So I use Ajax quite a bit in many of my projects. And why not? It kicks ass! I have one project which dynamically updates specific elements of an HTML page via Ajax. Something like this:
$.get('/travel_guide/Paris', function(data){
$('#advice').text(data);
});
The problem I have, is that sometimes that data can include HTML entities like & and >, and for reasons I don't want to bore you with, I cannot do anything about it on the server side. When inserting a block of text that contain HTML entities into the DOM, those entities are not parsed as such, and get printed exactly as they are.
What I need is a Javascript function that can take a string and parse it for any HTML entities, then replace each one with their HTML character. And this is what I came up with...
function entityToHtml(string) {
for (var i in entity_table) {
if (i != 38) {
string = string.replace(new RegExp(entity_table[i], "g"), String.fromCharCode(i));
}
}
string = string.replace(new RegExp("&#(x?)(\\d+);", "g"), String.fromCharCode(((p1 == 'x') ? parseInt(p2, 16) : p2)));
string = string.replace(new RegExp(entity_table[38], "g"), String.fromCharCode(38));
return string;
}
var entity_table = {
// 34: """, // Quotation mark. Not required
38: "&", // Ampersand. Applied before everything else in the application
60: "<", // Less-than sign
62: ">", // Greater-than sign
// 63: "?", // Question mark
// 111: "o", // Latin small letter o
160: " ", // Non-breaking space
161: "¡", // Inverted exclamation mark
162: "¢", // Cent sign
163: "£", // Pound sign
164: "¤", // Currency sign
165: "¥", // Yen sign
166: "¦", // Broken vertical bar
167: "§", // Section sign
168: "¨", // Diaeresis
169: "©", // Copyright sign
170: "ª", // Feminine ordinal indicator
171: "«", // Left-pointing double angle quotation mark
172: "¬", // Not sign
173: "­", // Soft hyphen
174: "®", // Registered sign
175: "¯", // Macron
176: "°", // Degree sign
177: "±", // Plus-minus sign
178: "²", // Superscript two
179: "³", // Superscript three
180: "´", // Acute accent
181: "µ", // Micro sign
182: "¶", // Pilcrow sign
183: "·", // Middle dot
184: "¸", // Cedilla
185: "¹", // Superscript one
186: "º", // Masculine ordinal indicator
187: "»", // Right-pointing double angle quotation mark
188: "¼", // Vulgar fraction one-quarter
189: "½", // Vulgar fraction one-half
190: "¾", // Vulgar fraction three-quarters
191: "¿", // Inverted question mark
192: "À", // A with grave
193: "Á", // A with acute
194: "Â", // A with circumflex
195: "Ã", // A with tilde
196: "Ä", // A with diaeresis
197: "Å", // A with ring above
198: "Æ", // AE
199: "Ç", // C with cedilla
200: "È", // E with grave
201: "É", // E with acute
202: "Ê", // E with circumflex
203: "Ë", // E with diaeresis
204: "Ì", // I with grave
205: "Í", // I with acute
206: "Î", // I with circumflex
207: "Ï", // I with diaeresis
208: "Ð", // Eth
209: "Ñ", // N with tilde
210: "Ò", // O with grave
211: "Ó", // O with acute
212: "Ô", // O with circumflex
213: "Õ", // O with tilde
214: "Ö", // O with diaeresis
215: "×", // Multiplication sign
216: "Ø", // O with stroke
217: "Ù", // U with grave
218: "Ú", // U with acute
219: "Û", // U with circumflex
220: "Ü", // U with diaeresis
221: "Ý", // Y with acute
222: "Þ", // Thorn
223: "ß", // Sharp s. Also known as ess-zed
224: "à", // a with grave
225: "á", // a with acute
226: "â", // a with circumflex
227: "ã", // a with tilde
228: "ä", // a with diaeresis
229: "å", // a with ring above
230: "æ", // ae. Also known as ligature ae
231: "ç", // c with cedilla
232: "è", // e with grave
233: "é", // e with acute
234: "ê", // e with circumflex
235: "ë", // e with diaeresis
236: "ì", // i with grave
237: "í", // i with acute
238: "î", // i with circumflex
239: "ï", // i with diaeresis
240: "ð", // eth
241: "ñ", // n with tilde
242: "ò", // o with grave
243: "ó", // o with acute
244: "ô", // o with circumflex
245: "õ", // o with tilde
246: "ö", // o with diaeresis
247: "÷", // Division sign
248: "ø", // o with stroke. Also known as o with slash
249: "ù", // u with grave
250: "ú", // u with acute
251: "û", // u with circumflex
252: "ü", // u with diaeresis
253: "ý", // y with acute
254: "þ", // thorn
255: "ÿ", // y with diaeresis
264: "Ĉ", // Latin capital letter C with circumflex
265: "ĉ", // Latin small letter c with circumflex
338: "Œ", // Latin capital ligature OE
339: "œ", // Latin small ligature oe
352: "Š", // Latin capital letter S with caron
353: "š", // Latin small letter s with caron
372: "Ŵ", // Latin capital letter W with circumflex
373: "ŵ", // Latin small letter w with circumflex
374: "Ŷ", // Latin capital letter Y with circumflex
375: "ŷ", // Latin small letter y with circumflex
376: "Ÿ", // Latin capital letter Y with diaeresis
402: "ƒ", // Latin small f with hook, function, florin
710: "ˆ", // Modifier letter circumflex accent
732: "˜", // Small tilde
913: "Α", // Alpha
914: "Β", // Beta
915: "Γ", // Gamma
916: "Δ", // Delta
917: "Ε", // Epsilon
918: "Ζ", // Zeta
919: "Η", // Eta
920: "Θ", // Theta
921: "Ι", // Iota
922: "Κ", // Kappa
923: "Λ", // Lambda
924: "Μ", // Mu
925: "Ν", // Nu
926: "Ξ", // Xi
927: "Ο", // Omicron
928: "Π", // Pi
929: "Ρ", // Rho
931: "Σ", // Sigma
932: "Τ", // Tau
933: "Υ", // Upsilon
934: "Φ", // Phi
935: "Χ", // Chi
936: "Ψ", // Psi
937: "Ω", // Omega
945: "α", // alpha
946: "β", // beta
947: "γ", // gamma
948: "δ", // delta
949: "ε", // epsilon
950: "ζ", // zeta
951: "η", // eta
952: "θ", // theta
953: "ι", // iota
954: "κ", // kappa
955: "λ", // lambda
956: "μ", // mu
957: "ν", // nu
958: "ξ", // xi
959: "ο", // omicron
960: "π", // pi
961: "ρ", // rho
962: "ς", // sigmaf
963: "σ", // sigma
964: "τ", // tau
965: "υ", // upsilon
966: "φ", // phi
967: "χ", // chi
968: "ψ", // psi
969: "ω", // omega
977: "ϑ", // Theta symbol
978: "ϒ", // Greek upsilon with hook symbol
982: "ϖ", // Pi symbol
8194: " ", // En space
8195: " ", // Em space
8201: " ", // Thin space
8204: "‌", // Zero width non-joiner
8205: "‍", // Zero width joiner
8206: "‎", // Left-to-right mark
8207: "‏", // Right-to-left mark
8211: "–", // En dash
8212: "—", // Em dash
8216: "‘", // Left single quotation mark
8217: "’", // Right single quotation mark
8218: "‚", // Single low-9 quotation mark
8220: "“", // Left double quotation mark
8221: "”", // Right double quotation mark
8222: "„", // Double low-9 quotation mark
8224: "†", // Dagger
8225: "‡", // Double dagger
8226: "•", // Bullet
8230: "…", // Horizontal ellipsis
8240: "‰", // Per mille sign
8242: "′", // Prime
8243: "″", // Double Prime
8249: "‹", // Single left-pointing angle quotation
8250: "›", // Single right-pointing angle quotation
8254: "‾", // Overline
8260: "⁄", // Fraction Slash
8364: "€", // Euro sign
8472: "℘", // Script capital
8465: "ℑ", // Blackletter capital I
8476: "ℜ", // Blackletter capital R
8482: "™", // Trade mark sign
8501: "ℵ", // Alef symbol
8592: "←", // Leftward arrow
8593: "↑", // Upward arrow
8594: "→", // Rightward arrow
8595: "↓", // Downward arrow
8596: "↔", // Left right arrow
8629: "↵", // Downward arrow with corner leftward. Also known as carriage return
8656: "⇐", // Leftward double arrow. ISO 10646 does not say that lArr is the same as the 'is implied by' arrow but also does not have any other character for that function. So ? lArr can be used for 'is implied by' as ISOtech suggests
