mirror of
https://github.com/php/php-src.git
synced 2026-04-20 14:31:06 +02:00
51b9d7a5e1
After mb_substitute_character("long"), mbstring will respond to
erroneous input by inserting 'long' error markers into the output.
Depending on the situation, these error markers will either look like
BAD+XXXX (for general bad input), U+XXXX (when the input is OK, but it
converts to Unicode codepoints which cannot be represented in the
output encoding), or an encoding-specific marker like JISX+XXXX or
W932+XXXX.
We have almost no tests for this feature. Add a bunch of tests to
ensure that all our legacy encoding handlers work in a reasonable
way when 'long' error markers are enabled.
50 lines
1.7 KiB
PHP
50 lines
1.7 KiB
PHP
--TEST--
|
|
Exhaustive test of verification and conversion of Big5 text
|
|
--EXTENSIONS--
|
|
mbstring
|
|
--SKIPIF--
|
|
<?php
|
|
if (getenv("SKIP_SLOW_TESTS")) die("skip slow test");
|
|
?>
|
|
--FILE--
|
|
<?php
|
|
include('encoding_tests.inc');
|
|
srand(1000); // Make results consistent
|
|
mb_substitute_character(0x25); // '%'
|
|
readConversionTable(__DIR__ . '/data/BIG5.txt', $toUnicode, $fromUnicode);
|
|
|
|
// Non-reversible mappings (two different BIG5 codepoints map to same Unicode codepoint)
|
|
$fromUnicode["\x25\x50"] = "\xA2\xA4";
|
|
$fromUnicode["\x25\x5E"] = "\xA2\xA5";
|
|
$fromUnicode["\x25\x61"] = "\xA2\xA7";
|
|
$fromUnicode["\x25\x6A"] = "\xA2\xA6";
|
|
$fromUnicode["\x25\x6D"] = "\xA2\x7E";
|
|
$fromUnicode["\x25\x6E"] = "\xA2\xA1";
|
|
$fromUnicode["\x25\x6F"] = "\xA2\xA3";
|
|
$fromUnicode["\x25\x70"] = "\xA2\xA2";
|
|
|
|
findInvalidChars($toUnicode, $invalid, $truncated);
|
|
testAllValidChars($toUnicode, 'BIG5', 'UTF-16BE', false);
|
|
testAllInvalidChars($invalid, $toUnicode, 'BIG5', 'UTF-16BE', "\x00%");
|
|
testTruncatedChars($truncated, 'BIG5', 'UTF-16BE', "\x00%");
|
|
echo "Tested BIG5 -> UTF-16BE\n";
|
|
|
|
testAllValidChars($fromUnicode, 'UTF-16BE', 'BIG5', false);
|
|
findInvalidChars($fromUnicode, $invalid, $unused, array_fill_keys(range(0,0xFF), 2));
|
|
convertAllInvalidChars($invalid, $fromUnicode, 'UTF-16BE', 'BIG5', '%');
|
|
echo "Tested UTF-16BE -> BIG5\n";
|
|
|
|
// Test "long" illegal character markers
|
|
mb_substitute_character("long");
|
|
convertInvalidString("\x80", "BAD+80", "BIG5", "UTF-8");
|
|
convertInvalidString("\xB0\x9F", "BAD+B09F", "BIG5", "UTF-8");
|
|
convertInvalidString("\xA3\xED", "?+A3ED", "BIG5", "UTF-8");
|
|
convertInvalidString("\x76\x54", "U+7654", "UTF-16BE", "BIG5");
|
|
|
|
echo "Done!\n";
|
|
?>
|
|
--EXPECT--
|
|
Tested BIG5 -> UTF-16BE
|
|
Tested UTF-16BE -> BIG5
|
|
Done!
|