Stories
Slash Boxes
Comments

Dev.SN ♥ developers

posted by martyb on Thursday July 24 2014, @01:55PM   Printer-friendly

Summary:

Tests all latin1 named character entities defined in HTML 4. Each test point contains:

  1. The named character entity's description taken from the HTML 4 specification.
  2. The entity displayed as a UTF-8 encoded character.
  3. The entity displayed as a Named Character Entity.
  4. The entity displayed as a Decimal Character Entity.
  5. The entity displayed as a Hexadecimal Character Entity.

Documents Referenced:

http://www.w3.org/TR/html4/sgml/entities.html
"Character entity references in HTML 4"
https://tools.ietf.org/html/rfc3629
"UTF-8, a transformation format of ISO 10646"

Tests:


<!-- Portions © International Organization for Standardization 1986
Permission to copy in any form is granted for use with
conforming SGML systems and applications as defined in
ISO 8879, provided this notice is included in all copies.
-->

<!-- Character entity set. Typical invocation:
<!ENTITY % HTMLlat1 PUBLIC
"-//W3C//ENTITIES Latin 1//EN//HTML">
%HTMLlat1;
-->
no-break space = non-breaking space, U+00A0 ISOnum:
" " = 0xc2 0xa0 (UTF-8 encoded octets)
" " = &nbsp;
" " = &#160;
" " = &#xa0;
inverted exclamation mark, U+00A1 ISOnum:
"¡" = 0xc2 0xa1 (UTF-8 encoded octets)
"¡" = &iexcl;
"¡" = &#161;
"¡" = &#xa1;
cent sign, U+00A2 ISOnum:
"¢" = 0xc2 0xa2 (UTF-8 encoded octets)
"¢" = &cent;
"¢" = &#162;
"¢" = &#xa2;
pound sign, U+00A3 ISOnum:
"£" = 0xc2 0xa3 (UTF-8 encoded octets)
"£" = &pound;
"£" = &#163;
"£" = &#xa3;
currency sign, U+00A4 ISOnum:
"¤" = 0xc2 0xa4 (UTF-8 encoded octets)
"¤" = &curren;
"¤" = &#164;
"¤" = &#xa4;
yen sign = yuan sign, U+00A5 ISOnum:
"¥" = 0xc2 0xa5 (UTF-8 encoded octets)
"¥" = &yen;
"¥" = &#165;
"¥" = &#xa5;
broken bar = broken vertical bar, U+00A6 ISOnum:
"¦" = 0xc2 0xa6 (UTF-8 encoded octets)
"¦" = &brvbar;
"¦" = &#166;
"¦" = &#xa6;
section sign, U+00A7 ISOnum:
"§" = 0xc2 0xa7 (UTF-8 encoded octets)
"§" = &sect;
"§" = &#167;
"§" = &#xa7;
diaeresis = spacing diaeresis, U+00A8 ISOdia:
"¨" = 0xc2 0xa8 (UTF-8 encoded octets)
"¨" = &uml;
"¨" = &#168;
"¨" = &#xa8;
copyright sign, U+00A9 ISOnum:
"©" = 0xc2 0xa9 (UTF-8 encoded octets)
"©" = &copy;
"©" = &#169;
"©" = &#xa9;
feminine ordinal indicator, U+00AA ISOnum:
"ª" = 0xc2 0xaa (UTF-8 encoded octets)
"ª" = &ordf;
"ª" = &#170;
"ª" = &#xaa;
left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum:
"«" = 0xc2 0xab (UTF-8 encoded octets)
"«" = &laquo;
"«" = &#171;
"«" = &#xab;
not sign, U+00AC ISOnum:
"¬" = 0xc2 0xac (UTF-8 encoded octets)
"¬" = &not;
"¬" = &#172;
"¬" = &#xac;
soft hyphen = discretionary hyphen, U+00AD ISOnum:
"­" = 0xc2 0xad (UTF-8 encoded octets)
"­" = &shy;
"­" = &#173;
"­" = &#xad;
registered sign = registered trade mark sign, U+00AE ISOnum:
"®" = 0xc2 0xae (UTF-8 encoded octets)
"®" = &reg;
"®" = &#174;
"®" = &#xae;
macron = spacing macron = overline = APL overbar, U+00AF ISOdia:
"¯" = 0xc2 0xaf (UTF-8 encoded octets)
"¯" = &macr;
"¯" = &#175;
"¯" = &#xaf;
degree sign, U+00B0 ISOnum:
"°" = 0xc2 0xb0 (UTF-8 encoded octets)
"°" = &deg;
"°" = &#176;
"°" = &#xb0;
plus-minus sign = plus-or-minus sign, U+00B1 ISOnum:
"±" = 0xc2 0xb1 (UTF-8 encoded octets)
"±" = &plusmn;
"±" = &#177;
"±" = &#xb1;
superscript two = superscript digit two = squared, U+00B2 ISOnum:
"²" = 0xc2 0xb2 (UTF-8 encoded octets)
"²" = &sup2;
"²" = &#178;
"²" = &#xb2;
superscript three = superscript digit three = cubed, U+00B3 ISOnum:
"³" = 0xc2 0xb3 (UTF-8 encoded octets)
"³" = &sup3;
"³" = &#179;
"³" = &#xb3;
acute accent = spacing acute, U+00B4 ISOdia:
"´" = 0xc2 0xb4 (UTF-8 encoded octets)
"´" = &acute;
"´" = &#180;
"´" = &#xb4;
micro sign, U+00B5 ISOnum:
"µ" = 0xc2 0xb5 (UTF-8 encoded octets)
"µ" = &micro;
"µ" = &#181;
"µ" = &#xb5;
pilcrow sign = paragraph sign, U+00B6 ISOnum:
"¶" = 0xc2 0xb6 (UTF-8 encoded octets)
"¶" = &para;
"¶" = &#182;
"¶" = &#xb6;
middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum:
"·" = 0xc2 0xb7 (UTF-8 encoded octets)
"·" = &middot;
"·" = &#183;
"·" = &#xb7;
cedilla = spacing cedilla, U+00B8 ISOdia:
"¸" = 0xc2 0xb8 (UTF-8 encoded octets)
"¸" = &cedil;
"¸" = &#184;
"¸" = &#xb8;
superscript one = superscript digit one, U+00B9 ISOnum:
"¹" = 0xc2 0xb9 (UTF-8 encoded octets)
"¹" = &sup1;
"¹" = &#185;
"¹" = &#xb9;
masculine ordinal indicator, U+00BA ISOnum:
"º" = 0xc2 0xba (UTF-8 encoded octets)
"º" = &ordm;
"º" = &#186;
"º" = &#xba;
right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum:
"»" = 0xc2 0xbb (UTF-8 encoded octets)
"»" = &raquo;
"»" = &#187;
"»" = &#xbb;
vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum:
"¼" = 0xc2 0xbc (UTF-8 encoded octets)
"¼" = &frac14;
"¼" = &#188;
"¼" = &#xbc;
vulgar fraction one half = fraction one half, U+00BD ISOnum:
"½" = 0xc2 0xbd (UTF-8 encoded octets)
"½" = &frac12;
"½" = &#189;
"½" = &#xbd;
vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum:
"¾" = 0xc2 0xbe (UTF-8 encoded octets)
"¾" = &frac34;
"¾" = &#190;
"¾" = &#xbe;
inverted question mark = turned question mark, U+00BF ISOnum:
"¿" = 0xc2 0xbf (UTF-8 encoded octets)
"¿" = &iquest;
"¿" = &#191;
"¿" = &#xbf;
latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1:
"À" = 0xc3 0x80 (UTF-8 encoded octets)
"À" = &Agrave;
"À" = &#192;
"À" = &#xc0;
latin capital letter A with acute, U+00C1 ISOlat1:
"Á" = 0xc3 0x81 (UTF-8 encoded octets)
"Á" = &Aacute;
"Á" = &#193;
"Á" = &#xc1;
latin capital letter A with circumflex, U+00C2 ISOlat1:
"Â" = 0xc3 0x82 (UTF-8 encoded octets)
"Â" = &Acirc;
"Â" = &#194;
"Â" = &#xc2;
latin capital letter A with tilde, U+00C3 ISOlat1:
"Ã" = 0xc3 0x83 (UTF-8 encoded octets)
"Ã" = &Atilde;
"Ã" = &#195;
"Ã" = &#xc3;
latin capital letter A with diaeresis, U+00C4 ISOlat1:
"Ä" = 0xc3 0x84 (UTF-8 encoded octets)
"Ä" = &Auml;
"Ä" = &#196;
"Ä" = &#xc4;
latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1:
"Å" = 0xc3 0x85 (UTF-8 encoded octets)
"Å" = &Aring;
"Å" = &#197;
"Å" = &#xc5;
latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1:
"Æ" = 0xc3 0x86 (UTF-8 encoded octets)
"Æ" = &AElig;
"Æ" = &#198;
"Æ" = &#xc6;
latin capital letter C with cedilla, U+00C7 ISOlat1:
"Ç" = 0xc3 0x87 (UTF-8 encoded octets)
"Ç" = &Ccedil;
"Ç" = &#199;
"Ç" = &#xc7;
latin capital letter E with grave, U+00C8 ISOlat1:
"È" = 0xc3 0x88 (UTF-8 encoded octets)
"È" = &Egrave;
"È" = &#200;
"È" = &#xc8;
latin capital letter E with acute, U+00C9 ISOlat1:
"É" = 0xc3 0x89 (UTF-8 encoded octets)
"É" = &Eacute;
"É" = &#201;
"É" = &#xc9;
latin capital letter E with circumflex, U+00CA ISOlat1:
"Ê" = 0xc3 0x8a (UTF-8 encoded octets)
"Ê" = &Ecirc;
"Ê" = &#202;
"Ê" = &#xca;
latin capital letter E with diaeresis, U+00CB ISOlat1:
"Ë" = 0xc3 0x8b (UTF-8 encoded octets)
"Ë" = &Euml;
"Ë" = &#203;
"Ë" = &#xcb;
latin capital letter I with grave, U+00CC ISOlat1:
"Ì" = 0xc3 0x8c (UTF-8 encoded octets)
"Ì" = &Igrave;
"Ì" = &#204;
"Ì" = &#xcc;
latin capital letter I with acute, U+00CD ISOlat1:
"Í" = 0xc3 0x8d (UTF-8 encoded octets)
"Í" = &Iacute;
"Í" = &#205;
"Í" = &#xcd;
latin capital letter I with circumflex, U+00CE ISOlat1:
"Î" = 0xc3 0x8e (UTF-8 encoded octets)
"Î" = &Icirc;
"Î" = &#206;
"Î" = &#xce;
latin capital letter I with diaeresis, U+00CF ISOlat1:
"Ï" = 0xc3 0x8f (UTF-8 encoded octets)
"Ï" = &Iuml;
"Ï" = &#207;
"Ï" = &#xcf;
latin capital letter ETH, U+00D0 ISOlat1:
"Ð" = 0xc3 0x90 (UTF-8 encoded octets)
"Ð" = &ETH;
"Ð" = &#208;
"Ð" = &#xd0;
latin capital letter N with tilde, U+00D1 ISOlat1:
"Ñ" = 0xc3 0x91 (UTF-8 encoded octets)
"Ñ" = &Ntilde;
"Ñ" = &#209;
"Ñ" = &#xd1;
latin capital letter O with grave, U+00D2 ISOlat1:
"Ò" = 0xc3 0x92 (UTF-8 encoded octets)
"Ò" = &Ograve;
"Ò" = &#210;
"Ò" = &#xd2;
latin capital letter O with acute, U+00D3 ISOlat1:
"Ó" = 0xc3 0x93 (UTF-8 encoded octets)
"Ó" = &Oacute;
"Ó" = &#211;
"Ó" = &#xd3;
latin capital letter O with circumflex, U+00D4 ISOlat1:
"Ô" = 0xc3 0x94 (UTF-8 encoded octets)
"Ô" = &Ocirc;
"Ô" = &#212;
"Ô" = &#xd4;
latin capital letter O with tilde, U+00D5 ISOlat1:
"Õ" = 0xc3 0x95 (UTF-8 encoded octets)
"Õ" = &Otilde;
"Õ" = &#213;
"Õ" = &#xd5;
latin capital letter O with diaeresis, U+00D6 ISOlat1:
"Ö" = 0xc3 0x96 (UTF-8 encoded octets)
"Ö" = &Ouml;
"Ö" = &#214;
"Ö" = &#xd6;
