Update the html2text class with a fork from https://github.com/mtibben/html2text
Hopefully it will fix the PHP 5.5 build as it no longer uses the deprecated `/e` modifier. I removed the namespace declaration so that it will work in older versions of PHP, and lower-cased the class name for backward compatibility.
This commit is contained in:
Synchro
parent
9a279e3a6f
commit
ac658cf21b
|
|
@ -1,15 +1,9 @@
|
|||
<?php
|
||||
|
||||
/*************************************************************************
|
||||
* *
|
||||
* class.html2text.php *
|
||||
* *
|
||||
*************************************************************************
|
||||
* *
|
||||
* Converts HTML to formatted plain text *
|
||||
* *
|
||||
* Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> *
|
||||
* All rights reserved. *
|
||||
* Portions Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> *
|
||||
* *
|
||||
* This script is free software; you can redistribute it and/or modify *
|
||||
* it under the terms of the GNU General Public License as published by *
|
||||
|
|
@ -24,86 +18,9 @@
|
|||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
|
||||
* GNU General Public License for more details. *
|
||||
* *
|
||||
* Author(s): Jon Abernathy <jon@chuggnutt.com> *
|
||||
* *
|
||||
* Last modified: 08/08/07 *
|
||||
* *
|
||||
*************************************************************************/
|
||||
|
||||
|
||||
/**
|
||||
* Takes HTML and converts it to formatted, plain text.
|
||||
*
|
||||
* Thanks to Alexander Krug (http://www.krugar.de/) to pointing out and
|
||||
* correcting an error in the regexp search array. Fixed 7/30/03.
|
||||
*
|
||||
* Updated set_html() function's file reading mechanism, 9/25/03.
|
||||
*
|
||||
* Thanks to Joss Sanglier (http://www.dancingbear.co.uk/) for adding
|
||||
* several more HTML entity codes to the $search and $replace arrays.
|
||||
* Updated 11/7/03.
|
||||
*
|
||||
* Thanks to Darius Kasperavicius (http://www.dar.dar.lt/) for
|
||||
* suggesting the addition of $allowed_tags and its supporting function
|
||||
* (which I slightly modified). Updated 3/12/04.
|
||||
*
|
||||
* Thanks to Justin Dearing for pointing out that a replacement for the
|
||||
* <TH> tag was missing, and suggesting an appropriate fix.
|
||||
* Updated 8/25/04.
|
||||
*
|
||||
* Thanks to Mathieu Collas (http://www.myefarm.com/) for finding a
|
||||
* display/formatting bug in the _build_link_list() function: email
|
||||
* readers would show the left bracket and number ("[1") as part of the
|
||||
* rendered email address.
|
||||
* Updated 12/16/04.
|
||||
*
|
||||
* Thanks to Wojciech Bajon (http://histeria.pl/) for submitting code
|
||||
* to handle relative links, which I hadn't considered. I modified his
|
||||
* code a bit to handle normal HTTP links and MAILTO links. Also for
|
||||
* suggesting three additional HTML entity codes to search for.
|
||||
* Updated 03/02/05.
|
||||
*
|
||||
* Thanks to Jacob Chandler for pointing out another link condition
|
||||
* for the _build_link_list() function: "https".
|
||||
* Updated 04/06/05.
|
||||
*
|
||||
* Thanks to Marc Bertrand (http://www.dresdensky.com/) for
|
||||
* suggesting a revision to the word wrapping functionality; if you
|
||||
* specify a $width of 0 or less, word wrapping will be ignored.
|
||||
* Updated 11/02/06.
|
||||
*
|
||||
* *** Big housecleaning updates below:
|
||||
*
|
||||
* Thanks to Colin Brown (http://www.sparkdriver.co.uk/) for
|
||||
* suggesting the fix to handle </li> and blank lines (whitespace).
|
||||
* Christian Basedau (http://www.movetheweb.de/) also suggested the
|
||||
* blank lines fix.
|
||||
*
|
||||
* Special thanks to Marcus Bointon (http://www.synchromedia.co.uk/),
|
||||
* Christian Basedau, Norbert Laposa (http://ln5.co.uk/),
|
||||
* Bas van de Weijer, and Marijn van Butselaar
|
||||
* for pointing out my glaring error in the <th> handling. Marcus also
|
||||
* supplied a host of fixes.
