Skip to content

D
dataease
Unverified 提交 b03598db authored 作者: taojinlong's avatar taojinlong 提交者： GitHub
浏览文件
操作

Merge pull request #267 from dataease/pr@dev@excel

Merge branch 'dev' into pr@dev@excel
上级 7ed6e642 403350e3
隐藏空白字符变更
内嵌 并排
正在显示 包含 1012 行增加 和 1 行删除
backend/src/main/java/io/dataease/commons/utils/ExcelReaderUtil.java 0 → 100644
浏览文件 @ b03598db
package io.dataease.commons.utils;
import com.google.gson.Gson;
import io.dataease.datasource.dto.TableFiled;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
public class ExcelReaderUtil {
//excel2003扩展名
public static final String EXCEL03_EXTENSION = ".xls";
//excel2007扩展名
public static final String EXCEL07_EXTENSION = ".xlsx";
public static void sendRows(String filePath, String sheetName, int sheetIndex, int curRow, List<String> cellList) {
StringBuffer oneLineSb = new StringBuffer();
oneLineSb.append(filePath);
oneLineSb.append("--");
oneLineSb.append("sheet" + sheetIndex);
oneLineSb.append("::" + sheetName);//加上sheet名
oneLineSb.append("--");
oneLineSb.append("row" + curRow);
oneLineSb.append("::");
// map.put(cellList.get(9),cellList.get(0)) ;
for (String cell : cellList) {
oneLineSb.append(cell.trim());
oneLineSb.append("|");
}
String oneLine = oneLineSb.toString();
if (oneLine.endsWith("|")) {
oneLine = oneLine.substring(0, oneLine.lastIndexOf("|"));
}// 去除最后一个分隔符
System.out.println(oneLine);
}
/**
* 读取excel文件路径
* @param fileName 文件路径
* @throws Exception
*/
public static void readExcel(String fileName, InputStream inputStream) throws Exception {
if (fileName.endsWith(EXCEL03_EXTENSION)) { //处理excel2003文件
ExcelXlsReader excelXls=new ExcelXlsReader();
excelXls.process(inputStream);
System.out.println(excelXls.totalSheets.size());
System.out.println(excelXls.totalSheets.get(0).getSheetName());
for (TableFiled field : excelXls.totalSheets.get(0).getFields()) {
System.out.println(new Gson().toJson(field));
}
System.out.println(excelXls.totalSheets.get(0).getData().get(0));
} else if (fileName.endsWith(EXCEL07_EXTENSION)) {//处理excel2007文件
ExcelXlsxReader excelXlsxReader = new ExcelXlsxReader();
excelXlsxReader.process(inputStream);
System.out.println(excelXlsxReader.totalSheets.size());
System.out.println(excelXlsxReader.totalSheets.get(0).getSheetName());
for (TableFiled field : excelXlsxReader.totalSheets.get(0).getFields()) {
System.out.println(new Gson().toJson(field));
}
System.out.println(excelXlsxReader.totalSheets.get(0).getData().get(0));
} else {
throw new Exception("文件格式错误，fileName的扩展名只能是xls或xlsx。");
}
}
public static void main(String[] args) throws Exception {
ExcelReaderUtil.readExcel("111.xls", new FileInputStream("/Users/taojinlong/Desktop/111.xls"));
}
}
backend/src/main/java/io/dataease/commons/utils/ExcelXlsReader.java 0 → 100644
浏览文件 @ b03598db
package io.dataease.commons.utils;
import com.google.gson.Gson;
import io.dataease.datasource.dto.TableFiled;
import io.dataease.dto.dataset.ExcelSheetData;
import io.dataease.i18n.Translator;
import org.apache.poi.hssf.eventusermodel.*;
import org.apache.poi.hssf.eventusermodel.dummyrecord.LastCellOfRowDummyRecord;
import org.apache.poi.hssf.eventusermodel.dummyrecord.MissingCellDummyRecord;
import org.apache.poi.hssf.model.HSSFFormulaParser;
import org.apache.poi.hssf.record.*;
import org.apache.poi.hssf.usermodel.HSSFDataFormatter;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
