Merge pull request #198 from wltrimbl/master

Some new tests, consistent use of argparse

Author: wilke

examples/python/annotation_table.py

@@ -45,20 +45,15 @@
     jsonstructure = async_rest_api(URI, auth=key)
     jsondata = jsonstructure["data"]
 # unpack and display the data table
-    cols = jsondata["columns"]
 #    rows = [x["id"] for x in jsondata["rows"]]
 
-    data = jsondata["data"]
+    data = jsondata # ["data"]
 
     if DEBUG:
         print(jsonstructure)
-        print("COLS", cols)
         print("DATA", data)
     h = data
 
-    for j in range(0, len(cols)):
-        sys.stdout.write(cols[j] +"\t")
-    sys.stdout.write("\n")
     for i in range(0, len(data)):
         sys.stdout.write("\t".join([str(s) for s in h[i]]))
         sys.stdout.write("\n")

examples/python/list_all_mg.py

@@ -18,6 +18,7 @@ def printlist(js):
                           public, item["created_on"],
                           item["name"]]) + "\n").encode("utf-8"))
 
+CALL = "/metagenome"
 CALL = "/search"
 
 key = get_auth_token()

scripts/jsonviewer.py

@@ -2,7 +2,7 @@
 
 import sys
 import json
-from optparse import OptionParser
+from argparse import ArgumentParser
 
 prehelp = """
 NAME
@@ -95,17 +95,17 @@ def to_string(x, dump=False, keys=False, expand=False, summary=False):
         return str(x)
 
 def main(args):
-    OptionParser.format_description = lambda self, formatter: self.description
-    OptionParser.format_epilog = lambda self, formatter: self.epilog
-    parser = OptionParser(usage='', description=prehelp, epilog=posthelp)
-    parser.add_option("", "--info", dest="info", action="store_true", default=False, help="give format and depth of JSON structure")
-    parser.add_option("", "--json", dest="json", action="store_true", default=False, help="pretty print of JSON structure")
-    parser.add_option("", "--keys", dest="keys", action="store_true", default=False, help="list of keys if hash, number of elements if array")
-    parser.add_option("", "--value", dest="value", default=None, help="value for a given key name or array index, use dot (.) to indicate multiple levels")
-    parser.add_option("", "--find", dest="find", default=None, help="value(s) for a given key name at any depth")
+    ArgumentParser.format_description = lambda self, formatter: self.description
+    ArgumentParser.format_epilog = lambda self, formatter: self.epilog
+    parser = ArgumentParser(usage='', description=prehelp, epilog=posthelp)
+    parser.add_argument("--info", dest="info", action="store_true", default=False, help="give format and depth of JSON structure")
+    parser.add_argument("--json", dest="json", action="store_true", default=False, help="pretty print of JSON structure")
+    parser.add_argument("--keys", dest="keys", action="store_true", default=False, help="list of keys if hash, number of elements if array")
+    parser.add_argument("--value", dest="value", default=None, help="value for a given key name or array index, use dot (.) to indicate multiple levels")
+    parser.add_argument("--find", dest="find", default=None, help="value(s) for a given key name at any depth")
 
     # get inputs
-    (opts, args) = parser.parse_args()
+    opts = parser.parse_args()
     try:
         jdata = json.load(sys.stdin)
     except:
@@ -150,4 +150,4 @@ def main(args):
     return 0
 
 if __name__ == "__main__":
-    sys.exit( main(sys.argv) )
+    sys.exit(main(sys.argv))

scripts/mg-abundant-functions.py

@@ -2,7 +2,7 @@
 
 import sys
 from operator import itemgetter
-from optparse import OptionParser
+from argparse import ArgumentParser
 from mglib import get_auth_token, obj_from_url, VERSION, API_URL, AUTH_LIST, async_rest_api, safe_print, urlencode
 
 prehelp = """
@@ -34,26 +34,26 @@
 """
 
 def main(args):
-    OptionParser.format_description = lambda self, formatter: self.description
-    OptionParser.format_epilog = lambda self, formatter: self.epilog
-    parser = OptionParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
-    parser.add_option("", "--id", dest="id", default=None, help="KBase Metagenome ID")
-    parser.add_option("", "--url", dest="url", default=API_URL, help="communities API url")
-    parser.add_option("", "--user", dest="user", default=None, help="OAuth username")
-    parser.add_option("", "--passwd", dest="passwd", default=None, help="OAuth password")
-    parser.add_option("", "--token", dest="token", default=None, help="OAuth token")
-    parser.add_option("", "--level", dest="level", default='function', help="functional level to retrieve abundances for, default is function")
-    parser.add_option("", "--source", dest="source", default='Subsystems', help="datasource to filter results by, default is Subsystems")
-    parser.add_option("", "--filter_name", dest="filter_name", default=None, help="function name to filter by")
-    parser.add_option("", "--filter_level", dest="filter_level", default=None, help="function level to filter by")
-    parser.add_option("", "--top", dest="top", type="int", default=10, help="display only the top N taxa, default is 10")
-    parser.add_option("", "--evalue", dest="evalue", type="int", default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_option("", "--identity", dest="identity", type="int", default=60, help="percent value for minimum % identity cutoff, default is 60")
-    parser.add_option("", "--length", dest="length", type="int", default=15, help="value for minimum alignment length cutoff, default is 15")
-    parser.add_option("", "--version", type="int", dest="version", default=1, help="M5NR annotation version to use, default is 1")
+    ArgumentParser.format_description = lambda self, formatter: self.description
+    ArgumentParser.format_epilog = lambda self, formatter: self.epilog
+    parser = ArgumentParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
+    parser.add_argument("--id", dest="id", default=None, help="KBase Metagenome ID")
+    parser.add_argument("--url", dest="url", default=API_URL, help="communities API url")
+    parser.add_argument("--user", dest="user", default=None, help="OAuth username")
+    parser.add_argument("--passwd", dest="passwd", default=None, help="OAuth password")
+    parser.add_argument("--token", dest="token", default=None, help="OAuth token")
+    parser.add_argument("--level", dest="level", default='function', help="functional level to retrieve abundances for, default is function")
+    parser.add_argument("--source", dest="source", default='Subsystems', help="datasource to filter results by, default is Subsystems")
+    parser.add_argument("--filter_name", dest="filter_name", default=None, help="function name to filter by")
+    parser.add_argument("--filter_level", dest="filter_level", default=None, help="function level to filter by")
+    parser.add_argument("--top", dest="top", type=int, default=10, help="display only the top N taxa, default is 10")
+    parser.add_argument("--evalue", dest="evalue", type=int, default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
+    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--length", dest="length", type=int, default=15, help="value for minimum alignment length cutoff, default is 15")
+    parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
 
     # get inputs
-    (opts, args) = parser.parse_args()
+    opts = parser.parse_args()
     opts.top = int(opts.top)
     if not opts.id:
         sys.stderr.write("ERROR: id required\n")
@@ -93,7 +93,7 @@ def main(args):
         url = opts.url+'/m5nr/ontology?'+urlencode(params, True)
         data = obj_from_url(url)
         level = 'level4' if opts.level == 'function' else opts.level
-        sub_ann = set( map(lambda x: x[level], data['data']) )
+        sub_ann = set(map(lambda x: x[level], data['data']))
 
     # sort data
     if biom["matrix_type"] == "sparse":
@@ -122,4 +122,4 @@ def main(args):
 
 
 if __name__ == "__main__":
-    sys.exit( main(sys.argv) )
+    sys.exit(main(sys.argv))

scripts/mg-abundant-taxa.py

@@ -2,7 +2,7 @@
 
 import sys
 from operator import itemgetter
-from optparse import OptionParser
+from argparse import ArgumentParser
 from mglib import get_auth_token, obj_from_url, async_rest_api, AUTH_LIST, sparse_to_dense, safe_print, API_URL, VERSION, urlencode
 
 prehelp = """
@@ -34,26 +34,26 @@
 """
 
 def main(args):
-    OptionParser.format_description = lambda self, formatter: self.description
-    OptionParser.format_epilog = lambda self, formatter: self.epilog
-    parser = OptionParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
-    parser.add_option("", "--id", dest="id", default=None, help="KBase Metagenome ID")
-    parser.add_option("", "--url", dest="url", default=API_URL, help="communities API url")
-    parser.add_option("", "--user", dest="user", default=None, help="OAuth username")
-    parser.add_option("", "--passwd", dest="passwd", default=None, help="OAuth password")
-    parser.add_option("", "--token", dest="token", default=None, help="OAuth token")
-    parser.add_option("", "--level", dest="level", default='species', help="taxon level to retrieve abundances for, default is species")
-    parser.add_option("", "--source", dest="source", default='SEED', help="datasource to filter results by, default is SEED")
-    parser.add_option("", "--filter_name", dest="filter_name", default=None, help="taxon name to filter by")
-    parser.add_option("", "--filter_level", dest="filter_level", default=None, help="taxon level to filter by")
-    parser.add_option("", "--top", dest="top", type="int", default=10, help="display only the top N taxa, default is 10")
-    parser.add_option("", "--evalue", dest="evalue", type="int", default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_option("", "--identity", dest="identity", type="int", default=60, help="percent value for minimum % identity cutoff, default is 60")
-    parser.add_option("", "--length", dest="length", type="int", default=15, help="value for minimum alignment length cutoff, default is 15")
-    parser.add_option("", "--version", type="int", dest="version", default=1, help="M5NR annotation version to use, default is 1")
+    ArgumentParser.format_description = lambda self, formatter: self.description
+    ArgumentParser.format_epilog = lambda self, formatter: self.epilog
+    parser = ArgumentParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
+    parser.add_argument("--id", dest="id", default=None, help="KBase Metagenome ID")
+    parser.add_argument("--url", dest="url", default=API_URL, help="communities API url")
+    parser.add_argument("--user", dest="user", default=None, help="OAuth username")
+    parser.add_argument("--passwd", dest="passwd", default=None, help="OAuth password")
+    parser.add_argument("--token", dest="token", default=None, help="OAuth token")
+    parser.add_argument("--level", dest="level", default='species', help="taxon level to retrieve abundances for, default is species")
+    parser.add_argument("--source", dest="source", default='SEED', help="datasource to filter results by, default is SEED")
+    parser.add_argument("--filter_name", dest="filter_name", default=None, help="taxon name to filter by")
+    parser.add_argument("--filter_level", dest="filter_level", default=None, help="taxon level to filter by")
+    parser.add_argument("--top", dest="top", type=int, default=10, help="display only the top N taxa, default is 10")
+    parser.add_argument("--evalue", dest="evalue", type=int, default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
+    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--length", dest="length", type=int, default=15, help="value for minimum alignment length cutoff, default is 15")
+    parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
 
     # get inputs
-    (opts, args) = parser.parse_args()
+    opts = parser.parse_args()
     opts.top = int(opts.top)
     if not opts.id:
         sys.stderr.write("ERROR: id required\n")
@@ -66,16 +66,16 @@ def main(args):
     token = get_auth_token(opts)
 
     # build url
-    params = [ ('id', opts.id),
-               ('group_level', opts.level),
-               ('source', opts.source),
-               ('evalue', opts.evalue),
-               ('identity', opts.identity),
-               ('length', opts.length),
-               ('version', opts.version),
-               ('result_type', 'abundance'),
-               ('asynchronous', '1'),
-               ('hide_metadata', '1') ]
+    params = [('id', opts.id),
+              ('group_level', opts.level),
+              ('source', opts.source),
+              ('evalue', opts.evalue),
+              ('identity', opts.identity),
+              ('length', opts.length),
+              ('version', opts.version),
+              ('result_type', 'abundance'),
+              ('asynchronous', '1'),
+              ('hide_metadata', '1')]
     url = opts.url+'/matrix/organism?'+urlencode(params, True)
 
     # retrieve data
@@ -85,20 +85,20 @@ def main(args):
     # get sub annotations
     sub_ann = set()
     if opts.filter_name and opts.filter_level:
-        params = [ ('filter', opts.filter_name),
-                   ('filter_level', opts.filter_level),
-                   ('min_level', opts.level),
-                   ('version', opts.version) ]
+        params = [('filter', opts.filter_name),
+                  ('filter_level', opts.filter_level),
+                  ('min_level', opts.level),
+                  ('version', opts.version)]
         url = opts.url+'/m5nr/taxonomy?'+urlencode(params, True)
         data = obj_from_url(url)
-        sub_ann = set( map(lambda x: x[opts.level], data['data']) )
+        sub_ann = set(map(lambda x: x[opts.level], data['data']))
     if biom['matrix_type'] == "dense":
         data = biom['data']
     else:
         data = sparse_to_dense(biom['data'], len(biom['rows']), len(biom['cols']))
     rows = [biom['rows'][i]['id'] for i in range(len(biom['rows']))]
     datalist = [biom['data'][i][0] for i in range(len(biom['rows']))]
-    data2 = zip( rows, datalist)
+    data2 = zip(rows, datalist)
     # sort data
     for d in sorted(data2, key=itemgetter(1), reverse=True):
         name = d[0]
@@ -116,4 +116,4 @@ def main(args):
 
 
 if __name__ == "__main__":
-    sys.exit( main(sys.argv) )
+    sys.exit(main(sys.argv))

scripts/mg-biom-merge.py

@@ -3,7 +3,7 @@
 import os
 import sys
 import json
-from optparse import OptionParser
+from argparse import ArgumentParser
 from mglib import merge_biom, AUTH_LIST, VERSION, safe_print
 
 prehelp = """
@@ -38,13 +38,13 @@
 """
 
 def main(args):
-    OptionParser.format_description = lambda self, formatter: self.description
-    OptionParser.format_epilog = lambda self, formatter: self.epilog
-    parser = OptionParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
-    parser.add_option("", "--retain_dup_ids", dest="retain_dups", action="store_true", default=False, help="append input number to duplicate input ID's rather than discarding duplicates, default is false")
+    ArgumentParser.format_description = lambda self, formatter: self.description
+    ArgumentParser.format_epilog = lambda self, formatter: self.epilog
+    parser = ArgumentParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
+    parser.add_argument("--retain_dup_ids", dest="retain_dups", action="store_true", default=False, help="append input number to duplicate input ID's rather than discarding duplicates, default is false")
 
     # get inputs
-    (opts, args) = parser.parse_args()
+    opts = parser.parse_args()
     if len(args) < 2:
         sys.stderr.write("ERROR: must have at least 2 file inputs\n")
         return 1
@@ -83,4 +83,4 @@ def main(args):
     return 0
 
 if __name__ == "__main__":
-    sys.exit( main(sys.argv) )
+    sys.exit(main(sys.argv))

scripts/mg-biom-view.py

@@ -3,7 +3,7 @@
 import os
 import sys
 import json
-from optparse import OptionParser
+from argparse import ArgumentParser
 from mglib import biom_to_matrix, AUTH_LIST, VERSION
 
 prehelp = """
@@ -38,19 +38,19 @@
 """
 
 def main(args):
-    OptionParser.format_description = lambda self, formatter: self.description
-    OptionParser.format_epilog = lambda self, formatter: self.epilog
-    parser = OptionParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
-    parser.add_option("-i", "--input", dest="input", default='-', help="input: filename or stdin (-), default is stdin")
-    parser.add_option("-o", "--output", dest="output", default='-', help="input: filename or stdout (-), default is stdout")
-    parser.add_option("", "--row_start", dest="row_start", type="int", default=None, help="row position to start table with, default is first")
-    parser.add_option("", "--row_end", dest="row_end", type="int", default=None, help="row position to end table with, default is last")
-    parser.add_option("", "--col_start", dest="col_start", type="int", default=None, help="column position to start table with, default is first")
-    parser.add_option("", "--col_end", dest="col_end", type="int", default=None, help="column position to end table with, default is last")
-    parser.add_option("", "--stats", dest="stats", action="store_true", default=False, help="include significance stats in output, default is off")
+    ArgumentParser.format_description = lambda self, formatter: self.description
+    ArgumentParser.format_epilog = lambda self, formatter: self.epilog
+    parser = ArgumentParser(usage='', description=prehelp%VERSION, epilog=posthelp%AUTH_LIST)
+    parser.add_argument("-i", "--input", dest="input", default='-', help="input: filename or stdin (-), default is stdin")
+    parser.add_argument("-o", "--output", dest="output", default='-', help="input: filename or stdout (-), default is stdout")
+    parser.add_argument("--row_start", dest="row_start", type=int, default=None, help="row position to start table with, default is first")
+    parser.add_argument("--row_end", dest="row_end", type=int, default=None, help="row position to end table with, default is last")
+    parser.add_argument("--col_start", dest="col_start", type=int, default=None, help="column position to start table with, default is first")
+    parser.add_argument("--col_end", dest="col_end", type=int, default=None, help="column position to end table with, default is last")
+    parser.add_argument("--stats", dest="stats", action="store_true", default=False, help="include significance stats in output, default is off")
 
     # get inputs
-    (opts, args) = parser.parse_args()
+    opts = parser.parse_args()
     if (opts.input != '-') and (not os.path.isfile(opts.input)):
         sys.stderr.write("ERROR: input data missing\n")
         return 1
@@ -81,9 +81,9 @@ def main(args):
     # output data
     try:
         sub_rows = rows[row_start:row_end]
-        out_hdl.write( "\t%s\n" %"\t".join(cols[col_start:col_end]) )
+        out_hdl.write("\t%s\n" %"\t".join(cols[col_start:col_end]))
         for i, d in enumerate(data[row_start:row_end]):
-            out_hdl.write( "%s\t%s\n" %(sub_rows[i], "\t".join(map(str, d[col_start:col_end]))) )
+            out_hdl.write("%s\t%s\n" %(sub_rows[i], "\t".join(map(str, d[col_start:col_end]))))
         out_hdl.close()
     except:
         sys.stderr.write("ERROR: unable to sub-select BIOM, inputted positions are out of bounds\n")
@@ -92,4 +92,4 @@ def main(args):
 
 
 if __name__ == "__main__":
-    sys.exit( main(sys.argv) )
+    sys.exit(main(sys.argv))