GeSHi: comparison plugins/geshi/base.php

equal deleted inserted replaced

-:9e3258dfae15
+:f3e2bbbd2155
 // their values - you never know when a value may change in a future
 // version
 //
 /** The version of this GeSHi file */
-define('GESHI_VERSION', '1.0.8.2');
+define('GESHI_VERSION', '1.0.8.4');
 // Define the root directory for the GeSHi code tree
 if (!defined('GESHI_ROOT')) {
 /** The root directory for GeSHi */
 define('GESHI_ROOT', dirname(__FILE__) . DIRECTORY_SEPARATOR);
 * @param string  The style to make the escape characters
 * @param boolean Whether to merge the new styles with the old or just
 *                to overwrite them
 * @since 1.0.0
 */
-function set_escape_characters_style($style, $preserve_defaults = false) {
+function set_escape_characters_style($style, $preserve_defaults = false, $group = 0) {
 if (!$preserve_defaults) {
-$this->language_data['STYLES']['ESCAPE_CHAR'][0] = $style;
+$this->language_data['STYLES']['ESCAPE_CHAR'][$group] = $style;
 } else {
-$this->language_data['STYLES']['ESCAPE_CHAR'][0] .= $style;
+$this->language_data['STYLES']['ESCAPE_CHAR'][$group] .= $style;
 }
 }
 /**
 * Turns highlighting on/off for escaped characters
 function set_strings_highlighting($flag) {
 $this->lexic_permissions['STRINGS'] = ($flag) ? true : false;
 }
 /**
+* Sets the styles for strict code blocks. If $preserve_defaults is
+* true, then styles are merged with the default styles, with the
+* user defined styles having priority
+*
+* @param string  The style to make the script blocks
+* @param boolean Whether to merge the new styles with the old or just
+*                to overwrite them
+* @param int     Tells the group of script blocks for which style should be set.
+* @since 1.0.8.4
+*/
+function set_script_style($style, $preserve_defaults = false, $group = 0) {
+// Update the style of symbols
+if (!$preserve_defaults) {
+$this->language_data['STYLES']['SCRIPT'][$group] = $style;
+} else {
+$this->language_data['STYLES']['SCRIPT'][$group] .= $style;
+}
+}
+/**
 * Sets the styles for numbers. If $preserve_defaults is
 * true, then styles are merged with the default styles, with the
 * user defined styles having priority
 *
 * @param string  The style to make the numbers
 * @todo static?
 */
 function get_language_name_from_extension( $extension, $lookup = array() ) {
 if ( !is_array($lookup) || empty($lookup)) {
 $lookup = array(
+'abap' => array('abap'),
 'actionscript' => array('as'),
 'ada' => array('a', 'ada', 'adb', 'ads'),
 'apache' => array('conf'),
 'asm' => array('ash', 'asm', 'inc'),
 'asp' => array('asp'),
 'tcl' => array('tcl'),
 'vb' => array('bas'),
 'vbnet' => array(),
 'visualfoxpro' => array(),
 'whitespace' => array('ws'),
-'xml' => array('xml', 'svg'),
+'xml' => array('xml', 'svg', 'xrc'),
 'z80' => array('z80', 'asm', 'inc')
 );
 }
 foreach ($lookup as $lang => $extensions) {
 * @since 1.0.8
 */
 function optimize_keyword_group($key) {
 $this->language_data['CACHED_KEYWORD_LISTS'][$key] =
 $this->optimize_regexp_list($this->language_data['KEYWORDS'][$key]);
+$space_as_whitespace = false;
+if(isset($this->language_data['PARSER_CONTROL'])) {
+if(isset($this->language_data['PARSER_CONTROL']['KEYWORDS'])) {
+if(isset($this->language_data['PARSER_CONTROL']['KEYWORDS']['SPACE_AS_WHITESPACE'])) {
+$space_as_whitespace = $this->language_data['PARSER_CONTROL']['KEYWORDS']['SPACE_AS_WHITESPACE'];
+}
+if(isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$key]['SPACE_AS_WHITESPACE'])) {
+if(isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$key]['SPACE_AS_WHITESPACE'])) {
+$space_as_whitespace = $this->language_data['PARSER_CONTROL']['KEYWORDS'][$key]['SPACE_AS_WHITESPACE'];
+}
+}
+}
+}
+if($space_as_whitespace) {
+foreach($this->language_data['CACHED_KEYWORD_LISTS'][$key] as $rxk => $rxv) {
+$this->language_data['CACHED_KEYWORD_LISTS'][$key][$rxk] =
+str_replace(" ", "\\s+", $rxv);
+}
+}
 }
 /**
 * Sets the content of the header block
 *
 //Number format specification
 //All this formats are matched case-insensitively!
 static $numbers_format = array(
 GESHI_NUMBER_INT_BASIC =>
-'(?<![0-9a-z_\.%])(?<![\d\.]e[+\-])([1-9]\d*?|0)(?![0-9a-z\.])',
+'(?<![0-9a-z_\.%])(?<![\d\.]e[+\-])([1-9]\d*?|0)(?![0-9a-z]|\.(?!(?m:$)))',
 GESHI_NUMBER_INT_CSTYLE =>
 '(?<![0-9a-z_\.%])(?<![\d\.]e[+\-])([1-9]\d*?|0)l(?![0-9a-z\.])',
 GESHI_NUMBER_BIN_SUFFIX =>
 '(?<![0-9a-z_\.])(?<![\d\.]e[+\-])[01]+?b(?![0-9a-z\.])',
 GESHI_NUMBER_BIN_PREFIX_PERCENT =>
 }
 $regexp = implode("|", $rxuse);
 }
 $this->language_data['NUMBERS_RXCACHE'][$key] =
-"/(?<!<\|\/NUM!)(?<!\d\/>)($regexp)(?!\|>)/i";
+"/(?<!<\|\/)(?<!<\|!REG3XP)(?<!<\|\/NUM!)(?<!\d\/>)($regexp)(?!\|>)(?![^\"\|\>\<]+<)/i";
 }
 }
 $this->parse_cache_built = true;
 }
 *  - Group 2 is the closer
 */
 if(!GESHI_PHP_PRE_433 && //Needs proper rewrite to work with PHP >=4.3.0; 4.3.3 is guaranteed to work.
 preg_match($delimiters, $code, $matches_rx, PREG_OFFSET_CAPTURE, $i)) {
 //We got a match ...
-$matches[$dk] = array(
+if(isset($matches_rx['start']) && isset($matches_rx['end']))
-'next_match' => $matches_rx[1][1],
+{
-'dk' => $dk,
+$matches[$dk] = array(
+'next_match' => $matches_rx['start'][1],
-'close_strlen' => strlen($matches_rx[2][0]),
+'dk' => $dk,
-'close_pos' => $matches_rx[2][1],
-);
+'close_strlen' => strlen($matches_rx['end'][0]),
+'close_pos' => $matches_rx['end'][1],
+);
+} else {
+$matches[$dk] = array(
+'next_match' => $matches_rx[1][1],
+'dk' => $dk,
+'close_strlen' => strlen($matches_rx[2][0]),
+'close_pos' => $matches_rx[2][1],
+);
+}
 } else {
 // no match for this delimiter ever
 unset($delim_copy[$dk]);
 continue;
 }
 $next_match_pointer =& $matches[$dk];
 $next_match_pos = $matches[$dk]['next_match'];
 }
 }
 }
 // non-highlightable text
 $parts[$k] = array(
 1 => substr($code, $i, $next_match_pos - $i)
 );
 ++$k;
 }
 }
 $char_len = strlen($char);
 }
-if ($string_started && $i != $next_comment_regexp_pos) {
+if ($string_started && ($i != $next_comment_regexp_pos)) {
 // Hand out the correct style information for this string
 $string_key = array_search($char, $this->language_data['QUOTEMARKS']);
 if (!isset($this->language_data['STYLES']['STRINGS'][$string_key]) ||
 !isset($this->language_data['STYLES']['ESCAPE_CHAR'][$string_key])) {
 $string_key = 0;
 $result .= $string;
 $string = '';
 $i = $start - 1;
 continue;
 } else if ($this->lexic_permissions['STRINGS'] && $hq && $hq[0] == $char &&
-substr($part, $i, $hq_strlen) == $hq) {
+substr($part, $i, $hq_strlen) == $hq && ($i != $next_comment_regexp_pos)) {
 // The start of a hard quoted string
 if (!$this->use_classes) {
 $string_attributes = ' style="' . $this->language_data['STYLES']['STRINGS']['HARD'] . '"';
 $escape_char_attributes = ' style="' . $this->language_data['STYLES']['ESCAPE_CHAR']['HARD'] . '"';
 } else {
 // look for closing quote
 $start = $i + $hq_strlen;
 while ($close_pos = strpos($part, $this->language_data['HARDQUOTE'][1], $start)) {
 $start = $close_pos + 1;
-if ($this->lexic_permissions['ESCAPE_CHAR'] && $part[$close_pos - 1] == $this->language_data['ESCAPE_CHAR']) {
+if ($this->lexic_permissions['ESCAPE_CHAR'] && $part[$close_pos - 1] == $this->language_data['HARDCHAR']) {
 // make sure this quote is not escaped
 foreach ($this->language_data['HARDESCAPE'] as $hardescape) {
 if (substr($part, $close_pos - 1, strlen($hardescape)) == $hardescape) {
 // check wether this quote is escaped or if it is something like '\\'
 $escape_char_pos = $close_pos - 1;
 while ($escape_char_pos > 0
-&& $part[$escape_char_pos - 1] == $this->language_data['ESCAPE_CHAR']) {
+&& $part[$escape_char_pos - 1] == $this->language_data['HARDCHAR']) {
 --$escape_char_pos;
 }
 if (($close_pos - $escape_char_pos) & 1) {
 // uneven number of escape chars => this quote is escaped
 continue 2;
 * @todo BUGGY! Why? Why not build string and return?
 */
 function parse_non_string_part($stuff_to_parse) {
 $stuff_to_parse = ' ' . $this->hsc($stuff_to_parse);
+// Highlight keywords
+$disallowed_before = "(?<![a-zA-Z0-9\$_\|\#;>|^&";
+$disallowed_after = "(?![a-zA-Z0-9_\|%\\-&;";
+if ($this->lexic_permissions['STRINGS']) {
+$quotemarks = preg_quote(implode($this->language_data['QUOTEMARKS']), '/');
+$disallowed_before .= $quotemarks;
+$disallowed_after .= $quotemarks;
+}
+$disallowed_before .= "])";
+$disallowed_after .= "])";
+$parser_control_pergroup = false;
+if (isset($this->language_data['PARSER_CONTROL'])) {
+if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'])) {
+$x = 0; // check wether per-keyword-group parser_control is enabled
+if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_BEFORE'])) {
+$disallowed_before = $this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_BEFORE'];
+++$x;
+}
+if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_AFTER'])) {
+$disallowed_after = $this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_AFTER'];
+++$x;
+}
+$parser_control_pergroup = (count($this->language_data['PARSER_CONTROL']['KEYWORDS']) - $x) > 0;
+}
+}
+foreach (array_keys($this->language_data['KEYWORDS']) as $k) {
+if (!isset($this->lexic_permissions['KEYWORDS'][$k]) ||
+$this->lexic_permissions['KEYWORDS'][$k]) {
+$case_sensitive = $this->language_data['CASE_SENSITIVE'][$k];
+$modifiers = $case_sensitive ? '' : 'i';
+// NEW in 1.0.8 - per-keyword-group parser control
+$disallowed_before_local = $disallowed_before;
+$disallowed_after_local = $disallowed_after;
+if ($parser_control_pergroup && isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k])) {
+if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_BEFORE'])) {
+$disallowed_before_local =
+$this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_BEFORE'];
+}
+if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_AFTER'])) {
+$disallowed_after_local =
+$this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_AFTER'];
+}
+}
+$this->_kw_replace_group = $k;
+//NEW in 1.0.8, the cached regexp list
+// since we don't want PHP / PCRE to crash due to too large patterns we split them into smaller chunks
+for ($set = 0, $set_length = count($this->language_data['CACHED_KEYWORD_LISTS'][$k]); $set <  $set_length; ++$set) {
+$keywordset =& $this->language_data['CACHED_KEYWORD_LISTS'][$k][$set];
