| 1 |
<?php
|
| 2 |
// $Id:$
|
| 3 |
|
| 4 |
// Author: Robert Castelo
|
| 5 |
// Support: development@cortextcommunications.com
|
| 6 |
// Info: http://www.cortextcommunications.com/development/newsletter
|
| 7 |
// This module based on class.html2text.inc
|
| 8 |
// by Jon Abernathy <jon@chuggnutt.com>
|
| 9 |
|
| 10 |
/**
|
| 11 |
* Converts HTML to plain text equivalent.
|
| 12 |
*/
|
| 13 |
|
| 14 |
/**
|
| 15 |
* Implementation of hook_help().
|
| 16 |
*/
|
| 17 |
function html2txt_help($section) {
|
| 18 |
switch ($section) {
|
| 19 |
case 'admin/modules#description':
|
| 20 |
return t('Converts HTML to plain text.');
|
| 21 |
}
|
| 22 |
}
|
| 23 |
|
| 24 |
|
| 25 |
/**
|
| 26 |
* Workhorse function that does actual conversion.
|
| 27 |
*
|
| 28 |
* First performs custom tag replacement specified by $search and
|
| 29 |
* $replace arrays. Then strips any remaining HTML tags, reduces whitespace
|
| 30 |
* and newlines to a readable format, and word wraps the text to
|
| 31 |
* $width characters.
|
| 32 |
*
|
| 33 |
*/
|
| 34 |
function html2txt_convert($html, $width = NULL, $list_links = NULL, $allowed_tags = '', $empty_lines_max = NULL) {
|
| 35 |
|
| 36 |
global $saved_snippets;
|
| 37 |
$snippet_count = 1;
|
| 38 |
$saved_snippets = array();
|
| 39 |
$converted->text = $html;
|
| 40 |
|
| 41 |
$converted->text = trim(stripslashes($converted->text));
|
| 42 |
|
| 43 |
// Get HTML to search for
|
| 44 |
// Get replacements for HTML
|
| 45 |
$search = _html2txt_define_search();
|
| 46 |
$replace = _html2txt_define_replace();
|
| 47 |
|
| 48 |
// Strip out links or list them?
|
| 49 |
if ($list_links) {
|
| 50 |
global $link_list;
|
| 51 |
$link_list = '';
|
| 52 |
$link_count = 1;
|
| 53 |
$search[] = '/<a href="([^"]+)"[^>]*>(.+?)<\/a>/ie';
|
| 54 |
$replace[] = '_html2txt_build_link_list($link_count++, "\\1", "\\2")';
|
| 55 |
}
|
| 56 |
|
| 57 |
// Run our defined search-and-replace
|
| 58 |
$converted->text = preg_replace($search, $replace, $converted->text);
|
| 59 |
|
| 60 |
// Strip any other HTML tags
|
| 61 |
$converted->text = strip_tags($converted->text, $allowed_tags);
|
| 62 |
|
| 63 |
// Bring down number of empty lines to 2 max
|
| 64 |
// TO DO
|
| 65 |
// Currently this is just TRUE or FALSE
|
| 66 |
// Add maximum line configuration
|
| 67 |
if ($empty_lines_max) {
|
| 68 |
$converted->text= preg_replace("/\n\s+\n/", "\n\n", $converted->text);
|
| 69 |
//$converted->text = preg_replace("/[\n]{3,}/", "\n\n", $converted->text);
|
| 70 |
}
|
| 71 |
|
| 72 |
// Add link list
|
| 73 |
if ( !empty($link_list) ) {
|
| 74 |
$converted->links = "\n\nLinks:\n------\n" . $link_list;
|
| 75 |
}
|
| 76 |
|
| 77 |
// Convert HTML entities
|
| 78 |
$translation_table = get_html_translation_table(HTML_ENTITIES);
|
| 79 |
$translation_table = array_flip($translation_table);
|
| 80 |
$converted->text = strtr($converted->text, $translation_table);
|
| 81 |
|
| 82 |
// Load <code>...</code> snippets back in to text
|
| 83 |
if ( !empty($saved_snippets) ) {
|
| 84 |
foreach ($saved_snippets as $count => $snippet) {
|
| 85 |
$converted->text = str_replace('[html2txt-code-snippet-' . $count . ']', "\n" . stripslashes($snippet), $converted->text);
|
| 86 |
}
|
| 87 |
}
|
| 88 |
|
| 89 |
// Wrap the text to a readable format
|
| 90 |
if ($width) {
|
| 91 |
$converted->text = wordwrap($converted->text, $width);
|
| 92 |
}
|
| 93 |
|
| 94 |
return $converted;
|
| 95 |
}
|
| 96 |
|
| 97 |
|
| 98 |
|
| 99 |
/**
|
| 100 |
* List of preg* regular expression patterns to search for,
|
| 101 |
* used in conjunction with $replace.
|
| 102 |
*
|
| 103 |
*/
|
| 104 |
function _html2txt_define_search() {
|
| 105 |
|
| 106 |
$search = array(
|
| 107 |
'@<code>(.+?)</code>@se', // Take out <code>...</code> snippets for later
|
| 108 |
"/\r/", // Non-legal carriage return
|
| 109 |
"/[\n\t]+/", // Newlines and tabs
|
| 110 |
'/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
|
| 111 |
//'/<!-- .* -->/', // Comments -- which strip_tags might have problem a with
|
| 112 |
'/<h[123][^>]*>(.+?)<\/h[123]>/ie', // H1 - H3
|
| 113 |
'/<h[456][^>]*>(.+?)<\/h[456]>/ie', // H4 - H6
|
| 114 |
'/<p[^>]*>/i', // <P>
|
| 115 |
'/<br[^>]*>/i', // <br>
|
| 116 |
'/<b[^>]*>(.+?)<\/b>/ie', // <b>
|
| 117 |
'/<i[^>]*>(.+?)<\/i>/i', // <i>
|
| 118 |
'/(<ul[^>]*>|<\/ul>)/i', // <ul> and </ul>
|
| 119 |
'/(<ol[^>]*>|<\/ol>)/i', // <ol> and </ol>
|
| 120 |
'/<li[^>]*>/i', // <li>
|
| 121 |
'/<hr[^>]*>/i', // <hr>
|
| 122 |
'/(<table[^>]*>|<\/table>)/i', // <table> and </table>
|
| 123 |
'/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
|
| 124 |
'/<td[^>]*>(.+?)<\/td>/i', // <td> and </td>
|
| 125 |
'/<th[^>]*>(.+?)<\/th>/i', // <th> and </th>
|
| 126 |
'/ /i',
|
| 127 |
'/"/i',
|
| 128 |
'/>/i',
|
| 129 |
'/</i',
|
| 130 |
'/&/i',
|
| 131 |
'/©/i',
|
| 132 |
'/™/i',
|
| 133 |
'/“/',
|
| 134 |
'/”/',
|
| 135 |
'/–/',
|
| 136 |
'/’/',
|
| 137 |
'/&/',
|
| 138 |
'/©/',
|
| 139 |
'/™/',
|
| 140 |
'/—/',
|
| 141 |
'/“/',
|
| 142 |
'/”/',
|
| 143 |
'/•/',
|
| 144 |
'/®/i',
|
| 145 |
'/•/i',
|
| 146 |
'/&[&;]+;/i',
|
| 147 |
'/'/'
|
| 148 |
);
|
| 149 |
|
| 150 |
return $search;
|
| 151 |
}
|
| 152 |
|
| 153 |
/**
|
| 154 |
* List of pattern replacements corresponding to patterns searched.
|
| 155 |
*
|
| 156 |
*/
|
| 157 |
function _html2txt_define_replace() {
|
| 158 |
|
| 159 |
$replace = array(
|
| 160 |
'_html2txt_get_code_snippets($snippet_count++, "\\1", "\\2")', // Take out <code>...</code> snippets for later
|
| 161 |
'', // Non-legal carriage return
|
| 162 |
' ', // Newlines and tabs
|
| 163 |
'', // <script>s -- which strip_tags supposedly has problems with
|
| 164 |
//'', // Comments -- which strip_tags might have problem a with
|
| 165 |
"strtoupper(\"\n\n\\1\n\")", // H1 - H3
|
| 166 |
"ucwords(\"\n\n\\1\n\n\")", // H4 - H6
|
| 167 |
"\n\n", // <P>
|
| 168 |
"\n", // <br>
|
| 169 |
'strtoupper("\\1")', // <b>
|
| 170 |
'_\\1_', // <i>
|
| 171 |
"\n\n", // <ul> and </ul>
|
| 172 |
"\n\n", // <ol> and </ol>
|
| 173 |
"\n\t*", // <li>
|
| 174 |
"\n-------------------------\n", // <hr>
|
| 175 |
"\n\n", // <table> and </table>
|
| 176 |
"\n", // <tr> and </tr>
|
| 177 |
"\t\t\\1\n", // <td> and </td>
|
| 178 |
"strtoupper(\"\t\t\\1\n\")", // <th> and </th>
|
| 179 |
' ',
|
| 180 |
'"',
|
| 181 |
'>',
|
| 182 |
'<',
|
| 183 |
'&',
|
| 184 |
'(c)',
|
| 185 |
'(tm)',
|
| 186 |
'"',
|
| 187 |
'"',
|
| 188 |
'-',
|
| 189 |
"'",
|
| 190 |
'&',
|
| 191 |
'(c)',
|
| 192 |
'(tm)',
|
| 193 |
'--',
|
| 194 |
'"',
|
| 195 |
'"',
|
| 196 |
'*',
|
| 197 |
'(R)',
|
| 198 |
'*',
|
| 199 |
'',
|
| 200 |
"'"
|
| 201 |
);
|
| 202 |
return $replace;
|
| 203 |
}
|
| 204 |
|
| 205 |
|
| 206 |
/**
|
| 207 |
*
|
| 208 |
* Maintains an internal list of links to be displayed seperate to the
|
| 209 |
* text, with numeric indices to the original point in the text they
|
| 210 |
* appeared. Also makes an effort at identifying and handling absolute
|
| 211 |
* and relative links.
|
| 212 |
*
|
| 213 |
*/
|
| 214 |
function _html2txt_build_link_list($link_count, $link, $display) {
|
| 215 |
|
| 216 |
global $base_url;
|
| 217 |
global $link_list;
|
| 218 |
|
| 219 |
if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 7) == 'mailto:' ) {
|
| 220 |
$link_list .= "[$link_count] $link\n";
|
| 221 |
} else {
|
| 222 |
$link_list .= "[$link_count] " . $base_url;
|
| 223 |
if ( substr($link, 0, 1) != '/' ) {
|
| 224 |
$link_list .= '/';
|
| 225 |
}
|
| 226 |
$link_list .= "$link\n";
|
| 227 |
}
|
| 228 |
|
| 229 |
return $display . ' [' . $link_count . ']';
|
| 230 |
}
|
| 231 |
|
| 232 |
/**
|
| 233 |
*
|
| 234 |
* Temporeraly replaces <code>...</code> with a placeholder
|
| 235 |
*
|
| 236 |
*/
|
| 237 |
function _html2txt_get_code_snippets($snippet_count, $snippet, $display) {
|
| 238 |
|
| 239 |
global $saved_snippets;
|
| 240 |
|
| 241 |
$saved_snippets[$snippet_count] = $snippet;
|
| 242 |
|
| 243 |
return $display . '[html2txt-code-snippet-' . $snippet_count . ']';
|
| 244 |
}
|
| 245 |
|
| 246 |
|
| 247 |
?>
|
Parent Directory
| 
Revision Log
| 
Revision Graph