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
|
#!/usr/bin/env python
from __future__ import print_function
"""
branching.py
test branching dependencies
"""
import os
tempdir = os.path.relpath(os.path.abspath(os.path.splitext(__file__)[0])) + "/"
import sys
# 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]
import ruffus
from ruffus import pipeline_run, pipeline_printout, Pipeline, follows, merge, posttask, split, collate, mkdir, regex, files_re, combine
from ruffus.ruffus_exceptions import RethrownJobError
from ruffus.ruffus_utility import CHECKSUM_FILE_TIMESTAMPS
from ruffus.combinatorics import *
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# imports
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
from collections import defaultdict
import json
# use simplejson in place of json for python < 2.6
#try:
# import json
#except ImportError:
# import simplejson
# json = simplejson
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# Main logic
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
species_list = defaultdict(list)
species_list["mammals"].append("cow" )
species_list["mammals"].append("horse" )
species_list["mammals"].append("sheep" )
species_list["reptiles"].append("snake" )
species_list["reptiles"].append("lizard" )
species_list["reptiles"].append("crocodile" )
species_list["fish" ].append("pufferfish")
def do_write(file_name, what):
with open(file_name, "a") as oo:
oo.write(what)
test_file = tempdir + "task.done"
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
# Tasks
#88888888888888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# task1
#
@follows(mkdir(tempdir, tempdir + "test"))
@posttask(lambda: do_write(test_file, "Task 1 Done\n"))
def prepare_files ():
for grouping in species_list.keys():
for species_name in species_list[grouping]:
filename = tempdir + "%s.%s.animal" % (species_name, grouping)
with open(filename, "w") as oo:
oo.write(species_name + "\n")
#
# task2
#
@files_re(tempdir + '*.animal', r'(.*/)(.*)\.(.*)\.animal', combine(r'\1\2.\3.animal'), r'\1\3.results')
@follows(prepare_files)
@posttask(lambda: do_write(test_file, "Task 2 Done\n"))
def summarise_by_grouping(infiles, outfile):
"""
Summarise by each species group, e.g. mammals, reptiles, fish
"""
with open(tempdir + "jobs.start", "a") as oo:
oo.write('job = %s\n' % json.dumps([infiles, outfile]))
with open(outfile, "w") as oo:
for i in infiles:
with open(i) as ii:
oo.write(ii.read())
with open(tempdir + "jobs.finish", "a") as oo:
oo.write('job = %s\n' % json.dumps([infiles, outfile]))
def check_species_correct():
"""
#cow.mammals.animal
#horse.mammals.animal
#sheep.mammals.animal
# -> mammals.results
#
#snake.reptiles.animal
#lizard.reptiles.animal
#crocodile.reptiles.animal
# -> reptiles.results
#
#pufferfish.fish.animal
# -> fish.results
"""
for grouping in species_list:
with open(tempdir + grouping + ".results") as ii:
assert(ii.read() ==
"".join(s + "\n" for s in sorted(species_list[grouping])))
import unittest, shutil
class Test_ruffus(unittest.TestCase):
def tearDown(self):
try:
shutil.rmtree(tempdir)
except:
pass
def setUp(self):
try:
shutil.rmtree(tempdir)
except:
pass
def test_ruffus (self):
""
pipeline_run(multiprocess = 10, verbose = 0, pipeline= "main")
check_species_correct()
if __name__ == '__main__':
unittest.main()
|