+// Might make a more unique string for putting the number in soon
+// Basically, we don't put the styles in yet because then the styles themselves will
+// get highlighted if the language has a CSS keyword in it (like CSS, for example ;))
+$stuff_to_parse = preg_replace_callback(
+"/$disallowed_before_local({$keywordset})(?!\<DOT\>(?:htm|php))$disallowed_after_local/$modifiers",
+array($this, 'handle_keyword_replace'),
+$stuff_to_parse
+);
+}
+}
+}
 // Regular expressions
 foreach ($this->language_data['REGEXPS'] as $key => $regexp) {
 if ($this->lexic_permissions['REGEXPS'][$key]) {
 if (is_array($regexp)) {
 if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) {
 }
 }
 }
 }
-// Highlight numbers. As of 1.0.8 we support diffent types of numbers
+// Highlight numbers. As of 1.0.8 we support different types of numbers
 $numbers_found = false;
 if ($this->lexic_permissions['NUMBERS'] && preg_match('#\d#', $stuff_to_parse )) {
 $numbers_found = true;
 //For each of the formats ...
 foreach($this->language_data['NUMBERS_RXCACHE'] as $id => $regexp) {
 //Check if it should be highlighted ...
 $stuff_to_parse = preg_replace($regexp, "<|/NUM!$id/>\\1|>", $stuff_to_parse);
-}
-}
-// Highlight keywords
-$disallowed_before = "(?<![a-zA-Z0-9\$_\|\#;>|^&";
-$disallowed_after = "(?![a-zA-Z0-9_\|%\\-&;";
-if ($this->lexic_permissions['STRINGS']) {
-$quotemarks = preg_quote(implode($this->language_data['QUOTEMARKS']), '/');
-$disallowed_before .= $quotemarks;
-$disallowed_after .= $quotemarks;
-}
-$disallowed_before .= "])";
-$disallowed_after .= "])";
-$parser_control_pergroup = false;
-if (isset($this->language_data['PARSER_CONTROL'])) {
-if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'])) {
-$x = 0; // check wether per-keyword-group parser_control is enabled
-if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_BEFORE'])) {
-$disallowed_before = $this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_BEFORE'];
-++$x;
-}
-if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_AFTER'])) {
-$disallowed_after = $this->language_data['PARSER_CONTROL']['KEYWORDS']['DISALLOWED_AFTER'];
-++$x;
-}
-$parser_control_pergroup = (count($this->language_data['PARSER_CONTROL']['KEYWORDS']) - $x) > 0;
-}
-}
-// if this is changed, don't forget to change it below
-//        if (!empty($disallowed_before)) {
-//            $disallowed_before = "(?<![$disallowed_before])";
-//        }
-//        if (!empty($disallowed_after)) {
-//            $disallowed_after = "(?![$disallowed_after])";
-//        }
-foreach (array_keys($this->language_data['KEYWORDS']) as $k) {
-if (!isset($this->lexic_permissions['KEYWORDS'][$k]) ||
-$this->lexic_permissions['KEYWORDS'][$k]) {
-$case_sensitive = $this->language_data['CASE_SENSITIVE'][$k];
-$modifiers = $case_sensitive ? '' : 'i';
-// NEW in 1.0.8 - per-keyword-group parser control
-$disallowed_before_local = $disallowed_before;
-$disallowed_after_local = $disallowed_after;
-if ($parser_control_pergroup && isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k])) {
-if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_BEFORE'])) {
-$disallowed_before_local =
-$this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_BEFORE'];
-}
-if (isset($this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_AFTER'])) {
-$disallowed_after_local =
-$this->language_data['PARSER_CONTROL']['KEYWORDS'][$k]['DISALLOWED_AFTER'];
-}
-}
-$this->_kw_replace_group = $k;
-//NEW in 1.0.8, the cached regexp list
-// since we don't want PHP / PCRE to crash due to too large patterns we split them into smaller chunks
-for ($set = 0, $set_length = count($this->language_data['CACHED_KEYWORD_LISTS'][$k]); $set <  $set_length; ++$set) {
-$keywordset =& $this->language_data['CACHED_KEYWORD_LISTS'][$k][$set];
-// Might make a more unique string for putting the number in soon
-// Basically, we don't put the styles in yet because then the styles themselves will
-// get highlighted if the language has a CSS keyword in it (like CSS, for example ;))
-$stuff_to_parse = preg_replace_callback(
-"/$disallowed_before_local({$keywordset})(?!\<DOT\>(?:htm|php))$disallowed_after_local/$modifiers",
-array($this, 'handle_keyword_replace'),
-$stuff_to_parse
-);
-}
 }
 }
 //
 // Now that's all done, replace /[number]/ with the correct styles
 }
 if ($numbers_found) {
 // Put number styles in
 foreach($this->language_data['NUMBERS_RXCACHE'] as $id => $regexp) {
 //Commented out for now, as this needs some review ...
 //                if ($numbers_permissions & $id) {
 //Get the appropriate style ...
 //Checking for unset styles is done by the style cache builder ...
 if (!$this->use_classes) {
 $attributes = ' style="' . $this->language_data['STYLES']['NUMBERS'][$id] . '"';
 } else {
 $attributes = ' class="nu'.$id.'"';
 }
 //Set in the correct styles ...
 $stuff_to_parse = str_replace("/NUM!$id/", $attributes, $stuff_to_parse);
 //                }
 }
 }
 // Highlight methods and fields in objects
 if ($this->lexic_permissions['METHODS'] && $this->language_data['OOLANG']) {
 } else {
 $this->lexic_permissions[$flag] = $perm;
 }
 }
 unset($this->language_data['PARSER_CONTROL']['ENABLE_FLAGS']);
+}
+//Fix: Problem where hardescapes weren't handled if no ESCAPE_CHAR was given
+//You need to set one for HARDESCAPES only in this case.
+if(!isset($this->language_data['HARDCHAR'])) {
+$this->language_data['HARDCHAR'] = $this->language_data['ESCAPE_CHAR'];
 }
 //NEW in 1.0.8: Allow styles to be loaded from a separate file to override defaults
 $style_filename = substr($file_name, 0, -4) . '.style.php';
 if (is_readable($style_filename)) {
 if ($this->use_classes) {
 $attr = ' class="foot"';
 } else {
 $attr = " style=\"{$this->footer_content_style}\"";
 }
-if ($this->header_type == GESHI_HEADER_PRE_TABLE && $this->linenumbers != GESHI_NO_LINE_NUMBERS) {
+if ($this->header_type == GESHI_HEADER_PRE_TABLE && $this->line_numbers != GESHI_NO_LINE_NUMBERS) {
 $footer = "<tfoot><tr><td colspan=\"2\">$footer</td></tr></tfoot>";
 } else {
 $footer = "<div$attr>$footer</div>";
 }
 }

changeset 3	f3e2bbbd2155
parent 2	9e3258dfae15