def findPhonetics(subject, bookshelf):
dictionary = open(bookshelf)
try:
subPhonetic = metaphone(subject)
except TypeError:
print("Soundex broke")
return
levenNumber = 0
similar = []
for line in dictionary:
if "-" not in line:
line = line.split("\n")[0]
try:
linePhonetic = metaphone(line)
if line != subject and linePhonetic.find(subPhonetic) != -1:
subjectIndex = findPhoneticIndex(subject, line)
similar.append(
(line,
levenshtein(
line[subjectIndex:subjectIndex + len(subject)],
subject)))
except TypeError:
#print("Broke on " + line + "... Continuing")
continue
similar.sort(key=lambda tup: tup[1])
return similar
def phonetic_weight(name_to_remember, current_trigger_word,pw):
#create metaphone codes without the first unnecessary letters
if name_to_remember[0] == ('w' or 'q'):
w1_without_fl = phonetics.metaphone(name_to_remember[2:])
else:
w1_without_fl = phonetics.metaphone(name_to_remember[1:])
if current_trigger_word[0] == ('w' or 'q'):
w2_without_fl = phonetics.metaphone(current_trigger_word[2:])
else:
w2_without_fl = phonetics.metaphone(current_trigger_word[1:])
#calculate the levenshtein distance between the two metaphone codes
score_without_fl = enchant.utils.levenshtein(w1_without_fl, w2_without_fl)
#create a list of all known rhyming words from the pronouncing library
checklist = pronouncing.rhymes(name_to_remember)
#check if the candidate trigger word is in the list of know rhyming words
if current_trigger_word in checklist:
return pw
#otherwise calculate its phonetic similarity using the users pw(phonetic weight) and ..
#..the levenshtein/metaphone score
elif score_without_fl == 0:
return pw/1.5
else:
return pw/(score_without_fl+1)
#the_list = create_output_list_v3(doc,start_word, pw, slw, flw, pwsw)
def get_similar_metaphone(DF_NAMELIST):
"""
match lastname -> match firstname -> match middlename's first letter
input:
pandas data frame of names(indexed)
output:
pandas data fame of matched names
"""
df = DF_NAMELIST
df['f_meta'] = [metaphone(s) for s in df['firstname']]
df['l_meta'] = [metaphone(s) for s in df['lastname']]
df.sort_values(['f_meta', 'l_meta'])
metamong = []
for i in range(df.shape[0]):
Collide1 = False
if i != 0:
Collide1 = True
for attr in ['f_meta', 'l_meta']:
if df.loc[i, attr] != df.loc[i - 1, attr]:
Collide1 = False
Collide2 = False
if i != df.shape[0] - 1:
Collide2 = True
for attr in ['f_meta', 'l_meta']:
if df.loc[i, attr] != df.loc[i + 1, attr]:
Collide2 = False
if Collide1 or Collide2:
metamong.append(df.loc[i])
metamong = pd.DataFrame(metamong)
print("metaphone list created")
return (metamong)
def compare(a,b):
a = a.lower() # convert all words to lower case for easier comparison.
b = b.lower()
m = ph.metaphone(a)==ph.metaphone(b) # compare strings using metaphone
s = ph.soundex(a)==ph.soundex(b) # compare strings using soundex
n = ph.nysiis(a)==ph.nysiis(b) # compare strings using nysiis
return m + s + n
def findPhoneticIndex(subject, word):
subjectPhone = metaphone(subject)
for i in range(0, len(word)):
wordPhone = metaphone(word[i:len(word)])
if subjectPhone == wordPhone[0:len(subjectPhone)]:
return i
def metaphone(collection):
"""
Returns a list of metaphone encoded collection.
Arguments:
collection -- the list of words to be encoded using metaphone.
limit -- the limit to the words.
"""
try:
assert type(collection) == list or type(collection) == str
except AssertionError:
print("The collection for metaphone is not a string or a list.")
from phonetics import metaphone
if type(collection) == str:
return metaphone(collection)
collectionEncoded = list()
for word in collection:
wordEncoded = metaphone(word)
collectionEncoded.append(wordEncoded)
return collectionEncoded
def similarity(word1, word2):
nysiis1 = phonetics.nysiis(word1)
nysiis2 = phonetics.nysiis(word2)
nysiis_distance = levenshtein(nysiis1, nysiis2)
metaphone1 = phonetics.metaphone(word1)
metaphone2 = phonetics.metaphone(word2)
metaphone_distance = levenshtein(metaphone1, metaphone2)
dmetaphone1 = phonetics.dmetaphone(word1)
dmetaphone2 = phonetics.dmetaphone(word2)
dmetaphone_distance = levenshtein(dmetaphone1, dmetaphone2)
# return a linear combination of these distances
return nysiis_distance * 0.2 + metaphone_distance * 0.4 + dmetaphone_distance * 0.6
def fuzzy_hash_string(self):
"""The fuzzy hash string, before hashing. Useful for computing string distances. """
import unicodedata
from phonetics import metaphone
s = '|'.join([
str(self.number),
self.multinumber or '.',
metaphone(self.street_name) if self.street_name else '.',
metaphone(self.city) if self.city else '.',
metaphone(self.state) if self.state else '.',
str(self.zip4) if self.zip4 else '.'
]).lower()
return unicodedata.normalize('NFC', s)
def phonetic_street_compare():
st_name = request.args.get("st_name")
st_name = re_pattern.sub("", st_name.lower())
soundex = phonetics.soundex(st_name)
print(soundex)
results = set()
soundexes = MongoAddress.objects(st_city="EL CAMPO", soundex=soundex)
if soundexes:
for address in soundexes:
if address["st_name"] in results:
continue
else:
results.add(address["st_name"])
metaphone = phonetics.metaphone(request.args.get("st_name").lower())
metaphones = MongoAddress.objects(st_city="EL CAMPO", metaphone=metaphone)
if soundexes:
for address in metaphones:
if address["st_name"] in results:
continue
else:
results.add(address["st_name"])
return jsonify({"phonetics": list(results)})
else:
return jsonify("")
def text2piano(text: str):
"""
Converts text string to piano sounds.
# text to metaphones
# metaphone to piano key
# generate piano key sequence
# write piano key sequence as mp3
# find audio files for piano keys in fingerprint
# concatenate audio files into one file
:param text:
:return: mp3 file
:example:
:TODO: at least one test. add rests.
"""
_notes = [
'A2', 'A3', 'A4', 'C1', 'C2', 'C3', 'C4', 'C5', 'C6', 'Ds1', 'Ds2',
'Ds3', 'Ds4', 'Fs2', 'Fs3', 'Fs4'
]
_metaphones = list('0BFHJKLMNPRSTWXY')
_meta2piano = dict(zip(_metaphones, _notes))
metaphones = list(phonetics.metaphone(text))
fingerprint = [_meta2piano[phone] for phone in metaphones]
filenames = [f'{mypath}{f}_quart.mp3' for f in fingerprint]
_mp3s = [AudioSegment.from_mp3(file) for file in filenames]
_mp3 = sum(_mp3s)
_outputmp3 = f"{mypath}{text}{''.join(metaphones)}.mp3".replace(' ', '')
logging.warning(_outputmp3)
_mp3.export(_outputmp3, format="mp3")
def similarity(self, other: str) -> float:
res_seqmat = SequenceMatcher(None, self.name, other).ratio()
res_lev = Levenshtein.distance(self.name, other)
res_met = Levenshtein.distance(phonetics.metaphone(self.name),
phonetics.metaphone(other))
phon_this = phonetics.dmetaphone(self.name)
phon_oher = phonetics.dmetaphone(other)
min_so_far = 9999999
for i in phon_this:
for j in phon_oher:
min_so_far = min(min_so_far, Levenshtein.distance(i, j))
res_dmet = min_so_far
weights = {"seqmat": 0.1, "lev": 0.5, "met": 0.2, "dmet": 0.3}
return (res_seqmat * weights['seqmat'] + res_lev * weights['lev'] +
res_met * weights['met'] +
res_dmet * weights['dmet']) / 4.0
def searchString(qNom, qReg, mode = 0):
qT = []
#pdb.set_trace()
if qNom != None:
regxN = re.compile(qNom, re.IGNORECASE)
regxV = re.compile(qVille, re.IGNORECASE)
q1 = {"$or": [ {"nom": {"$regex": regxN } } , {"ingr": {"$regex": regxV} } ]}
if mode == 1:
q1 = {"nomU": {"$regex": '.*' + scanName(qNom) + '.*'} }
if mode == 2:
phonetic=phonetics.metaphone(qNom)
q1 = {"nomP": {"$regex": '.*' + phonetic + '.*'} }
qT.append(q1)
if qReg != None:
#pdb.set_trace()
q2 = {'cat._id': qReg}
qT.append(q2)
#pdb.set_trace()
userRole = getUserRole()
if not (localHost or userRole == 'ADM' or userRole == 'MEA'):
qT.append({"state": 1 })
return { "$and": qT }
def create_metaphone_representation(lyrics):
""" Returns the Metaphone representation of a string """
metaphone_repr = ''
for word in lyrics.split():
try:
metaphone_repr += phonetics.metaphone(word) + ' '
except:
print(word)
return metaphone_repr.rstrip()
def word_to_phonetic_distance(word1, word2):
code_distance = dict()
# weights
weight = {"soundex": 0.3, "metaphone": 0.5, "nysiis": 0.2}
edit_distance = 0
try:
code_distance[
'soundex'] = weight['soundex'] * damerau_levenshtein_distance(
phonetics.soundex(word1), phonetics.soundex(word2))
code_distance[
'metaphone'] = weight['metaphone'] * damerau_levenshtein_distance(
phonetics.metaphone(word1), phonetics.metaphone(word2))
code_distance[
'nysiis'] = weight['nysiis'] * damerau_levenshtein_distance(
phonetics.nysiis(word1), phonetics.nysiis(word2))
# Edit distance according to weight vector
edit_distance = code_distance['soundex'] + code_distance[
'metaphone'] + code_distance['nysiis']
except:
pass
return (edit_distance)
def _misspelt(spell, spells):
"""
Returns None if the spell is correct or not existing. Otherwise returns the
misspelt spell.
:param spell:
:param spells:
:return:
"""
from phonetics import metaphone
from editdistance import eval as edit_distance
assert spell
# log.debug("Looking for %r in %r", spell, spells)
if spell in spells:
return (spell, SPELL_OK)
phonetic_spell = metaphone(spell)[:5]
for existing_spell in spells:
if edit_distance(metaphone(existing_spell)[:5], phonetic_spell) <= 2:
log.warning("Incantesimo scorretto: %r invece di %r", spell,
existing_spell)
return (existing_spell, SPELL_KO)
return (spell, SPELL_MISSING)
def __init__(self, dictionary):
GenericAlgorithm.__init__(self, dictionary)
self.phoneticDictionary = {}
for word in self.dictionary:
phono = phonetics.metaphone(word)
try:
self.phoneticDictionary[phono][word] = 1
except KeyError:
self.phoneticDictionary[phono] = {}
self.phoneticDictionary[phono][word] = 1
self.name = "metaphone"
tFinish = int(time.time() * 1000)
self.stats['runtime'] += tFinish - self.timeStart
def max_sound_like(self,word):
"""
Find all the words that are likely to be mistakes from the user not knowing how to spell it but knowing how it sounds.
"""
meta=metaphone(word)
rewords=[]
if meta in self.learned:
words=sorted(self.learned[meta].items(),key=operator.itemgetter(1),reverse=1)
if word not in [i[0] for i in words]:
if len(words) == 1:
rewords.append(words[0][0])
else:
rewords+=[i[0] for i in words]
if len(rewords) > 0:
return rewords
else:
return False
def max_sound_like(self,word):
"""
Find all the words that are likely to be mistakes from the user not knowing how to spell it but knowing how it sounds.
"""
meta=metaphone(word)
rewords=[]
if meta in self.learned:
words=sorted(self.learned[meta].items(),key=operator.itemgetter(1),reverse=1)
if word not in [i[0] for i in words]:
if len(words) == 1:
rewords.append(words[0][0])
else:
rewords+=[i[0] for i in words]
if len(rewords) > 0:
return rewords
else:
return False
def findCorrections(self, typo):
GenericAlgorithm.findCorrections(self, typo)
self.timeStart = int(time.time() * 1000)
# pass
# else:
try:
phono = phonetics.metaphone(typo)
if self.phoneticDictionary[phono]:
for word in self.phoneticDictionary[phono].keys():
self.possibleSpellings[typo][word] = 1
except KeyError:
pass
tFinish = int(time.time() * 1000)
self.stats['runtime'] += tFinish - self.timeStart
def read(self):
connection_file = open(self._connection_file, 'r')
try:
qByUser = connection_file.read()
self._User_Data = json.loads(qByUser)
except ValueError:
print
'Decoding JSON has failed'
connection_file.close()
for index, val in enumerate(self._User_Data):
self._Metaphone_User_Data.append(metaphone(val))
To_Add = dict(zip(self._User_Data, self._Metaphone_User_Data))
for key, val in To_Add.items():
if key in self._User_Data:
print(val)
self._User_Data[key] = [self._User_Data[key], val]
with open(self._Output_File_Name, 'w') as outfile:
json.dump(self._User_Data, outfile, indent=4)
def searchString(qNom, qReg, dist, lng, lat, mode = 0):
qT = []
#pdb.set_trace()
if qNom != None:
regxN = re.compile(qNom, re.IGNORECASE)
regxV = re.compile(qVille, re.IGNORECASE)
q1 = {"$or": [ {"nom": {"$regex": regxN } } , {"municipal": {"$regex": regxV} } ]}
if mode == 1:
q1 = {"nomU": {"$regex": '.*' + scanName(qNom) + '.*'} }
if mode == 2:
phonetic=phonetics.metaphone(qNom)
q1 = {"nomP": {"$regex": '.*' + phonetic + '.*'} }
qT.append(q1)
if qReg != None:
q2 = {'region': qReg}
qT.append(q2)
if dist != None:
q3 = {"location": { "$near" : {"$geometry": { "type": "Point", "coordinates": [ lng , lat ] }, "$maxDistance": dist }}};
qT.append(q3)
return { "$and": qT }
def Load_learned(self):
"""
Load the metaphone array, and if it doesn't exist, create it.
"""
if len(self.learned) == 0:
if os.path.exists(self.guten_pickle):
with open(self.guten_pickle, 'rb') as infile:
self.learned=pickle.load(infile)
else:
if len(self.gutenburg) == 0:
self.Load_dict()
for word,times in self.gutenburg.items():
meta=metaphone(word.replace("'",""))
#add and up the frequency of the words
if meta not in self.learned:
self.learned[meta]={word:int(times)}
elif word not in self.learned[meta]:
self.learned[meta][word]=int(times)
if len(self.learned) > 0:
with open(self.guten_pickle, 'wb') as outfile:
pickle.dump(self.learned, outfile)
def Load_learned(self):
"""
Load the metaphone array, and if it doesn't exist, create it.
"""
if len(self.learned) == 0:
if os.path.exists(self.guten_pickle):
with open(self.guten_pickle, 'rb') as infile:
self.learned=pickle.load(infile)
else:
if len(self.gutenburg) == 0:
self.Load_dict()
for word,times in self.gutenburg.items():
meta=metaphone(word.replace("'",""))
#add and up the frequency of the words
if meta not in self.learned:
self.learned[meta]={word:int(times)}
elif word not in self.learned[meta]:
self.learned[meta][word]=int(times)
if len(self.learned) > 0:
with open(self.guten_pickle, 'wb') as outfile:
pickle.dump(self.learned, outfile)
async def on_message(self, message):
if isinstance(message.channel, discord.DMChannel) == False:
return
if message.author.id == self.user.id:
return
words = message.content.lower()
words = re.sub(r'([^\s\w]|_)+', '', words)
words = words.split()
metaphones = []
for word in words:
metaphones.append(phonetics.metaphone(word))
desired_platform_name = ''
pc_keywords = ['AN', 'ANTS', 'PK', 'STM']
xbox_keywords = ['SPKS', 'SP']
playstation_keywords = ['S', 'PLSTXN']
for left_word in metaphones:
for right_word in pc_keywords:
if self.doWordsMatch(left_word, right_word) == True:
desired_platform_name = 'PC'
break
if desired_platform_name != '':
break
for right_word in xbox_keywords:
if self.doWordsMatch(left_word, right_word) == True:
desired_platform_name = 'Xbox'
break
if desired_platform_name != '':
break
for right_word in playstation_keywords:
if self.doWordsMatch(left_word, right_word) == True:
desired_platform_name = 'PlayStation'
break
if desired_platform_name != '':
break
if desired_platform_name == '':
await message.channel.send(
'Sorry, I didn\'t understand which platform you meant. Try saying `PC`, `Xbox`, or `PlayStation`.'
