bug #358 Update to Unicode 13 and other fixes (nicolas-grekas)

This PR was squashed before being merged into the 1.23-dev branch.

Discussion
----------

Update to Unicode 13 and other fixes

Commits
-------

fe2c571 Update to Unicode 13
34bcae6 Various fixes

Author: nicolas-grekas

CHANGELOG.md

@@ -1,14 +1,15 @@
-# 1.23.1
-
-  * Fix `IntlDateFormatter::format()` on 32b platforms
-
 # 1.23.0
 
   * added `CURLStringFile` to the PHP 8.1 polyfill
   * added `enum_exists()` to the PHP 8.1 polyfill
   * added `MYSQLI_REFRESH_REPLICA` constant to PHP 8.1 polyfill
+  * added `ReturnTypeWillChange` to PHP 8.1 polyfill
+  * updated Unicode maps to v13
   * removed `INTL_IDNA_VARIANT_2003` on PHP 8
   * fixed return value of `mb_parse_str()`
+  * fixed `IntlDateFormatter::format()` on 32b platforms
+  * fixed `mb_chr()` in the PHP 7.2 polyfill
+  * fixed `mb_strrchr()`, `mb_detect_order()`, `iconv_substr()`, `grapheme_substr()` on PHP 8
 
 # 1.22.1
 

src/Iconv/Resources/charset/translit.php

@@ -3995,8 +3995,8 @@
   '₣' => 'Fr.',
   '₤' => 'L.',
   '₧' => 'Pts',
-  '₺' => 'TL',
   '₹' => 'Rs',
+  '₺' => 'TL',
   '℗' => '(P)',
   '℘' => 'P',
   '℞' => 'Rx',
@@ -4043,6 +4043,8 @@
   '―' => '-',
   '︱' => '-',
   '︲' => '-',
+  '¡' => '!',
+  '¿' => '?',
   '˂' => '<',
   '˃' => '>',
   '˄' => '^',
@@ -4087,6 +4089,7 @@
   '﹀' => '>',
   '﹇' => '[',
   '﹈' => ']',
+  '±' => '+/-',
   '×' => '*',
   '÷' => '/',
   '˖' => '+',

src/Iconv/bootstrap80.php

@@ -51,7 +51,7 @@ function iconv_strpos(?string $haystack, ?string $needle, ?int $offset = 0, ?str
         function iconv_strrpos(?string $haystack, ?string $needle, ?string $encoding = null): int|false { null === $encoding && $encoding = p\Iconv::$internalEncoding; return mb_strrpos((string) $haystack, (string) $needle, 0, $encoding); }
     }
     if (!function_exists('iconv_substr')) {
-        function iconv_substr(?string $string, ?int $offset, ?int $length = null, ?string $encoding = null): string|false { null === $encoding && $encoding = p\Iconv::$internalEncoding; return mb_substr((string) $string, (int) $offset, (int) $length, $encoding); }
+        function iconv_substr(?string $string, ?int $offset, ?int $length = null, ?string $encoding = null): string|false { null === $encoding && $encoding = p\Iconv::$internalEncoding; return mb_substr((string) $string, (int) $offset, $length, $encoding); }
     }
     if (!function_exists('iconv_mime_decode')) {
         function iconv_mime_decode($string, $mode = 0, $encoding = null) { null === $encoding && $encoding = p\Iconv::$internalEncoding; return mb_decode_mimeheader($string, $mode, $encoding); }
@@ -72,7 +72,7 @@ function iconv_strpos(?string $haystack, ?string $needle, ?int $offset = 0, ?str
         function iconv_strrpos(?string $haystack, ?string $needle, ?string $encoding = null): int|false { return p\Iconv::iconv_strrpos((string) $haystack, (string) $needle, $encoding); }
     }
     if (!function_exists('iconv_substr')) {
-        function iconv_substr(?string $string, ?int $offset, ?int $length = null, ?string $encoding = null): string|false { return p\Iconv::iconv_substr((string) $string, (string) $offset, (int) $length, $encoding); }
+        function iconv_substr(?string $string, ?int $offset, ?int $length = null, ?string $encoding = null): string|false { return p\Iconv::iconv_substr((string) $string, (string) $offset, $length, $encoding); }
     }
     if (!function_exists('iconv_mime_decode')) {
         function iconv_mime_decode(?string $string, ?int $mode = 0, ?string $encoding = null): string|false { return p\Iconv::iconv_mime_decode((string) $string, (int) $mode, $encoding); }

src/Intl/Grapheme/bootstrap80.php

@@ -46,5 +46,5 @@ function grapheme_strrpos(?string $haystack, ?string $needle, ?int $offset = 0):
     function grapheme_strstr(?string $haystack, ?string $needle, ?bool $beforeNeedle = false): string|false { return p\Grapheme::grapheme_strstr((string) $haystack, (string) $needle, (bool) $beforeNeedle); }
 }
 if (!function_exists('grapheme_substr')) {
-    function grapheme_substr(?string $string, ?int $offset, ?int $length = null): string|false { return p\Grapheme::grapheme_substr((string) $string, (int) $offset, (int) $length); }
+    function grapheme_substr(?string $string, ?int $offset, ?int $length = null): string|false { return p\Grapheme::grapheme_substr((string) $string, (int) $offset, $length); }
 }

src/Intl/Idn/Resources/unidata/Regex.php

@@ -81,7 +81,7 @@
   'Ī' => 'ī',
   'Ĭ' => 'ĭ',
   'Į' => 'į',
-  'İ' => 'i',
+  'İ' => 'i̇',
   'IJ' => 'ij',
   'Ĵ' => 'ĵ',
   'Ķ' => 'ķ',

src/Mbstring/Resources/unidata/lowerCase.php

@@ -746,41 +746,41 @@
   'ύ' => 'Ύ',
   'ὼ' => 'Ὼ',
   'ώ' => 'Ώ',
-  'ᾀ' => 'ᾈ',
-  'ᾁ' => 'ᾉ',
-  'ᾂ' => 'ᾊ',
-  'ᾃ' => 'ᾋ',
-  'ᾄ' => 'ᾌ',
-  'ᾅ' => 'ᾍ',
-  'ᾆ' => 'ᾎ',
-  'ᾇ' => 'ᾏ',
-  'ᾐ' => 'ᾘ',
-  'ᾑ' => 'ᾙ',
-  'ᾒ' => 'ᾚ',
-  'ᾓ' => 'ᾛ',
-  'ᾔ' => 'ᾜ',
-  'ᾕ' => 'ᾝ',
-  'ᾖ' => 'ᾞ',
-  'ᾗ' => 'ᾟ',
-  'ᾠ' => 'ᾨ',
-  'ᾡ' => 'ᾩ',
-  'ᾢ' => 'ᾪ',
-  'ᾣ' => 'ᾫ',
-  'ᾤ' => 'ᾬ',
-  'ᾥ' => 'ᾭ',
-  'ᾦ' => 'ᾮ',
-  'ᾧ' => 'ᾯ',
+  'ᾀ' => 'ἈΙ',
+  'ᾁ' => 'ἉΙ',
+  'ᾂ' => 'ἊΙ',
+  'ᾃ' => 'ἋΙ',
+  'ᾄ' => 'ἌΙ',
+  'ᾅ' => 'ἍΙ',
+  'ᾆ' => 'ἎΙ',
+  'ᾇ' => 'ἏΙ',
+  'ᾐ' => 'ἨΙ',
+  'ᾑ' => 'ἩΙ',
+  'ᾒ' => 'ἪΙ',
+  'ᾓ' => 'ἫΙ',
+  'ᾔ' => 'ἬΙ',
+  'ᾕ' => 'ἭΙ',
+  'ᾖ' => 'ἮΙ',
+  'ᾗ' => 'ἯΙ',
+  'ᾠ' => 'ὨΙ',
+  'ᾡ' => 'ὩΙ',
+  'ᾢ' => 'ὪΙ',
+  'ᾣ' => 'ὫΙ',
+  'ᾤ' => 'ὬΙ',
+  'ᾥ' => 'ὭΙ',
+  'ᾦ' => 'ὮΙ',
+  'ᾧ' => 'ὯΙ',
   'ᾰ' => 'Ᾰ',
   'ᾱ' => 'Ᾱ',
-  'ᾳ' => 'ᾼ',
+  'ᾳ' => 'ΑΙ',
   'ι' => 'Ι',
-  'ῃ' => 'ῌ',
+  'ῃ' => 'ΗΙ',
   'ῐ' => 'Ῐ',
   'ῑ' => 'Ῑ',
   'ῠ' => 'Ῠ',
   'ῡ' => 'Ῡ',
   'ῥ' => 'Ῥ',
-  'ῳ' => 'ῼ',
+  'ῳ' => 'ΩΙ',
   'ⅎ' => 'Ⅎ',
   'ⅰ' => 'Ⅰ',
   'ⅱ' => 'Ⅱ',
@@ -1411,4 +1411,79 @@
   '𞥁' => '𞤟',
   '𞥂' => '𞤠',
   '𞥃' => '𞤡',
+  'ß' => 'SS',
+  'ff' => 'FF',
+  'fi' => 'FI',
+  'fl' => 'FL',
+  'ffi' => 'FFI',
+  'ffl' => 'FFL',
+  'ſt' => 'ST',
+  'st' => 'ST',
+  'և' => 'ԵՒ',
+  'ﬓ' => 'ՄՆ',
+  'ﬔ' => 'ՄԵ',
+  'ﬕ' => 'ՄԻ',
+  'ﬖ' => 'ՎՆ',
+  'ﬗ' => 'ՄԽ',
+  'ʼn' => 'ʼN',
+  'ΐ' => 'Ϊ́',
+  'ΰ' => 'Ϋ́',
+  'ǰ' => 'J̌',
+  'ẖ' => 'H̱',
+  'ẗ' => 'T̈',
+  'ẘ' => 'W̊',
+  'ẙ' => 'Y̊',
+  'ẚ' => 'Aʾ',
+  'ὐ' => 'Υ̓',
+  'ὒ' => 'Υ̓̀',
+  'ὔ' => 'Υ̓́',
+  'ὖ' => 'Υ̓͂',
+  'ᾶ' => 'Α͂',
+  'ῆ' => 'Η͂',
+  'ῒ' => 'Ϊ̀',
+  'ΐ' => 'Ϊ́',
+  'ῖ' => 'Ι͂',
+  'ῗ' => 'Ϊ͂',
+  'ῢ' => 'Ϋ̀',
+  'ΰ' => 'Ϋ́',
+  'ῤ' => 'Ρ̓',
+  'ῦ' => 'Υ͂',
+  'ῧ' => 'Ϋ͂',
+  'ῶ' => 'Ω͂',
+  'ᾈ' => 'ἈΙ',
+  'ᾉ' => 'ἉΙ',
+  'ᾊ' => 'ἊΙ',
+  'ᾋ' => 'ἋΙ',
+  'ᾌ' => 'ἌΙ',
+  'ᾍ' => 'ἍΙ',
+  'ᾎ' => 'ἎΙ',
+  'ᾏ' => 'ἏΙ',
+  'ᾘ' => 'ἨΙ',
+  'ᾙ' => 'ἩΙ',
+  'ᾚ' => 'ἪΙ',
+  'ᾛ' => 'ἫΙ',
+  'ᾜ' => 'ἬΙ',
+  'ᾝ' => 'ἭΙ',
+  'ᾞ' => 'ἮΙ',
+  'ᾟ' => 'ἯΙ',
+  'ᾨ' => 'ὨΙ',
+  'ᾩ' => 'ὩΙ',
+  'ᾪ' => 'ὪΙ',
+  'ᾫ' => 'ὫΙ',
+  'ᾬ' => 'ὬΙ',
+  'ᾭ' => 'ὭΙ',
+  'ᾮ' => 'ὮΙ',
+  'ᾯ' => 'ὯΙ',
+  'ᾼ' => 'ΑΙ',
+  'ῌ' => 'ΗΙ',
+  'ῼ' => 'ΩΙ',
+  'ᾲ' => 'ᾺΙ',
+  'ᾴ' => 'ΆΙ',
+  'ῂ' => 'ῊΙ',
+  'ῄ' => 'ΉΙ',
+  'ῲ' => 'ῺΙ',
+  'ῴ' => 'ΏΙ',
+  'ᾷ' => 'Α͂Ι',
+  'ῇ' => 'Η͂Ι',
+  'ῷ' => 'Ω͂Ι',
 );

