opencsv4.0 自定义规则

opencsv

java读取csv的类库主要有两种，opencsv和javacsv，研究发现，javacsv最后一次更新是2014-12-10，很久不维护了。opencsv是apache的项目，并且至今仍在维护，所以决定使用opencsv。

---

csv

csv文件，全名 comma separated values，默认以逗号分隔，是纯文本文件。虽然用excel打开后格式排版了，但是那是excel对他进行了处理。用notepad或者sublime text打开能看到最原始的文本。 
为了后续举例，这里编辑了一个test.csv

header1,header2,header31,a,102,b,203,c,304,d,405,e,506,f,60
1
2
3
4
5
6
7

---

读取方式

• 最原始的方式，逐行读取，然后操作

 CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk"));      /*       * 逐行读取       */      String[] strArr = null;      while((strArr = reader.readNext())!=null){          System.out.println(strArr[0]+"---"+strArr[1]+"----"+strArr[2]);      }      reader.close();
1
2
3
4
5
6
7
8
9
10
11

---

绑定csv文件转换成bean

逐行读取操作是最原始的操作方式，opencsv提供了基于“策略”的映射，将csv绑定到bean。

策略简介

观察一下策略的继承层次 

接口

• MappingStrategy 
  
  • 映射的顶层接口
• HeaderColumnNameMappingStrategy 
  
  • 列名映射策略，读取csv文件第一行作为header，比如header1,header2,header3,然后调用bean的setHeader1方法，setHeader2方法，setHeader3方法分别设置值，所以这种策略要求，列名与bean中的属性名完全一致，如果不一致，则值为空，不会出错。使用注解时，注解名字必须与csv中列名一致。
• ColumnPositionMappingStrategy 
  
  • 列位置映射策略，他没有header的概念，所以会输出取所有行。在columnMapping数组中指定bean的属性，第一个值对应csv的第一列，第二个值对应csv的第二类……
• HeaderColumnNameTranslateMappingStrategy 
  
  • 列头名字翻译映射策略,与HeaderColumnNameMappintStrategy相比，bean的属性名可以与csv列头不一样。通过指定map来映射。

---

具体映射用法

Java POJO类

public class SimpleBeanInfo {    private String header1;    private String header2;    private String header3;    public String getHeader1() {        return header1;    }    @Override    public String toString() {        return "SimpleBeanInfo [header1=" + header1 + ", header2=" + header2                + ", header3=" + header3 + "]";    }    public void setHeader1(String header1) {        this.header1 = header1;    }    public String getHeader2() {        return header2;    }    public void setHeader2(String header2) {        this.header2 = header2;    }    public String getHeader3() {        return header3;    }    public void setHeader3(String header3) {        this.header3 = header3;    }
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39

---

基于列索引的映射

• 通俗点来说就是列位置映射，csv文件中的列位置对应到bean中的列

• 非注解方式

CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk"));      /*       *基于列位置，映射成类        */       //csv文件中的第一列对应类的header，第二列对应类的header2，第三列对应类的header3      String[] columnMapping={"header1","header2","header3"};      ColumnPositionMappingStrategy<SimpleBeanInfo> mapper = new ColumnPositionMappingStrategy<SimpleBeanInfo>();      mapper.setColumnMapping(columnMapping);      mapper.setType(SimpleBeanInfo.class);      /* */       CsvToBean<SimpleBeanInfo>  csvToBean = new CsvToBean<SimpleBeanInfo>();      List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader);      for(SimpleBeanInfo e : list){          System.out.println(e);      }    }
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

• 注解方式

public class SimpleBeanInfo {    @CsvBindByPosition(position=0)    private String header1;    @CsvBindByPosition(position=1)    private String header2;    @CsvBindByPosition(position=2)    private String header3;}
1
2
3
4
5
6
7
8
9
10
11
12

CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk")); ColumnPositionMappingStrategy<SimpleBeanInfo> mapper = new ColumnPositionMappingStrategy<SimpleBeanInfo>();      mapper.setType(SimpleBeanInfo.class);      CsvToBean<SimpleBeanInfo>  csvToBean = new CsvToBean<SimpleBeanInfo>();      List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader);      for(SimpleBeanInfo e : list){          System.out.println(e);      }
1
2
3
4
5
6
7
8
9
10

---

基于列名的映射

• 非注解方式

 CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk"));      /* */       HeaderColumnNameMappingStrategy<SimpleBeanInfo> mapper = new              HeaderColumnNameMappingStrategy<SimpleBeanInfo>();      mapper.setType(SimpleBeanInfo.class);      CsvToBean<SimpleBeanInfo>  csvToBean = new CsvToBean<SimpleBeanInfo>();      List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader);      for(SimpleBeanInfo e : list){          System.out.println(e);      }
1
2
3
4
5
6
7
8
9
10
11
12
13
14

• 注解方式

public class SimpleBeanInfo {    @CsvBindByName(column="header1")    private String header1;    @CsvBindByName(column="header2")    private String header2;    @CsvBindByName(column="header3")    private String header3;}
1
2
3
4
5
6
7
8
9
10
11
12

CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk"));      HeaderColumnNameMappingStrategy<SimpleBeanInfo> mapper = new              HeaderColumnNameMappingStrategy<SimpleBeanInfo>();      mapper.setType(SimpleBeanInfo.class);      CsvToBean<SimpleBeanInfo>  csvToBean = new CsvToBean<SimpleBeanInfo>();      List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader);      for(SimpleBeanInfo e : list){          System.out.println(e);      }
1
2
3
4
5
6
7
8
9
10
11
12

---

基于列名转换映射

 CSVReader reader = new CSVReader(new InputStreamReader(new FileInputStream("test.csv"),"gbk"));      /*       * 基于列名转换，映射成类      */      HeaderColumnNameTranslateMappingStrategy<SimpleBeanInfo> mapper =               new HeaderColumnNameTranslateMappingStrategy<SimpleBeanInfo>();      mapper.setType(SimpleBeanInfo.class);      Map<String,String> columnMapping = new HashMap<String,String>();      columnMapping.put("header1", "header1");//csv中的header1对应bean的header1      columnMapping.put("header2", "header2");      columnMapping.put("header3", "header3");      mapper.setColumnMapping(columnMapping);      CsvToBean<SimpleBeanInfo>  csvToBean = new CsvToBean<SimpleBeanInfo>();      List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader);      for(SimpleBeanInfo e : list){          System.out.println(e);      }
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21

---

过滤器

opencsv提供了过滤器，可以过滤某些行，比如page header、page footer等

• 所有的过滤器必须实现CsvToBeanFilter 接口

public class MyCsvToBeanFilter implements CsvToBeanFilter {        public boolean allowLine(String[] line) {            //过滤第一列值等于1的行            if("1".equals(line[0])){                return false;            }            return true;        }}
1
2
3
4
5
6
7
8
9
10
11

 MyCsvToBeanFilter filter = new MyCsvToBeanFilter(); List<SimpleBeanInfo> list = csvToBean.parse(mapper, reader,filter);
1
2

---

转化器

类中的属性不一定都是字符串，比如数字、日期等，但是我们从csv中获取到的都是字符串，这种情况就应该使用转化器。 
这里定义一个SimpleBeanConverter，继承AbstractBeanField

public class SimpleBeanFieldConverter extends AbstractBeanField<SimpleBeanInfo> {    @Override    protected Object convert(String value) throws CsvDataTypeMismatchException,            CsvRequiredFieldEmptyException, CsvConstraintViolationException {        Field f = getField();        if("date".equals(f.getName())){            try {                return new SimpleDateFormat("yyyy-MM-dd").parse(value);            } catch (ParseException e) {                e.printStackTrace();            }        }        return null;    }}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

test.csv添加一列header4

header1,header2,header3,header41,a,10,2016-05-012,b,20,2016-05-023,c,30,2016-05-034,d,40,2016-05-045,e,50,2016-05-056,f,60,2016-05-06
1
2
3
4
5
6
7

SimpleBeanInfo添加属性

@CsvCustomBindByPosition(position=3,converter=SimpleBeanFieldConverter.class)private Date date;
1
2

输出结果 
由于ColumnPositionMappingStrategy会连header行也解析，所以第一行会打印异常信息。我们看到header4列已经转换为日期。如果不只一个列需要转换怎么办？在相应的属性上添加注解(@CsvCustomBindByPosition或@CsvCustomBindByName)，然后在convert(Object value)中扩展即可

java.text.ParseException: Unparseable date: "header4"    at java.text.DateFormat.parse(DateFormat.java:357)    at test_maven.SimpleBeanFieldConverter.convert(SimpleBeanFieldConverter.java:24)    at com.opencsv.bean.AbstractBeanField.setFieldValue(AbstractBeanField.java:70)    at com.opencsv.bean.CsvToBean.processField(CsvToBean.java:245)    at com.opencsv.bean.CsvToBean.processLine(CsvToBean.java:220)    at com.opencsv.bean.CsvToBean.processLine(CsvToBean.java:189)    at com.opencsv.bean.CsvToBean.parse(CsvToBean.java:166)    at com.opencsv.bean.CsvToBean.parse(CsvToBean.java:133)    at test_maven.TestCSV.main(TestCSV.java:46)SimpleBeanInfo [header1=header1, header2=header2, header3=header3, date=null]SimpleBeanInfo [header1=2, header2=b, header3=20, date=Mon May 02 00:00:00 CST 2016]SimpleBeanInfo [header1=3, header2=c, header3=30, date=Tue May 03 00:00:00 CST 2016]SimpleBeanInfo [header1=4, header2=d, header3=40, date=Wed May 04 00:00:00 CST 2016]SimpleBeanInfo [header1=5, header2=e, header3=50, date=Thu May 05 00:00:00 CST 2016]SimpleBeanInfo [header1=6, header2=f, header3=60, date=Fri May 06 00:00:00 CST 2016]