|
||||
*
|
||||
* Thanks to Jeffrey Silverman (http://www.newtnotes.com/) for pointing
|
||||
* out that extra spaces should be compressed--a problem addressed with
|
||||
* Marcus Bointon's fixes but that I had not yet incorporated.
|
||||
*
|
||||
* Thanks to Daniel Schledermann (http://www.typoconsult.dk/) for
|
||||
* suggesting a valuable fix with <a> tag handling.
|
||||
*
|
||||
* Thanks to Wojciech Bajon (again!) for suggesting fixes and additions,
|
||||
* including the <a> tag handling that Daniel Schledermann pointed
|
||||
* out but that I had not yet incorporated. I haven't (yet)
|
||||
* incorporated all of Wojciech's changes, though I may at some
|
||||
* future time.
|
||||
*
|
||||
* *** End of the housecleaning updates. Updated 08/08/07.
|
||||
*
|
||||
* @author Jon Abernathy <jon@chuggnutt.com>
|
||||
* @version 1.0.0
|
||||
* @since PHP 4.0.2
|
||||
*/
|
||||
class html2text
|
||||
{
|
||||
|
||||
|
|
@ -113,7 +30,7 @@ class html2text
|
|||
* @var string $html
|
||||
* @access public
|
||||
*/
|
||||
var $html;
|
||||
public $html;
|
||||
|
||||
/**
|
||||
* Contains the converted, formatted text.
|
||||
|
|
@ -121,7 +38,7 @@ class html2text
|
|||
* @var string $text
|
||||
* @access public
|
||||
*/
|
||||
var $text;
|
||||
public $text;
|
||||
|
||||
/**
|
||||
* Maximum width of the formatted text, in columns.
|
||||
|
|
@ -132,7 +49,7 @@ class html2text
|
|||
* @var integer $width
|
||||
* @access public
|
||||
*/
|
||||
var $width = 70;
|
||||
public $width = 70;
|
||||
|
||||
/**
|
||||
* List of preg* regular expression patterns to search for,
|
||||
|
|
@ -142,49 +59,26 @@ class html2text
|
|||
* @access public
|
||||
* @see $replace
|
||||
*/
|
||||
var $search = array(
|
||||
public $search = array(
|
||||
"/\r/", // Non-legal carriage return
|
||||
"/[\n\t]+/", // Newlines and tabs
|
||||
'/[ ]{2,}/', // Runs of spaces, pre-handling
|
||||
'/<head[^>]*>.*?<\/head>/i', // <head>
|
||||
'/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
|
||||
'/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems with
|
||||
//'/<!-- .* -->/', // Comments -- which strip_tags might have problem a with
|
||||
'/<h[123][^>]*>(.*?)<\/h[123]>/ie', // H1 - H3
|
||||
'/<h[456][^>]*>(.*?)<\/h[456]>/ie', // H4 - H6
|
||||
'/<p[^>]*>/i', // <P>
|
||||
'/<br[^>]*>/i', // <br>
|
||||
'/<b[^>]*>(.*?)<\/b>/ie', // <b>
|
||||
'/<strong[^>]*>(.*?)<\/strong>/ie', // <strong>
|
||||
'/<i[^>]*>(.*?)<\/i>/i', // <i>
|
||||
'/<em[^>]*>(.*?)<\/em>/i', // <em>
|
||||
'/(<ul[^>]*>|<\/ul>)/i', // <ul> and </ul>
|
||||
'/(<ol[^>]*>|<\/ol>)/i', // <ol> and </ol>
|
||||
'/<li[^>]*>(.*?)<\/li>/i', // <li> and </li>
|
||||
'/<li[^>]*>/i', // <li>
|
||||
'/<a [^>]*href="([^"]+)"[^>]*>(.*?)<\/a>/ie',
|
||||
// <a href="">
|
||||
'/<hr[^>]*>/i', // <hr>
|
||||
'/<div[^>]*>/i', // <div>
|
||||
'/(<table[^>]*>|<\/table>)/i', // <table> and </table>
|
||||
'/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
|
||||
'/<td[^>]*>(.*?)<\/td>/i', // <td> and </td>
|
||||
'/<th[^>]*>(.*?)<\/th>/ie', // <th> and </th>
|
||||
'/&(nbsp|#160);/i', // Non-breaking space
|
||||
'/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
