From 4ece066e7c05ae6c1e29c96784374f5d02aa3015 Mon Sep 17 00:00:00 2001 From: xue <> Date: Thu, 12 Jan 2006 23:01:44 +0000 Subject: Moved geshi to 3rdParty --- framework/3rdParty/geshi/docs/COPYING | 340 +++ framework/3rdParty/geshi/docs/README | 35 + framework/3rdParty/geshi/docs/THANKS | 87 + framework/3rdParty/geshi/geshi.php | 2648 +++++++++++++++++++++ framework/3rdParty/geshi/geshi/css.php | 178 ++ framework/3rdParty/geshi/geshi/html.php | 254 ++ framework/3rdParty/geshi/geshi/javascript.php | 146 ++ framework/3rdParty/geshi/geshi/php.php | 351 +++ framework/3rdParty/geshi/geshi/prado.php | 154 ++ framework/3rdParty/geshi/geshi/xml.php | 145 ++ framework/3rdParty/geshi/highlight.css | 96 + framework/3rdParty/readme.html | 34 + framework/Web/Services/TPageService.php | 13 + framework/Web/UI/TControl.php | 2 +- framework/Web/UI/WebControls/TTextHighlighter.php | 11 +- 15 files changed, 4489 insertions(+), 5 deletions(-) create mode 100644 framework/3rdParty/geshi/docs/COPYING create mode 100644 framework/3rdParty/geshi/docs/README create mode 100644 framework/3rdParty/geshi/docs/THANKS create mode 100644 framework/3rdParty/geshi/geshi.php create mode 100644 framework/3rdParty/geshi/geshi/css.php create mode 100644 framework/3rdParty/geshi/geshi/html.php create mode 100644 framework/3rdParty/geshi/geshi/javascript.php create mode 100644 framework/3rdParty/geshi/geshi/php.php create mode 100644 framework/3rdParty/geshi/geshi/prado.php create mode 100644 framework/3rdParty/geshi/geshi/xml.php create mode 100644 framework/3rdParty/geshi/highlight.css create mode 100644 framework/3rdParty/readme.html (limited to 'framework') diff --git a/framework/3rdParty/geshi/docs/COPYING b/framework/3rdParty/geshi/docs/COPYING new file mode 100644 index 00000000..5b6e7c66 --- /dev/null +++ b/framework/3rdParty/geshi/docs/COPYING @@ -0,0 +1,340 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, 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 or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +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 give any other recipients of the Program a copy of this License +along with the Program. + +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 Program or any portion +of it, thus forming a work based on the Program, 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) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +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 Program, 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 Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) 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; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, 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 executable. However, as a +special exception, the source code 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. + +If distribution of executable or 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 counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program 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. + + 5. 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 Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program 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 to +this License. + + 7. 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 Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program 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 Program. + +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. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program 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. + + 9. The Free Software Foundation may publish revised and/or new versions +of the 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 Program +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 Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, 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 + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "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 PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. 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 PROGRAM 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 PROGRAM (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 PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), 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 Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. 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 program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program 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 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + , 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/framework/3rdParty/geshi/docs/README b/framework/3rdParty/geshi/docs/README new file mode 100644 index 00000000..11857d5d --- /dev/null +++ b/framework/3rdParty/geshi/docs/README @@ -0,0 +1,35 @@ + + GeSHi - GEneric Syntax HIlighter + -------------------------------- + Version 1.0.7.4 + +Author: Nigel McNie +Email: nigel@geshi.org +GeSHi Website: http://qbnz.com/highlighter + +GeSHi is a generic syntax highlighter, written in PHP. You simply +input the source code you wish to highlight with the language you +wish to use, and the output will be a file syntax highlighted to +XHTML standards. + +For more information on how to use GeSHi, please consult the +documentation. If you got this readme from a GeSHi package, then +the documentation is available in the docs/ directory. Documentation +is also available at http://qbnz.com/highlighter/documentation.php + +If you think you've found a bug in GeSHi, contact me with a bug +report at nigel@geshi.org, or submit it to the bug tracker at +http://sourceforge.net/tracker/?group_id=114997&atid=670231. Be +aware that minor highlighting errors may well just be incorrect +language files, but if you do find something major please contact me. + +And if you're using GeSHi as a plugin/mod for some other software, +please tell me about it! It's worth a link to you, and I can give +you specialist help if you need it. + +GeSHi is free software, released under the GNU GPL. Please see the +COPYING file for more information. If you do modify this program, +please tell me about it! Perhaps you've made a good improvement that +I can learn from :) + + $Id: README,v 1.6 2005/10/22 07:52:59 oracleshinoda Exp $ diff --git a/framework/3rdParty/geshi/docs/THANKS b/framework/3rdParty/geshi/docs/THANKS new file mode 100644 index 00000000..540efbbe --- /dev/null +++ b/framework/3rdParty/geshi/docs/THANKS @@ -0,0 +1,87 @@ + + THANKS - List of credits for GeSHi + +I owe these people/groups my thanks for help with GeSHi. Thanks, guys! + +- Amit Gupta - Thanks for all that constructive criticism - it's + a great help for making GeSHi even better. And + thanks for the Wordpress plugin! (Anyone who is + interested in the plugin can visit: + http://blog.igeek.info/still-fresh/category/wp-plugins/igsyntax-hiliter/) +- Andreas Gohr - Thanks for language files and for using GeSHi for DokuWiki + (http://www.splitbrain.org/dokuwiki/wiki:dokuwiki). And thanks + for all your criticisms and for that stylesheet-maker code :). + Also, thanks for the UTF-8 patch. +- Andreas von Oettingen - Thanks for those great ideas! :) +- bbspliff - Thanks for pointing out that bug (pity I already + found it though ;)) +- Ben Keen - Thanks for the language files and pointing out some + ideas for future releases. Lookin' forward to seeing that + software soon! ;) +- Brian Cheesman - Thanks for using GeSHi in phpCvsView, and for the suggestion about + extension => language lookup +- Christian Weiske - Thanks for the inspiration for creating advanced regexp + highlighting :D +- David Gartner - Thanks for using GeSHi in net2ftp, and for the idea about a load_from_file + method +- forum.qbasicnews.com - Thanks for putting up with the crappy versions + that I "forced" on you guys before ;) +- Jack Lloyd - Thanks for pointing out the versioning and method CSS bugs, and giving + me the extra C/C++ keywords +- Karim Scheik - Thanks for the php5 support report +- Marcin Gryszkalis - Thanks for those links for C, Java, Perl +- M. Uli Kusterer - Thanks for the idea about URL case conversion +- Roberto Armellin - Thanks for pointing out some flaws in GeSHi (that will be solved + in 1.2 guaranteed) +- Sterling Christensen - Thanks for those links to language specs +- Tux - Thanks for making all those language files :D +- zbw - Thanks for proving a phpBB port was possible + +PEOPE WHO MADE LANGUAGE FILES + +- Actionscript Steffen Krause (french translation by NikO) +- Ada Tux +- Apache Tux +- Applescript Stephan Klimek +- ASM Tux +- ASP Amit Gupta +- Bash Andreas Gohr +- BlitzBasic Pŕdraig O`Connel +- C++ Dennis Bayer, M. Uli Kusterer +- C# Alan Juden +- C for Macs M. Uli Kusterer +- CADDCL Roberto Rossi +- CadLisp Roberto Rossi +- Delphi Járja Norbert +- Div Gabriel Lorenzo +- DOS Alessandro Staltari +- Eiffel Zoran Simic +- FreeBasic Roberto Rossi +- GML José Jorge Enríquez Rodríguez +- Ini Deguix +- Inno Thomas Klinger +- Javascript Ben Keen +- Lisp Roberto Rossi +- Lua Roberto Rossi +- MPASM Bakalex +- MySQL Carl Fürstenberg +- NSIS Tux (updated by Deguix) +- Objective C M. Uli Kusterer +- Ocaml Flaie +- Ocaml-brief Flaie +- OpenOffice.org BASIC Roberto Rossi +- Oracle 8 Guy Wicks +- Pascal Tux +- Perl Andreas Gohr, Ben Keen +- Python Roberto Rossi +- Ruby Amit Gupta +- SDLBasic Roberto Rossi +- Scheme Jon Raphaelson +- Smarty Alan Juden +- VB.NET Alan Juden +- VisualFoxPro Roberto Armellin + +Do you want your name in here? Help me out! Make a language file, or suggest a new +feature, or make a plugin for GeSHi for some other software, then tell me about it! + + $Id: THANKS,v 1.7 2005/11/19 01:02:50 oracleshinoda Exp $ diff --git a/framework/3rdParty/geshi/geshi.php b/framework/3rdParty/geshi/geshi.php new file mode 100644 index 00000000..b124c936 --- /dev/null +++ b/framework/3rdParty/geshi/geshi.php @@ -0,0 +1,2648 @@ + + * @copyright Copyright © 2004, 2005, Nigel McNie + * @license http://gnu.org/copyleft/gpl.html GNU GPL + * @version $Id: geshi.php,v 1.23 2005/11/19 02:23:37 oracleshinoda Exp $ + * + */ + +// +// GeSHi Constants +// You should use these constant names in your programs instead of +// their values - you never know when a value may change in a future +// version +// + +/** The version of this GeSHi file */ +define('GESHI_VERSION', '1.0.7.5'); + +/** For the future (though this may never be realised) */ +define('GESHI_OUTPUT_HTML', 0); + +/** Set the correct directory separator */ +define('GESHI_DIR_SEPARATOR', ('WIN' != substr(PHP_OS, 0, 3)) ? '/' : '\\'); + +// Define the root directory for the GeSHi code tree +if (!defined('GESHI_ROOT')) { + /** The root directory for GeSHi */ + define('GESHI_ROOT', dirname(__FILE__) . GESHI_DIR_SEPARATOR); +} +/** The language file directory for GeSHi + @access private */ +define('GESHI_LANG_ROOT', GESHI_ROOT . 