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
|
#!/usr/bin/env python
from __future__ import print_function
"""
test_split_regex_and_collate.py
"""
JOBS_PER_TASK = 5
import os
tempdir = os.path.relpath(os.path.abspath(os.path.splitext(__file__)[0])) + "/"
import sys
import re
# 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__), ".."))
import ruffus
from ruffus import pipeline_run, pipeline_printout, Pipeline, suffix, regex, formatter, originate, follows, merge, mkdir, posttask, subdivide, transform, collate, split
from ruffus.ruffus_exceptions import RethrownJobError
from ruffus.ruffus_utility import RUFFUS_HISTORY_FILE, CHECKSUM_FILE_TIMESTAMPS
from ruffus.combinatorics import *
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# options
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
try:
from StringIO import StringIO
except:
from io import StringIO
import shutil
import unittest
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# imports
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# use simplejson in place of json for python < 2.6
try:
import json
except ImportError:
import simplejson
json = simplejson
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# Main logic
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# Three starting files
#
original_files = [tempdir + "/original_%d.fa" % d for d in range(3)]
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# Tasks
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
@mkdir(tempdir)
@originate(original_files)
def generate_initial_files(out_name):
with open(out_name, 'w') as outfile:
pass
#
# split_fasta_file
#
@posttask(lambda: sys.stderr.write("\tSplit into %d files each\n" % JOBS_PER_TASK))
@subdivide(generate_initial_files,
regex(r".*\/original_(\d+).fa"), # match original files
[tempdir + r"/files.split.\1.success", # flag file for each original file
tempdir + r"/files.split.\1.*.fa"], # glob pattern
r"\1") # index of original file
def split_fasta_file (input_file, outputs, original_index):
#
# 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(JOBS_PER_TASK):
with open(tempdir + "/files.split.%s.%03d.fa" % (original_index, i), "w") as oo:
pass
with open(success_flag, "w") as oo:
pass
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# align_sequences
#
@posttask(lambda: sys.stderr.write("\tSequences 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: sys.stderr.write("\t%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: sys.stderr.write("\tResults recombined\n"))
@collate(percentage_identity, regex(r".*files.split\.(\d+)\.\d+.pcid"),
[tempdir + r"/\1.all.combine_results",
tempdir + r"/\1.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):
import os
try:
shutil.rmtree(tempdir)
except:
pass
os.makedirs(tempdir)
for f in original_files:
with open(f, "w") as p: pass
def cleanup_tmpdir(self):
os.system('rm -f %s %s' % (os.path.join(tempdir, '*'), RUFFUS_HISTORY_FILE))
#___________________________________________________________________________
#
# test product() pipeline_printout and pipeline_run
#___________________________________________________________________________
def test_collate(self):
self.cleanup_tmpdir()
s = StringIO()
pipeline_printout(s, [combine_results], verbose=5, wrap_width = 10000, pipeline= "main")
self.assertTrue(re.search('Job needs update:.*Missing files.*', s.getvalue(), re.DOTALL) is not None)
#print s.getvalue()
pipeline_run([combine_results], verbose=0, pipeline= "main")
def test_newstyle_collate (self):
"""
As above but create pipeline on the fly using object orientated syntax rather than decorators
"""
#
# Create pipeline on the fly, joining up tasks
#
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func = generate_initial_files,
output = original_files)\
.mkdir(tempdir, tempdir+"/test")
test_pipeline.subdivide( task_func = split_fasta_file,
input = generate_initial_files,
filter = regex(r".*\/original_(\d+).fa"), # match original files
output = [tempdir + r"/files.split.\1.success", # flag file for each original file
tempdir + r"/files.split.\1.*.fa"], # glob pattern
extras = [r"\1"])\
.posttask(lambda: sys.stderr.write("\tSplit into %d files each\n" % JOBS_PER_TASK))
test_pipeline.transform(task_func = align_sequences,
input = split_fasta_file,
filter = suffix(".fa"),
output = ".aln") \
.posttask(lambda: sys.stderr.write("\tSequences 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: sys.stderr.write("\t%Identity calculated\n"))
test_pipeline.collate(task_func = combine_results,
input = percentage_identity,
filter = regex(r".*files.split\.(\d+)\.\d+.pcid"),
output = [tempdir + r"/\1.all.combine_results",
tempdir + r"/\1.all.combine_results_success"])\
.posttask(lambda: sys.stderr.write("\tResults recombined\n"))
#
# Cleanup, printout and run
#
self.cleanup_tmpdir()
s = StringIO()
test_pipeline.printout(s, [combine_results], verbose=5, wrap_width = 10000)
self.assertTrue(re.search('Job needs update:.*Missing files.*', s.getvalue(), re.DOTALL) is not None)
test_pipeline.run(verbose=0)
#___________________________________________________________________________
#
# cleanup
#___________________________________________________________________________
def tearDown(self):
shutil.rmtree(tempdir)
#
# Necessary to protect the "entry point" of the program under windows.
# see: http://docs.python.org/library/multiprocessing.html#multiprocessing-programming
#
if __name__ == '__main__':
unittest.main()
|