8657: "⇑", // Upward double arrow
8658: "⇒", // Rightward double arrow. ISO 10646 does not say this is the 'implies' character but does not have another character with this function so ? rArr can be used for 'implies' as ISOtech suggests
8659: "⇓", // Downward double arrow
8660: "⇔", // Left-right double arrow
// Mathematical Operators
8704: "∀", // For all
8706: "∂", // Partial differential
8707: "∃", // There exists
8709: "∅", // Empty set. Also known as null set and diameter
8711: "∇", // Nabla. Also known as backward difference
8712: "∈", // Element of
8713: "∉", // Not an element of
8715: "∋", // Contains as member
8719: "∏", // N-ary product. Also known as product sign. Prod is not the same character as U+03A0 'greek capital letter pi' though the same glyph might be used for both
8721: "∑", // N-ary summation. Sum is not the same character as U+03A3 'greek capital letter sigma' though the same glyph might be used for both
8722: "−", // Minus sign
8727: "∗", // Asterisk operator
8729: "∙", // Bullet operator
8730: "√", // Square root. Also known as radical sign
8733: "∝", // Proportional to
8734: "∞", // Infinity
8736: "∠", // Angle
8743: "∧", // Logical and. Also known as wedge
8744: "∨", // Logical or. Also known as vee
8745: "∩", // Intersection. Also known as cap
8746: "∪", // Union. Also known as cup
8747: "∫", // Integral
8756: "∴", // Therefore
8764: "∼", // tilde operator. Also known as varies with and similar to. The tilde operator is not the same character as the tilde, U+007E, although the same glyph might be used to represent both
8773: "≅", // Approximately equal to
8776: "≈", // Almost equal to. Also known as asymptotic to
8800: "≠", // Not equal to
8801: "≡", // Identical to
8804: "≤", // Less-than or equal to
8805: "≥", // Greater-than or equal to
8834: "⊂", // Subset of
8835: "⊃", // Superset of. Note that nsup, 'not a superset of, U+2283' is not covered by the Symbol font encoding and is not included.
8836: "⊄", // Not a subset of
8838: "⊆", // Subset of or equal to
8839: "⊇", // Superset of or equal to
8853: "⊕", // Circled plus. Also known as direct sum
8855: "⊗", // Circled times. Also known as vector product
8869: "⊥", // Up tack. Also known as orthogonal to and perpendicular
8901: "⋅", // Dot operator. The dot operator is not the same character as U+00B7 middle dot
// Miscellaneous Technical
8968: "⌈", // Left ceiling. Also known as an APL upstile
8969: "⌉", // Right ceiling
8970: "⌊", // left floor. Also known as APL downstile
8971: "⌋", // Right floor
9001: "⟨", // Left-pointing angle bracket. Also known as bra. Lang is not the same character as U+003C 'less than'or U+2039 'single left-pointing angle quotation mark'
9002: "⟩", // Right-pointing angle bracket. Also known as ket. Rang is not the same character as U+003E 'greater than' or U+203A 'single right-pointing angle quotation mark'
// Geometric Shapes
9642: "▪", // Black small square
9643: "▫", // White small square
9674: "◊", // Lozenge
// Miscellaneous Symbols
9702: "◦", // White bullet
9824: "♠", // Black (filled) spade suit
9827: "♣", // Black (filled) club suit. Also known as shamrock
9829: "♥", // Black (filled) heart suit. Also known as shamrock
9830: "♦" // Black (filled) diamond suit
}
Unfortunately, there is no way to convert these entities without a big long list to look through. But it works nicely like so:
entityToHtml(string_with_entities);
Making my code now looking like this:
$.get('/travel_guide/Paris', function(data){
$('#advice').text(entityToHtml(data));
});