/**
* @author y
* @create 2018-01-19 14:18
* @desc 用于解决.xls2003版本大数据量问题
**/
public class ExcelXlsReader implements HSSFListener {
public ExcelReaderUtil excelReaderUtil = new ExcelReaderUtil();
private int minColums = -1;
private POIFSFileSystem fs;
/**
* 总行数
*/
private int totalRows = 0;
/**
* 上一行row的序号
*/
private int lastRowNumber;
/**
* 上一单元格的序号
*/
private int lastColumnNumber;
/**
* 是否输出formula，还是它对应的值
*/
private boolean outputFormulaValues = true;
/**
* 用于转换formulas
*/
private EventWorkbookBuilder.SheetRecordCollectingListener workbookBuildingListener;
//excel2003工作簿
private HSSFWorkbook stubWorkbook;
private SSTRecord sstRecord;
private FormatTrackingHSSFListener formatListener;
private final HSSFDataFormatter formatter = new HSSFDataFormatter();
/**
* 文件的绝对路径
*/
private String filePath = "";
//表索引
private int sheetIndex = 0;
private BoundSheetRecord[] orderedBSRs;
@SuppressWarnings("unchecked")
private ArrayList boundSheetRecords = new ArrayList();
private int nextRow;
private int nextColumn;
private boolean outputNextStringRecord;
//当前行
private int curRow = 0;
//存储一行记录所有单元格的容器
private List<String> cellList = new ArrayList<String>();
/**
* 判断整行是否为空行的标记
*/
private boolean flag = false;
@SuppressWarnings("unused")
private String sheetName;
public List<TableFiled> fields = new ArrayList<>();
public List<List<String>> data = new ArrayList<>();
public List<ExcelSheetData> totalSheets = new ArrayList<>();
/**
* 是否为日期
*/
private boolean isDateFormat = false;
public List<TableFiled> getFields() {
return fields;
}
public void setFields(List<TableFiled> fields) {
this.fields = fields;
}
public List<List<String>> getData() {
return data;
}
public void setData(List<List<String>> data) {
this.data = data;
}
/**
* 遍历excel下所有的sheet
*
* @param inputStream
* @throws Exception
*/
public int process(InputStream inputStream) throws Exception {
this.fs = new POIFSFileSystem(inputStream);
MissingRecordAwareHSSFListener listener = new MissingRecordAwareHSSFListener(this);
formatListener = new FormatTrackingHSSFListener(listener);
HSSFEventFactory factory = new HSSFEventFactory();
HSSFRequest request = new HSSFRequest();
if (outputFormulaValues) {
request.addListenerForAllRecords(formatListener);
} else {
workbookBuildingListener = new EventWorkbookBuilder.SheetRecordCollectingListener(formatListener);
request.addListenerForAllRecords(workbookBuildingListener);
}
factory.processWorkbookEvents(request, fs);
return totalRows; //返回该excel文件的总行数，不包括首列和空行
}
/**
* HSSFListener 监听方法，处理Record
* 处理每个单元格
*
* @param record
*/
@SuppressWarnings("unchecked")
public void processRecord(Record record) {
int thisRow = -1;
int thisColumn = -1;
String thisStr = null;
String value = null;
switch (record.getSid()) {
case BoundSheetRecord.sid:
boundSheetRecords.add(record);
break;
case BOFRecord.sid: //开始处理每个sheet
BOFRecord br = (BOFRecord) record;
if (br.getType() == BOFRecord.TYPE_WORKSHEET) {
//如果有需要，则建立子工作簿
if (workbookBuildingListener != null && stubWorkbook == null) {
stubWorkbook = workbookBuildingListener.getStubHSSFWorkbook();
}
if (orderedBSRs == null) {
orderedBSRs = BoundSheetRecord.orderByBofPosition(boundSheetRecords);
}
sheetName = orderedBSRs[sheetIndex].getSheetname();
sheetIndex++;
}
break;
case MergeCellsRecord.sid:
throw new RuntimeException(Translator.get("i18n_excel_have_merge_region"));
case SSTRecord.sid:
sstRecord = (SSTRecord) record;
break;
case BlankRecord.sid: //单元格为空白
BlankRecord brec = (BlankRecord) record;
thisRow = brec.getRow();
thisColumn = brec.getColumn();
thisStr = "";
cellList.add(thisColumn, thisStr);
break;
case BoolErrRecord.sid: //单元格为布尔类型
BoolErrRecord berec = (BoolErrRecord) record;
thisRow = berec.getRow();
thisColumn = berec.getColumn();
thisStr = berec.getBooleanValue() + "";
cellList.add(thisColumn, thisStr);
checkRowIsNull(thisStr); //如果里面某个单元格含有值，则标识该行不为空行
break;
case FormulaRecord.sid://单元格为公式类型
FormulaRecord frec = (FormulaRecord) record;
thisRow = frec.getRow();
thisColumn = frec.getColumn();
thisStr = String.valueOf(frec.getValue());
// if (outputFormulaValues) {
// if (Double.isNaN(frec.getValue())) {
// outputNextStringRecord = true;
// nextRow = frec.getRow();
// nextColumn = frec.getColumn();
// } else {
// thisStr = '"' + HSSFFormulaParser.toFormulaString(stubWorkbook, frec.getParsedExpression()) + '"';
// }
// } else {
// thisStr = '"' + HSSFFormulaParser.toFormulaString(stubWorkbook, frec.getParsedExpression()) + '"';
// }
String feildType = checkType(thisStr, thisColumn);
if(feildType.equalsIgnoreCase("LONG") && thisStr.endsWith(".0")){
thisStr = thisStr.substring(0, thisStr.length() -2);
}
cellList.add(thisColumn, thisStr);
checkRowIsNull(thisStr); //如果里面某个单元格含有值，则标识该行不为空行
break;
case StringRecord.sid: //单元格中公式的字符串
if (outputNextStringRecord) {
StringRecord srec = (StringRecord) record;
thisStr = srec.getString();
thisRow = nextRow;
thisColumn = nextColumn;
outputNextStringRecord = false;
}
break;
case LabelRecord.sid:
LabelRecord lrec = (LabelRecord) record;
curRow = thisRow = lrec.getRow();
thisColumn = lrec.getColumn();
value = lrec.getValue().trim();
value = value.equals("") ? "" : value;
cellList.add(thisColumn, value);
checkRowIsNull(value); //如果里面某个单元格含有值，则标识该行不为空行
break;
case LabelSSTRecord.sid: //单元格为字符串类型
LabelSSTRecord lsrec = (LabelSSTRecord) record;
curRow = thisRow = lsrec.getRow();
thisColumn = lsrec.getColumn();
if (sstRecord == null) {
cellList.add(thisColumn, "");
} else {
value = sstRecord.getString(lsrec.getSSTIndex()).toString().trim();
value = value.equals("") ? "" : value;
cellList.add(thisColumn, value);
checkRowIsNull(value); //如果里面某个单元格含有值，则标识该行不为空行
}
break;
case NumberRecord.sid: //单元格为数字类型
NumberRecord numrec = (NumberRecord) record;
curRow = thisRow = numrec.getRow();
thisColumn = numrec.getColumn();
//第一种方式
//value = formatListener.formatNumberDateCell(numrec).trim();//这个被写死，采用的m/d/yy h:mm格式，不符合要求
//第二种方式，参照formatNumberDateCell里面的实现方法编写
Double valueDouble = ((NumberRecord) numrec).getValue();
String formatString = formatListener.getFormatString(numrec);
if (formatString.contains("m/d/yy")) {
formatString = "yyyy-MM-dd hh:mm:ss";
}
int formatIndex = formatListener.getFormatIndex(numrec);
value = formatter.formatRawCellContents(valueDouble, formatIndex, formatString).trim();
value = value.equals("") ? "" : value;
//向容器加入列值
cellList.add(thisColumn, value);
if(formatIndex == 59){
totalSheets.get(totalSheets.size() -1).getFields().get(thisColumn).setFieldType("DATETIME");
}else {
checkType(value, thisColumn);
}
checkRowIsNull(value); //如果里面某个单元格含有值，则标识该行不为空行
break;
default:
break;
}
//遇到新行的操作
if (thisRow != -1 && thisRow != lastRowNumber) {
lastColumnNumber = -1;
}
//空值的操作
if (record instanceof MissingCellDummyRecord) {
MissingCellDummyRecord mc = (MissingCellDummyRecord) record;
curRow = thisRow = mc.getRow();
thisColumn = mc.getColumn();
cellList.add(thisColumn, "");
}
//更新行和列的值
if (thisRow > -1)
lastRowNumber = thisRow;
if (thisColumn > -1)
lastColumnNumber = thisColumn;
//行结束时的操作
if (record instanceof LastCellOfRowDummyRecord) {
if (minColums > 0) {
//列值重新置空
if (lastColumnNumber == -1) {
lastColumnNumber = 0;
}
}
lastColumnNumber = -1;
if(!totalSheets.stream().map(ExcelSheetData::getSheetName).collect(Collectors.toList()).contains(sheetName)){
ExcelSheetData excelSheetData = new ExcelSheetData();
excelSheetData.setSheetName(sheetName);
excelSheetData.setData(new ArrayList<>());
excelSheetData.setFields(new ArrayList<>());
totalSheets.add(excelSheetData);
}
if(curRow == 0){
for (String s : cellList) {
TableFiled tableFiled = new TableFiled();
tableFiled.setFieldType("TEXT");
tableFiled.setFieldSize(65533);
tableFiled.setFieldName(s);
tableFiled.setRemarks(s);
this.fields.add(tableFiled);
totalSheets.get(totalSheets.size() -1).getFields().add(tableFiled);
}
}
if (flag && curRow != 0) { //该行不为空行且该行不是第一行，发送（第一行为列名，不需要）
if(!totalSheets.stream().map(ExcelSheetData::getSheetName).collect(Collectors.toList()).contains(sheetName)){
ExcelSheetData excelSheetData = new ExcelSheetData();
excelSheetData.setData(new ArrayList<>(data));
excelSheetData.setSheetName(sheetName);
excelSheetData.setFields(new ArrayList<>(fields));
List<String> tmp = new ArrayList<>(cellList);
excelSheetData.getData().add(tmp);
totalRows++;
totalSheets.add(excelSheetData);
}else {
List<String> tmp = new ArrayList<>(cellList);
totalSheets.stream().filter(s->s.getSheetName().equalsIgnoreCase(sheetName)).collect(Collectors.toList()).get(0).getData().add(tmp);
totalRows++;
}
}
//清空容器
cellList.clear();
flag = false;
}
}
/**
* 如果里面某个单元格含有值，则标识该行不为空行
*
* @param value
*/
public void checkRowIsNull(String value) {
if (value != null && !"".equals(value)) {
flag = true;
}
}
private String checkType(String str, int thisColumn){
String type = null;
try {
double d = Double.valueOf(str);
try {
Double value = new Double(d);
double eps = 1e-10;
if (value - Math.floor(value) < eps) {
type = "LONG";
} else {
type = "DOUBLE";
}
} catch (Exception e) {
type = "TEXT";
}
}catch (Exception e){
type = "TEXT";
}
String oldType = totalSheets.get(totalSheets.size() -1).getFields().get(thisColumn).getFieldType();
if(type.equalsIgnoreCase("LONG") && oldType.equalsIgnoreCase("TEXT")){
totalSheets.get(totalSheets.size() -1).getFields().get(thisColumn).setFieldType(type);
}
if(type.equalsIgnoreCase("DOUBLE")){
totalSheets.get(totalSheets.size() -1).getFields().get(thisColumn).setFieldType(type);
}
return type;
}
}
\ No newline at end of file
backend/src/main/java/io/dataease/commons/utils/ExcelXlsxReader.java 0 → 100644
浏览文件 @ b03598db
package io.dataease.commons.utils;
import com.google.gson.Gson;
import io.dataease.datasource.dto.TableFiled;
import io.dataease.dto.dataset.ExcelSheetData;
import io.dataease.i18n.Translator;
import io.dataease.service.message.MsgAop;
import org.apache.commons.lang3.StringUtils;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.ss.usermodel.BuiltinFormats;
import org.apache.poi.ss.usermodel.DataFormatter;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
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 org.xml.sax.helpers.XMLReaderFactory;
import java.io.InputStream;
import java.util.*;
/**
* @author y
* @create 2018-01-18 14:28
* @desc POI读取excel有两种模式，一种是用户模式，一种是事件驱动模式
* 采用SAX事件驱动模式解决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下，容易出现内存溢出
* <p>
* 用于解决.xlsx2007版本大数据量问题
**/
public class ExcelXlsxReader extends DefaultHandler {
/**
* 自定义获取表格某些信息
*/
public Map map = new TreeMap<String,String>();
/**
* 单元格中的数据可能的数据类型
*/
enum CellDataType {
BOOL, ERROR, FORMULA, INLINESTR, SSTINDEX, NUMBER, DATE, NULL
}
/**
* 共享字符串表
*/
private SharedStringsTable sst;
/**
* 上一次的索引值
*/
private String lastIndex;
/**
* 总行数
*/
private int totalRows=0;
/**
* 一行内cell集合
*/
private List<String> cellList = new ArrayList<String>();
/**
* 判断整行是否为空行的标记
*/
private boolean flag = false;
/**
* 当前行
*/
private int curRow = 1;
/**
* 当前列
*/
private int curCol = 0;
/**
* T元素标识
*/
private boolean isTElement;
/**
* 单元格数据类型，默认为字符串类型
*/
private CellDataType nextDataType = CellDataType.SSTINDEX;
private final DataFormatter formatter = new DataFormatter();
/**
* 单元格日期格式的索引
*/
private short formatIndex;
/**
* 日期格式字符串
*/
private String formatString;
//定义前一个元素和当前元素的位置，用来计算其中空的单元格数量，如A6和A8等
private String preRef = null, ref = null;
//定义该文档一行最大的单元格数，用来补全一行最后可能缺失的单元格
private String maxRef = null;
/**
* 单元格
*/
private StylesTable stylesTable;
public List<TableFiled> fields = new ArrayList<>();
public List<List<String>> data = new ArrayList<>();
public List<ExcelSheetData> totalSheets = new ArrayList<>();
/**
* 是否为日期
*/
private boolean isDateFormat = false;
public List<TableFiled> getFields() {
return fields;
}
public void setFields(List<TableFiled> fields) {
this.fields = fields;
}
public List<List<String>> getData() {
return data;
}
public void setData(List<List<String>> data) {
this.data = data;
}
public int process(InputStream inputStream) throws Exception {
OPCPackage pkg = OPCPackage.open(inputStream);
XSSFReader xssfReader = new XSSFReader(pkg);
stylesTable = xssfReader.getStylesTable();
SharedStringsTable sst = xssfReader.getSharedStringsTable();
XMLReader parser = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
this.sst = sst;
parser.setContentHandler(this);
XSSFReader.SheetIterator sheets = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
while (sheets.hasNext()) { //遍历sheet
curRow = 1; //标记初始行为第一行
fields.clear();
data.clear();
InputStream sheet = sheets.next(); //sheets.next()和sheets.getSheetName()不能换位置，否则sheetName报错
InputSource sheetSource = new InputSource(sheet);
parser.parse(sheetSource); //解析excel的每条记录，在这个过程中startElement()、characters()、endElement()这三个函数会依次执行
ExcelSheetData excelSheetData = new ExcelSheetData();
excelSheetData.setData(new ArrayList<>(data));
excelSheetData.setSheetName(sheets.getSheetName());
excelSheetData.setFields(new ArrayList<>(fields));
totalSheets.add(excelSheetData);
sheet.close();
}
return totalRows; //返回该excel文件的总行数，不包括首列和空行
}
/**
* 第一个执行
*
* @param uri
* @param localName
* @param name
* @param attributes
* @throws SAXException
*/
@Override
public void startElement(String uri, String localName, String name, Attributes attributes) throws SAXException {
if(curRow>101){
return;
}
if(name.equalsIgnoreCase("mergeCell")){
throw new RuntimeException(Translator.get("i18n_excel_have_merge_region"));
}
//c => 单元格
if ("c".equals(name)) {
//当前单元格的位置
ref = attributes.getValue("r");
//设定单元格类型
this.setNextDataType(attributes);
}
//当元素为t时
if ("t".equals(name)) {
isTElement = true;
} else {
isTElement = false;
}
//置空
lastIndex = "";
}
/**
* 第二个执行
* 得到单元格对应的索引值或是内容值
* 如果单元格类型是字符串、INLINESTR、数字、日期，lastIndex则是索引值
* 如果单元格类型是布尔值、错误、公式，lastIndex则是内容值
* @param ch
* @param start
* @param length
* @throws SAXException
*/
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
if(curRow>101){
return;
}
lastIndex += new String(ch, start, length);
}
/**
* 第三个执行
*
* @param uri
* @param localName
* @param name
* @throws SAXException
*/
@Override
public void endElement(String uri, String localName, String name) throws SAXException {
if(curRow>101){
return;
}
//t元素也包含字符串
if (isTElement) {//这个程序没经过
//将单元格内容加入rowlist中，在这之前先去掉字符串前后的空白符
String value = lastIndex.trim();
cellList.add(curCol, value);
curCol++;
isTElement = false;
//如果里面某个单元格含有值，则标识该行不为空行
if (value != null && !"".equals(value)) {
flag = true;
}
} else if ("v".equals(name)) {
//v => 单元格的值，如果单元格是字符串，则v标签的值为该字符串在SST中的索引
String value = this.getDataValue(lastIndex.trim(), "");//根据索引值获取对应的单元格值
if (preRef == null) {
preRef = ref;
}
//补全单元格之间的空单元格
if (!ref.equals(preRef)) {
int len = countNullCell(ref, preRef);
for (int i = 0; i < len; i++) {
cellList.add(curCol, "");
curCol++;
}
}
cellList.add(curCol, value);
curCol++;
//如果里面某个单元格含有值，则标识该行不为空行
if (value != null && !"".equals(value)) {
flag = true;
}
preRef = ref;
} else {
//如果标签名称为row，这说明已到行尾
if ("row".equals(name)) {
//默认第一行为表头，以该行单元格数目为最大数目
if (curRow == 1) {
maxRef = ref;
}
//补全一行尾部可能缺失的单元格
if (maxRef != null) {
int len = countNullCell(maxRef, ref);
for (int i = 0; i <= len; i++) {
cellList.add(curCol, "");
curCol++;
}
}
if(curRow>1){
List<String> tmp = new ArrayList<>(cellList);
this.getData().add(tmp);
}
totalRows++;
cellList.clear();
curRow++;
curCol = 0;
preRef = null;
ref = null;
flag=false;
}
}
}
/**
* 处理数据类型
*
* @param attributes
*/
public void setNextDataType(Attributes attributes) {
nextDataType = CellDataType.NUMBER; //cellType为空，则表示该单元格类型为数字
formatIndex = -1;
formatString = null;
String cellType = attributes.getValue("t"); //单元格类型
if ("b".equals(cellType)) { //处理布尔值
nextDataType = CellDataType.BOOL;
} else if ("e".equals(cellType)) { //处理错误
nextDataType = CellDataType.ERROR;
} else if ("inlineStr".equals(cellType)) {
nextDataType = CellDataType.INLINESTR;
} else if ("s".equals(cellType)) { //处理字符串
nextDataType = CellDataType.SSTINDEX;
} else if ("str".equals(cellType)) {
nextDataType = CellDataType.FORMULA;
}
String cellStyleStr = attributes.getValue("s"); //
if (cellStyleStr != null) {
int styleIndex = Integer.parseInt(cellStyleStr);
XSSFCellStyle style = this.stylesTable.getStyleAt(styleIndex);
formatIndex = style.getDataFormat();
formatString = style.getDataFormatString();
short format = this.formatIndex;
if (format == 14 || format == 31 || format == 57 ||format == 59||
format == 58 || (176 <= format && format <= 178)
|| (182 <= format && format <= 196) ||
(210 <= format && format <= 213) || (208 == format))
{ // 日期
isDateFormat = true;
}
}
}
/**
* 对解析出来的数据进行类型处理
* @param value 单元格的值，
* value代表解析：BOOL的为0或1， ERROR的为内容值，FORMULA的为内容值，INLINESTR的为索引值需转换为内容值，
* SSTINDEX的为索引值需转换为内容值， NUMBER为内容值，DATE为内容值
* @param thisStr 一个空字符串
* @return
*/
@SuppressWarnings("deprecation")
public String getDataValue(String value, String thisStr) {
String type = "TEXT";
switch (nextDataType) {
// 这几个的顺序不能随便交换，交换了很可能会导致数据错误
case BOOL: //布尔值
char first = value.charAt(0);
thisStr = first == '0' ? "FALSE" : "TRUE";
type = "LONG";
break;
case ERROR: //错误
thisStr = "\"ERROR:" + value.toString() + '"';
break;
case FORMULA: //公式
thisStr = '"' + value.toString() + '"';
type = getType(thisStr);
break;
case INLINESTR:
XSSFRichTextString rtsi = new XSSFRichTextString(value.toString());
thisStr = rtsi.toString();
rtsi = null;
break;
case SSTINDEX: //字符串
String sstIndex = value.toString();
try {
int idx = Integer.parseInt(sstIndex);
XSSFRichTextString rtss = new XSSFRichTextString(sst.getEntryAt(idx));//根据idx索引值获取内容值
thisStr = rtss.toString();
rtss = null;
} catch (NumberFormatException ex) {
thisStr = value.toString();
}
break;
case NUMBER: //数字
if (formatString != null) {
thisStr = formatter.formatRawCellContents(Double.parseDouble(value), formatIndex, formatString).trim();
} else {
thisStr = value;
}
thisStr = thisStr.replace("_", "").trim();
if(isDateFormat){
type = "DATETIME";isDateFormat = false;
}else {
type = getType(thisStr);
}
break;
case DATE: //日期
thisStr = formatter.formatRawCellContents(Double.parseDouble(value), formatIndex, formatString);
// 对日期字符串作特殊处理，去掉T
thisStr = thisStr.replace("T", " ");
type = "DATETIME";
break;
default:
thisStr = " ";
break;
}
if(curRow==1){
TableFiled tableFiled = new TableFiled();
tableFiled.setFieldType(type);
tableFiled.setFieldSize(65533);
tableFiled.setFieldName(thisStr);
tableFiled.setRemarks(thisStr);
this.fields.add(tableFiled);
}else {
this.getFields().get(curCol).setFieldType(type);
}
return thisStr;
}
private String getType(String thisStr){
if(totalRows==0){
return "TEXT";
}
try{
if(thisStr.endsWith("%")){
thisStr = thisStr.substring(0, thisStr.length()-1);
thisStr = String.valueOf(Double.valueOf(thisStr)/100);
}
Long.valueOf(thisStr);
if(this.getFields().get(curCol).getFieldType().equalsIgnoreCase("TEXT")){
return "LONG";
}
}catch (Exception e){
try {
Double.valueOf(thisStr);
return "DOUBLE";
}catch (Exception ignore){ }
}
return "TEXT";
}
public int countNullCell(String ref, String preRef) {
//excel2007最大行数是1048576，最大列数是16384，最后一列列名是XFD
String xfd = ref.replaceAll("\\d+", "");
String xfd_1 = preRef.replaceAll("\\d+", "");
xfd = fillChar(xfd, 3, '@', true);
xfd_1 = fillChar(xfd_1, 3, '@', true);
char[] letter = xfd.toCharArray();
char[] letter_1 = xfd_1.toCharArray();
int res = (letter[0] - letter_1[0]) * 26 * 26 + (letter[1] - letter_1[1]) * 26 + (letter[2] - letter_1[2]);
return res - 1;
}
public String fillChar(String str, int len, char let, boolean isPre) {
int len_1 = str.length();
if (len_1 < len) {
if (isPre) {
for (int i = 0; i < (len - len_1); i++) {
str = let + str;
}
} else {
for (int i = 0; i < (len - len_1); i++) {
str = str + let;
}
}
}
return str;
}
}
\ No newline at end of file
backend/src/main/java/io/dataease/datasource/provider/JdbcProvider.java
浏览文件 @ b03598db
......@@ -185,6 +185,9 @@ public class JdbcProvider extends DatasourceProvider {
field.setFieldType(t);
field.setFieldSize(metaData.getColumnDisplaySize(j + 1));
if(t.equalsIgnoreCase("LONG")){field.setFieldSize(65533);} //oracle LONG
if(StringUtils.isNotEmpty(t) && t.toLowerCase().contains("date") && field.getFieldSize() < 50 ){
field.setFieldSize(50);
}
fieldList.add(field);
}
return fieldList;
......
backend/src/main/java/io/dataease/dto/dataset/ExcelSheetData.java 0 → 100644
浏览文件 @ b03598db
package io.dataease.dto.dataset;
import io.dataease.datasource.dto.TableFiled;
import lombok.Data;
import java.util.List;
@Data
public class ExcelSheetData {
private String sheetName;
private List<List<String>> data;
private List<TableFiled> fields;
}
backend/src/main/java/io/dataease/service/dataset/DataSetTableService.java
浏览文件 @ b03598db
......@@ -1012,7 +1012,7 @@ public class DataSetTableService {
public Map<String, Object> excelSaveAndParse(MultipartFile file, String tableId) throws Exception {
String filename = file.getOriginalFilename();
// parse file
Map<String, Object> fileMap = parseExcel(filename, file.getInputStream(), true);
Map<String, Object> fileMap = parseExcel2(filename, file.getInputStream(), true);
if (StringUtils.isNotEmpty(tableId)) {
List<DatasetTableField> datasetTableFields = dataSetTableFieldsService.getFieldsByTableId(tableId);
datasetTableFields.sort((o1, o2) -> {
......@@ -1038,6 +1038,52 @@ public class DataSetTableService {
return map;
}
private Map<String, Object> parseExcel2(String filename, InputStream inputStream, boolean isPreview) throws Exception {
String suffix = filename.substring(filename.lastIndexOf(".") + 1);
List<TableFiled> fields = new ArrayList<>();
List<List<String>> data = new ArrayList<>();
List<Map<String, Object>> jsonArray = new ArrayList<>();
List<String> sheets = new ArrayList<>();
if (StringUtils.equalsIgnoreCase(suffix, "xls")) {
ExcelXlsReader excelXlsReader = new ExcelXlsReader();
excelXlsReader.process(inputStream);
fields = excelXlsReader.totalSheets.get(0).getFields();
data = excelXlsReader.totalSheets.get(0).getData();
sheets = excelXlsReader.totalSheets.stream().map(ExcelSheetData::getSheetName).collect(Collectors.toList());
}
if (StringUtils.equalsIgnoreCase(suffix, "xlsx")) {
ExcelXlsxReader excelXlsxReader = new ExcelXlsxReader();
excelXlsxReader.process(inputStream);
fields = excelXlsxReader.totalSheets.get(0).getFields();
data = excelXlsxReader.totalSheets.get(0).getData();
sheets = excelXlsxReader.totalSheets.stream().map(ExcelSheetData::getSheetName).collect(Collectors.toList());
}
String[] fieldArray = fields.stream().map(TableFiled::getFieldName).toArray(String[]::new);
// 校验excel字段是否重名
if (checkIsRepeat(fieldArray)) {
DataEaseException.throwException(Translator.get("i18n_excel_field_repeat"));
}
if (CollectionUtils.isNotEmpty(data)) {
jsonArray = data.stream().map(ele -> {
Map<String, Object> map = new HashMap<>();
for (int i = 0; i < ele.size(); i++) {
map.put(fieldArray[i], ele.get(i));
}
return map;
}).collect(Collectors.toList());
}
inputStream.close();
Map<String, Object> map = new HashMap<>();
map.put("fields", fields);
map.put("data", jsonArray);
map.put("sheets", sheets);
return map;
}
private Map<String, Object> parseExcel(String filename, InputStream inputStream, boolean isPreview) throws Exception {
String suffix = filename.substring(filename.lastIndexOf(".") + 1);
List<TableFiled> fields = new ArrayList<>();
......@@ -1191,6 +1237,7 @@ public class DataSetTableService {
return map;
}
private String readCell(Cell cell, boolean cellType, TableFiled tableFiled) {
if (cell == null) {
return "";
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论