bio2zarr 0.0.10__py3-none-any.whl → 0.1.1__py3-none-any.whl

bio2zarr/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.10'
-__version_tuple__ = version_tuple = (0, 0, 10)
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)

bio2zarr/cli.py

@@ -44,7 +44,13 @@ zarr_path = click.argument(
     "zarr_path", type=click.Path(exists=True, file_okay=False, dir_okay=True)
 )
 
-num_partitions = click.argument("num_partitions", type=click.IntRange(min=1))
+num_partitions = click.option(
+    "-n",
+    "--num-partitions",
+    type=click.IntRange(min=1),
+    default=None,
+    help="Target number of partitions to split into",
+)
 
 partition = click.argument("partition", type=click.IntRange(min=0))
 
@@ -58,6 +64,13 @@ force = click.option(
     help="Force overwriting of existing directories",
 )
 
+progress = click.option(
+    "-P /-Q",
+    "--progress/--no-progress",
+    default=True,
+    help="Show progress bars (default: show)",
+)
+
 one_based = click.option(
     "--one-based",
     is_flag=True,
@@ -165,6 +178,15 @@ def check_overwrite_dir(path, force):
         shutil.rmtree(tmp_delete_path)
 
 
+def check_partitions(num_partitions):
+    if num_partitions is None:
+        raise click.UsageError(
+            "-n/--num-partitions must currently be specified. Future versions "
+            "will provide reasonable defaults or other means of specifying "
+            "partitions."
+        )
+
+
 def get_compressor(cname):
     if cname is None:
         return None
@@ -190,9 +212,17 @@ def show_work_summary(work_summary, json):
 @verbose
 @column_chunk_size
 @compressor
+@progress
 @worker_processes
 def explode(
-    vcfs, icf_path, force, verbose, column_chunk_size, compressor, worker_processes
+    vcfs,
+    icf_path,
+    force,
+    verbose,
+    column_chunk_size,
+    compressor,
+    progress,
+    worker_processes,
 ):
     """
     Convert VCF(s) to intermediate columnar format
@@ -205,7 +235,7 @@ def explode(
         worker_processes=worker_processes,
         column_chunk_size=column_chunk_size,
         compressor=get_compressor(compressor),
-        show_progress=True,
+        show_progress=progress,
     )
 
 
@@ -218,6 +248,7 @@ def explode(
 @compressor
 @json
 @verbose
+@progress
 @worker_processes
 def dexplode_init(
     vcfs,
@@ -228,14 +259,16 @@ def dexplode_init(
     compressor,
     json,
     verbose,
+    progress,
     worker_processes,
 ):
     """
     Initial step for distributed conversion of VCF(s) to intermediate columnar format
-    over the requested number of paritions.
+    over some number of paritions.
     """
     setup_logging(verbose)
     check_overwrite_dir(icf_path, force)
+    check_partitions(num_partitions)
     work_summary = vcf2zarr.explode_init(
         icf_path,
         vcfs,
@@ -243,7 +276,7 @@ def dexplode_init(
         column_chunk_size=column_chunk_size,
         worker_processes=worker_processes,
         compressor=get_compressor(compressor),
-        show_progress=True,
+        show_progress=progress,
     )
     show_work_summary(work_summary, json)
 
@@ -310,6 +343,7 @@ def mkschema(icf_path):
 @samples_chunk_size
 @max_variant_chunks
 @max_memory
+@progress
 @worker_processes
 def encode(
     icf_path,
@@ -321,6 +355,7 @@ def encode(
     samples_chunk_size,
     max_variant_chunks,
     max_memory,
+    progress,
     worker_processes,
 ):
     """
@@ -337,7 +372,7 @@ def encode(
         max_variant_chunks=max_variant_chunks,
         worker_processes=worker_processes,
         max_memory=max_memory,
-        show_progress=True,
+        show_progress=progress,
     )
 
 
@@ -351,6 +386,7 @@ def encode(
 @samples_chunk_size
 @max_variant_chunks
 @json
+@progress
 @verbose
 def dencode_init(
     icf_path,
@@ -362,12 +398,13 @@ def dencode_init(
     samples_chunk_size,
     max_variant_chunks,
     json,
+    progress,
     verbose,
 ):
     """
     Initialise conversion of intermediate format to VCF Zarr. This will
     set up the specified ZARR_PATH to perform this conversion over
-    NUM_PARTITIONS.
+    some number of partitions.
 
     The output of this commmand is the actual number of partitions generated
     (which may be less then the requested number, if there is not sufficient
@@ -379,6 +416,7 @@ def dencode_init(
     """
     setup_logging(verbose)
     check_overwrite_dir(zarr_path, force)
+    check_partitions(num_partitions)
     work_summary = vcf2zarr.encode_init(
         icf_path,
         zarr_path,
@@ -387,7 +425,7 @@ def dencode_init(
         variants_chunk_size=variants_chunk_size,
         samples_chunk_size=samples_chunk_size,
         max_variant_chunks=max_variant_chunks,
-        show_progress=True,
+        show_progress=progress,
     )
     show_work_summary(work_summary, json)
 
@@ -413,12 +451,13 @@ def dencode_partition(zarr_path, partition, verbose, one_based):
 @click.command
 @zarr_path
 @verbose
-def dencode_finalise(zarr_path, verbose):
+@progress
+def dencode_finalise(zarr_path, verbose, progress):
     """
     Final step for distributed conversion of ICF to VCF Zarr.
     """
     setup_logging(verbose)
-    vcf2zarr.encode_finalise(zarr_path, show_progress=True)
+    vcf2zarr.encode_finalise(zarr_path, show_progress=progress)
 
 
 @click.command(name="convert")
@@ -428,6 +467,7 @@ def dencode_finalise(zarr_path, verbose):
 @variants_chunk_size
 @samples_chunk_size
 @verbose
+@progress
 @worker_processes
 def convert_vcf(
     vcfs,
@@ -436,6 +476,7 @@ def convert_vcf(
     variants_chunk_size,
     samples_chunk_size,
     verbose,
+    progress,
     worker_processes,
 ):
     """
@@ -448,7 +489,7 @@ def convert_vcf(
         zarr_path,
         variants_chunk_size=variants_chunk_size,
         samples_chunk_size=samples_chunk_size,
-        show_progress=True,
+        show_progress=progress,
         worker_processes=worker_processes,
     )
 
@@ -481,6 +522,7 @@ vcf2zarr_main.add_command(dencode_finalise)
 @click.argument("in_path", type=click.Path())
 @click.argument("zarr_path", type=click.Path())
 @worker_processes
+@progress
 @verbose
 @variants_chunk_size
 @samples_chunk_size
@@ -489,6 +531,7 @@ def convert_plink(
     zarr_path,
     verbose,
     worker_processes,
+    progress,
     variants_chunk_size,
     samples_chunk_size,
 ):
@@ -499,7 +542,7 @@ def convert_plink(
     plink.convert(
         in_path,
         zarr_path,
-        show_progress=True,
+        show_progress=progress,
         worker_processes=worker_processes,
         samples_chunk_size=samples_chunk_size,
         variants_chunk_size=variants_chunk_size,
@@ -517,11 +560,39 @@ plink2zarr.add_command(convert_plink)
 
