Segment
CharacterReference
CharacterEntityReference
|
||||||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | |||||||||
java.lang.Object
Represents an HTML Character Entity Reference.
Click here to scroll down to the method summary.
The full list of HTML character entity references can be found at the following URL:
http://www.w3.org/TR/REC-html40/sgml/entities.html.
There are a total of 253 HTML character entity references, ranging from codepoints U+0022 to U+2666.
Static methods to encode and decode strings
and single characters can be found in the CharacterReference superclass.
The ' entity reference is not defined for use in HTML.
It is defined in the XHTML Special Characters Entity Set,
and is the only one that is not included in both HTML and XHTML.
For this reason, the ' entity reference is recognised by this library in decoding functions, but in encoding functions
the numeric character reference ' is used instead.
Most modern browsers support it in both XHTML and HTML, with the notable exception
of Microsoft Internet Explorer 6.0, which doesn't support it in either.
CharacterEntityReference instances are obtained using one of the following methods:
CharacterReference.parse(CharSequence characterReferenceText)
Source.findNextCharacterReference(int pos)
Source.findPreviousCharacterReference(int pos)
Segment.findAllCharacterReferences()
CharacterReference,
NumericCharacterReference| Field Summary | |
static char |
_aacute
á á = á -- latin small letter a with acute, U+00E1 ISOlat1. |
static char |
_Aacute
Á Á = Á -- latin capital letter A with acute, U+00C1 ISOlat1. |
static char |
_acirc
â â = â -- latin small letter a with circumflex, U+00E2 ISOlat1. |
static char |
_Acirc
  =  -- latin capital letter A with circumflex, U+00C2 ISOlat1. |
static char |
_acute
´ ´ = ´ -- acute accent = spacing acute, U+00B4 ISOdia. |
static char |
_aelig
æ æ = æ -- latin small letter ae = latin small ligature ae, U+00E6 ISOlat1. |
static char |
_AElig
Æ Æ = Æ -- latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1. |
static char |
_agrave
à à = à -- latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1. |
static char |
_Agrave
À À = À -- latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1. |
static char |
_alefsym
ℵ ℵ = ℵ -- alef symbol = first transfinite cardinal, U+2135 NEW(see comments). |
static char |
_alpha
α α = α -- greek small letter alpha, U+03B1 ISOgrk3. |
static char |
_Alpha
Α Α = Α -- greek capital letter alpha, U+0391. |
static char |
_amp
& & = & -- ampersand, U+0026 ISOnum. |
static char |
_and
∧ ∧ = ∧ -- logical and = wedge, U+2227 ISOtech. |
static char |
_ang
∠ ∠ = ∠ -- angle, U+2220 ISOamso. |
static char |
_apos
' ' = ' -- apostrophe = APL quote, U+0027 ISOnum(see comments). |
static char |
_aring
å å = å -- latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1. |
static char |
_Aring
Å Å = Å -- latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1. |
static char |
_asymp
≈ ≈ = ≈ -- almost equal to = asymptotic to, U+2248 ISOamsr. |
static char |
_atilde
ã ã = ã -- latin small letter a with tilde, U+00E3 ISOlat1. |
static char |
_Atilde
à à = à -- latin capital letter A with tilde, U+00C3 ISOlat1. |
static char |
