legend-pydataobj 1.12.0a2__py3-none-any.whl → 1.12.0a4__py3-none-any.whl

{legend_pydataobj-1.12.0a2.dist-info → legend_pydataobj-1.12.0a4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend_pydataobj
-Version: 1.12.0a2
+Version: 1.12.0a4
 Summary: LEGEND Python Data Objects
 Author: The LEGEND Collaboration
 Maintainer: The LEGEND Collaboration

{legend_pydataobj-1.12.0a2.dist-info → legend_pydataobj-1.12.0a4.dist-info}/RECORD

@@ -1,6 +1,6 @@
-legend_pydataobj-1.12.0a2.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+legend_pydataobj-1.12.0a4.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
 lgdo/__init__.py,sha256=fkRv79kdtBasw31gPVK9SdLQ2vEEajTV2t3UPDvFg9o,3206
-lgdo/_version.py,sha256=JnfDM_d42edyo74E887XCyb9fjk-f5Vnz-5nNPPYBpo,515
+lgdo/_version.py,sha256=lVyzAOse2pIwNX9sD_s_ucUhU5oPCN_lFpntrC7eKG8,521
 lgdo/cli.py,sha256=s_EWTBWW76l7zWb6gaTSTjiT-0RzzcYEmjeFEQCVxfk,4647
 lgdo/lgdo_utils.py,sha256=6a2YWEwpyEMXlAyTHZMO01aqxy6SxJzPZkGNWKNWuS0,2567
 lgdo/logging.py,sha256=82wIOj7l7xr3WYyeHdpSXbbjzHJsy-uRyKYUYx2vMfQ,1003
@@ -14,13 +14,13 @@ lgdo/compression/utils.py,sha256=W2RkBrxPpXlat84dnU9Ad7d_tTws0irtGl7O1dNWjnk,114
 lgdo/compression/varlen.py,sha256=6ZZUItyoOfygDdE0DyoISeFZfqdbH6xl7T0eclfarzg,15127
 lgdo/lh5/__init__.py,sha256=UTzKGmpgFoHwVB_yNULvJsHD_uQQGl-R87l-3QBkh7w,773
 lgdo/lh5/concat.py,sha256=BZCgK7TWPKK8fMmha8K83d3bC31FVO1b5LOW7x-Ru1s,6186
-lgdo/lh5/core.py,sha256=GjosZGUp4GSO5FtWV9eXUt_6DGU_OwJXODlj5K1j93M,13320
+lgdo/lh5/core.py,sha256=nULH5UoRjUCH0E3Z0-OH_DbFz2PRAQP73Qaf1kfnyPE,13481
 lgdo/lh5/datatype.py,sha256=O_7BqOlX8PFMyG0ppkfUT5aps5HEqX0bpuKcJO3jhu0,1691
 lgdo/lh5/exceptions.py,sha256=3kj8avXl4eBGvebl3LG12gJEmw91W0T8PYR0AfvUAyM,1211
 lgdo/lh5/iterator.py,sha256=1ob9B7Bf3ioGCtZkUZoL6ibTxAwLf4ld8_33ghVVEa4,20498
-lgdo/lh5/store.py,sha256=MYbMt-Mc7izELxuyLlSrrYrylCIzxc2CLzZYIVbZ33w,8455
+lgdo/lh5/store.py,sha256=qkBm3gPbr1R2UlQpUuDR5sGRMzpYJBWFL8fDIry6tmQ,8474
 lgdo/lh5/tools.py,sha256=drtJWHY82wCFuFr6LVVnm2AQgs_wZuFmAvyOB4tcOHs,6431
-lgdo/lh5/utils.py,sha256=ioz8DlyXZsejwnU2qYdIccdHcF12H62jgLkZsiDOLSM,6243
+lgdo/lh5/utils.py,sha256=f2H7H1D-RfDN3g_YrVDQEPaHevn5yDJFA-uznK9cgx8,6336
 lgdo/lh5/_serializers/__init__.py,sha256=eZzxMp1SeZWG0PkEXUiCz3XyprQ8EmelHUmJogC8xYE,1263
 lgdo/lh5/_serializers/read/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lgdo/lh5/_serializers/read/array.py,sha256=uWfMCihfAmW2DE2ewip2qCK_kvQC_mb2zvOv26uzijc,1000
@@ -32,7 +32,7 @@ lgdo/lh5/_serializers/read/utils.py,sha256=YfSqPO-83A1XvhhuULxQ0Qz2A5ODa3sb7ApNx
 lgdo/lh5/_serializers/read/vector_of_vectors.py,sha256=765P8mElGArAaEPkHTAUXFQ47t1_3-3BQAete0LckBQ,7207
 lgdo/lh5/_serializers/write/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lgdo/lh5/_serializers/write/array.py,sha256=66DKnW2yqIBlUGNBPWcE-m4W0B2-nTKusDHGX9m6GY0,3223
-lgdo/lh5/_serializers/write/composite.py,sha256=I6lH0nWFIpAfZyG4-0rLxzg3mfazZ_FEhQVp1FZ0aA4,9254
+lgdo/lh5/_serializers/write/composite.py,sha256=JYoLT9intT_Y4xPeL_l7CSd22O0ZKyEmd0flKkWWPFA,9268
 lgdo/lh5/_serializers/write/scalar.py,sha256=JPt_fcdTKOSFp5hfJdcKIfK4hxhcD8vhOlvDF-7btQ8,763
 lgdo/lh5/_serializers/write/vector_of_vectors.py,sha256=puGQX9XF5P_5DVbm_Cc6TvPrsDywgBLSYtkqFNltbB4,3493
 lgdo/types/__init__.py,sha256=DNfOErPiAZg-7Gygkp6ZKAi20Yrm1mfderZHvKo1Y4s,821
@@ -45,11 +45,11 @@ lgdo/types/lgdo.py,sha256=21YNtJCHnSO3M60rjsAdbMO5crDjL_0BtuFpudZ2xvU,4500
 lgdo/types/scalar.py,sha256=c5Es2vyDqyWTPV6mujzfIzMpC1jNWkEIcvYyWQUxH3Q,1933
 lgdo/types/struct.py,sha256=Q0OWLVd4B0ciLb8t6VsxU3MPbmGLZ7WfQNno1lSQS0Q,4918
 lgdo/types/table.py,sha256=FkWesoEA9bmGGSW8Ewig1Zs77ffUoR_nggfYSmkWpjU,20079
-lgdo/types/vectorofvectors.py,sha256=-5m3g5w03nqs__Uv4cO36A_7_h_4mJhFpIhzJh3Y5D0,24855
+lgdo/types/vectorofvectors.py,sha256=GbAKV_ehXN4XdWSwnmKS_ErCiudRetcH_3wo7iDrVjw,26854
 lgdo/types/vovutils.py,sha256=LW3ZcwECxVYxxcFadAtY3nnK-9-rk8Xbg_m8hY30lo4,10708
 lgdo/types/waveformtable.py,sha256=9S_NMg894NZTGt2pLuskwH4-zQ5EbLnzWI6FVui6fXE,9827
-legend_pydataobj-1.12.0a2.dist-info/METADATA,sha256=71-hhjEgQZ9NqNS7FQkFYPALw6VZJf6vDMtCGMrdohE,44445
-legend_pydataobj-1.12.0a2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-legend_pydataobj-1.12.0a2.dist-info/entry_points.txt,sha256=0KWfnwbuwhNn0vPUqARukjp04Ca6lzfZBSirouRmk7I,76
-legend_pydataobj-1.12.0a2.dist-info/top_level.txt,sha256=KyR-EUloqiXcQ62IWnzBmtInDtvsHl4q2ZJAZgTcLXE,5
-legend_pydataobj-1.12.0a2.dist-info/RECORD,,
+legend_pydataobj-1.12.0a4.dist-info/METADATA,sha256=eD1QW8NEKGSWEqxSes1-TFnq1VHoxtdLmLfafsB53nI,44445
+legend_pydataobj-1.12.0a4.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
+legend_pydataobj-1.12.0a4.dist-info/entry_points.txt,sha256=0KWfnwbuwhNn0vPUqARukjp04Ca6lzfZBSirouRmk7I,76
+legend_pydataobj-1.12.0a4.dist-info/top_level.txt,sha256=KyR-EUloqiXcQ62IWnzBmtInDtvsHl4q2ZJAZgTcLXE,5
+legend_pydataobj-1.12.0a4.dist-info/RECORD,,

{legend_pydataobj-1.12.0a2.dist-info → legend_pydataobj-1.12.0a4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

lgdo/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.12.0a2'
-__version_tuple__ = version_tuple = (1, 12, 0)
+__version__ = version = '1.12.0a4'
+__version_tuple__ = version_tuple = (1, 12, 0, 'a4')

lgdo/lh5/_serializers/write/composite.py

@@ -1,8 +1,8 @@
 from __future__ import annotations
 
 import logging
-import os
 from inspect import signature
+from pathlib import Path
 
 import h5py
 
@@ -53,7 +53,7 @@ def _h5_write_lgdo(
     # change any object in the file. So we use file:append for
     # write_object:overwrite.
     if not isinstance(lh5_file, h5py.File):
-        mode = "w" if wo_mode == "of" or not os.path.exists(lh5_file) else "a"
+        mode = "w" if wo_mode == "of" or not Path(lh5_file).exists() else "a"
         lh5_file = h5py.File(lh5_file, mode=mode, **file_kwargs)
 
     log.debug(

lgdo/lh5/core.py

@@ -113,7 +113,11 @@ def read(
         lh5_obj = lh5_file[name]
     elif isinstance(lh5_file, str):
         lh5_file = h5py.File(lh5_file, mode="r", locking=locking)
-        lh5_obj = lh5_file[name]
+        try:
+            lh5_obj = lh5_file[name]
+        except KeyError as ke:
+            err = f"Object {name} not found in file {lh5_file.filename}"
+            raise KeyError(err) from ke
     else:
         if obj_buf is not None:
             obj_buf.resize(obj_buf_start)

lgdo/lh5/store.py

@@ -6,11 +6,11 @@ HDF5 files.
 from __future__ import annotations
 
 import logging
-import os
 import sys
 from collections import OrderedDict
 from collections.abc import Mapping, Sequence
 from inspect import signature
+from pathlib import Path
 from typing import Any
 
 import h5py
@@ -92,16 +92,16 @@ class LH5Store:
             return self.files[lh5_file]
 
         if self.base_path != "":
-            full_path = os.path.join(self.base_path, lh5_file)
+            full_path = Path(self.base_path) / lh5_file
         else:
-            full_path = lh5_file
+            full_path = Path(lh5_file)
 
-        file_exists = os.path.exists(full_path)
+        file_exists = full_path.exists()
         if mode != "r":
-            directory = os.path.dirname(full_path)
-            if directory != "" and not os.path.exists(directory):
+            directory = full_path.parent
+            if directory != "" and not full_path.parent.exists():
                 log.debug(f"making path {directory}")
-                os.makedirs(directory)
+                directory.mkdir(parents=True, exist_ok=True)
 
         if mode == "r" and not file_exists:
             msg = f"file {full_path} not found"

lgdo/lh5/utils.py

@@ -7,6 +7,7 @@ import logging
 import os
 import string
 from collections.abc import Mapping, Sequence
+from pathlib import Path
 from typing import Any
 
 import h5py
@@ -153,7 +154,7 @@ def expand_vars(expr: str, substitute: dict[str, str] | None = None) -> str:
 
     # use provided mapping
     # then expand env variables
-    return os.path.expandvars(string.Template(expr).safe_substitute(substitute))
+    return os.path.expandvars(string.Template(str(expr)).safe_substitute(substitute))
 
 
 def expand_path(
@@ -183,14 +184,15 @@ def expand_path(
         Unique absolute path, or list of all absolute paths
     """
     if base_path is not None and base_path != "":
-        base_path = os.path.expanduser(os.path.expandvars(base_path))
-        path = os.path.join(base_path, path)
+        base_path = Path(os.path.expandvars(base_path)).expanduser()
+        path = base_path / path
 
     # first expand variables
     _path = expand_vars(path, substitute)
 
     # then expand wildcards
-    paths = sorted(glob.glob(os.path.expanduser(_path)))
+    # pathlib glob works differently so use glob for now
+    paths = sorted(glob.glob(str(Path(_path).expanduser())))  # noqa: PTH207
 
     if base_path is not None and base_path != "":
         paths = [os.path.relpath(p, base_path) for p in paths]

lgdo/types/vectorofvectors.py

@@ -130,20 +130,48 @@ class VectorOfVectors(LGDOCollection):
 
