poi文件读写方案
image
引入jar
org.apache.poi
poi
4.1.2
org.apache.poi
poi-ooxml
4.1.2
读取大批量数据，使用CVS模式解决内存溢出的问题
import org.apache.poi.hssf.usermodel.HSSFDateUtil;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackageAccess;
import org.apache.poi.ss.usermodel.BuiltinFormats;
import org.apache.poi.ss.usermodel.DataFormatter;
import org.apache.poi.xssf.eventusermodel.ReadOnlySharedStringsTable;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.StylesTable;
import org.apache.poi.xssf.usermodel.XSSFCellStyle;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintStream;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
/**
* 使用CVS模式解决XLSX文件，可以有效解决用户模式内存溢出的问题
*/
public class XLSXCovertCSVReader {
enum xssfDataType {
BOOL, ERROR, FORMULA, INLINESTR, SSTINDEX, NUMBER,
}
class MyXSSFSheetHandler extends DefaultHandler {
private int isNotNullIndex;
private StylesTable stylesTable;
private ReadOnlySharedStringsTable sharedStringsTable;
private final PrintStream output;
private final int minColumnCount;
private boolean vIsOpen;
private xssfDataType nextDataType;
private short formatIndex;
private String formatString;
private final DataFormatter formatter;
private int thisColumn = -1;
private int lastColumnNumber = -1;
private StringBuffer value;
private String[] record;
private List rows = new ArrayList();
private boolean isCellNull = false;
public MyXSSFSheetHandler(StylesTable styles, ReadOnlySharedStringsTable strings, int cols, PrintStream target
, int isNotNullIndex) {
this.isNotNullIndex = isNotNullIndex;
this.stylesTable = styles;
this.sharedStringsTable = strings;
this.minColumnCount = cols;
this.output = target;
this.value = new StringBuffer();
this.nextDataType = xssfDataType.NUMBER;
this.formatter = new DataFormatter();
record = new String[this.minColumnCount];
rows.clear();// 每次读取都清空行集合
}
public void startElement(String uri, String localName, String name, Attributes attributes) throws SAXException {
if ("inlineStr".equals(name) || "v".equals(name)) {
vIsOpen = true;
// Clear contents cache
value.setLength(0);
}
// c => cell
else if ("c".equals(name)) {
// Get the cell reference
String r = attributes.getValue("r");
int firstDigit = -1;
for (int c = 0; c < r.length(); ++c) {
if (Character.isDigit(r.charAt(c))) {
firstDigit = c;
break;
}
}
thisColumn = nameToColumn(r.substring(0, firstDigit));
// Set up defaults.
this.nextDataType = xssfDataType.NUMBER;
this.formatIndex = -1;
this.formatString = null;
String cellType = attributes.getValue("t");
String cellStyleStr = attributes.getValue("s");
if ("b".equals(cellType))
nextDataType = xssfDataType.BOOL;
else if ("e".equals(cellType))
nextDataType = xssfDataType.ERROR;
else if ("inlineStr".equals(cellType))
nextDataType = xssfDataType.INLINESTR;
else if ("s".equals(cellType))
nextDataType = xssfDataType.SSTINDEX;
else if ("str".equals(cellType))
nextDataType = xssfDataType.FORMULA;
else if (cellStyleStr != null) {
// It's a number, but almost certainly one
// with a special style or format
int styleIndex = Integer.parseInt(cellStyleStr);
XSSFCellStyle style = stylesTable.getStyleAt(styleIndex);
this.formatIndex = style.getDataFormat();
this.formatString = style.getDataFormatString();
if (this.formatString == null)
this.formatString = BuiltinFormats.getBuiltinFormat(this.formatIndex);
}
}
}
public void endElement(String uri, String localName, String name) throws SAXException {
String thisStr = null;
// v => contents of a cell
if ("v".equals(name)) {
// Process the value contents as required.
// Do now, as characters() may be called more than once
switch (nextDataType) {
case BOOL:
char first = value.charAt(0);
thisStr = first == '0' ? "FALSE" : "TRUE";
break;
case ERROR:
thisStr = "\"ERROR:" + value.toString() + '"';
break;
case FORMULA:
// A formula could result in a string value,
// so always add double-quote characters.
thisStr = '"' + value.toString() + '"';
break;
case INLINESTR:
XSSFRichTextString rtsi = new XSSFRichTextString(value.toString());
thisStr = '"' + rtsi.toString() + '"';
break;
case SSTINDEX:
String sstIndex = value.toString();
try {
int idx = Integer.parseInt(sstIndex);
XSSFRichTextString rtss = new XSSFRichTextString(sharedStringsTable.getEntryAt(idx));
thisStr = rtss.toString();
} catch (NumberFormatException ex) {
output.println("Failed to parse SST index '" + sstIndex + "': " + ex.toString());
}
break;
case NUMBER:
String n = value.toString();
// 判断是否是日期格式
if (HSSFDateUtil.isADateFormat(this.formatIndex, n)) {
Double d = Double.parseDouble(n);
Date date = HSSFDateUtil.getJavaDate(d);
thisStr = formateDateToString(date);
} else if (this.formatString != null)
thisStr = formatter.formatRawCellContents(Double.parseDouble(n), this.formatIndex, this.formatString);
else
thisStr = n;
break;
default:
thisStr = "(TODO: Unexpected type: " + nextDataType + ")";
break;
}
// Output after we've seen the string contents
// Emit commas for any fields that were missing on this row
if (lastColumnNumber == -1) {
lastColumnNumber = 0;
}
//判断单元格的值是否为空
if (thisStr == null || "".equals(isCellNull)) {
isCellNull = true;// 设置单元格是否为空值
}
record[thisColumn] = thisStr; //添加
// Update column
if (thisColumn > -1)
lastColumnNumber = thisColumn;
} else if ("row".equals(name)) {
// Print out any missing commas if needed
if (minColumns > 0) {
// Columns are 0 based
if (lastColumnNumber == -1) {
lastColumnNumber = 0;
}
if (isCellNull == false && record[isNotNullIndex] != null)// 判断是否空行
{
rows.add(record.clone()); //添加
isCellNull = false;
for (int i = 0; i < record.length; i++) {
record[i] = null;
}
}
}
lastColumnNumber = -1;
}
}
public List getRows() {
return rows;
}
public void setRows(List rows) {
this.rows = rows;
}
public void characters(char[] ch, int start, int length) throws SAXException {
if (vIsOpen)
value.append(ch, start, length);
}
private int nameToColumn(String name) {
int column = -1;
for (int i = 0; i < name.length(); ++i) {
int c = name.charAt(i);
column = (column + 1) * 26 + c - 'A';
}
return column;
}
private String formateDateToString(Date date) {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");//格式化日期
return sdf.format(date);
}
}
private OPCPackage xlsxPackage;
private int minColumns;
private PrintStream output;
private String sheetName;
private int isNotNullIndex;
public XLSXCovertCSVReader(OPCPackage pkg, PrintStream output,
String sheetName, int minColumns, int isNotNullIndex) {
this.isNotNullIndex = isNotNullIndex;
this.xlsxPackage = pkg;
this.output = output;
this.minColumns = minColumns;
this.sheetName = sheetName;
}
public List processSheet(StylesTable styles,
ReadOnlySharedStringsTable strings, InputStream sheetInputStream, int isNotNullIndex)
throws IOException, ParserConfigurationException, SAXException {
InputSource sheetSource = new InputSource(sheetInputStream);
SAXParserFactory saxFactory = SAXParserFactory.newInstance();
SAXParser saxParser = saxFactory.newSAXParser();
XMLReader sheetParser = saxParser.getXMLReader();
MyXSSFSheetHandler handler = new MyXSSFSheetHandler(styles, strings, this.minColumns, this.output, isNotNullIndex); //内部类
sheetParser.setContentHandler(handler);
sheetParser.parse(sheetSource);
return handler.getRows();
}
/**
* 初始化这个处理程序 将
*
* @throws IOException
* @throws OpenXML4JException
* @throws ParserConfigurationException
* @throws SAXException
*/
public List process(int isNotNullIndex) throws IOException, OpenXML4JException, ParserConfigurationException, SAXException {
ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(this.xlsxPackage);
XSSFReader xssfReader = new XSSFReader(this.xlsxPackage);
List list = null;
StylesTable styles = xssfReader.getStylesTable();
XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
int index = 0;
while (iter.hasNext()) {
InputStream stream = iter.next();
String sheetNameTemp = iter.getSheetName();
if (this.sheetName.equals(sheetNameTemp)) {
list = processSheet(styles, strings, stream, isNotNullIndex);
stream.close();
++index;
}
}
return list;
}
/**
* 读取Excel
*
* @param path 文件路径
* @param sheetName sheet名称
* @param minColumns 列总数（最后一列的下标）
* @param isNotNullIndex [0,minColumns-1]判断此列数据不为空，则整行数据有效
* @return
* @throws SAXException
* @throws ParserConfigurationException
* @throws OpenXML4JException
* @throws IOException
*/
public static List readerExcel(String path, String sheetName, int minColumns, int isNotNullIndex) throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
OPCPackage pkg = OPCPackage.open(path, PackageAccess.READ);
XLSXCovertCSVReader xlsx2csv = new XLSXCovertCSVReader(pkg, System.out, sheetName, minColumns, isNotNullIndex);
List list = xlsx2csv.process(isNotNullIndex);
pkg.close();
return list;
}
public static void main(String[] args) throws Exception {
try {
List list = XLSXCovertCSVReader.readerExcel("C:/Users/Administrator/Desktop/测试.xlsx", "Sheet1", 3, 0);
for (String[] record : list) {
for (String cell : record) {
System.out.print(cell + " ");
}
System.out.println();
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
直接调用XLSXCovertCSVReader.readerExcel得到list
List
参数说明
path：文件路径
sheetName：Sheet的名称
minColumns：读取的列数
isNotNullIndex：范围在[0,minColumns-1]，判断第isNotNullIndex列数据是否为空，第isNotNullIndex列为空的行不会被读取
大批量写出
//表头
List title = Arrays.asList("MSISDN", "ICCID");
// 获取SXSSFWorkbook实例
SXSSFWorkbook sxssfWorkbook = new SXSSFWorkbook();
Sheet sheet = sxssfWorkbook.createSheet(sheetName);
FileOutputStream outFile = new FileOutputStream(path);
//设置表头
Row header0 = sheet.createRow(0);
for(int c=0;c 参数说明
sheetName：Sheet的名称
path：写出文件路径
写出文件的样式设置
冻结行列
// 冻结最左边的两列、冻结最上面的一行
// 即：滚动横向滚动条时，左边的第一、二列固定不动;滚动纵向滚动条时，上面的第一行固定不动。
sheet.createFreezePane(2, 1);
列宽
// 设置第i列列宽
sheet.setColumnWidth(i, 16 * 256);