def yield_subset_biom_str(biom_str, new_data, new_axis_md, axis):
"""Sequentially yield the components of a reduced biom string"""
if axis not in ['samples', 'observations']:
raise InputError(\
'yield_subset_biom_str axis parameter must be either "samples" or "observations"')
# Still has multiple walks over the file. bad form, but easy right now
yield "{"
keys = ["id","format","format_url","type",\
"generated_by","date","matrix_type",\
"matrix_element_type"]
for key in keys:
yield direct_parse_key(biom_str, key)
yield ","
for entry in [new_data, new_axis_md]:
yield entry
yield ","
if axis == "observations":
yield direct_parse_key(biom_str, "columns")
else:
yield direct_parse_key(biom_str, "rows")
yield "}"
def yield_subset_biom_str(biom_str,new_data,new_axis_md,axis):
"""Sequentially yield the components of a reduced biom string"""
if axis not in ['samples','observations']:
raise InputError(\
'yield_subset_biom_str axis parameter must be either "samples" or "observations"')
# Still has multiple walks over the file. bad form, but easy right now
yield "{"
keys = ["id","format","format_url","type",\
"generated_by","date","matrix_type",\
"matrix_element_type"]
for key in keys:
yield direct_parse_key(biom_str,key)
yield ","
for entry in [new_data,new_axis_md]:
yield entry
yield ","
if axis == "observations":
yield direct_parse_key(biom_str, "columns")
else:
yield direct_parse_key(biom_str, "rows")
yield "}"
def subset_generator():
yield "{"
yield direct_parse_key(table_str, "id")
yield ","
yield direct_parse_key(table_str, "format")
yield ","
yield direct_parse_key(table_str, "format_url")
yield ","
yield direct_parse_key(table_str, "type")
yield ","
yield direct_parse_key(table_str, "generated_by")
yield ","
yield direct_parse_key(table_str, "date")
yield ","
yield direct_parse_key(table_str, "matrix_type")
yield ","
yield direct_parse_key(table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observations":
yield direct_parse_key(table_str, "columns")
else:
yield direct_parse_key(table_str, "rows")
yield "}"
def subset_generator():
yield "{"
yield direct_parse_key(json_table_str, "id")
yield ","
yield direct_parse_key(json_table_str, "format")
yield ","
yield direct_parse_key(json_table_str, "format_url")
yield ","
yield direct_parse_key(json_table_str, "type")
yield ","
yield direct_parse_key(json_table_str, "generated_by")
yield ","
yield direct_parse_key(json_table_str, "date")
yield ","
yield direct_parse_key(json_table_str, "matrix_type")
yield ","
yield direct_parse_key(json_table_str, "matrix_element_type")
yield ","
yield new_data
yield ","
yield new_axis_md
yield ","
if axis == "observation":
yield direct_parse_key(json_table_str, "columns")
else:
yield direct_parse_key(json_table_str, "rows")
yield "}"
parse_command_line_parameters(**script_info)
else:
parser = OptionParser(option_list=options)
opts, args = parser.parse_args()
ids = [l.strip() for l in open(opts.ids_fp)]
biom_str = open(opts.biom_fp).read()
idxs, new_axis_md = get_axis_indices(biom_str, ids, opts.axis)
new_data = direct_slice_data(biom_str, idxs, opts.axis)
output = open(opts.output_fp,'w')
# multiple walks over the file. bad form, but easy right now
# ...should add a yield_and_ignore parser or something.
output.write('{')
output.write(direct_parse_key(biom_str, "id"))
output.write(",")
output.write(direct_parse_key(biom_str, "format"))
output.write(",")
output.write(direct_parse_key(biom_str, "format_url"))
output.write(",")
output.write(direct_parse_key(biom_str, "type"))
output.write(",")
output.write(direct_parse_key(biom_str, "generated_by"))
output.write(",")
output.write(direct_parse_key(biom_str, "date"))
output.write(",")
output.write(direct_parse_key(biom_str, "matrix_type"))
output.write(",")
output.write(direct_parse_key(biom_str, "matrix_element_type"))
output.write(",")
