From db6bd48e2087ad330f9ccac64eb47cb5f962d613 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fran=C3=A7ois=20Poulain?= Date: Sat, 8 Aug 2020 16:56:52 +0200 Subject: [PATCH] ref(convert): filtrage html directement via le module drupal --- README.md | 3 + drupal2spip_lal/base/convert.py | 45 +- drupal2spip_lal/base/php/auto_p.php | 9 + drupal2spip_lal/base/php/drupal6/LICENSE | 339 +++++ .../php/drupal6/modules/filter/filter.module | 1255 +++++++++++++++++ 5 files changed, 1619 insertions(+), 32 deletions(-) create mode 100644 drupal2spip_lal/base/php/auto_p.php create mode 100644 drupal2spip_lal/base/php/drupal6/LICENSE create mode 100644 drupal2spip_lal/base/php/drupal6/modules/filter/filter.module diff --git a/README.md b/README.md index 198193f..01dc07e 100644 --- a/README.md +++ b/README.md @@ -109,3 +109,6 @@ There is some additional rules when developing, which are mainly wrappers for drupal2spip_lal is developed by François Poulain (April) and licensed under the [AGPLv3+](LICENSE). Its basis comes from https://forge.cliss21.org/cliss21/cookiecutter-django/ + +It embed code from Drupal 6 in drupal2spip_lal/base/php. This code is licensed +under the [GPLv2+](LICENSE). diff --git a/drupal2spip_lal/base/convert.py b/drupal2spip_lal/base/convert.py index 727ad4e..5cf4155 100644 --- a/drupal2spip_lal/base/convert.py +++ b/drupal2spip_lal/base/convert.py @@ -3,6 +3,7 @@ import os import re from datetime import datetime from itertools import groupby +from subprocess import PIPE, Popen from django.conf import settings from django.utils.timezone import make_aware, now @@ -13,14 +14,6 @@ from bs4 import BeautifulSoup as bs from drupal2spip_lal.drupal import models as drupal from drupal2spip_lal.spip import models as spip -# Questions -# - quelle utilisation des rubriques ? -# - quelle hiérarchie des mots clés ? -# - autobr sélectif ? -# - importer les drupaleries ? (fn, toc, etc.) + autobr selon le format -# - convertir en format SPIP ? - - logger = logging.getLogger('drupal2spip_lal') @@ -111,33 +104,21 @@ def fetch_and_remove_logo(article, force_download): def filter_html(html): - inline_elems = ['a', 'em', 'strong', 'cite', 'code', 'b', 'i'] - block_elems = ['p', 'dd', 'dt', 'dl', 'ul', 'ol', 'li', 'h2', 'h3', 'h4', 'img', 'audio', 'video'] - - def explicit_double_br(html): - double_br = re.compile(r'<\s*br\s*/?>\s*\n|\n\s*<\s*br\s*/?>') - return double_br.sub('\n\n', html) - def auto_p(html): - re_paragraph = re.compile(r'\s*\n\s*\n\s*') - return re_paragraph.sub('

', html) + """ + La façon la plus simple de reproduire le comportement de drupal + est de reprendre le code php. + """ + current_path = os.path.dirname(__file__) + script = os.path.join(current_path, 'php/auto_p.php') + try: + with Popen(['php', '-f', script], stdin=PIPE, stdout=PIPE) as proc: + stdout = proc.communicate(html.encode('utf8')) + return stdout[0].decode('utf8') + except Exception as e: + raise ValueError("Echec de auto_p: {}".format(e)) - def auto_br(html): - re_break = re.compile(r'\s*\n\s*') - return re_break.sub('
', html) - - def remove_spare_br(html): - soup = bs(html, 'html.parser') - # ou dernier premier élément d'un parent de type bloc - def spare_br(elem): - return elem.name == 'br' and getattr(elem.parent, 'name', None) in block_elems and not (elem.next_sibling and elem.previous_sibling) - [elem.clear() for elem in soup.find_all(spare_br)] - return str(soup) - - html = explicit_double_br(html) html = auto_p(html) - html = auto_br(html) - html = remove_spare_br(html) return html diff --git a/drupal2spip_lal/base/php/auto_p.php b/drupal2spip_lal/base/php/auto_p.php new file mode 100644 index 0000000..e44f443 --- /dev/null +++ b/drupal2spip_lal/base/php/auto_p.php @@ -0,0 +1,9 @@ + diff --git a/drupal2spip_lal/base/php/drupal6/LICENSE b/drupal2spip_lal/base/php/drupal6/LICENSE new file mode 100644 index 0000000..d159169 --- /dev/null +++ b/drupal2spip_lal/base/php/drupal6/LICENSE @@ -0,0 +1,339 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + 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 Lesser 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., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 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 Lesser General +Public License instead of this License. diff --git a/drupal2spip_lal/base/php/drupal6/modules/filter/filter.module b/drupal2spip_lal/base/php/drupal6/modules/filter/filter.module new file mode 100644 index 0000000..6ea0537 --- /dev/null +++ b/drupal2spip_lal/base/php/drupal6/modules/filter/filter.module @@ -0,0 +1,1255 @@ +'. t("The filter module allows administrators to configure text input formats for use on your site. An input format defines the HTML tags, codes, and other input allowed in both content and comments, and is a key feature in guarding against potentially damaging input from malicious users. Two input formats included by default are Filtered HTML (which allows only an administrator-approved subset of HTML tags) and Full HTML (which allows the full set of HTML tags). Additional input formats may be created by an administrator.") .'

'; + $output .= '

'. t('Each input format uses filters to manipulate text, and most input formats apply several different filters to text in a specific order. Each filter is designed for a specific purpose, and generally either adds, removes or transforms elements within user-entered text before it is displayed. A filter does not change the actual content of a post, but instead, modifies it temporarily before it is displayed. A filter may remove unapproved HTML tags, for instance, while another automatically adds HTML to make links referenced in text clickable.') .'

'; + $output .= '

'. t('Users can choose between the available input formats when creating or editing content. Administrators can configure which input formats are available to which user roles, as well as choose a default input format.') .'

'; + $output .= '

'. t('For more information, see the online handbook entry for Filter module.', array('@filter' => 'http://drupal.org/handbook/modules/filter/')) .'

