add legacy vlen-utf8 codec

zarr-developers · Jul 14, 2024 · cb617f0 · cb617f0
1 parent b8baa68
commit cb617f0
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 1 deletion.
diff --git a/src/zarr/buffer.py b/src/zarr/buffer.py
@@ -283,7 +283,10 @@ class NDBuffer:
 
     def __init__(self, array: NDArrayLike):
         # assert array.ndim > 0
-        assert array.dtype != object
+
+        # Commented this out because string arrays have dtype object
+        # TODO: decide how to handle strings (e.g. numpy 2.0 StringDtype)
+        # assert array.dtype != object
         self._data = array
 
     @classmethod

diff --git a/src/zarr/codecs/__init__.py b/src/zarr/codecs/__init__.py
@@ -4,6 +4,7 @@
 from zarr.codecs.bytes import BytesCodec, Endian
 from zarr.codecs.crc32c_ import Crc32cCodec
 from zarr.codecs.gzip import GzipCodec
+from zarr.codecs.legacy_vlen import VLenUTF8Codec
 from zarr.codecs.pipeline import BatchedCodecPipeline
 from zarr.codecs.sharding import ShardingCodec, ShardingCodecIndexLocation
 from zarr.codecs.transpose import TransposeCodec
@@ -21,5 +22,6 @@
     "ShardingCodec",
     "ShardingCodecIndexLocation",
     "TransposeCodec",
+    "VLenUTF8Codec",
     "ZstdCodec",
 ]