mirror of https://github.com/friendica/friendica
Merge pull request #1417 from annando/1502-improved-markdown
Updated libraries for Markdown and mobile detection
This commit is contained in:
commit
20208acb23
|
|
@ -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>
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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();
|
||||
*/
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
vendor/
|
||||
nbproject/
|
||||
/*.buildpath
|
||||
/*.project
|
||||
/.settings
|
||||
/error.log
|
||||
/export/nicejson
|
||||
.idea/
|
||||
*.iml
|
||||
/coverage
|
||||
/phpunit.phar
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
[submodule "export/nicejson"]
|
||||
path = export/nicejson
|
||||
url = https://github.com/GerHobbelt/nicejson-php.git
|
||||
|
|
@ -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)
|
||||
;
|
||||
|
||||
|
||||
|
|
@ -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
|
||||
|
|
@ -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.
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -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>
|
||||
|
|
@ -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/"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -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 {}
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
~*
|
||||
vendor
|
||||
composer.lock
|
||||
|
|
@ -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
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -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.
|
||||
|
|
@ -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.
|
||||
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
test:
|
||||
override:
|
||||
- phpunit --no-configuration HTML_To_MarkdownTest ./tests/HTML_To_MarkdownTest.php
|
||||
|
||||
|
|
@ -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.*"
|
||||
}
|
||||
}
|
||||
2944
library/markdown.php
2944
library/markdown.php
File diff suppressed because it is too large
Load Diff
|
|
@ -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.
|
||||
|
|
@ -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';
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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';
|
||||
|
|
@ -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.
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -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';
|
||||
|
|
@ -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);
|
||||
|
||||
}
|
||||
|
|
@ -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.
|
||||
|
|
@ -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>
|
||||
|
|
@ -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"
|
||||
}
|
||||
}
|
||||
}
|
||||
54
mod/help.php
54
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) {
|
||||
|
|
@ -66,8 +19,7 @@ if (!function_exists('load_doc_file')) {
|
|||
}
|
||||
|
||||
function help_content(&$a) {
|
||||
|
||||
|
||||
|
||||
nav_set_selected('help');
|
||||
|
||||
global $lang;
|
||||
|
|
@ -93,9 +45,9 @@ function help_content(&$a) {
|
|||
'$message' => t('Page not found.')
|
||||
));
|
||||
}
|
||||
|
||||
|
||||
$html = Markdown($text);
|
||||
$html = "<style>.md_warning { padding: 1em; border: #ff0000 solid 2px; background-color: #f9a3a3; color: #ffffff;</style>".$html;
|
||||
return $html;
|
||||
|
||||
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue