» Javascript equivalent for PHP's html_entity_decode
399 PHP equivalents
- PHP.JS Licensing
- PHP.JS SVN
- PHP.JS Namespaced
- abs
- acosh
- acos
- addslashes
- aggregate
- aggregate_info
- aggregate_methods
- aggregate_methods_by_list
- aggregate_methods_by_regexp
- aggregate_properties
- aggregate_properties_by_list
- aggregate_properties_by_regexp
- aggregation_info
- array
- array_change_key_case
- array_chunk
- array_combine
- array_count_values
- array_diff
- array_diff_assoc
- array_diff_key
- array_diff_uassoc
- array_diff_ukey
- array_fill
- array_fill_keys
- array_filter
- array_flip
- array_intersect
- array_intersect_assoc
- array_intersect_key
- array_intersect_uassoc
- array_intersect_ukey
- array_keys
- array_key_exists
- array_map
- array_merge
- array_merge_recursive
- array_multisort
- array_pad
- array_pop
- array_product
- array_push
- array_rand
- array_reduce
- array_reverse
- array_search
- array_shift
- array_slice
- array_splice
- array_sum
- array_udiff
- array_udiff_assoc
- array_udiff_uassoc
- array_uintersect
- array_uintersect_assoc
- array_uintersect_uassoc
- array_unique
- array_unshift
- array_values
- array_walk
- array_walk_recursive
- arsort
- asinh
- asin
- asort
- assert
- assert_options
- atan2
- atanh
- atan
- base64_decode
- base64_encode
- basename
- base_convert
- bin2hex
- bindec
- call_user_func
- call_user_func_array
- ceil
- checkdate
- chop
- chr
- chunk_split
- classkit_import
- classkit_method_add
- classkit_method_copy
- classkit_method_redefine
- classkit_method_remove
- classkit_method_rename
- class_exists
- compact
- constant
- convert_uuencode
- cosh
- cos
- count
- count_chars
- crc32
- create_function
- ctype_alnum
- ctype_alpha
- ctype_cntrl
- ctype_digit
- ctype_graph
- ctype_lower
- ctype_print
- ctype_punct
- ctype_space
- ctype_upper
- ctype_xdigit
- current
- date
- date_default_timezone_get
- date_default_timezone_set
- date_parse
- deaggregate
- decbin
- dechex
- decoct
- defined
- define
- deg2rad
- die
- dirname
- doubleval
- each
- echo
- empty
- end
- exit
- explode
- expm1
- exp
- extract
- fclose
- feof
- fgetcsv
- fgetc
- fgetss
- fgets
- filemtime
- filesize
- file
- file_exists
- file_get_contents
- floatval
- floor
- fmod
- fopen
- fpassthru
- fread
- fseek
- ftell
- function_exists
- func_get_args
- func_get_arg
- func_num_args
- getdate
- getenv
- getlastmod
- getrandmax
- gettimeofday
- gettype
- get_cfg_var
- get_class
- get_class_methods
- get_class_vars
- get_declared_classes
- get_defined_constants
- get_defined_functions
- get_defined_vars
- get_headers
- get_html_translation_table
- get_included_files
- get_meta_tags
- get_object_vars
- get_required_files
- get_resource_type
- gmdate
- gmmktime
- gmstrftime
- gopher_parsedir
- hexdec
- htmlentities
- htmlspecialchars
- htmlspecialchars_decode
- » html_entity_decode
- http_build_query
- hypot
- idate
- implode
- import_request_variables
- include
- include_once
- ini_alter
- ini_get
- ini_get_all
- ini_restore
- ini_set
- intval
- in_array
- ip2long
- isset
- is_array
- is_binary
- is_bool
- is_buffer
- is_callable
- is_double
- is_finite
- is_float
- is_infinite
- is_integer
- is_int
- is_long
- is_nan
- is_null
- is_numeric
- is_object
- is_real
- is_resource
- is_scalar
- is_string
- is_unicode
- join
- json_decode
- json_encode
- key
- krsort
- ksort
- lcfirst
- lcg_value
- levenshtein
- localeconv
- localtime
- log10
- log1p
- log
- long2ip
- ltrim
- max
- md5
- md5_file
- method_exists
- microtime
- min
- mktime
- mt_getrandmax
- mt_rand
- natcasesort
- natsort
- next
- nl2br
- nl_langinfo
- number_format
- octdec
- ord
- parse_str
- parse_url
- pathinfo
- pclose
- phpversion
- php_ini_loaded_file
- php_ini_scanned_files
- php_strip_whitespace
- pi
- popen
- pos
- pow
- preg_grep
- preg_quote
- prev
- printf
- print_r
- property_exists
- putenv
- quoted_printable_decode
- quoted_printable_encode
- quotemeta
- rad2deg
- rand
- range
- rawurldecode
- rawurlencode
- readfile
- realpath
- register_shutdown_function
- require
- require_once
- reset
- restore_exception_handler
- rewind
- round
- rsort
- rtrim
- runkit_class_adopt
- runkit_class_emancipate
- runkit_function_add
- runkit_function_copy
- runkit_function_redefine
- runkit_function_remove
- runkit_function_rename
- runkit_import
- runkit_method_add
- runkit_method_copy
- runkit_method_redefine
- runkit_method_remove
- runkit_method_rename
- runkit_superglobals
- serialize
- setcookie
- setlocale
- setrawcookie
- settype
- set_exception_handler
- set_time_limit
- sha1
- sha1_file
- shuffle
- sinh
- sin
- sizeof
- sleep
- sort
- soundex
- split
- sprintf
- sql_regcase
- sqrt
- strcasecmp
- strchr
- strcmp
- strcoll
- strcspn
- strftime
- stripos
- stripslashes
- strip_tags
- stristr
- strlen
- strnatcasecmp
- strnatcmp
- strncasecmp
- strncmp
- strpbrk
- strpos
- strrchr
- strrev
- strripos
- strrpos
- strspn
- strstr
- strtok
- strtolower
- strtotime
- strtoupper
- strtr
- strval
- str_getcsv
- str_ireplace
- str_pad
- str_repeat
- str_replace
- str_rot13
- str_shuffle
- str_split
- str_word_count
- substr
- substr_compare
- substr_count
- substr_replace
- tanh
- tan
- timezone_abbreviations_list
- timezone_identifiers_list
- time
- time_nanosleep
- time_sleep_until
- trim
- uasort
- ucfirst
- ucwords
- uksort
- uniqid
- unserialize
- urldecode
- urlencode
- usleep
- usort
- utf8_decode
- utf8_encode
- var_dump
- var_export
- vprintf
- vsprintf
- wordwrap
PHP to Javascript Project: php.js
This article is part of the 'Porting PHP to Javascript' Project, which aims to decrease the gap between developing for PHP & Javascript.
A lot of people are familiar with PHP's functions, and though Javascript functions are often quite similar, some functions may be missing or addressed differently. The Javascript implementations should be as compliant with the PHP versions as possible, a good indication is that the PHP function manual could also apply to the Javascript version.
Porting crucial PHP functions to Javascript can be fun & useful. Currently some PHP functions have been added, but readers are encouraged to contribute and improve functions by adding comments. Eventually the goal is to save all the functions in one php.js file and make it publicly available for your coding pleasure.
If you choose to contribute, let me know how you want to be credited in the function's comments. You may also want to subscribe to RSS so you receive updates whenever new functions are posted.
This is a Javascript version of the PHP function: html_entity_decode.
I have moved out PHP.JS to it's own site. For info & reactions on comments please goto phpjs.org
PHP html_entity_decode
Description
html_entity_decode - Convert all HTML entities to their applicable characters
string html_entity_decode( string string [, int quote_style [, string charset]] )
html_entity_decode() is the opposite of htmlentities() in that it converts all HTML entities to their applicable characters from string.
Parameters
-
string
The input string.
