File: ucs4_encoding.phpt

package info (click to toggle)
php8.4 8.4.11-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 208,108 kB
  • sloc: ansic: 1,060,628; php: 35,345; sh: 11,866; cpp: 7,201; pascal: 4,913; javascript: 3,091; asm: 2,810; yacc: 2,411; makefile: 689; xml: 446; python: 301; awk: 148
file content (39 lines) | stat: -rw-r--r-- 1,502 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
--TEST--
Test verification and conversion of UCS-4 text
--EXTENSIONS--
mbstring
--FILE--
<?php
include('encoding_tests.inc');
mb_substitute_character(0x25);

testValidString("\xFF\xFE\x00\x00\x00\x30\x00\x00", "\x30\x00", "UCS-4", "UTF-16BE", false);
testValidString("\x00\x00\xFE\xFF\x00\x00\x30\x01", "\x30\x01", "UCS-4", "UTF-16BE", false);
testValidString("\x02\x30\x00\x00", "\x30\x02", "UCS-4LE", "UTF-16BE");
testValidString("\x00\x00\x30\x03", "\x30\x03", "UCS-4BE", "UTF-16BE");

// Truncated input
convertInvalidString("\x01\x02\x03", "%", "UCS-4", "UTF-8");


// Codepoint above U+10FFFF
convertInvalidString("\x00\x11\x00\x00", "%", "UCS-4BE", "UTF-8");
convertInvalidString("\x00\x00\x11\x00", "%", "UCS-4LE", "UTF-8");

// Test "long" illegal character markers
mb_substitute_character("long");
convertInvalidString("\x6F\x00\x00\x00", "U+6F000000", "UCS-4BE", "UTF-8");
convertInvalidString("\x70\x00\x00\x00", "U+70000000", "UCS-4BE", "UTF-8");
convertInvalidString("\x78\x00\x00\x01", "U+78000001", "UCS-4BE", "UTF-8");
convertInvalidString("\x80\x01\x02\x03", "U+80010203", "UCS-4BE", "UTF-8");
convertInvalidString("\x00\x01\x02", "%", "UCS-4BE", "UTF-8");

convertInvalidString("\x00\x00\x00\x6F", "U+6F000000", "UCS-4LE", "UTF-8");
convertInvalidString("\x00\x00\x00\x70", "U+70000000", "UCS-4LE", "UTF-8");
convertInvalidString("\x01\x00\x00\x78", "U+78000001", "UCS-4LE", "UTF-8");
convertInvalidString("\x02\x01\x00", "%", "UCS-4LE", "UTF-8");

echo "Done!";
?>
--EXPECT--
Done!