Add goat link (#576)

* Add goat link

* fix a couple of tests for latest zarr

(still working)

Author: martindurant

docs/source/index.rst

@@ -79,6 +79,10 @@ Indices and tables
 * :ref:`modindex`
 * :ref:`search`
 
+These docs pages collect anonymous tracking data using goatcounter, and the
+dashboard is available to the public: https://kerchunk.goatcounter.com/ .
+
+
 .. raw:: html
 
     <script data-goatcounter="https://kerchunk.goatcounter.com/count"

kerchunk/hdf.py

@@ -340,7 +340,7 @@ def _translator(
                                             for v in val
                                         ]
                             kwargs["data"] = out
-                            kwargs["filters"] = [numcodecs.JSON()]
+                            kwargs["filters"] = [numcodecs.VLenUTF8()]
                             fill = None
                         elif self.vlen == "null":
                             dt = "O"
@@ -466,7 +466,7 @@ def _translator(
                                 )
                             dt = "O"
                             kwargs["data"] = data2
-                            kwargs["filters"] = [numcodecs.JSON()]
+                            kwargs["filters"] = [numcodecs.VLenUTF8()]
                             fill = None
                         else:
                             raise NotImplementedError
@@ -481,6 +481,8 @@ def _translator(
 
                 # Create a Zarr array equivalent to this HDF5 dataset.
                 data = kwargs.pop("data", None)
+                if (dt or h5obj.dtype) == object:
+                    dt = "string"
                 za = self._zroot.require_array(
                     name=h5obj.name.lstrip("/"),
                     shape=h5obj.shape,

tests/test_hdf.py

@@ -195,15 +195,15 @@ def test_times_str(times_data):
 
 def test_string_embed():
     fn = osp.join(here, "vlen.h5")
-    h = kerchunk.hdf.SingleHdf5ToZarr(fn, fn, vlen_encode="embed", error="pdb")
+    h = kerchunk.hdf.SingleHdf5ToZarr(fn, fn, vlen_encode="embed")
     out = h.translate()
 
     localfs = AsyncFileSystemWrapper(fsspec.filesystem("file"))
     fs = refs_as_fs(out, fs=localfs)
     # assert txt in fs.references["vlen_str/0"]
     store = fs_as_store(fs)
     z = zarr.open(store, zarr_format=2)
-    assert z["vlen_str"].dtype == "O"
+    assert "String" in str(z["vlen_str"])
     assert z["vlen_str"][0] == txt
     assert (z["vlen_str"][1:] == "").all()
 
@@ -218,14 +218,16 @@ def test_string_pathlib():
     fs = fsspec.filesystem("reference", fo=out)
     assert txt in fs.references["vlen_str/0"]
     z = zarr.open(fs_as_store(fs))
-    assert z["vlen_str"].dtype == "O"
+    assert "String" in str(z["vlen_str"])
     assert z["vlen_str"][0] == txt
     assert (z["vlen_str"][1:] == "").all()
 
 
 def test_string_null():
     fn = osp.join(here, "vlen.h5")
-    h = kerchunk.hdf.SingleHdf5ToZarr(fn, fn, vlen_encode="null", inline_threshold=0)
+    h = kerchunk.hdf.SingleHdf5ToZarr(
+        fn, fn, vlen_encode="null", inline_threshold=0, error="pdb"
+    )
     out = h.translate()
     localfs = AsyncFileSystemWrapper(fsspec.filesystem("file"))
     store = refs_as_store(out, fs=localfs)