updated parser Extract() commands function

- parser Extract() commands() now returns a single list
- parser Extract() commands now allows quotes to define keywords with spaces in them
- updated example for parser Extract() commands
- updated formatting and tabulation for certain files

Author: sedthh

examples/example_chatbot_1.py

@@ -15,8 +15,8 @@
 	order			= {
 		"pizza"			: [{"stem":"pizza","wordclass":"noun"}],
 		"cheese"		: [{"stem":"sajt","wordclass":"noun"}],
-		"pepperoni"	: [{"stem":"szalámi","wordclass":"noun"}],
-		"pineapple"	: [{"stem":"ananász","wordclass":"noun"}],
+		"pepperoni"		: [{"stem":"szalámi","wordclass":"noun"}],
+		"pineapple"		: [{"stem":"ananász","wordclass":"noun"}],
 	}
 	order_match		= parser.Intents(order).match_set(user_text)
 

examples/example_chatbot_5.py

@@ -12,10 +12,10 @@
 
 	###
 
-	tone				= entities.tone()
-	tone_match	= parser.Intents(tone).match_best(user_text,1) # match_best
-	common		= entities.common()
-	common_match= parser.Intents(common).match_set(user_text)
+	tone			= entities.tone()
+	tone_match		= parser.Intents(tone).match_best(user_text,1) # match_best
+	common			= entities.common()
+	common_match	= parser.Intents(common).match_set(user_text)
 
 	if 'formal' in tone_match:
 		if 'profanity' in common_match:

examples/example_chatbot_6.py

@@ -8,19 +8,19 @@
 
 if __name__ == "__main__":
 
-	user_text		= '/echo visszhang teszt'
+	user_text		= '/echo "visszhang teszt"'
 
 	###
 
 	info			= parser.Extract(user_text) # /echo command
-	commands	= info.commands()
+	commands		= info.commands()
 	func			= commands[0]
-	args			= commands[1]	# list
+	args			= commands[1]
 
 	if func:
 		if func == 'ping':
 			print('pong')
 		elif func == 'echo':
-			print(' '.join(args))
+			print(args)
 	else:
 		print('Parancs nélküli üzenet') # nem íródik ki

examples/example_chatbot_7.py

@@ -15,8 +15,8 @@
 	order			= {
 		"pizza"			: [{"stem":"pizza","wordclass":"noun"}],
 		"cheese"		: [{"stem":"sajt","wordclass":"noun"}],
-		"pepperoni"	: [{"stem":"szalámi","wordclass":"noun"}],
-		"pineapple"	: [{"stem":"ananász","wordclass":"noun"}],
+		"pepperoni"		: [{"stem":"szalámi","wordclass":"noun"}],
+		"pineapple"		: [{"stem":"ananász","wordclass":"noun"}],
 	}
 	order_match		= parser.Intents(order).match_set(user_text)
 

examples/example_news.py

@@ -14,7 +14,7 @@
 
 	important		= {
 		"lottery"		: [{"stem":"lottó","wordclass":"noun"}],
-		"winning"	: [{"stem":"nyer","wordclass":"verb"},{"stem":"nyertes","wordclass":"noun"}],
+		"winning"		: [{"stem":"nyer","wordclass":"verb"},{"stem":"nyertes","wordclass":"noun"}],
 		"losing"		: [{"stem":"veszt","wordclass":"verb"},{"stem":"veszít","wordclass":"verb"},{"stem":"vesztes","wordclass":"noun"}],
 	}
 	important_match	= parser.Intents(important).match(article)

examples/example_wiki_intents.py

@@ -38,15 +38,15 @@
 	print(busz_test.match("Lassan beérünk az autóbusszal a buszpályaudvarra."))
 
 	hasonul_intents	= {
-		"enni"		: [{"stem":"esz","wordclass":"verb","match_stem":False},{"stem":"en","wordclass":"verb","match_stem":False}]
+		"enni"			: [{"stem":"esz","wordclass":"verb","match_stem":False},{"stem":"en","wordclass":"verb","match_stem":False}]
 	}
 	hasonul_test	= parser.Intents(hasonul_intents)
 	print(hasonul_test.match("Tőmorfémák: esz, en."))		# nem veszi figyelembe
 	print(hasonul_test.match("Eszel valamit?"))
 	print(hasonul_test.match("Azt nem lehet megenni."))
 
