summaryrefslogtreecommitdiff
path: root/program
diff options
context:
space:
mode:
authoralecpl <alec@alec.pl>2008-08-30 11:24:39 +0000
committeralecpl <alec@alec.pl>2008-08-30 11:24:39 +0000
commit8ac6fd094af2ecc93ad8f750a0731c043f7f8a2a (patch)
tree12c0409e4ba8842a028fa0cf55e17978ade77f85 /program
parenta91c9ba12a3e04eb7564592016024b568fe12ec4 (diff)
- Improved HTML to TXT conversion by html2text class update to version 1.0.0
Diffstat (limited to 'program')
-rw-r--r--program/lib/html2text.php413
1 files changed, 225 insertions, 188 deletions
diff --git a/program/lib/html2text.php b/program/lib/html2text.php
index b476555ba..ee7b0dc40 100644
--- a/program/lib/html2text.php
+++ b/program/lib/html2text.php
@@ -1,78 +1,109 @@
<?php
/*************************************************************************
-* *
-* class.html2text.inc *
-* *
-*************************************************************************
-* *
-* Converts HTML to formatted plain text *
-* *
-* Copyright (c) 2005 Jon Abernathy <jon@chuggnutt.com> *
-* All rights reserved. *
-* *
-* 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 *
-* the Free Software Foundation; either version 2 of the License, or *
-* (at your option) any later version. *
-* *
-* The GNU General Public License can be found at *
-* http://www.gnu.org/copyleft/gpl.html. *
-* *
-* This script 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 General Public License for more details. *
-* *
-* Author(s): Jon Abernathy <jon@chuggnutt.com> *
-* *
-* Last modified: 04/06/05 *
-* Modified: 2004/05/19 (tbr) *
-* *
-*************************************************************************/
-
-/* 2008/08/29: Added PRE handling by A.L.E.C <alec@alec.pl> */
+ * *
+ * class.html2text.inc *
+ * *
+ *************************************************************************
+ * *
+ * Converts HTML to formatted plain text *
+ * *
+ * Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> *
+ * All rights reserved. *
+ * *
+ * 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 *
+ * the Free Software Foundation; either version 2 of the License, or *
+ * (at your option) any later version. *
+ * *
+ * The GNU General Public License can be found at *
+ * http://www.gnu.org/copyleft/gpl.html. *
+ * *
+ * This script 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 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.
-*
-* @author Jon Abernathy <jon@chuggnutt.com>
-* @version 0.6.1
-* @since PHP 4.0.2
-*/
+ * 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
{
@@ -95,6 +126,9 @@ class html2text
/**
* 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.
+ *
* @var integer $width
* @access public
*/
@@ -111,43 +145,46 @@ class html2text
var $search = array(
"/\r/", // Non-legal carriage return
"/[\n\t]+/", // Newlines and tabs
+ '/[ ]{2,}/', // Runs of spaces, pre-handling
'/<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
- '/<a [^>]*href=("|\')([^"\']+)\1[^>]*>(.+?)<\/a>/ie', // <a href="">
- '/<h[123][^>]*>(.+?)<\/h[123]>/ie', // H1 - H3
- '/<h[456][^>]*>(.+?)<\/h[456]>/ie', // H4 - H6
+ '/<h[123][^>]*>(.*?)<\/h[123]>/ie', // H1 - H3
+ '/<h[456][^>]*>(.*?)<\/h[456]>/ie', // H4 - H6
'/<p[^>]*>/i', // <P>
'/<br[^>]*>/i', // <br>
- '/<b[^>]*>(.+?)<\/b>/ie', // <b>
- '/<i[^>]*>(.+?)<\/i>/i', // <i>
+ '/<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=("|\')([^"\']+)\1[^>]*>(.*?)<\/a>/ie',
+ // <a href="">
'/<hr[^>]*>/i', // <hr>
'/(<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;/i',
- '/&quot;/i',
- '/&gt;/i',
- '/&lt;/i',
- '/&(amp|#38);/i',
- '/&copy;/i',
- '/&trade;/i',
- '/&#8220;/',
- '/&#8221;/',
- '/&#8211;/',
- '/&#(8217|39);/',
- '/&#169;/',
- '/&#8482;/',
- '/&#151;/',
- '/&#147;/',
- '/&#148;/',
- '/&#149;/',
- '/&reg;/i',
- '/&bull;/i',
- '/&[&;]+;/i'
+ '/<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
+ '/&gt;/i', // Greater-than
+ '/&lt;/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
);
/**
@@ -160,53 +197,55 @@ class html2text
var $replace = array(
'', // Non-legal carriage return
' ', // Newlines and tabs
+ ' ', // Runs of spaces, pre-handling
'', // <script>s -- which strip_tags supposedly has problems with
- //'', // Comments -- which strip_tags might have problem a with
- '$this->_build_link_list("\\2", "\\3")', // <a href="">
+ '', // <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\")", // H4 - H6
- "\n\n", // <P>
+ "ucwords(\"\n\n\\1\n\")", // H4 - H6
+ "\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*", // <li>
- "\n-------------------------\n", // <hr>
- "\n\n", // <table> and </table>
+ "\t* \\1\n", // <li> and </li>
+ "\n\t* ", // <li>
+ '$this->_build_link_list("\\2", "\\3")',
+ // <a href="">
+ "\n-------------------------\n", // <hr>
+ "\n\n", // <table> and </table>
"\n", // <tr> and </tr>
"\t\t\\1\n", // <td> and </td>
"strtoupper(\"\t\t\\1\n\")", // <th> and </th>
- ' ',
- '"',
+ ' ', // Non-breaking space
+ '"', // Double quotes
+ "'", // Single quotes
'>',
'<',
'&',
'(c)',
'(tm)',
- '"',
- '"',
- '-',
- "'",
- '(c)',
- '(tm)',
- '--',
- '"',
- '"',
- '*',
'(R)',
+ '--',
+ '-',
'*',
- ''
+ '£',
+ 'EUR', // Euro sign. € ?
+ '', // Unknown/unhandled entities
+ ' ' // Runs of spaces, post-handling
);
- /**
- * 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
- */
+ /**
+ * 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
+ */
var $pre_search = array(
"/\n/",
"/\t/",
@@ -250,7 +289,7 @@ class html2text
/**
* Indicates whether content in the $html variable has been converted yet.
*
- * @var boolean $converted
+ * @var boolean $_converted
* @access private
* @see $html, $text
*/
@@ -259,20 +298,21 @@ class html2text
/**
* Contains URL addresses from links to be rendered in plain text.
*
- * @var string $link_list
+ * @var string $_link_list
* @access private
* @see _build_link_list()
*/
- var $_link_list = array();
+ var $_link_list = '';
/**
- * Boolean flag, true if a table of link URLs should be listed after the text.
- *
- * @var boolean $_do_links
- * @access private
- * @see html2text()
+ * Number of valid links detected in the text, used for plain text
+ * display (rendered similar to footnotes).
+ *
+ * @var integer $_link_count
+ * @access private
+ * @see _build_link_list()
*/
- var $_do_links = true;
+ var $_link_count = 0;
/**
* Constructor.
@@ -283,17 +323,15 @@ class html2text
*
* @param string $source HTML content
* @param boolean $from_file Indicates $source is a file to pull content from
- * @param boolean $do_link_table indicate whether a table of link URLs is desired
* @access public
* @return void
*/
- function html2text( $source = '', $from_file = false, $produce_link_table = true )
+ function html2text( $source = '', $from_file = false )
{
if ( !empty($source) ) {
$this->set_html($source, $from_file);
}
$this->set_base_url();
- $this->_do_links = $produce_link_table;
}
/**
@@ -307,10 +345,11 @@ class html2text
function set_html( $source, $from_file = false )
{
if ( $from_file && file_exists($source) ) {
- $this->html = file_get_contents($source);
+ $this->html = file_get_contents($source);
}
- else
- $this->html = $source;
+ else
+ $this->html = $source;
+
$this->_converted = false;
}
@@ -377,7 +416,11 @@ class html2text
function set_base_url( $url = '' )
{
if ( empty($url) ) {
- $this->url = 'http://' . $_SERVER['HTTP_HOST'];
+ if ( !empty($_SERVER['HTTP_HOST']) ) {
+ $this->url = 'http://' . $_SERVER['HTTP_HOST'];
+ } else {
+ $this->url = '';
+ }
} else {
// Strip any trailing slashes for consistency (relative
// URLs may already start with a slash like "/file.html")
@@ -402,14 +445,14 @@ class html2text
function _convert()
{
// Variables used for building the link list
- //$link_count = 1;
- //$this->_link_list = '';
+ $this->_link_count = 0;
+ $this->_link_list = '';
$text = trim(stripslashes($this->html));
// Convert <PRE>
- $this->_convert_pre($text);
-
+ $this->_convert_pre($text);
+
// Run our defined search-and-replace
$text = preg_replace($this->search, $this->replace, $text);
@@ -417,20 +460,20 @@ class html2text
$text = strip_tags($text, $this->allowed_tags);
// Bring down number of empty lines to 2 max
- $text = preg_replace("/\n\s+\n/", "\n", $text);
+ $text = preg_replace("/\n\s+\n/", "\n\n", $text);
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
// Add link list
- if ( sizeof($this->_link_list) ) {
- $text .= "\n\nLinks:\n------\n";
- foreach ($this->_link_list as $id => $link) {
- $text .= '[' . ($id+1) . '] ' . $link . "\n";
- }
+ if ( !empty($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
- $text = wordwrap($text, $this->width);
+ // If width is 0 or less, don't wrap the text.
+ if ( $this->width > 0 ) {
+ $text = wordwrap($text, $this->width);
+ }
$this->text = $text;
@@ -445,55 +488,49 @@ class html2text
* appeared. Also makes an effort at identifying and handling absolute
* and relative links.
*
- * @param integer $link_count Counter tracking current link number
* @param string $link URL of the link
* @param string $display Part of the text to associate number with
* @access private
* @return string
- */
- function _build_link_list($link, $display)
- {
- if (! $this->_do_links) return $display;
-
- $link_lc = strtolower($link);
-
- if (substr($link_lc, 0, 7) == 'http://' || substr($link_lc, 0, 8) == 'https://' || substr($link_lc, 0, 7) == 'mailto:')
- {
- $url = $link;
- }
- else
- {
- $url = $this->url;
- if ($link{0} != '/') {
- $url .= '/';
+ */
+ function _build_link_list( $link, $display )
+ {
+ if ( substr($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 .= '/';
}
- $url .= $link;
+ $this->_link_list .= "$link\n";
+ $additional = ' [' . $this->_link_count . ']';
}
- $index = array_search($url, $this->_link_list);
- if ($index===FALSE)
- {
- $index = sizeof($this->_link_list);
- $this->_link_list[$index] = $url;
- }
-
- return $display . ' [' . ($index+1) . ']';
- }
-
+ return $display . $additional;
+ }
+
/**
* Helper function for PRE body conversion.
*
* @param string HTML content
* @access private
- */
+ */
function _convert_pre(&$text)
- {
- while(preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches))
- {
- $result = preg_replace($this->pre_search, $this->pre_replace, $matches[1]);
- $text = preg_replace('/<pre[^>]*>.*<\/pre>/ismU', '<div><br>' . $result . '<br></div>', $text);
- }
- }
+ {
+ while(preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches))
+ {
+ $result = preg_replace($this->pre_search, $this->pre_replace, $matches[1]);
+ $text = preg_replace('/<pre[^>]*>.*<\/pre>/ismU', '<div><br>' . $result . '<br></div>', $text);
+ }
+ }
}
?>