Merge pull request #1417 from annando/1502-improved-markdown
Updated libraries for Markdown and mobile detection
This commit is contained in:
commit
20208acb23
39 changed files with 6225 additions and 6158 deletions
|
|
@ -5,7 +5,7 @@ require_once("include/event.php");
|
|||
require_once("library/markdown.php");
|
||||
require_once("include/html2bbcode.php");
|
||||
require_once("include/bbcode.php");
|
||||
require_once("include/markdownify/markdownify.php");
|
||||
require_once("library/html-to-markdown/HTML_To_Markdown.php");
|
||||
|
||||
|
||||
// we don't want to support a bbcode specific markdown interpreter
|
||||
|
|
@ -17,19 +17,19 @@ function diaspora2bb($s) {
|
|||
|
||||
$s = html_entity_decode($s,ENT_COMPAT,'UTF-8');
|
||||
|
||||
// Simply remove cr.
|
||||
$s = str_replace("\r","",$s);
|
||||
// Remove CR to avoid problems with following code
|
||||
//$s = str_replace("\r","",$s);
|
||||
|
||||
// <br/> is invalid. Replace it with the valid expression
|
||||
$s = str_replace(array("<br/>", "</p>", "<p>", '<p dir="ltr">'),array("<br />", "<br />", "<br />", "<br />"),$s);
|
||||
|
||||
$s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s);
|
||||
// The parser cannot handle paragraphs correctly
|
||||
$s = str_replace(array("</p>", "<p>", '<p dir="ltr">'),array("<br>", "<br>", "<br>"),$s);
|
||||
|
||||
// Escaping the hash tags
|
||||
$s = preg_replace('/\#([^\s\#])/','#$1',$s);
|
||||
|
||||
$s = Markdown($s);
|
||||
|
||||
$s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s);
|
||||
|
||||
$s = str_replace('#','#',$s);
|
||||
|
||||
$s = html2bbcode($s);
|
||||
|
|
@ -56,6 +56,8 @@ function diaspora2bb($s) {
|
|||
|
||||
function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
|
||||
|
||||
$a = get_app();
|
||||
|
||||
$OriginalText = $Text;
|
||||
|
||||
// Since Diaspora is creating a summary for links, this function removes them before posting
|
||||
|
|
@ -88,41 +90,22 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
|
|||
$Text = $Text."<br />".$tagline;
|
||||
}
|
||||
|
||||
} else {
|
||||
} else
|
||||
$Text = bbcode($Text, $preserve_nl, false, 4);
|
||||
|
||||
// Libertree doesn't convert a harizontal rule if there isn't a linefeed
|
||||
$Text = str_replace(array("<hr />", "<hr>"), array("<br /><hr />", "<br><hr>"), $Text);
|
||||
}
|
||||
// If a link is followed by a quote then there should be a newline before it
|
||||
// Maybe we should make this newline at every time before a quote.
|
||||
$Text = str_replace(array("</a><blockquote>"), array("</a><br><blockquote>"), $Text);
|
||||
|
||||
$stamp1 = microtime(true);
|
||||
|
||||
// Now convert HTML to Markdown
|
||||
$md = new Markdownify(false, false, false);
|
||||
$Text = $md->parseString($Text);
|
||||
$Text = new HTML_To_Markdown($Text);
|
||||
|
||||
// The Markdownify converter converts underscores '_' in URLs to '\_', which
|
||||
// messes up the URL. Manually fix these
|
||||
$count = 1;
|
||||
$pos = bb_find_open_close($Text, '[', ']', $count);
|
||||
while($pos !== false) {
|
||||
$start = substr($Text, 0, $pos['start']);
|
||||
$subject = substr($Text, $pos['start'], $pos['end'] - $pos['start'] + 1);
|
||||
$end = substr($Text, $pos['end'] + 1);
|
||||
$a->save_timestamp($stamp1, "parser");
|
||||
|
||||
$subject = str_replace('\_', '_', $subject);
|
||||
$Text = $start . $subject . $end;
|
||||
|
||||
$count++;
|
||||
$pos = bb_find_open_close($Text, '[', ']', $count);
|
||||
}
|
||||
|
||||
// If the text going into bbcode() has a plain URL in it, i.e.
|
||||
// with no [url] tags around it, it will come out of parseString()
|
||||
// looking like: <http://url.com>, which gets removed by strip_tags().
|
||||
// So take off the angle brackets of any such URL
|
||||
$Text = preg_replace("/<http(.*?)>/is", "http$1", $Text);
|
||||
|
||||
// Remove all unconverted tags
|
||||
$Text = strip_tags($Text);
|
||||
// Libertree has a problem with escaped hashtags.
|
||||
$Text = str_replace(array('\#'), array('#'), $Text);
|
||||
|
||||
// Remove any leading or trailing whitespace, as this will mess up
|
||||
// the Diaspora signature verification and cause the item to disappear
|
||||
|
|
|
|||
|
|
@ -168,6 +168,8 @@ function bb_remove_share_information($Text, $plaintext = false, $nolink = false)
|
|||
}
|
||||
|
||||
function bb_cleanup_share($shared, $plaintext, $nolink) {
|
||||
$shared[1] = trim($shared[1]);
|
||||
|
||||
if (!in_array($shared[2], array("type-link", "type-video")))
|
||||
return($shared[0]);
|
||||
|
||||
|
|
@ -178,7 +180,7 @@ function bb_cleanup_share($shared, $plaintext, $nolink) {
|
|||
return($shared[0]);
|
||||
|
||||
if ($nolink)
|
||||
return(trim($shared[1]));
|
||||
return($shared[1]);
|
||||
|
||||
$title = "";
|
||||
$link = "";
|
||||
|
|
@ -189,6 +191,9 @@ function bb_cleanup_share($shared, $plaintext, $nolink) {
|
|||
if (isset($bookmark[1][0]))
|
||||
$link = $bookmark[1][0];
|
||||
|
||||
if (($shared[1] != "") AND (strpos($title, $shared[1]) !== false))
|
||||
$shared[1] = $title;
|
||||
|
||||
if (($title != "") AND ((strpos($shared[1],$title) !== false) OR
|
||||
(similar_text($shared[1],$title) / strlen($title)) > 0.9))
|
||||
$title = "";
|
||||
|
|
|
|||
|
|
@ -834,6 +834,7 @@ function diaspora_post($importer,$xml,$msg) {
|
|||
$str_tags = '';
|
||||
|
||||
$tags = get_tags($body);
|
||||
rsort($tags);
|
||||
|
||||
if(count($tags)) {
|
||||
foreach($tags as $tag) {
|
||||
|
|
@ -843,9 +844,9 @@ function diaspora_post($importer,$xml,$msg) {
|
|||
|
||||
// don't link tags that are already embedded in links
|
||||
|
||||
if(preg_match('/\[(.*?)' . preg_quote($tag,'/') . '(.*?)\]/',$body))
|
||||
if(preg_match('/\[(\S*?)' . preg_quote($tag,'/') . '(\S*?)\]/',$body))
|
||||
continue;
|
||||
if(preg_match('/\[(.*?)\]\((.*?)' . preg_quote($tag,'/') . '(.*?)\)/',$body))
|
||||
if(preg_match('/\[(\S*?)\]\((\S*?)' . preg_quote($tag,'/') . '(\S*?)\)/',$body))
|
||||
continue;
|
||||
|
||||
$basetag = str_replace('_',' ',substr($tag,1));
|
||||
|
|
|
|||
|
|
@ -1,504 +0,0 @@
|
|||
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!
|
||||
|
||||
|
||||
|
|
@ -1,29 +0,0 @@
|
|||
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.
|
||||
|
|
@ -1,51 +0,0 @@
|
|||
<?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>
|
||||
|
|
@ -1,1197 +0,0 @@
|
|||
<?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);
|
||||
}
|
||||
}
|
||||
|
|
@ -1,33 +0,0 @@
|
|||
#!/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";
|
||||
|
|
@ -1,489 +0,0 @@
|
|||
<?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);
|
||||
}
|
||||
}
|
||||
|
|
@ -1,618 +0,0 @@
|
|||
<?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();
|
||||
*/
|
||||
11
library/Mobile_Detect/.gitignore
vendored
Normal file
11
library/Mobile_Detect/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,11 @@
|
|||
vendor/
|
||||
nbproject/
|
||||
/*.buildpath
|
||||
/*.project
|
||||
/.settings
|
||||
/error.log
|
||||
/export/nicejson
|
||||
.idea/
|
||||
*.iml
|
||||
/coverage
|
||||
/phpunit.phar
|
||||
3
library/Mobile_Detect/.gitmodules
vendored
Normal file
3
library/Mobile_Detect/.gitmodules
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
[submodule "export/nicejson"]
|
||||
path = export/nicejson
|
||||
url = https://github.com/GerHobbelt/nicejson-php.git
|
||||
24
library/Mobile_Detect/.php_cs
Normal file
24
library/Mobile_Detect/.php_cs
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
<?php
|
||||
|
||||
use Symfony\CS\FixerInterface;
|
||||
|
||||
$finder = Symfony\CS\Finder\DefaultFinder::create()
|
||||
->notName('LICENSE')
|
||||
->notName('README.md')
|
||||
->notName('.php_cs')
|
||||
->notName('composer.*')
|
||||
->notName('phpunit.xml*')
|
||||
->notName('*.phar')
|
||||
->exclude('vendor')
|
||||
->exclude('examples')
|
||||
->exclude('Symfony/CS/Tests/Fixer')
|
||||
->notName('ElseifFixer.php')
|
||||
->exclude('data')
|
||||
->in(__DIR__)
|
||||
;
|
||||
|
||||
return Symfony\CS\Config\Config::create()
|
||||
->finder($finder)
|
||||
;
|
||||
|
||||
|
||||
17
library/Mobile_Detect/.travis.yml
Normal file
17
library/Mobile_Detect/.travis.yml
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
language: php
|
||||
php:
|
||||
- "5.2"
|
||||
- "5.3"
|
||||
- "5.4"
|
||||
- "5.5"
|
||||
- "5.6"
|
||||
|
||||
branches:
|
||||
only:
|
||||
- devel
|
||||
|
||||
script:
|
||||
- phpunit -v -c tests/phpunit.xml
|
||||
|
||||
notifications:
|
||||
email: false
|
||||
48
library/Mobile_Detect/LICENSE.txt
Normal file
48
library/Mobile_Detect/LICENSE.txt
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
MIT License
|
||||
|
||||
Copyright (c) <2011-2014> <Serban Ghita> <serbanghita@gmail.com>
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, sublicense, and/or sell copies of the Software, and to
|
||||
permit persons to whom the Software is furnished to do so, subject to
|
||||
the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included
|
||||
in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
|
||||
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
||||
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
||||
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
||||
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
||||
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
Developer’s Certificate of Origin 1.1
|
||||
|
||||
By making a contribution to this project, I certify that:
|
||||
|
||||
(a) The contribution was created in whole or in part by me and I
|
||||
have the right to submit it under the open source license
|
||||
indicated in the file; or
|
||||
|
||||
(b) The contribution is based upon previous work that, to the best
|
||||
of my knowledge, is covered under an appropriate open source
|
||||
license and I have the right under that license to submit that
|
||||
work with modifications, whether created in whole or in part
|
||||
by me, under the same open source license (unless I am
|
||||
permitted to submit under a different license), as indicated
|
||||
in the file; or
|
||||
|
||||
(c) The contribution was provided directly to me by some other
|
||||
person who certified (a), (b) or (c) and I have not modified
|
||||
it.
|
||||
|
||||
(d) I understand and agree that this project and the contribution
|
||||
are public and that a record of the contribution (including all
|
||||
personal information I submit with it, including my sign-off) is
|
||||
maintained indefinitely and may be redistributed consistent with
|
||||
this project or the open source license(s) involved.
|
||||
1
library/Mobile_Detect/Mobile_Detect.json
Normal file
1
library/Mobile_Detect/Mobile_Detect.json
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
219
library/Mobile_Detect/README.md
Normal file
219
library/Mobile_Detect/README.md
Normal file
|
|
@ -0,0 +1,219 @@
|
|||
[](https://travis-ci.org/serbanghita/Mobile-Detect) [](https://packagist.org/packages/mobiledetect/mobiledetectlib) [](https://packagist.org/packages/mobiledetect/mobiledetectlib) [](https://packagist.org/packages/mobiledetect/mobiledetectlib) [](https://packagist.org/packages/mobiledetect/mobiledetectlib)
|
||||
[](https://gitter.im/serbanghita/Mobile-Detect?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)
|
||||
|
||||
|
||||
|
||||
> Motto: "Every business should have a mobile detection script to detect mobile readers."
|
||||
|
||||
<i>Mobile_Detect is a lightweight PHP class for detecting mobile devices (including tablets).
|
||||
It uses the User-Agent string combined with specific HTTP headers to detect the mobile environment.</i>
|
||||
|
||||
> We're commited to make Mobile_Detect the best open-source mobile detection resource and this is why before each release we're running [unit tests](./tests), we also research and update the detection rules on <b>daily</b> and <b>weekly</b> basis.
|
||||
|
||||
Your website's _content strategy_ is important! You need a complete toolkit to deliver an experience that is _optimized_, _fast_ and _relevant_ to your users. Mobile_Detect class is a [server-side detection](http://www.w3.org/TR/mwabp/#bp-devcap-detection) tool that can help you with your RWD strategy, it is not a replacement for CSS3 media queries or other forms of client-side feature detection.
|
||||
|
||||
##### This month updates
|
||||
|
||||
First of all a **BIG THANK YOU** to our growing community for your continuous support and for all the feedback received! I'm still working my way with the current issues and all the emails.
|
||||
|
||||
Nick is almost done with all the code for the upcoming `3.0.0` so that I only have to integrate the new parsing engine. We will release minor `2.8.xx` versions until a feature freeze where we will switch to the new branch. You will all be announced before this and hopefully we can make the transition smooth for everyone.
|
||||
|
||||
<a href="http://trycatch.us/"><img align="left" src="http://assets.mobiledetect.net/img/try_catch_logo_80px.jpg" hspace="20"></a> Last but not least, special thanks for supporting us to our friends from [TryCatch.us](http://trycatch.us/) who _are set to carefully curate the most talented developers in Europe_!
|
||||
|
||||
Thank you all and we're excited for the new release!
|
||||
|
||||
##### Download and demo
|
||||
|
||||
|Download|Docs|Examples|
|
||||
|-------------|-------------|-------------|
|
||||
|[Go to releases](../../tags)|[Become a contributor](../../wiki/Become-a-contributor)|[Code examples](../../wiki/Code-examples)
|
||||
|[Mobile_Detect.php](./Mobile_Detect.php)|[History](../../wiki/History)|[:iphone: Live demo!](http://is.gd/mobiletest)
|
||||
|[Composer package](https://packagist.org/packages/mobiledetect/mobiledetectlib)|
|
||||
|
||||
##### Help
|
||||
|
||||
|Pledgie|Paypal|
|
||||
|-------|------|
|
||||
|[Donate :+1:](http://pledgie.com/campaigns/21856)|[Donate :beer:](https://www.paypal.com/cgi-bin/webscr?cmd=_donations&business=mobiledetectlib%40gmail%2ecom&lc=US&item_name=Mobile%20Detect¤cy_code=USD&bn=PP%2dDonationsBF%3abtn_donate_SM%2egif%3aNonHosted)|
|
||||
|
||||
|
||||
I'm currently paying for hosting and spend a lot of my family time to maintain the project and planning the future releases.
|
||||
I would highly appreciate any money donations that will keep the research going.
|
||||
|
||||
Special thanks to the community :+1: for donations, [BrowserStack](http://browserstack.com) - for providing access to their great platform, [Zend](http://zend.com) - for donating licenses, [Dragos Gavrila](https://twitter.com/grafician) who contributed with the logo.
|
||||
|
||||
##### 3rd party modules / [Submit new](../../issues/new?title=New%203rd%20party%20module&body=Name, Link and Description of the module.)
|
||||
|
||||
:point_right: Keep `Mobile_Detect.php` class in a separate `module` and do NOT include it in your script core because of the high frequency of updates.
|
||||
:point_right: When including the class into you `web application` or `module` always use `include_once '../path/to/Mobile_Detect.php` to prevent conflicts.
|
||||
|
||||
<table>
|
||||
|
||||
<tr>
|
||||
<td>Varnish Cache</td>
|
||||
<td>
|
||||
<p><a href="https://github.com/willemk/varnish-mobiletranslate">Varnish Mobile Detect</a> - Drop-in varnish solution to mobile user detection based on the Mobile-Detect library. Made by <a href="https://github.com/willemk">willemk</a></p>
|
||||
<p><a href="https://github.com/carlosabalde/mobiledetect2vcl">mobiledetect2vcl</a> - Python script to transform the Mobile Detect JSON database into an UA-based mobile detection VCL subroutine easily integrable in any Varnish Cache configuration. Made by <a href="https://github.com/carlosabalde">Carlos Abalde</a></p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>WordPress</td>
|
||||
<td>
|
||||
<p><a href="http://wordpress.org/extend/plugins/wp-mobile-detect/">WordPress Mobile Detect</a> - Gives you the ability to wrap that infographic in a `[notdevice][/notdevice]` shortcode so at the server level <code>WordPress</code> will decide to show that content only if the user is NOT on a phone or tablet. Made by <a href="http://profiles.wordpress.org/professor44/">Jesse Friedman</a>.</p>
|
||||
|
||||
<p><a href="http://wordpress.org/plugins/mobble/">mobble</a> - provides mobile related conditional functions for your site. e.g. is_iphone(), is_mobile() and is_tablet(). Made by Scott Evans.</p>
|
||||
|
||||
<p><a href="https://github.com/iamspacehead/responsage">WordPress Responsage</a> - A small <code>WordPress</code> theme plugin that allows you to make your images responsive. Made by <a href="https://github.com/iamspacehead">Adrian Ciaschetti</a>.</p>
|
||||
|
||||
<p><a href="http://wordpress.org/plugins/social-popup/">Social PopUP</a> - This plugin will display a popup or splash screen when a new user visit your site showing a Google+, Twitter and Facebook follow links. It uses Mobile_Detect to detect mobile devices.</p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Drupal</td>
|
||||
<td>
|
||||
<p><a href="http://drupal.org/project/mobile_switch">Drupal Mobile Switch</a> - The Mobile Switch <code>Drupal</code> module provides a automatic theme switch functionality for mobile devices,
|
||||
detected by Browscap or Mobile Detect. Made by <a href="http://drupal.org/user/45267">Siegfried Neumann</a>.</p>
|
||||
|
||||
<p><a href="http://drupal.org/project/context_mobile_detect">Drupal Context Mobile Detect</a> - This is a <code>Drupal context</code> module which integrates Context and PHP Mobile Detect library.
|
||||
Created by <a href="http://drupal.org/user/432492">Artem Shymko</a>.</p>
|
||||
|
||||
<p><a href="http://drupal.org/project/mobile_detect">Drupal Mobile Detect</a> - Lightweight mobile detect module for <code>Drupal</code> created by <a href="http://drupal.org/user/325244">Matthew Donadio</a></p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Joomla</td>
|
||||
<td><p><a href="http://www.yagendoo.com/en/blog/free-mobile-detection-plugin-for-joomla.html">yagendoo Joomla! Mobile Detection Plugin</a> - Lightweight PHP plugin for Joomla! that detects a mobile browser using the Mobile Detect class. Made by <a href="http://www.yagendoo.com/">yagendoo media</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Magento</td>
|
||||
<td><p><a href="http://www.magentocommerce.com/magento-connect/catalog/product/view/id/16835/">Magento</a> - This <code>Magento helper</code> from Optimise Web enables the use of all functions provided by MobileDetect.net.
|
||||
Made by <a href="http://www.kathirvel.com">Kathir Vel</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>PrestaShop</td>
|
||||
<td><p><a href="http://www.prestashop.com/">PrestaShop</a> is a free, secure and open source shopping cart platform. Mobile_Detect is included in the default package since 1.5.x.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Zend Framework</td>
|
||||
<td>
|
||||
<p><a href="https://github.com/neilime/zf2-mobile-detect.git">ZF2 Mobile-Detect</a> - Zend Framework 2 module that provides Mobile-Detect features (Mobile_Detect class as a service, helper for views and plugin controllers). Made by <a href="https://github.com/neilime">neilime</a></p>
|
||||
|
||||
<p><a href="https://github.com/nikolaposa/MobileDetectModule">ZF2 MobileDetectModule</a> - Facilitates integration of a PHP MobileDetect class with some ZF2-based application. Has similar idea like the existing ZF2 Mobile-Detect module, but differs in initialization and provision routine of the actual Mobile_Detect class. Appropriate view helper and controller plugin also have different conceptions. Made by <a href="https://github.com/nikolaposa">Nikola Posa</a></p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Symfony</td>
|
||||
<td><p><a href="https://github.com/suncat2000/MobileDetectBundle">Symfony2 Mobile Detect Bundle</a> - The bundle for detecting mobile devices, manage mobile view and redirect to the mobile and tablet version.
|
||||
Made by <a href="https://github.com/suncat2000">Nikolay Ivlev</a>.</p>
|
||||
<p><a href="https://github.com/jbinfo/MobileDetectServiceProvider">Silex Mobile Detect Service Provider</a> - <code>Silex</code> service provider to interact with Mobile detect class methods. Made by <a href="https://github.com/jbinfo">Lhassan Baazzi</a>.</p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Laravel</td>
|
||||
<td>
|
||||
<p><a href="https://github.com/jenssegers/Laravel-Agent">Laravel-Agent</a> a user agent class for Laravel, based on Mobile Detect with some additional functionality. Made by <a href="https://github.com/jenssegers">Jens Segers</a>.</p>
|
||||
<p><a href="https://github.com/hisorange/browser-detect">BrowserDetect</a> is a browser & mobile detection package, collects and wrap together the best user-agent identifiers for Laravel. Created by <a href="https://github.com/hisorange">Varga Zsolt</a>.</p>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>ExpressionEngine</td>
|
||||
<td><p><a href="https://github.com/garethtdavies/detect-mobile">EE2 Detect Mobile</a> - Lightweight PHP plugin for <code>EE2</code> that detects a mobile browser using the Mobile Detect class. Made by <a href="https://github.com/garethtdavies">Gareth Davies</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Yii Framework</td>
|
||||
<td><p><a href="https://github.com/iamsalnikov/MobileDetect">Yii Extension</a> - Mobile detect plugin for Yii framework. Made by <a href="https://github.com/iamsalnikov">Alexey Salnikov</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>CakePHP</td>
|
||||
<td><p><a href="https://github.com/chronon/CakePHP-MobileDetectComponent-Plugin">CakePHP MobileDetect</a> - <code>plugin</code> component for <code>CakePHP</code> 2.x. Made by <a href="https://github.com/chronon">Gregory Gaskill</a></p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>FuelPHP</td>
|
||||
<td><a href="https://github.com/rob-bar/special_agent">Special Agent</a> is a FuelPHP package which uses php-mobile-detect to determine whether a device is mobile or not.
|
||||
It overrides the Fuelphp Agent class its methods. Made by <a href="https://github.com/rob-bar">Robbie Bardjin</a>.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Typo3</td>
|
||||
<td><a href="http://docs.typo3.org/typo3cms/extensions/px_mobiledetect/1.0.2/">px_mobiledetect</a> is an extension that helps to detect visitor's mobile device class (if that’s tablet or mobile device like smartphone). Made by Alexander Tretyak.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Statamic</td>
|
||||
<td><p><a href="https://github.com/sergeifilippov/statamic-mobile-detect">Statamic CMS Mobile Detect</a> - <code>plugin</code>. Made by <a href="https://github.com/haikulab/statamic-mobile-detect">Sergei Filippov of Haiku Lab</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Kohana</td>
|
||||
<td><p><a href="https://github.com/madeinnordeste/kohana-mobile-detect">Kohana Mobile Detect</a> - an example of implementation of <code>Mobile_Detect</code> class with Kohana framework. Written by <a href="https://github.com/madeinnordeste">Luiz Alberto S. Ribeiro</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>mobile-detect.js</td>
|
||||
<td><p>A <a href="https://github.com/hgoebl/mobile-detect.js">JavaScript port</a> of Mobile-Detect class. Made by <a href="https://github.com/hgoebl">Heinrich Goebl</a></p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Perl</td>
|
||||
<td><p><a href="http://www.buzzerstar.com/development/">MobileDetect.pm</a> - <code>Perl module</code> for Mobile Detect. Made by <a href="http://www.buzzerstar.com/">Sebastian Enger</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>python</td>
|
||||
<td><p><a href="http://pypi.python.org/pypi/pymobiledetect">pymobiledetect</a> - Mobile detect <code>python package</code>. Made by Bas van Oostveen.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Ruby</td>
|
||||
<td><p><a href="https://github.com/ktaragorn/mobile_detect">mobile_detect.rb</a> - A <code>Ruby gem</code> using the JSON data exposed by the php project and implementing a basic subset of the API (as much as can be done by the exposed data). Made by <a href="https://github.com/ktaragorn">Karthik T</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>GoMobileDetect</td>
|
||||
<td><p><a href="https://github.com/Shaked/gomobiledetect">GoMobileDetect</a> - Go port of Mobile Detect class. Made by <a href="https://github.com/Shaked">Shaked</a>.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>MemHT</td>
|
||||
<td><p><a href="http://www.memht.com/">MemHT</a> is a Free PHP CMS and Blog that permit the creation and the management online of websites with few and easy steps. Has the class included in the core.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>concrete5</td>
|
||||
<td><p><a href="https://www.concrete5.org/">concrete5</a> is a CMS that is free and open source. The library is included in the core.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>engine7</td>
|
||||
<td><p><a href="https://github.com/gchiappe/exengine7">ExEngine 7</a> PHP Open Source Framework. The Mobile_Detect class is included in the engine.</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Zikula</td>
|
||||
<td><p><a href="http://zikula.org/">Zikula</a> is a free and open-source Content Management Framework, which allows you to run impressive websites and build powerful online applications. The core uses Mobile-Detect to switch to a special Mobile theme, using jQueryMobile</p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>UserAgentInfo</td>
|
||||
<td><p><a href="https://github.com/quentin389/UserAgentInfo">UserAgentInfo</a> is a PHP class for parsing user agent strings (HTTP_USER_AGENT). Includes mobile checks, bot checks, browser types/versions and more.
|
||||
Based on browscap, Mobile_Detect and ua-parser. Created for high traffic websites and fast batch processing. Made by <a href="https://github.com/quentin389">quentin389</a></p></td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td>Craft CMS</td>
|
||||
<td><p><a href="https://github.com/lewisjenkins/craft-lj-mobiledetect">LJ Mobile Detect</a> is a simple implementation of Mobile Detect for Craft CMS. Made by <a href="https://github.com/lewisjenkins">Lewis Jenkins</a></p></td>
|
||||
</tr>
|
||||
|
||||
</table>
|
||||
30
library/Mobile_Detect/composer.json
Normal file
30
library/Mobile_Detect/composer.json
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
{
|
||||
"name": "mobiledetect/mobiledetectlib",
|
||||
"type": "library",
|
||||
"description": "Mobile_Detect is a lightweight PHP class for detecting mobile devices. It uses the User-Agent string combined with specific HTTP headers to detect the mobile environment.",
|
||||
"keywords": ["mobile", "mobile detect", "mobile detector", "php mobile detect", "detect mobile devices"],
|
||||
"homepage": "https://github.com/serbanghita/Mobile-Detect",
|
||||
"license": "MIT",
|
||||
"authors": [
|
||||
{
|
||||
"name": "Serban Ghita",
|
||||
"email": "serbanghita@gmail.com",
|
||||
"homepage": "http://mobiledetect.net",
|
||||
"role": "Developer"
|
||||
}
|
||||
],
|
||||
"require": {
|
||||
"php": ">=5.0.0"
|
||||
},
|
||||
"require-dev": {
|
||||
"phpunit/phpunit": "*",
|
||||
"johnkary/phpunit-speedtrap": "~1.0@dev",
|
||||
"codeclimate/php-test-reporter": "dev-master"
|
||||
},
|
||||
"autoload": {
|
||||
"classmap": ["Mobile_Detect.php"],
|
||||
"psr-0": {
|
||||
"Detection": "namespaced/"
|
||||
}
|
||||
}
|
||||
}
|
||||
22
library/Mobile_Detect/namespaced/Detection/MobileDetect.php
Normal file
22
library/Mobile_Detect/namespaced/Detection/MobileDetect.php
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
<?php
|
||||
/**
|
||||
* Little piece of PHP to make Mobile_Detect auto-loadable in PSR-0 compatible PHP autoloaders like
|
||||
* the Symfony Universal ClassLoader by Fabien Potencier. Since PSR-0 handles an underscore in
|
||||
* classnames (on the filesystem) as a slash, "Mobile_Detect.php" autoloaders will try to convert
|
||||
* the classname and path to "Mobile\Detect.php". This script will ensure autoloading with:
|
||||
* - Namespace: Detection
|
||||
* - Classname: MobileDetect
|
||||
* - Namespased: \Detection\MobileDetect
|
||||
* - Autoload path: ./namespaced
|
||||
* - Converted path: ./namespaced/Detection/MobileDetect.php
|
||||
*
|
||||
* Don't forget to use MobileDetect (instead of Mobile_Detect) as class in code when autoloading.
|
||||
*
|
||||
* Thanks to @WietseWind.
|
||||
* For details please check: https://github.com/serbanghita/Mobile-Detect/pull/120
|
||||
*/
|
||||
|
||||
namespace Detection;
|
||||
require_once dirname(__FILE__) . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . 'Mobile_Detect.php';
|
||||
|
||||
class MobileDetect extends \Mobile_Detect {}
|
||||
3
library/html-to-markdown/.gitignore
vendored
Normal file
3
library/html-to-markdown/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
~*
|
||||
vendor
|
||||
composer.lock
|
||||
6
library/html-to-markdown/.travis.yml
Normal file
6
library/html-to-markdown/.travis.yml
Normal file
|
|
@ -0,0 +1,6 @@
|
|||
language: php
|
||||
php:
|
||||
- "5.5"
|
||||
- "5.4"
|
||||
- "5.3"
|
||||
script: phpunit --no-configuration HTML_To_MarkdownTest ./tests/HTML_To_MarkdownTest.php
|
||||
598
library/html-to-markdown/HTML_To_Markdown.php
Normal file
598
library/html-to-markdown/HTML_To_Markdown.php
Normal file
|
|
@ -0,0 +1,598 @@
|
|||
<?php
|
||||
/**
|
||||
* Class HTML_To_Markdown
|
||||
*
|
||||
* A helper class to convert HTML to Markdown.
|
||||
*
|
||||
* @version 2.2.1
|
||||
* @author Nick Cernis <nick@cern.is>
|
||||
* @link https://github.com/nickcernis/html2markdown/ Latest version on GitHub.
|
||||
* @link http://twitter.com/nickcernis Nick on twitter.
|
||||
* @license http://www.opensource.org/licenses/mit-license.php MIT
|
||||
*/
|
||||
class HTML_To_Markdown
|
||||
{
|
||||
/**
|
||||
* @var DOMDocument The root of the document tree that holds our HTML.
|
||||
*/
|
||||
private $document;
|
||||
|
||||
/**
|
||||
* @var string|boolean The Markdown version of the original HTML, or false if conversion failed
|
||||
*/
|
||||
private $output;
|
||||
|
||||
/**
|
||||
* @var array Class-wide options users can override.
|
||||
*/
|
||||
private $options = array(
|
||||
'header_style' => 'setext', // Set to "atx" to output H1 and H2 headers as # Header1 and ## Header2
|
||||
'suppress_errors' => true, // Set to false to show warnings when loading malformed HTML
|
||||
'strip_tags' => false, // Set to true to strip tags that don't have markdown equivalents. N.B. Strips tags, not their content. Useful to clean MS Word HTML output.
|
||||
'bold_style' => '**', // Set to '__' if you prefer the underlined style
|
||||
'italic_style' => '*', // Set to '_' if you prefer the underlined style
|
||||
'remove_nodes' => '', // space-separated list of dom nodes that should be removed. example: "meta style script"
|
||||
);
|
||||
|
||||
|
||||
/**
|
||||
* Constructor
|
||||
*
|
||||
* Set up a new DOMDocument from the supplied HTML, convert it to Markdown, and store it in $this->$output.
|
||||
*
|
||||
* @param string $html The HTML to convert to Markdown.
|
||||
* @param array $overrides [optional] List of style and error display overrides.
|
||||
*/
|
||||
public function __construct($html = null, $overrides = null)
|
||||
{
|
||||
if ($overrides)
|
||||
$this->options = array_merge($this->options, $overrides);
|
||||
|
||||
if ($html)
|
||||
$this->convert($html);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Setter for conversion options
|
||||
*
|
||||
* @param $name
|
||||
* @param $value
|
||||
*/
|
||||
public function set_option($name, $value)
|
||||
{
|
||||
$this->options[$name] = $value;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert
|
||||
*
|
||||
* Loads HTML and passes to get_markdown()
|
||||
*
|
||||
* @param $html
|
||||
* @return string The Markdown version of the html
|
||||
*/
|
||||
public function convert($html)
|
||||
{
|
||||
$html = preg_replace('~>\s+<~', '><', $html); // Strip white space between tags to prevent creation of empty #text nodes
|
||||
|
||||
$this->document = new DOMDocument();
|
||||
|
||||
if ($this->options['suppress_errors'])
|
||||
libxml_use_internal_errors(true); // Suppress conversion errors (from http://bit.ly/pCCRSX )
|
||||
|
||||
$this->document->loadHTML('<?xml encoding="UTF-8">' . $html); // Hack to load utf-8 HTML (from http://bit.ly/pVDyCt )
|
||||
$this->document->encoding = 'UTF-8';
|
||||
|
||||
if ($this->options['suppress_errors'])
|
||||
libxml_clear_errors();
|
||||
|
||||
return $this->get_markdown($html);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Is Child Of?
|
||||
*
|
||||
* Is the node a child of the given parent tag?
|
||||
*
|
||||
* @param $parent_name string|array The name of the parent node(s) to search for e.g. 'code' or array('pre', 'code')
|
||||
* @param $node
|
||||
* @return bool
|
||||
*/
|
||||
private static function is_child_of($parent_name, $node)
|
||||
{
|
||||
for ($p = $node->parentNode; $p != false; $p = $p->parentNode) {
|
||||
if (is_null($p))
|
||||
return false;
|
||||
|
||||
if ( is_array($parent_name) && in_array($p->nodeName, $parent_name) )
|
||||
return true;
|
||||
|
||||
if ($p->nodeName == $parent_name)
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert Children
|
||||
*
|
||||
* Recursive function to drill into the DOM and convert each node into Markdown from the inside out.
|
||||
*
|
||||
* Finds children of each node and convert those to #text nodes containing their Markdown equivalent,
|
||||
* starting with the innermost element and working up to the outermost element.
|
||||
*
|
||||
* @param $node
|
||||
*/
|
||||
private function convert_children($node)
|
||||
{
|
||||
// Don't convert HTML code inside <code> and <pre> blocks to Markdown - that should stay as HTML
|
||||
if (self::is_child_of(array('pre', 'code'), $node))
|
||||
return;
|
||||
|
||||
// If the node has children, convert those to Markdown first
|
||||
if ($node->hasChildNodes()) {
|
||||
$length = $node->childNodes->length;
|
||||
|
||||
for ($i = 0; $i < $length; $i++) {
|
||||
$child = $node->childNodes->item($i);
|
||||
$this->convert_children($child);
|
||||
}
|
||||
}
|
||||
|
||||
// Now that child nodes have been converted, convert the original node
|
||||
$markdown = $this->convert_to_markdown($node);
|
||||
|
||||
// Create a DOM text node containing the Markdown equivalent of the original node
|
||||
$markdown_node = $this->document->createTextNode($markdown);
|
||||
|
||||
// Replace the old $node e.g. "<h3>Title</h3>" with the new $markdown_node e.g. "### Title"
|
||||
$node->parentNode->replaceChild($markdown_node, $node);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Get Markdown
|
||||
*
|
||||
* Sends the body node to convert_children() to change inner nodes to Markdown #text nodes, then saves and
|
||||
* returns the resulting converted document as a string in Markdown format.
|
||||
*
|
||||
* @return string|boolean The converted HTML as Markdown, or false if conversion failed
|
||||
*/
|
||||
private function get_markdown()
|
||||
{
|
||||
// Work on the entire DOM tree (including head and body)
|
||||
$input = $this->document->getElementsByTagName("html")->item(0);
|
||||
|
||||
if (!$input)
|
||||
return false;
|
||||
|
||||
// Convert all children of this root element. The DOMDocument stored in $this->doc will
|
||||
// then consist of #text nodes, each containing a Markdown version of the original node
|
||||
// that it replaced.
|
||||
$this->convert_children($input);
|
||||
|
||||
// Sanitize and return the body contents as a string.
|
||||
$markdown = $this->document->saveHTML(); // stores the DOMDocument as a string
|
||||
$markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8');
|
||||
$markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8'); // Double decode to cover cases like &nbsp; http://www.php.net/manual/en/function.htmlentities.php#99984
|
||||
$markdown = preg_replace("/<!DOCTYPE [^>]+>/", "", $markdown); // Strip doctype declaration
|
||||
$unwanted = array('<html>', '</html>', '<body>', '</body>', '<head>', '</head>', '<?xml encoding="UTF-8">', '
');
|
||||
$markdown = str_replace($unwanted, '', $markdown); // Strip unwanted tags
|
||||
$markdown = trim($markdown, "\n\r\0\x0B");
|
||||
|
||||
$this->output = $markdown;
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert to Markdown
|
||||
*
|
||||
* Converts an individual node into a #text node containing a string of its Markdown equivalent.
|
||||
*
|
||||
* Example: An <h3> node with text content of "Title" becomes a text node with content of "### Title"
|
||||
*
|
||||
* @param $node
|
||||
* @return string The converted HTML as Markdown
|
||||
*/
|
||||
private function convert_to_markdown($node)
|
||||
{
|
||||
$tag = $node->nodeName; // the type of element, e.g. h1
|
||||
$value = $node->nodeValue; // the value of that element, e.g. The Title
|
||||
|
||||
// Strip nodes named in remove_nodes
|
||||
$tags_to_remove = explode(' ', $this->options['remove_nodes']);
|
||||
if ( in_array($tag, $tags_to_remove) )
|
||||
return false;
|
||||
|
||||
switch ($tag) {
|
||||
case "p":
|
||||
$markdown = (trim($value)) ? rtrim($value) . PHP_EOL . PHP_EOL : '';
|
||||
break;
|
||||
case "pre":
|
||||
$markdown = PHP_EOL . $this->convert_code($node) . PHP_EOL;
|
||||
break;
|
||||
case "h1":
|
||||
case "h2":
|
||||
$markdown = $this->convert_header($tag, $node);
|
||||
break;
|
||||
case "h3":
|
||||
$markdown = "### " . $value . PHP_EOL . PHP_EOL;
|
||||
break;
|
||||
case "h4":
|
||||
$markdown = "#### " . $value . PHP_EOL . PHP_EOL;
|
||||
break;
|
||||
case "h5":
|
||||
$markdown = "##### " . $value . PHP_EOL . PHP_EOL;
|
||||
break;
|
||||
case "h6":
|
||||
$markdown = "###### " . $value . PHP_EOL . PHP_EOL;
|
||||
break;
|
||||
case "em":
|
||||
case "i":
|
||||
case "strong":
|
||||
case "b":
|
||||
$markdown = $this->convert_emphasis($tag, $value);
|
||||
break;
|
||||
case "hr":
|
||||
$markdown = "- - - - - -" . PHP_EOL . PHP_EOL;
|
||||
break;
|
||||
case "br":
|
||||
$markdown = " " . PHP_EOL;
|
||||
break;
|
||||
case "blockquote":
|
||||
$markdown = $this->convert_blockquote($node);
|
||||
break;
|
||||
case "code":
|
||||
$markdown = $this->convert_code($node);
|
||||
break;
|
||||
case "ol":
|
||||
case "ul":
|
||||
$markdown = $value . PHP_EOL;
|
||||
break;
|
||||
case "li":
|
||||
$markdown = $this->convert_list($node);
|
||||
break;
|
||||
case "img":
|
||||
$markdown = $this->convert_image($node);
|
||||
break;
|
||||
case "a":
|
||||
$markdown = $this->convert_anchor($node);
|
||||
break;
|
||||
case "#text":
|
||||
$markdown = preg_replace('~\s+~', ' ', $value);
|
||||
$markdown = preg_replace('~^#~', '\\\\#', $markdown);
|
||||
break;
|
||||
case "#comment":
|
||||
$markdown = '';
|
||||
break;
|
||||
case "div":
|
||||
$markdown = ($this->options['strip_tags']) ? $value . PHP_EOL . PHP_EOL : html_entity_decode($node->C14N());
|
||||
break;
|
||||
default:
|
||||
// If strip_tags is false (the default), preserve tags that don't have Markdown equivalents,
|
||||
// such as <span> nodes on their own. C14N() canonicalizes the node to a string.
|
||||
// See: http://www.php.net/manual/en/domnode.c14n.php
|
||||
$markdown = ($this->options['strip_tags']) ? $value : html_entity_decode($node->C14N());
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert Header
|
||||
*
|
||||
* Converts h1 and h2 headers to Markdown-style headers in setext style,
|
||||
* matching the number of underscores with the length of the title.
|
||||
*
|
||||
* e.g. Header 1 Header Two
|
||||
* ======== ----------
|
||||
*
|
||||
* Returns atx headers instead if $this->options['header_style'] is "atx"
|
||||
*
|
||||
* e.g. # Header 1 ## Header Two
|
||||
*
|
||||
* @param string $level The header level, including the "h". e.g. h1
|
||||
* @param string $node The node to convert.
|
||||
* @return string The Markdown version of the header.
|
||||
*/
|
||||
private function convert_header($level, $node)
|
||||
{
|
||||
$content = $node->nodeValue;
|
||||
|
||||
if (!$this->is_child_of('blockquote', $node) && $this->options['header_style'] == "setext") {
|
||||
$length = (function_exists('mb_strlen')) ? mb_strlen($content, 'utf-8') : strlen($content);
|
||||
$underline = ($level == "h1") ? "=" : "-";
|
||||
$markdown = $content . PHP_EOL . str_repeat($underline, $length) . PHP_EOL . PHP_EOL; // setext style
|
||||
} else {
|
||||
$prefix = ($level == "h1") ? "# " : "## ";
|
||||
$markdown = $prefix . $content . PHP_EOL . PHP_EOL; // atx style
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Converts inline styles
|
||||
* This function is used to render strong and em tags
|
||||
*
|
||||
* eg <strong>bold text</strong> becomes **bold text** or __bold text__
|
||||
*
|
||||
* @param string $tag
|
||||
* @param string $value
|
||||
* @return string
|
||||
*/
|
||||
private function convert_emphasis($tag, $value)
|
||||
{
|
||||
if ($tag == 'i' || $tag == 'em') {
|
||||
$markdown = $this->options['italic_style'] . $value . $this->options['italic_style'];
|
||||
} else {
|
||||
$markdown = $this->options['bold_style'] . $value . $this->options['bold_style'];
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert Image
|
||||
*
|
||||
* Converts <img /> tags to Markdown.
|
||||
*
|
||||
* e.g. <img src="/path/img.jpg" alt="alt text" title="Title" />
|
||||
* becomes 
|
||||
*
|
||||
* @param $node
|
||||
* @return string
|
||||
*/
|
||||
private function convert_image($node)
|
||||
{
|
||||
$src = $node->getAttribute('src');
|
||||
$alt = $node->getAttribute('alt');
|
||||
$title = $node->getAttribute('title');
|
||||
|
||||
if ($title != "") {
|
||||
$markdown = ''; // No newlines added. <img> should be in a block-level element.
|
||||
} else {
|
||||
$markdown = '';
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert Anchor
|
||||
*
|
||||
* Converts <a> tags to Markdown.
|
||||
*
|
||||
* e.g. <a href="http://modernnerd.net" title="Title">Modern Nerd</a>
|
||||
* becomes [Modern Nerd](http://modernnerd.net "Title")
|
||||
*
|
||||
* @param $node
|
||||
* @return string
|
||||
*/
|
||||
private function convert_anchor($node)
|
||||
{
|
||||
$href = $node->getAttribute('href');
|
||||
$title = $node->getAttribute('title');
|
||||
$text = $node->nodeValue;
|
||||
|
||||
if ($title != "") {
|
||||
$markdown = '[' . $text . '](' . $href . ' "' . $title . '")';
|
||||
} else {
|
||||
$markdown = '[' . $text . '](' . $href . ')';
|
||||
}
|
||||
|
||||
if (! $href)
|
||||
$markdown = html_entity_decode($node->C14N());
|
||||
|
||||
// Append a space if the node after this one is also an anchor
|
||||
$next_node_name = $this->get_next_node_name($node);
|
||||
|
||||
if ($next_node_name == 'a')
|
||||
$markdown = $markdown . ' ';
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert List
|
||||
*
|
||||
* Converts <ul> and <ol> lists to Markdown.
|
||||
*
|
||||
* @param $node
|
||||
* @return string
|
||||
*/
|
||||
private function convert_list($node)
|
||||
{
|
||||
// If parent is an ol, use numbers, otherwise, use dashes
|
||||
$list_type = $node->parentNode->nodeName;
|
||||
$value = $node->nodeValue;
|
||||
|
||||
if ($list_type == "ul") {
|
||||
$markdown = "- " . trim($value) . PHP_EOL;
|
||||
} else {
|
||||
$number = $this->get_position($node);
|
||||
$markdown = $number . ". " . trim($value) . PHP_EOL;
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert Code
|
||||
*
|
||||
* Convert code tags by indenting blocks of code and wrapping single lines in backticks.
|
||||
*
|
||||
* @param DOMNode $node
|
||||
* @return string
|
||||
*/
|
||||
private function convert_code($node)
|
||||
{
|
||||
// Store the content of the code block in an array, one entry for each line
|
||||
|
||||
$markdown = '';
|
||||
|
||||
$code_content = html_entity_decode($node->C14N());
|
||||
$code_content = str_replace(array("<code>", "</code>"), "", $code_content);
|
||||
$code_content = str_replace(array("<pre>", "</pre>"), "", $code_content);
|
||||
|
||||
$lines = preg_split('/\r\n|\r|\n/', $code_content);
|
||||
$total = count($lines);
|
||||
|
||||
// If there's more than one line of code, prepend each line with four spaces and no backticks.
|
||||
if ($total > 1 || $node->nodeName === 'pre') {
|
||||
|
||||
// Remove the first and last line if they're empty
|
||||
$first_line = trim($lines[0]);
|
||||
$last_line = trim($lines[$total - 1]);
|
||||
$first_line = trim($first_line, "
"); //trim XML style carriage returns too
|
||||
$last_line = trim($last_line, "
");
|
||||
|
||||
if (empty($first_line))
|
||||
array_shift($lines);
|
||||
|
||||
if (empty($last_line))
|
||||
array_pop($lines);
|
||||
|
||||
$count = 1;
|
||||
foreach ($lines as $line) {
|
||||
$line = str_replace('
', '', $line);
|
||||
$markdown .= " " . $line;
|
||||
// Add newlines, except final line of the code
|
||||
if ($count != $total)
|
||||
$markdown .= PHP_EOL;
|
||||
$count++;
|
||||
}
|
||||
$markdown .= PHP_EOL;
|
||||
|
||||
} else { // There's only one line of code. It's a code span, not a block. Just wrap it with backticks.
|
||||
|
||||
$markdown .= "`" . $lines[0] . "`";
|
||||
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Convert blockquote
|
||||
*
|
||||
* Prepend blockquotes with > chars.
|
||||
*
|
||||
* @param $node
|
||||
* @return string
|
||||
*/
|
||||
private function convert_blockquote($node)
|
||||
{
|
||||
// Contents should have already been converted to Markdown by this point,
|
||||
// so we just need to add ">" symbols to each line.
|
||||
|
||||
$markdown = '';
|
||||
|
||||
$quote_content = trim($node->nodeValue);
|
||||
|
||||
$lines = preg_split('/\r\n|\r|\n/', $quote_content);
|
||||
|
||||
$total_lines = count($lines);
|
||||
|
||||
foreach ($lines as $i => $line) {
|
||||
$markdown .= "> " . $line . PHP_EOL;
|
||||
if ($i + 1 == $total_lines)
|
||||
$markdown .= PHP_EOL;
|
||||
}
|
||||
|
||||
return $markdown;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Get Position
|
||||
*
|
||||
* Returns the numbered position of a node inside its parent
|
||||
*
|
||||
* @param $node
|
||||
* @return int The numbered position of the node, starting at 1.
|
||||
*/
|
||||
private function get_position($node)
|
||||
{
|
||||
// Get all of the nodes inside the parent
|
||||
$list_nodes = $node->parentNode->childNodes;
|
||||
$total_nodes = $list_nodes->length;
|
||||
|
||||
$position = 1;
|
||||
|
||||
// Loop through all nodes and find the given $node
|
||||
for ($a = 0; $a < $total_nodes; $a++) {
|
||||
$current_node = $list_nodes->item($a);
|
||||
|
||||
if ($current_node->isSameNode($node))
|
||||
$position = $a + 1;
|
||||
}
|
||||
|
||||
return $position;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Get Next Node Name
|
||||
*
|
||||
* Return the name of the node immediately after the passed one.
|
||||
*
|
||||
* @param $node
|
||||
* @return string|null The node name (e.g. 'h1') or null.
|
||||
*/
|
||||
private function get_next_node_name($node)
|
||||
{
|
||||
$next_node_name = null;
|
||||
|
||||
$current_position = $this->get_position($node);
|
||||
$next_node = $node->parentNode->childNodes->item($current_position);
|
||||
|
||||
if ($next_node)
|
||||
$next_node_name = $next_node->nodeName;
|
||||
|
||||
return $next_node_name;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* To String
|
||||
*
|
||||
* Magic method to return Markdown output when HTML_To_Markdown instance is treated as a string.
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public function __toString()
|
||||
{
|
||||
return $this->output();
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Output
|
||||
*
|
||||
* Getter for the converted Markdown contents stored in $this->output
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public function output()
|
||||
{
|
||||
if (!$this->output) {
|
||||
return '';
|
||||
} else {
|
||||
return $this->output;
|
||||
}
|
||||
}
|
||||
}
|
||||
20
library/html-to-markdown/LICENSE
Normal file
20
library/html-to-markdown/LICENSE
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
The MIT License (MIT)
|
||||
|
||||
Copyright (c) 2013 Nick Cernis
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy of
|
||||
this software and associated documentation files (the "Software"), to deal in
|
||||
the Software without restriction, including without limitation the rights to
|
||||
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
|
||||
the Software, and to permit persons to whom the Software is furnished to do so,
|
||||
subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
|
||||
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
|
||||
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
|
||||
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
138
library/html-to-markdown/README.md
Normal file
138
library/html-to-markdown/README.md
Normal file
|
|
@ -0,0 +1,138 @@
|
|||
HTML To Markdown for PHP
|
||||
========================
|
||||
|
||||
A helper class that converts HTML to [Markdown](http://daringfireball.net/projects/markdown/) for your sanity and convenience.
|
||||
|
||||
[](https://travis-ci.org/nickcernis/html-to-markdown)
|
||||
|
||||
**Version**: 2.2.1
|
||||
**Requires**: PHP 5.3+
|
||||
**Author**: [@nickcernis](http://twitter.com/nickcernis)
|
||||
**License**: [MIT](http://www.opensource.org/licenses/mit-license.php)
|
||||
|
||||
### Why convert HTML to Markdown?
|
||||
|
||||
*"What alchemy is this?"* you mutter. *"I can see why you'd convert [Markdown to HTML](http://michelf.com/projects/php-markdown/),"* you continue, already labouring the question somewhat, *"but why go the other way?"*
|
||||
|
||||
Typically you would convert HTML to Markdown if:
|
||||
|
||||
1. You have an existing HTML document that needs to be edited by people with good taste.
|
||||
2. You want to store new content in HTML format but edit it as Markdown.
|
||||
3. You want to convert HTML email to plain text email.
|
||||
4. You know a guy who's been converting HTML to Markdown for years, and now he can speak Elvish. You'd quite like to be able to speak Elvish.
|
||||
5. You just really like Markdown.
|
||||
|
||||
### How to use it
|
||||
|
||||
Either include HTML_To_Markdown.php directly:
|
||||
|
||||
require_once( dirname( __FILE__) . '/HTML_To_Markdown.php' );
|
||||
|
||||
Or, require the library in your composer.json:
|
||||
|
||||
{
|
||||
"require": {
|
||||
"nickcernis/html-to-markdown": "dev-master"
|
||||
}
|
||||
}
|
||||
|
||||
Then `composer install` and add `require 'vendor/autoload.php';` to the top of your script.
|
||||
|
||||
Next, create a new HTML_To_Markdown instance, passing in your valid HTML code:
|
||||
|
||||
$html = "<h3>Quick, to the Batpoles!</h3>";
|
||||
$markdown = new HTML_To_Markdown($html);
|
||||
|
||||
The `$markdown` object now contains the Markdown version of your HTML. Use it like a string:
|
||||
|
||||
echo $markdown; // ==> ### Quick, to the Batpoles!
|
||||
|
||||
Or access the Markdown output directly:
|
||||
|
||||
$string = $markdown->output();
|
||||
|
||||
The included `demo` directory contains an HTML->Markdown conversion form to try out.
|
||||
|
||||
### Conversion options
|
||||
|
||||
By default, HTML To Markdown preserves HTML tags without Markdown equivalents, like `<span>` and `<div>`.
|
||||
|
||||
To strip HTML tags that don't have a Markdown equivalent while preserving the content inside them, set `strip_tags` to true, like this:
|
||||
|
||||
$html = '<span>Turnips!</span>';
|
||||
$markdown = new HTML_To_Markdown($html, array('strip_tags' => true)); // $markdown now contains "Turnips!"
|
||||
|
||||
Or more explicitly, like this:
|
||||
|
||||
$html = '<span>Turnips!</span>';
|
||||
$markdown = new HTML_To_Markdown();
|
||||
$markdown->set_option('strip_tags', true);
|
||||
$markdown->convert($html); // $markdown now contains "Turnips!"
|
||||
|
||||
Note that only the tags themselves are stripped, not the content they hold.
|
||||
|
||||
To strip tags and their content, pass a space-separated list of tags in `remove_nodes`, like this:
|
||||
|
||||
$html = '<span>Turnips!</span><div>Monkeys!</div>';
|
||||
$markdown = new HTML_To_Markdown($html, array('remove_nodes' => 'span div')); // $markdown now contains ""
|
||||
|
||||
### Style options
|
||||
|
||||
Bold and italic tags are converted using the asterisk syntax by default. Change this to the underlined syntax using the `bold_style` and `italic_style` options.
|
||||
|
||||
$html = '<em>Italic</em> and a <strong>bold</strong>';
|
||||
$markdown = new HTML_To_Markdown();
|
||||
$markdown->set_option('italic_style', '_');
|
||||
$markdown->set_option('bold_style', '__');
|
||||
$markdown->convert($html); // $markdown now contains "_Italic_ and a __bold__"
|
||||
|
||||
### Limitations
|
||||
|
||||
- Markdown Extra, MultiMarkdown and other variants aren't supported – just Markdown.
|
||||
|
||||
### Known issues
|
||||
|
||||
- Nested lists and lists containing multiple paragraphs aren't converted correctly.
|
||||
- Lists inside blockquotes aren't converted correctly.
|
||||
- Any reported [open issues here](https://github.com/nickcernis/html-to-markdown/issues?state=open).
|
||||
|
||||
[Report your issue or request a feature here.](https://github.com/nickcernis/html2markdown/issues/new) Issues with patches or failing tests are especially welcome.
|
||||
|
||||
### Style notes
|
||||
|
||||
- Setext (underlined) headers are the default for H1 and H2. If you prefer the ATX style for H1 and H2 (# Header 1 and ## Header 2), set `header_style` to 'atx' in the options array when you instantiate the object:
|
||||
|
||||
`$markdown = new HTML_To_Markdown( $html, array('header_style'=>'atx') );`
|
||||
|
||||
Headers of H3 priority and lower always use atx style.
|
||||
|
||||
- Links and images are referenced inline. Footnote references (where image src and anchor href attributes are listed in the footnotes) are not used.
|
||||
- Blockquotes aren't line wrapped – it makes the converted Markdown easier to edit.
|
||||
|
||||
### Dependencies
|
||||
|
||||
HTML To Markdown requires PHP's [xml](http://www.php.net/manual/en/xml.installation.php), [lib-xml](http://www.php.net/manual/en/libxml.installation.php), and [dom](http://www.php.net/manual/en/dom.installation.php) extensions, all of which are enabled by default on most distributions.
|
||||
|
||||
Errors such as "Fatal error: Class 'DOMDocument' not found" on distributions such as CentOS that disable PHP's xml extension can be resolved by installing php-xml.
|
||||
|
||||
### Architecture notes
|
||||
|
||||
HTML To Markdown is a single file that uses native DOM manipulation libraries (DOMDocument), not regex voodoo, to convert code.
|
||||
|
||||
### Contributors
|
||||
|
||||
Many thanks to all [contributors](https://github.com/nickcernis/html2markdown/graphs/contributors) so far. Further improvements and feature suggestions are very welcome.
|
||||
|
||||
### How it works
|
||||
|
||||
HTML To Markdown creates a DOMDocument from the supplied HTML, walks through the tree, and converts each node to a text node containing the equivalent markdown, starting from the most deeply nested node and working inwards towards the root node.
|
||||
|
||||
### To-do
|
||||
|
||||
- Support for nested lists and lists inside blockquotes.
|
||||
- Offer an option to preserve tags as HTML if they contain attributes that can't be represented with Markdown (e.g. `style`).
|
||||
|
||||
### Trying to convert Markdown to HTML?
|
||||
|
||||
Use [PHP Markdown](http://michelf.com/projects/php-markdown/) from Michel Fortin. No guarantees about the Elvish, though.
|
||||
|
||||
4
library/html-to-markdown/circle.yml
Normal file
4
library/html-to-markdown/circle.yml
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
test:
|
||||
override:
|
||||
- phpunit --no-configuration HTML_To_MarkdownTest ./tests/HTML_To_MarkdownTest.php
|
||||
|
||||
25
library/html-to-markdown/composer.json
Normal file
25
library/html-to-markdown/composer.json
Normal file
|
|
@ -0,0 +1,25 @@
|
|||
{
|
||||
"name": "nickcernis/html-to-markdown",
|
||||
"type": "library",
|
||||
"description": "An HTML-to-markdown conversion helper for PHP",
|
||||
"keywords": ["markdown", "html"],
|
||||
"homepage": "https://github.com/nickcernis/html-to-markdown",
|
||||
"license": "MIT",
|
||||
"authors": [
|
||||
{
|
||||
"name": "Nick Cernis",
|
||||
"email": "nick@cern.is",
|
||||
"homepage": "http://modernnerd.net"
|
||||
}
|
||||
],
|
||||
"autoload": {
|
||||
"classmap": [ "HTML_To_Markdown.php" ]
|
||||
},
|
||||
"require": {
|
||||
"php": ">=5.3"
|
||||
},
|
||||
"require-dev": {
|
||||
"php": ">=5.3.3",
|
||||
"phpunit/phpunit": "4.*"
|
||||
}
|
||||
}
|
||||
2942
library/markdown.php
2942
library/markdown.php
|
|
@ -1,2932 +1,24 @@
|
|||
<?php
|
||||
#
|
||||
# Markdown Extra - A text-to-HTML conversion tool for web writers
|
||||
#
|
||||
# PHP Markdown & Extra
|
||||
# Copyright (c) 2004-2012 Michel Fortin
|
||||
# <http://michelf.com/projects/php-markdown/>
|
||||
#
|
||||
# Original Markdown
|
||||
# Copyright (c) 2004-2006 John Gruber
|
||||
# <http://daringfireball.net/projects/markdown/>
|
||||
#
|
||||
//# Install PSR-0-compatible class autoloader
|
||||
//spl_autoload_register(function($class){
|
||||
// require preg_replace('{\\\\|_(?!.*\\\\)}', DIRECTORY_SEPARATOR, ltrim($class, '\\')).'.php';
|
||||
//});
|
||||
|
||||
|
||||
define( 'MARKDOWN_VERSION', "1.0.1o" ); # Sun 8 Jan 2012
|
||||
define( 'MARKDOWNEXTRA_VERSION', "1.2.5" ); # Sun 8 Jan 2012
|
||||
|
||||
|
||||
#
|
||||
# Global default settings:
|
||||
#
|
||||
|
||||
# Change to ">" for HTML output
|
||||
@define( 'MARKDOWN_EMPTY_ELEMENT_SUFFIX', " />");
|
||||
|
||||
# Define the width of a tab for code blocks.
|
||||
@define( 'MARKDOWN_TAB_WIDTH', 4 );
|
||||
|
||||
# Optional title attribute for footnote links and backlinks.
|
||||
@define( 'MARKDOWN_FN_LINK_TITLE', "" );
|
||||
@define( 'MARKDOWN_FN_BACKLINK_TITLE', "" );
|
||||
|
||||
# Optional class attribute for footnote links and backlinks.
|
||||
@define( 'MARKDOWN_FN_LINK_CLASS', "" );
|
||||
@define( 'MARKDOWN_FN_BACKLINK_CLASS', "" );
|
||||
|
||||
|
||||
#
|
||||
# WordPress settings:
|
||||
#
|
||||
|
||||
# Change to false to remove Markdown from posts and/or comments.
|
||||
@define( 'MARKDOWN_WP_POSTS', true );
|
||||
@define( 'MARKDOWN_WP_COMMENTS', true );
|
||||
|
||||
|
||||
|
||||
### Standard Function Interface ###
|
||||
|
||||
@define( 'MARKDOWN_PARSER_CLASS', 'MarkdownExtra_Parser' );
|
||||
require_once("library/php-markdown/Michelf/MarkdownExtra.inc.php");
|
||||
# Get Markdown class
|
||||
use \Michelf\MarkdownExtra;
|
||||
|
||||
function Markdown($text) {
|
||||
#
|
||||
# Initialize the parser and return the result of its transform method.
|
||||
#
|
||||
# Setup static parser variable.
|
||||
static $parser;
|
||||
if (!isset($parser)) {
|
||||
$parser_class = MARKDOWN_PARSER_CLASS;
|
||||
$parser = new $parser_class;
|
||||
}
|
||||
|
||||
# Transform text using parser.
|
||||
return $parser->transform($text);
|
||||
$a = get_app();
|
||||
|
||||
$stamp1 = microtime(true);
|
||||
|
||||
# Read file and pass content through the Markdown parser
|
||||
$html = MarkdownExtra::defaultTransform($text);
|
||||
|
||||
$a->save_timestamp($stamp1, "parser");
|
||||
|
||||
return $html;
|
||||
}
|
||||
|
||||
|
||||
### WordPress Plugin Interface ###
|
||||
|
||||
/*
|
||||
Plugin Name: Markdown Extra
|
||||
Plugin URI: http://michelf.com/projects/php-markdown/
|
||||
Description: <a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a>
|
||||
Version: 1.2.5
|
||||
Author: Michel Fortin
|
||||
Author URI: http://michelf.com/
|
||||
*/
|
||||
|
||||
if (isset($wp_version)) {
|
||||
# More details about how it works here:
|
||||
# <http://michelf.com/weblog/2005/wordpress-text-flow-vs-markdown/>
|
||||
|
||||
# Post content and excerpts
|
||||
# - Remove WordPress paragraph generator.
|
||||
# - Run Markdown on excerpt, then remove all tags.
|
||||
# - Add paragraph tag around the excerpt, but remove it for the excerpt rss.
|
||||
if (MARKDOWN_WP_POSTS) {
|
||||
remove_filter('the_content', 'wpautop');
|
||||
remove_filter('the_content_rss', 'wpautop');
|
||||
remove_filter('the_excerpt', 'wpautop');
|
||||
add_filter('the_content', 'mdwp_MarkdownPost', 6);
|
||||
add_filter('the_content_rss', 'mdwp_MarkdownPost', 6);
|
||||
add_filter('get_the_excerpt', 'mdwp_MarkdownPost', 6);
|
||||
add_filter('get_the_excerpt', 'trim', 7);
|
||||
add_filter('the_excerpt', 'mdwp_add_p');
|
||||
add_filter('the_excerpt_rss', 'mdwp_strip_p');
|
||||
|
||||
remove_filter('content_save_pre', 'balanceTags', 50);
|
||||
remove_filter('excerpt_save_pre', 'balanceTags', 50);
|
||||
add_filter('the_content', 'balanceTags', 50);
|
||||
add_filter('get_the_excerpt', 'balanceTags', 9);
|
||||
}
|
||||
|
||||
# Add a footnote id prefix to posts when inside a loop.
|
||||
function mdwp_MarkdownPost($text) {
|
||||
static $parser;
|
||||
if (!$parser) {
|
||||
$parser_class = MARKDOWN_PARSER_CLASS;
|
||||
$parser = new $parser_class;
|
||||
}
|
||||
if (is_single() || is_page() || is_feed()) {
|
||||
$parser->fn_id_prefix = "";
|
||||
} else {
|
||||
$parser->fn_id_prefix = get_the_ID() . ".";
|
||||
}
|
||||
return $parser->transform($text);
|
||||
}
|
||||
|
||||
# Comments
|
||||
# - Remove WordPress paragraph generator.
|
||||
# - Remove WordPress auto-link generator.
|
||||
# - Scramble important tags before passing them to the kses filter.
|
||||
# - Run Markdown on excerpt then remove paragraph tags.
|
||||
if (MARKDOWN_WP_COMMENTS) {
|
||||
remove_filter('comment_text', 'wpautop', 30);
|
||||
remove_filter('comment_text', 'make_clickable');
|
||||
add_filter('pre_comment_content', 'Markdown', 6);
|
||||
add_filter('pre_comment_content', 'mdwp_hide_tags', 8);
|
||||
add_filter('pre_comment_content', 'mdwp_show_tags', 12);
|
||||
add_filter('get_comment_text', 'Markdown', 6);
|
||||
add_filter('get_comment_excerpt', 'Markdown', 6);
|
||||
add_filter('get_comment_excerpt', 'mdwp_strip_p', 7);
|
||||
|
||||
global $mdwp_hidden_tags, $mdwp_placeholders;
|
||||
$mdwp_hidden_tags = explode(' ',
|
||||
'<p> </p> <pre> </pre> <ol> </ol> <ul> </ul> <li> </li>');
|
||||
$mdwp_placeholders = explode(' ', str_rot13(
|
||||
'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '.
