textractor.html
Class AbstractHtml2Text

java.lang.Object
  textractor.html.AbstractHtml2Text

Direct Known Subclasses:

Html2Text2DB

public abstract class AbstractHtml2Text
extends Object

Converts HTML to Text. This translator uses the alt text of images to replace images. This is useful since many journals use images for greek symbol, and use an alt attribute to render this for text-only browsers.

Field Summary

protected boolean	appendSentencesInOneDocument
protected int	articleChunkSize
protected boolean	noSentenceBoundaryTag
protected boolean	verbose

Constructor Summary

AbstractHtml2Text(String[] args)

Method Summary

protected Collection<Sentence>	createSentenceOneDocument(Article article, Iterator<MutableString> sentencesAsTextIterator, String title)
protected Collection<Sentence>	createSentences(Article article, Iterator<MutableString> sentencesAsTextIterator, String title)
abstract TextConsumer	getConsumer()
protected Collection<Sentence>	loadArticleSentences(Article article, String title, String text, Map<String,Object> additionalFieldsMap)
void	process(String[] args)
abstract void	setConsumer(TextConsumer consumer)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

appendSentencesInOneDocument

protected boolean appendSentencesInOneDocument

noSentenceBoundaryTag

protected boolean noSentenceBoundaryTag

verbose

protected final boolean verbose

articleChunkSize

protected int articleChunkSize

Constructor Detail

AbstractHtml2Text

public AbstractHtml2Text(String[] args)

Method Detail

process

public void process(String[] args)
             throws IOException,
                    org.htmlparser.util.ParserException,
                    ConfigurationException,
                    SentenceProcessingException

Throws:

IOException

org.htmlparser.util.ParserException

ConfigurationException

SentenceProcessingException

loadArticleSentences

protected final Collection<Sentence> loadArticleSentences(Article article,
                                                          String title,
                                                          String text,
                                                          Map<String,Object> additionalFieldsMap)
                                                   throws SentenceProcessingException

Throws:

SentenceProcessingException

createSentenceOneDocument

protected final Collection<Sentence> createSentenceOneDocument(Article article,
                                                               Iterator<MutableString> sentencesAsTextIterator,
                                                               String title)
                                                        throws SentenceProcessingException

Throws:

SentenceProcessingException

createSentences

protected final Collection<Sentence> createSentences(Article article,
                                                     Iterator<MutableString> sentencesAsTextIterator,
                                                     String title)
                                              throws SentenceProcessingException

Throws:

SentenceProcessingException

setConsumer

public abstract void setConsumer(TextConsumer consumer)

getConsumer

public abstract TextConsumer getConsumer()