From cd65604073a2ab3b4175671f35a20fada7bdc6e1 Mon Sep 17 00:00:00 2001
From: Clemens Schwaighofer <clemens.schwaighofer@egplusww.com>
Date: Wed, 14 Jan 2026 10:36:09 +0900
Subject: [PATCH] Add parseCharacterRanges function to Strings.php and tests

Parses character ranges like A-Z into individual characters and returns as an array
---
 4dev/checking/phan.sh                         |  2 +-
 4dev/checking/phpstan.sh                      |  2 +-
 4dev/checking/phpunit.sh                      |  2 +-
 .../Convert/CoreLibsConvertStringsTest.php    | 78 +++++++++++++++++++
 www/admin/class_test.strings.php              | 21 +++++
 www/lib/CoreLibs/Convert/Strings.php          | 45 +++++++++++
 6 files changed, 147 insertions(+), 3 deletions(-)

diff --git a/4dev/checking/phan.sh b/4dev/checking/phan.sh
index e4833205..06c6bd6e 100755
--- a/4dev/checking/phan.sh
+++ b/4dev/checking/phan.sh
@@ -6,7 +6,7 @@ function error() {
 
 usage() {
 	cat <<EOF
-Usage: $(basename "${BASH_SOURCE[0]}") [-h] [-p VERSION]
+Usage: $(basename "${BASH_SOURCE[0]}") [-h | --help] [-p | --php VERSION] [-c | --composer]
 
 Runs phan static analyzer.
 
diff --git a/4dev/checking/phpstan.sh b/4dev/checking/phpstan.sh
index 8fc1e647..1a3feb07 100755
--- a/4dev/checking/phpstan.sh
+++ b/4dev/checking/phpstan.sh
@@ -6,7 +6,7 @@ function error() {
 
 usage() {
 	cat <<EOF
-Usage: $(basename "${BASH_SOURCE[0]}") [-h] [-p VERSION]
+Usage: $(basename "${BASH_SOURCE[0]}") [-h] [-h | --help] [-p | --php VERSION] [-c | --composer]
 
 Runs phan static analyzer.
 
diff --git a/4dev/checking/phpunit.sh b/4dev/checking/phpunit.sh
index 86d0176b..130ebcba 100755
--- a/4dev/checking/phpunit.sh
+++ b/4dev/checking/phpunit.sh
@@ -6,7 +6,7 @@ function error() {
 
 usage() {
 	cat <<EOF
-Usage: $(basename "${BASH_SOURCE[0]}") [-h] [-t] [-v] [-p VERSION]
+Usage: $(basename "${BASH_SOURCE[0]}") [-h | --help] [-p | --php VERSION] [-c | --composer] [-t | --testdox] [-v | --verbose]
 
 Runs all the PHP unit tests.
 
diff --git a/4dev/tests/Convert/CoreLibsConvertStringsTest.php b/4dev/tests/Convert/CoreLibsConvertStringsTest.php
index ed4bbc97..26c635eb 100644
--- a/4dev/tests/Convert/CoreLibsConvertStringsTest.php
+++ b/4dev/tests/Convert/CoreLibsConvertStringsTest.php
@@ -698,6 +698,84 @@ final class CoreLibsConvertStringsTest extends TestCase
 			'Cannot match last preg error string'
 		);
 	}
+
+
+	/**
+	 * Undocumented function
+	 *
+	 * @return array
+	 */
+	public function parseCharacterRangesProvider(): array
+	{
+		return [
+			'simple a-z' => [
+				['a-z'],
+				implode('', range('a', 'z')),
+				null,
+			],
+			'simple A-Z' => [
+				['A-Z'],
+				implode('', range('A', 'Z')),
+				null,
+			],
+			'simple 0-9' => [
+				['0-9'],
+				implode('', range('0', '9')),
+				null,
+			],
+			'mixed ranges' => [
+				['a-c', 'X-Z', '3-5'],
+				'abcXYZ345',
+				null,
+			],
+			'reverse ranges' => [
+				['z-a'],
+				'abcdefghijklmnopqrstuvwxyz',
+				null,
+			],
+			'overlapping ranges' => [
+				['a-f', 'd-j'],
+				'abcdefghij',
+				null,
+			],
+			'mixed valid and overlap ranges' => [
+				['a-f', 'z-a', '0-3'],
+				'abcdefghijklmnopqrstuvwxyz0123',
+				null,
+			],
+			'invalid ranges' => [
+				['a-あ', 'A-あ', '0-あ'],
+				'',
+				\InvalidArgumentException::class,
+			],
+		];
+	}
+
+	/**
+	 * Undocumented function
+	 *
+	 * @covers ::parseCharacterRanges
+	 * @dataProvider parseCharacterRangesProvider
+	 * @testdox parseCharacterRanges $input to $expected [$_dataName]
+	 *
+	 * @param  array       $input
+	 * @param  string      $expected
+	 * @param  string|null $expected_exception
+	 * @return void
+	 */
+	public function testParseCharacterRanges(
+		array $input,
+		string $expected,
+		?string $expected_exception
+	): void {
+		if ($expected_exception !== null) {
+			$this->expectException($expected_exception);
+		}
+		$this->assertEquals(
+			$expected,
+			implode('', \CoreLibs\Convert\Strings::parseCharacterRanges(implode('', $input)))
+		);
+	}
 }
 
 // __END__
diff --git a/www/admin/class_test.strings.php b/www/admin/class_test.strings.php
index 95e4457a..95fb3f69 100644
--- a/www/admin/class_test.strings.php
+++ b/www/admin/class_test.strings.php
@@ -140,6 +140,27 @@ $preg_error = Strings::isValidRegex($regex_string);
 print "[B] LAST PREGE ERROR: " . preg_last_error() . " -> "
 	. Strings::getLastRegexErrorString() . " -> " . preg_last_error_msg() . "<br>";
 
+$base_strings = [
+	'A-Z',
+	'a-z',
+	'A-Za-z',
+	'A-Df-g',
+	'A-D0-9',
+	'D-A7-0',
+	'A-FB-G',
+	'0-9',
+	'あ-お',
+	'ア-オ',
+];
+foreach ($base_strings as $string) {
+	try {
+		$parsed = Strings::parseCharacterRanges($string);
+		print "Parsed ranges for '$string': " . DgS::printAr($parsed) . "<br>";
+	} catch (\InvalidArgumentException $e) {
+		print "Error parsing ranges for '$string': " . $e->getMessage() . "<br>";
+	}
+}
+
 print "</body></html>";
 
 // __END__
diff --git a/www/lib/CoreLibs/Convert/Strings.php b/www/lib/CoreLibs/Convert/Strings.php
index 30d4ad44..dd30b470 100644
--- a/www/lib/CoreLibs/Convert/Strings.php
+++ b/www/lib/CoreLibs/Convert/Strings.php
@@ -268,6 +268,51 @@ class Strings
 		));
 	}
 
+	/**
+	 * Split up character ranges in format A-Z, a-z, 0-9
+	 *
+	 * @param  string $input
+	 * @return string[]
+	 */
+	public static function parseCharacterRanges(string $input): array
+	{
+		// if not alphanumeric, throw value error
+		if (!preg_match("/^[A-Za-z0-9\-\s]+$/u", $input)) {
+			throw new \InvalidArgumentException(
+				"The input string contains invalid characters, "
+				. "only alphanumeric, dash (-), space and 'or' are allowed: "
+				. $input
+			);
+		}
+		// Remove all spaces
+		$input = str_replace(' ', '', $input);
+		$result = [];
+		// Find all patterns like "A-Z" (character-dash-character)
+		preg_match_all('/(.)-(.)/u', $input, $matches, PREG_SET_ORDER);
+		foreach ($matches as $match) {
+			$start = $match[1];
+			$end = $match[2];
+			// Get ASCII/Unicode values
+			$startOrd = ord($start[0]);
+			$endOrd = ord($end[0]);
+			// make sure start is before end
+			if ($startOrd > $endOrd) {
+				[$startOrd, $endOrd] = [$endOrd, $startOrd];
+			}
+
+			// Generate range of characters
+			for ($i = $startOrd; $i <= $endOrd; $i++) {
+				$char = chr($i);
+				if (!in_array($char, $result)) {
+					$result[] = $char;
+				}
+			}
+		}
+		// make the result unique
+		$result = array_unique($result);
+		return $result;
+	}
+
 	/**
 	 * Check if a regex is valid. Does not return the detail regex parser error
 	 *