|
||||
// Double quotes
|
||||
'/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes
|
||||
'/>/i', // Greater-than
|
||||
'/</i', // Less-than
|
||||
'/&(amp|#38);/i', // Ampersand
|
||||
'/&(copy|#169);/i', // Copyright
|
||||
'/&(trade|#8482|#153);/i', // Trademark
|
||||
'/&(reg|#174);/i', // Registered
|
||||
'/&(mdash|#151|#8212);/i', // mdash
|
||||
'/&(ndash|minus|#8211|#8722);/i', // ndash
|
||||
'/&(bull|#149|#8226);/i', // Bullet
|
||||
'/&(pound|#163);/i', // Pound sign
|
||||
'/&(euro|#8364);/i', // Euro sign
|
||||
'/&[^&;]+;/i', // Unknown/unhandled entities
|
||||
'/[ ]{2,}/' // Runs of spaces, post-handling
|
||||
'/<span class="_html2text_ignore">.+?<\/span>/i' // <span class="_html2text_ignore">...</span>
|
||||
);
|
||||
|
||||
/**
|
||||
|
|
@ -194,48 +88,124 @@ class html2text
|
|||
* @access public
|
||||
* @see $search
|
||||
*/
|
||||
var $replace = array(
|
||||
public $replace = array(
|
||||
'', // Non-legal carriage return
|
||||
' ', // Newlines and tabs
|
||||
' ', // Runs of spaces, pre-handling
|
||||
'', // <head>
|
||||
'', // <script>s -- which strip_tags supposedly has problems with
|
||||
'', // <style>s -- which strip_tags supposedly has problems with
|
||||
//'', // Comments -- which strip_tags might have problem a with
|
||||
"strtoupper(\"\n\n\\1\n\n\")", // H1 - H3
|
||||
"ucwords(\"\n\n\\1\n\n\")", // H4 - H6
|
||||
"\n\n\t", // <P>
|
||||
"\n\n", // <P>
|
||||
"\n", // <br>
|
||||
'strtoupper("\\1")', // <b>
|
||||
'strtoupper("\\1")', // <strong>
|
||||
'_\\1_', // <i>
|
||||
'_\\1_', // <em>
|
||||
"\n\n", // <ul> and </ul>
|
||||
"\n\n", // <ol> and </ol>
|
||||
"\t* \\1\n", // <li> and </li>
|
||||
"\n\t* ", // <li>
|
||||
'$this->_build_link_list("\\1", "\\2")',
|
||||
// <a href="">
|
||||
"\n-------------------------\n", // <hr>
|
||||
"<div>\n", // <div>
|
||||
"\n\n", // <table> and </table>
|
||||
"\n", // <tr> and </tr>
|
||||
"\t\t\\1\n", // <td> and </td>
|
||||
"strtoupper(\"\t\t\\1\n\")", // <th> and </th>
|
||||
"" // <span class="_html2text_ignore">...</span>
|
||||
);
|
||||
|
||||
/**
|
||||
* List of preg* regular expression patterns to search for,
|
||||
* used in conjunction with $ent_replace.
|
||||
*
|
||||
* @var array $ent_search
|
||||
* @access public
|
||||
* @see $ent_replace
|
||||
*/
|
||||
public $ent_search = array(
|
||||
'/&(nbsp|#160);/i', // Non-breaking space
|
||||
'/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
|
||||
// Double quotes
|
||||
'/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes
|
||||
'/>/i', // Greater-than
|
||||
'/</i', // Less-than
|
||||
'/&(copy|#169);/i', // Copyright
|
||||
'/&(trade|#8482|#153);/i', // Trademark
|
||||
'/&(reg|#174);/i', // Registered
|
||||
'/&(mdash|#151|#8212);/i', // mdash
|
||||
'/&(ndash|minus|#8211|#8722);/i', // ndash
|
||||
'/&(bull|#149|#8226);/i', // Bullet
|
||||
'/&(pound|#163);/i', // Pound sign
|
||||
'/&(euro|#8364);/i', // Euro sign
|
||||
'/&(amp|#38);/i', // Ampersand: see _converter()
|
||||
'/[ ]{2,}/', // Runs of spaces, post-handling
|
||||
);
|
||||
|
||||
/**
|
||||
* List of pattern replacements corresponding to patterns searched.
|
||||
*
|
||||
* @var array $ent_replace
|
||||
* @access public
|
||||
* @see $ent_search
|
||||
*/
|
||||
public $ent_replace = array(
|
||||
' ', // Non-breaking space
|
||||
'"', // Double quotes
|
||||
"'", // Single quotes
|
||||
'>',
|
||||
'<',
|
||||
'&',
|
||||
'(c)',
|
||||
'(tm)',
|
||||
'(R)',
|
||||
'--',
|
||||
'-',
|
||||
'*',
|
||||
'<27>',
|
||||
'EUR', // Euro sign. <20> ?
|
||||
'', // Unknown/unhandled entities
|
||||
' ' // Runs of spaces, post-handling
|
||||
'£',
|
||||
'EUR', // Euro sign. € ?
|
||||
'|+|amp|+|', // Ampersand: see _converter()
|
||||
' ', // Runs of spaces, post-handling
|
||||
);
|
||||
|
||||
/**
|
||||
* List of preg* regular expression patterns to search for
|
||||
* and replace using callback function.
|
||||
*
|
||||
* @var array $callback_search
|
||||
* @access public
|
||||
*/
|
||||
public $callback_search = array(
|
||||
'/<(a) [^>]*href=("|\')([^"\']+)\2([^>]*)>(.*?)<\/a>/i', // <a href="">
|
||||
'/<(h)[123456]( [^>]*)?>(.*?)<\/h[123456]>/i', // h1 - h6
|
||||
'/<(b)( [^>]*)?>(.*?)<\/b>/i', // <b>
|
||||
'/<(strong)( [^>]*)?>(.*?)<\/strong>/i', // <strong>
|
||||
'/<(th)( [^>]*)?>(.*?)<\/th>/i', // <th> and </th>
|
||||
);
|
||||
|
||||
/**
|
||||
* List of preg* regular expression patterns to search for in PRE body,
|
||||
* used in conjunction with $pre_replace.
|
||||
*
|
||||
* @var array $pre_search
|
||||
* @access public
|
||||
* @see $pre_replace
|
||||
*/
|
||||
public $pre_search = array(
|
||||
"/\n/",
|
||||
"/\t/",
|
||||
'/ /',
|
||||
'/<pre[^>]*>/',
|
||||
'/<\/pre>/'
|
||||
);
|
||||
|
||||
/**
|
||||
* List of pattern replacements corresponding to patterns searched for PRE body.
|
||||
*
|
||||
* @var array $pre_replace
|
||||
* @access public
|
||||
* @see $pre_search
|
||||
*/
|
||||
public $pre_replace = array(
|
||||
'<br>',
|
||||
' ',
|
||||
' ',
|
||||
'',
|
||||
''
|
||||
);
|
||||
|
||||
/**
|
||||
|
|
@ -245,7 +215,7 @@ class html2text
|
|||
* @access public
|
||||
* @see set_allowed_tags()
|
||||
*/
|
||||
var $allowed_tags = '';
|
||||
public $allowed_tags = '';
|
||||
|
||||
/**
|
||||
* Contains the base URL that relative links should resolve to.
|
||||
|
|
@ -253,7 +223,7 @@ class html2text
|
|||
* @var string $url
|
||||
* @access public
|
||||
*/
|
||||
var $url;
|
||||
public $url;
|
||||
|
||||
/**
|
||||
* Indicates whether content in the $html variable has been converted yet.
|
||||
|
|
@ -262,26 +232,38 @@ class html2text
|
|||
* @access private
|
||||
* @see $html, $text
|
||||
*/
|
||||
var $_converted = false;
|
||||
private $_converted = false;
|
||||
|
||||
/**
|
||||
* Contains URL addresses from links to be rendered in plain text.
|
||||
*
|
||||
* @var string $_link_list
|
||||
* @var array $_link_list
|
||||
* @access private
|
||||
* @see _build_link_list()
|
||||
*/
|
||||
var $_link_list = '';
|
||||
|
||||
private $_link_list = array();
|
||||
|
||||
|
||||
/**
|
||||
* Number of valid links detected in the text, used for plain text
|
||||
* display (rendered similar to footnotes).
|
||||
* Various configuration options (able to be set in the constructor)
|
||||
*
|
||||
* @var integer $_link_count
|
||||
* @var array $_options
|
||||
* @access private
|
||||
* @see _build_link_list()
|
||||
*/
|
||||
var $_link_count = 0;
|
||||
private $_options = array(
|
||||
|
||||
// 'none'
|
||||
// 'inline' (show links inline)
|
||||
// 'nextline' (show links on the next line)
|
||||
// 'table' (if a table of link URLs should be listed after the text.
|
||||
'do_links' => 'inline',
|
||||
|
||||
// Maximum width of the formatted text, in columns.
|
||||
// Set this value to 0 (or less) to ignore word wrapping
|
||||
// and not constrain text to a fixed-width column.
|
||||
'width' => 70,
|
||||
);
|
||||
|
||||
|
||||
/**
|
||||
* Constructor.
|
||||
|
|
@ -292,14 +274,18 @@ class html2text
|
|||
*
|
||||
* @param string $source HTML content
|
||||
* @param boolean $from_file Indicates $source is a file to pull content from
|
||||
* @param array $options Set configuration options
|
||||
* @access public
|
||||
* @return void
|
||||
*/
|
||||
function html2text( $source = '', $from_file = false )
|
||||
public function __construct( $source = '', $from_file = false, $options = array() )
|
||||
{
|
||||
$this->_options = array_merge($this->_options, $options);
|
||||
|
||||
if ( !empty($source) ) {
|
||||
$this->set_html($source, $from_file);
|
||||
}
|
||||
|
||||
$this->set_base_url();
|
||||
}
|
||||
|
||||
|
|
@ -311,15 +297,13 @@ class html2text
|
|||
* @access public
|
||||
* @return void
|
||||
*/
|
||||
function set_html( $source, $from_file = false )
|
||||
public function set_html( $source, $from_file = false )
|
||||
{
|
||||
$this->html = $source;
|
||||
|
||||
if ( $from_file && file_exists($source) ) {
|
||||
$fp = fopen($source, 'r');
|
||||
$this->html = fread($fp, filesize($source));
|
||||
fclose($fp);
|
||||
$this->html = file_get_contents($source);
|
||||
}
|
||||
else
|
||||
$this->html = $source;
|
||||
|
||||
$this->_converted = false;
|
||||
}
|
||||
|
|
@ -330,7 +314,7 @@ class html2text
|
|||
* @access public
|
||||
* @return string
|
||||
*/
|
||||
function get_text()
|
||||
public function get_text()
|
||||
{
|
||||
if ( !$this->_converted ) {
|
||||
$this->_convert();
|
||||
|
|
@ -345,7 +329,7 @@ class html2text
|
|||
* @access public
|
||||
* @return void
|
||||
*/
|
||||
function print_text()
|
||||
public function print_text()
|
||||
{
|
||||
print $this->get_text();
|
||||
}
|
||||
|
|
@ -357,7 +341,7 @@ class html2text
|
|||
* @return void
|
||||
* @see print_text()
|
||||
*/
|
||||
function p()
|
||||
public function p()
|
||||
{
|
||||
print $this->get_text();
|
||||
}
|
||||
|
|
@ -370,7 +354,7 @@ class html2text
|
|||
* @access public
|
||||
* @return void
|
||||
*/
|
||||
function set_allowed_tags( $allowed_tags = '' )
|
||||
public function set_allowed_tags( $allowed_tags = '' )
|
||||
{
|
||||
if ( !empty($allowed_tags) ) {
|
||||
$this->allowed_tags = $allowed_tags;
|
||||
|
|
@ -383,14 +367,14 @@ class html2text
|
|||
* @access public
|
||||
* @return void
|
||||
*/
|
||||
function set_base_url( $url = '' )
|
||||
public function set_base_url( $url = '' )
|
||||
{
|
||||
if ( empty($url) ) {
|
||||
if ( !empty($_SERVER['HTTP_HOST']) ) {
|
||||
$this->url = 'http://' . $_SERVER['HTTP_HOST'];
|
||||
} else {
|
||||
$this->url = '';
|
||||
}
|
||||
if ( !empty($_SERVER['HTTP_HOST']) ) {
|
||||
$this->url = 'http://' . $_SERVER['HTTP_HOST'];
|
||||
} else {
|
||||
$this->url = '';
|
||||
}
|
||||
} else {
|
||||
// Strip any trailing slashes for consistency (relative
|
||||
// URLs may already start with a slash like "/file.html")
|
||||
|
|
@ -402,44 +386,27 @@ class html2text
|
|||
}
|
||||
|
||||
/**
|
||||
* Workhorse function that does actual conversion.
|
||||
*
|
||||
* First performs custom tag replacement specified by $search and
|
||||
* $replace arrays. Then strips any remaining HTML tags, reduces whitespace
|
||||
* and newlines to a readable format, and word wraps the text to
|
||||
* $width characters.
|
||||
* Workhorse function that does actual conversion (calls _converter() method).
|
||||
*
|
||||
* @access private
|
||||
* @return void
|
||||
*/
|
||||
function _convert()
|
||||
private function _convert()
|
||||
{
|
||||
// Variables used for building the link list
|
||||
$this->_link_count = 0;
|
||||
$this->_link_list = '';
|
||||
$this->_link_list = array();
|
||||
|
||||
$text = trim(stripslashes($this->html));
|
||||
|
||||
// Run our defined search-and-replace
|
||||
$text = preg_replace($this->search, $this->replace, $text);
|
||||
|
||||
// Strip any other HTML tags
|
||||
$text = strip_tags($text, $this->allowed_tags);
|
||||
|
||||
// Bring down number of empty lines to 2 max
|
||||
$text = preg_replace("/\n\s+\n/", "\n\n", $text);
|
||||
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
|
||||
// Convert HTML to TXT
|
||||
$this->_converter($text);
|
||||
|
||||
// Add link list
|
||||
if ( !empty($this->_link_list) ) {
|
||||
$text .= "\n\nLinks:\n------\n" . $this->_link_list;
|
||||
}
|
||||
|
||||
// Wrap the text to a readable format
|
||||
// for PHP versions >= 4.0.2. Default width is 75
|
||||
// If width is 0 or less, don't wrap the text.
|
||||
if ( $this->width > 0 ) {
|
||||
$text = wordwrap($text, $this->width);
|
||||
if (!empty($this->_link_list)) {
|
||||
$text .= "\n\nLinks:\n------\n";
|
||||
foreach ($this->_link_list as $idx => $url) {
|
||||
$text .= '[' . ($idx+1) . '] ' . $url . "\n";
|
||||
}
|
||||
}
|
||||
|
||||
$this->text = $text;
|
||||
|
|
@ -447,6 +414,64 @@ class html2text
|
|||
$this->_converted = true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Workhorse function that does actual conversion.
|
||||
*
|
||||
* First performs custom tag replacement specified by $search and
|
||||
* $replace arrays. Then strips any remaining HTML tags, reduces whitespace
|
||||
* and newlines to a readable format, and word wraps the text to
|
||||
* $this->_options['width'] characters.
|
||||
*
|
||||
* @param string Reference to HTML content string
|
||||
*
|
||||
* @access private
|
||||
* @return void
|
||||
*/
|
||||
private function _converter(&$text)
|
||||
{
|
||||
// Convert <BLOCKQUOTE> (before PRE!)
|
||||
$this->_convert_blockquotes($text);
|
||||
|
||||
// Convert <PRE>
|
||||
$this->_convert_pre($text);
|
||||
|
||||
// Run our defined tags search-and-replace
|
||||
$text = preg_replace($this->search, $this->replace, $text);
|
||||
|
||||
// Run our defined tags search-and-replace with callback
|
||||
$text = preg_replace_callback($this->callback_search, array($this, '_preg_callback'), $text);
|
||||
|
||||
// Strip any other HTML tags
|
||||
$text = strip_tags($text, $this->allowed_tags);
|
||||
|
||||
// Run our defined entities/characters search-and-replace
|
||||
$text = preg_replace($this->ent_search, $this->ent_replace, $text);
|
||||
|
||||
// Replace known html entities
|
||||
$text = html_entity_decode($text, ENT_QUOTES);
|
||||
|
||||
// Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
|
||||
$text = preg_replace('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text);
|
||||
|
||||
// Convert "|+|amp|+|" into "&", need to be done after handling of unknown entities
|
||||
// This properly handles situation of "&quot;" in input string
|
||||
$text = str_replace('|+|amp|+|', '&', $text);
|
||||
|
||||
// Bring down number of empty lines to 2 max
|
||||
$text = preg_replace("/\n\s+\n/", "\n\n", $text);
|
||||
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
|
||||
|
||||
// remove leading empty lines (can be produced by eg. P tag on the beginning)
|
||||
$text = ltrim($text, "\n");
|
||||
|
||||
// Wrap the text to a readable format
|
||||
// for PHP versions >= 4.0.2. Default width is 75
|
||||
// If width is 0 or less, don't wrap the text.
|
||||
if ( $this->_options['width'] > 0 ) {
|
||||
$text = wordwrap($text, $this->_options['width']);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Helper function called by preg_replace() on link replacement.
|
||||
*
|
||||
|
|
@ -460,30 +485,211 @@ class html2text
|
|||
* @access private
|
||||
* @return string
|
||||
*/
|
||||
function _build_link_list( $link, $display )
|
||||
private function _build_link_list( $link, $display, $link_override = null)
|
||||
{
|
||||
if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' ||
|
||||
substr($link, 0, 7) == 'mailto:' ) {
|
||||
$this->_link_count++;
|
||||
$this->_link_list .= "[" . $this->_link_count . "] $link\n";
|
||||
$additional = ' [' . $this->_link_count . ']';
|
||||
} elseif ( substr($link, 0, 11) == 'javascript:' ) {
|
||||
// Don't count the link; ignore it
|
||||
$additional = '';
|
||||
// what about href="#anchor" ?
|
||||
} else {
|
||||
$this->_link_count++;
|
||||
$this->_link_list .= "[" . $this->_link_count . "] " . $this->url;
|
||||
if ( substr($link, 0, 1) != '/' ) {
|
||||
$this->_link_list .= '/';
|
||||
$link_method = ($link_override) ? $link_override : $this->_options['do_links'];
|
||||
if ($link_method == 'none')
|
||||
return $display;
|
||||
|
||||
|
||||
// Ignored link types
|
||||
if (preg_match('!^(javascript:|mailto:|#)!i', $link)) {
|
||||
return $display;
|
||||
}
|
||||
if (preg_match('!^([a-z][a-z0-9.+-]+:)!i', $link)) {
|
||||
$url = $link;
|
||||
}
|
||||
else {
|
||||
$url = $this->url;
|
||||
if (substr($link, 0, 1) != '/') {
|
||||
$url .= '/';
|
||||
}
|
||||
$this->_link_list .= "$link\n";
|
||||
$additional = ' [' . $this->_link_count . ']';
|
||||
$url .= "$link";
|
||||
}
|
||||
|
||||
return $display . $additional;
|
||||
if ($link_method == 'table')
|
||||
{
|
||||
if (($index = array_search($url, $this->_link_list)) === false) {
|
||||
$index = count($this->_link_list);
|
||||
$this->_link_list[] = $url;
|
||||
}
|
||||
|
||||
return $display . ' [' . ($index+1) . ']';
|
||||
}
|
||||
elseif ($link_method == 'nextline')
|
||||
{
|
||||
return $display . "\n[" . $url . ']';
|
||||
}
|
||||
else // link_method defaults to inline
|
||||
{
|
||||
return $display . ' [' . $url . ']';
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
/**
|
||||
* Helper function for PRE body conversion.
|
||||
*
|
||||
* @param string HTML content
|
||||
* @access private
|
||||
*/
|
||||
private function _convert_pre(&$text)
|
||||
{
|
||||
// get the content of PRE element
|
||||
while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
|
||||
$this->pre_content = $matches[1];
|
||||
|
||||
?>
|
||||
// Run our defined tags search-and-replace with callback
|
||||
$this->pre_content = preg_replace_callback($this->callback_search,
|
||||
array($this, '_preg_callback'), $this->pre_content);
|
||||
|
||||
// convert the content
|
||||
$this->pre_content = sprintf('<div><br>%s<br></div>',
|
||||
preg_replace($this->pre_search, $this->pre_replace, $this->pre_content));
|
||||
// replace the content (use callback because content can contain $0 variable)
|
||||
$text = preg_replace_callback('/<pre[^>]*>.*<\/pre>/ismU',
|
||||
array($this, '_preg_pre_callback'), $text, 1);
|
||||
|
||||
// free memory
|
||||
$this->pre_content = '';
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Helper function for BLOCKQUOTE body conversion.
|
||||
*
|
||||
* @param string HTML content
|
||||
* @access private
|
||||
*/
|
||||
private function _convert_blockquotes(&$text)
|
||||
{
|
||||
if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
|
||||
$level = 0;
|
||||
$diff = 0;
|
||||
$start = 0;
|
||||
$taglen = 0;
|
||||
foreach ($matches[0] as $m) {
|
||||
if ($m[0][0] == '<' && $m[0][1] == '/') {
|
||||
$level--;
|
||||
if ($level < 0) {
|
||||
$level = 0; // malformed HTML: go to next blockquote
|
||||
}
|
||||
else if ($level > 0) {
|
||||
// skip inner blockquote
|
||||
}
|
||||
else {
|
||||
$end = $m[1];
|
||||
$len = $end - $taglen - $start;
|
||||
// Get blockquote content
|
||||
$body = substr($text, $start + $taglen - $diff, $len);
|
||||
|
||||
// Set text width
|
||||
$p_width = $this->_options['width'];
|
||||
if ($this->_options['width'] > 0) $this->_options['width'] -= 2;
|
||||
// Convert blockquote content
|
||||
$body = trim($body);
|
||||
$this->_converter($body);
|
||||
// Add citation markers and create PRE block
|
||||
$body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body));
|
||||
$body = '<pre>' . htmlspecialchars($body) . '</pre>';
|
||||
// Re-set text width
|
||||
$this->_options['width'] = $p_width;
|
||||
// Replace content
|
||||
$text = substr($text, 0, $start - $diff)
|
||||
. $body . substr($text, $end + strlen($m[0]) - $diff);
|
||||
|
||||
$diff = $len + $taglen + strlen($m[0]) - strlen($body);
|
||||
unset($body);
|
||||
}
|
||||
}
|
||||
else {
|
||||
if ($level == 0) {
|
||||
$start = $m[1];
|
||||
$taglen = strlen($m[0]);
|
||||
}
|
||||
$level ++;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Callback function for preg_replace_callback use.
|
||||
*
|
||||
* @param array PREG matches
|
||||
* @return string
|
||||
*/
|
||||
private function _preg_callback($matches)
|
||||
{
|
||||
switch (strtolower($matches[1])) {
|
||||
case 'b':
|
||||
case 'strong':
|
||||
return $this->_toupper($matches[3]);
|
||||
case 'th':
|
||||
return $this->_toupper("\t\t". $matches[3] ."\n");
|
||||
case 'h':
|
||||
return $this->_toupper("\n\n". $matches[3] ."\n\n");
|
||||
case 'a':
|
||||
// override the link method
|
||||
$link_override = null;
|
||||
if (preg_match("/_html2text_link_(\w+)/", $matches[4], $link_override_match))
|
||||
{
|
||||
$link_override = $link_override_match[1];
|
||||
}
|
||||
// Remove spaces in URL (#1487805)
|
||||
$url = str_replace(' ', '', $matches[3]);
|
||||
return $this->_build_link_list($url, $matches[5], $link_override);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Callback function for preg_replace_callback use in PRE content handler.
|
||||
*
|
||||
* @param array PREG matches
|
||||
* @return string
|
||||
*/
|
||||
private function _preg_pre_callback($matches)
|
||||
{
|
||||
return $this->pre_content;
|
||||
}
|
||||
|
||||
/**
|
||||
* Strtoupper function with HTML tags and entities handling.
|
||||
*
|
||||
* @param string $str Text to convert
|
||||
* @return string Converted text
|
||||
*/
|
||||
private function _toupper($str)
|
||||
{
|
||||
// string can containg HTML tags
|
||||
$chunks = preg_split('/(<[^>]*>)/', $str, null, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE);
|
||||
|
||||
// convert toupper only the text between HTML tags
|
||||
foreach ($chunks as $idx => $chunk) {
|
||||
if ($chunk[0] != '<') {
|
||||
$chunks[$idx] = $this->_strtoupper($chunk);
|
||||
}
|
||||
}
|
||||
|
||||
return implode($chunks);
|
||||
}
|
||||
|
||||
/**
|
||||
* Strtoupper multibyte wrapper function with HTML entities handling.
|
||||
*
|
||||
* @param string $str Text to convert
|
||||
* @return string Converted text
|
||||
*/
|
||||
private function _strtoupper($str)
|
||||
{
|
||||
$str = html_entity_decode($str, ENT_COMPAT);
|
||||
|
||||
if (function_exists('mb_strtoupper'))
|
||||
$str = mb_strtoupper($str);
|
||||
else
|
||||
$str = strtoupper($str);
|
||||
|
||||
$str = htmlspecialchars($str, ENT_COMPAT);
|
||||
|
||||
return $str;
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue