approximative POS processing

parsers/en_constants.py

 string_values = {
 	"ety":"Etymology",
-	"ipa":"Pronunciation",
+	"pro":"Pronunciation",
 	"en":"English",
 	"fr":"French",
 	"t_ipa":"IPA", #template for transcription
 	"t_snd":"audio", #template for audio
-	"t_acc":"a" #template for accents
+	"t_acc":"a", #template for accents
+	"POS": { #https://en.wiktionary.org/wiki/Wiktionary:POS
+		"Adjective":"Adj",
+		"Adverb":"Adv",
+		"Ambiposition":"Ambip",
+		"Article":"Art",
+		"Circumposition":"Circump",
+		"Classifier":"Class",
+		"Conjunction":"Conj",
+		"Contraction":"Cont",
+		"Counter":"Count",
+		"Determiner":"Det",
+		"Ideophone":"Ideophone",
+		"Interjection":"Interj",
+		"Noun":"N",
+		"Numeral":"Num",
+		"Participle":"Part",
+		"Particle":"Particle",
+		"Postposition":"Postp",
+		"Preposition":"Prep",
+		"Pronoun":"Pro",
+		"Proper noun":"NP",
+		"Verb":"V" # TODO: compléter
+	}
 }

parsers/en_en.py

@@ -4,6 +4,8 @@ from pronunciation import Pronunciation
 
 from parsers.en_constants import string_values
 
+debugEty = 0
+
 class En_en_straktor(Wikstraktor):
 	def __init__(self):
 		super().__init__()
@@ -40,6 +42,15 @@ class En_en_straktor(Wikstraktor):
 		print(pronunciations[0], pronunciations[1])
 		return pronunciations
 
+	def process_etymology(self, etyContent):
+		global debugEty
+		debugEty += 1
+		return "Etymology" + str(debugEty)
+
+	def process_senses(self, sensesContent):
+		import random as r
+		return "Cool"+r.choice(['a', 'b', 'c', 'd', 'e', 'f', 'g'])
+
 if __name__ == "__main__":
 	ensk = En_en_straktor()
 	print(ensk.fetch("test"), "entries added")

wikstraktor.py

@@ -9,14 +9,20 @@ class Entry:
 	def __init__(self, lemma):
 		self.lemma = lemma
 
-	def set_pronunciation(self, pron):
+	def set_pronunciations(self, pron):
 		if isinstance(pron, Pronunciation):
-			self.pronunciation = pron
+			self.pronunciations = pron
 		else:
 			raise ValueError(f"Entry.set_pronunciation: {pron} is not a Pronunciation object ({pron.__class__.__name__}).")
 
+	def set_POS(self, pos):
+		self.pos = pos
+
 	def __str__(self):
-		res = f"{self.lemma} ({self.cat})"
+		res = f"{self.lemma} ({self.pos})\n"
+		for p in self.pronunciations:
+			res += f"{str(p)}\n"
+		return res
 
 class ParserContext:
 	def __init__(self, entry):
@@ -30,8 +36,8 @@ class ParserContext:
 			res = self.context[-1]["wiki"].level
 		return res
 
-	def push(self, wiki_context, entry_context=None):
-		self.context.append({"wiki":wiki_context, "entry_info":entry_context})
+	def push(self, wiki_context):
+		self.context.append({"wiki":wiki_context})
 
 	def pop(self):
 		return self.context.pop()
@@ -42,22 +48,22 @@ class ParserContext:
 		else:
 			self.context[-1]['wiki'] = wiki_context
 
-	def set_top_entry_info(self, entry_context):
+	def set_top_entry_info(self, key, entry_context):
 		if len(self.context) == 0:
 			raise ValueError(f"Trying to set up entry info ({entry_context}), in an empty parserContext.")
 		else:
-			self.context[-1]['entry_info'] = entry_context
+			self.context[-1][key] = entry_context
 
 	def create_entry(self):
 		res = Entry(self.lemma)
 		for l in self.context:
-			if l['entry_info'] == None:
-				pass
-			elif l['entry_info'].__class__.__name__ == "Pronunciation":
-				res.set_pronunciation(l['entry_info'])
-			else:
-				# TODO: Ajouter les autres types
-				pass
+			if l['pro'] != None:
+				res.set_pronunciations(l['entry_info'])
+			if l['ety'] != None:
+				pass #On ignore l'étymologie pour le moment
+			if l['POS'] != None:
+				res.set_pos(l['POS'])
+			# TODO: Ajouter les autres types
 		return res
 
 	def debug_top(self):
@@ -65,7 +71,13 @@ class ParserContext:
 		if len(self.context) == 0 :
 			res += "0"
 		else:
-			res += f"{len(self.context)}, {self.context[-1]['wiki'].level*'#'} {self.context[-1]['wiki'].title} / {str(self.context[-1]['entry_info'])}"
+			info = ""
+			for k,v in self.context[-1].items():
+				if k != 'wiki':
+					if info != "":
+						info += "\n\t\t\t"
+					info += f"{k} → {str(v)}"
+			res += f"{len(self.context)*'='} {self.context[-1]['wiki'].level*'#'} {self.context[-1]['wiki'].title} / {info}"
 		return res
 
 
@@ -125,8 +137,13 @@ class Wikstraktor:
 					while self.parserContext.get_level() > s.level:
 						self.parserContext.pop()
 					self.parserContext.set_top_wiki(s)
-				if s.title == self.constants['ipa']:
-					self.parserContext.set_top_entry_info(self.process_pronunciation(self.wtp.parse(s.contents)))
+				if s.title == self.constants['pro']:
+					self.parserContext.set_top_entry_info('pro', self.process_pronunciation(self.wtp.parse(s.contents)))
+				elif self.constants['ety'] in s.title:
+					self.parserContext.set_top_entry_info('ety', self.process_etymology(self.wtp.parse(s.contents)))
+				elif s.title in self.constants['POS'].keys():
+					self.parserContext.set_top_entry_info('POS', self.constants['POS'][s.title])
+					self.parserContext.set_top_entry_info('senses', self.process_senses(self.wtp.parse(s.contents)))
 			print(self.parserContext.debug_top())
 		print("ok")
 
@@ -139,8 +156,8 @@ class Wikstraktor:
 
 if __name__ == "__main__":
 	e = Wikstraktor.get_instance('en', "en")
-	print(e.get_file_url("File:LL-Q1860 (eng)-Nattes à chat----parent.wav"))
-	print(e.get_file_url("File:LL-Q1860 (eng)-Nattes à chat-parent.wav"))
+	# print(e.get_file_url("File:LL-Q1860 (eng)-Nattes à chat----parent.wav"))
+	# print(e.get_file_url("File:LL-Q1860 (eng)-Nattes à chat-parent.wav"))
 	print(e.fetch("test"), "entries added")
 	# site = pywikibot.Site(f'wiktionary:en')
 	# p = pywikibot.FilePage(site, "File:LL-Q1860 (eng)-Nattes à chat----parent.wav")