public class TagDereferencer
extends java.lang.Object
NamedEntitiesDereferencer
provides an extremely fast way
to map the set of known HTML tags to unique integer values.
Note: the Elements described below comes from the HTML 4.01 DTD with IE extensions. Also, notice that tag names are case insensitive.
Modifier and Type | Field and Description |
---|---|
static int |
A
Code identifying a "A" tag
|
static int |
ABBR
Code identifying a "ABBR" tag
|
static int |
ACRONYM
Code identifying a "ACRONYM" tag
|
static int |
ADDRESS
Code identifying a "ADDRESS" tag
|
static int |
APPLET
Code identifying a "APPLET" tag
|
static int |
AREA
Code identifying a "AREA" tag
|
static int |
B
Code identifying a "B" tag
|
static int |
BASE
Code identifying a "BASE" tag
|
static int |
BASEFONT
Code identifying a "BASEFONT" tag
|
static int |
BDO
Code identifying a "BDO" tag
|
static int |
BIG
Code identifying a "BIG" tag
|
static int |
BLOCKQUOTE
Code identifying a "BLOCKQUOTE" tag
|
static int |
BODY
Code identifying a "BODY" tag
|
static int |
BR
Code identifying a "BR" tag
|
static int |
BUTTON
Code identifying a "BUTTON" tag
|
static int |
CAPTION
Code identifying a "CAPTION" tag
|
static int |
CENTER
Code identifying a "CENTER" tag
|
static int |
CITE
Code identifying a "CITE" tag
|
static int |
CODE
Code identifying a "CODE" tag
|
static int |
COL
Code identifying a "COL" tag
|
static int |
COLGROUP
Code identifying a "COLGROUP" tag
|
static int |
COMMENT
Code identifying a "COMMENT" tag
|
static int |
DD
Code identifying a "DD" tag
|
static int |
DEL
Code identifying a "DEL" tag
|
static int |
DFN
Code identifying a "DFN" tag
|
static int |
DIR
Code identifying a "DIR" tag
|
static int |
DIV
Code identifying a "DIV" tag
|
static int |
DL
Code identifying a "DL" tag
|
static int |
DT
Code identifying a "DT" tag
|
static int |
EM
Code identifying a "EM" tag
|
static int |
EMBED
Code identifying a "EMBED" tag
|
static int |
FIELDSET
Code identifying a "FIELDSET" tag
|
static int |
FONT
Code identifying a "FONT" tag
|
static int |
FORM
Code identifying a "FORM" tag
|
static int |
FRAME
Code identifying a "FRAME" tag
|
static int |
FRAMESET
Code identifying a "FRAMESET" tag
|
static int |
H1
Code identifying a "H1" tag
|
static int |
H2
Code identifying a "H2" tag
|
static int |
H3
Code identifying a "H3" tag
|
static int |
H4
Code identifying a "H4" tag
|
static int |
H5
Code identifying a "H5" tag
|
static int |
H6
Code identifying a "H6" tag
|
static int |
HEAD
Code identifying a "HEAD" tag
|
static int |
HR
Code identifying a "HR" tag
|
static int |
HTML
Code identifying a "HTML" tag
|
static int |
I
Code identifying a "I" tag
|
static int |
IFRAME
Code identifying a "IFRAME" tag
|
static int |
IMG
Code identifying a "IMG" tag
|
static int |
INPUT
Code identifying a "INPUT" tag
|
static int |
INS
Code identifying a "INS" tag
|
static int |
ISINDEX
Code identifying a "ISINDEX" tag
|
static int |
KBD
Code identifying a "KBD" tag
|
static int |
LABEL
Code identifying a "LABEL" tag
|
static int |
LEGEND
Code identifying a "LEGEND" tag
|
static int |
LI
Code identifying a "LI" tag
|
static int |
LINK
Code identifying a "LINK" tag
|
static int |
MAP
Code identifying a "MAP" tag
|
static int |
MENU
Code identifying a "MENU" tag
|
static int |
META
Code identifying a "META" tag
|
static int |
NOFRAMES
Code identifying a "NOFRAMES" tag
|
static int |
NOSCRIPT
Code identifying a "NOSCRIPT" tag
|
static int |
OBJECT
Code identifying a "OBJECT" tag
|
static int |
OL
Code identifying a "OL" tag
|
static int |
OPTGROUP
Code identifying a "OPTGROUP" tag
|
static int |
OPTION
Code identifying a "OPTION" tag
|
static int |
P
Code identifying a "P" tag
|
static int |
PARAM
Code identifying a "PARAM" tag
|
static int |
PLAINTEXT
Code identifying a "PLAINTEXT" tag
|
static int |
PRE
Code identifying a "PRE" tag
|
static int |
Q
Code identifying a "Q" tag
|
static int |
S
Code identifying a "S" tag
|
static int |
SAMP
Code identifying a "SAMP" tag
|
static int |
SCRIPT
Code identifying a "SCRIPT" tag
|
static int |
SELECT
Code identifying a "SELECT" tag
|
static int |
SMALL
Code identifying a "SMALL" tag
|
static int |
SPAN
Code identifying a "SPAN" tag
|
static int |
STRIKE
Code identifying a "STRIKE" tag
|
static int |
STRONG
Code identifying a "STRONG" tag
|
static int |
STYLE
Code identifying a "STYLE" tag
|
