PageParser
public final class FastPageParser extends Object implements PageParser
Produces FastPage.
Modifier and Type | Class | Description |
---|---|---|
private class |
FastPageParser.Tag |
Deprecated.
|
Modifier and Type | Field | Description |
---|---|---|
private static int |
BODY_HASH |
Deprecated.
|
private static int |
CONTENT_HASH |
Deprecated.
|
private static int |
FRAME_HASH |
Deprecated.
|
private static int |
FRAMESET_HASH |
Deprecated.
|
private static int |
HEAD_HASH |
Deprecated.
|
private static int |
HTML_HASH |
Deprecated.
|
private static int |
META_HASH |
Deprecated.
|
private static int |
PARAMETER_HASH |
Deprecated.
|
private static int |
SLASH_BODY_HASH |
Deprecated.
|
private static int |
SLASH_HEAD_HASH |
Deprecated.
|
private static int |
SLASH_HTML_HASH |
Deprecated.
|
private static int |
SLASH_TITLE_HASH |
Deprecated.
|
private static int |
SLASH_XML_HASH |
Deprecated.
|
private static int |
SLASH_XMP_HASH |
Deprecated.
|
private static int |
STATE_CDATA |
Deprecated.
|
private static int |
STATE_COMMENT |
Deprecated.
|
private static int |
STATE_DOCTYPE |
Deprecated.
|
private static int |
STATE_EOF |
Deprecated.
|
private static int |
STATE_SCRIPT |
Deprecated.
|
private static int |
STATE_TAG |
Deprecated.
|
private static int |
STATE_TAG_QUOTE |
Deprecated.
|
private static int |
STATE_TEXT |
Deprecated.
|
private static int |
TAG_STATE_BODY |
Deprecated.
|
private static int |
TAG_STATE_HEAD |
Deprecated.
|
private static int |
TAG_STATE_HTML |
Deprecated.
|
private static int |
TAG_STATE_NONE |
Deprecated.
|
private static int |
TAG_STATE_TITLE |
Deprecated.
|
private static int |
TAG_STATE_XML |
Deprecated.
|
private static int |
TAG_STATE_XMP |
Deprecated.
|
private static int |
TITLE_HASH |
Deprecated.
|
private static int |
TOKEN_CDATA |
Deprecated.
|
private static int |
TOKEN_COMMENT |
Deprecated.
|
private static int |
TOKEN_DOCTYPE |
Deprecated.
|
private static int |
TOKEN_EMPTYTAG |
Deprecated.
|
private static int |
TOKEN_EOF |
Deprecated.
|
private static int |
TOKEN_NONE |
Deprecated.
|
private static int |
TOKEN_SCRIPT |
Deprecated.
|
private static int |
TOKEN_TAG |
Deprecated.
|
private static int |
TOKEN_TEXT |
Deprecated.
|
private static int |
XML_HASH |
Deprecated.
|
private static int |
XMP_HASH |
Deprecated.
|
Constructor | Description |
---|---|
FastPageParser() |
Deprecated.
|
Modifier and Type | Method | Description |
---|---|---|
private FastPage |
internalParse(Reader reader) |
Deprecated.
|
Page |
parse(char[] data) |
Deprecated.
This builds a Page.
|
Page |
parse(Reader reader) |
Deprecated.
|
private static FastPageParser.Tag |
parseProperties(FastPageParser.Tag tag,
CharArray buffer) |
Deprecated.
This is called when we need to extract the properties for the tag from the tag's HTML.
|
private FastPageParser.Tag |
parseTag(FastPageParser.Tag tag,
CharArray buf) |
Deprecated.
Populates a
FastPageParser.Tag object using data from the supplied CharArray . |
private static boolean |
shouldWriteToHead(int state,
int laststate) |
Deprecated.
|
private static void |
writeTag(int state,
int laststate,
boolean hide,
CharArray _head,
CharArray _buffer,
CharArray _body) |
Deprecated.
|
private static final int TOKEN_NONE
private static final int TOKEN_EOF
private static final int TOKEN_TEXT
private static final int TOKEN_TAG
private static final int TOKEN_COMMENT
private static final int TOKEN_CDATA
private static final int TOKEN_SCRIPT
private static final int TOKEN_DOCTYPE
private static final int TOKEN_EMPTYTAG
private static final int STATE_EOF
private static final int STATE_TEXT
private static final int STATE_TAG
private static final int STATE_COMMENT
private static final int STATE_TAG_QUOTE
private static final int STATE_CDATA
private static final int STATE_SCRIPT
private static final int STATE_DOCTYPE
private static final int TAG_STATE_NONE
private static final int TAG_STATE_HTML
private static final int TAG_STATE_HEAD
private static final int TAG_STATE_TITLE
private static final int TAG_STATE_BODY
private static final int TAG_STATE_XML
private static final int TAG_STATE_XMP
private static final int SLASH_XML_HASH
private static final int XML_HASH
private static final int SLASH_XMP_HASH
private static final int XMP_HASH
private static final int HTML_HASH
private static final int SLASH_HTML_HASH
private static final int HEAD_HASH
private static final int TITLE_HASH
private static final int SLASH_TITLE_HASH
private static final int PARAMETER_HASH
private static final int META_HASH
private static final int SLASH_HEAD_HASH
private static final int FRAMESET_HASH
private static final int FRAME_HASH
private static final int BODY_HASH
private static final int SLASH_BODY_HASH
private static final int CONTENT_HASH
public Page parse(char[] data) throws IOException
PageParser
parse
in interface PageParser
IOException
private static void writeTag(int state, int laststate, boolean hide, CharArray _head, CharArray _buffer, CharArray _body)
private static boolean shouldWriteToHead(int state, int laststate)
private FastPageParser.Tag parseTag(FastPageParser.Tag tag, CharArray buf)
FastPageParser.Tag
object using data from the supplied CharArray
.
The supplied tag parameter is reset and reused - this avoids excess object
creation which hwlps performance.private static FastPageParser.Tag parseProperties(FastPageParser.Tag tag, CharArray buffer)
tag
- the tag that is currently being processed. This should be the
tag that was returned as a result of a call to parseTag(FastPageParser.Tag, CharArray)
(ie, it has the name and nameEndIdx fields set correctly for the
tag in question. The properties field can be in an undefined state - it
will get replaced regardless).buffer
- a CharArray containing the entire tag that is being parsed.