Merge pull request #6 from yuriyzubov/refactor

add bokeh to the list of dependencies
fix click parameter typos
format parsing order
resolve dask serialization issue for the lambda function that contains reference to self instance

Author: yuriyzubov

pyproject.toml

@@ -17,10 +17,11 @@ dependencies = [
     "mrcfile>=1.5.3,<2.0.0",
     "natsort>=8.4.0,<9.0.0",
     "numcodecs>=0.13.0,<0.16",
-    "pydantic-zarr>=0.4.0,<1.0.0",
+    "pydantic-zarr==0.6.0",
     "pint>=0.20.0,<1.0.0",
     "tifffile>=2025.1.10,<2026.0.0",
-    "zarr==2.18.3"
+    "zarr==2.18.3",
+    "bokeh>=3.1.0"
 ]
 
 [project.scripts]

src/zarrify/formats/mrc.py

@@ -10,6 +10,7 @@
 from abc import ABCMeta
 from numcodecs import Zstd
 import logging
+import copy
 
 class Mrc3D(Volume):
 
@@ -30,20 +31,9 @@ def __init__(
 
         self.memmap = mrcfile.mmap(self.src_path, mode="r")
         self.ndim = self.memmap.data.ndim
-        self.shape = self.memmap.shape
+        self.shape = self.memmap.data.shape
         self.dtype = self.memmap.data.dtype
 
-    def save_chunk(self, z_arr: zarr.Array, chunk_slice: Tuple[slice, ...]):
-        """Copies data from a particular part of the input mrc array into a specific chunk of the output zarr array.
-
-        Args:
-            z_arr (zarr.core.Array): output zarr array object
-            chunk_slice (Tuple[slice, ...]): slice of the mrc array to copy.
-        """
-        mrc_file = mrcfile.mmap(self.src_path, mode="r")
-
-        if not (mrc_file.data[chunk_slice] == 0).all():
-            z_arr[chunk_slice] = mrc_file.data[chunk_slice]
 
     def write_to_zarr(
         self,
@@ -62,8 +52,9 @@ def write_to_zarr(
         logging.basicConfig(level=logging.INFO, 
                          format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 
-        
+        src_path = copy.copy(self.src_path)
         z_arr = self.get_output_array(dest, zarr_chunks, comp)
+        
         out_slices = slices_from_chunks(
             normalize_chunks(z_arr.chunks, shape=z_arr.shape)
         )
@@ -73,10 +64,22 @@ def write_to_zarr(
 
             logging.info(f"{idx + 1} / {len(out_slices_partitioned)}")
             start = time.time()
-            fut = client.map(lambda v: self.save_chunk(z_arr, v), part)
+            fut = client.map(lambda v: save_chunk(src_path, z_arr, v), part)
             logging.info(
                 f"Submitted {len(part)} tasks to the scheduler in {time.time()- start}s"
             )
             # wait for all the futures to complete
             result = wait(fut)
             logging.info(f"Completed {len(part)} tasks in {time.time() - start}s")
+
+def save_chunk(src_path, z_arr: zarr.Array, chunk_slice: Tuple[slice, ...]):
+    """Copies data from a particular part of the input mrc array into a specific chunk of the output zarr array.
+
+    Args:
+        z_arr (zarr.core.Array): output zarr array object
+        chunk_slice (Tuple[slice, ...]): slice of the mrc array to copy.
+    """
+    mrc_file = mrcfile.mmap(src_path, mode="r")
+
+    if not (mrc_file.data[chunk_slice] == 0).all():
+        z_arr[chunk_slice] = mrc_file.data[chunk_slice]

src/zarrify/to_zarr.py

@@ -38,13 +38,13 @@ def init_dataset(src :str,
     src_path = Path(src)
     params = (src, axes, scale, translation, units)
 
-    if src_path.is_dir():
-        return TiffStack(*params)
 
     ext = src_path.suffix.lower()
-    
-    if '.n5' in src_path.name:
+
+    if ext=='.n5':
         return N5Group(*params)
+    elif src_path.is_dir():
+        return TiffStack(*params)
     elif ext == ".mrc":
         return Mrc3D(*params)
     elif ext in (".tif", ".tiff"):
@@ -92,7 +92,7 @@ def to_zarr(src : str,
     type=click.Path(exists=True),
     help="Input file/directory location",
 )
-@click.option("--dest", "-s", type=click.STRING, help="Output .zarr file path.")
+@click.option("--dest", "-d", type=click.STRING, help="Output .zarr file path.")
 @click.option(
     "--num_workers", "-w", default=100, type=click.INT, help="Number of dask workers"
 )
@@ -129,11 +129,11 @@ def to_zarr(src : str,
 )
 @click.option(
     "--scale",
-    "-s",
+    "-sc",
     nargs=3,
     default=(1.0, 1.0, 1.0),
     type=float,
-    help="Metadata scale value. Order matters. \n Example: -s 1.0 2.0 3.0",
+    help="Metadata scale value. Order matters. \n Example: --scale 1.0 2.0 3.0",
 )
 @click.option(
     "--units",

src/zarrify/utils/dask_utils.py

@@ -33,6 +33,7 @@ def initialize_dask_client(cluster_type: str | None = None) -> Client:
         raise ValueError(f"Unsupported cluster type: {cluster_type}")
 
     client = Client(cluster)
+    print(str(client.dashboard_link))
     with open(
         os.path.join(os.getcwd(), "dask_dashboard_link" + ".txt"), "w"
     ) as text_file: