Apache NiFi 自定义Processor处理器编写

当我们在使用Apache NiFi时，当已有的processor不支持我们现有需求时，需要我们自己编写自定义处理器并且发布，以至于更好的支持我们的需求；

下面我写一个将JSON数据转化为Excel并且输出到本地文件的自定义Processor Demo

目录

实现方式

1.编写Java代码

1.1导入Maven Apache NiFi依赖，我这边nifi版本是1.26.0

1.2实现AbstractProcessor

1.3配置Processor路径

2.打包

2.1配置Maven插件，用于打nar包

2.2使用Maven 打包

2.3将打好的nar包拷贝进nifi安装目录下lib目录​编辑

2.4重启nifi

2.5添加Processor时，选择我们的自定义处理器

3参考nifi源码

实现方式

1.编写Java代码

1.1导入Maven Apache NiFi依赖，我这边nifi版本是1.26.0

        <dependency>
            <groupId>org.apache.nifi</groupId>
            <artifactId>nifi-api</artifactId>
            <version>${nifi.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.nifi</groupId>
            <artifactId>nifi-utils</artifactId>
            <version>${nifi.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.nifi</groupId>
            <artifactId>nifi-mock</artifactId>
            <version>${nifi.version}</version>
            <scope>test</scope>
        </dependency>

1.2实现AbstractProcessor

package com.example.testjsontoexcel;

import cn.hutool.json.JSONUtil;
import org.apache.nifi.annotation.behavior.WritesAttribute;
import org.apache.nifi.annotation.behavior.WritesAttributes;
import org.apache.nifi.annotation.documentation.CapabilityDescription;
import org.apache.nifi.annotation.documentation.Tags;
import org.apache.nifi.annotation.lifecycle.OnScheduled;
import org.apache.nifi.components.PropertyDescriptor;
import org.apache.nifi.expression.ExpressionLanguageScope;
import org.apache.nifi.flowfile.FlowFile;
import org.apache.nifi.processor.*;
import org.apache.nifi.processor.exception.ProcessException;
import org.apache.nifi.processor.util.StandardValidators;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.json.JSONArray;
import org.json.JSONObject;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.*;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.*;

@CapabilityDescription("将JSON内容转换为Excel (XLSX)文件.")
@Tags({"json", "excel", "xlsx", "convert"})
@WritesAttributes({@WritesAttribute(attribute="mime.type", description="Sets the mime type to application/vnd.openxmlformats-officedocument.spreadsheetml.sheet")})
public class ConvertJsonToExcel extends AbstractProcessor {

    private static final Logger logger = LoggerFactory.getLogger(ConvertJsonToExcel.class);

    public static final PropertyDescriptor FILE_EXCEL_NAME = new PropertyDescriptor.Builder()
            .name("Excel文件名")
            .description("填写你的Excel文件输出名称，默认值为output")
            .required(true)
            .defaultValue("output")
            .addValidator(StandardValidators.NON_EMPTY_VALIDATOR)
            .expressionLanguageSupported(ExpressionLanguageScope.NONE)
            .build();

    public static final PropertyDescriptor OUTPUT_PATH = new PropertyDescriptor.Builder()
            .name("输出文件的路径")
            .description("此处填写Excel的文件输入路径，你可以在这个路径找到文件")
            .required(true)
            .addValidator(StandardValidators.NON_EMPTY_VALIDATOR)
            .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
            .build();

    static final Relationship REL_SUCCESS = new Relationship.Builder()
            .name("success")
            .description("success description")
            .build();

    static final Relationship REL_FAILURE = new Relationship.Builder()
            .name("failure")
            .description("failure description")
            .build();

    private List<PropertyDescriptor> descriptors;
    private Set<Relationship> relationships;

    @Override
    protected void init(ProcessorInitializationContext context) {
        descriptors = Collections.unmodifiableList(Arrays.asList(FILE_EXCEL_NAME, OUTPUT_PATH));
        relationships = Collections.unmodifiableSet(new HashSet<>(Arrays.asList(REL_SUCCESS, REL_FAILURE)));
    }

