soldni

import re
import codecs


class WarcHeader(dict):
    def __init__(self):
        dict.__init__(self)
        self.__dict__ = self

soldni

# This script is largely based on this forum post from the elastic blog
# https://www.elastic.co/blog/loading-wikipedia


# variables
es="$ES_HOST:$ES_PORT"
site="en.wikipedia.org"
index="enwiki"
indexDate="20160919"
indexType="content"

soldni

import os
import json
from bs4 import BeautifulSoup

def get_extracted_concepts(doc, ctakes_doc_content):
    ctakes_doc = BeautifulSoup(ctakes_doc_content, 'xml')

    umls_concepts = []

    for cas_FSArray in ctakes_doc.find_all('uima.cas.FSArray'):

soldni

{"lastUpload":"2020-09-23T06:02:58.659Z","extensionVersion":"v3.4.3"}

soldni

from collections import namedtuple


def NamedTuple(key, data):
    data = [k[0] for k in data]
    return namedtuple(key, data)

class __List:
    def __getitem__(_, elem):
        return None

soldni

 function prompt
{
   #   How many characters of the $PWD should be kept
   local pwdmaxlen=30
   #   Indicator that there has been directory truncation:
   local trunc_symbol="..."
       if [ ${#PWD} -gt $pwdmaxlen ]
           then
               local pwdoffset=$(( ${#PWD} - $pwdmaxlen ))
               newPWD="${trunc_symbol}${PWD:$pwdoffset:$pwdmaxlen}"

soldni

#!/usr/bin/env python

"""
Call any command line process from Python.

Useful as a wrapper in PyCharm or other IDEs that
do not support running scripts in any other language
other than the one(s) supported by the IDE.
"""

soldni

From https://unix.stackexchange.com/a/93158

gzip a folder:

tar -zcvf archive.tar.gz directory/ 

unzip the folder:

soldni

From https://unix.stackexchange.com/a/93158

gzip a folder:

tar -zcvf archive.tar.gz directory/ 

unzip the folder:

soldni

# coding: utf-8

# In[1]:

from thinc.extra import datasets
import mxnet as mx
import random
import re
import tqdm