'; + return $output; + case 'admin/settings/filters': + $output = '

'. t('Input formats define a way of processing user-supplied text in Drupal. Each input format uses filters to manipulate text, and most input formats apply several different filters to text, in a specific order. Each filter is designed to accomplish a specific purpose, and generally either removes elements from or adds elements to text before it is displayed. Users can choose between the available input formats when submitting content.') .'

'; + $output .= '

'. t('Use the list below to configure which input formats are available to which roles, as well as choose a default input format (used for imported content, for example). The default format is always available to users. All input formats are available to users in a role with the "administer filters" permission.') .'

'; + return $output; + case 'admin/settings/filters/%': + return '

'. t('Every filter performs one particular change on the user input, for example stripping out malicious HTML or making URLs clickable. Choose which filters you want to apply to text in this input format. If you notice some filters are causing conflicts in the output, you can rearrange them.', array('@rearrange' => url('admin/settings/filters/'. $arg[3] .'/order'))) .'

'; + case 'admin/settings/filters/%/configure': + return '

'. t('If you cannot find the settings for a certain filter, make sure you have enabled it on the view tab first.', array('@url' => url('admin/settings/filters/'. $arg[3]))) .'

'; + case 'admin/settings/filters/%/order': + $output = '

'. t('Because of the flexible filtering system, you might encounter a situation where one filter prevents another from doing its job. For example: a word in an URL gets converted into a glossary term, before the URL can be converted to a clickable link. When this happens, rearrange the order of the filters.') .'

'; + $output .= '

'. t("Filters are executed from top-to-bottom. To change the order of the filters, modify the values in the Weight column or grab a drag-and-drop handle under the Name column and drag filters to new locations in the list. (Grab a handle by clicking and holding the mouse while hovering over a handle icon.) Remember that your changes will not be saved until you click the Save configuration button at the bottom of the page.") .'

'; + return $output; + } +} + +/** + * Implementation of hook_theme() + */ +function filter_theme() { + return array( + 'filter_admin_overview' => array( + 'arguments' => array('form' => NULL), + 'file' => 'filter.admin.inc', + ), + 'filter_admin_order' => array( + 'arguments' => array('form' => NULL), + 'file' => 'filter.admin.inc', + ), + 'filter_tips' => array( + 'arguments' => array('tips' => NULL, 'long' => FALSE, 'extra' => ''), + 'file' => 'filter.pages.inc', + ), + 'filter_tips_more_info' => array( + 'arguments' => array(), + ), + ); +} + +/** + * Implementation of hook_menu(). + */ +function filter_menu() { + $items['admin/settings/filters'] = array( + 'title' => 'Input formats', + 'description' => 'Configure how content input by users is filtered, including allowed HTML tags. Also allows enabling of module-provided filters.', + 'page callback' => 'drupal_get_form', + 'page arguments' => array('filter_admin_overview'), + 'access arguments' => array('administer filters'), + 'file' => 'filter.admin.inc', + ); + $items['admin/settings/filters/list'] = array( + 'title' => 'List', + 'type' => MENU_DEFAULT_LOCAL_TASK, + ); + $items['admin/settings/filters/add'] = array( + 'title' => 'Add input format', + 'page callback' => 'filter_admin_format_page', + 'access arguments' => array('administer filters'), + 'type' => MENU_LOCAL_TASK, + 'weight' => 1, + 'file' => 'filter.admin.inc', + ); + $items['admin/settings/filters/delete'] = array( + 'title' => 'Delete input format', + 'page callback' => 'drupal_get_form', + 'page arguments' => array('filter_admin_delete'), + 'access arguments' => array('administer filters'), + 'type' => MENU_CALLBACK, + 'file' => 'filter.admin.inc', + ); + $items['filter/tips'] = array( + 'title' => 'Compose tips', + 'page callback' => 'filter_tips_long', + 'access callback' => TRUE, + 'type' => MENU_SUGGESTED_ITEM, + 'file' => 'filter.pages.inc', + ); + $items['admin/settings/filters/%filter_format'] = array( + 'type' => MENU_CALLBACK, + 'title callback' => 'filter_admin_format_title', + 'title arguments' => array(3), + 'page callback' => 'filter_admin_format_page', + 'page arguments' => array(3), + 'access arguments' => array('administer filters'), + 'file' => 'filter.admin.inc', + ); + + $items['admin/settings/filters/%filter_format/edit'] = array( + 'title' => 'Edit', + 'type' => MENU_DEFAULT_LOCAL_TASK, + 'weight' => 0, + 'file' => 'filter.admin.inc', + ); + $items['admin/settings/filters/%filter_format/configure'] = array( + 'title' => 'Configure', + 'page callback' => 'filter_admin_configure_page', + 'page arguments' => array(3), + 'access arguments' => array('administer filters'), + 'type' => MENU_LOCAL_TASK, + 'weight' => 1, + 'file' => 'filter.admin.inc', + ); + $items['admin/settings/filters/%filter_format/order'] = array( + 'title' => 'Rearrange', + 'page callback' => 'filter_admin_order_page', + 'page arguments' => array(3), + 'access arguments' => array('administer filters'), + 'type' => MENU_LOCAL_TASK, + 'weight' => 2, + 'file' => 'filter.admin.inc', + ); + return $items; +} + +function filter_format_load($arg) { + return filter_formats($arg); +} + +/** + * Display a filter format form title. + */ +function filter_admin_format_title($format) { + return $format->name; +} + +/** + * Implementation of hook_perm(). + */ +function filter_perm() { + return array('administer filters'); +} + +/** + * Implementation of hook_cron(). + * + * Expire outdated filter cache entries + */ +function filter_cron() { + cache_clear_all(NULL, 'cache_filter'); +} + +/** + * Implementation of hook_filter_tips(). + */ +function filter_filter_tips($delta, $format, $long = FALSE) { + global $base_url; + switch ($delta) { + case 0: + if (variable_get("filter_html_$format", FILTER_HTML_STRIP) == FILTER_HTML_STRIP) { + if ($allowed_html = variable_get("allowed_html_$format", '
    1. ')) { + switch ($long) { + case 0: + return t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)); + case 1: + $output = '

      '. t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)) .'

      '; + if (!variable_get("filter_html_help_$format", 1)) { + return $output; + } + + $output .= t(' +

      This site allows HTML content. While learning all of HTML may feel intimidating, learning how to use a very small number of the most basic HTML "tags" is very easy. This table provides examples for each tag that is enabled on this site.

