legend-pydataobj 1.7.0__tar.gz → 1.7.1__tar.gz

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: legend_pydataobj
-Version: 1.7.0
+Version: 1.7.1
 Summary: LEGEND Python Data Objects
 Author: The LEGEND Collaboration
 Maintainer: The LEGEND Collaboration
@@ -707,7 +707,7 @@ Requires-Dist: numexpr
 Requires-Dist: numpy>=1.21
 Requires-Dist: pandas>=1.4.4
 Requires-Dist: parse
-Requires-Dist: pint
+Requires-Dist: pint!=0.24
 Requires-Dist: pint-pandas
 Provides-Extra: all
 Requires-Dist: legend-pydataobj[docs,test]; extra == "all"

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/pyproject.toml

@@ -41,7 +41,7 @@ dependencies = [
     "numpy>=1.21",
     "pandas>=1.4.4",
     "parse",
-    "pint",
+    "pint!=0.24",
     "pint-pandas",
 ]
 dynamic = [

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/legend_pydataobj.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: legend_pydataobj
-Version: 1.7.0
+Version: 1.7.1
 Summary: LEGEND Python Data Objects
 Author: The LEGEND Collaboration
 Maintainer: The LEGEND Collaboration
@@ -707,7 +707,7 @@ Requires-Dist: numexpr
 Requires-Dist: numpy>=1.21
 Requires-Dist: pandas>=1.4.4
 Requires-Dist: parse
-Requires-Dist: pint
+Requires-Dist: pint!=0.24
 Requires-Dist: pint-pandas
 Provides-Extra: all
 Requires-Dist: legend-pydataobj[docs,test]; extra == "all"

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/legend_pydataobj.egg-info/requires.txt

@@ -8,7 +8,7 @@ numexpr
 numpy>=1.21
 pandas>=1.4.4
 parse
-pint
+pint!=0.24
 pint-pandas
 
 [all]

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.7.0'
-__version_tuple__ = version_tuple = (1, 7, 0)
+__version__ = version = '1.7.1'
+__version_tuple__ = version_tuple = (1, 7, 1)

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/lh5/_serializers/read/composite.py

@@ -56,7 +56,7 @@ def _h5_read_lgdo(
         lh5_file = list(h5f)
         n_rows_read = 0
 
-        for i, h5f in enumerate(lh5_file):
+        for i, _h5f in enumerate(lh5_file):
             if isinstance(idx, list) and len(idx) > 0 and not np.isscalar(idx[0]):
                 # a list of lists: must be one per file
                 idx_i = idx[i]
@@ -65,7 +65,7 @@ def _h5_read_lgdo(
                 if not (isinstance(idx, tuple) and len(idx) == 1):
                     idx = (idx,)
                 # idx is a long continuous array
-                n_rows_i = read_n_rows(name, h5f)
+                n_rows_i = read_n_rows(name, _h5f)
                 # find the length of the subset of idx that contains indices
                 # that are less than n_rows_i
                 n_rows_to_read_i = bisect.bisect_left(idx[0], n_rows_i)
@@ -78,7 +78,7 @@ def _h5_read_lgdo(
 
             obj_buf, n_rows_read_i = _h5_read_lgdo(
                 name,
-                h5f,
+                _h5f,
                 start_row=start_row,
                 n_rows=n_rows_i,
                 idx=idx_i,

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/lh5/_serializers/write/vector_of_vectors.py

@@ -2,6 +2,8 @@ from __future__ import annotations
 
 import logging
 
+import numpy as np
+
 from .... import types
 from ... import utils
 from ...exceptions import LH5EncodeError
@@ -31,12 +33,15 @@ def _h5_write_vector_of_vectors(
 
     # if appending we need to add an appropriate offset to the
     # cumulative lengths as appropriate for the in-file object
-    offset = 0  # declare here because we have to subtract it off at the end
+    # declare here because we have to subtract it off at the end
+    offset = np.int64(0)
     if (wo_mode in ("a", "o")) and "cumulative_length" in group:
         len_cl = len(group["cumulative_length"])
+        # if append, ignore write_start and set it to total number of vectors
         if wo_mode == "a":
             write_start = len_cl
         if len_cl > 0:
+            # set offset to correct number of elements in flattened_data until write_start
             offset = group["cumulative_length"][write_start - 1]
 
