From 33300cfd7cae90c120de08b972625bd4b6ce52ca Mon Sep 17 00:00:00 2001
From: Vladimir Jimenez <allejo@me.com>
Date: Sat, 8 Jan 2022 22:58:07 -0800
Subject: [PATCH 1/2] slug(): partial optimizations + fix PHP 8.1
---
src/__/functions/slug.php | 107 ++++++++++++++++++++++++++++++--
tests/__/Functions/SlugTest.php | 18 +++---
2 files changed, 114 insertions(+), 11 deletions(-)
diff --git a/src/__/functions/slug.php b/src/__/functions/slug.php
index 6d54425..9e7ec66 100644
--- a/src/__/functions/slug.php
+++ b/src/__/functions/slug.php
@@ -2,6 +2,88 @@
namespace functions;
+class _StringOps
+{
+ private static $hasMultibyteSupport;
+ private $needsMultibyteSupport;
+
+ public function __construct($string)
+ {
+ $this->needsMultibyteSupport = preg_match('/[^\x00-\x7F]/', $string) === 1;
+ $this->assertMultibyte();
+ }
+
+ public function needsMultibyteSupport()
+ {
+ return $this->needsMultibyteSupport;
+ }
+
+ /**
+ * @return string
+ */
+ public function smart_substr()
+ {
+ $args = func_get_args();
+ $fxn = $this->needsMultibyteSupport ? 'mb_substr' : 'substr';
+
+ if (!$this->needsMultibyteSupport) {
+ array_pop($args);
+ }
+
+ return call_user_func_array($fxn, $args);
+ }
+
+ /**
+ * @return int
+ */
+ public function smart_strlen()
+ {
+ $args = func_get_args();
+
+ if ($this->needsMultibyteSupport) {
+ call_user_func_array('mb_strlen', $args);
+ }
+
+ return strlen($args[0]);
+ }
+
+ /**
+ * @return string
+ */
+ public function smart_strtolower()
+ {
+ $args = func_get_args();
+
+ if ($this->needsMultibyteSupport) {
+ return call_user_func_array('mb_strtolower', $args);
+ }
+
+ return strtolower($args[0]);
+ }
+
+ private function assertMultibyte()
+ {
+ if (!$this->needsMultibyteSupport) {
+ return;
+ }
+
+ if ($this->hasMultibyteSupport()) {
+ return;
+ }
+
+ throw new \RuntimeException('The `mbstring` extension is not available and is required.');
+ }
+
+ private function hasMultibyteSupport()
+ {
+ if (self::$hasMultibyteSupport === null) {
+ self::$hasMultibyteSupport = extension_loaded('mbstring');
+ }
+
+ return self::$hasMultibyteSupport;
+ }
+}
+
/**
* Create a web friendly URL slug from a string.
*
@@ -33,8 +115,25 @@
*/
function slug($str, array $options = [])
{
- // Make sure string is in UTF-8 and strip invalid UTF-8 characters
- $str = \mb_convert_encoding((string)$str, 'UTF-8', \mb_list_encodings());
+ if (!is_string($str)) {
+ throw new \InvalidArgumentException('The $str argument expends a string.');
+ }
+
+ $ops = new _StringOps($str);
+
+ // Let's not waste resources if we don't need to do multibyte string processing
+ if ($ops->needsMultibyteSupport()) {
+ // Make sure string is in UTF-8 and strip invalid UTF-8 characters
+ /** @var false|string $encodedString */
+ $encodedString = \mb_convert_encoding($str, 'UTF-8', \mb_list_encodings());
+
+ // PHP 8.1.0 has a bug where $encodedString can be an empty string, so
+ // we only want to override `$str` if we have a good value.
+ // https://github.com/php/php-src/issues/7898
+ if ($encodedString !== '' && $encodedString !== false) {
+ $str = $encodedString;
+ }
+ }
$defaults = [
'delimiter' => '-',
@@ -66,11 +165,11 @@ function slug($str, array $options = [])
// Truncate slug to max. characters
if ($options['limit']) {
- $str = \mb_substr($str, 0, ($options['limit'] ?: \mb_strlen($str, 'UTF-8')), 'UTF-8');
+ $str = $ops->smart_substr($str, 0, ($options['limit'] ?: $ops->smart_strlen($str, 'UTF-8')), 'UTF-8');
}
// Remove delimiter from ends
$str = \trim($str, $options['delimiter']);
- return $options['lowercase'] ? \mb_strtolower($str, 'UTF-8') : $str;
+ return $options['lowercase'] ? $ops->smart_strtolower($str, 'UTF-8') : $str;
}
diff --git a/tests/__/Functions/SlugTest.php b/tests/__/Functions/SlugTest.php
index 9509566..6e45aca 100644
--- a/tests/__/Functions/SlugTest.php
+++ b/tests/__/Functions/SlugTest.php
@@ -9,15 +9,19 @@
class SlugTest extends TestCase
{
- public function testSlug()
+ public function testSlugWithUtf8()
{
- // Arrange
- $a = 'Jakieś zdanie z dużą ilością obcych znaków!';
+ $input = 'Jakieś zdanie z dużą ilością obcych znaków!';
+ $actual = __::slug($input);
- // Act
- $x = __::slug($a);
+ $this->assertEquals('jakies-zdanie-z-duza-iloscia-obcych-znakow', $actual);
+ }
+
+ public function testSlugWithAscii()
+ {
+ $input = 'Hello World!';
+ $actual = __::slug($input);
- // Assert
- $this->assertEquals('jakies-zdanie-z-duza-iloscia-obcych-znakow', $x);
+ $this->assertEquals('hello-world', $actual);
}
}
From c299a185e8774a0d89b4f72b3395ddae438e66c8 Mon Sep 17 00:00:00 2001
From: Vladimir Jimenez <allejo@me.com>
Date: Sat, 8 Jan 2022 23:22:18 -0800
Subject: [PATCH 2/2] Update CHANGELOG with __::slug() updates
---
CHANGELOG.md | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index b3c4738..a5550f8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,13 @@
# Changelog
+## v0.2.3-dev
+
+**2022-??-?? — [Diff](https://github.com/maciejczyzewski/bottomline/compare/0.2.2...0.2.3) — [Docs](https://maciejczyzewski.github.io/bottomline/)**
+
+* Updates to the `__::slug()` function,
+ - Optimized to be more performant when given plain, old ASCII text
+ - Has a workaround for [a bug in PHP 8.1](https://github.com/php/php-src/issues/7898) that would return an empty string
+
## v0.2.2
**2022-01-07 — [Diff](https://github.com/maciejczyzewski/bottomline/compare/0.2.1...0.2.2) — [Docs](https://maciejczyzewski.github.io/bottomline/)**