Legalo/Trans_tools
2
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Generalize tag translation using emojis heck yeah

Browse Source
This commit is contained in:
GManon
2022-12-25 23:24:37 -03:00
parent ab65f0349a
commit 9464ade313
2 changed files with 51 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
Auto Trans/Translator.py
View File

@ -1,9 +1,10 @@
#Translates the game using good ol fashioned google translator. Be sure to replace the dialogue code in the translator and the tags in es_tags
#Also this breaks a tiny bit if the dialogue contains \n, but oh well. I don't want to open that can of worms.
#Also by break I mean that it may leave some text in english, is not that it will implode... I think
# Translates the game using good ol fashioned google translator. Be sure to replace the dialogue code in the translator.
# Also this breaks a tiny bit if the dialogue contains \n, but oh well. I don't want to open that can of worms.
# Also by break I mean that it may leave some text in english, is not that it will implode... I think.
import csv
import os
import re
from colorama import init
from colorama import Fore
from googletrans import Translator
@ -16,12 +17,30 @@ init()
times = []
# Good ol google doesn't know what renpy tags are, so it translates them. This was the cheapest solution.
es_tags = {
"{rápido}":"{fast}",
"{w =": "{w=",
"{alfa":"{alpha"
}
def translate(string):
# Split the string by it's tags
tokens = re.findall(r'\b\w+\b|{[^}]*}|[^\w\s]|\s+', string)
# We encode this bitch up so that google trans doesn't botch the tags
to_restore = []
for idx, token in enumerate(tokens):
if token[0] == "{":
to_restore.append(token)
# Emojis aren't touched by the translator and retain their position 😎
tokens[idx] = "🔠"
encoded_string = "".join(tokens)
# Translate the encoded string
trans = translator.translate(encoded_string, dest='es')
temp = list(trans.text)
# Restore the original tags
for tag in to_restore:
for idx, char in enumerate(temp):
if char == "🔠":
temp[idx] = tag
break
return "".join(temp)
def avrg(nums):
average = sum(nums)/len(nums)
@ -32,6 +51,7 @@ with open('original.csv', 'r', encoding='utf-8') as input_file, \
open('trans.csv', 'w', encoding='utf-8',newline='') as output_file:
length = len(input_file.readlines())
# Wacky hacks to calculate the time left
input_file.seek(0)
# Create readers and writers for the input and output files
@ -43,13 +63,10 @@ with open('original.csv', 'r', encoding='utf-8') as input_file, \
start_time = datetime.now().replace(microsecond=0)
try:
# Translate the string
translation = translator.translate(row[0], dest='es')
translation = translate(row[0])
for tag_es, tag in es_tags.items():
translation.text = translation.text.replace(tag_es,tag)
#Hope this works for escaping lol
translation.text = translation.text.replace('"',r'\"')
#Hope this works for escaping, lol
translation = translation.replace('"',r'\"')
except Exception as e:
print(f'{Fore.RESET}An error occurred: {e}')