Move pquery to 3rd party libs

The project is abandoned so the easiest way for patching it is adding it to the lib-3rd-party.
[MAILPOE-3980]
This commit is contained in:
Rostislav Wolny
2021-12-01 13:19:29 +01:00
committed by Veljko V
parent a96fc01c56
commit 539f518f64
13 changed files with 8812 additions and 55 deletions

View File

@@ -8,8 +8,7 @@
"require": {
"php": ">=7.1",
"mtdowling/cron-expression": "^1.1",
"soundasleep/html2text": "dev-master",
"tburry/pquery": "^1.1.1"
"soundasleep/html2text": "dev-master"
},
"require-dev": {
"ext-gd": "*",

54
composer.lock generated
View File

@@ -4,7 +4,7 @@
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
"This file is @generated automatically"
],
"content-hash": "44e6370ee3bd0f45a6ba712d32f54ef9",
"content-hash": "a736768274d32a1dbad34e9a59f8565d",
"packages": [
{
"name": "mtdowling/cron-expression",
@@ -103,58 +103,6 @@
"source": "https://github.com/mailpoet/html2text/tree/master"
},
"time": "2019-04-24T12:03:33+00:00"
},
{
"name": "tburry/pquery",
"version": "v1.1.1",
"source": {
"type": "git",
"url": "https://github.com/tburry/pquery.git",
"reference": "872339ffd38d261c4417ea1855428b1b4ff9abf1"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/tburry/pquery/zipball/872339ffd38d261c4417ea1855428b1b4ff9abf1",
"reference": "872339ffd38d261c4417ea1855428b1b4ff9abf1",
"shasum": ""
},
"require": {
"php": ">=5.3.0"
},
"require-dev": {
"htmlawed/htmlawed": "dev-master"
},
"type": "library",
"autoload": {
"classmap": [
"IQuery.php",
"gan_formatter.php",
"gan_node_html.php",
"gan_parser_html.php",
"gan_selector_html.php",
"gan_tokenizer.php",
"gan_xml2array.php",
"pQuery.php"
]
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"LGPL-2.1"
],
"authors": [
{
"name": "Todd Burry",
"email": "todd@vanillaforums.com",
"role": "developer"
}
],
"description": "A jQuery like html dom parser written in php.",
"keywords": [
"dom",
"ganon",
"php"
],
"time": "2016-01-14T20:55:00+00:00"
}
],
"packages-dev": [

151
lib-3rd-party/pquery/IQuery.php vendored Normal file
View File

@@ -0,0 +1,151 @@
<?php
namespace pQuery;
interface IQuery extends \Countable {
/// Methods ///
/**
* Adds the specified class(es) to each of the set of matched elements.
* @param string $classname The name of the class to add. You can add multiple classes by separating them with spaces.
* @return IQuery
*/
function addClass($classname);
/**
* Insert content, specified by the parameter, after each element in the set of matched elements.
* @param string $content The content to add.
* @return IQuery
*/
function after($content);
/**
* Insert content, specified by the parameter, to the end of each element in the set of matched elements.
* @param string $content The content to append.
* @return IQuery
*/
function append($content);
/**
* Get the value of an attribute for the first element in the set of matched elements or set one
* or more attributes for every matched element.
* @param string $name The name of the attribute.
* @param null|string $value The value to set or null to get the current attribute value.
* @return string|IQuery
*/
function attr($name, $value = null);
/**
* Insert content, specified by the parameter, before each element in the set of matched elements.
* @param string $content The content to add.
* @return IQuery
*/
function before($content);
/**
* Remove all child nodes of the set of matched elements from the DOM.
* @return IQuery;
*/
function clear();
/**
* Get the value of a style property for the first element in the set of matched elements or
* set one or more CSS properties for every matched element.
*/
// function css($name, $value = null);
/**
* Determine whether any of the matched elements are assigned the given class.
* @param string $classname The name of the class to check.
*/
function hasClass($classname);
/**
* Get the HTML contents of the first element in the set of matched elements
* or set the HTML contents of every matched element.
* @param string|null $value The value to set.
*/
function html($value = null);
/**
* Insert content, specified by the parameter, to the beginning of each element in the set of matched elements.
* @param string $content The content to add.
*/
function prepend($content);
/**
* Get the value of a property for the first element in the set of matched elements
* or set one or more properties for every matched element.
* @param string $name The name of the property.
* The currently supported properties are `tagname`, `selected`, and `checked`.
* @param null|string $value The value to set or null to get the current property value.
*/
function prop($name, $value = null);
/**
* Remove the set of matched elements from the DOM.
* @param null|string $selector A css query to filter the set of removed nodes.
*/
function remove($selector = null);
/**
* Remove an attribute from each element in the set of matched elements.
* @param string $name The name of the attribute to remove.
*/
function removeAttr($name);
/**
* Remove a single class, multiple classes, or all classes from each element in the set of matched elements.
* @param string $classname The name of the class to remove.
*/
function removeClass($classname);
/**
* Replace each element in the set of matched elements with the provided new content and return the set of elements that was removed.
* @param string $content The content that will replace the nodes.
*/
function replaceWith($content);
/**
* Returns the name of the element.
* @param null|string $tagName A new tag name or null to return the current tag name.
*/
function tagName($value = null);
/**
* Get the combined text contents of each element in the set of matched elements, including their descendants, or set the text contents of the matched elements.
* @param null|string $value A string to set the text or null to return the current text.
*/
function text($value = null);
/**
* Add or remove one or more classes from each element in the set of matched elements,
* depending on either the classs presence or the value of the switch argument.
* @param string $classname
* @param bool|null
*/
function toggleClass($classname, $switch = null);
/**
* Remove the parents of the set of matched elements from the DOM, leaving the matched elements in their place.
*/
function unwrap();
/**
* Get the current value of the first element in the set of matched elements or set the value of every matched element.
* @param string|null $value The new value of the element or null to return the current value.
*/
function val($value = null);
/**
* Wrap an HTML structure around each element in the set of matched elements.
* @param string A tag name or html string specifying the structure to wrap around the matched elements.
*/
function wrap($wrapping_element);
/**
* Wrap an HTML structure around the content of each element in the set of matched elements.
* @param string A tag name or html string specifying the structure to wrap around the content of the matched elements.
*/
function wrapInner($wrapping_element);
}

502
lib-3rd-party/pquery/LICENSE vendored Normal file
View File

@@ -0,0 +1,502 @@
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!