-
quote_style
The optional second quote_style parameter lets you define what will be done with 'single' and "double" quotes. It takes on one of three constants with the default being ENT_COMPAT:
Available quote_style constants
Constant Name Description ENT_COMPAT Will convert double-quotes and leave single-quotes alone. ENT_QUOTES Will convert both double and single quotes. ENT_NOQUOTES Will leave both double and single quotes unconverted. -
charset
The ISO-8859-1 character set is used as default for the optional third charset . This defines the character set used in conversion.
Following character sets are supported in PHP 4.3.0 and later.
Supported charsets
Charset Aliases Description ISO-8859-1 ISO8859-1 Western European, Latin-1 ISO-8859-15 ISO8859-15 Western European, Latin-9. Adds the Euro sign, French and Finnish letters missing in Latin-1(ISO-8859-1). UTF-8 ASCII compatible multi-byte 8-bit Unicode. cp866 ibm866, 866 DOS-specific Cyrillic charset. This charset is supported in 4.3.2. cp1251 Windows-1251, win-1251, 1251 Windows-specific Cyrillic charset. This charset is supported in 4.3.2. cp1252 Windows-1252, 1252 Windows specific charset for Western European. KOI8-R koi8-ru, koi8r Russian. This charset is supported in 4.3.2. BIG5 950 Traditional Chinese, mainly used in Taiwan. GB2312 936 Simplified Chinese, national standard character set. BIG5-HKSCS Big5 with Hong Kong extensions, Traditional Chinese. Shift_JIS SJIS, 932 Japanese EUC-JP EUCJP Japanese Note: Any other character sets are not recognized and ISO-8859-1 will be used instead.
Return Values
Returns the decoded string.
See Also
- javascript htmlentities()
- javascript htmlspecialchars()
- javascript get_html_translation_table()
- javascript urldecode()
Javascript html_entity_decode
Source
This is the main source of the Javascript version of PHP's html_entity_decode
function html_entity_decode( string, quote_style ) { // http://kevin.vanzonneveld.net // + original by: john (http://www.jd-tech.net) // + input by: ger // + improved by: Kevin van Zonneveld (http://kevin.vanzonneveld.net) // + revised by: Kevin van Zonneveld (http://kevin.vanzonneveld.net) // + bugfixed by: Onno Marsman // + improved by: marc andreu // + revised by: Kevin van Zonneveld (http://kevin.vanzonneveld.net) // + bugfixed by: Brett Zamir (http://brett-zamir.me) // - depends on: get_html_translation_table // * example 1: html_entity_decode('Kevin & van Zonneveld'); // * returns 1: 'Kevin & van Zonneveld' // * example 2: html_entity_decode('&lt;'); // * returns 2: '<' var histogram = {}, symbol = '', tmp_str = '', entity = ''; tmp_str = string.toString(); if (false === (histogram = this.get_html_translation_table('HTML_ENTITIES', quote_style))) { return false; } for (symbol in histogram) { entity = histogram[symbol]; tmp_str = tmp_str.split(entity).join(symbol); } tmp_str = tmp_str.split(''').join("'"); return tmp_str; }
To run the Javascript html_entity_decode, you will also need the following dependencies:
Examples
Currently there are 2 examples
Example 1
html_entity_decode('Kevin & van Zonneveld');And that would return
'Kevin & van Zonneveld'Example 2
html_entity_decode('<');And that would return
'<'More about this Project
Download php.js
To easily include it in your code, every function currently available is stored in
Normal
- uncompressed source: php.js
- minified: php.min.js [recommended]
- compressed: php.packed.js
Namespaced What is 'namespaced?'
- uncompressed source: php.namespaced.js
- minified: php.namespaced.min.js
- compressed: php.namespaced.packed.js
To download use Right click, Save Link As
Generally the best way is to use a minified version and gzip it
Credits
Respect & awards go to everybody who has contributed in some way so far:
Your name here?
Contributing is as easy as adding a comment with better code, or code for a new function.
Any contribution leading to improvement will directly get your name & link here.
