complex-text-tools 0.1.0__tar.gz

complex_text_tools-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Your Name
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+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 OR COPYRIGHT HOLDERS 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.

complex_text_tools-0.1.0/MANIFEST.in

@@ -0,0 +1,2 @@
+include README.md
+include LICENSE

complex_text_tools-0.1.0/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.1
+Name: complex-text-tools
+Version: 0.1.0
+Summary: A package for processing complex text with mixed Chinese and English characters
+Home-page: https://github.com/yourusername/complex-text-tools
+Author: Your Name
+Author-email: Your Name <your.email@example.com>
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/complex-text-tools
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# Complex Text Tools
+
+A Python package for processing complex text containing mixed Chinese and English characters, removing extra spaces and standardizing punctuation.
+
+## Features
+
+- Remove extra spaces between Chinese characters
+- Remove extra spaces between Chinese and English characters
+- Handle spacing around punctuation marks correctly
+- Process mixed language texts efficiently
+
+## Installation
+
+```bash
+pip install complex-text-tools
+```
+
+## Usage
+
+```python
+from complex_text_tools import remove_extra_spaces
+
+text = "这 是  中文 测试  文本 ，  mixed  English  text  here ， 还 有   symbols :  ;  !  "
+clean_text = remove_extra_spaces(text)
+print(clean_text)
+# Output: "这是中文测试文本，mixed English text here，还有 symbols:;!"
+```
+
+## License
+
+This project is licensed under the MIT License.

complex_text_tools-0.1.0/README.md

@@ -0,0 +1,31 @@
+# Complex Text Tools
+
+A Python package for processing complex text containing mixed Chinese and English characters, removing extra spaces and standardizing punctuation.
+
+## Features
+
+- Remove extra spaces between Chinese characters
+- Remove extra spaces between Chinese and English characters
+- Handle spacing around punctuation marks correctly
+- Process mixed language texts efficiently
+
+## Installation
+
+```bash
+pip install complex-text-tools
+```
+
+## Usage
+
+```python
+from complex_text_tools import remove_extra_spaces
+
+text = "这 是  中文 测试  文本 ，  mixed  English  text  here ， 还 有   symbols :  ;  !  "
+clean_text = remove_extra_spaces(text)
+print(clean_text)
+# Output: "这是中文测试文本，mixed English text here，还有 symbols:;!"
+```
+
+## License
+
+This project is licensed under the MIT License.

complex_text_tools-0.1.0/complex_text_tools/__init__.py

@@ -0,0 +1,3 @@
+from .text_processor import remove_extra_spaces
+
+__all__ = ['remove_extra_spaces']

complex_text_tools-0.1.0/complex_text_tools/test_processor.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from .text_processor import remove_extra_spaces
+
+
+def test_remove_extra_spaces():
+    # 测试用例：验证各种空格移除功能
+    test_text = "这 是  中文 测试  文本 ，  mixed  English  text  here ， 还 有   symbols :  ;  !  "
+    expected_result = "这是中文测试文本，mixed English text here，还有 symbols:;!"
+    result = remove_extra_spaces(test_text)
+
+    print("原始文本:", test_text)
+    print("处理结果:", result)
+    print("预期结果:", expected_result)
+    print("测试通过:", result == expected_result)
+    
+    return result == expected_result
+
+
+if __name__ == "__main__":
+    test_remove_extra_spaces()