    @Override
    public Set<Relationship> getRelationships() {
        return relationships;
    }

    @Override
    public final List<PropertyDescriptor> getSupportedPropertyDescriptors() {
        return descriptors;
    }

    @OnScheduled
    public void onScheduled(ProcessContext context) {
        // Initialization logic if needed
    }

    @Override
    public void onTrigger(ProcessContext context, ProcessSession session) throws ProcessException {
        FlowFile flowFile = session.get();
        if (flowFile == null) {
            return;
        }
        String filenamePre = context.getProperty(FILE_EXCEL_NAME).evaluateAttributeExpressions(flowFile).getValue();
        String outputPath = context.getProperty(OUTPUT_PATH).evaluateAttributeExpressions().getValue();
        try {
            InputStream inputStream = session.read(flowFile);
            ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
            convertJsonToExcel(inputStream, outputStream);
            byte[] excelBytes = outputStream.toByteArray();
            // 设置输出文件名和路径
            String filename = filenamePre + ".xlsx";
            flowFile = session.putAttribute(flowFile, "filename", filename);
            Path outputPathPath = Paths.get(outputPath, filename);
            // 确保输出目录存在
            Files.createDirectories(outputPathPath.getParent());
            // 写入文件
            Files.write(outputPathPath, excelBytes);
            // 更新FlowFile属性并传输
            flowFile = session.write(flowFile, out -> {});
            session.putAttribute(flowFile, "mime.type", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet");
            session.transfer(flowFile, REL_SUCCESS);
            logger.info("Successfully converted JSON to Excel and saved at {}", outputPathPath);
        } catch (IOException e) {
            logger.error("Failed to convert JSON to Excel or save file", e);
            session.transfer(flowFile, REL_FAILURE);
        }
    }

    private void convertJsonToExcel(InputStream jsonInputStream, OutputStream excelOutputStream) throws IOException {
        Workbook workbook = new XSSFWorkbook();
        Sheet sheet = workbook.createSheet("Sheet1");
        try (BufferedReader reader = new BufferedReader(new InputStreamReader(jsonInputStream))) {
            JSONArray jsonArray = new JSONArray(reader.readLine());
            for (int i = 0; i < jsonArray.length(); i++) {
                JSONObject jsonObject = jsonArray.getJSONObject(i);
                Row row = sheet.createRow(i);
                Iterator<String> keys = jsonObject.keys();
                int colNum = 0;
                while (keys.hasNext()) {
                    String key = keys.next();
                    Object value = jsonObject.get(key);
                    Cell cell = row.createCell(colNum++);
                    if (value instanceof Number) {
                        cell.setCellValue(((Number) value).doubleValue());
                    } else {
                        cell.setCellValue(value.toString());
                    }
                }
            }
            workbook.write(excelOutputStream);
        }
    }
}

其中PropertyDescriptor为参数，也就是我们在配置处理器时的属性，我这边需要传入两个参数，Excel的输出文件名和文件保存路径

1.3配置Processor路径

在项目resource目录下新增目录META-INF，META-INF目录下再新建services目录，最后在services目录下新建org.apache.nifi.processor.Processor文件，文件内容为上面写的处理器全路径，如下图

com.example.testjsontoexcel.ConvertJsonToExcel

2.打包

2.1配置Maven插件，用于打nar包

在pom中添加插件

        <plugins>
            <plugin>
                <groupId>org.apache.nifi</groupId>
                <artifactId>nifi-nar-maven-plugin</artifactId>
                <version>1.5.1</version>
                <extensions>true</extensions>
            </plugin>
        </plugins>

在pom根目录需要添加packaging配置，这样打完的包才是nifi能识别的nar包

<packaging>nar</packaging>

2.2使用Maven 打包

mvn clean package

2.3将打好的nar包拷贝进nifi安装目录下lib目录

2.4重启nifi

bin/nifi.sh restart #重启命令

2.5添加Processor时，选择我们的自定义处理器

3参考nifi源码

具体可以参考nifi官方源码，参考Processor的写法

GitHub地址：GitHub - apache/nifi: Apache NiFi