def test_msa2str(self):
aranger = '{body}{meta}'
# read msa traditionally into an object
msaA = lingpy.MSA(test_data('harry.msa'))
# read msa from dictionary
msaB = lingpy.read.qlc.read_msa(test_data('harry.msa'))
# read msa with IDs
msaC = lingpy.read.qlc.read_msa(test_data('harry_with_ids.msa'),
ids=True,
header=False)
# we adjust the dataset and the seq_id since otherwise we won't have
# similar output
msaC['seq_id'] = 'test'
msaC['dataset'] = 'file'
# when converting these different objects to string with the same body and
# the like, they should be identical, so we check this here
strA = msa2str(msaA, _arange=aranger)
strB = msa2str(msaB, _arange=aranger)
strC = msa2str(msaC, _arange=aranger, wordlist=False)
assert strA == strB == strC
# we next test for converting with the merging attribute
strD = msa2str(msaC, _arange=aranger, wordlist=True, merge=True)
strE = msa2str(msaC, _arange=aranger, wordlist=True, merge=False)
# remove tabstops for checking similar strings
strDst = strD.replace('\t', '')
strEst = strE.replace('\t', '')
# get index until 'COLUMN'
idx = strDst.index('COLUMNID')
assert strD != strE and strDst[:idx] == strEst[:idx]
# add a consensus string to all msa objects
consensusA = lingpy.align.sca.get_consensus(lingpy.align.sca.MSA(msaB),
gaps=True)
consensusB = lingpy.align.sca.get_consensus(lingpy.align.sca.MSA(msaC),
gaps=True)
msaB['consensus'] = consensusA
msaC['consensus'] = consensusB
assert msa2str(msaB) == msa2str(msaC, wordlist=False)
def test_msa2str(self):
aranger = '{body}{meta}'
# read msa traditionally into an object
msa_a = MSA(test_data('harry.msa'))
# read msa from dictionary
msa_b = qlc.read_msa(test_data('harry.msa'))
# read msa with IDs
msa_c = qlc.read_msa(test_data('harry_with_ids.msa'),
ids=True,
header=False)
# we adjust the dataset and the seq_id since otherwise we won't have
# similar output
msa_c['seq_id'] = 'test'
msa_c['dataset'] = 'file'
# when converting these different objects to string with the same body
# and the like, they should be identical, so we check this here
str_a = msa2str(msa_a, _arange=aranger)
str_b = msa2str(msa_b, _arange=aranger)
str_c = msa2str(msa_c, _arange=aranger, wordlist=False)
assert str_a == str_b == str_c
# we next test for converting with the merging attribute
str_d = msa2str(msa_c, _arange=aranger, wordlist=True, merge=True)
str_e = msa2str(msa_c, _arange=aranger, wordlist=True, merge=False)
# remove tabstops for checking similar strings
str_d_st = str_d.replace('\t', '')
str_e_st = str_e.replace('\t', '')
# get index until 'COLUMN'
idx = str_d_st.index('COLUMNID')
assert str_d != str_e and str_d_st[:idx] == str_e_st[:idx]
# add a consensus string to all msa objects
consensus_a = get_consensus(MSA(msa_b), gaps=True)
consensus_b = get_consensus(MSA(msa_c), gaps=True)
msa_b['consensus'] = consensus_a
msa_c['consensus'] = consensus_b
assert msa2str(msa_b) == msa2str(msa_c, wordlist=False)
def test_msa2str(self):
aranger = '{body}{meta}'
# read msa traditionally into an object
msaA = lingpy.MSA(test_data('harry.msa'))
# read msa from dictionary
msaB = lingpy.read.qlc.read_msa(test_data('harry.msa'))
# read msa with IDs
msaC = lingpy.read.qlc.read_msa(
test_data('harry_with_ids.msa'), ids=True, header=False)
# we adjust the dataset and the seq_id since otherwise we won't have
# similar output
msaC['seq_id'] = 'test'
msaC['dataset'] = 'file'
# when converting these different objects to string with the same body and
# the like, they should be identical, so we check this here
strA = msa2str(msaA, _arange=aranger)
strB = msa2str(msaB, _arange=aranger)
strC = msa2str(msaC, _arange=aranger, wordlist=False)
assert strA == strB == strC
# we next test for converting with the merging attribute
strD = msa2str(msaC, _arange=aranger, wordlist=True, merge=True)
strE = msa2str(msaC, _arange=aranger, wordlist=True, merge=False)
# remove tabstops for checking similar strings
strDst = strD.replace('\t', '')
strEst = strE.replace('\t', '')
# get index until 'COLUMN'
idx = strDst.index('COLUMNID')
assert strD != strE and strDst[:idx] == strEst[:idx]
# add a consensus string to all msa objects
consensusA = lingpy.align.sca.get_consensus(lingpy.align.sca.MSA(msaB), gaps=True)
consensusB = lingpy.align.sca.get_consensus(lingpy.align.sca.MSA(msaC), gaps=True)
msaB['consensus'] = consensusA
msaC['consensus'] = consensusB
assert msa2str(msaB) == msa2str(msaC, wordlist=False)
def wl2qlc(header, data, filename='', formatter='concept', **keywords):
"""
Write the basic data of a wordlist to file.
