oafuncs 0.0.97.13__py3-none-any.whl → 0.0.97.14__py3-none-any.whl

oafuncs/_script/netcdf_merge.py

@@ -1,354 +1,107 @@
-#!/usr/bin/env python
-# coding=utf-8
-"""
-Author: Liu Kun && 16031215@qq.com
-Date: 2025-03-30 11:16:29
-LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2025-03-30 11:16:31
-FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\_script\\netcdf_merge.py
-Description:
-EditPlatform: vscode
-ComputerInfo: XPS 15 9510
-SystemInfo: Windows 11
-Python Version: 3.12
-"""
-
-import logging
 import os
-from typing import Dict, List, Union
-
-import numpy as np
-import xarray as xr
+from typing import List, Optional, Union
 from dask.diagnostics import ProgressBar
+import xarray as xr
+from oafuncs import pbar
 
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-def merge(file_list: Union[str, List[str]], var_name: Union[str, List[str], None] = None, dim_name: str = "time", target_filename: str = "merged.nc", chunk_config: Dict = {"time": 1000}, compression: Union[bool, Dict] = True, sanity_check: bool = True, overwrite: bool = True, parallel: bool = True) -> None:
+def merge_nc(file_list: Union[str, List[str]], var_name: Optional[Union[str, List[str]]] = None, dim_name: Optional[str] = None, target_filename: Optional[str] = None) -> None:
     """
-    Ultimate NetCDF merge function
+    Description:
+        Merge variables from multiple NetCDF files along a specified dimension and write to a new file.
+        If var_name is a string, it is considered a single variable; if it is a list and has only one element, it is also a single variable;
+        If the list has more than one element, it is a multi-variable; if var_name is None, all variables are merged.
 
     Parameters:
-        file_list: List of file paths or single file path
-        var_name: Variables to merge (single variable name/list of variables/None means all)
-        dim_name: Dimension to merge along, default is 'time'
-        target_filename: Output file path
-        chunk_config: Dask chunking configuration, e.g. {"time": 1000}
-        compression: Compression configuration (True enables default compression, or custom encoding dictionary)
-        sanity_check: Whether to perform data integrity validation
-        overwrite: Whether to overwrite existing files
-        parallel: Whether to enable parallel processing
+        file_list: List of NetCDF file paths or a single file path as a string
+        var_name: Name of the variable to be extracted or a list of variable names, default is None, which means all variables are extracted
+        dim_name: Dimension name used for merging
+        target_filename: Target file name after merging
 
     Example:
-        merge(["data1.nc", "data2.nc"],
-             var_name=["temp", "salt"],
-             target_filename="result.nc",
-             chunk_config={"time": 500})
+        merge(file_list, var_name='u', dim_name='time', target_filename='merged.nc')
+        merge(file_list, var_name=['u', 'v'], dim_name='time', target_filename='merged.nc')
+        merge(file_list, var_name=None, dim_name='time', target_filename='merged.nc')
     """
-    # ------------------------ Parameter preprocessing ------------------------#
-    file_list = _validate_and_preprocess_inputs(file_list, target_filename, overwrite)
-    all_vars, var_names = _determine_variables(file_list, var_name)
-    static_vars = _identify_static_vars(file_list[0], var_names, dim_name)
-
-    # Estimate required memory for processing
-    _estimate_memory_usage(file_list, var_names, chunk_config)
-
-    # ------------------------ Data validation phase ------------------------#
-    if sanity_check:
-        _perform_sanity_checks(file_list, var_names, dim_name, static_vars)
-
-    # ------------------------ Core merging logic ------------------------#
-    with xr.set_options(keep_attrs=True):  # Preserve metadata attributes
-        # Merge dynamic variables
-        merged_ds = xr.open_mfdataset(
-            file_list,
-            combine="nested",
-            concat_dim=dim_name,
-            data_vars=[var for var in var_names if var not in static_vars],
-            chunks=chunk_config,
-            parallel=parallel,
-            preprocess=lambda ds: ds[var_names],  # Only load target variables
-        )
-
-        # Process static variables
-        if static_vars:
-            with xr.open_dataset(file_list[0], chunks=chunk_config) as ref_ds:
-                merged_ds = merged_ds.assign({var: ref_ds[var] for var in static_vars})
-
-    # ------------------------ Time dimension processing ------------------------#
-    if dim_name == "time":
-        merged_ds = _process_time_dimension(merged_ds)
-
-    # ------------------------ File output ------------------------#
-    encoding = _generate_encoding_config(merged_ds, compression)
-    _write_to_netcdf(merged_ds, target_filename, encoding)
-
-
-# ------------------------ Helper functions ------------------------#
-def _validate_and_preprocess_inputs(file_list: Union[str, List[str]], target_filename: str, overwrite: bool) -> List[str]:
-    """Input parameter validation and preprocessing"""
-    if not file_list:
-        raise ValueError("File list cannot be empty")
+    
+    if target_filename is None:
+        target_filename = "merged.nc"
 
-    file_list = [file_list] if isinstance(file_list, str) else file_list
-    for f in file_list:
-        if not os.path.exists(f):
-            raise FileNotFoundError(f"Input file does not exist: {f}")
+    # 确保目标路径存在
+    target_dir = os.path.dirname(target_filename)
+    if target_dir and not os.path.exists(target_dir):
+        os.makedirs(target_dir)
 
-    target_dir = os.path.dirname(os.path.abspath(target_filename))
-    os.makedirs(target_dir, exist_ok=True)
-
-    if os.path.exists(target_filename):
-        if overwrite:
-            logger.warning(f"Overwriting existing file: {target_filename}")
-            os.remove(target_filename)
-        else:
-            raise FileExistsError(f"Target file already exists: {target_filename}")
-
-    return file_list
-
-
-def _determine_variables(file_list: List[str], var_name: Union[str, List[str], None]) -> tuple:
-    """Determine the list of variables to process"""
-    with xr.open_dataset(file_list[0]) as ds:
-        all_vars = list(ds.data_vars.keys())
+    if isinstance(file_list, str):
+        file_list = [file_list]
 
+    # 初始化变量名列表
     if var_name is None:
-        return all_vars, all_vars
+        with xr.open_dataset(file_list[0]) as ds:
+            var_names = list(ds.variables.keys())
     elif isinstance(var_name, str):
-        if var_name not in all_vars:
-            raise ValueError(f"Invalid variable name: {var_name}")
-        return all_vars, [var_name]
+        var_names = [var_name]
     elif isinstance(var_name, list):
-        if not var_name:  # Handle empty list case
-            logger.warning("Empty variable list provided, will use all variables")
-            return all_vars, all_vars
-        invalid_vars = set(var_name) - set(all_vars)
-        if invalid_vars:
-            raise ValueError(f"Invalid variable names: {invalid_vars}")
-        return all_vars, var_name
+        var_names = var_name
     else:
-        raise TypeError("var_name parameter must be of type str/list/None")
-
-
-def _identify_static_vars(sample_file: str, var_names: List[str], dim_name: str) -> List[str]:
-    """Identify static variables"""
-    with xr.open_dataset(sample_file) as ds:
-        return [var for var in var_names if dim_name not in ds[var].dims]
+        raise ValueError("var_name must be a string, a list of strings, or None")
 
+    # 初始化合并数据字典
+    merged_data = {}
 
-def _perform_sanity_checks(file_list: List[str], var_names: List[str], dim_name: str, static_vars: List[str]) -> None:
-    """Perform data integrity validation"""
-    logger.info("Performing data integrity validation...")
-
-    # Check consistency of static variables
-    with xr.open_dataset(file_list[0]) as ref_ds:
-        for var in static_vars:
-            ref = ref_ds[var]
-            for f in file_list[1:]:
-                with xr.open_dataset(f) as ds:
-                    if not ref.equals(ds[var]):
-                        raise ValueError(f"Static variable {var} inconsistent\nReference file: {file_list[0]}\nProblem file: {f}")
-
-    # Check dimensions of dynamic variables
-    dim_sizes = {}
-    for f in file_list:
-        with xr.open_dataset(f) as ds:
+    for i, file in pbar(enumerate(file_list),description="Reading files", color="green",total=len(file_list)):
+        with xr.open_dataset(file) as ds:
             for var in var_names:
-                if var not in static_vars:
-                    dims = ds[var].dims
-                    if dim_name not in dims:
-                        raise ValueError(f"Variable {var} in file {f} missing merge dimension {dim_name}")
-                    dim_sizes.setdefault(var, []).append(ds[var].sizes[dim_name])
-
-    # Check dimension continuity
-    for var, sizes in dim_sizes.items():
-        if len(set(sizes[1:])) > 1:
-            raise ValueError(f"Variable {var} has inconsistent {dim_name} dimension lengths: {sizes}")
-
-
-def _process_time_dimension(ds: xr.Dataset) -> xr.Dataset:
-    """Special processing for time dimension"""
-    if "time" not in ds.dims:
-        return ds
-
-    # Sort and deduplicate
-    ds = ds.sortby("time")
-    # Find indices of unique timestamps
-    _, index = np.unique(ds["time"], return_index=True)
-    # No need to sort indices again as we want to keep original time order
-    return ds.isel(time=index)
-
-
-def _generate_encoding_config(ds: xr.Dataset, compression: Union[bool, Dict]) -> Dict:
-    """Generate compression encoding configuration"""
-    if not compression:
-        return {}
-
-    # Default compression settings base
-    def _get_default_encoding(var):
-        return {"zlib": True, "complevel": 3, "dtype": "float32" if ds[var].dtype == "float64" else ds[var].dtype}
-
-    # Handle custom compression configuration
-    encoding = {}
-    if isinstance(compression, dict):
-        for var in ds.data_vars:
-            encoding[var] = _get_default_encoding(var)
-            encoding[var].update(compression.get(var, {}))  # Use dict.update() to merge dictionaries
-    else:
-        for var in ds.data_vars:
-            encoding[var] = _get_default_encoding(var)
-
-    return encoding
-
-def _calculate_file_size(filepath: str) -> str:
-    """Calculate file size with adaptive unit conversion"""
-    if os.path.exists(filepath):
-        size_in_bytes = os.path.getsize(filepath)
-        if size_in_bytes < 1e3:
-            return f"{size_in_bytes:.2f} B"
-        elif size_in_bytes < 1e6:
-            return f"{size_in_bytes / 1e3:.2f} KB"
-        elif size_in_bytes < 1e9:
-            return f"{size_in_bytes / 1e6:.2f} MB"
-        else:
-            return f"{size_in_bytes / 1e9:.2f} GB"
-    else:
-        raise FileNotFoundError(f"File not found: {filepath}")
-
-def _write_to_netcdf(ds: xr.Dataset, filename: str, encoding: Dict) -> None:
-    """Improved safe writing to NetCDF file"""
-    logger.info("Starting file write...")
-    unlimited_dims = [dim for dim in ds.dims if ds[dim].encoding.get("unlimited", False)]
-
-    delayed = ds.to_netcdf(filename, encoding=encoding, compute=False, unlimited_dims=unlimited_dims)
-
-    try:
+                data_var = ds[var]
+                if dim_name in data_var.dims:
+                    merged_data.setdefault(var, []).append(data_var)
+                elif var not in merged_data:
+                    merged_data[var] = data_var.fillna(0)  # 用0填充NaN值
+
+    for var in pbar(merged_data, description="Merging variables", color="#9b45d1"):
+        if isinstance(merged_data[var], list):
+            merged_data[var] = xr.concat(merged_data[var], dim=dim_name).fillna(0)
+        # print(f"Variable '{var}' merged: min={merged_data[var].min().values:.3f}, max={merged_data[var].max().values:.3f}, mean={merged_data[var].mean().values:.3f}")
+
+    # 修改写入数据部分，支持压缩并设置基数和比例因子
+    # print("\nWriting data to file ...")
+    if os.path.exists(target_filename):
+        print("Warning: The target file already exists. Removing it ...")
+        os.remove(target_filename)
+
+    with xr.Dataset(merged_data) as merged_dataset:
+        encoding = {}
+        for var in merged_dataset.data_vars:
+            data = merged_dataset[var].values
+            # print(f"Variable '{var}' ready for writing: min={data.min():.3f}, max={data.max():.3f}, mean={data.mean():.3f}")
+            if data.dtype.kind in {"i", "u", "f"}:  # 仅对数值型数据进行压缩
+                data_range = data.max() - data.min()
+                if data_range > 0:  # 避免范围过小导致的精度问题
+                    scale_factor = data_range / (2**16 - 1)
+                    add_offset = data.min()
+                    encoding[var] = {
+                        "zlib": True,
+                        "complevel": 4,
+                        "dtype": "int16",
+                        "scale_factor": scale_factor,
+                        "add_offset": add_offset,
+                        "_FillValue": -32767,
+                    }
+                else:
+                    encoding[var] = {"zlib": True, "complevel": 4}  # 范围过小时禁用缩放
+            else:
+                encoding[var] = {"zlib": True, "complevel": 4}  # 非数值型数据不使用缩放
+
+        # 确保写入时不会因编码问题导致数据丢失
+        # merged_dataset.to_netcdf(target_filename, encoding=encoding)
+        delayed_write = merged_dataset.to_netcdf(target_filename, encoding=encoding, compute=False)
         with ProgressBar():
-            delayed.compute()
-
-        logger.info(f"Merge completed → {filename}")
-        # logger.info(f"File size: {os.path.getsize(filename) / 1e9:.2f}GB")
-        logger.info(f"File size: {_calculate_file_size(filename)}")
-    except MemoryError as e:
-        _handle_write_error(filename, "Insufficient memory to complete file write. Try adjusting chunk_config parameter to reduce memory usage", e)
-    except Exception as e:
-        _handle_write_error(filename, f"Failed to write file: {str(e)}", e)
-
-
-def _handle_write_error(filename: str, message: str, exception: Exception) -> None:
-    """Unified handling of file write exceptions"""
-    logger.error(message)
-    if os.path.exists(filename):
-        os.remove(filename)
-    raise exception
+            delayed_write.compute()
 
