textutils-py 0.1.1__tar.gz

textutils_py-0.1.1/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.1
+Name: textutils_py
+Version: 0.1.1
+Summary: 一个功能丰富的文本处理工具集
+Home-page: https://github.com/你的用户名/textutils-py
+Author: 袁培钦
+Author-email: 570686818@qq.com
+Project-URL: Bug Reports, https://github.com/你的用户名/textutils-py/issues
+Project-URL: Source, https://github.com/你的用户名/textutils-py
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# TextUtils-Py
+
+一个功能丰富的文本处理Python工具集。
+
+## 安装
+
+```bash
+pip install textutils-py

textutils_py-0.1.1/README.md

@@ -0,0 +1,8 @@
+# TextUtils-Py
+
+一个功能丰富的文本处理Python工具集。
+
+## 安装
+
+```bash
+pip install textutils-py

textutils_py-0.1.1/setup.cfg

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

textutils_py-0.1.1/setup.py

@@ -0,0 +1,37 @@
+from setuptools import setup, find_packages
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setup(
+    name="textutils_py",  # PyPI上的包名
+    version="0.1.1",
+    author="袁培钦",
+    author_email="570686818@qq.com",
+    description="一个功能丰富的文本处理工具集",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/你的用户名/textutils-py",
+    packages=find_packages(),
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "Topic :: Text Processing",
+    ],
+    python_requires=">=3.7",
+    install_requires=[
+        # 依赖包列表
+    ],
+    project_urls={
+        "Bug Reports": "https://github.com/你的用户名/textutils-py/issues",
+        "Source": "https://github.com/你的用户名/textutils-py",
+    },
+)

textutils_py-0.1.1/tests/test_core.py

@@ -0,0 +1,32 @@
+import unittest
+from textutils import TextProcessor
+
+
+class TestTextProcessor(unittest.TestCase):
+
+    def test_reverse(self):
+        self.assertEqual(TextProcessor.reverse("hello"), "olleh")
+        self.assertEqual(TextProcessor.reverse(""), "")
+
+    def test_count_words(self):
+        self.assertEqual(TextProcessor.count_words("hello world"), 2)
+        self.assertEqual(TextProcessor.count_words(""), 0)
+
+    def test_is_palindrome(self):
+        self.assertTrue(TextProcessor.is_palindrome("racecar"))
+        self.assertTrue(TextProcessor.is_palindrome("A man a plan a canal Panama"))
+        self.assertFalse(TextProcessor.is_palindrome("hello"))
+
+    def test_extract_emails(self):
+        text = "Contact me at test@example.com or support@test.org"
+        emails = TextProcessor.extract_emails(text)
+        self.assertEqual(len(emails), 2)
+        self.assertEqual(emails[0], "test@example.com")
+
+    def test_to_slug(self):
+        self.assertEqual(TextProcessor.to_slug("Hello World!"), "hello-world")
+        self.assertEqual(TextProcessor.to_slug("Python 3.9"), "python-39")
+
+
+if __name__ == '__main__':
+    unittest.main()

textutils_py-0.1.1/textutils/__init__.py

@@ -0,0 +1,25 @@
+"""
+textutils - 文本处理工具集
+一个功能丰富的文本处理Python库
+"""
+
+from textutils.core import TextProcessor
+from textutils.utils import (
+    generate_random_string,
+    generate_uuid,
+    truncate,
+    count_occurrences,
+    remove_stopwords,
+    is_valid_email
+)
+
+__version__ = "0.1.1"
+__all__ = [
+    'TextProcessor',
+    'generate_random_string',
+    'generate_uuid',
+    'truncate',
+    'count_occurrences',
+    'remove_stopwords',
+    'is_valid_email'
+]

