1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
|
#! /usr/bin/env python
##############################################################################
## DendroPy Phylogenetic Computing Library.
##
## Copyright 2010-2015 Jeet Sukumaran and Mark T. Holder.
## All rights reserved.
##
## See "LICENSE.rst" for terms and conditions of usage.
##
## If you use this work or any portion thereof in published work,
## please cite it as:
##
## Sukumaran, J. and M. T. Holder. 2010. DendroPy: a Python library
## for phylogenetic computing. Bioinformatics 26: 1569-1571.
##
##############################################################################
"""
Tests for NEWICK taxon handling.
"""
import sys
import os
import unittest
import dendropy
from dendropy.utility import error
from dendropy.test.support import dendropytest
from dendropy.dataio import nexusreader
from dendropy.dataio import nexusprocessing
class TaxonSymbolMappingTest(unittest.TestCase):
def test_standard_lookup_and_create(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
for idx, label in enumerate(labels):
self.assertEqual(len(tns), idx)
t1 = tsm.require_taxon_for_symbol(label)
self.assertEqual(len(tns), idx+1)
self.assertEqual(t1.label, label)
t2 = tsm.require_taxon_for_symbol(label)
self.assertEqual(len(tns), idx+1)
self.assertIs(t1, t2)
self.assertEqual(t2.label, label)
t3 = tsm.require_taxon_for_symbol(str(idx+1))
self.assertEqual(len(tns), idx+1)
self.assertIs(t1, t3)
self.assertEqual(t3.label, label)
assert label.upper() != label
t4 = tsm.require_taxon_for_symbol(label.upper())
self.assertEqual(len(tns), idx+1)
self.assertIs(t1, t4)
self.assertEqual(t4.label, label)
def test_no_number_lookup_and_create(self):
# looking up a number symbol should result in new taxon creation
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns,
enable_lookup_by_taxon_number=False)
for idx, label in enumerate(labels):
self.assertEqual(len(tns), idx)
t1 = tsm.require_taxon_for_symbol(label)
self.assertEqual(len(tns), idx+1)
self.assertEqual(t1.label, label)
t2 = tsm.require_taxon_for_symbol(label)
self.assertEqual(len(tns), idx+1)
self.assertIs(t1, t2)
self.assertEqual(t2.label, label)
t3 = tsm.lookup_taxon_symbol(str(idx+1), create_taxon_if_not_found=False)
self.assertIs(t3, None)
self.assertEqual(len(tns), idx+1)
def test_no_number_lookup_and_create2(self):
# looking up a number symbol should result in new taxon creation
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns,
enable_lookup_by_taxon_number=False)
taxa = []
for label_idx, label in enumerate(labels):
t = dendropy.Taxon(label)
tsm.add_taxon(t)
taxa.append(t)
self.assertEqual(len(tns), len(labels))
for label_idx, label in enumerate(labels):
t1 = tsm.require_taxon_for_symbol(label_idx+1)
self.assertNotIn(t1, taxa)
self.assertEqual(t1.label, str(label_idx+1))
self.assertEqual(len(tns), len(labels)+label_idx+1)
def test_new_taxon(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
for label_idx, label in enumerate(labels):
t = tsm.new_taxon(label)
self.assertEqual(len(tns), label_idx+1)
self.assertEqual(t.label, label)
self.assertIs(tsm.require_taxon_for_symbol(label), t)
self.assertEqual(len(tns), label_idx+1)
self.assertIs(tsm.require_taxon_for_symbol(str(label_idx+1)), t)
self.assertEqual(len(tns), label_idx+1)
self.assertEqual(len(tns), len(labels))
def test_add_taxon(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
for label_idx, label in enumerate(labels):
t = dendropy.Taxon(label)
tsm.add_taxon(t)
self.assertEqual(len(tns), label_idx+1)
self.assertEqual(t.label, label)
self.assertIs(tsm.require_taxon_for_symbol(label), t)
self.assertEqual(len(tns), label_idx+1)
self.assertIs(tsm.require_taxon_for_symbol(str(label_idx+1)), t)
self.assertEqual(len(tns), label_idx+1)
self.assertEqual(len(tns), len(labels))