)
return
for guild in client.guilds:
remove_roles = []
add_roles = []
for role in guild.roles:
if role.name == desired_platform_name:
add_roles.append(role)
elif role.name == 'Xbox' or role.name == 'PC' or role.name == 'PlayStation':
remove_roles.append(role)
member = guild.get_member(message.author.id)
if member == None:
continue
for role in remove_roles:
await member.remove_roles(role)
for role in add_roles:
await member.add_roles(role)
await message.channel.send(
'Ok, I\'ve set your platform to {0}. You can now access the Beacon Discord server\'s general channel.'
.format(desired_platform_name))
def phonetic_similarity(w1, w2):
w1 = w1.replace("'",'')
w2 = w2.replace("'", '')
# print(w1, w2)
return 0.7 * edit_distance(ph.metaphone(w1), ph.metaphone(w2)) + \
0.3 * edit_distance(ph.soundex(w1), ph.soundex(w2))
def saveRecet(param, self):
""" Save Recette data """
try:
if param.get("data"):
#pdb.set_trace()
obj = loads(param['data'][0])
imgURL = ""
if param.get("imgURL"):
imgURL = param['imgURL'][0]
#print(str(imgURL))
""" Save Recette data """
cookie = cherrypy.request.cookie
if localHost or checkSession(self, role = ['ADM','MEA']):
#if True:
coll = dataBase.recettes
oIngr = obj["ingr"]
oPrep = obj["prep"]
nomU = scanName(obj["nom"])
nomP = phonetics.metaphone(obj["nom"])
Cuser = getCurrentUser()
state = 1 if obj["state"] else 0
actTime = int(time.time() * 1000)
editData = ""
if param.get("editor"):
editData = param['editor'][0]
if obj["ID"] == "NEW": # Nouvelle recette
oID = ObjectId()
#doc = coll.insert({ '$set': {'nom': obj["nom"], 'nomU': nomU, 'nomP': nomP, "dateC": int(time.time() * 1000), "dateM": int(time.time() * 1000), 'temp': obj["temp"], 'port': obj["port"], 'cuis': obj["cuis"], 'cat': obj["cat"], 'url': obj["url"], "state": 1, 'ingr': oIngr, 'prep': oPrep } }, {"new":True} )
doc = coll.update({ '_id': oID}, { '$set': {'nom': obj["nom"], 'nomU': nomU, 'nomP': nomP, "dateC": actTime, "dateM": actTime, 'userID': Cuser, 'temp': obj["temp"], 'port': obj["port"], 'cuis': obj["cuis"], 'cat': obj["cat"], 'url': obj["url"], "state": state, 'imgURL': imgURL, 'ingr': oIngr, 'prep': oPrep, 'edit': editData } }, upsert=True )
else:
oldDoc = loads(getRecette({'data':[ obj["ID"] ]}, self))['rec'][0]
oID = ObjectId(obj["ID"])
doc = coll.update({ '_id': oID}, { '$set': {'nom': obj["nom"], 'nomU': nomU, 'nomP': nomP, "dateM": actTime, 'userID': Cuser, 'temp': obj["temp"], 'port': obj["port"], 'cuis': obj["cuis"], 'cat': obj["cat"], 'url': obj["url"], "state": state, 'imgURL': imgURL, 'ingr': oIngr, 'prep': oPrep, 'edit': editData } }, upsert=True )
#doc = coll.update_one({ '_id': oID}, { '$set': {'nom': obj["nom"], 'nomU': nomU, 'nomP': nomP, 'temp': obj["temp"], 'port': obj["port"], 'cuis': obj["cuis"], 'cat': obj["cat"], 'url': obj["url"], 'ingr': oIngr, 'prep': oPrep } }, upsert=True )
newDoc = loads(getRecette({'data':[ obj["ID"] ]}, self))['rec'][0]
obj={'time': actTime, 'userID': oldDoc['userID']}
for key in newDoc:
if key != "_id" and key != "hist" and key != "dateM" and key != "nomU" and key != "nomP":
#print(key + " = " + str(docs[0][key]))
if newDoc[key] != oldDoc[key]:
obj[key] = oldDoc[key]
if len(obj) > 2 and (actTime - oldDoc['dateM'] > 86400000 or oldDoc['userID'] != Cuser): # If modified add history
#pdb.set_trace()
doc = coll.update( { '_id': oID}, {'$push': {'hist': obj }}, upsert=True )
return dumps(doc)
else:
return ('{"n":0,"ok":0, "message": "S0062"}') # Check Session error
else:
return dumps({'ok': 0}) # No param
except Exception as ex:
return except_handler("saveRecet", ex)
def saveClub(param, self):
""" Save Club, courses and blocs data """
try:
if param.get("data"):
#pdb.set_trace()
obj = loads(param['data'][0])
def saveBlocs(tupC, Bids):
""" Save blocs data for the courses """
blocRes = []
coll = dataBase.blocs
def getBlocID():
docID = coll.find({}).sort("_id",-1).limit(1)
return int(docID[0]["_id"] + 1)
for bloc in oBlocs:
res=dict()
if len(str(bloc["_id"])) < 9 and int(bloc["_id"]) > 1000000: # Not ObjectID and new attributed bloc ID
res["oldID"] = bloc["_id"]
bloc["_id"] = ObjectId() #getBlocID()
res["newID"] = str(bloc["_id"])
for y in tupC:
if bloc["PARCOURS_ID"] in y:
bloc["PARCOURS_ID"] = y[1] # Replace PARCOURS_ID by res["newID"] attributed
else:
bloc["_id"] = getID(str(bloc["_id"]))
if bloc["_id"] in Bids:
Bids.remove(bloc["_id"])
#print("save id " + str(bloc["_id"]) + " PARCOURS_ID " + str(bloc["PARCOURS_ID"]))
doc = coll.update({ '_id': bloc["_id"]}, { '$set': {'PARCOURS_ID': bloc["PARCOURS_ID"], 'Bloc': bloc["Bloc"], 'T1': bloc["T1"], 'T2': bloc["T2"], 'T3': bloc["T3"], 'T4': bloc["T4"], 'T5': bloc["T5"], 'T6': bloc["T6"], 'T7': bloc["T7"], 'T8': bloc["T8"], 'T9': bloc["T9"], 'T10': bloc["T10"], 'T11': bloc["T11"], 'T12': bloc["T12"], 'T13': bloc["T13"], 'T14': bloc["T14"], 'T15': bloc["T15"], 'T16': bloc["T16"], 'T17': bloc["T17"], 'T18': bloc["T18"], 'Aller': bloc["Aller"], 'Retour': bloc["Retour"], 'Total': bloc["Total"], 'Eval': bloc["Eval"], 'Slope': bloc["Slope"] } }, upsert=True )
res["result"]=doc
res["result"]["_id"] = bloc["_id"]
blocRes.append(res)
docs = coll.remove({"_id": {"$in": Bids } })
return blocRes, Bids
def saveCourses(clubID, tupC, Pids):
""" Save courses data for the Club """
courseRes = []
coll = dataBase.parcours
def getCourseID():
docID = coll.find({}).sort("_id",-1).limit(1)
return int(docID[0]["_id"] + 1)
def removeCourse(Pids):
collB = dataBase.blocs
docs = coll.remove({"_id": {"$in": Pids } }) # Remove Courses
docs = collB.remove({"PARCOURS_ID": {"$in": Pids } }) # Remove Bloc Courses
collG = dataBase.golfGPS
docs = collG.remove({"Parcours_id": {"$in": Pids } }) # Remove GPS Courses À TESTER
return
for parc in oCourses:
res=dict()
if parc["_id"] > 1000000:
res["oldID"] = parc["_id"]
parc["_id"] = getCourseID()
res["newID"] = parc["_id"]
tupC = tupC,(res["oldID"],res["newID"])
#removeBloc(parc["_id"])
#print("save courses " + str(parc["_id"]))
doc = coll.update({ '_id': parc["_id"]}, { '$set': {'CLUB_ID': parc["CLUB_ID"], 'POINTS': parc["POINTS"], 'PARCOURS': parc["PARCOURS"], 'DEPUIS': parc["DEPUIS"], 'TROUS': parc["TROUS"], 'NORMALE': parc["NORMALE"], 'VERGES': parc["VERGES"], 'GPS': parc["GPS"] } }, upsert=True )
res["result"]=doc
res["result"]["_id"] = parc["_id"]
courseRes.append(res)
if parc["_id"] in Pids:
Pids.remove(parc["_id"])
if len(Pids) > 0:
removeCourse(Pids)
return courseRes, tupC, Pids
#[{'_id': '39', 'CLUB_ID': 47, 'POINTS': '24', 'PARCOURS': '', 'DEPUIS': '1990', 'TROUS': '18', 'NORMALE': '72', 'VERGES': '6322', 'GPS': True}, {'_id': 61, 'CLUB_ID': 47, 'POINTS': 'E', 'PARCOURS': '', 'DEPUIS': 0, 'TROUS': 9, 'NORMALE': 27, 'VERGES': 815, 'GPS': False}]
""" Save Club data """
if localHost or checkSession(self, role = ['ADM','MEA']):
#if True:
coll = dataBase.club
def getClubID():
docID = coll.find({}).sort("_id",-1).limit(1)
return int(docID[0]["_id"] + 1)
tupC = (0,0),(0,0) # For new PARCOURS_ID in blocs
oClub = obj["club"]
oCourses = obj["course"]
if 'blocs' in obj:
oBlocs = obj["blocs"]
#Postal code
cp = oClub["codp"]
cp = cp.upper()
cp = re.sub(r" ", "", cp)
cps = cp
matchObj = re.match("^(?!.*[DFIOQU])[A-VXY][0-9][A-Z]●?[0-9][A-Z][0-9]$" ,cp)
if (matchObj):
cps = cp[0:3] + " " + cp[3:6]
clubID = oClub["ID"]
if clubID > 1000000: # New club
clubID = getClubID()
nomU = scanName(oClub["name"])
nomP = phonetics.metaphone(oClub["name"])
doc = coll.update({ '_id': clubID}, { '$set': {'nom': oClub["name"], 'nomU': nomU, 'nomP': nomP, 'prive': oClub["prive"], 'adresse': oClub["addr"], 'municipal': oClub["ville"], 'codepostal': cp, 'codepostal2': cps, 'url_club': oClub["urlc"], 'url_ville': oClub["urlv"], 'telephone': oClub["tel1"], 'telephone2': oClub["tel2"], 'telephone3': oClub["tel3"], 'email': oClub["email"], 'region': oClub["region"], 'latitude': oClub["lat"], 'longitude': oClub["lng"] } }, upsert=True )
Pids = getCourseColl(clubID)
Bids = getBlocColl(Pids)
courseRes, tupC, cRem = saveCourses(clubID, tupC, Pids)
if 'oBlocs' in locals():
blocRes, bRem = saveBlocs(tupC, Bids)
else:
blocRes = []
bRem = []
upd=coll.update({'_id':clubID}, {'$set':{"courses": oCourses, "location": {'type': "Point", 'coordinates': [ oClub["lng"], oClub["lat"] ]} }});
doc["courses"] = courseRes
doc["blocs"] = blocRes
doc["removedC"] = cRem
doc["removedB"] = bRem
return dumps(doc)
else:
return ('{"n":0,"ok":0, "message": "S0062"}') # Check Session error
else:
return dumps({'ok': 0}) # No param
except Exception as ex:
return except_handler("saveClub", ex)
def metaphone_fuzzy_match(x,
against,
strategy=MatchStrategy.PARTIAL_TOKEN_SORT_RATIO):
return fuzzy_match(phonetics.metaphone(x), phonetics.metaphone(against),
strategy)
def getPhoneticsRatioMorada(str1, str2): return fuzz.ratio(phonetics.metaphone(str1),phonetics.metaphone(str2))
def phonetic_match(self, text_a, text_b):
return phonetics.metaphone(text_a) == phonetics.metaphone(text_b)
def unique_list(l):
ulist = []
[ulist.append(x.upper()) for x in re.findall(r'\w+', l) if (x.upper() not in ulist) ]
return ulist
k=0
nodes=dict()
file = open('paths.txt', 'r')
data = file.readlines()
for line in data:
chars = [char for char in line.split(' | ') if len(char)]
for i in range(0,len(chars)):
nodes[chars[i].strip()]=[k+i]
nodes[chars[i].strip()].append(ph.metaphone(str(unique_list(unidecode((chars[i]).strip())))))
k=k+len(chars)
print k
file.close()
for f in range(1,16):
file = open('train/train'+ str(f)+'.txt', 'r')
data = file.readlines()
for line in data:
chars = [char for char in line.split(' | ') if len(char)]
nodes[chars[0].strip()]=[k]
nodes[chars[0].strip()].append(ph.metaphone(str(unique_list(unidecode((chars[0]).strip())))))
nodes[chars[1].strip()]=[k+1]
nodes[chars[1].strip()].append(ph.metaphone(str(unique_list(unidecode((chars[1]).strip())))))
k=k+2