textutils_py-0.1.1/textutils/core.py

@@ -0,0 +1,106 @@
+"""
+textutils - 文本处理工具集核心模块
+"""
+
+import re
+import hashlib
+from typing import List, Optional, Union
+
+
+class TextProcessor:
+    """文本处理器类"""
+
+    @staticmethod
+    def reverse(text: str) -> str:
+        """反转字符串"""
+        return text[::-1]
+
+    @staticmethod
+    def count_words(text: str) -> int:
+        """统计单词数量"""
+        return len(text.split())
+
+    @staticmethod
+    def count_chars(text: str, ignore_spaces: bool = False) -> int:
+        """统计字符数量"""
+        if ignore_spaces:
+            return len(text.replace(" ", ""))
+        return len(text)
+
+    @staticmethod
+    def remove_duplicates(text: str) -> str:
+        """去除重复字符"""
+        seen = set()
+        result = []
+        for char in text:
+            if char not in seen:
+                seen.add(char)
+                result.append(char)
+        return ''.join(result)
+
+    @staticmethod
+    def extract_emails(text: str) -> List[str]:
+        """提取所有邮箱地址"""
+        pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
+        return re.findall(pattern, text)
+
+    @staticmethod
+    def extract_urls(text: str) -> List[str]:
+        """提取所有URL"""
+        pattern = r'https?://[^\s<>"{}|\\^`\[\]]+'
+        return re.findall(pattern, text)
+
+    @staticmethod
+    def to_slug(text: str) -> str:
+        """转换为URL友好的slug格式"""
+        text = text.lower()
+        text = re.sub(r'[^a-z0-9\s-]', '', text)
+        text = re.sub(r'[-\s]+', '-', text)
+        return text.strip('-')
+
+    @staticmethod
+    def is_palindrome(text: str) -> bool:
+        """判断是否为回文"""
+        cleaned = re.sub(r'[^a-zA-Z0-9]', '', text).lower()
+        return cleaned == cleaned[::-1]
+
+    @staticmethod
+    def get_hash(text: str, algorithm: str = 'sha256') -> str:
+        """计算文本哈希值"""
+        hash_func = hashlib.new(algorithm)
+        hash_func.update(text.encode('utf-8'))
+        return hash_func.hexdigest()
+
+    @staticmethod
+    def wrap_text(text: str, width: int = 70) -> str:
+        """按指定宽度换行"""
+        words = text.split()
+        lines = []
+        current_line = []
+        current_length = 0
+
+        for word in words:
+            if current_length + len(word) + 1 <= width:
+                current_line.append(word)
+                current_length += len(word) + 1
+            else:
+                if current_line:
+                    lines.append(' '.join(current_line))
+                current_line = [word]
+                current_length = len(word)
+
+        if current_line:
+            lines.append(' '.join(current_line))
+
+        return '\n'.join(lines)
+
+    @staticmethod
+    def find_most_common(text: str, n: int = 5) -> List[tuple]:
+        """找出最常见的n个单词"""
+        words = re.findall(r'\b[a-zA-Z]+\b', text.lower())
+        word_count = {}
+        for word in words:
+            word_count[word] = word_count.get(word, 0) + 1
+
+        sorted_words = sorted(word_count.items(), key=lambda x: x[1], reverse=True)
+        return sorted_words[:n]

textutils_py-0.1.1/textutils/utils.py

@@ -0,0 +1,61 @@
+"""
+textutils - 辅助工具函数
+"""
+
+import random
+import string
+from typing import List, Optional
+
+
+def generate_random_string(length: int = 8,
+                           include_digits: bool = True,
+                           include_punctuation: bool = False) -> str:
+    """生成随机字符串"""
+    chars = string.ascii_letters
+    if include_digits:
+        chars += string.digits
+    if include_punctuation:
+        chars += string.punctuation
+
+    return ''.join(random.choice(chars) for _ in range(length))
+
+
+def generate_uuid(prefix: str = '') -> str:
+    """生成短UUID"""
+    import uuid
+    uid = str(uuid.uuid4()).replace('-', '')[:12]
+    return f"{prefix}{uid}" if prefix else uid
+
+
+def truncate(text: str, max_length: int = 100, suffix: str = '...') -> str:
+    """截断文本"""
+    if len(text) <= max_length:
+        return text
+    return text[:max_length - len(suffix)] + suffix
+
+
+def count_occurrences(text: str, substring: str, ignore_case: bool = False) -> int:
+    """统计子串出现次数"""
+    if ignore_case:
+        text = text.lower()
+        substring = substring.lower()
+    return text.count(substring)
+
+
+def remove_stopwords(text: str, stopwords: Optional[List[str]] = None) -> str:
+    """移除停用词"""
+    if stopwords is None:
+        # 默认英文停用词
+        stopwords = ['a', 'an', 'the', 'and', 'or', 'but', 'in', 'on', 'at',
+                     'to', 'for', 'of', 'with', 'without', 'by']
+
+    words = text.split()
+    filtered = [w for w in words if w.lower() not in stopwords]
+    return ' '.join(filtered)
+
+
+def is_valid_email(email: str) -> bool:
+    """验证邮箱格式"""
+    import re
+    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
+    return bool(re.match(pattern, email))

textutils_py-0.1.1/textutils_py.egg-info/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.1
+Name: textutils-py
+Version: 0.1.1
+Summary: 一个功能丰富的文本处理工具集
+Home-page: https://github.com/你的用户名/textutils-py
+Author: 袁培钦
+Author-email: 570686818@qq.com
+Project-URL: Bug Reports, https://github.com/你的用户名/textutils-py/issues
+Project-URL: Source, https://github.com/你的用户名/textutils-py
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# TextUtils-Py
+
+一个功能丰富的文本处理Python工具集。
+
+## 安装
+
+```bash
+pip install textutils-py

textutils_py-0.1.1/textutils_py.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+LICENSE
+README.md
+setup.py
+tests/__init__.py
+tests/test_core.py
+textutils/__init__.py
+textutils/core.py
+textutils/utils.py
+textutils_py.egg-info/PKG-INFO
+textutils_py.egg-info/SOURCES.txt
+textutils_py.egg-info/dependency_links.txt
+textutils_py.egg-info/top_level.txt

textutils_py-0.1.1/textutils_py.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

textutils_py-0.1.1/textutils_py.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+tests
+textutils