php-src/ext/mbstring/tests/mb_detect_encoding.phpt
Peter Kokot d679f02295 Sync leading and final newlines in *.phpt sections
This patch adds missing newlines, trims multiple redundant final
newlines into a single one, and trims redundant leading newlines in all
*.phpt sections.

According to POSIX, a line is a sequence of zero or more non-' <newline>'
characters plus a terminating '<newline>' character. [1] Files should
normally have at least one final newline character.

C89 [2] and later standards [3] mention a final newline:
"A source file that is not empty shall end in a new-line character,
which shall not be immediately preceded by a backslash character."

Although it is not mandatory for all files to have a final newline
fixed, a more consistent and homogeneous approach brings less of commit
differences issues and a better development experience in certain text
editors and IDEs.

[1] http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap03.html#tag_03_206
[2] https://port70.net/~nsz/c/c89/c89-draft.html#2.1.1.2
[3] https://port70.net/~nsz/c/c99/n1256.html#5.1.1.2
2018-10-15 04:33:09 +02:00

119 lines
2.4 KiB
PHP
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

--TEST--
mb_detect_encoding()
--SKIPIF--
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
--INI--
mbstring.language=Japanese
--FILE--
<?php
// TODO: Add more tests
//$debug = true; // Uncomment this line to view error/warning/notice message in *.out file
ini_set('include_path', dirname(__FILE__));
include_once('common.inc');
// SJIS string (BASE64 encoded)
$sjis = base64_decode('k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==');
// JIS string (BASE64 encoded)
$jis = base64_decode('GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==');
// EUC-JP string
$euc_jp = '日本語テキストです。01234。';
// Test with sigle "form encoding"
// Note: For some reason it complains, results are differ. Not reserched.
echo "== BASIC TEST ==\n";
$s = $sjis;
$s = mb_detect_encoding($s, 'SJIS');
print("SJIS: $s\n");
$s = $jis;
$s = mb_detect_encoding($s, 'JIS');
print("JIS: $s\n");
$s = $euc_jp;
$s = mb_detect_encoding($s, 'UTF-8,EUC-JP,JIS');
print("EUC-JP: $s\n");
$s = $euc_jp;
$s = mb_detect_encoding($s, 'JIS,EUC-JP');
print("EUC-JP: $s\n");
// Using Encoding List Array
echo "== ARRAY ENCODING LIST ==\n";
$a = array(0=>'UTF-8',1=>'EUC-JP', 2=>'SJIS', 3=>'JIS');
// Note: Due to detect order, detected as UTF-8
$s = $jis;
$s = mb_detect_encoding($s, $a);
print("JIS: $s\n");
$s = $euc_jp;
$s = mb_detect_encoding($s, $a);
print("EUC-JP: $s\n");
$s = $sjis;
$s = mb_detect_encoding($s, $a);
print("SJIS: $s\n");
// Using Detect Order
echo "== DETECT ORDER ==\n";
mb_detect_order('auto');
$s = $jis;
$s = mb_detect_encoding($s);
print("JIS: $s\n");
$s = $euc_jp;
$s = mb_detect_encoding($s);
print("EUC-JP: $s\n");
$s = $sjis;
$s = mb_detect_encoding($s);
print("SJIS: $s\n");
// Invalid(?) Parameters
echo "== INVALID PARAMETER ==\n";
$s = mb_detect_encoding(1234, 'EUC-JP');
print("INT: $s\n"); // EUC-JP
$s = mb_detect_encoding('', 'EUC-JP');
print("EUC-JP: $s\n"); // SJIS
$s = $euc_jp;
$s = mb_detect_encoding($s, 'BAD');
print("BAD: $s\n"); // BAD
$s = $euc_jp;
$s = mb_detect_encoding();
print("MP: $s\n"); // Missing parameter
?>
--EXPECT--
== BASIC TEST ==
SJIS: SJIS
JIS: JIS
EUC-JP: EUC-JP
EUC-JP: EUC-JP
== ARRAY ENCODING LIST ==
JIS: UTF-8
EUC-JP: EUC-JP
SJIS: SJIS
== DETECT ORDER ==
JIS: JIS
EUC-JP: EUC-JP
SJIS: SJIS
== INVALID PARAMETER ==
INT: EUC-JP
EUC-JP: EUC-JP
ERR: Warning
BAD: EUC-JP
ERR: Warning
MP: