<!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>[27839] trunk: Texturize: Massive performance improvements (~600% faster); better handling of nbsp, double, and weird spaces; 136 new unit tests.</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 { 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">
<dt>Revision</dt> <dd><a href="http://core.trac.wordpress.org/changeset/27839">27839</a></dd>
<dt>Author</dt> <dd>nacin</dd>
<dt>Date</dt> <dd>2014-03-29 07:15:33 +0000 (Sat, 29 Mar 2014)</dd>
</dl>
<h3>Log Message</h3>
<pre>Texturize: Massive performance improvements (~600% faster); better handling of nbsp, double, and weird spaces; 136 new unit tests.
big props miqrogroove.
fixes <a href="http://core.trac.wordpress.org/ticket/22692">#22692</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludesformattingphp">trunk/src/wp-includes/formatting.php</a></li>
<li><a href="#trunktestsphpunittestsformattingWPTexturizephp">trunk/tests/phpunit/tests/formatting/WPTexturize.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludesformattingphp"></a>
<div class="modfile"><h4>Modified: trunk/src/wp-includes/formatting.php (27838 => 27839)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/src/wp-includes/formatting.php 2014-03-29 06:22:46 UTC (rev 27838)
+++ trunk/src/wp-includes/formatting.php 2014-03-29 07:15:33 UTC (rev 27839)
</span><span class="lines">@@ -73,28 +73,51 @@
</span><span class="cx"> $static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney );
</span><span class="cx"> $static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
</span><span class="cx">
</span><ins>+ /*
+ * Regex for common whitespace characters.
+ *
+ * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
+ * This is designed to replace the PCRE \s sequence. In #WP22692, that sequence
+ * was found to be unreliable due to random inclusion of the A0 byte.
+ */
+ $spaces = '[\r\n\t ]|\xC2\xA0| ';
+
+
+ // Pattern-based replacements of characters.
</ins><span class="cx"> $dynamic = array();
</span><del>- if ( "'" != $apos ) {
- $dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's
- $dynamic[ '/\'(\d)/' ] = $apos . '$1'; // '99
- }
</del><ins>+
+ // '99 '99s '99's (apostrophe)
+ if ( "'" != $apos )
+ $dynamic[ '/\'(?=\d)/' ] = $apos;
+
+ // Single quote at start, or preceded by (, {, <, [, ", or spaces.
</ins><span class="cx"> if ( "'" != $opening_single_quote )
</span><del>- $dynamic[ '/(\s|\A|[([{<]|")\'/' ] = '$1' . $opening_single_quote; // opening single quote, even after (, {, <, [
</del><ins>+ $dynamic[ '/(?<=\A|[([{<"]|' . $spaces . ')\'/' ] = $opening_single_quote;
+
+ // 9" (double prime)
</ins><span class="cx"> if ( '"' != $double_prime )
</span><del>- $dynamic[ '/(\d)"/' ] = '$1' . $double_prime; // 9" (double prime)
</del><ins>+ $dynamic[ '/(?<=\d)"/' ] = $double_prime;
+
+ // 9' (prime)
</ins><span class="cx"> if ( "'" != $prime )
</span><del>- $dynamic[ '/(\d)\'/' ] = '$1' . $prime; // 9' (prime)
</del><ins>+ $dynamic[ '/(?<=\d)\'/' ] = $prime;
+
+ // Apostrophe in a word. No spaces or double primes.
</ins><span class="cx"> if ( "'" != $apos )
</span><del>- $dynamic[ '/(\S)\'([^\'\s])/' ] = '$1' . $apos . '$2'; // apostrophe in a word
</del><ins>+ $dynamic[ '/(?<!' . $spaces . ')\'(?!\'|' . $spaces . ')/' ] = $apos;
+
+ // Double quote at start, or preceded by (, {, <, [, or spaces, and not followed by spaces.
</ins><span class="cx"> if ( '"' != $opening_quote )
</span><del>- $dynamic[ '/(\s|\A|[([{<])"(?!\s)/' ] = '$1' . $opening_quote . '$2'; // opening double quote, even after (, {, <, [
</del><ins>+ $dynamic[ '/(?<=\A|[([{<]|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
+
+ // Any remaining double quotes.
