Mercurial > repos > prog > lcmsmatching

annotate list-chrom-cols.py @ 1:45e985cd8e9e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
author prog
date Tue, 31 Jan 2017 05:27:24 -0500
parents
children b8f70d8216b3
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
1 #!/usr/bin/env python
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
2
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
3 import argparse
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
4 import subprocess
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
5 import re
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
6 import urllib2
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
7 import json
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
8 import csv
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
9
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
10 def get_chrom_cols(dbtype, dburl, dbtoken = None, dbfields = None):
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
11
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
12 cols = []
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
13
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
14 if dbtype == 'peakforest':
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
15 url = dburl + ( '' if dburl[-1] == '/' else '/' ) + 'metadata/lc/list-code-columns'
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
16 if dbtoken is not None:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
17 url += '?token=' + dbtoken
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
18 result = urllib2.urlopen(url).read()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
19 v = json.JSONDecoder().decode(result)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
20 i = 0
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
21 for colid, coldesc in v.iteritems():
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
22 cols.append( (coldesc['name'], colid, i == 0) )
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
23 ++i
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
24
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
25 elif dbtype == 'inhouse':
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
26 # Get field for chromatographic column name
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
27 col_field = 'chromcol'
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
28 if dbfields is not None:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
29 fields = dict(u.split("=") for u in dbfields.split(","))
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
30 if 'chromcol' in fields:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
31 col_field = fields['chromcol']
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
32
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
33 # Get all column names from file
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
34 with open(dburl if isinstance(dburl, str) else dburl.get_file_name(), 'rb') as dbfile:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
35 reader = csv.reader(dbfile, delimiter = "\t", quotechar='"')
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
36 header = reader.next()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
37 if col_field in header:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
38 i = header.index(col_field)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
39 allcols = []
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
40 for row in reader:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
41 col = row[i]
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
42 if col not in allcols:
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
43 allcols.append(col)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
44 for i, c in enumerate(allcols):
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
45 cols.append( (c, c, i == 0) )
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
46
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
47 return cols
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
48
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
49 ########
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
50 # MAIN #
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
51 ########
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
52
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
53 if __name__ == '__main__':
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
54
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
55 # Parse command line arguments
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
56 parser = argparse.ArgumentParser(description='Script for getting chromatographic columns of an RMSDB database for Galaxy tool lcmsmatching.')
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
57 parser.add_argument('-d', help = 'Database type', dest = 'dbtype', required = True)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
58 parser.add_argument('-u', help = 'Database URL', dest = 'dburl', required = True)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
59 parser.add_argument('-t', help = 'Database token', dest = 'dbtoken', required = False)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
60 parser.add_argument('-f', help = 'Database fields', dest = 'dbfields', required = False)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
61 args = parser.parse_args()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
62 args_dict = vars(args)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
63
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
64 print(get_chrom_cols(**args_dict))