Coming Project features
Project features that we are currently working on:
- Done - Site. A place for php.js of it's own. See: phpjs.org.
- Done - Compile. Compile your own php.js version, with only the functions you need. Should generate a hash with which you can retrieve latest versions of your php.js combination. Done - Testsuite. A better test-suite that can be ran locally so developers can easily test before commiting. Also the testing itself should be more thorough.
- Done - Versioning. Individual functions are versioned, but the entire library should be versioned as well.
Stay up to date
You can track my blog
articles and
comments. You may also find my
bookmarks interesting. Or
Follow me on Twitter
Like this article?
|
Then Dzone it! Or use another bookmark button below to show your support & help me spread the word. |
RelatedArticles like this one» PHP.JS Licensing |
tags: programming, php, javascript, phpjs
category: Programming - Javascript - PHP equivalents
read: 11,144 times
Add Comment
PHP.JS is outgroing this blog and moving to it's own space. Please leave your comment here: http://phpjs.org/functions/html_entity_decode










tagcloud

#13. Kevin on 31 December 2008
http://trac.plutonia.nl/projects/phpjs/wiki/DeveloperGuidelines#DependencyvsRedundancy
The less dependencies the better, but of course we are not about to duplicate the histogram from get_html_translation_table 4 times, so dependencies are already made in this function family.
... [more] I think we should probably first come up with the fastest str_replace as possible. And base our decision (Dependency vs Redundancy) on the final algorithm used.
#12. Azriel Fasten on 30 December 2008
#11. Kevin on 30 December 2008
I've read the bug report more thorough, and applied the same fix as was proposed there.
I put the & entity at the bottom of the histogram.
... [more] Faster ways to replace (without using regex) can still be explored.
#10. Kevin on 20 October 2008
#9. marc andreu on 15 October 2008
// {{{ html_entity_decode
function html_entity_decode(string, quote_style ) {
// Convert all HTML entities to their applicable characters
//
// + discuss at: http://kevin.vanzonneveld.net/techblog/article/javascript_equivalent_for_phps_html_entity_decode/
// + version: 810.621
// + original by: john (http://www.jd-tech.net)
// + input by: ger
// + improved by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
// + revised by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
// + bugfixed by: Onno Marsman
// % note: table from http://www.the-art-of-web.com/html/character-codes/
// * example 1: html_entity_decode('Kevin & van Zonneveld');
// * returns 1: 'Kevin & van Zonneveld'
var histogram = {}, histogram_r = {}, code = 0;
var entity = chr = '';
histogram['34'] = 'quot';
histogram['38'] = 'amp';
histogram['60'] = 'lt';
histogram['62'] = 'gt';
histogram['160'] = 'nbsp';
histogram['161'] = 'iexcl';
histogram['162'] = 'cent';
histogram['163'] = 'pound';
histogram['164'] = 'curren';
histogram['165'] = 'yen';
histogram['166'] = 'brvbar';
histogram['167'] = 'sect';
histogram['168'] = 'uml';
histogram['169'] = 'copy';
histogram['170'] = 'ordf';
histogram['171'] = 'laquo';
histogram['172'] = 'not';
histogram['173'] = 'shy';
histogram['174'] = 'reg';
histogram['175'] = 'macr';
histogram['176'] = 'deg';
histogram['177'] = 'plusmn';
histogram['178'] = 'sup2';
histogram['179'] = 'sup3';
histogram['180'] = 'acute';
histogram['181'] = 'micro';