_auml
ä ä = ä -- latin small letter a with diaeresis, U+00E4 ISOlat1. |
static char |
_Auml
Ä Ä = Ä -- latin capital letter A with diaeresis, U+00C4 ISOlat1. |
static char |
_bdquo
„ „ = „ -- double low-9 quotation mark, U+201E NEW. |
static char |
_beta
β β = β -- greek small letter beta, U+03B2 ISOgrk3. |
static char |
_Beta
Β Β = Β -- greek capital letter beta, U+0392. |
static char |
_brvbar
¦ ¦ = ¦ -- broken bar = broken vertical bar, U+00A6 ISOnum. |
static char |
_bull
• • = • -- bullet = black small circle, U+2022 ISOpub(see comments). |
static char |
_cap
∩ ∩ = ∩ -- intersection = cap, U+2229 ISOtech. |
static char |
_ccedil
ç ç = ç -- latin small letter c with cedilla, U+00E7 ISOlat1. |
static char |
_Ccedil
Ç Ç = Ç -- latin capital letter C with cedilla, U+00C7 ISOlat1. |
static char |
_cedil
¸ ¸ = ¸ -- cedilla = spacing cedilla, U+00B8 ISOdia. |
static char |
_cent
¢ ¢ = ¢ -- cent sign, U+00A2 ISOnum. |
static char |
_chi
χ χ = χ -- greek small letter chi, U+03C7 ISOgrk3. |
static char |
_Chi
Χ Χ = Χ -- greek capital letter chi, U+03A7. |
static char |
_circ
ˆ ˆ = ˆ -- modifier letter circumflex accent, U+02C6 ISOpub. |
static char |
_clubs
♣ ♣ = ♣ -- black club suit = shamrock, U+2663 ISOpub. |
static char |
_cong
≅ ≅ = ≅ -- approximately equal to, U+2245 ISOtech. |
static char |
_copy
© © = © -- copyright sign, U+00A9 ISOnum. |
static char |
_crarr
↵ ↵ = ↵ -- downwards arrow with corner leftwards = carriage return, U+21B5 NEW. |
static char |
_cup
∪ ∪ = ∪ -- union = cup, U+222A ISOtech. |
static char |
_curren
¤ ¤ = ¤ -- currency sign, U+00A4 ISOnum. |
static char |
_dagger
† † = † -- dagger, U+2020 ISOpub. |
static char |
_Dagger
‡ ‡ = ‡ -- double dagger, U+2021 ISOpub. |
static char |
_darr
↓ ↓ = ↓ -- downwards arrow, U+2193 ISOnum. |
static char |
_dArr
⇓ ⇓ = ⇓ -- downwards double arrow, U+21D3 ISOamsa. |
static char |
_deg
° ° = ° -- degree sign, U+00B0 ISOnum. |
static char |
_delta
δ δ = δ -- greek small letter delta, U+03B4 ISOgrk3. |
static char |
_Delta
Δ Δ = Δ -- greek capital letter delta, U+0394 ISOgrk3. |
static char |
_diams
♦ ♦ = ♦ -- black diamond suit, U+2666 ISOpub. |
static char |
_divide
÷ ÷ = ÷ -- division sign, U+00F7 ISOnum. |
static char |
_eacute
é é = é -- latin small letter e with acute, U+00E9 ISOlat1. |
static char |
_Eacute
É É = É -- latin capital letter E with acute, U+00C9 ISOlat1. |
static char |
_ecirc
ê ê = ê -- latin small letter e with circumflex, U+00EA ISOlat1. |
static char |
_Ecirc
Ê Ê = Ê -- latin capital letter E with circumflex, U+00CA ISOlat1. |
static char |
_egrave
è è = è -- latin small letter e with grave, U+00E8 ISOlat1. |
static char |
_Egrave
È È = È -- latin capital letter E with grave, U+00C8 ISOlat1. |
static char |
_empty
∅ ∅ = ∅ -- empty set = null set = diameter, U+2205 ISOamso. |
static char |
_emsp
  =   -- em space, U+2003 ISOpub. |
static char |
_ensp
  =   -- en space, U+2002 ISOpub. |
static char |
_epsilon
ε ε = ε -- greek small letter epsilon, U+03B5 ISOgrk3. |
static char |
_Epsilon
Ε Ε = Ε -- greek capital letter epsilon, U+0395. |
static char |
_equiv
≡ ≡ = ≡ -- identical to, U+2261 ISOtech. |
static char |
_eta
η η = η -- greek small letter eta, U+03B7 ISOgrk3. |
static char |
