← Go back

HTML entity decode for Pascal/Delphi


Posted on January 02, 2020 at 23:30 (GMT +00:00) by Colin

Today I found myself needing a simple conversion from HTML codes such as "À" to the equivalent "À" in Pascal, so rather than re-invent the wheel I done a quick Google search only to find over complicated functions that were 100's of lines of code.....

I've put together 2 functions that are the beginning for a simple decode process. You are free to use the code however you see fit with attribution.

//
// Simple HTML decoding
// Author: Colin J.D. Stewart
// Usage: writeLn( htmlReplaceCodes('Hello World!') );
// Updated: 30.01.2023
//

//
// replacement codes
//
function html_entity2char(const code: string): Char;
const
  html_code: array of string = [
    'nbsp', 'quot', 'amp', 'apos', 'lt', 'gt', 'iexcl', 'cent',
    'pound', 'curren', 'yen', 'brvbar', 'sect', 'uml', 'copy', 'ordf', 'laquo',
    'not', 'shy', 'reg', 'macr', 'deg', 'plusmn', 'sup2', 'sup3', 'acute',
    'micro', 'para', 'middot', 'cedil', 'sup1', 'ordm', 'raquo', 'frac14', 'frac12',
    'frac34', 'iquest', 'Agrave', 'Aacute', 'Acirc', 'Atilde', 'Auml', 'Aring', 'AElig',
    'Ccedil', 'Egrave', 'Eacute', 'Ecirc', 'Euml', 'Igrave', 'Iacute', 'Icirc', 'Iuml',
    'ETH', 'Ntilde', 'Ograve', 'Oacute', 'Ocirc', 'Otilde', 'Ouml', 'times', 'Oslash',
    'Ugrave', 'Uacute', 'Ucirc', 'Uuml', 'Yacute', 'THORN', 'szlig', 'agrave', 'aacute',
    'acirc', 'atilde', 'auml', 'aring', 'aelig', 'ccedil', 'egrave', 'eacute', 'ecirc',
    'euml', 'igrave', 'iacute', 'icirc', 'iuml', 'eth', 'ntilde', 'ograve', 'oacute',
    'ocirc', 'otilde', 'ouml', 'divide', 'oslash', 'ugrave', 'uacute', 'ucirc', 'uuml',
    'yacute', 'thorn', 'yuml', 'amp', 'bull', 'deg', 'infin', 'permil', 'sdot',
    'plusmn', 'dagger', 'mdash', 'not', 'micro', 'perp', 'par', 'euro', 'pound',
    'yen', 'cent', 'copy', 'reg', 'trade', 'alpha', 'beta', 'gamma', 'delta',
    'epsilon', 'zeta', 'eta', 'theta', 'iota', 'kappa', 'lambda', 'mu', 'nu',
    'xi', 'omicron', 'pi', 'rho', 'sigma', 'tau', 'upsilon', 'phi', 'chi',
    'psi', 'omega', 'Alpha', 'Beta', 'Gamma', 'Delta', 'Epsilon', 'Zeta', 'Eta',
    'Theta', 'Iota', 'Kappa', 'Lambda', 'Mu', 'Nu', 'Xi', 'Omicron', 'Pi',
    'Rho', 'Sigma', 'Tau', 'Upsilon', 'Phi', 'Chi', 'Psi', 'Omega'
  ];

  chars: array of Cardinal = [
    32, 34, 38, 39, 60, 62, 161, 162,
    163, 164, 165, 166, 167, 168, 169, 170, 171,
    172, 173, 174, 175, 176, 177, 178, 179, 180,
    181, 182, 183, 184, 185, 186, 187, 188, 189,
    190, 191, 192, 193, 194, 195, 196, 197, 198,
    199, 200, 201, 202, 203, 204, 205, 206, 207,
    208, 209, 210, 211, 212, 213, 214, 215, 216,
    217, 218, 219, 220, 221, 222, 223, 224, 225,
    226, 227, 228, 229, 230, 231, 232, 233, 234,
    235, 236, 237, 238, 239, 240, 241, 242, 243,
    244, 245, 246, 247, 248, 249, 250, 251, 252,
    253, 254, 255, 38, 8226, 176, 8734, 8240, 8901,
    177, 8224, 8212, 172, 181, 8869, 8741, 8364, 163,
    165, 162, 169, 174, 8482, 945, 946, 947, 948,
    949, 950, 951, 952, 953, 954, 955, 956, 957,
    958, 959, 960, 961, 963, 964, 965, 966, 967,
    968, 969, 913, 914, 915, 916, 917, 918, 919,
    920, 921, 922, 923, 924, 925, 926, 927, 928,
    929, 931, 932, 933, 934, 935, 936, 937
  ];

var
  i: Integer;


  function UCS4ToString(uch: UCS4Char): string; inline;
  var
    s: UCS4String;
  begin
    SetLength(s, 2);
    s[0] := uch;
    s[1] := 0;
    Result := UCS4StringToUnicodeString(s);
  end;
begin
  Result := Char(' ');
  if Length(code) < 2 then exit;
    //
  if code[1] = '#' then begin
    Result := UCS4ToString(StrToUInt(code.Substring(1)))[1];
  end else begin
    for i := Low(html_code) to High(html_code) do begin
      if html_code[i] = code then exit(UCS4ToString(chars[i])[1]);
    end;
  end;
end;


//
// run through the input and replace html codes
//
function html_replace_entities(const input: string): string;
var
  startPos, endPos: Integer;
begin
  startPos := 0;
  endPos := 0;

  Result := '';
  repeat
    endPos := input.IndexOf('&', startPos);
    if endPos = -1 then break;

    Result := Result + input.Substring(startPos, endPos-startPos);

    startPos := input.IndexOf(';', endPos)+1;
    if startPos = 0 then break;

    Result := Result + html_entity2char(input.Substring(endPos+1, startPos-endPos-2));
  until False;

  if startPos = 0 then
    Result := input
  else
    Result := Result + input.Substring(startPos+1);
end;


Simple call html_replace_entities with the string containing entities that requiring decoding, e.g.
myStr := html_replace_entities('Hello&nbsp;World!');


Alternatively, call the char decode function directly:

myChar := html_entity2char('#167');


If you find this useful or have any suggestions, drop me a comment below! :)

Edit (30.01.2023):
It was brought to my attention a small error ....note to self, always test code before posting.... I have updated the original code to fix the semicolon issue.
/Programming/Algorithms

Search
Tags
Accident Adoption Albums Algorithms Altcoins Animal Rescue AnL Aquarium Arma ArmA nd Leg Array Partitioning Arrays Assembler Assembly Atanasovsko Award Bazaar Binary Search Bitcoin Bohemia Bootstrap Bulgaria Bulgaria Za Mladite Burgas C C++ Celerity Charity Chemical Shock Chemlight Code Competition Compiler Contest Converter Covid-19 CPP Crypto Cryptocurrency css Data Recovery Database DataTables Decode Dedicated Dedicated Server Delphi Development Dialogs Divide & Conquer DIY Earplugs Event Exchange Eyes Fish Floating-point Flood Fog Freeware Function Funny Gallery Game Game Development Game Modding Gaming Garden Gardening Gazebo GERB GitHub Glitch Hamish Harding Happy New Year Heapify HeapSort Helga HTML HTML entities Introduction Jackie JavaScript JQuery Lake Language Linker Listbox ListNBox lnbSetTooltip MariaDB Maths Merry Christmas Mini Mining Miningpoolhub Mist Modding MPH Multiplayer MySql NGO OceanGate One Nature ORCA organisation OverHertz Paludarium Pandemic Pascal Paul-Henri Nargeolet Paws Furever Pergola Persistence Pets Photography Pier Plugin Programming progress bar Project PX Library Quicksort r53 Racing Replace Scripting Searching Server Shahzada Dawood Simulation Simulator Smoke Snippet Social media Software Sorting Source Sourcecode SQF Statistics Stockton Rush String Strings Submarine Suleman Dawood Terrain Detail Text Titan Tool Tragedy tutorial UCS4Char UE4 Unreal Engine Victims View Distance ViewBug web Web Development Website Welcome Woodworking Ziron Zynk