[V3] Allow for incomplete codec metadata using numcodecs.get_codec (#…

…1447) * refactor(v3): Allow for incomplete codec metadata using numcodecs.get_codec * add test * lint * add release note --------- Co-authored-by: Ryan Abernathey <ryan.abernathey@gmail.com>
zarr-developers · Jul 10, 2023 · aa5db9f · aa5db9f
1 parent 98f74d5
commit aa5db9f
Show file tree

Hide file tree

Showing 3 changed files with 43 additions and 15 deletions.
diff --git a/docs/release.rst b/docs/release.rst
@@ -18,10 +18,14 @@ Release notes
 Unreleased
 ----------
 
-Bug fixes
-~~~~~~~~~
+Enhancements
+~~~~~~~~~~~~
+
+* Allow for partial codec specification in V3 array metadata.
+  By :user:`Joe Hamman <jhamman>` :issue:`1443`.
 
-* Add ``__contains__`` method to ``KVStore``. By :user:`Christoph Gohlke <cgohlke>` :issue:`1454`.
+* Add ``__contains__`` method to ``KVStore``. 
+  By :user:`Christoph Gohlke <cgohlke>` :issue:`1454`.
 
     * **Block Indexing**: Implemented blockwise (chunk blocks) indexing to ``zarr.Array``.
       By :user:`Altay Sansal <tasansal>` :issue:`1428`

diff --git a/zarr/meta.py b/zarr/meta.py
@@ -441,26 +441,22 @@ def _decode_codec_metadata(cls, meta: Optional[Mapping]) -> Optional[Codec]:
         uri = 'https://purl.org/zarr/spec/codec/'
         conf = meta['configuration']
         if meta['codec'].startswith(uri + 'gzip/'):
-            codec = numcodecs.GZip(level=conf['level'])
+            conf["id"] = "gzip"
         elif meta['codec'].startswith(uri + 'zlib/'):
-            codec = numcodecs.Zlib(level=conf['level'])
+            conf["id"] = "zlib"
         elif meta['codec'].startswith(uri + 'blosc/'):
-            codec = numcodecs.Blosc(clevel=conf['clevel'],
-                                    shuffle=conf['shuffle'],
-                                    blocksize=conf['blocksize'],
-                                    cname=conf['cname'])
+            conf["id"] = "blosc"
         elif meta['codec'].startswith(uri + 'bz2/'):
-            codec = numcodecs.BZ2(level=conf['level'])
+            conf["id"] = "bz2"
         elif meta['codec'].startswith(uri + 'lz4/'):
-            codec = numcodecs.LZ4(acceleration=conf['acceleration'])
+            conf["id"] = "lz4"
         elif meta['codec'].startswith(uri + 'lzma/'):
-            codec = numcodecs.LZMA(format=conf['format'],
-                                   check=conf['check'],
-                                   preset=conf['preset'],
-                                   filters=conf['filters'])
+            conf["id"] = "lzma"
         else:
             raise NotImplementedError
 
+        codec = numcodecs.get_codec(conf)
+
         return codec
 
     @classmethod

diff --git a/zarr/tests/test_meta.py b/zarr/tests/test_meta.py
@@ -314,6 +314,34 @@ def test_encode_decode_array_dtype_shape_v3():
     assert 'filters' not in meta_dec
 
 
+@pytest.mark.parametrize("comp_id", ["gzip", "zlib", "blosc", "bz2", "lz4", "lzma"])
+def test_decode_metadata_implicit_compressor_config_v3(comp_id):
+    meta = {
+        "attributes": {},
+        "chunk_grid": {
+            "chunk_shape": [10],
+            "separator": "/",
+            "type": "regular"
+        },
+        "chunk_memory_layout": "C",
+        "compressor": {
+            "codec": f"https://purl.org/zarr/spec/codec/{comp_id}/1.0",
+            "configuration": {
+                # intentionally left empty
+            }
+        },
+        "data_type": "<f8",
+        "extensions": [],
+        "fill_value": None,
+        "shape": [100, 10, 10]
+    }
+    meta_json = json.dumps(meta)
+
+    # test decoding
+    meta_dec = Metadata3.decode_array_metadata(meta_json)
+    assert meta_dec['compressor'].codec_id == comp_id
+
+
 def test_encode_decode_array_structured():
 
     meta = dict(