histogram['182'] = 'para';
histogram['183'] = 'middot';
histogram['184'] = 'cedil';
histogram['185'] = 'sup1';
histogram['186'] = 'ordm';
histogram['187'] = 'raquo';
histogram['188'] = 'frac14';
histogram['189'] = 'frac12';
histogram['190'] = 'frac34';
histogram['191'] = 'iquest';
histogram['192'] = 'Agrave';
histogram['193'] = 'Aacute';
histogram['194'] = 'Acirc';
histogram['195'] = 'Atilde';
histogram['196'] = 'Auml';
histogram['197'] = 'Aring';
histogram['198'] = 'AElig';
histogram['199'] = 'Ccedil';
histogram['200'] = 'Egrave';
histogram['201'] = 'Eacute';
histogram['202'] = 'Ecirc';
histogram['203'] = 'Euml';
histogram['204'] = 'Igrave';
histogram['205'] = 'Iacute';
histogram['206'] = 'Icirc';
histogram['207'] = 'Iuml';
histogram['208'] = 'ETH';
histogram['209'] = 'Ntilde';
histogram['210'] = 'Ograve';
histogram['211'] = 'Oacute';
histogram['212'] = 'Ocirc';
histogram['213'] = 'Otilde';
histogram['214'] = 'Ouml';
histogram['215'] = 'times';
histogram['216'] = 'Oslash';
histogram['217'] = 'Ugrave';
histogram['218'] = 'Uacute';
histogram['219'] = 'Ucirc';
histogram['220'] = 'Uuml';
histogram['221'] = 'Yacute';
histogram['222'] = 'THORN';
histogram['223'] = 'szlig';
histogram['224'] = 'agrave';
histogram['225'] = 'aacute';
histogram['226'] = 'acirc';
histogram['227'] = 'atilde';
histogram['228'] = 'auml';
histogram['229'] = 'aring';
histogram['230'] = 'aelig';
histogram['231'] = 'ccedil';
histogram['232'] = 'egrave';
histogram['233'] = 'eacute';
histogram['234'] = 'ecirc';
histogram['235'] = 'euml';
histogram['236'] = 'igrave';
histogram['237'] = 'iacute';
histogram['238'] = 'icirc';
histogram['239'] = 'iuml';
histogram['240'] = 'eth';
histogram['241'] = 'ntilde';
histogram['242'] = 'ograve';
histogram['243'] = 'oacute';
histogram['244'] = 'ocirc';
histogram['245'] = 'otilde';
histogram['246'] = 'ouml';
histogram['247'] = 'divide';
histogram['248'] = 'oslash';
histogram['249'] = 'ugrave';
histogram['250'] = 'uacute';
histogram['251'] = 'ucirc';
histogram['252'] = 'uuml';
histogram['253'] = 'yacute';
histogram['254'] = 'thorn';
histogram['255'] = 'yuml';
// Reverse table. Cause for maintainability purposes, the histogram is
// identical to the one in htmlentities.
for (code in histogram) {
entity = histogram[code];
histogram_r[entity] = code;
}
var retTemp = (string+'').replace(/(\&([a-zA-Z]+)\;)/g, function(full, m1, m2){
if (m2 in histogram_r) {
return String.fromCharCode(histogram_r[m2]);
} else {
return m2;
}
});
//Add for Marc Andreu Fernadnez. To decode quotes.
// Encode depending on quote_style
if (quote_style == 'ENT_QUOTES') {
retTemp = retTemp.replace('"','"');
retTemp = retTemp.replace(''',"'");
} else if (quote_style != 'ENT_NOQUOTES') {
// All other cases (ENT_COMPAT, default, but not ENT_NOQUOTES)
retTemp = retTemp.replace('"','"');
}
return retTemp;
}// }}}
#8. rekcor on 23 June 2008
But shouldn't you destroy
[code]tarea[/code]
(otherwise we will end up with n numbers of textareas floating around in the DOM's hyperspace)
#7. Kevin on 20 March 2008
#6. lubber on 20 March 2008
#5. Kevin on 19 March 2008
However, when php.js gets a page for component customization, I will include the functions and just leave them unchecked by default. Sounds good?
#4. lubber on 19 March 2008
http://www.onicos.com/staff/iz/amuse/javascript/expert/inflate.txt
http://www.onicos.com/staff/iz/amuse/javascript/expert/deflate.txt
#3. john on 18 March 2008
#2. Kevin on 15 March 2008
#1. ger on 15 March 2008