使用POI（用户模式）导入大批量excel文件的情况下，会产生内存溢出的问题，如下:
image.png
1217276-20180120163349053-226959473.png
问题分析：
java.lang.OutOfMemoryError: GC overhead limit exceeded
问题排查：
- java服务启动添加jvm参数：
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=heapdump
heapdump是快照生成的路径
-
使用jvisualvm.exe打开快照文件
image.png 定位到问题所在，确定为POI用户输入模式导致内存溢出
解决方案：将excel文件转为csv，通过多维数组解析表中数据
package com.galaxyeye.icservice.utils;
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.springframework.web.multipart.MultipartFile;
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.*;
/**
* @Author: geyingke
* @Date: 2020/7/10
* @Class: XLSXConvertCSVReader
* @Discription: TODO
**/
public class XLSXConvertCSVReader {
/**
* The type of the data value is indicated by an attribute on the cell. The
* value is usually in a "v" element within the cell.
*/
enum xssfDataType {
BOOL, ERROR, FORMULA, INLINESTR, SSTINDEX, NUMBER,
}
/**
* 使用xssf_sax_API处理Excel,请参考： http://poi.apache.org/spreadsheet/how-to.html#xssf_sax_api
*
* Also see Standard ECMA-376, 1st edition, part 4, pages 1928ff, at
* http://www.ecma-international.org/publications/standards/Ecma-376.htm
*
* A web-friendly version is http://openiso.org/Ecma/376/Part4
*/
class MyXSSFSheetHandler extends DefaultHandler {
/**
* Table with styles
*/
private StylesTable stylesTable;
/**
* Table with unique strings
*/
private ReadOnlySharedStringsTable sharedStringsTable;
/**
* Destination for data
*/
private final PrintStream output;
/**
* Number of columns to read starting with leftmost
*/
private final int minColumnCount;
// Set when V start element is seen
private boolean vIsOpen;
// Set when cell start element is seen;
// used when cell close element is seen.
private xssfDataType nextDataType;
// Used to format numeric cell values.
private short formatIndex;
private String formatString;
private final DataFormatter formatter;
private int thisColumn = -1;
// The last column printed to the output stream
private int lastColumnNumber = -1;
// Gathers characters as they are seen.
private StringBuffer value;
private String[] record;
private List rows = new ArrayList();
private boolean isCellNull = false;
/**
* Accepts objects needed while parsing.
*
* @param styles Table of styles
* @param strings Table of shared strings
* @param cols Minimum number of columns to show
* @param target Sink for output
*/
public MyXSSFSheetHandler(StylesTable styles,
ReadOnlySharedStringsTable strings, int cols, PrintStream target) {
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
}
/*
* (non-Javadoc)
*
* @see
* org.xml.sax.helpers.DefaultHandler#startElement(java.lang.String,
* java.lang.String, java.lang.String, org.xml.sax.Attributes)
*/
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);
}
}
}
/*
* (non-Javadoc)
*
* @see org.xml.sax.helpers.DefaultHandler#endElement(java.lang.String,
* java.lang.String, java.lang.String)
*/
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:
// TODO: have seen an example of this, so it's untested.
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;
// 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[0] != null
&& record[1] != null)// 判断是否空行
{
rows.add(record.clone());
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;
}
/**
* Captures characters only if a suitable element is open. Originally
* was just "v"; extended for inlineStr also.
*/
public void characters(char[] ch, int start, int length)
throws SAXException {
if (vIsOpen)
value.append(ch, start, length);
}
/**
* Converts an Excel column name like "C" to a zero-based index.
*
* @param name
* @return Index corresponding to the specified name
*/
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;
/**
* Creates a new XLSX -> CSV converter
*
* @param pkg The XLSX package to process
* @param output The PrintStream to output the CSV to
* @param minColumns The minimum number of columns to output, or -1 for no minimum
*/
public XLSXConvertCSVReader(OPCPackage pkg, PrintStream output,
String sheetName, int minColumns) {
this.xlsxPackage = pkg;
this.output = output;
this.minColumns = minColumns;
this.sheetName = sheetName;
}
/**
* Parses and shows the content of one sheet using the specified styles and
* shared-strings tables.
*
* @param styles
* @param strings
* @param sheetInputStream
*/
public List processSheet(StylesTable styles,
ReadOnlySharedStringsTable strings, InputStream sheetInputStream)
throws IOException, ParserConfigurationException, SAXException {
InputSource sheetSource = new InputSource(sheetInputStream);
SAXParserFactory saxFactory = SAXParserFactory.newInstance();
SAXParser saxParser = saxFactory.newSAXParser();
XMLReader sheetParser = ((SAXParser) saxParser).getXMLReader();
MyXSSFSheetHandler handler = new MyXSSFSheetHandler(styles, strings,
this.minColumns, this.output);
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() throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(
this.xlsxPackage);
XSSFReader xssfReader = new XSSFReader(this.xlsxPackage);
Map> sheet2val = new HashMap<>();
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);
stream.close();
++index;
}
}
return list;
}
public Map> processAllSheet() throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(
this.xlsxPackage);
XSSFReader xssfReader = new XSSFReader(this.xlsxPackage);
Map> sheet2val = new HashMap<>();
List list = null;
StylesTable styles = xssfReader.getStylesTable();
XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader
.getSheetsData();
while (iter.hasNext()) {
InputStream stream = iter.next();
String sheetNameTemp = iter.getSheetName();
sheet2val.put(sheetNameTemp, processSheet(styles, strings, stream));
}
return sheet2val;
}
/**
* 读取Excel
*
* @param path 文件路径
* @param sheetName sheet名称
* @param minColumns 列总数
* @return
* @throws SAXException
* @throws ParserConfigurationException
* @throws OpenXML4JException
* @throws IOException
*/
private static List readerExcel(String path, String sheetName,
int minColumns) throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
OPCPackage p = OPCPackage.open(path, PackageAccess.READ);
XLSXConvertCSVReader xlsx2csv = new XLSXConvertCSVReader(p, System.out,
sheetName, minColumns);
List list = xlsx2csv.process();
p.close();
return list;
}
public static Map> readerExcel(MultipartFile file, int minColumns) throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
OPCPackage p = OPCPackage.open(file.getInputStream());
XLSXConvertCSVReader xlsx2csv = new XLSXConvertCSVReader(p, System.out,
null, minColumns);
Map> stringListMap = xlsx2csv.processAllSheet();
p.close();
return stringListMap;
}
public static void main(String[] args) throws Exception {
List list = XLSXConvertCSVReader
.readerExcel(
"E:\\平台知识库导入示例-温州社会保险.xlsx",
"社会保险", 16);
for (String[] record : list) {
for (String cell : record) {
System.out.print(cell + " ");
}
System.out.println();
}
}
}
数组解析关键代码
/**
* 导入excel文件，并转换成指定类型的List集合
*
* @param
* @param file
* @param fieldMap -- 标题和字段的映射，key为类中字段 |
* value为标题字段匹配规则集合（支持正则）（可以存在多个）
* @param tClass
* @return
* @throws Exception
*/
public static List importExcelSuper(MultipartFile file, Map> fieldMap, Class tClass, int titleRowIndex) throws Exception {
List result = new ArrayList<>();
Map> stringListMap = XLSXConvertCSVReader.readerExcel(file, 20);
for (Map.Entry> entry : stringListMap.entrySet()) {
int sheetIndex = 0;
convertExcelToBeans(result, entry.getValue(), fieldMap, tClass, titleRowIndex, sheetIndex);
sheetIndex++;
}
return result.size() > 0 ? result : null;
}
private static void convertExcelToBeans(List result, List sheet, Map> fieldMap, Class tClass, int titleRowIndex, int sheetIndex) throws Exception {
if (sheet != null) {
if (sheet.size() <= 1) {
throw new MyExcelException("CHECK_ME: file is empty.");
}
//获取标题行,并创建标题的列映射
Map> beanField2TitleMap = getBeanField2TitleMap(sheet.get(titleRowIndex), fieldMap);
if (beanField2TitleMap != null && beanField2TitleMap.size() > 0) {
//开始遍历除标题之外的行
for (int rowIndex = 0; rowIndex < sheet.size(); rowIndex++){
if (rowIndex < titleRowIndex + 1) {
//越过标题行,及标题行之前的所有内容
continue;
}
T tInstance = tClass.newInstance();
//处理多表格的表格编号
checkHasSheetIndexSetVal(tInstance, tClass, sheetIndex);
//处理类中其它字段的赋值
for (Map.Entry> entry : beanField2TitleMap.entrySet()) {
String fieldName = entry.getKey();
List cellIndexList = entry.getValue();
Field field = getBeanInnerField(tClass, fieldName);
Class fieldType = field.getType();
checkFieldTypeAndSetVal(sheet.get(rowIndex), fieldType, cellIndexList, fieldName, tClass, tInstance);
}
if (!BeanUtil.allFieldIsNull(tInstance)) {
result.add(tInstance);
}
}
} else {
throw new MyExcelException("字段匹配异常");
}
}
}
/**
* cvs格式，列头匹配
* @param titleRow
* @param fieldMap
* @return
*/
private static Map> getBeanField2TitleMap(String[] titleRow, Map> fieldMap) {
Map> beanField2TitleMap = new HashMap<>();
String[] fieldArr = fieldMap.keySet().toArray(new String[]{});
for (String key : fieldArr) {
List titleList = fieldMap.get(key);
List titleIndexList = new ArrayList<>();
for (String titleName : titleList) {
for (int index = 0; ; index++) {
String cell = titleRow[index];
if (null != cell) {
if (StringUtils.isEmpty(cell)) {
break;
} else {
if (cell.matches(titleName)) {
titleIndexList.add(index);
}
}
} else {
break;
}
}
}
if (titleIndexList != null && titleIndexList.size() > 0) {
beanField2TitleMap.put(key, titleIndexList);
}
}
return beanField2TitleMap;
}
/**
* 处理excel中表格编号
*
* @param tInstance
* @param tClass
* @param sheetIndex
* @param
* @throws NoSuchFieldException
* @throws NoSuchMethodException
* @throws InvocationTargetException
* @throws IllegalAccessException
*/
private static void checkHasSheetIndexSetVal(T tInstance, Class tClass, int sheetIndex) throws NoSuchFieldException, NoSuchMethodException, InvocationTargetException, IllegalAccessException {
List fieldNameList = Arrays.stream(tClass.getDeclaredFields()).map(Field::getName).collect(Collectors.toList());
if (fieldNameList.contains("sheetIndex")) {
Field sheetIndexField = tClass.getDeclaredField("sheetIndex");
Method method = tClass.getDeclaredMethod(generateSetMethodName("sheetIndex"), sheetIndexField.getType());
method.invoke(tInstance, sheetIndex);
}
}
/**
* 从当前类和父类，获取类中的feild
*
* @param tClass
* @param fieldName
* @param
* @return
* @throws NoSuchFieldException
*/
private static Field getBeanInnerField(Class tClass, String fieldName) throws NoSuchFieldException {
Field field = null;
try {
field = tClass.getDeclaredField(fieldName);
} catch (NoSuchFieldException e) {
field = tClass.getSuperclass().getDeclaredField(fieldName);
}
return field;
}
private static void checkFieldTypeAndSetVal(String[] row, Class fieldType, List cellIndexList, String fieldName, Class tClass, T tInstance) throws Exception {
if (null != cellIndexList && cellIndexList.size() > 0) {
if (fieldType.equals(List.class)) {
List cellValLis = new ArrayList<>();
for (Integer cellIndex : cellIndexList) {
String cell = row[cellIndex];
if (cell != null) {
//越过值为空的字段
if (StringUtils.isEmpty(cell)) {
continue;
}
cellValLis.add(cell);
}
}
Method method = getBeanInnerFieldMethod(tClass, fieldName, fieldType);
setFieldValue(method, tInstance, fieldType, cellValLis);
} else {
for (Integer cellIndex : cellIndexList) {
String cell = row[cellIndex];
if (cell != null) {
//越过值为空的字段
if (!StringUtils.isEmpty(cell)) {
Method method = getBeanInnerFieldMethod(tClass, fieldName, fieldType);
setFieldValue(method, tInstance, fieldType, cell);
}
}
}
}
}
}
/**
* 判断bean是否为全空，可以设置越过字段
* final字段默认越过
*
* @param bean
* @param skipFields
* @param
* @return
*/
public static boolean allFieldIsNull(T bean, String... skipFields) {
List skipFieldList = Arrays.stream(skipFields).collect(Collectors.toList());
try {
List fieldList = new ArrayList<>();
//获取当前类到最上层类的所有field
Class tempClass = bean.getClass();
while (tempClass != null) {
fieldList.addAll(Arrays.asList(tempClass.getDeclaredFields()));
tempClass = tempClass.getSuperclass();
}
for (Field field : fieldList) {
field.setAccessible(true);
if (skipFieldList.contains(field.getName()) || Modifier.isFinal(field.getModifiers())) {
continue;
}
Object o = field.get(bean);
if (!ObjectUtils.isEmpty(o)) {
return false;
}
}
} catch (IllegalAccessException e) {
logger.error("BeanUtil:allFieldIsNull =IllegalAccessException=>", e);
}
return true;
}