381
lib-3rd-party/pquery/gan_formatter.php vendored Normal file
View File

@@ -0,0 +1,381 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
namespace pQuery;
/**
* Indents text
* @param string $text
* @param int $indent
* @param string $indent_string
* @return string
*/
function indent_text($text, $indent, $indent_string = ' ') {
if ($indent && $indent_string) {
return str_replace("\n", "\n".str_repeat($indent_string, $indent), $text);
} else {
return $text;
}
}
/**
* Class used to format/minify HTML nodes
*
* Used like:
* <code>
* <?php
* $formatter = new HtmlFormatter();
* $formatter->format($root);
* ?>
* </code>
*/
class HtmlFormatter {
/**
* Determines which elements start on a new line and which function as block
* @var array('element' => array('new_line' => true, 'as_block' => true, 'format_inside' => true))
*/
var $block_elements = array(
'p' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h1' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h2' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h3' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h4' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h5' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'h6' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'form' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'fieldset' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'legend' => array('new_line' => true, 'as_block' => false, 'format_inside' => true),
'dl' => array('new_line' => true, 'as_block' => false, 'format_inside' => true),
'dt' => array('new_line' => true, 'as_block' => false, 'format_inside' => true),
'dd' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'ol' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'ul' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'li' => array('new_line' => true, 'as_block' => false, 'format_inside' => true),
'table' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'tr' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'dir' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'menu' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'address' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'blockquote' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'center' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'del' => array('new_line' => true, 'as_block' => false, 'format_inside' => true),
//'div' => array('new_line' => false, 'as_block' => true, 'format_inside' => true),
'hr' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'ins' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'noscript' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'pre' => array('new_line' => true, 'as_block' => true, 'format_inside' => false),
'script' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'style' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'html' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'head' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'body' => array('new_line' => true, 'as_block' => true, 'format_inside' => true),
'title' => array('new_line' => true, 'as_block' => false, 'format_inside' => false)
);
/**
* Determines which characters are considered whitespace
* @var array("\t" => true) True to recognize as new line
*/
var $whitespace = array(
' ' => false,
"\t" => false,
"\x0B" => false,
"\0" => false,
"\n" => true,
"\r" => true
);
/**
* String that is used to generate correct indenting
* @var string
*/
var $indent_string = ' ';
/**
* String that is used to break lines
* @var string
*/
var $linebreak_string = "\n";
/**
* Other formatting options
* @var array
*/
public $options = array(
'img_alt' => '',
'self_close_str' => null,
'attribute_shorttag' => false,
'sort_attributes' => false,
'attributes_case' => CASE_LOWER,
'minify_script' => true
);
/**
* Errors found during formatting
* @var array
*/
var $errors = array();
/**
* Class constructor
* @param array $options {@link $options}
*/
function __construct($options = array()) {
$this->options = array_merge($this->options, $options);
if (isset($options['indent_str']))
$this->indent_string = $options['indent_str'];
if (isset($options['linebreak_str']))
$this->linebreak_string = $options['linebreak_str'];
}
#php4 PHP4 class constructor compatibility
#function HtmlFormatter($options = array()) {return $this->__construct($options);}
#php4e
/**
* Class magic invoke method, performs {@link format()}
* @access private
*/
function __invoke(&$node) {
return $this->format($node);
}
/**
* Minifies HTML / removes unneeded whitespace
* @param DomNode $root
* @param bool $strip_comments
* @param bool $recursive
*/
static function minify_html(&$root, $strip_comments = true, $recursive = true) {
if ($strip_comments) {
foreach($root->select(':comment', false, $recursive, true) as $c) {
$prev = $c->getSibling(-1);
$next = $c->getSibling(1);
$c->delete();
if ($prev && $next && ($prev->isText()) && ($next->isText())) {
$prev->text .= $next->text;
$next->delete();
}
}
}
foreach($root->select('(!pre + !xmp + !style + !script + !"?php" + !"~text~" + !"~comment~"):not-empty > "~text~"', false, $recursive, true) as $c) {
$c->text = preg_replace('`\s+`', ' ', $c->text);
}
}
/**
* Minifies javascript using JSMin+
* @param DomNode $root
* @param string $indent_string
* @param bool $wrap_comment Wrap javascript in HTML comments (<!-- ~text~ //-->)
* @param bool $recursive
* @return bool|array Array of errors on failure, true on succes
*/
static function minify_javascript(&$root, $indent_string = ' ', $wrap_comment = true, $recursive = true) {
#php4 JSMin+ doesn't support PHP4
#return true;
#php4e
#php5
include_once('third_party/jsminplus.php');
$errors = array();
foreach($root->select('script:not-empty > "~text~"', false, $recursive, true) as $c) {
try {
$text = $c->text;
while ($text) {
$text = trim($text);
//Remove comment/CDATA tags at begin and end
if (substr($text, 0, 4) === '<!--') {
$text = substr($text, 5);
continue;
} elseif (strtolower(substr($text, 0, 9)) === '<![cdata[') {
$text = substr($text, 10);
continue;
}
if (($end = substr($text, -3)) && (($end === '-->') || ($end === ']]>'))) {
$text = substr($text, 0, -3);
continue;
}
break;
}
if (trim($text)) {
$text = \JSMinPlus::minify($text);
if ($wrap_comment) {
$text = "<!--\n".$text."\n//-->";
}
if ($indent_string && ($wrap_comment || (strpos($text, "\n") !== false))) {
$text = indent_text("\n".$text, $c->indent(), $indent_string);
}
}
$c->text = $text;
} catch (\Exception $e) {
$errors[] = array($e, $c->parent->dumpLocation());
}
}
return (($errors) ? $errors : true);
#php5e
}
/**
* Formats HTML
* @param DomNode $root
* @param bool $recursive
* @access private
*/
function format_html(&$root, $recursive = null) {
if ($recursive === null) {
$recursive = true;
self::minify_html($root);
} elseif (is_int($recursive)) {
$recursive = (($recursive > 1) ? $recursive - 1 : false);
}
$root_tag = strtolower($root->tag);
$in_block = isset($this->block_elements[$root_tag]) && $this->block_elements[$root_tag]['as_block'];
$child_count = count($root->children);
if (isset($this->options['attributes_case']) && $this->options['attributes_case']) {
$root->attributes = array_change_key_case($root->attributes, $this->options['attributes_case']);
$root->attributes_ns = null;
}
if (isset($this->options['sort_attributes']) && $this->options['sort_attributes']) {
if ($this->options['sort_attributes'] === 'reverse') {
krsort($root->attributes);
} else {
ksort($root->attributes);
}
}
if ($root->select(':element', true, false, true)) {
$root->setTag(strtolower($root->tag), true);
if (($this->options['img_alt'] !== null) && ($root_tag === 'img') && (!isset($root->alt))) {
$root->setAttribute('alt', $this->options['img_alt']);
}
}
if ($this->options['self_close_str'] !== null) {
$root->self_close_str = $this->options['self_close_str'];
}
if ($this->options['attribute_shorttag'] !== null) {
$root->attribute_shorttag = $this->options['attribute_shorttag'];
}
$prev = null;
$n_tag = '';
// $prev_tag = '';
$as_block = false;
$prev_asblock = false;
for($i = 0; $i < $child_count; $i++) {
$n =& $root->children[$i];
$indent = $n->indent();
if (!$n->isText()) {
$n_tag = strtolower($n->tag);
$new_line = isset($this->block_elements[$n_tag]) && $this->block_elements[$n_tag]['new_line'];
$as_block = isset($this->block_elements[$n_tag]) && $this->block_elements[$n_tag]['as_block'];
$format_inside = ((!isset($this->block_elements[$n_tag])) || $this->block_elements[$n_tag]['format_inside']);
if ($prev && ($prev->isText()) && $prev->text && ($char = $prev->text[strlen($prev->text) - 1]) && isset($this->whitespace[$char])) {
if ($this->whitespace[$char]) {
$prev->text .= str_repeat($this->indent_string, $indent);
} else {
$prev->text = substr_replace($prev->text, $this->linebreak_string.str_repeat($this->indent_string, $indent), -1, 1);
}
} elseif (($new_line || $prev_asblock || ($in_block && ($i === 0)))){
if ($prev && ($prev->isText())) {
$prev->text .= $this->linebreak_string.str_repeat($this->indent_string, $indent);
} else {
$root->addText($this->linebreak_string.str_repeat($this->indent_string, $indent), $i);
++$child_count;
}
}
if ($format_inside && count($n->children)) {
//$last = end($n->children);
$last = $n->children[count($n->children) - 1];
$last_tag = ($last) ? strtolower($last->tag) : '';
$last_asblock = ($last_tag && isset($this->block_elements[$last_tag]) && $this->block_elements[$last_tag]['as_block']);
if (($n->childCount(true) > 0) || (trim($n->getPlainText()))) {
if ($last && ($last->isText()) && $last->text && ($char = $last->text[strlen($last->text) - 1]) && isset($this->whitespace[$char])) {
if ($as_block || ($last->index() > 0) || isset($this->whitespace[$last->text[0]])) {
if ($this->whitespace[$char]) {
$last->text .= str_repeat($this->indent_string, $indent);
} else {
$last->text = substr_replace($last->text, $this->linebreak_string.str_repeat($this->indent_string, $indent), -1, 1);
}
}
} elseif (($as_block || $last_asblock || ($in_block && ($i === 0))) && $last) {
if ($last && ($last->isText())) {
$last->text .= $this->linebreak_string.str_repeat($this->indent_string, $indent);
} else {
$n->addText($this->linebreak_string.str_repeat($this->indent_string, $indent));
}
}
} elseif (!trim($n->getInnerText())) {
$n->clear();
}
if ($recursive) {
$this->format_html($n, $recursive);
}
}
} elseif (trim($n->text) && ((($i - 1 < $child_count) && ($char = $n->text[0]) && isset($this->whitespace[$char])) || ($in_block && ($i === 0)))) {
if (isset($this->whitespace[$char])) {
if ($this->whitespace[$char]) {
$n->text = str_repeat($this->indent_string, $indent).$n->text;
} else {
$n->text = substr_replace($n->text, $this->linebreak_string.str_repeat($this->indent_string, $indent), 0, 1);
}
} else {
$n->text = $this->linebreak_string.str_repeat($this->indent_string, $indent).$n->text;
}
}
$prev = $n;
// $prev_tag = $n_tag;
$prev_asblock = $as_block;
}
return true;
}
/**
* Formats HTML/Javascript
* @param DomNode $root
* @see format_html()
*/
function format(&$node) {
$this->errors = array();
if ($this->options['minify_script']) {
$a = self::minify_javascript($node, $this->indent_string, true, true);
if (is_array($a)) {
foreach($a as $error) {
$this->errors[] = $error[0]->getMessage().' >>> '.$error[1];
}
}
}
return $this->format_html($node);
}
}
?>