</ins><span class="cx"> if ( '"' != $closing_quote )
</span><del>- $dynamic[ '/"(\s|\S|\Z)/' ] = $closing_quote . '$1'; // closing double quote
</del><ins>+ $dynamic[ '/"/' ] = $closing_quote;
+
+ // Single quotes followed by spaces or a period.
</ins><span class="cx"> if ( "'" != $closing_single_quote )
</span><del>- $dynamic[ '/\'([\s.]|\Z)/' ] = $closing_single_quote . '$1'; // closing single quote
</del><ins>+ $dynamic[ '/\'(?=\Z|\.|' . $spaces . ')/' ] = $closing_single_quote;
</ins><span class="cx">
</span><del>- $dynamic[ '/\b(\d+)x(\d+)\b/' ] = '$1×$2'; // 9x9 (times)
-
</del><span class="cx"> $dynamic_characters = array_keys( $dynamic );
</span><span class="cx"> $dynamic_replacements = array_values( $dynamic );
</span><span class="cx"> }
</span><span class="lines">@@ -134,11 +157,21 @@
</span><span class="cx"> } elseif ( '[' === $first ) {
</span><span class="cx"> _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
</span><span class="cx"> } elseif ( empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack) ) {
</span><ins>+
</ins><span class="cx"> // This is not a tag, nor is the texturization disabled static strings
</span><span class="cx"> $curl = str_replace($static_characters, $static_replacements, $curl);
</span><ins>+
</ins><span class="cx"> // regular expressions
</span><span class="cx"> $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
</span><ins>+
+ // 9x9 (times)
+ if ( 1 === preg_match( '/(?<=\d)x\d/', $text ) ) {
+ // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
+ $curl = preg_replace( '/\b(\d+)x(\d+)\b/', '$1×$2', $curl );
+ }
</ins><span class="cx"> }
</span><ins>+
+ // Replace each & with & unless it already looks like an entity.
</ins><span class="cx"> $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
</span><span class="cx"> }
</span><span class="cx"> return implode( '', $textarr );
</span></span></pre></div>
<a id="trunktestsphpunittestsformattingWPTexturizephp"></a>
<div class="modfile"><h4>Modified: trunk/tests/phpunit/tests/formatting/WPTexturize.php (27838 => 27839)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/tests/phpunit/tests/formatting/WPTexturize.php 2014-03-29 06:22:46 UTC (rev 27838)
+++ trunk/tests/phpunit/tests/formatting/WPTexturize.php 2014-03-29 07:15:33 UTC (rev 27839)
</span><span class="lines">@@ -14,7 +14,11 @@
</span><span class="cx"> $this->assertEquals('[a]a–b[code]---[/code]a–b[/a]', wptexturize('[a]a--b[code]---[/code]a--b[/a]'));
</span><span class="cx"> $this->assertEquals('<pre><code></code>--</pre>', wptexturize('<pre><code></code>--</pre>'));
</span><span class="cx">
</span><del>- $this->assertEquals('<code>---</code>', wptexturize('<code>---</code>'));
</del><ins>+ $this->assertEquals( '<code>---</code>', wptexturize( '<code>---</code>' ) );
+ $this->assertEquals( '<kbd>---</kbd>', wptexturize( '<kbd>---</kbd>' ) );
+ $this->assertEquals( '<style>---</style>', wptexturize( '<style>---</style>' ) );
+ $this->assertEquals( '<script>---</script>', wptexturize( '<script>---</script>' ) );
+ $this->assertEquals( '<tt>---</tt>', wptexturize( '<tt>---</tt>' ) );
</ins><span class="cx">
</span><span class="cx"> $this->assertEquals('<code>href="baba"</code> “baba”', wptexturize('<code>href="baba"</code> "baba"'));
</span><span class="cx">
</span><span class="lines">@@ -44,7 +48,6 @@
</span><span class="cx"> //WP Ticket #4539
</span><span class="cx"> function test_basic_quotes() {
</span><span class="cx"> $this->assertEquals('test’s', wptexturize('test\'s'));
</span><del>- $this->assertEquals('test’s', wptexturize('test\'s'));
</del><span class="cx">
</span><span class="cx"> $this->assertEquals('‘quoted’', wptexturize('\'quoted\''));
</span><span class="cx"> $this->assertEquals('“quoted”', wptexturize('"quoted"'));
</span><span class="lines">@@ -194,4 +197,801 @@
</span><span class="cx"> $this->assertEquals( ' — ', wptexturize( ' -- ' ) );
</span><span class="cx"> $this->assertEquals( ' — ', wptexturize( ' -- ') );
</span><span class="cx"> }
</span><ins>+
+ /**
+ * Test spaces around quotes.
+ *
+ * These should never happen, even if the desired output changes some day.
+ *
+ * @ticket 22692
+ */
+ function test_spaces_around_quotes_never() {
+ $nbsp = "\xC2\xA0";
+
+ $problem_input = "$nbsp\"A";
+ $problem_output = "$nbsp”A";
+
+ $this->assertNotEquals( $problem_output, wptexturize( $problem_input ) );
+ }
+
+ /**
+ * Test spaces around quotes.
+ *
+ * These are desirable outputs for the current design.
+ *
+ * @ticket 22692
+ * @dataProvider data_spaces_around_quotes
+ */
+ function test_spaces_around_quotes( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_spaces_around_quotes() {
+ $nbsp = "\xC2\xA0";
+ $pi = "\xCE\xA0";
+
+ return array(
+ array(
+ "stop. $nbsp\"A quote after 2 spaces.\"",
+ "stop. $nbsp“A quote after 2 spaces.”",
+ ),
+ array(
+ "stop.$nbsp$nbsp\"A quote after 2 spaces.\"",
+ "stop.$nbsp$nbsp“A quote after 2 spaces.”",
+ ),
+ array(
+ "stop. $nbsp'A quote after 2 spaces.'",
+ "stop. $nbsp‘A quote after 2 spaces.’",
+ ),
+ array(
+ "stop.$nbsp$nbsp'A quote after 2 spaces.'",
+ "stop.$nbsp$nbsp‘A quote after 2 spaces.’",
+ ),
+ array(
+ "stop. \"A quote after 2 spaces.\"",
+ "stop. “A quote after 2 spaces.”",
+ ),
+ array(
+ "stop. \"A quote after 2 spaces.\"",
+ "stop. “A quote after 2 spaces.”",
+ ),
+ array(
+ "stop. 'A quote after 2 spaces.'",
+ "stop. ‘A quote after 2 spaces.’",
+ ),
+ array(
+ "stop. 'A quote after 2 spaces.'",
+ "stop. ‘A quote after 2 spaces.’",
+ ),
+ array(
+ "Contraction: $pi's",
+ "Contraction: $pi’s",
+ ),
+ );
+ }
+
+ /**
+ * Apostrophe before a number always becomes ’ (apos);
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_apos_before_digits
+ */
+ function test_apos_before_digits( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_apos_before_digits() {
+ return array(
+ array(
+ "word '99 word",
+ "word ’99 word",
+ ),
+ array(
+ "word'99 word",
+ "word’99 word",
+ ),
+ array(
+ "word '99word",
+ "word ’99word",
+ ),
+ array(
+ "word'99word",
+ "word’99word",
+ ),
+ array(
+ "word '99’s word", // Appears as a separate but logically superfluous pattern in 3.8.
+ "word ’99’s word",
+ ),
+ array(
+ "word '99's word", // Due to the logic error, second apos becomes a prime. See ticket #22823
+ "word ’99′s word",
+ ),
+ array(
+ "word '99'samsonite",
+ "word ’99′samsonite",
+ ),
+ array(
+ "according to our source, '33% of all students scored less than 50' on the test.", // Apostrophes and primes have priority over quotes
+ "according to our source, ’33% of all students scored less than 50′ on the test.",
+ ),
+ array(
+ "word '99' word", // See ticket #8775
+ "word ’99′ word",
+ ),
+ );
+ }
+
+ /**
+ * Apostrophe after a space or ([{<" becomes ‘ (opening_single_quote)
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_opening_single_quote
+ */
+ function test_opening_single_quote( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_opening_single_quote() {
+ return array(
+ array(
+ "word 'word word",
+ "word ‘word word",
+ ),
+ array(
+ "word ('word word",
+ "word (‘word word",
+ ),
+ array(
+ "word ['word word",
+ "word [‘word word",
+ ),
+ array(
+ "word <'word word", // Invalid HTML input?
+ "word <‘word word",
+ ),
+ array(
+ "word <'word word", // Valid HTML input triggers the apos in a word pattern
+ "word <’word word",
+ ),
+ array(
+ "word {'word word",
+ "word {‘word word",
+ ),
+ array(
+ "word \"'word word",
+ "word “‘word word", // Two opening quotes
+ ),
+ array(
+ "'word word",
+ "‘word word",
+ ),
+ array(
+ "word('word word",
+ "word(‘word word",
+ ),
+ array(
+ "word['word word",
+ "word[‘word word",
+ ),
+ array(
+ "word<'word word",
+ "word<‘word word",
+ ),
+ array(
+ "word<'word word",
+ "word<’word word",
+ ),
+ array(
+ "word{'word word",
+ "word{‘word word",
+ ),
+ array(
+ "word\"'word word",
+ "word”‘word word", // Closing quote, then opening quote
+ ),
+ array(
+ "word ' word word",
+ "word ‘ word word",
+ ),
+ array(
+ "word (' word word",
+ "word (‘ word word",
+ ),
+ array(
+ "word [' word word",
+ "word [‘ word word",
+ ),
+ array(
+ "word <' word word", // Invalid HTML input?
+ "word <‘ word word",
+ ),
+ array(
+ "word <' word word", // Valid HTML input triggers the closing single quote here
+ "word <’ word word",
+ ),
+ array(
+ "word {' word word",
+ "word {‘ word word",
+ ),
+ array(
+ "word \"' word word",
+ "word “‘ word word", // Two opening quotes
+ ),
+ array(
+ "' word word",
+ "‘ word word",
+ ),
+ array(
+ "word(' word word",
+ "word(‘ word word",
+ ),
+ array(
+ "word[' word word",
+ "word[‘ word word",
+ ),
+ array(
+ "word<' word word",
+ "word<‘ word word",
+ ),
+ array(
+ "word<' word word",
+ "word<’ word word",
+ ),
+ array(
+ "word{' word word",
+ "word{‘ word word",
+ ),
+ array(
+ "word\"' word word",
+ "word”‘ word word", // Closing quote, then opening quote
+ ),
+ );
+ }
+
+ /**
+ * Double quote after a number becomes ″ (double_prime)
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_double_prime
+ */
+ function test_double_prime( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_double_prime() {
+ return array(
+ array(
+ 'word 99" word',
+ 'word 99″ word',
+ ),
+ array(
+ 'word 99"word',
+ 'word 99″word',
+ ),
+ array(
+ 'word99" word',
+ 'word99″ word',
+ ),
+ array(
+ 'word99"word',
+ 'word99″word',
+ ),
+ );
+ }
+
+ /**
+ * Apostrophe after a number becomes ′ (prime)
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_single_prime
+ */
+ function test_single_prime( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_single_prime() {
+ return array(
+ array(
+ "word 99' word",
+ "word 99′ word",
+ ),
+ array(
+ "word 99'word",
+ "word 99′word",
+ ),
+ array(
+ "word99' word",
+ "word99′ word",
+ ),
+ array(
+ "word99'word",
+ "word99′word",
+ ),
+ );
+ }
+
+ /**
+ * Apostrophe "in a word" becomes ’ (apos)
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_contractions
+ */
+ function test_contractions( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_contractions() {
+ return array(
+ array(
+ "word word's word",
+ "word word’s word",
+ ),
+ array(
+ "word word'. word", // Quotes with outside punctuation could end with apostrophes instead of closing quotes (may affect i18n)
+ "word word’. word",
+ ),
+ array(
+ "word ]'. word",
+ "word ]’. word",
+ ),
+ array(
+ "word )'. word",
+ "word )’. word",
+ ),
+ array(
+ "word }'. word",
+ "word }’. word",
+ ),
+ array(
+ "word >'. word", // Not tested
+ "word >’. word",
+ ),
+ array(
+ "word >'. word",
+ "word >’. word",
+ ),
+ );
+ }
+
+ /**
+ * Double quote after a space or ([{< becomes “ (opening_quote) if not followed by spaces
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_opening_quote
+ */
+ function test_opening_quote( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_opening_quote() {
+ return array(
+ array(
+ 'word "word word',
+ 'word “word word',
+ ),
+ array(
+ 'word ("word word',
+ 'word (“word word',
+ ),
+ array(
+ 'word ["word word',
+ 'word [“word word',
+ ),
+ array(
+ 'word <"word word', // Invalid HTML input?