     # First write flattened_data array. Only write rows with data.
@@ -71,15 +76,23 @@ def _h5_write_vector_of_vectors(
     )
 
     # now offset is used to give appropriate in-file values for
-    # cumulative_length. Need to adjust it for start_row
+    # cumulative_length. Need to adjust it for start_row, if different from zero
     if start_row > 0:
         offset -= obj.cumulative_length.nda[start_row - 1]
 
     # Add offset to obj.cumulative_length itself to avoid memory allocation.
     # Then subtract it off after writing! (otherwise it will be changed
     # upon return)
-    cl_dtype = obj.cumulative_length.nda.dtype.type
-    obj.cumulative_length.nda += cl_dtype(offset)
+
+    # NOTE: this operation is not numerically safe (uint overflow in the lower
+    # part of the array), but this is not a problem because those values are
+    # not written to disk and we are going to restore the offset at the end
+    np.add(
+        obj.cumulative_length.nda,
+        offset,
+        out=obj.cumulative_length.nda,
+        casting="unsafe",
+    )
 
     _h5_write_array(
         obj.cumulative_length,
@@ -92,4 +105,10 @@ def _h5_write_vector_of_vectors(
         write_start=write_start,
         **h5py_kwargs,
     )
-    obj.cumulative_length.nda -= cl_dtype(offset)
+
+    np.subtract(
+        obj.cumulative_length.nda,
+        offset,
+        out=obj.cumulative_length.nda,
+        casting="unsafe",
+    )

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/lh5/tools.py

@@ -188,7 +188,20 @@ def show(
                 else:
                     toprint += f", \033[3mnumchunks\033[0m={val.id.get_num_chunks()}"
                     toprint += f", \033[3mchunkshape\033[0m={chunkshape}"
-                toprint += f", \033[3mcompression\033[0m={val.compression}"
+                toprint += ", \033[3mfilters\033[0m="
+
+                numfilters = val.id.get_create_plist().get_nfilters()
+                if numfilters == 0:
+                    toprint += "None"
+                else:
+                    toprint += "("
+                    for i in range(numfilters):
+                        thisfilter = val.id.get_create_plist().get_filter(i)[3].decode()
+                        if "lz4" in thisfilter:
+                            thisfilter = "lz4"
+                        toprint += f"{thisfilter},"
+                    toprint += ")"
+
             except TypeError:
                 toprint += "(scalar)"
 
@@ -268,7 +281,7 @@ def load_nda(
         f = sto.gimme_file(ff, "r")
         for par in par_list:
             if f"{lh5_group}/{par}" not in f:
-                msg = f"'{lh5_group}/{par}' not in file {f_list[ii]}"
+                msg = f"'{lh5_group}/{par}' not in file {ff}"
                 raise RuntimeError(msg)
 
             if idx_list is None:

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/types/fixedsizearray.py

@@ -50,4 +50,4 @@ class FixedSizeArray(Array):
         --------
         .LGDO.view_as
         """
-        return super.view_as(library, with_units=with_units)
+        return super().view_as(library, with_units=with_units)

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/types/vectorofvectors.py

@@ -480,7 +480,7 @@ class VectorOfVectors(LGDO):
                 lens = np.array([lens], dtype="u4")
 
             # calculate stop index in flattened_data
-            cum_lens = start + lens.cumsum()
+            cum_lens = np.add(start, lens.cumsum(), dtype=int)
 
             # fill with fast vectorized routine
             vovutils._nb_fill(vec, lens, self.flattened_data.nda[start : cum_lens[-1]])

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/src/lgdo/units.py

@@ -3,4 +3,4 @@ from __future__ import annotations
 import pint
 
 default_units_registry = pint.get_application_registry()
-default_units_registry.default_format = "~P"
+default_units_registry.formatter.default_format = "~P"

{legend_pydataobj-1.7.0 → legend_pydataobj-1.7.1}/tests/compression/test_uleb128_zigzag_diff.py

@@ -68,7 +68,7 @@ def test_uleb128zzdiff_encode_decode_equality():
         pos = varlen.uleb128_encode(varlen.zigzag_encode(int(s) - last), encx)
         assert np.array_equal(sig_out[offset : offset + pos], encx[:pos])
         offset += pos
-        last = s
+        last = int(s)
 
     sig_in_dec = np.empty(100, dtype="uint32")
     siglen = np.empty(1, dtype="uint32")