|
||||
'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli'));
|
||||
}
|
||||
|
||||
function mdwp_add_p($text) {
|
||||
if (!preg_match('{^$|^<(p|ul|ol|dl|pre|blockquote)>}i', $text)) {
|
||||
$text = '<p>'.$text.'</p>';
|
||||
$text = preg_replace('{\n{2,}}', "</p>\n\n<p>", $text);
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
|
||||
function mdwp_strip_p($t) { return preg_replace('{</?p>}i', '', $t); }
|
||||
|
||||
function mdwp_hide_tags($text) {
|
||||
global $mdwp_hidden_tags, $mdwp_placeholders;
|
||||
return str_replace($mdwp_hidden_tags, $mdwp_placeholders, $text);
|
||||
}
|
||||
function mdwp_show_tags($text) {
|
||||
global $mdwp_hidden_tags, $mdwp_placeholders;
|
||||
return str_replace($mdwp_placeholders, $mdwp_hidden_tags, $text);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
### bBlog Plugin Info ###
|
||||
|
||||
function identify_modifier_markdown() {
|
||||
return array(
|
||||
'name' => 'markdown',
|
||||
'type' => 'modifier',
|
||||
'nicename' => 'PHP Markdown Extra',
|
||||
'description' => 'A text-to-HTML conversion tool for web writers',
|
||||
'authors' => 'Michel Fortin and John Gruber',
|
||||
'licence' => 'GPL',
|
||||
'version' => MARKDOWNEXTRA_VERSION,
|
||||
'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a>',
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
### Smarty Modifier Interface ###
|
||||
|
||||
function smarty_modifier_markdown($text) {
|
||||
return Markdown($text);
|
||||
}
|
||||
|
||||
|
||||
### Textile Compatibility Mode ###
|
||||
|
||||
# Rename this file to "classTextile.php" and it can replace Textile everywhere.
|
||||
|
||||
if (strcasecmp(substr(__FILE__, -16), "classTextile.php") == 0) {
|
||||
# Try to include PHP SmartyPants. Should be in the same directory.
|
||||
@include_once 'smartypants.php';
|
||||
# Fake Textile class. It calls Markdown instead.
|
||||
class Textile {
|
||||
function TextileThis($text, $lite='', $encode='') {
|
||||
if ($lite == '' && $encode == '') $text = Markdown($text);
|
||||
if (function_exists('SmartyPants')) $text = SmartyPants($text);
|
||||
return $text;
|
||||
}
|
||||
# Fake restricted version: restrictions are not supported for now.
|
||||
function TextileRestricted($text, $lite='', $noimage='') {
|
||||
return $this->TextileThis($text, $lite);
|
||||
}
|
||||
# Workaround to ensure compatibility with TextPattern 4.0.3.
|
||||
function blockLite($text) { return $text; }
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
#
|
||||
# Markdown Parser Class
|
||||
#
|
||||
|
||||
class Markdown_Parser {
|
||||
|
||||
# Regex to match balanced [brackets].
|
||||
# Needed to insert a maximum bracked depth while converting to PHP.
|
||||
var $nested_brackets_depth = 6;
|
||||
var $nested_brackets_re;
|
||||
|
||||
var $nested_url_parenthesis_depth = 4;
|
||||
var $nested_url_parenthesis_re;
|
||||
|
||||
# Table of hash values for escaped characters:
|
||||
var $escape_chars = '\`*_{}[]()>#+-.!';
|
||||
var $escape_chars_re;
|
||||
|
||||
# Change to ">" for HTML output.
|
||||
var $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX;
|
||||
var $tab_width = MARKDOWN_TAB_WIDTH;
|
||||
|
||||
# Change to `true` to disallow markup or entities.
|
||||
var $no_markup = false;
|
||||
var $no_entities = false;
|
||||
|
||||
# Predefined urls and titles for reference links and images.
|
||||
var $predef_urls = array();
|
||||
var $predef_titles = array();
|
||||
|
||||
|
||||
function Markdown_Parser() {
|
||||
#
|
||||
# Constructor function. Initialize appropriate member variables.
|
||||
#
|
||||
$this->_initDetab();
|
||||
$this->prepareItalicsAndBold();
|
||||
|
||||
$this->nested_brackets_re =
|
||||
str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
|
||||
str_repeat('\])*', $this->nested_brackets_depth);
|
||||
|
||||
$this->nested_url_parenthesis_re =
|
||||
str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
|
||||
str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
|
||||
|
||||
$this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
|
||||
|
||||
# Sort document, block, and span gamut in ascendent priority order.
|
||||
asort($this->document_gamut);
|
||||
asort($this->block_gamut);
|
||||
asort($this->span_gamut);
|
||||
}
|
||||
|
||||
|
||||
# Internal hashes used during transformation.
|
||||
var $urls = array();
|
||||
var $titles = array();
|
||||
var $html_hashes = array();
|
||||
|
||||
# Status flag to avoid invalid nesting.
|
||||
var $in_anchor = false;
|
||||
|
||||
|
||||
function setup() {
|
||||
#
|
||||
# Called before the transformation process starts to setup parser
|
||||
# states.
|
||||
#
|
||||
# Clear global hashes.
|
||||
$this->urls = $this->predef_urls;
|
||||
$this->titles = $this->predef_titles;
|
||||
$this->html_hashes = array();
|
||||
|
||||
$in_anchor = false;
|
||||
}
|
||||
|
||||
function teardown() {
|
||||
#
|
||||
# Called after the transformation process to clear any variable
|
||||
# which may be taking up memory unnecessarly.
|
||||
#
|
||||
$this->urls = array();
|
||||
$this->titles = array();
|
||||
$this->html_hashes = array();
|
||||
}
|
||||
|
||||
|
||||
function transform($text) {
|
||||
#
|
||||
# Main function. Performs some preprocessing on the input text
|
||||
# and pass it through the document gamut.
|
||||
#
|
||||
$this->setup();
|
||||
|
||||
# Remove UTF-8 BOM and marker character in input, if present.
|
||||
$text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text);
|
||||
|
||||
# Standardize line endings:
|
||||
# DOS to Unix and Mac to Unix
|
||||
$text = preg_replace('{\r\n?}', "\n", $text);
|
||||
|
||||
# Make sure $text ends with a couple of newlines:
|
||||
$text .= "\n\n";
|
||||
|
||||
# Convert all tabs to spaces.
|
||||
$text = $this->detab($text);
|
||||
|
||||
# Turn block-level HTML blocks into hash entries
|
||||
$text = $this->hashHTMLBlocks($text);
|
||||
|
||||
# Strip any lines consisting only of spaces and tabs.
|
||||
# This makes subsequent regexen easier to write, because we can
|
||||
# match consecutive blank lines with /\n+/ instead of something
|
||||
# contorted like /[ ]*\n+/ .
|
||||
$text = preg_replace('/^[ ]+$/m', '', $text);
|
||||
|
||||
# Run document gamut methods.
|
||||
foreach ($this->document_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
$this->teardown();
|
||||
|
||||
return $text . "\n";
|
||||
}
|
||||
|
||||
var $document_gamut = array(
|
||||
# Strip link definitions, store in hashes.
|
||||
"stripLinkDefinitions" => 20,
|
||||
|
||||
"runBasicBlockGamut" => 30,
|
||||
);
|
||||
|
||||
|
||||
function stripLinkDefinitions($text) {
|
||||
#
|
||||
# Strips link definitions from text, stores the URLs and titles in
|
||||
# hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: ^[id]: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
|
||||
[ ]*
|
||||
\n? # maybe *one* newline
|
||||
[ ]*
|
||||
(?:
|
||||
<(.+?)> # url = $2
|
||||
|
|
||||
(\S+?) # url = $3
|
||||
)
|
||||
[ ]*
|
||||
\n? # maybe one newline
|
||||
[ ]*
|
||||
(?:
|
||||
(?<=\s) # lookbehind for whitespace
|
||||
["(]
|
||||
(.*?) # title = $4
|
||||
[")]
|
||||
[ ]*
|
||||
)? # title is optional
|
||||
(?:\n+|\Z)
|
||||
}xm',
|
||||
array(&$this, '_stripLinkDefinitions_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
function _stripLinkDefinitions_callback($matches) {
|
||||
$link_id = strtolower($matches[1]);
|
||||
$url = $matches[2] == '' ? $matches[3] : $matches[2];
|
||||
$this->urls[$link_id] = $url;
|
||||
$this->titles[$link_id] =& $matches[4];
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
function hashHTMLBlocks($text) {
|
||||
if ($this->no_markup) return $text;
|
||||
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Hashify HTML blocks:
|
||||
# We only want to do this for block-level HTML tags, such as headers,
|
||||
# lists, and tables. That's because we still want to wrap <p>s around
|
||||
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
|
||||
# phrase emphasis, and spans. The list of tags we're looking for is
|
||||
# hard-coded:
|
||||
#
|
||||
# * List "a" is made of tags which can be both inline or block-level.
|
||||
# These will be treated block-level when the start tag is alone on
|
||||
# its line, otherwise they're not matched here and will be taken as
|
||||
# inline later.
|
||||
# * List "b" is made of tags which are always block-level;
|
||||
#
|
||||
$block_tags_a_re = 'ins|del';
|
||||
$block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
|
||||
'script|noscript|form|fieldset|iframe|math';
|
||||
|
||||
# Regular expression for the content of a block tag.
|
||||
$nested_tags_level = 4;
|
||||
$attr = '
|
||||
(?> # optional tag attributes
|
||||
\s # starts with whitespace
|
||||
(?>
|
||||
[^>"/]+ # text outside quotes
|
||||
|
|
||||
/+(?!>) # slash not followed by ">"
|
||||
|
|
||||
"[^"]*" # text inside double quotes (tolerate ">")
|
||||
|
|
||||
\'[^\']*\' # text inside single quotes (tolerate ">")
|
||||
)*
|
||||
)?
|
||||
';
|
||||
$content =
|
||||
str_repeat('
|
||||
(?>
|
||||
[^<]+ # content without tag
|
||||
|
|
||||
<\2 # nested opening tag
|
||||
'.$attr.' # attributes
|
||||
(?>
|
||||
/>
|
||||
|
|
||||
>', $nested_tags_level). # end of opening tag
|
||||
'.*?'. # last level nested tag content
|
||||
str_repeat('
|
||||
</\2\s*> # closing nested tag
|
||||
)
|
||||
|
|
||||
<(?!/\2\s*> # other tags with a different name
|
||||
)
|
||||
)*',
|
||||
$nested_tags_level);
|
||||
$content2 = str_replace('\2', '\3', $content);
|
||||
|
||||
# First, look for nested blocks, e.g.:
|
||||
# <div>
|
||||
# <div>
|
||||
# tags for inner block must be indented.
|
||||
# </div>
|
||||
# </div>
|
||||
#
|
||||
# The outermost tags must start at the left margin for this to match, and
|
||||
# the inner nested divs must be indented.
|
||||
# We need to do this before the next, more liberal match, because the next
|
||||
# match will start at the first `<div>` and stop at the first `</div>`.
|
||||
$text = preg_replace_callback('{(?>
|
||||
(?>
|
||||
(?<=\n\n) # Starting after a blank line
|
||||
| # or
|
||||
\A\n? # the beginning of the doc
|
||||
)
|
||||
( # save in $1
|
||||
|
||||
# Match from `\n<tag>` to `</tag>\n`, handling nested tags
|
||||
# in between.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<('.$block_tags_b_re.')# start tag = $2
|
||||
'.$attr.'> # attributes followed by > and \n
|
||||
'.$content.' # content, support nesting
|
||||
</\2> # the matching end tag
|
||||
[ ]* # trailing spaces/tabs
|
||||
(?=\n+|\Z) # followed by a newline or end of document
|
||||
|
||||
| # Special version for tags of group a.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<('.$block_tags_a_re.')# start tag = $3
|
||||
'.$attr.'>[ ]*\n # attributes followed by >
|
||||
'.$content2.' # content, support nesting
|
||||
</\3> # the matching end tag
|
||||
[ ]* # trailing spaces/tabs
|
||||
(?=\n+|\Z) # followed by a newline or end of document
|
||||
|
||||
| # Special case just for <hr />. It was easier to make a special
|
||||
# case than to make the other regex more complicated.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<(hr) # start tag = $2
|
||||
'.$attr.' # attributes
|
||||
/?> # the matching end tag
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
| # Special case for standalone HTML comments:
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?s:
|
||||
<!-- .*? -->
|
||||
)
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
| # PHP and ASP-style processor instructions (<? and <%)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?s:
|
||||
<([?%]) # $2
|
||||
.*?
|
||||
\2>
|
||||
)
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
)
|
||||
)}Sxmi',
|
||||
array(&$this, '_hashHTMLBlocks_callback'),
|
||||
$text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _hashHTMLBlocks_callback($matches) {
|
||||
$text = $matches[1];
|
||||
$key = $this->hashBlock($text);
|
||||
return "\n\n$key\n\n";
|
||||
}
|
||||
|
||||
|
||||
function hashPart($text, $boundary = 'X') {
|
||||
#
|
||||
# Called whenever a tag must be hashed when a function insert an atomic
|
||||
# element in the text stream. Passing $text to through this function gives
|
||||
# a unique text-token which will be reverted back when calling unhash.
|
||||
#
|
||||
# The $boundary argument specify what character should be used to surround
|
||||
# the token. By convension, "B" is used for block elements that needs not
|
||||
# to be wrapped into paragraph tags at the end, ":" is used for elements
|
||||
# that are word separators and "X" is used in the general case.
|
||||
#
|
||||
# Swap back any tag hash found in $text so we do not have to `unhash`
|
||||
# multiple times at the end.
|
||||
$text = $this->unhash($text);
|
||||
|
||||
# Then hash the block.
|
||||
static $i = 0;
|
||||
$key = "$boundary\x1A" . ++$i . $boundary;
|
||||
$this->html_hashes[$key] = $text;
|
||||
return $key; # String that will replace the tag.
|
||||
}
|
||||
|
||||
|
||||
function hashBlock($text) {
|
||||
#
|
||||
# Shortcut function for hashPart with block-level boundaries.
|
||||
#
|
||||
return $this->hashPart($text, 'B');
|
||||
}
|
||||
|
||||
|
||||
var $block_gamut = array(
|
||||
#
|
||||
# These are all the transformations that form block-level
|
||||
# tags like paragraphs, headers, and list items.
|
||||
#
|
||||
"doHeaders" => 10,
|
||||
"doHorizontalRules" => 20,
|
||||
|
||||
"doLists" => 40,
|
||||
"doCodeBlocks" => 50,
|
||||
"doBlockQuotes" => 60,
|
||||
);
|
||||
|
||||
function runBlockGamut($text) {
|
||||
#
|
||||
# Run block gamut tranformations.
|
||||
#
|
||||
# We need to escape raw HTML in Markdown source before doing anything
|
||||
# else. This need to be done for each block, and not only at the
|
||||
# begining in the Markdown function since hashed blocks can be part of
|
||||
# list items and could have been indented. Indented blocks would have
|
||||
# been seen as a code block in a previous pass of hashHTMLBlocks.
|
||||
$text = $this->hashHTMLBlocks($text);
|
||||
|
||||
return $this->runBasicBlockGamut($text);
|
||||
}
|
||||
|
||||
function runBasicBlockGamut($text) {
|
||||
#
|
||||
# Run block gamut tranformations, without hashing HTML blocks. This is
|
||||
# useful when HTML blocks are known to be already hashed, like in the first
|
||||
# whole-document pass.
|
||||
#
|
||||
foreach ($this->block_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
# Finally form paragraph and restore hashed blocks.
|
||||
$text = $this->formParagraphs($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
function doHorizontalRules($text) {
|
||||
# Do Horizontal Rules:
|
||||
return preg_replace(
|
||||
'{
|
||||
^[ ]{0,3} # Leading space
|
||||
([-*_]) # $1: First marker
|
||||
(?> # Repeated marker group
|
||||
[ ]{0,2} # Zero, one, or two spaces.
|
||||
\1 # Marker character
|
||||
){2,} # Group repeated at least twice
|
||||
[ ]* # Tailing spaces
|
||||
$ # End of line.
|
||||
}mx',
|
||||
"\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n",
|
||||
$text);
|
||||
}
|
||||
|
||||
|
||||
var $span_gamut = array(
|
||||
#
|
||||
# These are all the transformations that occur *within* block-level
|
||||
# tags like paragraphs, headers, and list items.
|
||||
#
|
||||
# Process character escapes, code spans, and inline HTML
|
||||
# in one shot.
|
||||
"parseSpan" => -30,
|
||||
|
||||
# Process anchor and image tags. Images must come first,
|
||||
# because ![foo][f] looks like an anchor.
|
||||
"doImages" => 10,
|
||||
"doAnchors" => 20,
|
||||
|
||||
# Make links out of things like `<http://example.com/>`
|
||||
# Must come after doAnchors, because you can use < and >
|
||||
# delimiters in inline links like [this](<url>).
|
||||
"doAutoLinks" => 30,
|
||||
"encodeAmpsAndAngles" => 40,
|
||||
|
||||
"doItalicsAndBold" => 50,
|
||||
"doHardBreaks" => 60,
|
||||
);
|
||||
|
||||
function runSpanGamut($text) {
|
||||
#
|
||||
# Run span gamut tranformations.
|
||||
#
|
||||
foreach ($this->span_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
function doHardBreaks($text) {
|
||||
# Do hard breaks:
|
||||
return preg_replace_callback('/ {2,}\n/',
|
||||
array(&$this, '_doHardBreaks_callback'), $text);
|
||||
}
|
||||
function _doHardBreaks_callback($matches) {
|
||||
return $this->hashPart("<br$this->empty_element_suffix\n");
|
||||
}
|
||||
|
||||
|
||||
function doAnchors($text) {
|
||||
#
|
||||
# Turn Markdown link shortcuts into XHTML <a> tags.
|
||||
#
|
||||
if ($this->in_anchor) return $text;
|
||||
$this->in_anchor = true;
|
||||
|
||||
#
|
||||
# First, handle reference-style links: [link text] [id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array(&$this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, inline-style links: [link text](url "optional title")
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(.+?)> # href = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # href = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # Title = $7
|
||||
\6 # matching quote
|
||||
[ \n]* # ignore any spaces/tabs between closing quote and )
|
||||
)? # title is optional
|
||||
\)
|
||||
)
|
||||
}xs',
|
||||
array(&$this, '_doAnchors_inline_callback'), $text);
|
||||
|
||||
#
|
||||
# Last, handle reference-style shortcuts: [link text]
|
||||
# These must come last in case you've also got [link text][1]
|
||||
# or [link text](/foo)
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
([^\[\]]+) # link text = $2; can\'t contain [ or ]
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array(&$this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
$this->in_anchor = false;
|
||||
return $text;
|
||||
}
|
||||
function _doAnchors_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $matches[2];
|
||||
$link_id =& $matches[3];
|
||||
|
||||
if ($link_id == "") {
|
||||
# for shortcut links like [this][] or [this].
|
||||
$link_id = $link_text;
|
||||
}
|
||||
|
||||
# lower-case and turn embedded newlines into spaces
|
||||
$link_id = strtolower($link_id);
|
||||
$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
|
||||
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->urls[$link_id];
|
||||
$url = $this->encodeAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if ( isset( $this->titles[$link_id] ) ) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
$result = $whole_match;
|
||||
}
|
||||
return $result;
|
||||
}
|
||||
function _doAnchors_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $this->runSpanGamut($matches[2]);
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
|
||||
$url = $this->encodeAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
function doImages($text) {
|
||||
#
|
||||
# Turn Markdown image shortcuts into <img> tags.
|
||||
#
|
||||
#
|
||||
# First, handle reference-style labeled images: ![alt text][id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
|
||||
)
|
||||
}xs',
|
||||
array(&$this, '_doImages_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, handle inline images: 
|
||||
# Don't forget: encode * and _
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
\s? # One optional whitespace character
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(\S*)> # src url = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # src url = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # title = $7
|
||||
\6 # matching quote
|
||||
[ \n]*
|
||||
)? # title is optional
|
||||
\)
|
||||
)
|
||||
}xs',
|
||||
array(&$this, '_doImages_inline_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doImages_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$link_id = strtolower($matches[3]);
|
||||
|
||||
if ($link_id == "") {
|
||||
$link_id = strtolower($alt_text); # for shortcut links like ![this][].
|
||||
}
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->encodeAttribute($this->urls[$link_id]);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($this->titles[$link_id])) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
$result .= $this->empty_element_suffix;
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
# If there's no such link ID, leave intact:
|
||||
$result = $whole_match;
|
||||
}
|
||||
|
||||
return $result;
|
||||
}
|
||||
function _doImages_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
$url = $this->encodeAttribute($url);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\""; # $title already quoted
|
||||
}
|
||||
$result .= $this->empty_element_suffix;
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
function doHeaders($text) {
|
||||
# Setext-style headers:
|
||||
# Header 1
|
||||
# ========
|
||||
#
|
||||
# Header 2
|
||||
# --------
|
||||
#
|
||||
$text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
|
||||
array(&$this, '_doHeaders_callback_setext'), $text);
|
||||
|
||||
# atx-style headers:
|
||||
# # Header 1
|
||||
# ## Header 2
|
||||
# ## Header 2 with closing hashes ##
|
||||
# ...
|
||||
# ###### Header 6
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
^(\#{1,6}) # $1 = string of #\'s
|
||||
[ ]*
|
||||
(.+?) # $2 = Header text
|
||||
[ ]*
|
||||
\#* # optional closing #\'s (not counted)
|
||||
\n+
|
||||
}xm',
|
||||
array(&$this, '_doHeaders_callback_atx'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doHeaders_callback_setext($matches) {
|
||||
# Terrible hack to check we haven't found an empty list item.
|
||||
if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
|
||||
return $matches[0];
|
||||
|
||||
$level = $matches[2]{0} == '=' ? 1 : 2;
|
||||
$block = "<h$level>".$this->runSpanGamut($matches[1])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
function _doHeaders_callback_atx($matches) {
|
||||
$level = strlen($matches[1]);
|
||||
$block = "<h$level>".$this->runSpanGamut($matches[2])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
function doLists($text) {
|
||||
#
|
||||
# Form HTML ordered (numbered) and unordered (bulleted) lists.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$marker_ul_re = '[*+-]';
|
||||
$marker_ol_re = '\d+[\.]';
|
||||
$marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
|
||||
|
||||
$markers_relist = array(
|
||||
$marker_ul_re => $marker_ol_re,
|
||||
$marker_ol_re => $marker_ul_re,
|
||||
);
|
||||
|
||||
foreach ($markers_relist as $marker_re => $other_marker_re) {
|
||||
# Re-usable pattern to match any entirel ul or ol list:
|
||||
$whole_list_re = '
|
||||
( # $1 = whole list
|
||||
( # $2
|
||||
([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
|
||||
('.$marker_re.') # $4 = first list item marker
|
||||
[ ]+
|
||||
)
|
||||
(?s:.+?)
|
||||
( # $5
|
||||
\z
|
||||
|
|
||||
\n{2,}
|
||||
(?=\S)
|
||||
(?! # Negative lookahead for another list item marker
|
||||
[ ]*
|
||||
'.$marker_re.'[ ]+
|
||||
)
|
||||
|
|
||||
(?= # Lookahead for another kind of list
|
||||
\n
|
||||
\3 # Must have the same indentation
|
||||
'.$other_marker_re.'[ ]+
|
||||
)
|
||||
)
|
||||
)
|
||||
'; // mx
|
||||
|
||||
# We use a different prefix before nested lists than top-level lists.
|
||||
# See extended comment in _ProcessListItems().
|
||||
|
||||
if ($this->list_level) {
|
||||
$text = preg_replace_callback('{
|
||||
^
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array(&$this, '_doLists_callback'), $text);
|
||||
}
|
||||
else {
|
||||
$text = preg_replace_callback('{
|
||||
(?:(?<=\n)\n|\A\n?) # Must eat the newline
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array(&$this, '_doLists_callback'), $text);
|
||||
}
|
||||
}
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doLists_callback($matches) {
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$marker_ul_re = '[*+-]';
|
||||
$marker_ol_re = '\d+[\.]';
|
||||
$marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
|
||||
|
||||
$list = $matches[1];
|
||||
$list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
|
||||
|
||||
$marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
|
||||
|
||||
$list .= "\n";
|
||||
$result = $this->processListItems($list, $marker_any_re);
|
||||
|
||||
$result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>");
|
||||
return "\n". $result ."\n\n";
|
||||
}
|
||||
|
||||
var $list_level = 0;
|
||||
|
||||
function processListItems($list_str, $marker_any_re) {
|
||||
#
|
||||
# Process the contents of a single ordered or unordered list, splitting it
|
||||
# into individual list items.
|
||||
#
|
||||
# The $this->list_level global keeps track of when we're inside a list.
|
||||
# Each time we enter a list, we increment it; when we leave a list,
|
||||
# we decrement. If it's zero, we're not in a list anymore.
|
||||
#
|
||||
# We do this because when we're not inside a list, we want to treat
|
||||
# something like this:
|
||||
#
|
||||
# I recommend upgrading to version
|
||||
# 8. Oops, now this line is treated
|
||||
# as a sub-list.
|
||||
#
|
||||
# As a single paragraph, despite the fact that the second line starts
|
||||
# with a digit-period-space sequence.
|
||||
#
|
||||
# Whereas when we're inside a list (or sub-list), that line will be
|
||||
# treated as the start of a sub-list. What a kludge, huh? This is
|
||||
# an aspect of Markdown's syntax that's hard to parse perfectly
|
||||
# without resorting to mind-reading. Perhaps the solution is to
|
||||
# change the syntax rules such that sub-lists must start with a
|
||||
# starting cardinal number; e.g. "1." or "a.".
|
||||
|
||||
$this->list_level++;
|
||||
|
||||
# trim trailing blank lines:
|
||||
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
|
||||
|
||||
$list_str = preg_replace_callback('{
|
||||
(\n)? # leading line = $1
|
||||
(^[ ]*) # leading whitespace = $2
|
||||
('.$marker_any_re.' # list marker and space = $3
|
||||
(?:[ ]+|(?=\n)) # space only required if item is not empty
|
||||
)
|
||||
((?s:.*?)) # list item text = $4
|
||||
(?:(\n+(?=\n))|\n) # tailing blank line = $5
|
||||
(?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n))))
|
||||
}xm',
|
||||
array(&$this, '_processListItems_callback'), $list_str);
|
||||
|
||||
$this->list_level--;
|
||||
return $list_str;
|
||||
}
|
||||
function _processListItems_callback($matches) {
|
||||
$item = $matches[4];
|
||||
$leading_line =& $matches[1];
|
||||
$leading_space =& $matches[2];
|
||||
$marker_space = $matches[3];
|
||||
$tailing_blank_line =& $matches[5];
|
||||
|
||||
if ($leading_line || $tailing_blank_line ||
|
||||
preg_match('/\n{2,}/', $item))
|
||||
{
|
||||
# Replace marker with the appropriate whitespace indentation
|
||||
$item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
|
||||
$item = $this->runBlockGamut($this->outdent($item)."\n");
|
||||
}
|
||||
else {
|
||||
# Recursion for sub-lists:
|
||||
$item = $this->doLists($this->outdent($item));
|
||||
$item = preg_replace('/\n+$/', '', $item);
|
||||
$item = $this->runSpanGamut($item);
|
||||
}
|
||||
|
||||
return "<li>" . $item . "</li>\n";
|
||||
}
|
||||
|
||||
|
||||
function doCodeBlocks($text) {
|
||||
#
|
||||
# Process Markdown `<pre><code>` blocks.
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
(?:\n\n|\A\n?)
|
||||
( # $1 = the code block -- one or more lines, starting with a space/tab
|
||||
(?>
|
||||
[ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces
|
||||
.*\n+
|
||||
)+
|
||||
)
|
||||
((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
|
||||
}xm',
|
||||
array(&$this, '_doCodeBlocks_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doCodeBlocks_callback($matches) {
|
||||
$codeblock = $matches[1];
|
||||
|
||||
$codeblock = $this->outdent($codeblock);
|
||||
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
|
||||
|
||||
# trim leading newlines and trailing newlines
|
||||
$codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
|
||||
|
||||
$codeblock = "<pre><code>$codeblock\n</code></pre>";
|
||||
return "\n\n".$this->hashBlock($codeblock)."\n\n";
|
||||
}
|
||||
|
||||
|
||||
function makeCodeSpan($code) {
|
||||
#
|
||||
# Create a code span markup for $code. Called from handleSpanToken.
|
||||
#
|
||||
$code = htmlspecialchars(trim($code), ENT_NOQUOTES);
|
||||
return $this->hashPart("<code>$code</code>");
|
||||
}
|
||||
|
||||
|
||||
var $em_relist = array(
|
||||
'' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
|
||||
'_' => '(?<=\S|^)(?<!_)_(?!_)',
|
||||
);
|
||||
var $strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
|
||||
'__' => '(?<=\S|^)(?<!_)__(?!_)',
|
||||
);
|
||||
var $em_strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
|
||||
'___' => '(?<=\S|^)(?<!_)___(?!_)',
|
||||
);
|
||||
var $em_strong_prepared_relist;
|
||||
|
||||
function prepareItalicsAndBold() {
|
||||
#
|
||||
# Prepare regular expressions for searching emphasis tokens in any
|
||||
# context.
|
||||
#
|
||||
foreach ($this->em_relist as $em => $em_re) {
|
||||
foreach ($this->strong_relist as $strong => $strong_re) {
|
||||
# Construct list of allowed token expressions.
|
||||
$token_relist = array();
|
||||
if (isset($this->em_strong_relist["$em$strong"])) {
|
||||
$token_relist[] = $this->em_strong_relist["$em$strong"];
|
||||
}
|
||||
$token_relist[] = $em_re;
|
||||
$token_relist[] = $strong_re;
|
||||
|
||||
# Construct master expression from list.
|
||||
$token_re = '{('. implode('|', $token_relist) .')}';
|
||||
$this->em_strong_prepared_relist["$em$strong"] = $token_re;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function doItalicsAndBold($text) {
|
||||
$token_stack = array('');
|
||||
$text_stack = array('');
|
||||
$em = '';
|
||||
$strong = '';
|
||||
$tree_char_em = false;
|
||||
|
||||
while (1) {
|
||||
#
|
||||
# Get prepared regular expression for seraching emphasis tokens
|
||||
# in current context.
|
||||
#
|
||||
$token_re = $this->em_strong_prepared_relist["$em$strong"];
|
||||
|
||||
#
|
||||
# Each loop iteration search for the next emphasis token.
|
||||
# Each token is then passed to handleSpanToken.
|
||||
#
|
||||
$parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
$text_stack[0] .= $parts[0];
|
||||
$token =& $parts[1];
|
||||
$text =& $parts[2];
|
||||
|
||||
if (empty($token)) {
|
||||
# Reached end of text span: empty stack without emitting.
|
||||
# any more emphasis.
|
||||
while ($token_stack[0]) {
|
||||
$text_stack[1] .= array_shift($token_stack);
|
||||
$text_stack[0] .= array_shift($text_stack);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
$token_len = strlen($token);
|
||||
if ($tree_char_em) {
|
||||
# Reached closing marker while inside a three-char emphasis.
|
||||
if ($token_len == 3) {
|
||||
# Three-char closing marker, close em and strong.
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<strong><em>$span</em></strong>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$em = '';
|
||||
$strong = '';
|
||||
} else {
|
||||
# Other closing marker: close one em or strong and
|
||||
# change current token state to match the other
|
||||
$token_stack[0] = str_repeat($token{0}, 3-$token_len);
|
||||
$tag = $token_len == 2 ? "strong" : "em";
|
||||
$span = $text_stack[0];
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<$tag>$span</$tag>";
|
||||
$text_stack[0] = $this->hashPart($span);
|
||||
$$tag = ''; # $$tag stands for $em or $strong
|
||||
}
|
||||
$tree_char_em = false;
|
||||
} else if ($token_len == 3) {
|
||||
if ($em) {
|
||||
# Reached closing marker for both em and strong.
|
||||
# Closing strong marker:
|
||||
for ($i = 0; $i < 2; ++$i) {
|
||||
$shifted_token = array_shift($token_stack);
|
||||
$tag = strlen($shifted_token) == 2 ? "strong" : "em";
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<$tag>$span</$tag>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$$tag = ''; # $$tag stands for $em or $strong
|
||||
}
|
||||
} else {
|
||||
# Reached opening three-char emphasis marker. Push on token
|
||||
# stack; will be handled by the special condition above.
|
||||
$em = $token{0};
|
||||
$strong = "$em$em";
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$tree_char_em = true;
|
||||
}
|
||||
} else if ($token_len == 2) {
|
||||
if ($strong) {
|
||||
# Unwind any dangling emphasis marker:
|
||||
if (strlen($token_stack[0]) == 1) {
|
||||
$text_stack[1] .= array_shift($token_stack);
|
||||
$text_stack[0] .= array_shift($text_stack);
|
||||
}
|
||||
# Closing strong marker:
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<strong>$span</strong>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$strong = '';
|
||||
} else {
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$strong = $token;
|
||||
}
|
||||
} else {
|
||||
# Here $token_len == 1
|
||||
if ($em) {
|
||||
if (strlen($token_stack[0]) == 1) {
|
||||
# Closing emphasis marker:
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<em>$span</em>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$em = '';
|
||||
} else {
|
||||
$text_stack[0] .= $token;
|
||||
}
|
||||
} else {
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$em = $token;
|
||||
}
|
||||
}
|
||||
}
|
||||
return $text_stack[0];
|
||||
}
|
||||
|
||||
|
||||
function doBlockQuotes($text) {
|
||||
$text = preg_replace_callback('/
|
||||
( # Wrap whole match in $1
|
||||
(?>
|
||||
^[ ]*>[ ]? # ">" at the start of a line
|
||||
.+\n # rest of the first line
|
||||
(.+\n)* # subsequent consecutive lines
|
||||
\n* # blanks
|
||||
)+
|
||||
)
|
||||
/xm',
|
||||
array(&$this, '_doBlockQuotes_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doBlockQuotes_callback($matches) {
|
||||
$bq = $matches[1];
|
||||
# trim one level of quoting - trim whitespace-only lines
|
||||
$bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
|
||||
$bq = $this->runBlockGamut($bq); # recurse
|
||||
|
||||
$bq = preg_replace('/^/m', " ", $bq);
|
||||
# These leading spaces cause problem with <pre> content,
|
||||
# so we need to fix that:
|
||||
$bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx',
|
||||
array(&$this, '_doBlockQuotes_callback2'), $bq);
|
||||
|
||||
return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
|
||||
}
|
||||
function _doBlockQuotes_callback2($matches) {
|
||||
$pre = $matches[1];
|
||||
$pre = preg_replace('/^ /m', '', $pre);
|
||||
return $pre;
|
||||
}
|
||||
|
||||
|
||||
function formParagraphs($text) {
|
||||
#
|
||||
# Params:
|
||||
# $text - string to process with html <p> tags
|
||||
#
|
||||
# Strip leading and trailing lines:
|
||||
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
|
||||
|
||||
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
|
||||
|
||||
#
|
||||
# Wrap <p> tags and unhashify HTML blocks
|
||||
#
|
||||
foreach ($grafs as $key => $value) {
|
||||
if (!preg_match('/^B\x1A[0-9]+B$/', $value)) {
|
||||
# Is a paragraph.
|
||||
$value = $this->runSpanGamut($value);
|
||||
$value = preg_replace('/^([ ]*)/', "<p>", $value);
|
||||
$value .= "</p>";
|
||||
$grafs[$key] = $this->unhash($value);
|
||||
}
|
||||
else {
|
||||
# Is a block.
|
||||
# Modify elements of @grafs in-place...
|
||||
$graf = $value;
|
||||
$block = $this->html_hashes[$graf];
|
||||
$graf = $block;
|
||||
// if (preg_match('{
|
||||
// \A
|
||||
// ( # $1 = <div> tag
|
||||
// <div \s+
|
||||
// [^>]*
|
||||
// \b
|
||||
// markdown\s*=\s* ([\'"]) # $2 = attr quote char
|
||||
// 1
|
||||
// \2
|
||||
// [^>]*
|
||||
// >
|
||||
// )
|
||||
// ( # $3 = contents
|
||||
// .*
|
||||
// )
|
||||
// (</div>) # $4 = closing tag
|
||||
// \z
|
||||
// }xs', $block, $matches))
|
||||
// {
|
||||
// list(, $div_open, , $div_content, $div_close) = $matches;
|
||||
//
|
||||
// # We can't call Markdown(), because that resets the hash;
|
||||
// # that initialization code should be pulled into its own sub, though.
|
||||
// $div_content = $this->hashHTMLBlocks($div_content);
|
||||
//
|
||||
// # Run document gamut methods on the content.
|
||||
// foreach ($this->document_gamut as $method => $priority) {
|
||||
// $div_content = $this->$method($div_content);
|
||||
// }
|
||||
//
|
||||
// $div_open = preg_replace(
|
||||
// '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open);
|
||||
//
|
||||
// $graf = $div_open . "\n" . $div_content . "\n" . $div_close;
|
||||
// }
|
||||
$grafs[$key] = $graf;
|
||||
}
|
||||
}
|
||||
|
||||
return implode("\n\n", $grafs);
|
||||
}
|
||||
|
||||
|
||||
function encodeAttribute($text) {
|
||||
#
|
||||
# Encode text for a double-quoted HTML attribute. This function
|
||||
# is *not* suitable for attributes enclosed in single quotes.
|
||||
#
|
||||
$text = $this->encodeAmpsAndAngles($text);
|
||||
$text = str_replace('"', '"', $text);
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
function encodeAmpsAndAngles($text) {
|
||||
#
|
||||
# Smart processing for ampersands and angle brackets that need to
|
||||
# be encoded. Valid character entities are left alone unless the
|
||||
# no-entities mode is set.
|
||||
#
|
||||
if ($this->no_entities) {
|
||||
$text = str_replace('&', '&', $text);
|
||||
} else {
|
||||
# Ampersand-encoding based entirely on Nat Irons's Amputator
|
||||
# MT plugin: <http://bumppo.net/projects/amputator/>
|
||||
$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
|
||||
'&', $text);;
|
||||
}
|
||||
# Encode remaining <'s
|
||||
$text = str_replace('<', '<', $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
function doAutoLinks($text) {
|
||||
$text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}i',
|
||||
array(&$this, '_doAutoLinks_url_callback'), $text);
|
||||
|
||||
# Email addresses: <address@domain.foo>
|
||||
$text = preg_replace_callback('{
|
||||
<
|
||||
(?:mailto:)?
|
||||
(
|
||||
(?:
|
||||
[-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+
|
||||
|
|
||||
".*?"
|
||||
)
|
||||
\@
|
||||
(?:
|
||||
[-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
|
||||
|
|
||||
\[[\d.a-fA-F:]+\] # IPv4 & IPv6
|
||||
)
|
||||
)
|
||||
>
|
||||
}xi',
|
||||
array(&$this, '_doAutoLinks_email_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doAutoLinks_url_callback($matches) {
|
||||
$url = $this->encodeAttribute($matches[1]);
|
||||
$link = "<a href=\"$url\">$url</a>";
|
||||
return $this->hashPart($link);
|
||||
}
|
||||
function _doAutoLinks_email_callback($matches) {
|
||||
$address = $matches[1];
|
||||
$link = $this->encodeEmailAddress($address);
|
||||
return $this->hashPart($link);
|
||||
}
|
||||
|
||||
|
||||
function encodeEmailAddress($addr) {
|
||||
#
|
||||
# Input: an email address, e.g. "foo@example.com"
|
||||
#
|
||||
# Output: the email address as a mailto link, with each character
|
||||
# of the address encoded as either a decimal or hex entity, in
|
||||
# the hopes of foiling most address harvesting spam bots. E.g.:
|
||||
#
|
||||
# <p><a href="mailto:foo
|
||||
# @example.co
|
||||
# m">foo@exampl
|
||||
# e.com</a></p>
|
||||
#
|
||||
# Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
|
||||
# With some optimizations by Milian Wolff.
|
||||
#
|
||||
$addr = "mailto:" . $addr;
|
||||
$chars = preg_split('/(?<!^)(?!$)/', $addr);
|
||||
$seed = (int)abs(crc32($addr) / strlen($addr)); # Deterministic seed.
|
||||
|
||||
foreach ($chars as $key => $char) {
|
||||
$ord = ord($char);
|
||||
# Ignore non-ascii chars.
|
||||
if ($ord < 128) {
|
||||
$r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
|
||||
# roughly 10% raw, 45% hex, 45% dec
|
||||
# '@' *must* be encoded. I insist.
|
||||
if ($r > 90 && $char != '@') /* do nothing */;
|
||||
else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
|
||||
else $chars[$key] = '&#'.$ord.';';
|
||||
}
|
||||
}
|
||||
|
||||
$addr = implode('', $chars);
|
||||
$text = implode('', array_slice($chars, 7)); # text without `mailto:`
|
||||
$addr = "<a href=\"$addr\">$text</a>";
|
||||
|
||||
return $addr;
|
||||
}
|
||||
|
||||
|
||||
function parseSpan($str) {
|
||||
#
|
||||
# Take the string $str and parse it into tokens, hashing embeded HTML,
|
||||
# escaped characters and handling code spans.
|
||||
#
|
||||
$output = '';
|
||||
|
||||
$span_re = '{
|
||||
(
|
||||
\\\\'.$this->escape_chars_re.'
|
||||
|
|
||||
(?<![`\\\\])
|
||||
`+ # code span marker
|
||||
'.( $this->no_markup ? '' : '
|
||||
|
|
||||
<!-- .*? --> # comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # processing instruction
|
||||
|
|
||||
<[/!$]?[-a-zA-Z0-9:_]+ # regular tags
|
||||
(?>
|
||||
\s
|
||||
(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
|
||||
)?
|
||||
>
|
||||
').'
|
||||
)
|
||||
}xs';
|
||||
|
||||
while (1) {
|
||||
#
|
||||
# Each loop iteration seach for either the next tag, the next
|
||||
# openning code span marker, or the next escaped character.
|
||||
# Each token is then passed to handleSpanToken.
|
||||
#
|
||||
$parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
# Create token from text preceding tag.
|
||||
if ($parts[0] != "") {
|
||||
$output .= $parts[0];
|
||||
}
|
||||
|
||||
# Check if we reach the end.
|
||||
if (isset($parts[1])) {
|
||||
$output .= $this->handleSpanToken($parts[1], $parts[2]);
|
||||
$str = $parts[2];
|
||||
}
|
||||
else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return $output;
|
||||
}
|
||||
|
||||
|
||||
function handleSpanToken($token, &$str) {
|
||||
#
|
||||
# Handle $token provided by parseSpan by determining its nature and
|
||||
# returning the corresponding value that should replace it.
|
||||
#
|
||||
switch ($token{0}) {
|
||||
case "\\":
|
||||
return $this->hashPart("&#". ord($token{1}). ";");
|
||||
case "`":
|
||||
# Search for end marker in remaining text.
|
||||
if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
|
||||
$str, $matches))
|
||||
{
|
||||
$str = $matches[2];
|
||||
$codespan = $this->makeCodeSpan($matches[1]);
|
||||
return $this->hashPart($codespan);
|
||||
}
|
||||
return $token; // return as text since no ending marker found.
|
||||
default:
|
||||
return $this->hashPart($token);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
function outdent($text) {
|
||||
#
|
||||
# Remove one level of line-leading tabs or spaces
|
||||
#
|
||||
return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
|
||||
}
|
||||
|
||||
|
||||
# String length function for detab. `_initDetab` will create a function to
|
||||
# hanlde UTF-8 if the default function does not exist.
|
||||
var $utf8_strlen = 'mb_strlen';
|
||||
|
||||
function detab($text) {
|
||||
#
|
||||
# Replace tabs with the appropriate amount of space.
|
||||
#
|
||||
# For each line we separate the line in blocks delemited by
|
||||
# tab characters. Then we reconstruct every line by adding the
|
||||
# appropriate number of space between each blocks.
|
||||
|
||||
$text = preg_replace_callback('/^.*\t.*$/m',
|
||||
array(&$this, '_detab_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _detab_callback($matches) {
|
||||
$line = $matches[0];
|
||||
$strlen = $this->utf8_strlen; # strlen function for UTF-8.
|
||||
|
||||
# Split in blocks.
|
||||
$blocks = explode("\t", $line);
|
||||
# Add each blocks to the line.
|
||||
$line = $blocks[0];
|
||||
unset($blocks[0]); # Do not add first block twice.
|
||||
foreach ($blocks as $block) {
|
||||
# Calculate amount of space, insert spaces, insert block.
|
||||
$amount = $this->tab_width -
|
||||
$strlen($line, 'UTF-8') % $this->tab_width;
|
||||
$line .= str_repeat(" ", $amount) . $block;
|
||||
}
|
||||
return $line;
|
||||
}
|
||||
function _initDetab() {
|
||||
#
|
||||
# Check for the availability of the function in the `utf8_strlen` property
|
||||
# (initially `mb_strlen`). If the function is not available, create a
|
||||
# function that will loosely count the number of UTF-8 characters with a
|
||||
# regular expression.
|
||||
#
|
||||
if (function_exists($this->utf8_strlen)) return;
|
||||
$this->utf8_strlen = create_function('$text', 'return preg_match_all(
|
||||
"/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
|
||||
$text, $m);');
|
||||
}
|
||||
|
||||
|
||||
function unhash($text) {
|
||||
#
|
||||
# Swap back in all the tags hashed by _HashHTMLBlocks.
|
||||
#
|
||||
return preg_replace_callback('/(.)\x1A[0-9]+\1/',
|
||||
array(&$this, '_unhash_callback'), $text);
|
||||
}
|
||||
function _unhash_callback($matches) {
|
||||
return $this->html_hashes[$matches[0]];
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
#
|
||||
# Markdown Extra Parser Class
|
||||
#
|
||||
|
||||
class MarkdownExtra_Parser extends Markdown_Parser {
|
||||
|
||||
# Prefix for footnote ids.
|
||||
var $fn_id_prefix = "";
|
||||
|
||||
# Optional title attribute for footnote links and backlinks.
|
||||
var $fn_link_title = MARKDOWN_FN_LINK_TITLE;
|
||||
var $fn_backlink_title = MARKDOWN_FN_BACKLINK_TITLE;
|
||||
|
||||
# Optional class attribute for footnote links and backlinks.
|
||||
var $fn_link_class = MARKDOWN_FN_LINK_CLASS;
|
||||
var $fn_backlink_class = MARKDOWN_FN_BACKLINK_CLASS;
|
||||
|
||||
# Predefined abbreviations.
|
||||
var $predef_abbr = array();
|
||||
|
||||
|
||||
function MarkdownExtra_Parser() {
|
||||
#
|
||||
# Constructor function. Initialize the parser object.
|
||||
#
|
||||
# Add extra escapable characters before parent constructor
|
||||
# initialize the table.
|
||||
$this->escape_chars .= ':|';
|
||||
|
||||
# Insert extra document, block, and span transformations.
|
||||
# Parent constructor will do the sorting.
|
||||
$this->document_gamut += array(
|
||||
"doFencedCodeBlocks" => 5,
|
||||
"stripFootnotes" => 15,
|
||||
"stripAbbreviations" => 25,
|
||||
"appendFootnotes" => 50,
|
||||
);
|
||||
$this->block_gamut += array(
|
||||
"doFencedCodeBlocks" => 5,
|
||||
"doTables" => 15,
|
||||
"doDefLists" => 45,
|
||||
);
|
||||
$this->span_gamut += array(
|
||||
"doFootnotes" => 5,
|
||||
"doAbbreviations" => 70,
|
||||
);
|
||||
|
||||
parent::Markdown_Parser();
|
||||
}
|
||||
|
||||
|
||||
# Extra variables used during extra transformations.
|
||||
var $footnotes = array();
|
||||
var $footnotes_ordered = array();
|
||||
var $abbr_desciptions = array();
|
||||
var $abbr_word_re = '';
|
||||
|
||||
# Give the current footnote number.
|
||||
var $footnote_counter = 1;
|
||||
|
||||
|
||||
function setup() {
|
||||
#
|
||||
# Setting up Extra-specific variables.
|
||||
#
|
||||
parent::setup();
|
||||
|
||||
$this->footnotes = array();
|
||||
$this->footnotes_ordered = array();
|
||||
$this->abbr_desciptions = array();
|
||||
$this->abbr_word_re = '';
|
||||
$this->footnote_counter = 1;
|
||||
|
||||
foreach ($this->predef_abbr as $abbr_word => $abbr_desc) {
|
||||
if ($this->abbr_word_re)
|
||||
$this->abbr_word_re .= '|';
|
||||
$this->abbr_word_re .= preg_quote($abbr_word);
|
||||
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
|
||||
}
|
||||
}
|
||||
|
||||
function teardown() {
|
||||
#
|
||||
# Clearing Extra-specific variables.
|
||||
#
|
||||
$this->footnotes = array();
|
||||
$this->footnotes_ordered = array();
|
||||
$this->abbr_desciptions = array();
|
||||
$this->abbr_word_re = '';
|
||||
|
||||
parent::teardown();
|
||||
}
|
||||
|
||||
|
||||
### HTML Block Parser ###
|
||||
|
||||
# Tags that are always treated as block tags:
|
||||
var $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend';
|
||||
|
||||
# Tags treated as block tags only if the opening tag is alone on it's line:
|
||||
var $context_block_tags_re = 'script|noscript|math|ins|del';
|
||||
|
||||
# Tags where markdown="1" default to span mode:
|
||||
var $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
|
||||
|
||||
# Tags which must not have their contents modified, no matter where
|
||||
# they appear:
|
||||
var $clean_tags_re = 'script|math';
|
||||
|
||||
# Tags that do not need to be closed.
|
||||
var $auto_close_tags_re = 'hr|img';
|
||||
|
||||
|
||||
function hashHTMLBlocks($text) {
|
||||
#
|
||||
# Hashify HTML Blocks and "clean tags".
|
||||
#
|
||||
# We only want to do this for block-level HTML tags, such as headers,
|
||||
# lists, and tables. That's because we still want to wrap <p>s around
|
||||
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
|
||||
# phrase emphasis, and spans. The list of tags we're looking for is
|
||||
# hard-coded.
|
||||
#
|
||||
# This works by calling _HashHTMLBlocks_InMarkdown, which then calls
|
||||
# _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
|
||||
# attribute is found whitin a tag, _HashHTMLBlocks_InHTML calls back
|
||||
# _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
|
||||
# These two functions are calling each other. It's recursive!
|
||||
#
|
||||
#
|
||||
# Call the HTML-in-Markdown hasher.
|
||||
#
|
||||
list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
|
||||
$enclosing_tag_re = '', $span = false)
|
||||
{
|
||||
#
|
||||
# Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
|
||||
#
|
||||
# * $indent is the number of space to be ignored when checking for code
|
||||
# blocks. This is important because if we don't take the indent into
|
||||
# account, something like this (which looks right) won't work as expected:
|
||||
#
|
||||
# <div>
|
||||
# <div markdown="1">
|
||||
# Hello World. <-- Is this a Markdown code block or text?
|
||||
# </div> <-- Is this a Markdown code block or a real tag?
|
||||
# <div>
|
||||
#
|
||||
# If you don't like this, just don't indent the tag on which
|
||||
# you apply the markdown="1" attribute.
|
||||
#
|
||||
# * If $enclosing_tag_re is not empty, stops at the first unmatched closing
|
||||
# tag with that name. Nested tags supported.
|
||||
#
|
||||
# * If $span is true, text inside must treated as span. So any double
|
||||
# newline will be replaced by a single newline so that it does not create
|
||||
# paragraphs.
|
||||
#
|
||||
# Returns an array of that form: ( processed text , remaining text )
|
||||
#
|
||||
if ($text === '') return array('', '');
|
||||
|
||||
# Regex to check for the presense of newlines around a block tag.
|
||||
$newline_before_re = '/(?:^\n?|\n\n)*$/';
|
||||
$newline_after_re =
|
||||
'{
|
||||
^ # Start of text following the tag.
|
||||
(?>[ ]*<!--.*?-->)? # Optional comment.
|
||||
[ ]*\n # Must be followed by newline.
|
||||
}xs';
|
||||
|
||||
# Regex to match any tag.
|
||||
$block_tag_re =
|
||||
'{
|
||||
( # $2: Capture hole tag.
|
||||
</? # Any opening or closing tag.
|
||||
(?> # Tag name.
|
||||
'.$this->block_tags_re.' |
|
||||
'.$this->context_block_tags_re.' |
|
||||
'.$this->clean_tags_re.' |
|
||||
(?!\s)'.$enclosing_tag_re.'
|
||||
)
|
||||
(?:
|
||||
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
|
||||
(?>
|
||||
".*?" | # Double quotes (can contain `>`)
|
||||
\'.*?\' | # Single quotes (can contain `>`)
|
||||
.+? # Anything but quotes and `>`.
|
||||
)*?
|
||||
)?
|
||||
> # End of tag.
|
||||
|
|
||||
<!-- .*? --> # HTML Comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # Processing instruction
|
||||
|
|
||||
<!\[CDATA\[.*?\]\]> # CData Block
|
||||
|
|
||||
# Code span marker
|
||||
`+
|
||||
'. ( !$span ? ' # If not in span.
|
||||
|
|
||||
# Indented code block
|
||||
(?: ^[ ]*\n | ^ | \n[ ]*\n )
|
||||
[ ]{'.($indent+4).'}[^\n]* \n
|
||||
(?>
|
||||
(?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
|
||||
)*
|
||||
|
|
||||
# Fenced code block marker
|
||||
(?> ^ | \n )
|
||||
[ ]{0,'.($indent).'}~~~+[ ]*\n
|
||||
' : '' ). ' # End (if not is span).
|
||||
)
|
||||
}xs';
|
||||
|
||||
|
||||
$depth = 0; # Current depth inside the tag tree.
|
||||
$parsed = ""; # Parsed text that will be returned.
|
||||
|
||||
#
|
||||
# Loop through every tag until we find the closing tag of the parent
|
||||
# or loop until reaching the end of text if no parent tag specified.
|
||||
#
|
||||
do {
|
||||
#
|
||||
# Split the text using the first $tag_match pattern found.
|
||||
# Text before pattern will be first in the array, text after
|
||||
# pattern will be at the end, and between will be any catches made
|
||||
# by the pattern.
|
||||
#
|
||||
$parts = preg_split($block_tag_re, $text, 2,
|
||||
PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
# If in Markdown span mode, add a empty-string span-level hash
|
||||
# after each newline to prevent triggering any block element.
|
||||
if ($span) {
|
||||
$void = $this->hashPart("", ':');
|
||||
$newline = "$void\n";
|
||||
$parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
|
||||
}
|
||||
|
||||
$parsed .= $parts[0]; # Text before current tag.
|
||||
|
||||
# If end of $text has been reached. Stop loop.
|
||||
if (count($parts) < 3) {
|
||||
$text = "";
|
||||
break;
|
||||
}
|
||||
|
||||
$tag = $parts[1]; # Tag to handle.
|
||||
$text = $parts[2]; # Remaining text after current tag.
|
||||
$tag_re = preg_quote($tag); # For use in a regular expression.
|
||||
|
||||
#
|
||||
# Check for: Code span marker
|
||||
#
|
||||
if ($tag{0} == "`") {
|
||||
# Find corresponding end marker.
|
||||
$tag_re = preg_quote($tag);
|
||||
if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
|
||||
$text, $matches))
|
||||
{
|
||||
# End marker found: pass text unchanged until marker.
|
||||
$parsed .= $tag . $matches[0];
|
||||
$text = substr($text, strlen($matches[0]));
|
||||
}
|
||||
else {
|
||||
# Unmatched marker: just skip it.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
}
|
||||
#
|
||||
# Check for: Fenced code block marker.
|
||||
#
|
||||
else if (preg_match('{^\n?[ ]{0,'.($indent+3).'}~}', $tag)) {
|
||||
# Fenced code block marker: find matching end marker.
|
||||
$tag_re = preg_quote(trim($tag));
|
||||
if (preg_match('{^(?>.*\n)+?[ ]{0,'.($indent).'}'.$tag_re.'[ ]*\n}', $text,
|
||||
$matches))
|
||||
{
|
||||
# End marker found: pass text unchanged until marker.
|
||||
$parsed .= $tag . $matches[0];
|
||||
$text = substr($text, strlen($matches[0]));
|
||||
}
|
||||
else {
|
||||
# No end marker: just skip it.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
}
|
||||
#
|
||||
# Check for: Indented code block.
|
||||
#
|
||||
else if ($tag{0} == "\n" || $tag{0} == " ") {
|
||||
# Indented code block: pass it unchanged, will be handled
|
||||
# later.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
#
|
||||
# Check for: Opening Block level tag or
|
||||
# Opening Context Block tag (like ins and del)
|
||||
# used as a block tag (tag is alone on it's line).
|
||||
#
|
||||
else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) ||
|
||||
( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
|
||||
preg_match($newline_before_re, $parsed) &&
|
||||
preg_match($newline_after_re, $text) )
|
||||
)
|
||||
{
|
||||
# Need to parse tag and following text using the HTML parser.
|
||||
list($block_text, $text) =
|
||||
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
|
||||
|
||||
# Make sure it stays outside of any paragraph by adding newlines.
|
||||
$parsed .= "\n\n$block_text\n\n";
|
||||
}
|
||||
#
|
||||
# Check for: Clean tag (like script, math)
|
||||
# HTML Comments, processing instructions.
|
||||
#
|
||||
else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
|
||||
$tag{1} == '!' || $tag{1} == '?')
|
||||
{
|
||||
# Need to parse tag and following text using the HTML parser.
|
||||
# (don't check for markdown attribute)
|
||||
list($block_text, $text) =
|
||||
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
|
||||
|
||||
$parsed .= $block_text;
|
||||
}
|
||||
#
|
||||
# Check for: Tag with same name as enclosing tag.
|
||||
#
|
||||
else if ($enclosing_tag_re !== '' &&
|
||||
# Same name as enclosing tag.
|
||||
preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
|
||||
{
|
||||
#
|
||||
# Increase/decrease nested tag count.
|
||||
#
|
||||
if ($tag{1} == '/') $depth--;
|
||||
else if ($tag{strlen($tag)-2} != '/') $depth++;
|
||||
|
||||
if ($depth < 0) {
|
||||
#
|
||||
# Going out of parent element. Clean up and break so we
|
||||
# return to the calling function.
|
||||
#
|
||||
$text = $tag . $text;
|
||||
break;
|
||||
}
|
||||
|
||||
$parsed .= $tag;
|
||||
}
|
||||
else {
|
||||
$parsed .= $tag;
|
||||
}
|
||||
} while ($depth >= 0);
|
||||
|
||||
return array($parsed, $text);
|
||||
}
|
||||
function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
|
||||
#
|
||||
# Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
|
||||
#
|
||||
# * Calls $hash_method to convert any blocks.
|
||||
# * Stops when the first opening tag closes.
|
||||
# * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
|
||||
# (it is not inside clean tags)
|
||||
#
|
||||
# Returns an array of that form: ( processed text , remaining text )
|
||||
#
|
||||
if ($text === '') return array('', '');
|
||||
|
||||
# Regex to match `markdown` attribute inside of a tag.
|
||||
$markdown_attr_re = '
|
||||
{
|
||||
\s* # Eat whitespace before the `markdown` attribute
|
||||
markdown
|
||||
\s*=\s*
|
||||
(?>
|
||||
(["\']) # $1: quote delimiter
|
||||
(.*?) # $2: attribute value
|
||||
\1 # matching delimiter
|
||||
|
|
||||
([^\s>]*) # $3: unquoted attribute value
|
||||
)
|
||||
() # $4: make $3 always defined (avoid warnings)
|
||||
}xs';
|
||||
|
||||
# Regex to match any tag.
|
||||
$tag_re = '{
|
||||
( # $2: Capture hole tag.
|
||||
</? # Any opening or closing tag.
|
||||
[\w:$]+ # Tag name.
|
||||
(?:
|
||||
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
|
||||
(?>
|
||||
".*?" | # Double quotes (can contain `>`)
|
||||
\'.*?\' | # Single quotes (can contain `>`)
|
||||
.+? # Anything but quotes and `>`.
|
||||
)*?
|
||||
)?
|
||||
> # End of tag.
|
||||
|
|
||||
<!-- .*? --> # HTML Comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # Processing instruction
|
||||
|
|
||||
<!\[CDATA\[.*?\]\]> # CData Block
|
||||
)
|
||||
}xs';
|
||||
|
||||
$original_text = $text; # Save original text in case of faliure.
|
||||
|
||||
$depth = 0; # Current depth inside the tag tree.
|
||||
$block_text = ""; # Temporary text holder for current text.
|
||||
$parsed = ""; # Parsed text that will be returned.
|
||||
|
||||
#
|
||||
# Get the name of the starting tag.
|
||||
# (This pattern makes $base_tag_name_re safe without quoting.)
|
||||
#
|
||||
if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
|
||||
$base_tag_name_re = $matches[1];
|
||||
|
||||
#
|
||||
# Loop through every tag until we find the corresponding closing tag.
|
||||
#
|
||||
do {
|
||||
#
|
||||
# Split the text using the first $tag_match pattern found.
|
||||
# Text before pattern will be first in the array, text after
|
||||
# pattern will be at the end, and between will be any catches made
|
||||
# by the pattern.
|
||||
#
|
||||
$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
if (count($parts) < 3) {
|
||||
#
|
||||
# End of $text reached with unbalenced tag(s).
|
||||
# In that case, we return original text unchanged and pass the
|
||||
# first character as filtered to prevent an infinite loop in the
|
||||
# parent function.
|
||||
#
|
||||
return array($original_text{0}, substr($original_text, 1));
|
||||
}
|
||||
|
||||
$block_text .= $parts[0]; # Text before current tag.
|
||||
$tag = $parts[1]; # Tag to handle.
|
||||
$text = $parts[2]; # Remaining text after current tag.
|
||||
|
||||
#
|
||||
# Check for: Auto-close tag (like <hr/>)
|
||||
# Comments and Processing Instructions.
|
||||
#
|
||||
if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
|
||||
$tag{1} == '!' || $tag{1} == '?')
|
||||
{
|
||||
# Just add the tag to the block as if it was text.
|
||||
$block_text .= $tag;
|
||||
}
|
||||
else {
|
||||
#
|
||||
# Increase/decrease nested tag count. Only do so if
|
||||
# the tag's name match base tag's.
|
||||
#
|
||||
if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) {
|
||||
if ($tag{1} == '/') $depth--;
|
||||
else if ($tag{strlen($tag)-2} != '/') $depth++;
|
||||
}
|
||||
|
||||
#
|
||||
# Check for `markdown="1"` attribute and handle it.
|
||||
#
|
||||
if ($md_attr &&
|
||||
preg_match($markdown_attr_re, $tag, $attr_m) &&
|
||||
preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
|
||||
{
|
||||
# Remove `markdown` attribute from opening tag.
|
||||
$tag = preg_replace($markdown_attr_re, '', $tag);
|
||||
|
||||
# Check if text inside this tag must be parsed in span mode.
|
||||
$this->mode = $attr_m[2] . $attr_m[3];
|
||||
$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
|
||||
preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
|
||||
|
||||
# Calculate indent before tag.
|
||||
if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
|
||||
$strlen = $this->utf8_strlen;
|
||||
$indent = $strlen($matches[1], 'UTF-8');
|
||||
} else {
|
||||
$indent = 0;
|
||||
}
|
||||
|
||||
# End preceding block with this tag.
|
||||
$block_text .= $tag;
|
||||
$parsed .= $this->$hash_method($block_text);
|
||||
|
||||
# Get enclosing tag name for the ParseMarkdown function.
|
||||
# (This pattern makes $tag_name_re safe without quoting.)
|
||||
preg_match('/^<([\w:$]*)\b/', $tag, $matches);
|
||||
$tag_name_re = $matches[1];
|
||||
|
||||
# Parse the content using the HTML-in-Markdown parser.
|
||||
list ($block_text, $text)
|
||||
= $this->_hashHTMLBlocks_inMarkdown($text, $indent,
|
||||
$tag_name_re, $span_mode);
|
||||
|
||||
# Outdent markdown text.
|
||||
if ($indent > 0) {
|
||||
$block_text = preg_replace("/^[ ]{1,$indent}/m", "",
|
||||
$block_text);
|
||||
}
|
||||
|
||||
# Append tag content to parsed text.
|
||||
if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
|
||||
else $parsed .= "$block_text";
|
||||
|
||||
# Start over a new block.
|
||||
$block_text = "";
|
||||
}
|
||||
else $block_text .= $tag;
|
||||
}
|
||||
|
||||
} while ($depth > 0);
|
||||
|
||||
#
|
||||
# Hash last block text that wasn't processed inside the loop.
|
||||
#
|
||||
$parsed .= $this->$hash_method($block_text);
|
||||
|
||||
return array($parsed, $text);
|
||||
}
|
||||
|
||||
|
||||
function hashClean($text) {
|
||||
#
|
||||
# Called whenever a tag must be hashed when a function insert a "clean" tag
|
||||
# in $text, it pass through this function and is automaticaly escaped,
|
||||
# blocking invalid nested overlap.
|
||||
#
|
||||
return $this->hashPart($text, 'C');
|
||||
}
|
||||
|
||||
|
||||
function doHeaders($text) {
|
||||
#
|
||||
# Redefined to add id attribute support.
|
||||
#
|
||||
# Setext-style headers:
|
||||
# Header 1 {#header1}
|
||||
# ========
|
||||
#
|
||||
# Header 2 {#header2}
|
||||
# --------
|
||||
#
|
||||
$text = preg_replace_callback(
|
||||
'{
|
||||
(^.+?) # $1: Header text
|
||||
(?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? # $2: Id attribute
|
||||
[ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer
|
||||
}mx',
|
||||
array(&$this, '_doHeaders_callback_setext'), $text);
|
||||
|
||||
# atx-style headers:
|
||||
# # Header 1 {#header1}
|
||||
# ## Header 2 {#header2}
|
||||
# ## Header 2 with closing hashes ## {#header3}
|
||||
# ...
|
||||
# ###### Header 6 {#header2}
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
^(\#{1,6}) # $1 = string of #\'s
|
||||
[ ]*
|
||||
(.+?) # $2 = Header text
|
||||
[ ]*
|
||||
\#* # optional closing #\'s (not counted)
|
||||
(?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? # id attribute
|
||||
[ ]*
|
||||
\n+
|
||||
}xm',
|
||||
array(&$this, '_doHeaders_callback_atx'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doHeaders_attr($attr) {
|
||||
if (empty($attr)) return "";
|
||||
return " id=\"$attr\"";
|
||||
}
|
||||
function _doHeaders_callback_setext($matches) {
|
||||
if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
|
||||
return $matches[0];
|
||||
$level = $matches[3]{0} == '=' ? 1 : 2;
|
||||
$attr = $this->_doHeaders_attr($id =& $matches[2]);
|
||||
$block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
function _doHeaders_callback_atx($matches) {
|
||||
$level = strlen($matches[1]);
|
||||
$attr = $this->_doHeaders_attr($id =& $matches[3]);
|
||||
$block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
function doTables($text) {
|
||||
#
|
||||
# Form HTML tables.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
#
|
||||
# Find tables with leading pipe.
|
||||
#
|
||||
# | Header 1 | Header 2
|
||||
# | -------- | --------
|
||||
# | Cell 1 | Cell 2
|
||||
# | Cell 3 | Cell 4
|
||||
#
|
||||
$text = preg_replace_callback('
|
||||
{
|
||||
^ # Start of a line
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
[|] # Optional leading pipe (present)
|
||||
(.+) \n # $1: Header row (at least one pipe)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
[|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline
|
||||
|
||||
( # $3: Cells
|
||||
(?>
|
||||
[ ]* # Allowed whitespace.
|
||||
[|] .* \n # Row content.
|
||||
)*
|
||||
)
|
||||
(?=\n|\Z) # Stop at final double newline.
|
||||
}xm',
|
||||
array(&$this, '_doTable_leadingPipe_callback'), $text);
|
||||
|
||||
#
|
||||
# Find tables without leading pipe.
|
||||
#
|
||||
# Header 1 | Header 2
|
||||
# -------- | --------
|
||||
# Cell 1 | Cell 2
|
||||
# Cell 3 | Cell 4
|
||||
#
|
||||
$text = preg_replace_callback('
|
||||
{
|
||||
^ # Start of a line
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
(\S.*[|].*) \n # $1: Header row (at least one pipe)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
([-:]+[ ]*[|][-| :]*) \n # $2: Header underline
|
||||
|
||||
( # $3: Cells
|
||||
(?>
|
||||
.* [|] .* \n # Row content
|
||||
)*
|
||||
)
|
||||
(?=\n|\Z) # Stop at final double newline.
|
||||
}xm',
|
||||
array(&$this, '_DoTable_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doTable_leadingPipe_callback($matches) {
|
||||
$head = $matches[1];
|
||||
$underline = $matches[2];
|
||||
$content = $matches[3];
|
||||
|
||||
# Remove leading pipe for each row.
|
||||
$content = preg_replace('/^ *[|]/m', '', $content);
|
||||
|
||||
return $this->_doTable_callback(array($matches[0], $head, $underline, $content));
|
||||
}
|
||||
function _doTable_callback($matches) {
|
||||
$head = $matches[1];
|
||||
$underline = $matches[2];
|
||||
$content = $matches[3];
|
||||
|
||||
# Remove any tailing pipes for each line.
|
||||
$head = preg_replace('/[|] *$/m', '', $head);
|
||||
$underline = preg_replace('/[|] *$/m', '', $underline);
|
||||
$content = preg_replace('/[|] *$/m', '', $content);
|
||||
|
||||
# Reading alignement from header underline.
|
||||
$separators = preg_split('/ *[|] */', $underline);
|
||||
foreach ($separators as $n => $s) {
|
||||
if (preg_match('/^ *-+: *$/', $s)) $attr[$n] = ' align="right"';
|
||||
else if (preg_match('/^ *:-+: *$/', $s))$attr[$n] = ' align="center"';
|
||||
else if (preg_match('/^ *:-+ *$/', $s)) $attr[$n] = ' align="left"';
|
||||
else $attr[$n] = '';
|
||||
}
|
||||
|
||||
# Parsing span elements, including code spans, character escapes,
|
||||
# and inline HTML tags, so that pipes inside those gets ignored.
|
||||
$head = $this->parseSpan($head);
|
||||
$headers = preg_split('/ *[|] */', $head);
|
||||
$col_count = count($headers);
|
||||
|
||||
# Write column headers.
|
||||
$text = "<table>\n";
|
||||
$text .= "<thead>\n";
|
||||
$text .= "<tr>\n";
|
||||
foreach ($headers as $n => $header)
|
||||
$text .= " <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n";
|
||||
$text .= "</tr>\n";
|
||||
$text .= "</thead>\n";
|
||||
|
||||
# Split content by row.
|
||||
$rows = explode("\n", trim($content, "\n"));
|
||||
|
||||
$text .= "<tbody>\n";
|
||||
foreach ($rows as $row) {
|
||||
# Parsing span elements, including code spans, character escapes,
|
||||
# and inline HTML tags, so that pipes inside those gets ignored.
|
||||
$row = $this->parseSpan($row);
|
||||
|
||||
# Split row by cell.
|
||||
$row_cells = preg_split('/ *[|] */', $row, $col_count);
|
||||
$row_cells = array_pad($row_cells, $col_count, '');
|
||||
|
||||
$text .= "<tr>\n";
|
||||
foreach ($row_cells as $n => $cell)
|
||||
$text .= " <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n";
|
||||
$text .= "</tr>\n";
|
||||
}
|
||||
$text .= "</tbody>\n";
|
||||
$text .= "</table>";
|
||||
|
||||
return $this->hashBlock($text) . "\n";
|
||||
}
|
||||
|
||||
|
||||
function doDefLists($text) {
|
||||
#
|
||||
# Form HTML definition lists.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Re-usable pattern to match any entire dl list:
|
||||
$whole_list_re = '(?>
|
||||
( # $1 = whole list
|
||||
( # $2
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
((?>.*\S.*\n)+) # $3 = defined term
|
||||
\n?
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
(?s:.+?)
|
||||
( # $4
|
||||
\z
|
||||
|
|
||||
\n{2,}
|
||||
(?=\S)
|
||||
(?! # Negative lookahead for another term
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?: \S.*\n )+? # defined term
|
||||
\n?
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
(?! # Negative lookahead for another definition
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
)
|
||||
)
|
||||
)'; // mx
|
||||
|
||||
$text = preg_replace_callback('{
|
||||
(?>\A\n?|(?<=\n\n))
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array(&$this, '_doDefLists_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doDefLists_callback($matches) {
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$list = $matches[1];
|
||||
|
||||
# Turn double returns into triple returns, so that we can make a
|
||||
# paragraph for the last item in a list, if necessary:
|
||||
$result = trim($this->processDefListItems($list));
|
||||
$result = "<dl>\n" . $result . "\n</dl>";
|
||||
return $this->hashBlock($result) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
function processDefListItems($list_str) {
|
||||
#
|
||||
# Process the contents of a single definition list, splitting it
|
||||
# into individual term and definition list items.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# trim trailing blank lines:
|
||||
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
|
||||
|
||||
# Process definition terms.
|
||||
$list_str = preg_replace_callback('{
|
||||
(?>\A\n?|\n\n+) # leading line
|
||||
( # definition terms = $1
|
||||
[ ]{0,'.$less_than_tab.'} # leading whitespace
|
||||
(?![:][ ]|[ ]) # negative lookahead for a definition
|
||||
# mark (colon) or more whitespace.
|
||||
(?> \S.* \n)+? # actual term (not whitespace).
|
||||
)
|
||||
(?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
|
||||
# with a definition mark.
|
||||
}xm',
|
||||
array(&$this, '_processDefListItems_callback_dt'), $list_str);
|
||||
|
||||
# Process actual definitions.
|
||||
$list_str = preg_replace_callback('{
|
||||
\n(\n+)? # leading line = $1
|
||||
( # marker space = $2
|
||||
[ ]{0,'.$less_than_tab.'} # whitespace before colon
|
||||
[:][ ]+ # definition mark (colon)
|
||||
)
|
||||
((?s:.+?)) # definition text = $3
|
||||
(?= \n+ # stop at next definition mark,
|
||||
(?: # next term or end of text
|
||||
[ ]{0,'.$less_than_tab.'} [:][ ] |
|
||||
<dt> | \z
|
||||
)
|
||||
)
|
||||
}xm',
|
||||
array(&$this, '_processDefListItems_callback_dd'), $list_str);
|
||||
|
||||
return $list_str;
|
||||
}
|
||||
function _processDefListItems_callback_dt($matches) {
|
||||
$terms = explode("\n", trim($matches[1]));
|
||||
$text = '';
|
||||
foreach ($terms as $term) {
|
||||
$term = $this->runSpanGamut(trim($term));
|
||||
$text .= "\n<dt>" . $term . "</dt>";
|
||||
}
|
||||
return $text . "\n";
|
||||
}
|
||||
function _processDefListItems_callback_dd($matches) {
|
||||
$leading_line = $matches[1];
|
||||
$marker_space = $matches[2];
|
||||
$def = $matches[3];
|
||||
|
||||
if ($leading_line || preg_match('/\n{2,}/', $def)) {
|
||||
# Replace marker with the appropriate whitespace indentation
|
||||
$def = str_repeat(' ', strlen($marker_space)) . $def;
|
||||
$def = $this->runBlockGamut($this->outdent($def . "\n\n"));
|
||||
$def = "\n". $def ."\n";
|
||||
}
|
||||
else {
|
||||
$def = rtrim($def);
|
||||
$def = $this->runSpanGamut($this->outdent($def));
|
||||
}
|
||||
|
||||
return "\n<dd>" . $def . "</dd>\n";
|
||||
}
|
||||
|
||||
|
||||
function doFencedCodeBlocks($text) {
|
||||
#
|
||||
# Adding the fenced code block syntax to regular Markdown:
|
||||
#
|
||||
# ~~~
|
||||
# Code block
|
||||
# ~~~
|
||||
#
|
||||
$less_than_tab = $this->tab_width;
|
||||
|
||||
$text = preg_replace_callback('{
|
||||
(?:\n|\A)
|
||||
# 1: Opening marker
|
||||
(
|
||||
~{3,} # Marker: three tilde or more.
|
||||
)
|
||||
[ ]* \n # Whitespace and newline following marker.
|
||||
|
||||
# 2: Content
|
||||
(
|
||||
(?>
|
||||
(?!\1 [ ]* \n) # Not a closing marker.
|
||||
.*\n+
|
||||
)+
|
||||
)
|
||||
|
||||
# Closing marker.
|
||||
\1 [ ]* \n
|
||||
}xm',
|
||||
array(&$this, '_doFencedCodeBlocks_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
function _doFencedCodeBlocks_callback($matches) {
|
||||
$codeblock = $matches[2];
|
||||
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
|
||||
$codeblock = preg_replace_callback('/^\n+/',
|
||||
array(&$this, '_doFencedCodeBlocks_newlines'), $codeblock);
|
||||
$codeblock = "<pre><code>$codeblock</code></pre>";
|
||||
return "\n\n".$this->hashBlock($codeblock)."\n\n";
|
||||
}
|
||||
function _doFencedCodeBlocks_newlines($matches) {
|
||||
return str_repeat("<br$this->empty_element_suffix",
|
||||
strlen($matches[0]));
|
||||
}
|
||||
|
||||
|
||||
#
|
||||
# Redefining emphasis markers so that emphasis by underscore does not
|
||||
# work in the middle of a word.
|
||||
#
|
||||
var $em_relist = array(
|
||||
'' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
|
||||
'_' => '(?<=\S|^)(?<!_)_(?![a-zA-Z0-9_])',
|
||||
);
|
||||
var $strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
|
||||
'__' => '(?<=\S|^)(?<!_)__(?![a-zA-Z0-9_])',
|
||||
);
|
||||
var $em_strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?=\S|$)(?![\.,:;]\s)',
|
||||
'***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
|
||||
'___' => '(?<=\S|^)(?<!_)___(?![a-zA-Z0-9_])',
|
||||
);
|
||||
|
||||
|
||||
function formParagraphs($text) {
|
||||
#
|
||||
# Params:
|
||||
# $text - string to process with html <p> tags
|
||||
#
|
||||
# Strip leading and trailing lines:
|
||||
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
|
||||
|
||||
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
|
||||
|
||||
#
|
||||
# Wrap <p> tags and unhashify HTML blocks
|
||||
#
|
||||
foreach ($grafs as $key => $value) {
|
||||
$value = trim($this->runSpanGamut($value));
|
||||
|
||||
# Check if this should be enclosed in a paragraph.
|
||||
# Clean tag hashes & block tag hashes are left alone.
|
||||
$is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
|
||||
|
||||
if ($is_p) {
|
||||
$value = "<p>$value</p>";
|
||||
}
|
||||
$grafs[$key] = $value;
|
||||
}
|
||||
|
||||
# Join grafs in one text, then unhash HTML tags.
|
||||
$text = implode("\n\n", $grafs);
|
||||
|
||||
# Finish by removing any tag hashes still present in $text.
|
||||
$text = $this->unhash($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
### Footnotes
|
||||
|
||||
function stripFootnotes($text) {
|
||||
#
|
||||
# Strips link definitions from text, stores the URLs and titles in
|
||||
# hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: [^id]: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
|
||||
[ ]*
|
||||
\n? # maybe *one* newline
|
||||
( # text = $2 (no blank lines allowed)
|
||||
(?:
|
||||
.+ # actual text
|
||||
|
|
||||
\n # newlines but
|
||||
(?!\[\^.+?\]:\s)# negative lookahead for footnote marker.
|
||||
(?!\n+[ ]{0,3}\S)# ensure line is not blank and followed
|
||||
# by non-indented content
|
||||
)*
|
||||
)
|
||||
}xm',
|
||||
array(&$this, '_stripFootnotes_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
function _stripFootnotes_callback($matches) {
|
||||
$note_id = $this->fn_id_prefix . $matches[1];
|
||||
$this->footnotes[$note_id] = $this->outdent($matches[2]);
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
function doFootnotes($text) {
|
||||
#
|
||||
# Replace footnote references in $text [^id] with a special text-token
|
||||
# which will be replaced by the actual footnote marker in appendFootnotes.
|
||||
#
|
||||
if (!$this->in_anchor) {
|
||||
$text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
function appendFootnotes($text) {
|
||||
#
|
||||
# Append footnote list to text.
|
||||
#
|
||||
$text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
|
||||
array(&$this, '_appendFootnotes_callback'), $text);
|
||||
|
||||
if (!empty($this->footnotes_ordered)) {
|
||||
$text .= "\n\n";
|
||||
$text .= "<div class=\"footnotes\">\n";
|
||||
$text .= "<hr". $this->empty_element_suffix ."\n";
|
||||
$text .= "<ol>\n\n";
|
||||
|
||||
$attr = " rev=\"footnote\"";
|
||||
if ($this->fn_backlink_class != "") {
|
||||
$class = $this->fn_backlink_class;
|
||||
$class = $this->encodeAttribute($class);
|
||||
$attr .= " class=\"$class\"";
|
||||
}
|
||||
if ($this->fn_backlink_title != "") {
|
||||
$title = $this->fn_backlink_title;
|
||||
$title = $this->encodeAttribute($title);
|
||||
$attr .= " title=\"$title\"";
|
||||
}
|
||||
$num = 0;
|
||||
|
||||
while (!empty($this->footnotes_ordered)) {
|
||||
$footnote = reset($this->footnotes_ordered);
|
||||
$note_id = key($this->footnotes_ordered);
|
||||
unset($this->footnotes_ordered[$note_id]);
|
||||
|
||||
$footnote .= "\n"; # Need to append newline before parsing.
|
||||
$footnote = $this->runBlockGamut("$footnote\n");
|
||||
$footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
|
||||
array(&$this, '_appendFootnotes_callback'), $footnote);
|
||||
|
||||
$attr = str_replace("%%", ++$num, $attr);
|
||||
$note_id = $this->encodeAttribute($note_id);
|
||||
|
||||
# Add backlink to last paragraph; create new paragraph if needed.
|
||||
$backlink = "<a href=\"#fnref:$note_id\"$attr>↩</a>";
|
||||
if (preg_match('{</p>$}', $footnote)) {
|
||||
$footnote = substr($footnote, 0, -4) . " $backlink</p>";
|
||||
} else {
|
||||
$footnote .= "\n\n<p>$backlink</p>";
|
||||
}
|
||||
|
||||
$text .= "<li id=\"fn:$note_id\">\n";
|
||||
$text .= $footnote . "\n";
|
||||
$text .= "</li>\n\n";
|
||||
}
|
||||
|
||||
$text .= "</ol>\n";
|
||||
$text .= "</div>";
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
function _appendFootnotes_callback($matches) {
|
||||
$node_id = $this->fn_id_prefix . $matches[1];
|
||||
|
||||
# Create footnote marker only if it has a corresponding footnote *and*
|
||||
# the footnote hasn't been used by another marker.
|
||||
if (isset($this->footnotes[$node_id])) {
|
||||
# Transfert footnote content to the ordered list.
|
||||
$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
|
||||
unset($this->footnotes[$node_id]);
|
||||
|
||||
$num = $this->footnote_counter++;
|
||||
$attr = " rel=\"footnote\"";
|
||||
if ($this->fn_link_class != "") {
|
||||
$class = $this->fn_link_class;
|
||||
$class = $this->encodeAttribute($class);
|
||||
$attr .= " class=\"$class\"";
|
||||
}
|
||||
if ($this->fn_link_title != "") {
|
||||
$title = $this->fn_link_title;
|
||||
$title = $this->encodeAttribute($title);
|
||||
$attr .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$attr = str_replace("%%", $num, $attr);
|
||||
$node_id = $this->encodeAttribute($node_id);
|
||||
|
||||
return
|
||||
"<sup id=\"fnref:$node_id\">".
|
||||
"<a href=\"#fn:$node_id\"$attr>$num</a>".
|
||||
"</sup>";
|
||||
}
|
||||
|
||||
return "[^".$matches[1]."]";
|
||||
}
|
||||
|
||||
|
||||
### Abbreviations ###
|
||||
|
||||
function stripAbbreviations($text) {
|
||||
#
|
||||
# Strips abbreviations from text, stores titles in hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: [id]*: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1
|
||||
(.*) # text = $2 (no blank lines allowed)
|
||||
}xm',
|
||||
array(&$this, '_stripAbbreviations_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
function _stripAbbreviations_callback($matches) {
|
||||
$abbr_word = $matches[1];
|
||||
$abbr_desc = $matches[2];
|
||||
if ($this->abbr_word_re)
|
||||
$this->abbr_word_re .= '|';
|
||||
$this->abbr_word_re .= preg_quote($abbr_word);
|
||||
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
function doAbbreviations($text) {
|
||||
#
|
||||
# Find defined abbreviations in text and wrap them in <abbr> elements.
|
||||
#
|
||||
if ($this->abbr_word_re) {
|
||||
// cannot use the /x modifier because abbr_word_re may
|
||||
// contain significant spaces:
|
||||
$text = preg_replace_callback('{'.
|
||||
'(?<![\w\x1A])'.
|
||||
'(?:'.$this->abbr_word_re.')'.
|
||||
'(?![\w\x1A])'.
|
||||
'}',
|
||||
array(&$this, '_doAbbreviations_callback'), $text);
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
function _doAbbreviations_callback($matches) {
|
||||
$abbr = $matches[0];
|
||||
if (isset($this->abbr_desciptions[$abbr])) {
|
||||
$desc = $this->abbr_desciptions[$abbr];
|
||||
if (empty($desc)) {
|
||||
return $this->hashPart("<abbr>$abbr</abbr>");
|
||||
} else {
|
||||
$desc = $this->encodeAttribute($desc);
|
||||
return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>");
|
||||
}
|
||||
} else {
|
||||
return $matches[0];
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
|
||||
PHP Markdown Extra
|
||||
==================
|
||||
|
||||
Description
|
||||
-----------
|
||||
|
||||
This is a PHP port of the original Markdown formatter written in Perl
|
||||
by John Gruber. This special "Extra" version of PHP Markdown features
|
||||
further enhancements to the syntax for making additional constructs
|
||||
such as tables and definition list.
|
||||
|
||||
Markdown is a text-to-HTML filter; it translates an easy-to-read /
|
||||
easy-to-write structured text format into HTML. Markdown's text format
|
||||
is most similar to that of plain text email, and supports features such
|
||||
as headers, *emphasis*, code blocks, blockquotes, and links.
|
||||
|
||||
Markdown's syntax is designed not as a generic markup language, but
|
||||
specifically to serve as a front-end to (X)HTML. You can use span-level
|
||||
HTML tags anywhere in a Markdown document, and you can use block level
|
||||
HTML tags (like <div> and <table> as well).
|
||||
|
||||
For more information about Markdown's syntax, see:
|
||||
|
||||
<http://daringfireball.net/projects/markdown/>
|
||||
|
||||
|
||||
Bugs
|
||||
----
|
||||
|
||||
To file bug reports please send email to:
|
||||
|
||||
<michel.fortin@michelf.com>
|
||||
|
||||
Please include with your report: (1) the example input; (2) the output you
|
||||
expected; (3) the output Markdown actually produced.
|
||||
|
||||
|
||||
Version History
|
||||
---------------
|
||||
|
||||
See the readme file for detailed release notes for this version.
|
||||
|
||||
|
||||
Copyright and License
|
||||
---------------------
|
||||
|
||||
PHP Markdown & Extra
|
||||
Copyright (c) 2004-2009 Michel Fortin
|
||||
<http://michelf.com/>
|
||||
All rights reserved.
|
||||
|
||||
Based on Markdown
|
||||
Copyright (c) 2003-2006 John Gruber
|
||||
<http://daringfireball.net/>
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name "Markdown" nor the names of its contributors may
|
||||
be used to endorse or promote products derived from this software
|
||||
without specific prior written permission.
|
||||
|
||||
This software is provided by the copyright holders and contributors "as
|
||||
is" and any express or implied warranties, including, but not limited
|
||||
to, the implied warranties of merchantability and fitness for a
|
||||
particular purpose are disclaimed. In no event shall the copyright owner
|
||||
or contributors be liable for any direct, indirect, incidental, special,
|
||||
exemplary, or consequential damages (including, but not limited to,
|
||||
procurement of substitute goods or services; loss of use, data, or
|
||||
profits; or business interruption) however caused and on any theory of
|
||||
liability, whether in contract, strict liability, or tort (including
|
||||
negligence or otherwise) arising in any way out of the use of this
|
||||
software, even if advised of the possibility of such damage.
|
||||
|
||||
*/
|
||||
?>
|
||||
36
library/php-markdown/License.md
Normal file
36
library/php-markdown/License.md
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
PHP Markdown Lib
|
||||
Copyright (c) 2004-2014 Michel Fortin
|
||||
<http://michelf.ca/>
|
||||
All rights reserved.
|
||||
|
||||
Based on Markdown
|
||||
Copyright (c) 2003-2006 John Gruber
|
||||
<http://daringfireball.net/>
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name "Markdown" nor the names of its contributors may
|
||||
be used to endorse or promote products derived from this software
|
||||
without specific prior written permission.
|
||||
|
||||
This software is provided by the copyright holders and contributors "as
|
||||
is" and any express or implied warranties, including, but not limited
|
||||
to, the implied warranties of merchantability and fitness for a
|
||||
particular purpose are disclaimed. In no event shall the copyright owner
|
||||
or contributors be liable for any direct, indirect, incidental, special,
|
||||
exemplary, or consequential damages (including, but not limited to,
|
||||
procurement of substitute goods or services; loss of use, data, or
|
||||
profits; or business interruption) however caused and on any theory of
|
||||
liability, whether in contract, strict liability, or tort (including
|
||||
negligence or otherwise) arising in any way out of the use of this
|
||||
software, even if advised of the possibility of such damage.
|
||||
10
library/php-markdown/Michelf/Markdown.inc.php
Normal file
10
library/php-markdown/Michelf/Markdown.inc.php
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
|
||||
# Use this file if you cannot use class autoloading. It will include all the
|
||||
# files needed for the Markdown parser.
|
||||
#
|
||||
# Take a look at the PSR-0-compatible class autoloading implementation
|
||||
# in the Readme.php file if you want a simple autoloader setup.
|
||||
|
||||
require_once dirname(__FILE__) . '/MarkdownInterface.php';
|
||||
require_once dirname(__FILE__) . '/Markdown.php';
|
||||
3151
library/php-markdown/Michelf/Markdown.php
Normal file
3151
library/php-markdown/Michelf/Markdown.php
Normal file
|
|
@ -0,0 +1,3151 @@
|
|||
<?php
|
||||
#
|
||||
# Markdown - A text-to-HTML conversion tool for web writers
|
||||
#
|
||||
# PHP Markdown
|
||||
# Copyright (c) 2004-2014 Michel Fortin
|
||||
# <http://michelf.com/projects/php-markdown/>
|
||||
#
|
||||
# Original Markdown
|
||||
# Copyright (c) 2004-2006 John Gruber
|
||||
# <http://daringfireball.net/projects/markdown/>
|
||||
#
|
||||
namespace Michelf;
|
||||
|
||||
|
||||
#
|
||||
# Markdown Parser Class
|
||||
#
|
||||
|
||||
class Markdown implements MarkdownInterface {
|
||||
|
||||
### Version ###
|
||||
|
||||
const MARKDOWNLIB_VERSION = "1.4.1";
|
||||
|
||||
### Simple Function Interface ###
|
||||
|
||||
public static function defaultTransform($text) {
|
||||
#
|
||||
# Initialize the parser and return the result of its transform method.
|
||||
# This will work fine for derived classes too.
|
||||
#
|
||||
# Take parser class on which this function was called.
|
||||
$parser_class = \get_called_class();
|
||||
|
||||
# try to take parser from the static parser list
|
||||
static $parser_list;
|
||||
$parser =& $parser_list[$parser_class];
|
||||
|
||||
# create the parser it not already set
|
||||
if (!$parser)
|
||||
$parser = new $parser_class;
|
||||
|
||||
# Transform text using parser.
|
||||
return $parser->transform($text);
|
||||
}
|
||||
|
||||
### Configuration Variables ###
|
||||
|
||||
# Change to ">" for HTML output.
|
||||
public $empty_element_suffix = " />";
|
||||
public $tab_width = 4;
|
||||
|
||||
# Change to `true` to disallow markup or entities.
|
||||
public $no_markup = false;
|
||||
public $no_entities = false;
|
||||
|
||||
# Predefined urls and titles for reference links and images.
|
||||
public $predef_urls = array();
|
||||
public $predef_titles = array();
|
||||
|
||||
# Optional filter function for URLs
|
||||
public $url_filter_func = null;
|
||||
|
||||
|
||||
### Parser Implementation ###
|
||||
|
||||
# Regex to match balanced [brackets].
|
||||
# Needed to insert a maximum bracked depth while converting to PHP.
|
||||
protected $nested_brackets_depth = 6;
|
||||
protected $nested_brackets_re;
|
||||
|
||||
protected $nested_url_parenthesis_depth = 4;
|
||||
protected $nested_url_parenthesis_re;
|
||||
|
||||
# Table of hash values for escaped characters:
|
||||
protected $escape_chars = '\`*_{}[]()>#+-.!';
|
||||
protected $escape_chars_re;
|
||||
|
||||
|
||||
public function __construct() {
|
||||
#
|
||||
# Constructor function. Initialize appropriate member variables.
|
||||
#
|
||||
$this->_initDetab();
|
||||
$this->prepareItalicsAndBold();
|
||||
|
||||
$this->nested_brackets_re =
|
||||
str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
|
||||
str_repeat('\])*', $this->nested_brackets_depth);
|
||||
|
||||
$this->nested_url_parenthesis_re =
|
||||
str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
|
||||
str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
|
||||
|
||||
$this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
|
||||
|
||||
# Sort document, block, and span gamut in ascendent priority order.
|
||||
asort($this->document_gamut);
|
||||
asort($this->block_gamut);
|
||||
asort($this->span_gamut);
|
||||
}
|
||||
|
||||
|
||||
# Internal hashes used during transformation.
|
||||
protected $urls = array();
|
||||
protected $titles = array();
|
||||
protected $html_hashes = array();
|
||||
|
||||
# Status flag to avoid invalid nesting.
|
||||
protected $in_anchor = false;
|
||||
|
||||
|
||||
protected function setup() {
|
||||
#
|
||||
# Called before the transformation process starts to setup parser
|
||||
# states.
|
||||
#
|
||||
# Clear global hashes.
|
||||
$this->urls = $this->predef_urls;
|
||||
$this->titles = $this->predef_titles;
|
||||
$this->html_hashes = array();
|
||||
|
||||
$this->in_anchor = false;
|
||||
}
|
||||
|
||||
protected function teardown() {
|
||||
#
|
||||
# Called after the transformation process to clear any variable
|
||||
# which may be taking up memory unnecessarly.
|
||||
#
|
||||
$this->urls = array();
|
||||
$this->titles = array();
|
||||
$this->html_hashes = array();
|
||||
}
|
||||
|
||||
|
||||
public function transform($text) {
|
||||
#
|
||||
# Main function. Performs some preprocessing on the input text
|
||||
# and pass it through the document gamut.
|
||||
#
|
||||
$this->setup();
|
||||
|
||||
# Remove UTF-8 BOM and marker character in input, if present.
|
||||
$text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text);
|
||||
|
||||
# Standardize line endings:
|
||||
# DOS to Unix and Mac to Unix
|
||||
$text = preg_replace('{\r\n?}', "\n", $text);
|
||||
|
||||
# Make sure $text ends with a couple of newlines:
|
||||
$text .= "\n\n";
|
||||
|
||||
# Convert all tabs to spaces.
|
||||
$text = $this->detab($text);
|
||||
|
||||
# Turn block-level HTML blocks into hash entries
|
||||
$text = $this->hashHTMLBlocks($text);
|
||||
|
||||
# Strip any lines consisting only of spaces and tabs.
|
||||
# This makes subsequent regexen easier to write, because we can
|
||||
# match consecutive blank lines with /\n+/ instead of something
|
||||
# contorted like /[ ]*\n+/ .
|
||||
$text = preg_replace('/^[ ]+$/m', '', $text);
|
||||
|
||||
# Run document gamut methods.
|
||||
foreach ($this->document_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
$this->teardown();
|
||||
|
||||
return $text . "\n";
|
||||
}
|
||||
|
||||
protected $document_gamut = array(
|
||||
# Strip link definitions, store in hashes.
|
||||
"stripLinkDefinitions" => 20,
|
||||
|
||||
"runBasicBlockGamut" => 30,
|
||||
);
|
||||
|
||||
|
||||
protected function stripLinkDefinitions($text) {
|
||||
#
|
||||
# Strips link definitions from text, stores the URLs and titles in
|
||||
# hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: ^[id]: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
|
||||
[ ]*
|
||||
\n? # maybe *one* newline
|
||||
[ ]*
|
||||
(?:
|
||||
<(.+?)> # url = $2
|
||||
|
|
||||
(\S+?) # url = $3
|
||||
)
|
||||
[ ]*
|
||||
\n? # maybe one newline
|
||||
[ ]*
|
||||
(?:
|
||||
(?<=\s) # lookbehind for whitespace
|
||||
["(]
|
||||
(.*?) # title = $4
|
||||
[")]
|
||||
[ ]*
|
||||
)? # title is optional
|
||||
(?:\n+|\Z)
|
||||
}xm',
|
||||
array($this, '_stripLinkDefinitions_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
protected function _stripLinkDefinitions_callback($matches) {
|
||||
$link_id = strtolower($matches[1]);
|
||||
$url = $matches[2] == '' ? $matches[3] : $matches[2];
|
||||
$this->urls[$link_id] = $url;
|
||||
$this->titles[$link_id] =& $matches[4];
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
protected function hashHTMLBlocks($text) {
|
||||
if ($this->no_markup) return $text;
|
||||
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Hashify HTML blocks:
|
||||
# We only want to do this for block-level HTML tags, such as headers,
|
||||
# lists, and tables. That's because we still want to wrap <p>s around
|
||||
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
|
||||
# phrase emphasis, and spans. The list of tags we're looking for is
|
||||
# hard-coded:
|
||||
#
|
||||
# * List "a" is made of tags which can be both inline or block-level.
|
||||
# These will be treated block-level when the start tag is alone on
|
||||
# its line, otherwise they're not matched here and will be taken as
|
||||
# inline later.
|
||||
# * List "b" is made of tags which are always block-level;
|
||||
#
|
||||
$block_tags_a_re = 'ins|del';
|
||||
$block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
|
||||
'script|noscript|style|form|fieldset|iframe|math|svg|'.
|
||||
'article|section|nav|aside|hgroup|header|footer|'.
|
||||
'figure';
|
||||
|
||||
# Regular expression for the content of a block tag.
|
||||
$nested_tags_level = 4;
|
||||
$attr = '
|
||||
(?> # optional tag attributes
|
||||
\s # starts with whitespace
|
||||
(?>
|
||||
[^>"/]+ # text outside quotes
|
||||
|
|
||||
/+(?!>) # slash not followed by ">"
|
||||
|
|
||||
"[^"]*" # text inside double quotes (tolerate ">")
|
||||
|
|
||||
\'[^\']*\' # text inside single quotes (tolerate ">")
|
||||
)*
|
||||
)?
|
||||
';
|
||||
$content =
|
||||
str_repeat('
|
||||
(?>
|
||||
[^<]+ # content without tag
|
||||
|
|
||||
<\2 # nested opening tag
|
||||
'.$attr.' # attributes
|
||||
(?>
|
||||
/>
|
||||
|
|
||||
>', $nested_tags_level). # end of opening tag
|
||||
'.*?'. # last level nested tag content
|
||||
str_repeat('
|
||||
</\2\s*> # closing nested tag
|
||||
)
|
||||
|
|
||||
<(?!/\2\s*> # other tags with a different name
|
||||
)
|
||||
)*',
|
||||
$nested_tags_level);
|
||||
$content2 = str_replace('\2', '\3', $content);
|
||||
|
||||
# First, look for nested blocks, e.g.:
|
||||
# <div>
|
||||
# <div>
|
||||
# tags for inner block must be indented.
|
||||
# </div>
|
||||
# </div>
|
||||
#
|
||||
# The outermost tags must start at the left margin for this to match, and
|
||||
# the inner nested divs must be indented.
|
||||
# We need to do this before the next, more liberal match, because the next
|
||||
# match will start at the first `<div>` and stop at the first `</div>`.
|
||||
$text = preg_replace_callback('{(?>
|
||||
(?>
|
||||
(?<=\n) # Starting on its own line
|
||||
| # or
|
||||
\A\n? # the at beginning of the doc
|
||||
)
|
||||
( # save in $1
|
||||
|
||||
# Match from `\n<tag>` to `</tag>\n`, handling nested tags
|
||||
# in between.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<('.$block_tags_b_re.')# start tag = $2
|
||||
'.$attr.'> # attributes followed by > and \n
|
||||
'.$content.' # content, support nesting
|
||||
</\2> # the matching end tag
|
||||
[ ]* # trailing spaces/tabs
|
||||
(?=\n+|\Z) # followed by a newline or end of document
|
||||
|
||||
| # Special version for tags of group a.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<('.$block_tags_a_re.')# start tag = $3
|
||||
'.$attr.'>[ ]*\n # attributes followed by >
|
||||
'.$content2.' # content, support nesting
|
||||
</\3> # the matching end tag
|
||||
[ ]* # trailing spaces/tabs
|
||||
(?=\n+|\Z) # followed by a newline or end of document
|
||||
|
||||
| # Special case just for <hr />. It was easier to make a special
|
||||
# case than to make the other regex more complicated.
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
<(hr) # start tag = $2
|
||||
'.$attr.' # attributes
|
||||
/?> # the matching end tag
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
| # Special case for standalone HTML comments:
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?s:
|
||||
<!-- .*? -->
|
||||
)
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
| # PHP and ASP-style processor instructions (<? and <%)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?s:
|
||||
<([?%]) # $2
|
||||
.*?
|
||||
\2>
|
||||
)
|
||||
[ ]*
|
||||
(?=\n{2,}|\Z) # followed by a blank line or end of document
|
||||
|
||||
)
|
||||
)}Sxmi',
|
||||
array($this, '_hashHTMLBlocks_callback'),
|
||||
$text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _hashHTMLBlocks_callback($matches) {
|
||||
$text = $matches[1];
|
||||
$key = $this->hashBlock($text);
|
||||
return "\n\n$key\n\n";
|
||||
}
|
||||
|
||||
|
||||
protected function hashPart($text, $boundary = 'X') {
|
||||
#
|
||||
# Called whenever a tag must be hashed when a function insert an atomic
|
||||
# element in the text stream. Passing $text to through this function gives
|
||||
# a unique text-token which will be reverted back when calling unhash.
|
||||
#
|
||||
# The $boundary argument specify what character should be used to surround
|
||||
# the token. By convension, "B" is used for block elements that needs not
|
||||
# to be wrapped into paragraph tags at the end, ":" is used for elements
|
||||
# that are word separators and "X" is used in the general case.
|
||||
#
|
||||
# Swap back any tag hash found in $text so we do not have to `unhash`
|
||||
# multiple times at the end.
|
||||
$text = $this->unhash($text);
|
||||
|
||||
# Then hash the block.
|
||||
static $i = 0;
|
||||
$key = "$boundary\x1A" . ++$i . $boundary;
|
||||
$this->html_hashes[$key] = $text;
|
||||
return $key; # String that will replace the tag.
|
||||
}
|
||||
|
||||
|
||||
protected function hashBlock($text) {
|
||||
#
|
||||
# Shortcut function for hashPart with block-level boundaries.
|
||||
#
|
||||
return $this->hashPart($text, 'B');
|
||||
}
|
||||
|
||||
|
||||
protected $block_gamut = array(
|
||||
#
|
||||
# These are all the transformations that form block-level
|
||||
# tags like paragraphs, headers, and list items.
|
||||
#
|
||||
"doHeaders" => 10,
|
||||
"doHorizontalRules" => 20,
|
||||
|
||||
"doLists" => 40,
|
||||
"doCodeBlocks" => 50,
|
||||
"doBlockQuotes" => 60,
|
||||
);
|
||||
|
||||
protected function runBlockGamut($text) {
|
||||
#
|
||||
# Run block gamut tranformations.
|
||||
#
|
||||
# We need to escape raw HTML in Markdown source before doing anything
|
||||
# else. This need to be done for each block, and not only at the
|
||||
# begining in the Markdown function since hashed blocks can be part of
|
||||
# list items and could have been indented. Indented blocks would have
|
||||
# been seen as a code block in a previous pass of hashHTMLBlocks.
|
||||
$text = $this->hashHTMLBlocks($text);
|
||||
|
||||
return $this->runBasicBlockGamut($text);
|
||||
}
|
||||
|
||||
protected function runBasicBlockGamut($text) {
|
||||
#
|
||||
# Run block gamut tranformations, without hashing HTML blocks. This is
|
||||
# useful when HTML blocks are known to be already hashed, like in the first
|
||||
# whole-document pass.
|
||||
#
|
||||
foreach ($this->block_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
# Finally form paragraph and restore hashed blocks.
|
||||
$text = $this->formParagraphs($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function doHorizontalRules($text) {
|
||||
# Do Horizontal Rules:
|
||||
return preg_replace(
|
||||
'{
|
||||
^[ ]{0,3} # Leading space
|
||||
([-*_]) # $1: First marker
|
||||
(?> # Repeated marker group
|
||||
[ ]{0,2} # Zero, one, or two spaces.
|
||||
\1 # Marker character
|
||||
){2,} # Group repeated at least twice
|
||||
[ ]* # Tailing spaces
|
||||
$ # End of line.
|
||||
}mx',
|
||||
"\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n",
|
||||
$text);
|
||||
}
|
||||
|
||||
|
||||
protected $span_gamut = array(
|
||||
#
|
||||
# These are all the transformations that occur *within* block-level
|
||||
# tags like paragraphs, headers, and list items.
|
||||
#
|
||||
# Process character escapes, code spans, and inline HTML
|
||||
# in one shot.
|
||||
"parseSpan" => -30,
|
||||
|
||||
# Process anchor and image tags. Images must come first,
|
||||
# because ![foo][f] looks like an anchor.
|
||||
"doImages" => 10,
|
||||
"doAnchors" => 20,
|
||||
|
||||
# Make links out of things like `<http://example.com/>`
|
||||
# Must come after doAnchors, because you can use < and >
|
||||
# delimiters in inline links like [this](<url>).
|
||||
"doAutoLinks" => 30,
|
||||
"encodeAmpsAndAngles" => 40,
|
||||
|
||||
"doItalicsAndBold" => 50,
|
||||
"doHardBreaks" => 60,
|
||||
);
|
||||
|
||||
protected function runSpanGamut($text) {
|
||||
#
|
||||
# Run span gamut tranformations.
|
||||
#
|
||||
foreach ($this->span_gamut as $method => $priority) {
|
||||
$text = $this->$method($text);
|
||||
}
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function doHardBreaks($text) {
|
||||
# Do hard breaks:
|
||||
return preg_replace_callback('/ {2,}\n/',
|
||||
array($this, '_doHardBreaks_callback'), $text);
|
||||
}
|
||||
protected function _doHardBreaks_callback($matches) {
|
||||
return $this->hashPart("<br$this->empty_element_suffix\n");
|
||||
}
|
||||
|
||||
|
||||
protected function doAnchors($text) {
|
||||
#
|
||||
# Turn Markdown link shortcuts into XHTML <a> tags.
|
||||
#
|
||||
if ($this->in_anchor) return $text;
|
||||
$this->in_anchor = true;
|
||||
|
||||
#
|
||||
# First, handle reference-style links: [link text] [id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, inline-style links: [link text](url "optional title")
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(.+?)> # href = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # href = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # Title = $7
|
||||
\6 # matching quote
|
||||
[ \n]* # ignore any spaces/tabs between closing quote and )
|
||||
)? # title is optional
|
||||
\)
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_inline_callback'), $text);
|
||||
|
||||
#
|
||||
# Last, handle reference-style shortcuts: [link text]
|
||||
# These must come last in case you've also got [link text][1]
|
||||
# or [link text](/foo)
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
([^\[\]]+) # link text = $2; can\'t contain [ or ]
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
$this->in_anchor = false;
|
||||
return $text;
|
||||
}
|
||||
protected function _doAnchors_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $matches[2];
|
||||
$link_id =& $matches[3];
|
||||
|
||||
if ($link_id == "") {
|
||||
# for shortcut links like [this][] or [this].
|
||||
$link_id = $link_text;
|
||||
}
|
||||
|
||||
# lower-case and turn embedded newlines into spaces
|
||||
$link_id = strtolower($link_id);
|
||||
$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
|
||||
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->urls[$link_id];
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if ( isset( $this->titles[$link_id] ) ) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
$result = $whole_match;
|
||||
}
|
||||
return $result;
|
||||
}
|
||||
protected function _doAnchors_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $this->runSpanGamut($matches[2]);
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
|
||||
// if the URL was of the form <s p a c e s> it got caught by the HTML
|
||||
// tag parser and hashed. Need to reverse the process before using the URL.