'geshi' . GESHI_DIR_SEPARATOR); + + +// Line numbers - use with enable_line_numbers() +/** Use no line numbers when building the result */ +define('GESHI_NO_LINE_NUMBERS', 0); +/** Use normal line numbers when building the result */ +define('GESHI_NORMAL_LINE_NUMBERS', 1); +/** Use fancy line numbers when building the result */ +define('GESHI_FANCY_LINE_NUMBERS', 2); + +// Container HTML type +/** Use nothing to surround the source */ +define('GESHI_HEADER_NONE', 0); +/** Use a "div" to surround the source */ +define('GESHI_HEADER_DIV', 1); +/** Use a "pre" to surround the source */ +define('GESHI_HEADER_PRE', 2); + +// Capatalisation constants +/** Lowercase keywords found */ +define('GESHI_CAPS_NO_CHANGE', 0); +/** Uppercase keywords found */ +define('GESHI_CAPS_UPPER', 1); +/** Leave keywords found as the case that they are */ +define('GESHI_CAPS_LOWER', 2); + +// Link style constants +/** Links in the source in the :link state */ +define('GESHI_LINK', 0); +/** Links in the source in the :hover state */ +define('GESHI_HOVER', 1); +/** Links in the source in the :active state */ +define('GESHI_ACTIVE', 2); +/** Links in the source in the :visited state */ +define('GESHI_VISITED', 3); + +// Important string starter/finisher +// Note that if you change these, they should be as-is: i.e., don't +// write them as if they had been run through htmlentities() +/** The starter for important parts of the source */ +define('GESHI_START_IMPORTANT', ''); +/** The ender for important parts of the source */ +define('GESHI_END_IMPORTANT', ''); + +/**#@+ + * @access private + */ +// When strict mode applies for a language +/** Strict mode never applies (this is the most common) */ +define('GESHI_NEVER', 0); +/** Strict mode *might* apply, and can be enabled or + disabled by {@link GeSHi::enable_strict_mode()} */ +define('GESHI_MAYBE', 1); +/** Strict mode always applies */ +define('GESHI_ALWAYS', 2); + +// Advanced regexp handling constants, used in language files +/** The key of the regex array defining what to search for */ +define('GESHI_SEARCH', 0); +/** The key of the regex array defining what bracket group in a + matched search to use as a replacement */ +define('GESHI_REPLACE', 1); +/** The key of the regex array defining any modifiers to the regular expression */ +define('GESHI_MODIFIERS', 2); +/** The key of the regex array defining what bracket group in a + matched search to put before the replacement */ +define('GESHI_BEFORE', 3); +/** The key of the regex array defining what bracket group in a + matched search to put after the replacement */ +define('GESHI_AFTER', 4); + +/** Used in language files to mark comments */ +define('GESHI_COMMENTS', 0); + +// Error detection - use these to analyse faults +/** No sourcecode to highlight was specified */ +define('GESHI_ERROR_NO_INPUT', 1); +/** The language specified does not exist */ +define('GESHI_ERROR_NO_SUCH_LANG', 2); +/** GeSHi could not open a file for reading (generally a language file) */ +define('GESHI_ERROR_FILE_NOT_READABLE', 3); +/** The header type passed to {@link GeSHi::set_header_type()} was invalid */ +define('GESHI_ERROR_INVALID_HEADER_TYPE', 4); +/** The line number type passed to {@link GeSHi::enable_line_numbers()} was invalid */ +define('GESHI_ERROR_INVALID_LINE_NUMBER_TYPE', 5); +/**#@-*/ + + +/** + * The GeSHi Class. + * + * Please refer to the documentation for GeSHi 1.0.X that is available + * at http://qbnz.com/highlighter/documentation.php for more information + * about how to use this class. + * + * @package core + * @author Nigel McNie + * @copyright Copyright © 2004, 2005 Nigel McNie + */ +class GeSHi +{ + /**#@+ + * @access private + */ + /** + * The source code to highlight + * @var string + */ + protected $source = ''; + + /** + * The language to use when highlighting + * @var string + */ + protected $language = ''; + + /** + * The data for the language used + * @var array + */ + protected $language_data = array(); + + /** + * The path to the language files + * @var string + */ + protected $language_path = GESHI_LANG_ROOT; + + /** + * The error message associated with an error + * @var string + * @todo check err reporting works + */ + protected $error = false; + + /** + * Possible error messages + * @var array + */ + protected $error_messages = array( + GESHI_ERROR_NO_INPUT => 'No source code inputted', + GESHI_ERROR_NO_SUCH_LANG => 'GeSHi could not find the language {LANGUAGE} (using path {PATH})', + GESHI_ERROR_FILE_NOT_READABLE => 'The file specified for load_from_file was not readable', + GESHI_ERROR_INVALID_HEADER_TYPE => 'The header type specified is invalid', + GESHI_ERROR_INVALID_LINE_NUMBER_TYPE => 'The line number type specified is invalid' + ); + + /** + * Whether highlighting is strict or not + * @var boolean + */ + protected $strict_mode = false; + + /** + * Whether to use CSS classes in output + * @var boolean + */ + protected $use_classes = false; + + /** + * The type of header to use. Can be one of the following + * values: + * + *
    + *
  • GESHI_HEADER_PRE: Source is outputted in + * a <pre> HTML element.
    • + *
  • GESHI_HEADER_DIV: Source is outputted in + * a <div> HTML element.
    • + *
+ * + * @var int + */ + protected $header_type = GESHI_HEADER_PRE; + + /** + * Array of permissions for which lexics should be highlighted + * @var array + */ + protected $lexic_permissions = array( + 'KEYWORDS' => array(), + 'COMMENTS' => array('MULTI' => true), + 'REGEXPS' => array(), + 'ESCAPE_CHAR' => true, + 'BRACKETS' => true, + 'SYMBOLS' => true, + 'STRINGS' => true, + 'NUMBERS' => true, + 'METHODS' => true, + 'SCRIPT' => true + ); + + /** + * The time it took to parse the code + * @var double + */ + protected $time = 0; + + /** + * The content of the header block + * @var string + */ + protected $header_content = ''; + + /** + * The content of the footer block + * @var string + */ + protected $footer_content = ''; + + /** + * The style of the header block + * @var string + */ + protected $header_content_style = ''; + + /** + * The style of the footer block + * @var string + */ + protected $footer_content_style = ''; + + /** + * The styles for hyperlinks in the code + * @var array + */ + protected $link_styles = array(); + + /** + * Whether important blocks should be recognised or not + * @var boolean + * @deprecated + * @todo REMOVE THIS FUNCTIONALITY! + */ + protected $enable_important_blocks = false; + + /** + * Styles for important parts of the code + * @var string + * @deprecated + * @todo As above - rethink the whole idea of important blocks as it is buggy and + * will be hard to implement in 1.2 + */ + protected $important_styles = 'font-weight: bold; color: red;'; // Styles for important parts of the code + + /** + * Whether CSS IDs should be added to the code + * @var boolean + */ + protected $add_ids = false; + + /** + * Lines that should be highlighted extra + * @var array + */ + protected $highlight_extra_lines = array(); + + /** + * Styles of extra-highlighted lines + * @var string + */ + protected $highlight_extra_lines_style = 'color: #cc0; background-color: #ffc;'; + + /** + * Number at which line numbers should start at + * @var int + * @todo Warning documentation about XHTML compliance + */ + protected $line_numbers_start = 1; + + /** + * The overall style for this code block + * @var string + */ + protected $overall_style = ''; + + /** + * The style for the actual code + * @var string + */ + protected $code_style = 'font-family: \'Courier New\', Courier, monospace; font-weight: normal;'; + + /** + * The overall class for this code block + * @var string + */ + protected $overall_class = ''; + + /** + * The overall ID for this code block + * @var string + */ + protected $overall_id = ''; + + /** + * Line number styles + * @var string + */ + protected $line_style1 = 'font-family: \'Courier New\', Courier, monospace; color: black; font-weight: normal; font-style: normal;'; + + /** + * Line number styles for fancy lines + * @var string + */ + protected $line_style2 = 'font-weight: bold;'; + + /** + * Flag for how line nubmers are displayed + * @var boolean + */ + protected $line_numbers = GESHI_NO_LINE_NUMBERS; + + /** + * The "nth" value for fancy line highlighting + * @var int + */ + protected $line_nth_row = 0; + + /** + * The size of tab stops + * @var int + */ + protected $tab_width = 8; + + /** + * Default target for keyword links + * @var string + */ + protected $link_target = ''; + + /** + * The encoding to use for entity encoding + * @var string + */ + protected $encoding = 'ISO-8859-1'; + + /** + * Unused (planned for future) + * @var int + */ + protected $output_format = GESHI_OUTPUT_HTML; + + /**#@-*/ + + /** + * Creates a new GeSHi object, with source and language + * + * @param string The source code to highlight + * @param string The language to highlight the source with + * @param string The path to the language file directory. This + * is deprecated! I've backported the auto path + * detection from the 1.1.X dev branch, so now it + * should be automatically set correctly. If you have + * renamed the language directory however, you will + * still need to set the path using this parameter or + * {@link GeSHi::set_language_path()} + * @since 1.0.0 + */ + function __construct ($source, $language, $path = '') + { + $this->set_source($source); + $this->set_language_path($path); + $this->set_language($language); + } + + /** + * Returns an error message associated with the last GeSHi operation, + * or false if no error has occured + * + * @return string|false An error message if there has been an error, else false + * @since 1.0.0 + */ + function error () + { + if ($this->error) { + $msg = $this->error_messages[$this->error]; + $debug_tpl_vars = array( + '{LANGUAGE}' => $this->language, + '{PATH}' => $this->language_path + ); + foreach ($debug_tpl_vars as $tpl => $var) { + $msg = str_replace($tpl, $var, $msg); + } + return "
