def printrules(rules):
for rule in rules:
if rule[2] == '!ssi':
print(bc.CYAN, clean(rule[0]), '=>', clean(rule[1]), bc.RES)
if rule[2] == 'ssi':
print(bc.GREEN, clean(rule[0]), '<=>', clean(rule[1]), bc.RES)
print('')
def main_menu():
"""Main loop with options"""
while True:
choice = input(MAIN_MENU)
clean()
if choice.lower() == "a":
add_task()
elif choice.lower() == "s":
search_options()
elif choice.lower() == "q":
break
else:
print("'{}' invalid option! Please try again".format(choice))
def query(search: str) -> bytes:
"""
Query DBpedia, return response or exit with errorcode
"""
search = tools.clean(search, "search")
url = getAPIprefix() + search
return tools.url_reader(url)
def __init__(self, url: str):
"""
__init__ method, initializes the variables.
Args:
url (str): the url to use.
Raises:
ValueError(f"{url} is not a valid fanfiction.net URL for a story")
urllib.error.HTTPError
ValueError(f"{url} is not the URL of an accessible story.")
"""
if not tls.is_url(url):
raise ValueError(f"{url} is not a valid fanfiction.net URL for a "
"story.")
try:
# Ensure the url used is not a mobile one after that
page = tls.get_page(url.replace('://m', '://www'))
except urllib.error.HTTPError as e:
raise e
# Here I get the informations which will be needed to create self.ifs
try:
text_id = tls.clean(re.search(c.TEXT_ID_REGEX, page).group(1))
except AttributeError:
raise ValueError(f"{url} is not the URL of an accessible story.")
num_id = url.split('/')[4]
tokens = Story._get_tokens(page)
chap_count = Story._get_chap_count(tokens)
status = Story._get_status(tokens)
# Informations are sorted alphabetically here
self.ifs = {
'auth': re.search(c.AUTHOR_REGEX, page).group(1), # str
'auth_id': re.search(c.AUTHOR_ID_REGEX, page).group(1), # str
'c_count': Story._get_chap_count(tokens), # • int
'lang': tokens.split(' - ')[2], # str
'chap': re.findall(c.CHAPTERS_REGEX, page)[:chap_count], # • list
'n_id': num_id, # str
'publ': re.search(c.PUBLISHED_REGEX, tokens).group(1), # str
'rating': tokens.split(' - ')[1], # str
's_dir': f'{text_id}_{num_id}'.lower(), # str
'status': Story._get_status(tokens), # str
'smry': re.search(c.SUMMARY_REGEX, page).group(1), # str
't_id': text_id.lower(), # str
'title': re.search(c.STORY_TITLE_REGEX, page).group(1), # str
'tk': Story._insert_status(tokens, status), # str
'uni': Story._get_universe(page), # str
'upd': Story._get_update(tokens), # str
'url': f'{c.ROOT_URL}{num_id}/1/{text_id}', # str
'w_count': Story._get_words_count(tokens), # • int
}
def __init__(self,original, label=''):
self.label = label
self.original = original
self.tokenized = t.clean(self.original.split())
self.lemmas = []
self.unknown = []
self.bilemmas = []
self.postags = []
self.bipostags = []
self.markers = []
self.emendationLogs = []
def compute(self, bigrams=False):
self.lemmas, self.unknownLemmas = t.lemmatize(self.tokenized)
self.postags , self.unknownPostags = t.pos(self.lemmas)
if bigrams:
self.bilemmas = u.getNgrams(self.lemmas, min=2, max=3)
self.bipostags = u.getNgrams(self.postags, min=2, max=3)
def add_images(result: dict) -> dict:
"""
Add image links via Wikidata Linked Data
"""
# TO DO: add license information and show in result
COMMONS = "https://commons.wikimedia.org/wiki/File:"
images = {}
for section in result:
if "wikidata" in section:
wikidata = lookup_hit(result[section], "wikidata")
wikidata = json.loads(wikidata)
qcode = result[section].split("/")[-1]
image = wikidata["entities"][qcode]["claims"].get("P18")
if image is None:
return result
imageref = image[0]["mainsnak"]["datavalue"].get("value")
imageref = tools.clean(imageref.replace(" ", "_"), "url")
imagelink = COMMONS + imageref
imagelink = imagelink
images[section + "image"] = get_commonslink(imagelink)
newresult = {**result, **images}
return newresult
'...'),
end="")
shutil.copyfile(file,
os.path.join(dest_path, os.path.basename(file)))
print(' Done!')
if __name__ == '__main__':
print(chr(27) + "[2J")
print('Starting build!')
t1 = time.time()
production = False
print('\n\n=== C L E A N ===')
print(f'cleaning {data["options"]["prod"]}...', end='')
tools.clean(os.path.expanduser(data['options']['prod']))
print(' Done!')
if len(argv) > 1 and argv[1] == 'production':
production = True
s3 = None
if production:
## AWS ##
s3_bucket_name = data['options']['s3 bucket']
print('\n\n=== A W S ===\n\nCleaning {0}'.format(s3_bucket_name))
s3 = boto3.resource('s3')
s3_bucket = s3.Bucket(s3_bucket_name)
for key in s3_bucket.objects.all():
key.delete()
def predict(self, raw_text):
text = tools.clean(raw_text)
ngrams_text = ngrams.get_ngrams(text, self.ngram_dict.n)
hist = self.ngram_dict.get_histogram(ngrams_text)
cat = knn(hist, self.dataset, metrics.l2)
return cat
def run (self):
if self.dim.get () == "" or self.T.get () == "":
return
self.txt.delete('1.0', tk.END)
self.pbl = 0
if self.typeproblem.get () == "Transport":
self.pbl = transport_class.transport ()
elif self.typeproblem.get () == "Burgers":
self.pbl = burgers_class.burgers ()
else:
self.pbl = shallow_water_class.shallow_water ()
self.disp ("Equation : {}".format (self.typeproblem.get ()))
self.pbl.disp = self.disp
disp = self.disp
pdata = 0
if int (self.load_vtk.get ()) == 0:
if int (self.dim.get ()) == 1:
pdata = tools.clean (tools.gmsh1D ([[0.], [1.]], [0.01, 0.01]))
if int (self.dim.get ()) == 2:
pdata = tools.clean (tools.gmsh2D ([[0., 0., 0.], [1., 0., 0.], [1., 1., 0.], [0., 1., 0.]], [0.05, 0.05, 0.05, 0.05]))
else:
filename = filedialog.askopenfilename(initialdir = ".",title = "Select file", filetypes = (("vtk files","*.vtk"),("all files","*.*")))
self.disp ("Load VTK : {}".format (filename))
pdata = tools.readVTK (filename)
self.pbl.setPdata (pdata)
if self.pbl.pdata.GetNumberOfCells == 0 or self.pbl.pdata.GetNumberOfPoints == 0:
return
self.pbl.buildInterfaces ()
self.pbl.defineCond_init ()
self.pbl.useCFL = False
self.pbl.isPeriodic = False
if self.cfl_checkbox.get () == 1:
self.pbl.useCFL = True
if self.periodic.get () == 1:
self.pbl.isPeriodic = True
if self.imposeBoundary.get () == 1:
self.pbl.imposeBoundary = True
self.pbl.dt = float (self.dt.get ())
self.pbl.T = float (self.T.get ())
self.pbl.cfl_nu = float (self.nu.get ())
self.pbl.name_numericalFlow = self.scheme.get ()
if self.scheme.get () == "upwind":
self.pbl.numericalFlow = self.pbl.up_wind
elif self.scheme.get () == "laxfriedrichs":
self.pbl.numericalFlow = self.pbl.lax_friedrichs
elif self.scheme.get () == "laxwendroff":
self.pbl.numericalFlow = self.pbl.lax_wendroff
elif self.scheme.get () == "godunov":
self.pbl.numericalFlow = self.pbl.godunov
elif self.scheme.get () == "maccormak":
self.pbl.numericalFlow = self.pbl.mac_cormak
else:
self.pbl.numericalFlow = self.pbl.up_wind
self.pbl.analysis ()
self.pbl.iterate (self.fun_set_progress)
self.plot ()
def predict(self,raw_text):
text=tools.clean(raw_text)
ngrams_text=ngrams.get_ngrams(text,self.ngram_dict.n)
hist=self.ngram_dict.get_histogram(ngrams_text)
cat=knn(hist,self.dataset,metrics.l2)
return cat