def test_read_error_on_malformed(self):
outfile = os.path.join(self.tmpdir, 'read-error.txt')
with open(outfile, 'w') as handle:
handle.write('Aasasd\n')
t = TreeMaker()
with self.assertRaises(ValueError):
t.read(outfile)
def test_read_error_on_malformed(self):
outfile = os.path.join(self.tmpdir, 'read-error.txt')
with open(outfile, 'w') as handle:
handle.write('Aasasd\n')
t = TreeMaker()
with self.assertRaises(ValueError):
t.read(outfile)
def test_read_skips_empty_lines(self):
outfile = os.path.join(self.tmpdir, 'read-empty.txt')
with open(outfile, 'w') as handle:
handle.write('A a\n')
handle.write('\n')
handle.write('\n')
handle.write('B b\n')
t = TreeMaker()
t.read(outfile)
assert str(t.tree) == '(A,B)'
def test_read_with_tabs(self):
outfile = os.path.join(self.tmpdir, 'read.txt')
with open(outfile, 'w') as handle:
handle.write('A\ta\n')
handle.write('AB1\ta, b\n')
handle.write('AB2\ta, b\n')
handle.write('C\tc\n')
t = TreeMaker()
t.read(outfile)
assert str(self.t.tree) == str(t.tree)
def test_read_with_tabs(self):
outfile = os.path.join(self.tmpdir, 'read.txt')
with open(outfile, 'w') as handle:
handle.write('A\ta\n')
handle.write('AB1\ta, b\n')
handle.write('AB2\ta, b\n')
handle.write('C\tc\n')
t = TreeMaker()
t.read(outfile)
assert str(self.t.tree) == str(t.tree)
def test_read_skips_empty_lines(self):
outfile = os.path.join(self.tmpdir, 'read-empty.txt')
with open(outfile, 'w') as handle:
handle.write('A a\n')
handle.write('\n')
handle.write('\n')
handle.write('B b\n')
t = TreeMaker()
t.read(outfile)
assert str(t.tree) == '(A,B)'
def test_add_from(self):
taxa = [
('A1', 'family a, subgroup 1'),
('A2', 'family a, subgroup 2'),
('B1a', 'family b, subgroup 1'),
('B1b', 'family b, subgroup 1'),
('B2', 'family b, subgroup 2'),
]
t = TreeMaker()
t.add_from(taxa)
assert str(t.tree) == "((A1,A2),((B1a,B1b),B2))"
def test_add_from(self):
taxa = [
('A1', 'family a, subgroup 1'),
('A2', 'family a, subgroup 2'),
('B1a', 'family b, subgroup 1'),
('B1b', 'family b, subgroup 1'),
('B2', 'family b, subgroup 2'),
]
t = TreeMaker()
t.add_from(taxa)
assert str(t.tree) == "((A1,A2),((B1a,B1b),B2))"
def test_add(self):
t = TreeMaker()
t.add('A', 'a')
t.add('AB1', 'a, b')
t.add('AB2', 'a, b')
t.add('C', 'c')
assert str(t.tree) == "((A,(AB1,AB2)),C)"
def test_error_on_bad_taxon(self):
t = TreeMaker()
with self.assertRaises(ValueError):
t.add('A (x)', 'a')
with self.assertRaises(ValueError):
t.add('A)', 'a')
with self.assertRaises(ValueError):
t.add('A(', 'a')
def test_add_2(self):
t = TreeMaker()
t.add('A1', 'family a, subgroup 1')
t.add('A2', 'family a, subgroup 2')
t.add('B1a', 'family b, subgroup 1')
t.add('B1b', 'family b, subgroup 1')
t.add('B2', 'family b, subgroup 2')
assert str(t.tree) == "((A1,A2),((B1a,B1b),B2))"
def make_tree(*taxa):
# We create a dict to lookup Glottolog languoids by name, ISO- or Glottocode.
langs = {}
for lang in Glottolog().languoids():
if lang.iso:
langs[lang.iso] = lang
langs[lang.name] = lang
langs[lang.id] = lang
t = TreeMaker()
for taxon in taxa:
if taxon not in langs:
print('unknown taxon: {0}'.format(taxon))
continue
t.add(taxon, ', '.join(l[1] for l in langs[taxon].lineage))
return t
def setUpClass(cls):
cls.t = TreeMaker()
cls.t.add('A', 'a')
cls.t.add('AB1', 'a, b')
cls.t.add('AB2', 'a, b')
cls.t.add('C', 'c')
cls.tmpdir = mkdtemp()
def test_add_from_exception(self):
taxa = [
('A1', 'family a, subgroup 1'),
('A2family a, subgroup 2'), # oops.
('B1a', 'family b, subgroup 1'),
]
with self.assertRaises(ValueError):
t = TreeMaker().add_from(taxa)
def test_add(self):
t = TreeMaker()
t.add('A', 'a')
t.add('AB1', 'a, b')
t.add('AB2', 'a, b')
t.add('C', 'c')
assert str(t.tree) == "((A,(AB1,AB2)),C)"
def test_error_on_bad_taxon(self):
t = TreeMaker()
with self.assertRaises(ValueError):
t.add('A (x)', 'a')
with self.assertRaises(ValueError):
t.add('A)', 'a')
with self.assertRaises(ValueError):
t.add('A(', 'a')
def test_add_2(self):
t = TreeMaker()
t.add('A1', 'family a, subgroup 1')
t.add('A2', 'family a, subgroup 2')
t.add('B1a', 'family b, subgroup 1')
t.add('B1b', 'family b, subgroup 1')
t.add('B2', 'family b, subgroup 2')
assert str(t.tree) == "((A1,A2),((B1a,B1b),B2))"
#!/usr/bin/env python
# coding=utf-8
import os
try:
from treemaker import TreeMaker
except ImportError:
raise ImportError("Please install treemaker")
from tools import get_table, safe_name
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description="Constructs a tree from the glottolog data file")
parser.add_argument("glottfile", help="Glottolog data file")
parser.add_argument("treefile", help="Treefile to save as")
args = parser.parse_args()
if not os.path.isfile(args.glottfile):
raise IOError("File %s not found" % args.glottfile)
t = TreeMaker()
t.add_from((safe_name(o.Language), o.Classification)
for o in get_table(args.glottfile))
t.write_to_file(args.treefile)
def test_error_on_duplicate(self):
t = TreeMaker()
t.add('A', 'a')
with self.assertRaises(ValueError):
t.add('A', 'a')
def test_error_on_duplicate(self):
t = TreeMaker()
t.add('A', 'a')
with self.assertRaises(ValueError):
t.add('A', 'a')
def test_parse_classification(self):
t = TreeMaker()
assert t.parse_classification("a, b, c") == ['a', 'b', 'c']
assert t.parse_classification("family a, subgroup 1") == [
'family a', 'subgroup 1'
]
def test_parse_classification(self):
t = TreeMaker()
assert t.parse_classification("a, b, c") == ['a', 'b', 'c']
assert t.parse_classification("family a, subgroup 1") == [
'family a', 'subgroup 1'
]