David Rosson gartenfeld

Software Engineer

gartenfeld / flat_to_mongo.py

Last active April 17, 2020 05:35

Import data from a flat file into MongoDB.

	import sys
	import re
	import codecs # UniCode support
	from pymongo import Connection # For DB Connection
	from pymongo.errors import ConnectionFailure # For catching exeptions

	def main():

	# MongoDB connection
	try:

gartenfeld / star_files.py

Last active December 12, 2015 02:39

Processing multiple files.

	def main():
	# Command-line parsing supports filename*.txt
	# Make a list of command line arguments, omitting the [0] element which is the script itself.
	args = sys.argv[1:]

	if not args:
	print 'Some message.'
	sys.exit(1)

	for filename in args:

gartenfeld / name-scraper.py

Created February 23, 2013 05:50

Scraping names of participants in a class from a raw HTML dump.

	from bs4 import BeautifulSoup
	import re # Regular Expressions
	import collections # Data Types
	import sys # File operations
	import codecs # UniCode support

	def scrape(page):
	# Dump raw HTML into Soup
	raw_data = codecs.open(page, 'r', encoding='utf-8').read()
	soup = BeautifulSoup(raw_data)

gartenfeld / exact_class.py

Created July 10, 2014 06:07

Matching exact class attribute.

soup(lambda tag: tag.name == 'div' and tag.get('class') == ['some-class'])

gartenfeld / random_file.py

Created July 10, 2014 06:11

Choose random file in directory.

	import os, random
	random.choice(os.listdir("INSERT-DIR"))

gartenfeld / load_dir.py

Created July 12, 2014 02:30

Load directory.

	# Non-recursive
	import os
	def load_directory(data_path):

	files_list = []
	try:
	for file_name in os.listdir(data_path):
	if file_name.endswith(".html"):
	files_list.append(file_name)

gartenfeld / unicode_wrapper.py

Last active August 29, 2015 14:04

Unicode HTML wrapper

	file_header = "<html>\n<head>\n<meta charset='utf-8'>\n</head>\n<body>\n"
	file_footer = "\n</body>\n</html>"

gartenfeld / lcsub.py

Last active August 29, 2015 14:08

Find longest common substring.

	def longest_common_substring(s1, s2):
	m = [[0] * (1 + len(s2)) for i in range(1 + len(s1))]
	longest, x_up_to = 0, 0
	for x in range(1, 1 + len(s1)):
	for y in range(1, 1 + len(s2)): # match every char in s2 against every char in s1
	if s1[x - 1] == s2[y - 1]: # record a char match
	m[x][y] = m[x - 1][y - 1] + 1 # char match tally will accumulate if previous char also matched
	if m[x][y] > longest:
	longest = m[x][y]
	x_up_to = x # record char position of last found match

gartenfeld / arpabet.txt

Last active August 6, 2024 11:15

Frequency distribution of syllables using CMU dictionary and COCA.

gartenfeld / triage_fi_en.py

Created November 1, 2014 11:11

Cleaning up and separating lexical data files.

	from bs4 import BeautifulSoup
	import re # Regular Expressions
	import collections # Data Types
	import sys # File operations
	import codecs # UniCode support
	import os

	def clear_output_file(out_file):
	file_header ="""<html>
	<head>