2855
lib-3rd-party/pquery/gan_node_html.php vendored Normal file

File diff suppressed because it is too large Load Diff

839
lib-3rd-party/pquery/gan_parser_html.php vendored Normal file
View File

@@ -0,0 +1,839 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
namespace pQuery;
/**
* Parses a HTML document
*
* Functionality can be extended by overriding functions or adjusting the tag map.
* Document may contain small errors, the parser will try to recover and resume parsing.
*/
class HtmlParserBase extends TokenizerBase {
/**
* Tag open token, used for "<"
*/
const TOK_TAG_OPEN = 100;
/**
* Tag close token, used for ">"
*/
const TOK_TAG_CLOSE = 101;
/**
* Forward slash token, used for "/"
*/
const TOK_SLASH_FORWARD = 103;
/**
* Backslash token, used for "\"
*/
const TOK_SLASH_BACKWARD = 104;
/**
* String token, used for attribute values (" and ')
*/
const TOK_STRING = 104;
/**
* Equals token, used for "="
*/
const TOK_EQUALS = 105;
/**
* Sets HTML identifiers, tags/attributes are considered identifiers
* @see TokenizerBase::$identifiers
* @access private
*/
var $identifiers = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890:-_!?%';
/**
* Status of the parser (tagname, closing tag, etc)
* @var array
*/
var $status = array();
/**
* Map characters to match their tokens
* @see TokenizerBase::$custom_char_map
* @access private
*/
var $custom_char_map = array(
'<' => self::TOK_TAG_OPEN,
'>' => self::TOK_TAG_CLOSE,
"'" => 'parse_string',
'"' => 'parse_string',
'/' => self::TOK_SLASH_FORWARD,
'\\' => self::TOK_SLASH_BACKWARD,
'=' => self::TOK_EQUALS
);
function __construct($doc = '', $pos = 0) {
parent::__construct($doc, $pos);
$this->parse_all();
}
#php4 PHP4 class constructor compatibility
#function HtmlParserBase($doc = '', $pos = 0) {return $this->__construct($doc, $pos);}
#php4e
/**
Callback functions for certain tags
@var array (TAG_NAME => FUNCTION_NAME)
@internal Function should be a method in the class
@internal Tagname should be lowercase and is everything after <, e.g. "?php" or "!doctype"
@access private
*/
var $tag_map = array(
'!doctype' => 'parse_doctype',
'?' => 'parse_php',
'?php' => 'parse_php',
'%' => 'parse_asp',
'style' => 'parse_style',
'script' => 'parse_script'
);
/**
* Parse a HTML string (attributes)
* @internal Gets called with ' and "
* @return int
*/
protected function parse_string() {
if ($this->next_pos($this->doc[$this->pos], false) !== self::TOK_UNKNOWN) {
--$this->pos;
}
return self::TOK_STRING;
}
/**
* Parse text between tags
* @internal Gets called between tags, uses {@link $status}[last_pos]
* @internal Stores text in {@link $status}[text]
*/
function parse_text() {
$len = $this->pos - 1 - $this->status['last_pos'];
$this->status['text'] = (($len > 0) ? substr($this->doc, $this->status['last_pos'] + 1, $len) : '');
}
/**
* Parse comment tags
* @internal Gets called with HTML comments ("<!--")
* @internal Stores text in {@link $status}[comment]
* @return bool
*/
function parse_comment() {
$this->pos += 3;
if ($this->next_pos('-->', false) !== self::TOK_UNKNOWN) {
$this->status['comment'] = $this->getTokenString(1, -1);
--$this->pos;
} else {
$this->status['comment'] = $this->getTokenString(1, -1);
$this->pos += 2;
}
$this->status['last_pos'] = $this->pos;
return true;
}
/**
* Parse doctype tag
* @internal Gets called with doctype ("<!doctype")
* @internal Stores text in {@link $status}[dtd]
* @return bool
*/
function parse_doctype() {
$start = $this->pos;
if ($this->next_search('[>', false) === self::TOK_UNKNOWN) {
if ($this->doc[$this->pos] === '[') {
if (($this->next_pos(']', false) !== self::TOK_UNKNOWN) || ($this->next_pos('>', false) !== self::TOK_UNKNOWN)) {
$this->addError('Invalid doctype');
return false;
}
}
$this->token_start = $start;
$this->status['dtd'] = $this->getTokenString(2, -1);
$this->status['last_pos'] = $this->pos;
return true;
} else {
$this->addError('Invalid doctype');
return false;
}
}
/**
* Parse cdata tag
* @internal Gets called with cdata ("<![cdata")
* @internal Stores text in {@link $status}[cdata]
* @return bool
*/
function parse_cdata() {
if ($this->next_pos(']]>', false) === self::TOK_UNKNOWN) {
$this->status['cdata'] = $this->getTokenString(9, -1);
$this->status['last_pos'] = $this->pos + 2;
return true;
} else {
$this->addError('Invalid cdata tag');
return false;
}
}
/**
* Parse php tags
* @internal Gets called with php tags ("<?php")
* @return bool
*/
function parse_php() {
$start = $this->pos;
if ($this->next_pos('?>', false) !== self::TOK_UNKNOWN) {
$this->pos -= 2; //End of file
}
$len = $this->pos - 1 - $start;
$this->status['text'] = (($len > 0) ? substr($this->doc, $start + 1, $len) : '');
$this->status['last_pos'] = ++$this->pos;
return true;
}
/**
* Parse asp tags
* @internal Gets called with asp tags ("<%")
* @return bool
*/
function parse_asp() {
$start = $this->pos;
if ($this->next_pos('%>', false) !== self::TOK_UNKNOWN) {
$this->pos -= 2; //End of file
}
$len = $this->pos - 1 - $start;
$this->status['text'] = (($len > 0) ? substr($this->doc, $start + 1, $len) : '');
$this->status['last_pos'] = ++$this->pos;
return true;
}
/**
* Parse style tags
* @internal Gets called with php tags ("<style>")
* @return bool
*/
function parse_style() {
if ($this->parse_attributes() && ($this->token === self::TOK_TAG_CLOSE) && ($start = $this->pos) && ($this->next_pos('</style>', false) === self::TOK_UNKNOWN)) {
$len = $this->pos - 1 - $start;
$this->status['text'] = (($len > 0) ? substr($this->doc, $start + 1, $len) : '');
$this->pos += 7;
$this->status['last_pos'] = $this->pos;
return true;
} else {
$this->addError('No end for style tag found');
return false;
}
}
/**
* Parse script tags
* @internal Gets called with php tags ("<script>")
* @return bool
*/
function parse_script() {
if ($this->parse_attributes() && ($this->token === self::TOK_TAG_CLOSE) && ($start = $this->pos) && ($this->next_pos('</script>', false) === self::TOK_UNKNOWN)) {
$len = $this->pos - 1 - $start;
$this->status['text'] = (($len > 0) ? substr($this->doc, $start + 1, $len) : '');
$this->pos += 8;
$this->status['last_pos'] = $this->pos;
return true;
} else {
$this->addError('No end for script tag found');
return false;
}
}
/**
* Parse conditional tags (+ all conditional tags inside)
* @internal Gets called with IE conditionals ("<![if]" and "<!--[if]")
* @internal Stores condition in {@link $status}[tag_condition]
* @return bool
*/
function parse_conditional() {
if ($this->status['closing_tag']) {
$this->pos += 8;
} else {
$this->pos += (($this->status['comment']) ? 5 : 3);
if ($this->next_pos(']', false) !== self::TOK_UNKNOWN) {
$this->addError('"]" not found in conditional tag');
return false;
}
$this->status['tag_condition'] = $this->getTokenString(0, -1);
}
if ($this->next_no_whitespace() !== self::TOK_TAG_CLOSE) {
$this->addError('No ">" tag found 2 for conditional tag');
return false;
}
if ($this->status['comment']) {
$this->status['last_pos'] = $this->pos;
if ($this->next_pos('-->', false) !== self::TOK_UNKNOWN) {
$this->addError('No ending tag found for conditional tag');
$this->pos = $this->size - 1;
$len = $this->pos - 1 - $this->status['last_pos'];
$this->status['text'] = (($len > 0) ? substr($this->doc, $this->status['last_pos'] + 1, $len) : '');
} else {
$len = $this->pos - 10 - $this->status['last_pos'];
$this->status['text'] = (($len > 0) ? substr($this->doc, $this->status['last_pos'] + 1, $len) : '');
$this->pos += 2;
}
}
$this->status['last_pos'] = $this->pos;
return true;
}
/**
* Parse attributes (names + value)
* @internal Stores attributes in {@link $status}[attributes] (array(ATTR => VAL))
* @return bool
*/
function parse_attributes() {
$this->status['attributes'] = array();
while ($this->next_no_whitespace() === self::TOK_IDENTIFIER) {
$attr = $this->getTokenString();
if (($attr === '?') || ($attr === '%')) {
//Probably closing tags
break;
}
if ($this->next_no_whitespace() === self::TOK_EQUALS) {
if ($this->next_no_whitespace() === self::TOK_STRING) {
$val = $this->getTokenString(1, -1);
} else {
$this->token_start = $this->pos;
if (!isset($stop)) {
$stop = $this->whitespace;
$stop['<'] = true;
$stop['>'] = true;
}
while ((++$this->pos < $this->size) && (!isset($stop[$this->doc[$this->pos]]))) {
// Do nothing.
}
--$this->pos;
$val = $this->getTokenString();
if (trim($val) === '') {
$this->addError('Invalid attribute value');
return false;
}
}
} else {
$val = $attr;
$this->pos = (($this->token_start) ? $this->token_start : $this->pos) - 1;
}
$this->status['attributes'][$attr] = $val;
}
return true;
}
/**
* Default callback for tags
* @internal Gets called after the tagname (<html*ENTERS_HERE* attribute="value">)
* @return bool
*/
function parse_tag_default() {
if ($this->status['closing_tag']) {
$this->status['attributes'] = array();
$this->next_no_whitespace();
} else {
if (!$this->parse_attributes()) {
return false;
}
}
if ($this->token !== self::TOK_TAG_CLOSE) {
if ($this->token === self::TOK_SLASH_FORWARD) {
$this->status['self_close'] = true;
$this->next();
} elseif ((($this->status['tag_name'][0] === '?') && ($this->doc[$this->pos] === '?')) || (($this->status['tag_name'][0] === '%') && ($this->doc[$this->pos] === '%'))) {
$this->status['self_close'] = true;
$this->pos++;
if (isset($this->char_map[$this->doc[$this->pos]]) && (!is_string($this->char_map[$this->doc[$this->pos]]))) {
$this->token = $this->char_map[$this->doc[$this->pos]];
} else {
$this->token = self::TOK_UNKNOWN;
}
}/* else {
$this->status['self_close'] = false;
}*/
}
if ($this->token !== self::TOK_TAG_CLOSE) {
$this->addError('Expected ">", but found "'.$this->getTokenString().'"');
if ($this->next_pos('>', false) !== self::TOK_UNKNOWN) {
$this->addError('No ">" tag found for "'.$this->status['tag_name'].'" tag');
return false;
}
}
return true;
}
/**
* Parse tag
* @internal Gets called after opening tag (<*ENTERS_HERE*html attribute="value">)
* @internal Stores information about the tag in {@link $status} (comment, closing_tag, tag_name)
* @return bool
*/
function parse_tag() {
$start = $this->pos;
$this->status['self_close'] = false;
$this->parse_text();
$next = (($this->pos + 1) < $this->size) ? $this->doc[$this->pos + 1] : '';
if ($next === '!') {
$this->status['closing_tag'] = false;
if (substr($this->doc, $this->pos + 2, 2) === '--') {
$this->status['comment'] = true;
if (($this->doc[$this->pos + 4] === '[') && (strcasecmp(substr($this->doc, $this->pos + 5, 2), 'if') === 0)) {
return $this->parse_conditional();
} else {
return $this->parse_comment();
}
} else {
$this->status['comment'] = false;
if ($this->doc[$this->pos + 2] === '[') {
if (strcasecmp(substr($this->doc, $this->pos + 3, 2), 'if') === 0) {
return $this->parse_conditional();
} elseif (strcasecmp(substr($this->doc, $this->pos + 3, 5), 'endif') === 0) {
$this->status['closing_tag'] = true;
return $this->parse_conditional();
} elseif (strcasecmp(substr($this->doc, $this->pos + 3, 5), 'cdata') === 0) {
return $this->parse_cdata();
}
}
}
} elseif ($next === '/') {
$this->status['closing_tag'] = true;
++$this->pos;
} else {
$this->status['closing_tag'] = false;
}
if ($this->next() !== self::TOK_IDENTIFIER) {
$this->addError('Tagname expected');
//if ($this->next_pos('>', false) === self::TOK_UNKNOWN) {
$this->status['last_pos'] = $start - 1;
return true;
//} else {
// return false;
//}
}
$tag = $this->getTokenString();
$this->status['tag_name'] = $tag;
$tag = strtolower($tag);
if (isset($this->tag_map[$tag])) {
$res = $this->{$this->tag_map[$tag]}();
} else {
$res = $this->parse_tag_default();
}
$this->status['last_pos'] = $this->pos;
return $res;
}
/**
* Parse full document
* @return bool
*/
function parse_all() {
$this->errors = array();
$this->status['last_pos'] = -1;
if (($this->token === self::TOK_TAG_OPEN) || ($this->next_pos('<', false) === self::TOK_UNKNOWN)) {
do {
if (!$this->parse_tag()) {
return false;
}
} while ($this->next_pos('<') !== self::TOK_NULL);
}
$this->pos = $this->size;
$this->parse_text();
return true;
}
}
/**
* Parses a HTML document into a HTML DOM
*/
class HtmlParser extends HtmlParserBase {
/**
* Root object
* @internal If string, then it will create a new instance as root
* @var DomNode
*/
var $root = 'pQuery\\DomNode';
/**
* Current parsing hierarchy
* @internal Root is always at index 0, current tag is at the end of the array
* @var array
* @access private
*/
var $hierarchy = array();
/**
* Tags that don't need closing tags
* @var array
* @access private
*/
var $tags_selfclose = array(
'area' => true,
'base' => true,
'basefont' => true,
'br' => true,
'col' => true,
'command' => true,
'embed' => true,
'frame' => true,
'hr' => true,
'img' => true,
'input' => true,
'ins' => true,
'keygen' => true,
'link' => true,
'meta' => true,
'param' => true,
'source' => true,
'track' => true,
'wbr' => true
);
/**
* Class constructor
* @param string $doc Document to be tokenized
* @param int $pos Position to start parsing
* @param DomNode $root Root node, null to auto create
*/
function __construct($doc = '', $pos = 0, $root = null) {
if ($root === null) {
$root = new $this->root('~root~', null);
}
$this->root =& $root;
parent::__construct($doc, $pos);
}
#php4 PHP4 class constructor compatibility
#function HtmlParser($doc = '', $pos = 0, $root = null) {return $this->__construct($doc, $pos, $root);}
#php4e
/**
* Class magic invoke method, performs {@link select()}
* @return array
* @access private
*/
function __invoke($query = '*') {
return $this->select($query);
}
/**
* Class magic toString method, performs {@link DomNode::toString()}
* @return string
* @access private
*/
function __toString() {
return $this->root->getInnerText();
}
/**
* Performs a css select query on the root node
* @see DomNode::select()
* @return array
*/
function select($query = '*', $index = false, $recursive = true, $check_self = false) {
return $this->root->select($query, $index, $recursive, $check_self);
}
/**
* Updates the current hierarchy status and checks for
* correct opening/closing of tags
* @param bool $self_close Is current tag self closing? Null to use {@link tags_selfclose}
* @internal This is were most of the nodes get added
* @access private
*/
protected function parse_hierarchy($self_close = null) {
if ($self_close === null) {
$this->status['self_close'] = ($self_close = isset($this->tags_selfclose[strtolower($this->status['tag_name'])]));
}
if ($self_close) {
if ($this->status['closing_tag']) {
//$c = end($this->hierarchy)->children
$c = $this->hierarchy[count($this->hierarchy) - 1]->children;
$found = false;
for ($count = count($c), $i = $count - 1; $i >= 0; $i--) {
if (strcasecmp($c[$i]->tag, $this->status['tag_name']) === 0) {
for($ii = $i + 1; $ii < $count; $ii++) {
$index = null; //Needs to be passed by ref
$c[$i + 1]->changeParent($c[$i], $index);
}
$c[$i]->self_close = false;
$found = true;
break;
}
}
if (!$found) {
$this->addError('Closing tag "'.$this->status['tag_name'].'" which is not open');
}
} elseif ($this->status['tag_name'][0] === '?') {
//end($this->hierarchy)->addXML($this->status['tag_name'], '', $this->status['attributes']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addXML($this->status['tag_name'], '', $this->status['attributes'], $index);
} elseif ($this->status['tag_name'][0] === '%') {
//end($this->hierarchy)->addASP($this->status['tag_name'], '', $this->status['attributes']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addASP($this->status['tag_name'], '', $this->status['attributes'], $index);
} else {
//end($this->hierarchy)->addChild($this->status);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addChild($this->status, $index);
}
} elseif ($this->status['closing_tag']) {
$found = false;
for ($count = count($this->hierarchy), $i = $count - 1; $i >= 0; $i--) {
if (strcasecmp($this->hierarchy[$i]->tag, $this->status['tag_name']) === 0) {
for($ii = ($count - $i - 1); $ii >= 0; $ii--) {
$e = array_pop($this->hierarchy);
if ($ii > 0) {
$this->addError('Closing tag "'.$this->status['tag_name'].'" while "'.$e->tag.'" is not closed yet');
}
}
$found = true;
break;
}
}
if (!$found) {
$this->addError('Closing tag "'.$this->status['tag_name'].'" which is not open');
}
} else {
//$this->hierarchy[] = end($this->hierarchy)->addChild($this->status);
$index = null; //Needs to be passed by ref
$this->hierarchy[] = $this->hierarchy[count($this->hierarchy) - 1]->addChild($this->status, $index);
}
}
function parse_cdata() {
if (!parent::parse_cdata()) {return false;}
//end($this->hierarchy)->addCDATA($this->status['cdata']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addCDATA($this->status['cdata'], $index);
return true;
}
function parse_comment() {
if (!parent::parse_comment()) {return false;}
//end($this->hierarchy)->addComment($this->status['comment']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addComment($this->status['comment'], $index);
return true;
}
function parse_conditional() {
if (!parent::parse_conditional()) {return false;}
if ($this->status['comment']) {
//$e = end($this->hierarchy)->addConditional($this->status['tag_condition'], true);
$index = null; //Needs to be passed by ref
$e = $this->hierarchy[count($this->hierarchy) - 1]->addConditional($this->status['tag_condition'], true, $index);
if ($this->status['text'] !== '') {
$index = null; //Needs to be passed by ref
$e->addText($this->status['text'], $index);
}
} else {
if ($this->status['closing_tag']) {
$this->parse_hierarchy(false);
} else {
//$this->hierarchy[] = end($this->hierarchy)->addConditional($this->status['tag_condition'], false);
$index = null; //Needs to be passed by ref
$this->hierarchy[] = $this->hierarchy[count($this->hierarchy) - 1]->addConditional($this->status['tag_condition'], false, $index);
}
}
return true;
}
function parse_doctype() {
if (!parent::parse_doctype()) {return false;}
//end($this->hierarchy)->addDoctype($this->status['dtd']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addDoctype($this->status['dtd'], $index);
return true;
}
function parse_php() {
if (!parent::parse_php()) {return false;}
//end($this->hierarchy)->addXML('php', $this->status['text']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addXML('php', $this->status['text'], $index);
return true;
}
function parse_asp() {
if (!parent::parse_asp()) {return false;}
//end($this->hierarchy)->addASP('', $this->status['text']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addASP('', $this->status['text'], $index);
return true;
}
function parse_script() {
if (!parent::parse_script()) {return false;}
//$e = end($this->hierarchy)->addChild($this->status);
$index = null; //Needs to be passed by ref
$e = $this->hierarchy[count($this->hierarchy) - 1]->addChild($this->status, $index);
if ($this->status['text'] !== '') {
$index = null; //Needs to be passed by ref
$e->addText($this->status['text'], $index);
}
return true;
}
function parse_style() {
if (!parent::parse_style()) {return false;}
//$e = end($this->hierarchy)->addChild($this->status);
$index = null; //Needs to be passed by ref
$e = $this->hierarchy[count($this->hierarchy) - 1]->addChild($this->status, $index);
if ($this->status['text'] !== '') {
$index = null; //Needs to be passed by ref
$e->addText($this->status['text'], $index);
}
return true;
}
function parse_tag_default() {
if (!parent::parse_tag_default()) {return false;}
$this->parse_hierarchy(($this->status['self_close']) ? true : null);
return true;
}
function parse_text() {
parent::parse_text();
if ($this->status['text'] !== '') {
//end($this->hierarchy)->addText($this->status['text']);
$index = null; //Needs to be passed by ref
$this->hierarchy[count($this->hierarchy) - 1]->addText($this->status['text'], $index);
}
}
function parse_all() {
$this->hierarchy = array(&$this->root);
return ((parent::parse_all()) ? $this->root : false);
}
}
/**
* HTML5 specific parser (adds support for omittable closing tags)
*/
class Html5Parser extends HtmlParser {
/**
* Tags with ommitable closing tags
* @var array array('tag2' => 'tag1') will close tag1 if following (not child) tag is tag2
* @access private
*/
var $tags_optional_close = array(
//Current tag => Previous tag
'li' => array('li' => true),
'dt' => array('dt' => true, 'dd' => true),
'dd' => array('dt' => true, 'dd' => true),
'address' => array('p' => true),
'article' => array('p' => true),
'aside' => array('p' => true),
'blockquote' => array('p' => true),
'dir' => array('p' => true),
'div' => array('p' => true),
'dl' => array('p' => true),
'fieldset' => array('p' => true),
'footer' => array('p' => true),
'form' => array('p' => true),
'h1' => array('p' => true),
'h2' => array('p' => true),
'h3' => array('p' => true),
'h4' => array('p' => true),
'h5' => array('p' => true),
'h6' => array('p' => true),
'header' => array('p' => true),
'hgroup' => array('p' => true),
'hr' => array('p' => true),
'menu' => array('p' => true),
'nav' => array('p' => true),
'ol' => array('p' => true),
'p' => array('p' => true),
'pre' => array('p' => true),
'section' => array('p' => true),
'table' => array('p' => true),
'ul' => array('p' => true),
'rt' => array('rt' => true, 'rp' => true),
'rp' => array('rt' => true, 'rp' => true),
'optgroup' => array('optgroup' => true, 'option' => true),
'option' => array('option'),
'tbody' => array('thread' => true, 'tbody' => true, 'tfoot' => true),
'tfoot' => array('thread' => true, 'tbody' => true),
'tr' => array('tr' => true),
'td' => array('td' => true, 'th' => true),
'th' => array('td' => true, 'th' => true),
'body' => array('head' => true)
);
protected function parse_hierarchy($self_close = null) {
$tag_curr = strtolower($this->status['tag_name']);
if ($self_close === null) {
$this->status['self_close'] = ($self_close = isset($this->tags_selfclose[$tag_curr]));
}
if (! ($self_close || $this->status['closing_tag'])) {
//$tag_prev = strtolower(end($this->hierarchy)->tag);
$tag_prev = strtolower($this->hierarchy[count($this->hierarchy) - 1]->tag);
if (isset($this->tags_optional_close[$tag_curr]) && isset($this->tags_optional_close[$tag_curr][$tag_prev])) {
array_pop($this->hierarchy);
}
}
return parent::parse_hierarchy($self_close);
}
}
?>

View File

@@ -0,0 +1,949 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
namespace pQuery;
/**
* Tokenizes a css selector query
*/
class CSSQueryTokenizer extends TokenizerBase {
/**
* Opening bracket token, used for "["
*/
const TOK_BRACKET_OPEN = 100;
/**
* Closing bracket token, used for "]"
*/
const TOK_BRACKET_CLOSE = 101;
/**
* Opening brace token, used for "("
*/
const TOK_BRACE_OPEN = 102;
/**
* Closing brace token, used for ")"
*/
const TOK_BRACE_CLOSE = 103;
/**
* String token
*/
const TOK_STRING = 104;
/**
* Colon token, used for ":"
*/
const TOK_COLON = 105;
/**
* Comma token, used for ","
*/
const TOK_COMMA = 106;
/**
* "Not" token, used for "!"
*/
const TOK_NOT = 107;
/**
* "All" token, used for "*" in query
*/
const TOK_ALL = 108;
/**
* Pipe token, used for "|"
*/
const TOK_PIPE = 109;
/**
* Plus token, used for "+"
*/
const TOK_PLUS = 110;
/**
* "Sibling" token, used for "~" in query
*/
const TOK_SIBLING = 111;
/**
* Class token, used for "." in query
*/
const TOK_CLASS = 112;
/**
* ID token, used for "#" in query
*/
const TOK_ID = 113;
/**
* Child token, used for ">" in query
*/
const TOK_CHILD = 114;
/**
* Attribute compare prefix token, used for "|="
*/
const TOK_COMPARE_PREFIX = 115;
/**
* Attribute contains token, used for "*="
*/
const TOK_COMPARE_CONTAINS = 116;
/**
* Attribute contains word token, used for "~="
*/
const TOK_COMPARE_CONTAINS_WORD = 117;
/**
* Attribute compare end token, used for "$="
*/
const TOK_COMPARE_ENDS = 118;
/**
* Attribute equals token, used for "="
*/
const TOK_COMPARE_EQUALS = 119;
/**
* Attribute not equal token, used for "!="
*/
const TOK_COMPARE_NOT_EQUAL = 120;
/**
* Attribute compare bigger than token, used for ">="
*/
const TOK_COMPARE_BIGGER_THAN = 121;
/**
* Attribute compare smaller than token, used for "<="
*/
const TOK_COMPARE_SMALLER_THAN = 122;
/**
* Attribute compare with regex, used for "%="
*/
const TOK_COMPARE_REGEX = 123;
/**
* Attribute compare start token, used for "^="
*/
const TOK_COMPARE_STARTS = 124;
/**
* Sets query identifiers
* @see TokenizerBase::$identifiers
* @access private
*/
var $identifiers = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890_-?';
/**
* Map characters to match their tokens
* @see TokenizerBase::$custom_char_map
* @access private
*/
var $custom_char_map = array(
'.' => self::TOK_CLASS,
'#' => self::TOK_ID,
',' => self::TOK_COMMA,
'>' => 'parse_gt',//self::TOK_CHILD,
'+' => self::TOK_PLUS,
'~' => 'parse_sibling',
'|' => 'parse_pipe',
'*' => 'parse_star',
'$' => 'parse_compare',
'=' => self::TOK_COMPARE_EQUALS,
'!' => 'parse_not',
'%' => 'parse_compare',
'^' => 'parse_compare',
'<' => 'parse_compare',
'"' => 'parse_string',
"'" => 'parse_string',
'(' => self::TOK_BRACE_OPEN,
')' => self::TOK_BRACE_CLOSE,
'[' => self::TOK_BRACKET_OPEN,
']' => self::TOK_BRACKET_CLOSE,
':' => self::TOK_COLON
);
/**
* Parse ">" character
* @internal Could be {@link TOK_CHILD} or {@link TOK_COMPARE_BIGGER_THAN}
* @return int
*/
protected function parse_gt() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
++$this->pos;
return ($this->token = self::TOK_COMPARE_BIGGER_THAN);
} else {
return ($this->token = self::TOK_CHILD);
}
}
/**
* Parse "~" character
* @internal Could be {@link TOK_SIBLING} or {@link TOK_COMPARE_CONTAINS_WORD}
* @return int
*/
protected function parse_sibling() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
++$this->pos;
return ($this->token = self::TOK_COMPARE_CONTAINS_WORD);
} else {
return ($this->token = self::TOK_SIBLING);
}
}
/**
* Parse "|" character
* @internal Could be {@link TOK_PIPE} or {@link TOK_COMPARE_PREFIX}
* @return int
*/
protected function parse_pipe() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
++$this->pos;
return ($this->token = self::TOK_COMPARE_PREFIX);
} else {
return ($this->token = self::TOK_PIPE);
}
}
/**
* Parse "*" character
* @internal Could be {@link TOK_ALL} or {@link TOK_COMPARE_CONTAINS}
* @return int
*/
protected function parse_star() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
++$this->pos;
return ($this->token = self::TOK_COMPARE_CONTAINS);
} else {
return ($this->token = self::TOK_ALL);
}
}
/**
* Parse "!" character
* @internal Could be {@link TOK_NOT} or {@link TOK_COMPARE_NOT_EQUAL}
* @return int
*/
protected function parse_not() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
++$this->pos;
return ($this->token = self::TOK_COMPARE_NOT_EQUAL);
} else {
return ($this->token = self::TOK_NOT);
}
}
/**
* Parse several compare characters
* @return int
*/
protected function parse_compare() {
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === '=')) {
switch($this->doc[$this->pos++]) {
case '$':
return ($this->token = self::TOK_COMPARE_ENDS);
case '%':
return ($this->token = self::TOK_COMPARE_REGEX);
case '^':
return ($this->token = self::TOK_COMPARE_STARTS);
case '<':
return ($this->token = self::TOK_COMPARE_SMALLER_THAN);
}
}
return false;
}
/**
* Parse strings (" and ')
* @return int
*/
protected function parse_string() {
$char = $this->doc[$this->pos];
while (true) {
if ($this->next_search($char.'\\', false) !== self::TOK_NULL) {
if($this->doc[$this->pos] === $char) {
break;
} else {
++$this->pos;
}
} else {
$this->pos = $this->size - 1;
break;
}
}
return ($this->token = self::TOK_STRING);
}
}
/**
* Performs a css select query on HTML nodes
*/
class HtmlSelector {
/**
* Parser object
* @internal If string, then it will create a new instance as parser
* @var CSSQueryTokenizer
*/
var $parser = 'pQuery\\CSSQueryTokenizer';
/**
* Target of queries
* @var DomNode
*/
var $root = null;
/**
* Last performed query, result in {@link $result}
* @var string
*/
var $query = '';
/**
* Array of matching nodes
* @var array
*/
var $result = array();
/**
* Include root in search, if false the only child nodes are evaluated
* @var bool
*/
var $search_root = false;
/**
* Search recursively
* @var bool
*/
var $search_recursive = true;
/**
* Extra function map for custom filters
* @var array
* @internal array('root' => 'filter_root') will cause the
* selector to call $this->filter_root at :root
* @see DomNode::$filter_map
*/
var $custom_filter_map = array();
/**
* Class constructor
* @param DomNode $root {@link $root}
* @param string $query
* @param bool $search_root {@link $search_root}
* @param bool $search_recursive {@link $search_recursive}
* @param CSSQueryTokenizer $parser If null, then default class will be used
*/
function __construct($root, $query = '*', $search_root = false, $search_recursive = true, $parser = null) {
if ($parser === null) {
$parser = new $this->parser();
}
$this->parser = $parser;
$this->root =& $root;
$this->search_root = $search_root;
$this->search_recursive = $search_recursive;
$this->select($query);
}
#php4 PHP4 class constructor compatibility
#function HtmlSelector($root, $query = '*', $search_root = false, $search_recursive = true, $parser = null) {return $this->__construct($root, $query, $search_root, $search_recursive, $parser);}
#php4e
/**
* toString method, returns {@link $query}
* @return string
* @access private
*/
function __toString() {
return $this->query;
}
/**
* Class magic invoke method, performs {@link select()}
* @return array
* @access private
*/
function __invoke($query = '*') {
return $this->select($query);
}
/**
* Perform query
* @param string $query
* @return array False on failure
*/
function select($query = '*') {
$this->parser->setDoc($query);
$this->query = $query;
return (($this->parse()) ? $this->result : false);
}
/**
* Trigger error
* @param string $error
* @internal %pos% and %tok% will be replace in string with position and token(string)
* @access private
*/
protected function error($error) {
$error = htmlentities(str_replace(
array('%tok%', '%pos%'),
array($this->parser->getTokenString(), (int) $this->parser->getPos()),
$error
));
trigger_error($error);
}
/**
* Get identifier (parse identifier or string)
* @param bool $do_error Error on failure
* @return string False on failure
* @access private
*/
protected function parse_getIdentifier($do_error = true) {
$p =& $this->parser;
$tok = $p->token;
if ($tok === CSSQueryTokenizer::TOK_IDENTIFIER) {
return $p->getTokenString();
} elseif($tok === CSSQueryTokenizer::TOK_STRING) {
return str_replace(array('\\\'', '\\"', '\\\\'), array('\'', '"', '\\'), $p->getTokenString(1, -1));
} elseif ($do_error) {
$this->error('Expected identifier at %pos%!');
}
return false;
}
/**
* Get query conditions (tag, attribute and filter conditions)
* @return array False on failure
* @see DomNode::match()
* @access private
*/
protected function parse_conditions() {
$p =& $this->parser;
$tok = $p->token;
if ($tok === CSSQueryTokenizer::TOK_NULL) {
$this->error('Invalid search pattern(1): Empty string!');
return false;
}
$conditions_all = array();
//Tags
while ($tok !== CSSQueryTokenizer::TOK_NULL) {
$conditions = array('tags' => array(), 'attributes' => array());
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$tok = $p->next();
if (($tok === CSSQueryTokenizer::TOK_PIPE) && ($tok = $p->next()) && ($tok !== CSSQueryTokenizer::TOK_ALL)) {
if (($tag = $this->parse_getIdentifier()) === false) {
return false;
}
$conditions['tags'][] = array(
'tag' => $tag,
'compare' => 'name'
);
$tok = $p->next_no_whitespace();
} else {
$conditions['tags'][''] = array(
'tag' => '',
'match' => false
);
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$tok = $p->next_no_whitespace();
}
}
} elseif ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$conditions['tags'][] = array(
'tag' => '',
'compare' => 'namespace',
);
} elseif (($tag = $this->parse_getIdentifier()) !== false) {
$conditions['tags'][] = array(
'tag' => $tag,
'compare' => 'total',
);
} else {
return false;
}
$tok = $p->next_no_whitespace();
} elseif ($tok === CSSQueryTokenizer::TOK_BRACE_OPEN) {
$tok = $p->next_no_whitespace();
$last_mode = 'or';
while (true) {
$match = true;
$compare = 'total';
if ($tok === CSSQueryTokenizer::TOK_NOT) {
$match = false;
$tok = $p->next_no_whitespace();
}
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_PIPE) {
$this->next();
$compare = 'name';
if (($tag = $this->parse_getIdentifier()) === false) {
return false;
}
}
} elseif ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$tag = '';
$compare = 'namespace';
} elseif (($tag = $this->parse_getIdentifier()) === false) {
return false;
}
$tok = $p->next_no_whitespace();
} else {
if (($tag = $this->parse_getIdentifier()) === false) {
return false;
}
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$compare = 'namespace';
} elseif (($tag_name = $this->parse_getIdentifier()) !== false) {
$tag = $tag.':'.$tag_name;
} else {
return false;
}
$tok = $p->next_no_whitespace();
}
}
if ($tok === CSSQueryTokenizer::TOK_WHITESPACE) {
$tok = $p->next_no_whitespace();
}
$conditions['tags'][] = array(
'tag' => $tag,
'match' => $match,
'operator' => $last_mode,
'compare' => $compare
);
switch($tok) {
case CSSQueryTokenizer::TOK_COMMA:
$tok = $p->next_no_whitespace();
$last_mode = 'or';
continue 2;
case CSSQueryTokenizer::TOK_PLUS:
$tok = $p->next_no_whitespace();
$last_mode = 'and';
continue 2;
case CSSQueryTokenizer::TOK_BRACE_CLOSE:
$tok = $p->next();
break 2;
default:
$this->error('Expected closing brace or comma at pos %pos%!');
return false;
}
}
} elseif (($tag = $this->parse_getIdentifier(false)) !== false) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$conditions['tags'][] = array(
'tag' => $tag,
'compare' => 'namespace'
);
} elseif (($tag_name = $this->parse_getIdentifier()) !== false) {
$tag = $tag.':'.$tag_name;
$conditions['tags'][] = array(
'tag' => $tag,
'match' => true
);
} else {
return false;
}
$tok = $p->next();
} elseif ($tag === 'text' && $tok === CSSQueryTokenizer::TOK_BRACE_OPEN) {
$pos = $p->getPos();
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_BRACE_CLOSE) {
$conditions['tags'][] = array(
'tag' => '~text~',
'match' => true
);
$p->next();
} else {
$p->setPos($pos);
}
} else {
$conditions['tags'][] = array(
'tag' => $tag,
'match' => true
);
}
} else {
unset($conditions['tags']);
}
//Class
$last_mode = 'or';
if ($tok === CSSQueryTokenizer::TOK_CLASS) {
$p->next();
if (($class = $this->parse_getIdentifier()) === false) {
return false;
}
$conditions['attributes'][] = array(
'attribute' => 'class',
'operator_value' => 'contains_word',
'value' => $class,
'operator_result' => $last_mode
);
$last_mode = 'and';
$tok = $p->next();
}
//ID
if ($tok === CSSQueryTokenizer::TOK_ID) {
$p->next();
if (($id = $this->parse_getIdentifier()) === false) {
return false;
}
$conditions['attributes'][] = array(
'attribute' => 'id',
'operator_value' => 'equals',
'value' => $id,
'operator_result' => $last_mode
);
$last_mode = 'and';
$tok = $p->next();
}
//Attributes
if ($tok === CSSQueryTokenizer::TOK_BRACKET_OPEN) {
$tok = $p->next_no_whitespace();
while (true) {
$match = true;
$compare = 'total';
if ($tok === CSSQueryTokenizer::TOK_NOT) {
$match = false;
$tok = $p->next_no_whitespace();
}
if ($tok === CSSQueryTokenizer::TOK_ALL) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if (($attribute = $this->parse_getIdentifier()) === false) {
return false;
}
$compare = 'name';
$tok = $p->next();
} else {
$this->error('Expected pipe at pos %pos%!');
return false;
}
} elseif ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if (($tag = $this->parse_getIdentifier()) === false) {
return false;
}
$tok = $p->next_no_whitespace();
} elseif (($attribute = $this->parse_getIdentifier()) !== false) {
$tok = $p->next();
if ($tok === CSSQueryTokenizer::TOK_PIPE) {
$tok = $p->next();
if (($attribute_name = $this->parse_getIdentifier()) !== false) {
$attribute = $attribute.':'.$attribute_name;
} else {
return false;
}
$tok = $p->next();
}
} else {
return false;
}
if ($tok === CSSQueryTokenizer::TOK_WHITESPACE) {
$tok = $p->next_no_whitespace();
}
$operator_value = '';
$val = '';
switch($tok) {
case CSSQueryTokenizer::TOK_COMPARE_PREFIX:
case CSSQueryTokenizer::TOK_COMPARE_CONTAINS:
case CSSQueryTokenizer::TOK_COMPARE_CONTAINS_WORD:
case CSSQueryTokenizer::TOK_COMPARE_ENDS:
case CSSQueryTokenizer::TOK_COMPARE_EQUALS:
case CSSQueryTokenizer::TOK_COMPARE_NOT_EQUAL:
case CSSQueryTokenizer::TOK_COMPARE_REGEX:
case CSSQueryTokenizer::TOK_COMPARE_STARTS:
case CSSQueryTokenizer::TOK_COMPARE_BIGGER_THAN:
case CSSQueryTokenizer::TOK_COMPARE_SMALLER_THAN:
$operator_value = $p->getTokenString(($tok === CSSQueryTokenizer::TOK_COMPARE_EQUALS) ? 0 : -1);
$p->next_no_whitespace();
if (($val = $this->parse_getIdentifier()) === false) {
return false;
}
$tok = $p->next_no_whitespace();
break;
}
if ($operator_value && $val) {
$conditions['attributes'][] = array(
'attribute' => $attribute,
'operator_value' => $operator_value,
'value' => $val,
'match' => $match,
'operator_result' => $last_mode,
'compare' => $compare
);
} else {
$conditions['attributes'][] = array(
'attribute' => $attribute,
'value' => $match,
'operator_result' => $last_mode,
'compare' => $compare
);
}
switch($tok) {
case CSSQueryTokenizer::TOK_COMMA:
$tok = $p->next_no_whitespace();
$last_mode = 'or';
continue 2;
case CSSQueryTokenizer::TOK_PLUS:
$tok = $p->next_no_whitespace();
$last_mode = 'and';
continue 2;
case CSSQueryTokenizer::TOK_BRACKET_CLOSE:
$tok = $p->next();
break 2;
default:
$this->error('Expected closing bracket or comma at pos %pos%!');
return false;
}
}
}
if (count($conditions['attributes']) < 1) {
unset($conditions['attributes']);
}
while($tok === CSSQueryTokenizer::TOK_COLON) {
if (count($conditions) < 1) {
$conditions['tags'] = array(array(
'tag' => '',
'match' => false
));
}
$tok = $p->next();
if (($filter = $this->parse_getIdentifier()) === false) {
return false;
}
if (($tok = $p->next()) === CSSQueryTokenizer::TOK_BRACE_OPEN) {
$start = $p->pos;
$count = 1;
while ((($tok = $p->next()) !== CSSQueryTokenizer::TOK_NULL) && !(($tok === CSSQueryTokenizer::TOK_BRACE_CLOSE) && (--$count === 0))) {
if ($tok === CSSQueryTokenizer::TOK_BRACE_OPEN) {
++$count;
}
}
if ($tok !== CSSQueryTokenizer::TOK_BRACE_CLOSE) {
$this->error('Expected closing brace at pos %pos%!');
return false;
}
$len = $p->pos - 1 - $start;
$params = (($len > 0) ? substr($p->doc, $start + 1, $len) : '');
$tok = $p->next();
} else {
$params = '';
}
$conditions['filters'][] = array('filter' => $filter, 'params' => $params);
}
if (count($conditions) < 1) {
$this->error('Invalid search pattern(2): No conditions found!');
return false;
}
$conditions_all[] = $conditions;
if ($tok === CSSQueryTokenizer::TOK_WHITESPACE) {
$tok = $p->next_no_whitespace();
}
if ($tok === CSSQueryTokenizer::TOK_COMMA) {
$tok = $p->next_no_whitespace();
continue;
} else {
break;
}
}
return $conditions_all;
}
/**
* Evaluate root node using custom callback
* @param array $conditions {@link parse_conditions()}
* @param bool|int $recursive
* @param bool $check_root
* @return array
* @access private
*/
protected function parse_callback($conditions, $recursive = true, $check_root = false) {
return ($this->result = $this->root->getChildrenByMatch(
$conditions,
$recursive,
$check_root,
$this->custom_filter_map
));
}
/**
* Parse first bit of query, only root node has to be evaluated now
* @param bool|int $recursive
* @return bool
* @internal Result of query is set in {@link $result}
* @access private
*/
protected function parse_single($recursive = true) {
if (($c = $this->parse_conditions()) === false) {
return false;
}
$this->parse_callback($c, $recursive, $this->search_root);
return true;
}
/**
* Evaluate sibling nodes
* @return bool
* @internal Result of query is set in {@link $result}
* @access private
*/
protected function parse_adjacent() {
$tmp = $this->result;
$this->result = array();
if (($c = $this->parse_conditions()) === false) {
return false;
}
foreach($tmp as $t) {
if (($sibling = $t->getNextSibling()) !== false) {
if ($sibling->match($c, true, $this->custom_filter_map)) {
$this->result[] = $sibling;
}
}
}
return true;
}
/**
* Evaluate {@link $result}
* @param bool $parent Evaluate parent nodes
* @param bool|int $recursive
* @return bool
* @internal Result of query is set in {@link $result}
* @access private
*/
protected function parse_result($parent = false, $recursive = true) {
$tmp = $this->result;
$tmp_res = array();
if (($c = $this->parse_conditions()) === false) {
return false;
}
foreach(array_keys($tmp) as $t) {
$this->root = (($parent) ? $tmp[$t]->parent : $tmp[$t]);
$this->parse_callback($c, $recursive);
foreach(array_keys($this->result) as $r) {
if (!in_array($this->result[$r], $tmp_res, true)) {
$tmp_res[] = $this->result[$r];
}
}
}
$this->result = $tmp_res;
return true;
}
/**
* Parse full query
* @return bool
* @internal Result of query is set in {@link $result}
* @access private
*/
protected function parse() {
$p =& $this->parser;
$p->setPos(0);
$this->result = array();
if (!$this->parse_single()) {
return false;
}
while (count($this->result) > 0) {
switch($p->token) {
case CSSQueryTokenizer::TOK_CHILD:
$this->parser->next_no_whitespace();
if (!$this->parse_result(false, 1)) {
return false;
}
break;
case CSSQueryTokenizer::TOK_SIBLING:
$this->parser->next_no_whitespace();
if (!$this->parse_result(true, 1)) {
return false;
}
break;
case CSSQueryTokenizer::TOK_PLUS:
$this->parser->next_no_whitespace();
if (!$this->parse_adjacent()) {
return false;
}
break;
case CSSQueryTokenizer::TOK_ALL:
case CSSQueryTokenizer::TOK_IDENTIFIER:
case CSSQueryTokenizer::TOK_STRING:
case CSSQueryTokenizer::TOK_BRACE_OPEN:
case CSSQueryTokenizer::TOK_BRACKET_OPEN:
case CSSQueryTokenizer::TOK_ID:
case CSSQueryTokenizer::TOK_CLASS:
case CSSQueryTokenizer::TOK_COLON:
if (!$this->parse_result()) {
return false;
}
break;
case CSSQueryTokenizer::TOK_NULL:
break 2;
default:
$this->error('Invalid search pattern(3): No result modifier found!');
return false;
}
}
return true;
}
}
?>

566
lib-3rd-party/pquery/gan_tokenizer.php vendored Normal file
View File

@@ -0,0 +1,566 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
namespace pQuery;
/**
* Converts a document into tokens
*
* Can convert any string into tokens. The base class only supports
* identifier/whitespace tokens. For more tokens, the class can be
* easily extended.
*
* Use like:
* <code>
* <?php
* $a = new TokenizerBase('hello word');
* while ($a->next() !== $a::TOK_NULL) {
* echo $a->token, ': ',$a->getTokenString(), "<br>\n";
* }
* ?>
* </code>
*
* @internal The tokenizer works with a character map that connects a certain
* character to a certain function/token. This class is build with speed in mind.
*/
class TokenizerBase {
/**
* NULL Token, used at end of document (parsing should stop after this token)
*/
const TOK_NULL = 0;
/**
* Unknown token, used at unidentified character
*/
const TOK_UNKNOWN = 1;
/**
* Whitespace token, used with whitespace
*/
const TOK_WHITESPACE = 2;
/**
* Identifier token, used with identifiers
*/
const TOK_IDENTIFIER = 3;
/**
* The document that is being tokenized
* @var string
* @internal Public for faster access!
* @see setDoc()
* @see getDoc()
* @access private
*/
var $doc = '';
/**
* The size of the document (length of string)
* @var int
* @internal Public for faster access!
* @see $doc
* @access private
*/
var $size = 0;
/**
* Current (character) position in the document
* @var int
* @internal Public for faster access!
* @see setPos()
* @see getPos()
* @access private
*/
var $pos = 0;
/**
* Current (Line/Column) position in document
* @var array (Current_Line, Line_Starting_Pos)
* @internal Public for faster access!
* @see getLinePos()
* @access private
*/
var $line_pos = array(0, 0);
/**
* Current token
* @var int
* @internal Public for faster access!
* @see getToken()
* @access private
*/
var $token = self::TOK_NULL;
/**
* Start position of token. If NULL, then current position is used.
* @var int
* @internal Public for faster access!
* @see getTokenString()
* @access private
*/
var $token_start = null;
/**
* List with all the character that can be considered as whitespace
* @var array|string
* @internal Variable is public + associated array for faster access!
* @internal array(' ' => true) will recognize space (' ') as whitespace
* @internal String will be converted to array in constructor
* @internal Result token will be {@link self::TOK_WHITESPACE};
* @see setWhitespace()
* @see getWhitespace()
* @access private
*/
var $whitespace = " \t\n\r\0\x0B";
/**
* List with all the character that can be considered as identifier
* @var array|string
* @internal Variable is public + associated array for faster access!
* @internal array('a' => true) will recognize 'a' as identifier
* @internal String will be converted to array in constructor
* @internal Result token will be {@link self::TOK_IDENTIFIER};
* @see setIdentifiers()
* @see getIdentifiers()
* @access private
*/
var $identifiers = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890_';
/**
* All characters that should be mapped to a token/function that cannot be considered as whitespace or identifier
* @var array
* @internal Variable is public + associated array for faster access!
* @internal array('a' => 'parse_a') will call $this->parse_a() if it matches the character 'a'
* @internal array('a' => self::TOK_A) will set token to TOK_A if it matches the character 'a'
* @see mapChar()
* @see unmapChar()
* @access private
*/
var $custom_char_map = array();
/**
* Automatically built character map. Built using {@link $identifiers}, {@link $whitespace} and {@link $custom_char_map}
* @var array
* @internal Public for faster access!
* @access private
*/
var $char_map = array();
/**
* All errors found while parsing the document
* @var array
* @see addError()
*/
var $errors = array();
/**
* Class constructor
* @param string $doc Document to be tokenized
* @param int $pos Position to start parsing
* @see setDoc()
* @see setPos()
*/
function __construct($doc = '', $pos = 0) {
$this->setWhitespace($this->whitespace);
$this->setIdentifiers($this->identifiers);
$this->setDoc($doc, $pos);
}
#php4 PHP4 class constructor compatibility
#function TokenizerBase($doc = '', $pos = 0) {return $this->__construct($doc, $pos);}
#php4e
/**
* Sets target document
* @param string $doc Document to be tokenized
* @param int $pos Position to start parsing
* @see getDoc()
* @see setPos()
*/
function setDoc($doc, $pos = 0) {
$this->doc = $doc;
$this->size = strlen($doc);
$this->setPos($pos);
}
/**
* Returns target document
* @return string
* @see setDoc()
*/
function getDoc() {
return $this->doc;
}
/**
* Sets position in document
* @param int $pos
* @see getPos()
*/
function setPos($pos = 0) {
$this->pos = $pos - 1;
$this->line_pos = array(0, 0);
$this->next();
}
/**
* Returns current position in document (Index)
* @return int
* @see setPos()
*/
function getPos() {
return $this->pos;
}
/**
* Returns current position in document (Line/Char)
* @return array array(Line, Column)
*/
function getLinePos() {
return array($this->line_pos[0], $this->pos - $this->line_pos[1]);
}
/**
* Returns current token
* @return int
* @see $token
*/
function getToken() {
return $this->token;
}
/**
* Returns current token as string
* @param int $start_offset Offset from token start
* @param int $end_offset Offset from token end
* @return string
*/
function getTokenString($start_offset = 0, $end_offset = 0) {
$token_start = ((is_int($this->token_start)) ? $this->token_start : $this->pos) + $start_offset;
$len = $this->pos - $token_start + 1 + $end_offset;
return (($len > 0) ? substr($this->doc, $token_start, $len) : '');
}
/**
* Sets characters to be recognized as whitespace
*
* Used like: setWhitespace('ab') or setWhitespace(array('a' => true, 'b', 'c'));
* @param string|array $ws
* @see getWhitespace();
*/
function setWhitespace($ws) {
if (is_array($ws)) {
$this->whitespace = array_fill_keys(array_values($ws), true);
$this->buildCharMap();
} else {
$this->setWhiteSpace(str_split($ws));
}
}
/**
* Returns whitespace characters as string/array
* @param bool $as_string Should the result be a string or an array?
* @return string|array
* @see setWhitespace()
*/
function getWhitespace($as_string = true) {
$ws = array_keys($this->whitespace);
return (($as_string) ? implode('', $ws) : $ws);
}
/**
* Sets characters to be recognized as identifier
*
* Used like: setIdentifiers('ab') or setIdentifiers(array('a' => true, 'b', 'c'));
* @param string|array $ident
* @see getIdentifiers();
*/
function setIdentifiers($ident) {
if (is_array($ident)) {
$this->identifiers = array_fill_keys(array_values($ident), true);
$this->buildCharMap();
} else {
$this->setIdentifiers(str_split($ident));
}
}
/**
* Returns identifier characters as string/array
* @param bool $as_string Should the result be a string or an array?
* @return string|array
* @see setIdentifiers()
*/
function getIdentifiers($as_string = true) {
$ident = array_keys($this->identifiers);
return (($as_string) ? implode('', $ident) : $ident);
}
/**
* Maps a custom character to a token/function
*
* Used like: mapChar('a', self::{@link TOK_IDENTIFIER}) or mapChar('a', 'parse_identifier');
* @param string $char Character that should be mapped. If set, it will be overridden
* @param int|string $map If function name, then $this->function will be called, otherwise token is set to $map
* @see unmapChar()
*/
function mapChar($char, $map) {
$this->custom_char_map[$char] = $map;
$this->buildCharMap();
}
/**
* Removes a char mapped with {@link mapChar()}
* @param string $char Character that should be unmapped
* @see mapChar()
*/
function unmapChar($char) {
unset($this->custom_char_map[$char]);
$this->buildCharMap();
}
/**
* Builds the {@link $map_char} array
* @internal Builds single array that maps all characters. Gets called if {@link $whitespace}, {@link $identifiers} or {@link $custom_char_map} get modified
*/
protected function buildCharMap() {
$this->char_map = $this->custom_char_map;
if (is_array($this->whitespace)) {
foreach($this->whitespace as $w => $v) {
$this->char_map[$w] = 'parse_whitespace';
}
}
if (is_array($this->identifiers)) {
foreach($this->identifiers as $i => $v) {
$this->char_map[$i] = 'parse_identifier';
}
}
}
/**
* Add error to the array and appends current position
* @param string $error
*/
function addError($error) {
$this->errors[] = htmlentities($error.' at '.($this->line_pos[0] + 1).', '.($this->pos - $this->line_pos[1] + 1).'!');
}
/**
* Parse line breaks and increase line number
* @internal Gets called to process line breaks
*/
protected function parse_linebreak() {
if($this->doc[$this->pos] === "\r") {
++$this->line_pos[0];
if ((($this->pos + 1) < $this->size) && ($this->doc[$this->pos + 1] === "\n")) {
++$this->pos;
}
$this->line_pos[1] = $this->pos;
} elseif($this->doc[$this->pos] === "\n") {
++$this->line_pos[0];
$this->line_pos[1] = $this->pos;
}
}
/**
* Parse whitespace
* @return int Token
* @internal Gets called with {@link $whitespace} characters
*/
protected function parse_whitespace() {
$this->token_start = $this->pos;
while(++$this->pos < $this->size) {
if (!isset($this->whitespace[$this->doc[$this->pos]])) {
break;
} else {
$this->parse_linebreak();
}
}
--$this->pos;
return self::TOK_WHITESPACE;
}
/**
* Parse identifiers
* @return int Token
* @internal Gets called with {@link $identifiers} characters
*/
protected function parse_identifier() {
$this->token_start = $this->pos;
while((++$this->pos < $this->size) && isset($this->identifiers[$this->doc[$this->pos]])) {}
--$this->pos;
return self::TOK_IDENTIFIER;
}
/**
* Continues to the next token
* @return int Next token ({@link TOK_NULL} if none)
*/
function next() {
$this->token_start = null;
if (++$this->pos < $this->size) {
if (isset($this->char_map[$this->doc[$this->pos]])) {
if (is_string($this->char_map[$this->doc[$this->pos]])) {
return ($this->token = $this->{$this->char_map[$this->doc[$this->pos]]}());
} else {
return ($this->token = $this->char_map[$this->doc[$this->pos]]);
}
} else {
return ($this->token = self::TOK_UNKNOWN);
}
} else {
return ($this->token = self::TOK_NULL);
}
}
/**
* Finds the next token, but skips whitespace
* @return int Next token ({@link TOK_NULL} if none)
*/
function next_no_whitespace() {
$this->token_start = null;
while (++$this->pos < $this->size) {
if (!isset($this->whitespace[$this->doc[$this->pos]])) {
if (isset($this->char_map[$this->doc[$this->pos]])) {
if (is_string($this->char_map[$this->doc[$this->pos]])) {
return ($this->token = $this->{$this->char_map[$this->doc[$this->pos]]}());
} else {
return ($this->token = $this->char_map[$this->doc[$this->pos]]);
}
} else {
return ($this->token = self::TOK_UNKNOWN);
}
} else {
$this->parse_linebreak();
}
}
return ($this->token = self::TOK_NULL);
}
/**
* Finds the next token using stop characters.
*
* Used like: next_search('abc') or next_search(array('a' => true, 'b' => true, 'c' => true));
* @param string|array $characters Characters to search for
* @param bool $callback Should the function check the charmap after finding a character?
* @return int Next token ({@link TOK_NULL} if none)
*/
function next_search($characters, $callback = true) {
$this->token_start = $this->pos;
if (!is_array($characters)) {
$characters = array_fill_keys(str_split($characters), true);
}
while(++$this->pos < $this->size) {
if (isset($characters[$this->doc[$this->pos]])) {
if ($callback && isset($this->char_map[$this->doc[$this->pos]])) {
if (is_string($this->char_map[$this->doc[$this->pos]])) {
return ($this->token = $this->{$this->char_map[$this->doc[$this->pos]]}());
} else {
return ($this->token = $this->char_map[$this->doc[$this->pos]]);
}
} else {
return ($this->token = self::TOK_UNKNOWN);
}
} else {
$this->parse_linebreak();
}
}
return ($this->token = self::TOK_NULL);
}
/**
* Finds the next token by searching for a string
* @param string $needle The needle that's being searched for
* @param bool $callback Should the function check the charmap after finding the needle?
* @return int Next token ({@link TOK_NULL} if none)
*/
function next_pos($needle, $callback = true) {
$this->token_start = $this->pos;
if (($this->pos < $this->size) && (($p = stripos($this->doc, $needle, $this->pos + 1)) !== false)) {
$len = $p - $this->pos - 1;
if ($len > 0) {
$str = substr($this->doc, $this->pos + 1, $len);
if (($l = strrpos($str, "\n")) !== false) {
++$this->line_pos[0];
$this->line_pos[1] = $l + $this->pos + 1;
$len -= $l;
if ($len > 0) {
$str = substr($str, 0, -$len);
$this->line_pos[0] += substr_count($str, "\n");
}
}
}
$this->pos = $p;
if ($callback && isset($this->char_map[$this->doc[$this->pos]])) {
if (is_string($this->char_map[$this->doc[$this->pos]])) {
return ($this->token = $this->{$this->char_map[$this->doc[$this->pos]]}());
} else {
return ($this->token = $this->char_map[$this->doc[$this->pos]]);
}
} else {
return ($this->token = self::TOK_UNKNOWN);
}
} else {
$this->pos = $this->size;
return ($this->token = self::TOK_NULL);
}
}
/**
* Expect a specific token or character. Adds error if token doesn't match.
* @param string|int $token Character or token to expect
* @param bool|int $do_next Go to next character before evaluating. 1 for next char, true to ignore whitespace
* @param bool|int $try_next Try next character if current doesn't match. 1 for next char, true to ignore whitespace
* @param bool|int $next_on_match Go to next character after evaluating. 1 for next char, true to ignore whitespace
* @return bool
*/
protected function expect($token, $do_next = true, $try_next = false, $next_on_match = 1) {
if ($do_next) {
if ($do_next === 1) {
$this->next();
} else {
$this->next_no_whitespace();
}
}
if (is_int($token)) {
if (($this->token !== $token) && ((!$try_next) || ((($try_next === 1) && ($this->next() !== $token)) || (($try_next === true) && ($this->next_no_whitespace() !== $token))))) {
$this->addError('Unexpected "'.$this->getTokenString().'"');
return false;
}
} else {
if (($this->doc[$this->pos] !== $token) && ((!$try_next) || (((($try_next === 1) && ($this->next() !== self::TOK_NULL)) || (($try_next === true) && ($this->next_no_whitespace() !== self::TOK_NULL))) && ($this->doc[$this->pos] !== $token)))) {
$this->addError('Expected "'.$token.'", but found "'.$this->getTokenString().'"');
return false;
}
}
if ($next_on_match) {
if ($next_on_match === 1) {
$this->next();
} else {
$this->next_no_whitespace();
}
}
return true;
}
}
?>

101
lib-3rd-party/pquery/gan_xml2array.php vendored Normal file
View File

@@ -0,0 +1,101 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
namespace pQuery;
/**
* Converts a XML document to an array
*/
class XML2ArrayParser extends HtmlParserBase {
/**
* Holds the document structure
* @var array array('name' => 'tag', 'attrs' => array('attr' => 'val'), 'childen' => array())
*/
var $root = array(
'name' => '',
'attrs' => array(),
'children' => array()
);
/**
* Current parsing hierarchy
* @var array
* @access private
*/
var $hierarchy = array();
protected function parse_hierarchy($self_close) {
if ($this->status['closing_tag']) {
$found = false;
for ($count = count($this->hierarchy), $i = $count - 1; $i >= 0; $i--) {
if (strcasecmp($this->hierarchy[$i]['name'], $this->status['tag_name']) === 0) {
for($ii = ($count - $i - 1); $ii >= 0; $ii--) {
$e = array_pop($this->hierarchy);
if ($ii > 0) {
$this->addError('Closing tag "'.$this->status['tag_name'].'" while "'.$e['name'].'" is not closed yet');
}
}
$found = true;
break;
}
}
if (!$found) {
$this->addError('Closing tag "'.$this->status['tag_name'].'" which is not open');
}
} else {
$tag = array(
'name' => $this->status['tag_name'],
'attrs' => $this->status['attributes'],
'children' => array()
);
if ($this->hierarchy) {
$current =& $this->hierarchy[count($this->hierarchy) - 1];
$current['children'][] = $tag;
$tag =& $current['children'][count($current['children']) - 1];
unset($current['tagData']);
} else {
$this->root = $tag;
$tag =& $this->root;
$self_close = false;
}
if (!$self_close) {
$this->hierarchy[] =& $tag;
}
}
}
function parse_tag_default() {
if (!parent::parse_tag_default()) {return false;}
if ($this->status['tag_name'][0] !== '?') {
$this->parse_hierarchy(($this->status['self_close']) ? true : null);
}
return true;
}
function parse_text() {
parent::parse_text();
if (($this->status['text'] !== '') && $this->hierarchy) {
$current =& $this->hierarchy[count($this->hierarchy) - 1];
if (!$current['children']) {
$current['tagData'] = $this->status['text'];
}
}
}
function parse_all() {
return ((parent::parse_all()) ? $this->root : false);
}
}
?>

101
lib-3rd-party/pquery/ganon.php vendored Normal file
View File

@@ -0,0 +1,101 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
use pQuery\Html5Parser;
use pQuery\HtmlFormatter;
/**
* Returns HTML DOM from string
* @param string $str
* @param bool $return_root Return root node or return parser object
* @return Html5Parser|DomNode
*/
function str_get_dom($str, $return_root = true) {
$a = new Html5Parser($str);
return (($return_root) ? $a->root : $a);
}
/**
* Returns HTML DOM from file/website
* @param string $str
* @param bool $return_root Return root node or return parser object
* @param bool $use_include_path Use include path search in file_get_contents
* @param resource $context Context resource used in file_get_contents (PHP >= 5.0.0)
* @return Html5Parser|DomNode
*/
function file_get_dom($file, $return_root = true, $use_include_path = false, $context = null) {
if (version_compare(PHP_VERSION, '5.0.0', '>='))
$f = file_get_contents($file, $use_include_path, $context);
else {
if ($context !== null)
trigger_error('Context parameter not supported in this PHP version');
$f = file_get_contents($file, $use_include_path);
}
return (($f === false) ? false : str_get_dom($f, $return_root));
}
/**
* Format/beautify DOM
* @param DomNode $root
* @param array $options Extra formatting options {@link Formatter::$options}
* @return bool
*/
function dom_format(&$root, $options = array()) {
$formatter = new HtmlFormatter($options);
return $formatter->format($root);
}
if (version_compare(PHP_VERSION, '5.0.0', '<')) {
/**
* PHP alternative to str_split, for backwards compatibility
* @param string $string
* @return string
*/
function str_split($string) {
$res = array();
$size = strlen($string);
for ($i = 0; $i < $size; $i++) {
$res[] = $string[$i];
}
return $res;
}
}
if (version_compare(PHP_VERSION, '5.2.0', '<')) {
/**
* PHP alternative to array_fill_keys, for backwards compatibility
* @param array $keys
* @param mixed $value
* @return array
*/
function array_fill_keys($keys, $value) {
$res = array();
foreach($keys as $k) {
$res[$k] = $value;
}
return $res;
}
}
#!! <- Ignore when converting to single file
if (!defined('GANON_NO_INCLUDES')) {
define('GANON_NO_INCLUDES', true);
include_once('IQuery.php');
include_once('gan_tokenizer.php');
include_once('gan_parser_html.php');
include_once('gan_node_html.php');
include_once('gan_selector_html.php');
include_once('gan_formatter.php');
}
#!
?>

279
lib-3rd-party/pquery/pQuery.php vendored Normal file
View File

@@ -0,0 +1,279 @@
<?php
/**
* @author Niels A.D.
* @author Todd Burry <todd@vanillaforums.com>
* @copyright 2010 Niels A.D., 2014 Todd Burry
* @license http://opensource.org/licenses/LGPL-2.1 LGPL-2.1
* @package pQuery
*/
use pQuery\IQuery;
/**
* A jQuery-like object for php.
*/
class pQuery implements ArrayAccess, IteratorAggregate, IQuery {
/// Properties ///
/**
* @var IQuery[]
*/
protected $nodes = array();
/// Methods ///
public function __construct($nodes = array()) {
$this->nodes = $nodes;
}
public function addClass($classname) {
foreach ($this->nodes as $node) {
$node->addClass($classname);
}
return $this;
}
public function after($content) {
foreach ($this->nodes as $node) {
$node->after($content);
}
return $this;
}
public function append($content) {
foreach ($this->nodes as $node) {
$node->append($content);
}
return $this;
}
public function attr($name, $value = null) {
if (empty($this->nodes) && $value === null)
return '';
foreach ($this->nodes as $node) {
if ($value === null)
return $node->attr($name);
$node->attr($name, $value);
}
return $this;
}
public function before($content) {
foreach ($this->nodes as $node) {
$node->before($content);
}
return $this;
}
public function clear() {
foreach ($this->nodes as $node) {
$node->clear();
}
return $this;
}
/**
* Get the count of matched elements.
*
* @return int Returns the count of matched elements.
*/
public function count() {
return count($this->nodes);
}
/**
* Format/beautify a DOM.
*
* @param pQuery\DomNode $dom The dom to format.
* @param array $options Extra formatting options. See {@link pQuery\HtmlFormatter::$options}.
* @return bool Returns `true` on sucess and `false` on failure.
*/
// public static function format($dom, $options = array()) {
// $formatter = new pQuery\HtmlFormatter($options);
// return $formatter->format($dom);
// }
public function getIterator() {
return new ArrayIterator($this->nodes);
}
public function hasClass($classname) {
foreach ($this->nodes as $node) {
if ($node->hasClass($classname))
return true;
}
return false;
}
public function html($value = null) {
if (empty($this->nodes) && $value === null)
return '';
foreach ($this->nodes as $node) {
if ($value === null)
return $node->html();
$node->html($value);
}
return $this;
}
public function offsetExists($offset) {
return isset($this->nodes[$offset]);
}
public function offsetGet($offset) {
return isset($this->nodes[$offset]) ? $this->nodes[$offset] : null;
}
public function offsetSet($offset, $value) {
if (is_null($offset) || !isset($this->nodes[$offset])) {
throw new \BadMethodCallException("You are not allowed to add new nodes to the pQuery object.");
} else {
$this->nodes[$offset]->replaceWith($value);
}
}
public function offsetUnset($offset) {
if (isset($this->nodes[$offset])) {
$this->nodes[$offset]->remove();
unset($this->nodes[$offset]);
}
}
/**
* Query a file or url.
*
* @param string $path The path to the url.
* @param resource $context A context suitable to be passed into {@link file_get_contents}
* @return pQuery\DomNode Returns the root dom node for the html file.
*/
public static function parseFile($path, $context = null) {
$html_str = file_get_contents($path, false, $context);
return static::parseStr($html_str);
}
/**
* Query a string of html.
*
* @param string $html
* @return pQuery\DomNode Returns the root dom node for the html string.
*/
public static function parseStr($html) {
$parser = new pQuery\Html5Parser($html);
return $parser->root;
}
public function prepend($content = null) {
foreach ($this->nodes as $node) {
$node->prepend($content);
}
return $this;
}
public function prop($name, $value = null) {
if (empty($this->nodes) && $value === null)
return '';
foreach ($this->nodes as $node) {
if ($value === null)
return $node->prop($name);
$node->prop($name, $value);
}
return $this;
}
public function remove($selector = null) {
foreach ($this->nodes as $node) {
$node->remove($selector);
}
if ($selector === null)
$this->nodes = array();
return $this;
}
public function removeAttr($name) {
foreach ($this->nodes as $node) {
$node->removeAttr($name);
}
return $this;
}
public function removeClass($classname) {
foreach ($this->nodes as $node) {
$node->removeClass($classname);
}
return $this;
}
public function replaceWith($content) {
foreach ($this->nodes as &$node) {
$node = $node->replaceWith($content);
}
return $this;
}
public function tagName($value = null) {
foreach ($this->nodes as $node) {
if ($value === null)
return $node->tagName();
$node->tagName($value);
}
return $this;
}
public function text($value = null) {
if (empty($this->nodes) && $value === null)
return '';
foreach ($this->nodes as $node) {
if ($value === null)
return $node->text();
$node->text($value);
}
return $this;
}
public function toggleClass($classname, $switch = null) {
foreach ($this->nodes as $node) {
$node->toggleClass($classname, $switch);
}
return $this;
}
public function unwrap() {
foreach ($this->nodes as $node) {
$node->unwrap();
}
return $this;
}
public function val($value = null) {
if (empty($this->nodes) && $value === null)
return '';
foreach ($this->nodes as $node) {
if ($value === null)
return $node->val();
$node->val($value);
}
return $this;
}
public function wrap($wrapping_element) {
foreach ($this->nodes as $node) {
$node->wrap($wrapping_element);
}
return $this;
}
public function wrapInner($wrapping_element) {
foreach ($this->nodes as $node) {
$node->wrapInner($wrapping_element);
}
return $this;
}
}

File diff suppressed because it is too large Load Diff