Restructuration factorisation de la pile (ParserContext)

parsers/en_en.py

 #!/usr/bin/env python3
 from wikstraktor import Wikstraktor
-from parsers.en_constants import string_values
 from pronunciation import Pronunciation
 
-def debugC(c, e):
-	res = "Context: "
-	if len(c) == 0 :
-		res += "0"
-	else:
-		res += f"{len(c)}, {c[-1].level*'#'} {c[-1].title}"
-	res += " / "
-	if len(e) == 0:
-		res += "0"
-	else:
-		res += f"{len(e)}, {(len(e) - 1)*'='} {e[-1]}"
-	return res
+from parsers.en_constants import string_values
 
 class En_en_straktor(Wikstraktor):
 	def __init__(self):
@@ -52,24 +40,6 @@ class En_en_straktor(Wikstraktor):
 		print(pronunciations[0], pronunciations[1])
 		return pronunciations
 
-
-	def parse(self, entry, sections):
-		wiki_context = []
-		entry_context = [] #todo récupérer les infos section par section et créer des entrées avec les infos des niveaux supérieurs.
-		for s in sections:
-			if s.title != None :
-				#handle wiki context
-				if len(wiki_context) == 0 or s.level > wiki_context[-1].level:
-					wiki_context.append(s)
-				else:
-					while len(wiki_context)>0 and s.level < wiki_context[-1].level:
-						wiki_context.pop()
-					wiki_context[-1] = s
-				if s.title == self.constants['ipa']:
-					entry_context.append(self.process_pronunciation(self.wtp.parse(s.contents)))
-			print(s.level, debugC(wiki_context, entry_context))
-		print("ok")
-
 if __name__ == "__main__":
 	ensk = En_en_straktor()
 	print(ensk.fetch("test"), "entries added")

wikstraktor.py

@@ -2,14 +2,73 @@
 import pywikibot
 import wikitextparser
 import importlib
+from pronunciation import Pronunciation
+
 
 class Entry:
 	def __init__(self, lemma):
 		self.lemma = lemma
 
+	def set_pronunciation(self, pron):
+		if isinstance(pron, Pronunciation):
+			self.pronunciation = pron
+		else:
+			raise ValueError(f"Entry.set_pronunciation: {pron} is not a Pronunciation object ({pron.__class__.__name__}).")
+
 	def __str__(self):
 		res = f"{self.lemma} ({self.cat})"
 
+class ParserContext:
+	def __init__(self, entry):
+		self.lemma = entry
+		self.context = []
+
+	def get_level(self):
+		if len(self.context) == 0:
+			res = -1
+		else:
+			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 pop(self):
+		return self.context.pop()
+
+	def set_top_wiki(self, wiki_context):
+		if len(self.context) == 0:
+			self.push(wiki_context)
+		else:
+			self.context[-1]['wiki'] = wiki_context
+
+	def set_top_entry_info(self, 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
+
+	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
+		return res
+
+	def debug_top(self):
+		res = "Context: "
+		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'])}"
+		return res
+
+
 class Wikstraktor:
 	@classmethod
 	def get_instance(cls, wiki_language, entry_language):
@@ -21,6 +80,12 @@ class Wikstraktor:
 			instance = None
 		return instance
 
+	def __init__(self):
+		self.entries = []
+		self.pwb = pywikibot
+		self.wtp = wikitextparser
+		self.parserContext = None
+
 	def get_file_url(self, file_page_name):
 		res = None
 		try:
@@ -30,11 +95,6 @@ class Wikstraktor:
 			print(f"{file_page_name} does not exist in {self.site}.")
 		return res
 
-	def __init__(self):
-		self.entries = []
-		self.pwb = pywikibot
-		self.wtp = wikitextparser
-
 	#retrieves the content of a page and processes it (adding the entries to the list of entries)
 	#returns the number of entries added
 	def fetch(self, graphy):
@@ -54,9 +114,21 @@ class Wikstraktor:
 				nb_entries_added = self.parse(page.title(), sections[i].sections)#self.wtp.parse(s.contents).sections)
 		return nb_entries_added
 
-	def parse(self):
-		#handled by subclass
-		return -1
+	def parse(self, entry, sections):
+		self.parserContext = ParserContext(entry)
+		for s in sections:
+			if s.title != None :
+				#handle wiki context
+				if self.parserContext.get_level() < s.level:
+					self.parserContext.push(s)
+				else:
+					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)))
+			print(self.parserContext.debug_top())
+		print("ok")
 
 	def __str__(self):
 		res = ""