def test_simple_token_lookup(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
translate = {}
t_labels = {}
for label_idx, label in enumerate(labels):
t = dendropy.Taxon(label)
t_labels[t] = t.label
tsm.add_taxon(t)
token = label_idx + 1
translate[token] = t
tsm.add_translate_token(token, t)
self.assertEqual(len(tns), len(labels))
for token in translate:
t1 = translate[token]
t2 = tsm.require_taxon_for_symbol(token)
self.assertIs(t1, t2)
self.assertEqual(t2.label, t_labels[t1])
self.assertEqual(len(tns), len(labels))
def test_tricky_token_lookup(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
translate = {}
t_labels = {}
for label_idx, label in enumerate(labels):
t = dendropy.Taxon(label)
t_labels[t] = t.label
tsm.add_taxon(t)
token = str(len(labels) - label_idx)
translate[token] = t
tsm.add_translate_token(token, t)
self.assertEqual(len(tns), len(labels))
for token in translate:
t1 = translate[token]
t2 = tsm.require_taxon_for_symbol(token)
self.assertIs(t1, t2)
self.assertEqual(t2.label, t_labels[t1])
self.assertEqual(len(tns), len(labels))
def test_mixed_token_lookup(self):
labels = ["t{}".format(i) for i in range(1, 101)]
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
translate = {}
t_labels = {}
labels_t = {}
for label_idx, label in enumerate(labels):
t = dendropy.Taxon(label)
t_labels[t] = t.label
labels_t[t.label] = t
tsm.add_taxon(t)
if label_idx % 2 == 0:
token = str(label_idx+1)
translate[token] = t
tsm.add_translate_token(token, t)
self.assertEqual(len(tns), len(labels))
for label_idx, label in enumerate(labels):
token = label_idx + 1
t1 = tsm.require_taxon_for_symbol(token)
self.assertEqual(len(tns), len(labels))
self.assertEqual(t1.label, label)
self.assertIs(t1, labels_t[label])
if token in translate:
self.assertIs(t1, translate[token])
self.assertEqual(len(tns), len(labels))
def test_taxon_namespace_locking(self):
tns = dendropy.TaxonNamespace()
tsm = nexusprocessing.NexusTaxonSymbolMapper(taxon_namespace=tns)
self.assertFalse(tns.is_mutable)
del tsm
self.assertTrue(tns.is_mutable)
class NexusTaxaCaseInsensitivityTest(unittest.TestCase):
def setUp(self):
self.data_str = """\
#NEXUS
BEGIN TAXA;
DIMENSIONS NTAX=5;
TAXLABELS AAA BBB CCC DDD EEE;
END;
BEGIN CHARACTERS;
DIMENSIONS NCHAR=8;
FORMAT DATATYPE=DNA GAP=- MISSING=? MATCHCHAR=. INTERLEAVE;
MATRIX
AAA ACGT
BBB ACGT
CCC ACGT
DDD ACGT
EEE ACGT
aaa ACGT
bbb ACGT
ccc ACGT
ddd ACGT
eee ACGT
;
END;
"""
def testCaseInsensitiveChars(self):
d = dendropy.DnaCharacterMatrix.get_from_string(self.data_str, 'nexus', case_sensitive_taxon_labels=False)
expected = ["AAA", "BBB", "CCC", "DDD", "EEE"]
observed = [t.label.upper() for t in d.taxon_namespace]
for i, x in enumerate(expected):
self.assertTrue(x in observed)
for i, x in enumerate(observed):
self.assertTrue(x in expected)
self.assertEqual(len(d.taxon_namespace), 5)
def testCaseSensitiveChars(self):
#d = dendropy.DnaCharacterMatrix.get_from_string(self.data_str, 'nexus', case_sensitive_taxon_labels=False)
self.assertRaises(error.DataParseError,
dendropy.DnaCharacterMatrix.get_from_string,
self.data_str,
'nexus',
case_sensitive_taxon_labels=True)
def testDefaultCaseSensitivityChars(self):
d = dendropy.DnaCharacterMatrix.get_from_string(self.data_str, 'nexus')
expected = ["AAA", "BBB", "CCC", "DDD", "EEE"]
observed = [t.label.upper() for t in d.taxon_namespace]
for i, x in enumerate(expected):
self.assertTrue(x in observed)
for i, x in enumerate(observed):
self.assertTrue(x in expected)
self.assertEqual(len(d.taxon_namespace), 5)
class NexusTooManyTaxaTest(
dendropytest.ExtendedTestCase):
def testTooManyTaxaNonInterleaved(self):
data_str = """\
#NEXUS
BEGIN TAXA;
DIMENSIONS NTAX=2;
TAXLABELS AAA BBB CCC DDD EEE;
END;
"""
self.assertRaises(nexusreader.NexusReader.TooManyTaxaError,
dendropy.DnaCharacterMatrix.get_from_string,
data_str,
'nexus')
if __name__ == "__main__":
unittest.main()
|
