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
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
|
# This file is part of khmer, https://github.com/dib-lab/khmer/, and is
# Copyright (C) 2014-2015, Michigan State University.
# Copyright (C) 2015, The Regents of the University of California.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following
# disclaimer in the documentation and/or other materials provided
# with the distribution.
#
# * Neither the name of the Michigan State University nor the names
# of its contributors may be used to endorse or promote products
# derived from this software without specific prior written
# permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# Contact: khmer-project@idyll.org
# pylint: disable=C0111,C0103,E1103,W0612
from __future__ import print_function
from __future__ import absolute_import
from __future__ import unicode_literals
import sys
import os
import os.path
import shutil
from io import StringIO
import traceback
import nose
from nose.plugins.attrib import attr
import glob
import imp
from . import khmer_tst_utils as utils
import khmer
import screed
from .test_scripts import _make_counting
def scriptpath(script):
return script
def teardown():
utils.cleanup()
def test_import_all():
sandbox_path = os.path.join(os.path.dirname(__file__), "../sandbox")
if not os.path.exists(sandbox_path):
raise nose.SkipTest("sandbox scripts are only tested in a repository")
path = os.path.join(sandbox_path, "*.py")
scripts = glob.glob(path)
for s in scripts:
s = os.path.normpath(s)
yield _checkImportSucceeds('test_sandbox_scripts.py', s)
class _checkImportSucceeds(object):
def __init__(self, tag, filename):
self.tag = tag
self.filename = filename
self.description = '%s: test import %s' % (self.tag,
os.path.split(filename)[-1])
def __call__(self):
try:
mod = imp.load_source('__zzz', self.filename)
except:
print(traceback.format_exc())
raise AssertionError("%s cannot be imported" % (self.filename,))
#
oldargs = sys.argv
sys.argv = [self.filename]
oldout, olderr = sys.stdout, sys.stderr
sys.stdout = StringIO()
sys.stderr = StringIO()
try:
try:
global_dict = {'__name__': '__main__'}
exec(
compile(open(self.filename).read(), self.filename, 'exec'),
global_dict)
except (ImportError, SyntaxError) as err:
print("{0}".format(err))
raise AssertionError("%s cannot be exec'd" % (self.filename),
"{0}".format(traceback))
except:
pass # other failures are expected :)
finally:
sys.argv = oldargs
out, err = sys.stdout.getvalue(), sys.stderr.getvalue()
sys.stdout, sys.stderr = oldout, olderr
def test_sweep_reads():
readfile = utils.get_temp_filename('reads.fa')
contigfile = utils.get_temp_filename('contigs.fp')
in_dir = os.path.dirname(contigfile)
shutil.copyfile(utils.get_test_data('test-sweep-reads.fa'), readfile)
shutil.copyfile(utils.get_test_data('test-sweep-contigs.fp'), contigfile)
script = scriptpath('sweep-reads.py')
args = ['-k', '25', '--prefix', 'test', '--label-by-pid',
contigfile, readfile, 'junkfile.fa']
status, out, err = utils.runscript(
script, args, in_dir, sandbox=True)
# check if the bad file was skipped without issue
assert 'ERROR' in err, err
assert 'skipping' in err, err
out1 = os.path.join(in_dir, 'test_0.fa')
out2 = os.path.join(in_dir, 'test_1.fa')
mout = os.path.join(in_dir, 'test_multi.fa')
oout = os.path.join(in_dir, 'test_orphaned.fa')
print(os.listdir(in_dir))
assert os.path.exists(out1)
assert os.path.exists(out2)
assert os.path.exists(mout)
assert os.path.exists(oout)
seqs1 = set([r.name for r in screed.open(out1)])
seqs2 = set([r.name for r in screed.open(out2)])
seqsm = set([r.name for r in screed.open(mout)])
seqso = set([r.name for r in screed.open(oout)])
print(seqs1)
print(seqs2)
print(seqsm)
print(seqso)
assert seqs1 == set(['read1_p0\t0', 'read2_p0\t0'])
assert seqs2 == set(['read3_p1\t1'])
assert (seqsm == set(['read4_multi\t0\t1']) or
seqsm == set(['read4_multi\t1\t0']))
assert seqso == set(['read5_orphan'])
def test_sweep_reads_fq():
readfile = utils.get_temp_filename('reads.fa')
contigfile = utils.get_temp_filename('contigs.fp')
in_dir = os.path.dirname(contigfile)
shutil.copyfile(utils.get_test_data('test-sweep-reads.fq'), readfile)
shutil.copyfile(utils.get_test_data('test-sweep-contigs.fp'), contigfile)
script = scriptpath('sweep-reads.py')
args = ['-k', '25', '--prefix', 'test', '--label-by-pid',
contigfile, readfile, 'junkfile.fa']
status, out, err = utils.runscript(
script, args, in_dir, sandbox=True)
