From 1069cfb91833e0264adcf89b0005de284a2edf25 Mon Sep 17 00:00:00 2001
From: Ayesh Karunaratne <ayesh@aye.sh>
Date: Wed, 10 Jan 2024 16:58:49 +0700
Subject: [PATCH] Add initial version with tests

---
 composer.json        |  6 +--
 src/mb_trim.php      | 99 ++++++++++++++++++++++++++++++++++++++++++++
 tests/MbTrimTest.php | 75 +++++++++++++++++++++++++++++++++
 3 files changed, 177 insertions(+), 3 deletions(-)
 create mode 100644 src/mb_trim.php
 create mode 100644 tests/MbTrimTest.php

diff --git a/composer.json b/composer.json
index 0f7193f..2a5d7cb 100644
--- a/composer.json
+++ b/composer.json
@@ -14,9 +14,9 @@
     },
     "license": "MIT",
     "autoload": {
-        "psr-4": {
-            "Phpwatch\\MbTrimPolyfill\\": "src/"
-        }
+        "files": [
+            "src/mb_trim.php"
+        ]
     },
     "authors": [
         {
diff --git a/src/mb_trim.php b/src/mb_trim.php
new file mode 100644
index 0000000..50451b5
--- /dev/null
+++ b/src/mb_trim.php
@@ -0,0 +1,99 @@
+<?php
+
+function mb_trim(string $string, string $characters = " \f\n\r\t\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}", ?string $encoding = null): string {
+    try {
+        @mb_check_encoding('', $encoding);
+    } catch (ValueError $e) {
+        throw new ValueError(sprintf('%s(): Argument #3 ($encoding) must be a valid encoding, "%s" given', __FUNCTION__, $encoding));
+    }
+
+    if ($characters === "") {
+        return $string;
+    }
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $string = mb_convert_encoding($string, "UTF-8", $encoding);
+        $characters = mb_convert_encoding($characters, "UTF-8", $encoding);
+    }
+
+    $charMap = array_map(static function(string $char) {
+        return preg_quote($char, '/');
+    }, mb_str_split($characters));
+
+    $regexClass = implode('', $charMap);
+
+    $regex = "/^[" . $regexClass . "]+|[" . $regexClass . "]+$/u";
+
+    $return = preg_replace($regex, '', $string);
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $return = mb_convert_encoding($return, $encoding, "UTF-8");
+    }
+
+    return $return;
+}
+
+function mb_ltrim(string $string, string $characters = " \f\n\r\t\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}", ?string $encoding = null): string {
+    if ($characters === "") {
+        return $string;
+    }
+    try {
+        @mb_check_encoding('', $encoding);
+    } catch (ValueError $e) {
+        throw new ValueError(sprintf('%s(): Argument #3 ($encoding) must be a valid encoding, "%s" given', __FUNCTION__, $encoding));
+    }
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $string = mb_convert_encoding($string, "UTF-8", $encoding);
+        $characters = mb_convert_encoding($characters, "UTF-8", $encoding);
+    }
+
+    $charMap = array_map(static function(string $char) {
+        return preg_quote($char, '/');
+    }, mb_str_split($characters));
+
+    $regexClass = implode('', $charMap);
+
+    $regex = "/^[" . $regexClass . "]+/u";
+
+    $return = preg_replace($regex, '', $string);
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $return = mb_convert_encoding($return, $encoding, "UTF-8");
+    }
+
+    return $return;
+}
+
+function mb_rtrim(string $string, string $characters = " \f\n\r\t\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}", ?string $encoding = null): string {
+    if ($characters === "") {
+        return $string;
+    }
+    try {
+        @mb_check_encoding('', $encoding);
+    } catch (ValueError $e) {
+        throw new ValueError(sprintf('%s(): Argument #3 ($encoding) must be a valid encoding, "%s" given', __FUNCTION__, $encoding));
+    }
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $string = mb_convert_encoding($string, "UTF-8", $encoding);
+        $characters = mb_convert_encoding($characters, "UTF-8", $encoding);
+    }
+
+    $charMap = array_map(static function(string $char) {
+        return preg_quote($char, '/');
+    }, mb_str_split($characters));
+
+    $regexClass = implode('', $charMap);
+
+    $regex = "/[" . $regexClass . "]+$/u";
+
+    $return = preg_replace($regex, '', $string);
+
+    if ($encoding !== null && $encoding !== 'UTF-8') {
+        $return = mb_convert_encoding($return, $encoding, "UTF-8");
+    }
+
+    return $return;
+}
+
diff --git a/tests/MbTrimTest.php b/tests/MbTrimTest.php
new file mode 100644
index 0000000..217d275
--- /dev/null
+++ b/tests/MbTrimTest.php
@@ -0,0 +1,75 @@
+<?php
+
+namespace PHPWatch\MbTrimPolyfill\Tests;
+
+use PHPUnit\Framework\TestCase;
+
+use function mb_ltrim;
+use function mb_rtrim;
+use function mb_trim;
+
+class MbTrimTest extends TestCase {
+
+    public function testMbTrim(): void {
+        $this->assertSame("ABC", mb_trim("ABC"));
+        $this->assertSame("ABC", mb_ltrim("ABC"));
+        $this->assertSame("ABC", mb_rtrim("ABC"));
+
+        $this->assertSame('ABC', mb_trim(" \0\t\nABC \0\t\n"));
+        $this->assertSame("ABC \0\t\n", mb_ltrim(" \0\t\nABC \0\t\n"));
+        $this->assertSame(" \0\t\nABC", mb_rtrim(" \0\t\nABC \0\t\n"));
+        $this->assertSame(" \0\t\nABC \0\t\n", mb_rtrim(" \0\t\nABC \0\t\n",''));
+
+        $this->assertSame("", mb_trim(""));
+        $this->assertSame("", mb_ltrim(""));
+        $this->assertSame("", mb_rtrim(""));
+
+        $this->assertSame(" test ", mb_ltrim(' test ', ''));
+        $this->assertSame("あいうえおあお", mb_trim("　あいうえおあお　", "　", "UTF-8"));
+        $this->assertSame("foo BAR Spa", mb_trim('foo BAR Spaß', 'ß', "UTF-8"));
+        $this->assertSame("oo BAR Spaß", mb_trim('foo BAR Spaß', 'f', "UTF-8"));
+
+        $this->assertSame("oo BAR Spa", mb_trim('foo BAR Spaß', 'ßf', "UTF-8"));
+        $this->assertSame("oo BAR Spa", mb_trim('foo BAR Spaß', 'fß', "UTF-8"));
+        $this->assertSame("いうおえお ", mb_trim("　あいうおえお 　あ", "　あ", "UTF-8"));
+        $this->assertSame("いうおえお ", mb_trim("　あいうおえお 　あ", "あ　", "UTF-8"));
+        $this->assertSame("　あいうおえお 　", mb_trim("　あいうおえお 　a", "あa", "UTF-8"));
+        //$this->assertSame("　あいうおえお 　a", mb_trim("　あいうおえお 　a", "\xe3", "UTF-8"));
+
+        $this->assertSame("", mb_trim(str_repeat("　", 129)));
+        $this->assertSame("a", mb_trim(str_repeat("　", 129) . "a"));
+        $this->assertSame("　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　a", mb_rtrim(str_repeat("　", 129) . "a"));
+
+        $trim_chars = "";
+        for ($i = 1024; $i < 2048; $i++) {
+            $trim_chars .= mb_chr($i);
+        }
+        $this->assertSame("hello", mb_trim($trim_chars . "hello" . $trim_chars, $trim_chars));
+        $this->assertSame(2053, strlen(mb_ltrim($trim_chars . "hello" . $trim_chars, $trim_chars)));
+        $this->assertSame(2053, strlen(mb_ltrim($trim_chars . "hello" . $trim_chars, $trim_chars)));
+
+        $this->assertSame("いああああ", mb_ltrim("あああああああああああああああああああああああああああああああああいああああ", "あ"));
+
+        $this->assertSame("あああああああああああああああああああああああああああああああああい", mb_rtrim("あああああああああああああああああああああああああああああああああいああああ", "あ"));
+
+        $this->assertSame("", mb_trim(" \f\n\r\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}"));
+
+        $this->assertSame("", mb_trim(" \f\n\r\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}"));
+
+        $this->assertSame("漢字", mb_ltrim("\u{FFFE}漢字", "\u{FFFE}\u{FEFF}"));
+        $this->assertSame("226f575b", bin2hex(mb_ltrim(mb_convert_encoding("\u{FFFE}漢字", "UTF-16LE", "UTF-8"), mb_convert_encoding("\u{FFFE}\u{FEFF}", "UTF-16LE", "UTF-8"), "UTF-16LE")));
+        $this->assertSame("6f225b57", bin2hex(mb_ltrim(mb_convert_encoding("\u{FEFF}漢字", "UTF-16BE", "UTF-8"), mb_convert_encoding("\u{FFFE}\u{FEFF}", "UTF-16BE", "UTF-8"), "UTF-16BE")));
+
+        $this->assertSame(" abcd ", mb_trim(" abcd ", ""));
+        $this->assertSame(" abcd ", mb_ltrim(" abcd ", ""));
+        $this->assertSame(" abcd ", mb_rtrim(" abcd ", ""));
+
+        $this->assertSame("あ", mb_convert_encoding(mb_trim("\x81\x40\x82\xa0\x81\x40", "\x81\x40", "SJIS"), "UTF-8", "SJIS"));
+
+        $this->assertSame("f", mb_trim("foo", "oo"));
+
+
+        $this->expectException(\ValueError::class);
+        mb_trim( "\u{180F}", "", "NULL");
+    }
+}