很希望能在hadoop上做c++程序,自己对c++还是有点情节的,根据《hadoop权威指南中文第二版》Hadoop的Pipes进行了试验,并测试成功
#include <algorithm>
#include <limits.h>
#include <stdint.h>
#include <string>
#include "Pipes.hh"
#include "TemplateFactory.hh"
#include "StringUtils.hh"
class MaxTemperatureMapper : public HadoopPipes::Mapper {
public:
MaxTemperatureMapper(HadoopPipes::TaskContext& context) {
}
void map(HadoopPipes::MapContext& context) {
std::string line = context.getInputValue();
std::string year = line.substr(15, 4);
std::string airTemperature = line.substr(87, 5);
std::string q = line.substr(92, 1);
if (airTemperature != "+9999" &&
(q == "0" || q == "1" || q == "4" || q == "5" || q == "9")) {
context.emit(year, airTemperature);
}
}
};
class MapTemperatureReducer : public HadoopPipes::Reducer {
public:
MapTemperatureReducer(HadoopPipes::TaskContext& context) {
}
void reduce(HadoopPipes::ReduceContext& context) {
int maxValue = INT_MIN;
while (context.nextValue()) {
maxValue = std::max(maxValue, HadoopUtils::toInt(context.getInputValue()));
}
context.emit(context.getInputKey(), HadoopUtils::toString(maxValue));
}
};
int main(int argc, char *argv[]) {
return HadoopPipes::runTask(HadoopPipes::TemplateFactory<MaxTemperatureMapper,
MapTemperatureReducer>());
}
注意:和书上不一样的地方:limit.h头文件
Makefile文件(自己进行了修改):
.SUFFIXES:.h .c .cpp .o
CC=g++
CPPFLAGS = -m64
RM = rm
SRCS = max_temperature.cpp
PROGRAM = max_temperature
INC_PATH = -I$(HADOOP_DEV_HOME)/include
LIB_PATH = -L$(HADOOP_DEV_HOME)/lib/native
LIBS = -lhadooppipes -lcrypto -lhadooputils -lpthread
$(PROGRAM):$(SRCS)
$(CC) $(CPPFLAGS) $(INC_PATH) $< -Wall $(LIB_PATH) $(LIBS) -g -O2 -o $@
.PHONY:clean
clean:
$(RM) $(PROGRAM)
源数据文件:
0067011990999991950051507004+68750+023550FM-12+038299999V0203301N00671220001CN9999999N9+00001+99999999999
0043011990999991950051512004+68750+023550FM-12+038299999V0203201N00671220001CN9999999N9+00221+99999999999
0043011990999991950051518004+68750+023550FM-12+038299999V0203201N00261220001CN9999999N9-00111+99999999999
0043012650999991949032412004+62300+010750FM-12+048599999V0202701N00461220001CN0500001N9+01111+99999999999
0043012650999991949032418004+62300+010750FM-12+048599999V0202701N00461220001CN0500001N9+00781+99999999999
上传到HDFS:hdfs dfs -put sample.txt
make后生成了可执行文件上传到HDFS: hdfs dfs -put max_temperature /bin
执行方法: hadoop pipes -D hadoop.pipes.java.recordreader=true -D hadoop.pipes.java.recordwriter=true -input /user/root/sample.txt -output /output -program /bin/max_temperature
数据输出结果: