Select Git revision
test_rad_pressure.py
Forked from
finesse / pykat
Source project has a limited visibility.
text_transform.inc 10.81 KiB
<?php
// This file is part of BOINC.
// http://boinc.berkeley.edu
// Copyright (C) 2008 University of California
//
// BOINC 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 3 of the License, or (at your option) any later version.
//
// BOINC 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 BOINC. If not, see <http://www.gnu.org/licenses/>.
// Functions that process user-supplied text (e.g. messages)
// prior to displaying it to users.
// Goals:
// - Security (don't send evil javascript)
// - obey user preferences
// - improve formatting (e.g., convert newlines to <br> tags)
require_once('../inc/sanitize_html.inc');
class output_options {
var $bb2html; // BBCode as HTML? (on)
var $images_as_links; // Images as hyperlinks? (off)
var $link_popup; // Links in new windows? (off)
var $nl2br; // Convert newlines to <br>'s? (on)
var $htmlitems; // Convert special chars to HTML entities? (on)
var $htmlscrub; // Scrub "bad" HTML tags? (off)
var $highlight_terms;// Array of terms to be highlighted (off)
// Constructor - set the defaults.
function __construct() {
$this->bb2html = 1;
$this->images_as_links = 0;
$this->link_popup = 0;
$this->nl2br = 1;
$this->htmlitems = 1;
$this->htmlscrub = 0;
$this->highlight_terms = 0;
return true;
}
// Define the terms to be highlighted (for use with searches and such)
function setHighlightTerms($terms) {
if (is_array($terms)) {
$this->highlight_terms = $terms;
} else {
return false;
}
return true;
}
}
// Do the actual transformation of the text.
// TODO: Make this part of the above class.
function output_transform($text, $options = NULL) {
// Options is a output_options object, defined above
if (!$options) {
$options = new output_options; // Defaults in the class definition
}
if ($options->htmlitems) { $text = htmlspecialchars($text, ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE);
}
if (is_array($options->highlight_terms)) {
$text = highlight_terms($text, $options->highlight_terms);
}
// if ($options->htmlscrub) {
// $text = sanitize_html($text);
// }
if ($options->nl2br) {
$text = nl2br($text);
}
if ($options->bb2html) {
$text = bb2html($text);
}
if ($options->images_as_links) {
$text = image_as_link($text);
}
if ($options->link_popup) {
$text = externalize_links($text);
}
return $text;
}
function get_output_options($user) {
$options = new output_options();
if ($user) {
if ($user->prefs->images_as_links) $options->images_as_links = 1;
if ($user->prefs->link_popup) $options->link_popup = 1;
}
return $options;
}
// Converts bbcode to HTML
// If $export is true, don't use BOINC CSS
function substr2($s, $n1, $n2) {
return substr($s, $n1, $n2-$n1);
}
// process non-nestable constructs: [pre] and [code]
//
function replace_pre_code($text, $export) {
$out = '';
$pos = 0;
while (true) {
$n1 = strpos($text, '[code]', $pos);
$n2 = strpos($text, '[pre]', $pos);
if ($n1 === false && $n2 === false) {
$out .= substr($text, $pos);
break;
}
if ($n1 === false) $n1 = 9999;
if ($n2 === false) $n2 = 9999;
if ($n1 < $n2) {
$n = $n1;
$tag = '[code]';
$tag2 = '[/code]';
} else {
$n = $n2;
$tag = '[pre]';
$tag2 = '[/pre]';
}
$out .= substr2($text, $pos, $n);
$n2 = strpos($text, $tag2, $n);
$n += strlen($tag);
if (!$n2) {
$out .= substr($text, $n);
break;
}
$x = substr2($text, $n, $n2); $x = remove_br($x);
$x = htmlspecialchars($x, ENT_COMPAT, "UTF-8", false);
$x = str_replace("[", "[", $x);
if ($export) {
if ($tag == '[pre]') {
$out .= "<pre>$x</pre>";
} else {
$out .= "<code>$x</code>";
}
} else {
$out .= "<pre style=\"white-space:pre-wrap;\">$x</pre>";
}
$pos = $n2 + strlen($tag2);
}
return $out;
}
// process nestable constructs
//
function bb2html_aux($text, $export) {
$urlregex = "(?:\"?)(?:(http\:\/\/)?)([^\[\"<\ ]+)(?:\"?)";
// NOTE:
// This matches https:// too; I don't understand why.
// sample results:
// Array
// (
// [0] => [img]https://a.b.c[/img]
// [1] =>
// [2] => https://a.b.c
// )
// Array
// (
// [0] => [img]http://a.b.c[/img]
// [1] => http://
// [2] => a.b.c
// )
$email_addr_regex = "([A-Za-z0-9\.\-\_\@]*)";
// should match all valid email addrs,
// but not any hacker stuff like " alert(1)
$httpsregex = "(?:\"?)https\:\/\/([^\[\"<\ ]+)(?:\"?)";
// List of allowable tags
$bbtags = array (
"@\[b\](.*?)\[/b\]@is",
"@\[i\](.*?)\[/i\]@is",
"@\[u\](.*?)\[/u\]@is",
"@\[s\](.*?)\[/s\]@is",
"@\[sup\](.*?)\[/sup\]@is",
"@\[url=$httpsregex\](.*?)\[/url\]@is",
"@\[url\]$httpsregex\[/url\]@is",
"@\[link=$urlregex\](.*?)\[/link\]@is",
"@\[link\]$urlregex\[/link\]@is",
"@\[url=$urlregex\](.*?)\[/url\]@is",
"@\[url\]$urlregex\[/url\]@is",
"@\[quote=(.*?)\](.*?)\[/quote\]@is",
"@\[quote\](.*?)\[/quote\]@is",
"@\[list\](.*?)\[/list\]@is",
"@\[list=1\](.*?)\[/list\]@is",
"@\[img\]$urlregex\[/img\]@is",
"@\[sm_img\]$urlregex\[/sm_img\]@is",
"@\[color=(?:\"?)(.{3,8})(?:\"?)\](.*?)\[/color\]@is",
"@((?:<ol>|<ul>).*?)\n\*([^\n]+)\n(.*?(</ol>|</ul>))@is",
"@\[size=([1-9]|[0-2][0-9])\](.*?)\[/size\]@is",
"@\[mailto\]$email_addr_regex\[/mailto\]@is",
"@\[email\]$email_addr_regex\[/email\]@is",
"@\[github\](?:\#|ticket:)(\d+)\[/github\]@is",
"@\[github\]wiki:(.*?)\[/github\]@is",
);
// What the above tags are turned in to if ($export) {
$htmltags = array (
"<b>\\1</b>",
"<i>\\1</i>",
"<u>\\1</u>",
"<s>\\1</s>",
"<sup>\\1</sup>",
"<a href=\"https://\\1\" rel=\"nofollow\">\\2</a>",
"<a href=\"https://\\1\" rel=\"nofollow\">https://\\1</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">\\3</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">http://\\2</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">\\3</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">http://\\2</a>",
"<i>\\1 wrote:</i><blockquote>\\2</blockquote>",
"<blockquote>\\1</blockquote>",
"<ul>\\1</ul><p>",
"<ol>\\1</ol><p>",
"<img hspace=\"8\" src=\"\\1\\2\"> ",
"<img hspace=\"8\" width=400 src=\"\\1\\2\"> ",
"<font color=\"\\1\">\\2</font>",
"\\1<li>\\2\n\\3",
"<span style=\"font-size: \\1px;\">\\2</span>",
"<a href=\"mailto:\\1\">\\1</a>",
"<a href=\"mailto:\\1\">\\1</a>",
"<a href=\"https://github.com/BOINC/boinc/issues/\\1\">#\\1</a>",
"<a href=\"https://github.com/BOINC/boinc/wiki/\\1\">\\1</a>",
);
} else {
$htmltags = array (
"<b>\\1</b>",
"<i>\\1</i>",
"<u>\\1</u>",
"<s>\\1</s>",
"<sup>\\1</sup>",
"<a href=\"https://\\1\" rel=\"nofollow\">\\2</a>",
"<a href=\"https://\\1\" rel=\"nofollow\">https://\\1</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">\\3</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">http://\\2</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">\\3</a>",
"<a href=\"http://\\2\" rel=\"nofollow\">http://\\2</a>",
"<em>\\1 wrote:</em><blockquote>\\2</blockquote>",
"<blockquote>\\1</blockquote>",
"<ul>\\1</ul><p>",
"<ol>\\1</ol><p>",
"<img hspace=\"8\" class=\"img-responsive\" src=\"\\1\\2\"> ",
"<img hspace=\"8\" width=400 src=\"\\1\\2\"> ",
"<font color=\"\\1\">\\2</font>",
"\\1<li>\\2\n\\3",
"<span style=\"font-size: \\1px;\">\\2</span>",
"<a href=\"mailto:\\1\">\\1</a>",
"<a href=\"mailto:\\1\">\\1</a>",
"<a href=\"https://github.com/BOINC/boinc/issues/\\1\">#\\1</a>",
"<a href=\"https://github.com/BOINC/boinc/wiki/\\1\">\\1</a>",
);
}
// Do the actual replacing - iterations for nested items
$lasttext = "";
$i = 0;
// $i<1000 to prevent DoS
while ($text != $lasttext && $i<1000) {
$lasttext = $text;
$text = preg_replace($bbtags, $htmltags, $text);
$i = $i + 1;
}
$text = str_replace("<ul>", '<ul style="word-break:break-word;">', $text);
$text = str_replace("<ol>", '<ol style="word-break:break-word;">', $text);
return $text;
}
function bb2html($text, $export=false) {
$text = replace_pre_code($text, $export);
return bb2html_aux($text, $export);
}
// Remove any <br> tags added by nl2br which are not wanted,
// for example inside <pre> containers
// The original \n was retained after the br when it was added
//
function remove_br($text){
return str_replace("<br />", "", $text);
}
// Make links open in new windows.
//
function externalize_links($text) {
// TODO: Convert this to PCRE
$i=0;
$linkpos=true;
$out = "";
while (true){
// Find a link
//
$linkpos=strpos($text, "<a ", $i);
if ($linkpos===false) break;
// Replace with target='_new'
//
$out .= substr($text, $i, $linkpos-$i)."<a target=\"_new\" ";
$i = $linkpos+3;
}
$out .= substr($text, $i);
return $out;
}
// Converts image tags to links to the images.
//
function image_as_link($text){
$pattern = '@<img([\S\s]+?)src=([^>]+?)>@si';
$replacement = '<a href=${2}>[Image link]</a>';
return preg_replace($pattern, $replacement, $text);
}
// Highlight terms in text (used in search results)
//
function highlight_terms($text, $terms) {
$search = $terms;
$replace = array();
foreach ($search as $key => $value) {
$replace[$key] = "<span class=\"mark\">".$value."</span>";
}
return str_ireplace($search, $replace, $text);
}
?>