使用XSS和事件读取Java中大型excel文件的多个选项卡
我使用的代码来自(作者:lchen),它根据我提供给方法“readRow()”的行数从excel文件中读取内容使用XSS和事件读取Java中大型excel文件的多个选项卡,java,excel,apache-poi,Java,Excel,Apache Poi,我使用的代码来自(作者:lchen),它根据我提供给方法“readRow()”的行数从excel文件中读取内容 import java.io.InputStream; import java.util.ArrayList; import java.util.Iterator; import java.util.List; import javax.xml.stream.XMLInputFactory; import javax.xml.stream.XMLStreamException; i
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.XMLStreamReader;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackageAccess;
import org.apache.poi.ss.util.CellReference;
import org.apache.poi.xssf.eventusermodel.ReadOnlySharedStringsTable;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.InputSource;
public class TestLargeFileRead {
private int rowNum = 0;
private OPCPackage opcPkg;
private ReadOnlySharedStringsTable stringsTable;
private XMLStreamReader xmlReader;
public void XExcelFileReader(String excelPath) throws Exception {
opcPkg = OPCPackage.open(excelPath, PackageAccess.READ);
this.stringsTable = new ReadOnlySharedStringsTable(opcPkg);
XSSFReader xssfReader = new XSSFReader(opcPkg);
XMLInputFactory factory = XMLInputFactory.newInstance();
InputStream inputStream = xssfReader.getSheetsData().next();
xmlReader = factory.createXMLStreamReader(inputStream);
while (xmlReader.hasNext()) {
xmlReader.next();
if (xmlReader.isStartElement()) {
if (xmlReader.getLocalName().equals("sheetData"))
break;
}
}
}
public int rowNum() {
return rowNum;
}
public List<String[]> readRows(int batchSize) throws XMLStreamException {
String elementName = "row";
List<String[]> dataRows = new ArrayList<String[]>();
if (batchSize > 0) {
while (xmlReader.hasNext()) {
xmlReader.next();
if (xmlReader.isStartElement()) {
if (xmlReader.getLocalName().equals(elementName)) {
rowNum++;
dataRows.add(getDataRow());
if (dataRows.size() == batchSize)
break;
}
}
}
}
return dataRows;
}
private String[] getDataRow() throws XMLStreamException {
List<String> rowValues = new ArrayList<String>();
while (xmlReader.hasNext()) {
xmlReader.next();
if (xmlReader.isStartElement()) {
if (xmlReader.getLocalName().equals("c")) {
CellReference cellReference = new CellReference(
xmlReader.getAttributeValue(null, "r"));
// Fill in the possible blank cells!
while (rowValues.size() < cellReference.getCol()) {
rowValues.add("");
}
String cellType = xmlReader.getAttributeValue(null, "t");
rowValues.add(getCellValue(cellType));
}
} else if (xmlReader.isEndElement()
&& xmlReader.getLocalName().equals("row")) {
break;
}
}
return rowValues.toArray(new String[rowValues.size()]);
}
private String getCellValue(String cellType) throws XMLStreamException {
String value = ""; // by default
while (xmlReader.hasNext()) {
xmlReader.next();
if (xmlReader.isStartElement()) {
if (xmlReader.getLocalName().equals("v")) {
if (cellType != null && cellType.equals("s")) {
int idx = Integer.parseInt(xmlReader.getElementText());
return new XSSFRichTextString(
stringsTable.getEntryAt(idx)).toString();
} else {
return xmlReader.getElementText();
}
}
} else if (xmlReader.isEndElement()
&& xmlReader.getLocalName().equals("c")) {
break;
}
}
return value;
}
@Override
protected void finalize() throws Throwable {
if (opcPkg != null)
opcPkg.close();
super.finalize();
}
public static void main(String[] args) {
try {
TestLargeFileRead howto = new TestLargeFileRead();
howto.XExcelFileReader("D:\\TEMP_CATALOG\\H1.xlsx");
} catch (Exception e) {
e.printStackTrace();
}
}
}
import java.io.InputStream;
导入java.util.ArrayList;
导入java.util.Iterator;
导入java.util.List;
导入javax.xml.stream.XMLInputFactory;
导入javax.xml.stream.XMLStreamException;
导入javax.xml.stream.XMLStreamReader;
导入org.apache.poi.openxml4j.opc.OPCPackage;
导入org.apache.poi.openxml4j.opc.PackageAccess;
导入org.apache.poi.ss.util.CellReference;
导入org.apache.poi.xssf.eventusermodel.ReadOnlySharedStringsTable;
导入org.apache.poi.xssf.eventusermodel.XSSFReader;
导入org.apache.poi.xssf.usermodel.XSSFRichTextString;
导入org.xml.sax.InputSource;
公共类TestLargeFileRead{
private int rowNum=0;
私人OPCPackage opcPkg;
私有只读共享stringsTable stringsTable;
私有XMLStreamReader;
公共void XExcelFileReader(字符串excelPath)引发异常{
opcPkg=OPCPackage.open(excelPath,PackageAccess.READ);
this.stringsTable=新的只读共享stringsTable(opcPkg);
XSSFReader XSSFReader=新的XSSFReader(opcPkg);
XMLInputFactory=XMLInputFactory.newInstance();
InputStream InputStream=xssfReader.getSheetsData().next();
xmlReader=factory.createXMLStreamReader(inputStream);
while(xmlReader.hasNext()){
xmlReader.next();
if(xmlReader.isStartElement()){
if(xmlReader.getLocalName().equals(“sheetData”))
打破
}
}
}
public int rowNum(){
返回rowNum;
}
公共列表readRows(int batchSize)引发XMLStreamException{
String elementName=“行”;
List dataRows=new ArrayList();
如果(批量大小>0){
while(xmlReader.hasNext()){
xmlReader.next();
if(xmlReader.isStartElement()){
if(xmlReader.getLocalName().equals(elementName)){
rowNum++;
add(getDataRow());
if(dataRows.size()==batchSize)
打破
}
}
}
}
返回数据行;
}
私有字符串[]getDataRow()引发XMLStreamException{
List rowValues=new ArrayList();
while(xmlReader.hasNext()){
xmlReader.next();
if(xmlReader.isStartElement()){
if(xmlReader.getLocalName().equals(“c”)){
CellReference CellReference=新的CellReference(
getAttributeValue(null,“r”);
//填写可能的空白单元格!
while(rowValues.size()
但它只读取第一页的内容,并丢弃其他后续页。我的要求是读表名;根据名字读那张纸的内容。有人能帮我自定义上述代码获取表名称及其内容吗?请?您需要使用的关键类是。如果查看,您将看到它提供了所有工作表的输入流的迭代器,以及获取根工作簿流的方法 如果要访问所有图纸,需要更改以下行:
InputStream inputStream = xssfReader.getSheetsData().next();
xmlReader = factory.createXMLStreamReader(inputStream);
更像是:
Iterator<InputStream> sheetsData = xssfReader.getSheetsData();
while (sheetsData.hasNext()) {
InputStream inputStream = sheetsData.next();
xmlReader = factory.createXMLStreamReader(inputStream);
....
}
如果你想知道更多关于做这些事情的信息,那么最好的例子之一,很容易阅读和理解,就是ApachePOI附带的——阅读代码并学习 谢谢你-Gagravarr的回答!!我将按照您的建议工作,并将更新结果:)
XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
while (sheetsData.hasNext()) {
InputStream inputStream = sheetsData.next();
String sheetName = iter.getSheetName();
if (sheetName.equalsIgnoreCase("TheSheetIWant")) {
xmlReader = factory.createXMLStreamReader(inputStream);
....
}
}