Merge branch 'main' into split_p

Author: jeffery9

.github/workflows/make_test_ebook.yaml

@@ -37,6 +37,10 @@ jobs:
         run: |
           python3 make_book.py --book_name "test_books/the_little_prince.txt" --test --test_num 20 --model google
 
+      - name: make txt book test with batch_size
+        run: |
+          python3 make_book.py --book_name "test_books/the_little_prince.txt" --test --batch_size 30 --test_num 20 --model google
+
 
       - name: make openai key ebook test
         if: env.OPENAI_API_KEY != null

README-CN.md

@@ -15,7 +15,7 @@ bilingual_book_maker 是一个 AI 翻译工具，使用 ChatGPT 帮助用户制
 
 ## 使用
 
-1. `pip install -r requirements.txt`
+1. `pip install -r requirements.txt` 或 `pip install -U bbook_maker`
 2. 使用 `--openai_key` 指定 OpenAI API key，如果有多个可以用英文逗号分隔(xxx,xxx,xxx)，可以减少接口调用次数限制带来的错误。  
    或者，指定环境变量 `BMM_OPENAI_API_KEY` 来略过这个选项。
 3. 本地放了一个 `test_books/animal_farm.epub` 给大家测试
@@ -42,9 +42,11 @@ bilingual_book_maker 是一个 AI 翻译工具，使用 ChatGPT 帮助用户制
 16. 翻译完会生成一本 ${book_name}_bilingual.epub 的双语书
 17. 如果出现了错误或使用 `CTRL+C` 中断命令，不想接下来继续翻译了，会生成一本 ${book_name}_bilingual_temp.epub 的书，直接改成你想要的名字就可以了
 18. 如果你想要翻译电子书中的无标签字符串，可以使用 `--allow_navigable_strings` 参数，会将可遍历字符串加入翻译队列，**注意，在条件允许情况下，请寻找更规范的电子书**
-
+19. 使用`--batch_size` 参数，指定批量翻译的行数(默认行数为10，目前只对txt生效)
 ### 示范用例
 
+**如果使用 `pip install bbook_maker` 以下命令都可以改成 `bbook args`**
+
 ```shell
 # 如果你想快速测一下
 python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --test
@@ -70,6 +72,9 @@ python3 make_book.py --book_from kobo --device_path /tmp/kobo
 
 # 翻译 txt 文件
 python3 make_book.py --book_name test_books/the_little_prince.txt --test 
+# 聚合多行翻译 txt 文件 
+python3 make_book.py --book_name test_books/the_little_prince.txt --test --batch_size 20
+
 ```
 
 更加小白的示例

README.md

@@ -1,7 +1,3 @@
-This forked added Google Translate support, only supported translate to `zh-CN`.
-Usage: make sure to add `--model google` in the command.
-
-
 **[中文](./README-CN.md) | English**
 
 # bilingual_book_maker
@@ -19,7 +15,7 @@ The bilingual_book_maker is an AI translation tool that uses ChatGPT to assist u
 
 ## Use
 
-1. `pip install -r requirements.txt`
+1. `pip install -r requirements.txt` or `pip install -U bbook_maker`(you can use)
 2. Use `--openai_key` option to specify OpenAI API key. If you have multiple keys, separate them by commas (xxx,xxx,xxx) to reduce errors caused by API call limits.  
    Or, just set environment variable `BMM_OPENAI_API_KEY` instead.
 3. A sample book, `test_books/animal_farm.epub`, is provided for testing purposes.
@@ -45,9 +41,12 @@ The bilingual_book_maker is an AI translation tool that uses ChatGPT to assist u
 16. Once the translation is complete, a bilingual book named `${book_name}_bilingual.epub` would be generated.
 17. If there are any errors or you wish to interrupt the translation by pressing `CTRL+C`. A book named `${book_name}_bilingual_temp.epub` would be generated. You can simply rename it to any desired name.
 18. If you want to translate strings in an e-book that aren't labeled with any tags, you can use the `--allow_navigable_strings` parameter. This will add the strings to the translation queue. **Note that it's best to look for e-books that are more standardized if possible.**
+19. Use the `--batch_size` parameter to specify the number of lines for batch translation (default is 10, currently only effective for txt files).
 
 ### Examples
 
+**Note if use `pip install bbook_maker` all commands can change to `bbook args`**
+
 ```shell
 # Test quickly
 python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key}  --test --language zh-hans
@@ -76,6 +75,8 @@ python3 make_book.py --book_from kobo --device_path /tmp/kobo
 
 # translate txt file
 python3 make_book.py --book_name test_books/the_little_prince.txt --test --language zh-hans
+# aggregated translation txt file
+python3 make_book.py --book_name test_books/the_little_prince.txt --test --batch_size 20
 ```
 
 More understandable example

book_maker/cli.py

@@ -1,12 +1,12 @@
 import argparse
+import json
 import os
 from os import environ as env
-import json
 
+import book_maker.obok as obok
 from book_maker.loader import BOOK_LOADER_DICT
 from book_maker.translator import MODEL_DICT
 from book_maker.utils import LANGUAGES, TO_LANGUAGE_CODE
-import book_maker.obok as obok
 
 
 def parse_prompt_arg(prompt_arg):
@@ -156,6 +156,13 @@ def main():
         metavar="PROMPT_ARG",
         help="used for customizing the prompt. It can be the prompt template string, or a path to the template file. The valid placeholders are `{text}` and `{language}`.",
     )
+    parser.add_argument(
+        "--batch_size",
+        dest="batch_size",
+        type=int,
+        default=10,
+        help="how many lines will be translated by aggregated translation(This options currently only applies to txt files)",
+    )
 
     options = parser.parse_args()
     PROXY = options.proxy
@@ -219,6 +226,7 @@ def main():
         translate_tags=options.translate_tags,
         allow_navigable_strings=options.allow_navigable_strings,
         prompt_config=parse_prompt_arg(options.prompt_arg),
+        batch_size=options.batch_size,
     )
     e.make_bilingual_book()
 

book_maker/loader/__init__.py

@@ -1,5 +1,4 @@
 from book_maker.loader.epub_loader import EPUBBookLoader
-
 from book_maker.loader.txt_loader import TXTBookLoader
 
