diff options
Diffstat (limited to 'library/markdownify')
| -rw-r--r-- | library/markdownify/LICENSE_LGPL.txt | 504 | ||||
| -rw-r--r-- | library/markdownify/TODO | 29 | ||||
| -rw-r--r-- | library/markdownify/example.php | 51 | ||||
| -rw-r--r-- | library/markdownify/markdownify.php | 1197 | ||||
| -rwxr-xr-x | library/markdownify/markdownify_cli.php | 33 | ||||
| -rw-r--r-- | library/markdownify/markdownify_extra.php | 489 | ||||
| -rw-r--r-- | library/markdownify/parsehtml/parsehtml.php | 618 |
7 files changed, 2921 insertions, 0 deletions
diff --git a/library/markdownify/LICENSE_LGPL.txt b/library/markdownify/LICENSE_LGPL.txt new file mode 100644 index 000000000..5ab7695ab --- /dev/null +++ b/library/markdownify/LICENSE_LGPL.txt @@ -0,0 +1,504 @@ + GNU LESSER GENERAL PUBLIC LICENSE + Version 2.1, February 1999 + + Copyright (C) 1991, 1999 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. + +[This is the first released version of the Lesser GPL. It also counts + as the successor of the GNU Library Public License, version 2, hence + the version number 2.1.] + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +Licenses are intended to guarantee your freedom to share and change +free software--to make sure the software is free for all its users. + + This license, the Lesser General Public License, applies to some +specially designated software packages--typically libraries--of the +Free Software Foundation and other authors who decide to use it. You +can use it too, but we suggest you first think carefully about whether +this license or the ordinary General Public License is the better +strategy to use in any particular case, based on the explanations below. + + When we speak of free software, we are referring to freedom of use, +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 and use pieces of +it in new free programs; and that you are informed that you can do +these things. + + To protect your rights, we need to make restrictions that forbid +distributors to deny you these rights or to ask you to surrender these +rights. These restrictions translate to certain responsibilities for +you if you distribute copies of the library or if you modify it. + + For example, if you distribute copies of the library, whether gratis +or for a fee, you must give the recipients all the rights that we gave +you. You must make sure that they, too, receive or can get the source +code. If you link other code with the library, you must provide +complete object files to the recipients, so that they can relink them +with the library after making changes to the library and recompiling +it. And you must show them these terms so they know their rights. + + We protect your rights with a two-step method: (1) we copyright the +library, and (2) we offer you this license, which gives you legal +permission to copy, distribute and/or modify the library. + + To protect each distributor, we want to make it very clear that +there is no warranty for the free library. Also, if the library is +modified by someone else and passed on, the recipients should know +that what they have is not the original version, so that the original +author's reputation will not be affected by problems that might be +introduced by others. + + Finally, software patents pose a constant threat to the existence of +any free program. We wish to make sure that a company cannot +effectively restrict the users of a free program by obtaining a +restrictive license from a patent holder. Therefore, we insist that +any patent license obtained for a version of the library must be +consistent with the full freedom of use specified in this license. + + Most GNU software, including some libraries, is covered by the +ordinary GNU General Public License. This license, the GNU Lesser +General Public License, applies to certain designated libraries, and +is quite different from the ordinary General Public License. We use +this license for certain libraries in order to permit linking those +libraries into non-free programs. + + When a program is linked with a library, whether statically or using +a shared library, the combination of the two is legally speaking a +combined work, a derivative of the original library. The ordinary +General Public License therefore permits such linking only if the +entire combination fits its criteria of freedom. The Lesser General +Public License permits more lax criteria for linking other code with +the library. + + We call this license the "Lesser" General Public License because it +does Less to protect the user's freedom than the ordinary General +Public License. It also provides other free software developers Less +of an advantage over competing non-free programs. These disadvantages +are the reason we use the ordinary General Public License for many +libraries. However, the Lesser license provides advantages in certain +special circumstances. + + For example, on rare occasions, there may be a special need to +encourage the widest possible use of a certain library, so that it becomes +a de-facto standard. To achieve this, non-free programs must be +allowed to use the library. A more frequent case is that a free +library does the same job as widely used non-free libraries. In this +case, there is little to gain by limiting the free library to free +software only, so we use the Lesser General Public License. + + In other cases, permission to use a particular library in non-free +programs enables a greater number of people to use a large body of +free software. For example, permission to use the GNU C Library in +non-free programs enables many more people to use the whole GNU +operating system, as well as its variant, the GNU/Linux operating +system. + + Although the Lesser General Public License is Less protective of the +users' freedom, it does ensure that the user of a program that is +linked with the Library has the freedom and the wherewithal to run +that program using a modified version of the Library. + + The precise terms and conditions for copying, distribution and +modification follow. Pay close attention to the difference between a +"work based on the library" and a "work that uses the library". The +former contains code derived from the library, whereas the latter must +be combined with the library in order to run. + + GNU LESSER GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License Agreement applies to any software library or other +program which contains a notice placed by the copyright holder or +other authorized party saying it may be distributed under the terms of +this Lesser General Public License (also called "this License"). +Each licensee is addressed as "you". + + A "library" means a collection of software functions and/or data +prepared so as to be conveniently linked with application programs +(which use some of those functions and data) to form executables. + + The "Library", below, refers to any such software library or work +which has been distributed under these terms. A "work based on the +Library" means either the Library or any derivative work under +copyright law: that is to say, a work containing the Library or a +portion of it, either verbatim or with modifications and/or translated +straightforwardly into another language. (Hereinafter, translation is +included without limitation in the term "modification".) + + "Source code" for a work means the preferred form of the work for +making modifications to it. For a library, 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 library. + + Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running a program using the Library is not restricted, and output from +such a program is covered only if its contents constitute a work based +on the Library (independent of the use of the Library in a tool for +writing it). Whether that is true depends on what the Library does +and what the program that uses the Library does. + + 1. You may copy and distribute verbatim copies of the Library's +complete 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 distribute a copy of this License along with the +Library. + + 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 Library or any portion +of it, thus forming a work based on the Library, 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) The modified work must itself be a software library. + + b) You must cause the files modified to carry prominent notices + stating that you changed the files and the date of any change. + + c) You must cause the whole of the work to be licensed at no + charge to all third parties under the terms of this License. + + d) If a facility in the modified Library refers to a function or a + table of data to be supplied by an application program that uses + the facility, other than as an argument passed when the facility + is invoked, then you must make a good faith effort to ensure that, + in the event an application does not supply such function or + table, the facility still operates, and performs whatever part of + its purpose remains meaningful. + + (For example, a function in a library to compute square roots has + a purpose that is entirely well-defined independent of the + application. Therefore, Subsection 2d requires that any + application-supplied function or table used by this function must + be optional: if the application does not supply it, the square + root function must still compute square roots.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Library, +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 Library, 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 Library. + +In addition, mere aggregation of another work not based on the Library +with the Library (or with a work based on the Library) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may opt to apply the terms of the ordinary GNU General Public +License instead of this License to a given copy of the Library. To do +this, you must alter all the notices that refer to this License, so +that they refer to the ordinary GNU General Public License, version 2, +instead of to this License. (If a newer version than version 2 of the +ordinary GNU General Public License has appeared, then you can specify +that version instead if you wish.) Do not make any other change in +these notices. + + Once this change is made in a given copy, it is irreversible for +that copy, so the ordinary GNU General Public License applies to all +subsequent copies and derivative works made from that copy. + + This option is useful when you wish to copy part of the code of +the Library into a program that is not a library. + + 4. You may copy and distribute the Library (or a portion or +derivative of it, under Section 2) in object code or executable form +under the terms of Sections 1 and 2 above provided that you 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. + + If distribution of 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 satisfies the requirement to +distribute the source code, even though third parties are not +compelled to copy the source along with the object code. + + 5. A program that contains no derivative of any portion of the +Library, but is designed to work with the Library by being compiled or +linked with it, is called a "work that uses the Library". Such a +work, in isolation, is not a derivative work of the Library, and +therefore falls outside the scope of this License. + + However, linking a "work that uses the Library" with the Library +creates an executable that is a derivative of the Library (because it +contains portions of the Library), rather than a "work that uses the +library". The executable is therefore covered by this License. +Section 6 states terms for distribution of such executables. + + When a "work that uses the Library" uses material from a header file +that is part of the Library, the object code for the work may be a +derivative work of the Library even though the source code is not. +Whether this is true is especially significant if the work can be +linked without the Library, or if the work is itself a library. The +threshold for this to be true is not precisely defined by law. + + If such an object file uses only numerical parameters, data +structure layouts and accessors, and small macros and small inline +functions (ten lines or less in length), then the use of the object +file is unrestricted, regardless of whether it is legally a derivative +work. (Executables containing this object code plus portions of the +Library will still fall under Section 6.) + + Otherwise, if the work is a derivative of the Library, you may +distribute the object code for the work under the terms of Section 6. +Any executables containing that work also fall under Section 6, +whether or not they are linked directly with the Library itself. + + 6. As an exception to the Sections above, you may also combine or +link a "work that uses the Library" with the Library to produce a +work containing portions of the Library, and distribute that work +under terms of your choice, provided that the terms permit +modification of the work for the customer's own use and reverse +engineering for debugging such modifications. + + You must give prominent notice with each copy of the work that the +Library is used in it and that the Library and its use are covered by +this License. You must supply a copy of this License. If the work +during execution displays copyright notices, you must include the +copyright notice for the Library among them, as well as a reference +directing the user to the copy of this License. Also, you must do one +of these things: + + a) Accompany the work with the complete corresponding + machine-readable source code for the Library including whatever + changes were used in the work (which must be distributed under + Sections 1 and 2 above); and, if the work is an executable linked + with the Library, with the complete machine-readable "work that + uses the Library", as object code and/or source code, so that the + user can modify the Library and then relink to produce a modified + executable containing the modified Library. (It is understood + that the user who changes the contents of definitions files in the + Library will not necessarily be able to recompile the application + to use the modified definitions.) + + b) Use a suitable shared library mechanism for linking with the + Library. A suitable mechanism is one that (1) uses at run time a + copy of the library already present on the user's computer system, + rather than copying library functions into the executable, and (2) + will operate properly with a modified version of the library, if + the user installs one, as long as the modified version is + interface-compatible with the version that the work was made with. + + c) Accompany the work with a written offer, valid for at + least three years, to give the same user the materials + specified in Subsection 6a, above, for a charge no more + than the cost of performing this distribution. + + d) If distribution of the work is made by offering access to copy + from a designated place, offer equivalent access to copy the above + specified materials from the same place. + + e) Verify that the user has already received a copy of these + materials or that you have already sent this user a copy. + + For an executable, the required form of the "work that uses the +Library" must include any data and utility programs needed for +reproducing the executable from it. However, as a special exception, +the materials to be 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. + + It may happen that this requirement contradicts the license +restrictions of other proprietary libraries that do not normally +accompany the operating system. Such a contradiction means you cannot +use both them and the Library together in an executable that you +distribute. + + 7. You may place library facilities that are a work based on the +Library side-by-side in a single library together with other library +facilities not covered by this License, and distribute such a combined +library, provided that the separate distribution of the work based on +the Library and of the other library facilities is otherwise +permitted, and provided that you do these two things: + + a) Accompany the combined library with a copy of the same work + based on the Library, uncombined with any other library + facilities. This must be distributed under the terms of the + Sections above. + + b) Give prominent notice with the combined library of the fact + that part of it is a work based on the Library, and explaining + where to find the accompanying uncombined form of the same work. + + 8. You may not copy, modify, sublicense, link with, or distribute +the Library except as expressly provided under this License. Any +attempt otherwise to copy, modify, sublicense, link with, or +distribute the Library 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. + + 9. 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 Library or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Library (or any work based on the +Library), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Library or works based on it. + + 10. Each time you redistribute the Library (or any work based on the +Library), the recipient automatically receives a license from the +original licensor to copy, distribute, link with or modify the Library +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 with +this License. + + 11. 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 Library at all. For example, if a patent +license would not permit royalty-free redistribution of the Library 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 Library. + +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. + + 12. If the distribution and/or use of the Library is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Library 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. + + 13. The Free Software Foundation may publish revised and/or new +versions of the Lesser 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 Library +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 Library does not specify a +license version number, you may choose any version ever published by +the Free Software Foundation. + + 14. If you wish to incorporate parts of the Library into other free +programs whose distribution conditions are incompatible with these, +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 + + 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO +WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. +EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR +OTHER PARTIES PROVIDE THE LIBRARY "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 +LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME +THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. 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 LIBRARY 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 +LIBRARY (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 LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), 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 Libraries + + If you develop a new library, and you want it to be of the greatest +possible use to the public, we recommend making it free software that +everyone can redistribute and change. You can do so by permitting +redistribution under these terms (or, alternatively, under the terms of the +ordinary General Public License). + + To apply these terms, attach the following notices to the library. 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. + + <one line to give the library's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + This library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with this library; 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. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the library, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the + library `Frob' (a library for tweaking knobs) written by James Random Hacker. + + <signature of Ty Coon>, 1 April 1990 + Ty Coon, President of Vice + +That's all there is to it! + + diff --git a/library/markdownify/TODO b/library/markdownify/TODO new file mode 100644 index 000000000..06ec8508b --- /dev/null +++ b/library/markdownify/TODO @@ -0,0 +1,29 @@ +Markdownify +=========== +* handle non-markdownifiable lists (i.e. `<ul><li id="foobar">asdf</li></ul>`) +* organize methods better (i.e. flushlinebreaks & setlinebreaks close to each other) +* take a look at function names etc. +* is the new (in rev. 93) lastclosedtag property needed? +* word wrapping (some work is done but it's still very buggy) + + +Markdownify Extra +================= + +* handle table alignment with KEEP_HTML=false +* handle tables without headings when KEEP_HTML=false is set +* handle Markdown inside non-markdownable tags + + +Implementation Thoughts +======================= +* non-markdownifiable lists and markdown inside non-markdownable tags as well as the current + table implementation could be rewritten by using a rollback mechanism. + + example: + + <ul><li>asdf</li><li id="foobar">asdf</li></ul> + + we come to `<ul>`, know that this might fail and create a snapshot of our current parser + we keep on parsing and when we reach `<li id="foobar">` we gotta rollback and keep this + list in HTML format. diff --git a/library/markdownify/example.php b/library/markdownify/example.php new file mode 100644 index 000000000..ef86dca83 --- /dev/null +++ b/library/markdownify/example.php @@ -0,0 +1,51 @@ +<?php + error_reporting(E_ALL); + if (!empty($_POST['input'])) { + include 'markdownify_extra.php'; + if (!isset($_POST['leap'])) { + $leap = MDFY_LINKS_EACH_PARAGRAPH; + } else { + $leap = $_POST['leap']; + } + + if (!isset($_POST['keepHTML'])) { + $keephtml = MDFY_KEEPHTML; + } else { + $keephtml = $_POST['keepHTML']; + } + if (!empty($_POST['extra'])) { + $md = new Markdownify_Extra($leap, MDFY_BODYWIDTH, $keephtml); + } else { + $md = new Markdownify($leap, MDFY_BODYWIDTH, $keephtml); + } + if (ini_get('magic_quotes_gpc')) { + $_POST['input'] = stripslashes($_POST['input']); + } + $output = $md->parseString($_POST['input']); + } else { + $_POST['input'] = ''; + } +?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en-US" lang="en-US"> + <head> + <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/> + <title>HTML to Markdown Converter</title> + </head> + <body> + <?php if (empty($_POST['input'])): ?> + <form action="<?php echo $_SERVER['PHP_SELF']; ?>" method="post"> + <fieldset> + <legend>HTML Input</legend> + <textarea style="width:100%;" cols="85" rows="40" name="input"><?php echo htmlspecialchars($_POST['input'], ENT_NOQUOTES, 'UTF-8'); ?></textarea> + </fieldset> + <label for="extra">Markdownify Extra: <input name="extra" checked="checked" id="extra" type="checkbox" value="1" /></label> + <label for="leap">Links after each block elem: <input name="leap" id="leap" type="checkbox" value="1" /></label> + <label for="keepHTML">keep HTML: <input name="keepHTML" id="keepHTML" type="checkbox" value="1" checked="checked" /></label> + <input type="submit" name="submit" value="submit" /> + </form> + <?php else: ?> + <h1 style="text-align:right;"><a href="<?php echo $_SERVER['PHP_SELF']; ?>">BACK</a></h1> + <pre><?php echo htmlspecialchars($output, ENT_NOQUOTES, 'UTF-8'); ?></pre> + <?php endif; ?> + </body> +</html>
\ No newline at end of file diff --git a/library/markdownify/markdownify.php b/library/markdownify/markdownify.php new file mode 100644 index 000000000..0d4429a01 --- /dev/null +++ b/library/markdownify/markdownify.php @@ -0,0 +1,1197 @@ +<?php +/** + * Markdownify converts HTML Markup to [Markdown][1] (by [John Gruber][2]. It + * also supports [Markdown Extra][3] by [Michel Fortin][4] via Markdownify_Extra. + * + * It all started as `html2text.php` - a port of [Aaron Swartz'][5] [`html2text.py`][6] - but + * got a long way since. This is far more than a mere port now! + * Starting with version 2.0.0 this is a complete rewrite and cannot be + * compared to Aaron Swatz' `html2text.py` anylonger. I'm now using a HTML parser + * (see `parsehtml.php` which I also wrote) which makes most of the evil + * RegEx magic go away and additionally it gives a much cleaner class + * structure. Also notably is the fact that I now try to prevent regressions by + * utilizing testcases of Michel Fortin's [MDTest][7]. + * + * [1]: http://daringfireball.com/projects/markdown + * [2]: http://daringfireball.com/ + * [3]: http://www.michelf.com/projects/php-markdown/extra/ + * [4]: http://www.michelf.com/ + * [5]: http://www.aaronsw.com/ + * [6]: http://www.aaronsw.com/2002/html2text/ + * [7]: http://article.gmane.org/gmane.text.markdown.general/2540 + * + * @version 2.0.0 alpha + * @author Milian Wolff (<mail@milianw.de>, <http://milianw.de>) + * @license LGPL, see LICENSE_LGPL.txt and the summary below + * @copyright (C) 2007 Milian Wolff + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/** + * HTML Parser, see http://sf.net/projects/parseHTML + */ +require_once dirname(__FILE__).'/parsehtml/parsehtml.php'; + +/** + * default configuration + */ +define('MDFY_LINKS_EACH_PARAGRAPH', false); +define('MDFY_BODYWIDTH', false); +define('MDFY_KEEPHTML', true); + +/** + * HTML to Markdown converter class + */ +class Markdownify { + /** + * html parser object + * + * @var parseHTML + */ + var $parser; + /** + * markdown output + * + * @var string + */ + var $output; + /** + * stack with tags which where not converted to html + * + * @var array<string> + */ + var $notConverted = array(); + /** + * skip conversion to markdown + * + * @var bool + */ + var $skipConversion = false; + /* options */ + /** + * keep html tags which cannot be converted to markdown + * + * @var bool + */ + var $keepHTML = false; + /** + * wrap output, set to 0 to skip wrapping + * + * @var int + */ + var $bodyWidth = 0; + /** + * minimum body width + * + * @var int + */ + var $minBodyWidth = 25; + /** + * display links after each paragraph + * + * @var bool + */ + var $linksAfterEachParagraph = false; + /** + * constructor, set options, setup parser + * + * @param bool $linksAfterEachParagraph wether or not to flush stacked links after each paragraph + * defaults to false + * @param int $bodyWidth wether or not to wrap the output to the given width + * defaults to false + * @param bool $keepHTML wether to keep non markdownable HTML or to discard it + * defaults to true (HTML will be kept) + * @return void + */ + function Markdownify($linksAfterEachParagraph = MDFY_LINKS_EACH_PARAGRAPH, $bodyWidth = MDFY_BODYWIDTH, $keepHTML = MDFY_KEEPHTML) { + $this->linksAfterEachParagraph = $linksAfterEachParagraph; + $this->keepHTML = $keepHTML; + + if ($bodyWidth > $this->minBodyWidth) { + $this->bodyWidth = intval($bodyWidth); + } else { + $this->bodyWidth = false; + } + + $this->parser = new parseHTML; + $this->parser->noTagsInCode = true; + + # we don't have to do this every time + $search = array(); + $replace = array(); + foreach ($this->escapeInText as $s => $r) { + array_push($search, '#(?<!\\\)'.$s.'#U'); + array_push($replace, $r); + } + $this->escapeInText = array( + 'search' => $search, + 'replace' => $replace + ); + } + /** + * parse a HTML string + * + * @param string $html + * @return string markdown formatted + */ + function parseString($html) { + $this->parser->html = $html; + $this->parse(); + return $this->output; + } + /** + * tags with elements which can be handled by markdown + * + * @var array<string> + */ + var $isMarkdownable = array( + 'p' => array(), + 'ul' => array(), + 'ol' => array(), + 'li' => array(), + 'br' => array(), + 'blockquote' => array(), + 'code' => array(), + 'pre' => array(), + 'a' => array( + 'href' => 'required', + 'title' => 'optional', + ), + 'strong' => array(), + 'b' => array(), + 'em' => array(), + 'i' => array(), + 'img' => array( + 'src' => 'required', + 'alt' => 'optional', + 'title' => 'optional', + ), + 'h1' => array(), + 'h2' => array(), + 'h3' => array(), + 'h4' => array(), + 'h5' => array(), + 'h6' => array(), + 'hr' => array(), + ); + /** + * html tags to be ignored (contents will be parsed) + * + * @var array<string> + */ + var $ignore = array( + 'html', + 'body', + ); + /** + * html tags to be dropped (contents will not be parsed!) + * + * @var array<string> + */ + var $drop = array( + 'script', + 'head', + 'style', + 'form', + 'area', + 'object', + 'param', + 'iframe', + ); + /** + * Markdown indents which could be wrapped + * @note: use strings in regex format + * + * @var array<string> + */ + var $wrappableIndents = array( + '\* ', # ul + '\d. ', # ol + '\d\d. ', # ol + '> ', # blockquote + '', # p + ); + /** + * list of chars which have to be escaped in normal text + * @note: use strings in regex format + * + * @var array + * + * TODO: what's with block chars / sequences at the beginning of a block? + */ + var $escapeInText = array( + '([-*_])([ ]{0,2}\1){2,}' => '\\\\$0|', # hr + '\*\*([^*\s]+)\*\*' => '\*\*$1\*\*', # strong + '\*([^*\s]+)\*' => '\*$1\*', # em + '__(?! |_)(.+)(?!<_| )__' => '\_\_$1\_\_', # em + '_(?! |_)(.+)(?!<_| )_' => '\_$1\_', # em + '`(.+)`' => '\`$1\`', # code + '\[(.+)\](\s*\()' => '\[$1\]$2', # links: [text] (url) => [text\] (url) + '\[(.+)\](\s*)\[(.*)\]' => '\[$1\]$2\[$3\]', # links: [text][id] => [text\][id\] + ); + /** + * wether last processed node was a block tag or not + * + * @var bool + */ + var $lastWasBlockTag = false; + /** + * name of last closed tag + * + * @var string + */ + var $lastClosedTag = ''; + /** + * iterate through the nodes and decide what we + * shall do with the current node + * + * @param void + * @return void + */ + function parse() { + $this->output = ''; + # drop tags + $this->parser->html = preg_replace('#<('.implode('|', $this->drop).')[^>]*>.