GeSHi Error: $msg (code $this->error)
"; + } + return false; + } + + /** + * Gets a human-readable language name (thanks to Simon Patterson + * for the idea :)) + * + * @return string The name for the current language + * @since 1.0.2 + */ + function get_language_name () + { + if (GESHI_ERROR_NO_SUCH_LANG == $this->_error) { + return $this->language_data['LANG_NAME'] . ' (Unknown Language)'; + } + return $this->language_data['LANG_NAME']; + } + + /** + * Sets the source code for this object + * + * @param string The source code to highlight + * @since 1.0.0 + */ + function set_source ($source) + { + if ('' == trim($source)) { + $this->error = GESHI_ERROR_NO_INPUT; + } + $this->source = $source; + } + + /** + * Sets the language for this object + * + * @param string The name of the language to use + * @since 1.0.0 + */ + function set_language ($language) + { + $this->error = false; + $this->strict_mode = GESHI_NEVER; + + $language = preg_replace('#[^a-zA-Z0-9\-_]#', '', $language); + $this->language = strtolower($language); + + $file_name = $this->language_path . $this->language . '.php'; + if (!is_readable($file_name)) { + $this->error = GESHI_ERROR_NO_SUCH_LANG; + return; + } + // Load the language for parsing + $this->load_language($file_name); + } + + /** + * Sets the path to the directory containing the language files. Note + * that this path is relative to the directory of the script that included + * geshi.php, NOT geshi.php itself. + * + * @param string The path to the language directory + * @since 1.0.0 + * @deprecated The path to the language files should now be automatically + * detected, so this method should no longer be needed. The + * 1.1.X branch handles manual setting of the path differently + * so this method will disappear in 1.2.0. + */ + function set_language_path ($path) + { + if ($path) { + $this->language_path = ('/' == substr($path, strlen($path) - 1, 1)) ? $path : $path . '/'; + } + } + + /** + * Sets the type of header to be used. + * + * If GESHI_HEADER_DIV is used, the code is surrounded in a "div".This + * means more source code but more control over tab width and line-wrapping. + * GESHI_HEADER_PRE means that a "pre" is used - less source, but less + * control. Default is GESHI_HEADER_PRE. + * + * From 1.0.7.2, you can use GESHI_HEADER_NONE to specify that no header code + * should be outputted. + * + * @param int The type of header to be used + * @since 1.0.0 + */ + function set_header_type ($type) + { + if (GESHI_HEADER_DIV != $type && GESHI_HEADER_PRE != $type && GESHI_HEADER_NONE != $type) { + $this->error = GESHI_ERROR_INVALID_HEADER_TYPE; + return; + } + $this->header_type = $type; + } + + /** + * Sets the styles for the code that will be outputted + * when this object is parsed. The style should be a + * string of valid stylesheet declarations + * + * @param string The overall style for the outputted code block + * @param boolean Whether to merge the styles with the current styles or not + * @since 1.0.0 + */ + function set_overall_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->overall_style = $style; + } else { + $this->overall_style .= $style; + } + } + + /** + * Sets the overall classname for this block of code. This + * class can then be used in a stylesheet to style this object's + * output + * + * @param string The class name to use for this block of code + * @since 1.0.0 + */ + function set_overall_class ($class) + { + $this->overall_class = $class; + } + + /** + * Sets the overall id for this block of code. This id can then + * be used in a stylesheet to style this object's output + * + * @param string The ID to use for this block of code + * @since 1.0.0 + */ + function set_overall_id ($id) + { + $this->overall_id = $id; + } + + /** + * Sets whether CSS classes should be used to highlight the source. Default + * is off, calling this method with no arguments will turn it on + * + * @param boolean Whether to turn classes on or not + * @since 1.0.0 + */ + function enable_classes ($flag = true) + { + $this->use_classes = ($flag) ? true : false; + } + + /** + * Sets the style for the actual code. This should be a string + * containing valid stylesheet declarations. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * Note: Use this method to override any style changes you made to + * the line numbers if you are using line numbers, else the line of + * code will have the same style as the line number! Consult the + * GeSHi documentation for more information about this. + * + * @param string The style to use for actual code + * @param boolean Whether to merge the current styles with the new styles + */ + function set_code_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->code_style = $style; + } else { + $this->code_style .= $style; + } + } + + /** + * Sets the styles for the line numbers. + * + * @param string The style for the line numbers that are "normal" + * @param string|boolean If a string, this is the style of the line + * numbers that are "fancy", otherwise if boolean then this + * defines whether the normal styles should be merged with the + * new normal styles or not + * @param boolean If set, is the flag for whether to merge the "fancy" + * styles with the current styles or not + * @since 1.0.2 + */ + function set_line_style ($style1, $style2 = '', $preserve_defaults = false) + { + if (is_bool($style2)) { + $preserve_defaults = $style2; + $style2 = ''; + } + if (!$preserve_defaults) { + $this->line_style1 = $style1; + $this->line_style2 = $style2; + } else { + $this->line_style1 .= $style1; + $this->line_style2 .= $style2; + } + } + + /** + * Sets whether line numbers should be displayed. + * + * Valid values for the first parameter are: + * + *
    + *
  • GESHI_NO_LINE_NUMBERS: Line numbers will not be displayed
    • + *
  • GESHI_NORMAL_LINE_NUMBERS: Line numbers will be displayed
    • + *
  • GESHI_FANCY_LINE_NUMBERS: Fancy line numbers will be displayed
    • + *
+ * + * For fancy line numbers, the second parameter is used to signal which lines + * are to be fancy. For example, if the value of this parameter is 5 then every + * 5th line will be fancy. + * + * @param int How line numbers should be displayed + * @param int Defines which lines are fancy + * @since 1.0.0 + */ + function enable_line_numbers ($flag, $nth_row = 5) + { + if (GESHI_NO_LINE_NUMBERS != $flag && GESHI_NORMAL_LINE_NUMBERS != $flag + && GESHI_FANCY_LINE_NUMBERS != $flag) { + $this->error = GESHI_ERROR_INVALID_LINE_NUMBER_TYPE; + } + $this->line_numbers = $flag; + $this->line_nth_row = $nth_row; + } + + /** + * Sets the style for a keyword group. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param int The key of the keyword group to change the styles of + * @param string The style to make the keywords + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_keyword_group_style ($key, $style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['KEYWORDS'][$key] = $style; + } else { + $this->language_data['STYLES']['KEYWORDS'][$key] .= $style; + } + } + + /** + * Turns highlighting on/off for a keyword group + * + * @param int The key of the keyword group to turn on or off + * @param boolean Whether to turn highlighting for that group on or off + * @since 1.0.0 + */ + function set_keyword_group_highlighting ( $key, $flag = true ) + { + $this->lexic_permissions['KEYWORDS'][$key] = ($flag) ? true : false; + } + + /** + * Sets the styles for comment groups. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param int The key of the comment group to change the styles of + * @param string The style to make the comments + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_comments_style ($key, $style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['COMMENTS'][$key] = $style; + } else { + $this->language_data['STYLES']['COMMENTS'][$key] .= $style; + } + } + + /** + * Turns highlighting on/off for comment groups + * + * @param int The key of the comment group to turn on or off + * @param boolean Whether to turn highlighting for that group on or off + * @since 1.0.0 + */ + function set_comments_highlighting ($key, $flag = true) + { + $this->lexic_permissions['COMMENTS'][$key] = ($flag) ? true : false; + } + + /** + * Sets the styles for escaped characters. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param string The style to make the escape characters + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_escape_characters_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['ESCAPE_CHAR'][0] = $style; + } else { + $this->language_data['STYLES']['ESCAPE_CHAR'][0] .