|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectinfo.bliki.htmlcleaner.HtmlCleaner
public class HtmlCleaner
Main HtmlCleaner class.
It represents public interface to the user. It's task is to call tokenizer with specified source HTML, traverse list of produced token list and create internal object model. It also offers a set of methods to write resulting XML to string, file or any output stream.
Typical usage is the following:
Field Summary | |
---|---|
static java.lang.String |
DEFAULT_CHARSET
|
Constructor Summary | |
---|---|
HtmlCleaner(java.io.File file)
Constructor - creates the instance for specified file and charset. |
|
HtmlCleaner(java.io.File file,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance for specified file and charset. |
|
HtmlCleaner(java.io.File file,
java.lang.String charset)
Constructor - creates the instance for specified file. |
|
HtmlCleaner(java.io.File file,
java.lang.String charset,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance for specified file. |
|
HtmlCleaner(java.io.InputStream in)
Constructor - creates the instance for the specified inpout stream |
|
HtmlCleaner(java.io.InputStream in,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance for the specified inpout stream |
|
HtmlCleaner(java.io.InputStream in,
java.lang.String charset)
Constructor - creates the instance for the specified inpout stream and the charset |
|
HtmlCleaner(java.lang.String htmlContent)
Constructor - creates the instance with specified html content as String. |
|
HtmlCleaner(java.lang.String htmlContent,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance with specified html content as String. |
|
HtmlCleaner(java.net.URL url)
Constructor - creates the instance for specified URL and charset. |
|
HtmlCleaner(java.net.URL url,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance for specified URL and charset. |
|
HtmlCleaner(java.net.URL url,
java.lang.String charset)
Constructor - creates the instance for specified URL and charset. |
|
HtmlCleaner(java.net.URL url,
java.lang.String charset,
ITagInfoProvider tagInfoProvider)
Constructor - creates the instance for specified URL and charset. |
Method Summary | |
---|---|
void |
clean()
|
java.util.Set |
getAllTags()
|
TagNode |
getBodyNode()
|
java.lang.String |
getCompactXmlAsString()
|
java.lang.String |
getHyphenReplacementInComment()
|
java.util.List |
getNodeList()
|
java.lang.String |
getPrettyXmlAsString()
|
java.lang.String |
getXmlAsString()
|
boolean |
isAdvancedXmlEscape()
|
boolean |
isOmitComments()
|
boolean |
isOmitDeprecatedTags()
|
boolean |
isOmitDoctypeDeclaration()
|
boolean |
isOmitUnknownTags()
|
boolean |
isOmitXmlDeclaration()
|
boolean |
isOmitXmlnsAttributes()
|
boolean |
isRecognizeUnicodeChars()
|
boolean |
isTranslateSpecialEntities()
|
boolean |
isUseCdataForScriptAndStyle()
|
void |
setAdvancedXmlEscape(boolean advancedXmlEscape)
|
void |
setBodyNode(TagNode bodyNode)
|
void |
setHyphenReplacementInComment(java.lang.String hyphenReplacementInComment)
|
void |
setOmitComments(boolean omitComments)
|
void |
setOmitDeprecatedTags(boolean omitDeprecatedTags)
|
void |
setOmitDoctypeDeclaration(boolean omitDoctypeDeclaration)
|
void |
setOmitUnknownTags(boolean omitUnknownTags)
|
void |
setOmitXmlDeclaration(boolean omitXmlDeclaration)
|
void |
setOmitXmlnsAttributes(boolean omitXmlnsAttributes)
|
void |
setRecognizeUnicodeChars(boolean recognizeUnicodeChars)
|
void |
setTranslateSpecialEntities(boolean translateSpecialEntities)
|
void |
setUseCdataForScriptAndStyle(boolean useCdataForScriptAndStyle)
|
void |
writeCompactXmlToFile(java.lang.String fileName)
|
void |
writeCompactXmlToFile(java.lang.String fileName,
java.lang.String charset)
|
void |
writeCompactXmlToStream(java.io.OutputStream out)
|
void |
writeCompactXmlToStream(java.io.OutputStream out,
java.lang.String charset)
|
void |
writePrettyXmlToFile(java.lang.String fileName)
|
void |
writePrettyXmlToFile(java.lang.String fileName,
java.lang.String charset)
|
void |
writePrettyXmlToStream(java.io.OutputStream out)
|
void |
writePrettyXmlToStream(java.io.OutputStream out,
java.lang.String charset)
|
void |
writeXml(XmlSerializer xmlSerializer)
The most general way to serialize resulting XML. |
void |
writeXmlToFile(java.lang.String fileName)
|
void |
writeXmlToFile(java.lang.String fileName,
java.lang.String charset)
|
void |
writeXmlToStream(java.io.OutputStream out)
|
void |
writeXmlToStream(java.io.OutputStream out,
java.lang.String charset)
|
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final java.lang.String DEFAULT_CHARSET
Constructor Detail |
---|
public HtmlCleaner(java.lang.String htmlContent, ITagInfoProvider tagInfoProvider)
htmlContent
- public HtmlCleaner(java.lang.String htmlContent)
htmlContent
- public HtmlCleaner(java.io.File file, java.lang.String charset, ITagInfoProvider tagInfoProvider) throws java.io.IOException
file
- charset
-
java.io.IOException
public HtmlCleaner(java.io.File file, java.lang.String charset) throws java.io.IOException
file
- charset
-
java.io.IOException
public HtmlCleaner(java.io.File file, ITagInfoProvider tagInfoProvider) throws java.io.IOException
file
-
java.io.IOException
public HtmlCleaner(java.io.File file) throws java.io.IOException
file
-
java.io.IOException
public HtmlCleaner(java.net.URL url, java.lang.String charset, ITagInfoProvider tagInfoProvider) throws java.io.IOException
url
- charset
-
java.io.IOException
public HtmlCleaner(java.net.URL url, ITagInfoProvider tagInfoProvider) throws java.io.IOException
url
- tagInfoProvider
-
java.io.IOException
public HtmlCleaner(java.net.URL url, java.lang.String charset) throws java.io.IOException
url
- charset
-
java.io.IOException
public HtmlCleaner(java.net.URL url) throws java.io.IOException
url
-
java.io.IOException
public HtmlCleaner(java.io.InputStream in, ITagInfoProvider tagInfoProvider)
in
- tagInfoProvider
- public HtmlCleaner(java.io.InputStream in)
in
- public HtmlCleaner(java.io.InputStream in, java.lang.String charset) throws java.io.IOException
in
- charset
-
java.io.IOException
Method Detail |
---|
public void clean() throws java.io.IOException
java.io.IOException
public java.util.List getNodeList() throws java.io.IOException
java.io.IOException
public boolean isOmitUnknownTags()
public void setOmitUnknownTags(boolean omitUnknownTags)
public boolean isOmitDeprecatedTags()
public void setOmitDeprecatedTags(boolean omitDeprecatedTags)
public boolean isAdvancedXmlEscape()
public void setAdvancedXmlEscape(boolean advancedXmlEscape)
public boolean isUseCdataForScriptAndStyle()
public void setUseCdataForScriptAndStyle(boolean useCdataForScriptAndStyle)
public boolean isTranslateSpecialEntities()
public void setTranslateSpecialEntities(boolean translateSpecialEntities)
public boolean isRecognizeUnicodeChars()
public void setRecognizeUnicodeChars(boolean recognizeUnicodeChars)
public boolean isOmitComments()
public void setOmitComments(boolean omitComments)
public boolean isOmitXmlDeclaration()
public void setOmitXmlDeclaration(boolean omitXmlDeclaration)
public boolean isOmitDoctypeDeclaration()
public void setOmitDoctypeDeclaration(boolean omitDoctypeDeclaration)
public boolean isOmitXmlnsAttributes()
public void setOmitXmlnsAttributes(boolean omitXmlnsAttributes)
public java.lang.String getHyphenReplacementInComment()
public void setHyphenReplacementInComment(java.lang.String hyphenReplacementInComment)
public java.util.Set getAllTags()
public void writeXml(XmlSerializer xmlSerializer) throws java.io.IOException
xmlSerializer
-
java.io.IOException
public void writeXmlToStream(java.io.OutputStream out) throws java.io.IOException
java.io.IOException
public void writeXmlToStream(java.io.OutputStream out, java.lang.String charset) throws java.io.IOException
java.io.IOException
public void writeCompactXmlToStream(java.io.OutputStream out) throws java.io.IOException
java.io.IOException
public void writeCompactXmlToStream(java.io.OutputStream out, java.lang.String charset) throws java.io.IOException
java.io.IOException
public void writePrettyXmlToStream(java.io.OutputStream out) throws java.io.IOException
java.io.IOException
public void writePrettyXmlToStream(java.io.OutputStream out, java.lang.String charset) throws java.io.IOException
java.io.IOException
public void writeXmlToFile(java.lang.String fileName) throws java.io.IOException
java.io.IOException
public void writeXmlToFile(java.lang.String fileName, java.lang.String charset) throws java.io.IOException
java.io.IOException
public void writeCompactXmlToFile(java.lang.String fileName) throws java.io.IOException
java.io.IOException
public void writeCompactXmlToFile(java.lang.String fileName, java.lang.String charset) throws java.io.IOException
java.io.IOException
public void writePrettyXmlToFile(java.lang.String fileName) throws java.io.IOException
java.io.IOException
public void writePrettyXmlToFile(java.lang.String fileName, java.lang.String charset) throws java.io.IOException
java.io.IOException
public java.lang.String getXmlAsString() throws java.io.IOException
java.io.IOException
public java.lang.String getCompactXmlAsString() throws java.io.IOException
java.io.IOException
public java.lang.String getPrettyXmlAsString() throws java.io.IOException
java.io.IOException
public TagNode getBodyNode()
public void setBodyNode(TagNode bodyNode)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |