\db_path style

ntfs_utils/db_node.py

@@ -3,8 +3,7 @@ import os
 import sqlite3
 from datetime import datetime
 
-# 导入你的模块函数
-from mft_analyze import GetFile80hPattern, GetFragmentData, ExtractSequenceHexValues, hex_list_to_int
+from ntfs_utils.mft_analyze import GetFile80hPattern, GetFragmentData, ExtractSequenceHexValues, hex_list_to_int
 
 
 # 工具函数：获取文件扩展名
@@ -132,11 +131,20 @@ def GetFragmentLength(fragment):
 
 
 # 主函数：将 db_path 数据导入 db_node
-# 主函数：将 db_path 数据导入 db_node
-def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
+def InsertNodeDataToDB(volume_letter: str, db_path='../src/db_ntfs_info.db', table_name='db_node', batch_size=20):
     conn = sqlite3.connect(db_path)
     cursor = conn.cursor()
 
+    volume_letter = volume_letter.upper().strip()
+    if len(volume_letter) == 1:
+        volume_root = f"{volume_letter}:\\"
+    elif volume_letter.endswith(':'):
+        volume_root = f"{volume_letter}\\"
+    else:
+        volume_root = f"{volume_letter}:\\"  # 支持 "Y" 或 "Y:" 输入
+
+    print(f"🔍 当前处理磁盘根目录：{volume_root}")
+
     group_id = GetFirstGroupId(cursor)
     user_id = GetFirstUserId(cursor)
     device_id = GetDeviceId(cursor)
@@ -144,8 +152,26 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
     cursor.execute("SELECT ID, Path, Name, ParentID FROM db_path")
     rows = cursor.fetchall()
 
+    insert_fields = [
+        'PathID', 'ParentID', 'NameHash', 'PathHash',
+        'ExtendNameID', 'DirLayer', 'GroupID', 'UserID',
+        'FileCreateTime', 'FileModifyTime', 'FileAccessTime', 'FileAuthTime',
+        'FileSize', 'FileMode', 'FileHash', 'ExtentCount',
+        # extent 字段
+        "extent1_DeviceID", "extent1_Location", "extent1_Length",
+        "extent2_DeviceID", "extent2_Location", "extent2_Length",
+        "extent3_DeviceID", "extent3_Location", "extent3_Length",
+        "extent4_DeviceID", "extent4_Location", "extent4_Length"
+    ]
+    insert_placeholders = ', '.join('?' * len(insert_fields))
+    insert_sql = f"INSERT INTO {table_name} ({', '.join(insert_fields)}) VALUES ({insert_placeholders})"
+
+    batch = []
+
     for row in rows:
-        path_id, full_path, name, parent_id = row
+        path_id, relative_path, name, parent_id = row
+
+        full_path = os.path.join(volume_root, relative_path)
 
         # 检查是否已存在相同 PathID
         cursor.execute("SELECT COUNT(*) FROM db_node WHERE PathID = ?", (path_id,))
@@ -154,13 +180,10 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
             print(f"⚠️ PathID {path_id} 已存在，跳过插入")
             continue
 
-        # 获取文件的80h属性数据
         try:
             file80h_pattern = GetFile80hPattern(full_path)
             fragments = GetFragmentData(file80h_pattern)
-            extent_count = min(len(fragments), 4)  # 最多支持4个fragment
-            print(f"✅ 分片数量为: {extent_count}")
-
+            extent_count = min(len(fragments), 4)
         except Exception as e:
             print(f"⚠️ 获取 ExtentCount 失败，使用默认值 0: {e}")
             fragments = []
@@ -168,10 +191,9 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
 
         # 计算字段
         name_hash = hashlib.sha256(name.encode()).hexdigest()
-        dir_layer = GetDirLayer(full_path)
+        dir_layer = GetDirLayer(relative_path)
         extend_name_id = GetExtendNameId(name, cursor)
 
-        # ✅ 现在可以安全调用 GetFileSize(file80h_pattern)
         try:
             file_size = GetFileSize(file80h_pattern)
         except Exception as e:
@@ -180,7 +202,7 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
 
         file_hash = GetFileHash(full_path)
 
-        # 获取文件的时间属性
+        # 获取时间信息
         file_times = GetFilesTime(full_path)
         create_time = file_times["FileCreateTime"]
         modify_time = file_times["FileModifyTime"]
@@ -192,21 +214,7 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
         path_hash_result = cursor.fetchone()
         path_hash = path_hash_result[0] if path_hash_result else ""
 
-        # 构建插入语句字段和参数（保持原样）
-        fields = [
-            'PathID', 'ParentID', 'NameHash', 'PathHash',
-            'ExtendNameID', 'DirLayer', 'GroupID', 'UserID',
-            'FileCreateTime', 'FileModifyTime', 'FileAccessTime', 'FileAuthTime',
-            'FileSize', 'FileMode', 'FileHash', 'ExtentCount'
-        ]
-        values = [
-            path_id, parent_id, name_hash, path_hash,
-            extend_name_id, dir_layer, group_id, user_id,
-            create_time, modify_time, access_time, auth_time,
-            file_size, 'default', file_hash, extent_count
-        ]
-
-        # 处理 Extent 片段字段
+        # 构建 extent 字段
         extent_data = []
         for i in range(4):  # 最多4个 extent
             if i < len(fragments):
@@ -217,27 +225,34 @@ def InsertNodeDataToDB(db_path='../src/db_ntfs_info.db', table_name='db_node'):
             else:
                 extent_data.extend([None, None, None])
 
-        # 拼接字段和值
-        extent_fields = [
-            "extent1_DeviceID", "extent1_Location", "extent1_Length",
-            "extent2_DeviceID", "extent2_Location", "extent2_Length",
-            "extent3_DeviceID", "extent3_Location", "extent3_Length",
-            "extent4_DeviceID", "extent4_Location", "extent4_Length"
+        # 构建插入数据
+        values = [
+            path_id, parent_id, name_hash, path_hash,
+            extend_name_id, dir_layer, group_id, user_id,
+            create_time, modify_time, access_time, auth_time,
+            file_size, 'default', file_hash, extent_count,
+            *extent_data
         ]
-        fields += extent_fields
-        values += extent_data
 
-        # 构建 SQL 插入语句
-        placeholders = ', '.join('?' * len(values))
-        insert_sql = f"INSERT INTO {table_name} ({', '.join(fields)}) VALUES ({placeholders})"
+        batch.append(values)
 
-        # 执行插入
-        cursor.execute(insert_sql, values)
+        # 批量插入
+        if len(batch) >= batch_size:
+            cursor.executemany(insert_sql, batch)
+            conn.commit()
+            print(f"✅ 提交一批 {len(batch)} 条记录到 {table_name}")
+            batch.clear()
+
+    # 插入剩余不足一批的数据
+    if batch:
+        cursor.executemany(insert_sql, batch)
+        conn.commit()
+        print(f"✅ 提交最后一批 {len(batch)} 条记录到 {table_name}")
 
-    conn.commit()
     conn.close()
     print(f"✅ 数据已成功插入到 {table_name} 表")
 
 
-if __name__ == '__main__':
-    InsertNodeDataToDB()
+if __name__ == "__main__":
+    volume_letter_test = "Y"
+    InsertNodeDataToDB(volume_letter=volume_letter_test)