lukehollis

"""

Inspired by "Quantifying origin and character of long-range correlations in narrative texts"
by Stanisław Drożdż, Paweł Oświȩcimkaa, Andrzej Kuliga, Jarosław Kwapieńa, Katarzyna Bazarnikb,
Iwona Grabska-Gradzińskac, Jan Rybickib, and Marek Stanuszekd, this is an attempt to implement
the CLTK tokenizers to sentence lengths of works from the Greek and Latin corpora from the
Perseus Digital Archive for analysis via the methods used by the above researchers.


"""

lukehollis

import pdb
import os, json, re
from bs4 import BeautifulSoup
import html.parser
import pymongo
from db import mongo

class PerseusToMongo:
# a class to migrate Perseus XML file data to mongo db

lukehollis

import pdb
import re
import string
import sys

class ScansionToHTML:

	def __init__(self, line, scansion):

		self.scansion = scansion

lukehollis

# Ignore configuration files that may contain sensitive information.
sites/*/settings*.php

# Ignore paths that contain user-generated content.
sites/*/files
sites/*/private
sites/*/~private

.svn
*.svn/

lukehollis

	conj_list = ['ac', 'at', 'atque', 'aut', 'et', 'ne', 'nec', 'non', 'sed', 'si', 'uel', 
			'cum', 'quum', 'donec', 'dum', 'enim', 'enimuero', 'etiam', 'etsi', 'igitur',
			'itaque', 'nam', 'necnon', 'neque', 'nisi', 'postquam', 'quamquam', 'quamuis',
			'quando', 'que', 'quia', 'quin', 'quippe', 'quinetiam', 'quod', 'quodque',
			'siue', 'ut', 'tam', 'necdum']

	prep_list = ['ante', 'ad', 'circum', 'contra', 'inter', 'intra', 'post', 'in', 'en', 'praeter',
			'per', 'propter', 'super', 'uersus', 'extra', 'trans', 'sub', 'ob', 'a', 'ab',
			'de', 'cum', 'e', 'ex', 'sine', 'pro', 'prae', 'sub', 'super']

lukehollis

import pymongo
import json
import pdb


def mongo(db):
	host = "localhost" 
	port = 27017
	client = pymongo.MongoClient(host, port, max_pool_size=None)
	return client[db]