= $style; + } + } + + /** + * Turns highlighting on/off for escaped characters + * + * @param boolean Whether to turn highlighting for escape characters on or off + * @since 1.0.0 + */ + function set_escape_characters_highlighting ($flag = true) + { + $this->lexic_permissions['ESCAPE_CHAR'] = ($flag) ? true : false; + } + + /** + * Sets the styles for brackets. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * This method is DEPRECATED: use set_symbols_style instead. + * This method will be removed in 1.2.X + * + * @param string The style to make the brackets + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + * @deprecated In favour of set_symbols_style + */ + function set_brackets_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['BRACKETS'][0] = $style; + } else { + $this->language_data['STYLES']['BRACKETS'][0] .= $style; + } + } + + /** + * Turns highlighting on/off for brackets + * + * This method is DEPRECATED: use set_symbols_highlighting instead. + * This method will be remove in 1.2.X + * + * @param boolean Whether to turn highlighting for brackets on or off + * @since 1.0.0 + * @deprecated In favour of set_symbols_highlighting + */ + function set_brackets_highlighting ($flag) + { + $this->lexic_permissions['BRACKETS'] = ($flag) ? true : false; + } + + /** + * Sets the styles for symbols. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param string The style to make the symbols + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.1 + */ + function set_symbols_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['SYMBOLS'][0] = $style; + } else { + $this->language_data['STYLES']['SYMBOLS'][0] .= $style; + } + // For backward compatibility + $this->set_brackets_style ($style, $preserve_defaults); + } + + /** + * Turns highlighting on/off for symbols + * + * @param boolean Whether to turn highlighting for symbols on or off + * @since 1.0.0 + */ + function set_symbols_highlighting ($flag) + { + $this->lexic_permissions['SYMBOLS'] = ($flag) ? true : false; + // For backward compatibility + $this->set_brackets_highlighting ($flag); + } + + /** + * Sets the styles for strings. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param string The style to make the escape characters + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_strings_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['STRINGS'][0] = $style; + } else { + $this->language_data['STYLES']['STRINGS'][0] .= $style; + } + } + + /** + * Turns highlighting on/off for strings + * + * @param boolean Whether to turn highlighting for strings on or off + * @since 1.0.0 + */ + function set_strings_highlighting ($flag) + { + $this->lexic_permissions['STRINGS'] = ($flag) ? true : false; + } + + /** + * Sets the styles for numbers. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param string The style to make the numbers + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_numbers_style ($style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['NUMBERS'][0] = $style; + } else { + $this->language_data['STYLES']['NUMBERS'][0] .= $style; + } + } + + /** + * Turns highlighting on/off for numbers + * + * @param boolean Whether to turn highlighting for numbers on or off + * @since 1.0.0 + */ + function set_numbers_highlighting ($flag) + { + $this->lexic_permissions['NUMBERS'] = ($flag) ? true : false; + } + + /** + * Sets the styles for methods. $key is a number that references the + * appropriate "object splitter" - see the language file for the language + * you are highlighting to get this number. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param int The key of the object splitter to change the styles of + * @param string The style to make the methods + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_methods_style ($key, $style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['METHODS'][$key] = $style; + } else { + $this->language_data['STYLES']['METHODS'][$key] .= $style; + } + } + + /** + * Turns highlighting on/off for methods + * + * @param boolean Whether to turn highlighting for methods on or off + * @since 1.0.0 + */ + function set_methods_highlighting ($flag) + { + $this->lexic_permissions['METHODS'] = ($flag) ? true : false; + } + + /** + * Sets the styles for regexps. If $preserve_defaults is + * true, then styles are merged with the default styles, with the + * user defined styles having priority + * + * @param string The style to make the regular expression matches + * @param boolean Whether to merge the new styles with the old or just + * to overwrite them + * @since 1.0.0 + */ + function set_regexps_style ($key, $style, $preserve_defaults = false) + { + if (!$preserve_defaults) { + $this->language_data['STYLES']['REGEXPS'][$key] = $style; + } else { + $this->language_data['STYLES']['REGEXPS'][$key] .= $style; + } + } + + /** + * Turns highlighting on/off for regexps + * + * @param int The key of the regular expression group to turn on or off + * @param boolean Whether to turn highlighting for the regular expression group on or off + * @since 1.0.0 + */ + function set_regexps_highlighting ($key, $flag) + { + $this->lexic_permissions['REGEXPS'][$key] = ($flag) ? true : false; + } + + /** + * Sets whether a set of keywords are checked for in a case sensitive manner + * + * @param int The key of the keyword group to change the case sensitivity of + * @param boolean Whether to check in a case sensitive manner or not + * @since 1.0.0 + */ + function set_case_sensitivity ($key, $case) + { + $this->language_data['CASE_SENSITIVE'][$key] = ($case) ? true : false; + } + + /** + * Sets the case that keywords should use when found. Use the constants: + * + *
    + *
  • GESHI_CAPS_NO_CHANGE: leave keywords as-is
    • + *
  • GESHI_CAPS_UPPER: convert all keywords to uppercase where found
    • + *
  • GESHI_CAPS_LOWER: convert all keywords to lowercase where found
    • + *
+ * + * @param int A constant specifying what to do with matched keywords + * @since 1.0.1 + * @todo Error check the passed value + */ + function set_case_keywords ($case) + { + $this->language_data['CASE_KEYWORDS'] = $case; + } + + /** + * Sets how many spaces a tab is substituted for + * + * Widths below zero are ignored + * + * @param int The tab width + * @since 1.0.0 + */ + function set_tab_width ($width) + { + $this->tab_width = intval($width); + } + + /** + * Enables/disables strict highlighting. Default is off, calling this + * method without parameters will turn it on. See documentation + * for more details on strict mode and where to use it. + * + * @param boolean Whether to enable strict mode or not + * @since 1.0.0 + */ + function enable_strict_mode ($mode = true) + { + if (GESHI_MAYBE == $this->language_data['STRICT_MODE_APPLIES']) { + $this->strict_mode = ($mode) ? true : false; + } + } + + /** + * Disables all highlighting + * + * @since 1.0.0 + * @todo Rewrite with an array traversal + */ + function disable_highlighting () + { + foreach ($this->lexic_permissions as $key => $value) { + if (is_array($value)) { + foreach ($value as $k => $v) { + $this->lexic_permissions[$key][$k] = false; + } + } else { + $this->lexic_permissions[$key] = false; + } + } + // Context blocks + $this->enable_important_blocks = false; + } + + /** + * Enables all highlighting + * + * @since 1.0.0 + * @todo Rewrite with array traversal + */ + function enable_highlighting () + { + foreach ($this->lexic_permissions as $key => $value) { + if (is_array($value)) { + foreach ($value as $k => $v) { + $this->lexic_permissions[$key][$k] = true; + } + } else { + $this->lexic_permissions[$key] = true; + } + } + // Context blocks + $this->enable_important_blocks = true; + } + + /** + * Given a file extension, this method returns either a valid geshi language + * name, or the empty string if it couldn't be found + * + * @param string The extension to get a language name for + * @param array A lookup array to use instead of the default + * @since 1.0.5 + * @todo Re-think about how this method works (maybe make it private and/or make it + * a extension->lang lookup?) + * @todo static? + */ + function get_language_name_from_extension ( $extension, $lookup = array() ) + { + if ( !$lookup ) + { + $lookup = array( + 'actionscript' => array('as'), + 'ada' => array('a', 'ada', 'adb', 'ads'), + 'apache' => array('conf'), + 'asm' => array('ash', 'asm'), + 'asp' => array('asp'), + 'bash' => array('sh'), + 'c' => array('c'), + 'c_mac' => array('c'), + 'caddcl' => array(), + 'cadlisp' => array(), + 'cpp' => array('cpp'), + 'csharp' => array(), + 'css' => array('css'), + 'delphi' => array('dpk', 'dpr'), + 'html4strict' => array('html', 'htm'), + 'java' => array('java'), + 'javascript' => array('js'), + 'lisp' => array('lisp'), + 'lua' => array('lua'), + 'mpasm' => array(), + 'nsis' => array(), + 'objc' => array(), + 'oobas' => array(), + 'oracle8' => array(), + 'pascal' => array('pas'), + 'perl' => array('pl', 'pm'), + 'php' => array('php', 'php5', 'phtml', 'phps'), + 'python' => array('py'), + 'qbasic' => array('bi'), + 'smarty' => array(), + 'vb' => array('bas'), + 'vbnet' => array(), + 'visualfoxpro' => array(), + 'xml' => array('xml') + ); + } + + foreach ($lookup as $lang => $extensions) { + foreach ($extensions as $ext) { + if ($ext == $extension) { + return $lang; + } + } + } + return ''; + } + + /** + * Given a file name, this method loads its contents in, and attempts + * to set the language automatically. An optional lookup table can be + * passed for looking up the language name. If not specified a default + * table is used + * + * The language table is in the form + * 
array(
+	 *   'lang_name' => array('extension', 'extension', ...),
+	 *   'lang_name' ...
+	 * );
+ * + * @todo Complete rethink of this and above method + * @since 1.0.5 + */ + function load_from_file ($file_name, $lookup = array()) + { + if (is_readable($file_name)) { + $this->set_source(implode('', file($file_name))); + $this->set_language($this->get_language_name_from_extension(substr(strrchr($file_name, '.'), 1), $lookup)); + } else { + $this->error = GESHI_ERROR_FILE_NOT_READABLE; + } + } + + /** + * Adds a keyword to a keyword group for highlighting + * + * @param int The key of the keyword group to add the keyword to + * @param string The word to add to the keyword group + * @since 1.0.0 + */ + function add_keyword ($key, $word) + { + $this->language_data['KEYWORDS'][$key][] = $word; + } + + /** + * Removes a keyword from a keyword group + * + * @param int The key of the keyword group to remove the keyword from + * @param string The word to remove from the keyword group + * @since 1.0.0 + */ + function remove_keyword ($key, $word) + { + $this->language_data['KEYWORDS'][$key] = + array_diff($this->language_data['KEYWORDS'][$key], array($word)); + } + + /** + * Creates a new keyword group + * + * @param int The key of the keyword group to create + * @param string The styles for the keyword group + * @param boolean Whether the keyword group is case sensitive ornot + * @param array The words to use for the keyword group + * @since 1.0.0 + */ + function add_keyword_group ( $key, $styles, $case_sensitive = true, $words = array() ) + { + $words = (array) $words; + $this->language_data['KEYWORDS'][$key] = $words; + $this->lexic_permissions['KEYWORDS'][$key] = true; + $this->language_data['CASE_SENSITIVE'][$key] = $case_sensitive; + $this->language_data['STYLES']['KEYWORDS'][$key] = $styles; + } + + /** + * Removes a keyword group + * + * @param int The key of the keyword group to remove + * @since 1.0.0 + */ + function remove_keyword_group ($key) + { + unset($this->language_data['KEYWORDS'][$key]); + unset($this->lexic_permissions['KEYWORDS'][$key]); + unset($this->language_data['CASE_SENSITIVE'][$key]); + unset($this->language_data['STYLES']['KEYWORDS'][$key]); + } + + /** + * Sets the content of the header block + * + * @param string The content of the header block + * @since 1.0.2 + */ + function set_header_content ($content) + { + $this->header_content = $content; + } + + /** + * Sets the content of the footer block + * + * @param string The content of the footer block + * @since 1.0.2 + */ + function set_footer_content ($content) + { + $this->footer_content = $content; + } + + /** + * Sets the style for the header content + * + * @param string The style for the header content + * @since 1.0.2 + */ + function set_header_content_style ($style) + { + $this->header_content_style = $style; + } + + /** + * Sets the style for the footer content + * + * @param string The style for the footer content + * @since 1.0.2 + */ + function set_footer_content_style ($style) + { + $this->footer_content_style = $style; + } + + /** + * Sets the base URL to be used for keywords + * + * @param int The key of the keyword group to set the URL for + * @param string The URL to set for the group. If {FNAME} is in + * the url somewhere, it is replaced by the keyword + * that the URL is being made for + * @since 1.0.2 + */ + function set_url_for_keyword_group ($group, $url) + { + $this->language_data['URLS'][$group] = $url; + } + + /** + * Sets styles for links in code + * + * @param int A constant that specifies what state the style is being + * set for - e.g. :hover or :visited + * @param string The styles to use for that state + * @since 1.0.2 + */ + function set_link_styles ($type, $styles) + { + $this->link_styles[$type] = $styles; + } + + /** + * Sets the target for links in code + * + * @param string The target for links in the code, e.g. _blank + * @since 1.0.3 + */ + function set_link_target ( $target ) + { + if (!$target) { + $this->link_target = ''; + } else { + $this->link_target = ' target="' . $target . '" '; + } + } + + /** + * Sets styles for important parts of the code + * + * @param string The styles to use on important parts of the code + * @since 1.0.2 + */ + function set_important_styles ($styles) + { + $this->important_styles = $styles; + } + + /** + * Sets whether context-important blocks are highlighted + * + * @todo REMOVE THIS SHIZ FROM GESHI! + * @deprecated + */ + function enable_important_blocks ( $flag ) + { + $this->enable_important_blocks = ( $flag ) ? true : false; + } + + /** + * Whether CSS IDs should be added to each line + * + * @param boolean If true, IDs will be added to each line. + * @since 1.0.2 + */ + function enable_ids ($flag = true) + { + $this->add_ids = ($flag) ? true : false; + } + + /** + * Specifies which lines to highlight extra + * + * @param mixed An array of line numbers to highlight, or just a line + * number on its own. + * @since 1.0.2 + * @todo Some data replication here that could be cut down on + */ + function highlight_lines_extra ($lines) + { + if (is_array($lines)) { + foreach ($lines as $line) { + $this->highlight_extra_lines[intval($line)] = intval($line); + } + } else { + $this->highlight_extra_lines[intval($lines)] = intval($lines); + } + } + + /** + * Sets the style for extra-highlighted lines + * + * @param string The style for extra-highlighted lines + * @since 1.0.2 + */ + function set_highlight_lines_extra_style ($styles) + { + $this->highlight_extra_lines_style = $styles; + } + + /** + * Sets what number line numbers should start at. Should + * be a positive integer, and will be converted to one. + * + * Warning: Using this method will add the "start" + * attribute to the <ol> that is used for line numbering. + * This is not valid XHTML strict, so if that's what you + * care about then don't use this method. Firefox is getting + * support for the CSS method of doing this in 1.1 and Opera + * has support for the CSS method, but (of course) IE doesn't + * so it's not worth doing it the CSS way yet. + * + * @param int The number to start line numbers at + * @since 1.0.2 + */ + function start_line_numbers_at ($number) + { + $this->line_numbers_start = abs(intval($number)); + } + + /** + * Sets the encoding used for htmlspecialchars(), for international + * support. + * + * @param string The encoding to use for the source + * @since 1.0.3 + */ + function set_encoding ($encoding) + { + if ($encoding) { + $this->encoding = $encoding; + } + } + + /** + * Returns the code in $this->source, highlighted and surrounded by the + * nessecary HTML. + * + * This should only be called ONCE, cos it's SLOW! If you want to highlight + * the same source multiple times, you're better off doing a whole lot of + * str_replaces to replace the <span>s + * + * @since 1.0.0 + */ + function parse_code () + { + // Start the timer + $start_time = microtime(); + + // Firstly, if there is an error, we won't highlight + if ($this->error) { + $result = $this->header(); + if ($this->header_type != GESHI_HEADER_PRE) { + $result .= $this->indent(@htmlspecialchars($this->source, ENT_COMPAT, $this->encoding)); + } else { + $result .= @htmlspecialchars($this->source, ENT_COMPAT, $this->encoding); + } + // Stop Timing + $this->set_time($start_time, microtime()); + return $result . $this->footer(); + } + + // Add spaces for regular expression matching and line numbers + $code = ' ' . $this->source . ' '; + // Replace all newlines to a common form. + $code = str_replace("\r\n", "\n", $code); + $code = str_replace("\r", "\n", $code); + + // Initialise various stuff + $length = strlen($code); + $STRING_OPEN = ''; + $CLOSE_STRING = false; + $ESCAPE_CHAR_OPEN = false; + $COMMENT_MATCHED = false; + // Turn highlighting on if strict mode doesn't apply to this language + $HIGHLIGHTING_ON = ( !$this->strict_mode ) ? true : ''; + // Whether to highlight inside a block of code + $HIGHLIGHT_INSIDE_STRICT = false; + $stuff_to_parse = ''; + $result = ''; + + // "Important" selections are handled like multiline comments + // @todo GET RID OF THIS SHIZ + if ($this->enable_important_blocks) { + $this->language_data['COMMENT_MULTI'][GESHI_START_IMPORTANT] = GESHI_END_IMPORTANT; + } + + if ($this->strict_mode) { + // Break the source into bits. Each bit will be a portion of the code + // within script delimiters - for example, HTML between < and > + $parts = array(0 => array(0 => '')); + $k = 0; + for ($i = 0; $i < $length; $i++) { + $char = substr($code, $i, 1); + if (!$HIGHLIGHTING_ON) { + foreach ($this->language_data['SCRIPT_DELIMITERS'] as $key => $delimiters) { + foreach ($delimiters as $open => $close) { + // Get the next little bit for this opening string + $check = substr($code, $i, strlen($open)); + // If it matches... + if ($check == $open) { + // We start a new block with the highlightable + // code in it + $HIGHLIGHTING_ON = $open; + $i += strlen($open) - 1; + $char = $open; + $parts[++$k][0] = $char; + + // No point going around again... + break(2); + } + } + } + } else { + foreach ($this->language_data['SCRIPT_DELIMITERS'] as $key => $delimiters) { + foreach ($delimiters as $open => $close) { + if ($open == $HIGHLIGHTING_ON) { + // Found the closing tag + break(2); + } + } + } + // We check code from our current position BACKWARDS. This is so + // the ending string for highlighting can be included in the block + $check = substr($code, $i - strlen($close) + 1, strlen($close)); + if ($check == $close) { + $HIGHLIGHTING_ON = ''; + // Add the string to the rest of the string for this part + $parts[$k][1] = ( isset($parts[$k][1]) ) ? $parts[$k][1] . $char : $char; + $parts[++$k][0] = ''; + $char = ''; + } + } + $parts[$k][1] = ( isset($parts[$k][1]) ) ? $parts[$k][1] . $char : $char; + } + $HIGHLIGHTING_ON = ''; + } else { + // Not strict mode - simply dump the source into + // the array at index 1 (the first highlightable block) + $parts = array( + 1 => array( + 0 => '', + 1 => $code + ) + ); + } + + // Now we go through each part. We know that even-indexed parts are + // code that shouldn't be highlighted, and odd-indexed parts should + // be highlighted + foreach ($parts as $key => $data) { + $part = $data[1]; + // If this block should be highlighted... + if ($key % 2) { + if ($this->strict_mode) { + // Find the class key for this block of code + foreach ($this->language_data['SCRIPT_DELIMITERS'] as $script_key => $script_data) { + foreach ($script_data as $open => $close) { + if ($data[0] == $open) { + break(2); + } + } + } + + if ($this->language_data['STYLES']['SCRIPT'][$script_key] != '' && + $this->lexic_permissions['SCRIPT']) { + // Add a span element around the source to + // highlight the overall source block + if (!