1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
|
from gffutils import parser, feature, helpers, constants
def test_feature_from_line():
# spaces and tabs should give identical results
line1 = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
line2 = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
assert feature.feature_from_line(
line1, strict=False, keep_order=True
) == feature.feature_from_line(line2, strict=False, keep_order=True)
def test_default_feature():
# Default Feature is 8 tab-delimited ".", with a trailing tab
assert str(feature.Feature()) == ". . . . . . . . "
def test_attributes_representations():
# These different ways of supplying attributes should yield identical
# results:
s = ". . . . . . . . ID=asdf"
for item in ('{"ID": ["asdf"]}', dict(ID=["asdf"]), "ID=asdf"):
result = str(feature.Feature(attributes=item))
assert result == s, result
def test_default_start_stop():
# Whether start or end is "." or None, attribute should always be None and
# printing should show "."
c = [".", None]
for i1 in c:
for i2 in c:
f = feature.Feature(start=i1, end=i2)
assert f.start is None
assert f.end is None
assert f.stop is None
assert str(f) == ". . . . . . . . ", str(f)
# Make sure zero works (protects against sloppy "if start:")
f = feature.Feature(start=0, end=0)
assert f.start == f.end == f.stop == 0
assert str(f) == ". . . 0 0 . . . ", str(f)
def test_aliases():
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
f = feature.feature_from_line(line, keep_order=True)
assert f.chrom == "chr2L" == f.seqid
assert f.end == 8116 == f.stop
f.chrom = "fake"
f.stop = 1
assert f.chrom == "fake" == f.seqid
assert f.stop == 1 == f.end
def test_string_representation():
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
f = feature.feature_from_line(line, keep_order=True)
assert line == str(f), str(f)
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690 some more stuff"
f = feature.feature_from_line(line, keep_order=True)
assert line == str(f)
def test_pbt_interval_conversion():
try:
import pybedtools
except ImportError:
return
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
f = feature.feature_from_line(line, strict=False, keep_order=True)
pbt = helpers.asinterval(f)
assert pbt.chrom == f.chrom == f.seqid
assert pbt.start == f.start - 1
assert pbt.stop == f.stop == f.end
pn = pbt.name
fn = f.attributes["Name"][0]
assert pn == fn, "%s, %s" % (pn, fn)
def test_hash():
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690 some more stuff"
f = feature.feature_from_line(line, keep_order=True)
assert hash(f) == hash(line)
def test_repr():
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690 some more stuff"
f = feature.feature_from_line(line, keep_order=True)
print(repr(f))
print(hex(id(f)))
assert repr(f) == ("<Feature exon (chr2L:7529-8116[+]) at %s>" % hex(id(f)))
def test_attribute_order():
# default order is gene_id, transcript_id. But feature_from_line -- if
# dialect not provided -- will infer its own dialect. In this case,
# transcript_id comes first.
attributes = 'transcript_id "mRNA1"; gene_id "gene1";'
a = feature.feature_from_line(
"""
chr1 . mRNA 1 100 . + . %s
"""
% attributes,
strict=False,
keep_order=True,
)
a.strict = True
a.keep_order = True
assert (
str(a) == 'chr1 . mRNA 1 100 . + . transcript_id "mRNA1"; gene_id "gene1";'
), str(a)
# ensure that using the default dialect uses the default order (and
# indidentally converts to GFF3 format)
orig_dialect = a.dialect
a.dialect = constants.dialect
a.keep_order = True
assert str(a) == "chr1 . mRNA 1 100 . + . gene_id=gene1;transcript_id=mRNA1", str(a)
# adding an attribute shoud always result in that attribute coming last (as
# long as that attribute is not in the dialect order)
a["dummy"] = ["asdf"]
a.strict = True
assert (
str(a) == "chr1 . mRNA 1 100 . + . gene_id=gene1;transcript_id=mRNA1;dummy=asdf"
), str(a)
def test_unjsonify():
attributes, dialect = parser._split_keyvals('transcript_id "mRNA1"')
assert attributes == {"transcript_id": ["mRNA1"]}, attributes
s = helpers._jsonify(attributes)
assert s == '{"transcript_id":["mRNA1"]}', s
d = helpers._unjsonify(s, isattributes=True)
assert d == attributes
class IsolatedTestCase(object):
"""
Isolated test case for checking that the module-level
constants.always_return_list works.
This was needed because having this test as a function caused other tests
to fail even though constants.always_return_list was put back to its
original setting. Apparently nose runs tests concurrently in the same
namespace or something? Anyway, these setup/teardowns do the trick.
"""
def setup_method(self):
constants.always_return_list = False
def teardown_method(self):
constants.always_return_list = True
def test_feature_single_item(self):
line = "chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690 some more stuff"
f = feature.feature_from_line(line, keep_order=True)
assert f["Name"] == ["CG11023:1"]
|