+ 'word <“word word',
+ ),
+ array(
+ 'word <"word word', // Valid HTML input triggers the closing quote pattern
+ 'word <”word word',
+ ),
+ array(
+ 'word {"word word',
+ 'word {“word word',
+ ),
+ array(
+ '"word word',
+ '“word word',
+ ),
+ array(
+ 'word("word word',
+ 'word(“word word',
+ ),
+ array(
+ 'word["word word',
+ 'word[“word word',
+ ),
+ array(
+ 'word<"word word', // Invalid HTML input?
+ 'word<“word word',
+ ),
+ array(
+ 'word<"word word', // Valid HTML input triggers the closing quote pattern
+ 'word<”word word',
+ ),
+ array(
+ 'word{"word word',
+ 'word{“word word',
+ ),
+ array(
+ 'word "99 word',
+ 'word “99 word',
+ ),
+ );
+ }
+
+ /**
+ * Double quote becomes ” (closing_quote) unless it is already converted to double_prime or opening_quote.
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_closing_quote
+ */
+ function test_closing_quote( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_closing_quote() {
+ return array(
+ array(
+ 'word word" word',
+ 'word word” word',
+ ),
+ array(
+ 'word word") word',
+ 'word word”) word',
+ ),
+ array(
+ 'word word"] word',
+ 'word word”] word',
+ ),
+ array(
+ 'word word"} word',
+ 'word word”} word',
+ ),
+ array(
+ 'word word"> word', // Invalid HTML input?
+ 'word word”> word',
+ ),
+ array(
+ 'word word"> word', // Valid HTML should work
+ 'word word”> word',
+ ),
+ array(
+ 'word word"',
+ 'word word”',
+ ),
+ array(
+ 'word word"word',
+ 'word word”word',
+ ),
+ array(
+ 'word"word"word',
+ 'word”word”word',
+ ),
+ array(
+ 'test sentence".',
+ 'test sentence”.',
+ ),
+ array(
+ 'test sentence."',
+ 'test sentence.”',
+ ),
+ array(
+ 'test sentence". word',
+ 'test sentence”. word',
+ ),
+ array(
+ 'test sentence." word',
+ 'test sentence.” word',
+ ),
+ );
+ }
+
+ /**
+ * Test that single quotes followed by a space or a period become ’ (closing_single_quote)
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_closing_single_quote
+ */
+ function test_closing_single_quote( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_closing_single_quote() {
+ return array(
+ array(
+ "word word' word",
+ "word word’ word",
+ ),
+ array(
+ "word word'. word",
+ "word word’. word",
+ ),
+ array(
+ "word word'.word",
+ "word word’.word",
+ ),
+ array(
+ "word word'",
+ "word word’",
+ ),
+ array(
+ "test sentence'.",
+ "test sentence’.",
+ ),
+ array(
+ "test sentence.'",
+ "test sentence.’",
+ ),
+ array(
+ "test sentence'. word",
+ "test sentence’. word",
+ ),
+ array(
+ "test sentence.' word",
+ "test sentence.’ word",
+ ),
+ );
+ }
+
+ /**
+ * Tests multiplication.
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_multiplication
+ */
+ function test_multiplication( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_multiplication() {
+ return array(
+ array(
+ "9x9",
+ "9×9",
+ ),
+ array(
+ "12x34",
+ "12×34",
+ ),
+ array(
+ "9 x 9",
+ "9 x 9",
+ ),
+ );
+ }
+
+ /**
+ * Test ampersands. & always becomes & unless it is followed by # or ;
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_ampersand
+ */
+ function test_ampersand( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_ampersand() {
+ return array(
+ array(
+ "word & word",
+ "word & word",
+ ),
+ array(
+ "word&word",
+ "word&word",
+ ),
+ array(
+ "word word",
+ "word word",
+ ),
+ array(
+ "word & word",
+ "word & word",
+ ),
+ array(
+ "word &# word",
+ "word &# word", // invalid output?
+ ),
+ array(
+ "word &44; word",
+ "word &44; word",
+ ),
+ array(
+ "word && word",
+ "word && word",
+ ),
+ array(
+ "word &!amp; word",
+ "word &!amp; word",
+ ),
+ );
+ }
+
+ /**
+ * Test "cockney" phrases, which begin with an apostrophe instead of an opening single quote.
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_cockney
+ */
+ function test_cockney( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_cockney() {
+ return array(
+ array(
+ "word 'tain't word",
+ "word ’tain’t word",
+ ),
+ array(
+ "word 'twere word",
+ "word ’twere word",
+ ),
+ array(
+ "word 'twas word",
+ "word ’twas word",
+ ),
+ array(
+ "word 'tis word",
+ "word ’tis word",
+ ),
+ array(
+ "word 'twill word",
+ "word ’twill word",
+ ),
+ array(
+ "word 'til word",
+ "word ’til word",
+ ),
+ array(
+ "word 'bout word",
+ "word ’bout word",
+ ),
+ array(
+ "word 'nuff word",
+ "word ’nuff word",
+ ),
+ array(
+ "word 'round word",
+ "word ’round word",
+ ),
+ array(
+ "word 'cause word",
+ "word ’cause word",
+ ),
+ array(
+ "word 'em word",
+ "word ‘em word",
+ ),
+ );
+ }
+
+ /**
+ * Test smart dashes.
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_smart_dashes
+ */
+ function test_smart_dashes( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_smart_dashes() {
+ return array(
+ array(
+ "word --- word",
+ "word — word",
+ ),
+ array(
+ "word---word",
+ "word—word",
+ ),
+ array(
+ "word -- word",
+ "word — word",
+ ),
+ array(
+ "word--word",
+ "word–word",
+ ),
+ array(
+ "word - word",
+ "word – word",
+ ),
+ array(
+ "word-word",
+ "word-word",
+ ),
+ array(
+ "word xn– word",
+ "word xn-- word",
+ ),
+ array(
+ "wordxn–word",
+ "wordxn--word",
+ ),
+ );
+ }
+
+ /**
+ * Test miscellaneous static replacements.
+ *
+ * Checks all baseline patterns. If anything ever changes in wptexturize(), these tests may fail.
+ *
+ * @ticket 22692
+ * @dataProvider data_misc_static_replacements
+ */
+ function test_misc_static_replacements( $input, $output ) {
+ return $this->assertEquals( $output, wptexturize( $input ) );
+ }
+
+ function data_misc_static_replacements() {
+ return array(
+ array(
+ "word ... word",
+ "word … word",
+ ),
+ array(
+ "word...word",
+ "word…word",
+ ),
+ array(
+ "word `` word",
+ "word “ word",
+ ),
+ array(
+ "word``word",
+ "word“word",
+ ),
+ array(
+ "word '' word",
+ "word ” word",
+ ),
+ array(
+ "word''word",
+ "word”word",
+ ),
+ array(
+ "word (tm) word",
+ "word ™ word",
+ ),
+ array(
+ "word (tm)word",
+ "word ™word",
+ ),
+ array(
+ "word(tm) word",
+ "word(tm) word",
+ ),
+ array(
+ "word(tm)word",
+ "word(tm)word",
+ ),
+ );
+ }
</ins><span class="cx"> }
</span></span></pre>
</div>
</div>
</body>
</html>