Created
March 21, 2011 10:08
-
-
Save mattattui/879249 to your computer and use it in GitHub Desktop.
Convert named HTML entities to numeric for XML compatibility
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| /* html_convert_entities($string) -- convert named HTML entities to | |
| * XML-compatible numeric entities. | |
| */ | |
| function html_convert_entities($string) { | |
| return preg_replace_callback('/&([a-zA-Z][a-zA-Z0-9]+);/S', | |
| 'convert_entity', $string); | |
| } | |
| /* Swap HTML named entity with its numeric equivalent. If the entity | |
| * isn't in the lookup table, this function returns a blank, which | |
| * destroys the character in the output - this is probably the | |
| * desired behaviour when producing XML. */ | |
| function convert_entity($matches) { | |
| static $table = array('quot' => '"', | |
| 'amp' => '&', | |
| 'lt' => '<', | |
| 'gt' => '>', | |
| 'OElig' => 'Œ', | |
| 'oelig' => 'œ', | |
| 'Scaron' => 'Š', | |
| 'scaron' => 'š', | |
| 'Yuml' => 'Ÿ', | |
| 'circ' => 'ˆ', | |
| 'tilde' => '˜', | |
| 'ensp' => ' ', | |
| 'emsp' => ' ', | |
| 'thinsp' => ' ', | |
| 'zwnj' => '‌', | |
| 'zwj' => '‍', | |
| 'lrm' => '‎', | |
| 'rlm' => '‏', | |
| 'ndash' => '–', | |
| 'mdash' => '—', | |
| 'lsquo' => '‘', | |
| 'rsquo' => '’', | |
| 'sbquo' => '‚', | |
| 'ldquo' => '“', | |
| 'rdquo' => '”', | |
| 'bdquo' => '„', | |
| 'dagger' => '†', | |
| 'Dagger' => '‡', | |
| 'permil' => '‰', | |
| 'lsaquo' => '‹', | |
| 'rsaquo' => '›', | |
| 'euro' => '€', | |
| 'fnof' => 'ƒ', | |
| 'Alpha' => 'Α', | |
| 'Beta' => 'Β', | |
| 'Gamma' => 'Γ', | |
| 'Delta' => 'Δ', | |
| 'Epsilon' => 'Ε', | |
| 'Zeta' => 'Ζ', | |
| 'Eta' => 'Η', | |
| 'Theta' => 'Θ', | |
| 'Iota' => 'Ι', | |
| 'Kappa' => 'Κ', | |
| 'Lambda' => 'Λ', | |
| 'Mu' => 'Μ', | |
| 'Nu' => 'Ν', | |
| 'Xi' => 'Ξ', | |
| 'Omicron' => 'Ο', | |
| 'Pi' => 'Π', | |
| 'Rho' => 'Ρ', | |
| 'Sigma' => 'Σ', | |
| 'Tau' => 'Τ', | |
| 'Upsilon' => 'Υ', | |
| 'Phi' => 'Φ', | |
| 'Chi' => 'Χ', | |
| 'Psi' => 'Ψ', | |
| 'Omega' => 'Ω', | |
| 'alpha' => 'α', | |
| 'beta' => 'β', | |
| 'gamma' => 'γ', | |
| 'delta' => 'δ', | |
| 'epsilon' => 'ε', | |
| 'zeta' => 'ζ', | |
| 'eta' => 'η', | |
| 'theta' => 'θ', | |
| 'iota' => 'ι', | |
| 'kappa' => 'κ', | |
| 'lambda' => 'λ', | |
| 'mu' => 'μ', | |
| 'nu' => 'ν', | |
| 'xi' => 'ξ', | |
| 'omicron' => 'ο', | |
| 'pi' => 'π', | |
| 'rho' => 'ρ', | |
| 'sigmaf' => 'ς', | |
| 'sigma' => 'σ', | |
| 'tau' => 'τ', | |
| 'upsilon' => 'υ', | |
| 'phi' => 'φ', | |
| 'chi' => 'χ', | |
| 'psi' => 'ψ', | |
| 'omega' => 'ω', | |
| 'thetasym' => 'ϑ', | |
| 'upsih' => 'ϒ', | |
| 'piv' => 'ϖ', | |
| 'bull' => '•', | |
| 'hellip' => '…', | |
| 'prime' => '′', | |
| 'Prime' => '″', | |
| 'oline' => '‾', | |
| 'frasl' => '⁄', | |
| 'weierp' => '℘', | |
| 'image' => 'ℑ', | |
| 'real' => 'ℜ', | |
| 'trade' => '™', | |
| 'alefsym' => 'ℵ', | |
| 'larr' => '←', | |
| 'uarr' => '↑', | |
| 'rarr' => '→', | |
| 'darr' => '↓', | |
| 'harr' => '↔', | |
| 'crarr' => '↵', | |
| 'lArr' => '⇐', | |
| 'uArr' => '⇑', | |
| 'rArr' => '⇒', | |
| 'dArr' => '⇓', | |
| 'hArr' => '⇔', | |
| 'forall' => '∀', | |
| 'part' => '∂', | |
| 'exist' => '∃', | |
| 'empty' => '∅', | |
| 'nabla' => '∇', | |
| 'isin' => '∈', | |
| 'notin' => '∉', | |
| 'ni' => '∋', | |
| 'prod' => '∏', | |
| 'sum' => '∑', | |
| 'minus' => '−', | |
| 'lowast' => '∗', | |
| 'radic' => '√', | |
| 'prop' => '∝', | |
| 'infin' => '∞', | |
| 'ang' => '∠', | |
| 'and' => '∧', | |
| 'or' => '∨', | |
| 'cap' => '∩', | |
| 'cup' => '∪', | |
| 'int' => '∫', | |
| 'there4' => '∴', | |
| 'sim' => '∼', | |
| 'cong' => '≅', | |
| 'asymp' => '≈', | |
| 'ne' => '≠', | |
| 'equiv' => '≡', | |
| 'le' => '≤', | |
| 'ge' => '≥', | |
| 'sub' => '⊂', | |
| 'sup' => '⊃', | |
| 'nsub' => '⊄', | |
| 'sube' => '⊆', | |
| 'supe' => '⊇', | |
| 'oplus' => '⊕', | |
| 'otimes' => '⊗', | |
| 'perp' => '⊥', | |
| 'sdot' => '⋅', | |
| 'lceil' => '⌈', | |
| 'rceil' => '⌉', | |
| 'lfloor' => '⌊', | |
| 'rfloor' => '⌋', | |
| 'lang' => '〈', | |
| 'rang' => '〉', | |
| 'loz' => '◊', | |
| 'spades' => '♠', | |
| 'clubs' => '♣', | |
| 'hearts' => '♥', | |
| 'diams' => '♦', | |
| 'nbsp' => ' ', | |
| 'iexcl' => '¡', | |
| 'cent' => '¢', | |
| 'pound' => '£', | |
| 'curren' => '¤', | |
| 'yen' => '¥', | |
| 'brvbar' => '¦', | |
| 'sect' => '§', | |
| 'uml' => '¨', | |
| 'copy' => '©', | |
| 'ordf' => 'ª', | |
| 'laquo' => '«', | |
| 'not' => '¬', | |
| 'shy' => '­', | |
| 'reg' => '®', | |
| 'macr' => '¯', | |
| 'deg' => '°', | |
| 'plusmn' => '±', | |
| 'sup2' => '²', | |
| 'sup3' => '³', | |
| 'acute' => '´', | |
| 'micro' => 'µ', | |
| 'para' => '¶', | |
| 'middot' => '·', | |
| 'cedil' => '¸', | |
| 'sup1' => '¹', | |
| 'ordm' => 'º', | |
| 'raquo' => '»', | |
| 'frac14' => '¼', | |
| 'frac12' => '½', | |
| 'frac34' => '¾', | |
| 'iquest' => '¿', | |
| 'Agrave' => 'À', | |
| 'Aacute' => 'Á', | |
| 'Acirc' => 'Â', | |
| 'Atilde' => 'Ã', | |
| 'Auml' => 'Ä', | |
| 'Aring' => 'Å', | |
| 'AElig' => 'Æ', | |
| 'Ccedil' => 'Ç', | |
| 'Egrave' => 'È', | |
| 'Eacute' => 'É', | |
| 'Ecirc' => 'Ê', | |
| 'Euml' => 'Ë', | |
| 'Igrave' => 'Ì', | |
| 'Iacute' => 'Í', | |
| 'Icirc' => 'Î', | |
| 'Iuml' => 'Ï', | |
| 'ETH' => 'Ð', | |
| 'Ntilde' => 'Ñ', | |
| 'Ograve' => 'Ò', | |
| 'Oacute' => 'Ó', | |
| 'Ocirc' => 'Ô', | |
| 'Otilde' => 'Õ', | |
| 'Ouml' => 'Ö', | |
| 'times' => '×', | |
| 'Oslash' => 'Ø', | |
| 'Ugrave' => 'Ù', | |
| 'Uacute' => 'Ú', | |
| 'Ucirc' => 'Û', | |
| 'Uuml' => 'Ü', | |
| 'Yacute' => 'Ý', | |
| 'THORN' => 'Þ', | |
| 'szlig' => 'ß', | |
| 'agrave' => 'à', | |
| 'aacute' => 'á', | |
| 'acirc' => 'â', | |
| 'atilde' => 'ã', | |
| 'auml' => 'ä', | |
| 'aring' => 'å', | |
| 'aelig' => 'æ', | |
| 'ccedil' => 'ç', | |
| 'egrave' => 'è', | |
| 'eacute' => 'é', | |
| 'ecirc' => 'ê', | |
| 'euml' => 'ë', | |
| 'igrave' => 'ì', | |
| 'iacute' => 'í', | |
| 'icirc' => 'î', | |
| 'iuml' => 'ï', | |
| 'eth' => 'ð', | |
| 'ntilde' => 'ñ', | |
| 'ograve' => 'ò', | |
| 'oacute' => 'ó', | |
| 'ocirc' => 'ô', | |
| 'otilde' => 'õ', | |
| 'ouml' => 'ö', | |
| 'divide' => '÷', | |
| 'oslash' => 'ø', | |
| 'ugrave' => 'ù', | |
| 'uacute' => 'ú', | |
| 'ucirc' => 'û', | |
| 'uuml' => 'ü', | |
| 'yacute' => 'ý', | |
| 'thorn' => 'þ', | |
| 'yuml' => 'ÿ' | |
| ); | |
| // Entity not found? Destroy it. | |
| return isset($table[$matches[1]]) ? $table[$matches[1]] : ''; | |
| } | |
| ?> |
Thanks - I intend on using this to get RSS feeds working in xoxco/PeoplePods#7 !
@sebm : happy to help. Make sure that the (much) shorter version doesn't work just as well first, though. :)
As it turns out, the shorter version does the trick, too. 👏
The shorter solution does not make rid of inexistent entities, this one does. Entity translation suits perfect for my project since HTML5 doesn't have such thing as a DTD, and that was causing problems on my HTMLUnknownElement::innerHTML method (which is based on DOMDocumentFragment::appendXML). Thanks a lot for this solution.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
See http://inanimatt.com/php-convert-entities.php for context and a much shorter and (mostly) better alternative.