c5064474bf1da0099d8c84e5c2001aa639e151b0
[squirrelmail.git] / functions / htmlentities / readme.php
1 <?php
2
3 /**
4 * SquirrelMail html translation table documentation
5 *
6 * SquirrelMail provides own implementation of htmlentities() and
7 * get_html_translation_table() functions. Functions are called
8 * sq_get_html_translation_table() and sq_htmlentities(). They are
9 * included in functions/strings.php
10 *
11 * sq_htmlentities uses same syntax as functions available in php 4.1.0
12 * sq_get_html_translation_table adds third option that sets charset.
13 *
14 * <pre>
15 * string sq_htmlentities ( string string [, int quote_style [, string charset]])
16 * array sq_get_html_translation_table ( int table [, int quote_style [, string charset]])
17 * </pre>
18 *
19 * If sq_get_html_translation_table function is called with HTML_SPECIALCHARS option,
20 * it returns us-ascii translation table. If it is called with HTML_ENTITIES option,
21 * it returns translation table defined by charset. Function defaults to us-ascii charset
22 * and not to iso-8859-1.
23 *
24 * Why own functions are used instead of htmlspecialchars() and
25 * htmlentities() provided by php.
26 *
27 * <ul>
28 * <li>a) removes dependency on options available only in php v.4.1+</li>
29 * <li>b) default behavior of htmlentities() is disastrous in non iso-8859-1 environment.</li>
30 * <li>c) provides better control of transformations.</li>
31 * </ul>
32 *
33 * <pre>
34 * --- Full list of entities (w3.org html4.01 recommendations)
35 * 1. regural symbols
36 * U+0022 - &quot;
37 * (replaced only when $style is not ENT_NOQUOTES or 0)
38 * U+0026 - &amp;
39 * U+0027 - &#39;
40 * (replaced only when $style is ENT_QUOTES or 3)
41 * U+003C - &lt;
42 * U+003E - &gt;
43 *
44 * 2. latin1 symbols (HTMLlat1.ent)
45 * U+00A0 - &nbsp; -- no-break space = non-breaking space
46 * U+00A1 - &iexcl; -- inverted exclamation mark
47 * U+00A2 - &cent; -- cent sign
48 * U+00A3 - &pound; -- pound sign
49 * U+00A4 - &curren; -- currency sign
50 * U+00A5 - &yen; -- yen sign
51 * U+00A6 - &brvbar; -- broken bar
52 * U+00A7 - &sect; -- section sign
53 * U+00A8 - &uml; -- diaeresis
54 * U+00A9 - &copy; -- copyright sign
55 * U+00AA - &ordf; -- feminine ordinal indicator
56 * U+00AB - &laquo; -- left-pointing double angle quotation mark = left pointing guillemet
57 * U+00AC - &not; -- not sign
58 * U+00AD - &shy; -- soft hyphen = discretionary hyphen
59 * U+00AE - &reg; -- registered sign = registered trade mark sign
60 * U+00AF - &macr; -- macron = spacing macron = overline = APL overbar
61 * U+00B0 - &deg; -- degree sign
62 * U+00B1 - &plusmn; -- plus-minus sign = plus-or-minus sign
63 * U+00B2 - &sup2; -- superscript two = superscript digit two = squared
64 * U+00B3 - &sup3; -- superscript three = superscript digit three = cubed
65 * U+00B4 - &acute; -- acute accent = spacing acute
66 * U+00B5 - &micro; -- micro sign
67 * U+00B6 - &para; -- pilcrow sign = paragraph sign
68 * U+00B7 - &middot; -- middle dot = Georgian comma = Greek middle dot
69 * U+00B8 - &cedil; -- cedilla = spacing cedilla
70 * U+00B9 - &sup1; -- superscript one = superscript digit one
71 * U+00BA - &ordm; -- masculine ordinal indicator
72 * U+00BB - &raquo; -- right-pointing double angle quotation mark = right pointing guillemet
73 * U+00BC - &frac14; -- vulgar fraction one quarter = fraction one quarter
74 * U+00BD - &frac12; -- vulgar fraction one half = fraction one half
75 * U+00BE - &frac34; -- vulgar fraction three quarters = fraction three quarters
76 * U+00BF - &iquest; -- inverted question mark = turned question mark
77 * U+0180 - &Agrave; -- latin capital letter A with grave = latin capital letter A grave,
78 * U+0181 - &Aacute; -- latin capital letter A with acute
79 * U+0182 - &Acirc; -- latin capital letter A with circumflex
80 * U+0183 - &Atilde; -- latin capital letter A with tilde
81 * U+0184 - &Auml; -- latin capital letter A with diaeresis
