zapalote

# Data source: https://storage.googleapis.com/books/ngrams/books/datasetsv2.html

# extraction pattern: ngram TAB year TAB match_count TAB volume_count NEWLINE
# out: unique_ngram TAB sum(match_count) NEWLINE

import os, sys
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor
from multiprocessing import freeze_support
import polars as pl

zapalote

// decode credentials upon receiving them from store
function decodeCredentials(crd){
	// decrypt it first
	const dec = CryptoJS.AES.decrypt(crd, saltCredentials).toString(CryptoJS.enc.Utf8);
	// extract the creds length and pepper step
	const len = dec.charCodeAt(0) - 96;
	const step = dec.charCodeAt(1) - 96;
	let i = 0, j = 2, d = [];

	// extract the pepper from the salt

zapalote

// used to obfuscate and encrypt the credentials
const saltCredentials = "jf02heg9u64a{%m<83#@;Pxrjg17uyr#@&*%^Y";

// encode credentials before storing
function encodeCredentials(crds){
	// json object expected e.g. {'api-id':'K0xf56g', 'pwd':'Some.Pa$$w0rd'}
	const crd = JSON.stringify(crds);
	const len = crd.length;
	// this constraint is due to storing the length in one byte 
	if (len > 159) return null;

zapalote

<script src="https://cdnjs.cloudflare.com/ajax/libs/crypto-js/4.0.0/crypto-js.min.js"></script>
<script>
// used to obfuscate and encrypt the credentials
const saltCredentials = "jf02heg9u64a{%m<83#@;Pxrjg17uyr#@&*%^Y";

// encode credentials before storing
function encodeCredentials(crds){
	// json object expected e.g. {'api-id':'K0xf56g', 'pwd':'Some.Pa$$w0rd'}
	const crd = JSON.stringify(crds);

zapalote

# extraction pattern: ngram TAB year TAB match_count TAB volume_count NEWLINE
# out: unique_ngram TAB sum(match_count) NEWLINE

import re
import os, sys, mmap
from pathlib import Path
from tqdm import tqdm
from concurrent.futures import ThreadPoolExecutor

abv = re.compile(r'^(([A-Z]\.){1,})(_|[^\w])')  # A.B.C.