multiplication sign, U+00D7 ISOnum:
"×" = 0xc3 0x97 (UTF-8 encoded octets)
"×" = &times;
"×" = &#215;
"×" = &#xd7;
latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1:
"Ø" = 0xc3 0x98 (UTF-8 encoded octets)
"Ø" = &Oslash;
"Ø" = &#216;
"Ø" = &#xd8;
latin capital letter U with grave, U+00D9 ISOlat1:
"Ù" = 0xc3 0x99 (UTF-8 encoded octets)
"Ù" = &Ugrave;
"Ù" = &#217;
"Ù" = &#xd9;
latin capital letter U with acute, U+00DA ISOlat1:
"Ú" = 0xc3 0x9a (UTF-8 encoded octets)
"Ú" = &Uacute;
"Ú" = &#218;
"Ú" = &#xda;
latin capital letter U with circumflex, U+00DB ISOlat1:
"Û" = 0xc3 0x9b (UTF-8 encoded octets)
"Û" = &Ucirc;
"Û" = &#219;
"Û" = &#xdb;
latin capital letter U with diaeresis, U+00DC ISOlat1:
"Ü" = 0xc3 0x9c (UTF-8 encoded octets)
"Ü" = &Uuml;
"Ü" = &#220;
"Ü" = &#xdc;
latin capital letter Y with acute, U+00DD ISOlat1:
"Ý" = 0xc3 0x9d (UTF-8 encoded octets)
"Ý" = &Yacute;
"Ý" = &#221;
"Ý" = &#xdd;
latin capital letter THORN, U+00DE ISOlat1:
"Þ" = 0xc3 0x9e (UTF-8 encoded octets)
"Þ" = &THORN;
"Þ" = &#222;
"Þ" = &#xde;
latin small letter sharp s = ess-zed, U+00DF ISOlat1:
"ß" = 0xc3 0x9f (UTF-8 encoded octets)
"ß" = &szlig;
"ß" = &#223;
"ß" = &#xdf;
latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1:
"à" = 0xc3 0xa0 (UTF-8 encoded octets)
"à" = &agrave;
"à" = &#224;
"à" = &#xe0;
latin small letter a with acute, U+00E1 ISOlat1:
"á" = 0xc3 0xa1 (UTF-8 encoded octets)
"á" = &aacute;
"á" = &#225;
"á" = &#xe1;
latin small letter a with circumflex, U+00E2 ISOlat1:
"â" = 0xc3 0xa2 (UTF-8 encoded octets)
"â" = &acirc;
"â" = &#226;
"â" = &#xe2;
latin small letter a with tilde, U+00E3 ISOlat1:
"ã" = 0xc3 0xa3 (UTF-8 encoded octets)
"ã" = &atilde;
"ã" = &#227;
"ã" = &#xe3;
latin small letter a with diaeresis, U+00E4 ISOlat1:
"ä" = 0xc3 0xa4 (UTF-8 encoded octets)
"ä" = &auml;
"ä" = &#228;
"ä" = &#xe4;
latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1:
"å" = 0xc3 0xa5 (UTF-8 encoded octets)
"å" = &aring;
"å" = &#229;
"å" = &#xe5;
latin small letter ae = latin small ligature ae, U+00E6 ISOlat1:
"æ" = 0xc3 0xa6 (UTF-8 encoded octets)
"æ" = &aelig;
"æ" = &#230;
"æ" = &#xe6;
latin small letter c with cedilla, U+00E7 ISOlat1:
"ç" = 0xc3 0xa7 (UTF-8 encoded octets)
"ç" = &ccedil;
"ç" = &#231;
"ç" = &#xe7;
latin small letter e with grave, U+00E8 ISOlat1:
"è" = 0xc3 0xa8 (UTF-8 encoded octets)
"è" = &egrave;
"è" = &#232;
"è" = &#xe8;
latin small letter e with acute, U+00E9 ISOlat1:
"é" = 0xc3 0xa9 (UTF-8 encoded octets)
"é" = &eacute;
"é" = &#233;
"é" = &#xe9;
latin small letter e with circumflex, U+00EA ISOlat1:
"ê" = 0xc3 0xaa (UTF-8 encoded octets)
"ê" = &ecirc;
"ê" = &#234;
"ê" = &#xea;
latin small letter e with diaeresis, U+00EB ISOlat1:
"ë" = 0xc3 0xab (UTF-8 encoded octets)
"ë" = &euml;
"ë" = &#235;
"ë" = &#xeb;
latin small letter i with grave, U+00EC ISOlat1:
"ì" = 0xc3 0xac (UTF-8 encoded octets)
"ì" = &igrave;
"ì" = &#236;
"ì" = &#xec;
latin small letter i with acute, U+00ED ISOlat1:
"í" = 0xc3 0xad (UTF-8 encoded octets)
"í" = &iacute;
"í" = &#237;
"í" = &#xed;
latin small letter i with circumflex, U+00EE ISOlat1:
"î" = 0xc3 0xae (UTF-8 encoded octets)
"î" = &icirc;
"î" = &#238;
"î" = &#xee;
latin small letter i with diaeresis, U+00EF ISOlat1:
"ï" = 0xc3 0xaf (UTF-8 encoded octets)
"ï" = &iuml;
"ï" = &#239;
"ï" = &#xef;
latin small letter eth, U+00F0 ISOlat1:
"ð" = 0xc3 0xb0 (UTF-8 encoded octets)
"ð" = &eth;
"ð" = &#240;
"ð" = &#xf0;
latin small letter n with tilde, U+00F1 ISOlat1:
"ñ" = 0xc3 0xb1 (UTF-8 encoded octets)
"ñ" = &ntilde;
"ñ" = &#241;
"ñ" = &#xf1;
latin small letter o with grave, U+00F2 ISOlat1:
"ò" = 0xc3 0xb2 (UTF-8 encoded octets)
"ò" = &ograve;
"ò" = &#242;
"ò" = &#xf2;
latin small letter o with acute, U+00F3 ISOlat1:
"ó" = 0xc3 0xb3 (UTF-8 encoded octets)
"ó" = &oacute;
"ó" = &#243;
"ó" = &#xf3;
latin small letter o with circumflex, U+00F4 ISOlat1:
"ô" = 0xc3 0xb4 (UTF-8 encoded octets)
"ô" = &ocirc;
"ô" = &#244;
"ô" = &#xf4;
latin small letter o with tilde, U+00F5 ISOlat1:
"õ" = 0xc3 0xb5 (UTF-8 encoded octets)
"õ" = &otilde;
"õ" = &#245;
"õ" = &#xf5;
latin small letter o with diaeresis, U+00F6 ISOlat1:
"ö" = 0xc3 0xb6 (UTF-8 encoded octets)
"ö" = &ouml;
"ö" = &#246;
"ö" = &#xf6;
division sign, U+00F7 ISOnum:
"÷" = 0xc3 0xb7 (UTF-8 encoded octets)
"÷" = &divide;
"÷" = &#247;
"÷" = &#xf7;
latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1:
"ø" = 0xc3 0xb8 (UTF-8 encoded octets)
"ø" = &oslash;
"ø" = &#248;
"ø" = &#xf8;
latin small letter u with grave, U+00F9 ISOlat1:
"ù" = 0xc3 0xb9 (UTF-8 encoded octets)
"ù" = &ugrave;
"ù" = &#249;
"ù" = &#xf9;
latin small letter u with acute, U+00FA ISOlat1:
"ú" = 0xc3 0xba (UTF-8 encoded octets)
"ú" = &uacute;
"ú" = &#250;
"ú" = &#xfa;
latin small letter u with circumflex, U+00FB ISOlat1:
"û" = 0xc3 0xbb (UTF-8 encoded octets)
"û" = &ucirc;
"û" = &#251;
"û" = &#xfb;
latin small letter u with diaeresis, U+00FC ISOlat1:
"ü" = 0xc3 0xbc (UTF-8 encoded octets)
"ü" = &uuml;
"ü" = &#252;
"ü" = &#xfc;
latin small letter y with acute, U+00FD ISOlat1:
"ý" = 0xc3 0xbd (UTF-8 encoded octets)
"ý" = &yacute;
"ý" = &#253;
"ý" = &#xfd;
latin small letter thorn, U+00FE ISOlat1:
"þ" = 0xc3 0xbe (UTF-8 encoded octets)
"þ" = &thorn;
"þ" = &#254;
"þ" = &#xfe;
latin small letter y with diaeresis, U+00FF ISOlat1:
"ÿ" = 0xc3 0xbf (UTF-8 encoded octets)
"ÿ" = &yuml;
"ÿ" = &#255;
"ÿ" = &#xff;
This discussion has been archived. No new comments can be posted.
Display Options Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.