82 * U+0185 - &Aring; -- latin capital letter A with ring above = latin capital letter A ring
83 * U+0186 - &AElig; -- latin capital letter AE = latin capital ligature AE
84 * U+0187 - &Ccedil; -- latin capital letter C with cedilla
85 * U+0188 - &Egrave; -- latin capital letter E with grave
86 * U+0189 - &Eacute; -- latin capital letter E with acute
87 * U+018A - &Ecirc; -- latin capital letter E with circumflex
88 * U+018B - &Euml; -- latin capital letter E with diaeresis
89 * U+018C - &Igrave; -- latin capital letter I with grave
90 * U+018D - &Iacute; -- latin capital letter I with acute
91 * U+018E - &Icirc; -- latin capital letter I with circumflex
92 * U+018F - &Iuml; -- latin capital letter I with diaeresis
93 * U+0190 - &ETH; -- latin capital letter ETH
94 * U+0191 - &Ntilde; -- latin capital letter N with tilde
95 * U+0192 - &Ograve; -- latin capital letter O with grave
96 * U+0193 - &Oacute; -- latin capital letter O with acute
97 * U+0194 - &Ocirc; -- latin capital letter O with circumflex
98 * U+0195 - &Otilde; -- latin capital letter O with tilde
99 * U+0196 - &Ouml; -- latin capital letter O with diaeresis
100 * U+0197 - &times; -- multiplication sign
101 * U+0198 - &Oslash; -- latin capital letter O with stroke = latin capital letter O slash
102 * U+0199 - &Ugrave; -- latin capital letter U with grave
103 * U+019A - &Uacute; -- latin capital letter U with acute
104 * U+019B - &Ucirc; -- latin capital letter U with circumflex
105 * U+019C - &Uuml; -- latin capital letter U with diaeresis
106 * U+019D - &Yacute; -- latin capital letter Y with acute
107 * U+019E - &THORN; -- latin capital letter THORN
108 * U+019F - &szlig; -- latin small letter sharp s = ess-zed
109 * U+01A0 - &agrave; -- latin small letter a with grave = latin small letter a grave
110 * U+01A1 - &aacute; -- latin small letter a with acute
111 * U+01A2 - &acirc; -- latin small letter a with circumflex
112 * U+01A3 - &atilde; -- latin small letter a with tilde
113 * U+01A4 - &auml; -- latin small letter a with diaeresis
114 * U+01A5 - &aring; -- latin small letter a with ring above = latin small letter a ring
115 * U+01A6 - &aelig; -- latin small letter ae = latin small ligature ae
116 * U+01A7 - &ccedil; -- latin small letter c with cedilla
117 * U+01A8 - &egrave; -- latin small letter e with grave
118 * U+01A9 - &eacute; -- latin small letter e with acute
119 * U+01AA - &ecirc; -- latin small letter e with circumflex
120 * U+01AB - &euml; -- latin small letter e with diaeresis
121 * U+01AC - &igrave; -- latin small letter i with grave
122 * U+01AD - &iacute; -- latin small letter i with acute
123 * U+01AE - &icirc; -- latin small letter i with circumflex
124 * U+01AF - &iuml; -- latin small letter i with diaeresis
125 * U+01B0 - &eth; -- latin small letter eth
126 * U+01B1 - &ntilde; -- latin small letter n with tilde
127 * U+01B2 - &ograve; -- latin small letter o with grave
128 * U+01B3 - &oacute; -- latin small letter o with acute
129 * U+01B4 - &ocirc; -- latin small letter o with circumflex
130 * U+01B5 - &otilde; -- latin small letter o with tilde
131 * U+01B6 - &ouml; -- latin small letter o with diaeresis
132 * U+01B7 - &divide; -- division sign
133 * U+01B8 - &oslash; -- latin small letter o with stroke = latin small letter o slash,
134 * U+01B9 - &ugrave; -- latin small letter u with grave
135 * U+01BA - &uacute; -- latin small letter u with acute
136 * U+01BB - &ucirc; -- latin small letter u with circumflex
137 * U+01BC - &uuml; -- latin small letter u with diaeresis
138 * U+01BD - &yacute; -- latin small letter y with acute
139 * U+01BE - &thorn; -- latin small letter thorn,
140 * U+01BF - &yuml; -- latin small letter y with diaeresis
141 *
142 * 3. Special symbols (HTMLspecial.ent)
143 * Latin Extended-A
144 * U+0152 - &OElig; --
145 * U+0153 - &oelig; -- latin small ligature oe
146 * U+0160 - &Scaron; -- latin capital letter S with caron
147 * U+0161 - &scaron; -- latin small letter s with caron
148 * U+0178 - &Yuml; -- latin capital letter Y with diaeresis
149 * Spacing Modifier Letters
150 * U+02C6 - &circ; -- modifier letter circumflex accent
151 * U+02DC - &tilde; -- small tilde
152 * General Punctuation
153 * U+2002 - &ensp; -- en space
154 * U+2003 - &emsp; -- em space
155 * U+2009 - &thinsp; -- thin space
156 * U+200C - &zwnj; -- zero width non-joiner
157 * U+200D - &zwj; -- zero width joiner
158 * U+200E - &lrm; -- left-to-right mark
159 * U+200F - &rlm; -- right-to-left mark
160 * U+2013 - &ndash; -- en dash
161 * U+2014 - &mdash; -- em dash
162 * U+2018 - &lsquo; -- left single quotation mark
163 * U+2019 - &rsquo; -- right single quotation mark
164 * U+201A - &sbquo; -- single low-9 quotation mark
165 * U+201C - &ldquo; -- left double quotation mark
166 * U+201D - &rdquo; -- right double quotation mark
167 * U+201E - &bdquo; -- double low-9 quotation mark
168 * U+2020 - &dagger; -- dagger
169 * U+2021 - &Dagger; -- double dagger
170 * U+2030 - &permil; -- per mille sign
171 * U+2039 - &lsaquo; -- single left-pointing angle quotation mark
172 * U+203A - &rsaquo; -- single right-pointing angle quotation mark
173 * U+20AC - &euro; -- euro sign
174 *
175 * 4. Other symbols (HTMLsymbol.ent)
176 * Latin Extended-B
177 * U+0192 - &fnof; -- latin small f with hook = function = florin
178 * Greek
179 * U+0391 - &Alpha; -- greek capital letter alpha
180 * U+0392 - &Beta; -- greek capital letter beta
181 * U+0393 - &Gamma; -- greek capital letter gamma
182 * U+0394 - &Delta; -- greek capital letter delta
183 * U+0395 - &Epsilon; -- greek capital letter epsilon
184 * U+0396 - &Zeta; -- greek capital letter zeta
185 * U+0397 - &Eta; -- greek capital letter eta
186 * U+0398 - &Theta; -- greek capital letter theta
187 * U+0399 - &Iota; -- greek capital letter iota
188 * U+039A - &Kappa; -- greek capital letter kappa
189 * U+039B - &Lambda; -- greek capital letter lambda
190 * U+039C - &Mu; -- greek capital letter mu
191 * U+039D - &Nu; -- greek capital letter nu
192 * U+039E - &Xi; -- greek capital letter xi
193 * U+039F - &Omicron; -- greek capital letter omicron
194 * U+03A0 - &Pi; -- greek capital letter pi
195 * U+03A1 - &Rho; -- greek capital letter rho
196 * U+03A3 - &Sigma; -- greek capital letter sigma
197 * U+03A4 - &Tau; -- greek capital letter tau
198 * U+03A5 - &Upsilon; -- greek capital letter upsilon
199 * U+03A6 - &Phi; -- greek capital letter phi
200 * U+03A7 - &Chi; -- greek capital letter chi
201 * U+03A8 - &Psi; -- greek capital letter psi
202 * U+03A9 - &Omega; -- greek capital letter omega
203 * U+03B1 - &alpha; -- greek small letter alpha
204 * U+03B2 - &beta; -- greek small letter beta
205 * U+03B3 - &gamma; -- greek small letter gamma
206 * U+03B4 - &delta; -- greek small letter delta
207 * U+03B5 - &epsilon; -- greek small letter epsilon
208 * U+03B6 - &zeta; -- greek small letter zeta
209 * U+03B7 - &eta; -- greek small letter eta
210 * U+03B8 - &theta; -- greek small letter theta
211 * U+03B9 - &iota; -- greek small letter iota
212 * U+03BA - &kappa; -- greek small letter kappa
213 * U+03BB - &lambda; -- greek small letter lambda
214 * U+03BC - &mu; -- greek small letter mu
215 * U+03BD - &nu; -- greek small letter nu
216 * U+03BE - &xi; -- greek small letter xi
217 * U+03BF - &omicron; -- greek small letter omicron
218 * U+03C0 - &pi; -- greek small letter pi
219 * U+03C1 - &rho; -- greek small letter rho
220 * U+03C2 - &sigmaf; -- greek small letter final sigma
221 * U+03C3 - &sigma; -- greek small letter sigma
222 * U+03C4 - &tau; -- greek small letter tau
223 * U+03C5 - &upsilon; -- greek small letter upsilon
224 * U+03C6 - &phi; -- greek small letter phi
225 * U+03C7 - &chi; -- greek small letter chi
226 * U+03C8 - &psi; -- greek small letter psi
227 * U+03C9 - &omega; -- greek small letter omega
228 * U+03D1 - &thetasym; -- greek small letter theta symbol
229 * U+03D2 - &upsih; -- greek upsilon with hook symbol
230 * U+03D6 - &piv; -- greek pi symbol
231 *
232 * General Punctuation
233 * U+2022 - &bull; -- bullet = black small circle
234 * U+2026 - &hellip; -- horizontal ellipsis = three dot leader
235 * U+2032 - &prime; -- prime = minutes = feet
236 * U+2033 - &Prime; -- double prime = seconds = inches
237 * U+203E - &oline; -- overline = spacing overscore
238 * U+2044 - &frasl; -- fraction slash
239 *
240 * Letterlike Symbols
241 * U+2118 - &weierp; -- script capital P = power set = Weierstrass p
242 * U+2111 - &image; -- blackletter capital I = imaginary part
243 * U+211C - &real; -- blackletter capital R = real part symbol
244 * U+2122 - &trade; -- trade mark sign
245 * U+2135 - &alefsym; -- alef symbol = first transfinite cardinal
246 *
247 * Arrows
248 * U+2190 - &larr; -- leftwards arrow
249 * U+2191 - &uarr; -- upwards arrow
250 * U+2192 - &rarr; -- rightwards arrow
251 * U+2193 - &darr; -- downwards arrow
252 * U+2194 - &harr; -- left right arrow
253 * U+21B5 - &crarr; -- downwards arrow with corner leftwards = carriage return
254 * U+21D0 - &lArr; -- leftwards double arrow
255 * U+21D1 - &uArr; -- upwards double arrow
256 * U+21D2 - &rArr; -- rightwards double arrow
257 * U+21D3 - &dArr; -- downwards double arrow
258 * U+21D4 - &hArr; -- left right double arrow
259 *
260 * Mathematical Operators
261 * U+2200 - &forall; -- for all
262 * U+2202 - &part; -- partial differential
263 * U+2203 - &exist; -- there exists
264 * U+2205 - &empty; -- empty set = null set = diameter
265 * U+2207 - &nabla; -- nabla = backward difference
266 * U+2208 - &isin; -- element of
267 * U+2209 - &notin; -- not an element of
268 * U+220B - &ni; -- contains as member
269 * U+220F - &prod; -- n-ary product = product sign
270 * U+2211 - &sum; -- n-ary sumation
271 * U+2212 - &minus; -- minus sign
272 * U+2217 - &lowast; -- asterisk operator
273 * U+221A - &radic; -- square root = radical sign
274 * U+221D - &prop; -- proportional to
275 * U+221E - &infin; -- infinity
276 * U+2220 - &ang; -- angle
277 * U+2227 - &and; -- logical and = wedge
278 * U+2228 - &or; -- logical or = vee
279 * U+2229 - &cap; -- intersection = cap
280 * U+222A - &cup; -- union = cup
281 * U+222B - &int; -- integral
282 * U+2234 - &there4; -- therefore
283 * U+223C - &sim; -- tilde operator = varies with = similar to
284 * U+2245 - &cong; -- approximately equal to
285 * U+2248 - &asymp; -- almost equal to = asymptotic to
286 * U+2260 - &ne; -- not equal to
287 * U+2261 - &equiv; -- identical to
288 * U+2264 - &le; -- less-than or equal to
289 * U+2265 - &ge; -- greater-than or equal to
290 * U+2282 - &sub; -- subset of
291 * U+2283 - &sup; -- superset of
292 * U+2284 - &nsub; -- not a subset of
293 * U+2286 - &sube; -- subset of or equal to
294 * U+2287 - &supe; -- superset of or equal to
295 * U+2295 - &oplus; -- circled plus = direct sum
296 * U+2297 - &otimes; -- circled times = vector product
297 * U+22A5 - &perp; -- up tack = orthogonal to = perpendicular
298 * U+22C5 - &sdot; -- dot operator
299 *
300 * Miscellaneous Technical
301 * U+2308 - &lceil; -- left ceiling = apl upstile
302 * U+2309 - &rceil; -- right ceiling
303 * U+230A - &lfloor; -- left floor = apl downstile
304 * U+230B - &rfloor; -- right floor
305 * U+2329 - &lang; -- left-pointing angle bracket = bra
306 * U+232A - &rang; -- right-pointing angle bracket = ket
307 *
308 * Geometric Shapes
309 * U+25CA - &loz; -- lozenge
310 *
311 * Miscellaneous Symbols
312 * U+2660 - &spades; -- black spade suit
313 * U+2663 - &clubs; -- black club suit = shamrock
314 * U+2665 - &hearts; -- black heart suit = valentine
315 * U+2666 - &diams; -- black diamond suit
316 * </pre>
317 *
318 * @copyright 2004-2019 The SquirrelMail Project Team
319 * @license http://opensource.org/licenses/gpl-license.php GNU Public License
320 * @version $Id$
321 * @package squirrelmail
322 * @subpackage strings
323 */