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
|
#!/usr/bin/env python
from __future__ import print_function
"""
test_split_and_combine.py
test branching dependencies
"""
import sys
import os
tempdir = os.path.relpath(os.path.abspath(os.path.splitext(__file__)[0])) + "/"
verbose_output = sys.stderr
# add grandparent to search path for testing
grandparent_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
sys.path.insert(0, grandparent_dir)
# module name = script name without extension
module_name = os.path.splitext(os.path.basename(__file__))[0]
# funky code to import by file name
parent_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
from ruffus import posttask, split, merge, transform, pipeline_printout, pipeline_run, Pipeline, suffix
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# imports
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
import unittest
import shutil
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# Tasks
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# split_fasta_file
#
@posttask(lambda: verbose_output.write(" Split into %d files\n" % 10))
@split(tempdir + "original.fa", [tempdir + "files.split.success", tempdir + "files.split.*.fa"])
def split_fasta_file (input_file, outputs):
#
# remove previous fasta files
#
success_flag = outputs[0]
output_file_names = outputs[1:]
for f in output_file_names:
os.unlink(f)
#
# create as many files as we are simulating in jobs_per_task
#
for i in range(10):
with open(tempdir + "files.split.%03d.fa" % i, "w") as oo:
pass
with open(success_flag, "w") as oo:
pass
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# align_sequences
#
@posttask(lambda: verbose_output.write(" Sequences aligned\n"))
@transform(split_fasta_file, suffix(".fa"), ".aln") # fa -> aln
def align_sequences (input_file, output_filename):
with open(output_filename, "w") as oo:
oo.write("%s\n" % output_filename)
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# percentage_identity
#
@posttask(lambda: verbose_output.write(" %Identity calculated\n"))
@transform(align_sequences, # find all results from align_sequences
suffix(".aln"), # replace suffix with:
[r".pcid", # .pcid suffix for the result
r".pcid_success"]) # .pcid_success to indicate job completed
def percentage_identity (input_file, output_files):
(output_filename, success_flag_filename) = output_files
with open(output_filename, "w") as oo:
oo.write("%s\n" % output_filename)
with open(success_flag_filename, "w") as oo:
pass
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# combine_results
#
@posttask(lambda: verbose_output.write(" Results recombined\n"))
@merge(percentage_identity, [tempdir + "all.combine_results",
tempdir + "all.combine_results_success"])
def combine_results (input_files, output_files):
"""
Combine all
"""
(output_filename, success_flag_filename) = output_files
with open(output_filename, "w") as out:
for inp, flag in input_files:
with open(inp) as ii:
out.write(ii.read())
with open(success_flag_filename, "w") as oo:
pass
class Test_ruffus(unittest.TestCase):
def setUp(self):
try:
shutil.rmtree(tempdir)
except:
pass
os.makedirs(tempdir)
open(tempdir + "original.fa", "w").close()
def tearDown(self):
try:
shutil.rmtree(tempdir)
pass
except:
pass
def test_ruffus (self):
pipeline_run(multiprocess = 50, verbose = 0, pipeline= "main")
if not os.path.exists(tempdir + "all.combine_results"):
raise Exception("Missing %s" % (tempdir + "all.combine_results"))
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.split(task_func = split_fasta_file,
input = tempdir + "original.fa",
output = [tempdir + "files.split.success",
tempdir + "files.split.*.fa"])\
.posttask(lambda: verbose_output.write(" Split into %d files\n" % 10))
test_pipeline.transform(task_func = align_sequences,
input = split_fasta_file,
filter = suffix(".fa"),
output = ".aln" # fa -> aln
)\
.posttask(lambda: verbose_output.write(" Sequences aligned\n"))
test_pipeline.transform(task_func = percentage_identity,
input = align_sequences, # find all results from align_sequences
filter = suffix(".aln"), # replace suffix with:
output = [r".pcid", # .pcid suffix for the result
r".pcid_success"] # .pcid_success to indicate job completed
)\
.posttask(lambda: verbose_output.write(" %Identity calculated\n"))
test_pipeline.merge(task_func = combine_results,
input = percentage_identity,
output = [tempdir + "all.combine_results",
tempdir + "all.combine_results_success"])\
.posttask(lambda: verbose_output.write(" Results recombined\n"))
test_pipeline.run(multiprocess = 50, verbose = 0)
if not os.path.exists(tempdir + "all.combine_results"):
raise Exception("Missing %s" % (tempdir + "all.combine_results"))
if __name__ == '__main__':
unittest.main()
|