$this->use_classes && + $this->language_data['STYLES']['SCRIPT'][$script_key] != '') { + $attributes = ' style="' . $this->language_data['STYLES']['SCRIPT'][$script_key] . '"'; + } else { + $attributes = ' class="sc' . $script_key . '"'; + } + $result .= ""; + } + } + + if (!$this->strict_mode || $this->language_data['HIGHLIGHT_STRICT_BLOCK'][$script_key]) { + // Now, highlight the code in this block. This code + // is really the engine of GeSHi (along with the method + // parse_non_string_part). + $length = strlen($part); + for ($i = 0; $i < $length; $i++) { + // Get the next char + $char = substr($part, $i, 1); + // Is this char the newline and line numbers being used? + if (($this->line_numbers != GESHI_NO_LINE_NUMBERS + || count($this->highlight_extra_lines) > 0) + && $char == "\n") { + // If so, is there a string open? If there is, we should end it before + // the newline and begin it again (so when
  • s are put in the source + // remains XHTML compliant) + // note to self: This opens up possibility of config files specifying + // that languages can/cannot have multiline strings??? + if ($STRING_OPEN) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['STRINGS'][0] . '"'; + } else { + $attributes = ' class="st0"'; + } + $char = '' . $char . ""; + } + } elseif ($char == $STRING_OPEN) { + // A match of a string delimiter + if (($this->lexic_permissions['ESCAPE_CHAR'] && $ESCAPE_CHAR_OPEN) || + ($this->lexic_permissions['STRINGS'] && !$ESCAPE_CHAR_OPEN)) { + $char .= ''; + } + if (!$ESCAPE_CHAR_OPEN) { + $STRING_OPEN = ''; + $CLOSE_STRING = true; + } + $ESCAPE_CHAR_OPEN = false; + } elseif (in_array($char, $this->language_data['QUOTEMARKS']) && + ($STRING_OPEN == '') && $this->lexic_permissions['STRINGS']) { + // The start of a new string + $STRING_OPEN = $char; + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['STRINGS'][0] . '"'; + } else { + $attributes = ' class="st0"'; + } + $char = "" . $char; + + $result .= $this->parse_non_string_part( $stuff_to_parse ); + $stuff_to_parse = ''; + } elseif (($char == $this->language_data['ESCAPE_CHAR']) && ($STRING_OPEN != '')) { + // An escape character + if (!$ESCAPE_CHAR_OPEN) { + $ESCAPE_CHAR_OPEN = true; + if ($this->lexic_permissions['ESCAPE_CHAR']) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['ESCAPE_CHAR'][0] . '"'; + } else { + $attributes = ' class="es0"'; + } + $char = "" . $char; + if (substr($code, $i + 1, 1) == "\n") { + // escaping a newline, what's the point in putting the span around + // the newline? It only causes hassles when inserting line numbers + $char .= ''; + $ESCAPE_CHAR_OPEN = false; + } + } + } else { + $ESCAPE_CHAR_OPEN = false; + if ($this->lexic_permissions['ESCAPE_CHAR']) { + $char .= ''; + } + } + } elseif ($ESCAPE_CHAR_OPEN) { + if ($this->lexic_permissions['ESCAPE_CHAR']) { + $char .= ''; + } + $ESCAPE_CHAR_OPEN = false; + $test_str = $char; + } elseif ($STRING_OPEN == '') { + // Is this a multiline comment? + foreach ($this->language_data['COMMENT_MULTI'] as $open => $close) { + $com_len = strlen($open); + $test_str = substr( $part, $i, $com_len ); + $test_str_match = $test_str; + if ($open == $test_str) { + $COMMENT_MATCHED = true; + //@todo If remove important do remove here + if ($this->lexic_permissions['COMMENTS']['MULTI'] || + $test_str == GESHI_START_IMPORTANT) { + if ($test_str != GESHI_START_IMPORTANT) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['COMMENTS']['MULTI'] . '"'; + } else { + $attributes = ' class="coMULTI"'; + } + $test_str = "" . @htmlspecialchars($test_str, ENT_COMPAT, $this->encoding); + } else { + if (!$this->use_classes) { + $attributes = ' style="' . $this->important_styles . '"'; + } else { + $attributes = ' class="imp"'; + } + // We don't include the start of the comment if it's an + // "important" part + $test_str = ""; + } + } else { + $test_str = @htmlspecialchars($test_str, ENT_COMPAT, $this->encoding); + } + + $close_pos = strpos( $part, $close, $i + strlen($close) ); + + if ($close_pos === false) { + $close_pos = strlen($part); + } + + // Short-cut through all the multiline code + $rest_of_comment = @htmlspecialchars(substr($part, $i + $com_len, $close_pos - $i), ENT_COMPAT, $this->encoding); + if (($this->lexic_permissions['COMMENTS']['MULTI'] || + $test_str_match == GESHI_START_IMPORTANT) && + ($this->line_numbers != GESHI_NO_LINE_NUMBERS || + count($this->highlight_extra_lines) > 0)) { + // strreplace to put close span and open span around multiline newlines + $test_str .= str_replace("\n", "\n", $rest_of_comment); + } else { + $test_str .= $rest_of_comment; + } + + if ($this->lexic_permissions['COMMENTS']['MULTI'] || + $test_str_match == GESHI_START_IMPORTANT) { + $test_str .= ''; + } + $i = $close_pos + $com_len - 1; + // parse the rest + $result .= $this->parse_non_string_part($stuff_to_parse); + $stuff_to_parse = ''; + break; + } + } + // If we haven't matched a multiline comment, try single-line comments + if (!$COMMENT_MATCHED) { + foreach ($this->language_data['COMMENT_SINGLE'] as $comment_key => $comment_mark) { + $com_len = strlen($comment_mark); + $test_str = substr($part, $i, $com_len); + if ($this->language_data['CASE_SENSITIVE'][GESHI_COMMENTS]) { + $match = ($comment_mark == $test_str); + } else { + $match = (strtolower($comment_mark) == strtolower($test_str)); + } + if ($match) { + $COMMENT_MATCHED = true; + if ($this->lexic_permissions['COMMENTS'][$comment_key]) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['COMMENTS'][$comment_key] . '"'; + } else { + $attributes = ' class="co' . $comment_key . '"'; + } + $test_str = "" . @htmlspecialchars($this->change_case($test_str), ENT_COMPAT, $this->encoding); + } else { + $test_str = @htmlspecialchars($test_str, ENT_COMPAT, $this->encoding); + } + $close_pos = strpos($part, "\n", $i); + $oops = false; + if ($close_pos === false) { + $close_pos = strlen($part); + $oops = true; + } + $test_str .= @htmlspecialchars(substr($part, $i + $com_len, $close_pos - $i - $com_len), ENT_COMPAT, $this->encoding); + if ($this->lexic_permissions['COMMENTS'][$comment_key]) { + $test_str .= ""; + } + // Take into account that the comment might be the last in the source + if (!$oops) { + $test_str .= "\n"; + } + $i = $close_pos; + // parse the rest + $result .= $this->parse_non_string_part($stuff_to_parse); + $stuff_to_parse = ''; + break; + } + } + } + } elseif ($STRING_OPEN != '') { + // Otherwise, convert it to HTML form + if (strtolower($this->encoding) == 'utf-8') { + //only escape <128 (we don't want to break multibyte chars) + if (ord($char) < 128) { + $char = @htmlspecialchars($char, ENT_COMPAT, $this->encoding); + } + } else { + //encode everthing + $char = @htmlspecialchars($char, ENT_COMPAT, $this->encoding); + } + } + // Where are we adding this char? + if (!$COMMENT_MATCHED) { + if (($STRING_OPEN == '') && !$CLOSE_STRING) { + $stuff_to_parse .= $char; + } else { + $result .= $char; + $CLOSE_STRING = false; + } + } else { + $result .= $test_str; + $COMMENT_MATCHED = false; + } + } + // Parse the last bit + $result .= $this->parse_non_string_part($stuff_to_parse); + $stuff_to_parse = ''; + } else { + $result .= @htmlspecialchars($part, ENT_COMPAT, $this->encoding); + } + // Close the that surrounds the block + if ($this->strict_mode && $this->language_data['STYLES']['SCRIPT'][$script_key] != '' && + $this->lexic_permissions['SCRIPT']) { + $result .= ''; + } + } else { + // Else not a block to highlight + $result .= @htmlspecialchars($part, ENT_COMPAT, $this->encoding); + } + } + + // Parse the last stuff (redundant?) + $result .= $this->parse_non_string_part($stuff_to_parse); + + // Lop off the very first and last spaces + $result = substr($result, 1, strlen($result) - 1); + + // Are we still in a string? + if ($STRING_OPEN) { + $result .= ''; + } + + // We're finished: stop timing + $this->set_time($start_time, microtime()); + + return $this->finalise($result); + } + + /** + * Swaps out spaces and tabs for HTML indentation. Not needed if + * the code is in a pre block... + * + * @param string The source to indent + * @return string The source with HTML indenting applied + * @since 1.0.0 + * @access private + */ + function indent ($result) + { + /// Replace tabs with the correct number of spaces + if (false !== strpos($result, "\t")) { + $lines = explode("\n", $result); + foreach ($lines as $key => $line) { + if (false === strpos($line, "\t")) { + $lines[$key] = $line; + continue; + }//echo 'checking line ' . $key . '
    '; + + $pos = 0; + $tab_width = $this->tab_width; + $length = strlen($line); + $result_line = ''; + + //echo '
    line: ' . htmlspecialchars($line) . '
