public class XSSFEventBasedExcelExtractor extends POIXMLTextExtractor implements ExcelExtractor
Modifier and Type | Class and Description |
---|---|
protected class |
XSSFEventBasedExcelExtractor.SheetTextExtractor |
Modifier and Type | Field and Description |
---|---|
protected boolean |
concatenatePhoneticRuns |
protected OPCPackage |
container |
protected boolean |
formulasNotResults |
protected boolean |
includeCellComments |
protected boolean |
includeHeadersFooters |
protected boolean |
includeSheetNames |
protected boolean |
includeTextBoxes |
protected java.util.Locale |
locale |
protected POIXMLProperties |
properties |
Constructor and Description |
---|
XSSFEventBasedExcelExtractor(OPCPackage container) |
XSSFEventBasedExcelExtractor(java.lang.String path) |
Modifier and Type | Method and Description |
---|---|
void |
close()
Allows to free resources of the Extractor as soon as
it is not needed any more.
|
protected SharedStrings |
createSharedStringsTable(XSSFReader xssfReader,
OPCPackage container) |
POIXMLProperties.CoreProperties |
getCoreProperties()
Returns the core document properties
|
POIXMLProperties.CustomProperties |
getCustomProperties()
Returns the custom document properties
|
POIXMLProperties.ExtendedProperties |
getExtendedProperties()
Returns the extended document properties
|
boolean |
getFormulasNotResults() |
boolean |
getIncludeCellComments() |
boolean |
getIncludeHeadersFooters() |
boolean |
getIncludeSheetNames() |
boolean |
getIncludeTextBoxes() |
java.util.Locale |
getLocale() |
OPCPackage |
getPackage()
Returns the opened OPCPackage container.
|
java.lang.String |
getText()
Processes the file and returns the text
|
static void |
main(java.lang.String[] args) |
void |
processSheet(XSSFSheetXMLHandler.SheetContentsHandler sheetContentsExtractor,
Styles styles,
Comments comments,
SharedStrings strings,
java.io.InputStream sheetInputStream)
Processes the given sheet
|
void |
setConcatenatePhoneticRuns(boolean concatenatePhoneticRuns)
Concatenate text from <rPh> text elements in SharedStringsTable
Default is true;
|
void |
setFormulasNotResults(boolean formulasNotResults)
Should we return the formula itself, and not
the result it produces? Default is false
|
void |
setIncludeCellComments(boolean includeCellComments)
Should cell comments be included? Default is false
|
void |
setIncludeHeadersFooters(boolean includeHeadersFooters)
Should headers and footers be included? Default is true
|
void |
setIncludeSheetNames(boolean includeSheetNames)
Should sheet names be included? Default is true
|
void |
setIncludeTextBoxes(boolean includeTextBoxes)
Should text from textboxes be included? Default is true
|
void |
setLocale(java.util.Locale locale) |
checkMaxTextSize, getDocument, getMetadataTextExtractor
setFilesystem
protected OPCPackage container
protected POIXMLProperties properties
protected java.util.Locale locale
protected boolean includeTextBoxes
protected boolean includeSheetNames
protected boolean includeCellComments
protected boolean includeHeadersFooters
protected boolean formulasNotResults
protected boolean concatenatePhoneticRuns
public XSSFEventBasedExcelExtractor(java.lang.String path) throws org.apache.xmlbeans.XmlException, OpenXML4JException, java.io.IOException
org.apache.xmlbeans.XmlException
OpenXML4JException
java.io.IOException
public XSSFEventBasedExcelExtractor(OPCPackage container) throws org.apache.xmlbeans.XmlException, OpenXML4JException, java.io.IOException
org.apache.xmlbeans.XmlException
OpenXML4JException
java.io.IOException
public static void main(java.lang.String[] args) throws java.lang.Exception
java.lang.Exception
public void setIncludeSheetNames(boolean includeSheetNames)
setIncludeSheetNames
in interface ExcelExtractor
includeSheetNames
- true
if the sheet names should be includedpublic boolean getIncludeSheetNames()
public void setFormulasNotResults(boolean formulasNotResults)
setFormulasNotResults
in interface ExcelExtractor
formulasNotResults
- true
if the formula itself is returnedpublic boolean getFormulasNotResults()
public void setIncludeHeadersFooters(boolean includeHeadersFooters)
setIncludeHeadersFooters
in interface ExcelExtractor
includeHeadersFooters
- true
if headers and footers should be includedpublic boolean getIncludeHeadersFooters()
public void setIncludeTextBoxes(boolean includeTextBoxes)
public boolean getIncludeTextBoxes()
public void setIncludeCellComments(boolean includeCellComments)
setIncludeCellComments
in interface ExcelExtractor
includeCellComments
- true
if cell comments should be includedpublic boolean getIncludeCellComments()
public void setConcatenatePhoneticRuns(boolean concatenatePhoneticRuns)
concatenatePhoneticRuns
- true if runs should be concatenated, false otherwisepublic void setLocale(java.util.Locale locale)
public java.util.Locale getLocale()
public OPCPackage getPackage()
getPackage
in class POIXMLTextExtractor
public POIXMLProperties.CoreProperties getCoreProperties()
getCoreProperties
in class POIXMLTextExtractor
public POIXMLProperties.ExtendedProperties getExtendedProperties()
getExtendedProperties
in class POIXMLTextExtractor
public POIXMLProperties.CustomProperties getCustomProperties()
getCustomProperties
in class POIXMLTextExtractor
public void processSheet(XSSFSheetXMLHandler.SheetContentsHandler sheetContentsExtractor, Styles styles, Comments comments, SharedStrings strings, java.io.InputStream sheetInputStream) throws java.io.IOException, org.xml.sax.SAXException
java.io.IOException
org.xml.sax.SAXException
protected SharedStrings createSharedStringsTable(XSSFReader xssfReader, OPCPackage container) throws java.io.IOException, org.xml.sax.SAXException
java.io.IOException
org.xml.sax.SAXException
public java.lang.String getText()
getText
in interface ExcelExtractor
getText
in class POITextExtractor
public void close() throws java.io.IOException
POITextExtractor
close
in interface java.io.Closeable
close
in interface java.lang.AutoCloseable
close
in class POIXMLTextExtractor
java.io.IOException
Copyright 2020 The Apache Software Foundation or its licensors, as applicable.