bio2zarr 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

bio2zarr/vcf2zarr/verification.py

@@ -4,6 +4,8 @@ import numpy.testing as nt
 import tqdm
 import zarr
 
+from bio2zarr.zarr_utils import first_dim_iter
+
 from .. import constants
 
 
@@ -77,7 +79,7 @@ def assert_info_val_equal(vcf_val, zarr_val, vcf_type):
     if vcf_type in ("String", "Character"):
         split = list(vcf_val.split(","))
         k = len(split)
-        if isinstance(zarr_val, str):
+        if isinstance(zarr_val, str) or zarr_val.ndim == 0:
             assert k == 1
             # Scalar
             assert vcf_val == zarr_val
@@ -109,19 +111,17 @@ def assert_info_val_equal(vcf_val, zarr_val, vcf_type):
             assert_all_fill(zarr_val[1:], vcf_type)
 
 
-def assert_format_val_equal(vcf_val, zarr_val, vcf_type):
+def assert_format_val_equal(vcf_val, zarr_val, vcf_type, vcf_number):
     assert vcf_val is not None
     assert isinstance(vcf_val, np.ndarray)
     if vcf_type in ("String", "Character"):
         assert len(vcf_val) == len(zarr_val)
         for v, z in zip(vcf_val, zarr_val):
-            split = list(v.split(","))
-            # Note: deliberately duplicating logic here between this and the
-            # INFO col above to make sure all combinations are covered by tests
-            k = len(split)
-            if k == 1:
+            if vcf_number == "1":
                 assert v == z
             else:
+                split = list(v.split(","))
+                k = len(split)
                 nt.assert_equal(split, z[:k])
                 assert_all_fill(z[k:], vcf_type)
     else:
@@ -147,16 +147,14 @@ def assert_format_val_equal(vcf_val, zarr_val, vcf_type):
 
 
 def verify(vcf_path, zarr_path, show_progress=False):
-    store = zarr.DirectoryStore(zarr_path)
-
-    root = zarr.group(store=store)
+    root = zarr.open(store=zarr_path, mode="r")
     pos = root["variant_position"][:]
     allele = root["variant_allele"][:]
     chrom = root["contig_id"][:][root["variant_contig"][:]]
     vid = root["variant_id"][:]
     call_genotype = None
-    if "call_genotype" in root:
-        call_genotype = iter(root["call_genotype"])
+    if "call_genotype" in root and root["call_genotype"].size > 0:
+        call_genotype = first_dim_iter(root["call_genotype"])
 
     vcf = cyvcf2.VCF(vcf_path)
     format_headers = {}
@@ -173,12 +171,17 @@ def verify(vcf_path, zarr_path, show_progress=False):
         if colname.startswith("call") and not colname.startswith("call_genotype"):
             vcf_name = colname.split("_", 1)[1]
             vcf_type = format_headers[vcf_name]["Type"]
-            format_fields[vcf_name] = vcf_type, iter(root[colname])
+            vcf_number = format_headers[vcf_name]["Number"]
+            format_fields[vcf_name] = (
+                vcf_type,
+                vcf_number,
+                first_dim_iter(root[colname]),
+            )
         if colname.startswith("variant"):
             name = colname.split("_", 1)[1]
             if name.isupper():
                 vcf_type = info_headers[name]["Type"]
-                info_fields[name] = vcf_type, iter(root[colname])
+                info_fields[name] = vcf_type, first_dim_iter(root[colname])
 
     first_pos = next(vcf).POS
     start_index = np.searchsorted(pos, first_pos)
@@ -221,10 +224,10 @@ def verify(vcf_path, zarr_path, show_progress=False):
             else:
                 assert_info_val_equal(vcf_val, zarr_val, vcf_type)
 
-        for name, (vcf_type, zarr_iter) in format_fields.items():
+        for name, (vcf_type, vcf_number, zarr_iter) in format_fields.items():
             vcf_val = row.format(name)
             zarr_val = next(zarr_iter)
             if vcf_val is None:
                 assert_format_val_missing(zarr_val, vcf_type)
             else:
-                assert_format_val_equal(vcf_val, zarr_val, vcf_type)
+                assert_format_val_equal(vcf_val, zarr_val, vcf_type, vcf_number)

bio2zarr/vcf_utils.py

@@ -6,6 +6,7 @@ import pathlib
 import struct
 from collections.abc import Sequence
 from dataclasses import dataclass
+from enum import Enum
 from typing import IO, Any, Optional, Union
 
 import cyvcf2
@@ -382,46 +383,61 @@ def read_tabix(
         )
 
 
+class VcfFileType(Enum):
+    VCF = ".vcf"
+    BCF = ".bcf"
+
+
+class VcfIndexType(Enum):
+    CSI = ".csi"
+    TABIX = ".tbi"
+
+
 class IndexedVcf(contextlib.AbstractContextManager):
     def __init__(self, vcf_path, index_path=None):
         self.vcf = None
         vcf_path = pathlib.Path(vcf_path)
         if not vcf_path.exists():
             raise FileNotFoundError(vcf_path)
-        # TODO use constants here instead of strings
         if index_path is None:
-            index_path = vcf_path.with_suffix(vcf_path.suffix + ".tbi")
+            index_path = vcf_path.with_suffix(
+                vcf_path.suffix + VcfIndexType.TABIX.value
+            )
             if not index_path.exists():
-                index_path = vcf_path.with_suffix(vcf_path.suffix + ".csi")
+                index_path = vcf_path.with_suffix(
+                    vcf_path.suffix + VcfIndexType.CSI.value
+                )
                 if not index_path.exists():
                     raise FileNotFoundError(
-                        "Cannot find .tbi or .csi file for {vcf_path}"
+                        f"Cannot find .tbi or .csi file for {vcf_path}"
                     )
         else:
             index_path = pathlib.Path(index_path)
 
         self.vcf_path = vcf_path
         self.index_path = index_path
-        # TODO use Enums for these
         self.file_type = None
         self.index_type = None
-        if index_path.suffix == ".csi":
-            self.index_type = "csi"
-        elif index_path.suffix == ".tbi":
-            self.index_type = "tabix"
-            self.file_type = "vcf"
+
+        if index_path.suffix == VcfIndexType.CSI.value:
+            self.index_type = VcfIndexType.CSI
+        elif index_path.suffix == VcfIndexType.TABIX.value:
+            self.index_type = VcfIndexType.TABIX
+            self.file_type = VcfFileType.VCF
         else:
             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":
+
+        if self.index_type == VcfIndexType.CSI:
             # Determine the file-type based on the "aux" field.
             self.index = read_csi(self.index_path)
-            self.file_type = "bcf"
+            self.file_type = VcfFileType.BCF
             if len(self.index.aux) > 0:
-                self.file_type = "vcf"
+                self.file_type = VcfFileType.VCF
                 self.sequence_names = self.index.parse_vcf_aux()
             else:
                 self.sequence_names = self.vcf.seqnames
@@ -437,7 +453,7 @@ class IndexedVcf(contextlib.AbstractContextManager):
 
     def contig_record_counts(self):
         d = dict(zip(self.sequence_names, self.index.record_counts))
-        if self.file_type == "bcf":
+        if self.file_type == VcfFileType.BCF:
             d = {k: v for k, v in d.items() if v > 0}
         return d
 

bio2zarr/zarr_utils.py

@@ -0,0 +1,18 @@
+import zarr
+
+
+def zarr_v3() -> bool:
+    return zarr.__version__ >= "3"
+
+
+if zarr_v3():
+    # Use zarr format v2 even when running with zarr-python v3
+    ZARR_FORMAT_KWARGS = dict(zarr_format=2)
+else:
+    ZARR_FORMAT_KWARGS = dict()
+
+
+# See discussion in https://github.com/zarr-developers/zarr-python/issues/2529
+def first_dim_iter(z):
+    for chunk in range(z.cdata_shape[0]):
+        yield from z.blocks[chunk]

{bio2zarr-0.1.1.dist-info → bio2zarr-0.1.3.dist-info}/METADATA

@@ -1,9 +1,9 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: bio2zarr
-Version: 0.1.1
+Version: 0.1.3
 Summary: Convert bioinformatics data to Zarr
 Author-email: sgkit Developers <project@sgkit.dev>
-License: Apache License
+License:                                  Apache License
                                    Version 2.0, January 2004
                                 http://www.apache.org/licenses/
         