|
||||
$unhashed = $this->unhash($url);
|
||||
if ($unhashed != $url)
|
||||
$url = preg_replace('/^<(.*)>$/', '\1', $unhashed);
|
||||
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
protected function doImages($text) {
|
||||
#
|
||||
# Turn Markdown image shortcuts into <img> tags.
|
||||
#
|
||||
#
|
||||
# First, handle reference-style labeled images: ![alt text][id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doImages_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, handle inline images: 
|
||||
# Don't forget: encode * and _
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
\s? # One optional whitespace character
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(\S*)> # src url = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # src url = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # title = $7
|
||||
\6 # matching quote
|
||||
[ \n]*
|
||||
)? # title is optional
|
||||
\)
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doImages_inline_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doImages_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$link_id = strtolower($matches[3]);
|
||||
|
||||
if ($link_id == "") {
|
||||
$link_id = strtolower($alt_text); # for shortcut links like ![this][].
|
||||
}
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->encodeURLAttribute($this->urls[$link_id]);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($this->titles[$link_id])) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
$result .= $this->empty_element_suffix;
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
# If there's no such link ID, leave intact:
|
||||
$result = $whole_match;
|
||||
}
|
||||
|
||||
return $result;
|
||||
}
|
||||
protected function _doImages_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\""; # $title already quoted
|
||||
}
|
||||
$result .= $this->empty_element_suffix;
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
protected function doHeaders($text) {
|
||||
# Setext-style headers:
|
||||
# Header 1
|
||||
# ========
|
||||
#
|
||||
# Header 2
|
||||
# --------
|
||||
#
|
||||
$text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
|
||||
array($this, '_doHeaders_callback_setext'), $text);
|
||||
|
||||
# atx-style headers:
|
||||
# # Header 1
|
||||
# ## Header 2
|
||||
# ## Header 2 with closing hashes ##
|
||||
# ...
|
||||
# ###### Header 6
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
^(\#{1,6}) # $1 = string of #\'s
|
||||
[ ]*
|
||||
(.+?) # $2 = Header text
|
||||
[ ]*
|
||||
\#* # optional closing #\'s (not counted)
|
||||
\n+
|
||||
}xm',
|
||||
array($this, '_doHeaders_callback_atx'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doHeaders_callback_setext($matches) {
|
||||
# Terrible hack to check we haven't found an empty list item.
|
||||
if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
|
||||
return $matches[0];
|
||||
|
||||
$level = $matches[2]{0} == '=' ? 1 : 2;
|
||||
$block = "<h$level>".$this->runSpanGamut($matches[1])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
protected function _doHeaders_callback_atx($matches) {
|
||||
$level = strlen($matches[1]);
|
||||
$block = "<h$level>".$this->runSpanGamut($matches[2])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
protected function doLists($text) {
|
||||
#
|
||||
# Form HTML ordered (numbered) and unordered (bulleted) lists.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$marker_ul_re = '[*+-]';
|
||||
$marker_ol_re = '\d+[\.]';
|
||||
|
||||
$markers_relist = array(
|
||||
$marker_ul_re => $marker_ol_re,
|
||||
$marker_ol_re => $marker_ul_re,
|
||||
);
|
||||
|
||||
foreach ($markers_relist as $marker_re => $other_marker_re) {
|
||||
# Re-usable pattern to match any entirel ul or ol list:
|
||||
$whole_list_re = '
|
||||
( # $1 = whole list
|
||||
( # $2
|
||||
([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
|
||||
('.$marker_re.') # $4 = first list item marker
|
||||
[ ]+
|
||||
)
|
||||
(?s:.+?)
|
||||
( # $5
|
||||
\z
|
||||
|
|
||||
\n{2,}
|
||||
(?=\S)
|
||||
(?! # Negative lookahead for another list item marker
|
||||
[ ]*
|
||||
'.$marker_re.'[ ]+
|
||||
)
|
||||
|
|
||||
(?= # Lookahead for another kind of list
|
||||
\n
|
||||
\3 # Must have the same indentation
|
||||
'.$other_marker_re.'[ ]+
|
||||
)
|
||||
)
|
||||
)
|
||||
'; // mx
|
||||
|
||||
# We use a different prefix before nested lists than top-level lists.
|
||||
# See extended comment in _ProcessListItems().
|
||||
|
||||
if ($this->list_level) {
|
||||
$text = preg_replace_callback('{
|
||||
^
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array($this, '_doLists_callback'), $text);
|
||||
}
|
||||
else {
|
||||
$text = preg_replace_callback('{
|
||||
(?:(?<=\n)\n|\A\n?) # Must eat the newline
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array($this, '_doLists_callback'), $text);
|
||||
}
|
||||
}
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doLists_callback($matches) {
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$marker_ul_re = '[*+-]';
|
||||
$marker_ol_re = '\d+[\.]';
|
||||
$marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
|
||||
|
||||
$list = $matches[1];
|
||||
$list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
|
||||
|
||||
$marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
|
||||
|
||||
$list .= "\n";
|
||||
$result = $this->processListItems($list, $marker_any_re);
|
||||
|
||||
$result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>");
|
||||
return "\n". $result ."\n\n";
|
||||
}
|
||||
|
||||
protected $list_level = 0;
|
||||
|
||||
protected function processListItems($list_str, $marker_any_re) {
|
||||
#
|
||||
# Process the contents of a single ordered or unordered list, splitting it
|
||||
# into individual list items.
|
||||
#
|
||||
# The $this->list_level global keeps track of when we're inside a list.
|
||||
# Each time we enter a list, we increment it; when we leave a list,
|
||||
# we decrement. If it's zero, we're not in a list anymore.
|
||||
#
|
||||
# We do this because when we're not inside a list, we want to treat
|
||||
# something like this:
|
||||
#
|
||||
# I recommend upgrading to version
|
||||
# 8. Oops, now this line is treated
|
||||
# as a sub-list.
|
||||
#
|
||||
# As a single paragraph, despite the fact that the second line starts
|
||||
# with a digit-period-space sequence.
|
||||
#
|
||||
# Whereas when we're inside a list (or sub-list), that line will be
|
||||
# treated as the start of a sub-list. What a kludge, huh? This is
|
||||
# an aspect of Markdown's syntax that's hard to parse perfectly
|
||||
# without resorting to mind-reading. Perhaps the solution is to
|
||||
# change the syntax rules such that sub-lists must start with a
|
||||
# starting cardinal number; e.g. "1." or "a.".
|
||||
|
||||
$this->list_level++;
|
||||
|
||||
# trim trailing blank lines:
|
||||
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
|
||||
|
||||
$list_str = preg_replace_callback('{
|
||||
(\n)? # leading line = $1
|
||||
(^[ ]*) # leading whitespace = $2
|
||||
('.$marker_any_re.' # list marker and space = $3
|
||||
(?:[ ]+|(?=\n)) # space only required if item is not empty
|
||||
)
|
||||
((?s:.*?)) # list item text = $4
|
||||
(?:(\n+(?=\n))|\n) # tailing blank line = $5
|
||||
(?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n))))
|
||||
}xm',
|
||||
array($this, '_processListItems_callback'), $list_str);
|
||||
|
||||
$this->list_level--;
|
||||
return $list_str;
|
||||
}
|
||||
protected function _processListItems_callback($matches) {
|
||||
$item = $matches[4];
|
||||
$leading_line =& $matches[1];
|
||||
$leading_space =& $matches[2];
|
||||
$marker_space = $matches[3];
|
||||
$tailing_blank_line =& $matches[5];
|
||||
|
||||
if ($leading_line || $tailing_blank_line ||
|
||||
preg_match('/\n{2,}/', $item))
|
||||
{
|
||||
# Replace marker with the appropriate whitespace indentation
|
||||
$item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
|
||||
$item = $this->runBlockGamut($this->outdent($item)."\n");
|
||||
}
|
||||
else {
|
||||
# Recursion for sub-lists:
|
||||
$item = $this->doLists($this->outdent($item));
|
||||
$item = preg_replace('/\n+$/', '', $item);
|
||||
$item = $this->runSpanGamut($item);
|
||||
}
|
||||
|
||||
return "<li>" . $item . "</li>\n";
|
||||
}
|
||||
|
||||
|
||||
protected function doCodeBlocks($text) {
|
||||
#
|
||||
# Process Markdown `<pre><code>` blocks.
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
(?:\n\n|\A\n?)
|
||||
( # $1 = the code block -- one or more lines, starting with a space/tab
|
||||
(?>
|
||||
[ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces
|
||||
.*\n+
|
||||
)+
|
||||
)
|
||||
((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
|
||||
}xm',
|
||||
array($this, '_doCodeBlocks_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doCodeBlocks_callback($matches) {
|
||||
$codeblock = $matches[1];
|
||||
|
||||
$codeblock = $this->outdent($codeblock);
|
||||
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
|
||||
|
||||
# trim leading newlines and trailing newlines
|
||||
$codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
|
||||
|
||||
$codeblock = "<pre><code>$codeblock\n</code></pre>";
|
||||
return "\n\n".$this->hashBlock($codeblock)."\n\n";
|
||||
}
|
||||
|
||||
|
||||
protected function makeCodeSpan($code) {
|
||||
#
|
||||
# Create a code span markup for $code. Called from handleSpanToken.
|
||||
#
|
||||
$code = htmlspecialchars(trim($code), ENT_NOQUOTES);
|
||||
return $this->hashPart("<code>$code</code>");
|
||||
}
|
||||
|
||||
|
||||
protected $em_relist = array(
|
||||
'' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?![\.,:;]?\s)',
|
||||
'*' => '(?<![\s*])\*(?!\*)',
|
||||
'_' => '(?<![\s_])_(?!_)',
|
||||
);
|
||||
protected $strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?![\.,:;]?\s)',
|
||||
'**' => '(?<![\s*])\*\*(?!\*)',
|
||||
'__' => '(?<![\s_])__(?!_)',
|
||||
);
|
||||
protected $em_strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?![\.,:;]?\s)',
|
||||
'***' => '(?<![\s*])\*\*\*(?!\*)',
|
||||
'___' => '(?<![\s_])___(?!_)',
|
||||
);
|
||||
protected $em_strong_prepared_relist;
|
||||
|
||||
protected function prepareItalicsAndBold() {
|
||||
#
|
||||
# Prepare regular expressions for searching emphasis tokens in any
|
||||
# context.
|
||||
#
|
||||
foreach ($this->em_relist as $em => $em_re) {
|
||||
foreach ($this->strong_relist as $strong => $strong_re) {
|
||||
# Construct list of allowed token expressions.
|
||||
$token_relist = array();
|
||||
if (isset($this->em_strong_relist["$em$strong"])) {
|
||||
$token_relist[] = $this->em_strong_relist["$em$strong"];
|
||||
}
|
||||
$token_relist[] = $em_re;
|
||||
$token_relist[] = $strong_re;
|
||||
|
||||
# Construct master expression from list.
|
||||
$token_re = '{('. implode('|', $token_relist) .')}';
|
||||
$this->em_strong_prepared_relist["$em$strong"] = $token_re;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
protected function doItalicsAndBold($text) {
|
||||
$token_stack = array('');
|
||||
$text_stack = array('');
|
||||
$em = '';
|
||||
$strong = '';
|
||||
$tree_char_em = false;
|
||||
|
||||
while (1) {
|
||||
#
|
||||
# Get prepared regular expression for seraching emphasis tokens
|
||||
# in current context.
|
||||
#
|
||||
$token_re = $this->em_strong_prepared_relist["$em$strong"];
|
||||
|
||||
#
|
||||
# Each loop iteration search for the next emphasis token.
|
||||
# Each token is then passed to handleSpanToken.
|
||||
#
|
||||
$parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
$text_stack[0] .= $parts[0];
|
||||
$token =& $parts[1];
|
||||
$text =& $parts[2];
|
||||
|
||||
if (empty($token)) {
|
||||
# Reached end of text span: empty stack without emitting.
|
||||
# any more emphasis.
|
||||
while ($token_stack[0]) {
|
||||
$text_stack[1] .= array_shift($token_stack);
|
||||
$text_stack[0] .= array_shift($text_stack);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
$token_len = strlen($token);
|
||||
if ($tree_char_em) {
|
||||
# Reached closing marker while inside a three-char emphasis.
|
||||
if ($token_len == 3) {
|
||||
# Three-char closing marker, close em and strong.
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<strong><em>$span</em></strong>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$em = '';
|
||||
$strong = '';
|
||||
} else {
|
||||
# Other closing marker: close one em or strong and
|
||||
# change current token state to match the other
|
||||
$token_stack[0] = str_repeat($token{0}, 3-$token_len);
|
||||
$tag = $token_len == 2 ? "strong" : "em";
|
||||
$span = $text_stack[0];
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<$tag>$span</$tag>";
|
||||
$text_stack[0] = $this->hashPart($span);
|
||||
$$tag = ''; # $$tag stands for $em or $strong
|
||||
}
|
||||
$tree_char_em = false;
|
||||
} else if ($token_len == 3) {
|
||||
if ($em) {
|
||||
# Reached closing marker for both em and strong.
|
||||
# Closing strong marker:
|
||||
for ($i = 0; $i < 2; ++$i) {
|
||||
$shifted_token = array_shift($token_stack);
|
||||
$tag = strlen($shifted_token) == 2 ? "strong" : "em";
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<$tag>$span</$tag>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$$tag = ''; # $$tag stands for $em or $strong
|
||||
}
|
||||
} else {
|
||||
# Reached opening three-char emphasis marker. Push on token
|
||||
# stack; will be handled by the special condition above.
|
||||
$em = $token{0};
|
||||
$strong = "$em$em";
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$tree_char_em = true;
|
||||
}
|
||||
} else if ($token_len == 2) {
|
||||
if ($strong) {
|
||||
# Unwind any dangling emphasis marker:
|
||||
if (strlen($token_stack[0]) == 1) {
|
||||
$text_stack[1] .= array_shift($token_stack);
|
||||
$text_stack[0] .= array_shift($text_stack);
|
||||
}
|
||||
# Closing strong marker:
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<strong>$span</strong>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$strong = '';
|
||||
} else {
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$strong = $token;
|
||||
}
|
||||
} else {
|
||||
# Here $token_len == 1
|
||||
if ($em) {
|
||||
if (strlen($token_stack[0]) == 1) {
|
||||
# Closing emphasis marker:
|
||||
array_shift($token_stack);
|
||||
$span = array_shift($text_stack);
|
||||
$span = $this->runSpanGamut($span);
|
||||
$span = "<em>$span</em>";
|
||||
$text_stack[0] .= $this->hashPart($span);
|
||||
$em = '';
|
||||
} else {
|
||||
$text_stack[0] .= $token;
|
||||
}
|
||||
} else {
|
||||
array_unshift($token_stack, $token);
|
||||
array_unshift($text_stack, '');
|
||||
$em = $token;
|
||||
}
|
||||
}
|
||||
}
|
||||
return $text_stack[0];
|
||||
}
|
||||
|
||||
|
||||
protected function doBlockQuotes($text) {
|
||||
$text = preg_replace_callback('/
|
||||
( # Wrap whole match in $1
|
||||
(?>
|
||||
^[ ]*>[ ]? # ">" at the start of a line
|
||||
.+\n # rest of the first line
|
||||
(.+\n)* # subsequent consecutive lines
|
||||
\n* # blanks
|
||||
)+
|
||||
)
|
||||
/xm',
|
||||
array($this, '_doBlockQuotes_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doBlockQuotes_callback($matches) {
|
||||
$bq = $matches[1];
|
||||
# trim one level of quoting - trim whitespace-only lines
|
||||
$bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
|
||||
$bq = $this->runBlockGamut($bq); # recurse
|
||||
|
||||
$bq = preg_replace('/^/m', " ", $bq);
|
||||
# These leading spaces cause problem with <pre> content,
|
||||
# so we need to fix that:
|
||||
$bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx',
|
||||
array($this, '_doBlockQuotes_callback2'), $bq);
|
||||
|
||||
return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
|
||||
}
|
||||
protected function _doBlockQuotes_callback2($matches) {
|
||||
$pre = $matches[1];
|
||||
$pre = preg_replace('/^ /m', '', $pre);
|
||||
return $pre;
|
||||
}
|
||||
|
||||
|
||||
protected function formParagraphs($text) {
|
||||
#
|
||||
# Params:
|
||||
# $text - string to process with html <p> tags
|
||||
#
|
||||
# Strip leading and trailing lines:
|
||||
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
|
||||
|
||||
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
|
||||
|
||||
#
|
||||
# Wrap <p> tags and unhashify HTML blocks
|
||||
#
|
||||
foreach ($grafs as $key => $value) {
|
||||
if (!preg_match('/^B\x1A[0-9]+B$/', $value)) {
|
||||
# Is a paragraph.
|
||||
$value = $this->runSpanGamut($value);
|
||||
$value = preg_replace('/^([ ]*)/', "<p>", $value);
|
||||
$value .= "</p>";
|
||||
$grafs[$key] = $this->unhash($value);
|
||||
}
|
||||
else {
|
||||
# Is a block.
|
||||
# Modify elements of @grafs in-place...
|
||||
$graf = $value;
|
||||
$block = $this->html_hashes[$graf];
|
||||
$graf = $block;
|
||||
// if (preg_match('{
|
||||
// \A
|
||||
// ( # $1 = <div> tag
|
||||
// <div \s+
|
||||
// [^>]*
|
||||
// \b
|
||||
// markdown\s*=\s* ([\'"]) # $2 = attr quote char
|
||||
// 1
|
||||
// \2
|
||||
// [^>]*
|
||||
// >
|
||||
// )
|
||||
// ( # $3 = contents
|
||||
// .*
|
||||
// )
|
||||
// (</div>) # $4 = closing tag
|
||||
// \z
|
||||
// }xs', $block, $matches))
|
||||
// {
|
||||
// list(, $div_open, , $div_content, $div_close) = $matches;
|
||||
//
|
||||
// # We can't call Markdown(), because that resets the hash;
|
||||
// # that initialization code should be pulled into its own sub, though.
|
||||
// $div_content = $this->hashHTMLBlocks($div_content);
|
||||
//
|
||||
// # Run document gamut methods on the content.
|
||||
// foreach ($this->document_gamut as $method => $priority) {
|
||||
// $div_content = $this->$method($div_content);
|
||||
// }
|
||||
//
|
||||
// $div_open = preg_replace(
|
||||
// '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open);
|
||||
//
|
||||
// $graf = $div_open . "\n" . $div_content . "\n" . $div_close;
|
||||
// }
|
||||
$grafs[$key] = $graf;
|
||||
}
|
||||
}
|
||||
|
||||
return implode("\n\n", $grafs);
|
||||
}
|
||||
|
||||
|
||||
protected function encodeAttribute($text) {
|
||||
#
|
||||
# Encode text for a double-quoted HTML attribute. This function
|
||||
# is *not* suitable for attributes enclosed in single quotes.
|
||||
#
|
||||
$text = $this->encodeAmpsAndAngles($text);
|
||||
$text = str_replace('"', '"', $text);
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function encodeURLAttribute($url, &$text = null) {
|
||||
#
|
||||
# Encode text for a double-quoted HTML attribute containing a URL,
|
||||
# applying the URL filter if set. Also generates the textual
|
||||
# representation for the URL (removing mailto: or tel:) storing it in $text.
|
||||
# This function is *not* suitable for attributes enclosed in single quotes.
|
||||
#
|
||||
if ($this->url_filter_func)
|
||||
$url = call_user_func($this->url_filter_func, $url);
|
||||
|
||||
if (preg_match('{^mailto:}i', $url))
|
||||
$url = $this->encodeEntityObfuscatedAttribute($url, $text, 7);
|
||||
else if (preg_match('{^tel:}i', $url))
|
||||
{
|
||||
$url = $this->encodeAttribute($url);
|
||||
$text = substr($url, 4);
|
||||
}
|
||||
else
|
||||
{
|
||||
$url = $this->encodeAttribute($url);
|
||||
$text = $url;
|
||||
}
|
||||
|
||||
return $url;
|
||||
}
|
||||
|
||||
|
||||
protected function encodeAmpsAndAngles($text) {
|
||||
#
|
||||
# Smart processing for ampersands and angle brackets that need to
|
||||
# be encoded. Valid character entities are left alone unless the
|
||||
# no-entities mode is set.
|
||||
#
|
||||
if ($this->no_entities) {
|
||||
$text = str_replace('&', '&', $text);
|
||||
} else {
|
||||
# Ampersand-encoding based entirely on Nat Irons's Amputator
|
||||
# MT plugin: <http://bumppo.net/projects/amputator/>
|
||||
$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
|
||||
'&', $text);
|
||||
}
|
||||
# Encode remaining <'s
|
||||
$text = str_replace('<', '<', $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function doAutoLinks($text) {
|
||||
$text = preg_replace_callback('{<((https?|ftp|dict|tel):[^\'">\s]+)>}i',
|
||||
array($this, '_doAutoLinks_url_callback'), $text);
|
||||
|
||||
# Email addresses: <address@domain.foo>
|
||||
$text = preg_replace_callback('{
|
||||
<
|
||||
(?:mailto:)?
|
||||
(
|
||||
(?:
|
||||
[-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+
|
||||
|
|
||||
".*?"
|
||||
)
|
||||
\@
|
||||
(?:
|
||||
[-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
|
||||
|
|
||||
\[[\d.a-fA-F:]+\] # IPv4 & IPv6
|
||||
)
|
||||
)
|
||||
>
|
||||
}xi',
|
||||
array($this, '_doAutoLinks_email_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doAutoLinks_url_callback($matches) {
|
||||
$url = $this->encodeURLAttribute($matches[1], $text);
|
||||
$link = "<a href=\"$url\">$text</a>";
|
||||
return $this->hashPart($link);
|
||||
}
|
||||
protected function _doAutoLinks_email_callback($matches) {
|
||||
$addr = $matches[1];
|
||||
$url = $this->encodeURLAttribute("mailto:$addr", $text);
|
||||
$link = "<a href=\"$url\">$text</a>";
|
||||
return $this->hashPart($link);
|
||||
}
|
||||
|
||||
|
||||
protected function encodeEntityObfuscatedAttribute($text, &$tail = null, $head_length = 0) {
|
||||
#
|
||||
# Input: some text to obfuscate, e.g. "mailto:foo@example.com"
|
||||
#
|
||||
# Output: the same text but with most characters encoded as either a
|
||||
# decimal or hex entity, in the hopes of foiling most address
|
||||
# harvesting spam bots. E.g.:
|
||||
#
|
||||
# mailto:foo
|
||||
# @example.co
|
||||
# m
|
||||
#
|
||||
# Note: the additional output $tail is assigned the same value as the
|
||||
# ouput, minus the number of characters specified by $head_length.
|
||||
#
|
||||
# Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
|
||||
# With some optimizations by Milian Wolff. Forced encoding of HTML
|
||||
# attribute special characters by Allan Odgaard.
|
||||
#
|
||||
if ($text == "") return $tail = "";
|
||||
|
||||
$chars = preg_split('/(?<!^)(?!$)/', $text);
|
||||
$seed = (int)abs(crc32($text) / strlen($text)); # Deterministic seed.
|
||||
|
||||
foreach ($chars as $key => $char) {
|
||||
$ord = ord($char);
|
||||
# Ignore non-ascii chars.
|
||||
if ($ord < 128) {
|
||||
$r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
|
||||
# roughly 10% raw, 45% hex, 45% dec
|
||||
# '@' *must* be encoded. I insist.
|
||||
# '"' and '>' have to be encoded inside the attribute
|
||||
if ($r > 90 && strpos('@"&>', $char) === false) /* do nothing */;
|
||||
else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
|
||||
else $chars[$key] = '&#'.$ord.';';
|
||||
}
|
||||
}
|
||||
|
||||
$text = implode('', $chars);
|
||||
$tail = $head_length ? implode('', array_slice($chars, $head_length)) : $text;
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function parseSpan($str) {
|
||||
#
|
||||
# Take the string $str and parse it into tokens, hashing embeded HTML,
|
||||
# escaped characters and handling code spans.
|
||||
#
|
||||
$output = '';
|
||||
|
||||
$span_re = '{
|
||||
(
|
||||
\\\\'.$this->escape_chars_re.'
|
||||
|
|
||||
(?<![`\\\\])
|
||||
`+ # code span marker
|
||||
'.( $this->no_markup ? '' : '
|
||||
|
|
||||
<!-- .*? --> # comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # processing instruction
|
||||
|
|
||||
<[!$]?[-a-zA-Z0-9:_]+ # regular tags
|
||||
(?>
|
||||
\s
|
||||
(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
|
||||
)?
|
||||
>
|
||||
|
|
||||
<[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag
|
||||
|
|
||||
</[-a-zA-Z0-9:_]+\s*> # closing tag
|
||||
').'
|
||||
)
|
||||
}xs';
|
||||
|
||||
while (1) {
|
||||
#
|
||||
# Each loop iteration seach for either the next tag, the next
|
||||
# openning code span marker, or the next escaped character.
|
||||
# Each token is then passed to handleSpanToken.
|
||||
#
|
||||
$parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
# Create token from text preceding tag.
|
||||
if ($parts[0] != "") {
|
||||
$output .= $parts[0];
|
||||
}
|
||||
|
||||
# Check if we reach the end.
|
||||
if (isset($parts[1])) {
|
||||
$output .= $this->handleSpanToken($parts[1], $parts[2]);
|
||||
$str = $parts[2];
|
||||
}
|
||||
else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return $output;
|
||||
}
|
||||
|
||||
|
||||
protected function handleSpanToken($token, &$str) {
|
||||
#
|
||||
# Handle $token provided by parseSpan by determining its nature and
|
||||
# returning the corresponding value that should replace it.
|
||||
#
|
||||
switch ($token{0}) {
|
||||
case "\\":
|
||||
return $this->hashPart("&#". ord($token{1}). ";");
|
||||
case "`":
|
||||
# Search for end marker in remaining text.
|
||||
if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
|
||||
$str, $matches))
|
||||
{
|
||||
$str = $matches[2];
|
||||
$codespan = $this->makeCodeSpan($matches[1]);
|
||||
return $this->hashPart($codespan);
|
||||
}
|
||||
return $token; // return as text since no ending marker found.
|
||||
default:
|
||||
return $this->hashPart($token);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
protected function outdent($text) {
|
||||
#
|
||||
# Remove one level of line-leading tabs or spaces
|
||||
#
|
||||
return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
|
||||
}
|
||||
|
||||
|
||||
# String length function for detab. `_initDetab` will create a function to
|
||||
# hanlde UTF-8 if the default function does not exist.
|
||||
protected $utf8_strlen = 'mb_strlen';
|
||||
|
||||
protected function detab($text) {
|
||||
#
|
||||
# Replace tabs with the appropriate amount of space.
|
||||
#
|
||||
# For each line we separate the line in blocks delemited by
|
||||
# tab characters. Then we reconstruct every line by adding the
|
||||
# appropriate number of space between each blocks.
|
||||
|
||||
$text = preg_replace_callback('/^.*\t.*$/m',
|
||||
array($this, '_detab_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _detab_callback($matches) {
|
||||
$line = $matches[0];
|
||||
$strlen = $this->utf8_strlen; # strlen function for UTF-8.
|
||||
|
||||
# Split in blocks.
|
||||
$blocks = explode("\t", $line);
|
||||
# Add each blocks to the line.
|
||||
$line = $blocks[0];
|
||||
unset($blocks[0]); # Do not add first block twice.
|
||||
foreach ($blocks as $block) {
|
||||
# Calculate amount of space, insert spaces, insert block.
|
||||
$amount = $this->tab_width -
|
||||
$strlen($line, 'UTF-8') % $this->tab_width;
|
||||
$line .= str_repeat(" ", $amount) . $block;
|
||||
}
|
||||
return $line;
|
||||
}
|
||||
protected function _initDetab() {
|
||||
#
|
||||
# Check for the availability of the function in the `utf8_strlen` property
|
||||
# (initially `mb_strlen`). If the function is not available, create a
|
||||
# function that will loosely count the number of UTF-8 characters with a
|
||||
# regular expression.
|
||||
#
|
||||
if (function_exists($this->utf8_strlen)) return;
|
||||
$this->utf8_strlen = create_function('$text', 'return preg_match_all(
|
||||
"/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
|
||||
$text, $m);');
|
||||
}
|
||||
|
||||
|
||||
protected function unhash($text) {
|
||||
#
|
||||
# Swap back in all the tags hashed by _HashHTMLBlocks.
|
||||
#
|
||||
return preg_replace_callback('/(.)\x1A[0-9]+\1/',
|
||||
array($this, '_unhash_callback'), $text);
|
||||
}
|
||||
protected function _unhash_callback($matches) {
|
||||
return $this->html_hashes[$matches[0]];
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
#
|
||||
# Temporary Markdown Extra Parser Implementation Class
|
||||
#
|
||||
# NOTE: DON'T USE THIS CLASS
|
||||
# Currently the implementation of of Extra resides here in this temporary class.
|
||||
# This makes it easier to propagate the changes between the three different
|
||||
# packaging styles of PHP Markdown. When this issue is resolved, this
|
||||
# MarkdownExtra_TmpImpl class here will disappear and \Michelf\MarkdownExtra
|
||||
# will contain the code. So please use \Michelf\MarkdownExtra and ignore this
|
||||
# one.
|
||||
#
|
||||
|
||||
abstract class _MarkdownExtra_TmpImpl extends \Michelf\Markdown {
|
||||
|
||||
### Configuration Variables ###
|
||||
|
||||
# Prefix for footnote ids.
|
||||
public $fn_id_prefix = "";
|
||||
|
||||
# Optional title attribute for footnote links and backlinks.
|
||||
public $fn_link_title = "";
|
||||
public $fn_backlink_title = "";
|
||||
|
||||
# Optional class attribute for footnote links and backlinks.
|
||||
public $fn_link_class = "footnote-ref";
|
||||
public $fn_backlink_class = "footnote-backref";
|
||||
|
||||
# Class name for table cell alignment (%% replaced left/center/right)
|
||||
# For instance: 'go-%%' becomes 'go-left' or 'go-right' or 'go-center'
|
||||
# If empty, the align attribute is used instead of a class name.
|
||||
public $table_align_class_tmpl = '';
|
||||
|
||||
# Optional class prefix for fenced code block.
|
||||
public $code_class_prefix = "";
|
||||
# Class attribute for code blocks goes on the `code` tag;
|
||||
# setting this to true will put attributes on the `pre` tag instead.
|
||||
public $code_attr_on_pre = false;
|
||||
|
||||
# Predefined abbreviations.
|
||||
public $predef_abbr = array();
|
||||
|
||||
|
||||
### Parser Implementation ###
|
||||
|
||||
public function __construct() {
|
||||
#
|
||||
# Constructor function. Initialize the parser object.
|
||||
#
|
||||
# Add extra escapable characters before parent constructor
|
||||
# initialize the table.
|
||||
$this->escape_chars .= ':|';
|
||||
|
||||
# Insert extra document, block, and span transformations.
|
||||
# Parent constructor will do the sorting.
|
||||
$this->document_gamut += array(
|
||||
"doFencedCodeBlocks" => 5,
|
||||
"stripFootnotes" => 15,
|
||||
"stripAbbreviations" => 25,
|
||||
"appendFootnotes" => 50,
|
||||
);
|
||||
$this->block_gamut += array(
|
||||
"doFencedCodeBlocks" => 5,
|
||||
"doTables" => 15,
|
||||
"doDefLists" => 45,
|
||||
);
|
||||
$this->span_gamut += array(
|
||||
"doFootnotes" => 5,
|
||||
"doAbbreviations" => 70,
|
||||
);
|
||||
|
||||
parent::__construct();
|
||||
}
|
||||
|
||||
|
||||
# Extra variables used during extra transformations.
|
||||
protected $footnotes = array();
|
||||
protected $footnotes_ordered = array();
|
||||
protected $footnotes_ref_count = array();
|
||||
protected $footnotes_numbers = array();
|
||||
protected $abbr_desciptions = array();
|
||||
protected $abbr_word_re = '';
|
||||
|
||||
# Give the current footnote number.
|
||||
protected $footnote_counter = 1;
|
||||
|
||||
|
||||
protected function setup() {
|
||||
#
|
||||
# Setting up Extra-specific variables.
|
||||
#
|
||||
parent::setup();
|
||||
|
||||
$this->footnotes = array();
|
||||
$this->footnotes_ordered = array();
|
||||
$this->footnotes_ref_count = array();
|
||||
$this->footnotes_numbers = array();
|
||||
$this->abbr_desciptions = array();
|
||||
$this->abbr_word_re = '';
|
||||
$this->footnote_counter = 1;
|
||||
|
||||
foreach ($this->predef_abbr as $abbr_word => $abbr_desc) {
|
||||
if ($this->abbr_word_re)
|
||||
$this->abbr_word_re .= '|';
|
||||
$this->abbr_word_re .= preg_quote($abbr_word);
|
||||
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
|
||||
}
|
||||
}
|
||||
|
||||
protected function teardown() {
|
||||
#
|
||||
# Clearing Extra-specific variables.
|
||||
#
|
||||
$this->footnotes = array();
|
||||
$this->footnotes_ordered = array();
|
||||
$this->footnotes_ref_count = array();
|
||||
$this->footnotes_numbers = array();
|
||||
$this->abbr_desciptions = array();
|
||||
$this->abbr_word_re = '';
|
||||
|
||||
parent::teardown();
|
||||
}
|
||||
|
||||
|
||||
### Extra Attribute Parser ###
|
||||
|
||||
# Expression to use to catch attributes (includes the braces)
|
||||
protected $id_class_attr_catch_re = '\{((?:[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,})[ ]*\}';
|
||||
# Expression to use when parsing in a context when no capture is desired
|
||||
protected $id_class_attr_nocatch_re = '\{(?:[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,}[ ]*\}';
|
||||
|
||||
protected function doExtraAttributes($tag_name, $attr) {
|
||||
#
|
||||
# Parse attributes caught by the $this->id_class_attr_catch_re expression
|
||||
# and return the HTML-formatted list of attributes.
|
||||
#
|
||||
# Currently supported attributes are .class and #id.
|
||||
#
|
||||
if (empty($attr)) return "";
|
||||
|
||||
# Split on components
|
||||
preg_match_all('/[#.a-z][-_:a-zA-Z0-9=]+/', $attr, $matches);
|
||||
$elements = $matches[0];
|
||||
|
||||
# handle classes and ids (only first id taken into account)
|
||||
$classes = array();
|
||||
$attributes = array();
|
||||
$id = false;
|
||||
foreach ($elements as $element) {
|
||||
if ($element{0} == '.') {
|
||||
$classes[] = substr($element, 1);
|
||||
} else if ($element{0} == '#') {
|
||||
if ($id === false) $id = substr($element, 1);
|
||||
} else if (strpos($element, '=') > 0) {
|
||||
$parts = explode('=', $element, 2);
|
||||
$attributes[] = $parts[0] . '="' . $parts[1] . '"';
|
||||
}
|
||||
}
|
||||
|
||||
# compose attributes as string
|
||||
$attr_str = "";
|
||||
if (!empty($id)) {
|
||||
$attr_str .= ' id="'.$id.'"';
|
||||
}
|
||||
if (!empty($classes)) {
|
||||
$attr_str .= ' class="'.implode(" ", $classes).'"';
|
||||
}
|
||||
if (!$this->no_markup && !empty($attributes)) {
|
||||
$attr_str .= ' '.implode(" ", $attributes);
|
||||
}
|
||||
return $attr_str;
|
||||
}
|
||||
|
||||
|
||||
protected function stripLinkDefinitions($text) {
|
||||
#
|
||||
# Strips link definitions from text, stores the URLs and titles in
|
||||
# hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: ^[id]: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
|
||||
[ ]*
|
||||
\n? # maybe *one* newline
|
||||
[ ]*
|
||||
(?:
|
||||
<(.+?)> # url = $2
|
||||
|
|
||||
(\S+?) # url = $3
|
||||
)
|
||||
[ ]*
|
||||
\n? # maybe one newline
|
||||
[ ]*
|
||||
(?:
|
||||
(?<=\s) # lookbehind for whitespace
|
||||
["(]
|
||||
(.*?) # title = $4
|
||||
[")]
|
||||
[ ]*
|
||||
)? # title is optional
|
||||
(?:[ ]* '.$this->id_class_attr_catch_re.' )? # $5 = extra id & class attr
|
||||
(?:\n+|\Z)
|
||||
}xm',
|
||||
array($this, '_stripLinkDefinitions_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
protected function _stripLinkDefinitions_callback($matches) {
|
||||
$link_id = strtolower($matches[1]);
|
||||
$url = $matches[2] == '' ? $matches[3] : $matches[2];
|
||||
$this->urls[$link_id] = $url;
|
||||
$this->titles[$link_id] =& $matches[4];
|
||||
$this->ref_attr[$link_id] = $this->doExtraAttributes("", $dummy =& $matches[5]);
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
### HTML Block Parser ###
|
||||
|
||||
# Tags that are always treated as block tags:
|
||||
protected $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption|figure';
|
||||
|
||||
# Tags treated as block tags only if the opening tag is alone on its line:
|
||||
protected $context_block_tags_re = 'script|noscript|style|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
|
||||
|
||||
# Tags where markdown="1" default to span mode:
|
||||
protected $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
|
||||
|
||||
# Tags which must not have their contents modified, no matter where
|
||||
# they appear:
|
||||
protected $clean_tags_re = 'script|style|math|svg';
|
||||
|
||||
# Tags that do not need to be closed.
|
||||
protected $auto_close_tags_re = 'hr|img|param|source|track';
|
||||
|
||||
|
||||
protected function hashHTMLBlocks($text) {
|
||||
#
|
||||
# Hashify HTML Blocks and "clean tags".
|
||||
#
|
||||
# We only want to do this for block-level HTML tags, such as headers,
|
||||
# lists, and tables. That's because we still want to wrap <p>s around
|
||||
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
|
||||
# phrase emphasis, and spans. The list of tags we're looking for is
|
||||
# hard-coded.
|
||||
#
|
||||
# This works by calling _HashHTMLBlocks_InMarkdown, which then calls
|
||||
# _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
|
||||
# attribute is found within a tag, _HashHTMLBlocks_InHTML calls back
|
||||
# _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
|
||||
# These two functions are calling each other. It's recursive!
|
||||
#
|
||||
if ($this->no_markup) return $text;
|
||||
|
||||
#
|
||||
# Call the HTML-in-Markdown hasher.
|
||||
#
|
||||
list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
|
||||
$enclosing_tag_re = '', $span = false)
|
||||
{
|
||||
#
|
||||
# Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
|
||||
#
|
||||
# * $indent is the number of space to be ignored when checking for code
|
||||
# blocks. This is important because if we don't take the indent into
|
||||
# account, something like this (which looks right) won't work as expected:
|
||||
#
|
||||
# <div>
|
||||
# <div markdown="1">
|
||||
# Hello World. <-- Is this a Markdown code block or text?
|
||||
# </div> <-- Is this a Markdown code block or a real tag?
|
||||
# <div>
|
||||
#
|
||||
# If you don't like this, just don't indent the tag on which
|
||||
# you apply the markdown="1" attribute.
|
||||
#
|
||||
# * If $enclosing_tag_re is not empty, stops at the first unmatched closing
|
||||
# tag with that name. Nested tags supported.
|
||||
#
|
||||
# * If $span is true, text inside must treated as span. So any double
|
||||
# newline will be replaced by a single newline so that it does not create
|
||||
# paragraphs.
|
||||
#
|
||||
# Returns an array of that form: ( processed text , remaining text )
|
||||
#
|
||||
if ($text === '') return array('', '');
|
||||
|
||||
# Regex to check for the presense of newlines around a block tag.
|
||||
$newline_before_re = '/(?:^\n?|\n\n)*$/';
|
||||
$newline_after_re =
|
||||
'{
|
||||
^ # Start of text following the tag.
