_mode->getCurrent()]; + return $this->_parser->$handler($content, $is_match); + } + + /** + * Tries to match a chunk of text and if successful + * removes the recognised chunk and any leading + * unparsed data. Empty strings will not be matched. + * @param string $raw The subject to parse. This is the + * content that will be eaten. + * @return array/boolean Three item list of unparsed + * content followed by the + * recognised token and finally the + * action the parser is to take. + * True if no match, false if there + * is a parsing error. + * @access private + */ + function _reduce($raw) { + if ($action = $this->_regexes[$this->_mode->getCurrent()]->match($raw, $match)) { + $unparsed_character_count = strpos($raw, $match); + $unparsed = substr($raw, 0, $unparsed_character_count); + $raw = substr($raw, $unparsed_character_count + strlen($match)); + return array($raw, $unparsed, $match, $action); + } + return true; + } + } + + /** + * Converts HTML tokens into selected SAX events. + * @package SimpleTest + * @subpackage WebTester + */ + class SimpleSaxParser { + protected $_lexer; + protected $_listener; + protected $_tag; + protected $_attributes; + protected $_current_attribute; + + /** + * Sets the listener. + * @param SimpleSaxListener $listener SAX event handler. + * @access public + */ + function SimpleSaxParser($listener) { + $this->_listener = $listener; + $this->_lexer = $this->createLexer($this); + $this->_tag = ''; + $this->_attributes = array(); + $this->_current_attribute = ''; + } + + /** + * Runs the content through the lexer which + * should call back to the acceptors. + * @param string $raw Page text to parse. + * @return boolean False if parse error. + * @access public + */ + function parse($raw) { + return $this->_lexer->parse($raw); + } + + /** + * Sets up the matching lexer. Starts in 'text' mode. + * @param SimpleSaxParser $parser Event generator, usually $self. + * @return SimpleLexer Lexer suitable for this parser. + * @access public + * @static + */ + function createLexer($parser) { + $lexer = new SimpleLexer($parser, 'text'); + $lexer->mapHandler('text', 'acceptTextToken'); + SimpleSaxParser::_addSkipping($lexer); + foreach (SimpleSaxParser::_getParsedTags() as $tag) { + SimpleSaxParser::_addTag($lexer, $tag); + } + SimpleSaxParser::_addInTagTokens($lexer); + return $lexer; + } + + /** + * List of parsed tags. Others are ignored. + * @return array List of searched for tags. + * @access private + */ + function _getParsedTags() { + return array('a', 'title', 'form', 'input', 'button', 'textarea', 'select', + 'option', 'frameset', 'frame'); + } + + /** + * The lexer has to skip certain sections such + * as server code, client code and styles. + * @param SimpleLexer $lexer Lexer to add patterns to. + * @access private + * @static + */ + function _addSkipping($lexer) { + $lexer->mapHandler('css', 'ignore'); + $lexer->addEntryPattern('addExitPattern('', 'css'); + $lexer->mapHandler('js', 'ignore'); + $lexer->addEntryPattern('addExitPattern('', 'js'); + $lexer->mapHandler('comment', 'ignore'); + $lexer->addEntryPattern('', 'comment'); + } + + /** + * Pattern matches to start and end a tag. + * @param SimpleLexer $lexer Lexer to add patterns to. + * @param string $tag Name of tag to scan for. + * @access private + * @static + */ + function _addTag($lexer, $tag) { + $lexer->addSpecialPattern("", 'text', 'acceptEndToken'); + $lexer->addEntryPattern("<$tag", 'text', 'tag'); + } + + /** + * Pattern matches to parse the inside of a tag + * including the attributes and their quoting. + * @param SimpleLexer $lexer Lexer to add patterns to. + * @access private + * @static + */ + function _addInTagTokens($lexer) { + $lexer->mapHandler('tag', 'acceptStartToken'); + $lexer->addSpecialPattern('\s+', 'tag', 'ignore'); + SimpleSaxParser::_addAttributeTokens($lexer); + $lexer->addExitPattern('>', 'tag'); + } + + /** + * Matches attributes that are either single quoted, + * double quoted or unquoted. + * @param SimpleLexer $lexer Lexer to add patterns to. + * @access private + * @static + */ + function _addAttributeTokens($lexer) { + $lexer->mapHandler('dq_attribute', 'acceptAttributeToken'); + $lexer->addEntryPattern('=\s*"', 'tag', 'dq_attribute'); + $lexer->addPattern("\\\\\"", 'dq_attribute'); + $lexer->addExitPattern('"', 'dq_attribute'); + $lexer->mapHandler('sq_attribute', 'acceptAttributeToken'); + $lexer->addEntryPattern("=\s*'", 'tag', 'sq_attribute'); + $lexer->addPattern("\\\\'", 'sq_attribute'); + $lexer->addExitPattern("'", 'sq_attribute'); + $lexer->mapHandler('uq_attribute', 'acceptAttributeToken'); + $lexer->addSpecialPattern('=\s*[^>\s]*', 'tag', 'uq_attribute'); + } + + /** + * Accepts a token from the tag mode. If the + * starting element completes then the element + * is dispatched and the current attributes + * set back to empty. The element or attribute + * name is converted to lower case. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function acceptStartToken($token, $event) { + if ($event == LEXER_ENTER) { + $this->_tag = strtolower(substr($token, 1)); + return true; + } + if ($event == LEXER_EXIT) { + $success = $this->_listener->startElement( + $this->_tag, + $this->_attributes); + $this->_tag = ""; + $this->_attributes = array(); + return $success; + } + if ($token != "=") { + $this->_current_attribute = strtolower(SimpleSaxParser::decodeHtml($token)); + $this->_attributes[$this->_current_attribute] = ""; + } + return true; + } + + /** + * Accepts a token from the end tag mode. + * The element name is converted to lower case. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function acceptEndToken($token, $event) { + if (! preg_match('/<\/(.*)>/', $token, $matches)) { + return false; + } + return $this->_listener->endElement(strtolower($matches[1])); + } + + /** + * Part of the tag data. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function acceptAttributeToken($token, $event) { + if ($event == LEXER_UNMATCHED) { + $this->_attributes[$this->_current_attribute] .= + SimpleSaxParser::decodeHtml($token); + } + if ($event == LEXER_SPECIAL) { + $this->_attributes[$this->_current_attribute] .= + preg_replace('/^=\s*/' , '', SimpleSaxParser::decodeHtml($token)); + } + return true; + } + + /** + * A character entity. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function acceptEntityToken($token, $event) { + } + + /** + * Character data between tags regarded as + * important. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function acceptTextToken($token, $event) { + return $this->_listener->addContent($token); + } + + /** + * Incoming data to be ignored. + * @param string $token Incoming characters. + * @param integer $event Lexer event type. + * @return boolean False if parse error. + * @access public + */ + function ignore($token, $event) { + return true; + } + + /** + * Decodes any HTML entities. + * @param string $html Incoming HTML. + * @return string Outgoing plain text. + * @access public + * @static + */ + function decodeHtml($html) { + static $translations; + if (! isset($translations)) { + $translations = array_flip(get_html_translation_table(HTML_ENTITIES)); + } + return strtr($html, $translations); + } + + /** + * Turns HTML into text browser visible text. Images + * are converted to their alt text and tags are supressed. + * Entities are converted to their visible representation. + * @param string $html HTML to convert. + * @return string Plain text. + * @access public + * @static + */ + function normalise($html) { + $text = preg_replace('||', ' \1 ', $html); + $text = preg_replace('||', ' \1 ', $text); + $text = preg_replace('||', ' \1 ', $text); + $text = preg_replace('|<.*?>|', '', $text); + $text = SimpleSaxParser::decodeHtml($text); + $text = preg_replace('|\s+|', ' ', $text); + return trim($text); + } + } + + /** + * SAX event handler. + * @package SimpleTest + * @subpackage WebTester + * @abstract + */ + class SimpleSaxListener { + + /** + * Sets the document to write to. + * @access public + */ + function SimpleSaxListener() { + } + + /** + * Start of element event. + * @param string $name Element name. + * @param hash $attributes Name value pairs. + * Attributes without content + * are marked as true. + * @return boolean False on parse error. + * @access public + */ + function startElement($name, $attributes) { + } + + /** + * End of element event. + * @param string $name Element name. + * @return boolean False on parse error. + * @access public + */ + function endElement($name) { + } + + /** + * Unparsed, but relevant data. + * @param string $text May include unparsed tags. + * @return boolean False on parse error. + * @access public + */ + function addContent($text) { + } + } +?> \ No newline at end of file -- cgit v1.2.3