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
|
# Usage: python make_upload_chip_parameter.py
#
# Purpose: make a part of parameter_for_buildCmatrix.txt given the uploaded files in UPLOAD_DIR.
# Each unique uploaded file will be assigned an ID.
# The assigned ID starts with C0000, followed by 9 digits.
# The following cases are handled: (i) the same bed file uploaded several times. the latest submission will be used.
#
# TBD: append to PARAMETER_FOR_BUILDCMATRIX
# Created 20 July 2017, slcu, hui
import os, sys, glob
from datetime import datetime
PARAMETER_FOR_BUILDCMATRIX = '../Data/upload/parameter_for_buildCmatrix.txt' # [change]
UPLOAD_DIR = '../Data/upload/chipseq'
INCLUDE_STAMP = 'BRAIN_HAS_INCLUDED_ME'
def good_file(fname):
f = open(fname)
lines = f.readlines()
f.close()
for line in lines:
line = line.strip()
if line.startswith('#') and 'STATUS:' in line:
if 'SUCC' in line or 'UNKNOWN' in line:
return True
if 'FAIL' in line:
return False
return False
def already_included(fname):
''' If fname is already procesed, then its head line is marked with BRAIN_HAS_INCLUDED_ME'''
f = open(fname)
lines = f.readlines()
n = len(lines)
f.close()
for line in lines[0:min(n, 5)]: # the first five lines should include INCLUDE_STAMP if this file is already included.
line = line.strip()
if line.startswith('#') and INCLUDE_STAMP in line:
return True
return False
def same_content(f1, f2):
''' Test if two file, f1 and f2, have the same content. '''
if os.path.exists(f1) and not os.path.exists(f2):
return False
if not os.path.exists(f1) and os.path.exists(f2):
return False
if not os.path.exists(f1) and not os.path.exists(f2):
return False
if os.path.exists(f1) and os.path.exists(f2):
a = open(f1)
b = open(f2)
s1 = ''
for line in a:
line = line.strip()
if not line.startswith('#'): # don't include lines starting with '#'
s1 += line
s2 = ''
for line in b:
line = line.strip()
if not line.startswith('#'):
s2 += line
a.close()
b.close()
if s1 == s2:
return True
else:
return False
def repeat(fname, d):
''' Are there other files having the same content as fname? Return '' if no; otherwise return the conflicting file name. '''
for k in d:
if same_content(fname, d[k]['LOCATION']):
return k
return ''
def update_dict(d, k, fname):
d[k] = make_chip_info_dict(fname)
# def update_it(upload_dir, upload_dict):
# id_lst = sorted(upload_dict.keys())
# if id_lst != []:
# last_id = id_lst[-1]
# last_id_number = int(last_id[5:])
# else:
# last_id_number = 0
# for fname in sorted(glob.glob(os.path.join(UPLOAD_DIR, '20*.*'))): # all uploaded BED files start with time stamp 20.....
# if good_file(fname) and not already_included(fname):
# #print(upload_dict)
# k = repeat(fname, upload_dict)
# if k == '':
# k = '%d' % (last_id_number + 1)
# k = 'C0000' + k.zfill(9)
# upload_dict[k] = make_chip_info_dict(fname)
# else:
# update_dict(upload_dict, k, fname)
# mark_it_as_included(fname)
def make_chip_info_dict(fname):
''' Return a dictionary given a user submitted file. '''
d = {'PROTEIN_ID':'', 'PROTEIN_NAME':'', 'DATA_NAME':'', 'DATA_FORMAT':'narrowPeak', 'DESCRIPTION':'user upload', 'LOCATION':'', 'NOTE':''}
f = open(fname)
lines = f.readlines()
f.close()
for line in lines:
line = line.strip()
if line.startswith('#'):
s = line[(line.rfind('#')+1):]
s = s.strip()
lst = s.split(':')
k = lst[0].strip()
v = line[(line.find(':')+1):]
d[k] = v
d['DATA_NAME'] = os.path.basename(fname)
d['LOCATION'] = os.path.abspath(fname)
d['NOTE'] = 'update:%s' % datetime.now().strftime('%Y%m%d')
return d
def mark_it_as_included(fname):
''' Prepend a head line including INCLUDE_STAMP'''
f = open(fname)
s = f.read()
f.close()
f = open(fname, 'w')
curr_time = datetime.now().strftime('%Y-%m-%d %H:%M')
f.write('# %s %s\n' % (INCLUDE_STAMP, curr_time) + s)
f.close()
def make_string(d):
s = ''
for k in sorted(d.keys()):
s += '@%s\n' % k
s += 'PROTEIN_ID:%s\n' % d[k]['PROTEIN_ID']
s += 'PROTEIN_NAME:%s\n' % d[k]['PROTEIN_NAME']
s += 'DATA_NAME:%s\n' % d[k]['DATA_NAME']
s += 'DATA_FORMAT:narrowPeak\n'
s += 'DESCRIPTION:%s\n' % d[k]['DESCRIPTION']
s += 'LOCATION:%s\n' % d[k]['LOCATION']
s += 'NOTE:%s\n\n' % d[k]['NOTE']
return s
def md(fname):
''' Return a dictionary containing the paramter information. '''
d = {}
if not os.path.exists(fname):
return {}
else:
f = open(fname)
lines = f.readlines()
f.close()
for line in lines:
line = line.strip()
if line != '' and line.startswith('@'):
k = line[1:]
d[k] = {}
elif line != '':
lst = line.split(':')
k2 = lst[0].strip()
v = line[(line.find(':')+1):]
d[k][k2] = v
return d
def is_empty(fname):
''' Return True if fname has no content. '''
if os.path.exists(fname):
f = open(fname)
s = f.read()
f.close()
return s.strip() == ''
return False
def get_largest_upload_chip_id(fname):
lst = []
f = open(fname)
for line in f:
line = line.strip()
if line.startswith('@C0000'):
lst.append(int(line[2:]))
f.close()
if lst != []:
return max(lst)
else:
return 0
def make_upload_dict(param_fname, included_path):
d = {}
i = get_largest_upload_chip_id(param_fname) + 1 # staring id
for fn in sorted(glob.glob(os.path.join(UPLOAD_DIR, '20*.*')), reverse=False): # newer files are considered first
k = 'C0000' + ('%d' % (i)).zfill(9)
if good_file(fn) and not already_included(fn) and repeat(fn, d) == '':
d[k] = make_chip_info_dict(fn)
i += 1
if good_file(fn):
mark_it_as_included(fn)
cmd = 'mv %s %s' % (fn, included_path)
os.system(cmd)
return d
def append_to_file(fname, s):
f = open(fname, 'a')
f.write('\n' + s + '\n')
f.close()
def make_directory(my_dir):
if not os.path.exists(my_dir):
os.makedirs(my_dir)
def make_copy(fname):
if os.path.exists(fname):
curr_time = datetime.now().strftime('%Y%m%d_%H%M%S')
new_fname = fname + '.copy.%s' % (curr_time)
f = open(fname)
s = f.read()
f.close()
f = open(new_fname, 'w')
f.write(s)
f.close()
## main
included_path = os.path.join(UPLOAD_DIR, 'included')
make_directory(included_path)
upload_dict = make_upload_dict(PARAMETER_FOR_BUILDCMATRIX, included_path)
s = make_string(upload_dict)
if s != '':
# before changing PARAMETER_FOR_BUILDCMATRIX, make a copy of it
make_copy(PARAMETER_FOR_BUILDCMATRIX)
append_to_file(PARAMETER_FOR_BUILDCMATRIX, s)
|