    '; + $IN_TAG = false; + for ($i = 0; $i < $length; $i++) { + $char = substr($line, $i, 1); + // Simple engine to work out whether we're in a tag. + // If we are we modify $pos. This is so we ignore HTML + // in the line and only workout the tab replacement + // via the actual content of the string + // This test could be improved to include strings in the + // html so that < or > would be allowed in user's styles + // (e.g. quotes: '<' '>'; or similar) + if ($IN_TAG && '>' == $char) { + $IN_TAG = false; + $result_line .= '>'; + ++$pos; + } elseif (!$IN_TAG && '<' == $char) { + $IN_TAG = true; + $result_line .= '<'; + ++$pos; + } elseif (!$IN_TAG && '&' == $char) { + //echo "matched & in line... "; + $substr = substr($line, $i + 3, 4); + //$substr_5 = substr($line, 5, 1); + $posi = strpos($substr, ';'); + if (false !== $posi) { + //echo "found entity at $posi\n"; + $pos += $posi + 3; + } + $result_line .= '&'; + } elseif (!$IN_TAG && "\t" == $char) { + $str = ''; + // OPTIMISE - move $strs out. Make an array: + // $tabs = array( + // 1 => ' ', + // 2 => '  ', + // 3 => '   ' etc etc + // to use instead of building a string every time + $strs = array(0 => ' ', 1 => ' '); + //echo "building (pos=$pos i=$i) (" . ($i - $pos) . ") " . ($tab_width - (($i - $pos) % $tab_width)) . " spaces\n"; + for ($k = 0; $k < ($tab_width - (($i - $pos) % $tab_width)); $k++) $str .= $strs[$k % 2]; + $result_line .= $str; + //$pos--; + $pos++; + //$pos -= $tab_width-1; + + if (false === strpos($line, "\t", $i + 1)) { + //$lines[$key] = $result_line; + //echo 'got here'; + $result_line .= substr($line, $i + 1); + break; + } + } elseif ( $IN_TAG ) { + ++$pos; + $result_line .= $char; + } else { + $result_line .= $char; + //++$pos; + } + } + $lines[$key] = $result_line; + } + $result = implode("\n", $lines); + } + // Other whitespace + $result = str_replace(' ', '  ', $result); + $result = str_replace(' ', '  ', $result); + $result = str_replace("\n ", "\n ", $result); + + if ($this->line_numbers == GESHI_NO_LINE_NUMBERS) { + $result = nl2br($result); + } + return $result; + } + + /** + * Changes the case of a keyword for those languages where a change is asked for + * + * @param string The keyword to change the case of + * @return string The keyword with its case changed + * @since 1.0.0 + * @access private + */ + function change_case ($instr) + { + if ($this->language_data['CASE_KEYWORDS'] == GESHI_CAPS_UPPER) { + return strtoupper($instr); + } elseif ($this->language_data['CASE_KEYWORDS'] == GESHI_CAPS_LOWER) { + return strtolower($instr); + } + return $instr; + } + + /** + * Adds a url to a keyword where needed. + * + * @param string The keyword to add the URL HTML to + * @param int What group the keyword is from + * @param boolean Whether to get the HTML for the start or end + * @return The HTML for either the start or end of the HTML <a> tag + * @since 1.0.2 + * @access private + * @todo Get rid of ender + */ + function add_url_to_keyword ($keyword, $group, $start_or_end) + { + if (isset($this->language_data['URLS'][$group]) && + $this->language_data['URLS'][$group] != '' && + substr($keyword, 0, 5) != '</') { + // There is a base group for this keyword + if ($start_or_end == 'BEGIN') { + // HTML workaround... not good form (tm) but should work for 1.0.X + $keyword = ( substr($keyword, 0, 4) == '<' ) ? substr($keyword, 4) : $keyword; + $keyword = ( substr($keyword, -4) == '>' ) ? substr($keyword, 0, strlen($keyword) - 4) : $keyword; + if ($keyword != '') { + $keyword = ( $this->language_data['CASE_SENSITIVE'][$group] ) ? $keyword : strtolower($keyword); + return '<|UR1|"' . + str_replace( + array('{FNAME}', '.'), + array(@htmlspecialchars($keyword, ENT_COMPAT, $this->encoding), ''), + $this->language_data['URLS'][$group] + ) . '">'; + } + return ''; + // HTML fix. Again, dirty hackage... + } elseif (!($this->language == 'html4strict' && '>' == $keyword)) { + return ''; + } + } + } + + /** + * Takes a string that has no strings or comments in it, and highlights + * stuff like keywords, numbers and methods. + * + * @param string The string to parse for keyword, numbers etc. + * @since 1.0.0 + * @access private + * @todo BUGGY! Why? Why not build string and return? + */ + function parse_non_string_part (&$stuff_to_parse) + { + $stuff_to_parse = ' ' . quotemeta(@htmlspecialchars($stuff_to_parse, ENT_COMPAT, $this->encoding)); + // These vars will disappear in the future + $func = '$this->change_case'; + $func2 = '$this->add_url_to_keyword'; + + // + // Regular expressions + // + foreach ($this->language_data['REGEXPS'] as $key => $regexp) { + if ($this->lexic_permissions['REGEXPS'][$key]) { + if (is_array($regexp)) { + $stuff_to_parse = preg_replace( + "#" . + $regexp[GESHI_SEARCH] . + "#{$regexp[GESHI_MODIFIERS]}", + "{$regexp[GESHI_BEFORE]}<|!REG3XP$key!>{$regexp[GESHI_REPLACE]}|>{$regexp[GESHI_AFTER]}", + $stuff_to_parse + ); + } else { + $stuff_to_parse = preg_replace( "#(" . $regexp . ")#", "<|!REG3XP$key!>\\1|>", $stuff_to_parse); + } + } + } + + // + // Highlight numbers. This regexp sucks... anyone with a regexp that WORKS + // here wins a cookie if they send it to me. At the moment there's two doing + // almost exactly the same thing, except the second one prevents a number + // being highlighted twice (eg 5) + // Put /NUM!/ in for the styles, which gets replaced at the end. + // + if ($this->lexic_permissions['NUMBERS'] && preg_match('#[0-9]#', $stuff_to_parse )) { + $stuff_to_parse = preg_replace('#([^a-zA-Z0-9\#])([0-9]+)([^a-zA-Z0-9])#', "\\1<|/NUM!/>\\2|>\\3", $stuff_to_parse); + $stuff_to_parse = preg_replace('#([^a-zA-Z0-9\#>])([0-9]+)([^a-zA-Z0-9])#', "\\1<|/NUM!/>\\2|>\\3", $stuff_to_parse); + } + + // Highlight keywords + // if there is a couple of alpha symbols there *might* be a keyword + if (preg_match('#[a-zA-Z]{2,}#', $stuff_to_parse)) { + foreach ($this->language_data['KEYWORDS'] as $k => $keywordset) { + if ($this->lexic_permissions['KEYWORDS'][$k]) { + foreach ($keywordset as $keyword) { + $keyword = quotemeta($keyword); + // + // This replacement checks the word is on it's own (except if brackets etc + // are next to it), then highlights it. We don't put the color=" for the span + // in just yet - otherwise languages with the keywords "color" or "or" have + // a fit. + // + if (false !== stristr($stuff_to_parse, $keyword )) { + $stuff_to_parse .= ' '; + // 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 ;)) + $styles = "/$k/"; + $keyword = quotemeta($keyword); + if ($this->language_data['CASE_SENSITIVE'][$k]) { + $stuff_to_parse = preg_replace( + "#([^a-zA-Z0-9\$_\|\#;>])($keyword)([^a-zA-Z0-9_<\|%\-&])#e", + "'\\1' . $func2('\\2', '$k', 'BEGIN') . '<|$styles>' . $func('\\2') . '|>' . $func2('\\2', '$k', 'END') . '\\3'", + $stuff_to_parse + ); + } else { + // Change the case of the word. + $stuff_to_parse = preg_replace( + "#([^a-zA-Z0-9\$_\|\#;>])($keyword)([^a-zA-Z0-9_<\|%\-&])#ie", + "'\\1' . $func2('\\2', '$k', 'BEGIN') . '<|$styles>' . $func('\\2') . '|>' . $func2('\\2', '$k', 'END') . '\\3'", + $stuff_to_parse + ); + } + $stuff_to_parse = substr($stuff_to_parse, 0, strlen($stuff_to_parse) - 1); + } + } + } + } + } + + // + // Now that's all done, replace /[number]/ with the correct styles + // + foreach ($this->language_data['KEYWORDS'] as $k => $kws) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['KEYWORDS'][$k] . '"'; + } else { + $attributes = ' class="kw' . $k . '"'; + } + $stuff_to_parse = str_replace("/$k/", $attributes, $stuff_to_parse); + } + + // Put number styles in + if (!$this->use_classes && $this->lexic_permissions['NUMBERS']) { + $attributes = ' style="' . $this->language_data['STYLES']['NUMBERS'][0] . '"'; + } else { + $attributes = ' class="nu0"'; + } + $stuff_to_parse = str_replace('/NUM!/', $attributes, $stuff_to_parse); + + // + // Highlight methods and fields in objects + // + if ($this->lexic_permissions['METHODS'] && $this->language_data['OOLANG']) { + foreach ($this->language_data['OBJECT_SPLITTERS'] as $key => $splitter) { + if (false !== stristr($stuff_to_parse, $splitter)) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['METHODS'][$key] . '"'; + } else { + $attributes = ' class="me' . $key . '"'; + } + $stuff_to_parse = preg_replace("#(" . quotemeta($this->language_data['OBJECT_SPLITTERS'][$key]) . "[\s]*)([a-zA-Z\*\(][a-zA-Z0-9_\*]*)#", "\\1<|$attributes>\\2|>", $stuff_to_parse); + } + } + } + + // + // Highlight brackets. Yes, I've tried adding a semi-colon to this list. + // You try it, and see what happens ;) + // TODO: Fix lexic permissions not converting entities if shouldn't + // be highlighting regardless + // + if ($this->lexic_permissions['BRACKETS']) { + $code_entities_match = array('[', ']', '(', ')', '{', '}'); + if (!$this->use_classes) { + $code_entities_replace = array( + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">[|>', + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">]|>', + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">(|>', + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">)|>', + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">{|>', + '<| style="' . $this->language_data['STYLES']['BRACKETS'][0] . '">}|>', + ); + } else { + $code_entities_replace = array( + '<| class="br0">[|>', + '<| class="br0">]|>', + '<| class="br0">(|>', + '<| class="br0">)|>', + '<| class="br0">{|>', + '<| class="br0">}|>', + ); + } + $stuff_to_parse = str_replace( $code_entities_match, $code_entities_replace, $stuff_to_parse ); + } + + // + // Add class/style for regexps + // + foreach ($this->language_data['REGEXPS'] as $key => $regexp) { + if ($this->lexic_permissions['REGEXPS'][$key]) { + if (!$this->use_classes) { + $attributes = ' style="' . $this->language_data['STYLES']['REGEXPS'][$key] . '"'; + } else { + $attributes = ' class="re' . $key . '"'; + } + $stuff_to_parse = str_replace("!REG3XP$key!", "$attributes", $stuff_to_parse); + } + } + + // Replace with . for urls + $stuff_to_parse = str_replace('', '.', $stuff_to_parse); + // Replace <|UR1| with link_styles[GESHI_LINK])) { + if ($this->use_classes) { + $stuff_to_parse = str_replace('<|UR1|', 'link_target . ' href=', $stuff_to_parse); + } else { + $stuff_to_parse = str_replace('<|UR1|', 'link_target . ' style="' . $this->link_styles[GESHI_LINK] . '" href=', $stuff_to_parse); + } + } else { + $stuff_to_parse = str_replace('<|UR1|', 'link_target . ' href=', $stuff_to_parse); + } + + // + // NOW we add the span thingy ;) + // + + $stuff_to_parse = str_replace('<|', '', '', $stuff_to_parse ); + + return substr(stripslashes($stuff_to_parse), 1); + } + + /** + * Sets the time taken to parse the code + * + * @param microtime The time when parsing started + * @param microtime The time when parsing ended + * @since 1.0.2 + * @access private + */ + function set_time ($start_time, $end_time) + { + $start = explode(' ', $start_time); + $end = explode(' ', $end_time); + $this->time = $end[0] + $end[1] - $start[0] - $start[1]; + } + + /** + * Gets the time taken to parse the code + * + * @return double The time taken to parse the code + * @since 1.0.2 + */ + function get_time () + { + return $this->time; + } + + /** + * Gets language information and stores it for later use + * + * @access private + * @todo Needs to load keys for lexic permissions for keywords, regexps etc + */ + function load_language ($file_name) + { + $language_data = array(); + require $file_name; + // Perhaps some checking might be added here later to check that + // $language data is a valid thing but maybe not + $this->language_data = $language_data; + // Set strict mode if should be set + if ($this->language_data['STRICT_MODE_APPLIES'] == GESHI_ALWAYS) { + $this->strict_mode = true; + } + // Set permissions for all lexics to true + // so they'll be highlighted by default + foreach ($this->language_data['KEYWORDS'] as $key => $words) { + $this->lexic_permissions['KEYWORDS'][$key] = true; + } + foreach ($this->language_data['COMMENT_SINGLE'] as $key => $comment) { + $this->lexic_permissions['COMMENTS'][$key] = true; + } + foreach ($this->language_data['REGEXPS'] as $key => $regexp) { + $this->lexic_permissions['REGEXPS'][$key] = true; + } + $this->enable_highlighting(); + // Set default class for CSS + $this->overall_class = $this->language; + } + + /** + * Takes the parsed code and various options, and creates the HTML + * surrounding it to make it look nice. + * + * @param string The code already parsed + * @return string The code nicely finalised + * @since 1.0.0 + * @access private + */ + function finalise ($parsed_code) + { + // Remove end parts of important declarations + // This is BUGGY!! My fault for bad code: fix coming in 1.2 + // @todo Remove this crap + if ($this->enable_important_blocks && + (strstr($parsed_code, @htmlspecialchars(GESHI_START_IMPORTANT, ENT_COMPAT, $this->encoding)) === false)) { + $parsed_code = str_replace(@htmlspecialchars(GESHI_END_IMPORTANT, ENT_COMPAT, $this->encoding), '', $parsed_code); + } + + // Add HTML whitespace stuff if we're using the
    header + if ($this->header_type != GESHI_HEADER_PRE) { + $parsed_code = $this->indent($parsed_code); + } + + // If we're using line numbers, we insert
  • s and appropriate + // markup to style them (otherwise we don't need to do anything) + if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) { + // If we're using the 
     header, we shouldn't add newlines because
+            // the 
     will line-break them (and the 
  • s already do this for us)
+            $ls = ($this->header_type != GESHI_HEADER_PRE) ? "\n" : '';
+            // Get code into lines
+            $code = explode("\n", $parsed_code);
+            // Set vars to defaults for following loop
+            $parsed_code = '';
+            $i = 0;
+            // Foreach line...
+            foreach ($code as $line) {
+                $line = ( $line ) ? $line : ' ';
+                // If this is a "special line"...
+        	    if ($this->line_numbers == GESHI_FANCY_LINE_NUMBERS &&
+                    $i % $this->line_nth_row == ($this->line_nth_row - 1)) {
+            		// Set the attributes to style the line
+                    if ($this->use_classes) {
+            			$attr = ' class="li2"';
+            			$def_attr = ' class="de2"';
+                    } else {
+            			$attr = ' style="' . $this->line_style2 . '"';
+            			// This style "covers up" the special styles set for special lines
+            			// so that styles applied to special lines don't apply to the actual
+            			// code on that line
+            			$def_attr = ' style="' . $this->code_style . '"';
+                    }
+            		// Span or div?
+            		$start = "";
+            		$end = '';
+            	} else {
+            		if ($this->use_classes) {
+                        $attr = ' class="li1"';
+            			$def_attr = ' class="de1"';
+            		} else {
+                        $attr = ' style="' . $this->line_style1 . '"';
+            			$def_attr = ' style="' . $this->code_style . '"';
+            		}
+            		$start = "";
+            		$end = '';
+            	}
+        
+            	++$i;
+            	// Are we supposed to use ids? If so, add them
+            	if ($this->add_ids) {
+            		$attr .= " id=\"{$this->overall_id}-{$i}\"";
+            	}
+            	if ($this->use_classes && in_array($i, $this->highlight_extra_lines)) {
+            		$attr .= " class=\"ln-xtra\"";
+            	}
+            	if (!$this->use_classes && in_array($i, $this->highlight_extra_lines)) {
+            		$attr .= " style=\"{$this->highlight_extra_lines_style}\"";
+            	}
+
+            	// Add in the line surrounded by appropriate list HTML
+            	$parsed_code .= "$start$line$end
    • $ls";
+        	}
+        } else {
+            // No line numbers, but still need to handle highlighting lines extra.
+            // Have to use divs so the full width of the code is highlighted
+            $code = explode("\n", $parsed_code);
+            $parsed_code = '';
+            $i = 0;
+            foreach ($code as $line)
+            {
+            	// Make lines have at least one space in them if they're empty
+            	$line = ($line) ? $line : ' ';
+            	if (in_array(++$i, $this->highlight_extra_lines)) {
+            		if ($this->use_classes) {
+            			$parsed_code .= '
    ';
+            		} else {
+            			$parsed_code .= "
    highlight_extra_lines_style}\">";
+            		}
+            		$parsed_code .= $line . "
    \n";
+            	} else {
+            		$parsed_code .= $line . "\n";
+            	}
+        	}
+        }
+        
+        // purge some unnecessary stuff
+        $parsed_code = preg_replace('#]+>(\s*)#', '\\1', $parsed_code);
+        $parsed_code = preg_replace('#]+>(\s*)
    #', '\\1', $parsed_code);
+        
+        if ($this->header_type == GESHI_HEADER_PRE) {
+        	// enforce line numbers when using pre
+            $parsed_code = str_replace('
  • ', '
  •  
    • ', $parsed_code);
+        }
+        
+        return $this->header() . chop($parsed_code) . $this->footer();
+    }
+
+	/**
+	 * Creates the header for the code block (with correct attributes)
+     * 
+     * @return string The header for the code block
+     * @since  1.0.0
+     * @access private
+	 */
+	function header ()
+	{
+		// Get attributes needed
+		$attributes = $this->get_attributes();
+
+		$ol_attributes = '';
+
+		if ($this->line_numbers_start != 1) {
+			$ol_attributes .= ' start="' . $this->line_numbers_start . '"';
+		}
+
+		// Get the header HTML
+		$header = $this->format_header_content();
+
+        if (GESHI_HEADER_NONE == $this->header_type) {
+            if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) {
+                return "$header";
+            }
+            return $header;
+        }
+        
+		// Work out what to return and do it
+		if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) {
+			if ($this->header_type == GESHI_HEADER_PRE) {
+				return "$header";
+			} elseif ($this->header_type == GESHI_HEADER_DIV) {
+				return "$header";
+			}
+		} else {
+			if ($this->header_type == GESHI_HEADER_PRE) {
+				return "$header";
+			} elseif ($this->header_type == GESHI_HEADER_DIV) {
+				return "$header";
+			}
+		}
+	}
+
+	/**
+	 * Returns the header content, formatted for output
+     * 
+     * @return string The header content, formatted for output
+     * @since  1.0.2
+     * @access private
+	 */
+	function format_header_content ()
+	{
+		$header = $this->header_content;
+		if ($header) {
+			if ($this->header_type == GESHI_HEADER_PRE) {
+				$header = str_replace("\n", '', $header);
+			}
+			$header = $this->replace_keywords($header);
+
+			if ($this->use_classes) {
+				$attr = ' class="head"';
+			} else {
+				$attr = " style=\"{$this->header_content_style}\"";
+			}
+			return "$header";
+		}
+	}
+
+	/**
+	 * Returns the footer for the code block.
+     * 
+     * @return string The footer for the code block
+     * @since  1.0.0
+     * @access private
+	 */
+	function footer ()
+	{
+		$footer_content = $this->format_footer_content();
+
+        if (GESHI_HEADER_NONE == $this->header_type) {
+            return ($this->line_numbers != GESHI_NO_LINE_NUMBERS) ? '' . $footer_content
+                : $footer_content;
+        }
+        
+		if ($this->header_type == GESHI_HEADER_DIV) {
+			if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) {
+				return "$footer_content";
+			}
+			return "$footer_content";
+		} else {
+			if ($this->line_numbers != GESHI_NO_LINE_NUMBERS) {
+				return "$footer_content
    ";
+			}
+			return "$footer_content
    "; + } + } + + /** + * Returns the footer content, formatted for output + * + * @return string The footer content, formatted for output + * @since 1.0.2 + * @access private + */ + function format_footer_content () + { + $footer = $this->footer_content; + if ($footer) { + if ($this->header_type == GESHI_HEADER_PRE) { + $footer = str_replace("\n", '', $footer);; + } + $footer = $this->replace_keywords($footer); + + if ($this->use_classes) { + $attr = ' class="foot"'; + } else { + $attr = " style=\"{$this->footer_content_style}\""; + } + return "$footer"; + } + } + + /** + * Replaces certain keywords in the header and footer with + * certain configuration values + * + * @param string The header or footer content to do replacement on + * @return string The header or footer with replaced keywords + * @since 1.0.2 + * @access private + */ + function replace_keywords ($instr) + { + $keywords = $replacements = array(); + + $keywords[] = '