V0.14rc

.github/workflows/main.yml

@@ -18,9 +18,8 @@ jobs:
 
       - name: conda env
         run: |
-          wget -O Mambaforge.sh  "https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-$(uname)-$(uname -m).sh"
-          curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-$(uname)-$(uname -m).sh"
-          bash Mambaforge.sh -b -p "${HOME}/conda"
+          wget -O Miniforge3.sh "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
+          bash Miniforge3.sh -b -p "${HOME}/conda"
           source "${HOME}/conda/etc/profile.d/conda.sh"
           source "${HOME}/conda/etc/profile.d/mamba.sh"
           which conda
@@ -102,7 +101,7 @@ jobs:
 
       - name: push artifact
         if: ${{ (matrix.python-version == 3.9) }}
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: doc
           path: /tmp/docs

doc/source/api.rst

@@ -117,10 +117,10 @@ Integration with other tools
     :toctree: autodocs
     :nosignatures:
 
-    gffutils.biopython_integration.to_seqfeature
-    gffutils.biopython_integration.from_seqfeature
-    gffutils.pybedtools_integration.tsses
-    gffutils.pybedtools_integration.to_bedtool
+    biopython_integration.to_seqfeature
+    biopython_integration.from_seqfeature
+    pybedtools_integration.tsses
+    pybedtools_integration.to_bedtool
 
 
 
@@ -131,10 +131,10 @@ Utilities
     :toctree: autodocs
     :nosignatures:
 
-    gffutils.helpers.asinterval
-    gffutils.helpers.merge_attributes
-    gffutils.helpers.sanitize_gff_db
-    gffutils.helpers.annotate_gff_db
-    gffutils.helpers.infer_dialect
-    gffutils.helpers.example_filename
-    gffutils.inspect.inspect
+    helpers.asinterval
+    helpers.merge_attributes
+    helpers.sanitize_gff_db
+    helpers.annotate_gff_db
+    helpers.infer_dialect
+    helpers.example_filename
+    inspect.inspect

doc/source/conf.py

@@ -53,5 +53,3 @@
 templates_path = ['_templates']
 exclude_patterns = []
 html_theme = 'sphinx_rtd_theme'
-html_static_path = ['_static']
-html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]

gffutils/interface.py

@@ -1285,7 +1285,7 @@ def create_introns(
 
             with open('tmp.gtf', 'w') as fout:
                 for intron in db.create_introns(**intron_kwargs):
-                    fout.write(str(intron) + "\n")
+                    fout.write(str(intron) + "\\n")
             db.update(gffutils.DataIterator('tmp.gtf'), **create_kwargs)
 
         """

gffutils/pybedtools_integration.py

@@ -113,7 +113,7 @@ def tsses(
     if they overlap (as in the first two):
 
 
-    >>> print(tsses(db))                        # doctest: +NORMALIZE_WHITESPACE
+    >>> print(gffutils.pybedtools_integration.tsses(db))                        # doctest: +NORMALIZE_WHITESPACE
     chr2L	gffutils_derived	transcript_TSS	7529	7529	.	+	.	gene_id "FBgn0031208"; transcript_id "FBtr0300689";
     chr2L	gffutils_derived	transcript_TSS	7529	7529	.	+	.	gene_id "FBgn0031208"; transcript_id "FBtr0300690";
     chr2L	gffutils_derived	transcript_TSS	11000	11000	.	-	.	gene_id "Fk_gene_1"; transcript_id "transcript_Fk_gene_1";
@@ -124,7 +124,7 @@ def tsses(
     Default merging, showing the first two TSSes merged and reported as
     a single unique TSS for the gene. Note the conversion to BED:
 
-    >>> x = tsses(db, merge_overlapping=True)
+    >>> x = gffutils.pybedtools_integration.tsses(db, merge_overlapping=True)
     >>> print(x)  # doctest: +NORMALIZE_WHITESPACE
     chr2L	7528	7529	FBgn0031208	.	+
     chr2L	10999	11000	Fk_gene_1	.	-
@@ -135,7 +135,7 @@ def tsses(
     be easier to parse than the original GTF or GFF file. With no merging
     specified, we must add `as_bed6=True` to see the names in BED format.
 