@@ -219,26 +219,28 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy <2
-Requires-Dist: zarr <3,>=2.17
+Requires-Dist: numpy>=1.26
+Requires-Dist: zarr<3,>=2.17
 Requires-Dist: click
 Requires-Dist: tabulate
 Requires-Dist: tqdm
 Requires-Dist: humanfriendly
 Requires-Dist: cyvcf2
-Requires-Dist: bed-reader
+Requires-Dist: bed_reader
 Provides-Extra: dev
-Requires-Dist: msprime ; extra == 'dev'
-Requires-Dist: pysam ; extra == 'dev'
-Requires-Dist: pytest ; extra == 'dev'
-Requires-Dist: pytest-coverage ; extra == 'dev'
-Requires-Dist: pytest-xdist ; extra == 'dev'
-Requires-Dist: sgkit >=0.8.0 ; extra == 'dev'
-Requires-Dist: tqdm ; extra == 'dev'
+Requires-Dist: hypothesis-vcf; extra == "dev"
+Requires-Dist: msprime; extra == "dev"
+Requires-Dist: pysam; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-coverage; extra == "dev"
+Requires-Dist: pytest-xdist; extra == "dev"
+Requires-Dist: sgkit>=0.8.0; extra == "dev"
+Requires-Dist: tqdm; extra == "dev"
 
 [![CI](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml)
 [![Coverage Status](https://coveralls.io/repos/github/sgkit-dev/bio2zarr/badge.svg)](https://coveralls.io/github/sgkit-dev/bio2zarr)

bio2zarr-0.1.3.dist-info/RECORD

@@ -0,0 +1,21 @@
+bio2zarr/__init__.py,sha256=KiUGyya-9RHNcBldB8Lc1g3rP3CRjaL-5Olben0_6qA,49
+bio2zarr/__main__.py,sha256=wUKNNps8MAAEpMvLgVaI449eKyfr7Jpk2mMtYbNl4Ek,531
+bio2zarr/_version.py,sha256=NIzzV8ZM0W-CSLuEs1weG4zPrn_-8yr1AwwI1iuS6yo,511
+bio2zarr/cli.py,sha256=Iife89BfTR_AUarm-AIW0lAIYxd370OmP1KKePgFXzk,16008
+bio2zarr/constants.py,sha256=QjbtFeBUZ-XqG35ZFIFj8EYrta_EwUkC2B5VGRP7oQs,425
+bio2zarr/core.py,sha256=4xqNf3Txgyhcx23bzXZHq3GW0Jh24fPQwob7lKO7s0w,11668
+bio2zarr/plink.py,sha256=Yr1meT4AgS2qnwM64-Nmthh4HbjaPXsddYiJdtfYWBg,6999
+bio2zarr/provenance.py,sha256=c_Z__QbWkLS0Rfa8D7LgEhtStng_zRMJX8comaDXIkw,142
+bio2zarr/typing.py,sha256=BYxhL16sKRoNxa6amf6AYxvt5Ke9qzv2np_kOT_zPJo,79
+bio2zarr/vcf_utils.py,sha256=tuPzuMiwGYgMlQA49L6EuIplw9DOVaOw1DTa03OJS7k,18268
+bio2zarr/zarr_utils.py,sha256=99J7ycaG92K_AcWRF2S9A4ec2_4cXL6kjYT99GBfli4,415
+bio2zarr/vcf2zarr/__init__.py,sha256=0_of1iGzIDhvti49Gbcgd47oP63mKvouk9uLgKgiwoQ,791
+bio2zarr/vcf2zarr/icf.py,sha256=wGYgDMvfZBgNp2KuUiVhxbG9KIeT0W4-gQOb7SfZkis,42418
+bio2zarr/vcf2zarr/vcz.py,sha256=cfUCBsQW5dbhDu7NzXkd1Dalsev7UkFDXVOyChAHw8Q,49409
+bio2zarr/vcf2zarr/verification.py,sha256=uM-mg0yvUTBs-MvWBd4jxTS0zKCUbxEQpm4ALJADdMI,8037
+bio2zarr-0.1.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+bio2zarr-0.1.3.dist-info/METADATA,sha256=Joji4xU0q9NoTKh1qiM1opSrNDDdzG6V05t0qx_emj4,14978
+bio2zarr-0.1.3.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+bio2zarr-0.1.3.dist-info/entry_points.txt,sha256=3adtRrClMpjatEbiYqK5bm9WHA2PaJN5hK-Cs_zkpaI,97
+bio2zarr-0.1.3.dist-info/top_level.txt,sha256=ouAvp3u9N25eKrQbN8BCDLPcWWQLhtlgdHKu8AtEj5Q,9
+bio2zarr-0.1.3.dist-info/RECORD,,

{bio2zarr-0.1.1.dist-info → bio2zarr-0.1.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (75.8.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

bio2zarr-0.1.1.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=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,,