xiaom

Research Data Metadata Extraction

The overall code are shown as follows.

• Closed pull requests for the Zenodo project
• invenio-files-processor module
  • Closed pull requests for the invenio-files-processor module

Here is a zip file containing all patches.

xiaom

NS = {'tei': 'http://www.tei-c.org/ns/1.0'}

def tei_to_fulltext(tei):
    from lxml import etree
    from six import text_type
    parser = etree.XMLParser(encoding='UTF-8', recover=True)
    tei = tei if not isinstance(tei, text_type) else tei.encode('utf-8')
    root = etree.fromstring(tei, parser)
    return get_fulltext(root)

xiaom

from fabric.api import *


class Tmux(object):
    """Tmux helper for fabric"""
    def __init__(self, session_name, run_cmd=run):
        self.session_name = session_name
        self.run_cmd = run_cmd

        self.create_session()

xiaom

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

xiaom

should we always use ::std::cout?

Use it only when you have to do. For example,

namespace X {
    double std(::std::vector<double> const& values) { … }

 void foo(::std::vector const&amp; values) {

xiaom

select
cast('2008-2-23' as date) as DATE_TYPE,
cast('12:20:30' as time) as TIME_TYPE,
cast('2008-2-23 12:00:00' as timestamp) as TIMESTAMP_TYPE
FROM
INFORMATION_SCHEMA.`SCHEMATA`;

xiaom

#!/bin/sh
# Stop Hive (kill all process owened by user 'hive')

ps aux | awk '{print $1,$2}' | grep hive | awk '{print $2}' | xargs kill >/dev/null 2>&1  

xiaom

#!/bin/sh

# http://docs.hortonworks.com/HDPDocuments/HDP2/HDP-2.0.0.2/bk_reference/content/reference_chap3_1.html

export HIVE_HOME=/opt/hive/hive-0.12.0-bin/
export HIVE_CONF=$HIVE_HOME/conf.drill/
su -l hive -c "env HADOOP_HOME=/usr nohup $HIVE_HOME/bin/hive --service metastore > /tmp/hive.out 2> /tmp/hive.log   &"  
su -l hive -c "nohup $HIVE_HOME/bin/hiveserver2 -hiveconf hive.metastore.uris=\" \" > /tmp/hiveServer2.out 2>/tmp/hiveServer2.log &" 

xiaom

# Let us assume
#
# - you have a laptop A
# - you work at company C
# 
# how can you access C from A?
#
# Solution: a middle man B
# 
# http://www.revsys.com/writings/quicktips/ssh-tunnel.html

xiaom

ack DataMode.OPTIONAL | awk 'BEGIN {FS =":"} {print $1}' | xargs sed -i "s/DataMode.OPTIONAL/DataMode.DM_OPTIONAL/g"