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
|
[GENERAL]
root.dir=/var/lib/biomaj
conf.dir=%(root.dir)s/conf
log.dir=%(root.dir)s/log
process.dir=%(root.dir)s/process
cache.dir=%(root.dir)s/cache
lock.dir=%(root.dir)s/lock
#The root directory where all databases are stored.
#If your data is not stored under one directory hirearchy
#you can override this value in the database properties file.
data.dir=%(root.dir)s//data
db.url=mongodb://localhost:27017
db.name=biomaj
use_ldap=0
ldap.host=localhost
ldap.port=389
ldap.dn=nodomain
use_elastic=0
#Comma separated list of elasticsearch nodes host1,host2:port2
elastic_nodes=localhost
elastic_index=biomaj
# Calculate data.dir size stats
data.stats=1
redis.host=localhost
redis.port=6379
redis.db=0
redis.prefix=biomaj
# options to send to downloaders (protocol dependent)
# options.names=option1,option2
# options.option1=value1
# options.option2=value2
#
# Example supported options for ftp/http
# tcp_keepalive: number of seconds for curl keep alive (maps to curl option TCP_KEEPALIVE, TCP_KEEPINTVL and TCP_KEEPIDLE)
# ssl_verifyhost: boolean, check or skips SSL host (maps to curl option SSL_VERIFYHOST)
# ssl_verifypeer: boolean, SSL checks (maps to curl option SSL_VERIFYPEER)
# ssl_server_cert: path to certificate (maps to curl option CAINFO).
# Influxdb configuration (optional)
# User and db must be manually created in influxdb before use
influxdb.host=
influxdb.port=8086
influxdb.user=root
influxdb.password=root
influxdb.db=biomaj
# Needed for download remote service (should be a load balancer to services
#micro.biomaj.proxy=http://127.0.0.1:5000
#micro.biomaj.rabbit_mq=127.0.0.1
#micro.biomaj.rabbit_mq_port=5672
#micro.biomaj.rabbit_mq_user=
#micro.biomaj.rabbit_mq_password=
#micro.biomaj.rabbit_mq_virtualhost=
#micro.biomaj.service.download=1
#micro.biomaj.service.process=1
#micro.biomaj.service.user=1
#micro.biomaj.service.daemon=1
## Optional
# micro.biomaj.proxy.[user,cron,release,daemon,download,process]=http://127.0.0.1:5000
auto_publish=1
########################
# Global properties file
#To override these settings for a specific database go to its
#properties file and uncomment or add the specific line you want
#to override.
#----------------
# Mail Configuration
#---------------
#Uncomment thes lines if you want receive mail when the workflow is finished
mail.smtp.host=
mail.admin=
mail.from=
mail.user=
mail.password=
mail.tls=true
mail.body.tail=2000000
mail.body.attach=9000000
#---------------------
#Proxy authentification
#---------------------
#proxyHost=
#proxyPort=
#proxyUser=
#proxyPassword=
#---------------------
# PROTOCOL
#-------------------
#possible values : ftp, http, rsync, local
port=21
username=anonymous
password=anonymous@nowhere.com
#access user for production directories
production.directory.chmod=775
#Number of thread during the download
bank.num.threads=4
#Number of threads to use for downloading and processing
files.num.threads=4
#Timeout for a download, in seconds (applies for each file, not for the whole downloads)
timeout.download=3600
#to keep more than one release increase this value
keep.old.version=0
#Link copy property
do.link.copy=true
#The historic log file is generated in log/
#define level information for output : DEBUG,INFO,WARN,ERR
historic.logfile.level=DEBUG
# Hint: you can use online service https://regex101.com/ to test your regexps
http.parse.dir.line=<a[\\s]+href=\"([\\S]+)/\".*alt=\"\\[DIR\\]\">.*([\\d]{2}-[\\w\\d]{2,5}-[\\d]{4}\\s[\\d]{2}:[\\d]{2})
http.parse.file.line=<a[\\s]+href=\"([\\S]+)\".*([\\d]{2}-[\\w\\d]{2,5}-[\\d]{4}\\s[\\d]{2}:[\\d]{2})[\\s]+([\\d\\.]+[MKG]{0,1})
http.group.dir.name=1
http.group.dir.date=2
http.group.file.name=1
http.group.file.date=2
http.group.file.size=3
#Needed if data sources are contains in an archive
log.files=true
local.files.excluded=\\.panfs.*
#~40mn
ftp.timeout=2000000
ftp.automatic.reconnect=5
ftp.active.mode=false
# Bank default access
visibility.default=public
# use hard links instead of copy
# use_hardlinks=0
[loggers]
keys = root, biomaj
[handlers]
keys = console
[formatters]
keys = generic
[logger_root]
level = DEBUG
handlers = console
[logger_biomaj]
level = DEBUG
handlers = console
qualname = biomaj
propagate=0
[handler_console]
class = StreamHandler
args = (sys.stderr,)
level = DEBUG
formatter = generic
[formatter_generic]
format = %(asctime)s %(levelname)-5.5s [%(name)s][%(threadName)s] %(message)s
|
