toolkitx 0.0.1__tar.gz

toolkitx-0.0.1/.gitignore

@@ -0,0 +1,174 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

toolkitx-0.0.1/.python-version

@@ -0,0 +1 @@
+3.13

toolkitx-0.0.1/LICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <https://unlicense.org>

toolkitx-0.0.1/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: toolkitx
+Version: 0.0.1
+Summary: A personal Python toolkit for common tasks
+Project-URL: Homepage, https://github.com/ider-zh/toolkitx
+Project-URL: Bug Tracker, https://github.com/ider-zh/toolkitx/issues
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: diskcache>=5.6.3
+Requires-Dist: py-transgpt>=2.0
+Provides-Extra: dev
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-dotenv; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# toolkitx
+
+A personal Python toolkit for common tasks. This package provides various utility functions to simplify common development workflows.
+
+## Features
+
+*   **Text Utilities** (`toolkitx.text_utils`):
+    *   `truncate_text_smart`: Smartly truncates text by characters or words, with options for suffix and tolerance, attempting to preserve sentence or word boundaries.
+    *   `split_text_by_word_count`: Splits long text into overlapping chunks based on word count.
+*   **Command-Line Script**:
+    *   `hello`: A simple script accessible via `hello` command after installation, prints a greeting message.
+*   **Experimental Translator** (`toolkitx.lab.translator`):
+    *   `Translator`: A class providing translation capabilities using Baidu or Tencent translation APIs, with disk-based caching for performance. (Requires API credentials)
+
+## Installation
+
+1.  Clone the repository:
+    ```bash
+    git clone https://github.com/ider-zh/toolkitx.git
+    cd toolkitx
+    ```
+2.  Install the package. For development, you can install it in editable mode with development dependencies:
+    ```bash
+    pip install -e ".[dev]"
+    ```
+    For regular installation:
+    ```bash
+    pip install .
+    ```
+
+## Usage
+
+### Text Utilities
+
+```python
+from toolkitx import truncate_text_smart, split_text_by_word_count
+
+# Smart Truncation
+text = "This is a very long sentence that needs to be truncated."
+truncated_char = truncate_text_smart(text, limit=20, mode="char", suffix="...")
+print(f"Char truncated: {truncated_char}")
+
+truncated_word = truncate_text_smart(text, limit=5, mode="word", suffix="...")
+print(f"Word truncated: {truncated_word}")
+
+# Split Text
+long_text = "This is a long piece of text that we want to split into several smaller chunks with some overlap between them for context."
+chunks = split_text_by_word_count(long_text, max_words=10, overlap=2)
+for i, chunk in enumerate(chunks):
+    print(f"Chunk {i+1}: {chunk}")
+```

toolkitx-0.0.1/README.md

@@ -0,0 +1,51 @@
+# toolkitx
+
+A personal Python toolkit for common tasks. This package provides various utility functions to simplify common development workflows.
+
+## Features
+
+*   **Text Utilities** (`toolkitx.text_utils`):
+    *   `truncate_text_smart`: Smartly truncates text by characters or words, with options for suffix and tolerance, attempting to preserve sentence or word boundaries.
+    *   `split_text_by_word_count`: Splits long text into overlapping chunks based on word count.
+*   **Command-Line Script**:
+    *   `hello`: A simple script accessible via `hello` command after installation, prints a greeting message.
+*   **Experimental Translator** (`toolkitx.lab.translator`):
+    *   `Translator`: A class providing translation capabilities using Baidu or Tencent translation APIs, with disk-based caching for performance. (Requires API credentials)
+
+## Installation
+
+1.  Clone the repository:
+    ```bash
+    git clone https://github.com/ider-zh/toolkitx.git
+    cd toolkitx
+    ```
+2.  Install the package. For development, you can install it in editable mode with development dependencies:
+    ```bash
+    pip install -e ".[dev]"
+    ```
+    For regular installation:
+    ```bash
+    pip install .
+    ```
+
+## Usage
+
+### Text Utilities
+
+```python
+from toolkitx import truncate_text_smart, split_text_by_word_count
+
+# Smart Truncation
+text = "This is a very long sentence that needs to be truncated."
+truncated_char = truncate_text_smart(text, limit=20, mode="char", suffix="...")
+print(f"Char truncated: {truncated_char}")
+
+truncated_word = truncate_text_smart(text, limit=5, mode="word", suffix="...")
+print(f"Word truncated: {truncated_word}")
+
+# Split Text
+long_text = "This is a long piece of text that we want to split into several smaller chunks with some overlap between them for context."
+chunks = split_text_by_word_count(long_text, max_words=10, overlap=2)
+for i, chunk in enumerate(chunks):
+    print(f"Chunk {i+1}: {chunk}")
+```

toolkitx-0.0.1/pyproject.toml

@@ -0,0 +1,30 @@
+[project]
+name = "toolkitx"
+version = "0.0.1"
+description = "A personal Python toolkit for common tasks"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "diskcache>=5.6.3",
+    "py-transgpt>=2.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "pytest-dotenv",
+]
+
+[project.scripts]
+hello = "toolkitx.hello:hello"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["toolkitx"]
+
+[project.urls]
+"Homepage" = "https://github.com/ider-zh/toolkitx"
+"Bug Tracker" = "https://github.com/ider-zh/toolkitx/issues"

toolkitx-0.0.1/tests/lab/test_translator.py

@@ -0,0 +1,240 @@
+import os
+import pytest
+from unittest.mock import patch, MagicMock
+from toolkitx.lab.translator import Translator # 假设 Translator 类在这个路径下
+
+# --- API Key Availability Check ---
+# 这些变量将在模块加载时评估，反映环境变量的初始状态
+# pytest-dotenv 应该在 pytest 收集测试之前加载 .env 文件
+BAIDU_KEYS_AVAILABLE = bool(os.getenv("BAIDU_API_ID") and os.getenv("BAIDU_API_KEY"))
+TENCENT_KEYS_AVAILABLE = bool(os.getenv("TENCENT_API_ID") and os.getenv("TENCENT_API_KEY"))
+
+# --- Test API Credentials (can be overridden by .env for actual integration tests if not mocked) ---
+# 这些主要用于那些不依赖 .env 文件，而是直接传递参数或使用 monkeypatch 的测试
+TEST_BAIDU_API_ID_PARAM = "param_baidu_id"
+TEST_BAIDU_API_KEY_PARAM = "param_baidu_key"
+TEST_TENCENT_API_ID_PARAM = "param_tencent_id"
+TEST_TENCENT_API_KEY_PARAM = "param_tencent_key"
+
+
+@pytest.fixture
+def temp_cache_path(tmp_path):
+    """提供一个临时的缓存路径"""
+    cache_dir = tmp_path / "translator_cache"
+    cache_dir.mkdir()
+    return str(cache_dir)
+
+@pytest.fixture
+def mock_baidu_engine_class():
+    """模拟 BaiduTranslation 类，并返回被 mock 的类本身以便检查构造函数调用"""
+    with patch('toolkitx.lab.translator.BaiduTranslation') as MockBaiduEngine:
+        mock_instance = MagicMock()
+        mock_instance.translate.return_value = "translated_from_baidu"
+        MockBaiduEngine.return_value = mock_instance
+        yield MockBaiduEngine
+
+@pytest.fixture
+def mock_tencent_engine_class():
+    """模拟 TencentTranslation 类，并返回被 mock 的类本身"""
+    with patch('toolkitx.lab.translator.TencentTranslation') as MockTencentEngine:
+        mock_instance = MagicMock()
+        mock_instance.translate.return_value = "translated_from_tencent"
+        MockTencentEngine.return_value = mock_instance
+        yield MockTencentEngine
+
+# --- Initialization Tests ---
+
+def test_translator_init_baidu_with_direct_params(temp_cache_path, mock_baidu_engine_class):
+    """测试使用直接参数初始化百度翻译引擎"""
+    translator = Translator(
+        engine="baidu",
+        cache_path=temp_cache_path,
+        api_id=TEST_BAIDU_API_ID_PARAM,
+        api_key=TEST_BAIDU_API_KEY_PARAM
+    )
+    assert translator.engine_name == "baidu"
+    # 验证 BaiduTranslation 构造函数是否用提供的参数被调用
+    mock_baidu_engine_class.assert_called_once_with(api_id=TEST_BAIDU_API_ID_PARAM, api_key=TEST_BAIDU_API_KEY_PARAM)
+    translator.close_cache()
+
+def test_translator_init_baidu_with_monkeypatched_env(temp_cache_path, mock_baidu_engine_class, monkeypatch):
+    """测试使用 monkeypatch 设置的环境变量初始化百度翻译引擎"""
+    monkeypatch.setenv("BAIDU_API_ID", "env_baidu_id_monkey")
+    monkeypatch.setenv("BAIDU_API_KEY", "env_baidu_key_monkey")
+    translator = Translator(engine="baidu", cache_path=temp_cache_path)
+    assert translator.engine_name == "baidu"
+    mock_baidu_engine_class.assert_called_once_with(api_id="env_baidu_id_monkey", api_key="env_baidu_key_monkey")
+    translator.close_cache()
+
+def test_translator_init_baidu_missing_keys_error(temp_cache_path, monkeypatch):
+    """测试当百度密钥缺失时是否抛出 ValueError"""
+    monkeypatch.delenv("BAIDU_API_ID", raising=False)
+    monkeypatch.delenv("BAIDU_API_KEY", raising=False)
+    with pytest.raises(ValueError, match="Baidu API ID and API Key are required"):
+        Translator(engine="baidu", cache_path=temp_cache_path)
+
+def test_translator_init_tencent_with_direct_params(temp_cache_path, mock_tencent_engine_class):
+    """测试使用直接参数初始化腾讯翻译引擎"""
+    translator = Translator(
+        engine="tencent",
+        cache_path=temp_cache_path,
+        api_id=TEST_TENCENT_API_ID_PARAM,
+        api_key=TEST_TENCENT_API_KEY_PARAM
+    )
+    assert translator.engine_name == "tencent"
+    mock_tencent_engine_class.assert_called_once_with(api_id=TEST_TENCENT_API_ID_PARAM, api_key=TEST_TENCENT_API_KEY_PARAM)
+    translator.close_cache()
+
+def test_translator_init_tencent_with_monkeypatched_env(temp_cache_path, mock_tencent_engine_class, monkeypatch):
+    """测试使用 monkeypatch 设置的环境变量初始化腾讯翻译引擎"""
+    monkeypatch.setenv("TENCENT_API_ID", "env_tencent_id_monkey")
+    monkeypatch.setenv("TENCENT_API_KEY", "env_tencent_key_monkey")
+    translator = Translator(engine="tencent", cache_path=temp_cache_path)
+    assert translator.engine_name == "tencent"
+    mock_tencent_engine_class.assert_called_once_with(api_id="env_tencent_id_monkey", api_key="env_tencent_key_monkey")
+    translator.close_cache()
+
+def test_translator_init_tencent_missing_keys_error(temp_cache_path, monkeypatch):
+    """测试当腾讯密钥缺失时是否抛出 ValueError (根据用户代码中的错误信息)"""
+    monkeypatch.delenv("TENCENT_API_ID", raising=False)
+    monkeypatch.delenv("TENCENT_API_KEY", raising=False)
+    with pytest.raises(ValueError, match="Tencent Secret ID and Secret Key are required"):
+        Translator(engine="tencent", cache_path=temp_cache_path)
+
+def test_translator_init_unsupported_engine(temp_cache_path):
+    """测试初始化不支持的引擎时是否抛出 ValueError"""
+    with pytest.raises(ValueError, match="Unsupported engine: unsupported_engine"):
+        Translator(engine="unsupported_engine", cache_path=temp_cache_path)
+
+# --- Translation and Cache Tests (Relying on .env loaded keys) ---
+
+@pytest.mark.skipif(not BAIDU_KEYS_AVAILABLE, reason="BAIDU_API_ID and/or BAIDU_API_KEY not set in environment (e.g., via .env)")
+def test_translate_baidu_with_env_keys_cache_miss_and_hit(temp_cache_path, mock_baidu_engine_class):
+    """测试百度翻译（使用环境变量中的密钥），包括缓存未命中和命中"""
+    # 从环境变量获取预期的密钥，因为 BAIDU_KEYS_AVAILABLE 为 True
+    expected_api_id = os.getenv("BAIDU_API_ID")
+    expected_api_key = os.getenv("BAIDU_API_KEY")
+
+    translator = Translator(engine="baidu", cache_path=temp_cache_path) # 不传递 api_id/key
+    
+    # 验证 BaiduTranslation 构造函数是否用环境变量中的密钥被调用
+    mock_baidu_engine_class.assert_called_once_with(api_id=expected_api_id, api_key=expected_api_key)
+    
+    # 获取 mock 的翻译实例 (由 mock_baidu_engine_class 的 return_value 提供)
+    mock_baidu_engine_instance = translator.translator_instance
+
+    text = "你好"
+    target_lang = "en"
+    source_lang = "zh"
+
+    # 首次翻译 (cache miss)
+    result1 = translator.translate(text, target_lang=target_lang, source_lang=source_lang)
+    assert result1 == "translated_from_baidu" # 这是 mock_engine_instance.translate 的返回值
+    mock_baidu_engine_instance.translate.assert_called_once_with(text, target_lang, source_lang)
+
+    # 再次翻译 (cache hit)
+    mock_baidu_engine_instance.translate.reset_mock() # 重置 mock 调用计数
+    result2 = translator.translate(text, target_lang=target_lang, source_lang=source_lang)
+    assert result2 == "translated_from_baidu"
+    mock_baidu_engine_instance.translate.assert_not_called() # 不应再次调用实际翻译引擎的 translate
+
+    translator.close_cache()
+
+@pytest.mark.skipif(not TENCENT_KEYS_AVAILABLE, reason="TENCENT_API_ID and/or TENCENT_API_KEY not set in environment (e.g., via .env)")
+def test_translate_tencent_with_env_keys_cache_miss_and_hit(temp_cache_path, mock_tencent_engine_class):
+    """测试腾讯翻译（使用环境变量中的密钥），包括缓存未命中和命中"""
+    expected_api_id = os.getenv("TENCENT_API_ID")
+    expected_api_key = os.getenv("TENCENT_API_KEY")
+
+    translator = Translator(engine="tencent", cache_path=temp_cache_path)
+    mock_tencent_engine_class.assert_called_once_with(api_id=expected_api_id, api_key=expected_api_key)
+    mock_tencent_engine_instance = translator.translator_instance
+    
+    text = "Hello"
+    target_lang = "zh"
+    source_lang = "en"
+
+    result1 = translator.translate(text, target_lang=target_lang, source_lang=source_lang)
+    assert result1 == "translated_from_tencent"
+    mock_tencent_engine_instance.translate.assert_called_once_with(text, target_lang, source_lang)
+
+    mock_tencent_engine_instance.translate.reset_mock()
+    result2 = translator.translate(text, target_lang=target_lang, source_lang=source_lang)
+    assert result2 == "translated_from_tencent"
+    mock_tencent_engine_instance.translate.assert_not_called()
+
+    translator.close_cache()
+
+@pytest.mark.skipif(not BAIDU_KEYS_AVAILABLE, reason="Baidu keys not in .env")
+def test_translate_empty_string_with_env_keys(temp_cache_path, mock_baidu_engine_class):
+    """测试使用环境变量密钥翻译空字符串"""
+    translator = Translator(engine="baidu", cache_path=temp_cache_path)
+    assert translator.translate("") == ""
+    # BaiduTranslation 构造函数会被调用，但其 translate 方法不应被调用
+    mock_baidu_engine_class.return_value.translate.assert_not_called()
+    translator.close_cache()
+
+@pytest.mark.skipif(not BAIDU_KEYS_AVAILABLE, reason="Baidu keys not in .env")
+def test_translate_uses_default_langs_with_env_keys(temp_cache_path, mock_baidu_engine_class):
+    """测试使用环境变量密钥时，是否使用默认语言"""
+    default_target = "fr"
+    default_source = "de"
+    translator = Translator(
+        engine="baidu",
+        cache_path=temp_cache_path,
+        target_lang=default_target,
+        source_lang=default_source
+    )
+    mock_engine_instance = translator.translator_instance
+    text = "Guten Tag"
+    translator.translate(text) # 不传递 target_lang/source_lang
+    mock_engine_instance.translate.assert_called_once_with(text, default_target, default_source)
+    translator.close_cache()
+
+@pytest.mark.skipif(not BAIDU_KEYS_AVAILABLE, reason="Baidu keys not in .env")
+def test_translate_api_error_with_env_keys(temp_cache_path, mock_baidu_engine_class):
+    """测试使用环境变量密钥时，API 错误是否正确传递"""
+    translator = Translator(engine="baidu", cache_path=temp_cache_path)
+    mock_engine_instance = translator.translator_instance
+    mock_engine_instance.translate.side_effect = RuntimeError("API communication error")
+    
+    with pytest.raises(RuntimeError, match="API communication error"):
+        translator.translate("text to fail")
+    translator.close_cache()
+
+# --- Cache Management Tests (Relying on .env loaded keys) ---
+
+@pytest.mark.skipif(not BAIDU_KEYS_AVAILABLE, reason="Baidu keys not in .env")
+def test_clear_cache_with_env_keys(temp_cache_path, mock_baidu_engine_class):
+    """测试使用环境变量密钥时，清除缓存的功能"""
+    translator = Translator(engine="baidu", cache_path=temp_cache_path)
+    mock_engine_instance = translator.translator_instance
+    text = "Cache me"
+    target_lang = "en"
+    
+    # 翻译并缓存
+    translator.translate(text, target_lang=target_lang)
+    mock_engine_instance.translate.assert_called_once()
+
+    # 清除缓存
+    translator.clear_cache()
+    
+    # 再次翻译，应该会调用API (cache miss)
+    mock_engine_instance.translate.reset_mock()
+    translator.translate(text, target_lang=target_lang)
+    mock_engine_instance.translate.assert_called_once()
+    
+    translator.close_cache()
+
+def test_close_cache_direct_params(temp_cache_path, mock_baidu_engine_class): # 这个测试不需要依赖环境变量
+    """测试 close_cache 方法（不依赖环境变量密钥）"""
+    translator = Translator(
+        engine="baidu", 
+        cache_path=temp_cache_path, 
+        api_id="dummy_id", 
+        api_key="dummy_key"
+    )
+    # 模拟 Cache 对象的 close 方法
+    with patch.object(translator.cache, 'close', wraps=translator.cache.close) as mock_cache_close:
+        translator.close_cache()
+        mock_cache_close.assert_called_once()