-    >>> x = tsses(db, attrs=['gene_id', 'transcript_id'], as_bed6=True)
+    >>> x = gffutils.pybedtools_integration.tsses(db, attrs=['gene_id', 'transcript_id'], as_bed6=True)
     >>> print(x)  # doctest: +NORMALIZE_WHITESPACE
     chr2L	7528	7529	FBgn0031208:FBtr0300689	.	+
     chr2L	7528	7529	FBgn0031208:FBtr0300690	.	+
@@ -145,7 +145,7 @@ def tsses(
 
     Use a 3kb merge distance so the last 2 features are merged together:
 
-    >>> x = tsses(db, merge_overlapping=True, merge_kwargs=dict(d=3000))
+    >>> x = gffutils.pybedtools_integration.tsses(db, merge_overlapping=True, merge_kwargs=dict(d=3000))
     >>> print(x)  # doctest: +NORMALIZE_WHITESPACE
     chr2L	7528	7529	FBgn0031208	.	+
     chr2L	10999	12500	Fk_gene_1,Fk_gene_2	.	-
@@ -154,7 +154,7 @@ def tsses(
 
     The set of unique TSSes for each gene, +1kb upstream and 500bp downstream:
 
-    >>> x = tsses(db, merge_overlapping=True)
+    >>> x = gffutils.pybedtools_integration.tsses(db, merge_overlapping=True)
     >>> x = x.slop(l=1000, r=500, s=True, genome='dm3')
     >>> print(x)  # doctest: +NORMALIZE_WHITESPACE
     chr2L	6528	8029	FBgn0031208	.	+

gffutils/scripts/gffutils-cli

@@ -76,7 +76,7 @@ def fetch(db, ids):
      (like grep -v)''')
 @arg('--exclude-self', help='''Use this to suppress reporting the IDs you've
      provided.''')
-def children(db, ids, limit=None, exclude=None, exclude_self=False):
+def children(db, ids, *, limit=None, exclude=None, exclude_self=False):
     """
     Fetch children from the database according to ID.
     """
@@ -110,7 +110,7 @@ def children(db, ids, limit=None, exclude=None, exclude_self=False):
      (like grep -v)''')
 @arg('--exclude-self', help='''Use this to suppress reporting the IDs you've
      provided.''')
-def parents(db, ids, limit=None, exclude=None, exclude_self=False):
+def parents(db, ids, *, limit=None, exclude=None, exclude_self=False):
     """
     Fetch parents from the database according to ID.
     """
@@ -167,7 +167,7 @@ def common(db):
 @arg('--disable-infer-transcripts', help='''Disable inferring of transcript
      extents for GTF files. Use this if your GTF file already has "transcript"
      featuretypes''')
-def create(filename, output=None, force=False, quiet=False, merge="merge",
+def create(filename, *, output=None, force=False, quiet=False, merge="merge",
            disable_infer_genes=False, disable_infer_transcripts=False):
     """
     Create a database.
@@ -198,7 +198,7 @@ def clean(filename):
 @arg('--in-place',
      help='''Sanitize file in-place: overwrites current file with sanitized
      version.''')
-def sanitize(filename,
+def sanitize(filename, *,
              in_memory=True,
              in_place=False):
     """
@@ -225,7 +225,7 @@ def sanitize(filename,
 @arg('filename', help='''GFF or GTF file to use.''')
 @arg('--in-place', help='''Remove duplicates in place (overwrite current
      file.)''')
-def rmdups(filename, in_place=False):
+def rmdups(filename, *, in_place=False):
     """
     Remove duplicates from a GFF file.
     """
@@ -278,7 +278,7 @@ def convert(filename):
 @arg('--featuretype', help='''Restrict to a particular featuretype.  This can
      be faster than doing a grep on the output, since it restricts the search
      space in the database''')
-def search(db, text, featuretype=None):
+def search(db, text, *, featuretype=None):
     """
     Search the attributes.
     """

gffutils/test/test_1.py

@@ -482,58 +482,51 @@ def test_sanitize_gff():
     print("Sanitized GFF successfully.")
 
