Util/Punycode.php

Classes: Kwf_Util_Punycode

\Kwf_Util_Punycode
jump to top

author: Matthias Sommerfeld <mso@phlylabs.de>
author: Leonid Kogan <lko@neuse.de>
copyright: 2004-2010 phlyLabs Berlin, http://phlylabs.de
version: 0.6.9 2010-11-04
Properties: $NP; $_allow_overlong; $_api_encoding; $_base; $_damp; $_encode_german_sz; $_error; $_initial_bias; $_initial_n; $_invalid_ucs; $_lbase; $_lcount; $_max_ucs; $_ncount; $_punycode_prefix; $_sbase; $_scount; $_skew; $_strict_mode; $_tbase; $_tcount; $_tmax; $_tmin; $_vbase; $_vcount
Methods: __construct; _adapt; _apply_cannonical_ordering; _combine; _decode; _decode_digit; _encode; _encode_digit; _error; _get_combining_class; _hangul_compose; _hangul_decompose; _nameprep; _ucs4_string_to_ucs4; _ucs4_to_ucs4_string; _ucs4_to_utf8; _utf8_to_ucs4; decode; encode; encode_uri; get_last_error; set_parameter

Description

Encode/decode Internationalized Domain Names.

The class allows to convert internationalized domain names (see RFC 3490 for details) as they can be used with various registries worldwide to be translated between their original (localized) form and their encoded form as it will be used in the DNS (Domain Name System).

The class provides two public methods, encode() and decode(), which do exactly what you would expect them to do. You are allowed to use complete domain names, simple strings and complete email addresses as well. That means, that you might use any of the following notations:

www.nörgler.com
xn--nrgler-wxa
xn--brse-5qa.xn--knrz-1ra.info

Unicode input might be given as either UTF-8 string, UCS-4 string or UCS-4 array. Unicode output is available in the same formats. You can select your preferred format via {@link set_paramter()}.

ACE input and output is always expected to be ASCII.

Properties

$NP
jump to class

$NP = 'array'

Holds all relevant mapping tables See RFC3454 for details

Details

visibility: protected
default: array
final: false
static: false
private: array
since: 0.5.2

$_allow_overlong
jump to class

$_allow_overlong = 'false'

Details

visibility: protected
default: false
final: false
static: false

$_api_encoding
jump to class

$_api_encoding = 'utf8'

Details

visibility: protected
default: utf8
final: false
static: false

$_base
jump to class

$_base = '36'

Details

visibility: protected
default: 36
final: false
static: false

$_damp
jump to class

$_damp = '700'

Details

visibility: protected
default: 700
final: false
static: false

$_encode_german_sz
jump to class

$_encode_german_sz = 'true'

Details

visibility: protected
default: true
final: false
static: false

$_error
jump to class

$_error = 'false'

Details

visibility: protected
default: false
final: false
static: false

$_initial_bias
jump to class

$_initial_bias = '72'

Details

visibility: protected
default: 72
final: false
static: false

$_initial_n
jump to class

$_initial_n = '0x80'

Details

visibility: protected
default: 0x80
final: false
static: false

$_invalid_ucs
jump to class

$_invalid_ucs = '0x80000000'

Details

visibility: protected
default: 0x80000000
final: false
static: false

$_lbase
jump to class

$_lbase = '0x1100'

Details

visibility: protected
default: 0x1100
final: false
static: false

$_lcount
jump to class

$_lcount = '19'

Details

visibility: protected
default: 19
final: false
static: false

$_max_ucs
jump to class

$_max_ucs = '0x10FFFF'

Details

visibility: protected
default: 0x10FFFF
final: false
static: false

$_ncount
jump to class

$_ncount = '588'

Details

visibility: protected
default: 588
final: false
static: false

$_punycode_prefix
jump to class

$_punycode_prefix = 'xn--'

Details

visibility: protected
default: xn--
final: false
static: false

$_sbase
jump to class

$_sbase = '0xAC00'

Details

visibility: protected
default: 0xAC00
final: false
static: false

$_scount
jump to class

$_scount = '11172'

Details

visibility: protected
default: 11172
final: false
static: false

$_skew
jump to class

$_skew = '38'

Details

visibility: protected
default: 38
final: false
static: false

$_strict_mode
jump to class

$_strict_mode = 'false'

Details

visibility: protected
default: false
final: false
static: false

$_tbase
jump to class

$_tbase = '0x11A7'

Details

visibility: protected
default: 0x11A7
final: false
static: false

$_tcount
jump to class

$_tcount = '28'

Details

visibility: protected
default: 28
final: false
static: false

$_tmax
jump to class

$_tmax = '26'

Details

visibility: protected
default: 26
final: false
static: false

$_tmin
jump to class

$_tmin = '1'

Details

visibility: protected
default: 1
final: false
static: false

$_vbase
jump to class

$_vbase = '0x1161'

Details

visibility: protected
default: 0x1161
final: false
static: false

$_vcount
jump to class

$_vcount = '21'

