public class Hocr2PdfParser
extends java.lang.Object
implements org.xml.sax.ContentHandler, org.xml.sax.ErrorHandler
| Modifier and Type | Field and Description |
|---|---|
static java.lang.String |
BBOX |
static java.lang.String |
CLASS |
static java.lang.String |
DIV |
static java.lang.String |
OCR_LINE |
static java.lang.String |
OCR_PAGE |
static java.lang.String |
OCR_WORD |
static java.lang.String |
OCRX_WORD |
static java.lang.String |
SEMICOL |
static java.lang.String |
SPACE |
static java.lang.String |
SPAN |
static java.lang.String |
TITLE |
| Constructor and Description |
|---|
Hocr2PdfParser(java.lang.String hocrFilepath,
org.apache.pdfbox.pdmodel.PDDocument pdDocument,
boolean visible,
boolean useHocrLineToY,
java.lang.String fontName) |
| Modifier and Type | Method and Description |
|---|---|
void |
addTextToPDF(java.lang.String[] imgCoords,
java.lang.String text) |
void |
characters(char[] ch,
int start,
int length) |
void |
endDocument() |
void |
endElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName) |
void |
endPrefixMapping(java.lang.String prefix) |
void |
error(org.xml.sax.SAXParseException exception) |
void |
fatalError(org.xml.sax.SAXParseException exception) |
void |
ignorableWhitespace(char[] ch,
int start,
int length) |
void |
parse() |
void |
processingInstruction(java.lang.String target,
java.lang.String data) |
void |
setDocumentLocator(org.xml.sax.Locator locator) |
void |
skippedEntity(java.lang.String name) |
void |
startDocument() |
void |
startElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName,
org.xml.sax.Attributes atts) |
void |
startPrefixMapping(java.lang.String prefix,
java.lang.String uri) |
void |
warning(org.xml.sax.SAXParseException exception) |
public static final java.lang.String SPACE
public static final java.lang.String BBOX
public static final java.lang.String TITLE
public static final java.lang.String SEMICOL
public static final java.lang.String DIV
public static final java.lang.String SPAN
public static final java.lang.String OCRX_WORD
public static final java.lang.String OCR_WORD
public static final java.lang.String OCR_LINE
public static final java.lang.String CLASS
public static final java.lang.String OCR_PAGE
public Hocr2PdfParser(java.lang.String hocrFilepath,
org.apache.pdfbox.pdmodel.PDDocument pdDocument,
boolean visible,
boolean useHocrLineToY,
java.lang.String fontName)
throws java.io.IOException
java.io.IOExceptionpublic void setDocumentLocator(org.xml.sax.Locator locator)
setDocumentLocator in interface org.xml.sax.ContentHandlerpublic void startDocument()
throws org.xml.sax.SAXException
startDocument in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endDocument()
throws org.xml.sax.SAXException
endDocument in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void startPrefixMapping(java.lang.String prefix,
java.lang.String uri)
throws org.xml.sax.SAXException
startPrefixMapping in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endPrefixMapping(java.lang.String prefix)
throws org.xml.sax.SAXException
endPrefixMapping in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void startElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName,
org.xml.sax.Attributes atts)
throws org.xml.sax.SAXException
startElement in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName)
throws org.xml.sax.SAXException
endElement in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void characters(char[] ch,
int start,
int length)
throws org.xml.sax.SAXException
characters in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void ignorableWhitespace(char[] ch,
int start,
int length)
throws org.xml.sax.SAXException
ignorableWhitespace in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void processingInstruction(java.lang.String target,
java.lang.String data)
throws org.xml.sax.SAXException
processingInstruction in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void skippedEntity(java.lang.String name)
throws org.xml.sax.SAXException
skippedEntity in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void warning(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
warning in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void error(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
error in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void fatalError(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
fatalError in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void addTextToPDF(java.lang.String[] imgCoords,
java.lang.String text)
throws org.xml.sax.SAXException
org.xml.sax.SAXExceptionpublic void parse()
throws org.xml.sax.SAXException,
java.io.IOException,
javax.xml.parsers.ParserConfigurationException
org.xml.sax.SAXExceptionjava.io.IOExceptionjavax.xml.parsers.ParserConfigurationExceptionCopyright © 2024 Tess4J. All rights reserved.