Elisp: Replace HTML Entities

By Xah Lee. Date: 2011-09-27. Last updated: 2024-05-27.

(defun xah-html-encode-ampersand-entity (&optional Begin End Report-p Highlight-p)
  "Replace HTML chars & < > to & < > on current block or selection.

URL `http://xahlee.info/emacs/emacs/elisp_replace_html_entities_command.html'
Created: 2020-08-30
Version: 2024-01-07 2024-03-19"
  (interactive (list nil nil t t))
  (let (xp1 xp2)
    (seq-setq (xp1 xp2) (if (and Begin End) (vector Begin End) (xah-get-pos-of-block-or)))
    (message "Calling %s" this-command)
    (xah-replace-pairs-region
     xp1 xp2
     [ ["&" "&"] ["<" "<"] [">" ">"] ] Report-p Highlight-p)))

(defun xah-html-decode-ampersand-entity (&optional Begin End Report-p Highlight-p)
  "Replace & < > to & < > on current block or selection.

URL `http://xahlee.info/emacs/emacs/elisp_replace_html_entities_command.html'
Created: 2020-08-30
Version: 2024-01-07 2024-03-19"
  (interactive (list nil nil t t))
  (let (xp1 xp2)
    (seq-setq (xp1 xp2) (if (and Begin End) (vector Begin End) (xah-get-pos-of-block-or)))
    (message "Calling %s" this-command)
    (xah-replace-pairs-region
     xp1 xp2
     [ ["&" "&"] ["<" "<"] [">" ">"] ]
     Report-p Highlight-p)))

(defun xah-html-named-entity-to-char (Begin End)
  "Replace named entity to Unicode character in current block or selection.
Changed places are highlighted.
For example, “©” becomes “©”.
The following HTML Entities are not replaced: & < >

When called in lisp code, Begin End are region begin/end positions.

URL `http://xahlee.info/emacs/emacs/elisp_replace_html_entities_command.html'
Created: 2020-08-30
Version: 2024-03-19"
  (interactive
   (seq-let (xp1 xp2) (xah-get-pos-of-block-or) (list xp1 xp2)))
  (let ((xreplaceMap
         [
          ["&nbsp;" " "] ["&ensp;" " "] ["&emsp;" " "] ["&thinsp;" " "]
          ["&rlm;" "‏"] ["&lrm;" "‎"] ["&zwj;" "‍"] ["&zwnj;" "‌"]
          ["&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"] ["&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;" "♦"] ["&quot;" "\""] ["&OElig;" "Œ"] ["&oelig;" "œ"] ["&Scaron;" "Š"]
          ["&scaron;" "š"] ["&Yuml;" "Ÿ"] ["&circ;" "ˆ"] ["&tilde;" "˜"] ["&ndash;" "–"]
          ["&mdash;" "—"] ["&lsquo;" "‘"] ["&rsquo;" "’"] ["&sbquo;" "‚"] ["&ldquo;" "“"]
          ["&rdquo;" "”"] ["&bdquo;" "„"] ["&dagger;" "†"] ["&Dagger;" "‡"] ["&permil;" "‰"]
          ["&lsaquo;" "‹"] ["&rsaquo;" "›"] ["&euro;" "€"]
          ]))
    (xah-replace-pairs-region Begin End xreplaceMap nil t)))