"""
util.setdefaults(keywords,
ignore=['taxa', 'doculects', 'msa'],
fileformat='qlc',
prettify=True)
if keywords['ignore'] == 'all':
keywords['ignore'] = [
'taxa', 'scorer', 'meta', 'distances', 'doculects', 'msa', 'json'
]
formatter = formatter.upper()
if not filename:
filename = rcParams['filename']
# create output string
out = '# Wordlist\n' if keywords['prettify'] else ''
# write meta to file
meta = keywords.get("meta", {})
kvpairs = {}
jsonpairs = {}
msapairs = {}
trees = {}
distances = ''
taxa = ''
scorer = ''
for k, v in meta.items():
# simple key-value-pairs
if isinstance(v, (str, int)) or k == "tree":
kvpairs[k] = v
elif k == 'msa' and k not in keywords['ignore']:
# go a level deeper, checking for keys
for ref in v:
if ref not in msapairs:
msapairs[ref] = {}
for a, b in v[ref].items():
msapairs[ref][a] = b
elif k == 'distances':
distances = matrix2dst(v, meta['taxa'])
elif k in ['taxa', 'doculect', 'taxon', 'doculects']:
# we need to find a better solution here, since it is not nice to
# have taxa written to json again and again
pass
elif k == 'trees' and k not in keywords['ignore']:
trees = ''
for key, value in v.items():
trees += '<tre id="{0}">\n{1}\n</tre>\n'.format(key, value)
elif k == 'scorer' and k not in keywords['ignore']:
for key, value in v.items():
scorer += '<{2} id="{0}">\n{1}</{2}>\n\n'.format(
key, scorer2str(value), k)
else:
# check whether serialization works
try:
json.dumps(v)
jsonpairs[k] = v
except TypeError:
pass
if kvpairs and 'meta' not in keywords['ignore']:
out += '\n# META\n' if keywords['prettify'] else ''
for k, v in sorted(kvpairs.items(), key=lambda x: x[0]):
out += '@{0}:{1}\n'.format(k, v)
if taxa and keywords['taxa']:
out += '\n# TAXA\n<taxa>\n' + taxa + '\n</taxa>\n'
if jsonpairs and 'json' not in keywords['ignore']:
out += "@json: " + json.dumps(jsonpairs) + '\n'
if msapairs and 'msa' not in keywords['ignore']:
for ref in msapairs:
out += "\n# MSA reference: {0}\n".format(ref)
for k, v in msapairs[ref].items():
if 'consensus' in v:
out += '#\n<msa '
out += 'id="{0}" ref="{1}" consensus="{2}">\n'.format(
k, ref, ' '.join(v['consensus']))
else:
out += '#\n<msa id="{0}" ref="{1}">\n'.format(k, ref)
outs = msa2str(v, wordlist=True)
out += outs
out += "</msa>\n"
if distances and 'distances' not in keywords['ignore']:
out += '\n# DISTANCES\n<dst>\n'
out += distances + '</dst>\n'
if trees:
out += '\n# TREES\n' + trees
if scorer and 'scorer' not in keywords['ignore']:
out += '\n# SCORER\n' + scorer
out += '\n# DATA\n' if keywords['prettify'] else ''
out += 'ID\t' + '\t'.join(header) + '\n'
# check for gloss in header to create nice output format
if formatter in header:
idx = header.index(formatter)
formatter = None
sorted_data = sorted(data.keys(), key=lambda x: data[x][idx])
elif len(formatter.split(',')) == 2:
idxA, idxB = formatter.split(',')
idxA = header.index(idxA)
idxB = header.index(idxB)
idx = idxA
formatter = None
sorted_data = sorted(data.keys(),
key=lambda x: (data[x][idxA], data[x][idxB]))
else:
idx = False
formatter = ''
sorted_data = sorted(data.keys())
for key in sorted_data:
# get the line
line = data[key]
# check for formatter
if idx in range(len(line)):
if line[idx] != formatter:
out += '#\n' if keywords['prettify'] else ''
formatter = line[idx]
# add the key
out += str(key)
# add the rest of the values
for value in line:
if type(value) == list:
try:
out += '\t' + ' '.join(value)
except:
out += '\t' + ' '.join([str(v) for v in value])
elif type(value) == int:
out += '\t' + str(value)
elif type(value) == float:
out += '\t{0:.4f}'.format(value)
elif value is None:
out += '\t'
else:
out += '\t{:}'.format(value)
out += '\n'
util.write_text_file(filename + '.' + keywords['fileformat'],
out + keywords.get('stamp', ''),
normalize="NFC")
return
def wl2qlc(
header,
data,
filename='',
formatter='concept',
**keywords):
"""
Write the basic data of a wordlist to file.