      +

      For more information see W3C\'s HTML Specifications or use your favorite search engine to find other sites that explain HTML.

      '); + $tips = array( + 'a' => array( t('Anchors are used to make links to other pages.'), ''. variable_get('site_name', 'Drupal') .''), + 'br' => array( t('By default line break tags are automatically added, so use this tag to add additional ones. Use of this tag is different because it is not used with an open/close pair like all the others. Use the extra " /" inside the tag to maintain XHTML 1.0 compatibility'), t('Text with
      line break')), + 'p' => array( t('By default paragraph tags are automatically added, so use this tag to add additional ones.'), '

      '. t('Paragraph one.') .'

      '. t('Paragraph two.') .'

      '), + 'strong' => array( t('Strong'), ''. t('Strong') .''), + 'em' => array( t('Emphasized'), ''. t('Emphasized') .''), + 'cite' => array( t('Cited'), ''. t('Cited') .''), + 'code' => array( t('Coded text used to show programming source code'), ''. t('Coded') .''), + 'b' => array( t('Bolded'), ''. t('Bolded') .''), + 'u' => array( t('Underlined'), ''. t('Underlined') .''), + 'i' => array( t('Italicized'), ''. t('Italicized') .''), + 'sup' => array( t('Superscripted'), t('Superscripted')), + 'sub' => array( t('Subscripted'), t('Subscripted')), + 'pre' => array( t('Preformatted'), '
      '. t('Preformatted') .'
      '), + 'abbr' => array( t('Abbreviation'), t('Abbrev.')), + 'acronym' => array( t('Acronym'), t('TLA')), + 'blockquote' => array( t('Block quoted'), '
      '. t('Block quoted') .'
      '), + 'q' => array( t('Quoted inline'), ''. t('Quoted inline') .''), + // Assumes and describes tr, td, th. + 'table' => array( t('Table'), '
      '. t('Table header') .'
      '. t('Table cell') .'
      '), + 'tr' => NULL, 'td' => NULL, 'th' => NULL, + 'del' => array( t('Deleted'), ''. t('Deleted') .''), + 'ins' => array( t('Inserted'), ''. t('Inserted') .''), + // Assumes and describes li. + 'ol' => array( t('Ordered list - use the <li> to begin each list item'), '
      1. '. t('First item') .'
      2. '. t('Second item') .'
      '), + 'ul' => array( t('Unordered list - use the <li> to begin each list item'), '
      • '. t('First item') .'
      • '. t('Second item') .'
      '), + 'li' => NULL, + // Assumes and describes dt and dd. + 'dl' => array( t('Definition lists are similar to other HTML lists. <dl> begins the definition list, <dt> begins the definition term and <dd> begins the definition description.'), '
      '. t('First term') .'
      '. t('First definition') .'
      '. t('Second term') .'
      '. t('Second definition') .'
      '), + 'dt' => NULL, 'dd' => NULL, + 'h1' => array( t('Header'), '

      '. t('Title') .'

      '), + 'h2' => array( t('Header'), '

      '. t('Subtitle') .'

      '), + 'h3' => array( t('Header'), '

      '. t('Subtitle three') .'

      '), + 'h4' => array( t('Header'), '

      '. t('Subtitle four') .'

      '), + 'h5' => array( t('Header'), '
      '. t('Subtitle five') .'
      '), + 'h6' => array( t('Header'), '
      '. t('Subtitle six') .'
      ') + ); + $header = array(t('Tag Description'), t('You Type'), t('You Get')); + preg_match_all('/<([a-z0-9]+)[^a-z0-9]/i', $allowed_html, $out); + foreach ($out[1] as $tag) { + if (array_key_exists($tag, $tips)) { + if ($tips[$tag]) { + $rows[] = array( + array('data' => $tips[$tag][0], 'class' => 'description'), + array('data' => ''. check_plain($tips[$tag][1]) .'', 'class' => 'type'), + array('data' => $tips[$tag][1], 'class' => 'get') + ); + } + } + else { + $rows[] = array( + array('data' => t('No help provided for tag %tag.', array('%tag' => $tag)), 'class' => 'description', 'colspan' => 3), + ); + } + } + $output .= theme('table', $header, $rows); + + $output .= t(' +

      Most unusual characters can be directly entered without any problems.

      +

      If you do encounter problems, try using HTML character entities. A common example looks like &amp; for an ampersand & character. For a full list of entities see HTML\'s entities page. Some of the available characters include:

      '); + $entities = array( + array( t('Ampersand'), '&'), + array( t('Greater than'), '>'), + array( t('Less than'), '<'), + array( t('Quotation mark'), '"'), + ); + $header = array(t('Character Description'), t('You Type'), t('You Get')); + unset($rows); + foreach ($entities as $entity) { + $rows[] = array( + array('data' => $entity[0], 'class' => 'description'), + array('data' => ''. check_plain($entity[1]) .'', 'class' => 'type'), + array('data' => $entity[1], 'class' => 'get') + ); + } + $output .= theme('table', $header, $rows); + return $output; + } + } + else { + return t('No HTML tags allowed'); + } + } + break; + + case 1: + switch ($long) { + case 0: + return t('Lines and paragraphs break automatically.'); + case 1: + return t('Lines and paragraphs are automatically recognized. The <br /> line break, <p> paragraph and </p> close paragraph tags are inserted automatically. If paragraphs are not recognized simply add a couple blank lines.'); + } + break; + case 2: + return t('Web page addresses and e-mail addresses turn into links automatically.'); + } +} + +/** + * Retrieve a list of input formats. + */ +function filter_formats($index = NULL) { + global $user; + static $formats; + + // Administrators can always use all input formats. + $all = user_access('administer filters'); + + if (!isset($formats)) { + $formats = array(); + + $query = 'SELECT * FROM {filter_formats}'; + + // Build query for selecting the format(s) based on the user's roles. + $args = array(); + if (!$all) { + $where = array(); + foreach ($user->roles as $rid => $role) { + $where[] = "roles LIKE '%%,%d,%%'"; + $args[] = $rid; + } + $query .= ' WHERE '. implode(' OR ', $where) .' OR format = %d'; + $args[] = variable_get('filter_default_format', 1); + } + + $result = db_query($query, $args); + while ($format = db_fetch_object($result)) { + $formats[$format->format] = $format; + } + } + if (isset($index)) { + return isset($formats[$index]) ? $formats[$index] : FALSE; + } + return $formats; +} + +/** + * Build a list of all filters. + */ +function filter_list_all() { + $filters = array(); + + foreach (module_list() as $module) { + $list = module_invoke($module, 'filter', 'list'); + if (isset($list) && is_array($list)) { + foreach ($list as $delta => $name) { + $filters[$module .'/'. $delta] = (object)array('module' => $module, 'delta' => $delta, 'name' => $name); + } + } + } + + uasort($filters, '_filter_list_cmp'); + + return $filters; +} + +/** + * Helper function for sorting the filter list by filter name. + */ +function _filter_list_cmp($a, $b) { + return strcmp($a->name, $b->name); +} + +/** + * Resolve a format id, including the default format. + */ +function filter_resolve_format($format) { + return $format == FILTER_FORMAT_DEFAULT ? variable_get('filter_default_format', 1) : $format; +} +/** + * Check if text in a certain input format is allowed to be cached. + */ +function filter_format_allowcache($format) { + static $cache = array(); + $format = filter_resolve_format($format); + if (!isset($cache[$format])) { + $cache[$format] = db_result(db_query('SELECT cache FROM {filter_formats} WHERE format = %d', $format)); + } + return $cache[$format]; +} + +/** + * Retrieve a list of filters for a certain format. + */ +function filter_list_format($format) { + static $filters = array(); + + if (!isset($filters[$format])) { + $result = db_query("SELECT * FROM {filters} WHERE format = %d ORDER BY weight, module, delta", $format); + if (db_affected_rows($result) == 0 && !db_result(db_query("SELECT 1 FROM {filter_formats} WHERE format = %d", $format))) { + // The format has no filters and does not exist, use the default input + // format. + $filters[$format] = filter_list_format(variable_get('filter_default_format', 1)); + } + else { + $filters[$format] = array(); + while ($filter = db_fetch_object($result)) { + $list = module_invoke($filter->module, 'filter', 'list'); + if (isset($list) && is_array($list) && isset($list[$filter->delta])) { + $filter->name = $list[$filter->delta]; + $filters[$format][$filter->module .'/'. $filter->delta] = $filter; + } + } + } + } + + return $filters[$format]; +} + +/** + * @defgroup filtering_functions Filtering functions + * @{ + * Functions for interacting with the content filtering system. + * + * For more info, see the hook_filter() documentation. + * + * Note: because filters can inject JavaScript or execute PHP code, security is + * vital here. When a user supplies a $format, you should validate it with + * filter_access($format) before accepting/using it. This is normally done in + * the validation stage of the node system. You should for example never make a + * preview of content in a disallowed format. + */ + +/** + * Run all the enabled filters on a piece of text. + * + * @param $text + * The text to be filtered. + * @param $format + * The format of the text to be filtered. Specify FILTER_FORMAT_DEFAULT for + * the default format. + * @param $check + * Whether to check the $format with filter_access() first. Defaults to TRUE. + * Note that this will check the permissions of the current user, so you + * should specify $check = FALSE when viewing other people's content. When + * showing content that is not (yet) stored in the database (eg. upon preview), + * set to TRUE so the user's permissions are checked. + */ +function check_markup($text, $format = FILTER_FORMAT_DEFAULT, $check = TRUE) { + // When $check = TRUE, do an access check on $format. + if (isset($text) && (!$check || filter_access($format))) { + $format = filter_resolve_format($format); + + // Check for a cached version of this piece of text. + $cache_id = $format .':'. md5($text); + if ($cached = cache_get($cache_id, 'cache_filter')) { + return $cached->data; + } + + // See if caching is allowed for this format. + $cache = filter_format_allowcache($format); + + // Convert all Windows and Mac newlines to a single newline, + // so filters only need to deal with one possibility. + $text = str_replace(array("\r\n", "\r"), "\n", $text); + + // Get a complete list of filters, ordered properly. + $filters = filter_list_format($format); + + // Give filters the chance to escape HTML-like data such as code or formulas. + foreach ($filters as $filter) { + $text = module_invoke($filter->module, 'filter', 'prepare', $filter->delta, $format, $text, $cache_id); + } + + // Perform filtering. + foreach ($filters as $filter) { + $text = module_invoke($filter->module, 'filter', 'process', $filter->delta, $format, $text, $cache_id); + } + + // Store in cache with a minimum expiration time of 1 day. + if ($cache) { + cache_set($cache_id, $text, 'cache_filter', time() + (60 * 60 * 24)); + } + } + else { + $text = t('n/a'); + } + + return $text; +} + +/** + * Generates a selector for choosing a format in a form. + * + * @param $value + * The ID of the format that is currently selected; uses the default format + * if not provided. + * @param $weight + * The weight of the form element within the form. + * @param $parents + * The parents array of the element. Required when defining multiple text + * formats on a single form or having a different parent than 'format'. + * + * @return + * Form API array for the form element. + * + * @see filter_form_validate() + * @ingroup forms + */ +function filter_form($value = FILTER_FORMAT_DEFAULT, $weight = NULL, $parents = array('format')) { + $value = filter_resolve_format($value); + $formats = filter_formats(); + + $extra = theme('filter_tips_more_info'); + + if (count($formats) > 1) { + $form = array( + '#type' => 'fieldset', + '#title' => t('Input format'), + '#collapsible' => TRUE, + '#collapsed' => TRUE, + '#weight' => $weight, + '#element_validate' => array('filter_form_validate'), + ); + // Multiple formats available: display radio buttons with tips. + foreach ($formats as $format) { + // Generate the parents as the autogenerator does, so we will have a + // unique id for each radio button. + $parents_for_id = array_merge($parents, array($format->format)); + $form[$format->format] = array( + '#type' => 'radio', + '#title' => $format->name, + '#default_value' => $value, + '#return_value' => $format->format, + '#parents' => $parents, + '#description' => theme('filter_tips', _filter_tips($format->format, FALSE)), + '#id' => form_clean_id('edit-'. implode('-', $parents_for_id)), + ); + } + } + else { + // Only one format available: use a hidden form item and only show tips. + $format = array_shift($formats); + $form[$format->format] = array('#type' => 'value', '#value' => $format->format, '#parents' => $parents); + $tips = _filter_tips(variable_get('filter_default_format', 1), FALSE); + $form['format']['guidelines'] = array( + '#title' => t('Formatting guidelines'), + '#value' => theme('filter_tips', $tips, FALSE, $extra), + ); + } + $form[] = array('#value' => $extra); + return $form; +} + +/** + * Validation callback for filter elements in a form. + * + * @see filter_form(). + */ +function filter_form_validate($form) { + foreach (element_children($form) as $key) { + if ($form[$key]['#value'] == $form[$key]['#return_value']) { + return; + } + } + form_error($form, t('An illegal choice has been detected. Please contact the site administrator.')); + watchdog('form', 'Illegal choice %choice in %name element.', array('%choice' => $form[$key]['#value'], '%name' => empty($form['#title']) ? $form['#parents'][0] : $form['#title']), WATCHDOG_ERROR); +} + +/** + * Returns TRUE if the user is allowed to access this format. + */ +function filter_access($format) { + $format = filter_resolve_format($format); + if (user_access('administer filters') || ($format == variable_get('filter_default_format', 1))) { + return TRUE; + } + else { + $formats = filter_formats(); + return isset($formats[$format]); + } +} + +/** + * @} End of "Filtering functions". + */ + + +/** + * Helper function for fetching filter tips. + */ +function _filter_tips($format, $long = FALSE) { + if ($format == -1) { + $formats = filter_formats(); + } + else { + $formats = array(db_fetch_object(db_query("SELECT * FROM {filter_formats} WHERE format = %d", $format))); + } + + $tips = array(); + + foreach ($formats as $format) { + $filters = filter_list_format($format->format); + + $tips[$format->name] = array(); + foreach ($filters as $id => $filter) { + if ($tip = module_invoke($filter->module, 'filter_tips', $filter->delta, $format->format, $long)) { + $tips[$format->name][] = array('tip' => $tip, 'id' => $id); + } + } + } + + return $tips; +} + + +/** + * Format a link to the more extensive filter tips. + * + * @ingroup themeable + */ +function theme_filter_tips_more_info() { + return '

      '. l(t('More information about formatting options'), 'filter/tips') .'

      '; +} + +/** + * @defgroup standard_filters Standard filters + * @{ + * Filters implemented by the filter.module. + */ + +/** + * Implementation of hook_filter(). + * + * Sets up a basic set of essential filters. + * - HTML filter: Restricts user-supplied HTML to certain tags, and removes + * dangerous components in allowed tags. + * - Line break converter: Converts newlines into paragraph and break tags. + * - URL filter: Converts URLs and e-mail addresses into links. + * - HTML corrector: Fixes faulty HTML. + */ +function filter_filter($op, $delta = 0, $format = -1, $text = '') { + switch ($op) { + case 'list': + return array(0 => t('HTML filter'), 1 => t('Line break converter'), 2 => t('URL filter'), 3 => t('HTML corrector')); + + case 'description': + switch ($delta) { + case 0: + return t('Allows you to restrict whether users can post HTML and which tags to filter out. It will also remove harmful content such as JavaScript events, JavaScript URLs and CSS styles from those tags that are not removed.'); + case 1: + return t('Converts line breaks into HTML (i.e. <br> and <p> tags).'); + case 2: + return t('Turns web and e-mail addresses into clickable links.'); + case 3: + return t('Corrects faulty and chopped off HTML in postings.'); + default: + return; + } + + case 'process': + switch ($delta) { + case 0: + return _filter_html($text, $format); + case 1: + return _filter_autop($text); + case 2: + return _filter_url($text, $format); + case 3: + return _filter_htmlcorrector($text); + default: + return $text; + } + + case 'settings': + switch ($delta) { + case 0: + return _filter_html_settings($format); + case 2: + return _filter_url_settings($format); + default: + return; + } + + default: + return $text; + } +} + +/** + * Settings for the HTML filter. + */ +function _filter_html_settings($format) { + $form['filter_html'] = array( + '#type' => 'fieldset', + '#title' => t('HTML filter'), + '#collapsible' => TRUE, + ); + $form['filter_html']["filter_html_$format"] = array( + '#type' => 'radios', + '#title' => t('Filter HTML tags'), + '#default_value' => variable_get("filter_html_$format", FILTER_HTML_STRIP), + '#options' => array(FILTER_HTML_STRIP => t('Strip disallowed tags'), FILTER_HTML_ESCAPE => t('Escape all tags')), + '#description' => t('How to deal with HTML tags in user-contributed content. If set to "Strip disallowed tags", dangerous tags are removed (see below). If set to "Escape tags", all HTML is escaped and presented as it was typed.'), + ); + $form['filter_html']["allowed_html_$format"] = array( + '#type' => 'textfield', + '#title' => t('Allowed HTML tags'), + '#default_value' => variable_get("allowed_html_$format", '
        1. '), + '#size' => 64, + '#maxlength' => 1024, + '#description' => t('If "Strip disallowed tags" is selected, optionally specify tags which should not be stripped. JavaScript event attributes are always stripped.'), + ); + $form['filter_html']["filter_html_help_$format"] = array( + '#type' => 'checkbox', + '#title' => t('Display HTML help'), + '#default_value' => variable_get("filter_html_help_$format", 1), + '#description' => t('If enabled, Drupal will display some basic HTML help in the long filter tips.'), + ); + $form['filter_html']["filter_html_nofollow_$format"] = array( + '#type' => 'checkbox', + '#title' => t('Spam link deterrent'), + '#default_value' => variable_get("filter_html_nofollow_$format", FALSE), + '#description' => t('If enabled, Drupal will add rel="nofollow" to all links, as a measure to reduce the effectiveness of spam links. Note: this will also prevent valid links from being followed by search engines, therefore it is likely most effective when enabled for anonymous users.'), + ); + return $form; +} + +/** + * HTML filter. Provides filtering of input into accepted HTML. + */ +function _filter_html($text, $format) { + if (variable_get("filter_html_$format", FILTER_HTML_STRIP) == FILTER_HTML_STRIP) { + $allowed_tags = preg_split('/\s+|<|>/', variable_get("allowed_html_$format", '
            1. '), -1, PREG_SPLIT_NO_EMPTY); + $text = filter_xss($text, $allowed_tags); + } + + if (variable_get("filter_html_$format", FILTER_HTML_STRIP) == FILTER_HTML_ESCAPE) { + // Escape HTML + $text = check_plain($text); + } + + if (variable_get("filter_html_nofollow_$format", FALSE)) { + $text = preg_replace('/]+)>/i', '', $text); + } + + return trim($text); +} + +/** + * Settings for URL filter. + */ +function _filter_url_settings($format) { + $form['filter_urlfilter'] = array( + '#type' => 'fieldset', + '#title' => t('URL filter'), + '#collapsible' => TRUE, + ); + $form['filter_urlfilter']['filter_url_length_'. $format] = array( + '#type' => 'textfield', + '#title' => t('Maximum link text length'), + '#default_value' => variable_get('filter_url_length_'. $format, 72), + '#maxlength' => 4, + '#description' => t('URLs longer than this number of characters will be truncated to prevent long strings that break formatting. The link itself will be retained; just the text portion of the link will be truncated.'), + ); + return $form; +} + +/** + * URL filter. Automatically converts text web addresses (URLs, e-mail addresses, + * FTP links, etc.) into hyperlinks. + */ +function _filter_url($text, $format) { + // Pass length to regexp callback + _filter_url_trim(NULL, variable_get('filter_url_length_'. $format, 72)); + + $text = ' '. $text .' '; + + // Match absolute URLs. + $text = preg_replace_callback("`(

              |

            2. ||[ \n\r\t\(])((http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://)([a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-]))([.,?!]*?)(?=(

              |
              3. ||[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text); + + // Match e-mail addresses. + $text = preg_replace("`(

              |

            3. ||[ \n\r\t\(])([A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4})([.,?!]*?)(?=(

              |
              4. ||[ \n\r\t\)]))`i", '\1              \2\3', $text); + + // Match www domains/addresses. + $text = preg_replace_callback("`(

              |

            4. |[ \n\r\t\(])(www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-])([.,?!]*?)(?=(

              |
              5. ||[ \n\r\t\)]))`i", '_filter_url_parse_partial_links', $text); + $text = substr($text, 1, -1); + + return $text; +} + +/** + * Scan input and make sure that all HTML tags are properly closed and nested. + */ +function _filter_htmlcorrector($text) { + // Prepare tag lists. + static $no_nesting, $single_use; + if (!isset($no_nesting)) { + // Tags which cannot be nested but are typically left unclosed. + $no_nesting = drupal_map_assoc(array('li', 'p')); + + // Single use tags in HTML4 + $single_use = drupal_map_assoc(array('base', 'meta', 'link', 'hr', 'br', 'param', 'img', 'area', 'input', 'col', 'frame')); + } + + // Properly entify angles. + $text = preg_replace('@<(?=[^a-zA-Z!/]|$)@', '<', $text); + + // Split tags from text. + $split = preg_split('/<(!--.*?--|[^>]+?)>/s', $text, -1, PREG_SPLIT_DELIM_CAPTURE); + // Note: PHP ensures the array consists of alternating delimiters and literals + // and begins and ends with a literal (inserting $null as required). + + $tag = false; // Odd/even counter. Tag or no tag. + $stack = array(); + $output = ''; + foreach ($split as $value) { + // Process HTML tags. + if ($tag) { + // Passthrough comments. + if (substr($value, 0, 3) == '!--') { + $output .= '<'. $value .'>'; + } + else { + list($tagname) = preg_split('/\s/', strtolower($value), 2); + // Closing tag + if ($tagname{0} == '/') { + $tagname = substr($tagname, 1); + // Discard XHTML closing tags for single use tags. + if (!isset($single_use[$tagname])) { + // See if we possibly have a matching opening tag on the stack. + if (in_array($tagname, $stack)) { + // Close other tags lingering first. + do { + $output .= ''; + } while (array_shift($stack) != $tagname); + } + // Otherwise, discard it. + } + } + // Opening tag + else { + // See if we have an identical 'no nesting' tag already open and close it if found. + if (count($stack) && ($stack[0] == $tagname) && isset($no_nesting[$stack[0]])) { + $output .= ''; + } + // Push non-single-use tags onto the stack + if (!isset($single_use[$tagname])) { + array_unshift($stack, $tagname); + } + // Add trailing slash to single-use tags as per X(HT)ML. + else { + $value = rtrim($value, ' /') .' /'; + } + $output .= '<'. $value .'>'; + } + } + } + else { + // Passthrough all text. + $output .= $value; + } + $tag = !$tag; + } + // Close remaining tags. + while (count($stack) > 0) { + $output .= ''; + } + return $output; +} + +/** + * Make links out of absolute URLs. + */ +function _filter_url_parse_full_links($match) { + $match[2] = decode_entities($match[2]); + $caption = check_plain(_filter_url_trim($match[2])); + $match[2] = check_url($match[2]); + return $match[1] .''. $caption .''. $match[5]; +} + +/** + * Make links out of domain names starting with "www." + */ +function _filter_url_parse_partial_links($match) { + $match[2] = decode_entities($match[2]); + $caption = check_plain(_filter_url_trim($match[2])); + $match[2] = check_plain($match[2]); + return $match[1] .''. $caption .''. $match[3]; +} + +/** + * Shortens long URLs to http://www.example.com/long/url... + */ +function _filter_url_trim($text, $length = NULL) { + static $_length; + if ($length !== NULL) { + $_length = $length; + } + + // Use +3 for '...' string length. + if (strlen($text) > $_length + 3) { + $text = substr($text, 0, $_length) .'...'; + } + + return $text; +} + +/** + * Convert line breaks into

              and
              in an intelligent fashion. + * Based on: http://photomatt.net/scripts/autop + */ +function _filter_autop($text) { + // All block level tags + $block = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|p|h[1-6]|hr)'; + + // Split at 

