170 lines
5.9 KiB
Python
170 lines
5.9 KiB
Python
import pandas as pd
|
|
from openai import OpenAI
|
|
import os
|
|
import re
|
|
import logging
|
|
from openai_api_key import api_key
|
|
from master_export2translate import transformar_texto
|
|
|
|
client = OpenAI(api_key=api_key())
|
|
|
|
# Diccionario de idiomas
|
|
IDIOMAS = {
|
|
1: ("English", "en"),
|
|
2: ("Portuguese", "pt"),
|
|
3: ("Spanish", "es"),
|
|
4: ("Russian", "ru"),
|
|
5: ("French", "fr"),
|
|
6: ("German", "de"),
|
|
}
|
|
|
|
|
|
def configurar_logger():
|
|
logger = logging.getLogger("translate_logger")
|
|
logger.setLevel(logging.DEBUG) # Cambiado a DEBUG para más información
|
|
fh = logging.FileHandler("translate_log.log", encoding="utf-8")
|
|
fh.setLevel(logging.DEBUG)
|
|
formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
|
|
fh.setFormatter(formatter)
|
|
logger.addHandler(fh)
|
|
return logger
|
|
|
|
|
|
logger = configurar_logger()
|
|
|
|
|
|
def mostrar_idiomas():
|
|
print("Selecciona el idioma de destino:")
|
|
for numero, (nombre, _) in IDIOMAS.items():
|
|
print(f"{numero}: {nombre}")
|
|
|
|
|
|
def translate_text(text, source_lang, target_lang):
|
|
logger.info(
|
|
f"Solicitando traducción de {source_lang} a {target_lang} para el texto: {text}"
|
|
)
|
|
response = client.chat.completions.create(
|
|
model="gpt-3.5-turbo",
|
|
messages=[
|
|
{"role": "system", "content": f"You are a translator."},
|
|
{
|
|
"role": "user",
|
|
"content": f"Translate the following text from {source_lang} to {target_lang} while preserving special fields like <> and <#>. This texts are for an HMI industrial machine: {text}",
|
|
},
|
|
],
|
|
max_tokens=150,
|
|
temperature=0.3,
|
|
)
|
|
translated_text = response.choices[0].message.content.strip()
|
|
logger.info(f"Respuesta recibida: {translated_text}")
|
|
return translated_text
|
|
|
|
|
|
def translate_batch(texts, source_lang, target_lang):
|
|
joined_text = "\n".join(texts)
|
|
logger.info(
|
|
f"Solicitando traducción de {source_lang} a {target_lang} para el lote de textos:\n{joined_text}"
|
|
)
|
|
response = client.chat.completions.create(
|
|
model="gpt-3.5-turbo",
|
|
messages=[
|
|
{"role": "system", "content": f"You are a translator."},
|
|
{
|
|
"role": "user",
|
|
"content": f"Translate the following texts from {source_lang} to {target_lang} while preserving special fields like <> and <#>:\n\n{joined_text}",
|
|
},
|
|
],
|
|
max_tokens=1500,
|
|
temperature=0.3,
|
|
)
|
|
translations = response.choices[0].message.content.strip().split("\n")
|
|
logger.info(f"Respuestas recibidas:\n{translations}")
|
|
return translations
|
|
|
|
|
|
def texto_requiere_traduccion(texto):
|
|
palabras = re.findall(r"\b\w{4,}\b", texto)
|
|
campos_especiales = re.findall(r"<.*?>", texto)
|
|
requiere_traduccion = len(palabras) > 0 or len(campos_especiales) != len(
|
|
re.findall(r"<#>", texto)
|
|
)
|
|
logger.debug(
|
|
f"Decisión de traducción para texto '{texto}': {'Sí' if requiere_traduccion else 'No'} (palabras > 3 letras: {len(palabras) > 0}, solo campos especiales: {len(campos_especiales) == len(re.findall(r'<#>', texto))})"
|
|
)
|
|
return requiere_traduccion
|
|
|
|
|
|
def main(file_path, target_lang_code, traducir_todo, batch_size=10):
|
|
df = pd.read_excel(file_path)
|
|
source_col = "it-IT"
|
|
target_col = f"{target_lang_code} Translated"
|
|
|
|
if target_col in df.columns and not traducir_todo:
|
|
df[target_col] = df[target_col]
|
|
else:
|
|
df[target_col] = None
|
|
|
|
texts_to_translate = []
|
|
indices_to_translate = []
|
|
|
|
if traducir_todo:
|
|
for index, text in df[source_col].astype(str).items():
|
|
processed_text = transformar_texto(text)
|
|
if texto_requiere_traduccion(processed_text):
|
|
texts_to_translate.append(text)
|
|
indices_to_translate.append(index)
|
|
else:
|
|
for index, text in (
|
|
df.loc[df[target_col].isnull(), source_col].astype(str).items()
|
|
):
|
|
processed_text = transformar_texto(text)
|
|
if texto_requiere_traduccion(processed_text):
|
|
texts_to_translate.append(text)
|
|
indices_to_translate.append(index)
|
|
|
|
num_texts = len(texts_to_translate)
|
|
logger.info(f"Número total de textos a traducir: {num_texts}")
|
|
|
|
translations = []
|
|
for start_idx in range(0, num_texts, batch_size):
|
|
end_idx = min(start_idx + batch_size, num_texts)
|
|
batch_texts = texts_to_translate[start_idx:end_idx]
|
|
batch_translations = translate_batch(batch_texts, "Italian", target_lang_code)
|
|
translations.extend(batch_translations)
|
|
|
|
logger.info(f"Número total de traducciones recibidas: {len(translations)}")
|
|
|
|
if len(translations) != len(indices_to_translate):
|
|
logger.warning(
|
|
f"Desajuste entre el número de traducciones ({len(translations)}) y el número de índices ({len(indices_to_translate)})"
|
|
)
|
|
|
|
for i, index in enumerate(indices_to_translate):
|
|
if i < len(translations):
|
|
df.at[index, target_col] = translations[i]
|
|
else:
|
|
logger.error(f"No hay traducción disponible para el índice {index}")
|
|
|
|
output_path = os.path.join(
|
|
os.path.dirname(file_path), "master_export2translate_translated.xlsx"
|
|
)
|
|
df.to_excel(output_path, index=False)
|
|
logger.info(f"Archivo traducido guardado en: {output_path}")
|
|
print(f"Archivo traducido guardado en: {output_path}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
batch_size = 10
|
|
translate_file = "master_export2translate.xlsx"
|
|
|
|
mostrar_idiomas()
|
|
seleccion_idioma = int(input("Introduce el número del idioma de destino: "))
|
|
if seleccion_idioma not in IDIOMAS:
|
|
print("Selección inválida.")
|
|
else:
|
|
_, target_lang_code = IDIOMAS[seleccion_idioma]
|
|
traducir_todo = (
|
|
input("¿Desea traducir todas las celdas (s/n)? ").strip().lower() == "s"
|
|
)
|
|
main(translate_file, target_lang_code, traducir_todo, batch_size)
|