*</\\1>#sU', '', $this->parser->html); + while ($this->parser->nextNode()) { + switch ($this->parser->nodeType) { + case 'doctype': + break; + case 'pi': + case 'comment': + if ($this->keepHTML) { + $this->flushLinebreaks(); + $this->out($this->parser->node); + $this->setLineBreaks(2); + } + # else drop + break; + case 'text': + $this->handleText(); + break; + case 'tag': + if (in_array($this->parser->tagName, $this->ignore)) { + break; + } + if ($this->parser->isStartTag) { + $this->flushLinebreaks(); + } + if ($this->skipConversion) { + $this->isMarkdownable(); # update notConverted + $this->handleTagToText(); + continue; + } + if (!$this->parser->keepWhitespace && $this->parser->isBlockElement && $this->parser->isStartTag) { + $this->parser->html = ltrim($this->parser->html); + } + if ($this->isMarkdownable()) { + if ($this->parser->isBlockElement && $this->parser->isStartTag && !$this->lastWasBlockTag && !empty($this->output)) { + if (!empty($this->buffer)) { + $str =& $this->buffer[count($this->buffer) -1]; + } else { + $str =& $this->output; + } + if (substr($str, -strlen($this->indent)-1) != "\n".$this->indent) { + $str .= "\n".$this->indent; + } + } + $func = 'handleTag_'.$this->parser->tagName; + $this->$func(); + if ($this->linksAfterEachParagraph && $this->parser->isBlockElement && !$this->parser->isStartTag && empty($this->parser->openTags)) { + $this->flushStacked(); + } + if (!$this->parser->isStartTag) { + $this->lastClosedTag = $this->parser->tagName; + } + } else { + $this->handleTagToText(); + $this->lastClosedTag = ''; + } + break; + default: + trigger_error('invalid node type', E_USER_ERROR); + break; + } + $this->lastWasBlockTag = $this->parser->nodeType == 'tag' && $this->parser->isStartTag && $this->parser->isBlockElement; + } + if (!empty($this->buffer)) { + trigger_error('buffer was not flushed, this is a bug. please report!', E_USER_WARNING); + while (!empty($this->buffer)) { + $this->out($this->unbuffer()); + } + } + ### cleanup + $this->output = rtrim(str_replace('&', '&', str_replace('<', '<', str_replace('>', '>', $this->output)))); + # end parsing, flush stacked tags + $this->flushStacked(); + $this->stack = array(); + } + /** + * check if current tag can be converted to Markdown + * + * @param void + * @return bool + */ + function isMarkdownable() { + if (!isset($this->isMarkdownable[$this->parser->tagName])) { + # simply not markdownable + return false; + } + if ($this->parser->isStartTag) { + $return = true; + if ($this->keepHTML) { + $diff = array_diff(array_keys($this->parser->tagAttributes), array_keys($this->isMarkdownable[$this->parser->tagName])); + if (!empty($diff)) { + # non markdownable attributes given + $return = false; + } + } + if ($return) { + foreach ($this->isMarkdownable[$this->parser->tagName] as $attr => $type) { + if ($type == 'required' && !isset($this->parser->tagAttributes[$attr])) { + # required markdown attribute not given + $return = false; + break; + } + } + } + if (!$return) { + array_push($this->notConverted, $this->parser->tagName.'::'.implode('/', $this->parser->openTags)); + } + return $return; + } else { + if (!empty($this->notConverted) && end($this->notConverted) === $this->parser->tagName.'::'.implode('/', $this->parser->openTags)) { + array_pop($this->notConverted); + return false; + } + return true; + } + } + /** + * output all stacked tags + * + * @param void + * @return void + */ + function flushStacked() { + # links + foreach ($this->stack as $tag => $a) { + if (!empty($a)) { + call_user_func(array(&$this, 'flushStacked_'.$tag)); + } + } + } + /** + * output link references (e.g. [1]: http://example.com "title"); + * + * @param void + * @return void + */ + function flushStacked_a() { + $out = false; + foreach ($this->stack['a'] as $k => $tag) { + if (!isset($tag['unstacked'])) { + if (!$out) { + $out = true; + $this->out("\n\n", true); + } else { + $this->out("\n", true); + } + $this->out(' ['.$tag['linkID'].']: '.$tag['href'].(isset($tag['title']) ? ' "'.$tag['title'].'"' : ''), true); + $tag['unstacked'] = true; + $this->stack['a'][$k] = $tag; + } + } + } + /** + * flush enqued linebreaks + * + * @param void + * @return void + */ + function flushLinebreaks() { + if ($this->lineBreaks && !empty($this->output)) { + $this->out(str_repeat("\n".$this->indent, $this->lineBreaks), true); + } + $this->lineBreaks = 0; + } + /** + * handle non Markdownable tags + * + * @param void + * @return void + */ + function handleTagToText() { + if (!$this->keepHTML) { + if (!$this->parser->isStartTag && $this->parser->isBlockElement) { + $this->setLineBreaks(2); + } + } else { + # dont convert to markdown inside this tag + /** TODO: markdown extra **/ + if (!$this->parser->isEmptyTag) { + if ($this->parser->isStartTag) { + if (!$this->skipConversion) { + $this->skipConversion = $this->parser->tagName.'::'.implode('/', $this->parser->openTags); + } + } else { + if ($this->skipConversion == $this->parser->tagName.'::'.implode('/', $this->parser->openTags)) { + $this->skipConversion = false; + } + } + } + + if ($this->parser->isBlockElement) { + if ($this->parser->isStartTag) { + if (in_array($this->parent(), array('ins', 'del'))) { + # looks like ins or del are block elements now + $this->out("\n", true); + $this->indent(' '); + } + if ($this->parser->tagName != 'pre') { + $this->out($this->parser->node."\n".$this->indent); + if (!$this->parser->isEmptyTag) { + $this->indent(' '); + } else { + $this->setLineBreaks(1); + } + $this->parser->html = ltrim($this->parser->html); + } else { + # don't indent inside <pre> tags + $this->out($this->parser->node); + static $indent; + $indent = $this->indent; + $this->indent = ''; + } + } else { + if (!$this->parser->keepWhitespace) { + $this->output = rtrim($this->output); + } + if ($this->parser->tagName != 'pre') { + $this->indent(' '); + $this->out("\n".$this->indent.$this->parser->node); + } else { + # reset indentation + $this->out($this->parser->node); + static $indent; + $this->indent = $indent; + } + + if (in_array($this->parent(), array('ins', 'del'))) { + # ins or del was block element + $this->out("\n"); + $this->indent(' '); + } + if ($this->parser->tagName == 'li') { + $this->setLineBreaks(1); + } else { + $this->setLineBreaks(2); + } + } + } else { + $this->out($this->parser->node); + } + if (in_array($this->parser->tagName, array('code', 'pre'))) { + if ($this->parser->isStartTag) { + $this->buffer(); + } else { + # add stuff so cleanup just reverses this + $this->out(str_replace('<', '&lt;', str_replace('>', '&gt;', $this->unbuffer()))); + } + } + } + } + /** + * handle plain text + * + * @param void + * @return void + */ + function handleText() { + if ($this->hasParent('pre') && strpos($this->parser->node, "\n") !== false) { + $this->parser->node = str_replace("\n", "\n".$this->indent, $this->parser->node); + } + if (!$this->hasParent('code') && !$this->hasParent('pre')) { + # entity decode + $this->parser->node = $this->decode($this->parser->node); + if (!$this->skipConversion) { + # escape some chars in normal Text + $this->parser->node = preg_replace($this->escapeInText['search'], $this->escapeInText['replace'], $this->parser->node); + } + } else { + $this->parser->node = str_replace(array('"', '&apos'), array('"', '\''), $this->parser->node); + } + $this->out($this->parser->node); + $this->lastClosedTag = ''; + } + /** + * handle <em> and <i> tags + * + * @param void + * @return void + */ + function handleTag_em() { + $this->out('*', true); + } + function handleTag_i() { + $this->handleTag_em(); + } + /** + * handle <strong> and <b> tags + * + * @param void + * @return void + */ + function handleTag_strong() { + $this->out('**', true); + } + function handleTag_b() { + $this->handleTag_strong(); + } + /** + * handle <h1> tags + * + * @param void + * @return void + */ + function handleTag_h1() { + $this->handleHeader(1); + } + /** + * handle <h2> tags + * + * @param void + * @return void + */ + function handleTag_h2() { + $this->handleHeader(2); + } + /** + * handle <h3> tags + * + * @param void + * @return void + */ + function handleTag_h3() { + $this->handleHeader(3); + } + /** + * handle <h4> tags + * + * @param void + * @return void + */ + function handleTag_h4() { + $this->handleHeader(4); + } + /** + * handle <h5> tags + * + * @param void + * @return void + */ + function handleTag_h5() { + $this->handleHeader(5); + } + /** + * handle <h6> tags + * + * @param void + * @return void + */ + function handleTag_h6() { + $this->handleHeader(6); + } + /** + * number of line breaks before next inline output + */ + var $lineBreaks = 0; + /** + * handle header tags (<h1> - <h6>) + * + * @param int $level 1-6 + * @return void + */ + function handleHeader($level) { + if ($this->parser->isStartTag) { + $this->out(str_repeat('#', $level).' ', true); + } else { + $this->setLineBreaks(2); + } + } + /** + * handle <p> tags + * + * @param void + * @return void + */ + function handleTag_p() { + if (!$this->parser->isStartTag) { + $this->setLineBreaks(2); + } + } + /** + * handle <a> tags + * + * @param void + * @return void + */ + function handleTag_a() { + if ($this->parser->isStartTag) { + $this->buffer(); + if (isset($this->parser->tagAttributes['title'])) { + $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']); + } else { + $this->parser->tagAttributes['title'] = null; + } + $this->parser->tagAttributes['href'] = $this->decode(trim($this->parser->tagAttributes['href'])); + $this->stack(); + } else { + $tag = $this->unstack(); + $buffer = $this->unbuffer(); + + if (empty($tag['href']) && empty($tag['title'])) { + # empty links... testcase mania, who would possibly do anything like that?! + $this->out('['.$buffer.']()', true); + return; + } + + if ($buffer == $tag['href'] && empty($tag['title'])) { + # <http://example.com> + $this->out('<'.$buffer.'>', true); + return; + } + + $bufferDecoded = $this->decode(trim($buffer)); + if (substr($tag['href'], 0, 7) == 'mailto:' && 'mailto:'.$bufferDecoded == $tag['href']) { + if (is_null($tag['title'])) { + # <mail@example.com> + $this->out('<'.$bufferDecoded.'>', true); + return; + } + # [mail@example.com][1] + # ... + # [1]: mailto:mail@example.com Title + $tag['href'] = 'mailto:'.$bufferDecoded; + } + + $this->out('['.$buffer.']('.$tag['href'].' "'.$tag['title'].'")', true); + +/* + # [This link][id] + foreach ($this->stack['a'] as $tag2) { + if ($tag2['href'] == $tag['href'] && $tag2['title'] === $tag['title']) { + $tag['linkID'] = $tag2['linkID']; + break; + } + } + if (!isset($tag['linkID'])) { + $tag['linkID'] = count($this->stack['a']) + 1; + array_push($this->stack['a'], $tag); + } + + $this->out('['.$buffer.']['.$tag['linkID'].']', true); +*/ + } + } + /** + * handle <img /> tags + * + * @param void + * @return void + */ + function handleTag_img() { + if (!$this->parser->isStartTag) { + return; # just to be sure this is really an empty tag... + } + + if (isset($this->parser->tagAttributes['title'])) { + $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']); + } else { + $this->parser->tagAttributes['title'] = null; + } + if (isset($this->parser->tagAttributes['alt'])) { + $this->parser->tagAttributes['alt'] = $this->decode($this->parser->tagAttributes['alt']); + } else { + $this->parser->tagAttributes['alt'] = null; + } + + if (empty($this->parser->tagAttributes['src'])) { + # support for "empty" images... dunno if this is really needed + # but there are some testcases which do that... + if (!empty($this->parser->tagAttributes['title'])) { + $this->parser->tagAttributes['title'] = ' '.$this->parser->tagAttributes['title'].' '; + } + $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['title'].')', true); + return; + } else { + $this->parser->tagAttributes['src'] = $this->decode($this->parser->tagAttributes['src']); + } + +//  + if ($this->parser->tagAttributes['title'] != "") + $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].' "'.$this->parser->tagAttributes['title'].'")', true); + else + $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].')', true); + +/* + # [This link][id] + $link_id = false; + if (!empty($this->stack['a'])) { + foreach ($this->stack['a'] as $tag) { + if ($tag['href'] == $this->parser->tagAttributes['src'] + && $tag['title'] === $this->parser->tagAttributes['title']) { + $link_id = $tag['linkID']; + break; + } + } + } else { + $this->stack['a'] = array(); + } + if (!$link_id) { + $link_id = count($this->stack['a']) + 1; + $tag = array( + 'href' => $this->parser->tagAttributes['src'], + 'linkID' => $link_id, + 'title' => $this->parser->tagAttributes['title'] + ); + array_push($this->stack['a'], $tag); + } + + $this->out('!['.$this->parser->tagAttributes['alt'].']['.$link_id.']', true); +*/ + } + /** + * handle <code> tags + * + * @param void + * @return void + */ + function handleTag_code() { + if ($this->hasParent('pre')) { + # ignore code blocks inside <pre> + return; + } + if ($this->parser->isStartTag) { + $this->buffer(); + } else { + $buffer = $this->unbuffer(); + # use as many backticks as needed + preg_match_all('#`+#', $buffer, $matches); + if (!empty($matches[0])) { + rsort($matches[0]); + + $ticks = '`'; + while (true) { + if (!in_array($ticks, $matches[0])) { + break; + } + $ticks .= '`'; + } + } else { + $ticks = '`'; + } + if ($buffer[0] == '`' || substr($buffer, -1) == '`') { + $buffer = ' '.$buffer.' '; + } + $this->out($ticks.$buffer.$ticks, true); + } + } + /** + * handle <pre> tags + * + * @param void + * @return void + */ + function handleTag_pre() { + if ($this->keepHTML && $this->parser->isStartTag) { + # check if a simple <code> follows + if (!preg_match('#^\s*<code\s*>#Us', $this->parser->html)) { + # this is no standard markdown code block + $this->handleTagToText(); + return; + } + } + $this->indent(' '); + if (!$this->parser->isStartTag) { + $this->setLineBreaks(2); + } else { + $this->parser->html = ltrim($this->parser->html); + } + } + /** + * handle <blockquote> tags + * + * @param void + * @return void + */ + function handleTag_blockquote() { + $this->indent('> '); + } + /** + * handle <ul> tags + * + * @param void + * @return void + */ + function handleTag_ul() { + if ($this->parser->isStartTag) { + $this->stack(); + if (!$this->keepHTML && $this->lastClosedTag == $this->parser->tagName) { + $this->out("\n".$this->indent.'<!-- -->'."\n".$this->indent."\n".$this->indent); + } + } else { + $this->unstack(); + if ($this->parent() != 'li' || preg_match('#^\s*(</li\s*>\s*<li\s*>\s*)?<(p|blockquote)\s*>#sU', $this->parser->html)) { + # dont make Markdown add unneeded paragraphs + $this->setLineBreaks(2); + } + } + } + /** + * handle <ul> tags + * + * @param void + * @return void + */ + function handleTag_ol() { + # same as above + $this->parser->tagAttributes['num'] = 0; + $this->handleTag_ul(); + } + /** + * handle <li> tags + * + * @param void + * @return void + */ + function handleTag_li() { + if ($this->parent() == 'ol') { + $parent =& $this->getStacked('ol'); + if ($this->parser->isStartTag) { + $parent['num']++; + $this->out($parent['num'].'.'.str_repeat(' ', 3 - strlen($parent['num'])), true); + } + $this->indent(' ', false); + } else { + if ($this->parser->isStartTag) { + $this->out('* ', true); + } + $this->indent(' ', false); + } + if (!$this->parser->isStartTag) { + $this->setLineBreaks(1); + } + } + /** + * handle <hr /> tags + * + * @param void + * @return void + */ + function handleTag_hr() { + if (!$this->parser->isStartTag) { + return; # just to be sure this really is an empty tag + } + $this->out('* * *', true); + $this->setLineBreaks(2); + } + /** + * handle <br /> tags + * + * @param void + * @return void + */ + function handleTag_br() { + $this->out(" \n".$this->indent, true); + $this->parser->html = ltrim($this->parser->html); + } + /** + * node stack, e.g. for <a> and <abbr> tags + * + * @var array<array> + */ + var $stack = array(); + /** + * add current node to the stack + * this only stores the attributes + * + * @param void + * @return void + */ + function stack() { + if (!isset($this->stack[$this->parser->tagName])) { + $this->stack[$this->parser->tagName] = array(); + } + array_push($this->stack[$this->parser->tagName], $this->parser->tagAttributes); + } + /** + * remove current tag from stack + * + * @param void + * @return array + */ + function unstack() { + if (!isset($this->stack[$this->parser->tagName]) || !is_array($this->stack[$this->parser->tagName])) { + trigger_error('Trying to unstack from empty stack. This must not happen.', E_USER_ERROR); + } + return array_pop($this->stack[$this->parser->tagName]); + } + /** + * get last stacked element of type $tagName + * + * @param string $tagName + * @return array + */ + function & getStacked($tagName) { + // no end() so it can be referenced + return $this->stack[$tagName][count($this->stack[$tagName])-1]; + } + /** + * set number of line breaks before next start tag + * + * @param int $number + * @return void + */ + function setLineBreaks($number) { + if ($this->lineBreaks < $number) { + $this->lineBreaks = $number; + } + } + /** + * stores current buffers + * + * @var array<string> + */ + var $buffer = array(); + /** + * buffer next parser output until unbuffer() is called + * + * @param void + * @return void + */ + function buffer() { + array_push($this->buffer, ''); + } + /** + * end current buffer and return buffered output + * + * @param void + * @return string + */ + function unbuffer() { + return array_pop($this->buffer); + } + /** + * append string to the correct var, either + * directly to $this->output or to the current + * buffers + * + * @param string $put + * @return void + */ + function out($put, $nowrap = false) { + if (empty($put)) { + return; + } + if (!empty($this->buffer)) { + $this->buffer[count($this->buffer) - 1] .= $put; + } else { + if ($this->bodyWidth && !$this->parser->keepWhitespace) { # wrap lines + // get last line + $pos = strrpos($this->output, "\n"); + if ($pos === false) { + $line = $this->output; + } else { + $line = substr($this->output, $pos); + } + + if ($nowrap) { + if ($put[0] != "\n" && $this->strlen($line) + $this->strlen($put) > $this->bodyWidth) { + $this->output .= "\n".$this->indent.$put; + } else { + $this->output .= $put; + } + return; + } else { + $put .= "\n"; # make sure we get all lines in the while below + $lineLen = $this->strlen($line); + while ($pos = strpos($put, "\n")) { + $putLine = substr($put, 0, $pos+1); + $put = substr($put, $pos+1); + $putLen = $this->strlen($putLine); + if ($lineLen + $putLen < $this->bodyWidth) { + $this->output .= $putLine; + $lineLen = $putLen; + } else { + $split = preg_split('#^(.{0,'.($this->bodyWidth - $lineLen).'})\b#', $putLine, 2, PREG_SPLIT_OFFSET_CAPTURE | PREG_SPLIT_DELIM_CAPTURE); + $this->output .= rtrim($split[1][0])."\n".$this->indent.$this->wordwrap(ltrim($split[2][0]), $this->bodyWidth, "\n".$this->indent, false); + } + } + $this->output = substr($this->output, 0, -1); + return; + } + } else { + $this->output .= $put; + } + } + } + /** + * current indentation + * + * @var string + */ + var $indent = ''; + /** + * indent next output (start tag) or unindent (end tag) + * + * @param string $str indentation + * @param bool $output add indendation to output + * @return void + */ + function indent($str, $output = true) { + if ($this->parser->isStartTag) { + $this->indent .= $str; + if ($output) { + $this->out($str, true); + } + } else { + $this->indent = substr($this->indent, 0, -strlen($str)); + } + } + /** + * decode email addresses + * + * @author derernst@gmx.ch <http://www.php.net/manual/en/function.html-entity-decode.php#68536> + * @author Milian Wolff <http://milianw.de> + */ + function decode($text, $quote_style = ENT_QUOTES) { + if (version_compare(PHP_VERSION, '5', '>=')) { + # UTF-8 is only supported in PHP 5.x.x and above + $text = html_entity_decode($text, $quote_style, 'UTF-8'); + } else { + if (function_exists('html_entity_decode')) { + $text = html_entity_decode($text, $quote_style, 'ISO-8859-1'); + } else { + static $trans_tbl; + if (!isset($trans_tbl)) { + $trans_tbl = array_flip(get_html_translation_table(HTML_ENTITIES, $quote_style)); + } + $text = strtr($text, $trans_tbl); + } + $text = preg_replace_callback('~&#x([0-9a-f]+);~i', array(&$this, '_decode_hex'), $text); + $text = preg_replace_callback('~&#(\d{2,5});~', array(&$this, '_decode_numeric'), $text); + } + return $text; + } + /** + * callback for decode() which converts a hexadecimal entity to UTF-8 + * + * @param array $matches + * @return string UTF-8 encoded + */ + function _decode_hex($matches) { + return $this->unichr(hexdec($matches[1])); + } + /** + * callback for decode() which converts a numerical entity to UTF-8 + * + * @param array $matches + * @return string UTF-8 encoded + */ + function _decode_numeric($matches) { + return $this->unichr($matches[1]); + } + /** + * UTF-8 chr() which supports numeric entities + * + * @author grey - greywyvern - com <http://www.php.net/manual/en/function.chr.php#55978> + * @param array $matches + * @return string UTF-8 encoded + */ + function unichr($dec) { + if ($dec < 128) { + $utf = chr($dec); + } else if ($dec < 2048) { + $utf = chr(192 + (($dec - ($dec % 64)) / 64)); + $utf .