- Fixed bug #52981 (Unicode casing table was out-of-date).

  Updated with UnicodeData-6.0.0d7.txt and included the
  source of the generator program with the distribution.
#The replaced tables, generated circa 2002, seem to reflect
#Unicode 3.2. I was unable to generate the same property
#offsets with Unicode 3.2 data, but all the tests I made
#indicate php_unicode_is_prop() is returning the correct
#values. The replaced file merely says it used a "modified
#version" of ucgendat, which is not very helpful. The results
#I got were not significantly different, only slightly higher
#offsets at two properties, which were carried over to the
#subsequent properties.
#I was, however, able to replicate precisely the casing table.
#The extent of the "modifications" besides omitting most of
#the tables, a slightly different layout and the casing table
#offsets having been multiplied by 3 is unclear.
#The test suite showed no regressions; however, it's very poor
#in testing the modified portion of the extension.

1 files changed, 23 insertions, 0 deletions

diff --git a/ext/mbstring/tests/bug52981.phpt b/ext/mbstring/tests/bug52981.phpt
new file mode 100644
index 0000000000..fe96a56f08
--- /dev/null
+++ b/ext/mbstring/tests/bug52981.phpt
@@ -0,0 +1,23 @@
+--TEST--

+Bug #52981 (Unicode properties are outdated (from Unicode 3.2))

+--SKIPIF--

+<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>

+--FILE--

+<?php

+function test($str)

+{

+	$upper = mb_strtoupper($str, 'UTF-8');

+	$len = strlen($upper);

+	for ($i = 0; $i < $len; ++$i) echo dechex(ord($upper[$i])) . ' ';

+	echo "\n";

+}

+

+// OK

+test("\xF0\x90\x90\xB8");// U+10438 DESERET SMALL LETTER H (added in 3.1.0, March 2001)

+// not OK

+test("\xE2\xB0\xB0");	// U+2C30 GLAGOLITIC SMALL LETTER AZU (added in 4.1.0, March 2005)

+test("\xD4\xA5");		// U+0525 CYRILLIC SMALL LETTER PE WITH DESCENDER (added in 5.2.0, October 2009)

+--EXPECTF--

+f0 90 90 90 

+e2 b0 80 

+d4 a4