FilesExpand file tree

 develop

/

unicode_testing.php

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

118 lines (109 loc) · 2.67 KB

 develop

/

unicode_testing.php

Copy path

Top

File metadata and controls

• Code
• Blame

118 lines (109 loc) · 2.67 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

<?php

//

// This file provides some useful functions for debugging the unicode/UTF-8 library

// It requires utf_tools.php to be loaded

//

die("Please read the first lines of this script for instructions on how to enable it");

if (!headers_sent())

{

header('Content-type: text/html; charset=UTF-8');

}

/**

* Converts unicode escape sequences (\u0123) into UTF-8 characters

*

* @param string A unicode sequence

* @return string UTF-8 representation of the given unicode sequence

*/

function unicode_to_utf8($string)

{

$utf8 = '';

$chars = array();

for ($i = 0; $i < strlen($string); $i++)

{

if (isset($string[$i + 5]) && substr($string, $i, 2) == '\\u' && ctype_xdigit(substr($string, $i + 2, 4)))

{

$utf8 .= utf8_from_unicode(array(base_convert(substr($string, $i + 2, 4), 16, 10)));

$i += 5;

}

else

{

$utf8 .= $string[$i];

}

}

return $utf8;

}

/**

* Takes an array of ints representing the Unicode characters and returns

* a UTF-8 string.

*

* @param array $array array of unicode code points representing a string

* @return string UTF-8 character string

*/

function utf8_from_unicode($array)

{

$str = '';

foreach ($array as $value)

{

$str .= utf8_chr($value);

}

return $str;

}

/**

* Converts a UTF-8 string to unicode code points

*

* @param string $text UTF-8 string

* @return string Unicode code points

*/

function utf8_to_unicode($text)

{

return preg_replace_callback(

'#[\\xC2-\\xF4][\\x80-\\xBF]?[\\x80-\\xBF]?[\\x80-\\xBF]#',

'utf8_to_unicode_callback',

preg_replace_callback(

'#[\\x00-\\x7f]#',

'utf8_to_unicode_callback',

$text

)

);

}

/**

* Takes a UTF-8 char and replaces it with its unicode escape sequence. Attention, $m is an array

*

* @param array $m 0-based numerically indexed array passed by preg_replace_callback()

* @return string A unicode escape sequence

*/

function utf8_to_unicode_callback($m)

{

return '\u' . str_pad(base_convert(utf8_ord($m[0]), 10, 16), 4, '0', STR_PAD_LEFT) . '';

}

/**

* A wrapper function for the normalizer which takes care of including the class if required and modifies the passed strings

* to be in NFKC

*

* @param mixed $strings a string or an array of strings to normalize

* @return mixed the normalized content, preserving array keys if array given.

*/

function utf8_normalize_nfkc($strings)

{

if (empty($strings))

{

return $strings;

}

if (!class_exists('utf_normalizer'))

{

global $phpbb_root_path, $phpEx;

include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx);

}

if (!is_array($strings))

{

utf_normalizer::nfkc($strings);

}

else if (is_array($strings))

{

foreach ($strings as $key => $string)

{

utf_normalizer::nfkc($strings[$key]);

}

}

return $strings;

}