auto-coder 1.0.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

autocoder/common/text_similarity/demo.py

@@ -0,0 +1,216 @@
+
+
+#!/usr/bin/env python3
+"""
+Text Similarity Module Demo
+
+演示两个版本的 get_best_matching_window 函数的差异和用法。
+"""
+
+import sys
+import os
+
+# 添加项目根目录到Python路径
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '../../../..'))
+sys.path.insert(0, project_root)
+
+try:
+    from .text_similarity import TextSimilarity
+except ImportError:
+    from text_similarity import TextSimilarity
+
+
+def demo_two_versions():
+    """演示两个版本的get_best_matching_window函数"""
+    print("=" * 60)
+    print("Text Similarity Module - 两个版本函数演示")
+    print("=" * 60)
+    
+    # 测试案例1：展示两个版本的基本差异
+    print("\n【测试案例1】基本功能对比")
+    print("-" * 40)
+    
+    source_text = """def hello():
+    print("Hello")
+    return True"""
+    
+    target_text = """import os
+import sys
+
+def hello():
+    print("Hello")
+    return True
+
+def goodbye():
+    print("Goodbye")
+    return False
+
+def main():
+    hello()
+    goodbye()
+
+if __name__ == "__main__":
+    main()"""
+    
+    similarity = TextSimilarity(source_text, target_text)
+    
+    # 版本1：原始实现（固定窗口大小）
+    print("版本1 - get_best_matching_window()（原始实现）:")
+    score1, window1 = similarity.get_best_matching_window()
+    print(f"  得分: {score1:.4f}")
+    print(f"  窗口大小: {len(window1.splitlines())} 行（固定为源文本行数）")
+    print(f"  匹配内容:\n{window1}")
+    
+    # 版本2：遍历所有窗口大小
+    print("\n版本2 - get_best_matching_window_all_sizes()（遍历所有窗口）:")
+    score2, window2, info2 = similarity.get_best_matching_window_all_sizes()
+    print(f"  得分: {score2:.4f}")
+    print(f"  最佳窗口大小: {info2['window_size']} 行")
+    print(f"  窗口位置: {info2['start_position']}-{info2['end_position']}")
+    print(f"  检查的窗口总数: {info2['total_windows_checked']}")
+    print(f"  匹配内容:\n{window2}")
+    
+    print(f"\n性能对比:")
+    print(f"  得分提升: {score2 - score1:.4f}")
+    print(f"  效率差异: 版本2检查了 {info2['total_windows_checked']} 个窗口，版本1只检查了 {similarity.n - similarity.m + 1} 个")
+    
+    # 测试案例2：展示版本2能找到更好匹配的情况
+    print("\n\n【测试案例2】版本2优势展示")
+    print("-" * 40)
+    
+    query = "error handling"
+    
+    code_base = """import logging
+logger = logging.getLogger(__name__)
+
+def process_data(data):
+    try:
+        result = complex_operation(data)
+        return result
+    except ValueError as e:
+        logger.error(f"Data processing error: {e}")
+        raise
+    except Exception as e:
+        logger.error(f"Unexpected error: {e}")
+        raise
+
+def error_handling():
+    print("This function handles errors")
+
+def main():
+    try:
+        process_data(None)
+    except Exception:
+        print("Error handled in main")"""
+    
+    similarity2 = TextSimilarity(query, code_base)
+    
+    print(f"查询: '{query}'")
+    
+    # 版本1结果
+    score1, window1 = similarity2.get_best_matching_window()
+    print(f"\n版本1结果:")
+    print(f"  得分: {score1:.4f}")
+    print(f"  匹配内容: {repr(window1)}")
+    
+    # 版本2结果
+    score2, window2, info2 = similarity2.get_best_matching_window_all_sizes()
+    print(f"\n版本2结果:")
+    print(f"  得分: {score2:.4f}")
+    print(f"  最佳窗口大小: {info2['window_size']} 行")
+    print(f"  匹配内容: {repr(window2)}")
+    
+    if score2 > score1:
+        print(f"\n✓ 版本2找到了更好的匹配！得分提升: {score2 - score1:.4f}")
+    elif score2 == score1:
+        print(f"\n= 两个版本找到了相同质量的匹配")
+    else:
+        print(f"\n? 意外情况：版本1得分更高")
+
+
+def demo_practical_usage():
+    """演示实际使用场景"""
+    print("\n\n【实际使用场景演示】")
+    print("-" * 40)
+    
+    # 代码片段搜索场景
+    function_signature = "def calculate(a, b):"
+    
+    codebase = """class Calculator:
+    def __init__(self):
+        self.history = []
+    
+    def add(self, a, b):
+        result = a + b
+        self.history.append(f"{a} + {b} = {result}")
+        return result
+    
+    def calculate(a, b):
+        return a * b
+    
+    def subtract(self, a, b):
+        result = a - b
+        self.history.append(f"{a} - {b} = {result}")
+        return result
+    
+    def calculate_advanced(self, operation, a, b):
+        if operation == "power":
+            return a ** b
+        elif operation == "divide":
+            return a / b if b != 0 else None
+        return None"""
+    
+    print(f"搜索函数签名: '{function_signature}'")
+    
+    similarity = TextSimilarity(function_signature, codebase)
+    
+    # 获取所有窗口的相似度排序
+    all_matches = similarity.get_window_similarities()
+    
+    print(f"\n找到 {len(all_matches)} 个可能的匹配:")
+    for i, (start_pos, score, window_text) in enumerate(all_matches[:3]):
+        print(f"  {i+1}. 得分: {score:.4f} | 位置: {start_pos} | 内容: {repr(window_text[:30])}...")
+    
+    # 比较两个版本
+    score1, window1 = similarity.get_best_matching_window()
+    score2, window2, info2 = similarity.get_best_matching_window_all_sizes()
+    
+    print(f"\n版本对比:")
+    print(f"  版本1 (固定窗口): {score1:.4f}")
+    print(f"  版本2 (全搜索): {score2:.4f}")
+    print(f"  版本2检查了 {info2['total_windows_checked']} 个窗口")
+
+
+def demo_statistics():
+    """演示统计功能"""
+    print("\n\n【统计信息演示】")
+    print("-" * 40)
+    
+    text_a = "Hello World\nPython Programming"
+    text_b = "Welcome to Python\nHello World\nProgramming Tutorial\nGoodbye World"
+    
+    similarity = TextSimilarity(text_a, text_b)
+    stats = similarity.get_statistics()
+    
+    print("文本统计信息:")
+    for key, value in stats.items():
+        print(f"  {key}: {value}")
+    
+    # 相似度矩阵
+    matrix = similarity.get_similarity_matrix()
+    print(f"\n相似度矩阵 ({len(matrix)}x{len(matrix[0])}):")
+    for i, row in enumerate(matrix):
+        formatted_row = [f"{val:.2f}" for val in row]
+        print(f"  行{i+1}: {formatted_row}")
+
+
+if __name__ == "__main__":
+    demo_two_versions()
+    demo_practical_usage()
+    demo_statistics()
+    
+    print("\n" + "=" * 60)
+    print("演示完成！")
+    print("=" * 60)
+
+

autocoder/common/text_similarity/examples.py

@@ -0,0 +1,266 @@
+
+
+"""
+Text Similarity Module Usage Examples
+
+展示文本相似度模块的各种使用方式和应用场景。
+"""
+
+import sys
+import os
+
+
+from autocoder.common.text_similarity.text_similarity import TextSimilarity
+from autocoder.common.text_similarity.utils import compare_texts_simple, find_best_matches, analyze_text_similarity
+
+
+
+def basic_usage_example():
+    """基本使用示例"""
+    print("=== 基本使用示例 ===")
+    
+    # 示例代码片段
+    code_snippet = """def calculate_sum(a, b):
+    result = a + b
+    return result"""
+    
+    full_code = """import math
+
+def calculate_sum(a, b):
+    result = a + b
+    return result
+
+def calculate_product(a, b):
+    result = a * b
+    return result
+
+def main():
+    print(calculate_sum(1, 2))
+    print(calculate_product(3, 4))
+
+if __name__ == "__main__":
+    main()"""
+    
+    # 创建相似度计算器
+    similarity = TextSimilarity(code_snippet, full_code)
+    
+    # 基本匹配
+    score, window = similarity.get_best_matching_window()
+    print(f"基本匹配得分: {score:.4f}")
+    print(f"匹配到的代码片段:\n{window}")
+    
+    # 全面匹配
+    full_score, full_window, info = similarity.get_best_matching_window_all_sizes()
+    print(f"\n全面匹配得分: {full_score:.4f}")
+    print(f"最佳窗口大小: {info['window_size']} 行")
+    print(f"匹配位置: {info['start_position']}-{info['end_position']}")
+    print(f"匹配到的代码片段:\n{full_window}")
+    
+    print(f"\n得分提升: {full_score - score:.4f}")
+
+
+def documentation_matching_example():
+    """文档匹配示例"""
+    print("\n=== 文档匹配示例 ===")
+    
+    query_text = """如何使用Python处理文件？
+需要打开文件、读取内容、处理数据。"""
+    
+    documentation = """Python文件操作指南
+
+1. 文件打开
+使用open()函数打开文件：
+file = open('filename.txt', 'r')
+
+2. 读取文件内容
+可以使用read()、readline()或readlines()方法
+
+3. 如何使用Python处理文件？
+需要打开文件、读取内容、处理数据。
+这是Python中常见的文件操作流程。
+
+4. 文件写入
+使用write()方法写入内容
+
+5. 关闭文件
+记得使用close()方法关闭文件"""
+    
+    # 使用工具函数进行分析
+    result = analyze_text_similarity(query_text, documentation)
+    
+    print(f"最佳匹配得分: {result['comprehensive_matching']['score']:.4f}")
+    print(f"检查了 {result['summary']['total_windows_checked']} 个窗口")
+    print(f"匹配的文档片段:\n{result['comprehensive_matching']['window']}")
+
+
+def code_similarity_comparison():
+    """代码相似度比较示例"""
+    print("\n=== 代码相似度比较示例 ===")
+    
+    original_function = """def fibonacci(n):
+    if n <= 1:
+        return n
+    return fibonacci(n-1) + fibonacci(n-2)"""
+    
+    code_file = """import sys
+
+def factorial(n):
+    if n <= 1:
+        return 1
+    return n * factorial(n-1)
+
+def fibonacci(n):
+    if n <= 1:
+        return n
+    return fibonacci(n-1) + fibonacci(n-2)
+
+def prime_check(n):
+    if n < 2:
+        return False
+    for i in range(2, int(n**0.5) + 1):
+        if n % i == 0:
+            return False
+    return True
+
+def main():
+    print(fibonacci(10))
+    print(factorial(5))"""
+    
+    # 查找最佳匹配
+    matches = find_best_matches(original_function, code_file, top_k=3)
+    
+    print("前3个最佳匹配:")
+    for match in matches:
+        print(f"\n排名 {match['rank']}: 得分 {match['similarity_score']:.4f}")
+        print(f"位置: {match['start_position']}-{match['end_position']}")
+        print(f"匹配代码:\n{match['window_text']}")
+
+
+def performance_comparison_example():
+    """性能对比示例"""
+    print("\n=== 性能对比示例 ===")
+    
+    import time
+    
+    # 创建较大的测试文本
+    small_text = "def test():\n    return True"
+    large_text = "\n".join([f"def function_{i}():\n    return {i}" for i in range(50)])
+    
+    similarity = TextSimilarity(small_text, large_text)
+    
+    # 测试基本匹配性能
+    start_time = time.time()
+    basic_score, basic_window = similarity.get_best_matching_window()
+    basic_time = time.time() - start_time
+    
+    # 测试全面匹配性能
+    start_time = time.time()
+    full_score, full_window, info = similarity.get_best_matching_window_all_sizes()
+    full_time = time.time() - start_time
+    
+    print(f"基本匹配:")
+    print(f"  得分: {basic_score:.4f}")
+    print(f"  时间: {basic_time:.4f} 秒")
+    
+    print(f"\n全面匹配:")
+    print(f"  得分: {full_score:.4f}")
+    print(f"  时间: {full_time:.4f} 秒")
+    print(f"  检查窗口数: {info['total_windows_checked']}")
+    
+    print(f"\n性能对比:")
+    print(f"  得分提升: {full_score - basic_score:.4f}")
+    print(f"  时间比率: {full_time/basic_time:.2f}x")
+
+
+def text_analysis_example():
+    """文本分析示例"""
+    print("\n=== 文本分析示例 ===")
+    
+    poem_verse = """春眠不觉晓
+处处闻啼鸟"""
+    
+    full_poem = """春晓
+
+春眠不觉晓
+处处闻啼鸟
+夜来风雨声
+花落知多少
+
+这是孟浩然的著名诗作
+描写了春天清晨的美好景象"""
+    
+    # 获取详细统计信息
+    similarity = TextSimilarity(poem_verse, full_poem)
+    stats = similarity.get_statistics()
+    
+    print("文本统计信息:")
+    for key, value in stats.items():
+        print(f"  {key}: {value}")
+    
+    # 获取相似度矩阵
+    matrix = similarity.get_similarity_matrix()
+    print(f"\n相似度矩阵 ({len(matrix)}x{len(matrix[0])}):")
+    for i, row in enumerate(matrix):
+        print(f"  第{i+1}行: {[f'{val:.2f}' for val in row]}")
+
+
+def integration_example():
+    """集成应用示例"""
+    print("\n=== 集成应用示例 ===")
+    
+    # 模拟代码搜索场景
+    search_query = "处理用户输入验证"
+    
+    code_database = [
+        ("user_validation.py", """def validate_user_input(data):
+    if not data:
+        return False
+    # 处理用户输入验证
+    return True"""),
+        
+        ("data_processing.py", """def process_data(input_data):
+    cleaned = clean_data(input_data)
+    return cleaned"""),
+        
+        ("auth_system.py", """def authenticate_user(username, password):
+    # 用户身份验证
+    if validate_credentials(username, password):
+        return create_session(username)
+    return None
+
+def validate_credentials(username, password):
+    # 处理用户输入验证
+    return check_database(username, password)""")
+    ]
+    
+    print(f"搜索查询: '{search_query}'")
+    print("\n搜索结果:")
+    
+    results = []
+    for filename, code in code_database:
+        similarity = TextSimilarity(search_query, code)
+        score, window = similarity.get_best_matching_window()
+        results.append((filename, score, window))
+    
+    # 按相似度排序
+    results.sort(key=lambda x: x[1], reverse=True)
+    
+    for i, (filename, score, window) in enumerate(results, 1):
+        print(f"\n{i}. {filename} (相似度: {score:.4f})")
+        print(f"   匹配片段: {window[:50]}...")
+
+
+if __name__ == "__main__":
+    """运行所有示例"""
+    print("文本相似度模块使用示例\n")
+    
+    basic_usage_example()
+    documentation_matching_example()
+    code_similarity_comparison()
+    performance_comparison_example()
+    text_analysis_example()
+    integration_example()
+    
+    print("\n=== 示例运行完成 ===")
+
+