complex_text_tools-0.1.0/complex_text_tools/text_processor.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+import re
+
+
+def remove_extra_spaces(text: str) -> str:
+    """
+    移除混合字符串中多余的空格
+    """
+    # 移除中文字符（包括符号）之间的空格
+    pattern1 = r"(?<=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])\s+(?=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])"
+    
+    # 移除中英文字符（包括符号）之间的空格
+    pattern2 = r"(?<=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])\s+(?=[a-zA-Z])|(?<=[a-zA-Z])\s+(?=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])"
+    
+    # 移除中文字符与英文符号之间的空格（扩展支持更多符号）
+    pattern3 = r"(?<=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])\s+(?=[\[\]\(\)\{\}\"\'\:\;\?\!\,\.\`\~])|(?<=[\[\]\(\)\{\}\"\'\:\;\?\!\,\.\`\~])\s+(?=[\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])"
+    
+    # 处理英文单词与标点之间的空格
+    # 单词和后面的标点应该是紧挨着的（无空格）
+    # 标点后面的单词之间应该有且仅有一个空格
+    pattern4a = r"(\w)\s+([^\w\s])"     # 单词和标点之间（移除空格）
+    pattern4b = r"([^\w\s])\s+(\w)"     # 标点和单词之间（保留一个空格）
+    pattern4c = r"(\w)\s{2,}(\w)"       # 单词和单词之间多余的空格（替换为一个空格）
+    
+    # 处理英文符号之间的多余空格（确保符号之间只有一个空格）
+    pattern5 = r"([^\w\s])\s{2,}([^\w\s])"
+    # 移除英文标点之间的空格
+    pattern7 = r"([^\w\s])\s+([^\w\s])"
+    # 处理英文符号和中文之间的空格问题
+    # pattern6 = r"([\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])([^\w\s])|([^\w\s])([\u4e00-\u9fff\u3000-\u303f\uff00-\uffef])"
+    
+    # 按顺序处理各种空格
+    # 先处理中英文之间的空格
+    text = re.sub(pattern2, "", text)
+    # 再处理中文之间的空格
+    text = re.sub(pattern1, "", text)
+    # 然后处理中文与英文符号之间的空格
+    text = re.sub(pattern3, "", text)
+    # 处理英文单词和标点之间的空格
+    text = re.sub(pattern4a, r"\1\2", text)      # 单词和标点之间无空格
+    text = re.sub(pattern4b, r"\1 \2", text)     # 标点和单词之间保留一个空格
+    text = re.sub(pattern4c, r"\1 \2", text)     # 单词间多余空格替换为一个空格
+    # 处理英文符号之间的多余空格
+    text = re.sub(pattern5, r"\1\2", text)
+    # 处理英文符号和中文之间的空格（确保有空格）
+    text = re.sub(pattern7, r"\1\2", text)
+    
+    return text

complex_text_tools-0.1.0/complex_text_tools.egg-info/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.1
+Name: complex-text-tools
+Version: 0.1.0
+Summary: A package for processing complex text with mixed Chinese and English characters
+Home-page: https://github.com/yourusername/complex-text-tools
+Author: Your Name
+Author-email: Your Name <your.email@example.com>
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/complex-text-tools
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# Complex Text Tools
+
+A Python package for processing complex text containing mixed Chinese and English characters, removing extra spaces and standardizing punctuation.
+
+## Features
+
+- Remove extra spaces between Chinese characters
+- Remove extra spaces between Chinese and English characters
+- Handle spacing around punctuation marks correctly
+- Process mixed language texts efficiently
+
+## Installation
+
+```bash
+pip install complex-text-tools
+```
+
+## Usage
+
+```python
+from complex_text_tools import remove_extra_spaces
+
+text = "这 是  中文 测试  文本 ，  mixed  English  text  here ， 还 有   symbols :  ;  !  "
+clean_text = remove_extra_spaces(text)
+print(clean_text)
+# Output: "这是中文测试文本，mixed English text here，还有 symbols:;!"
+```
+
+## License
+
+This project is licensed under the MIT License.

complex_text_tools-0.1.0/complex_text_tools.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+setup.py
+complex_text_tools/__init__.py
+complex_text_tools/test_processor.py
+complex_text_tools/text_processor.py
+complex_text_tools.egg-info/PKG-INFO
+complex_text_tools.egg-info/SOURCES.txt
+complex_text_tools.egg-info/dependency_links.txt
+complex_text_tools.egg-info/top_level.txt

complex_text_tools-0.1.0/complex_text_tools.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

complex_text_tools-0.1.0/complex_text_tools.egg-info/top_level.txt

@@ -0,0 +1 @@
+complex_text_tools

complex_text_tools-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "complex-text-tools"
+version = "0.1.0"
+description = "A package for processing complex text with mixed Chinese and English characters"
+readme = "README.md"
+authors = [
+    {name = "Your Name", email = "your.email@example.com"}
+]
+license = {text = "MIT"}
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.6",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+]
+requires-python = ">=3.6"
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/yourusername/complex-text-tools"

complex_text_tools-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

complex_text_tools-0.1.0/setup.py

@@ -0,0 +1,32 @@
+from setuptools import setup, find_packages
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setup(
+    name="complex-text-tools",
+    version="0.1.0",
+    author="Your Name",
+    author_email="your.email@example.com",
+    description="A package for processing complex text with mixed Chinese and English characters",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/yourusername/complex-text-tools",
+    packages=find_packages(),
+    classifiers=[
+        "Development Status :: 3 - Alpha",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+    ],
+    python_requires=">=3.6",
+    install_requires=[
+        # 无额外依赖
+    ],
+)