"""
util.setdefaults(
keywords,
ignore=['taxa', 'doculects', 'msa'],
fileformat='qlc',
prettify=True)
if keywords['ignore'] == 'all':
keywords['ignore'] = [
'taxa', 'scorer', 'meta', 'distances', 'doculects', 'msa', 'json']
formatter = formatter.upper()
if not filename:
filename = rcParams['filename']
# create output string
out = '# Wordlist\n' if keywords['prettify'] else ''
# write meta to file
meta = keywords.get("meta", {})
kvpairs = {}
jsonpairs = {}
msapairs = {}
trees = {}
distances = ''
taxa = ''
scorer = ''
for k, v in meta.items():
# simple key-value-pairs
if isinstance(v, (text_type, int)) or k == "tree":
kvpairs[k] = v
elif k == 'msa' and k not in keywords['ignore']:
# go a level deeper, checking for keys
for ref in v:
if ref not in msapairs:
msapairs[ref] = {}
for a, b in v[ref].items():
msapairs[ref][a] = b
elif k == 'distances':
distances = matrix2dst(v, meta['taxa'])
elif k in ['taxa', 'doculect', 'taxon', 'doculects']:
# we need to find a better solution here, since it is not nice to
# have taxa written to json again and again
pass
elif k == 'trees' and k not in keywords['ignore']:
trees = ''
for key, value in v.items():
trees += '<tre id="{0}">\n{1}\n</tre>\n'.format(key, value)
elif k == 'scorer' and k not in keywords['ignore']:
for key, value in v.items():
scorer += '<{2} id="{0}">\n{1}</{2}>\n\n'.format(
key, scorer2str(value), k)
else:
# check whether serialization works
try:
json.dumps(v)
jsonpairs[k] = v
except TypeError:
pass
if kvpairs and 'meta' not in keywords['ignore']:
out += '\n# META\n' if keywords['prettify'] else ''
for k, v in sorted(kvpairs.items(), key=lambda x: x[0]):
out += '@{0}:{1}\n'.format(k, v)
if taxa and keywords['taxa']:
out += '\n# TAXA\n<taxa>\n' + taxa + '\n</taxa>\n'
if jsonpairs and 'json' not in keywords['ignore']:
out += "@json: " + json.dumps(jsonpairs) + '\n'
if msapairs and 'msa' not in keywords['ignore']:
for ref in msapairs:
out += "\n# MSA reference: {0}\n".format(ref)
for k, v in msapairs[ref].items():
if 'consensus' in v:
out += '#\n<msa '
out += 'id="{0}" ref="{1}" consensus="{2}">\n'.format(
k, ref, ' '.join(v['consensus']))
else:
out += '#\n<msa id="{0}" ref="{1}">\n'.format(k, ref)
outs = msa2str(v, wordlist=True)
out += outs
out += "</msa>\n"
if distances and 'distances' not in keywords['ignore']:
out += '\n# DISTANCES\n<dst>\n'
out += distances + '</dst>\n'
if trees:
out += '\n# TREES\n' + trees
if scorer and 'scorer' not in keywords['ignore']:
out += '\n# SCORER\n' + scorer
out += '\n# DATA\n' if keywords['prettify'] else ''
out += 'ID\t' + '\t'.join(header) + '\n'
# check for gloss in header to create nice output format
if formatter in header:
idx = header.index(formatter)
formatter = None
sorted_data = sorted(data.keys(), key=lambda x: data[x][idx])
elif len(formatter.split(',')) == 2:
idxA, idxB = formatter.split(',')
idxA = header.index(idxA)
idxB = header.index(idxB)
idx = idxA
formatter = None
sorted_data = sorted(data.keys(), key=lambda x: (
data[x][idxA], data[x][idxB]))
else:
idx = False
formatter = ''
sorted_data = sorted(data.keys())
for key in sorted_data:
# get the line
line = data[key]
# check for formatter
if idx in range(len(line)):
if line[idx] != formatter:
out += '#\n' if keywords['prettify'] else ''
formatter = line[idx]
# add the key
out += text_type(key)
# add the rest of the values
for value in line:
if type(value) == list:
try:
out += '\t' + ' '.join(value)
except:
out += '\t' + ' '.join([text_type(v) for v in value])
elif type(value) == int:
out += '\t' + text_type(value)
elif type(value) == float:
out += '\t{0:.4f}'.format(value)
elif value is None:
out += '\t'
else:
out += '\t{:}'.format(value)
out += '\n'
util.write_text_file(
filename + '.' + keywords['fileformat'],
out + keywords.get('stamp', ''),
normalize="NFC")
return