Question

我有几个我需要解析的CSV文件。并在以后用于MYSQL中的Insert。我已经写了一个解析器，但我想尽可能避免编码重复

我已经记住，我应该使用抽象类，或者可能是工厂，但我无法真正指出设计它的最佳方法。

所以这是我的解析器：

public class LocusAliasCsvParser {

private static final String[] FILE_HEADER_MAPPING = {"id", "locusID", "organismid", "variable", "alias"};

private static final String ID = "id";
private static final String LOCUS_ID = "locusID";
private static final String ORGANISM_ID = "organismid";
private static final String VARIABLE = "variable";
private static final String ALIAS = "alias";


public static List<AliasLocus> readCsvFile(String fileName) {

    FileReader fileReader = null;
    CSVParser csvFileParser = null;

    CSVFormat csvFileFormat = CSVFormat.DEFAULT.withHeader(FILE_HEADER_MAPPING);
    List<AliasLocus> aliases = new ArrayList();

    try {
        fileReader = new FileReader(fileName);
        csvFileParser = new CSVParser(fileReader, csvFileFormat);

        //Get a list of CSV file records
        List csvRecords = csvFileParser.getRecords();

        //Read the CSV file. Header is ignored (i == 1)
        for (int i = 1; i < csvRecords.size(); i++) {
            CSVRecord record = (CSVRecord) csvRecords.get(i);

            AliasLocus aliasLocus = new AliasLocus(Integer.parseInt(record.get(ID)),
                    record.get(LOCUS_ID),
                    record.get(ORGANISM_ID),
                    record.get(VARIABLE),
                    record.get(ALIAS));

            aliases.add(aliasLocus);
        }

    } catch (Exception e) {
        System.out.println("Error in CsvFileReader !!!");
        e.printStackTrace();
    } finally {
        try {
            fileReader.close();
            csvFileParser.close();
        } catch (IOException e) {
            System.out.println("Error while closing fileReader/csvFileParser !!!");
            e.printStackTrace();
        }
    }

    return aliases;
}

每次改变的事情是：

public class LocusAliasCsvParser {

private static final String[] FILE_HEADER_MAPPING = {"id", "locusID", "organismid", "variable", "alias"};

private static final String ID = "id";
private static final String LOCUS_ID = "locusID";
private static final String ORGANISM_ID = "organismid";
private static final String VARIABLE = "variable";
private static final String ALIAS = "alias";

和：

 public static List<AliasLocus> readCsvFile(String fileName) {

 AliasLocus aliasLocus = new AliasLocus(Integer.parseInt(record.get(ID)),
                    record.get(LOCUS_ID),
                    record.get(ORGANISM_ID),
                    record.get(VARIABLE),
                    record.get(ALIAS));

是否有人可以建议使用最佳设计模式或结构来进行最少的代码重复？

感谢

Answer 1

您应该使用接口分离不同的问题，并实现用于读取csv文件的模板方法。

让我们分6个步骤设置一个简单的框架。

您需要一个知道如何获取csv结构的类。

public interface CsvMetadataSource {
     public CsvMetadata getCsvMetadata();
}

您需要一个可以解析csv行的类。来自1的CsvMetadata是放置逻辑的好地方。

public class CsvMetadata {

    private List<String> columns;

    public CsvMetadata(List<String> columns) {
        this.columns = columns;
    }

    public Map<String, String> parseLine(String line) {
        // simple implementation 
        String[] values = line.split(",");

        Map<String, String> record = new HashMap<>();

        for (int i = 0; i < columns.size(); i++) {
            String column = columns.get(i);

            String value = null;

            if (i < values.length) {
                value = values[i];
            }

            record.put(column, value);
        }

        return record;
    }

}

您需要一个可以将已解析的行映射到对象的类。知道行号也可能有用。

public interface CsvRecordMapper<T> {
    public T map(Map<String, String> csvRecord, int lineNumber);
}

您需要一个知道如何处理映射对象的类。

public interface CsvObjectCallback<T> {
    public void process(T object);
}

您需要一个实现模板方法的类来读取csv数据，并且可以通过上述接口的实现进行扩展。使用便捷方法将所有对象作为列表读取也可能是好事。

public class CsvReader {

    private CsvMetadataSource csvMetadataSource = null;

    public CsvReader() {
    }

    public CsvReader(CsvMetadataSource csvMetadataSource) {
        this.csvMetadataSource = csvMetadataSource;
    }

    public <T> List<T> readAll(Reader csvInputReader, CsvRecordMapper<T> csvLineMapper) throws IOException {
        CollectCsvObjectCallback<T> collectCsvObjectCallback = new CollectCsvObjectCallback<>();
        read(csvInputReader, csvLineMapper, collectCsvObjectCallback);
        return collectCsvObjectCallback.getObjects();
    }

    public <T> void read(Reader csvInputReader, CsvRecordMapper<T> csvLineMapper,
            CsvObjectCallback<T> csvObjectCallback) throws IOException {
        try (BufferedReader lineReader = new BufferedReader(csvInputReader);) {
            CsvMetadataSource effectiveCsvMetadataSource = getCsvMetadataSource(lineReader);

            read(csvLineMapper, csvObjectCallback, lineReader, effectiveCsvMetadataSource);
        }
    }

    private CsvMetadataSource getCsvMetadataSource(BufferedReader lineReader) throws IOException {
        CsvMetadataSource effectiveCsvMetadataSource = csvMetadataSource;
        if (effectiveCsvMetadataSource == null) {
            String headerLine = lineReader.readLine();
            effectiveCsvMetadataSource = new RowBasedCsvMetadataSource(headerLine);
        }
        return effectiveCsvMetadataSource;
    }

    private <T> void read(CsvRecordMapper<T> csvLineMapper, CsvObjectCallback<T> csvObjectCallback,
            BufferedReader lineReader, CsvMetadataSource effectiveCsvMetadataSource) throws IOException {
        CsvMetadata effectiveCsvMetadata = effectiveCsvMetadataSource.getCsvMetadata();
        if (effectiveCsvMetadata != null) {
            String line;
            int csvRecordNumber = 0;

            while ((line = lineReader.readLine()) != null) {
                Map<String, String> csvRecordValues = effectiveCsvMetadata.parseLine(line);
                T object = csvLineMapper.map(csvRecordValues, csvRecordNumber++);
                csvObjectCallback.process(object);
            }
        }
    }

}

class RowBasedCsvMetadataSource implements CsvMetadataSource {

    private String row;

    public RowBasedCsvMetadataSource(String row) {
        this.row = row;
    }

    @Override
    public CsvMetadata getCsvMetadata() {
        String[] columns = row.split(",");
        return new CsvMetadata(Arrays.asList(columns));
    }

}

class CollectCsvObjectCallback<T> implements CsvObjectCallback<T> {

    private List<T> objects = new ArrayList<>();

    @Override
    public void process(T object) {
        objects.add(object);
    }

    public List<T> getObjects() {
        return objects;
    }

}

最后，您只需实施CsvRecordMapper即可轻松调整新的csv文件格式。 E.g。

public class UserCsvRecordMapper implements CsvRecordMapper<User> {

    public User map(Map<String, String> csvRecord, int lineNumber) {
        String firstname = csvRecord.get("FIRST NAME");
        String lastname = csvRecord.get("LAST NAME");
        String username = csvRecord.get("USERNAME");
        String email = csvRecord.get("EMAIL ADDRESS");

        return new User(firstname, lastname, username, email);
    }
}

public class User {

    private String firstname;
    private String lastname;
    private String username;
    private String email;

    public User(String firstname, String lastname, String username, String email) {
        this.firstname = firstname;
        this.lastname = lastname;
        this.username = username;
        this.email = email;
    }

    public String getFirstname() {
        return firstname;
    }

    public String getLastname() {
        return lastname;
    }

    public String getUsername() {
        return username;
    }

    public String getEmail() {
        return email;
    }

    @Override
    public String toString() {
        return "User [firstname=" + firstname + ", lastname=" + lastname + ", username=" + username + ", email=" + email
                + "]";
    }

}

从客户的角度来看，它很容易使用。

CSV

FIRST NAME,LAST NAME,USERNAME,PASSWORD,EMAIL ADDRESS,PHONE NUMBER,PASSPORT,GROUPS,USERCODE,TITLE,ADDRESS 1 ,ADDRESS 2,CITY,STATE,ZIP
Frank,Riley,friley,changeme,friley@kanab.org,123-456-7890,3,"1,3",1040,Teacher,328 Innovation,Suite # 200 ,state college,PA,16803
Steve,Brannigan,sbrannigan,changeme,sbrannigan@kanab.org,123-456-7890,3,1,1041,Teacher,328 Innovation,Suite # 200 ,state college,PA,16803
Marie,Ambrose,mambrose,changeme,mambrose@kanab.org,123-456-7890,3,1,1042,Teacher,328 Innovation,Suite # 200 ,state college,PA,16803

一个简单的主类

public class Main {

    public static void main(String[] args) throws IOException {
        InputStream csvInputStream = Main.class.getResourceAsStream("example.csv");
        InputStreamReader inputStreamReader = new InputStreamReader(csvInputStream);

        CsvReader csvReader = new CsvReader();
        List<User> users = csvReader.readAll(inputStreamReader, new UserCsvRecordMapper());

        for (User user : users) {
            System.out.println(user);
        }

    }
}

结果是

User [firstname=Frank, lastname=Riley, username=friley, email=friley@kanab.org]
User [firstname=Steve, lastname=Brannigan, username=sbrannigan, email=sbrannigan@kanab.org]
User [firstname=Marie, lastname=Ambrose, username=mambrose, email=mambrose@kanab.org]

Answer 2

这是我非常直截了当的解决方案。

将CSVRecord中的转换器声明为每个所需的实体：

class FirstModel(models.Model):
    first_model_item = models.ForeignKey(Item)
    quantity =  models.IntegerField()

class SecondModel(models.Model):
    second_model_item = models.ForeignKey(FirstModel)
    quantity = models.IntegerField()

然后使Parser更具普遍性

class CreateSecondModelView(generics.CreateAPIView):
    permission_classes = ()
    queryset = SecondModel.objects.all()
    serializer_class = SecondModeSerializer

    def perform_create(self, serializer):
        instance = serializer.save()
        first_model_item = instance.item
        first_model_item.quantity -= instance.quantity
        first_model_item.save()


class UpdateSecondModelView(generics.RetrieveUpdateAPIView):
    permission_classes = ()
    queryset = SecondModel.objects.all()
    serializer_class = SecondModeSerializer

    def perform_update(self, serializer):
        instance = serializer.save()
        #here i want old value of quantity before updating.

然后按以下方式使用

class AliasLocusMapper { 
    public static final String[] FILE_HEADER_MAPPING = {"id", "locusID", "organismid", "variable", "alias"};

    private static final String ID = "id";
    private static final String LOCUS_ID = "locusID";
    private static final String ORGANISM_ID = "organismid";
    private static final String VARIABLE = "variable";
    private static final String ALIAS = "alias";

    public static AliasLocus mapRecord(CSVRecord record) {
        return new AliasLocus(Integer.parseInt(record.get(ID)),
                record.get(LOCUS_ID),
                record.get(ORGANISM_ID),
                record.get(VARIABLE),
                record.get(ALIAS));
    }
}

class ProductMapper { // Product is an example class
    public static final String[] FILE_HEADER_MAPPING = {"id", "title", "price"};

    private static final String ID = "id";
    private static final String TITLE = "title";
    private static final String PRICE = "price";

    public static Product mapRecord(CSVRecord record) {
        return new Product(Integer.parseInt(record.get(ID)),
                record.get(TITLE),
                record.get(PRICE));
    }
}

Java的最佳设计解析具有不同标头和模型对象的多个CSV文件

2 个答案: