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
|
import logging
import tempfile
from pbcore.io.dataset.DataSetMetaTypes import dsIdToSuffix
from pbcore.io import (DataSetMetaTypes, divideKeys,
SubreadSet, getDataSetUuid, getDataSetMetaType)
import pbcore.data as upstreamdata
log = logging.getLogger(__name__)
def keysToRanges(keys):
key_ranges = [[min(k), max(k)] for k in keys]
return key_ranges
class TestDataSetUtils:
"""Unit and integrationt tests for the DataSet class and \
associated module functions"""
def test_get_dataset_uuid(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
uuid = getDataSetUuid(ds_file)
assert uuid == ds.uuid
with open(ds_file, "w") as out:
out.write("hello world!")
uuid = getDataSetUuid(ds_file)
assert uuid is None
def test_get_dataset_metatype(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
meta_type = getDataSetMetaType(ds_file)
assert meta_type == "PacBio.DataSet.SubreadSet"
def test_dsIdToSuffix(self):
suffixes = ['subreadset.xml', 'alignmentset.xml',
'barcodeset.xml', 'consensusreadset.xml',
'consensusalignmentset.xml',
'referenceset.xml', 'contigset.xml']
for dsId, exp in zip(DataSetMetaTypes.ALL, suffixes):
assert dsIdToSuffix(dsId) == exp
def test_divideKeys_keysToRanges(self):
keys = [0, 1, 2, 3, 5, 8, 50]
res = divideKeys(keys, 0)
assert res == []
res = keysToRanges(res)
assert res == []
res = divideKeys(keys, 1)
assert res == [[0, 1, 2, 3, 5, 8, 50]]
res = keysToRanges(res)
assert res == [[0, 50]]
res = divideKeys(keys, 2)
assert res == [[0, 1, 2], [3, 5, 8, 50]]
res = keysToRanges(res)
assert res == [[0, 2], [3, 50]]
res = divideKeys(keys, 3)
assert res == [[0, 1], [2, 3], [5, 8, 50]]
res = keysToRanges(res)
assert res == [[0, 1], [2, 3], [5, 50]]
res = divideKeys(keys, 7)
assert res == [[0], [1], [2], [3], [5], [8], [50]]
res = keysToRanges(res)
assert res == [[0, 0], [1, 1], [2, 2], [3, 3],
[5, 5], [8, 8], [50, 50]]
res = divideKeys(keys, 8)
assert res == [[0], [1], [2], [3], [5], [8], [50]]
res = keysToRanges(res)
assert res == [[0, 0], [1, 1], [2, 2], [3, 3],
[5, 5], [8, 8], [50, 50]]
keys = [0, 1, 2, 2, 3, 5, 8, 50, 50]
res = divideKeys(keys, 0)
assert res == []
res = keysToRanges(res)
assert res == []
res = divideKeys(keys, 1)
assert res == [[0, 1, 2, 2, 3, 5, 8, 50, 50]]
res = keysToRanges(res)
assert res == [[0, 50]]
res = divideKeys(keys, 2)
assert res == [[0, 1, 2, 2], [3, 5, 8, 50, 50]]
res = keysToRanges(res)
assert res == [[0, 2], [3, 50]]
res = divideKeys(keys, 3)
assert res == [[0, 1, 2], [2, 3, 5], [8, 50, 50]]
res = keysToRanges(res)
assert res == [[0, 2], [2, 5], [8, 50]]
res = divideKeys(keys, 9)
assert res == [[0], [1], [2], [2], [3], [5], [8], [50], [50]]
res = keysToRanges(res)
assert res == [[0, 0], [1, 1], [2, 2], [2, 2], [3, 3],
[5, 5], [8, 8], [50, 50], [50, 50]]
res = divideKeys(keys, 10)
assert res == [[0], [1], [2], [2], [3], [5], [8], [50], [50]]
res = keysToRanges(res)
assert res == [[0, 0], [1, 1], [2, 2], [2, 2], [3, 3],
[5, 5], [8, 8], [50, 50], [50, 50]]
|
