A = LOAD 'tablename' USING org.apache.HCatalog.pig.HCatLoader();
方法名称和描述 |
public InputFormat
getInputFormat()throws IOException
使用 HCatloader 类读取加载数据的输入格式。
|
public String relativeToAbsolutePath(String location, Path curDir) throws IOException
返回
绝对路径的String格式。
|
public void setLocation(String location, Job job) throws IOException
它设置了可以执行作业的位置。
|
public Tuple getNext() throws IOException
返回当前元组(
key 和
value)来自循环。
|
A = LOAD ... B = FOREACH A ... ... ... my_processed_data = ... STORE my_processed_data INTO 'tablename' USING org.apache.HCatalog.pig.HCatStorer();
方法名称和描述 |
public OutputFormat getOutputFormat() throws IOException
使用 HCatStorer 类读取存储数据的输出格式。
|
public void setStoreLocation (String location, Job job) throws IOException
设置执行这个
store应用程序的位置。
|
public void storeSchema (ResourceSchema schema, String arg1, Job job) throws IOException
存储架构。
|
public void prepareToWrite (RecordWriter writer) throws IOException
它有助于使用 RecordWriter 将数据写入特定文件。
|
public void putNext (Tuple tuple) throws IOException
将元组数据写入文件。
|
pig –useHCatalog <Sample pig scripts file>
export HADOOP_HOME = <path_to_hadoop_install> export HIVE_HOME = <path_to_hive_install> export HCAT_HOME = <path_to_hcat_install> export PIG_CLASSPATH = $HCAT_HOME/share/HCatalog/HCatalog-core*.jar:\ $HCAT_HOME/share/HCatalog/HCatalog-pig-adapter*.jar:\ $HIVE_HOME/lib/hive-metastore-*.jar:$HIVE_HOME/lib/libthrift-*.jar:\ $HIVE_HOME/lib/hive-exec-*.jar:$HIVE_HOME/lib/libfb303-*.jar:\ $HIVE_HOME/lib/jdo2-api-*-ec.jar:$HIVE_HOME/conf:$HADOOP_HOME/conf:\ $HIVE_HOME/lib/slf4j-api-*.jar
001, Rajiv, Reddy, 21, 9848022337, Hyderabad 002, siddarth, Battacharya, 22, 9848022338, Kolkata 003, Rajesh, Khanna, 22, 9848022339, Delhi 004, Preethi, Agarwal, 21, 9848022330, Pune 005, Trupthi, Mohanthy, 23, 9848022336, Bhuwaneshwar 006, Archana, Mishra, 23, 9848022335, Chennai 007, Komal, Nayak, 24, 9848022334, trivendram 008, Bharathi, Nambiayar, 24, 9848022333, Chennai
student = LOAD 'hdfs://localhost:9000/pig_data/student_details.txt' USING PigStorage(',') as (id:int, firstname:chararray, lastname:chararray, phone:chararray, city:chararray); student_order = ORDER student BY age DESC; STORE student_order INTO 'student_order_table' USING org.apache.HCatalog.pig.HCatStorer(); student_limit = LIMIT student_order 4; Dump student_limit;
$./pig-useHCatalog hdfs://localhost:9000/pig_data/sample_script.pig