Copiate nella cartella “testi” la cartella “UD_Coptic-Scriptorium-master” scaricabile in formato compresso da questo link. <code python ud_explorer.py> # -*- coding: utf-8 -*- #Copyright 2021 P. Milizia CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/) import re import glob import sys

#CLASSE PYTHON PER LA LETTURA DI UN TREEBANK UD class UD:

def __init__(self, data):
	self.data=self.add_sent_id(data)
	self.tokens=self.create_tokens(self.data)
	self.sentences=self.create_sentences(self.tokens)

#aggiunge il campo sent_id
def add_sent_id(self, text):
	sid_expr=re.compile('(?<=sent_id\s=\s).*')
	text=re.split('\n',text)
	output=''
	sid=''
	for line in text:
		found=re.search(sid_expr,line)
		if found != None:
			sid=found.group()
		if line !='' and line[0] != '#':
			line = line+'\t'+sid
		output += line+'\n'
	return output

#crea la lista dei tokens
def create_tokens(self, data):
	expr=re.compile('\n([^#].*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*)')
	tokens = re.findall(expr, data)
	for i in range(len(tokens)):
		tokens[i]=list(tokens[i])
		for ii in (5,9):
			tokens[i][ii]=re.split('\|',tokens[i][ii])
		try:
			tokens[i][0]=int(tokens[i][0])
		except ValueError:
			pass
		try:
			tokens[i][6]=int(tokens[i][6])
		except ValueError:
			pass
	return tokens

#crea il dizionario delle frasi
def create_sentences(self, tokens):
	sentences={}
	sid=''
	for t in tokens:
		if t[10] != sid:
			sid=t[10]
			sentences[sid]=['root']
		if type(t[0])==int:
			tt=t[:]
			sentences[sid].append(tt)
	return sentences

def parent_of(self, occurrence):
	x=self.sentences[occurrence[10]][occurrence[0]]
	return self.sentences[x[10]][x[6]]

def grandparent_of(self, occurrence):
	return self.parent_of(self.parent_of(occurrence))

def subsequent_of(self, occurrence):
	try:
		outp=self.sentences[occurrence[10]][occurrence[0]+1]
	except IndexError:
		outp=None
	return outp

def precedent_of(self, occurrence):
	try:
		outp=self.sentences[occurrence[10]][occurrence[0]-1]
	except IndexError:
		outp=None
	except TypeError:
		outp=None
	return outp
	
def children_of(self,occurrence):
	x=self.sentences[occurrence[10]][occurrence[0]]
	return [t for t in self.sentences[occurrence[10]][1:] if self.parent_of(t)==x]

def ancestors_of(self, occurrence):
	x=self.sentences[occurrence[10]][occurrence[0]]
	output = [x]
	while x != 'root':
		y=self.parent_of(x)
		output.append(y)
		x=y
	return output

def get_sentence(self, x):
	return [j[1] for j in self.sentences[x][1:]]

#PREPARAZIONE DEI DATI PER LA CLASSE

#lettura file directory_name='testi/UD_Coptic-Scriptorium-master' path = directory_name+'/*conllu' files=glob.glob(path) data='' for filepath in files:

with open(filepath, 'r') as file:
	file_data=file.read()
	data+=file_data

#ordina i file e crea una variabile text_list con l'elenco dei testi data=data.split('# newdoc ')[1:] data.sort() data='# newdoc '+'# newdoc '.join(data) text_list=re.findall('#\snewdoc\s.*', data)

#ESEMPIO DI UTILIZZO

#trova tutte le occorrenze di 'ⲙⲙⲟ' e di 'ⲛ' come marca dell'oggetto diretto #alle seguenti condizioni: #1) che la frase sia al passato perfettivo positivo #2) che almeno un elemento sia interposto tra verbo e preposizione

coptic=UD(data)

found_tokens=[]

def is_past(o):

answer = False
for child in coptic.children_of(o):
	if child[1]=='ⲁ' and child[3]=='AUX':
		answer = True
		break
return answer

for token in coptic.tokens:

if (token[1] == 'ⲙⲙⲟ' or token[1] == 'ⲛ') and token[7]=='case':
	try:
		regens = coptic.grandparent_of(token)
		noun_pronoun = coptic.parent_of(token)
		if noun_pronoun[7]=='obj' and is_past(regens) and (int(token[0]) - int(regens[0]))>1:
			found_tokens.append(token)
	except:
		pass

<\code>