Package io.goobi.viewer.controller

Class ALTOTools

java.lang.Object

io.goobi.viewer.controller.ALTOTools

public final class ALTOTools
extends Object

ALTOTools class.

Field Summary

Fields

Modifier and Type	Field	Description
static final String	ALTO_PROBLEMATIC_CHARS	Characters that can cause an "Invalid UTF-8 middle byte" error in the parser.
static final String	TAG_LABEL_IGNORE_REGEX	Constant TAG_LABEL_IGNORE_REGEX.

Method Summary

Modifier and Type	Method	Description
protected static String	alto2Txt(String alto, String charset, boolean mergeLineBreakWords)	alto2Txt.
static XMLStreamReader	createXmlParser(InputStream is)
static String	getALTOCoords(de.intranda.digiverso.ocr.alto.model.superclasses.GeometricData element)	getALTOCoords.
static String	getFulltext(String alto, String charset, boolean mergeLineBreakWords)	getFullText.
static String	getFulltext(Path path, String encoding)	Read the plain full-text from an alto file.
static int	getMatchALTOWord(de.intranda.digiverso.ocr.alto.model.structureclasses.lineelements.Word eleWord, String[] words)	getMatchALTOWord.
static List<TagCount>	getNERTags(String alto, String inCharset, NERTag.Type type)	getNERTags.
static String	getRotatedCoordinates(String inCoords, int rotation, Dimension pageSize)	getRotatedCoordinates.
static List<String>	getWordCoords(String altoString, String charset, Set<String> searchTerms)	getWordCoords.
static List<String>	getWordCoords(String altoString, String charset, Set<String> searchTerms, int rotation)
static List<String>	getWordCoords(String altoString, String charset, Set<String> searchTerms, int proximitySearchDistance, int rotation)
protected static Rectangle	rotate(Rectangle rect, int rotation, Dimension imageSize)	rotate.

Methods inherited from class java.lang.Object

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

Field Details

TAG_LABEL_IGNORE_REGEX

public static final String TAG_LABEL_IGNORE_REGEX

Constant TAG_LABEL_IGNORE_REGEX.

See Also:

• Constant Field Values

ALTO_PROBLEMATIC_CHARS

public static final String ALTO_PROBLEMATIC_CHARS

Characters that can cause an "Invalid UTF-8 middle byte" error in the parser.

See Also:

• Constant Field Values

Method Details

getFulltext

public static String getFulltext(Path path,
 String encoding)
                          throws IOException

Read the plain full-text from an alto file. Don't merge line breaks.

Parameters:

path -

encoding -

Returns:

String containing plain text from ALTO at the given path

Throws:

IOException

getFulltext

public static String getFulltext(String alto,
 String charset,
 boolean mergeLineBreakWords)

getFullText.

Parameters:

alto - a String object.

charset -

mergeLineBreakWords - a boolean.

Returns:

a String object.

getNERTags

public static List<TagCount> getNERTags(String alto,
 String inCharset,
 NERTag.Type type)

getNERTags.

Parameters:

alto - a String object.

inCharset -

type - a NERTag.Type object.

Returns:

a List object.

alto2Txt

protected static String alto2Txt(String alto,
 String charset,
 boolean mergeLineBreakWords)
                          throws IOException,
XMLStreamException,
org.jdom2.JDOMException

alto2Txt.

Parameters:

alto - a String object.

charset - ALTO charset

mergeLineBreakWords - a boolean.

Returns:

a String object.

Throws:

IOException - if any.

XMLStreamException - if any.

org.jdom2.JDOMException

createXmlParser

public static XMLStreamReader createXmlParser(InputStream is)
                                       throws FactoryConfigurationError,
XMLStreamException

Throws:

FactoryConfigurationError

XMLStreamException

getWordCoords

public static List<String> getWordCoords(String altoString,
 String charset,
 Set<String> searchTerms)

getWordCoords.

Parameters:

altoString - a String object.

charset -

searchTerms - a Set object.

Returns:

a List object.

getRotatedCoordinates

public static String getRotatedCoordinates(String inCoords,
 int rotation,
 Dimension pageSize)

getRotatedCoordinates.

Parameters:

inCoords - a String object.

rotation - a int.

pageSize - a Dimension object.

Returns:

a String object.

getWordCoords

public static List<String> getWordCoords(String altoString,
 String charset,
 Set<String> searchTerms,
 int rotation)

Parameters:

altoString - String containing the ALTO XML document

charset -

searchTerms - Set of search terms

rotation - Image rotation in degrees

Returns:

a List object.

getWordCoords

public static List<String> getWordCoords(String altoString,
 String charset,
 Set<String> searchTerms,
 int proximitySearchDistance,
 int rotation)

rotate

protected static Rectangle rotate(Rectangle rect,
 int rotation,
 Dimension imageSize)

rotate.

Parameters:

rect - a Rectangle object.

rotation - a int.

imageSize - a Dimension object.

Returns:

a Rectangle object.

getMatchALTOWord

public static int getMatchALTOWord(de.intranda.digiverso.ocr.alto.model.structureclasses.lineelements.Word eleWord,
 String[] words)

getMatchALTOWord.

Parameters:

eleWord - a Word object.

words - an array of String objects.

Returns:

1 if there is a match; 0 otherwise

getALTOCoords

public static String getALTOCoords(de.intranda.digiverso.ocr.alto.model.superclasses.GeometricData element)

getALTOCoords.

Parameters:

element - a GeometricData object.

Returns:

a String object.