= chr(128 + ($dec % 64)); + } else { + $utf = chr(224 + (($dec - ($dec % 4096)) / 4096)); + $utf .= chr(128 + ((($dec % 4096) - ($dec % 64)) / 64)); + $utf .= chr(128 + ($dec % 64)); + } + return $utf; + } + /** + * UTF-8 strlen() + * + * @param string $str + * @return int + * + * @author dtorop 932 at hotmail dot com <http://www.php.net/manual/en/function.strlen.php#37975> + * @author Milian Wolff <http://milianw.de> + */ + function strlen($str) { + if (function_exists('mb_strlen')) { + return mb_strlen($str, 'UTF-8'); + } else { + return preg_match_all('/[\x00-\x7F\xC0-\xFD]/', $str, $var_empty); + } + } + /** + * wordwrap for utf8 encoded strings + * + * @param string $str + * @param integer $len + * @param string $what + * @return string + */ + function wordwrap($str, $width, $break, $cut = false){ + if (!$cut) { + $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){1,'.$width.'}\b#'; + } else { + $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){'.$width.'}#'; + } + $return = ''; + while (preg_match($regexp, $str, $matches)) { + $string = $matches[0]; + $str = ltrim(substr($str, strlen($string))); + if (!$cut && isset($str[0]) && in_array($str[0], array('.', '!', ';', ':', '?', ','))) { + $string .= $str[0]; + $str = ltrim(substr($str, 1)); + } + $return .= $string.$break; + } + return $return.ltrim($str); + } + /** + * check if current node has a $tagName as parent (somewhere, not only the direct parent) + * + * @param string $tagName + * @return bool + */ + function hasParent($tagName) { + return in_array($tagName, $this->parser->openTags); + } + /** + * get tagName of direct parent tag + * + * @param void + * @return string $tagName + */ + function parent() { + return end($this->parser->openTags); + } +} diff --git a/library/markdownify/markdownify_cli.php b/library/markdownify/markdownify_cli.php new file mode 100755 index 000000000..b3fffbd5c --- /dev/null +++ b/library/markdownify/markdownify_cli.php @@ -0,0 +1,33 @@ +#!/usr/bin/php +<?php +require dirname(__FILE__) .'/markdownify_extra.php'; + +function param($name, $default = false) { + if (!in_array('--'.$name, $_SERVER['argv'])) + return $default; + reset($_SERVER['argv']); + while (each($_SERVER['argv'])) { + if (current($_SERVER['argv']) == '--'.$name) + break; + } + $value = next($_SERVER['argv']); + if ($value === false || substr($value, 0, 2) == '--') + return true; + else + return $value; +} + + +$input = stream_get_contents(STDIN); + +$linksAfterEachParagraph = param('links'); +$bodyWidth = param('width'); +$keepHTML = param('html', true); + +if (param('no_extra')) { + $parser = new Markdownify($linksAfterEachParagraph, $bodyWidth, $keepHTML); +} else { + $parser = new Markdownify_Extra($linksAfterEachParagraph, $bodyWidth, $keepHTML); +} + +echo $parser->parseString($input) ."\n";
\ No newline at end of file diff --git a/library/markdownify/markdownify_extra.php b/library/markdownify/markdownify_extra.php new file mode 100644 index 000000000..e978a1c8a --- /dev/null +++ b/library/markdownify/markdownify_extra.php @@ -0,0 +1,489 @@ +<?php +/** + * Class to convert HTML to Markdown with PHP Markdown Extra syntax support. + * + * @version 1.0.0 alpha + * @author Milian Wolff (<mail@milianw.de>, <http://milianw.de>) + * @license LGPL, see LICENSE_LGPL.txt and the summary below + * @copyright (C) 2007 Milian Wolff + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/** + * standard Markdownify class + */ +require_once dirname(__FILE__).'/markdownify.php'; + +class Markdownify_Extra extends Markdownify { + /** + * table data, including rows with content and the maximum width of each col + * + * @var array + */ + var $table = array(); + /** + * current col + * + * @var int + */ + var $col = -1; + /** + * current row + * + * @var int + */ + var $row = 0; + /** + * constructor, see Markdownify::Markdownify() for more information + */ + function Markdownify_Extra($linksAfterEachParagraph = MDFY_LINKS_EACH_PARAGRAPH, $bodyWidth = MDFY_BODYWIDTH, $keepHTML = MDFY_KEEPHTML) { + parent::Markdownify($linksAfterEachParagraph, $bodyWidth, $keepHTML); + + ### new markdownable tags & attributes + # header ids: # foo {bar} + $this->isMarkdownable['h1']['id'] = 'optional'; + $this->isMarkdownable['h2']['id'] = 'optional'; + $this->isMarkdownable['h3']['id'] = 'optional'; + $this->isMarkdownable['h4']['id'] = 'optional'; + $this->isMarkdownable['h5']['id'] = 'optional'; + $this->isMarkdownable['h6']['id'] = 'optional'; + # tables + $this->isMarkdownable['table'] = array(); + $this->isMarkdownable['th'] = array( + 'align' => 'optional', + ); + $this->isMarkdownable['td'] = array( + 'align' => 'optional', + ); + $this->isMarkdownable['tr'] = array(); + array_push($this->ignore, 'thead'); + array_push($this->ignore, 'tbody'); + array_push($this->ignore, 'tfoot'); + # definition lists + $this->isMarkdownable['dl'] = array(); + $this->isMarkdownable['dd'] = array(); + $this->isMarkdownable['dt'] = array(); + # footnotes + $this->isMarkdownable['fnref'] = array( + 'target' => 'required', + ); + $this->isMarkdownable['footnotes'] = array(); + $this->isMarkdownable['fn'] = array( + 'name' => 'required', + ); + $this->parser->blockElements['fnref'] = false; + $this->parser->blockElements['fn'] = true; + $this->parser->blockElements['footnotes'] = true; + # abbr + $this->isMarkdownable['abbr'] = array( + 'title' => 'required', + ); + # build RegEx lookahead to decide wether table can pe parsed or not + $inlineTags = array_keys($this->parser->blockElements, false); + $colContents = '(?:[^<]|<(?:'.implode('|', $inlineTags).'|[^a-z]))+'; + $this->tableLookaheadHeader = '{ + ^\s*(?:<thead\s*>)?\s* # open optional thead + <tr\s*>\s*(?: # start required row with headers + <th(?:\s+align=("|\')(?:left|center|right)\1)?\s*> # header with optional align + \s*'.$colContents.'\s* # contents + </th>\s* # close header + )+</tr> # close row with headers + \s*(?:</thead>)? # close optional thead + }sxi'; + $this->tdSubstitute = '\s*'.$colContents.'\s* # contents + </td>\s*'; + $this->tableLookaheadBody = '{ + \s*(?:<tbody\s*>)?\s* # open optional tbody + (?:<tr\s*>\s* # start row + %s # cols to be substituted + </tr>)+ # close row + \s*(?:</tbody>)? # close optional tbody + \s*</table> # close table + }sxi'; + } + /** + * handle header tags (<h1> - <h6>) + * + * @param int $level 1-6 + * @return void + */ + function handleHeader($level) { + static $id = null; + if ($this->parser->isStartTag) { + if (isset($this->parser->tagAttributes['id'])) { + $id = $this->parser->tagAttributes['id']; + } + } else { + if (!is_null($id)) { + $this->out(' {#'.$id.'}'); + $id = null; + } + } + parent::handleHeader($level); + } + /** + * handle <abbr> tags + * + * @param void + * @return void + */ + function handleTag_abbr() { + if ($this->parser->isStartTag) { + $this->stack(); + $this->buffer(); + } else { + $tag = $this->unstack(); + $tag['text'] = $this->unbuffer(); + $add = true; + foreach ($this->stack['abbr'] as $stacked) { + if ($stacked['text'] == $tag['text']) { + /** TODO: differing abbr definitions, i.e. different titles for same text **/ + $add = false; + break; + } + } + $this->out($tag['text']); + if ($add) { + array_push($this->stack['abbr'], $tag); + } + } + } + /** + * flush stacked abbr tags + * + * @param void + * @return void + */ + function flushStacked_abbr() { + $out = array(); + foreach ($this->stack['abbr'] as $k => $tag) { + if (!isset($tag['unstacked'])) { + array_push($out, ' *['.$tag['text'].']: '.$tag['title']); + $tag['unstacked'] = true; + $this->stack['abbr'][$k] = $tag; + } + } + if (!empty($out)) { + $this->out("\n\n".implode("\n", $out)); + } + } + /** + * handle <table> tags + * + * @param void + * @return void + */ + function handleTag_table() { + if ($this->parser->isStartTag) { + # check if upcoming table can be converted + if ($this->keepHTML) { + if (preg_match($this->tableLookaheadHeader, $this->parser->html, $matches)) { + # header seems good, now check body + # get align & number of cols + preg_match_all('#<th(?:\s+align=("|\')(left|right|center)\1)?\s*>#si', $matches[0], $cols); + $regEx = ''; + $i = 1; + $aligns = array(); + foreach ($cols[2] as $align) { + $align = strtolower($align); + array_push($aligns, $align); + if (empty($align)) { + $align = 'left'; # default value + } + $td = '\s+align=("|\')'.$align.'\\'.$i; + $i++; + if ($align == 'left') { + # look for empty align or left + $td = '(?:'.$td.')?'; + } + $td = '<td'.$td.'\s*>'; + $regEx .= $td.$this->tdSubstitute; + } + $regEx = sprintf($this->tableLookaheadBody, $regEx); + if (preg_match($regEx, $this->parser->html, $matches, null, strlen($matches[0]))) { + # this is a markdownable table tag! + $this->table = array( + 'rows' => array(), + 'col_widths' => array(), + 'aligns' => $aligns, + ); + $this->row = 0; + } else { + # non markdownable table + $this->handleTagToText(); + } + } else { + # non markdownable table + $this->handleTagToText(); + } + } else { + $this->table = array( + 'rows' => array(), + 'col_widths' => array(), + 'aligns' => array(), + ); + $this->row = 0; + } + } else { + # finally build the table in Markdown Extra syntax + $separator = array(); + # seperator with correct align identifikators + foreach($this->table['aligns'] as $col => $align) { + if (!$this->keepHTML && !isset($this->table['col_widths'][$col])) { + break; + } + $left = ' '; + $right = ' '; + switch ($align) { + case 'left': + $left = ':'; + break; + case 'center': + $right = ':'; + $left = ':'; + case 'right': + $right = ':'; + break; + } + array_push($separator, $left.str_repeat('-', $this->table['col_widths'][$col]).$right); + } + $separator = '|'.implode('|', $separator).'|'; + + $rows = array(); + # add padding + array_walk_recursive($this->table['rows'], array(&$this, 'alignTdContent')); + $header = array_shift($this->table['rows']); + array_push($rows, '| '.implode(' | ', $header).' |'); + array_push($rows, $separator); + foreach ($this->table['rows'] as $row) { + array_push($rows, '| '.implode(' | ', $row).' |'); + } + $this->out(implode("\n".$this->indent, $rows)); + $this->table = array(); + $this->setLineBreaks(2); + } + } + /** + * properly pad content so it is aligned as whished + * should be used with array_walk_recursive on $this->table['rows'] + * + * @param string &$content + * @param int $col + * @return void + */ + function alignTdContent(&$content, $col) { + switch ($this->table['aligns'][$col]) { + default: + case 'left': + $content .= str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content)); + break; + case 'right': + $content = str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content)).$content; + break; + case 'center': + $paddingNeeded = $this->table['col_widths'][$col] - $this->strlen($content); + $left = floor($paddingNeeded / 2); + $right = $paddingNeeded - $left; + $content = str_repeat(' ', $left).$content.str_repeat(' ', $right); + break; + } + } + /** + * handle <tr> tags + * + * @param void + * @return void + */ + function handleTag_tr() { + if ($this->parser->isStartTag) { + $this->col = -1; + } else { + $this->row++; + } + } + /** + * handle <td> tags + * + * @param void + * @return void + */ + function handleTag_td() { + if ($this->parser->isStartTag) { + $this->col++; + if (!isset($this->table['col_widths'][$this->col])) { + $this->table['col_widths'][$this->col] = 0; + } + $this->buffer(); + } else { + $buffer = trim($this->unbuffer()); + $this->table['col_widths'][$this->col] = max($this->table['col_widths'][$this->col], $this->strlen($buffer)); + $this->table['rows'][$this->row][$this->col] = $buffer; + } + } + /** + * handle <th> tags + * + * @param void + * @return void + */ + function handleTag_th() { + if (!$this->keepHTML && !isset($this->table['rows'][1]) && !isset($this->table['aligns'][$this->col+1])) { + if (isset($this->parser->tagAttributes['align'])) { + $this->table['aligns'][$this->col+1] = $this->parser->tagAttributes['align']; + } else { + $this->table['aligns'][$this->col+1] = ''; + } + } + $this->handleTag_td(); + } + /** + * handle <dl> tags + * + * @param void + * @return void + */ + function handleTag_dl() { + if (!$this->parser->isStartTag) { + $this->setLineBreaks(2); + } + } + /** + * handle <dt> tags + * + * @param void + * @return void + **/ + function handleTag_dt() { + if (!$this->parser->isStartTag) { + $this->setLineBreaks(1); + } + } + /** + * handle <dd> tags + * + * @param void + * @return void + */ + function handleTag_dd() { + if ($this->parser->isStartTag) { + if (substr(ltrim($this->parser->html), 0, 3) == '<p>') { + # next comes a paragraph, so we'll need an extra line + $this->out("\n".$this->indent); + } elseif (substr($this->output, -2) == "\n\n") { + $this->output = substr($this->output, 0, -1); + } + $this->out(': '); + $this->indent(' ', false); + } else { + # lookahead for next dt + if (substr(ltrim($this->parser->html), 0, 4) == '<dt>') { + $this->setLineBreaks(2); + } else { + $this->setLineBreaks(1); + } + $this->indent(' '); + } + } + /** + * handle <fnref /> tags (custom footnote references, see markdownify_extra::parseString()) + * + * @param void + * @return void + */ + function handleTag_fnref() { + $this->out('[^'.$this->parser->tagAttributes['target'].']'); + } + /** + * handle <fn> tags (custom footnotes, see markdownify_extra::parseString() + * and markdownify_extra::_makeFootnotes()) + * + * @param void + * @return void + */ + function handleTag_fn() { + if ($this->parser->isStartTag) { + $this->out('[^'.$this->parser->tagAttributes['name'].']:'); + $this->setLineBreaks(1); + } else { + $this->setLineBreaks(2); + } + $this->indent(' '); + } + /** + * handle <footnotes> tag (custom footnotes, see markdownify_extra::parseString() + * and markdownify_extra::_makeFootnotes()) + * + * @param void + * @return void + */ + function handleTag_footnotes() { + if (!$this->parser->isStartTag) { + $this->setLineBreaks(2); + } + } + /** + * parse a HTML string, clean up footnotes prior + * + * @param string $HTML input + * @return string Markdown formatted output + */ + function parseString($html) { + /** TODO: custom markdown-extra options, e.g. titles & classes **/ + # <sup id="fnref:..."><a href"#fn..." rel="footnote">...</a></sup> + # => <fnref target="..." /> + $html = preg_replace('@<sup id="fnref:([^"]+)">\s*<a href="#fn:\1" rel="footnote">\s*\d+\s*</a>\s*</sup>@Us', '<fnref target="$1" />', $html); + # <div class="footnotes"> + # <hr /> + # <ol> + # + # <li id="fn:...">...</li> + # ... + # + # </ol> + # </div> + # => + # <footnotes> + # <fn name="...">...</fn> + # ... + # </footnotes> + $html = preg_replace_callback('#<div class="footnotes">\s*<hr />\s*<ol>\s*(.+)\s*</ol>\s*</div>#Us', array(&$this, '_makeFootnotes'), $html); + return parent::parseString($html); + } + /** + * replace HTML representation of footnotes with something more easily parsable + * + * @note this is a callback to be used in parseString() + * + * @param array $matches + * @return string + */ + function _makeFootnotes($matches) { + # <li id="fn:1"> + # ... + # <a href="#fnref:block" rev="footnote">↩</a></p> + # </li> + # => <fn name="1">...</fn> + # remove footnote link + $fns = preg_replace('@\s*( \s*)?<a href="#fnref:[^"]+" rev="footnote"[^>]*>↩</a>\s*@s', '', $matches[1]); + # remove empty paragraph + $fns = preg_replace('@<p>\s*</p>@s', '', $fns); + # <li id="fn:1">...</li> -> <footnote nr="1">...</footnote> + $fns = str_replace('<li id="fn:', '<fn name="', $fns); + + $fns = '<footnotes>'.$fns.'</footnotes>'; + return preg_replace('#</li>\s*(?=(?:<fn|</footnotes>))#s', '</fn>$1', $fns); + } +}
\ No newline at end of file diff --git a/library/markdownify/parsehtml/parsehtml.php b/library/markdownify/parsehtml/parsehtml.php new file mode 100644 index 000000000..1a8ecacda --- /dev/null +++ b/library/markdownify/parsehtml/parsehtml.php @@ -0,0 +1,618 @@ +<?php +/** + * parseHTML is a HTML parser which works with PHP 4 and above. + * It tries to handle invalid HTML to some degree. + * + * @version 1.0 beta + * @author Milian Wolff (mail@milianw.de, http://milianw.de) + * @license LGPL, see LICENSE_LGPL.txt and the summary below + * @copyright (C) 2007 Milian Wolff + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ +class parseHTML { + /** + * tags which are always empty (<br /> etc.) + * + * @var array<string> + */ + var $emptyTags = array( + 'br', + 'hr', + 'input', + 'img', + 'area', + 'link', + 'meta', + 'param', + ); + /** + * tags with preformatted text + * whitespaces wont be touched in them + * + * @var array<string> + */ + var $preformattedTags = array( + 'script', + 'style', + 'pre', + 'code', + ); + /** + * supress HTML tags inside preformatted tags (see above) + * + * @var bool + */ + var $noTagsInCode = false; + /** + * html to be parsed + * + * @var string + */ + var $html = ''; + /** + * node type: + * + * - tag (see isStartTag) + * - text (includes cdata) + * - comment + * - doctype + * - pi (processing instruction) + * + * @var string + */ + var $nodeType = ''; + /** + * current node content, i.e. either a + * simple string (text node), or something like + * <tag attrib="value"...> + * + * @var string + */ + var $node = ''; + /** + * wether current node is an opening tag (<a>) or not (</a>) + * set to NULL if current node is not a tag + * NOTE: empty tags (<br />) set this to true as well! + * + * @var bool | null + */ + var $isStartTag = null; + /** + * wether current node is an empty tag (<br />) or not (<a></a>) + * + * @var bool | null + */ + var $isEmptyTag = null; + /** + * tag name + * + * @var string | null + */ + var $tagName = ''; + /** + * attributes of current tag + * + * @var array (attribName=>value) | null + */ + var $tagAttributes = null; + /** + * wether the current tag is a block element + * + * @var bool | null + */ + var $isBlockElement = null; + + /** + * keep whitespace + * + * @var int + */ + var $keepWhitespace = 0; + /** + * list of open tags + * count this to get current depth + * + * @var array + */ + var $openTags = array(); + /** + * list of block elements + * + * @var array + * TODO: what shall we do with <del> and <ins> ?! + */ + var $blockElements = array ( + # tag name => <bool> is block + # block elements + 'address' => true, + 'blockquote' => true, + 'center' => true, + 'del' => true, + 'dir' => true, + 'div' => true, + 'dl' => true, + 'fieldset' => true, + 'form' => true, + 'h1' => true, + 'h2' => true, + 'h3' => true, + 'h4' => true, + 'h5' => true, + 'h6' => true, + 'hr' => true, + 'ins' => true, + 'isindex' => true, + 'menu' => true, + 'noframes' => true, + 'noscript' => true, + 'ol' => true, + 'p' => true, + 'pre' => true, + 'table' => true, + 'ul' => true, + # set table elements and list items to block as well + 'thead' => true, + 'tbody' => true, + 'tfoot' => true, + 'td' => true, + 'tr' => true, + 'th' => true, + 'li' => true, + 'dd' => true, + 'dt' => true, + # header items and html / body as well + 'html' => true, + 'body' => true, + 'head' => true, + 'meta' => true, + 'link' => true, + 'style' => true, + 'title' => true, + # unfancy media tags, when indented should be rendered as block + 'map' => true, + 'object' => true, + 'param' => true, + 'embed' => true, + 'area' => true, + # inline elements + 'a' => false, + 'abbr' => false, + 'acronym' => false, + 'applet' => false, + 'b' => false, + 'basefont' => false, + 'bdo' => false, + 'big' => false, + 'br' => false, + 'button' => false, + 'cite' => false, + 'code' => false, + 'del' => false, + 'dfn' => false, + 'em' => false, + 'font' => false, + 'i' => false, + 'img' => false, + 'ins' => false, + 'input' => false, + 'iframe' => false, + 'kbd' => false, + 'label' => false, + 'q' => false, + 'samp' => false, + 'script' => false, + 'select' => false, + 'small' => false, + 'span' => false, + 'strong' => false, + 'sub' => false, + 'sup' => false, + 'textarea' => false, + 'tt' => false, + 'var' => false, + ); + /** + * get next node, set $this->html prior! + * + * @param void + * @return bool + */ + function nextNode() { + if (empty($this->html)) { + # we are done with parsing the html string + return false; + } + static $skipWhitespace = true; + if ($this->isStartTag && !$this->isEmptyTag) { + array_push($this->openTags, $this->tagName); + if (in_array($this->tagName, $this->preformattedTags)) { + # dont truncate whitespaces for <code> or <pre> contents + $this->keepWhitespace++; + } + } + + if ($this->html[0] == '<') { + $token = substr($this->html, 0, 9); + if (substr($token, 0, 2) == '<?') { + # xml prolog or other pi's + /** TODO **/ + #trigger_error('this might need some work', E_USER_NOTICE); + $pos = strpos($this->html, '>'); + $this->setNode('pi', $pos + 1); + return true; + } + if (substr($token, 0, 4) == '<!--') { + # comment + $pos = strpos($this->html, '-->'); + if ($pos === false) { + # could not find a closing -->, use next gt instead + # this is firefox' behaviour + $pos = strpos($this->html, '>') + 1; + } else { + $pos += 3; + } + $this->setNode('comment', $pos); + + $skipWhitespace = true; + return true; + } + if ($token == '<!DOCTYPE') { + # doctype + $this->setNode('doctype', strpos($this->html, '>')+1); + + $skipWhitespace = true; + return true; + } + if ($token == '<![CDATA[') { + # cdata, use text node + + # remove leading <![CDATA[ + $this->html = substr($this->html, 9); + + $this->setNode('text', strpos($this->html, ']]>')+3); + + # remove trailing ]]> and trim + $this->node = substr($this->node, 0, -3); + $this->handleWhitespaces(); + + $skipWhitespace = true; + return true; + } + if ($this->parseTag()) { + # seems to be a tag + # handle whitespaces + if ($this->isBlockElement) { + $skipWhitespace = true; + } else { + $skipWhitespace = false; + } + return true; + } + } + if ($this->keepWhitespace) { + $skipWhitespace = false; + } + # when we get here it seems to be a text node + $pos = strpos($this->html, '<'); + if ($pos === false) { + $pos = strlen($this->html); + } + $this->setNode('text', $pos); + $this->handleWhitespaces(); + if ($skipWhitespace && $this->node == ' ') { + return $this->nextNode(); + } + $skipWhitespace = false; + return true; + } + /** + * parse tag, set tag name and attributes, see if it's a closing tag and so forth... + * + * @param void + * @return bool + */ + function parseTag() { + static $a_ord, $z_ord, $special_ords; + if (!isset($a_ord)) { + $a_ord = ord('a'); + $z_ord = ord('z'); + $special_ords = array( + ord(':'), // for xml:lang + ord('-'), // for http-equiv + ); + } + + $tagName = ''; + + $pos = 1; + $isStartTag = $this->html[$pos] != '/'; + if (!$isStartTag) { + $pos++; + } + # get tagName + while (isset($this->html[$pos])) { + $pos_ord = ord(strtolower($this->html[$pos])); + if (($pos_ord >= $a_ord && $pos_ord <= $z_ord) || (!empty($tagName) && is_numeric($this->html[$pos]))) { + $tagName .= $this->html[$pos]; + $pos++; + } else { + $pos--; + break; + } + } + + $tagName = strtolower($tagName); + if (empty($tagName) || !isset($this->blockElements[$tagName])) { + # something went wrong => invalid tag + $this->invalidTag(); + return false; + } + if ($this->noTagsInCode && end($this->openTags) == 'code' && !($tagName == 'code' && !$isStartTag)) { + # we supress all HTML tags inside code tags + $this->invalidTag(); + return false; + } + + # get tag attributes + /** TODO: in html 4 attributes do not need to be quoted **/ + $isEmptyTag = false; + $attributes = array(); + $currAttrib = ''; + while (isset($this->html[$pos+1])) { + $pos++; + # close tag + if ($this->html[$pos] == '>' || $this->html[$pos].$this->html[$pos+1] == '/>') { + if ($this->html[$pos] == '/') { + $isEmptyTag = true; + $pos++; + } + break; + } + + $pos_ord = ord(strtolower($this->html[$pos])); + if ( ($pos_ord >= $a_ord && $pos_ord <= $z_ord) || in_array($pos_ord, $special_ords)) { + # attribute name + $currAttrib .= $this->html[$pos]; + } elseif (in_array($this->html[$pos], array(' ', "\t", "\n"))) { + # drop whitespace + } elseif (in_array($this->html[$pos].$this->html[$pos+1], array('="', "='"))) { + # get attribute value + $pos++; + $await = $this->html[$pos]; # single or double quote + $pos++; + $value = ''; + while (isset($this->html[$pos]) && $this->html[$pos] != $await) { + $value .= $this->html[$pos]; + $pos++; + } + $attributes[$currAttrib] = $value; + $currAttrib = ''; + } else { + $this->invalidTag(); + return false; + } + } + if ($this->html[$pos] != '>') { + $this->invalidTag(); + return false; + } + + if (!empty($currAttrib)) { + # html 4 allows something like <option selected> instead of <option selected="selected"> + $attributes[$currAttrib] = $currAttrib; + } + if (!$isStartTag) { + if (!empty($attributes) || $tagName != end($this->openTags)) { + # end tags must not contain any attributes + # or maybe we did not expect a different tag to be closed + $this->invalidTag(); + return false; + } + array_pop($this->openTags); + if (in_array($tagName, $this->preformattedTags)) { + $this->keepWhitespace--; + } + } + $pos++; + $this->node = substr($this->html, 0, $pos); + $this->html = substr($this->html, $pos); + $this->tagName = $tagName; + $this->tagAttributes = $attributes; + $this->isStartTag = $isStartTag; + $this->isEmptyTag = $isEmptyTag || in_array($tagName, $this->emptyTags); + if ($this->isEmptyTag) { + # might be not well formed + $this->node = preg_replace('# */? *>$#', ' />', $this->node); + } + $this->nodeType = 'tag'; + $this->isBlockElement = $this->blockElements[$tagName]; + return true; + } + /** + * handle invalid tags + * + * @param void + * @return void + */ + function invalidTag() { + $this->html = substr_replace($this->html, '<', 0, 1); + } + /** + * update all vars and make $this->html shorter + * + * @param string $type see description for $this->nodeType + * @param int $pos to which position shall we cut? + * @return void + */ + function setNode($type, $pos) { + if ($this->nodeType == 'tag') { + # set tag specific vars to null + # $type == tag should not be called here + # see this::parseTag() for more + $this->tagName = null; + $this->tagAttributes = null; + $this->isStartTag = null; + $this->isEmptyTag = null; + $this->isBlockElement = null; + + } + $this->nodeType = $type; + $this->node = substr($this->html, 0, $pos); + $this->html = substr($this->html, $pos); + } + /** + * check if $this->html begins with $str + * + * @param string $str + * @return bool + */ + function match($str) { + return substr($this->html, 0, strlen($str)) == $str; + } + /** + * truncate whitespaces + * + * @param void + * @return void + */ + function handleWhitespaces() { + if ($this->keepWhitespace) { + # <pre> or <code> before... + return; + } + # truncate multiple whitespaces to a single one + $this->node = preg_replace('#\s+#s', ' ', $this->node); + } + /** + * normalize self::node + * + * @param void + * @return void + */ + function normalizeNode() { + $this->node = '<'; + if (!$this->isStartTag) { + $this->node .= '/'.$this->tagName.'>'; + return; + } + $this->node .= $this->tagName; + foreach ($this->tagAttributes as $name => $value) { + $this->node .= ' '.$name.'="'.str_replace('"', '"', $value).'"'; + } + if ($this->isEmptyTag) { + $this->node .= ' /'; + } + $this->node .= '>'; + } +} + +/** + * indent a HTML string properly + * + * @param string $html + * @param string $indent optional + * @return string + */ +function indentHTML($html, $indent = " ", $noTagsInCode = false) { + $parser = new parseHTML; + $parser->noTagsInCode = $noTagsInCode; + $parser->html = $html; + $html = ''; + $last = true; # last tag was block elem + $indent_a = array(); + while($parser->nextNode()) { + if ($parser->nodeType == 'tag') { + $parser->normalizeNode(); + } + if ($parser->nodeType == 'tag' && $parser->isBlockElement) { + $isPreOrCode = in_array($parser->tagName, array('code', 'pre')); + if (!$parser->keepWhitespace && !$last && !$isPreOrCode) { + $html = rtrim($html)."\n"; + } + if ($parser->isStartTag) { + $html .= implode($indent_a); + if (!$parser->isEmptyTag) { + array_push($indent_a, $indent); + } + } else { + array_pop($indent_a); + if (!$isPreOrCode) { + $html .= implode($indent_a); + } + } + $html .= $parser->node; + if (!$parser->keepWhitespace && !($isPreOrCode && $parser->isStartTag)) { + $html .= "\n"; + } + $last = true; + } else { + if ($parser->nodeType == 'tag' && $parser->tagName == 'br') { + $html .= $parser->node."\n"; + $last = true; + continue; + } elseif ($last && !$parser->keepWhitespace) { + $html .= implode($indent_a); + $parser->node = ltrim($parser->node); + } + $html .= $parser->node; + + if (in_array($parser->nodeType, array('comment', 'pi', 'doctype'))) { + $html .= "\n"; + } else { + $last = false; + } + } + } + return $html; +} +/* +# testcase / example +error_reporting(E_ALL); + +$html = '<p>Simple block on one line:</p> + +<div>foo</div> + +<p>And nested without indentation:</p> + +<div> +<div> +<div> +foo +</div> +<div style=">"/> +</div> +<div>bar</div> +</div> + +<p>And with attributes:</p> + +<div> + <div id="foo"> + </div> +</div> + +<p>This was broken in 1.0.2b7:</p> + +<div class="inlinepage"> +<div class="toggleableend"> +foo +</div> +</div>'; +#$html = '<a href="asdfasdf" title=\'asdf\' foo="bar">asdf</a>'; +echo indentHTML($html); +die(); +*/ |