Fix dependency chain broken by newer Polars versions

Makefile

@@ -13,8 +13,7 @@ PYTHON3 ?= python3
 all: check
 
 check:
-	./lint.sh
-	cd test && pytest
+	./lint-and-test.sh
 
 #: Clean up temporary files
 clean:

lint-and-test.sh

@@ -0,0 +1 @@
+./lint.sh && ./test.sh 

lint.sh

@@ -10,6 +10,6 @@ set -o errexit
 find pyensembl -name '*.py' \
   | xargs pylint \
   --errors-only \
-  --disable=print-statement,unsubscriptable-object,not-an-iterable,no-member
+  --disable=unsubscriptable-object,not-an-iterable,no-member
 
 echo 'Passes pylint check'

pyensembl/species.py

@@ -100,7 +100,8 @@ def __init__(self, latin_name, synonyms=[], reference_assemblies={}):
             for i in range(start, end + 1):
                 if i in self._release_to_genome:
                     raise ValueError(
-                        "Ensembl release %d already has an associated genome" % i
+                        "Ensembl release %d for %s already has an associated genome"
+                        % (i, latin_name)
                     )
                 self._release_to_genome[i] = genome_name
 
@@ -304,6 +305,18 @@ def check_species_object(species_name_or_object):
     reference_assemblies={"Sscrofa11.1": (75, MAX_ENSEMBL_RELEASE)},
 )
 
+zebrafish = Species.register(
+    latin_name="danio_rerio",
+    synonyms=["zebrafish"],
+    reference_assemblies={
+        "ZFISH7": (47, 53),
+        "Zv8": (54, 59),
+        "Zv9": (60, 79),
+        "GRCz10": (80, 91),
+        "GRCz11": (92, MAX_ENSEMBL_RELEASE),
+    },
+)
+
 fly = Species.register(
     latin_name="drosophila_melanogaster",
     synonyms=["drosophila", "fruit fly", "fly"],
@@ -316,10 +329,24 @@ def check_species_object(species_name_or_object):
     },
 )
 
+nematode = Species.register(
+    latin_name="caenorhabditis_elegans",
+    synonyms=["nematode", "C_elegans"],
+    reference_assemblies={
+        "WS180": (47, 49),
+        "WS190": (50, 54),
+        "WS200": (55, 57),
+        "WS210": (58, 59),
+        "WS220": (61, 66),
+        "WBcel215": (67, 70),
+        "WBcel235": (71, MAX_ENSEMBL_RELEASE),
+    },
+)
+
 yeast = Species.register(
     latin_name="saccharomyces_cerevisiae",
-    synonyms=["yeast","budding_yeast"],
+    synonyms=["yeast", "budding_yeast"],
     reference_assemblies={
         "R64-1-1": (76, MAX_ENSEMBL_RELEASE),
     },
-)
+)

pyensembl/version.py

@@ -1 +1 @@
-__version__ = "2.2.9"
+__version__ = "2.3.0"

requirements.txt

@@ -2,7 +2,7 @@ typechecks>=0.0.2
 datacache>=1.1.4
 memoized-property>=1.0.2
 tinytimer
-gtfparse>=1.3.0,<2.0.0
+gtfparse>=2.1.0,<2.2.0
 serializable
 nose>=1.3.3
 pylint>=1.4.4

test.sh

@@ -0,0 +1 @@
+pytest --cov=pyensembl/ --cov-report=term-missing tests

tests/common.py

@@ -0,0 +1,88 @@
+import functools
+
+from pyensembl import genome_for_reference_name, cached_release
+
+import pytest
+
+
+grch37 = genome_for_reference_name("GRCh37")
+grch38 = genome_for_reference_name("GRCh38")
+
+major_releases = [grch37, grch38]
+
+contigs = [str(c) for c in range(1, 23)] + ["X", "Y", "M"]
+
+
+def run_multiple_genomes(*versions):
+    if len(versions) == 1 and callable(versions[0]):
+        return pytest.mark.parametrize("genome", major_releases)(versions[0])
+    if not versions:
+        genomes = major_releases
+    else:
+        genomes = [cached_release(v) for v in versions]
+    return lambda fn: pytest.mark.parametrize("genome", genomes)(fn)
+
+
+# TemporaryDirectory only got added to Python in version 3.2
+try:
+    # pylint: disable=no-name-in-module
+    from tempfile import TemporaryDirectory
+
+except ImportError:
+    # only added in Python 3.2
+    from tempfile import mkdtemp
+    from shutil import rmtree
+
+    class TemporaryDirectory(object):
+        def __init__(self):
+            self.name = mkdtemp()
+
+        def __enter__(self, *args, **kwargs):
+            return self.name
+
+        def __exit__(self, type, value, traceback):
+            rmtree(self.name)
+            # don't suppress exceptions
+            return False
+
+
+def eq_(x, y, msg=None):
+    if msg is None:
+        assert x == y
+    else:
+        assert x == y, msg
+
+
+def neq_(x, y, msg=None):
+    if msg is None:
+        assert x != y
+    else:
+        assert x != y, msg
+
+
+def gt_(x, y, msg=None):
+    if msg is None:
+        assert x > y
+    else:
+        assert x > y, msg
+
+
+def gte_(x, y, msg=None):
+    if msg is None:
+        assert x >= y
+    else:
+        assert x >= y, msg
+
+
+def lt_(x, y, msg=None):
+    if msg is None:
+        assert x < y
+    else:
+        assert x < y, msg
+
+
+def lte_(x, y, msg=None):
+    if msg is None:
+        assert x <= y
+    else:
+        assert x <= y, msg

test/data/gencode.ucsc.small.gtf → tests/data/gencode.ucsc.small.gtf

@@ -1,3 +1,4 @@
+# expected format is <seqname> <source> <feature> <start> <end> <score> <strand> <frame> [attributes] [comments]
 chr1	hg38_knownGene	exon	17369	17436	0.000000	-	.	gene_id "uc031tla.1"; transcript_id "uc031tla.1"; 
 chr1	hg38_knownGene	exon	29554	30039	0.000000	+	.	gene_id "uc057aty.1"; transcript_id "uc057aty.1"; 
 chr1	hg38_knownGene	exon	30564	30667	0.000000	+	.	gene_id "uc057aty.1"; transcript_id "uc057aty.1"; 
@@ -12,4 +13,4 @@ chr1	hg38_knownGene	exon	35245	35481	0.000000	-	.	gene_id "uc057aua.1"; transcri
 chr1	hg38_knownGene	exon	35721	36073	0.000000	-	.	gene_id "uc057aua.1"; transcript_id "uc057aua.1"; 
 chr1	hg38_knownGene	start_codon	69091	69093	0.000000	+	.	gene_id "uc001aal.1"; transcript_id "uc001aal.1"; 
 chr1	hg38_knownGene	CDS	69091	70005	0.000000	+	0	gene_id "uc001aal.1"; transcript_id "uc001aal.1"; 
-chr1	hg38_knownGene	stop_codon	70006	70008	0.000000	+	.	gene_id "uc001aal.1"; transcript_id "uc001aal.1";
+chr1	hg38_knownGene	stop_codon	70006	70008	0.000000	+	.	gene_id "uc001aal.1"; transcript_id "uc001aal.1";

test/data/refseq.ucsc.small.gtf → tests/data/refseq.ucsc.small.gtf

@@ -21,4 +21,4 @@ chr1	hg38_refGene	CDS	67115352	67115464	0.000000	-	1	gene_id "NM_001276352"; tra
 chr1	hg38_refGene	exon	67115352	67115464	0.000000	-	.	gene_id "NM_001276352"; transcript_id "NM_001276352";
 chr1	hg38_refGene	CDS	67125752	67125909	0.000000	-	0	gene_id "NM_001276352"; transcript_id "NM_001276352";
 chr1	hg38_refGene	exon	67125752	67125909	0.000000	-	.	gene_id "NM_001276352"; transcript_id "NM_001276352";
-chr1	hg38_refGene	CDS	67127166	67127240	0.000000	-	0	gene_id "NM_001276352"; transcript_id "NM_001276352";
+chr1	hg38_refGene	CDS	67127166	67127240	0.000000	-	0	gene_id "NM_001276352"; transcript_id "NM_001276352";

test/test_ensembl_gtf.py → tests/test_ensembl_gtf.py

@@ -2,9 +2,10 @@
 from os.path import exists
 
 
-from .common import test_ensembl_releases
+from .common import run_multiple_genomes
 
-@test_ensembl_releases()
+
+@run_multiple_genomes()
 def gtf_path_endswith_gtf_gz(ensembl):
     path = ensembl.gtf.gtf_path
     assert exists(path)

test/test_gene_ids.py → tests/test_gene_ids.py

@@ -6,13 +6,14 @@
 """
 from __future__ import absolute_import
 
-from nose.tools import assert_raises, ok_
+from pytest import raises
 from pyensembl import ensembl_grch38, cached_release
 
-from .common import test_ensembl_releases
+from .common import run_multiple_genomes, eq_
 
 ensembl77 = cached_release(77, "human")
 
+
 def test_gene_ids_grch38_hla_a():
     # chr6:29,945,884  is a position for HLA-A
     # Gene ID = ENSG00000206503
@@ -21,40 +22,55 @@ def test_gene_ids_grch38_hla_a():
     # Summary?db=core;g=ENSG00000206503;r=6:29941260-29945884
     ids = ensembl_grch38.gene_ids_at_locus(6, 29945884)
     expected = "ENSG00000206503"
-    assert ids == ["ENSG00000206503"], \
-        "Expected HLA-A, gene ID = %s, got: %s" % (expected, ids)
+    assert ids == ["ENSG00000206503"], "Expected HLA-A, gene ID = %s, got: %s" % (
+        expected,
+        ids,
+    )
+
 
 def test_gene_ids_of_gene_name_hla_grch38():
     hla_a_gene_ids = ensembl_grch38.gene_ids_of_gene_name("HLA-A")
-    assert 'ENSG00000206503' in hla_a_gene_ids, hla_a_gene_ids
+    assert "ENSG00000206503" in hla_a_gene_ids, hla_a_gene_ids
 
     hla_b_gene_ids = ensembl_grch38.gene_ids_of_gene_name("HLA-B")
-    assert 'ENSG00000234745' in hla_b_gene_ids, hla_b_gene_ids
+    assert "ENSG00000234745" in hla_b_gene_ids, hla_b_gene_ids
 
     hla_c_gene_ids = ensembl_grch38.gene_ids_of_gene_name("HLA-C")
-    assert 'ENSG00000204525' in hla_c_gene_ids, hla_c_gene_ids
+    assert "ENSG00000204525" in hla_c_gene_ids, hla_c_gene_ids
+
 
 def test_gene_id_of_protein_id_release77():
     gene_id = ensembl77.gene_id_of_protein_id("ENSP00000485677")
-    ok_('ENSG00000279634', gene_id)
+    eq_("ENSG00000279634", gene_id)
+
 
 def test_gene_id_of_invalid_name():
-    with assert_raises(Exception):
-        ensembl_grch38.gene_ids_of_gene_name(
-            "A wonderous pony sees through your soul")
+    with raises(Exception):
+        ensembl_grch38.gene_ids_of_gene_name("A wonderous pony sees through your soul")
+
 
-@test_ensembl_releases()
-def test_gene_ids_on_contig(ensembl):
-    gene_ids_chr17 = ensembl.gene_ids(contig=17)
+@run_multiple_genomes()
+def test_gene_ids_on_contig(genome):
+    gene_ids_chr17 = genome.gene_ids(contig=17)
     # gene ID of TP53
     tp53 = "ENSG00000141510"
-    assert tp53 in gene_ids_chr17, \
-        "Missing %s from %s on chr17, example IDs: %s (total = %d)" % (
-            tp53, ensembl, gene_ids_chr17[:5], len(gene_ids_chr17))
+    assert (
+        tp53 in gene_ids_chr17
+    ), "Missing %s from %s on chr17, example IDs: %s (total = %d)" % (
+        tp53,
+        genome,
+        gene_ids_chr17[:5],
+        len(gene_ids_chr17),
+    )
 
     # gene ID of SMAD4
-    gene_ids_chr18 = ensembl.gene_ids(contig=18)
+    gene_ids_chr18 = genome.gene_ids(contig=18)
     smad4 = "ENSG00000141646"
-    assert smad4 in gene_ids_chr18, \
-        "Missing %s from %s on chr18, example result: %s (total = %d)" % (
-            smad4, ensembl, gene_ids_chr18[:5], len(gene_ids_chr18))
+    assert (
+        smad4 in gene_ids_chr18
+    ), "Missing %s from %s on chr18, example result: %s (total = %d)" % (
+        smad4,
+        genome,
+        gene_ids_chr18[:5],
+        len(gene_ids_chr18),
+    )