-
-def _estimate_memory_usage(file_list: List[str], var_names: List[str], chunk_config: Dict) -> None:
-    """Improved memory usage estimation"""
-    try:
-        total_size = 0
-        sample_file = file_list[0]
-        with xr.open_dataset(sample_file) as ds:
-            for var in var_names:
-                if var in ds:
-                    # Consider variable dimension sizes
-                    var_size = np.prod([ds[var].sizes[dim] for dim in ds[var].dims]) * ds[var].dtype.itemsize
-                    total_size += var_size * len(file_list)
-
-        # Estimate memory usage during Dask processing (typically 2-3x original data)
-        estimated_memory = total_size * 3
-
-        if estimated_memory > 8e9:
-            logger.warning(f"Estimated memory usage may be high (approx. {estimated_memory / 1e9:.1f}GB). If memory issues occur, adjust chunk_config parameter: {chunk_config}")
-    except Exception as e:
-        logger.debug(f"Memory estimation failed: {str(e)}")
+    print(f'\nFile "{target_filename}" has been successfully created.')
 
 
+# Example usage
 if __name__ == "__main__":
-    # 示例文件列表（请替换为实际文件路径）
-    sample_files = ["data/file1.nc", "data/file2.nc", "data/file3.nc"]
-
-    # 示例1: 基础用法 - 合并全部变量
-    print("\n" + "=" * 40)
-    print("示例1: 合并所有变量（默认配置）")
-    merge(file_list=sample_files, target_filename="merged_all_vars.nc")
-
-    # 示例2: 合并指定变量
-    print("\n" + "=" * 40)
-    print("示例2: 合并指定变量（温度、盐度）")
-    merge(
-        file_list=sample_files,
-        var_name=["temperature", "salinity"],
-        target_filename="merged_selected_vars.nc",
-        chunk_config={"time": 500},  # 更保守的内存分配
-    )
-
-    # 示例3: 自定义压缩配置
-    print("\n" + "=" * 40)
-    print("示例3: 自定义压缩参数")
-    merge(file_list=sample_files, var_name="chlorophyll", compression={"chlorophyll": {"zlib": True, "complevel": 5, "dtype": "float32"}}, target_filename="merged_compressed.nc")
-
-    # 示例4: 处理大型数据集
-    print("\n" + "=" * 40)
-    print("示例4: 大文件分块策略")
-    merge(file_list=sample_files, chunk_config={"time": 2000, "lat": 100, "lon": 100}, target_filename="merged_large_dataset.nc", parallel=True)
-
-    # 示例5: 时间维度特殊处理
-    print("\n" + "=" * 40)
-    print("示例5: 时间维度排序去重")
-    merge(
-        file_list=sample_files,
-        dim_name="time",
-        target_filename="merged_time_processed.nc",
-        sanity_check=True,  # 强制数据校验
-    )
-
-    # 示例6: 覆盖已存在文件
-    print("\n" + "=" * 40)
-    print("示例6: 强制覆盖现有文件")
-    try:
-        merge(
-            file_list=sample_files,
-            target_filename="merged_all_vars.nc",  # 与示例1相同文件名
-            overwrite=True,  # 显式启用覆盖
-        )
-    except FileExistsError as e:
-        print(f"捕获预期外异常: {str(e)}")
-
-    # 示例7: 禁用并行处理
-    print("\n" + "=" * 40)
-    print("示例7: 单线程模式运行")
-    merge(file_list=sample_files, target_filename="merged_single_thread.nc", parallel=False)
-
-    # 示例8: 处理特殊维度
-    print("\n" + "=" * 40)
-    print("示例8: 按深度维度合并")
-    merge(file_list=sample_files, dim_name="depth", var_name=["density", "oxygen"], target_filename="merged_by_depth.nc")
-
-    # 示例9: 混合变量类型处理
-    print("\n" + "=" * 40)
-    print("示例9: 混合静态/动态变量")
-    merge(
-        file_list=sample_files,
-        var_name=["bathymetry", "temperature"],  # bathymetry为静态变量
-        target_filename="merged_mixed_vars.nc",
-        sanity_check=True,  # 验证静态变量一致性
-    )
-
-    # 示例10: 完整配置演示
-    print("\n" + "=" * 40)
-    print("示例10: 全参数配置演示")
-    merge(
-        file_list=sample_files,
-        var_name=None,  # 所有变量
-        dim_name="time",
-        target_filename="merged_full_config.nc",
-        chunk_config={"time": 1000, "lat": 500, "lon": 500},
-        compression={"temperature": {"complevel": 4}, "salinity": {"zlib": False}},
-        sanity_check=True,
-        overwrite=True,
-        parallel=True,
-    )
+    files_to_merge = ["file1.nc", "file2.nc", "file3.nc"]
+    output_path = "merged_output.nc"
+    merge_nc(files_to_merge, var_name=None, dim_name="time", target_filename=output_path)

oafuncs/{oa_tool → _script}/parallel.py

@@ -2,10 +2,10 @@
 # coding=utf-8
 """
 Author: Liu Kun && 16031215@qq.com
-Date: 2025-01-11 19:47:08
+Date: 2025-04-04 20:19:23
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2025-03-18 19:21:36
-FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_tool\\parallel.py
+LastEditTime: 2025-04-04 20:19:23
+FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\_script\\parallel.py
 Description:
 EditPlatform: vscode
 ComputerInfo: XPS 15 9510
@@ -13,6 +13,8 @@ SystemInfo: Windows 11
 Python Version: 3.12
 """
 
+
+
 import contextlib
 import logging
 import multiprocessing as mp

oafuncs/oa_data.py

@@ -17,14 +17,13 @@ import itertools
 import multiprocessing as mp
 from concurrent.futures import ThreadPoolExecutor
 
+
 import numpy as np
 import salem
 import xarray as xr
-from scipy.interpolate import griddata
-from scipy.interpolate import interp1d
-from typing import Iterable
+from scipy.interpolate import griddata, interp1d
 
-__all__ = ["interp_along_dim", "interp_2d", "ensure_list", "mask_shapefile", "pbar"]
+__all__ = ["interp_along_dim", "interp_2d", "ensure_list", "mask_shapefile"]
 
 
 def ensure_list(input_data):
@@ -255,26 +254,6 @@ def mask_shapefile(data: np.ndarray, lons: np.ndarray, lats: np.ndarray, shapefi
         return None
 
 
-def pbar(iterable: Iterable, prefix: str = "", color: str = "cyan", cmap: str = None, **kwargs) -> Iterable:
-    """
-    快速创建进度条的封装函数
-    :param iterable: 可迭代对象
-    :param prefix: 进度条前缀
-    :param color: 基础颜色
-    :param cmap: 渐变色名称
-    :param kwargs: 其他ColorProgressBar支持的参数
-    
-    example:
-    from oafuncs.oa_data import pbar
-    from time import sleep
-    for i in pbar(range(100), prefix="Processing", color="green", cmap="viridis"):
-        sleep(0.1)
-    """
-    from ._script.cprogressbar import ColorProgressBar  # 从progressbar.py导入类
-
-    return ColorProgressBar(iterable=iterable, prefix=prefix, color=color, cmap=cmap, **kwargs)
-
-
 if __name__ == "__main__":
     pass
     """ import time

oafuncs/oa_date.py

@@ -4,7 +4,7 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2025-03-27 16:56:57
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2025-03-27 16:56:57
+LastEditTime: 2025-04-04 12:58:15
 FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_date.py
 Description:
 EditPlatform: vscode
@@ -13,10 +13,12 @@ SystemInfo: Windows 11
 Python Version: 3.12
 """
 
+
+
 import calendar
 import datetime
 
-__all__ = ["get_days_in_month", "generate_hour_list", "adjust_time"]
+__all__ = ["get_days_in_month", "generate_hour_list", "adjust_time", "timeit"]
 
 
 def get_days_in_month(year, month):
@@ -88,3 +90,23 @@ def adjust_time(initial_time, amount, time_unit="hours", output_format=None):
         elif time_unit == "days":
             default_format = "%Y%m%d"
         return time_obj.strftime(default_format)
+
+class timeit:
+    """
+    A decorator to measure the execution time of a function.
+
+    Usage:
+        @timeit
+        def my_function():
+            # Function code here
+    """
+    def __init__(self, func):
+        self.func = func
+
+    def __call__(self, *args, **kwargs):
+        start_time = datetime.datetime.now()
+        result = self.func(*args, **kwargs)
+        end_time = datetime.datetime.now()
+        elapsed_time = (end_time - start_time).total_seconds()
+        print(f"Function '{self.func.__name__}' executed in {elapsed_time:.2f} seconds.")
+        return result

oafuncs/oa_nc.py

@@ -14,12 +14,12 @@ Python Version: 3.11
 """
 
 import os
+from typing import List, Optional, Union
 
 import netCDF4 as nc
 import numpy as np
 import xarray as xr
 from rich import print
-from typing import Dict, List, Union
 
 __all__ = ["get_var", "extract", "save", "merge", "modify", "rename", "check", "convert_longitude", "isel", "draw"]
 
@@ -136,7 +136,18 @@ def save(file, data, varname=None, coords=None, mode="w", scale_offset_switch=Tr
     with nc.Dataset(file, mode, format="NETCDF4") as ncfile:
         # 如果 data 是 DataArray 并且没有提供 varname 和 coords
         if varname is None and coords is None and isinstance(data, xr.DataArray):
-            data.to_netcdf(file, mode=mode)
+            encoding = {}
+            for var in data.data_vars:
+                scale_factor, add_offset = _calculate_scale_and_offset(data[var].values)
+                encoding[var] = {
+                    "zlib": True,
+                    "complevel": 4,
+                    "dtype": "int16",
+                    "scale_factor": scale_factor,
+                    "add_offset": add_offset,
+                    "_FillValue": -32767,
+                }
+            data.to_netcdf(file, mode=mode, encoding=encoding)
             return
 
         # 添加坐标
@@ -182,29 +193,10 @@ def save(file, data, varname=None, coords=None, mode="w", scale_offset_switch=Tr
                     var.setncattr(key, value)
 
 
-def merge(file_list: Union[str, List[str]], var_name: Union[str, List[str], None] = None, dim_name: str = "time", target_filename: str = "merged.nc", chunk_config: Dict = {"time": 1000}, compression: Union[bool, Dict] = True, sanity_check: bool = True, overwrite: bool = True, parallel: bool = True) -> None:
-    """
-    NetCDF合并函数
-
-    Parameters:
-        file_list: 文件路径列表或单个文件路径
-        var_name: 需要合并的变量（单个变量名/变量列表/None表示全部）
-        dim_name: 合并维度，默认为'time'
-        target_filename: 输出文件路径
-        chunk_config: Dask分块配置，如{"time": 1000}
-        compression: 压缩配置（True启用默认压缩，或自定义编码字典）
-        sanity_check: 是否执行数据完整性校验
-        overwrite: 是否覆盖已存在文件
-        parallel: 是否启用并行处理
+def merge(file_list: Union[str, List[str]], var_name: Optional[Union[str, List[str]]] = None, dim_name: Optional[str] = None, target_filename: Optional[str] = None) -> None:
+    from ._script.netcdf_merge import merge_nc
 
-    Example:
-        merge(["data1.nc", "data2.nc"],
-             var_name=["temp", "salt"],
-             target_filename="result.nc",
-             chunk_config={"time": 500})
-    """
-    from ._script.netcdf_merge import merge as nc_merge
-    nc_merge(file_list, var_name, dim_name, target_filename, chunk_config, compression, sanity_check, overwrite, parallel)
+    merge_nc(file_list, var_name, dim_name, target_filename)
 
 
 def _modify_var(nc_file_path, variable_name, new_value):
@@ -230,8 +222,7 @@ def _modify_var(nc_file_path, variable_name, new_value):
             variable = dataset.variables[variable_name]
             # Check if the shape of the new value matches the variable's shape
             if variable.shape != new_value.shape:
-                raise ValueError(f"Shape mismatch: Variable '{variable_name}' has shape {variable.shape}, "
-                                 f"but new value has shape {new_value.shape}.")
+                raise ValueError(f"Shape mismatch: Variable '{variable_name}' has shape {variable.shape}, but new value has shape {new_value.shape}.")
             # Modify the value of the variable
             variable[:] = new_value
         print(f"Successfully modified variable '{variable_name}' in '{nc_file_path}'.")
@@ -264,8 +255,7 @@ def _modify_attr(nc_file_path, variable_name, attribute_name, attribute_value):
             variable.setncattr(attribute_name, attribute_value)
         print(f"Successfully modified attribute '{attribute_name}' of variable '{variable_name}' in '{nc_file_path}'.")
     except Exception as e:
-        print(f"[red]Error:[/red] Failed to modify attribute '{attribute_name}' of variable '{variable_name}' "
-              f"in file '{nc_file_path}'. [bold]Details:[/bold] {e}")
+        print(f"[red]Error:[/red] Failed to modify attribute '{attribute_name}' of variable '{variable_name}' in file '{nc_file_path}'. [bold]Details:[/bold] {e}")
 
 
 def modify(nc_file, var_name, attr_name=None, new_value=None):
@@ -435,7 +425,7 @@ def isel(ncfile, dim_name, slice_list):
     return ds_new
 
 
-def draw(output_dir=None, dataset=None, ncfile=None, xyzt_dims=("longitude", "latitude", "level", "time"), plot_type="contourf",fixed_colorscale=False):
+def draw(output_dir=None, dataset=None, ncfile=None, xyzt_dims=("longitude", "latitude", "level", "time"), plot_type="contourf", fixed_colorscale=False):
     """
     Description:
         Draw the data in the netCDF file
@@ -454,6 +444,7 @@ def draw(output_dir=None, dataset=None, ncfile=None, xyzt_dims=("longitude", "la
         draw(ncfile, output_dir, x_dim="longitude", y_dim="latitude", z_dim="level", t_dim="time", fixed_colorscale=False)
     """
     from ._script.plot_dataset import func_plot_dataset
+
     if output_dir is None:
         output_dir = str(os.getcwd())
     if isinstance(xyzt_dims, (list, tuple)):