_Eta
Η Η = Η -- greek capital letter eta, U+0397. |
static char |
_eth
ð ð = ð -- latin small letter eth, U+00F0 ISOlat1. |
static char |
_ETH
Ð Ð = Ð -- latin capital letter ETH, U+00D0 ISOlat1. |
static char |
_euml
ë ë = ë -- latin small letter e with diaeresis, U+00EB ISOlat1. |
static char |
_Euml
Ë Ë = Ë -- latin capital letter E with diaeresis, U+00CB ISOlat1. |
static char |
_euro
€ € = € -- euro sign, U+20AC NEW. |
static char |
_exist
∃ ∃ = ∃ -- there exists, U+2203 ISOtech. |
static char |
_fnof
ƒ ƒ = ƒ -- latin small letter f with hook = function = florin, U+0192 ISOtech. |
static char |
_forall
∀ ∀ = ∀ -- for all, U+2200 ISOtech. |
static char |
_frac12
½ ½ = ½ -- vulgar fraction one half = fraction one half, U+00BD ISOnum. |
static char |
_frac14
¼ ¼ = ¼ -- vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum. |
static char |
_frac34
¾ ¾ = ¾ -- vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum. |
static char |
_frasl
⁄ ⁄ = ⁄ -- fraction slash, U+2044 NEW. |
static char |
_gamma
γ γ = γ -- greek small letter gamma, U+03B3 ISOgrk3. |
static char |
_Gamma
Γ Γ = Γ -- greek capital letter gamma, U+0393 ISOgrk3. |
static char |
_ge
≥ ≥ = ≥ -- greater-than or equal to, U+2265 ISOtech. |
static char |
_gt
> > = > -- greater-than sign, U+003E ISOnum. |
static char |
_harr
↔ ↔ = ↔ -- left right arrow, U+2194 ISOamsa. |
static char |
_hArr
⇔ ⇔ = ⇔ -- left right double arrow, U+21D4 ISOamsa. |
static char |
_hearts
♥ ♥ = ♥ -- black heart suit = valentine, U+2665 ISOpub. |
static char |
_hellip
… … = … -- horizontal ellipsis = three dot leader, U+2026 ISOpub. |
static char |
_iacute
í í = í -- latin small letter i with acute, U+00ED ISOlat1. |
static char |
_Iacute
Í Í = Í -- latin capital letter I with acute, U+00CD ISOlat1. |
static char |
_icirc
î î = î -- latin small letter i with circumflex, U+00EE ISOlat1. |
static char |
_Icirc
Î Î = Î -- latin capital letter I with circumflex, U+00CE ISOlat1. |
static char |
_iexcl
¡ ¡ = ¡ -- inverted exclamation mark, U+00A1 ISOnum. |
static char |
_igrave
ì ì = ì -- latin small letter i with grave, U+00EC ISOlat1. |
static char |
_Igrave
Ì Ì = Ì -- latin capital letter I with grave, U+00CC ISOlat1. |
static char |
_image
ℑ ℑ = ℑ -- black-letter capital I = imaginary part, U+2111 ISOamso. |
static char |
_infin
∞ ∞ = ∞ -- infinity, U+221E ISOtech. |
static char |
_int
∫ ∫ = ∫ -- integral, U+222B ISOtech. |
static char |
_iota
ι ι = ι -- greek small letter iota, U+03B9 ISOgrk3. |
static char |
_Iota
Ι Ι = Ι -- greek capital letter iota, U+0399. |
static char |
_iquest
¿ ¿ = ¿ -- inverted question mark = turned question mark, U+00BF ISOnum. |
static char |
_isin
∈ ∈ = ∈ -- element of, U+2208 ISOtech. |
static char |
_iuml
ï ï = ï -- latin small letter i with diaeresis, U+00EF ISOlat1. |
static char |
_Iuml
Ï Ï = Ï -- latin capital letter I with diaeresis, U+00CF ISOlat1. |
static char |
_kappa
κ κ = κ -- greek small letter kappa, U+03BA ISOgrk3. |
static char |
_Kappa
Κ Κ = Κ -- greek capital letter kappa, U+039A. |
static char |
_lambda
λ λ = λ -- greek small letter lambda, U+03BB ISOgrk3. |
static char |
_Lambda
Λ Λ = Λ -- greek capital letter lambda, U+039B ISOgrk3. |
static char |
_lang
