Eclipse 导入Hadoop 2.6.0 源码

1. 首先前往 官网（Hadoop 2.6 下载地址）上下载Hadoop的源码文件，并解压

2. 事先请确定已经安装好jdk以及maven（Maven安装教程 这是其他人写的一篇博文，保存profile后，记得source下）

3. 进入到hadoop-2.6.0-src/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop 目录

可以看到有很多文件夹，找到ipc目录，在里面mkdir protobuf文件夹（还有一丢丢问题，这个后面解决）

4. 安装protobuf

下载地址 ： http://pan.baidu.com/s/1pJlZubT  并解压

切换到protobuf文件夹，依次在终端下输入：

. / configure

make

make check

make install

全部执行完后再输入protoc - - version检查是否安装成功。

5. hadoop-2.6.0-src/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/serializer/avro/TestAvroSerialization.java显示找不到AvroRecord类

去grepcode下载2.5.0或者更高版本的。放到相应位置

6. cd到 hadoop-2.6.0-src/hadoop-maven-plugins 目录下 使用：mvn intall

7. cd到hadoop-2.6.0-src 目录下 使用mvn eclipse:eclipse -DskipTests

8. 在Eclipse中：File-Import-Existing Projects into Workspace 选择hadoop-2.6.0-src目录导入（推荐换一个workspace再导入，因为project的数目挺多的）

到了这一步，基本上已经没什么问题了，但是还有一些小问题，需要解决

可能遇到的问题：

1.org.apache.hadoop.ipc.protobuf 包下，可能是空包。

去grepcode上搜索TestProtos和TestRpcServiceProtos两个类，我遇到的情况是本地目录已经存在那两个文件，却没有导入。

没有上述两个类，会提示一大片的EmptyRequestProto之类的无法解析

2.会提示com.sum.tool或者javadoc包无法解析

右键选择buildpath -> configure build path -> library -> add library -> ire system 即可

3. hadoop-streaming 工程中的build path 有问题

把source中的hadoop-yarn-server-resourcemanager/conf删除掉，然后Link Source:源码根目录/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/conf

4. mac下发现classes.jar找不到的问题：

Exception in thread "main" java.lang.AssertionError: Missing tools.jar at: /Library/Java/JavaVirtualMachines/jdk1.7.0_45.jdk/Contents/Home/Classes/classes.jar. Expression: file.exists()

this is as the compiler needs a file named tools.jar but localted at classes.jar under dir Classes but found nothing.so u can do workaround:

解决办法：

cd $JAVA_HOME
mkdir Classes
cd Classes
ln -s ../lib/tools.jar classes.jar

附件：AvroRecord.java hadoop2.6版本

/**
 * Autogenerated by Avro
 *
 * DO NOT EDIT DIRECTLY
 */
package org.apache.hadoop.io.serializer.avro;
@SuppressWarnings("all")
@org.apache.avro.specific.AvroGenerated
public class AvroRecord extends org.apache.avro.specific.SpecificRecordBase implements org.apache.avro.specific.SpecificRecord {
  public static final org.apache.avro.Schema SCHEMA$ = new org.apache.avro.Schema.Parser().parse("{\"type\":\"record\",\"name\":\"AvroRecord\",\"namespace\":\"org.apache.hadoop.io.serializer.avro\",\"fields\":[{\"name\":\"intField\",\"type\":\"int\"}]}");
  public static org.apache.avro.Schema getClassSchema() { return SCHEMA$; }
  @Deprecated public int intField;

  /**
   * Default constructor.
   */
  public AvroRecord() {}

  /**
   * All-args constructor.
   */
  public AvroRecord(java.lang.Integer intField) {
    this.intField = intField;
  }

  public org.apache.avro.Schema getSchema() { return SCHEMA$; }
  // Used by DatumWriter.  Applications should not call.
  public java.lang.Object get(int field$) {
    switch (field$) {
    case 0: return intField;
    default: throw new org.apache.avro.AvroRuntimeException("Bad index");
    }
  }
  // Used by DatumReader.  Applications should not call.
  @SuppressWarnings(value="unchecked")
  public void put(int field$, java.lang.Object value$) {
    switch (field$) {
    case 0: intField = (java.lang.Integer)value$; break;
    default: throw new org.apache.avro.AvroRuntimeException("Bad index");
    }
  }

  /**
   * Gets the value of the 'intField' field.
   */
  public java.lang.Integer getIntField() {
    return intField;
  }

  /**
   * Sets the value of the 'intField' field.
   * @param value the value to set.
   */
  public void setIntField(java.lang.Integer value) {
    this.intField = value;
  }

  /** Creates a new AvroRecord RecordBuilder */
  public static org.apache.hadoop.io.serializer.avro.AvroRecord.Builder newBuilder() {
    return new org.apache.hadoop.io.serializer.avro.AvroRecord.Builder();
  }

  /** Creates a new AvroRecord RecordBuilder by copying an existing Builder */
  public static org.apache.hadoop.io.serializer.avro.AvroRecord.Builder newBuilder(org.apache.hadoop.io.serializer.avro.AvroRecord.Builder other) {
    return new org.apache.hadoop.io.serializer.avro.AvroRecord.Builder(other);
  }

  /** Creates a new AvroRecord RecordBuilder by copying an existing AvroRecord instance */
  public static org.apache.hadoop.io.serializer.avro.AvroRecord.Builder newBuilder(org.apache.hadoop.io.serializer.avro.AvroRecord other) {
    return new org.apache.hadoop.io.serializer.avro.AvroRecord.Builder(other);
  }

  /**
   * RecordBuilder for AvroRecord instances.
   */
  public static class Builder extends org.apache.avro.specific.SpecificRecordBuilderBase<AvroRecord>
    implements org.apache.avro.data.RecordBuilder<AvroRecord> {

    private int intField;

    /** Creates a new Builder */
    private Builder() {
      super(org.apache.hadoop.io.serializer.avro.AvroRecord.SCHEMA$);
    }

    /** Creates a Builder by copying an existing Builder */
    private Builder(org.apache.hadoop.io.serializer.avro.AvroRecord.Builder other) {
      super(other);
    }

    /** Creates a Builder by copying an existing AvroRecord instance */
    private Builder(org.apache.hadoop.io.serializer.avro.AvroRecord other) {
            super(org.apache.hadoop.io.serializer.avro.AvroRecord.SCHEMA$);
      if (isValidValue(fields()[0], other.intField)) {
        this.intField = data().deepCopy(fields()[0].schema(), other.intField);
        fieldSetFlags()[0] = true;
      }
    }

    /** Gets the value of the 'intField' field */
    public java.lang.Integer getIntField() {
      return intField;
    }

    /** Sets the value of the 'intField' field */
    public org.apache.hadoop.io.serializer.avro.AvroRecord.Builder setIntField(int value) {
      validate(fields()[0], value);
      this.intField = value;
      fieldSetFlags()[0] = true;
      return this;
    }

    /** Checks whether the 'intField' field has been set */
    public boolean hasIntField() {
      return fieldSetFlags()[0];
    }

    /** Clears the value of the 'intField' field */
    public org.apache.hadoop.io.serializer.avro.AvroRecord.Builder clearIntField() {
      fieldSetFlags()[0] = false;
      return this;
    }

    @Override
    public AvroRecord build() {
      try {
        AvroRecord record = new AvroRecord();
        record.intField = fieldSetFlags()[0] ? this.intField : (java.lang.Integer) defaultValue(fields()[0]);
        return record;
      } catch (Exception e) {
        throw new org.apache.avro.AvroRuntimeException(e);
      }
    }
  }
}

　　

参考资料：

1. 在mac中导入hadoop2.6.0源代码至eclipse教程

2. Eclipse导入Hadoop源码

3.  hadoop-2.6.0-src源码导入Eclipse

4. grepcode TestProtos

5. 百度知道：导入时可能遇到的错误以及解决办法 （请参考其他1条回答）