From 63d6e6dfc35e6d82c4a64f37c408794c163becd4 Mon Sep 17 00:00:00 2001
From: thomascube <thomas@roundcube.net>
Date: Wed, 28 Sep 2011 15:16:41 -0400
Subject: [PATCH] Bump versions to 0.6 stable
---
program/lib/html2text.php | 287 +++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 215 insertions(+), 72 deletions(-)
diff --git a/program/lib/html2text.php b/program/lib/html2text.php
index efc38a6..1ab1605 100644
--- a/program/lib/html2text.php
+++ b/program/lib/html2text.php
@@ -148,33 +148,25 @@
'/[ ]{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
- '/<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=("|\')([^"\']+)\1[^>]*>(.*?)<\/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
@@ -183,7 +175,7 @@
'/&(bull|#149|#8226);/i', // Bullet
'/&(pound|#163);/i', // Pound sign
'/&(euro|#8364);/i', // Euro sign
- '/&[^&;]+;/i', // Unknown/unhandled entities
+ '/&(amp|#38);/i', // Ampersand: see _converter()
'/[ ]{2,}/' // Runs of spaces, post-handling
);
@@ -200,42 +192,50 @@
' ', // Runs of spaces, pre-handling
'', // <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\")", // H4 - H6
- "\n\n", // <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("\\2", "\\3")',
- // <a href="">
- "\n-------------------------\n", // <hr>
- "\n\n", // <table> and </table>
+ "\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>
' ', // Non-breaking space
'"', // Double quotes
"'", // Single quotes
'>',
'<',
- '&',
'(c)',
'(tm)',
'(R)',
'--',
'-',
'*',
- '�',
+ '£',
'EUR', // Euro sign. � ?
- '', // Unknown/unhandled entities
+ '|+|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
+ */
+ var $callback_search = array(
+ '/<(h)[123456][^>]*>(.*?)<\/h[123456]>/i', // H1 - H3
+ '/<(b)[^>]*>(.*?)<\/b>/i', // <b>
+ '/<(strong)[^>]*>(.*?)<\/strong>/i', // <strong>
+ '/<(a) [^>]*href=("|\')([^"\']+)\2[^>]*>(.*?)<\/a>/i',
+ // <a href="">
+ '/<(th)[^>]*>(.*?)<\/th>/i', // <th> and </th>
);
/**
@@ -247,11 +247,11 @@
* @see $pre_replace
*/
var $pre_search = array(
- "/\n/",
- "/\t/",
- '/ /',
- '/<pre[^>]*>/',
- '/<\/pre>/'
+ "/\n/",
+ "/\t/",
+ '/ /',
+ '/<pre[^>]*>/',
+ '/<\/pre>/'
);
/**
@@ -262,11 +262,11 @@
* @see $pre_search
*/
var $pre_replace = array(
- '<br>',
- ' ',
- ' ',
- '',
- ''
+ '<br>',
+ ' ',
+ ' ',
+ '',
+ ''
);
/**
@@ -342,10 +342,10 @@
if ( !empty($source) ) {
$this->set_html($source, $from_file);
}
-
+
$this->set_base_url();
- $this->_do_links = $do_links;
- $this->width = $width;
+ $this->_do_links = $do_links;
+ $this->width = $width;
}
/**
@@ -359,10 +359,10 @@
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;
+ $this->html = $source;
$this->_converted = false;
}
@@ -445,12 +445,7 @@
}
/**
- * 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
@@ -463,11 +458,55 @@
$text = trim(stripslashes($this->html));
- // Convert <PRE>
+ // Convert HTML to TXT
+ $this->_converter($text);
+
+ // Add link list
+ if ( !empty($this->_link_list) ) {
+ $text .= "\n\nLinks:\n------\n" . $this->_link_list;
+ }
+
+ $this->text = $text;
+
+ $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
+ * $width characters.
+ *
+ * @param string Reference to HTML content string
+ *
+ * @access private
+ * @return void
+ */
+ function _converter(&$text)
+ {
+ // Convert <BLOCKQUOTE> (before PRE!)
+ $this->_convert_blockquotes($text);
+
+ // Convert <PRE>
$this->_convert_pre($text);
-
+
// Run our defined search-and-replace
$text = preg_replace($this->search, $this->replace, $text);
+
+ // Replace known html entities
+ $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');
+
+ // Run our defined search-and-replace with callback
+ $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);
+
+ // 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);
// Strip any other HTML tags
$text = strip_tags($text, $this->allowed_tags);
@@ -476,10 +515,8 @@
$text = preg_replace("/\n\s+\n/", "\n\n", $text);
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
- // Add link list
- if ( !empty($this->_link_list) ) {
- $text .= "\n\nLinks:\n------\n" . $this->_link_list;
- }
+ // remove leading empty lines (can be produced by eg. P tag on the beginning)
+ $text = preg_replace('/^\n+/', '', $text);
// Wrap the text to a readable format
// for PHP versions >= 4.0.2. Default width is 75
@@ -487,10 +524,6 @@
if ( $this->width > 0 ) {
$text = wordwrap($text, $this->width);
}
-
- $this->text = $text;
-
- $this->_converted = true;
}
/**
@@ -508,20 +541,22 @@
*/
function _build_link_list( $link, $display )
{
- if ( !$this->_do_links ) return $display;
-
- if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' ||
- substr($link, 0, 7) == 'mailto:' ) {
+ if ( !$this->_do_links )
+ return $display;
+
+ if ( substr($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";
+ $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
- $additional = '';
+ } elseif ( substr($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;
+ $this->_link_list .= '[' . $this->_link_count . '] ' . $this->url;
if ( substr($link, 0, 1) != '/' ) {
$this->_link_list .= '/';
}
@@ -531,7 +566,7 @@
return $display . $additional;
}
-
+
/**
* Helper function for PRE body conversion.
*
@@ -540,12 +575,120 @@
*/
function _convert_pre(&$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);
- }
+ // get the content of PRE element
+ while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
+ // convert the content
+ $this->pre_content = sprintf('<div><br>%s<br></div>',
+ preg_replace($this->pre_search, $this->pre_replace, $matches[1]));
+ // replace the content (use callback because content can contain $0 variable)
+ $text = preg_replace_callback('/<pre[^>]*>.*<\/pre>/ismU',
+ array('html2text', '_preg_pre_callback'), $text, 1);
+ // free memory
+ $this->pre_content = '';
+ }
+ }
+
+ /**
+ * Helper function for BLOCKQUOTE body conversion.
+ *
+ * @param string HTML content
+ * @access private
+ */
+ function _convert_blockquotes(&$text)
+ {
+ if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
+ $level = 0;
+ $diff = 0;
+ foreach ($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 = $this->width;
+ if ($this->width > 0) $this->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->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($matches[1]) {
+ case 'b':
+ case 'strong':
+ return $this->_strtoupper($matches[2]);
+ case 'th':
+ return $this->_strtoupper("\t\t". $matches[2] ."\n");
+ case 'h':
+ return $this->_strtoupper("\n\n". $matches[2] ."\n\n");
+ case 'a':
+ // Remove spaces in URL (#1487805)
+ $url = str_replace(' ', '', $matches[3]);
+ return $this->_build_link_list($url, $matches[4]);
+ }
+ }
+
+ /**
+ * Callback function for preg_replace_callback use in PRE content handler.
+ *
+ * @param array PREG matches
+ * @return string
+ */
+ private function _preg_pre_callback($matches)
+ {
+ return $this->pre_content;
+ }
+
+ /**
+ * Strtoupper multibyte wrapper function
+ *
+ * @param string
+ * @return string
+ */
+ private function _strtoupper($str)
+ {
+ if (function_exists('mb_strtoupper'))
+ return mb_strtoupper($str);
+ else
+ return strtoupper($str);
}
}
-
-?>
--
Gitblit v1.9.1