⟨ ⟨ = 〈 -- left-pointing angle bracket = bra, U+2329 ISOtech(see comments). |
static char |
_laquo
« « = « -- left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum. |
static char |
_larr
← ← = ← -- leftwards arrow, U+2190 ISOnum. |
static char |
_lArr
⇐ ⇐ = ⇐ -- leftwards double arrow, U+21D0 ISOtech(see comments). |
static char |
_lceil
⌈ ⌈ = ⌈ -- left ceiling = APL upstile, U+2308 ISOamsc. |
static char |
_ldquo
“ “ = “ -- left double quotation mark, U+201C ISOnum. |
static char |
_le
≤ ≤ = ≤ -- less-than or equal to, U+2264 ISOtech. |
static char |
_lfloor
⌊ ⌊ = ⌊ -- left floor = APL downstile, U+230A ISOamsc. |
static char |
_lowast
∗ ∗ = ∗ -- asterisk operator, U+2217 ISOtech. |
static char |
_loz
◊ ◊ = ◊ -- lozenge, U+25CA ISOpub. |
static char |
_lrm
‎ = ‎ -- left-to-right mark, U+200E NEW RFC 2070. |
static char |
_lsaquo
‹ ‹ = ‹ -- single left-pointing angle quotation mark, U+2039 ISO proposed(see comments). |
static char |
_lsquo
‘ ‘ = ‘ -- left single quotation mark, U+2018 ISOnum. |
static char |
_lt
< < = < -- less-than sign, U+003C ISOnum. |
static char |
_macr
¯ ¯ = ¯ -- macron = spacing macron = overline = APL overbar, U+00AF ISOdia. |
static char |
_mdash
— — = — -- em dash, U+2014 ISOpub. |
static char |
_micro
µ µ = µ -- micro sign, U+00B5 ISOnum. |
static char |
_middot
· · = · -- middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum. |
static char |
_minus
− − = − -- minus sign, U+2212 ISOtech. |
static char |
_mu
μ μ = μ -- greek small letter mu, U+03BC ISOgrk3. |
static char |
_Mu
Μ Μ = Μ -- greek capital letter mu, U+039C. |
static char |
_nabla
∇ ∇ = ∇ -- nabla = backward difference, U+2207 ISOtech. |
static char |
_nbsp
=   -- no-break space = non-breaking space, U+00A0 ISOnum. |
static char |
_ndash
– – = – -- en dash, U+2013 ISOpub. |
static char |
_ne
≠ ≠ = ≠ -- not equal to, U+2260 ISOtech. |
static char |
_ni
∋ ∋ = ∋ -- contains as member, U+220B ISOtech(see comments). |
static char |
_not
¬ ¬ = ¬ -- not sign = angled dash, U+00AC ISOnum. |
static char |
_notin
∉ ∉ = ∉ -- not an element of, U+2209 ISOtech. |
static char |
_nsub
⊄ ⊄ = ⊄ -- not a subset of, U+2284 ISOamsn. |
static char |
_ntilde
ñ ñ = ñ -- latin small letter n with tilde, U+00F1 ISOlat1. |
static char |
_Ntilde
Ñ Ñ = Ñ -- latin capital letter N with tilde, U+00D1 ISOlat1. |
static char |
_nu
ν ν = ν -- greek small letter nu, U+03BD ISOgrk3. |
static char |
_Nu
Ν Ν = Ν -- greek capital letter nu, U+039D. |
static char |
_oacute
ó ó = ó -- latin small letter o with acute, U+00F3 ISOlat1. |
static char |
_Oacute
Ó Ó = Ó -- latin capital letter O with acute, U+00D3 ISOlat1. |
static char |
_ocirc
ô ô = ô -- latin small letter o with circumflex, U+00F4 ISOlat1. |
static char |
_Ocirc
Ô Ô = Ô -- latin capital letter O with circumflex, U+00D4 ISOlat1. |
static char |
_oelig
œ œ = œ -- latin small ligature oe, U+0153 ISOlat2(see comments). |
static char |
_OElig
ΠΠ= Π-- latin capital ligature OE, U+0152 ISOlat2. |
static char |
_ograve
ò ò = ò -- latin small letter o with grave, U+00F2 ISOlat1. |
static char |
_Ograve
Ò Ò = Ò -- latin capital letter O with grave, U+00D2 ISOlat1. |
static char |
_oline
‾ ‾ = ‾ -- overline = spacing overscore, U+203E NEW. |
