def main():
args = docopt(__doc__, version="0.1")
fileops = FileOps(casemode=args["--casemode"],
countpos=args["--count"],
dirsonly=args["--dirsonly"],
exclude=args["--exclude"],
filesonly=args["--filesonly"],
hidden=args["--all"],
ignorecase=args["--ignorecase"],
interactive=args["--interactive"],
keepext=args["--keep-extension"],
mediamode=args["--media"],
noclobber=args["--no-clobber"],
recursive=args["--recursive"],
regex=args["--regex"],
remdups=args["--remduplicates"],
remext=args["--remextensions"],
remnonwords=args["--no-wordchars"],
remsymbols=args["--remsymbols"],
simulate=args["--simulate"],
spacemode=args["--spacemode"],
quiet=args["--quiet"],
verbosity=args["-v"],
matchpattern=args["<matchpattern>"],
replacepattern=args["<replacepattern>"])
fileops.get_previews(fileops.get_targets(args["--path"]))
def main():
args = docopt(__doc__, version="0.1")
fileops = FileOps(casemode=args["--casemode"],
countpos=args["--count"],
dirsonly=args["--dirsonly"],
exclude=args["--exclude"],
filesonly=args["--filesonly"],
hidden=args["--all"],
ignorecase=args["--ignorecase"],
interactive=args["--interactive"],
keepext=args["--keep-extension"],
mediamode=args["--media"],
noclobber=args["--no-clobber"],
recursive=args["--recursive"],
regex=args["--regex"],
remdups=args["--remduplicates"],
remext=args["--remextensions"],
remnonwords=args["--no-wordchars"],
remsymbols=args["--remsymbols"],
simulate=args["--simulate"],
spacemode=args["--spacemode"],
quiet=args["--quiet"],
verbosity=args["-v"],
matchpattern=args["<matchpattern>"],
replacepattern=args["<replacepattern>"])
fileops.get_previews(fileops.get_targets(args["--path"]))
def get_corpus_info(categories, **kwargs):
corpus_info = []
for category in categories:
if not 'stopwords' in kwargs:
tokens = [w for w in brown.words(categories=category)]
else:
if kwargs['stopwords'] == 'english':
tokens = [w for w in brown.words(categories=category) if w not in FileOps.get_stopwords('stopwords.txt')]
token_count = len(tokens)
type_count = len(set(tokens))
diversity = "%.3f" % (type_count/token_count)
tmp = category.split('_')
category = ' '.join(tmp)
category_info = (category, token_count, type_count, diversity)
print(category_info)
corpus_info.append(category_info)
return corpus_info
for category in categories:
if not 'stopwords' in kwargs:
tokens = [w for w in brown.words(categories=category)]
else:
if kwargs['stopwords'] == 'english':
tokens = [w for w in brown.words(categories=category) if w not in FileOps.get_stopwords('stopwords.txt')]
token_count = len(tokens)
type_count = len(set(tokens))
diversity = "%.3f" % (type_count/token_count)
tmp = category.split('_')
category = ' '.join(tmp)
category_info = (category, token_count, type_count, diversity)
print(category_info)
corpus_info.append(category_info)
return corpus_info
if __name__ == "__main__":
<<<<<<< HEAD
=======
plurals_info = get_plurals_info(brown.categories())
FileOps.write_plurals_table(plurals_info)
>>>>>>> a4d8d09f16fdcb0d863e6b8683049a38be7be961
corpus_info = get_corpus_info(brown.categories())
stopwords_info = get_corpus_info(brown.categories(), stopwords='english')
FileOps.write_table(corpus_info, stopwords_info)
print_corpus_info(brown.categories(), FileOps.get_stopwords('stopwords.txt'))
"""
Skeleton code for a flask website
"""
import flask
from flask import render_template
from flask import request
from flask import url_for
from fileops import FileOps
fo = FileOps()
import json
import logging
###
# Globals
###
app = flask.Flask(__name__)
import CONFIG
###
# Pages
###
@app.route("/")
@app.route("/index")
def index():