 BOOK_LOADER_DICT = {

book_maker/loader/epub_loader.py

@@ -9,9 +9,10 @@
 from rich import print
 from tqdm import tqdm
 
-from .base_loader import BaseBookLoader
 from book_maker.utils import prompt_config_to_kwargs
 
+from .base_loader import BaseBookLoader
+
 
 class EPUBBookLoader(BaseBookLoader):
     def __init__(
@@ -21,6 +22,7 @@ def __init__(
         key,
         resume,
         language,
+        batch_size,
         model_api_base=None,
         is_test=False,
         test_num=5,

book_maker/loader/txt_loader.py

@@ -1,9 +1,10 @@
 import sys
 from pathlib import Path
 
-from .base_loader import BaseBookLoader
 from book_maker.utils import prompt_config_to_kwargs
 
+from .base_loader import BaseBookLoader
+
 
 class TXTBookLoader(BaseBookLoader):
     def __init__(
@@ -13,6 +14,7 @@ def __init__(
         key,
         resume,
         language,
+        batch_size,
         translate_tags,
         allow_navigable_strings,
         model_api_base=None,
@@ -32,6 +34,7 @@ def __init__(
         self.bilingual_result = []
         self.bilingual_temp_result = []
         self.test_num = test_num
+        self.batch_size = batch_size
 
         try:
             with open(f"{txt_name}", "r", encoding="utf-8") as f:
@@ -57,17 +60,22 @@ def make_bilingual_book(self):
         p_to_save_len = len(self.p_to_save)
 
         try:
-            for i in self.origin_book:
-                if self._is_special_text(i):
+            sliced_list = [
+                self.origin_book[i : i + self.batch_size]
+                for i in range(0, len(self.origin_book), self.batch_size)
+            ]
+            for i in sliced_list:
+                batch_text = "".join(i)
+                if self._is_special_text(batch_text):
                     continue
                 if self.resume and index < p_to_save_len:
                     pass
                 else:
-                    temp = self.translate_model.translate(i)
+                    temp = self.translate_model.translate(batch_text)
                     self.p_to_save.append(temp)
-                    self.bilingual_result.append(i)
+                    self.bilingual_result.append(batch_text)
                     self.bilingual_result.append(temp)
-                index += 1
+                index += self.batch_size
                 if self.is_test and index > self.test_num:
                     break
 
@@ -85,8 +93,14 @@ def make_bilingual_book(self):
 
     def _save_temp_book(self):
         index = 0
-        for i in range(0, len(self.origin_book)):
-            self.bilingual_temp_result.append(self.origin_book[i])
+        sliced_list = [
+            self.origin_book[i : i + self.batch_size]
+            for i in range(0, len(self.origin_book), self.batch_size)
+        ]
+
+        for i in range(0, len(sliced_list)):
+            batch_text = "".join(sliced_list[i])
+            self.bilingual_temp_result.append(batch_text)
             if self._is_special_text(self.origin_book[i]):
                 continue
             if index < len(self.p_to_save):

book_maker/obok.py

@@ -164,19 +164,19 @@
 __version__ = "4.0.0"
 __about__ = "Obok v{0}\nCopyright © 2012-2020 Physisticated et al.".format(__version__)
 
-import sys
-import os
-import subprocess
-import sqlite3
 import base64
 import binascii
-import re
-import zipfile
 import hashlib
-import xml.etree.ElementTree as ET
-import string
+import os
+import re
 import shutil
+import sqlite3
+import string
+import subprocess
+import sys
 import tempfile
+import xml.etree.ElementTree as ET
+import zipfile
 
 can_parse_xml = True
 try:
@@ -199,14 +199,14 @@ def _load_crypto_libcrypto():
     from ctypes import (
         CDLL,
         POINTER,
-        c_void_p,
+        Structure,
         c_char_p,
         c_int,
         c_long,
-        Structure,
         c_ulong,
-        create_string_buffer,
+        c_void_p,
         cast,
+        create_string_buffer,
     )
     from ctypes.util import find_library
 

book_maker/translator/chatgptapi_translator.py

@@ -1,12 +1,11 @@
 import time
+from os import environ
 
 import openai
-from os import environ
 
 from .base_translator import Base
 from ..utils import num_tokens_from_messages
 
-
 PROMPT_ENV_MAP = {
     "user": "BBM_CHATGPTAPI_USER_MSG_TEMPLATE",
     "system": "BBM_CHATGPTAPI_SYS_MSG",

setup.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+from setuptools import find_packages, setup
+
+setup(
+    name="bbook_maker",
+    description="The bilingual_book_maker is an AI translation tool that uses ChatGPT to assist users in creating multi-language versions of epub/txt files and books.",
+    version="0.1.0",
+    license="MIT",
+    author="yihong0618",
+    author_email="zouzou0208@gmail.com",
+    packages=find_packages(),
+    url="https://github.com/yihong0618/bilingual_book_maker",
+    python_requires=">=3.7",
+    install_requires=["bs4", "openai", "requests", "ebooklib", "rich", "tqdm"],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    entry_points={
+        "console_scripts": ["bbook_maker = book_maker.cli:main"],
+    },
+)