Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Always use multibyte string functions #53

Merged
merged 1 commit into from
Feb 22, 2016
Merged

Always use multibyte string functions #53

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions composer.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,5 +8,9 @@
},
"require-dev": {
"phpunit/phpunit": "~4"
},
"suggest": {
"ext-mbstring": "For best performance",
"symfony/polyfill-mbstring": "If you can't install ext-mbstring"
}
}
46 changes: 28 additions & 18 deletions src/Html2Text.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@ class Html2Text
{
const ENCODING = 'UTF-8';

protected $htmlFuncFlags;

/**
* Contains the HTML content to convert.
*
Expand Down Expand Up @@ -236,6 +238,9 @@ public function __construct($html = '', $options = array())

$this->html = $html;
$this->options = array_merge($this->options, $options);
$this->htmlFuncFlags = (PHP_VERSION_ID < 50400)
? ENT_COMPAT
: ENT_COMPAT | ENT_HTML5;
}

/**
Expand Down Expand Up @@ -318,6 +323,16 @@ public function set_base_url($baseurl)
}

protected function convert()
{
$origEncoding = mb_internal_encoding();
mb_internal_encoding(self::ENCODING);

$this->doConvert();

mb_internal_encoding($origEncoding);
}

protected function doConvert()
{
$this->linkList = array();

Expand Down Expand Up @@ -345,7 +360,7 @@ protected function converter(&$text)
$text = preg_replace_callback($this->callbackSearch, array($this, 'pregCallback'), $text);
$text = strip_tags($text);
$text = preg_replace($this->entSearch, $this->entReplace, $text);
$text = html_entity_decode($text, ENT_QUOTES, self::ENCODING);
$text = html_entity_decode($text, $this->htmlFuncFlags, self::ENCODING);

// 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});/', '', $text);
Expand Down Expand Up @@ -395,7 +410,7 @@ protected function buildlinkList($link, $display, $linkOverride = null)
$url = $link;
} else {
$url = $this->baseurl;
if (substr($link, 0, 1) != '/') {
if (mb_substr($link, 0, 1) != '/') {
$url .= '/';
}
$url .= $link;
Expand Down Expand Up @@ -472,7 +487,7 @@ protected function convertBlockquotes(&$text)
$end = $m[1];
$len = $end - $taglen - $start;
// Get blockquote content
$body = substr($text, $start + $taglen - $diff, $len);
$body = mb_substr($text, $start + $taglen - $diff, $len);

// Set text width
$pWidth = $this->options['width'];
Expand All @@ -482,20 +497,21 @@ protected function convertBlockquotes(&$text)
$this->converter($body);
// Add citation markers and create PRE block
$body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body));
$body = '<pre>' . htmlspecialchars($body) . '</pre>';
$body = '<pre>' . htmlspecialchars($body, $this->htmlFuncFlags, self::ENCODING) . '</pre>';
// Re-set text width
$this->options['width'] = $pWidth;
// Replace content
$text = substr($text, 0, $start - $diff)
. $body . substr($text, $end + strlen($m[0]) - $diff);
$text = mb_substr($text, 0, $start - $diff)
. $body
. mb_substr($text, $end + mb_strlen($m[0]) - $diff);

$diff += $len + $taglen + strlen($m[0]) - strlen($body);
$diff += $len + $taglen + mb_strlen($m[0]) - mb_strlen($body);
unset($body);
}
} else {
if ($level == 0) {
$start = $m[1];
$taglen = strlen($m[0]);
$taglen = mb_strlen($m[0]);
}
$level++;
}
Expand All @@ -511,7 +527,7 @@ protected function convertBlockquotes(&$text)
*/
protected function pregCallback($matches)
{
switch (strtolower($matches[1])) {
switch (mb_strtolower($matches[1])) {
case 'p':
// Replace newlines with spaces.
$para = str_replace("\n", " ", $matches[3]);
Expand Down Expand Up @@ -585,15 +601,9 @@ protected function toupper($str)
*/
protected function strtoupper($str)
{
$str = html_entity_decode($str, ENT_COMPAT, self::ENCODING);

if (function_exists('mb_strtoupper')) {
$str = mb_strtoupper($str, self::ENCODING);
} else {
$str = strtoupper($str);
}

$str = htmlspecialchars($str, ENT_COMPAT, self::ENCODING);
$str = html_entity_decode($str, $this->htmlFuncFlags, self::ENCODING);
$str = mb_strtoupper($str);
$str = htmlspecialchars($str, $this->htmlFuncFlags, self::ENCODING);

return $str;
}
Expand Down