Menu
▾
▴
[GeSHi-commit] SF.net SVN: geshi: [1167] branches/RELEASE_1_1_X_DEVEL/geshi-src
|
From: <be...@us...> - 2008-05-18 15:33:09
|
Revision: 1167
http://geshi.svn.sourceforge.net/geshi/?rev=1167&view=rev
Author: benbe
Date: 2008-05-18 08:33:07 -0700 (Sun, 18 May 2008)
Log Message:
-----------
add: Building up GeSHi 1.1.X developement branch using old releases
Modified Paths:
--------------
branches/RELEASE_1_1_X_DEVEL/geshi-src/class.geshi.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshicontext.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshisinglecharcontext.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshistringcontext.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/functions.geshi.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/c.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/class.geshiccodeparser.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/common.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/codeworker/codeworker.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/css/css.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/delphi/common.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/delphi/delphi.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/java/java.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/javascript/javascript.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/php/class.geshiphpcodeparser.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/php/common.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/sql/sql.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/vhdl/vhdl.php
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/themes/default/c/c.php
Added Paths:
-----------
branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/NOTES
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/class.geshi.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/class.geshi.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/class.geshi.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -42,7 +42,7 @@
$geshi_old_reporting_level = error_reporting(E_ALL);
/** GeSHi Version */
-define('GESHI_VERSION', '1.1.2alpha2');
+define('GESHI_VERSION', '1.1.2alpha3');
/** Set the correct directory separator */
define('GESHI_DIR_SEP', ('WIN' != substr(PHP_OS, 0, 3)) ? '/' : '\\');
@@ -318,7 +318,7 @@
* language. If caching of the root context is enabled, then this time will likely
* be close to zero if you are calling this method after second and subsequent calls
* to {@link GeSHi::parseCode()}.</li>
- * <li>If youpass <b>'parse'</b>, you will get the time it took to parse the last
+ * <li>If you pass <b>'parse'</b>, you will get the time it took to parse the last
* time {@link GeSHi::parseCode()} was called.
* </ul>
*
@@ -382,6 +382,43 @@
}
// }}}
+ // {{{ getSupportedLanguages()
+
+ /**
+ * @todo document this function
+ * @todo This and other methods share a lot of directory traversal
+ * functionality, which could be split out somehow.
+ * @todo actually, this should be implemented using a registry
+ */
+ function getSupportedLanguages ($return_human = false)
+ {
+ $languages = array();
+
+ $ignore = array('.', '..', 'CVS');
+ $dh = opendir(GESHI_LANGUAGES_ROOT);
+ while (false !== ($dir = readdir($dh))) {
+ if (in_array($dir, $ignore) || is_file(GESHI_LANGUAGES_ROOT . $dir)) continue;
+ // Check the directory for the dialect files
+ $ldh = opendir(GESHI_LANGUAGES_ROOT . $dir);
+ while (false !== ($file = readdir($ldh))) {
+ if (in_array($file, $ignore) || is_dir(GESHI_LANGUAGES_ROOT . "$dir/$file") || substr($file, -4) != '.php') continue;
+
+ // Found a language file
+ $file = substr($file, 0, -4);
+ if ('common' == $file || 'class' == substr($file, 0, 5)) continue;
+
+ if ($return_human) {
+ $languages["$dir/$file"] = GeSHi::getHumanLanguageName("$dir/$file");
+ } else {
+ $languages[] = "$dir/$file";
+ }
+ }
+ }
+
+ return $languages;
+ }
+
+ // }}}
// {{{ getSupportedThemes()
/**
@@ -504,6 +541,26 @@
}
// }}}
+ // {{{ getHumanLanguageName()
+
+ /**
+ * Given a language name, return a human version of it
+ *
+ * @param string $language The language name to get the human version of
+ * @return string The human language name, or <kbd>false</kbd> if the
+ * language does not exist
+ * @static
+ * @todo actually implement this function
+ * @since 1.1.2
+ */
+ function getHumanLanguageName ($language)
+ {
+ $human_name = '';
+ $language = GeSHi::_clean($language);
+ return $language;
+ }
+
+ // }}}
// {{{ getHumanThemeName()
/**
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshicontext.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshicontext.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshicontext.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -786,8 +786,6 @@
$length = $data['len'];
if (isset($data['tab'])) {
geshi_dbg('Table: ' . print_r($data['tab'], true));
- $this->_startRegexTable = $data['tab'];
- $delimiter = $data['tab'][0];
}
if (false !== $position) {
@@ -798,6 +796,10 @@
$first_position = $position;
$first_length = $length;
$first_key = $key;
+ if (isset($data['tab'])) {
+ $this->_startRegexTable = $data['tab'];
+ $delimiter = $data['tab'][0];
+ }
$first_dlm = $delimiter;
}
} else {
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshisinglecharcontext.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshisinglecharcontext.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshisinglecharcontext.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -6,10 +6,10 @@
* Author: Nigel McNie
* E-mail: ni...@ge...
* </pre>
- *
+ *
* For information on how to use GeSHi, please consult the documentation
* found in the docs/ directory, or online at http://geshi.org/docs/
- *
+ *
* This program is part of GeSHi.
*
* This program is free software; you can redistribute it and/or modify
@@ -21,160 +21,236 @@
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
- *
+ *
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
* @package geshi
* @subpackage core
- * @author Nigel McNie <ni...@ge...>
+ * @author Nigel McNie <ni...@ge...>;
+ * http://clc-wiki.net/wiki/User:Netocrat
* @license http://www.gnu.org/copyleft/gpl.html GNU GPL
* @copyright (C) 2004 - 2006 Nigel McNie
* @version $Id$
- *
+ *
*/
/**
* The GeSHiSingleCharContext class. This class extends GeSHiContext to handle
* "single character" strings - strings that are only one character long, like
* in java.
- *
- * Note that this functionality assumes that the delimiters for single character
- * contexts are just one character long (a sensible assumption made for speed
- * reasons). If required in the future this class could support longer delimiters.
- *
+ *
+ * Escape sequences need not be limited to one character and may be REGEX-
+ * specified, to allow for situations such as C's octal and hexadecimal escapes,
+ * e.g. '\xFF'. Likewise for the start and end delimiter, and the escape
+ * "character". This is handy for situations such as C's widestring
+ * characters, which are prefixed by an L.