 
-def test_region():
-
+@pytest.mark.parametrize("kwargs,expected", [
+    # previously failed, see issue #45
+    (dict(seqid="chr2L", start=1, end=2e9, completely_within=True), 27),
+    (dict(region="chr2L", start=0), ValueError),
+    (dict(region="chr2L", end=0), ValueError),
+    (dict(region="chr2L", seqid=0), ValueError),
+    # these coords should catch everything
+    (dict(region="chr2L:7529-12500"), 27),
+    # stranded versions:
+    (dict(region="chr2L:7529-12500", strand="."), 0),
+    (dict(region="chr2L:7529-12500", strand="+"), 21),
+    (dict(region="chr2L:7529-12500", strand="-"), 6),
+    # different ways of selecting only that last exon in the last gene:
+    (dict(seqid="chr2L", start=11500, featuretype="exon"), 1),
+    (dict(seqid="chr2L", start=9500, featuretype="exon", strand="+"), 1),
+    # alternative method
+    (dict(seqid="chr2L", start=7529, end=12500), 27),
+    # since default completely_within=False, this catches anything that
+    # falls after 7680.  So it only excludes the 5'UTR, which ends at 7679.
+    (dict(seqid="chr2L", start=7680), 26),
+    # but completely_within=True will exclude the gene and mRNAs, first
+    # exon and the 5'UTR
+    (dict(seqid="chr2L", start=7680, completely_within=True), 22),
+    # similarly, this will *exclude* anything before 7680
+    (dict(seqid="chr2L", end=7680), 5),
+    # and also similarly, this will only get us the 5'UTR which is the only
+    # feature falling completely before 7680
+    (dict(seqid="chr2L", end=7680, completely_within=True), 1),
+    # and there's only features from chr2L in this file, so this catches
+    # everything too
+    (dict(region="chr2L"), 27),
+    # using seqid should work similarly to `region` with only chromosome
+    (dict(seqid="chr2L"), 27),
+    # nonexistent
+    (dict(region="nowhere"), 0),
+])
+def test_region(kwargs, expected):
     db_fname = gffutils.example_filename("FBgn0031208.gff")
     db = gffutils.create_db(db_fname, ":memory:", keep_order=True)
 
-    def _check(item):
-        kwargs, expected = item
-        try:
-            obs = list(db.region(**kwargs))
-            assert len(obs) == expected, "expected %s got %s" % (expected, len(obs))
-        except expected:
-            pass
-
-    regions = [
-        # previously failed, see issue #45
-        (dict(seqid="chr2L", start=1, end=2e9, completely_within=True), 27),
-        (dict(region="chr2L", start=0), ValueError),
-        (dict(region="chr2L", end=0), ValueError),
-        (dict(region="chr2L", seqid=0), ValueError),
-        # these coords should catch everything
-        (dict(region="chr2L:7529-12500"), 27),
-        # stranded versions:
-        (dict(region="chr2L:7529-12500", strand="."), 0),
-        (dict(region="chr2L:7529-12500", strand="+"), 21),
-        (dict(region="chr2L:7529-12500", strand="-"), 6),
-        # different ways of selecting only that last exon in the last gene:
-        (dict(seqid="chr2L", start=11500, featuretype="exon"), 1),
-        (dict(seqid="chr2L", start=9500, featuretype="exon", strand="+"), 1),
-        # alternative method
-        (dict(seqid="chr2L", start=7529, end=12500), 27),
-        # since default completely_within=False, this catches anything that
-        # falls after 7680.  So it only excludes the 5'UTR, which ends at 7679.
-        (dict(seqid="chr2L", start=7680), 26),
-        # but completely_within=True will exclude the gene and mRNAs, first
-        # exon and the 5'UTR
-        (dict(seqid="chr2L", start=7680, completely_within=True), 22),
-        # similarly, this will *exclude* anything before 7680
-        (dict(seqid="chr2L", end=7680), 5),
-        # and also similarly, this will only get us the 5'UTR which is the only
-        # feature falling completely before 7680
-        (dict(seqid="chr2L", end=7680, completely_within=True), 1),
-        # and there's only features from chr2L in this file, so this catches
-        # everything too
-        (dict(region="chr2L"), 27),
-        # using seqid should work similarly to `region` with only chromosome
-        (dict(seqid="chr2L"), 27),
-        # nonexistent
-        (dict(region="nowhere"), 0),
-    ]
-
-    for item in regions:
-        yield _check, item
+    try:
+        obs = list(db.region(**kwargs))
+        assert len(obs) == expected, "expected %s got %s" % (expected, len(obs))
+    except expected:
+        pass
 
 
 def test_nonascii():

gffutils/test/test_biopython_integration.py

@@ -1,6 +1,10 @@
 from gffutils import example_filename
 import gffutils
 import gffutils.biopython_integration as bp
+import pytest
+
+# Skip tests entirely if BioPython not available
+pytest.importorskip('Bio')
 
 
 def test_roundtrip():