              , ,  tags.
+  // We don't apply any processing to the contents of these tags to avoid messing
+  // up code. We look for matched pairs and allow basic nesting. For example:
+  // "processed 
               ignored  ignored 
               processed"
+  $chunks = preg_split('@(<(?:!--.*?--|/?(?:pre|script|style|object)[^>]*)>)@si', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+  // Note: PHP ensures the array consists of alternating delimiters and literals
+  // and begins and ends with a literal (inserting NULL as required).
+  $ignore = FALSE;
+  $ignoretag = '';
+  $output = '';
+  foreach ($chunks as $i => $chunk) {
+    if ($i % 2) {
+      // Passthrough comments.
+      if (substr($chunk, 1, 3) == '!--') {
+        $output .= $chunk;
+      }
+      else {
+        // Opening or closing tag?
+        $open = ($chunk[1] != '/');
+        list($tag) = split('[ >]', substr($chunk, 2 - $open), 2);
+        if (!$ignore) {
+          if ($open) {
+            $ignore = TRUE;
+            $ignoretag = $tag;
+          }
+        }
+        // Only allow a matching tag to close it.
+        else if (!$open && $ignoretag == $tag) {
+          $ignore = FALSE;
+          $ignoretag = '';
+        }
+      }
+    }
+    else if (!$ignore) {
+      $chunk = preg_replace('|\n*$|', '', $chunk) ."\n\n"; // just to make things a little easier, pad the end
+      $chunk = preg_replace('|
              \s*
              |', "\n\n", $chunk);
+      $chunk = preg_replace('!(<'. $block .'[^>]*>)!', "\n$1", $chunk); // Space things out a little
+      $chunk = preg_replace('!()!', "$1\n\n", $chunk); // Space things out a little
+      $chunk = preg_replace("/\n\n+/", "\n\n", $chunk); // take care of duplicates
+      $chunk = preg_replace('/^\n|\n\s*\n$/', '', $chunk);
+      $chunk = '
              '. preg_replace('/\n\s*\n\n?(.)/', "
              \n
              $1", $chunk) ."
              \n"; // make paragraphs, including one at the end
+      $chunk = preg_replace("|
              (|", "$1", $chunk); // problem with nested lists
+      $chunk = preg_replace('|
              ]*)>|i', "
              ", $chunk);
+      $chunk = str_replace('
              ', '
              ', $chunk);
+      $chunk = preg_replace('|
              \s*
              \n?|', '', $chunk); // under certain strange conditions it could create a P of entirely whitespace
+      $chunk = preg_replace('!
              \s*(]*>)!', "$1", $chunk);
+      $chunk = preg_replace('!(]*>)\s*
              !', "$1", $chunk);
+      $chunk = preg_replace('|(?)\s*\n|', "
              \n", $chunk); // make line breaks
+      $chunk = preg_replace('!(]*>)\s*
              !', "$1", $chunk);
+      $chunk = preg_replace('!
              (\s*)!', '$1', $chunk);
+      $chunk = preg_replace('/&([^#])(?![A-Za-z0-9]{1,8};)/', '&$1', $chunk);
+    }
+    $output .= $chunk;
+  }
+  return $output;
+}
+
+/**
+ * Very permissive XSS/HTML filter for admin-only use.
+ *
+ * Use only for fields where it is impractical to use the
+ * whole filter system, but where some (mainly inline) mark-up
+ * is desired (so check_plain() is not acceptable).
+ *
+ * Allows all tags that can be used inside an HTML body, save
+ * for scripts and styles.
+ */
+function filter_xss_admin($string) {
+  return filter_xss($string, array('a', 'abbr', 'acronym', 'address', 'b', 'bdo', 'big', 'blockquote', 'br', 'caption', 'cite', 'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'div', 'dl', 'dt', 'em', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', 'li', 'ol', 'p', 'pre', 'q', 'samp', 'small', 'span', 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', 'tr', 'tt', 'ul', 'var'));
+}
+
+/**
+ * Filters an HTML string to prevent cross-site-scripting (XSS) vulnerabilities.
+ *
+ * Based on kses by Ulf Harnhammar, see http://sourceforge.net/projects/kses.
+ * For examples of various XSS attacks, see http://ha.ckers.org/xss.html.
+ *
+ * This code does four things:
+ * - Removes characters and constructs that can trick browsers.
+ * - Makes sure all HTML entities are well-formed.
+ * - Makes sure all HTML tags and attributes are well-formed.
+ * - Makes sure no HTML tags contain URLs with a disallowed protocol (e.g.
+ *   javascript:).
+ *
+ * @param $string
+ *   The string with raw HTML in it. It will be stripped of everything that can
+ *   cause an XSS attack.
+ * @param $allowed_tags
+ *   An array of allowed tags.
+ *
+ * @return
+ *   An XSS safe version of $string, or an empty string if $string is not
+ *   valid UTF-8.
+ *
+ * @see drupal_validate_utf8()
+ * @ingroup sanitization
+ */
+function filter_xss($string, $allowed_tags = array('a', 'em', 'strong', 'cite', 'code', 'ul', 'ol', 'li', 'dl', 'dt', 'dd')) {
+  // Only operate on valid UTF-8 strings. This is necessary to prevent cross
+  // site scripting issues on Internet Explorer 6.
+  if (!drupal_validate_utf8($string)) {
+    return '';
+  }
+  // Store the input format
+  _filter_xss_split($allowed_tags, TRUE);
+  // Remove NUL characters (ignored by some browsers)
+  $string = str_replace(chr(0), '', $string);
+  // Remove Netscape 4 JS entities
+  $string = preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string);
+
+  // Defuse all HTML entities
+  $string = str_replace('&', '&', $string);
+  // Change back only well-formed entities in our whitelist
+  // Decimal numeric entities
+  $string = preg_replace('/&#([0-9]+;)/', '&#\1', $string);
+  // Hexadecimal numeric entities
+  $string = preg_replace('/&#[Xx]0*((?:[0-9A-Fa-f]{2})+;)/', '&#x\1', $string);
+  // Named entities
+  $string = preg_replace('/&([A-Za-z][A-Za-z0-9]*;)/', '&\1', $string);
+
+  return preg_replace_callback('%
+    (
+    <(?=[^a-zA-Z!/])  # a lone <
+    |                 # or
+            # a comment
+    |                 # or
+    <[^>]*(>|$)       # a string that starts with a <, up until the > or the end of the string
+    |                 # or
+    >                 # just a >
+    )%x', '_filter_xss_split', $string);
+}
+
+/**
+ * Processes an HTML tag.
+ *
+ * @param @m
+ *   An array with various meaning depending on the value of $store.
+ *   If $store is TRUE then the array contains the allowed tags.
+ *   If $store is FALSE then the array has one element, the HTML tag to process.
+ * @param $store
+ *   Whether to store $m.
+ * @return
+ *   If the element isn't allowed, an empty string. Otherwise, the cleaned up
