ext/mbstring: Update to Unicode 18.0 (#23755)

* ext/mbstring: Update to Unicode 18.0

Previously:
 - #15898
 - 0fdffc1
 - #7502
 - #14680

* Update NEWS and UPGRADING

Author: youkidearitai

NEWS

@@ -40,6 +40,7 @@ PHP                                                                        NEWS
 - MBString:
   . Fixed bug GH-23106 (mb_strpos() reads past the end of a haystack ending in
     a truncated UTF-8 sequence). (Lazizbek Ergashev)
+  . Updated Unicode data tables to Unicode 18.0 (Yuya Hamada)
 
 - PDO:
   . Fixed PDOStatement::getColumnMeta() reading out of bounds for an invalid

UPGRADING

@@ -99,6 +99,9 @@ PHP 8.6 UPGRADE NOTES
     intl.use_exceptions enabled, these failures throw IntlException. Previously,
     these paths emitted a warning and compared the value as an empty string.
 
+- MBstring:
+  . Unicode data tables have been updated to Unicode 18.0
+
 - PCNTL:
   . pcntl_alarm() now raises a ValueError if the seconds argument is
     lower than zero or greater than the platform's UINT_MAX.

ext/mbstring/libmbfl/mbfl/eaw_table.h

@@ -81,24 +81,27 @@ static const struct {
 	{ 0xffe0, 0xffe6 },
 	{ 0x16fe0, 0x16fe4 },
 	{ 0x16ff0, 0x16ff6 },
-	{ 0x17000, 0x18cd5 },
-	{ 0x18cff, 0x18d1e },
+	{ 0x17000, 0x18cda },
+	{ 0x18cff, 0x18d20 },
 	{ 0x18d80, 0x18df2 },
+	{ 0x18e00, 0x19191 },
+	{ 0x191a0, 0x191d2 },
 	{ 0x1aff0, 0x1aff3 },
 	{ 0x1aff5, 0x1affb },
 	{ 0x1affd, 0x1affe },
-	{ 0x1b000, 0x1b122 },
+	{ 0x1b000, 0x1b128 },
 	{ 0x1b132, 0x1b132 },
 	{ 0x1b150, 0x1b152 },
 	{ 0x1b155, 0x1b155 },
-	{ 0x1b164, 0x1b167 },
+	{ 0x1b164, 0x1b168 },
 	{ 0x1b170, 0x1b2fb },
 	{ 0x1d300, 0x1d356 },
 	{ 0x1d360, 0x1d376 },
 	{ 0x1f004, 0x1f004 },
 	{ 0x1f0cf, 0x1f0cf },
 	{ 0x1f18e, 0x1f18e },
 	{ 0x1f191, 0x1f19a },
+	{ 0x1f1ae, 0x1f1ae },
 	{ 0x1f200, 0x1f202 },
 	{ 0x1f210, 0x1f23b },
 	{ 0x1f240, 0x1f248 },
@@ -125,22 +128,22 @@ static const struct {
 	{ 0x1f680, 0x1f6c5 },
 	{ 0x1f6cc, 0x1f6cc },
 	{ 0x1f6d0, 0x1f6d2 },
-	{ 0x1f6d5, 0x1f6d8 },
+	{ 0x1f6d5, 0x1f6d9 },
 	{ 0x1f6dc, 0x1f6df },
 	{ 0x1f6eb, 0x1f6ec },
 	{ 0x1f6f4, 0x1f6fc },
+	{ 0x1f7da, 0x1f7da },
 	{ 0x1f7e0, 0x1f7eb },
 	{ 0x1f7f0, 0x1f7f0 },
 	{ 0x1f90c, 0x1f93a },
 	{ 0x1f93c, 0x1f945 },
 	{ 0x1f947, 0x1f9ff },
 	{ 0x1fa70, 0x1fa7c },
-	{ 0x1fa80, 0x1fa8a },
-	{ 0x1fa8e, 0x1fac6 },
+	{ 0x1fa80, 0x1fac6 },
 	{ 0x1fac8, 0x1fac8 },
-	{ 0x1facd, 0x1fadc },
-	{ 0x1fadf, 0x1faea },
-	{ 0x1faef, 0x1faf8 },
+	{ 0x1facc, 0x1fadd },
+	{ 0x1fadf, 0x1faeb },
+	{ 0x1faef, 0x1fafa },
 	{ 0x20000, 0x2fffd },
 	{ 0x30000, 0x3fffd },
 };

ext/mbstring/tests/unicode_versions.phpt

@@ -26,6 +26,11 @@ print "Emoji (\u{2630}): " . mb_strwidth("\u{2630}", 'UTF-8') . "\n";
 // New in Unicode 17.0, width=2
 print "Emoji (\u{1FAEA}): " . mb_strwidth("\u{1FAEA}", "UTF-8") . "\n";
 
+// New in Unicode 18.0, width=2
+print "RUFIYAA SIGN (\u{20C2}): " . mb_strwidth("\u{20C2}", "UTF-8") . "\n";
+print "CJK Unified Ideograph-2B81E (\u{2B81E}): " . mb_strwidth("\u{2B81E}", "UTF-8") . "\n";
+print "Emoji (\u{1FAEB}): " . mb_strwidth("\u{1FAEB}", "UTF-8") . "\n";
+
 echo "Char case changes:\n";
 
 print "Upper(\u{019b}) = \u{a7dc} : ";
@@ -41,5 +46,8 @@ Emoji (🐘): 2
 Emoji (🛜): 2
 Emoji (☰): 2
 Emoji (🫪): 2
+RUFIYAA SIGN (⃂): 1
+CJK Unified Ideograph-2B81E (𫠞): 2
+Emoji (🫫): 2
 Char case changes:
 Upper(ƛ) = Ƛ : bool(true)