From 303e5cb1e4ceb2827b96b23fbf1cca56e4fc0424 Mon Sep 17 00:00:00 2001
From: Matthew Iannucci <matthew@earthmover.io>
Date: Mon, 21 Oct 2024 21:31:10 -0400
Subject: [PATCH] Add accessor, simple docs

---
 docs/usage.md            | 17 +++++++++++++++++
 virtualizarr/accessor.py | 17 +++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/docs/usage.md b/docs/usage.md
index a0f9d058..30eab144 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -396,6 +396,23 @@ combined_ds = xr.open_dataset('combined.parq', engine="kerchunk")
 
 By default references are placed in separate parquet file when the total number of references exceeds `record_size`. If there are fewer than `categorical_threshold` unique urls referenced by a particular variable, url will be stored as a categorical variable.
 
+### Writing to an Icechunk Store
+
+We can also write these references out as an [IcechunkStore](https://icechunk.io/). `Icechunk` is a Open-source, cloud-native transactional tensor storage engine that is compatible with zarr version 3. To export our virtual dataset to an `Icechunk` Store, we simply use the {py:meth}`ds.virtualize.to_icechunk <virtualizarr.xarray.VirtualiZarrDatasetAccessor.to_icechunk>` accessor method.
+
+```python
+# create an icechunk store
+from icechunk import IcechunkStore, StorageConfig, StoreConfig, VirtualRefConfig
+storage = StorageConfig.filesystem(str('combined'))
+store = IcechunkStore.create(storage=storage, mode="w", config=StoreConfig(
+    virtual_ref_config=VirtualRefConfig.s3_anonymous(region='us-east-1'),
+))
+
+combined_vds.virtualize.to_icechunk(store)
+```
+
+See the [Icechunk documentation](https://icechunk.io/icechunk-python/virtual/#creating-a-virtual-dataset-with-virtualizarr) for more details.
+
 ### Writing as Zarr
 
 Alternatively, we can write these references out as an actual Zarr store, at least one that is compliant with the [proposed "Chunk Manifest" ZEP](https://github.com/zarr-developers/zarr-specs/issues/287). To do this we simply use the {py:meth}`ds.virtualize.to_zarr <virtualizarr.xarray.VirtualiZarrDatasetAccessor.to_zarr>` accessor method.
diff --git a/virtualizarr/accessor.py b/virtualizarr/accessor.py
index cc251e63..d6091613 100644
--- a/virtualizarr/accessor.py
+++ b/virtualizarr/accessor.py
@@ -1,5 +1,6 @@
 from pathlib import Path
 from typing import (
+    TYPE_CHECKING,
     Callable,
     Literal,
     overload,
@@ -9,9 +10,13 @@
 
 from virtualizarr.manifests import ManifestArray
 from virtualizarr.types.kerchunk import KerchunkStoreRefs
+from virtualizarr.writers.icechunk import dataset_to_icechunk
 from virtualizarr.writers.kerchunk import dataset_to_kerchunk_refs
 from virtualizarr.writers.zarr import dataset_to_zarr
 
+if TYPE_CHECKING:
+    from icechunk import IcechunkStore  # type: ignore[import-not-found]
+
 
 @register_dataset_accessor("virtualize")
 class VirtualiZarrDatasetAccessor:
@@ -39,6 +44,18 @@ def to_zarr(self, storepath: str) -> None:
         """
         dataset_to_zarr(self.ds, storepath)
 
+    def to_icechunk(self, store: "IcechunkStore") -> None:
+        """
+        Write an xarray dataset whose variables wrap ManifestArrays to an Icechunk store.
+
+        Currently requires all variables to be backed by ManifestArray objects.
+
+        Parameters
+        ----------
+        store: IcechunkStore
+        """
+        dataset_to_icechunk(self.ds, store)
+
     @overload
     def to_kerchunk(
         self, filepath: None, format: Literal["dict"]