             # ak.to_buffer helps in de-serialization
             # NOTE: ak.to_packed() needed?
-            form, length, container = ak.to_buffers(ak.to_packed(data))
-
-            # NOTE: node#-data is not even in the dict if the awkward array is empty
-            # NOTE: if the data arg was a numpy array, to_buffers() preserves
-            # the original dtype
-            # FIXME: have to copy the buffers, otherwise self will not own the
-            # data and self.resize() will fail. Is it possible to avoid this?
-            flattened_data = np.copy(
-                container.pop(f"node{data.ndim - 1}-data", np.empty(0, dtype=dtype))
-            )
+            form, _, container = ak.to_buffers(ak.to_packed(data))
+
+            # check if bytestring
+            curr = form
+            for _ in range(data.ndim - 1):
+                curr = curr.content
+            if (
+                "__array__" in curr.parameters
+                and curr.parameters["__array__"] == "bytestring"
+            ):
+                diffs = np.diff(container[f"node{data.ndim - 1}-offsets"])
+                if (diffs != diffs[0]).all():
+                    err_msg = "Non uniform string lengths not supported"
+                    raise NotImplementedError(err_msg)
+                flattened_data = np.asarray(
+                    ak.enforce_type(
+                        ak.unflatten(
+                            container.pop(
+                                f"node{data.ndim}-data", np.empty(0, dtype=dtype)
+                            ),
+                            diffs[0],
+                        ),
+                        "bytes",
+                    )
+                )
 
-            # if user-provided dtype is different than dtype from Awkward, cast
-            # NOTE: makes a copy only if needed
-            flattened_data = np.asarray(flattened_data, dtype=dtype)
+                # if user-provided dtype is different than dtype from Awkward, cast
+                # NOTE: makes a copy only if needed
+                flattened_data = np.asarray(flattened_data, dtype=dtype)
+            else:
+                # NOTE: node#-data is not even in the dict if the awkward array is empty
+                # NOTE: if the data arg was a numpy array, to_buffers() preserves
+                # the original dtype
+                # FIXME: have to copy the buffers, otherwise self will not own the
+                # data and self.resize() will fail. Is it possible to avoid this?
+                flattened_data = np.copy(
+                    container.pop(f"node{data.ndim - 1}-data", np.empty(0, dtype=dtype))
+                )
+
+                # if user-provided dtype is different than dtype from Awkward, cast
+                # NOTE: makes a copy only if needed
+                flattened_data = np.asarray(flattened_data, dtype=dtype)
 
             # start from innermost VoV and build nested structure
             for i in range(data.ndim - 2, -1, -1):
@@ -630,11 +658,25 @@ class VectorOfVectors(LGDOCollection):
             offsets[1:] = self.cumulative_length.nda
             offsets[0] = 0
 
-            content = (
-                ak.contents.NumpyArray(self.flattened_data.nda)
-                if self.ndim == 2
-                else self.flattened_data.view_as(library, with_units=with_units).layout
-            )
+            if self.ndim != 2:
+                content = self.flattened_data.view_as(
+                    library, with_units=with_units
+                ).layout
+            # need to handle strings separately
+            elif np.issubdtype(self.flattened_data.nda.dtype, np.bytes_):
+                byte_arrays = []
+                for s in self.flattened_data.nda:
+                    # Convert each string to array of bytes
+                    byte_array = np.frombuffer(s, dtype=np.uint8)
+                    byte_arrays.append(byte_array)
+                max_len = max(len(b) for b in byte_arrays)
+                raw_arrays = ak.contents.NumpyArray(np.concatenate(byte_arrays))
+                array_of_chars = ak.contents.RegularArray(
+                    raw_arrays, max_len, parameters={"__array__": "bytes"}
+                )
+                content = ak.enforce_type(array_of_chars, "bytes", highlevel=False)
+            else:
+                content = ak.contents.NumpyArray(self.flattened_data.nda)
 
             layout = ak.contents.ListOffsetArray(
                 offsets=ak.index.Index(offsets),