+ *   version of the HTML element.
+ */
+function _filter_xss_split($m, $store = FALSE) {
+  static $allowed_html;
+
+  if ($store) {
+    $allowed_html = array_flip($m);
+    return;
+  }
+
+  $string = $m[1];
+
+  if (substr($string, 0, 1) != '<') {
+    // We matched a lone ">" character
+    return '>';
+  }
+  else if (strlen($string) == 1) {
+    // We matched a lone "<" character
+    return '<';
+  }
+
+  if (!preg_match('%^(?:<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?|())$%', $string, $matches)) {
+    // Seriously malformed
+    return '';
+  }
+
+  $slash = trim($matches[1]);
+  $elem = &$matches[2];
+  $attrlist = &$matches[3];
+  $comment = &$matches[4];
+
+  if ($comment) {
+    $elem = '!--';
+  }
+
+  if (!isset($allowed_html[strtolower($elem)])) {
+    // Disallowed HTML element
+    return '';
+  }
+
+  if ($comment) {
+    return $comment;
+  }
+
+  if ($slash != '') {
+    return "";
+  }
+
+  // Is there a closing XHTML slash at the end of the attributes?
+  // In PHP 5.1.0+ we could count the changes, currently we need a separate match
+  $xhtml_slash = preg_match('%\s?/\s*$%', $attrlist) ? ' /' : '';
+  $attrlist = preg_replace('%(\s?)/\s*$%', '\1', $attrlist);
+
+  // Clean up attributes
+  $attr2 = implode(' ', _filter_xss_attributes($attrlist));
+  $attr2 = preg_replace('/[<>]/', '', $attr2);
+  $attr2 = strlen($attr2) ? ' '. $attr2 : '';
+
+  return "<$elem$attr2$xhtml_slash>";
+}
+
+/**
+ * Processes a string of HTML attributes.
+ *
+ * @return
+ *   Cleaned up version of the HTML attributes.
+ */
+function _filter_xss_attributes($attr) {
+  $attrarr = array();
+  $mode = 0;
+  $attrname = '';
+
+  while (strlen($attr) != 0) {
+    // Was the last operation successful?
+    $working = 0;
+
+    switch ($mode) {
+      case 0:
+        // Attribute name, href for instance
+        if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) {
+          $attrname = strtolower($match[1]);
+          $skip = ($attrname == 'style' || substr($attrname, 0, 2) == 'on');
+          $working = $mode = 1;
+          $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr);
+        }
+
+        break;
+
+      case 1:
+        // Equals sign or valueless ("selected")
+        if (preg_match('/^\s*=\s*/', $attr)) {
+          $working = 1; $mode = 2;
+          $attr = preg_replace('/^\s*=\s*/', '', $attr);
+          break;
+        }
+
+        if (preg_match('/^\s+/', $attr)) {
+          $working = 1; $mode = 0;
+          if (!$skip) {
+            $attrarr[] = $attrname;
+          }
+          $attr = preg_replace('/^\s+/', '', $attr);
+        }
+
+        break;
+
+      case 2:
+        // Attribute value, a URL after href= for instance
+        if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) {
+          $thisval = filter_xss_bad_protocol($match[1]);
+
+          if (!$skip) {
+            $attrarr[] = "$attrname=\"$thisval\"";
+          }
+          $working = 1;
+          $mode = 0;
+          $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr);
+          break;
+        }
+
+        if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) {
+          $thisval = filter_xss_bad_protocol($match[1]);
+
+          if (!$skip) {
+            $attrarr[] = "$attrname='$thisval'";;
+          }
+          $working = 1; $mode = 0;
+          $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr);
+          break;
+        }
+
+        if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) {
+          $thisval = filter_xss_bad_protocol($match[1]);
+
+          if (!$skip) {
+            $attrarr[] = "$attrname=\"$thisval\"";
+          }
+          $working = 1; $mode = 0;
+          $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr);
+        }
+
+        break;
+    }
+
+    if ($working == 0) {
+      // not well formed, remove and try again
+      $attr = preg_replace('/
+        ^
+        (
+        "[^"]*("|$)     # - a string that starts with a double quote, up until the next double quote or the end of the string
+        |               # or
+        \'[^\']*(\'|$)| # - a string that starts with a quote, up until the next quote or the end of the string
+        |               # or
+        \S              # - a non-whitespace character
+        )*              # any number of the above three
+        \s*             # any number of whitespaces
+        /x', '', $attr);
+      $mode = 0;
+    }
+  }
+
+  // the attribute list ends with a valueless attribute like "selected"
+  if ($mode == 1) {
+    $attrarr[] = $attrname;
+  }
+  return $attrarr;
+}
+
+/**
+ * Processes an HTML attribute value and ensures it does not contain an URL
+ * with a disallowed protocol (e.g. javascript:)
+ *
+ * @param $string
+ *   The string with the attribute value.
+ * @param $decode
+ *   Whether to decode entities in the $string. Set to FALSE if the $string
+ *   is in plain text, TRUE otherwise. Defaults to TRUE.
+ * @return
+ *   Cleaned up and HTML-escaped version of $string.
+ */
+function filter_xss_bad_protocol($string, $decode = TRUE) {
+  static $allowed_protocols;
+  if (!isset($allowed_protocols)) {
+    $allowed_protocols = array_flip(variable_get('filter_allowed_protocols', array('http', 'https', 'ftp', 'news', 'nntp', 'tel', 'telnet', 'mailto', 'irc', 'ssh', 'sftp', 'webcal', 'rtsp')));
+  }
+
+  // Get the plain text representation of the attribute value (i.e. its meaning).
+  if ($decode) {
+    $string = decode_entities($string);
+  }
+
+  // Iteratively remove any invalid protocol found.
+
+  do {
+    $before = $string;
+    $colonpos = strpos($string, ':');
+    if ($colonpos > 0) {
+      // We found a colon, possibly a protocol. Verify.
+      $protocol = substr($string, 0, $colonpos);
+      // If a colon is preceded by a slash, question mark or hash, it cannot
+      // possibly be part of the URL scheme. This must be a relative URL,
+      // which inherits the (safe) protocol of the base document.
+      if (preg_match('![/?#]!', $protocol)) {
+        break;
+      }
+      // Per RFC2616, section 3.2.3 (URI Comparison) scheme comparison must be case-insensitive
+      // Check if this is a disallowed protocol.
+      if (!isset($allowed_protocols[strtolower($protocol)])) {
+        $string = substr($string, $colonpos + 1);
+      }
+    }
+  } while ($before != $string);
+  return check_plain($string);
+}
+
+/**
+ * @} End of "Standard filters".
+ */