初次提交

backend/check_files_table.py

@@ -0,0 +1,219 @@
+#!/usr/bin/env python3
+"""
+检查数据库files表和实际文件存储情况
+"""
+
+import mysql.connector
+import os
+import hashlib
+
+def check_database_files():
+    """检查数据库中的文件记录"""
+
+    try:
+        # 连接数据库
+        conn = mysql.connector.connect(
+            host="101.126.85.76",
+            user="mytest_db",
+            password="mytest_db",
+            database="mytest_db"
+        )
+        cursor = conn.cursor()
+
+        # 查询files表中的所有记录
+        cursor.execute("""
+            SELECT id, user_id, original_filename, filename, file_path, file_size,
+                   file_hash, mime_type, created_at
+            FROM files
+            ORDER BY created_at DESC
+        """)
+
+        files = cursor.fetchall()
+
+        print("=== 数据库 files 表中的记录 ===")
+        if files:
+            for file in files:
+                (id, user_id, original_filename, filename, file_path,
+                 file_size, file_hash, mime_type, created_at) = file
+
+                print(f"ID: {id}")
+                print(f"  用户ID: {user_id}")
+                print(f"  原始文件名: {original_filename}")
+                print(f"  存储文件名: {filename}")
+                print(f"  文件路径: {file_path}")
+                print(f"  文件大小: {file_size} bytes")
+                print(f"  文件哈希: {file_hash}")
+                print(f"  MIME类型: {mime_type}")
+                print(f"  创建时间: {created_at}")
+                print("-" * 50)
+        else:
+            print("files 表中没有记录")
+
+        print(f"\n总记录数: {len(files)}")
+
+        # 检查每个文件是否真实存在
+        print("\n=== 文件存在性检查 ===")
+        existing_count = 0
+        missing_files = []
+
+        for file in files:
+            (id, user_id, original_filename, filename, file_path,
+             file_size, file_hash, mime_type, created_at) = file
+
+            full_path = os.path.join("uploads", filename)
+            if os.path.exists(full_path):
+                existing_count += 1
+                print(f"✅ ID {id}: {original_filename} - 文件存在")
+
+                # 检查文件大小
+                actual_size = os.path.getsize(full_path)
+                if actual_size != file_size:
+                    print(f"   ⚠️  文件大小不匹配! 数据库: {file_size}, 实际: {actual_size}")
+
+                # 检查文件哈希
+                try:
+                    with open(full_path, 'rb') as f:
+                        content = f.read()
+                        actual_hash = hashlib.sha256(content).hexdigest()
+                        if actual_hash != file_hash:
+                            print(f"   ❌ 文件哈希不匹配! 数据库: {file_hash}")
+                            print(f"      实际: {actual_hash}")
+                except Exception as e:
+                    print(f"   ❌ 无法读取文件或计算哈希: {e}")
+
+            else:
+                missing_files.append((id, original_filename, filename))
+                print(f"❌ ID {id}: {original_filename} - 文件不存在!")
+
+        print(f"\n实际存在的文件: {existing_count}")
+        print(f"缺失的文件: {len(missing_files)}")
+
+        if missing_files:
+            print("\n缺失文件详情:")
+            for (id, original_filename, filename) in missing_files:
+                print(f"  ID {id}: {original_filename} (应存储为: {filename})")
+
+    except Exception as e:
+        print(f"数据库查询出错: {e}")
+    finally:
+        if 'conn' in locals() and conn.is_connected():
+            cursor.close()
+            conn.close()
+
+def check_uploads_directory():
+    """检查uploads目录中的实际文件"""
+
+    print("\n=== uploads 目录中的实际文件 ===")
+
+    uploads_dir = "uploads"
+    if os.path.exists(uploads_dir):
+        files = os.listdir(uploads_dir)
+        if files:
+            print(f"目录: {uploads_dir}")
+            print(f"文件数量: {len(files)}")
+
+            for file in files:
+                file_path = os.path.join(uploads_dir, file)
+                file_size = os.path.getsize(file_path)
+
+                # 计算文件哈希
+                try:
+                    with open(file_path, 'rb') as f:
+                        content = f.read()
+                        file_hash = hashlib.sha256(content).hexdigest()
+
+                    # 尝试读取文本内容
+                    try:
+                        with open(file_path, 'r', encoding='utf-8') as f:
+                            text_content = f.read()
+                        content_preview = text_content[:100] + "..." if len(text_content) > 100 else text_content
+                        content_preview = repr(content_preview)  # 显示引号和特殊字符
+                    except:
+                        content_preview = "(二进制文件)"
+
+                except Exception as e:
+                    file_hash = f"无法计算哈希: {e}"
+                    content_preview = f"无法读取: {e}"
+
+                print(f"\n📄 {file}")
+                print(f"   大小: {file_size} bytes")
+                print(f"   哈希: {file_hash}")
+                print(f"   内容预览: {content_preview}")
+        else:
+            print(f"目录 {uploads_dir} 为空")
+    else:
+        print(f"目录 {uploads_dir} 不存在")
+
+def check_file_integrity():
+    """检查文件完整性，对比数据库和实际文件"""
+
+    print("\n=== 文件完整性检查 ===")
+
+    try:
+        # 连接数据库
+        conn = mysql.connector.connect(
+            host="101.126.85.76",
+            user="mytest_db",
+            password="mytest_db",
+            database="mytest_db"
+        )
+        cursor = conn.cursor()
+
+        # 查询所有文件
+        cursor.execute("SELECT id, filename, file_hash, file_size FROM files")
+        db_files = cursor.fetchall()
+
+        integrity_issues = []
+
+        for (id, filename, expected_hash, expected_size) in db_files:
+            full_path = os.path.join("uploads", filename)
+
+            if os.path.exists(full_path):
+                # 检查大小
+                actual_size = os.path.getsize(full_path)
+                if actual_size != expected_size:
+                    integrity_issues.append(f"ID {id}: 文件大小不匹配 (期望: {expected_size}, 实际: {actual_size})")
+                    continue
+
+                # 检查哈希
+                try:
+                    with open(full_path, 'rb') as f:
+                        content = f.read()
+                        actual_hash = hashlib.sha256(content).hexdigest()
+
+                    if actual_hash != expected_hash:
+                        integrity_issues.append(f"ID {id}: 文件哈希不匹配")
+                        print(f"   期望哈希: {expected_hash}")
+                        print(f"   实际哈希: {actual_hash}")
+
+                except Exception as e:
+                    integrity_issues.append(f"ID {id}: 无法计算文件哈希 - {e}")
+            else:
+                integrity_issues.append(f"ID {id}: 文件不存在")
+
+        if integrity_issues:
+            print(f"❌ 发现 {len(integrity_issues)} 个完整性问题:")
+            for issue in integrity_issues:
+                print(f"   - {issue}")
+        else:
+            print("✅ 所有文件完整性检查通过!")
+
+    except Exception as e:
+        print(f"完整性检查出错: {e}")
+    finally:
+        if 'conn' in locals() and conn.is_connected():
+            cursor.close()
+            conn.close()
+
+if __name__ == "__main__":
+    check_database_files()
+    check_uploads_directory()
+    check_file_integrity()
+
+    print("\n=== 总结 ===")
+    print("文件存储情况:")
+    print("1. 数据库存储文件的元数据信息")
+    print("2. 实际文件存储在 backend/uploads/ 目录")
+    print("3. 文件名使用UUID格式确保唯一性")
+    print("4. 通过file_hash确保文件完整性")
+    print("5. 支持文件去重功能")