+ *
* @package geshi
* @subpackage core
- * @author Nigel McNie <ni...@ge...>
+ * @author Nigel McNie <ni...@ge...>; Netocrat
* @since 1.1.1
* @version $Revision$
* @see GeSHiContext
*/
class GeSHiSingleCharContext extends GeSHiContext
{
-
+
// {{{ properties
-
+
/**#@-
* @access private
*/
+ /** The parsed data when getContextStartData() is successful. */
+ var $_characterLen;
+ var $_endDelimiterLen;
+ var $_isEscapeSeq;
+
+ var $_disallowEmpty;
+
+ /** Characters that start an escape sequence... */
var $_escapeCharacters;
-
- // Characters that should be escaped
+ /** ...and the valid escape sequences that can follow. */
var $_charsToEscape;
-
+
/**#@-*/
-
+
// }}}
// {{{ setEscapeCharacters()
-
+ /**
+ * Specifies each "character" that should be interpreted as the start of an
+ * escape sequence when it occurs immediately subsequent to a start
+ * delimiter. Each "character" may be greater than one actual character in
+ * length, and may optionally be specified by a REGEX-string - look-behind
+ * assertions on such regexes are not supported.
+ * @param Mixed Array of strings or single string.
+ */
function setEscapeCharacters ($chars)
{
$this->_escapeCharacters = (array) $chars;
}
-
+
// }}}
// {{{ setCharactersToEscape()
-
+ /**
+ * Specifies all escape sequences that are valid following any of the
+ * escape characters. Each escape sequence may be greater than one
+ * character in length and may be specified by a REGEX-string - look-behind
+ * assertions on such regexes are not supported.
+ * @param Mixed Array of strings or single string.
+ */
function setCharactersToEscape ($chars)
{
- $this->_charsToEscape = (array) $chars;
+ static $re_starter_c = 'REGEX';
+ static $re_starter_len_c = 5/*strlen($re_starter_c)*/;
+ $this->_charsToEscape = array();
+ /* Save a little time and processing by anchoring all regexes now,
+ * rather than each time geshi_whichsubstr() is called.
+ */
+ foreach ((array)$chars as $escSeq) {
+ if (strncmp($escSeq, $re_starter_c, $re_starter_len_c) == 0) {
+ $re = substr($escSeq, $re_starter_len_c);
+ $re = geshi_anchor_re($re);
+ $this->_charsToEscape[] = $re_starter_c.$re;
+ } else $this->_charsToEscape[] = $escSeq;
+ }
}
-
+
// }}}
+ // {{{ setDisallowEmpty()
+ /**
+ * Call this to specify whether to disallow empty characters - e.g. in C, ''
+ * is invalid. By default empty characters are allowed. The default
+ * parameter value of this function is true so e.g. in C's case this can be
+ * called simply as $context->setDisallowEmptyChars().
+ * @param boolean $value Defaults to true.
+ */
+ function setDisallowEmptyChars ($value = true)
+ {
+ $this->_disallowEmpty = $value;
+ }
+
+ // }}}
// {{{ getContextStartData()
/**
* GetContextStartData
- *
- * Overridden to check if this context should even start. If we can't find
- * a valid end-of-string character in the correct place this context should
- * not even start.
- *
+ *
+ * Overrides the parent method to check whether this context should even
+ * start. Checks for a complete character including start and end
+ * delimiters and valid contained character, which might be an escape
+ * sequence. Stores all data found so that it may be used by
+ * _getContextEndData() and _addParseData(), to avoid reparsing.
+ *
* @param string $code
* @param string $start_of_context
*/
function getContextStartData ($code, $start_of_context)
{
- geshi_dbg('GeSHiSingleCharContext::getContextStartData(' . $this->_contextName . ', ' . $start_of_context . ')');
-
+ geshi_dbg('GeSHiSingleCharContext::getContextStartData(' .
+ $this->_contextName . ', ' . $start_of_context . ')');
+
$offset = 0;
+ $data = null;
while (true) {
+ /* For retries, strip to just past the last failed start. */
+ if ($data != null) {
+ $code = substr($code, $data['pos'] + 1);
+ $offset += $data['pos'] + 1;
+ }
+
$data = parent::getContextStartData($code, $start_of_context);
-
- // First, if no match then bail
- if (-1 === $data['pos']) {
- return $data;
- }
-
- $first_position = $data['pos'];
- $first_length = $data['len'];
- $first_key = $data['key'];
- $first_dlm = $data['dlm'];
-
- // Check for empty character
- // WARN: claim here that delimiters are only one char long!
- if (in_array(substr($code, $first_position + 1, 1), $this->_contextDelimiters[$first_key][1])) {
- // Nothing wrong with this
+
+ /* First, if no match then bail */
+ if (-1 === $data['pos']) break;
+
+ /* Check for empty character */
+ $end_delim = geshi_whichsubstr($code, $this->_contextDelimiters[
+ $data['key']][1], $data['pos'] + $data['len'],
+ GESHI_WHICHSS_MAXIMAL|GESHI_WHICHSS_TRYREGEX);
+ if ($end_delim !== null) {
+ if (!$this->_disallowEmpty) {
+ $data['pos'] += $offset;
+ $this->_characterLen = 0;
+ $this->_endDelimiterLen = strlen($end_delim);
+ $this->_isEscapeSeq = false;
+ break;
+ } else {
+ /* Support a (hypothetical) syntax where empty characters
+ * are not permitted but where the end delimiter doubles as
+ * an escape character. */
+ $empty = true;
+ }
+ } else $empty = false;
+
+ /* Check for the start of an escape sequence */
+ $esc_start = geshi_whichsubstr($code, $this->_escapeCharacters,
+ $data['pos'] + $data['len'], GESHI_WHICHSS_MAXIMAL|
+ GESHI_WHICHSS_TRYREGEX);
+ $esc_len = strlen($esc_start);
+ if ($esc_start !== null) {
+ /* Check for a valid full escape sequence; allow regexes
+ * that match sequences of length > 1. Match the most
+ * inclusive char/regex. */
+ $start = $data['pos'] + $data['len'] + $esc_len;
+ $esc_seq = geshi_whichsubstr($code, $this->_charsToEscape,
+ $start, GESHI_WHICHSS_MAXIMAL|GESHI_WHICHSS_TRYREGEX|
+ GESHI_WHICHSS_SKIPANCHORINSERT);
+ if ($esc_seq === null) continue;
+ else $char_len = $esc_len + strlen($esc_seq);
+ } else if ($empty) continue;
+ else $char_len = 1; /* Possible single unescaped character */
+
+ $final_char_offset = $data['len'] + $char_len;
+
+ /* Check for an end delimiter and if found, return successfully */
+ $end_delim = geshi_whichsubstr($code, $this->_contextDelimiters[
+ $data['key']][1], $data['pos'] + $final_char_offset,
+ GESHI_WHICHSS_MAXIMAL|GESHI_WHICHSS_TRYREGEX);
+ if ($end_delim !== null) {
$data['pos'] += $offset;
- return $data;
+ $this->_characterLen = $char_len;
+ $this->_endDelimiterLen = strlen($end_delim);
+ $this->_isEscapeSeq = ($esc_start !== null);
+ break;
}
-
- // Check for single alone character
- $final_char_offset = (in_array(substr($code, $first_position + 1, 1), $this->_escapeCharacters))
- ? 3 : 2;
- if (in_array(substr($code, $first_position + $final_char_offset, 1),
- $this->_contextDelimiters[$first_key][1])) {
- $data['pos'] += $offset;
- return $data;
- }
-
-
- // End: strip to just past where the character failed to start and try again
- $code = substr($code, $first_position + 1);
- $offset += $first_position + 1;
}
-
- return array('pos' => $first_position, 'len' => $first_length,
- 'key' => $first_key, 'dlm' => $first_dlm);
+ return $data;
}
-
+
// }}}
// {{{ _getContextEndData()
-
+
/**
- * In this case we don't need to worry about much because we have made sure in
- * _getContextStartData that we are starting in the right place.
+ * In this case we don't need to worry about much because we have made sure
+ * in _getContextStartData that we are starting in the right place.
*/
- function _getContextEndData ($code, $context_open_key, $context_opener, $beginning_of_context)
+ function _getContextEndData ($code, $context_open_key, $context_opener,
+ $beginning_of_context)
{
- $pos = 1;
- $first_char = substr($code, 0, 1);
- if (in_array($first_char, $this->_escapeCharacters)) {
- $pos = 2;
- } elseif (in_array($first_char, $this->_contextDelimiters[$context_open_key][1])) {
- $pos = 0;
- }
- return array('pos' => $pos, 'len' => 1 /*see WARN above*/, 'dlm' => '');
+ return array('pos' => $this->_characterLen,
+ 'len' => $this->_endDelimiterLen,
+ 'dlm' => '');
}
-
+
// }}}
// {{{ _addParseData()
-
+
/**
* Overrides _addParseData to add escape characters also
*/
function _addParseData ($code, $first_char_of_next_context = '')
{
- geshi_dbg('GeSHiSingleCharContext::_addParseData(' . substr($code, 0, 15) . '...)');
- if (in_array(substr($code, 0, 1), $this->_escapeCharacters)) {
+ geshi_dbg('GeSHiSingleCharContext::_addParseData(' .
+ substr($code, 0, 15) . '...)');
+ if ($this->_isEscapeSeq) {
$this->_styler->addParseData($code, $this->_contextName . '/esc',
$this->_getExtraParseData(), $this->_complexFlag);
} else {
parent::_addParseData($code, $first_char_of_next_context);
}
}
-
+
// }}}
}
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshistringcontext.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshistringcontext.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/classes/class.geshistringcontext.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -54,115 +54,237 @@
/**#@-
* @access private
*/
- var $_escapeCharacters = array();
- // Characters that should be escaped
- var $_charsToEscape = array();
+ /**
+ * Escape character groups.
+ *
+ * @var array
+ */
+ var $_escapeGroups = array();
/**#@-*/
// }}}
- // {{{ setEscapeCharacters()
+ // {{{ addEscapeGroup()
/**
- * Sets the characters that are used to escape other characters in a string
+ * Adds an escape group to this string context.
+ *
+ * An escape group consists of a group of characters that are escape
+ * characters, and another group of characters or regexes that are
+ * the characters to escape. You can also specify a context name for
+ * the escaped characters.
+ *
+ * The escape characters MUST be one character in length, and are
+ * automatically assumed to escape themselves.
+ *
+ * @param mixed $escape_characters The characters that escape others
+ * @param mixed $characters_to_escape The characters/regexes that are
+ * escaped
+ * @param string $context_name A name for the escaped characters
*/
- function setEscapeCharacters ($chars)
+ function addEscapeGroup ($escape_characters,
+ $characters_to_escape = array(), $context_name = 'esc')
{
- $this->_escapeCharacters = (array) $chars;
+ // Sanity checking
+ $escape_characters = (array) $escape_characters;
+ $characters_to_escape = (array) $characters_to_escape;
+ foreach ($escape_characters as $char) {
+ if (strlen($char) != 1) {
+ trigger_error('GeSHiStringContext::addEscapeGroup(): malformed'
+ . ' language file: cannot have escape characters that are'
+ . ' longer than one character in length');
+ }
+ if (!in_array($char, $characters_to_escape)) {
+ $characters_to_escape[] = $char;
+ }
+ }
+
+ $this->_escapeGroups[] = array(
+ $escape_characters,
+ $characters_to_escape,
+ $context_name
+ );
}
// }}}
- // {{{ setCharactersToEscape()
+ // {{{ _getContextEndData()
- function setCharactersToEscape ($chars)
- {
- $this->_charsToEscape = (array) $chars;
- }
-
- // }}}
-
/**
- * GetContextEndData
+ * Finds the end of a string context, taking the escape characters into
+ * account.
+ *
+ * @param string $code The code to look for the end of the
+ * context in
+ * @param int $context_open_key The key in the array of delimiters
+ * which corresponds to the opener
+ * @param string $context_opener The actual opener for the string
*/
function _getContextEndData ($code, $context_open_key, $context_opener)
{
- geshi_dbg('GeSHiStringContext::_getContextEndData(' . $this->_contextName . ', ' . $context_open_key . ', ' . $context_opener . ')');
+ geshi_dbg('GeSHiStringContext::_getContextEndData('
+ . $this->_contextName . ')');
$this->_lastOpener = $context_opener;
$ender_data = array();
foreach ($this->_contextDelimiters[$context_open_key][1] as $ender) {
- geshi_dbg(' Checking ender: ' . $ender);
-
// Prepare ender regexes if needed
$ender = $this->_substitutePlaceholders($ender);
- geshi_dbg(' ender after substitution: ' . $ender);
+ geshi_dbg(' Checking ender: ' . str_replace("\n", '\n', $ender));
- $pos = 0;
+ $tmp_str = $code;
+ $current_pos = 0;
+
while (true) {
- $pos = geshi_get_position($code, $ender, $pos);
- if (false === $pos) {
+ geshi_dbg("@btop of loop; current_pos = $current_pos; str="
+ . substr($tmp_str, 0, 10));
+ $pos_data = geshi_get_position($tmp_str, $ender);
+ if (false === $pos_data['pos']) {
+ geshi_dbg("could not find ender $ender in string "
+ . substr($tmp_str, 0, 10));
break;
}
- $len = $pos['len'];
- $pos = $pos['pos'];
-
- $possible_string = substr($code, 0, $pos);
- geshi_dbg(' String might be: ' . $possible_string);
-
- $not_escaped = true;
- if ($this->_escapeCharacters) {
- foreach ($this->_escapeCharacters as $escape_char) {
- // remove escaped escape characters
- $possible_string = str_replace($escape_char . $escape_char, '', $possible_string);
- }
-
- geshi_dbg(' String with double escapes removed: ' . $possible_string);
+ geshi_dbg("found ender $ender at position " . $pos_data['pos']);
- foreach ($this->_escapeCharacters as $escape_char) {
- if (substr($possible_string, -1) == $escape_char) {
- $not_escaped = false;
- break;
+ // While we may have found an ender, it might be escaped.
+ // Finding out for sure whether it is escaped is harder than
+ // it may initially seem - we have to check each previous
+ // character to see if it escapes the one after it, and flip
+ // a flag which detects whether the initial character is
+ // escaped, or whether the character before the initial
+ // character is escaped (and thus the ender we found is the
+ // real thing).
+ $i = $pos_data['pos'] - 1;
+ if ($i >= 0) {
+ $current_char = substr($tmp_str, $i, 1);
+ $after_char = substr($tmp_str, $i + 1, 1);
+ geshi_dbg("checking char $current_char to see if it"
+ . " escapes the char $after_char");
+ if ($this->_charEscapesChar($current_char, $after_char)) {
+ geshi_dbg(" it does! Might not have found the ender");
+ $found_ender = true;
+ geshi_dbg('checking whether ' . substr($tmp_str, $i, 1)
+ . ' escapes ' . substr($tmp_str, $i + 1, 1));
+ while (($i == 0 && $this->_isEscapeChar(substr($tmp_str, $i, 1))) ||
+ $i > 0
+ && $this->_charEscapesChar(substr($tmp_str, $i, 1),
+ substr($tmp_str, $i + 1, 1))) {
+ $found_ender = !$found_ender;
+ if (0 == $i) {
+ geshi_dbg('reached start of string and char is escape');
+ } else {
+ geshi_dbg(substr($tmp_str, $i, 1) . ' escapes '
+ . substr($tmp_str, $i + 1, 1) . ': found_ender='
+ . $found_ender);
+ }
+ --$i;
}
-
- if ($escape_char == $ender
- && substr($code, $pos + 1, 1) == $escape_char) {
- // We have encountered the case where a string
- // has its own ender as a delimiter and as an
- // escape character
- $not_escaped = false;
- break;
+ geshi_dbg('finished: found_ender=' . $found_ender);
+ if (!$found_ender) {
+ geshi_dbg('we did NOT find ender, it was escaped');
+ $current_pos += $pos_data['pos'] + 1;
+ $tmp_str = substr($tmp_str, $pos_data['pos'] + 1);
+ continue;
}
+ geshi_dbg('Found ender since the last char is escaped');
}
+ else {
+ geshi_dbg(" does not seem to escape the next char");
+ }
}
-
- if ($not_escaped) {
- // We may have found the correct ender. If we haven't, then this string
- // never ends and we will set the end position to the length of the code
- // substr($code, $pos, 1) == $ender
- $endpos = geshi_get_position($code, $ender, $pos);
- geshi_dbg(' position of ender: ' . $endpos['pos']);
- $pos = (false !== $pos && $endpos['pos'] === $pos) ? $pos : strlen($code);
- if (!$ender_data || $ender_data['pos'] > $pos) {
- $ender_data = array('pos' => $pos, 'len' => $len, 'dlm' => $ender);
+
+ if ($pos_data['pos'] != strlen($tmp_str)
+ && $this->_charEscapesChar($ender,
+ substr($tmp_str, $pos_data['pos'] + 1, 1))) {
+ // We did not find the ender
+ geshi_dbg('ender is escaping the next char - '
+ . substr($tmp_str, $pos_data['pos'] + 1, 1));
+ $current_pos += $pos_data['pos'] + 1 + $pos_data['len'];
+ $tmp_str = substr($tmp_str, $pos_data['pos'] + 1
+ + $pos_data['len']);
+ continue;
+ }
+ else {
+ geshi_dbg("Not escaped or escaping: Found at position "
+ . $pos_data['pos']);
+ if (!$ender_data || $pos_data['pos'] < $ender_data['pos']) {
+ geshi_dbg('earliest');
+ $ender_data['pos'] = $pos_data['pos'] + $current_pos;
+ $ender_data['dlm'] = $ender;
+ $ender_data['len'] = $pos_data['len'];
}
+
break;
}
-
- // else, start further up
- ++$pos;
}
}
geshi_dbg('Ender data: ' . print_r($ender_data, true));
return ($ender_data) ? $ender_data : false;
}
+ // }}}
+ // {{{ _charEscapesChar()
+
/**
- * Overrides addParseData to add escape characters also
+ * Returns true if $escape_char escapes $char_to_escape.
+ *
+ * @param string $escape_char The escape character
+ * @param string $char_to_escape The character being escaped
+ * @return boolean
*/
+ function _charEscapesChar ($escape_char, $char_to_escape)
+ {
+ static $result_table = array();
+ if (isset($result_table[$escape_char][$char_to_escape])) {
+ return $result_table[$escape_char][$char_to_escape];
+ }
+
+ foreach ($this->_escapeGroups as $group) {
+ if (in_array($escape_char, $group[0])) {
+ return $result_table[$escape_char][$char_to_escape]
+ = in_array($char_to_escape, $group[1]);
+ }
+ }
+
+ return $result_table[$escape_char][$char_to_escape] = false;
+ }
+
+ // }}}
+ // {{{ _isEscapeChar()
+
+ /**
+ * Returns true if $escape_char is an escape character in any group.
+ *
+ * @param string $escape_char The escape character
+ * @return boolean
+ */
+ function _isEscapeChar ($escape_char)
+ {
+ static $result_table = array();
+ if (isset($result_table[$escape_char])) {
+ return $result_table[$escape_char];
+ }
+
+ foreach ($this->_escapeGroups as $group) {
+ if (in_array($escape_char, $group[0])) {
+ return $result_table[$escape_char] = true;
+ }
+ }
+ return $result_table[$escape_char] = false;
+ }
+
+ // }}}
+ // {{{ _addParseData()
+
+ /**
+ * Overrides addParseData to add escape characters also.
+ *
+ * @param string $code
+ * @param string $first_char_of_next_context
+ */
function _addParseData ($code, $first_char_of_next_context = '')
{
- geshi_dbg('GeSHiStringContext::_addParseData(' . substr($code, 0, 15) . '...)');
+ geshi_dbg('GeSHiStringContext::_addParseData(' . substr($code, 0, 15));
$length = strlen($code);
$string = '';
@@ -171,22 +293,30 @@
geshi_dbg('Char: ' . $char);
$skip = false;
- foreach ($this->_escapeCharacters as $escape_char) {
- $len = 1;
- if ($char == $escape_char && (false !== ($len = $this->_shouldBeEscaped(substr($code, $i + 1))))) {
- geshi_dbg('Match: len = ' . $len);
- if ($string) {
- $this->_styler->addParseData($string, $this->_contextName,
- $this->_getExtraParseData(), $this->_complexFlag);
- $string = '';
+ foreach ($this->_escapeGroups as $group) {
+ foreach ($group[0] as $escape_char) {
+ $len = 1;
+ if ($char == $escape_char
+ && (false !== ($len = $this->_shouldBeEscaped(
+ substr($code, $i + 1), $group[1])))) {
+ geshi_dbg('Match: len = ' . $len);
+ if ($string) {
+ $this->_styler->addParseData($string,
+ $this->_contextName,
+ $this->_getExtraParseData(),
+ $this->_complexFlag);
+ $string = '';
+ }
+
+ $this->_styler->addParseData($escape_char
+ . substr($code, $i + 1, $len),
+ "$this->_contextName/$group[2]",
+ $this->_getExtraParseData(),
+ $this->_complexFlag);
+ $i += $len;
+ $skip = true;
+ break;
}
- // Needs a better name than /esc
- $this->_styler->addParseData($escape_char . substr($code, $i + 1, $len), $this->_contextName . '/esc',
- $this->_getExtraParseData(), $this->_complexFlag);
- // FastForward
- $i += $len;
- $skip = true;
- break;
}
}
@@ -195,10 +325,14 @@
}
}
if ($string) {
- $this->_styler->addParseData($string, $this->_contextName, $this->_getExtraParseData(),
+ $this->_styler->addParseData($string, $this->_contextName,
+ $this->_getExtraParseData(),
$this->_complexFlag);
}
- }
+ }
+
+ // }}}
+ // {{{ _shouldBeEscaped()
/**
* Checks whether the character(s) at the start of the parameter string are
@@ -207,16 +341,17 @@
* @param string The string to check the beginning of for escape characters
* @return int|false The length of the escape character sequence, else false
*/
- function _shouldBeEscaped ($code)
+ function _shouldBeEscaped ($code, $chars_to_escape)
{
geshi_dbg('Checking: ' . substr($code, 0, 15));
- foreach ($this->_charsToEscape as $match) {
+ foreach ($chars_to_escape as $match) {
if ('REGEX' != substr($match, 0, 5)) {
geshi_dbg('Test: ' . $match);
if (substr($code, 0, 1) == $match) {
return 1;
}
- } else {
+ }
+ else {
geshi_dbg(' Testing via regex: ' . $match . '... ', false);
$data = geshi_get_position($code, $match, 0);
if (0 === $data['pos']) {
@@ -229,6 +364,9 @@
// No matches...
return false;
}
+
+ // }}}
+
}
?>
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/functions.geshi.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/functions.geshi.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/functions.geshi.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -6,10 +6,10 @@
* Author: Nigel McNie
* E-mail: ni...@ge...
* </pre>
- *
+ *
* For information on how to use GeSHi, please consult the documentation
* found in the docs/ directory, or online at http://geshi.org/docs/
- *
+ *
* This program is part of GeSHi.
*
* This program is free software; you can redistribute it and/or modify
@@ -21,7 +21,7 @@
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
- *
+ *
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
@@ -32,7 +32,7 @@
* @license http://www.gnu.org/copyleft/gpl.html GNU GPL
* @copyright (C) 2004 - 2006 Nigel McNie
* @version $Id$
- *
+ *
*/
$GLOBALS['geshi_dbg'] = false;
@@ -52,7 +52,7 @@
/**
* Handles debugging by printing a message according to current debug level,
* mask of context and other things.
- *
+ *
* @param string The message to print out
* @param int The context in which this message is to be printed out in - see
* the GESHI_DBG_* constants
@@ -78,15 +78,15 @@
case '@b':
$start = '<span style="font-weight:bold;">';
break;
-
+
case '@i':
$start = '<span style="font-style:italic;">';
break;
-
+
case '@o':
$start = '<span style="color:green;background-color:#efe;border:1px solid #393;">';
break;
-
+
case '@w':
$start = '<span style="color:#660;background-color:#ffe;border:1px solid #993;">';
break;
@@ -94,22 +94,22 @@
case '@e':
$start = '<span style="color:red;background-color:#fee;border:1px solid #933;">';
break;
-
+
default:
$end = '';
}
-
+
if (preg_match('#(.*?)::(.*?)\((.*?)\)#si', $message)) {
$start = '<span style="font-weight:bold;">';
$end = '</span>';
}
-
+
if (preg_match('#^@[a-z]#', $message)) {
$message = substr($message, 2);
}
echo $start . htmlspecialchars(str_replace("\n", '', $message)) . $end;
if ($add_nl) echo "\n";
- }
+ }
}
/**
@@ -157,56 +157,148 @@
}
/**
- * Drop-in replacement for strpos and stripos. Also can handle regular expression
+ * A replacement for strpos and stripos that can also handle regular expression
* string positions.
- *
+ *
* @param string The string in which to search for the $needle
- * @param string The string to search for. If this string starts with "REGEX" then
- * a regular expression search is performed.
- * @param int The offset in the string in which to start searching
+ * @param string The string to search for. If this string starts with "REGEX"
+ * then a regular expression search is performed.
+ * @param int The offset in the string in which to start searching. Look-
+ * behind assertions in a regex that refer to characters prior to
+ * this point will not match.
* @param boolean Whether the search is case sensitive or not
- * @param boolean Whether the match table is needed (almost never, and it makes things slower)
+ * @param boolean Whether the match table is needed (almost never, and it makes
+ * things slower, but probably not noticeably).
* @return array An array of data:
* <pre> 'pos' => position in string of needle,
* 'len' => length of match
- * 'tab' => a table of the stuff matched in brackets for a regular expression</pre>
+ * 'tab' => a tabular array containing the parenthesised sub-matches of a
+ * regular expression. [0] is the complete match, [1] the first parenthesized
+ * sub-match, and so on.
+ * </pre>
* @access private
*/
-function geshi_get_position ($haystack, $needle, $offset = 0, $case_sensitive = false, $need_table = false)
+function geshi_get_position ($haystack, $needle, $offset = 0,
+ $case_sensitive = false, $need_table = false)
{
if ('REGEX' != substr($needle, 0, 5)) {
if (!$case_sensitive) {
- return array('pos' => stripos($haystack, $needle, $offset), 'len' => strlen($needle));
+ // @todo [blocking 1.1.4] This line is marked by BenBE as
+ // one of the slowest. If you don't have PHP5 then this is
+ // done manually, the function for it should probably be
+ // cleaned up a bit.
+ return array('pos' => stripos($haystack, $needle, $offset),
+ 'len' => strlen($needle));
} else {
- return array('pos' => strpos($haystack, $needle, $offset), 'len' => strlen($needle));
+ return array('pos' => strpos($haystack, $needle, $offset),
+ 'len' => strlen($needle));
}
}
-
+
$regex = substr($needle, 5);
+ $haystack_offset = substr($haystack, $offset);
+ $table = array();
+ $length = 0;
+ $flags = PREG_SPLIT_OFFSET_CAPTURE;
+ if ($need_table) $flags |= PREG_SPLIT_DELIM_CAPTURE;
+ // @todo [blocking 1.1.4] This line is marked by BenBE as one of the
+ // slowest. There's not too much that can be done to speed up the line
+ // per se, but possibly something similar to the "here's a character
+ // you can check to see if this is ever going to pass" might be useful.
+ $splits = preg_split($regex, $haystack_offset, 2, $flags);
+ if (count($splits) > 1) {
+ $first = array_shift($splits);
+ $last = array_pop($splits);
+ $pos = strlen($first[0]);
+ $length = $last[1] - $pos;
+ $pos += $offset;
+ if ($need_table) {
+ $table[] = substr($haystack_offset, $pos, $length);
+ foreach ($splits as $match) $table[] = $match[0];
+ }
+ } else $pos = false;
+ return array('pos' => $pos, 'len' => $length, 'tab' => $table);
+}
- // Get the location of the first match of the regular expression
- $foo = microtime();
- $foo_len = strlen($foo);
- $len = strlen($haystack);
- $str = preg_replace($regex, $foo, $haystack, 1);
- $length = $len - (strlen($str) - $foo_len);
+/**
+ * Which, if any, of the strings in the array $substrs occurs at offset $offset
+ * in the string $str?
+ * If $flags contains GESHI_WHICHSS_MAXIMAL, then the largest of multiple
+ * matches will be returned, otherwise and by default: the first encountered.
+ * If $flags contains GESHI_WHICHSS_CASEINSENSITIVE then the comparison will be
+ * case-insensitive; otherwise and by default it will be case-sensitive.
+ * If $flags contains GESHI_WHICHSS_TRYREGEX then the remaining portion of any
+ * string in $substrs that starts with 'REGEX' will be treated as a (Perl-
+ * compatible) regular expression to match, anchored to the start of the string
+ * at $offset. Look-behind assertions that refer to parts of the string prior
+ * to $offset will not work. If $flags contains GESHI_WHICHSS_SKIPANCHORINSERT
+ * then the anchor insertion on each regex in $substr will not be performed -
+ * it will be assumed to have already been performed but in any case only
+ * matches at the start of the string will ever be returned.
+ * @return Null if no match is found, otherwise the matching substring, with
+ * case as in the $substrs element rather than the matching portion of $str.
+ */
+define('GESHI_WHICHSS_MAXIMAL', 1);
+define('GESHI_WHICHSS_CASEINSENSITIVE', 2);
+define('GESHI_WHICHSS_TRYREGEX', 4);
+define('GESHI_WHICHSS_SKIPANCHORINSERT', 8);
+function geshi_whichsubstr($str, $substrs, $offset = 0, $flags = 0) {
+ /* Constants */
+ static $re_starter_c = 'REGEX';
+ static $re_starter_len_c = 5/*strlen($re_starter_c)*/;
- // Return match table if requested
- if ($need_table) {
- $matches = array();
- preg_match_all($regex, $haystack, $matches);
- $i = 0;
- $table = array();
- foreach ( $matches as $match ) {
- $table[$i++] = (isset($match[0])) ? $match[0] : null;
+ $ret = null;
+ $max_len = -1;
+ foreach ($substrs as $substr) {
+ if (($flags & GESHI_WHICHSS_TRYREGEX) &&
+ strncmp($substr,$re_starter_c,$re_starter_len_c)==0) {
+ $re = substr($substr, $re_starter_len_c);
+ if (!($flags & GESHI_WHICHSS_SKIPANCHORINSERT)) {
+ $re = geshi_anchor_re($re);
+ }
+ $haystack = $offset > 0 ? substr($str, $offset) : $str;
+ $match = preg_match($re, $haystack, $matches, PREG_OFFSET_CAPTURE) ?
+ $matches[0][0] : null;
+ $len = strlen($match);
+ /* This code is reached only if GESHI_WHICHSS_SKIPANCHORINSERT was
+ * specified without a pre-existing anchor and with a match that
+ * started beyond $offset.
+ */
+ if ($match !== null && $matches[0][1]) $len = $match = null;
+ } else {
+ $len = strlen($substr);
+ if (!($flags & GESHI_WHICHSS_CASEINSENSITIVE)) {
+ $match = substr($str,$offset,$len) == $substr ? $substr : null;
+ } else if (strcasecmp(substr($str, $offset, $len), $substr) == 0) {
+ $match = $substr;
+ } else $match = null;
}
- } else {
- $table = array();
+ if ($match !== null) {
+ if (!($flags & GESHI_WHICHSS_MAXIMAL)) {
+ $ret = $match;
+ break;
+ } else if ($len > $max_len) {
+ $ret = $match;
+ $max_len = $len;
+ }
+ }
}
- return array('pos' => strpos($str, $foo), 'len' => $length, 'tab' => $table);
+ return $ret;
}
/**
+ * Safely inserts an anchor into the regex $regex so that it only matches at the
+ * start of the searched string.
+ * @return string The regex with anchor inserted.
+ */
+function geshi_anchor_re($regex) {
+ $delim = $regex{0};
+ $endPos = strrpos($regex, $delim);
+ $endChars = substr($regex, $endPos);
+ return "$delim^(".substr($regex, 1, $endPos - 1).')'.$endChars;
+}
+
+/**
* @todo [blocking 1.1.5] Octal/hexadecimal numbers are common, so should have functions
* for those, and make sure that integers/doubles do not collide
* @access private
@@ -236,9 +328,9 @@
//
/**
* Replace stripos()
- *
+ *
* This function lifted from the PHP_Compat PEAR package, and optimised
- *
+ *
* @author Aidan Lister <ai...@ph...>, Nigel McNie <ni...@ge...>
* @version $Revision$
* @access private
@@ -267,7 +359,7 @@
/**
* Returns the GeSHi_Styler object used to help with parsing
- *
+ *
* @param boolean $force_new If true, forces the creation of
* a new GeSHi_Parser object
* @return GeSHi_Styler
Copied: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/NOTES (from rev 1166, tags/RELEASE_1_1_2_ALPHA3/geshi-src/geshi/languages/c/NOTES)
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/NOTES (rev 0)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/NOTES 2008-05-18 15:33:07 UTC (rev 1167)
@@ -0,0 +1,87 @@
+Here are several notes on C highlighting as originally contained as extended
+comments within c.php. Mostly this relates to preprocessor-context
+highlighting and the situations in which the C parser function
+GeSHiCCodeParser::parseToken() adjusts it.
+
+== (Un)Highlighted keywords in the preprocessor context ==
+
+It might seem questionable at first whether declarator/type/qualifier keywords,
+standard functions and standard macros or objects will ever occur, thus
+requiring highlighting, within some preprocessor directives - namely #(el)if,
+#ifdef, #ifndef and #undef. They can and do occur in practice though because
+these directives can be used to test whether at preprocessor level the keyword,
+type or function in question has been subverted (or for a function, whether
+it's been legitimately defined as a macro), and/or to undo or change that
+subversion; for #if/#elif, sizeof should be highlighted in any case - it's been
+categorised as a standard function for GeSHi's purposes.
+
+For #(el)if, a type might also appear as the subject of sizeof.
+
+It's also debatable whether such tokens should be highlighted within #error and
+#pragma directives - it seems most appropriate that they are not, because within
+those directives their occurrence can be likened to their appearance within a
+comment. GeSHiCCodeParser::parseToken() therefore adjusts those contexts;
+their highlighting when the parser is disabled is tolerable as a minor glitch.
+
+It's less debatable that within a #include filename, these keywords should not
+be highlighted. That's handled in GeSHiCCodeParser::parseToken() for <>
+includes - quoted includes are already protected by the string_literal context
+(which parseToken() reclassifies). It's borderline tolerable that this
+incorrect highlighting will appear when the parser is disabled.
+
+Within a #include where the filename is specified by a macro, the only keywords
+that should be highlighted out of the list at the top of this section are:
+standard macros (because they might be used in a stringising macro "call"), any
+standard functions that are implementable as macros (for the same reason),
+"sizeof" (because it might be used to generate an argument for a macro "call")
+and types (but not qualifiers) where they appear as the subject of sizeof. The
+remainder have no meaning in preprocessor macro-"call" context. Separating out
+"implementable-as-a-macro" from the other standard functions is a longer-term
+future task to complete alongside comprehensively filling out what's missing
+from the keyword lists. Separating qualifiers from types is another task to
+consider. To start with, GeSHiCCodeParser::parseToken() disables highlighting
+for the context 'declarator-keyword' within #include:s where the filename is
+specified by a macro, and /all/ highlighting is disabled for the macro name
+itself - i.e. highlighting applies only to macro arguments.
+
+The same reasoning of the above paragraph can be applied to the #line directive
+where its "arguments" are specified by a macro: GeSHiCCodeParser::parseToken()
+similarly disables highlighting in that situation.
+
+== Symbols in C preprocessor directives ==
+
+Not all of the symbols added by the call:
+ $context->addSymbolGroup(geshi_c_get_standard_symbols(),
+ 'c/c/preprocessor/symbol');
+have meaning for all preprocessor directives and in some directives they are
+illegal. This GeSHi C module assumes well-formed input code so illegal
+occurrences need not concern it.
+
+In #(el)if directives, any symbol except the semicolon can legally occur.
+At first it might seem that & has no place either because at preprocessing stage
+no objects exist to take an address of, but & can also act as a bitwise
+operator or be part of the logical && operator. Due to the lack of objects it
+might also at first seem that [] has no use, however it can be applied to
+string literals for esoteric uses in a preprocessor constant such as this
+expression equating to 1:
+"abcd"[1] == 'b'
+A semicolon though is only used to end single statements in code - this can't
+apply to a constant preprocessor expression.
+
+In #include and #line directives, the header filename and new effective source
+file name (respectively) may be specified by a macro. A macro may take a
+constant preprocessor expression as an argument, so by this reasoning it can be
+seen that within #include and #line directives the same set of symbols can
+occur as within an #(el)if directive - namely, anything except a semicolon.
+
+In a #define, even a semicolon can occur because the macro can substitute for
+code.
+
+#ifdef, #ifndef, #undef, #endif and #else do not allow any symbol except by
+proxy for comments and line continuation slashes.
+
+Likewise for #error and #pragma except that any symbol could occur as part of
+the subsequent (unquoted) freeform text. These should not be highlighted, and
+thus GeSHiCCodeParser::parseToken() recontextualises them so that they aren't
+highlighted. Their highlighting when the parser is disabled is tolerable as a
+minor glitch.
Modified: branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/c.php
===================================================================
--- branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/c.php 2008-05-18 15:24:09 UTC (rev 1166)
+++ branches/RELEASE_1_1_X_DEVEL/geshi-src/geshi/languages/c/c.php 2008-05-18 15:33:07 UTC (rev 1167)
@@ -54,33 +54,34 @@
$context->addChild('multi_comment');
$context->addChild('single_comment');
$context->addChild('string_literal', 'string');
+ $context->addChild('widestring_literal', 'string');
$context->addChild('character_constant', 'singlechar');
+ $context->addChild('widecharacter_constant', 'singlechar');
$context->addChild('preprocessor', 'code');
-
+
$context->addKeywordGroup(geshi_c_get_ctlflow_keywords(),
'ctlflow-keyword', true, geshi_c_get_ctlflow_keywords_url());
$context->addKeywordGroup(geshi_c_get_declarator_keywords(),
'declarator-keyword', true, geshi_c_get_declarator_keywords_url());
-
+
$context->addKeywordGroup(geshi_c_get_types_and_qualifiers(),
'typeorqualifier', true, geshi_c_get_types_and_qualifiers_url());
-
+
$context->addKeywordGroup(geshi_c_get_standard_functions(),
'stdfunction', true, geshi_c_get_standard_functions_url());
-
+
$context->addKeywordGroup(geshi_c_get_standard_macros_and_objects(),
'stdmacroorobject', true, geshi_c_get_standard_macros_and_objects_url());
-
+
$context->addSymbolGroup(geshi_c_get_standard_symbols(), 'symbol');
-
+
$context->useStandardIntegers();
$context->useStandardDoubles(array('chars_after_number' => array('f','l')));
-
+
$context->addObjectSplitter(geshi_c_get_structure_access_symbols(),
'member', 'symbol');
$context->setComplexFlag(GESHI_COMPLEX_TOKENISE);
-
}
function geshi_c_c_multi_comment (&$context)
@@ -91,45 +92,60 @@
function geshi_c_c_single_comment (&$context)
{
- $context->addDelimiters('//', 'REGEX#(?<!\\\)\n#');
+ $context->addDelimiters('//', "\n");
$context->setComplexFlag(GESHI_COMPLEX_PASSALL);
- // without this, detection of a following preprocessor directive is
- // inhibited [due to changes this might no longer apply]
+ /* Without this, and when the comment occurs at the end of a preprocessor
+ * directive, any immediately subsequent preprocessor directive is treated
+ * as a continuation of the first one. */
$context->parseDelimiters(GESHI_CHILD_PARSE_LEFT);
}
+/* A (wide)string literal may be continued to the next line through the use of a
+ * trailing \ but otherwise multiline strings are illegal. This code doesn't
+ * attempt to mark erroroneous multiline strings, and slash-continuation is
+ * handled generically in GeSHiCCodeParser::parseToken(). This code does
+ * terminate strings on newlines though due to the legality of the appearance
+ * of unmatched double quote marks in #error and #pragma directives.
+ * GeSHiCCodeParser::parseToken() later unhighlights such unterminated strings
+ * but they can't be allowed to continue over the line otherwise the
+ * #error/#pragma directive will be incorrectly continued over multiple lines.
+ * prior to GeSHiCCodeParser receiving it.
+ */
function geshi_c_c_string_literal (&$context)
{
- /*
- * A string literal may be continued to the next line with a trailing \ but
- * otherwise multiline strings are illegal; we don't attempt to mark that
- * error here though.
- */
- $context->addDelimiters('"', '"');
-
- $context->setEscapeCharacters('\\');
- /** @todo string literals and character constants may be immediately
- * preceded by a capital L to indicate a wide-character constant and it
- * would be nice to include that in the highlighting.
- */
- $context->setCharactersToEscape(array("'", '?', 'a', 'b', 'f',
- 'v', 'n', 'r', 't', 'REGEX#[0-7]{1,3}#',
- 'REGEX#x[0-9a-f]{1,}#i', '\\', '"'));
+ geshi_c_base_string($context, '"', array('"', 'REGEX#(?=\n)#'), false);
}
-
+function geshi_c_c_widestring_literal (&$context)
+{
+ geshi_c_base_string($context, 'L"', array('"', 'REGEX#(?=\n)#'), true);
+}
function geshi_c_c_character_constant (&$context)
{
- $context->addDelimiters("'", "'");
+ geshi_c_base_singlechar($context, "'", "'", false);
+ $context->setDisallowEmptyChars();
+}
+function geshi_c_c_widecharacter_constant (&$context)
+{
+ geshi_c_base_singlechar($context, "L'", "'", true);
+ $context->setDisallowEmptyChars();
+}
- $context->setEscapeCharacters('\\');
+function geshi_c_base_string (&$context, $delim_start, $delim_end, $delim_cs) {
+ $context->addDelimiters($delim_start, $delim_end, $delim_cs);
+ $context->addEscapeGroup('\\', array("'", '"', '?', '\\', 'a', 'b', 'f',
+ 'n', 'r', 't', 'v', 'REGEX#([0-7]{1,3}|x[0-9a-f]{1,})#i'));
+ $context->setComplexFlag(GESHI_COMPLEX_PASSALL);
+}
- /** @todo same todo as for geshi_c_c_string_literal(). */
- $context->setCharactersToEscape(array("'", '?', 'a', 'b', 'f',
- 'v', 'n', 'r', 't', 'REGEX#[0-7]{1,3}#',
- 'REGEX#x[0-9a-f]{1,}#i', '\\', '"'));
+function geshi_c_base_singlechar (&$context, $delim_start, $delim_end, $delim_cs) {
+ $context->addDelimiters($delim_start, $delim_end, $delim_cs);
+ $context->setEscapeCharacters('\\');
+ $context->setCharactersToEscape(array("'", '"', '?', '\\', 'a', 'b', 'f',
+ 'n', 'r', 't', 'v', 'REGEX#([0-7]{1,3}|x[0-9a-f]{1,})#i'));
+ $context->setComplexFlag(GESHI_COMPLEX_PASSALL);
}
-/**
+/*
* Duplicate these functions for the preprocessor simply so that they can have
* a different highlighting context.
*/
@@ -143,127 +159,60 @@
}
function geshi_c_c_preprocessor_string_literal (&$context)
{
- geshi_c_c_string_literal($context);
+ geshi_c_c_string_literal ($context);
}
+function geshi_c_c_preprocessor_widestring_literal (&$context)
+{
+ geshi_c_c_widestring_literal ($context);
+}
function geshi_c_c_preprocessor_character_constant (&$context)
{
geshi_c_c_character_constant ($context);
}
+function geshi_c_c_preprocessor_widecharacter_constant (&$context)
+{
+ geshi_c_c_widecharacter_constant ($context);
+}
function geshi_c_c_preprocessor (&$context)
{
- /**
- * A preprocessing directive beginning with a # must occur at the start
+ /* A preprocessing directive beginning with a # must occur at the start
* of a line, but may optionally be preceded by whitespace. The hash may
- * optionally be followed by whitespace in the same manner, after which
- * the actual directive keyword is specified. Finally though, a hash
- * without a following directive is allowed as a 'null directive'.
+ * optionally be followed by whitespace, after which the actual directive
+ * keyword is specified. Finally though, a hash without a following
+ * directive is allowed as a 'null directive'.
*
* There is also a single preprocessing directive (_Pragma) that follows
- * the same rules but is not preceded by a hash
+ * the same rules but that is not preceded by a hash
*
* The list of non-newline whitespace characters recognised by C and
- * used in the r.e. below is: [ \t\f\v]
- ...
[truncated message content] |