src/Mbstring/Resources/unidata/upperCase.php

@@ -48,7 +48,7 @@ function mb_check_encoding(array|string|null $value = null, ?string $encoding =
     function mb_detect_encoding(?string $string, array|string|null $encodings = null, ?bool $strict = false): string|false { return p\Mbstring::mb_detect_encoding((string) $string, $encodings, (bool) $strict); }
 }
 if (!function_exists('mb_detect_order')) {
-    function mb_detect_order(array|string|null $encoding = null): array|bool { return p\Mbstring::mb_detect_order((string) $encoding); }
+    function mb_detect_order(array|string|null $encoding = null): array|bool { return p\Mbstring::mb_detect_order($encoding); }
 }
 if (!function_exists('mb_parse_str')) {
     function mb_parse_str(?string $string, &$result = []): bool { parse_str((string) $string, $result); return (bool) $result; }
@@ -78,7 +78,7 @@ function mb_stripos(?string $haystack, ?string $needle, ?int $offset = 0, ?strin
     function mb_stristr(?string $haystack, ?string $needle, ?bool $before_needle = false, ?string $encoding = null): string|false { return p\Mbstring::mb_stristr((string) $haystack, (string) $needle, (bool) $before_needle, $encoding); }
 }
 if (!function_exists('mb_strrchr')) {
-    function mb_strrchr(?string $haystack, ?string $needle, ?bool $before_needle = false, ?string $encoding = null): string|false { return p\Mbstring::mb_strrchr((string) $haystack, (string) $needle, $before_needle, (bool) $encoding); }
+    function mb_strrchr(?string $haystack, ?string $needle, ?bool $before_needle = false, ?string $encoding = null): string|false { return p\Mbstring::mb_strrchr((string) $haystack, (string) $needle, (bool) $before_needle, $encoding); }
 }
 if (!function_exists('mb_strrichr')) {
     function mb_strrichr(?string $haystack, ?string $needle, ?bool $before_needle = false, ?string $encoding = null): string|false { return p\Mbstring::mb_strrichr((string) $haystack, (string) $needle, (bool) $before_needle, $encoding); }

src/Mbstring/bootstrap80.php

@@ -182,7 +182,7 @@ public static function mb_chr($code, $encoding = null)
             $s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
         }
 
-        if ('UTF-8' !== $encoding) {
+        if ('UTF-8' !== $encoding = $encoding ?? mb_internal_encoding()) {
             $s = mb_convert_encoding($s, $encoding, 'UTF-8');
         }
 

src/Php72/Php72.php

@@ -139,6 +139,25 @@ public static function unicodeMaps($out_dir)
         }
         fclose($h);
 
+        $h = fopen(self::getFile('SpecialCasing.txt'), 'r');
+        while (false !== $m = fgets($h)) {
+            if ('#' === $m[0] || 5 !== \count($m = explode('; ', $m))) {
+                continue;
+            }
+
+            $k = self::chr(hexdec($m[0]));
+            $lower = implode('', array_map([__CLASS__, 'chr'], array_map('hexdec', explode(' ', $m[1]))));
+            $upper = implode('', array_map([__CLASS__, 'chr'], array_map('hexdec', explode(' ', $m[3]))));
+
+            if ($lower !== $k) {
+                $lowerCase[$k] = $lower;
+            }
+            if ($upper !== $k) {
+                $upperCase[$k] = $upper;
+            }
+        }
+        fclose($h);
+
         do {
             $m = 0;