以下のPythonコードは、指定された要件を満たすように設計されています。このコードは、入力として日本語のJSONファイルを受け取り、それを英語に翻訳し、翻訳されたJSONファイルを出力します。

まず、translate()関数を作成して、ChatGPT APIを使用して翻訳を行います。次に、メインの処理でJSONファイルを読み込み、指定された手順に従って翻訳を実行します。

pythonCopy code
import json
import openai

def translate(text, role="user"):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant that translates Japanese text to English."},
            {"role": role, "content": text}
        ]
    )
    return response.choices[0].message.content

def translate_json_file(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as f:
        data = json.load(f)

    title_translation_dict = {}

    # Translate page titles
    for page in data['pages']:
        translated_title = translate(page['title'])
        title_translation_dict[page['title']] = translated_title
        page['title'] = translated_title

    # Translate lines with translated titles replaced
    for page in data['pages']:
        translated_lines = []
        for line in page['lines']:
            for jp_title, en_title in title_translation_dict.items():
                line = line.replace(f"[{jp_title}]", f"[{en_title}]")
            translated_line = translate(line)
            translated_lines.append(translated_line)
        page['lines'] = translated_lines

    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

# Replace 'input.json' and 'output.json' with your desired file paths
translate_json_file('input.json', 'output.json')

このコードを実行する前に、openaiモジュールをインストールし、OpenAI APIキーを設定しておく必要があります。

bashCopy code
pip install openai

Pythonコード内でAPIキーを設定する方法は次のとおりです。

pythonCopy code
import openai

openai.api_key = "your_api_key_here"

APIキーを環境変数として設定することもできます。これを行うには、次のコマンドを実行してください（環境変数名は OPENAI_API_KEY です）。

bashCopy code
export OPENAI_API_KEY=your_api_key_here

このコードは、指定されたJSONファイルを翻訳し、翻訳されたテキストを含む新しいJSONファイルを出力します。ファイル名は、translate_json_file関数の引数として指定できます。

指定された要件に従って、API呼び出し回数を最小限に抑えるようにコードを修正しました。以下のコードでは、タイトルの翻訳時に一度に翻訳できるだけ翻訳し、ページの翻訳時にも一度に翻訳するようにしています。ただし、文字数制限に引っかかる場合は、適宜分割して翻訳します。

pythonCopy code
import json
import openai

MAX_TOKENS = 8000

def translate(text, role="user"):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant that translates Japanese text to English."},
            {"role": role, "content": text}
        ]
    )
    return response.choices[0].message.content

def translate_titles(title_list):
    translated_titles = []
    title_chunk = ""

    for title in title_list:
        if len(title_chunk) + len(title) + 1 < MAX_TOKENS:
            title_chunk += title + "\n"
        else:
            translated_chunk = translate(title_chunk, role="title_translation")
            translated_titles.extend(translated_chunk.split("\n")[:-1])
            title_chunk = title + "\n"

    if title_chunk:
        translated_chunk = translate(title_chunk, role="title_translation")
        translated_titles.extend(translated_chunk.split("\n")[:-1])

    return translated_titles

def translate_page(page_text):
    if len(page_text) <= MAX_TOKENS:
        return translate(page_text, role="page_translation")
    else:
        split_point = page_text.rfind("\n", 0, MAX_TOKENS)
        first_half = page_text[:split_point]
        second_half = page_text[split_point + 1:]
        return translate_page(first_half) + "\n" + translate_page(second_half)

def translate_json_file(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as f:
        data = json.load(f)

    title_translation_dict = {}

    # Translate page titles
    title_list = [page['title'] for page in data['pages']]
    translated_titles = translate_titles(title_list)

    for original_title, translated_title in zip(title_list, translated_titles):
        title_translation_dict[original_title] = translated_title

    for page, translated_title in zip(data['pages'], translated_titles):
        page['title'] = translated_title

    # Translate lines with translated titles replaced
    for page in data['pages']:
        page_text = "\n".join(page['lines'])

        for jp_title, en_title in title_translation_dict.items():
            page_text = page_text.replace(f"[{jp_title}]", f"[{en_title}]")

        translated_text = translate_page(page_text)
        page['lines'] = translated_text.split("\n")

    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

# Replace 'input.json' and 'output.json' with your desired file paths
translate_json_file('input.json', 'output.json')

このコードでは、タイトル翻訳用に translate_titles 関数を、ページ翻訳用に translate_page 関数を作成しています。

了解しました。以下のコードでは、aiohttpとasyncioを使って、ChatCompletionを非同期で並列処理するように変更しました。これにより、翻訳のパフォーマンスが向上するはずです。

まず、aiohttpとasyncioをインストールしてください。

bashCopy code
pip install aiohttp asyncio

次に、以下のコードを実行します。

pythonCopy code
import json
import asyncio
import aiohttp
import openai

MAX_TOKENS = 8000

async def async_translate(session, text, role="user"):
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {openai.api_key}"
    }

    data = {
        "model": "gpt-3.5-turbo",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant that translates Japanese text to English."},
            {"role": role, "content": text}
        ]
    }

    async with session.post("https://api.openai.com/v1/chat/completions", headers=headers, json=data) as resp:
        response = await resp.json()
        return response["choices"][0]["message"]["content"]

async def translate_titles(session, title_list):
    translated_titles = []
    title_chunk = ""

    for title in title_list:
        if len(title_chunk) + len(title) + 1 < MAX_TOKENS:
            title_chunk += title + "\n"
        else:
            translated_chunk = await async_translate(session, title_chunk, role="title_translation")
            translated_titles.extend(translated_chunk.split("\n")[:-1])
            title_chunk = title + "\n"

    if title_chunk:
        translated_chunk = await async_translate(session, title_chunk, role="title_translation")
        translated_titles.extend(translated_chunk.split("\n")[:-1])

    return translated_titles

async def translate_page(session, page_text):
    if len(page_text) <= MAX_TOKENS:
        return await async_translate(session, page_text, role="page_translation")
    else:
        split_point = page_text.rfind("\n", 0, MAX_TOKENS)
        first_half = page_text[:split_point]
        second_half = page_text[split_point + 1:]
        first_half_translated = await async_translate(session, first_half, role="page_translation")
        second_half_translated = await translate_page(session, second_half)
        return first_half_translated + "\n" + second_half_translated

async def translate_json_file(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as f:
        data = json.load(f)

    title_translation_dict = {}

    # Translate page titles
    title_list = [page['title'] for page in data['pages']]

    async with aiohttp.ClientSession() as session:
        translated_titles = await translate_titles(session, title_list)

        for original_title, translated_title in zip(title_list, translated_titles):
            title_translation_dict[original_title] = translated_title

        for page, translated_title in zip(data['pages'], translated_titles):
            page['title'] = translated_title

        # Translate lines with translated titles replaced
        for page in data['pages']:
            page_text = "\n".join(page['lines'])

            for jp_title, en_title in title_translation_dict.items():
                page_text = page_text.replace(f"[{jp_title}]", f"[{en_title}]")

            translated_text = await translate

My apologies for the incomplete response. Here is the complete code:

pythonCopy code
            translated_text = await translate_page(session, page_text)
            page['lines'] = translated_text.split("\n")

    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

# Replace 'input.json' and 'output.json' with your desired file paths
async def main():
    await translate_json_file('input.json', 'output.json')

asyncio.run(main())

In the updated code, we have defined the main function as asynchronous, and then use asyncio.run(main()) to run the async translate_json_file function. This way, the translation process takes advantage of asynchronous processing, which should improve the performance of the translation tasks.

了解しました。以下のコードでは、roleを常にsystemかuserに設定し、translate_pageの処理を並行して実行するように変更しました。

pythonCopy code
import json
import asyncio
import aiohttp
import openai

MAX_TOKENS = 8000

async def async_translate(session, text):
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {openai.api_key}"
    }

    data = {
        "model": "gpt-3.5-turbo",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant that translates Japanese text to English."},
            {"role": "user", "content": text}
        ]
    }

    async with session.post("https://api.openai.com/v1/chat/completions", headers=headers, json=data) as resp:
        response = await resp.json()
        return response["choices"][0]["message"]["content"]

async def translate_titles(session, title_list):
    translated_titles = []
    title_chunk = ""

    for title in title_list:
        if len(title_chunk) + len(title) + 1 < MAX_TOKENS:
            title_chunk += title + "\n"
        else:
            translated_chunk = await async_translate(session, title_chunk)
            translated_titles.extend(translated_chunk.split("\n")[:-1])
            title_chunk = title + "\n"

    if title_chunk:
        translated_chunk = await async_translate(session, title_chunk)
        translated_titles.extend(translated_chunk.split("\n")[:-1])

    return translated_titles

async def translate_page(session, page_text):
    if len(page_text) <= MAX_TOKENS:
        return await async_translate(session, page_text)
    else:
        split_point = page_text.rfind("\n", 0, MAX_TOKENS)
        first_half = page_text[:split_point]
        second_half = page_text[split_point + 1:]
        first_half_translated = await async_translate(session, first_half)
        second_half_translated = await translate_page(session, second_half)
        return first_half_translated + "\n" + second_half_translated

async def translate_json_file(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as f:
        data = json.load(f)

    title_translation_dict = {}

    # Translate page titles
    title_list = [page['title'] for page in data['pages']]

    async with aiohttp.ClientSession() as session:
        translated_titles = await translate_titles(session, title_list)

        for original_title, translated_title in zip(title_list, translated_titles):
            title_translation_dict[original_title] = translated_title

        for page, translated_title in zip(data['pages'], translated_titles):
            page['title'] = translated_title

        # Translate lines with translated titles replaced
        translation_tasks = []

        for page in data['pages']:
            page_text = "\n".join(page['lines'])

            for jp_title, en_title in title_translation_dict.items():
                page_text = page_text.replace(f"[{jp_title}]", f"[{en_title}]")

            translation_tasks.append(translate_page(session, page_text))

        translated_texts = await asyncio.gather(*translation_tasks)

        for page, translated_text in zip(data['pages'], translated_texts):
            page['lines'] = translated_text.split("\n")

    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

# Replace 'input

Here is the continuation of the code:

pythonCopy code
# Replace 'input.json' and 'output.json' with your desired file paths
async def main():
    await translate_json_file('input.json', 'output.json')

asyncio.run(main())

In this updated code, the translate_page tasks are executed concurrently using asyncio.gather. This should further improve the performance of the translation process.

To achieve this, we'll use the re module for handling regular expressions. Here's the modified async_translate function that replaces leading spaces/tabs/full width spaces with \s and newlines with \n before translation, and then reverts them back after translation:

pythonCopy code
import re

async def async_translate(session, text):
    # Replace leading spaces/tabs/full width spaces with \s
    text = re.sub(r'^([ \t　]+)', lambda m: '\\s' * len(m.group(1)), text, flags=re.MULTILINE)

    # Replace newlines with \n
    text = text.replace('\n', '\\n')

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {openai.api_key}"
    }

    data = {
        "model": "gpt-3.5-turbo",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant that translates Japanese text to English."},
            {"role": "user", "content": text}
        ]
    }

    async with session.post("https://api.openai.com/v1/chat/completions", headers=headers, json=data) as resp:
        response = await resp.json()
        translated_text = response["choices"][0]["message"]["content"]

    # Replace \n back to newline
    translated_text = translated_text.replace('\\n', '\n')

    # Replace \s back to spaces
    translated_text = re.sub(r'\\s', ' ', translated_text)

    return translated_text

Now, the async_translate function replaces the specified characters before sending the text for translation and reverts them back in the translated text.