# check if the bad file was skipped without issue
assert 'ERROR' in err, err
assert 'skipping' in err, err
out1 = os.path.join(in_dir, 'test_0.fq')
out2 = os.path.join(in_dir, 'test_1.fq')
mout = os.path.join(in_dir, 'test_multi.fq')
oout = os.path.join(in_dir, 'test_orphaned.fq')
assert os.path.exists(out1)
assert os.path.exists(out2)
assert os.path.exists(mout)
assert os.path.exists(oout)
print(open(out1).read())
print(os.listdir(in_dir))
seqs1 = set([r.name for r in screed.open(out1)])
seqs2 = set([r.name for r in screed.open(out2)])
seqsm = set([r.name for r in screed.open(mout)])
seqso = set([r.name for r in screed.open(oout)])
print(seqs1)
print(seqs2)
print(seqsm)
print(seqso)
assert seqs1 == set(['read1_p0\t0', 'read2_p0\t0'])
assert seqs2 == set(['read3_p1\t1'])
assert (seqsm == set(['read4_multi\t0\t1']) or
seqsm == set(['read4_multi\t1\t0']))
assert seqso == set(['read5_orphan'])
seqs1 = set([r.quality for r in screed.open(out1)])
seqs2 = set([r.quality for r in screed.open(out2)])
seqsm = set([r.quality for r in screed.open(mout)])
seqso = set([r.quality for r in screed.open(oout)])
def test_sweep_reads_2():
infile = utils.get_temp_filename('seqs.fa')
inref = utils.get_temp_filename('ref.fa')
shutil.copyfile(utils.get_test_data('random-20-X2.fa'), infile)
shutil.copyfile(utils.get_test_data('random-20-a.fa'), inref)
wdir = os.path.dirname(inref)
script = scriptpath('sweep-reads.py')
args = ['-m', '50', '-k', '20', '-l', '9', '-b', '60', '--prefix',
'test', '--label-by-seq', inref, infile]
status, out, err = utils.runscript(script, args, wdir, sandbox=True)
for i in range(99):
p = os.path.join(wdir, 'test_{i}.fa'.format(i=i))
print(p, err, out)
assert os.path.exists(p)
os.remove(p)
assert os.path.exists(os.path.join(wdir, 'test.counts.csv'))
assert os.path.exists(os.path.join(wdir, 'test.dist.txt'))
assert not os.path.exists(os.path.join(wdir, 'test_multi.fa'))
def test_sweep_reads_3():
infile = utils.get_temp_filename('seqs.fa')
shutil.copyfile(utils.get_test_data('random-20-a.fa'), infile)
wdir = os.path.dirname(infile)
script = scriptpath('sweep-reads.py')
args = ['-m', '75', '-k', '20', '-l', '1', '--prefix',
'test', '--label-by-group', '10', infile, infile]
status, out, err = utils.runscript(script, args, wdir, sandbox=True)
for i in range(10):
p = os.path.join(wdir, 'test_{i}.fa'.format(i=i))
print(p, err, out)
assert os.path.exists(p)
os.remove(p)
counts_fn = os.path.join(wdir, 'test.counts.csv')
with open(counts_fn) as cfp:
for line in cfp:
_, _, c = line.partition(',')
assert int(c) in [9, 10]
assert os.path.exists(counts_fn)
assert os.path.exists(os.path.join(wdir, 'test.dist.txt'))
assert not os.path.exists(os.path.join(wdir, 'test_multi.fa'))
def test_collect_reads():
outfile = utils.get_temp_filename('out.graph')
infile = utils.get_test_data('test-reads.fa')
script = 'collect-reads.py'
args = ['-M', '1e7', outfile, infile]
status, out, err = utils.runscript(script, args, sandbox=True)
assert status == 0
assert os.path.exists(outfile)
def test_saturate_by_median():
infile = utils.get_test_data('test-reads.fa')
script = 'saturate-by-median.py'
args = ['-M', '1e7', infile]
status, out, err = utils.runscript(script, args, sandbox=True)
assert status == 0
def test_count_kmers_1():
infile = utils.get_temp_filename('input.fa')
shutil.copyfile(utils.get_test_data('random-20-a.fa'), infile)
ctfile = _make_counting(infile)
script = scriptpath('count-kmers.py')
args = [ctfile, infile]
status, out, err = utils.runscript(script, args, os.path.dirname(infile),
sandbox=True)
out = out.splitlines()
assert 'TTGTAACCTGTGTGGGGTCG,1' in out
def test_count_kmers_2_single():
infile = utils.get_temp_filename('input.fa')
shutil.copyfile(utils.get_test_data('random-20-a.fa'), infile)
script = scriptpath('count-kmers-single.py')
args = ['-x', '1e7', '-k', '20', '-N', '2', infile]
status, out, err = utils.runscript(script, args, os.path.dirname(infile),
sandbox=True)
out = out.splitlines()
assert 'TTGTAACCTGTGTGGGGTCG,1' in out
def test_multirename_fasta():
infile1 = utils.get_temp_filename('test-multi.fa')
multioutfile = utils.get_temp_filename('out.fa')
infile2 = utils.get_temp_filename('out.fa')
shutil.copyfile(utils.get_test_data('test-multi.fa'), infile1)
shutil.copyfile(utils.get_test_data('multi-output.fa'), infile2)
args = ['assembly', infile1]
_, out, err = utils.runscript('multi-rename.py', args, sandbox=True)
r = open(infile2).read()
assert r in out
|
