1
0
mirror of https://github.com/php/php-src.git synced 2026-04-24 16:38:25 +02:00
Files
archived-php-src/ext/mbstring/tests/mb_ereg_variation6.phpt
T
Peter Kokot b746e69887 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 04:32:30 +02:00

193 lines
3.5 KiB
PHP

--TEST--
Test mb_ereg() function : usage variations - match special characters
--SKIPIF--
<?php
extension_loaded('mbstring') or die('skip');
function_exists('mb_ereg') or die("skip mb_ereg() is not available in this build");
?>
--FILE--
<?php
/* Prototype : int mb_ereg(string $pattern, string $string [, array $registers])
* Description: Regular expression match for multibyte string
* Source code: ext/mbstring/php_mbregex.c
*/
/*
* Test how mb_ereg() matches special characters for $pattern
*/
echo "*** Testing mb_ereg() : usage variations ***\n";
if(mb_regex_encoding('utf-8') == true) {
echo "Regex encoding set to utf-8\n";
} else {
echo "Could not set regex encoding to utf-8\n";
}
$regex_char = array ('\w+' => '\w+',
'\W+' => '\W+',
'\s+' => '\s+',
'\S+' => '\S+',
'\d+' => '\d+',
'\D+' => '\D+',
'\b' => '\b',
'\B' => '\B');
$string_ascii = 'This is an English string. 0123456789.';
$string_mb = base64_decode('5pel5pys6Kqe44OG44Kt44K544OI44Gn44GZ44CCMDEyMzTvvJXvvJbvvJfvvJjvvJnjgII=');
foreach ($regex_char as $displayChar => $char) {
echo "\n--** Pattern is: $displayChar **--\n";
if (@$regs_ascii || @$regs_mb) {
$regs_ascii = null;
$regs_mb = null;
}
echo "-- ASCII String: --\n";
var_dump(mb_ereg($char, $string_ascii, $regs_ascii));
base64_encode_var_dump($regs_ascii);
echo "-- Multibyte String: --\n";
var_dump(mb_ereg($char, $string_mb, $regs_mb));
base64_encode_var_dump($regs_mb);
}
/**
* replicate a var dump of an array but outputted string values are base64 encoded
*
* @param array $regs
*/
function base64_encode_var_dump($regs) {
if ($regs) {
echo "array(" . count($regs) . ") {\n";
foreach ($regs as $key => $value) {
echo " [$key]=>\n ";
if (is_string($value)) {
var_dump(base64_encode($value));
} else {
var_dump($value);
}
}
echo "}\n";
} else {
echo "NULL\n";
}
}
echo "Done";
?>
--EXPECT--
*** Testing mb_ereg() : usage variations ***
Regex encoding set to utf-8
--** Pattern is: \w+ **--
-- ASCII String: --
int(4)
array(1) {
[0]=>
string(8) "VGhpcw=="
}
-- Multibyte String: --
int(27)
array(1) {
[0]=>
string(36) "5pel5pys6Kqe44OG44Kt44K544OI44Gn44GZ"
}
--** Pattern is: \W+ **--
-- ASCII String: --
int(1)
array(1) {
[0]=>
string(4) "IA=="
}
-- Multibyte String: --
int(3)
array(1) {
[0]=>
string(4) "44CC"
}
--** Pattern is: \s+ **--
-- ASCII String: --
int(1)
array(1) {
[0]=>
string(4) "IA=="
}
-- Multibyte String: --
bool(false)
NULL
--** Pattern is: \S+ **--
-- ASCII String: --
int(4)
array(1) {
[0]=>
string(8) "VGhpcw=="
}
-- Multibyte String: --
int(53)
array(1) {
[0]=>
string(72) "5pel5pys6Kqe44OG44Kt44K544OI44Gn44GZ44CCMDEyMzTvvJXvvJbvvJfvvJjvvJnjgII="
}
--** Pattern is: \d+ **--
-- ASCII String: --
int(10)
array(1) {
[0]=>
string(16) "MDEyMzQ1Njc4OQ=="
}
-- Multibyte String: --
int(20)
array(1) {
[0]=>
string(28) "MDEyMzTvvJXvvJbvvJfvvJjvvJk="
}
--** Pattern is: \D+ **--
-- ASCII String: --
int(27)
array(1) {
[0]=>
string(36) "VGhpcyBpcyBhbiBFbmdsaXNoIHN0cmluZy4g"
}
-- Multibyte String: --
int(30)
array(1) {
[0]=>
string(40) "5pel5pys6Kqe44OG44Kt44K544OI44Gn44GZ44CC"
}
--** Pattern is: \b **--
-- ASCII String: --
int(1)
array(1) {
[0]=>
bool(false)
}
-- Multibyte String: --
int(1)
array(1) {
[0]=>
bool(false)
}
--** Pattern is: \B **--
-- ASCII String: --
int(1)
array(1) {
[0]=>
bool(false)
}
-- Multibyte String: --
int(1)
array(1) {
[0]=>
bool(false)
}
Done