Details

visibility: protected
default: 21
final: false
static: false

Methods

__construct
jump to class

__construct(
          array $options
              =
              false
          )
        
        :
        boolean

the constructor

Arguments

$options: array

Output

boolean

Details

visibility: public
final: false
static: false
since: 0.5.2

_adapt
jump to class

_adapt(
          int $delta, int $npoints, int $is_first
          )
        
        :
        int

Adapt the bias according to the current code point and position

Arguments

$delta: int
$npoints: int
$is_first: int

Output

int

Details

visibility: protected
final: false
static: false

_apply_cannonical_ordering
jump to class

_apply_cannonical_ordering(
          array $input
          )
        
        :
        array

Apllies the cannonical ordering of a decomposed UCS4 sequence

Arguments

$input: array
Decomposed UCS4 sequence

Output

array: Ordered USC4 sequence

Details

visibility: protected
final: false
static: false

_combine
jump to class

_combine(
          array $input
          )
        
        :
        array

Do composition of a sequence of starter and non-starter

Arguments

$input: array
UCS4 Decomposed sequence

Output

array: Ordered USC4 sequence

Details

visibility: protected
final: false
static: false

_decode
jump to class

_decode(
           $encoded
          )
        
        :
        mixed

The actual decoding algorithm

Arguments

$encoded: string

Output

mixed

Details

visibility: protected
final: false
static: false

_decode_digit
jump to class

_decode_digit(
          int $cp
          )
        
        :
        int

Decode a certain digit

Arguments

$cp: int

Output

int

Details

visibility: protected
final: false
static: false

_encode
jump to class

_encode(
           $decoded
          )
        
        :
        mixed

The actual encoding algorithm

Arguments

$decoded: string

Output

mixed

Details

visibility: protected
final: false
static: false

_encode_digit
jump to class

_encode_digit(
          int $d
          )
        
        :
        string

Encoding a certain digit

Arguments

$d: int

Output

string

Details

visibility: protected
final: false
static: false

_error
jump to class

_error(
          string $error
          )
        
        :

Internal error handling method

Arguments

$error: string

Details

visibility: protected
final: false
static: false

_get_combining_class
jump to class

_get_combining_class(
          integer $char
          )
        
        :
        integer

Returns the combining class of a certain wide char

Arguments

$char: integer
Wide char to check (32bit integer)

Output

integer: Combining class if found, else 0

Details

visibility: protected
final: false
static: false

_hangul_compose
jump to class

_hangul_compose(
          array $input
          )
        
        :
        array

Ccomposes a Hangul syllable (see http://www.unicode.org/unicode/reports/tr15/#Hangul

Arguments

$input: array
Decomposed UCS4 sequence

Output

array: UCS4 sequence with syllables composed

Details

visibility: protected
final: false
static: false

_hangul_decompose
jump to class

_hangul_decompose(
          integer $char
          )
        
        :
        array

Decomposes a Hangul syllable (see http://www.unicode.org/unicode/reports/tr15/#Hangul

Arguments

$char: integer
32bit UCS4 code point

Output

array: Either Hangul Syllable decomposed or original 32bit value as one value array

Details

visibility: protected
final: false
static: false

_nameprep
jump to class

_nameprep(
          array $input
          )
        
        :
        string

Do Nameprep according to RFC3491 and RFC3454

Arguments

$input: array
Unicode Characters

Output

string: Unicode Characters, Nameprep'd

Details

visibility: protected
final: false
static: false

_ucs4_string_to_ucs4
jump to class

_ucs4_string_to_ucs4(
          string $input
          )
        
        :
        array

Convert UCS-4 strin into UCS-4 garray

Arguments

$input: string

Output

array

Details

visibility: protected
final: false
static: false

_ucs4_to_ucs4_string
jump to class

_ucs4_to_ucs4_string(
          array $input
          )
        
        :
        string

Convert UCS-4 array into UCS-4 string

Arguments

$input: array

Output

string

Details

visibility: protected
final: false
static: false

_ucs4_to_utf8
jump to class

_ucs4_to_utf8(
          string $input
          )
        
        :
        string

Convert UCS-4 string into UTF-8 string See _utf8_to_ucs4() for details

Arguments

$input: string

Output

string

Details

visibility: protected
final: false
static: false

_utf8_to_ucs4
jump to class

_utf8_to_ucs4(
          string $input
          )
        
        :
        string

This converts an UTF-8 encoded string to its UCS-4 representation By talking about UCS-4 "strings" we mean arrays of 32bit integers representing each of the "chars". This is due to PHP not being able to handle strings with bit depth different from 8. This apllies to the reverse method _ucs4_to_utf8(), too.

The following UTF-8 encodings are supported: bytes bits representation 1 7 0xxxxxxx 2 11 110xxxxx 10xxxxxx 3 16 1110xxxx 10xxxxxx 10xxxxxx 4 21 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 5 26 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 6 31 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx Each x represents a bit that can be used to store character data. The five and six byte sequences are part of Annex D of ISO/IEC 10646-1:2000

Arguments

$input: string

Output

string

Details

visibility: protected
final: false
static: false

decode
jump to class

decode(
          string $input,  $one_time_encoding
              =
              false
          )
        
        :
        string

Decode a given ACE domain name

Arguments

$input: string
Domain name (ACE string) [@param string Desired output encoding, see {@link set_parameter}]
$one_time_encoding

Output

string: Decoded Domain name (UTF-8 or UCS-4)

Details

visibility: public
final: false
static: false

encode
jump to class

encode(
          string $decoded,  $one_time_encoding
              =
              false
          )
        
        :
        string

Encode a given UTF-8 domain name

Arguments

$decoded: string
Domain name (UTF-8 or UCS-4) [@param string Desired input encoding, see {@link set_parameter}]
$one_time_encoding

Output

string: Encoded Domain name (ACE string)

Details

visibility: public
final: false
static: false

encode_uri
jump to class

encode_uri(
          string $uri
          )
        
        :
        string

Removes a weakness of encode(), which cannot properly handle URIs but instead encodes their path or query components, too.

Arguments

$uri: string
Expects the URI as a UTF-8 (or ASCII) string

Output

string: The URI encoded to Punycode, everything but the host component is left alone

Details

visibility: public
final: false
static: false
since: 0.6.4

get_last_error
jump to class

get_last_error(
          
          )
        
        :
        string

Use this method to get the last error ocurred

Output

string: The last error, that occured

Details

visibility: public
final: false
static: false

set_parameter
jump to class

set_parameter(
          mixed $option, string $value
              =
              false
          )
        
        :
        boolean

Sets a new option value. Available options and values: [encoding - Use either UTF-8, UCS4 as array or UCS4 as string as input ('utf8' for UTF-8, 'ucs4_string' and 'ucs4_array' respectively for UCS4); The output is always UTF-8] [overlong - Unicode does not allow unnecessarily long encodings of chars, to allow this, set this parameter to true, else to false; default is false.] [strict - true: strict mode, good for registration purposes - Causes errors on failures; false: loose mode, ideal for "wildlife" applications by silently ignoring errors and returning the original input instead

Arguments

$option: mixed
Parameter to set (string: single parameter; array of Parameter => Value pairs)
$value: string
Value to use (if parameter 1 is a string)

Output

boolean: true on success, false otherwise

Details

visibility: public
final: false
static: false

Util/Punycode.php

\Kwf_Util_Punycodejump to top

Description

Properties

$NPjump to class

Details

$_allow_overlongjump to class

Details

$_api_encodingjump to class

Details

$_basejump to class

Details

$_dampjump to class

Details

$_encode_german_szjump to class

Details

$_errorjump to class

Details

$_initial_biasjump to class

Details

$_initial_njump to class

Details

$_invalid_ucsjump to class

Details

$_lbasejump to class

Details

$_lcountjump to class

Details

$_max_ucsjump to class

Details

$_ncountjump to class

Details

$_punycode_prefixjump to class

Details

$_sbasejump to class

Details

$_scountjump to class

Details

$_skewjump to class

Details

$_strict_modejump to class

Details

$_tbasejump to class

Details

$_tcountjump to class

Details

$_tmaxjump to class

Details

$_tminjump to class

Details

$_vbasejump to class

Details

$_vcountjump to class

Details

Methods

__constructjump to class

Arguments

Output

Details

_adaptjump to class

Arguments

Output

Details

_apply_cannonical_orderingjump to class

Arguments

Output

Details

_combinejump to class

Arguments

Output

Details

_decodejump to class

Arguments

Output

Details

_decode_digitjump to class

Arguments

Output

Details

_encodejump to class

\Kwf_Util_Punycode
jump to top

$NP
jump to class

$_allow_overlong
jump to class

$_api_encoding
jump to class

$_base
jump to class

$_damp
jump to class

$_encode_german_sz
jump to class

$_error
jump to class

$_initial_bias
jump to class

$_initial_n
jump to class

$_invalid_ucs
jump to class

$_lbase
jump to class

$_lcount
jump to class

$_max_ucs
jump to class

$_ncount
jump to class

$_punycode_prefix
jump to class

$_sbase
jump to class

$_scount
jump to class

$_skew
jump to class

$_strict_mode
jump to class

$_tbase
jump to class

$_tcount
jump to class

$_tmax
jump to class

$_tmin
jump to class

$_vbase
jump to class

$_vcount
jump to class

__construct
jump to class

_adapt
jump to class

_apply_cannonical_ordering
jump to class

_combine
jump to class

_decode
jump to class

_decode_digit
jump to class

_encode
jump to class

_encode_digit
jump to class

_error
jump to class

_get_combining_class
jump to class

_hangul_compose
jump to class

_hangul_decompose
jump to class

_nameprep
jump to class

_ucs4_string_to_ucs4
jump to class

_ucs4_to_ucs4_string
jump to class

_ucs4_to_utf8
jump to class

_utf8_to_ucs4
jump to class

decode
jump to class

encode
jump to class

encode_uri
jump to class

get_last_error
jump to class

set_parameter
jump to class