Merge pull request #551 from alibaba/2.0.0-beta4

2.0.0 beta4

.github/ISSUE_TEMPLATE/1question.md

@@ -1,18 +0,0 @@
-name: 使用疑问
-about: 请先阅读“快速使用”,上面无法解决再提交问题
-name: 给出建议
-about: 给出一些建议的能
-title: ''
-labels: help wanted
-labels: suggest
-assignees: ''
-
----
-
-**异常代码**
-```java
-   这里写你的代码
-```
-**异常提示**
-请提供完整的异常提示
-**建议描述**

pom.xml

@@ -4,7 +4,7 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>com.alibaba</groupId>
     <artifactId>easyexcel</artifactId>
-    <version>2.0.0-beta3</version>
+    <version>2.0.0-beta4</version>
     <packaging>jar</packaging>
     <name>easyexcel</name>
 

quickstart.md

@@ -13,6 +13,7 @@
 * ExcelReaderSheetBuilder ExcelWriterSheetBuilder 构建出一个 ReadSheet WriteSheet对象，可以理解成excel里面的一页,每一页都要构建一个
 * ReadListener 在每一行读取完毕后都会调用ReadListener来处理数据
 * WriteHandler 在每一个操作包括创建单元格、创建表格等都会调用WriteHandler来处理数据
+* 所有配置都是继承的，Workbook的配置会被Sheet继承，所以在用EasyExcel设置参数的时候，在EasyExcel...sheet()方法之前作用域是整个sheet,之后针对单个sheet
 #### 开源项目不容易，如果觉得本项目对您的工作还是有帮助的话，请在右上角帮忙点个★Star。
 ### 读
 DEMO代码地址：[https://github.com/alibaba/easyexcel/blob/master/src/test/java/com/alibaba/easyexcel/demo/read/ReadTest.java](/src/test/java/com/alibaba/easyexcel/test/demo/read/ReadTest.java)

src/main/java/com/alibaba/excel/analysis/v03/XlsSaxAnalyser.java

@@ -14,6 +14,8 @@ import org.apache.poi.hssf.eventusermodel.HSSFListener;
 import org.apache.poi.hssf.eventusermodel.HSSFRequest;
 import org.apache.poi.hssf.eventusermodel.MissingRecordAwareHSSFListener;
 import org.apache.poi.hssf.eventusermodel.dummyrecord.LastCellOfRowDummyRecord;
+import org.apache.poi.hssf.record.BOFRecord;
+import org.apache.poi.hssf.record.BoundSheetRecord;
 import org.apache.poi.hssf.record.Record;
 import org.apache.poi.hssf.usermodel.HSSFWorkbook;
 import org.apache.poi.poifs.filesystem.POIFSFileSystem;
@@ -83,6 +85,7 @@ public class XlsSaxAnalyser implements HSSFListener, ExcelExecutor {
 
     @Override
     public void execute() {
+        analysisContext.readSheetHolder().getSheetNo();
         MissingRecordAwareHSSFListener listener = new MissingRecordAwareHSSFListener(this);
         formatListener = new FormatTrackingHSSFListener(listener);
         workbookBuildingListener = new EventWorkbookBuilder.SheetRecordCollectingListener(formatListener);
@@ -121,6 +124,10 @@ public class XlsSaxAnalyser implements HSSFListener, ExcelExecutor {
 
     @Override
     public void processRecord(Record record) {
+        // Not data from the current sheet
+        if (ignoreRecord(record)) {
+            return;
+        }
         int thisRow = -1;
         int thisColumn = -1;
         CellData cellData = null;
@@ -164,6 +171,11 @@ public class XlsSaxAnalyser implements HSSFListener, ExcelExecutor {
         processLastCellOfRow(record);
     }
 
+    private boolean ignoreRecord(Record record) {
+        return analysisContext.readWorkbookHolder().getIgnoreRecord03() && record.getSid() != BoundSheetRecord.sid
+            && record.getSid() != BOFRecord.sid;
+    }
+
     private void processLastCellOfRow(Record record) {
         // Handle end of row
         if (record instanceof LastCellOfRowDummyRecord) {

src/main/java/com/alibaba/excel/analysis/v03/handlers/BofRecordHandler.java

@@ -23,7 +23,6 @@ public class BofRecordHandler extends AbstractXlsRecordHandler {
     private int sheetIndex;
     private List<ReadSheet> sheets;
     private AnalysisContext context;
-    private boolean analyAllSheet;
     private EventWorkbookBuilder.SheetRecordCollectingListener workbookBuildingListener;
 
     public BofRecordHandler(EventWorkbookBuilder.SheetRecordCollectingListener workbookBuildingListener,
@@ -48,21 +47,20 @@ public class BofRecordHandler extends AbstractXlsRecordHandler {
                 if (orderedBsrs == null) {
                     orderedBsrs = BoundSheetRecord.orderByBofPosition(boundSheetRecords);
                 }
-                sheetIndex++;
+                ReadSheet readSheet = new ReadSheet(sheetIndex, orderedBsrs[sheetIndex].getSheetname());
-                ReadSheet readSheet = new ReadSheet(sheetIndex, orderedBsrs[sheetIndex - 1].getSheetname());
                 sheets.add(readSheet);
-                if (this.analyAllSheet) {
+                if (sheetIndex == context.readSheetHolder().getSheetNo()) {
-                    context.currentSheet(null, readSheet);
+                    context.readWorkbookHolder().setIgnoreRecord03(Boolean.FALSE);
+                } else {
+                    context.readWorkbookHolder().setIgnoreRecord03(Boolean.TRUE);
                 }
+                sheetIndex++;
             }
         }
     }
 
     @Override
     public void init() {
-        if (context.readSheetHolder() == null) {
-            this.analyAllSheet = true;
-        }
         sheetIndex = 0;
         orderedBsrs = null;
         boundSheetRecords.clear();

src/main/java/com/alibaba/excel/analysis/v07/SharedStringsTableHandler.java

@@ -13,6 +13,11 @@ import com.alibaba.excel.cache.ReadCache;
 public class SharedStringsTableHandler extends DefaultHandler {
     private static final String T_TAG = "t";
     private static final String SI_TAG = "si";
+    /**
+     * Mac 2016 2017 will have this extra field to ignore
+     */
+    private static final String RPH_TAG = "rPh";
+
     /**
      * The final piece of data
      */
@@ -23,6 +28,14 @@ public class SharedStringsTableHandler extends DefaultHandler {
     private StringBuilder currentElementData;
 
     private ReadCache readCache;
+    /**
+     * Some fields in the T tag need to be ignored
+     */
+    private boolean ignoreTagt = false;
+    /**
+     * The only time you need to read the characters in the T tag is when it is used
+     */
+    private boolean isTagt = false;
 
     public SharedStringsTableHandler(ReadCache readCache) {
         this.readCache = readCache;
@@ -32,8 +45,11 @@ public class SharedStringsTableHandler extends DefaultHandler {
     public void startElement(String uri, String localName, String name, Attributes attributes) {
         if (T_TAG.equals(name)) {
             currentElementData = null;
+            isTagt = true;
         } else if (SI_TAG.equals(name)) {
             currentData = null;
+        } else if (RPH_TAG.equals(name)) {
+            ignoreTagt = true;
         }
     }
 
@@ -46,17 +62,23 @@ public class SharedStringsTableHandler extends DefaultHandler {
                 }
                 currentData.append(currentElementData);
             }
+            isTagt = false;
         } else if (SI_TAG.equals(name)) {
             if (currentData == null) {
                 readCache.put(null);
             } else {
                 readCache.put(currentData.toString());
             }
+        } else if (RPH_TAG.equals(name)) {
+            ignoreTagt = false;
         }
     }
 
     @Override
     public void characters(char[] ch, int start, int length) {
+        if (!isTagt || ignoreTagt) {
+            return;
+        }
         if (currentElementData == null) {
             currentElementData = new StringBuilder();
         }

src/main/java/com/alibaba/excel/read/metadata/holder/ReadWorkbookHolder.java

@@ -101,6 +101,12 @@ public class ReadWorkbookHolder extends AbstractReadHolder {
      */
     private POIFSFileSystem poifsFileSystem;
 
+    /**
+     * Excel 2003 cannot read specific sheet. It can only read sheet by sheet.So when you specify one sheet, you ignore
+     * the others.
+     */
+    private Boolean ignoreRecord03;
+
     public ReadWorkbookHolder(ReadWorkbook readWorkbook) {
         super(readWorkbook, null, readWorkbook.getConvertAllFiled());
         this.readWorkbook = readWorkbook;
@@ -144,6 +150,7 @@ public class ReadWorkbookHolder extends AbstractReadHolder {
             this.defaultReturnMap = readWorkbook.getDefaultReturnMap();
         }
         this.hasReadSheet = new HashSet<Integer>();
+        this.ignoreRecord03 = Boolean.FALSE;
     }
 
     public ReadWorkbook getReadWorkbook() {
@@ -258,6 +265,14 @@ public class ReadWorkbookHolder extends AbstractReadHolder {
         this.poifsFileSystem = poifsFileSystem;
     }
 
+    public Boolean getIgnoreRecord03() {
+        return ignoreRecord03;
+    }
+
+    public void setIgnoreRecord03(Boolean ignoreRecord03) {
+        this.ignoreRecord03 = ignoreRecord03;
+    }
+
     @Override
     public HolderEnum holderType() {
         return HolderEnum.WORKBOOK;

src/main/java/com/alibaba/excel/util/BooleanUtils.java

@@ -8,7 +8,6 @@ package com.alibaba.excel.util;
 public class BooleanUtils {
 
     private static final String TRUE_NUMBER = "1";
-    private static final String FALSE_NUMBER = "0";
 
     private BooleanUtils() {}
 

src/main/java/com/alibaba/excel/write/ExcelBuilderImpl.java

@@ -174,7 +174,8 @@ public class ExcelBuilderImpl implements ExcelBuilder {
         if (cellIndex != 0) {
             cellIndex++;
         }
-        for (int i = 0; i < oneRowData.size() - dataIndex; i++) {
+        int size = oneRowData.size() - dataIndex;
+        for (int i = 0; i < size; i++) {
             doAddBasicTypeToExcel(oneRowData, null, row, relativeRowIndex, dataIndex++, cellIndex++);
         }
     }
@@ -184,7 +185,8 @@ public class ExcelBuilderImpl implements ExcelBuilder {
         beforeCellCreate(row, head, relativeRowIndex);
         Cell cell = WorkBookUtil.createCell(row, cellIndex);
         Object value = oneRowData.get(dataIndex);
-        CellData cellData = converterAndSet(context.currentWriteHolder(), value.getClass(), cell, value, null);
+        CellData cellData =
+            converterAndSet(context.currentWriteHolder(), value == null ? null : value.getClass(), cell, value, null);
         afterCellCreate(head, cellData, cell, relativeRowIndex);
     }
 

src/test/java/com/alibaba/easyexcel/test/temp/poi/PoiFormatTest.java

@@ -28,7 +28,7 @@ public class PoiFormatTest {
 
     @Test
     public void lastRowNum() throws IOException {
-        String file = TestFileUtil.getPath() + "demo" + File.separator + "demo.xlsx";
+        String file = "D:\\test\\原文件.xlsx";
         SXSSFWorkbook xssfWorkbook = new SXSSFWorkbook(new XSSFWorkbook(file));
         SXSSFSheet xssfSheet = xssfWorkbook.getSheetAt(0);
         LOGGER.info("一共行数:{}", xssfSheet.getLastRowNum());

src/test/java/com/alibaba/easyexcel/test/temp/simple/HgTest.java

@@ -23,8 +23,8 @@ public class HgTest {
 
     @Test
     public void hh() throws IOException {
-        List<Object> list = EasyExcel.read(new FileInputStream("D:\\test\\hg2.xlsx")).autoTrim(Boolean.FALSE).sheet()
+        List<Object> list =
-            .headRowNumber(0).doReadSync();
+            EasyExcel.read(new FileInputStream("D:\\test\\原文件.xlsx")).headRowNumber(0).sheet().doReadSync();
         for (Object data : list) {
             LOGGER.info("返回数据：{}", JSON.toJSONString(data));
         }

src/test/java/com/alibaba/easyexcel/test/temp/simple/RepeatListener.java

@@ -0,0 +1,51 @@
+package com.alibaba.easyexcel.test.temp.simple;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.alibaba.easyexcel.test.demo.read.DemoDataListener;
+import com.alibaba.easyexcel.test.temp.LockData;
+import com.alibaba.excel.context.AnalysisContext;
+import com.alibaba.excel.event.AnalysisEventListener;
+import com.alibaba.fastjson.JSON;
+
+/**
+ * 模板的读取类
+ *
+ * @author Jiaju Zhuang
+ */
+public class RepeatListener extends AnalysisEventListener<LockData> {
+    private static final Logger LOGGER = LoggerFactory.getLogger(DemoDataListener.class);
+    /**
+     * 每隔5条存储数据库，实际使用中可以3000条，然后清理list ，方便内存回收
+     */
+    private static final int BATCH_COUNT = 5;
+    List<LockData> list = new ArrayList<LockData>();
+
+    @Override
+    public void invoke(LockData data, AnalysisContext context) {
+        LOGGER.info("解析到一条数据:{}", JSON.toJSONString(data));
+        list.add(data);
+        if (list.size() >= BATCH_COUNT) {
+            saveData();
+            list.clear();
+        }
+    }
+
+    @Override
+    public void doAfterAllAnalysed(AnalysisContext context) {
+        saveData();
+        LOGGER.info("所有数据解析完成！");
+    }
+
+    /**
+     * 加上存储数据库
+     */
+    private void saveData() {
+        LOGGER.info("{}条数据，开始存储数据库！", list.size());
+        LOGGER.info("存储数据库成功！");
+    }
+}

src/test/java/com/alibaba/easyexcel/test/temp/simple/RepeatTest.java

@@ -0,0 +1,58 @@
+package com.alibaba.easyexcel.test.temp.simple;
+
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.List;
+
+import org.junit.Ignore;
+import org.junit.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.alibaba.easyexcel.test.temp.LockData;
+import com.alibaba.excel.EasyExcel;
+import com.alibaba.excel.ExcelReader;
+import com.alibaba.excel.read.metadata.ReadSheet;
+import com.alibaba.fastjson.JSON;
+
+/**
+ * 测试poi
+ *
+ * @author Jiaju Zhuang
+ **/
+@Ignore
+public class RepeatTest {
+    private static final Logger LOGGER = LoggerFactory.getLogger(RepeatTest.class);
+
+    @Test
+    public void hh() throws IOException {
+        ExcelReader reader =
+            EasyExcel.read(new FileInputStream("D:\\test\\hg2.xls"), LockData.class, new RepeatListener())
+                .headRowNumber(0).build();
+        ReadSheet r1 = EasyExcel.readSheet(0).build();
+        ReadSheet r2 = EasyExcel.readSheet(2).build();
+        reader.read(r1);
+        reader.read(r2);
+        reader.finish();
+    }
+
+    @Test
+    public void hh2() throws IOException {
+        ExcelReader reader =
+            EasyExcel.read(new FileInputStream("D:\\test\\sheet.xls"), LockData.class, new RepeatListener())
+                .headRowNumber(0).build();
+        ReadSheet r2 = EasyExcel.readSheet(1).build();
+        reader.read(r2);
+        reader.finish();
+    }
+
+    @Test
+    public void hh1() throws IOException {
+        ExcelReader reader =
+            EasyExcel.read(new FileInputStream("D:\\test\\hg2.xls"), LockData.class, new RepeatListener())
+                .headRowNumber(0).build();
+        ReadSheet r2 = EasyExcel.readSheet(0).build();
+        reader.read(r2);
+        reader.finish();
+    }
+}

src/test/java/com/alibaba/easyexcel/test/temp/simple/Wirte.java

@@ -0,0 +1,51 @@
+package com.alibaba.easyexcel.test.temp.simple;
+
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Date;
+import java.util.List;
+
+import org.junit.Ignore;
+import org.junit.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.alibaba.easyexcel.test.demo.write.DemoData;
+import com.alibaba.easyexcel.test.util.TestFileUtil;
+import com.alibaba.excel.EasyExcel;
+import com.alibaba.excel.ExcelWriter;
+import com.alibaba.excel.write.metadata.WriteSheet;
+import com.alibaba.fastjson.JSON;
+
+/**
+ * 测试poi
+ *
+ * @author Jiaju Zhuang
+ **/
+@Ignore
+public class Wirte {
+    private static final Logger LOGGER = LoggerFactory.getLogger(Wirte.class);
+
+    @Test
+    public void simpleWrite() {
+        // 写法1
+        String fileName = TestFileUtil.getPath() + "ttttttttt11" + System.currentTimeMillis() + ".xlsx";
+        // 这里 需要指定写用哪个class去读，然后写到第一个sheet，名字为模板 然后文件流会自动关闭
+        // 如果这里想使用03 则 传入excelType参数即可
+        EasyExcel.write(fileName).sheet("模板").doWrite(data());
+    }
+
+    private List<List<Object>> data() {
+        List<List<Object>> list = new ArrayList<List<Object>>();
+        for (int i = 0; i < 10; i++) {
+            List<Object> list1 = new ArrayList<Object>();
+
+            list1.add("字符串" + i);
+            list1.add(new Date());
+            list1.add(0.56);
+            list.add(list1);
+        }
+        return list;
+    }
+}

update.md

@@ -1,3 +1,8 @@
+# 2.0.0-beta4
+* 修改在传入List<List<Object>>判断行数错误 [Issue #526](https://github.com/alibaba/easyexcel/issues/526)
+* 修复在mac 2016 2017导出的excel 可能存在多余字段的问题
+* 修复03版 读取无法指定sheet的问题 [Issue #533](https://github.com/alibaba/easyexcel/issues/533)
+
 # 2.0.0-beta3
 * 导出完成移除临时目录 [Issue #386](https://github.com/alibaba/easyexcel/issues/386)
 * 新增读取返回头数据