Package net.sourceforge.tess4j.util

Class Hocr2PdfParser

java.lang.Object

net.sourceforge.tess4j.util.Hocr2PdfParser

All Implemented Interfaces:

ContentHandler, ErrorHandler

public class Hocr2PdfParser
extends Object
implements ContentHandler, ErrorHandler

Field Summary

Fields

Modifier and Type	Field	Description
static final String	BBOX
static final String	CLASS
static final String	DIV
static final String	OCR_LINE
static final String	OCR_PAGE
static final String	OCR_WORD
static final String	OCRX_WORD
static final String	SEMICOL
static final String	SPACE
static final String	SPAN
static final String	TITLE

Constructor Summary

Constructors

Constructor	Description
Hocr2PdfParser(String hocrFilepath, org.apache.pdfbox.pdmodel.PDDocument pdDocument, boolean visible, boolean useHocrLineToY, String fontName)

Method Summary

Modifier and Type	Method	Description
void	addTextToPDF(String[] imgCoords, String text)
void	characters(char[] ch, int start, int length)
void	endDocument()
void	endElement(String uri, String localName, String qName)
void	endPrefixMapping(String prefix)
void	error(SAXParseException exception)
void	fatalError(SAXParseException exception)
void	ignorableWhitespace(char[] ch, int start, int length)
void	parse()
void	processingInstruction(String target, String data)
void	setDocumentLocator(Locator locator)
void	skippedEntity(String name)
void	startDocument()
void	startElement(String uri, String localName, String qName, Attributes atts)
void	startPrefixMapping(String prefix, String uri)
void	warning(SAXParseException exception)

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.xml.sax.ContentHandler

declaration

Field Details

SPACE

public static final String SPACE

See Also:

• Constant Field Values

BBOX

public static final String BBOX

See Also:

• Constant Field Values

TITLE

public static final String TITLE

See Also:

• Constant Field Values

SEMICOL

public static final String SEMICOL

See Also:

• Constant Field Values

DIV

public static final String DIV

See Also:

• Constant Field Values

SPAN

public static final String SPAN

See Also:

• Constant Field Values

OCRX_WORD

public static final String OCRX_WORD

See Also:

• Constant Field Values

OCR_WORD

public static final String OCR_WORD

See Also:

• Constant Field Values

OCR_LINE

public static final String OCR_LINE

See Also:

• Constant Field Values

CLASS

public static final String CLASS

See Also:

• Constant Field Values

OCR_PAGE

public static final String OCR_PAGE

See Also:

• Constant Field Values

Constructor Details

Hocr2PdfParser

public Hocr2PdfParser(String hocrFilepath,
 org.apache.pdfbox.pdmodel.PDDocument pdDocument,
 boolean visible,
 boolean useHocrLineToY,
 String fontName)
               throws IOException

Throws:

IOException

Method Details

setDocumentLocator

public void setDocumentLocator(Locator locator)

Specified by:

setDocumentLocator in interface ContentHandler

startDocument

public void startDocument()
                   throws SAXException

Specified by:

startDocument in interface ContentHandler

Throws:

SAXException

endDocument

public void endDocument()
                 throws SAXException

Specified by:

endDocument in interface ContentHandler

Throws:

SAXException

startPrefixMapping

public void startPrefixMapping(String prefix,
 String uri)
                        throws SAXException

Specified by:

startPrefixMapping in interface ContentHandler

Throws:

SAXException

endPrefixMapping

public void endPrefixMapping(String prefix)
                      throws SAXException

Specified by:

endPrefixMapping in interface ContentHandler

Throws:

SAXException

startElement

public void startElement(String uri,
 String localName,
 String qName,
 Attributes atts)
                  throws SAXException

Specified by:

startElement in interface ContentHandler

Throws:

SAXException

endElement

public void endElement(String uri,
 String localName,
 String qName)
                throws SAXException

Specified by:

endElement in interface ContentHandler

Throws:

SAXException

characters

public void characters(char[] ch,
 int start,
 int length)
                throws SAXException

Specified by:

characters in interface ContentHandler

Throws:

SAXException

ignorableWhitespace

public void ignorableWhitespace(char[] ch,
 int start,
 int length)
                         throws SAXException

Specified by:

ignorableWhitespace in interface ContentHandler

Throws:

SAXException

processingInstruction

public void processingInstruction(String target,
 String data)
                           throws SAXException

Specified by:

processingInstruction in interface ContentHandler

Throws:

SAXException

skippedEntity

public void skippedEntity(String name)
                   throws SAXException

Specified by:

skippedEntity in interface ContentHandler

Throws:

SAXException

warning

public void warning(SAXParseException exception)
             throws SAXException

Specified by:

warning in interface ErrorHandler

Throws:

SAXException

error

public void error(SAXParseException exception)
           throws SAXException

Specified by:

error in interface ErrorHandler

Throws:

SAXException

fatalError

public void fatalError(SAXParseException exception)
                throws SAXException

Specified by:

fatalError in interface ErrorHandler

Throws:

SAXException

addTextToPDF

public void addTextToPDF(String[] imgCoords,
 String text)
                  throws SAXException

Throws:

SAXException

parse

public void parse()
           throws SAXException,
IOException,
ParserConfigurationException

Throws:

SAXException

IOException

ParserConfigurationException