Add test for surrogate half encoding

hikari-no-yume · hikari-no-yume · commit aba051e2f7a8 · 2015-01-04T15:32:27.000Z
diff --git a/tests/lexical_structure/unicode_string_escape_sequence/unicode_escape_surrogates.php b/tests/lexical_structure/unicode_string_escape_sequence/unicode_escape_surrogates.php
@@ -0,0 +1,8 @@
+<?php
+
+// Surrogate pairs are non-well-formed UTF-8 - however, it is sometimes useful
+// to be able to produce these (e.g. CESU-8 handling)
+
+var_dump(bin2hex("\u{D801}"));
+var_dump(bin2hex("\u{DC00}"));
+var_dump(bin2hex("\u{D801}\u{DC00}")); // CESU-8 encoding of U+10400
diff --git a/tests/lexical_structure/unicode_string_escape_sequence/unicode_escape_surrogates.php.expect b/tests/lexical_structure/unicode_string_escape_sequence/unicode_escape_surrogates.php.expect
@@ -0,0 +1,3 @@
+string(6) "eda081"
+string(6) "edb080"
+string(12) "eda081edb080"