static char |
_omega
ω ω = ω -- greek small letter omega, U+03C9 ISOgrk3. |
static char |
_Omega
Ω Ω = Ω -- greek capital letter omega, U+03A9 ISOgrk3. |
static char |
_omicron
ο ο = ο -- greek small letter omicron, U+03BF NEW. |
static char |
_Omicron
Ο Ο = Ο -- greek capital letter omicron, U+039F. |
static char |
_oplus
⊕ ⊕ = ⊕ -- circled plus = direct sum, U+2295 ISOamsb. |
static char |
_or
∨ ∨ = ∨ -- logical or = vee, U+2228 ISOtech. |
static char |
_ordf
ª ª = ª -- feminine ordinal indicator, U+00AA ISOnum. |
static char |
_ordm
º º = º -- masculine ordinal indicator, U+00BA ISOnum. |
static char |
_oslash
ø ø = ø -- latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1. |
static char |
_Oslash
Ø Ø = Ø -- latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1. |
static char |
_otilde
õ õ = õ -- latin small letter o with tilde, U+00F5 ISOlat1. |
static char |
_Otilde
Õ Õ = Õ -- latin capital letter O with tilde, U+00D5 ISOlat1. |
static char |
_otimes
⊗ ⊗ = ⊗ -- circled times = vector product, U+2297 ISOamsb. |
static char |
_ouml
ö ö = ö -- latin small letter o with diaeresis, U+00F6 ISOlat1. |
static char |
_Ouml
Ö Ö = Ö -- latin capital letter O with diaeresis, U+00D6 ISOlat1. |
static char |
_para
¶ ¶ = ¶ -- pilcrow sign = paragraph sign, U+00B6 ISOnum. |
static char |
_part
∂ ∂ = ∂ -- partial differential, U+2202 ISOtech. |
static char |
_permil
‰ ‰ = ‰ -- per mille sign, U+2030 ISOtech. |
static char |
_perp
⊥ ⊥ = ⊥ -- up tack = orthogonal to = perpendicular, U+22A5 ISOtech. |
static char |
_phi
φ φ = φ -- greek small letter phi, U+03C6 ISOgrk3. |
static char |
_Phi
Φ Φ = Φ -- greek capital letter phi, U+03A6 ISOgrk3. |
static char |
_pi
π π = π -- greek small letter pi, U+03C0 ISOgrk3. |
static char |
_Pi
Π Π = Π -- greek capital letter pi, U+03A0 ISOgrk3. |
static char |
_piv
ϖ ϖ = ϖ -- greek pi symbol, U+03D6 ISOgrk3. |
static char |
_plusmn
± ± = ± -- plus-minus sign = plus-or-minus sign, U+00B1 ISOnum. |
static char |
_pound
£ £ = £ -- pound sign, U+00A3 ISOnum. |
static char |
_prime
′ ′ = ′ -- prime = minutes = feet, U+2032 ISOtech. |
static char |
_Prime
″ ″ = ″ -- double prime = seconds = inches, U+2033 ISOtech. |
static char |
_prod
∏ ∏ = ∏ -- n-ary product = product sign, U+220F ISOamsb(see comments). |
static char |
_prop
∝ ∝ = ∝ -- proportional to, U+221D ISOtech. |
static char |
_psi
ψ ψ = ψ -- greek small letter psi, U+03C8 ISOgrk3. |
static char |
_Psi
Ψ Ψ = Ψ -- greek capital letter psi, U+03A8 ISOgrk3. |
static char |
_quot
" " = " -- quotation mark = APL quote, U+0022 ISOnum. |
static char |
_radic
√ √ = √ -- square root = radical sign, U+221A ISOtech. |
static char |
_rang
⟩ ⟩ = 〉 -- right-pointing angle bracket = ket, U+232A ISOtech(see comments). |
static char |
_raquo
» » = » -- right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum. |
static char |
_rarr
→ → = → -- rightwards arrow, U+2192 ISOnum. |
static char |
_rArr
⇒ ⇒ = ⇒ -- rightwards double arrow, U+21D2 ISOtech(see comments). |
static char |
_rceil
⌉ ⌉ = ⌉ -- right ceiling, U+2309 ISOamsc. |
static char |
_rdquo
” ” = ” -- right double quotation mark, U+201D ISOnum. |
static char |
_real
ℜ ℜ = ℜ -- black-letter capital R = real part symbol, U+211C ISOamso. |
static char |
_reg
® ® = ® -- registered sign = registered trade mark sign, U+00AE ISOnum. |
static char |
_rfloor
⌋ ⌋ = ⌋ -- right floor, U+230B ISOamsc. |
static char |
_rho
ρ ρ = ρ -- greek small letter rho, U+03C1 ISOgrk3. |
static char |
_Rho
Ρ Ρ = Ρ -- greek capital letter rho, U+03A1. |
static char |
_rlm
‏ = ‏ -- right-to-left mark, U+200F NEW RFC 2070. |
static char |
_rsaquo
› › = › -- single right-pointing angle quotation mark, U+203A ISO proposed(see comments). |
static char |
_rsquo
’ ’ = ’ -- right single quotation mark, U+2019 ISOnum. |
static char |
_sbquo
‚ ‚ = ‚ -- single low-9 quotation mark, U+201A NEW. |
static char |
_scaron
š š = š -- latin small letter s with caron, U+0161 ISOlat2. |
static char |
_Scaron
Š Š = Š -- latin capital letter S with caron, U+0160 ISOlat2. |
static char |
_sdot
⋅ ⋅ = ⋅ -- dot operator, U+22C5 ISOamsb(see comments). |
static char |
_sect
§ § = § -- section sign, U+00A7 ISOnum. |
static char |
_shy
­ = ­ -- soft hyphen = discretionary hyphen, U+00AD ISOnum. |
static char |
_sigma
σ σ = σ -- greek small letter sigma, U+03C3 ISOgrk3. |
static char |
_Sigma
Σ Σ = Σ -- greek capital letter sigma, U+03A3 ISOgrk3. |
static char |
_sigmaf
ς ς = ς -- greek small letter final sigma, U+03C2 ISOgrk3. |
static char |
_sim
∼ ∼ = ∼ -- tilde operator = varies with = similar to, U+223C ISOtech(see comments). |
static char |
_spades
♠ ♠ = ♠ -- black spade suit, U+2660 ISOpub(see comments). |
static char |
_sub
⊂ ⊂ = ⊂ -- subset of, U+2282 ISOtech. |
static char |
_sube
⊆ ⊆ = ⊆ -- subset of or equal to, U+2286 ISOtech. |
static char |
_sum
∑ ∑ = ∑ -- n-ary summation, U+2211 ISOamsb(see comments). |
static char |
_sup
⊃ ⊃ = ⊃ -- superset of, U+2283 ISOtech(see comments). |
static char |
_sup1
¹ ¹ = ¹ -- superscript one = superscript digit one, U+00B9 ISOnum. |
static char |
_sup2
² ² = ² -- superscript two = superscript digit two = squared, U+00B2 ISOnum. |
static char |
_sup3
³ ³ = ³ -- superscript three = superscript digit three = cubed, U+00B3 ISOnum. |
static char |
_supe
⊇ ⊇ = ⊇ -- superset of or equal to, U+2287 ISOtech. |
static char |
_szlig
ß ß = ß -- latin small letter sharp s = ess-zed, U+00DF ISOlat1. |
static char |
_tau
τ τ = τ -- greek small letter tau, U+03C4 ISOgrk3. |
static char |
_Tau
Τ Τ = Τ -- greek capital letter tau, U+03A4. |
static char |
_there4
∴ ∴ = ∴ -- therefore, U+2234 ISOtech. |
static char |
_theta
θ θ = θ -- greek small letter theta, U+03B8 ISOgrk3. |
static char |
_Theta
Θ Θ = Θ -- greek capital letter theta, U+0398 ISOgrk3. |
static char |
_thetasym
ϑ ϑ = ϑ -- greek small letter theta symbol, U+03D1 NEW. |
static char |
_thinsp
  =   -- thin space, U+2009 ISOpub. |
static char |
_thorn
þ þ = þ -- latin small letter thorn, U+00FE ISOlat1. |
static char |
_THORN
Þ Þ = Þ -- latin capital letter THORN, U+00DE ISOlat1. |
static char |
_tilde
˜ ˜ = ˜ -- small tilde, U+02DC ISOdia. |
static char |
_times
× × = × -- multiplication sign, U+00D7 ISOnum. |
static char |
_trade
™ ™ = ™ -- trade mark sign, U+2122 ISOnum. |
static char |
_uacute
ú ú = ú -- latin small letter u with acute, U+00FA ISOlat1. |
static char |
_Uacute
Ú Ú = Ú -- latin capital letter U with acute, U+00DA ISOlat1. |
static char |
_uarr
↑ ↑ = ↑ -- upwards arrow, U+2191 ISOnum. |
static char |
_uArr
⇑ ⇑ = ⇑ -- upwards double arrow, U+21D1 ISOamsa. |
static char |
_ucirc
û û = û -- latin small letter u with circumflex, U+00FB ISOlat1. |
static char |
_Ucirc
Û Û = Û -- latin capital letter U with circumflex, U+00DB ISOlat1. |
static char |
_ugrave
ù ù = ù -- latin small letter u with grave, U+00F9 ISOlat1. |
static char |
_Ugrave
Ù Ù = Ù -- latin capital letter U with grave, U+00D9 ISOlat1. |
static char |
_uml
¨ ¨ = ¨ -- diaeresis = spacing diaeresis, U+00A8 ISOdia. |
static char |
_upsih
ϒ ϒ = ϒ -- greek upsilon with hook symbol, U+03D2 NEW. |
static char |
_upsilon
υ υ = υ -- greek small letter upsilon, U+03C5 ISOgrk3. |
static char |
_Upsilon
Υ Υ = Υ -- greek capital letter upsilon, U+03A5 ISOgrk3. |
static char |
_uuml
ü ü = ü -- latin small letter u with diaeresis, U+00FC ISOlat1. |
static char |
_Uuml
Ü Ü = Ü -- latin capital letter U with diaeresis, U+00DC ISOlat1. |
static char |
_weierp
℘ ℘ = ℘ -- script capital P = power set = Weierstrass p, U+2118 ISOamso. |
static char |
_xi
ξ ξ = ξ -- greek small letter xi, U+03BE ISOgrk3. |
static char |
_Xi
Ξ Ξ = Ξ -- greek capital letter xi, U+039E ISOgrk3. |
static char |
_yacute
ý ý = ý -- latin small letter y with acute, U+00FD ISOlat1. |
static char |
_Yacute
Ý Ý = Ý -- latin capital letter Y with acute, U+00DD ISOlat1. |
static char |
_yen
¥ ¥ = ¥ -- yen sign = yuan sign, U+00A5 ISOnum. |
static char |
_yuml
ÿ ÿ = ÿ -- latin small letter y with diaeresis, U+00FF ISOlat1. |
static char |
_Yuml
Ÿ Ÿ = Ÿ -- latin capital letter Y with diaeresis, U+0178 ISOlat2. |
static char |
_zeta
ζ ζ = ζ -- greek small letter zeta, U+03B6 ISOgrk3. |
static char |
_Zeta
Ζ Ζ = Ζ -- greek capital letter zeta, U+0396. |
static char |
_zwj
‍ = ‍ -- zero width joiner, U+200D NEW RFC 2070. |
static char |
_zwnj
‌ = ‌ -- zero width non-joiner, U+200C NEW RFC 2070. |
| Fields inherited from class CharacterReference |
INVALID_CODE_POINT |
| Method Summary | |
java.lang.String |
getCharacterReferenceString()
Returns the correct encoded form of this character entity reference. |
static java.lang.String |
getCharacterReferenceString(int codePoint)
Returns the character entity reference encoded form of the specified unicode code point. |
static int |
getCodePointFromName(java.lang.String name)
Returns the unicode code point of the specified character entity reference name. |
java.lang.String |
getDebugInfo()
Returns a string representation of this object useful for debugging purposes. |
java.lang.String |
getName()
Returns the name of this character entity reference. |
static java.lang.String |
getName(char ch)
Returns the character entity reference name of the specified character. |
static java.lang.String |
getName(int codePoint)
Returns the character entity reference name of the specified unicode code point. |
static java.util.Map |
getNameToCodePointMap()
Returns a map of character entity reference names ( String) to unicode code points (Integer). |
| Methods inherited from class Segment |
charAt, compareTo, encloses, encloses, equals, extractText, extractText, findAllCharacterReferences, findAllElements, findAllElements, findAllElements, |