<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" />
<title>[47638] trunk: Formatting: Expand `sanitize_file_name` to have better support for utf8 characters.</title>
</head>
<body>
<style type="text/css"><!--
#msg dl.meta { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dl.meta dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer, #logmsg { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre { white-space: pre-line; overflow: auto; background: #ffc; border: 1px #fa0 solid; padding: 6px; }
#logmsg { background: #ffc; border: 1px #fa0 solid; padding: 1em 1em 0 1em; }
#logmsg p, #logmsg pre, #logmsg blockquote { margin: 0 0 1em 0; }
#logmsg p, #logmsg li, #logmsg dt, #logmsg dd { line-height: 14pt; }
#logmsg h1, #logmsg h2, #logmsg h3, #logmsg h4, #logmsg h5, #logmsg h6 { margin: .5em 0; }
#logmsg h1:first-child, #logmsg h2:first-child, #logmsg h3:first-child, #logmsg h4:first-child, #logmsg h5:first-child, #logmsg h6:first-child { margin-top: 0; }
#logmsg ul, #logmsg ol { padding: 0; list-style-position: inside; margin: 0 0 0 1em; }
#logmsg ul { text-indent: -1em; padding-left: 1em; }#logmsg ol { text-indent: -1.5em; padding-left: 1.5em; }
#logmsg > ul, #logmsg > ol { margin: 0 0 1em 0; }
#logmsg pre { background: #eee; padding: 1em; }
#logmsg blockquote { border: 1px solid #fa0; border-left-width: 10px; padding: 1em 1em 0 1em; background: white;}
#logmsg dl { margin: 0; }
#logmsg dt { font-weight: bold; }
#logmsg dd { margin: 0; padding: 0 0 0.5em 0; }
#logmsg dd:before { content:'\00bb';}
#logmsg table { border-spacing: 0px; border-collapse: collapse; border-top: 4px solid #fa0; border-bottom: 1px solid #fa0; background: #fff; }
#logmsg table th { text-align: left; font-weight: normal; padding: 0.2em 0.5em; border-top: 1px dotted #fa0; }
#logmsg table td { text-align: right; border-top: 1px dotted #fa0; padding: 0.2em 0.5em; }
#logmsg table thead th { text-align: center; border-bottom: 1px solid #fa0; }
#logmsg table th.Corner { text-align: left; }
#logmsg hr { border: none 0; border-top: 2px dashed #fa0; height: 1px; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<div id="msg">
<dl class="meta" style="font-size: 105%">
<dt style="float: left; width: 6em; font-weight: bold">Revision</dt> <dd><a style="font-weight: bold" href="https://core.trac.wordpress.org/changeset/47638">47638</a><script type="application/ld+json">{"@context":"http://schema.org","@type":"EmailMessage","description":"Review this Commit","action":{"@type":"ViewAction","url":"https://core.trac.wordpress.org/changeset/47638","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>whyisjake</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2020-04-29 15:38:43 +0000 (Wed, 29 Apr 2020)</dd>
</dl>
<pre style='padding-left: 1em; margin: 2em 0; border-left: 2px solid #ccc; line-height: 1.25; font-size: 105%; font-family: sans-serif'>Formatting: Expand `sanitize_file_name` to have better support for utf8 characters.
Props: xknown, peterwilsoncc.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludesformattingphp">trunk/src/wp-includes/formatting.php</a></li>
<li><a href="#trunktestsphpunittestsformattingSanitizeFileNamephp">trunk/tests/phpunit/tests/formatting/SanitizeFileName.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludesformattingphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/src/wp-includes/formatting.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/formatting.php 2020-04-29 15:34:55 UTC (rev 47637)
+++ trunk/src/wp-includes/formatting.php 2020-04-29 15:38:43 UTC (rev 47638)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2005,6 +2005,24 @@
</span><span class="cx" style="display: block; padding: 0 10px"> function sanitize_file_name( $filename ) {
</span><span class="cx" style="display: block; padding: 0 10px"> $filename_raw = $filename;
</span><span class="cx" style="display: block; padding: 0 10px"> $special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', chr( 0 ) );
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+ // Check for support for utf8 in the installed PCRE library once and store the result in a static.
+ static $utf8_pcre = null;
+ if ( ! isset( $utf8_pcre ) ) {
+ // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged
+ $utf8_pcre = @preg_match( '/^./u', 'a' );
+ }
+
+ if ( ! seems_utf8( $filename ) ) {
+ $_ext = pathinfo( $filename, PATHINFO_EXTENSION );
+ $_name = pathinfo( $filename, PATHINFO_FILENAME );
+ $filename = sanitize_title_with_dashes( $_name ) . '.' . $_ext;
+ }
+
+ if ( $utf8_pcre ) {
+ $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
+ }
+
</ins><span class="cx" style="display: block; padding: 0 10px"> /**
</span><span class="cx" style="display: block; padding: 0 10px"> * Filters the list of characters to remove from a filename.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2014,7 +2032,6 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * @param string $filename_raw The original filename to be sanitized.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
</del><span class="cx" style="display: block; padding: 0 10px"> $filename = str_replace( $special_chars, '', $filename );
</span><span class="cx" style="display: block; padding: 0 10px"> $filename = str_replace( array( '%20', '+' ), '-', $filename );
</span><span class="cx" style="display: block; padding: 0 10px"> $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
</span></span></pre></div>
<a id="trunktestsphpunittestsformattingSanitizeFileNamephp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/tests/phpunit/tests/formatting/SanitizeFileName.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/formatting/SanitizeFileName.php 2020-04-29 15:34:55 UTC (rev 47637)
+++ trunk/tests/phpunit/tests/formatting/SanitizeFileName.php 2020-04-29 15:38:43 UTC (rev 47638)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -68,4 +68,20 @@
</span><span class="cx" style="display: block; padding: 0 10px"> // Test a filenames that becomes extensionless.
</span><span class="cx" style="display: block; padding: 0 10px"> $this->assertEquals( 'no-extension', sanitize_file_name( '_.no-extension' ) );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+ /**
+ * @dataProvider data_wp_filenames
+ */
+ function test_replaces_invalid_utf8_characters( $input, $expected ) {
+ $this->assertEquals( $expected, sanitize_file_name( $input ) );
+ }
+
+ function data_wp_filenames() {
+ return array(
+ [ urldecode( '%B1myfile.png' ), 'myfile.png' ],
+ [ urldecode( '%B1myfile' ), 'myfile' ],
+ [ 'demo bar.png', 'demo-bar.png' ],
+ [ 'demo' . json_decode( '"\u00a0"' ) . 'bar.png', 'demo-bar.png' ],
+ );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>