ext/mbstring: Update to Unicode 17.0

Author: youkidearitai

NEWS

@@ -7,6 +7,9 @@ PHP                                                                        NEWS
     checks). (timwolla)
   . The __sleep() and __wakeup() magic methods have been deprecated. (Girgias)
 
+- MBstring:
+  . Updated Unicode data tables to Unicode 17.0. (Yuya Hamada)
+
 - URI:
   . Fixed bug GH-19780 (InvalidUrlException should check $errors argument).
     (nielsdos)

UPGRADING

@@ -84,6 +84,9 @@ PHP 8.5 UPGRADE NOTES
   . ldap_get_option() and ldap_set_option() now throw a ValueError when
     passing an invalid option.
 
+- MBstring:
+  . Unicode data tables have been updated to Unicode 17.0
+
 - MySQLi:
   . Calling the mysqli constructor on an already-constructed object
     is now no longer possible and throws an Error.

ext/mbstring/libmbfl/mbfl/eaw_table.h

@@ -80,10 +80,10 @@ static const struct {
 	{ 0xff01, 0xff60 },
 	{ 0xffe0, 0xffe6 },
 	{ 0x16fe0, 0x16fe4 },
-	{ 0x16ff0, 0x16ff1 },
-	{ 0x17000, 0x187f7 },
-	{ 0x18800, 0x18cd5 },
-	{ 0x18cff, 0x18d08 },
+	{ 0x16ff0, 0x16ff6 },
+	{ 0x17000, 0x18cd5 },
+	{ 0x18cff, 0x18d1e },
+	{ 0x18d80, 0x18df2 },
 	{ 0x1aff0, 0x1aff3 },
 	{ 0x1aff5, 0x1affb },
 	{ 0x1affd, 0x1affe },
@@ -125,7 +125,7 @@ static const struct {
 	{ 0x1f680, 0x1f6c5 },
 	{ 0x1f6cc, 0x1f6cc },
 	{ 0x1f6d0, 0x1f6d2 },
-	{ 0x1f6d5, 0x1f6d7 },
+	{ 0x1f6d5, 0x1f6d8 },
 	{ 0x1f6dc, 0x1f6df },
 	{ 0x1f6eb, 0x1f6ec },
 	{ 0x1f6f4, 0x1f6fc },
@@ -135,11 +135,12 @@ static const struct {
 	{ 0x1f93c, 0x1f945 },
 	{ 0x1f947, 0x1f9ff },
 	{ 0x1fa70, 0x1fa7c },
-	{ 0x1fa80, 0x1fa89 },
-	{ 0x1fa8f, 0x1fac6 },
-	{ 0x1face, 0x1fadc },
-	{ 0x1fadf, 0x1fae9 },
-	{ 0x1faf0, 0x1faf8 },
+	{ 0x1fa80, 0x1fa8a },
+	{ 0x1fa8e, 0x1fac6 },
+	{ 0x1fac8, 0x1fac8 },
+	{ 0x1facd, 0x1fadc },
+	{ 0x1fadf, 0x1faea },
+	{ 0x1faef, 0x1faf8 },
 	{ 0x20000, 0x2fffd },
 	{ 0x30000, 0x3fffd },
 };

ext/mbstring/tests/unicode_versions.phpt

@@ -23,6 +23,9 @@ print "Emoji (\u{1F6DC}): " . mb_strwidth("\u{1F6DC}", 'UTF-8') . "\n";
 // Changed in Unicode 16.0, U+2630...U+2637 are wide
 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";
+
 echo "Char case changes:\n";
 
 print "Upper(\u{019b}) = \u{a7dc} : ";
@@ -37,5 +40,6 @@ Sinhalese (අයේෂ්): 5
 Emoji (🐘): 2
 Emoji (🛜): 2
 Emoji (☰): 2
+Emoji (🫪): 2
 Char case changes:
 Upper(ƛ) = Ƛ : bool(true)