 	egyutt_intents	= {
-		"jo_ido"	: [{"stem":"jó","wordclass":"adjective",
+		"jo_ido"		: [{"stem":"jó","wordclass":"adjective",
 						"inc":[{"stem":"idő","wordclass":"noun","affix":["járás"]},{"stem":"meleg","wordclass":"adjective"}]}]
 	}
 	egyutt_test		= parser.Intents(egyutt_intents)
@@ -59,7 +59,7 @@
 	print(egyutt_test.match("Jó meleg az időjárás."))		# dupla pont
 
 	kulon_intents	= {
-		"jobb_ido"	: [{"stem":"jó","wordclass":"adjective",
+		"jobb_ido"		: [{"stem":"jó","wordclass":"adjective",
 						"inc":[{"stem":"idő","wordclass":"noun","affix":["járás"]},{"stem":"meleg","wordclass":"adjective"}],
 						"exc":[{"stem":"este","wordclass":"noun"}]}]
 	}
@@ -70,8 +70,8 @@
 	print(kulon_test.match("Jó meleg esténk van!"))			# szintén nem veszi figyelembe
 
 	fals_pozitiv	= {
-		"megszerel"	: [{"stem":"szerel","wordclass":"verb"}],
-		"hibasan"	: [{"stem":"alma","wordclass":"noun"}],
+		"megszerel"		: [{"stem":"szerel","wordclass":"verb"}],
+		"hibasan"		: [{"stem":"alma","wordclass":"noun"}],
 	}
 	hibas_test		= parser.Intents(fals_pozitiv)
 	print(hibas_test.match("Gyönyörű dolog a szerelem"))	# elfogadja hibásan

lara/parser.py

@@ -956,7 +956,7 @@ def currencies(self,normalize=True,convert=True):
 		return []
 
 	def _currencies_fallback(self):
-		dates		= [item.replace('-',':') for item in self.dates()]
+		dates	= [item.replace('-',':') for item in self.dates()]
 		number	= [str(item) for item in self.numbers()]
 		against	= [item[-2] if (len(item)>2 and item[-1]==0 and item[-2]=='.') else item for item in number]
 		ignore	= []
@@ -977,15 +977,39 @@ def _currencies_fallback(self):
 					okay.append(item)
 		return okay
 
-	# extract commands and arguments from text: "/help lara" will return ('help',['lara'])
+	# extract commands and arguments from text: /help "about lara" will return ['help','about lara']
 	def commands(self):
-		if self.text and self.text[0] == '/':
-			commands				= (lara.nlp.trim(str(self.text[1:]))).split(" ")
-			if len(commands)>1:
-				return (commands[0],commands[1:])
-			else:
-				return (commands[0],[])
-		return ('',[])
+		result	= []
+		if len(self.text)>1 and self.text[0] in ('/','\\'):
+			quote	= ''
+			keyword	= ''
+			for char in self.text[1:]:
+				if char in (' ','"',"'"):
+					if char==' ':
+						if quote:
+							keyword	+= ' '
+						else:
+							if keyword:
+								result.append(keyword)
+								keyword	= ''
+					elif char in ('"',"'"):
+						if not quote:
+							if keyword:
+								result.append(keyword)
+								keyword	= ''
+							quote	= char
+						elif quote==char:
+							if keyword:
+								result.append(keyword)
+								keyword	= ''
+							quote	= ''
+						else:
+							keyword	+= char
+				else:
+					keyword	+= char
+			if keyword:
+				result.append(keyword)
+		return result
 
 	# extract list of emojis from text via https://gist.github.com/naotokui/
 	def emojis(self):
@@ -1065,9 +1089,9 @@ def timestamps(self,current=False):
 		dates			= self.dates(False)
 		relative		= self.relative_dates(False,c_relative)
 		times			= self.times(False,True,c_times)
-		dates_pos	= []
-		relative_pos= []
-		times_pos	= []
+		dates_pos		= []
+		relative_pos	= []
+		times_pos		= []
 		for item in dates:
 			for match in _re.finditer(r'\b'+re.escape(item), re.IGNORECASE, self.ntext):
 				dates_pos.append(match.span()[0])
@@ -1083,13 +1107,13 @@ def timestamps(self,current=False):
 		dates			= self.dates()
 		relative		= self.relative_dates(True,c_relative)
 		times			= self.times(True,True,c_times)
-		results		= []
-		last_date	= ''
-		last_date_a= ''
-		last_time	= ''
-		dates_i		= 0
-		relative_i	= 0
-		times_i		= 0
+		results			= []
+		last_date		= ''
+		last_date_a		= ''
+		last_time		= ''
+		dates_i			= 0
+		relative_i		= 0
+		times_i			= 0
 		for i in range(max(dates_pos+relative_pos+times_pos)+1):
 			if i == dates_pos[dates_i]:
 				if last_date or last_time: