def main():
with open('last.log', 'r') as fd:
global EVENTS
EVENTS = parse(fd)
g = Graph(EVENTS)
g.make_graph()
# make_graph()
#
## with open('my.dot', 'wb') as fd:
## make_mydot(fd)
#
with closing(StringIO()) as fd:
g.make_dot(fd)
with open('test.dot', 'wb') as ffd:
ffd.write(fd.getvalue())
win = xdot.DotWindow()
win.set_dotcode(fd.getvalue())
win.connect('destroy', gtk.main_quit)
gtk.main()
pass
def parse_one_person():
file = io.StringIO("1;Nicolette Champlin")
res = file_parser.parse(file)
person = res[0]
assert_that(person.name, equal_to("Nicolette Champlin"))
assert_that(person.id, equal_to("1"))
def parse_one_person():
file = io.StringIO("1;Nicolette Champlin")
res = file_parser.parse(file)
person = res[0]
assert_that(person.name, equal_to("Nicolette Champlin"))
assert_that(person.id, equal_to("1"))
def returns_one_user():
res = io.StringIO('''1;Jens Gustafsson
2; Henrik Gudmunssson''')
persons = file_parser.parse(res)
assert_that(persons, has_length(2))
assert_that(persons[0].id, equal_to("1"))
assert_that(persons[0].name, equal_to("Jens Gustafsson"))
def returns_person_with_appointment():
res = io.StringIO('''1;3/13/2015 8:00:00 AM;3/13/2015 1:00:00 PM;C5CA
1;Jens Gustafsson''')
person_with_appointment = file_parser.parse(res)
assert_that(person_with_appointment, has_length(1))
person = person_with_appointment[0]
assert_that(person, instance_of(file_parser.Person))
assert_that(person.appointments, has_length(1))
def HandleNewEmail(mail_path):
#Parse email to store in DB
#print(type(mail_path))
#added this for image remove if problematic
if (mail_path.endswith('.png') or mail_path.endswith('.jpg') or mail_path.endswith('.jpeg')):
#print('Email Image uploaded!!')
extracted_text = ocr(mail_path)
email = extracted_text.split('\n')
if (mail_path.endswith('.pdf')):
#print('PDF received')
extracted_text = parse(mail_path)
email = extracted_text.split('\n')
#print(email)
if (mail_path.endswith('.txt')):
#print('txt received')
email=open(mail_path, "r")
to_add=''
from_add=''
sub=''
body=''
for line in email:
#print(f'**{line}**')
if line.startswith('To: ') or line.startswith('to: '):
pieces = line.split()
to_add = pieces[1]
#print(f'To---->Found!!!{to_add}')
continue
if line.startswith('From: ') or line.startswith('from: '):
pieces=line.split()
from_add=pieces[1]
continue
if line.startswith('Subject: ') or line.startswith('subject: '):
pieces=line.split()
subject=pieces[1:]#remove word subject
for word in subject:
sub = sub + " " + word
# text=text+" "
continue
body=body + line
text=sub + " " + body
receivedDate = time.ctime(os.path.getctime(mail_path))
if (mail_path.endswith('.txt')):
email.close()
#print(encoded_mail)
outputclass , id = inp(to_add,from_add,sub,body)
#addtoDB(to_add, from_add, receivedDate, sub, id, body, outputclass)
moveEmail(mail_path, outputclass)
print(f'====>Event Processing completed')
return to_add, from_add, receivedDate, sub, id, body, outputclass
def parse_person_with_appointment():
file = io.StringIO('''1;Nicolette Champlin
1;1/8/2015 11:30:00 AM;1/8/2015 2:00:00 PM;ABC''')
res = file_parser.parse(file)
person = res[0]
assert_that(person.id, equal_to("1"))
assert_that(person.name, equal_to("Nicolette Champlin"))
assert_that(person.appointments, has_length(1))
def parse_person_with_appointment():
file = io.StringIO('''1;Nicolette Champlin
1;1/8/2015 11:30:00 AM;1/8/2015 2:00:00 PM;ABC''')
res = file_parser.parse(file)
person = res[0]
assert_that(person.id, equal_to("1"))
assert_that(person.name, equal_to("Nicolette Champlin"))
assert_that(person.appointments, has_length(1))
def generate(dna_path, header, filename, output_path, loading_bar):
"""
Pulls together numerous functions to generate the pdf report
:param dna_path:
Path to the DNA file
:param header:
Paragraph at the top of the document
:param filename:
Name of the file to be created
:param output_path:
Destination for the report
:return:
The path to the generated report
"""
# Get the predefined groups
groups = group_mngr.load_groups()
loading_bar.value = 10
# Create variable to hold the active service, assigned below
service = _detect_service(dna_path) # Returns "AncestryDNA" or "23&Me"
loading_bar.value = 20
# Get the genes from the provided file
pulled_genes = file_parser.parse(groups, dna_path, service)
loading_bar.value += 50
# Create the pdf with given info
write_report(groups,
pulled_genes,
filename,
output_path,
service,
header=header)
loading_bar.value = 75
# Return the path the file was saved to
file_path = output_path + f"/{filename}.pdf"
return file_path
def returns_one_user():
res = io.StringIO("1;Jens Gustafsson")
persons = file_parser.parse(res)
assert_that(persons, has_length(1))
assert_that(persons[0].id, equal_to("1"))
assert_that(persons[0].name, equal_to("Jens Gustafsson"))
def returns_empty_result_when_file_is_empty():
res = io.StringIO("")
persons = file_parser.parse(res)
assert_that(persons, has_length(0))
import file_parser as file_parser
import requests
from bs4 import BeautifulSoup
import json
import goslate
from langdetect import detect
sites, label = file_parser.parse("dataset.txt")
gs = goslate.Goslate()
i = 0
x_training = []
x_test = []
y_training = []
y_test = []
with open("lang_file.json", encoding="utf8") as json_file:
data = json.load(json_file)
print(data["it"])
j = 0
print("==================== Download Pages =====================")
e_commerce = []
for site in sites:
try:
i = i + 1
if "amazon" in site:
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36'
}
page = requests.get(site, headers=headers)
soup = BeautifulSoup(page.content, 'lxml')
def returns_empty_list_if_file_is_empty():
empty_file = io.StringIO("")
res = file_parser.parse(empty_file)
assert_that(res, empty())
def parse(d):
return file_parser.parse(d)
def returns_a_user_without_name_and_one_meeting():
res = io.StringIO("1;3/13/2015 8:00:00 AM;3/13/2015 1:00:00 PM;C5CA")
persons = file_parser.parse(res)
assert_that(persons[0].name, equal_to(""))
assert_that(persons[0].appointments[0].start, equal_to(file_parser.parse_date("3/13/2015 8:00:00 AM")))
def convert_rules_list_to_dict(rules):
rules_dict = {}
for rule in rules:
rules_dict[rule.head] = rule
return rules_dict
if __name__ == "__main__":
rules_files = ['Sample4.in']
input_string_file_template = 'input{0}.in'
output_parse_tree_file_template = 'my-ouput{0}.out'
parse_trees = []
for file in rules_files:
variables, terminals, rules = file_parser.parse(file)
rules_dict = convert_rules_list_to_dict(rules)
first_sets = first.get(variables, rules_dict)
follow_sets = follow.get(variables, rules, first_sets)
# change terminals to include $ instead of !
terminals[-1] = '$'
parsing_table = table_builder.build(variables, terminals, first_sets, follow_sets, rules_dict)
print('Rules: ')
print('\n'.join(map(str, rules)))
print(' ---------------')
print('First Sets: ')
print(first_sets)
print(' ---------------')
print('Follow Sets: ')
print(follow_sets)
print(' ---------------')
def handle_new_email(mail_path):
"""
Extract text from email depending on file type
Call model to get output class
Return to_add, from_add, received_date, sub, tid, body, outputclass
"""
#print(type(mail_path))
#added this for image remove if problematic
if (mail_path.endswith('.png') or mail_path.endswith('.jpg') or
mail_path.endswith('.jpeg')):
#print('Email Image uploaded!!')
extracted_text = ocr(mail_path)
email = extracted_text.split('\n')
elif mail_path.endswith('.pdf'):
#print('PDF received')
extracted_text = parse(mail_path)
email = extracted_text.split('\n')
#print(email)
elif mail_path.endswith('.txt'):
#print('txt received')
email = open(mail_path, "r")
else:
#Unhandled file type
return '', '', '', '', '', '', ''
to_add = ''
from_add = ''
sub = ''
body = ''
for line in email:
#print(f'**{line}**')
if line.startswith('To: ') or line.startswith('to: '):
pieces = line.split()
to_add = pieces[1]
#print(f'To---->Found!!!{to_add}')
continue
if line.startswith('From: ') or line.startswith('from: '):
pieces = line.split()
from_add = pieces[1]
continue
if line.startswith('Subject: ') or line.startswith('subject: '):
pieces = line.split()
subject = pieces[1:]#remove word subject
for word in subject:
sub = sub + " " + word
# text=text+" "
continue
body = body + line
#text = sub + " " + body
received_date = time.ctime(os.path.getctime(mail_path))
if mail_path.endswith('.txt'):
email.close()
#print(encoded_mail)
outputclass, tid, amt = inp(to_add, from_add, sub, body)
#add_to_db(to_add, from_add, received_date, sub, tid, body, outputclass)
#move_email(mail_path, outputclass)
print(f'====>Event Processing completed')
return to_add, from_add, received_date, sub, tid, body, outputclass
from file_parser import parse
from rank_counter import count
from page_downloader import download
'''
Scrape https://moongourd.com/ "Class Rankings" stats for Solo Heal for your desired dungeon & boss
Outputs the number of times a class has been found
'''
if __name__ == '__main__':
# your desired url here
url = "https://moongourd.com/eu/hiscores?area=3126&boss=1000&class=All%20Classes"
# the number of ranks to take into account
target_ranks = 100
download(url)
filename = "input.html"
rank = {
"Valkyrie": 0,
"Warrior": 0,
"Berserker": 0,
"Slayer": 0,
"Ninja": 0,
"Sorcerer": 0,
"Gunner": 0,
"Archer": 0,
"Reaper": 0
}
parsed_file = parse(filename, target_ranks)
result = count(rank, parsed_file)
for i in result:
print(f"Class: {i}, Appeared {rank[i]} times")
def returns_empty_list_if_file_is_empty():
empty_file = io.StringIO("")
res = file_parser.parse(empty_file)
assert_that(res, empty())
for item in only_shopping_list_updated:
all_possible_sorted_combinations.append(sorted(list(set(itertools.combinations(item, step)))))
return all_possible_sorted_combinations
def get_candidate_list_allowed(flatten_list, allow_level, mode=0):
if mode == 1:
res = Counter(flatten_list)
else:
res = Counter(map(tuple, flatten_list))
return [key for key, value in res.items() if value >= allow_level]
file_path = "TestFiles/client_product.txt"
file_content = file_reader.read(file_path)
content_matrix, client_product = file_parser.parse(file_content)
clients = content_matrix[0]
clients_unique = set(clients)
products = content_matrix[1]
products_unique = set(products)
products_occurrences = dict()
for product in products_unique:
products_occurrences[product] = products.count(product)
clients_shopping_list = []
client_product.sort(key=itemgetter(0))
groups = groupby(client_product, itemgetter(0))
clients_shopping_list = [[key, sorted([item[1] for item in data])] for (key, data) in groups]