Miopas Miopas

## url_encoder.py
#coding=utf8
import sys
import urllib.parse
import traceback

keyword = '测试'
try:
  url = "http:/127.0.0.1:8983/solr/demo/query?q=titile_t:" + urllib.parse.quote(keyword, "utf-8")
  print(url)
except:

## hadoop_sort
-partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner \
-jobconf stream.num.map.output.key.fields=2 \
-jobconf num.key.fields.for.partition=1

## hadoop_zip.sh
source ~/.bashrc
input=***
output=***
hadoop fs -rmr ${output}
$HADOOP_HOME/bin/hadoop  jar $HADOOP_STREAMING \
    -D mapred.reduce.tasks=100 \
    -D mapred.job.name="zip" \
    -D mapred.job.priority=VERY_HIGH  \
    -D mapred.map.max.attempts="1" \
    -D mapreduce.output.fileoutputformat.compress=true \

## hive_output_hdfs.hql
insert overwrite directory "/tmp/out/"
row format delimited fields terminated by "\t"
select user, login_time from user_login;

## vim_clear_symbol.note
1. Vim 去掉 ^M 字符

单个文件：
```
%s/^M//g
```
(^M是ctrl+v,ctrl+m)

## upload.php
<?php
$header_prefix = 'file';
$slots = 6;
?>
<html>
<head>
<title>Test upload</title>
</head>
<body>
<?php

## sed.sh
# 删除 tmp 文件第一行
sed -i '1d' tmp

# 给 tmp 文件增加一列 '1' 的标签，分隔符为“\t”
cat tmp | awk 'BEGIN{OFS="\t"} {print $0,"1"}'

## dict_sort.py
import pprint
class data:
    def __init__(self, name, value):
        self.name = name
        self.value = value

a = data('a', 2)
b = data('b', 3)
c = data('c', 1)
mydict = {'keyOfA':a, 'keyOfB':b, 'keyOfC':c}

## loop.sh

total=10
startFrom=0

for ((i=${startFrom}; i<${startFrom}+$total; i++)); do

    echo starting $i of $total ...

done

## mvn_sbt.sh
# mvn run main
# 网上的例子给的是：mvn exec:java -D"exec.mainClass"="com.example.Main"，但是我这边是去掉 Main 才能跑通
mvn exec:java -D"exec.mainClass"="com.example"

# sbt run main (background)
setsid nohup sbt -mem 2048 "runMain example.YourClassName ${dataSet} ${normOutput}" > norm.log &
	#coding=utf8
	import sys
	import urllib.parse
	import traceback

	keyword = '测试'
	try:
	url = "http:/127.0.0.1:8983/solr/demo/query?q=titile_t:" + urllib.parse.quote(keyword, "utf-8")
	print(url)
	except:
	-partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner \
	-jobconf stream.num.map.output.key.fields=2 \
	-jobconf num.key.fields.for.partition=1
	source ~/.bashrc
	input=***
	output=***
	hadoop fs -rmr ${output}
	$HADOOP_HOME/bin/hadoop jar $HADOOP_STREAMING \
	-D mapred.reduce.tasks=100 \
	-D mapred.job.name="zip" \
	-D mapred.job.priority=VERY_HIGH \
	-D mapred.map.max.attempts="1" \
	-D mapreduce.output.fileoutputformat.compress=true \
	insert overwrite directory "/tmp/out/"
	row format delimited fields terminated by "\t"
	select user, login_time from user_login;
	1. Vim 去掉 ^M 字符

	单个文件：
	```
	%s/^M//g
	```
	(^M是ctrl+v,ctrl+m)
	<?php
	$header_prefix = 'file';
	$slots = 6;
	?>
	<html>
	<head>
	<title>Test upload</title>
	</head>
	<body>
	<?php
	# 删除 tmp 文件第一行
	sed -i '1d' tmp

	# 给 tmp 文件增加一列 '1' 的标签，分隔符为“\t”
	cat tmp \| awk 'BEGIN{OFS="\t"} {print $0,"1"}'
	import pprint
	class data:
	def __init__(self, name, value):
	self.name = name
	self.value = value

	a = data('a', 2)
	b = data('b', 3)
	c = data('c', 1)
	mydict = {'keyOfA':a, 'keyOfB':b, 'keyOfC':c}

	total=10
	startFrom=0

	for ((i=${startFrom}; i<${startFrom}+$total; i++)); do

	echo starting $i of $total ...

	done
	# mvn run main
	# 网上的例子给的是：mvn exec:java -D"exec.mainClass"="com.example.Main"，但是我这边是去掉 Main 才能跑通
	mvn exec:java -D"exec.mainClass"="com.example"

	# sbt run main (background)
	setsid nohup sbt -mem 2048 "runMain example.YourClassName ${dataSet} ${normOutput}" > norm.log &