 @click.command
 @version
-@click.argument("vcf_path", type=click.Path())
-@click.option("-i", "--index", type=click.Path(), default=None)
-@click.option("-n", "--num-parts", type=int, default=None)
-# @click.option("-s", "--part-size", type=int, default=None)
-def vcfpartition(vcf_path, index, num_parts):
-    indexed_vcf = vcf_utils.IndexedVcf(vcf_path, index)
-    regions = indexed_vcf.partition_into_regions(num_parts=num_parts)
-    click.echo("\n".join(map(str, regions)))
+@click.argument("vcf_path", type=click.Path(exists=True, dir_okay=False))
+@verbose
+@num_partitions
+@click.option(
+    "-s",
+    "--partition-size",
+    type=str,
+    default=None,
+    help="Target (compressed) size of VCF partitions, e.g. 100KB, 10MiB, 1G.",
+)
+def vcfpartition(vcf_path, verbose, num_partitions, partition_size):
+    """
+    Output bcftools region strings that partition an indexed VCF/BCF file
+    into either an approximate number of parts (-n), or parts of approximately
+    a given size (-s). One of -n or -s must be supplied.
+
+    Note that both the number of partitions and sizes are a target, and the
+    returned number of partitions may not exactly correspond. In particular,
+    there is a maximum level of granularity determined by the associated index
+    which cannot be exceeded.
+
+    Note also that the partitions returned may vary considerably in the number
+    of records that they contain.
+    """
+    setup_logging(verbose)
+    if num_partitions is None and partition_size is None:
+        raise click.UsageError(
+            "Either --num-partitions or --partition-size must be specified"
+        )
+
+    indexed_vcf = vcf_utils.IndexedVcf(vcf_path)
+    regions = indexed_vcf.partition_into_regions(
+        num_parts=num_partitions, target_part_size=partition_size
+    )
+    for region in regions:
+        click.echo(f"{region}\t{vcf_path}")

bio2zarr/core.py

@@ -7,8 +7,10 @@ import math
 import multiprocessing
 import os
 import os.path
+import sys
 import threading
 import time
+import warnings
 
 import humanfriendly
 import numcodecs
@@ -78,6 +80,11 @@ def du(path):
 
 
 class SynchronousExecutor(cf.Executor):
+    # Arguably we should use workers=0 as the default and use this
+    # executor implementation. However, the docs are fairly explicit
+    # about saying we shouldn't instantiate Future objects directly,
+    # so it's best to keep this as a semi-secret debugging interface
+    # for now.
     def submit(self, fn, /, *args, **kwargs):
         future = cf.Future()
         future.set_result(fn(*args, **kwargs))
@@ -191,8 +198,11 @@ _progress_counter = None
 
 
 def update_progress(inc):
-    with _progress_counter.get_lock():
-        _progress_counter.value += inc
+    # If the _progress_counter has not been set we are working in a
+    # synchronous non-progress tracking context
+    if _progress_counter is not None:
+        with _progress_counter.get_lock():
+            _progress_counter.value += inc
 
 
 def get_progress():
@@ -206,6 +216,22 @@ def setup_progress_counter(counter):
     _progress_counter = counter
 
 
+def warn_py39_mac():
+    if sys.platform == "darwin" and sys.version_info[:2] == (3, 9):
+        warnings.warn(
+            "There is a known issue with bio2zarr on MacOS Python 3.9 "
+            "in which OS-level named semaphores are leaked. "
+            "You will also probably see warnings like 'There appear to be N "
+            "leaked semaphore objects at shutdown'. "
+            "While this is likely harmless for a few runs, it could lead to "
+            "issues if you do a lot of conversion. To get prevent this issue "
+            "either: (1) use --worker-processes=0 or (2) upgrade to a newer "
+            "Python version. See https://github.com/sgkit-dev/bio2zarr/issues/209 "
+            "for more details.",
+            stacklevel=2,
+        )
+
+
 class ParallelWorkManager(contextlib.AbstractContextManager):
     def __init__(self, worker_processes=1, progress_config=None):
         # Need to specify this explicitly to suppport Macs and
@@ -214,9 +240,11 @@ class ParallelWorkManager(contextlib.AbstractContextManager):
         global _progress_counter
         _progress_counter = ctx.Value("Q", 0)
         if worker_processes <= 0:
-            # NOTE: this is only for testing, not for production use!
+            # NOTE: this is only for testing and debugging, not for
+            # production. See note on the SynchronousExecutor class.
             self.executor = SynchronousExecutor()
         else:
+            warn_py39_mac()
             self.executor = cf.ProcessPoolExecutor(
                 max_workers=worker_processes,
                 mp_context=ctx,
@@ -248,7 +276,6 @@ class ParallelWorkManager(contextlib.AbstractContextManager):
     def _update_progress(self):
         current = get_progress()
         inc = current - self.progress_bar.n
-        # print("UPDATE PROGRESS: current = ", current, self.progress_config.total, inc)
         self.progress_bar.update(inc)
 
     def _update_progress_worker(self):

bio2zarr/vcf2zarr/icf.py

@@ -263,9 +263,6 @@ def scan_vcf(path, target_num_partitions):
         )
 
         regions = indexed_vcf.partition_into_regions(num_parts=target_num_partitions)
-        logger.info(
-            f"Split {path} into {len(regions)} regions (target={target_num_partitions})"
-        )
         for region in regions:
             metadata.partitions.append(
                 VcfPartition(
@@ -275,6 +272,10 @@ def scan_vcf(path, target_num_partitions):
                     region=region,
                 )
             )
+        logger.info(
+            f"Split {path} into {len(metadata.partitions)} "
+            f"partitions target={target_num_partitions})"
+        )
         core.update_progress(1)
         return metadata, vcf.raw_header
 

bio2zarr/vcf2zarr/vcz.py

@@ -34,7 +34,7 @@ DEFAULT_ZARR_COMPRESSOR = numcodecs.Blosc(cname="zstd", clevel=7)
 
 
 @dataclasses.dataclass
-class ZarrColumnSpec:
+class ZarrArraySpec:
     name: str
     dtype: str
     shape: tuple
@@ -54,7 +54,7 @@ class ZarrColumnSpec:
 
     @staticmethod
     def new(**kwargs):
-        spec = ZarrColumnSpec(
+        spec = ZarrArraySpec(
             **kwargs, compressor=DEFAULT_ZARR_COMPRESSOR.get_config(), filters=[]
         )
         spec._choose_compressor_settings()
@@ -94,7 +94,7 @@ class ZarrColumnSpec:
                 dimensions.append("genotypes")
             else:
                 dimensions.append(f"{vcf_field.category}_{vcf_field.name}_dim")
-        return ZarrColumnSpec.new(
+        return ZarrArraySpec.new(
             vcf_field=vcf_field.full_name,
             name=variable_name,
             dtype=vcf_field.smallest_dtype(),
@@ -127,6 +127,23 @@ class ZarrColumnSpec:
 
         self.compressor["shuffle"] = shuffle
 
+    @property
+    def chunk_nbytes(self):
+        """
+        Returns the nbytes for a single chunk in this array.
+        """
+        items = 1
+        dim = 0
+        for chunk_size in self.chunks:
+            size = min(chunk_size, self.shape[dim])
+            items *= size
+            dim += 1
+        # Include sizes for extra dimensions.
+        for size in self.shape[dim:]:
+            items *= size
+        dt = np.dtype(self.dtype)
+        return items * dt.itemsize
+
     @property
     def variant_chunk_nbytes(self):
         """
@@ -157,6 +174,24 @@ class VcfZarrSchema(core.JsonDataclass):
     filters: list
     fields: list
 
+    def validate(self):
+        """
+        Checks that the schema is well-formed and within required limits.
+        """
+        for field in self.fields:
+            # This is the Blosc max buffer size
+            if field.chunk_nbytes > 2147483647:
+                # TODO add some links to documentation here advising how to
+                # deal with PL values.
+                raise ValueError(
+                    f"Field {field.name} chunks are too large "
+                    f"({field.chunk_nbytes} > 2**31 - 1 bytes). "
+                    "Either generate a schema and drop this field (if you don't "
+                    "need it) or reduce the variant or sample chunk sizes."
+                )
+            # TODO other checks? There must be lots of ways people could mess
+            # up the schema leading to cryptic errors.
+
     def field_map(self):
         return {field.name: field for field in self.fields}
 
@@ -171,7 +206,7 @@ class VcfZarrSchema(core.JsonDataclass):
         ret.samples = [icf.Sample(**sd) for sd in d["samples"]]
         ret.contigs = [icf.Contig(**sd) for sd in d["contigs"]]
         ret.filters = [icf.Filter(**sd) for sd in d["filters"]]
-        ret.fields = [ZarrColumnSpec(**sd) for sd in d["fields"]]
+        ret.fields = [ZarrArraySpec(**sd) for sd in d["fields"]]
         return ret
 
     @staticmethod
@@ -192,7 +227,7 @@ class VcfZarrSchema(core.JsonDataclass):
         )
 
         def spec_from_field(field, variable_name=None):
-            return ZarrColumnSpec.from_field(
+            return ZarrArraySpec.from_field(
                 field,
                 num_samples=n,
                 num_variants=m,
@@ -204,7 +239,7 @@ class VcfZarrSchema(core.JsonDataclass):
         def fixed_field_spec(
             name, dtype, vcf_field=None, shape=(m,), dimensions=("variants",)
         ):
-            return ZarrColumnSpec.new(
+            return ZarrArraySpec.new(
                 vcf_field=vcf_field,
                 name=name,
                 dtype=dtype,
@@ -230,13 +265,13 @@ class VcfZarrSchema(core.JsonDataclass):
             ),
             fixed_field_spec(
                 name="variant_allele",
-                dtype="str",
+                dtype="O",
                 shape=(m, max_alleles),
                 dimensions=["variants", "alleles"],
             ),
             fixed_field_spec(
                 name="variant_id",
-                dtype="str",
+                dtype="O",
             ),
             fixed_field_spec(
                 name="variant_id_mask",
@@ -267,7 +302,7 @@ class VcfZarrSchema(core.JsonDataclass):
             chunks = [variants_chunk_size, samples_chunk_size]
             dimensions = ["variants", "samples"]
             colspecs.append(
-                ZarrColumnSpec.new(
+                ZarrArraySpec.new(
                     vcf_field=None,
                     name="call_genotype_phased",
                     dtype="bool",
@@ -280,7 +315,7 @@ class VcfZarrSchema(core.JsonDataclass):
             shape += [ploidy]
             dimensions += ["ploidy"]
             colspecs.append(
-                ZarrColumnSpec.new(
+                ZarrArraySpec.new(
                     vcf_field=None,
                     name="call_genotype",
                     dtype=gt_field.smallest_dtype(),
@@ -291,7 +326,7 @@ class VcfZarrSchema(core.JsonDataclass):
                 )
             )
             colspecs.append(
-                ZarrColumnSpec.new(
+                ZarrArraySpec.new(
                     vcf_field=None,
                     name="call_genotype_mask",
                     dtype="bool",
@@ -447,6 +482,7 @@ class VcfZarrWriter:
         self.icf = icf
         if self.path.exists():
             raise ValueError("Zarr path already exists")  # NEEDS TEST
+        schema.validate()
         partitions = VcfZarrPartition.generate_partitions(
             self.icf.num_records,
             schema.variants_chunk_size,

bio2zarr/vcf_utils.py

@@ -1,5 +1,6 @@
 import contextlib
 import gzip
+import logging
 import os
 import pathlib
 import struct
@@ -13,6 +14,8 @@ import numpy as np
 
 from bio2zarr.typing import PathType
 
+logger = logging.getLogger(__name__)
+
 CSI_EXTENSION = ".csi"
 TABIX_EXTENSION = ".tbi"
 TABIX_LINEAR_INDEX_INTERVAL_SIZE = 1 << 14  # 16kb interval size
@@ -411,6 +414,7 @@ class IndexedVcf(contextlib.AbstractContextManager):
             raise ValueError("Only .tbi or .csi indexes are supported.")
         self.vcf = cyvcf2.VCF(vcf_path)
         self.vcf.set_index(str(self.index_path))
+        logger.debug(f"Loaded {vcf_path} with index {self.index_path}")
         self.sequence_names = None
         if self.index_type == "csi":
             # Determine the file-type based on the "aux" field.
@@ -450,15 +454,16 @@ class IndexedVcf(contextlib.AbstractContextManager):
     def _filter_empty_and_refine(self, regions):
         """
         Return all regions in the specified list that have one or more records,
-        and refine the start coordinate of the region to be the actual first coord
+        and refine the start coordinate of the region to be the actual first coord.
+
+        Because this is a relatively expensive operation requiring seeking around
+        the file, we return the results as an iterator.
         """
-        ret = []
         for region in regions:
             var = next(self.variants(region), None)
             if var is not None:
                 region.start = var.POS
-                ret.append(region)
-        return ret
+                yield region
 
     def partition_into_regions(
         self,
@@ -490,7 +495,7 @@ class IndexedVcf(contextlib.AbstractContextManager):
             target_part_size_bytes = file_length // num_parts
         elif target_part_size_bytes is not None:
             num_parts = ceildiv(file_length, target_part_size_bytes)
-        part_lengths = np.array([i * target_part_size_bytes for i in range(num_parts)])
+        part_lengths = target_part_size_bytes * np.arange(num_parts, dtype=int)
         file_offsets, region_contig_indexes, region_positions = self.index.offsets()
 
         # Search the file offsets to find which indexes the part lengths fall at

{bio2zarr-0.0.10.dist-info → bio2zarr-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bio2zarr
-Version: 0.0.10
+Version: 0.1.1
 Summary: Convert bioinformatics data to Zarr
 Author-email: sgkit Developers <project@sgkit.dev>
 License: Apache License
@@ -207,7 +207,7 @@ License: Apache License
         
 Project-URL: repository, https://github.com/sgkit-dev/bio2zarr
 Project-URL: documentation, https://sgkit-dev.github.io/bio2zarr/
-Classifier: Development Status :: 3 - Alpha
+Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: POSIX
 Classifier: Operating System :: POSIX :: Linux
@@ -223,8 +223,8 @@ Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: zarr >=2.17
+Requires-Dist: numpy <2
+Requires-Dist: zarr <3,>=2.17
 Requires-Dist: click
 Requires-Dist: tabulate
 Requires-Dist: tqdm

bio2zarr-0.1.1.dist-info/RECORD

@@ -0,0 +1,20 @@
+bio2zarr/__init__.py,sha256=KiUGyya-9RHNcBldB8Lc1g3rP3CRjaL-5Olben0_6qA,49
+bio2zarr/__main__.py,sha256=wUKNNps8MAAEpMvLgVaI449eKyfr7Jpk2mMtYbNl4Ek,531
+bio2zarr/_version.py,sha256=PKIMyjdUACH4-ONvtunQCnYE2UhlMfp9su83e3HXl5E,411
+bio2zarr/cli.py,sha256=-6cU26n5f8CpBSj6RGC-fpNByjuJ0KxSFz85O9tITPg,14961
+bio2zarr/constants.py,sha256=QjbtFeBUZ-XqG35ZFIFj8EYrta_EwUkC2B5VGRP7oQs,425
+bio2zarr/core.py,sha256=Yd3Z6-mFI_neaxoWT6t6Tip0k1VZEcWbautHcJ0ep8Q,10486
+bio2zarr/plink.py,sha256=huXMlxQ5C3gPmOYCavA-QW7PzaV48I2lo80cQqHT1wY,6768
+bio2zarr/provenance.py,sha256=c_Z__QbWkLS0Rfa8D7LgEhtStng_zRMJX8comaDXIkw,142
+bio2zarr/typing.py,sha256=BYxhL16sKRoNxa6amf6AYxvt5Ke9qzv2np_kOT_zPJo,79
+bio2zarr/vcf_utils.py,sha256=R3bes-xYLZ4ekaxtqDd39YVV20qHmwei3XiIg1UFhRA,17996
+bio2zarr/vcf2zarr/__init__.py,sha256=0_of1iGzIDhvti49Gbcgd47oP63mKvouk9uLgKgiwoQ,791
+bio2zarr/vcf2zarr/icf.py,sha256=rIC35RIfkk5gEE8cOmBg1d9Pj-HkPivmGvYp4PrVN1Q,41589
+bio2zarr/vcf2zarr/vcz.py,sha256=2WE4RX5jZBiKDFEztNGYgXyrLRmVWeLKlFzh0GOzylk,38198
+bio2zarr/vcf2zarr/verification.py,sha256=6xcBy-cJLaQz2Qj2crffXFMjUG-H7z637Csxe5ZCmds,7898
+bio2zarr-0.1.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+bio2zarr-0.1.1.dist-info/METADATA,sha256=RR9oM_5UYB5slsheIFzkIlRZt5du8eCb1_bMT_e7QjY,14854
+bio2zarr-0.1.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+bio2zarr-0.1.1.dist-info/entry_points.txt,sha256=3adtRrClMpjatEbiYqK5bm9WHA2PaJN5hK-Cs_zkpaI,97
+bio2zarr-0.1.1.dist-info/top_level.txt,sha256=ouAvp3u9N25eKrQbN8BCDLPcWWQLhtlgdHKu8AtEj5Q,9
+bio2zarr-0.1.1.dist-info/RECORD,,

bio2zarr-0.0.10.dist-info/RECORD

@@ -1,20 +0,0 @@
-bio2zarr/__init__.py,sha256=KiUGyya-9RHNcBldB8Lc1g3rP3CRjaL-5Olben0_6qA,49
-bio2zarr/__main__.py,sha256=wUKNNps8MAAEpMvLgVaI449eKyfr7Jpk2mMtYbNl4Ek,531
-bio2zarr/_version.py,sha256=IBUgg21Ew0JtWj9Z6eN1r4zXlrNseQQNV4zo-nYzlEY,413
-bio2zarr/cli.py,sha256=Bv4k9V-5HJVVbqBMiYLWz5IQyILQ0bTicqgkQrr9hd0,13209
-bio2zarr/constants.py,sha256=QjbtFeBUZ-XqG35ZFIFj8EYrta_EwUkC2B5VGRP7oQs,425
-bio2zarr/core.py,sha256=3UFh7nKB3CbAIaJV3wgoqlkRy1M235C2vz7Iua73qwM,9234
-bio2zarr/plink.py,sha256=huXMlxQ5C3gPmOYCavA-QW7PzaV48I2lo80cQqHT1wY,6768
-bio2zarr/provenance.py,sha256=c_Z__QbWkLS0Rfa8D7LgEhtStng_zRMJX8comaDXIkw,142
-bio2zarr/typing.py,sha256=BYxhL16sKRoNxa6amf6AYxvt5Ke9qzv2np_kOT_zPJo,79
-bio2zarr/vcf_utils.py,sha256=b3Ti1AFXFlK7S1mu6jotqHPrujCIQXBKIHH8yIzd3zk,17781
-bio2zarr/vcf2zarr/__init__.py,sha256=0_of1iGzIDhvti49Gbcgd47oP63mKvouk9uLgKgiwoQ,791
-bio2zarr/vcf2zarr/icf.py,sha256=BJKPJDeqP8QtVz7ebm6NQQgvsba8H-JLsNEz4whOxsw,41559
-bio2zarr/vcf2zarr/vcz.py,sha256=sy8VVYuOntMuPs5gUwQx6IA39_Gl_YFW2h-CeRyQw2A,36865
-bio2zarr/vcf2zarr/verification.py,sha256=6xcBy-cJLaQz2Qj2crffXFMjUG-H7z637Csxe5ZCmds,7898
-bio2zarr-0.0.10.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-bio2zarr-0.0.10.dist-info/METADATA,sha256=7su1JbkFtR7eDjq2Rp5A8CjP9KnvwWaDS6bPH43Z2qI,14850
-bio2zarr-0.0.10.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-bio2zarr-0.0.10.dist-info/entry_points.txt,sha256=3adtRrClMpjatEbiYqK5bm9WHA2PaJN5hK-Cs_zkpaI,97
-bio2zarr-0.0.10.dist-info/top_level.txt,sha256=ouAvp3u9N25eKrQbN8BCDLPcWWQLhtlgdHKu8AtEj5Q,9
-bio2zarr-0.0.10.dist-info/RECORD,,