Changing the class names of LH5Store and LH5Iterator to Store a…

…nd `Iterator`

docs/source/notebooks/LH5Files.ipynb

@@ -101,7 +101,7 @@
    "id": "ef09f43c",
    "metadata": {},
    "source": [
-    "The group contains several LGDOs. Let's read them in memory. We start by initializing an `LH5Store` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.LH5Store) object:"
+    "The group contains several LGDOs. Let's read them in memory. We start by initializing an `Store` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.Store) object:"
    ]
   },
   {
@@ -111,17 +111,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from lgdo import LH5Store\n",
+    "from lgdo import Store\n",
     "\n",
-    "store = LH5Store()"
+    "store = Store()"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "60ce5b61",
    "metadata": {},
    "source": [
-    "`read_object()` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.LH5Store.read_object) reads an LGDO from disk and returns the object in memory together with the number of rows (as a tuple), if an object has such a property. Let's try to read `geds/raw`:"
+    "`read_object()` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.Store.read_object) reads an LGDO from disk and returns the object in memory together with the number of rows (as a tuple), if an object has such a property. Let's try to read `geds/raw`:"
    ]
   },
   {
@@ -200,7 +200,7 @@
    "id": "b3f52d77",
    "metadata": {},
    "source": [
-    "As you might have noticed, `read_object()` loads all the requested data in memory at once. This can be a problem when dealing with large datasets. `LH5Iterator` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.LH5Iterator) makes it possible to handle data one chunk at a time (sequentially) to avoid running out of memory:"
+    "As you might have noticed, `read_object()` loads all the requested data in memory at once. This can be a problem when dealing with large datasets. `Iterator` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.Iterator) makes it possible to handle data one chunk at a time (sequentially) to avoid running out of memory:"
    ]
   },
   {
@@ -210,9 +210,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from lgdo import LH5Iterator\n",
+    "from lgdo import Iterator\n",
     "\n",
-    "for lh5_obj, entry, n_rows in LH5Iterator(lh5_file, \"geds/raw/energy\", buffer_len=20):\n",
+    "for lh5_obj, entry, n_rows in Iterator(lh5_file, \"geds/raw/energy\", buffer_len=20):\n",
     "    print(f\"entry {entry}, energy = {lh5_obj} ({n_rows} rows)\")"
    ]
   },
@@ -248,7 +248,7 @@
    "id": "cbfd91c2",
    "metadata": {},
    "source": [
-    "The `write_object()` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.LH5Store.write_object) method of `LH5Store` makes it possible to write LGDO objects on disk. Let's start by writing `scalar` with name `message` in a file named `my_data.lh5` in the current directory:"
+    "The `write_object()` [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.Store.write_object) method of `Store` makes it possible to write LGDO objects on disk. Let's start by writing `scalar` with name `message` in a file named `my_data.lh5` in the current directory:"
    ]
   },
   {
@@ -258,7 +258,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "store = LH5Store()\n",
+    "store = Store()\n",
     "\n",
     "store.write_object(\n",
     "    scalar, name=\"message\", lh5_file=\"my_objects.lh5\", wo_mode=\"overwrite_file\"\n",
@@ -316,7 +316,7 @@
     "\n",
     "<div class=\"alert alert-info\">\n",
     "\n",
-    "**Note:** `write_objects()` allows for more advanced usage, like writing only some rows of the input object or appending to existing array-like structures. Have a look at the [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.LH5Store.write_object) for more information.\n",
+    "**Note:** `write_objects()` allows for more advanced usage, like writing only some rows of the input object or appending to existing array-like structures. Have a look at the [[docs]](https://legend-pydataobj.readthedocs.io/en/stable/api/lgdo.html#lgdo.lh5_store.Store.write_object) for more information.\n",
     "\n",
     "</div>"
    ]

src/lgdo/__init__.py

@@ -33,13 +33,13 @@
   types with the same length (number of rows)
 
 Currently the primary on-disk format for LGDO object is LEGEND HDF5 (LH5) files. IO
-is done via the class :class:`.lh5_store.LH5Store`. LH5 files can also be
+is done via the class :class:`.lh5_store.Store`. LH5 files can also be
 browsed easily in python like any `HDF5 <https://www.hdfgroup.org>`_ file using
 `h5py <https://www.h5py.org>`_.
 """
 
 from ._version import version as __version__
-from .lh5 import LH5Iterator, LH5Store, load_dfs, load_nda, ls, show
+from .lh5 import Iterator, Store, load_dfs, load_nda, ls, show
 from .types import (
     LGDO,
     Array,
@@ -66,8 +66,8 @@
     "VectorOfVectors",
     "VectorOfEncodedVectors",
     "WaveformTable",
-    "LH5Iterator",
-    "LH5Store",
+    "Iterator",
+    "Store",
     "load_dfs",
     "load_nda",
     "ls",

src/lgdo/lh5/__init__.py

@@ -1,16 +1,16 @@
 """Routines from reading and writing LEGEND Data Objects in HDF5 files.
 Currently the primary on-disk format for LGDO object is LEGEND HDF5 (LH5) files. IO
-is done via the class :class:`.store.LH5Store`. LH5 files can also be
+is done via the class :class:`.store.Store`. LH5 files can also be
 browsed easily in python like any `HDF5 <https://www.hdfgroup.org>`_ file using
 `h5py <https://www.h5py.org>`_.
 """
 
-from .iterator import LH5Iterator
-from .store import LH5Store, load_dfs, load_nda, ls, show
+from .iterator import Iterator
+from .store import Store, load_dfs, load_nda, ls, show
 
 __all__ = [
-    "LH5Iterator",
-    "LH5Store",
+    "Iterator",
+    "Store",
     "load_dfs",
     "load_nda",
     "ls",

src/lgdo/lh5/iterator.py

@@ -7,13 +7,13 @@
 import pandas as pd
 
 from ..types import Array, Scalar, Struct, VectorOfVectors
-from .store import LH5Store
+from .store import Store
 from .utils import expand_path
 
 LGDO = Union[Array, Scalar, Struct, VectorOfVectors]
 
 
-class LH5Iterator(Iterator):
+class Iterator(Iterator):
     """
     A class for iterating through one or more LH5 files, one block of entries
     at a time. This also accepts an entry list/mask to enable event selection,
@@ -29,7 +29,7 @@ class LH5Iterator(Iterator):
 
     This can also be used as an iterator:
 
-    >>> for lh5_obj, entry, n_rows in LH5Iterator(...):
+    >>> for lh5_obj, entry, n_rows in Iterator(...):
     >>>    # do the thing!
 
     This is intended for if you are reading a large quantity of data but
@@ -48,7 +48,7 @@ def __init__(
         entry_mask: list[bool] | list[list[bool]] = None,
         field_mask: dict[str, bool] | list[str] | tuple[str] = None,
         buffer_len: int = 3200,
-        friend: LH5Iterator = None,
+        friend: Iterator = None,
     ) -> None:
         """
         Parameters
@@ -68,16 +68,16 @@ def __init__(
             mask of entries to read. If a list of arrays is provided, expect
             one for each file. Ignore if a selection list is provided.
         field_mask
-            mask of which fields to read. See :meth:`LH5Store.read_object` for
+            mask of which fields to read. See :meth:`Store.read_object` for
             more details.
         buffer_len
             number of entries to read at a time while iterating through files.
         friend
-            a ''friend'' LH5Iterator that will be read in parallel with this.
+            a ''friend'' Iterator that will be read in parallel with this.
             The friend should have the same length and entry list. A single
             LH5 table containing columns from both iterators will be returned.
         """
-        self.lh5_st = LH5Store(base_path=base_path, keep_open=True)
+        self.lh5_st = Store(base_path=base_path, keep_open=True)
 
         # List of files, with wildcards and env vars expanded
         if isinstance(lh5_files, str):
@@ -162,8 +162,8 @@ def __init__(
 
         # Attach the friend
         if friend is not None:
-            if not isinstance(friend, LH5Iterator):
-                raise ValueError("Friend must be an LH5Iterator")
+            if not isinstance(friend, Iterator):
+                raise ValueError("Friend must be an Iterator")
             self.lh5_buffer.join(friend.lh5_buffer)
         self.friend = friend
 

src/lgdo/lh5/store.py

@@ -41,15 +41,15 @@
 DEFAULT_HDF5_COMPRESSION = None
 
 
-class LH5Store:
+class Store:
     """
     Class to represent a store of LEGEND HDF5 files. The two main methods
     implemented by the class are :meth:`read_object` and :meth:`write_object`.
 
     Examples
     --------
-    >>> from lgdo import LH5Store
-    >>> store = LH5Store()
+    >>> from lgdo import Store
+    >>> store = Store()
     >>> obj, _ = store.read_object("/geds/waveform", "file.lh5")
     >>> type(obj)
     lgdo.waveform_table.WaveformTable
@@ -1214,7 +1214,7 @@ def ls(lh5_file: str | h5py.Group, lh5_group: str = "") -> list[str]:
         + ("" if lh5_group == "" else f" (and group {lh5_group})")
     )
 
-    lh5_st = LH5Store()
+    lh5_st = Store()
     # To use recursively, make lh5_file a h5group instead of a string
     if isinstance(lh5_file, str):
         lh5_file = lh5_st.gimme_file(lh5_file, "r")
@@ -1378,7 +1378,7 @@ def load_nda(
     # Expand wildcards
     f_list = [f for f_wc in f_list for f in sorted(glob.glob(os.path.expandvars(f_wc)))]
 
-    sto = LH5Store()
+    sto = Store()
     par_data = {par: [] for par in par_list}
     for ii, f in enumerate(f_list):
         f = sto.gimme_file(f, "r")

src/lgdo/lh5/utils.py

@@ -24,7 +24,7 @@ def parse_datatype(datatype: str) -> tuple[str, tuple[int, ...], str | list[str]
         LGDO. Note this is not the same as the NumPy shape of the underlying
         data object. See the LGDO specification for more information. Also see
         :class:`~.types.ArrayOfEqualSizedArrays` and
-        :meth:`.lh5_store.LH5Store.read_object` for example code elements for
+        :meth:`.lh5_store.Store.read_object` for example code elements for
         numeric objects, the element type for struct-like  objects, the list of
         fields in the struct.
     """

tests/compression/conftest.py

@@ -1,11 +1,11 @@
 import pytest
 
-from lgdo import LH5Store
+from lgdo import Store
 
 
 @pytest.fixture()
 def wftable(lgnd_test_data):
-    store = LH5Store()
+    store = Store()
     wft, _ = store.read_object(
         "/geds/raw/waveform",
         lgnd_test_data.get_path("lh5/LDQTA_r117_20200110T105115Z_cal_geds_raw.lh5"),

tests/compression/test_radware_sigcompress.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-from lgdo import ArrayOfEncodedEqualSizedArrays, ArrayOfEqualSizedArrays, LH5Store
+from lgdo import ArrayOfEncodedEqualSizedArrays, ArrayOfEqualSizedArrays, Store
 from lgdo.compression.radware import (
     _get_hton_u16,
     _radware_sigcompress_decode,
@@ -168,7 +168,7 @@ def test_aoesa(wftable):
 
 
 def test_performance(lgnd_test_data):
-    store = LH5Store()
+    store = Store()
     obj, _ = store.read_object(
         "/geds/raw/waveform",
         lgnd_test_data.get_path("lh5/LDQTA_r117_20200110T105115Z_cal_geds_raw.lh5"),

tests/lh5/test_lh5_iterator.py

@@ -2,7 +2,7 @@
 import pytest
 
 import lgdo
-from lgdo.lh5 import LH5Iterator
+from lgdo.lh5 import Iterator
 
 
 @pytest.fixture(scope="module")
@@ -11,7 +11,7 @@ def lgnd_file(lgnd_test_data):
 
 
 def test_basics(lgnd_file):
-    lh5_it = LH5Iterator(
+    lh5_it = Iterator(
         lgnd_file,
         "/geds/raw",
         entry_list=range(100),
@@ -35,14 +35,14 @@ def test_basics(lgnd_file):
 
 def test_errors(lgnd_file):
     with pytest.raises(RuntimeError):
-        LH5Iterator("non-existent-file.lh5", "random-group")
+        Iterator("non-existent-file.lh5", "random-group")
 
     with pytest.raises(ValueError):
-        LH5Iterator(1, 2)
+        Iterator(1, 2)
 
 
 def test_lgnd_waveform_table_fancy_idx(lgnd_file):
-    lh5_it = LH5Iterator(
+    lh5_it = Iterator(
         lgnd_file,
         "geds/raw/waveform",
         entry_list=[
@@ -97,13 +97,13 @@ def more_lgnd_files(lgnd_test_data):
 
 
 def test_friend(more_lgnd_files):
-    lh5_raw_it = LH5Iterator(
+    lh5_raw_it = Iterator(
         more_lgnd_files[0],
         "ch1084803/raw",
         field_mask=["waveform", "baseline"],
         buffer_len=5,
     )
-    lh5_it = LH5Iterator(
+    lh5_it = Iterator(
         more_lgnd_files[1],
         "ch1084803/hit",
         field_mask=["is_valid_0vbb"],