| 1 | #!./perl |
| 2 | |
| 3 | BEGIN { |
| 4 | chdir 't' if -d 't'; |
| 5 | @INC = qw(. ../lib); # ../lib needed for test.deparse |
| 6 | require "test.pl"; |
| 7 | } |
| 8 | |
| 9 | plan tests => 35; |
| 10 | |
| 11 | # compile time evaluation |
| 12 | |
| 13 | # 'A' 65 ASCII |
| 14 | # 'A' 193 EBCDIC |
| 15 | |
| 16 | ok(ord('A') == 65 || ord('A') == 193, "ord('A') is ".ord('A')); |
| 17 | |
| 18 | is(ord(chr(500)), 500, "compile time chr 500"); |
| 19 | |
| 20 | # run time evaluation |
| 21 | |
| 22 | $x = 'ABC'; |
| 23 | |
| 24 | ok(ord($x) == 65 || ord($x) == 193, "ord('$x') is ".ord($x)); |
| 25 | |
| 26 | ok(chr 65 eq 'A' || chr 193 eq 'A', "chr can produce 'A'"); |
| 27 | |
| 28 | $x = 500; |
| 29 | is(ord(chr($x)), $x, "runtime chr $x"); |
| 30 | |
| 31 | is(ord("\x{1234}"), 0x1234, 'compile time ord \x{....}'); |
| 32 | |
| 33 | $x = "\x{1234}"; |
| 34 | is(ord($x), 0x1234, 'runtime ord \x{....}'); |
| 35 | |
| 36 | { |
| 37 | no warnings 'utf8'; # avoid Unicode warnings |
| 38 | |
| 39 | # The following code points are some interesting steps. |
| 40 | is(ord(chr( 0x100)), 0x100, '0x0100'); |
| 41 | is(ord(chr( 0x3FF)), 0x3FF, 'last two-byte char in UTF-EBCDIC'); |
| 42 | is(ord(chr( 0x400)), 0x400, 'first three-byte char in UTF-EBCDIC'); |
| 43 | is(ord(chr( 0x7FF)), 0x7FF, 'last two-byte char in UTF-8'); |
| 44 | is(ord(chr( 0x800)), 0x800, 'first three-byte char in UTF-8'); |
| 45 | is(ord(chr( 0xFFF)), 0xFFF, '0x0FFF'); |
| 46 | is(ord(chr( 0x1000)), 0x1000, '0x1000'); |
| 47 | is(ord(chr( 0x3FFF)), 0x3FFF, 'last three-byte char in UTF-EBCDIC'); |
| 48 | is(ord(chr( 0x4000)), 0x4000, 'first four-byte char in UTF-EBCDIC'); |
| 49 | is(ord(chr( 0xCFFF)), 0xCFFF, '0xCFFF'); |
| 50 | is(ord(chr( 0xD000)), 0xD000, '0xD000'); |
| 51 | is(ord(chr( 0xD7FF)), 0xD7FF, '0xD7FF'); |
| 52 | is(ord(chr( 0xD800)), 0xD800, 'surrogate begin (not strict utf-8)'); |
| 53 | is(ord(chr( 0xDFFF)), 0xDFFF, 'surrogate end (not strict utf-8)'); |
| 54 | is(ord(chr( 0xE000)), 0xE000, '0xE000'); |
| 55 | is(ord(chr( 0xFDD0)), 0xFDD0, 'first additional noncharacter in BMP'); |
| 56 | is(ord(chr( 0xFDEF)), 0xFDEF, 'last additional noncharacter in BMP'); |
| 57 | is(ord(chr( 0xFFFE)), 0xFFFE, '0xFFFE'); |
| 58 | is(ord(chr( 0xFFFF)), 0xFFFF, 'last three-byte char in UTF-8'); |
| 59 | is(ord(chr( 0x10000)), 0x10000, 'first four-byte char in UTF-8'); |
| 60 | is(ord(chr( 0x3FFFF)), 0x3FFFF, 'last four-byte char in UTF-EBCDIC'); |
| 61 | is(ord(chr( 0x40000)), 0x40000, 'first five-byte char in UTF-EBCDIC'); |
| 62 | is(ord(chr( 0xFFFFF)), 0xFFFFF, '0xFFFFF'); |
| 63 | is(ord(chr(0x100000)), 0x100000, '0x100000'); |
| 64 | is(ord(chr(0x10FFFF)), 0x10FFFF, 'Unicode last code point'); |
| 65 | is(ord(chr(0x110000)), 0x110000, '0x110000'); |
| 66 | is(ord(chr(0x1FFFFF)), 0x1FFFFF, 'last four-byte char in UTF-8'); |
| 67 | is(ord(chr(0x200000)), 0x200000, 'first five-byte char in UTF-8'); |
| 68 | } |