static int |
SUB
Code identifying a "SUB" tag
|
static int |
SUP
Code identifying a "SUP" tag
|
static int |
TABLE
Code identifying a "TABLE" tag
|
static int |
TBODY
Code identifying a "TBODY" tag
|
static int |
TD
Code identifying a "TD" tag
|
static int |
TEXTAREA
Code identifying a "TEXTAREA" tag
|
static int |
TFOOT
Code identifying a "TFOOT" tag
|
static int |
TH
Code identifying a "TH" tag
|
static int |
THEAD
Code identifying a "THEAD" tag
|
static int |
TITLE
Code identifying a "TITLE" tag
|
static int |
TR
Code identifying a "TR" tag
|
static int |
TT
Code identifying a "TT" tag
|
static int |
U
Code identifying a "U" tag
|
static int |
UL
Code identifying a "UL" tag
|
static int |
UNKNOWN
Code identifying an unknown, possibly invalid, tag
|
static int |
VAR
Code identifying a "VAR" tag
|
static int |
WBR
Code identifying a "WBR" tag
|
static int |
XMP
Code identifying a "XMP" tag
|
Constructor and Description |
---|
TagDereferencer() |
Modifier and Type | Method and Description |
---|---|
static int |
hashCode(byte[] b,
int offset,
int count)
Returns the hash code of the given string, automatically converting the chars to upper case.
|
static char |
toCode(byte[] b,
int offset,
int count)
Get the code associated to a key.
|
public static final int UNKNOWN
public static final int A
public static final int ABBR
public static final int ACRONYM
public static final int ADDRESS
public static final int APPLET
public static final int AREA
public static final int B
public static final int BASE
public static final int BASEFONT
public static final int BDO
public static final int BIG
public static final int BLOCKQUOTE
public static final int BODY
public static final int BR
public static final int BUTTON
public static final int CAPTION
public static final int CENTER
public static final int CITE
public static final int CODE
public static final int COL
public static final int COLGROUP
public static final int COMMENT
public static final int DD
public static final int DEL
public static final int DFN
public static final int DIR
public static final int DIV
public static final int DL
public static final int DT
public static final int EM
public static final int EMBED
public static final int FIELDSET
public static final int FONT
public static final int FORM
public static final int FRAME
public static final int FRAMESET
public static final int H1
public static final int H2
public static final int H3
public static final int H4
public static final int H5
public static final int H6
public static final int HEAD
public static final int HR
public static final int HTML
public static final int I
public static final int IFRAME
public static final int IMG
public static final int INPUT
public static final int INS
public static final int ISINDEX
public static final int KBD
public static final int LABEL
public static final int LEGEND
public static final int LI
public static final int LINK
public static final int MAP
public static final int MENU
public static final int META
public static final int NOFRAMES
public static final int NOSCRIPT
public static final int OBJECT
public static final int OL
public static final int OPTGROUP
public static final int OPTION
public static final int P
public static final int PARAM
public static final int PLAINTEXT
public static final int PRE
public static final int Q
public static final int S
public static final int SAMP
public static final int SCRIPT
public static final int SELECT
public static final int SMALL
public static final int SPAN
public static final int STRIKE
public static final int STRONG
public static final int STYLE
public static final int SUB
public static final int SUP
public static final int TABLE
public static final int TBODY
public static final int TD
public static final int TEXTAREA
public static final int TFOOT
public static final int TH
public static final int THEAD
public static final int TITLE
public static final int TR
public static final int TT
public static final int U
public static final int UL
public static final int VAR
public static final int WBR
public static final int XMP
public static int hashCode(byte[] b, int offset, int count)
b
- offset
- count
- public static char toCode(byte[] b, int offset, int count)
b
- byte array containing the keyoffset
- position of the first byte of the key in the arraycount
- number of bytes composing the key