backupbrain

import re
import nltk
from nltk.corpus import stopwords
import pandas as pd
stop_words = set(stopwords.words("english"))


def get_first_title(title):
    # keep "co-founder, co-ceo, etc"
    title = re.sub(r"[Cc]o[\-\ ]","", title)

backupbrain

backupbrain

#!/usr/bin/env python3
import urllib.request
import json
import requests

full_name = "Professor John Roberts Smith Jr."
domain = "example.com"
api_key = "<neverbounce_api_key>"

name_parts = full_name.lower().split(" ")

backupbrain

import re
import requests
import nltk
from lxml import html
from nltk.corpus import stopwords
stop_words = set(stopwords.words("english"))

# A Company Name
company_name = "The Boring Company"
search_terms = ["flamethrower"]  # The Boring Company sells flamethrowers

backupbrain

LexicalAnalyzer.prototype.generateParseError = function(lineNumber=null, message="") {
  error = {"line": lineNumber, "message": message};
  return error;
}

backupbrain

function LexicalAnalyzer() {
	this.tokenTypes = {
		"include": /^include$/,
		"string": /^\"[^\"]+\"$/,
		"unaryop": /^(sin|cos|tan|exp|ln|sqrt)$/,
		"exp": /^(\+|\-|\*|\/|\^)$/,
		"comma": /^\,$/,
		"openparen": /^\($/,
		"closeparen": /^\)$/,
		"openbracket": /^\[$/,

backupbrain

LexicalAnalyzer.prototype.getClassifiedTokenFromLines = function(tokenLines) {
	classifiedTokens = [];
	errors = [];
	// loop through each line of code
	for (var lineId = 0; lineId < tokenLines.length; lineId++) {
		line = tokenLines[lineId];
		// loop through each token in each line
		for (var tokenId = 0; tokenId < line.length; tokenId++) {
			token = line[tokenId];
			classifiedToken = null;

backupbrain

LexicalAnalyzer.prototype.run = function(tokenLines) {
	lexOutput = this.getClassifiedTokenFromLines(tokenLines);
	return lexOutput;
};

backupbrain

Tokenizer.prototype.trimWhitespace = function(text) {
	cleanedText = text.replace(/\n+/g, "\n");
	cleanedText = cleanedText.replace(/[ ]+/g, " ");
	cleanedText = cleanedText.trim();
	return cleanedText;
}

backupbrain

Tokenizer.prototype.getTokenLines = function(text) {
	lines = text.split("\n");
	tokenLines = [];
	for (var lineId = 0; lineId < lines.length; lineId++) {
		line = lines[lineId];
		tokens = line.split(" ");
		tokenLines.push(tokens);
	}
	return tokenLines;
}