|
||||
(?>[ ]*<!--.*?-->)? # Optional comment.
|
||||
[ ]*\n # Must be followed by newline.
|
||||
}xs';
|
||||
|
||||
# Regex to match any tag.
|
||||
$block_tag_re =
|
||||
'{
|
||||
( # $2: Capture whole tag.
|
||||
</? # Any opening or closing tag.
|
||||
(?> # Tag name.
|
||||
'.$this->block_tags_re.' |
|
||||
'.$this->context_block_tags_re.' |
|
||||
'.$this->clean_tags_re.' |
|
||||
(?!\s)'.$enclosing_tag_re.'
|
||||
)
|
||||
(?:
|
||||
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
|
||||
(?>
|
||||
".*?" | # Double quotes (can contain `>`)
|
||||
\'.*?\' | # Single quotes (can contain `>`)
|
||||
.+? # Anything but quotes and `>`.
|
||||
)*?
|
||||
)?
|
||||
> # End of tag.
|
||||
|
|
||||
<!-- .*? --> # HTML Comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # Processing instruction
|
||||
|
|
||||
<!\[CDATA\[.*?\]\]> # CData Block
|
||||
'. ( !$span ? ' # If not in span.
|
||||
|
|
||||
# Indented code block
|
||||
(?: ^[ ]*\n | ^ | \n[ ]*\n )
|
||||
[ ]{'.($indent+4).'}[^\n]* \n
|
||||
(?>
|
||||
(?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
|
||||
)*
|
||||
|
|
||||
# Fenced code block marker
|
||||
(?<= ^ | \n )
|
||||
[ ]{0,'.($indent+3).'}(?:~{3,}|`{3,})
|
||||
[ ]*
|
||||
(?:
|
||||
\.?[-_:a-zA-Z0-9]+ # standalone class name
|
||||
|
|
||||
'.$this->id_class_attr_nocatch_re.' # extra attributes
|
||||
)?
|
||||
[ ]*
|
||||
(?= \n )
|
||||
' : '' ). ' # End (if not is span).
|
||||
|
|
||||
# Code span marker
|
||||
# Note, this regex needs to go after backtick fenced
|
||||
# code blocks but it should also be kept outside of the
|
||||
# "if not in span" condition adding backticks to the parser
|
||||
`+
|
||||
)
|
||||
}xs';
|
||||
|
||||
|
||||
$depth = 0; # Current depth inside the tag tree.
|
||||
$parsed = ""; # Parsed text that will be returned.
|
||||
|
||||
#
|
||||
# Loop through every tag until we find the closing tag of the parent
|
||||
# or loop until reaching the end of text if no parent tag specified.
|
||||
#
|
||||
do {
|
||||
#
|
||||
# Split the text using the first $tag_match pattern found.
|
||||
# Text before pattern will be first in the array, text after
|
||||
# pattern will be at the end, and between will be any catches made
|
||||
# by the pattern.
|
||||
#
|
||||
$parts = preg_split($block_tag_re, $text, 2,
|
||||
PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
# If in Markdown span mode, add a empty-string span-level hash
|
||||
# after each newline to prevent triggering any block element.
|
||||
if ($span) {
|
||||
$void = $this->hashPart("", ':');
|
||||
$newline = "$void\n";
|
||||
$parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
|
||||
}
|
||||
|
||||
$parsed .= $parts[0]; # Text before current tag.
|
||||
|
||||
# If end of $text has been reached. Stop loop.
|
||||
if (count($parts) < 3) {
|
||||
$text = "";
|
||||
break;
|
||||
}
|
||||
|
||||
$tag = $parts[1]; # Tag to handle.
|
||||
$text = $parts[2]; # Remaining text after current tag.
|
||||
$tag_re = preg_quote($tag); # For use in a regular expression.
|
||||
|
||||
#
|
||||
# Check for: Fenced code block marker.
|
||||
# Note: need to recheck the whole tag to disambiguate backtick
|
||||
# fences from code spans
|
||||
#
|
||||
if (preg_match('{^\n?([ ]{0,'.($indent+3).'})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+|'.$this->id_class_attr_nocatch_re.')?[ ]*\n?$}', $tag, $capture)) {
|
||||
# Fenced code block marker: find matching end marker.
|
||||
$fence_indent = strlen($capture[1]); # use captured indent in re
|
||||
$fence_re = $capture[2]; # use captured fence in re
|
||||
if (preg_match('{^(?>.*\n)*?[ ]{'.($fence_indent).'}'.$fence_re.'[ ]*(?:\n|$)}', $text,
|
||||
$matches))
|
||||
{
|
||||
# End marker found: pass text unchanged until marker.
|
||||
$parsed .= $tag . $matches[0];
|
||||
$text = substr($text, strlen($matches[0]));
|
||||
}
|
||||
else {
|
||||
# No end marker: just skip it.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
}
|
||||
#
|
||||
# Check for: Indented code block.
|
||||
#
|
||||
else if ($tag{0} == "\n" || $tag{0} == " ") {
|
||||
# Indented code block: pass it unchanged, will be handled
|
||||
# later.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
#
|
||||
# Check for: Code span marker
|
||||
# Note: need to check this after backtick fenced code blocks
|
||||
#
|
||||
else if ($tag{0} == "`") {
|
||||
# Find corresponding end marker.
|
||||
$tag_re = preg_quote($tag);
|
||||
if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
|
||||
$text, $matches))
|
||||
{
|
||||
# End marker found: pass text unchanged until marker.
|
||||
$parsed .= $tag . $matches[0];
|
||||
$text = substr($text, strlen($matches[0]));
|
||||
}
|
||||
else {
|
||||
# Unmatched marker: just skip it.
|
||||
$parsed .= $tag;
|
||||
}
|
||||
}
|
||||
#
|
||||
# Check for: Opening Block level tag or
|
||||
# Opening Context Block tag (like ins and del)
|
||||
# used as a block tag (tag is alone on it's line).
|
||||
#
|
||||
else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) ||
|
||||
( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
|
||||
preg_match($newline_before_re, $parsed) &&
|
||||
preg_match($newline_after_re, $text) )
|
||||
)
|
||||
{
|
||||
# Need to parse tag and following text using the HTML parser.
|
||||
list($block_text, $text) =
|
||||
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
|
||||
|
||||
# Make sure it stays outside of any paragraph by adding newlines.
|
||||
$parsed .= "\n\n$block_text\n\n";
|
||||
}
|
||||
#
|
||||
# Check for: Clean tag (like script, math)
|
||||
# HTML Comments, processing instructions.
|
||||
#
|
||||
else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
|
||||
$tag{1} == '!' || $tag{1} == '?')
|
||||
{
|
||||
# Need to parse tag and following text using the HTML parser.
|
||||
# (don't check for markdown attribute)
|
||||
list($block_text, $text) =
|
||||
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
|
||||
|
||||
$parsed .= $block_text;
|
||||
}
|
||||
#
|
||||
# Check for: Tag with same name as enclosing tag.
|
||||
#
|
||||
else if ($enclosing_tag_re !== '' &&
|
||||
# Same name as enclosing tag.
|
||||
preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
|
||||
{
|
||||
#
|
||||
# Increase/decrease nested tag count.
|
||||
#
|
||||
if ($tag{1} == '/') $depth--;
|
||||
else if ($tag{strlen($tag)-2} != '/') $depth++;
|
||||
|
||||
if ($depth < 0) {
|
||||
#
|
||||
# Going out of parent element. Clean up and break so we
|
||||
# return to the calling function.
|
||||
#
|
||||
$text = $tag . $text;
|
||||
break;
|
||||
}
|
||||
|
||||
$parsed .= $tag;
|
||||
}
|
||||
else {
|
||||
$parsed .= $tag;
|
||||
}
|
||||
} while ($depth >= 0);
|
||||
|
||||
return array($parsed, $text);
|
||||
}
|
||||
protected function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
|
||||
#
|
||||
# Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
|
||||
#
|
||||
# * Calls $hash_method to convert any blocks.
|
||||
# * Stops when the first opening tag closes.
|
||||
# * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
|
||||
# (it is not inside clean tags)
|
||||
#
|
||||
# Returns an array of that form: ( processed text , remaining text )
|
||||
#
|
||||
if ($text === '') return array('', '');
|
||||
|
||||
# Regex to match `markdown` attribute inside of a tag.
|
||||
$markdown_attr_re = '
|
||||
{
|
||||
\s* # Eat whitespace before the `markdown` attribute
|
||||
markdown
|
||||
\s*=\s*
|
||||
(?>
|
||||
(["\']) # $1: quote delimiter
|
||||
(.*?) # $2: attribute value
|
||||
\1 # matching delimiter
|
||||
|
|
||||
([^\s>]*) # $3: unquoted attribute value
|
||||
)
|
||||
() # $4: make $3 always defined (avoid warnings)
|
||||
}xs';
|
||||
|
||||
# Regex to match any tag.
|
||||
$tag_re = '{
|
||||
( # $2: Capture whole tag.
|
||||
</? # Any opening or closing tag.
|
||||
[\w:$]+ # Tag name.
|
||||
(?:
|
||||
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
|
||||
(?>
|
||||
".*?" | # Double quotes (can contain `>`)
|
||||
\'.*?\' | # Single quotes (can contain `>`)
|
||||
.+? # Anything but quotes and `>`.
|
||||
)*?
|
||||
)?
|
||||
> # End of tag.
|
||||
|
|
||||
<!-- .*? --> # HTML Comment
|
||||
|
|
||||
<\?.*?\?> | <%.*?%> # Processing instruction
|
||||
|
|
||||
<!\[CDATA\[.*?\]\]> # CData Block
|
||||
)
|
||||
}xs';
|
||||
|
||||
$original_text = $text; # Save original text in case of faliure.
|
||||
|
||||
$depth = 0; # Current depth inside the tag tree.
|
||||
$block_text = ""; # Temporary text holder for current text.
|
||||
$parsed = ""; # Parsed text that will be returned.
|
||||
|
||||
#
|
||||
# Get the name of the starting tag.
|
||||
# (This pattern makes $base_tag_name_re safe without quoting.)
|
||||
#
|
||||
if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
|
||||
$base_tag_name_re = $matches[1];
|
||||
|
||||
#
|
||||
# Loop through every tag until we find the corresponding closing tag.
|
||||
#
|
||||
do {
|
||||
#
|
||||
# Split the text using the first $tag_match pattern found.
|
||||
# Text before pattern will be first in the array, text after
|
||||
# pattern will be at the end, and between will be any catches made
|
||||
# by the pattern.
|
||||
#
|
||||
$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
if (count($parts) < 3) {
|
||||
#
|
||||
# End of $text reached with unbalenced tag(s).
|
||||
# In that case, we return original text unchanged and pass the
|
||||
# first character as filtered to prevent an infinite loop in the
|
||||
# parent function.
|
||||
#
|
||||
return array($original_text{0}, substr($original_text, 1));
|
||||
}
|
||||
|
||||
$block_text .= $parts[0]; # Text before current tag.
|
||||
$tag = $parts[1]; # Tag to handle.
|
||||
$text = $parts[2]; # Remaining text after current tag.
|
||||
|
||||
#
|
||||
# Check for: Auto-close tag (like <hr/>)
|
||||
# Comments and Processing Instructions.
|
||||
#
|
||||
if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
|
||||
$tag{1} == '!' || $tag{1} == '?')
|
||||
{
|
||||
# Just add the tag to the block as if it was text.
|
||||
$block_text .= $tag;
|
||||
}
|
||||
else {
|
||||
#
|
||||
# Increase/decrease nested tag count. Only do so if
|
||||
# the tag's name match base tag's.
|
||||
#
|
||||
if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) {
|
||||
if ($tag{1} == '/') $depth--;
|
||||
else if ($tag{strlen($tag)-2} != '/') $depth++;
|
||||
}
|
||||
|
||||
#
|
||||
# Check for `markdown="1"` attribute and handle it.
|
||||
#
|
||||
if ($md_attr &&
|
||||
preg_match($markdown_attr_re, $tag, $attr_m) &&
|
||||
preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
|
||||
{
|
||||
# Remove `markdown` attribute from opening tag.
|
||||
$tag = preg_replace($markdown_attr_re, '', $tag);
|
||||
|
||||
# Check if text inside this tag must be parsed in span mode.
|
||||
$this->mode = $attr_m[2] . $attr_m[3];
|
||||
$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
|
||||
preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
|
||||
|
||||
# Calculate indent before tag.
|
||||
if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
|
||||
$strlen = $this->utf8_strlen;
|
||||
$indent = $strlen($matches[1], 'UTF-8');
|
||||
} else {
|
||||
$indent = 0;
|
||||
}
|
||||
|
||||
# End preceding block with this tag.
|
||||
$block_text .= $tag;
|
||||
$parsed .= $this->$hash_method($block_text);
|
||||
|
||||
# Get enclosing tag name for the ParseMarkdown function.
|
||||
# (This pattern makes $tag_name_re safe without quoting.)
|
||||
preg_match('/^<([\w:$]*)\b/', $tag, $matches);
|
||||
$tag_name_re = $matches[1];
|
||||
|
||||
# Parse the content using the HTML-in-Markdown parser.
|
||||
list ($block_text, $text)
|
||||
= $this->_hashHTMLBlocks_inMarkdown($text, $indent,
|
||||
$tag_name_re, $span_mode);
|
||||
|
||||
# Outdent markdown text.
|
||||
if ($indent > 0) {
|
||||
$block_text = preg_replace("/^[ ]{1,$indent}/m", "",
|
||||
$block_text);
|
||||
}
|
||||
|
||||
# Append tag content to parsed text.
|
||||
if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
|
||||
else $parsed .= "$block_text";
|
||||
|
||||
# Start over with a new block.
|
||||
$block_text = "";
|
||||
}
|
||||
else $block_text .= $tag;
|
||||
}
|
||||
|
||||
} while ($depth > 0);
|
||||
|
||||
#
|
||||
# Hash last block text that wasn't processed inside the loop.
|
||||
#
|
||||
$parsed .= $this->$hash_method($block_text);
|
||||
|
||||
return array($parsed, $text);
|
||||
}
|
||||
|
||||
|
||||
protected function hashClean($text) {
|
||||
#
|
||||
# Called whenever a tag must be hashed when a function inserts a "clean" tag
|
||||
# in $text, it passes through this function and is automaticaly escaped,
|
||||
# blocking invalid nested overlap.
|
||||
#
|
||||
return $this->hashPart($text, 'C');
|
||||
}
|
||||
|
||||
|
||||
protected function doAnchors($text) {
|
||||
#
|
||||
# Turn Markdown link shortcuts into XHTML <a> tags.
|
||||
#
|
||||
if ($this->in_anchor) return $text;
|
||||
$this->in_anchor = true;
|
||||
|
||||
#
|
||||
# First, handle reference-style links: [link text] [id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, inline-style links: [link text](url "optional title")
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
('.$this->nested_brackets_re.') # link text = $2
|
||||
\]
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(.+?)> # href = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # href = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # Title = $7
|
||||
\6 # matching quote
|
||||
[ \n]* # ignore any spaces/tabs between closing quote and )
|
||||
)? # title is optional
|
||||
\)
|
||||
(?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_inline_callback'), $text);
|
||||
|
||||
#
|
||||
# Last, handle reference-style shortcuts: [link text]
|
||||
# These must come last in case you've also got [link text][1]
|
||||
# or [link text](/foo)
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
\[
|
||||
([^\[\]]+) # link text = $2; can\'t contain [ or ]
|
||||
\]
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doAnchors_reference_callback'), $text);
|
||||
|
||||
$this->in_anchor = false;
|
||||
return $text;
|
||||
}
|
||||
protected function _doAnchors_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $matches[2];
|
||||
$link_id =& $matches[3];
|
||||
|
||||
if ($link_id == "") {
|
||||
# for shortcut links like [this][] or [this].
|
||||
$link_id = $link_text;
|
||||
}
|
||||
|
||||
# lower-case and turn embedded newlines into spaces
|
||||
$link_id = strtolower($link_id);
|
||||
$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
|
||||
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->urls[$link_id];
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if ( isset( $this->titles[$link_id] ) ) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
if (isset($this->ref_attr[$link_id]))
|
||||
$result .= $this->ref_attr[$link_id];
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
$result = $whole_match;
|
||||
}
|
||||
return $result;
|
||||
}
|
||||
protected function _doAnchors_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$link_text = $this->runSpanGamut($matches[2]);
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
$attr = $this->doExtraAttributes("a", $dummy =& $matches[8]);
|
||||
|
||||
// if the URL was of the form <s p a c e s> it got caught by the HTML
|
||||
// tag parser and hashed. Need to reverse the process before using the URL.
|
||||
$unhashed = $this->unhash($url);
|
||||
if ($unhashed != $url)
|
||||
$url = preg_replace('/^<(.*)>$/', '\1', $unhashed);
|
||||
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
|
||||
$result = "<a href=\"$url\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
$result .= $attr;
|
||||
|
||||
$link_text = $this->runSpanGamut($link_text);
|
||||
$result .= ">$link_text</a>";
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
protected function doImages($text) {
|
||||
#
|
||||
# Turn Markdown image shortcuts into <img> tags.
|
||||
#
|
||||
#
|
||||
# First, handle reference-style labeled images: ![alt text][id]
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
|
||||
[ ]? # one optional space
|
||||
(?:\n[ ]*)? # one optional newline followed by spaces
|
||||
|
||||
\[
|
||||
(.*?) # id = $3
|
||||
\]
|
||||
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doImages_reference_callback'), $text);
|
||||
|
||||
#
|
||||
# Next, handle inline images: 
|
||||
# Don't forget: encode * and _
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
( # wrap whole match in $1
|
||||
!\[
|
||||
('.$this->nested_brackets_re.') # alt text = $2
|
||||
\]
|
||||
\s? # One optional whitespace character
|
||||
\( # literal paren
|
||||
[ \n]*
|
||||
(?:
|
||||
<(\S*)> # src url = $3
|
||||
|
|
||||
('.$this->nested_url_parenthesis_re.') # src url = $4
|
||||
)
|
||||
[ \n]*
|
||||
( # $5
|
||||
([\'"]) # quote char = $6
|
||||
(.*?) # title = $7
|
||||
\6 # matching quote
|
||||
[ \n]*
|
||||
)? # title is optional
|
||||
\)
|
||||
(?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
|
||||
)
|
||||
}xs',
|
||||
array($this, '_doImages_inline_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doImages_reference_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$link_id = strtolower($matches[3]);
|
||||
|
||||
if ($link_id == "") {
|
||||
$link_id = strtolower($alt_text); # for shortcut links like ![this][].
|
||||
}
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
if (isset($this->urls[$link_id])) {
|
||||
$url = $this->encodeURLAttribute($this->urls[$link_id]);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($this->titles[$link_id])) {
|
||||
$title = $this->titles[$link_id];
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\"";
|
||||
}
|
||||
if (isset($this->ref_attr[$link_id]))
|
||||
$result .= $this->ref_attr[$link_id];
|
||||
$result .= $this->empty_element_suffix;
|
||||
$result = $this->hashPart($result);
|
||||
}
|
||||
else {
|
||||
# If there's no such link ID, leave intact:
|
||||
$result = $whole_match;
|
||||
}
|
||||
|
||||
return $result;
|
||||
}
|
||||
protected function _doImages_inline_callback($matches) {
|
||||
$whole_match = $matches[1];
|
||||
$alt_text = $matches[2];
|
||||
$url = $matches[3] == '' ? $matches[4] : $matches[3];
|
||||
$title =& $matches[7];
|
||||
$attr = $this->doExtraAttributes("img", $dummy =& $matches[8]);
|
||||
|
||||
$alt_text = $this->encodeAttribute($alt_text);
|
||||
$url = $this->encodeURLAttribute($url);
|
||||
$result = "<img src=\"$url\" alt=\"$alt_text\"";
|
||||
if (isset($title)) {
|
||||
$title = $this->encodeAttribute($title);
|
||||
$result .= " title=\"$title\""; # $title already quoted
|
||||
}
|
||||
$result .= $attr;
|
||||
$result .= $this->empty_element_suffix;
|
||||
|
||||
return $this->hashPart($result);
|
||||
}
|
||||
|
||||
|
||||
protected function doHeaders($text) {
|
||||
#
|
||||
# Redefined to add id and class attribute support.
|
||||
#
|
||||
# Setext-style headers:
|
||||
# Header 1 {#header1}
|
||||
# ========
|
||||
#
|
||||
# Header 2 {#header2 .class1 .class2}
|
||||
# --------
|
||||
#
|
||||
$text = preg_replace_callback(
|
||||
'{
|
||||
(^.+?) # $1: Header text
|
||||
(?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
|
||||
[ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer
|
||||
}mx',
|
||||
array($this, '_doHeaders_callback_setext'), $text);
|
||||
|
||||
# atx-style headers:
|
||||
# # Header 1 {#header1}
|
||||
# ## Header 2 {#header2}
|
||||
# ## Header 2 with closing hashes ## {#header3.class1.class2}
|
||||
# ...
|
||||
# ###### Header 6 {.class2}
|
||||
#
|
||||
$text = preg_replace_callback('{
|
||||
^(\#{1,6}) # $1 = string of #\'s
|
||||
[ ]*
|
||||
(.+?) # $2 = Header text
|
||||
[ ]*
|
||||
\#* # optional closing #\'s (not counted)
|
||||
(?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
|
||||
[ ]*
|
||||
\n+
|
||||
}xm',
|
||||
array($this, '_doHeaders_callback_atx'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doHeaders_callback_setext($matches) {
|
||||
if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
|
||||
return $matches[0];
|
||||
$level = $matches[3]{0} == '=' ? 1 : 2;
|
||||
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[2]);
|
||||
$block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
protected function _doHeaders_callback_atx($matches) {
|
||||
$level = strlen($matches[1]);
|
||||
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[3]);
|
||||
$block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>";
|
||||
return "\n" . $this->hashBlock($block) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
protected function doTables($text) {
|
||||
#
|
||||
# Form HTML tables.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
#
|
||||
# Find tables with leading pipe.
|
||||
#
|
||||
# | Header 1 | Header 2
|
||||
# | -------- | --------
|
||||
# | Cell 1 | Cell 2
|
||||
# | Cell 3 | Cell 4
|
||||
#
|
||||
$text = preg_replace_callback('
|
||||
{
|
||||
^ # Start of a line
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
[|] # Optional leading pipe (present)
|
||||
(.+) \n # $1: Header row (at least one pipe)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
[|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline
|
||||
|
||||
( # $3: Cells
|
||||
(?>
|
||||
[ ]* # Allowed whitespace.
|
||||
[|] .* \n # Row content.
|
||||
)*
|
||||
)
|
||||
(?=\n|\Z) # Stop at final double newline.
|
||||
}xm',
|
||||
array($this, '_doTable_leadingPipe_callback'), $text);
|
||||
|
||||
#
|
||||
# Find tables without leading pipe.
|
||||
#
|
||||
# Header 1 | Header 2
|
||||
# -------- | --------
|
||||
# Cell 1 | Cell 2
|
||||
# Cell 3 | Cell 4
|
||||
#
|
||||
$text = preg_replace_callback('
|
||||
{
|
||||
^ # Start of a line
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
(\S.*[|].*) \n # $1: Header row (at least one pipe)
|
||||
|
||||
[ ]{0,'.$less_than_tab.'} # Allowed whitespace.
|
||||
([-:]+[ ]*[|][-| :]*) \n # $2: Header underline
|
||||
|
||||
( # $3: Cells
|
||||
(?>
|
||||
.* [|] .* \n # Row content
|
||||
)*
|
||||
)
|
||||
(?=\n|\Z) # Stop at final double newline.
|
||||
}xm',
|
||||
array($this, '_DoTable_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doTable_leadingPipe_callback($matches) {
|
||||
$head = $matches[1];
|
||||
$underline = $matches[2];
|
||||
$content = $matches[3];
|
||||
|
||||
# Remove leading pipe for each row.
|
||||
$content = preg_replace('/^ *[|]/m', '', $content);
|
||||
|
||||
return $this->_doTable_callback(array($matches[0], $head, $underline, $content));
|
||||
}
|
||||
protected function _doTable_makeAlignAttr($alignname)
|
||||
{
|
||||
if (empty($this->table_align_class_tmpl))
|
||||
return " align=\"$alignname\"";
|
||||
|
||||
$classname = str_replace('%%', $alignname, $this->table_align_class_tmpl);
|
||||
return " class=\"$classname\"";
|
||||
}
|
||||
protected function _doTable_callback($matches) {
|
||||
$head = $matches[1];
|
||||
$underline = $matches[2];
|
||||
$content = $matches[3];
|
||||
|
||||
# Remove any tailing pipes for each line.
|
||||
$head = preg_replace('/[|] *$/m', '', $head);
|
||||
$underline = preg_replace('/[|] *$/m', '', $underline);
|
||||
$content = preg_replace('/[|] *$/m', '', $content);
|
||||
|
||||
# Reading alignement from header underline.
|
||||
$separators = preg_split('/ *[|] */', $underline);
|
||||
foreach ($separators as $n => $s) {
|
||||
if (preg_match('/^ *-+: *$/', $s))
|
||||
$attr[$n] = $this->_doTable_makeAlignAttr('right');
|
||||
else if (preg_match('/^ *:-+: *$/', $s))
|
||||
$attr[$n] = $this->_doTable_makeAlignAttr('center');
|
||||
else if (preg_match('/^ *:-+ *$/', $s))
|
||||
$attr[$n] = $this->_doTable_makeAlignAttr('left');
|
||||
else
|
||||
$attr[$n] = '';
|
||||
}
|
||||
|
||||
# Parsing span elements, including code spans, character escapes,
|
||||
# and inline HTML tags, so that pipes inside those gets ignored.
|
||||
$head = $this->parseSpan($head);
|
||||
$headers = preg_split('/ *[|] */', $head);
|
||||
$col_count = count($headers);
|
||||
$attr = array_pad($attr, $col_count, '');
|
||||
|
||||
# Write column headers.
|
||||
$text = "<table>\n";
|
||||
$text .= "<thead>\n";
|
||||
$text .= "<tr>\n";
|
||||
foreach ($headers as $n => $header)
|
||||
$text .= " <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n";
|
||||
$text .= "</tr>\n";
|
||||
$text .= "</thead>\n";
|
||||
|
||||
# Split content by row.
|
||||
$rows = explode("\n", trim($content, "\n"));
|
||||
|
||||
$text .= "<tbody>\n";
|
||||
foreach ($rows as $row) {
|
||||
# Parsing span elements, including code spans, character escapes,
|
||||
# and inline HTML tags, so that pipes inside those gets ignored.
|
||||
$row = $this->parseSpan($row);
|
||||
|
||||
# Split row by cell.
|
||||
$row_cells = preg_split('/ *[|] */', $row, $col_count);
|
||||
$row_cells = array_pad($row_cells, $col_count, '');
|
||||
|
||||
$text .= "<tr>\n";
|
||||
foreach ($row_cells as $n => $cell)
|
||||
$text .= " <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n";
|
||||
$text .= "</tr>\n";
|
||||
}
|
||||
$text .= "</tbody>\n";
|
||||
$text .= "</table>";
|
||||
|
||||
return $this->hashBlock($text) . "\n";
|
||||
}
|
||||
|
||||
|
||||
protected function doDefLists($text) {
|
||||
#
|
||||
# Form HTML definition lists.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Re-usable pattern to match any entire dl list:
|
||||
$whole_list_re = '(?>
|
||||
( # $1 = whole list
|
||||
( # $2
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
((?>.*\S.*\n)+) # $3 = defined term
|
||||
\n?
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
(?s:.+?)
|
||||
( # $4
|
||||
\z
|
||||
|
|
||||
\n{2,}
|
||||
(?=\S)
|
||||
(?! # Negative lookahead for another term
|
||||
[ ]{0,'.$less_than_tab.'}
|
||||
(?: \S.*\n )+? # defined term
|
||||
\n?
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
(?! # Negative lookahead for another definition
|
||||
[ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
|
||||
)
|
||||
)
|
||||
)
|
||||
)'; // mx
|
||||
|
||||
$text = preg_replace_callback('{
|
||||
(?>\A\n?|(?<=\n\n))
|
||||
'.$whole_list_re.'
|
||||
}mx',
|
||||
array($this, '_doDefLists_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doDefLists_callback($matches) {
|
||||
# Re-usable patterns to match list item bullets and number markers:
|
||||
$list = $matches[1];
|
||||
|
||||
# Turn double returns into triple returns, so that we can make a
|
||||
# paragraph for the last item in a list, if necessary:
|
||||
$result = trim($this->processDefListItems($list));
|
||||
$result = "<dl>\n" . $result . "\n</dl>";
|
||||
return $this->hashBlock($result) . "\n\n";
|
||||
}
|
||||
|
||||
|
||||
protected function processDefListItems($list_str) {
|
||||
#
|
||||
# Process the contents of a single definition list, splitting it
|
||||
# into individual term and definition list items.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# trim trailing blank lines:
|
||||
$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
|
||||
|
||||
# Process definition terms.
|
||||
$list_str = preg_replace_callback('{
|
||||
(?>\A\n?|\n\n+) # leading line
|
||||
( # definition terms = $1
|
||||
[ ]{0,'.$less_than_tab.'} # leading whitespace
|
||||
(?!\:[ ]|[ ]) # negative lookahead for a definition
|
||||
# mark (colon) or more whitespace.
|
||||
(?> \S.* \n)+? # actual term (not whitespace).
|
||||
)
|
||||
(?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
|
||||
# with a definition mark.
|
||||
}xm',
|
||||
array($this, '_processDefListItems_callback_dt'), $list_str);
|
||||
|
||||
# Process actual definitions.
|
||||
$list_str = preg_replace_callback('{
|
||||
\n(\n+)? # leading line = $1
|
||||
( # marker space = $2
|
||||
[ ]{0,'.$less_than_tab.'} # whitespace before colon
|
||||
\:[ ]+ # definition mark (colon)
|
||||
)
|
||||
((?s:.+?)) # definition text = $3
|
||||
(?= \n+ # stop at next definition mark,
|
||||
(?: # next term or end of text
|
||||
[ ]{0,'.$less_than_tab.'} \:[ ] |
|
||||
<dt> | \z
|
||||
)
|
||||
)
|
||||
}xm',
|
||||
array($this, '_processDefListItems_callback_dd'), $list_str);
|
||||
|
||||
return $list_str;
|
||||
}
|
||||
protected function _processDefListItems_callback_dt($matches) {
|
||||
$terms = explode("\n", trim($matches[1]));
|
||||
$text = '';
|
||||
foreach ($terms as $term) {
|
||||
$term = $this->runSpanGamut(trim($term));
|
||||
$text .= "\n<dt>" . $term . "</dt>";
|
||||
}
|
||||
return $text . "\n";
|
||||
}
|
||||
protected function _processDefListItems_callback_dd($matches) {
|
||||
$leading_line = $matches[1];
|
||||
$marker_space = $matches[2];
|
||||
$def = $matches[3];
|
||||
|
||||
if ($leading_line || preg_match('/\n{2,}/', $def)) {
|
||||
# Replace marker with the appropriate whitespace indentation
|
||||
$def = str_repeat(' ', strlen($marker_space)) . $def;
|
||||
$def = $this->runBlockGamut($this->outdent($def . "\n\n"));
|
||||
$def = "\n". $def ."\n";
|
||||
}
|
||||
else {
|
||||
$def = rtrim($def);
|
||||
$def = $this->runSpanGamut($this->outdent($def));
|
||||
}
|
||||
|
||||
return "\n<dd>" . $def . "</dd>\n";
|
||||
}
|
||||
|
||||
|
||||
protected function doFencedCodeBlocks($text) {
|
||||
#
|
||||
# Adding the fenced code block syntax to regular Markdown:
|
||||
#
|
||||
# ~~~
|
||||
# Code block
|
||||
# ~~~
|
||||
#
|
||||
$less_than_tab = $this->tab_width;
|
||||
|
||||
$text = preg_replace_callback('{
|
||||
(?:\n|\A)
|
||||
# 1: Opening marker
|
||||
(
|
||||
(?:~{3,}|`{3,}) # 3 or more tildes/backticks.
|
||||
)
|
||||
[ ]*
|
||||
(?:
|
||||
\.?([-_:a-zA-Z0-9]+) # 2: standalone class name
|
||||
|
|
||||
'.$this->id_class_attr_catch_re.' # 3: Extra attributes
|
||||
)?
|
||||
[ ]* \n # Whitespace and newline following marker.
|
||||
|
||||
# 4: Content
|
||||
(
|
||||
(?>
|
||||
(?!\1 [ ]* \n) # Not a closing marker.
|
||||
.*\n+
|
||||
)+
|
||||
)
|
||||
|
||||
# Closing marker.
|
||||
\1 [ ]* (?= \n )
|
||||
}xm',
|
||||
array($this, '_doFencedCodeBlocks_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
protected function _doFencedCodeBlocks_callback($matches) {
|
||||
$classname =& $matches[2];
|
||||
$attrs =& $matches[3];
|
||||
$codeblock = $matches[4];
|
||||
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
|
||||
$codeblock = preg_replace_callback('/^\n+/',
|
||||
array($this, '_doFencedCodeBlocks_newlines'), $codeblock);
|
||||
|
||||
if ($classname != "") {
|
||||
if ($classname{0} == '.')
|
||||
$classname = substr($classname, 1);
|
||||
$attr_str = ' class="'.$this->code_class_prefix.$classname.'"';
|
||||
} else {
|
||||
$attr_str = $this->doExtraAttributes($this->code_attr_on_pre ? "pre" : "code", $attrs);
|
||||
}
|
||||
$pre_attr_str = $this->code_attr_on_pre ? $attr_str : '';
|
||||
$code_attr_str = $this->code_attr_on_pre ? '' : $attr_str;
|
||||
$codeblock = "<pre$pre_attr_str><code$code_attr_str>$codeblock</code></pre>";
|
||||
|
||||
return "\n\n".$this->hashBlock($codeblock)."\n\n";
|
||||
}
|
||||
protected function _doFencedCodeBlocks_newlines($matches) {
|
||||
return str_repeat("<br$this->empty_element_suffix",
|
||||
strlen($matches[0]));
|
||||
}
|
||||
|
||||
|
||||
#
|
||||
# Redefining emphasis markers so that emphasis by underscore does not
|
||||
# work in the middle of a word.
|
||||
#
|
||||
protected $em_relist = array(
|
||||
'' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?![\.,:;]?\s)',
|
||||
'*' => '(?<![\s*])\*(?!\*)',
|
||||
'_' => '(?<![\s_])_(?![a-zA-Z0-9_])',
|
||||
);
|
||||
protected $strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?![\.,:;]?\s)',
|
||||
'**' => '(?<![\s*])\*\*(?!\*)',
|
||||
'__' => '(?<![\s_])__(?![a-zA-Z0-9_])',
|
||||
);
|
||||
protected $em_strong_relist = array(
|
||||
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?![\.,:;]?\s)',
|
||||
'***' => '(?<![\s*])\*\*\*(?!\*)',
|
||||
'___' => '(?<![\s_])___(?![a-zA-Z0-9_])',
|
||||
);
|
||||
|
||||
|
||||
protected function formParagraphs($text) {
|
||||
#
|
||||
# Params:
|
||||
# $text - string to process with html <p> tags
|
||||
#
|
||||
# Strip leading and trailing lines:
|
||||
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
|
||||
|
||||
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
|
||||
|
||||
#
|
||||
# Wrap <p> tags and unhashify HTML blocks
|
||||
#
|
||||
foreach ($grafs as $key => $value) {
|
||||
$value = trim($this->runSpanGamut($value));
|
||||
|
||||
# Check if this should be enclosed in a paragraph.
|
||||
# Clean tag hashes & block tag hashes are left alone.
|
||||
$is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
|
||||
|
||||
if ($is_p) {
|
||||
$value = "<p>$value</p>";
|
||||
}
|
||||
$grafs[$key] = $value;
|
||||
}
|
||||
|
||||
# Join grafs in one text, then unhash HTML tags.
|
||||
$text = implode("\n\n", $grafs);
|
||||
|
||||
# Finish by removing any tag hashes still present in $text.
|
||||
$text = $this->unhash($text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
### Footnotes
|
||||
|
||||
protected function stripFootnotes($text) {
|
||||
#
|
||||
# Strips link definitions from text, stores the URLs and titles in
|
||||
# hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: [^id]: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
|
||||
[ ]*
|
||||
\n? # maybe *one* newline
|
||||
( # text = $2 (no blank lines allowed)
|
||||
(?:
|
||||
.+ # actual text
|
||||
|
|
||||
\n # newlines but
|
||||
(?!\[.+?\][ ]?:\s)# negative lookahead for footnote or link definition marker.
|
||||
(?!\n+[ ]{0,3}\S)# ensure line is not blank and followed
|
||||
# by non-indented content
|
||||
)*
|
||||
)
|
||||
}xm',
|
||||
array($this, '_stripFootnotes_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
protected function _stripFootnotes_callback($matches) {
|
||||
$note_id = $this->fn_id_prefix . $matches[1];
|
||||
$this->footnotes[$note_id] = $this->outdent($matches[2]);
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
protected function doFootnotes($text) {
|
||||
#
|
||||
# Replace footnote references in $text [^id] with a special text-token
|
||||
# which will be replaced by the actual footnote marker in appendFootnotes.
|
||||
#
|
||||
if (!$this->in_anchor) {
|
||||
$text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
|
||||
|
||||
protected function appendFootnotes($text) {
|
||||
#
|
||||
# Append footnote list to text.
|
||||
#
|
||||
$text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
|
||||
array($this, '_appendFootnotes_callback'), $text);
|
||||
|
||||
if (!empty($this->footnotes_ordered)) {
|
||||
$text .= "\n\n";
|
||||
$text .= "<div class=\"footnotes\">\n";
|
||||
$text .= "<hr". $this->empty_element_suffix ."\n";
|
||||
$text .= "<ol>\n\n";
|
||||
|
||||
$attr = "";
|
||||
if ($this->fn_backlink_class != "") {
|
||||
$class = $this->fn_backlink_class;
|
||||
$class = $this->encodeAttribute($class);
|
||||
$attr .= " class=\"$class\"";
|
||||
}
|
||||
if ($this->fn_backlink_title != "") {
|
||||
$title = $this->fn_backlink_title;
|
||||
$title = $this->encodeAttribute($title);
|
||||
$attr .= " title=\"$title\"";
|
||||
}
|
||||
$num = 0;
|
||||
|
||||
while (!empty($this->footnotes_ordered)) {
|
||||
$footnote = reset($this->footnotes_ordered);
|
||||
$note_id = key($this->footnotes_ordered);
|
||||
unset($this->footnotes_ordered[$note_id]);
|
||||
$ref_count = $this->footnotes_ref_count[$note_id];
|
||||
unset($this->footnotes_ref_count[$note_id]);
|
||||
unset($this->footnotes[$note_id]);
|
||||
|
||||
$footnote .= "\n"; # Need to append newline before parsing.
|
||||
$footnote = $this->runBlockGamut("$footnote\n");
|
||||
$footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
|
||||
array($this, '_appendFootnotes_callback'), $footnote);
|
||||
|
||||
$attr = str_replace("%%", ++$num, $attr);
|
||||
$note_id = $this->encodeAttribute($note_id);
|
||||
|
||||
# Prepare backlink, multiple backlinks if multiple references
|
||||
$backlink = "<a href=\"#fnref:$note_id\"$attr>↩</a>";
|
||||
for ($ref_num = 2; $ref_num <= $ref_count; ++$ref_num) {
|
||||
$backlink .= " <a href=\"#fnref$ref_num:$note_id\"$attr>↩</a>";
|
||||
}
|
||||
# Add backlink to last paragraph; create new paragraph if needed.
|
||||
if (preg_match('{</p>$}', $footnote)) {
|
||||
$footnote = substr($footnote, 0, -4) . " $backlink</p>";
|
||||
} else {
|
||||
$footnote .= "\n\n<p>$backlink</p>";
|
||||
}
|
||||
|
||||
$text .= "<li id=\"fn:$note_id\">\n";
|
||||
$text .= $footnote . "\n";
|
||||
$text .= "</li>\n\n";
|
||||
}
|
||||
|
||||
$text .= "</ol>\n";
|
||||
$text .= "</div>";
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
protected function _appendFootnotes_callback($matches) {
|
||||
$node_id = $this->fn_id_prefix . $matches[1];
|
||||
|
||||
# Create footnote marker only if it has a corresponding footnote *and*
|
||||
# the footnote hasn't been used by another marker.
|
||||
if (isset($this->footnotes[$node_id])) {
|
||||
$num =& $this->footnotes_numbers[$node_id];
|
||||
if (!isset($num)) {
|
||||
# Transfer footnote content to the ordered list and give it its
|
||||
# number
|
||||
$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
|
||||
$this->footnotes_ref_count[$node_id] = 1;
|
||||
$num = $this->footnote_counter++;
|
||||
$ref_count_mark = '';
|
||||
} else {
|
||||
$ref_count_mark = $this->footnotes_ref_count[$node_id] += 1;
|
||||
}
|
||||
|
||||
$attr = "";
|
||||
if ($this->fn_link_class != "") {
|
||||
$class = $this->fn_link_class;
|
||||
$class = $this->encodeAttribute($class);
|
||||
$attr .= " class=\"$class\"";
|
||||
}
|
||||
if ($this->fn_link_title != "") {
|
||||
$title = $this->fn_link_title;
|
||||
$title = $this->encodeAttribute($title);
|
||||
$attr .= " title=\"$title\"";
|
||||
}
|
||||
|
||||
$attr = str_replace("%%", $num, $attr);
|
||||
$node_id = $this->encodeAttribute($node_id);
|
||||
|
||||
return
|
||||
"<sup id=\"fnref$ref_count_mark:$node_id\">".
|
||||
"<a href=\"#fn:$node_id\"$attr>$num</a>".
|
||||
"</sup>";
|
||||
}
|
||||
|
||||
return "[^".$matches[1]."]";
|
||||
}
|
||||
|
||||
|
||||
### Abbreviations ###
|
||||
|
||||
protected function stripAbbreviations($text) {
|
||||
#
|
||||
# Strips abbreviations from text, stores titles in hash references.
|
||||
#
|
||||
$less_than_tab = $this->tab_width - 1;
|
||||
|
||||
# Link defs are in the form: [id]*: url "optional title"
|
||||
$text = preg_replace_callback('{
|
||||
^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1
|
||||
(.*) # text = $2 (no blank lines allowed)
|
||||
}xm',
|
||||
array($this, '_stripAbbreviations_callback'),
|
||||
$text);
|
||||
return $text;
|
||||
}
|
||||
protected function _stripAbbreviations_callback($matches) {
|
||||
$abbr_word = $matches[1];
|
||||
$abbr_desc = $matches[2];
|
||||
if ($this->abbr_word_re)
|
||||
$this->abbr_word_re .= '|';
|
||||
$this->abbr_word_re .= preg_quote($abbr_word);
|
||||
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
|
||||
return ''; # String that will replace the block
|
||||
}
|
||||
|
||||
|
||||
protected function doAbbreviations($text) {
|
||||
#
|
||||
# Find defined abbreviations in text and wrap them in <abbr> elements.
|
||||
#
|
||||
if ($this->abbr_word_re) {
|
||||
// cannot use the /x modifier because abbr_word_re may
|
||||
// contain significant spaces:
|
||||
$text = preg_replace_callback('{'.
|
||||
'(?<![\w\x1A])'.
|
||||
'(?:'.$this->abbr_word_re.')'.
|
||||
'(?![\w\x1A])'.
|
||||
'}',
|
||||
array($this, '_doAbbreviations_callback'), $text);
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
protected function _doAbbreviations_callback($matches) {
|
||||
$abbr = $matches[0];
|
||||
if (isset($this->abbr_desciptions[$abbr])) {
|
||||
$desc = $this->abbr_desciptions[$abbr];
|
||||
if (empty($desc)) {
|
||||
return $this->hashPart("<abbr>$abbr</abbr>");
|
||||
} else {
|
||||
$desc = $this->encodeAttribute($desc);
|
||||
return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>");
|
||||
}
|
||||
} else {
|
||||
return $matches[0];
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
11
library/php-markdown/Michelf/MarkdownExtra.inc.php
Normal file
11
library/php-markdown/Michelf/MarkdownExtra.inc.php
Normal file
|
|
@ -0,0 +1,11 @@
|
|||
<?php
|
||||
|
||||
# Use this file if you cannot use class autoloading. It will include all the
|
||||
# files needed for the MarkdownExtra parser.
|
||||
#
|
||||
# Take a look at the PSR-0-compatible class autoloading implementation
|
||||
# in the Readme.php file if you want a simple autoloader setup.
|
||||
|
||||
require_once dirname(__FILE__) . '/MarkdownInterface.php';
|
||||
require_once dirname(__FILE__) . '/Markdown.php';
|
||||
require_once dirname(__FILE__) . '/MarkdownExtra.php';
|
||||
38
library/php-markdown/Michelf/MarkdownExtra.php
Normal file
38
library/php-markdown/Michelf/MarkdownExtra.php
Normal file
|
|
@ -0,0 +1,38 @@
|
|||
<?php
|
||||
#
|
||||
# Markdown Extra - A text-to-HTML conversion tool for web writers
|
||||
#
|
||||
# PHP Markdown Extra
|
||||
# Copyright (c) 2004-2014 Michel Fortin
|
||||
# <http://michelf.com/projects/php-markdown/>
|
||||
#
|
||||
# Original Markdown
|
||||
# Copyright (c) 2004-2006 John Gruber
|
||||
# <http://daringfireball.net/projects/markdown/>
|
||||
#
|
||||
namespace Michelf;
|
||||
|
||||
|
||||
# Just force Michelf/Markdown.php to load. This is needed to load
|
||||
# the temporary implementation class. See below for details.
|
||||
\Michelf\Markdown::MARKDOWNLIB_VERSION;
|
||||
|
||||
#
|
||||
# Markdown Extra Parser Class
|
||||
#
|
||||
# Note: Currently the implementation resides in the temporary class
|
||||
# \Michelf\MarkdownExtra_TmpImpl (in the same file as \Michelf\Markdown).
|
||||
# This makes it easier to propagate the changes between the three different
|
||||
# packaging styles of PHP Markdown. Once this issue is resolved, the
|
||||
# _MarkdownExtra_TmpImpl will disappear and this one will contain the code.
|
||||
#
|
||||
|
||||
class MarkdownExtra extends \Michelf\_MarkdownExtra_TmpImpl {
|
||||
|
||||
### Parser Implementation ###
|
||||
|
||||
# Temporarily, the implemenation is in the _MarkdownExtra_TmpImpl class.
|
||||
# See note above.
|
||||
|
||||
}
|
||||
|
||||
9
library/php-markdown/Michelf/MarkdownInterface.inc.php
Normal file
9
library/php-markdown/Michelf/MarkdownInterface.inc.php
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
<?php
|
||||
|
||||
# Use this file if you cannot use class autoloading. It will include all the
|
||||
# files needed for the MarkdownInterface interface.
|
||||
#
|
||||
# Take a look at the PSR-0-compatible class autoloading implementation
|
||||
# in the Readme.php file if you want a simple autoloader setup.
|
||||
|
||||
require_once dirname(__FILE__) . '/MarkdownInterface.php';
|
||||
34
library/php-markdown/Michelf/MarkdownInterface.php
Normal file
34
library/php-markdown/Michelf/MarkdownInterface.php
Normal file
|
|
@ -0,0 +1,34 @@
|
|||
<?php
|
||||
#
|
||||
# Markdown - A text-to-HTML conversion tool for web writers
|
||||
#
|
||||
# PHP Markdown
|
||||
# Copyright (c) 2004-2014 Michel Fortin
|
||||
# <http://michelf.com/projects/php-markdown/>
|
||||
#
|
||||
# Original Markdown
|
||||
# Copyright (c) 2004-2006 John Gruber
|
||||
# <http://daringfireball.net/projects/markdown/>
|
||||
#
|
||||
namespace Michelf;
|
||||
|
||||
|
||||
#
|
||||
# Markdown Parser Interface
|
||||
#
|
||||
|
||||
interface MarkdownInterface {
|
||||
|
||||
#
|
||||
# Initialize the parser and return the result of its transform method.
|
||||
# This will work fine for derived classes too.
|
||||
#
|
||||
public static function defaultTransform($text);
|
||||
|
||||
#
|
||||
# Main function. Performs some preprocessing on the input text
|
||||
# and pass it through the document gamut.
|
||||
#
|
||||
public function transform($text);
|
||||
|
||||
}
|
||||
315
library/php-markdown/Readme.md
Normal file
315
library/php-markdown/Readme.md
Normal file
|
|
@ -0,0 +1,315 @@
|
|||
PHP Markdown
|
||||
============
|
||||
|
||||
PHP Markdown Lib 1.4.1 - 4 May 2013
|
||||
|
||||
by Michel Fortin
|
||||
<http://michelf.ca/>
|
||||
|
||||
based on Markdown by John Gruber
|
||||
<http://daringfireball.net/>
|
||||
|
||||
|
||||
Introduction
|
||||
------------
|
||||
|
||||
This is a library package that includes the PHP Markdown parser and its
|
||||
sibling PHP Markdown Extra with additional features.
|
||||
|
||||
Markdown is a text-to-HTML conversion tool for web writers. Markdown
|
||||
allows you to write using an easy-to-read, easy-to-write plain text
|
||||
format, then convert it to structurally valid XHTML (or HTML).
|
||||
|
||||
"Markdown" is actually two things: a plain text markup syntax, and a
|
||||
software tool, originally written in Perl, that converts the plain text
|
||||
markup to HTML. PHP Markdown is a port to PHP of the original Markdown
|
||||
program by John Gruber.
|
||||
|
||||
* [Full documentation of the Markdown syntax](<http://daringfireball.net/projects/markdown/>)
|
||||
- Daring Fireball (John Gruber)
|
||||
* [Markdown Extra syntax additions](<http://michelf.ca/projects/php-markdown/extra/>)
|
||||
- Michel Fortin
|
||||
|
||||
|
||||
Requirement
|
||||
-----------
|
||||
|
||||
This library package requires PHP 5.3 or later.
|
||||
|
||||
Note: The older plugin/library hybrid package for PHP Markdown and
|
||||
PHP Markdown Extra is still maintained and will work with PHP 4.0.5 and later.
|
||||
|
||||
Before PHP 5.3.7, pcre.backtrack_limit defaults to 100 000, which is too small
|
||||
in many situations. You might need to set it to higher values. Later PHP
|
||||
releases defaults to 1 000 000, which is usually fine.
|
||||
|
||||
|
||||
Usage
|
||||
-----
|
||||
|
||||
This library package is meant to be used with class autoloading. For autoloading
|
||||
to work, your project needs have setup a PSR-0-compatible autoloader. See the
|
||||
included Readme.php file for a minimal autoloader setup. (If you cannot use
|
||||
autoloading, see below.)
|
||||
|
||||
With class autoloading in place, putting the 'Michelf' folder in your
|
||||
include path should be enough for this to work:
|
||||
|
||||
use \Michelf\Markdown;
|
||||
$my_html = Markdown::defaultTransform($my_text);
|
||||
|
||||
Markdown Extra syntax is also available the same way:
|
||||
|
||||
use \Michelf\MarkdownExtra;
|
||||
$my_html = MarkdownExtra::defaultTransform($my_text);
|
||||
|
||||
If you wish to use PHP Markdown with another text filter function
|
||||
built to parse HTML, you should filter the text *after* the `transform`
|
||||
function call. This is an example with [PHP SmartyPants][psp]:
|
||||
|
||||
use \Michelf\Markdown, \Michelf\SmartyPants;
|
||||
$my_html = Markdown::defaultTransform($my_text);
|
||||
$my_html = SmartyPants::defaultTransform($my_html);
|
||||
|
||||
All these examples are using the static `defaultTransform` static function
|
||||
found inside the parser class. If you want to customize the parser
|
||||
configuration, you can also instantiate it directly and change some
|
||||
configuration variables:
|
||||
|
||||
use \Michelf\MarkdownExtra;
|
||||
$parser = new MarkdownExtra;
|
||||
$parser->fn_id_prefix = "post22-";
|
||||
$my_html = $parser->transform($my_text);
|
||||
|
||||
To learn more, see the full list of [configuration variables].
|
||||
|
||||
[configuration variables]: http://michelf.ca/projects/php-markdown/configuration/
|
||||
|
||||
|
||||
### Usage without an autoloader
|
||||
|
||||
If you cannot use class autoloading, you can still use `include` or `require`
|
||||
to access the parser. To load the `\Michelf\Markdown` parser, do it this way:
|
||||
|
||||
require_once 'Michelf/Markdown.inc.php';
|
||||
|
||||
Or, if you need the `\Michelf\MarkdownExtra` parser:
|
||||
|
||||
require_once 'Michelf/MarkdownExtra.inc.php';
|
||||
|
||||
While the plain `.php` files depend on autoloading to work correctly, using the
|
||||
`.inc.php` files instead will eagerly load the dependencies that would be
|
||||
loaded on demand if you were using autoloading.
|
||||
|
||||
|
||||
Public API and Versioning Policy
|
||||
---------------------------------
|
||||
|
||||
Version numbers are of the form *major*.*minor*.*patch*.
|
||||
|
||||
The public API of PHP Markdown consist of the two parser classes `Markdown`
|
||||
and `MarkdownExtra`, their constructors, the `transform` and `defaultTransform`
|
||||
functions and their configuration variables. The public API is stable for
|
||||
a given major version number. It might get additions when the minor version
|
||||
number increments.
|
||||
|
||||
**Protected members are not considered public API.** This is unconventional
|
||||
and deserves an explanation. Incrementing the major version number every time
|
||||
the underlying implementation of something changes is going to give
|
||||
nonessential version numbers for the vast majority of people who just use the
|
||||
parser. Protected members are meant to create parser subclasses that behave in
|
||||
different ways. Very few people create parser subclasses. I don't want to
|
||||
discourage it by making everything private, but at the same time I can't
|
||||
guarantee any stable hook between versions if you use protected members.
|
||||
|
||||
**Syntax changes** will increment the minor number for new features, and the
|
||||
patch number for small corrections. A *new feature* is something that needs a
|
||||
change in the syntax documentation. Note that since PHP Markdown Lib includes
|
||||
two parsers, a syntax change for either of them will increment the minor
|
||||
number. Also note that there is nothing perfectly backward-compatible with the
|
||||
Markdown syntax: all inputs are always valid, so new features always replace
|
||||
something that was previously legal, although generally nonsensical to do.
|
||||
|
||||
|
||||
Bugs
|
||||
----
|
||||
|
||||
To file bug reports please send email to:
|
||||
<michel.fortin@michelf.ca>
|
||||
|
||||
Please include with your report: (1) the example input; (2) the output you
|
||||
expected; (3) the output PHP Markdown actually produced.
|
||||
|
||||
If you have a problem where Markdown gives you an empty result, first check
|
||||
that the backtrack limit is not too low by running `php --info | grep pcre`.
|
||||
See Installation and Requirement above for details.
|
||||
|
||||
|
||||
Development and Testing
|
||||
-----------------------
|
||||
|
||||
Pull requests for fixing bugs are welcome. Proposed new features are
|
||||
going meticulously reviewed -- taking into account backward compatibility,
|
||||
potential side effects, and future extensibility -- before deciding on
|
||||
acceptance or rejection.
|
||||
|
||||
If you make a pull request that includes changes to the parser please add
|
||||
tests for what is being changed to [MDTest][] and make a pull request there
|
||||
too.
|
||||
|
||||
[MDTest]: https://github.com/michelf/mdtest/
|
||||
|
||||
|
||||
Donations
|
||||
---------
|
||||
|
||||
If you wish to make a donation that will help me devote more time to
|
||||
PHP Markdown, please visit [michelf.ca/donate] or send Bitcoin to
|
||||
[1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH].
|
||||
|
||||
[michelf.ca/donate]: https://michelf.ca/donate/#!Thanks%20for%20PHP%20Markdown
|
||||
[1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH]: bitcoin:1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH
|
||||
|
||||
|
||||
Version History
|
||||
---------------
|
||||
|
||||
Unreleased
|
||||
|
||||
* Added the ability to insert custom HTML attributes everywhere an extra
|
||||
attribute block is allowed (links, images, headers). Credits to
|
||||
Peter Droogmans for providing the implementation.
|
||||
|
||||
* Added a `url_filter_func` configuration variable which takes a function
|
||||
that can rewrite any link or image URL to something different.
|
||||
|
||||
|
||||
PHP Markdown Lib 1.4.1 (4 May 2014)
|
||||
|
||||
* The HTML block parser will now treat `<figure>` as a block-level element
|
||||
(as it should) and no longer wrap it in `<p>` or parse it's content with
|
||||
the as Markdown syntax (although with Extra you can use `markdown="1"`
|
||||
if you wish to use the Markdown syntax inside it).
|
||||
|
||||
* The content of `<style>` elements will now be left alone, its content
|
||||
won't be interpreted as Markdown.
|
||||
|
||||
* Corrected an bug where some inline links with spaces in them would not
|
||||
work even when surounded with angle brackets:
|
||||
|
||||
[link](<s p a c e s>)
|
||||
|
||||
* Fixed an issue where email addresses with quotes in them would not always
|
||||
have the quotes escaped in the link attribute, causing broken links (and
|
||||
invalid HTML).
|
||||
|
||||
* Fixed the case were a link definition following a footnote definition would
|
||||
be swallowed by the footnote unless it was separated by a blank line.
|
||||
|
||||
|
||||
PHP Markdown Lib 1.4.0 (29 Nov 2013)
|
||||
|
||||
* Added support for the `tel:` URL scheme in automatic links.
|
||||
|
||||
<tel:+1-111-111-1111>
|
||||
|
||||
It gets converted to this (note the `tel:` prefix becomes invisible):
|
||||
|
||||
<a href="tel:+1-111-111-1111">+1-111-111-1111</a>
|
||||
|
||||
* Added backtick fenced code blocks to MarkdownExtra, originally from
|
||||
Github-Flavored Markdown.
|
||||
|
||||
* Added an interface called MarkdownInterface implemented by both
|
||||
the Markdown and MarkdownExtra parsers. You can use the interface if
|
||||
you want to create a mockup parser object for unit testing.
|
||||
|
||||
* For those of you who cannot use class autoloading, you can now
|
||||
include `Michelf/Markdown.inc.php` or `Michelf/MarkdownExtra.inc.php` (note
|
||||
the `.inc.php` extension) to automatically include other files required
|
||||
by the parser.
|
||||
|
||||
|
||||
PHP Markdown Lib 1.3 (11 Apr 2013)
|
||||
|
||||
This is the first release of PHP Markdown Lib. This package requires PHP
|
||||
version 5.3 or later and is designed to work with PSR-0 autoloading and,
|
||||
optionally with Composer. Here is a list of the changes since
|
||||
PHP Markdown Extra 1.2.6:
|
||||
|
||||
* Plugin interface for WordPress and other systems is no longer present in
|
||||
the Lib package. The classic package is still available if you need it:
|
||||
<http://michelf.ca/projects/php-markdown/classic/>
|
||||
|
||||
* Added `public` and `protected` protection attributes, plus a section about
|
||||
what is "public API" and what isn't in the Readme file.
|
||||
|
||||
* Changed HTML output for footnotes: now instead of adding `rel` and `rev`
|
||||
attributes, footnotes links have the class name `footnote-ref` and
|
||||
backlinks `footnote-backref`.
|
||||
|
||||
* Fixed some regular expressions to make PCRE not shout warnings about POSIX
|
||||
collation classes (dependent on your version of PCRE).
|
||||
|
||||
* Added optional class and id attributes to images and links using the same
|
||||
syntax as for headers:
|
||||
|
||||
[link](url){#id .class}
|
||||
{#id .class}
|
||||
|
||||
It work too for reference-style links and images. In this case you need
|
||||
to put those attributes at the reference definition:
|
||||
|
||||
[link][linkref] or [linkref]
|
||||
![img][linkref]
|
||||
|
||||
[linkref]: url "optional title" {#id .class}
|
||||
|
||||
* Fixed a PHP notice message triggered when some table column separator
|
||||
markers are missing on the separator line below column headers.
|
||||
|
||||
* Fixed a small mistake that could cause the parser to retain an invalid
|
||||
state related to parsing links across multiple runs. This was never
|
||||
observed (that I know of), but it's still worth fixing.
|
||||
|
||||
|
||||
Copyright and License
|
||||
---------------------
|
||||
|
||||
PHP Markdown Lib
|
||||
Copyright (c) 2004-2014 Michel Fortin
|
||||
<http://michelf.ca/>
|
||||
All rights reserved.
|
||||
|
||||
Based on Markdown
|
||||
Copyright (c) 2003-2005 John Gruber
|
||||
<http://daringfireball.net/>
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
* Neither the name "Markdown" nor the names of its contributors may
|
||||
be used to endorse or promote products derived from this software
|
||||
without specific prior written permission.
|
||||
|
||||
This software is provided by the copyright holders and contributors "as
|
||||
is" and any express or implied warranties, including, but not limited
|
||||
to, the implied warranties of merchantability and fitness for a
|
||||
particular purpose are disclaimed. In no event shall the copyright owner
|
||||
or contributors be liable for any direct, indirect, incidental, special,
|
||||
exemplary, or consequential damages (including, but not limited to,
|
||||
procurement of substitute goods or services; loss of use, data, or
|
||||
profits; or business interruption) however caused and on any theory of
|
||||
liability, whether in contract, strict liability, or tort (including
|
||||
negligence or otherwise) arising in any way out of the use of this
|
||||
software, even if advised of the possibility of such damage.
|
||||
31
library/php-markdown/Readme.php
Normal file
31
library/php-markdown/Readme.php
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
<?php
|
||||
|
||||
# This file passes the content of the Readme.md file in the same directory
|
||||
# through the Markdown filter. You can adapt this sample code in any way
|
||||
# you like.
|
||||
|
||||
# Install PSR-0-compatible class autoloader
|
||||
spl_autoload_register(function($class){
|
||||
require preg_replace('{\\\\|_(?!.*\\\\)}', DIRECTORY_SEPARATOR, ltrim($class, '\\')).'.php';
|
||||
});
|
||||
|
||||
# Get Markdown class
|
||||
use \Michelf\Markdown;
|
||||
|
||||
# Read file and pass content through the Markdown parser
|
||||
$text = file_get_contents('Readme.md');
|
||||
$html = Markdown::defaultTransform($text);
|
||||
|
||||
?>
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>PHP Markdown Lib - Readme</title>
|
||||
</head>
|
||||
<body>
|
||||
<?php
|
||||
# Put HTML content in the document
|
||||
echo $html;
|
||||
?>
|
||||
</body>
|
||||
</html>
|
||||
31
library/php-markdown/composer.json
Normal file
31
library/php-markdown/composer.json
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
{
|
||||
"name": "michelf/php-markdown",
|
||||
"type": "library",
|
||||
"description": "PHP Markdown",
|
||||
"homepage": "http://michelf.ca/projects/php-markdown/",
|
||||
"keywords": ["markdown"],
|
||||
"license": "BSD-3-Clause",
|
||||
"authors": [
|
||||
{
|
||||
"name": "Michel Fortin",
|
||||
"email": "michel.fortin@michelf.ca",
|
||||
"homepage": "http://michelf.ca/",
|
||||
"role": "Developer"
|
||||
},
|
||||
{
|
||||
"name": "John Gruber",
|
||||
"homepage": "http://daringfireball.net/"
|
||||
}
|
||||
],
|
||||
"require": {
|
||||
"php": ">=5.3.0"
|
||||
},
|
||||
"autoload": {
|
||||
"psr-0": { "Michelf": "" }
|
||||
},
|
||||
"extra": {
|
||||
"branch-alias": {
|
||||
"dev-lib": "1.4.x-dev"
|
||||
}
|
||||
}
|
||||
}
|
||||
48
mod/help.php
48
mod/help.php
|
|
@ -1,53 +1,6 @@
|
|||
<?php
|
||||
define( 'MARKDOWN_PARSER_CLASS', 'ExtendedMarkdown' );
|
||||
require_once('library/markdown.php');
|
||||
|
||||
class ExtendedMarkdown extends MarkdownExtra_Parser {
|
||||
|
||||
function ExtendedMarkdown() {
|
||||
$this->block_gamut += array(
|
||||
"doBlockWarning" => 45,
|
||||
);
|
||||
parent::MarkdownExtra_Parser();
|
||||
}
|
||||
|
||||
function doBlockWarning($text) {
|
||||
$text = preg_replace_callback('/
|
||||
( # Wrap whole match in $1
|
||||
(?>
|
||||
^[ ]*![ ]? # "!" at the start of a line
|
||||
.+\n # rest of the first line
|
||||
(.+\n)* # subsequent consecutive lines
|
||||
\n* # blanks
|
||||
)+
|
||||
)
|
||||
/xm', array(&$this, '_doBlockWarning_callback'), $text);
|
||||
|
||||
return $text;
|
||||
}
|
||||
|
||||
function _doBlockWarning_callback($matches) {
|
||||
$bq = $matches[1];
|
||||
# trim one level of quoting - trim whitespace-only lines
|
||||
$bq = preg_replace('/^[ ]*![ ]?|^[ ]+$/m', '', $bq);
|
||||
$bq = $this->runBlockGamut($bq); # recurse
|
||||
|
||||
$bq = preg_replace('/^/m', " ", $bq);
|
||||
# These leading spaces cause problem with <pre> content,
|
||||
# so we need to fix that:
|
||||
// $bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx', array(&$this, '__doBlockWarning_callback2'), $bq);
|
||||
|
||||
return "\n" . $this->hashBlock("<div class='md_warning'>\n$bq\n</div>") . "\n\n";
|
||||
}
|
||||
|
||||
function _doBlockWarning_callback2($matches) {
|
||||
$pre = $matches[1];
|
||||
$pre = preg_replace('/^ /m', '', $pre);
|
||||
return $pre;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
if (!function_exists('load_doc_file')) {
|
||||
|
||||
function load_doc_file($s) {
|
||||
|
|
@ -67,7 +20,6 @@ if (!function_exists('load_doc_file')) {
|
|||
|
||||
function help_content(&$a) {
|
||||
|
||||
|
||||
nav_set_selected('help');
|
||||
|
||||
global $lang;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue