本文介绍使用SAX模式处理XLSX文件的方法，有效避免内存溢出问题，适用于大数据量、多Sheet及含有大量空白行的Excel文件。通过XLSXSaxReader类，实现对XLSX文件的高效读取。
-
引包
org.apache.poi poi 3.8 org.apache.poi poi-ooxml 3.8 -
使用方式：
XLSXSaxReader.readerExcelByInputStream(multipartFile.getInputStream(), “Sheet1”, 42);
import org.apache.log4j.Logger;
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.*;
/**
* 使用SAX模式解决XLSX文件，可以有效解决用户模式内存溢出的问题
* 该模式是POI官方推荐的读取大数据的模式，在用户模式下，数据量较大、Sheet较多、或者是有很多无用的空行的情况
* ，容易出现内存溢出,用户模式读取Excel的典型代码如下： FileInputStream file=new
* FileInputStream("c:\\test.xlsx"); Workbook wb=new XSSFWorkbook(file);
*/
public class XLSXSaxReader {
private static final Logger logger = Logger.getLogger(XLSXSaxReader.class);
enum xssfDataType {
BOOL, ERROR, FORMULA, INLINESTR, SSTINDEX, NUMBER,
}
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<String[]> rows = new ArrayList<String[]>();
private boolean isCellNull = false;
private Map<String, Object> resultMap = new HashMap<String, Object>();
private List<String> checkList = new ArrayList<String>(); //校验始发城市和目的站点的唯一性
/**
* 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
resultMap.clear();//清空结果集
checkList.clear();
}
/*
* (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)) {//一行结尾.校验数据有效性病并缓存数据
// Print out any missing commas if needed
if (minColumns > 0) {
// Columns are 0 based
if (lastColumnNumber == -1) {
lastColumnNumber = 0;
}
if (isCellNull == false && StringUtils.isNotEmpty(record[0]) && StringUtils.isNotEmpty(record[2]))// 判断前两个单元格是否为空值 ，为空值则不添加此行
{
//校验某几列的组合的唯一性
if (rows.size() > 0) {
String uniqueId = String.valueOf(record[0]) + "-" + String.valueOf(record[2]);
if (checkList.contains(uniqueId)) {
logger.error("请检查第" + rows.size() + "行指定列是唯一的");
resultMap.put("error", "请检查第" + rows.size() + "行是唯一的");
throw new SAXException();
} else {
checkList.add(uniqueId);
}
}
rows.add(record.clone());
isCellNull = false;
for (int i = 0; i < record.length; i++) {
record[i] = null;
}
} else {
logger.info("第" + rows.size() + "行ID为空,请检查后再上传");
resultMap.put("error", "第" + rows.size() + "行ID为空,请检查后再上传");
throw new SAXException();
}
}
lastColumnNumber = -1;
}
}
public List<String[]> getRows() {
return rows;
}
public void setRows(List<String[]> 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);
}
public Map<String, Object> getResultMap() {
return resultMap;
}
public void setResultMap(Map<String, Object> resultMap) {
this.resultMap = resultMap;
}
}
// /////////////////////////////////////
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 XLSXSaxReader(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 Map<String, Object> 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.getXMLReader();
MyXSSFSheetHandler handler = new MyXSSFSheetHandler(styles, strings, this.minColumns, this.output);
sheetParser.setContentHandler(handler);
try {
sheetParser.parse(sheetSource);
} catch (Exception e) {
//logger.error("捕获到异常",e);
return handler.getResultMap();
}
handler.getResultMap().put("result", handler.getRows());
return handler.getResultMap();
}
/**
* 初始化这个处理程序 将
*
* @throws IOException
* @throws OpenXML4JException
* @throws ParserConfigurationException
* @throws SAXException
*/
public Map<String, Object> process() throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(
this.xlsxPackage);
XSSFReader xssfReader = new XSSFReader(this.xlsxPackage);
Map<String, Object> map = 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)) {
map = processSheet(styles, strings, stream);
stream.close();
++index;
}
}
return map;
}
/**
* 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 Map<String, Object> readerExcel(String path, String sheetName,
int minColumns) throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
OPCPackage p = OPCPackage.open(path, PackageAccess.READ);
XLSXSaxReader xlsx2csv = new XLSXSaxReader(p, System.out,
sheetName, minColumns);
Map<String, Object> map = xlsx2csv.process();
p.close();
return map;
}
public static Map<String, Object> readerExcelByInputStream(InputStream inputStream, String sheetName, int minColumns) throws IOException, OpenXML4JException,
ParserConfigurationException, SAXException {
OPCPackage p = OPCPackage.open(inputStream);
XLSXSaxReader xlsx2csv = new XLSXSaxReader(p, null,
sheetName, minColumns);
Map<String, Object> map = xlsx2csv.process();
logger.info("解析数据成功");
p.close();
inputStream.close();
return map;
}
/* public void error (SAXParseException e)
throws SAXException
{
return;
}*/
}
扫一扫
596
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
