á á = á
-- latin small letter a with acute, U+00E1 ISOlat1.
â â = â
-- latin small letter a with circumflex, U+00E2 ISOlat1.
´ ´ = ´
-- acute accent = spacing acute, U+00B4 ISOdia.
æ æ = æ
-- latin small letter ae = latin small ligature ae, U+00E6 ISOlat1.
à à = à
-- latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1.
ℵ ℵ = ℵ
-- alef symbol = first transfinite cardinal, U+2135 NEW
(see
comments).
α α = α
-- greek small letter alpha, U+03B1 ISOgrk3.
& & = &
-- ampersand, U+0026 ISOnum.
∧ ∧ = ∧
-- logical and = wedge, U+2227 ISOtech.
∠ ∠ = ∠
-- angle, U+2220 ISOamso.
' ' = '
-- apostrophe = APL quote, U+0027 ISOnum
(see
comments).
å å = å
-- latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1.
≈ ≈ = ≈
-- almost equal to = asymptotic to, U+2248 ISOamsr.
ã ã = ã
-- latin small letter a with tilde, U+00E3 ISOlat1.
ä ä = ä
-- latin small letter a with diaeresis, U+00E4 ISOlat1.
„ „ = „
-- double low-9 quotation mark, U+201E NEW.
β β = β
-- greek small letter beta, U+03B2 ISOgrk3.
¦ ¦ = ¦
-- broken bar = broken vertical bar, U+00A6 ISOnum.
• • = •
-- bullet = black small circle, U+2022 ISOpub
(see
comments).
∩ ∩ = ∩
-- intersection = cap, U+2229 ISOtech.
ç ç = ç
-- latin small letter c with cedilla, U+00E7 ISOlat1.
¸ ¸ = ¸
-- cedilla = spacing cedilla, U+00B8 ISOdia.
¢ ¢ = ¢
-- cent sign, U+00A2 ISOnum.
χ χ = χ
-- greek small letter chi, U+03C7 ISOgrk3.
ˆ ˆ = ˆ
-- modifier letter circumflex accent, U+02C6 ISOpub.
♣ ♣ = ♣
-- black club suit = shamrock, U+2663 ISOpub.
≅ ≅ = ≅
-- approximately equal to, U+2245 ISOtech.
© © = ©
-- copyright sign, U+00A9 ISOnum.
↵ ↵ = ↵
-- downwards arrow with corner leftwards = carriage return, U+21B5 NEW.
∪ ∪ = ∪
-- union = cup, U+222A ISOtech.
¤ ¤ = ¤
-- currency sign, U+00A4 ISOnum.
‡ ‡ = ‡
-- double dagger, U+2021 ISOpub.
⇓ ⇓ = ⇓
-- downwards double arrow, U+21D3 ISOamsa.
° ° = °
-- degree sign, U+00B0 ISOnum.
δ δ = δ
-- greek small letter delta, U+03B4 ISOgrk3.
♦ ♦ = ♦
-- black diamond suit, U+2666 ISOpub.
÷ ÷ = ÷
-- division sign, U+00F7 ISOnum.
é é = é
-- latin small letter e with acute, U+00E9 ISOlat1.
ê ê = ê
-- latin small letter e with circumflex, U+00EA ISOlat1.
è è = è
-- latin small letter e with grave, U+00E8 ISOlat1.
∅ ∅ = ∅
-- empty set = null set = diameter, U+2205 ISOamso.
  =  
-- em space, U+2003 ISOpub.
  =  
-- en space, U+2002 ISOpub.
ε ε = ε
-- greek small letter epsilon, U+03B5 ISOgrk3.
≡ ≡ = ≡
-- identical to, U+2261 ISOtech.
η η = η
-- greek small letter eta, U+03B7 ISOgrk3.
ð ð = ð
-- latin small letter eth, U+00F0 ISOlat1.
ë ë = ë
-- latin small letter e with diaeresis, U+00EB ISOlat1.
€ € = €
-- euro sign, U+20AC NEW.
∃ ∃ = ∃
-- there exists, U+2203 ISOtech.
ƒ ƒ = ƒ
-- latin small letter f with hook = function = florin, U+0192 ISOtech.
∀ ∀ = ∀
-- for all, U+2200 ISOtech.
½ ½ = ½
-- vulgar fraction one half = fraction one half, U+00BD ISOnum.
¼ ¼ = ¼
-- vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum.
¾ ¾ = ¾
-- vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum.
⁄ ⁄ = ⁄
-- fraction slash, U+2044 NEW.
γ γ = γ
-- greek small letter gamma, U+03B3 ISOgrk3.
≥ ≥ = ≥
-- greater-than or equal to, U+2265 ISOtech.
> > = >
-- greater-than sign, U+003E ISOnum.
⇔ ⇔ = ⇔
-- left right double arrow, U+21D4 ISOamsa.
♥ ♥ = ♥
-- black heart suit = valentine, U+2665 ISOpub.
… … = …
-- horizontal ellipsis = three dot leader, U+2026 ISOpub.
í í = í
-- latin small letter i with acute, U+00ED ISOlat1.
î î = î
-- latin small letter i with circumflex, U+00EE ISOlat1.
¡ ¡ = ¡
-- inverted exclamation mark, U+00A1 ISOnum.
ì ì = ì
-- latin small letter i with grave, U+00EC ISOlat1.
ℑ ℑ = ℑ
-- black-letter capital I = imaginary part, U+2111 ISOamso.
∞ ∞ = ∞
-- infinity, U+221E ISOtech.
∫ ∫ = ∫
-- integral, U+222B ISOtech.
ι ι = ι
-- greek small letter iota, U+03B9 ISOgrk3.
¿ ¿ = ¿
-- inverted question mark = turned question mark, U+00BF ISOnum.
∈ ∈ = ∈
-- element of, U+2208 ISOtech.
ï ï = ï
-- latin small letter i with diaeresis, U+00EF ISOlat1.
κ κ = κ
-- greek small letter kappa, U+03BA ISOgrk3.
λ λ = λ
-- greek small letter lambda, U+03BB ISOgrk3.
〈 ⟨ = 〈
-- left-pointing angle bracket = bra, U+2329 ISOtech
(see
comments).
« « = «
-- left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum.
⇐ ⇐ = ⇐
-- leftwards double arrow, U+21D0 ISOtech
(see
comments).
⌈ ⌈ = ⌈
-- left ceiling = APL upstile, U+2308 ISOamsc.
“ “ = “
-- left double quotation mark, U+201C ISOnum.
≤ ≤ = ≤
-- less-than or equal to, U+2264 ISOtech.
⌊ ⌊ = ⌊
-- left floor = APL downstile, U+230A ISOamsc.
∗ ∗ = ∗
-- asterisk operator, U+2217 ISOtech.
◊ ◊ = ◊
-- lozenge, U+25CA ISOpub.
‎ = ‎
-- left-to-right mark, U+200E NEW RFC 2070.
‹ ‹ = ‹
-- single left-pointing angle quotation mark, U+2039 ISO proposed
(see
comments).
‘ ‘ = ‘
-- left single quotation mark, U+2018 ISOnum.
< < = <
-- less-than sign, U+003C ISOnum.
¯ ¯ = ¯
-- macron = spacing macron = overline = APL overbar, U+00AF ISOdia.
— — = —
-- em dash, U+2014 ISOpub.
µ µ = µ
-- micro sign, U+00B5 ISOnum.
· · = ·
-- middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum.
− − = −
-- minus sign, U+2212 ISOtech.
μ μ = μ
-- greek small letter mu, U+03BC ISOgrk3.
∇ ∇ = ∇
-- nabla = backward difference, U+2207 ISOtech.
=  
-- no-break space = non-breaking space, U+00A0 ISOnum.
– – = –
-- en dash, U+2013 ISOpub.
≠ ≠ = ≠
-- not equal to, U+2260 ISOtech.
∋ ∋ = ∋
-- contains as member, U+220B ISOtech
(see
comments).
¬ ¬ = ¬
-- not sign = angled dash, U+00AC ISOnum.
∉ ∉ = ∉
-- not an element of, U+2209 ISOtech.
⊄ ⊄ = ⊄
-- not a subset of, U+2284 ISOamsn.
ñ ñ = ñ
-- latin small letter n with tilde, U+00F1 ISOlat1.
ν ν = ν
-- greek small letter nu, U+03BD ISOgrk3.
ó ó = ó
-- latin small letter o with acute, U+00F3 ISOlat1.
ô ô = ô
-- latin small letter o with circumflex, U+00F4 ISOlat1.
œ œ = œ
-- latin small ligature oe, U+0153 ISOlat2
(see
comments).
ò ò = ò
-- latin small letter o with grave, U+00F2 ISOlat1.
‾ ‾ = ‾
-- overline = spacing overscore, U+203E NEW.
ω ω = ω
-- greek small letter omega, U+03C9 ISOgrk3.
ο ο = ο
-- greek small letter omicron, U+03BF NEW.
⊕ ⊕ = ⊕
-- circled plus = direct sum, U+2295 ISOamsb.
∨ ∨ = ∨
-- logical or = vee, U+2228 ISOtech.
ª ª = ª
-- feminine ordinal indicator, U+00AA ISOnum.
º º = º
-- masculine ordinal indicator, U+00BA ISOnum.
ø ø = ø
-- latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1.
õ õ = õ
-- latin small letter o with tilde, U+00F5 ISOlat1.
⊗ ⊗ = ⊗
-- circled times = vector product, U+2297 ISOamsb.
ö ö = ö
-- latin small letter o with diaeresis, U+00F6 ISOlat1.
¶ ¶ = ¶
-- pilcrow sign = paragraph sign, U+00B6 ISOnum.
∂ ∂ = ∂
-- partial differential, U+2202 ISOtech.
‰ ‰ = ‰
-- per mille sign, U+2030 ISOtech.
⊥ ⊥ = ⊥
-- up tack = orthogonal to = perpendicular, U+22A5 ISOtech.
φ φ = φ
-- greek small letter phi, U+03C6 ISOgrk3.
π π = π
-- greek small letter pi, U+03C0 ISOgrk3.
ϖ ϖ = ϖ
-- greek pi symbol, U+03D6 ISOgrk3.
± ± = ±
-- plus-minus sign = plus-or-minus sign, U+00B1 ISOnum.
£ £ = £
-- pound sign, U+00A3 ISOnum.
″ ″ = ″
-- double prime = seconds = inches, U+2033 ISOtech.
∏ ∏ = ∏
-- n-ary product = product sign, U+220F ISOamsb
(see
comments).
∝ ∝ = ∝
-- proportional to, U+221D ISOtech.
ψ ψ = ψ
-- greek small letter psi, U+03C8 ISOgrk3.
" " = "
-- quotation mark = APL quote, U+0022 ISOnum.
√ √ = √
-- square root = radical sign, U+221A ISOtech.
〉 ⟩ = 〉
-- right-pointing angle bracket = ket, U+232A ISOtech
(see
comments).
» » = »
-- right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum.
⇒ ⇒ = ⇒
-- rightwards double arrow, U+21D2 ISOtech
(see
comments).
⌉ ⌉ = ⌉
-- right ceiling, U+2309 ISOamsc.
” ” = ”
-- right double quotation mark, U+201D ISOnum.
ℜ ℜ = ℜ
-- black-letter capital R = real part symbol, U+211C ISOamso.
® ® = ®
-- registered sign = registered trade mark sign, U+00AE ISOnum.
⌋ ⌋ = ⌋
-- right floor, U+230B ISOamsc.
ρ ρ = ρ
-- greek small letter rho, U+03C1 ISOgrk3.
‏ = ‏
-- right-to-left mark, U+200F NEW RFC 2070.
› › = ›
-- single right-pointing angle quotation mark, U+203A ISO proposed
(see
comments).
’ ’ = ’
-- right single quotation mark, U+2019 ISOnum.
‚ ‚ = ‚
-- single low-9 quotation mark, U+201A NEW.
š š = š
-- latin small letter s with caron, U+0161 ISOlat2.
⋅ ⋅ = ⋅
-- dot operator, U+22C5 ISOamsb
(see
comments).
§ § = §
-- section sign, U+00A7 ISOnum.
­ = ­
-- soft hyphen = discretionary hyphen, U+00AD ISOnum.
σ σ = σ
-- greek small letter sigma, U+03C3 ISOgrk3.
ς ς = ς
-- greek small letter final sigma, U+03C2 ISOgrk3.
∼ ∼ = ∼
-- tilde operator = varies with = similar to, U+223C ISOtech
(see
comments).
♠ ♠ = ♠
-- black spade suit, U+2660 ISOpub
(see
comments).
⊂ ⊂ = ⊂
-- subset of, U+2282 ISOtech.
⊆ ⊆ = ⊆
-- subset of or equal to, U+2286 ISOtech.
∑ ∑ = ∑
-- n-ary summation, U+2211 ISOamsb
(see
comments).
⊃ ⊃ = ⊃
-- superset of, U+2283 ISOtech
(see
comments).
¹ ¹ = ¹
-- superscript one = superscript digit one, U+00B9 ISOnum.
² ² = ²
-- superscript two = superscript digit two = squared, U+00B2 ISOnum.
³ ³ = ³
-- superscript three = superscript digit three = cubed, U+00B3 ISOnum.
⊇ ⊇ = ⊇
-- superset of or equal to, U+2287 ISOtech.
ß ß = ß
-- latin small letter sharp s = ess-zed, U+00DF ISOlat1.
τ τ = τ
-- greek small letter tau, U+03C4 ISOgrk3.
∴ ∴ = ∴
-- therefore, U+2234 ISOtech.
θ θ = θ
-- greek small letter theta, U+03B8 ISOgrk3.
ϑ ϑ = ϑ
-- greek small letter theta symbol, U+03D1 NEW.
  =  
-- thin space, U+2009 ISOpub.
þ þ = þ
-- latin small letter thorn, U+00FE ISOlat1.
˜ ˜ = ˜
-- small tilde, U+02DC ISOdia.
× × = ×
-- multiplication sign, U+00D7 ISOnum.
™ ™ = ™
-- trade mark sign, U+2122 ISOnum.
ú ú = ú
-- latin small letter u with acute, U+00FA ISOlat1.
⇑ ⇑ = ⇑
-- upwards double arrow, U+21D1 ISOamsa.
û û = û
-- latin small letter u with circumflex, U+00FB ISOlat1.
ù ù = ù
-- latin small letter u with grave, U+00F9 ISOlat1.
¨ ¨ = ¨
-- diaeresis = spacing diaeresis, U+00A8 ISOdia.
ϒ ϒ = ϒ
-- greek upsilon with hook symbol, U+03D2 NEW.
υ υ = υ
-- greek small letter upsilon, U+03C5 ISOgrk3.
ü ü = ü
-- latin small letter u with diaeresis, U+00FC ISOlat1.
℘ ℘ = ℘
-- script capital P = power set = Weierstrass p, U+2118 ISOamso.
ξ ξ = ξ
-- greek small letter xi, U+03BE ISOgrk3.
ý ý = ý
-- latin small letter y with acute, U+00FD ISOlat1.
¥ ¥ = ¥
-- yen sign = yuan sign, U+00A5 ISOnum.
Ÿ Ÿ = Ÿ
-- latin capital letter Y with diaeresis, U+0178 ISOlat2.
ζ ζ = ζ
-- greek small letter zeta, U+03B6 ISOgrk3.
‍ = ‍
-- zero width joiner, U+200D NEW RFC 2070.
‌ = ‌
-- zero width non-joiner, U+200C NEW RFC 2070.
Returns the contents of the specified
attributes map as HTML attribute name/value pairs.
Generates the HTML text of a
normal end tag with the specified tag
name.
Returns the
Attribute
with the specified name (case insensitive).
Returns the
FormField
with the specified
name.
Returns the attributes specified in this element's start tag.
Returns the attributes specified in this start tag.
Returns the
decoded value of the attribute with the specified name (case insensitive).
Returns the
decoded value of the attribute with the specified name (case insensitive).
Returns the character position in the
Source
document at which this segment begins.
Returns the size of the indent to be used for anything other than
LI
elements.
Returns a string representation of the tag cache, useful for debugging purposes.
Returns the character represented by this character reference.
Returns the correct encoded form of this character entity reference.
Returns the encoded form of this character reference.
Returns the correct encoded form of this numeric character reference.
Returns the character entity reference encoded form of the specified unicode code point.
Returns the encoded form of the specified unicode code point.
Returns the numeric character reference encoded form of the specified unicode code point.
Returns a list of the immediate children of this element in the document element hierarchy.
Returns a list of the immediate children of this segment in the document element hierarchy.
Returns a list of the top-level
elements in the document element hierarchy.
Returns the character sequence that marks the end of the tag.
Returns the
unicode code point represented by this character reference.
Parses a single encoded character reference text into a unicode code point.
Returns the unicode code point of the specified character entity reference name.
Indicates whether
white space in the text between the tags is to be collapsed.
Returns the column number of this character position in the source document.
Returns the column number of the specified character position in the source document.
Returns a string array containing the column labels corresponding to the values from the
getColumnValues(Map)
method.
Converts all the
form submission values of the constituent form fields into a simple string array,
suitable for storage in a tabular format such as a database table or
.CSV
file.
Converts the data values in the specified
field data set into a simple string array,
suitable for storage in a tabular format such as a database table or
.CSV
file.
Returns the segment representing the
content of the element.
Indicates whether non-breaking space (CharacterEntityReference._nbsp
) character entity references are converted to spaces.
Indicates whether non-breaking space (CharacterEntityReference._nbsp
) character entity references are converted to spaces.
Returns the number of attributes.
Returns the number of FormField
objects.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns a string representation of this object useful for debugging purposes.
Returns the default maximum error count allowed when parsing attributes.
Returns a set containing the
names of all
deprecated elements in HTML 4.01.
Returns the nesting depth of this element in the document element hierarchy.
Returns a description of this tag type useful for debugging purposes.
Returns the document
encoding specified within the text of the document.
Returns the
element that is ended by this end tag.
Returns the
element representing this form control in the source document.
Returns the
element that is started by this start tag.
Returns the
element that is started or ended by this tag.
Returns the
Element
with the specified
id
attribute value.
Returns the
name of the
Element
that constitues this form control type.
Returns the character encoding scheme of the source byte stream used to create this object.
Returns a filter
Writer
that
encodes all text before passing it through to the specified
Writer
.
Returns a concise description of how the
encoding of the source document was determined.
Returns the character position in the
Source
document immediately after the end of this segment.
Returns the end tag of the element.
Returns the
type of this end tag.
Returns the estimated maximum number of characters in the output, or -1
if no estimate is available.
Returns the estimated maximum number of characters in the output, or -1
if no estimate is available.
Returns the estimated maximum number of characters in the output, or -1
if no estimate is available.
Returns the estimated maximum number of characters in the output, or -1
if no estimate is available.
Returns a collection of all the constituent
form controls in this field.
Returns the
type of this form control.
Indicates whether all elements are to be indented, including
inline-level elements and those with preformatted contents.
Returns the string to be used for indentation.
Returns the name of this attribute in lower case.
Returns the bullet characters to use for list items inside
UL
elements.
Returns the size of the indent to be used for
LI
elements.
Returns the
Logger
that handles log messages.
Creates a new
Logger
instance with the specified name.
Returns the destination Writer
for log messages.
Returns the column at which lines are to be wrapped.
Returns the name of this attribute in original case.
Returns the name of this character entity reference.
Returns the name of this compatibility mode.
Returns the
name of the
start tag of this element, always in lower case.
Returns the
name of the control.
Returns the name of this tag, always in lower case.
Returns the name of this logger.
Returns the character entity reference name of the specified character.
Returns the character entity reference name of the specified unicode code point.
Returns the
name prefix required by this tag type.
Returns the segment spanning the
name of this attribute.
Returns the segment spanning the
name of this tag.
Returns a map of character entity reference names (String
) to unicode code points (Integer
).
Returns a set containing the
names of all of the
HTML elements
which should never contain elements of the same name, either as direct or indirect descendants.
Returns the string to be used to represent a
newline in the output.
Returns the
newline character sequence used in the source document.
Returns the string to be used to represent a
newline in the output.
Returns an iterator over the
OPTION
elements contained within this control, in order of appearance.
Returns null
as this exception is never thrown.
Returns the parent of this element in the document element hierarchy.
Returns the character position in the source document.
Returns the preliminary encoding of the source document together with a concise description of how it was determined.
Returns the character used to quote the value.
Returns a list of all the currently registered tag types in order of lowest to highest
precedence.
Performs a simple rendering of the HTML markup in this segment into text.
Returns the row number of this character position in the source document.
Returns the row number of the specified character position in the source document.
Returns a
RowColumnVector
object representing the row and column number of the specified character position in the source document.
Formats the HTML source by laying out each non-inline-level element on a new line with an appropriate indent.
Returns the original source text upon which this output document is based.
Returns the character sequence that marks the start of the tag.
Returns the start tag of the element.
Returns the
type of this start tag.
Returns the text loaded from the specified Reader
as a string.
Returns the string that is to separate table cells.
Returns the
Tag
at the specified position in the source document.
Returns the segment between the end of the tag's
name and the start of its
end delimiter.
Returns the
type of this tag.
Returns the
type of this tag.
Returns the
type of this tag.
Returns an array of all the tag types inside which the parser ignores all other non-
server tags
in
parse on demand mode.
Extracts the textual content from the HTML markup of this segment.
Indicates whether the original text of each tag is to be replaced with the output from its
Tag.tidy()
method.
Returns the unicode code point of this character reference in
U+ notation.
Returns the specified unicode code point in
U+ notation.
Returns the general purpose user data object that has previously been associated with this tag via the
setUserData(Object)
method.
Returns the
decoded value of the attribute with the specified name (case insensitive).
Returns the segment spanning the
value of this attribute, or
null
if it
has no value.
Returns the segment spanning the
value of this attribute, including quotation marks if any,
or
null
if it
has no value.
Returns the Writer
to which all output is sent.