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
280
281
282
283
284
285
286
287
288
|
# !/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 general NEXUS character matrix reading.
"""
import unittest
import dendropy
from dendropy.utility import error
from dendropy.test.support import dendropytest
from dendropy.test.support import pathmap
from dendropy.test.support import standard_file_test_chars
from dendropy.test.support import compare_and_validate
from dendropy.dataio import nexusreader
from dendropy.utility import messaging
_LOG = messaging.get_logger(__name__)
class NexusCharactersReaderDnaTestCase(
standard_file_test_chars.DnaTestChecker,
dendropytest.ExtendedTestCase):
@classmethod
def setUpClass(cls):
cls.build()
def test_basic_nexus(self):
src_filenames = [
"standard-test-chars-dna.simple.nexus",
"standard-test-chars-dna.basic.nexus",
"standard-test-chars-dna.interleaved.nexus",
"standard-test-chars-dna.matchchar.nexus",
"standard-test-chars-dna.multi.nexus",
]
for src_idx, src_filename in enumerate(src_filenames):
# print(src_idx, src_filename)
src_path = pathmap.char_source_path(src_filename)
self.verify_get_from(
matrix_type=dendropy.DnaCharacterMatrix,
src_filepath=src_path,
schema="nexus",
factory_kwargs={},
check_taxon_annotations=False,
check_matrix_annotations=False,
check_sequence_annotations=False,
check_column_annotations=False,
check_cell_annotations=False)
class NexusCharactersReaderRnaTestCase(
standard_file_test_chars.RnaTestChecker,
dendropytest.ExtendedTestCase):
@classmethod
def setUpClass(cls):
cls.build()
def test_basic_nexus(self):
src_filenames = [
"standard-test-chars-rna.simple.nexus",
"standard-test-chars-rna.basic.nexus",
"standard-test-chars-rna.interleaved.nexus",
"standard-test-chars-rna.matchchar.nexus",
"standard-test-chars-rna.multi.nexus",
]
for src_idx, src_filename in enumerate(src_filenames):
# print(src_idx, src_filename)
src_path = pathmap.char_source_path(src_filename)
self.verify_get_from(
matrix_type=dendropy.RnaCharacterMatrix,
src_filepath=src_path,
schema="nexus",
factory_kwargs={},
check_taxon_annotations=False,
check_matrix_annotations=False,
check_sequence_annotations=False,
check_column_annotations=False,
check_cell_annotations=False)
class NexusCharactersReaderProteinTestCase(
standard_file_test_chars.ProteinTestChecker,
dendropytest.ExtendedTestCase):
@classmethod
def setUpClass(cls):
cls.build()
def test_basic_nexus(self):
src_filenames = [
"standard-test-chars-protein.simple.nexus",
"standard-test-chars-protein.basic.nexus",
"standard-test-chars-protein.interleaved.nexus",
"standard-test-chars-protein.matchchar.nexus",
"standard-test-chars-protein.multi.nexus",
]
for src_idx, src_filename in enumerate(src_filenames):
# print(src_idx, src_filename)
src_path = pathmap.char_source_path(src_filename)
self.verify_get_from(
matrix_type=dendropy.ProteinCharacterMatrix,
src_filepath=src_path,
schema="nexus",
factory_kwargs={},
check_taxon_annotations=False,
check_matrix_annotations=False,
check_sequence_annotations=False,
check_column_annotations=False,
check_cell_annotations=False)
class NexusCharactersContinuousTestCase(
standard_file_test_chars.ContinuousTestChecker,
dendropytest.ExtendedTestCase):
@classmethod
def setUpClass(cls):
cls.build()
def test_basic_nexus(self):
src_filenames = [
"standard-test-chars-continuous.mesquite.nexus",
"standard-test-chars-continuous.mesquite.interleaved.nexus",
]
for src_idx, src_filename in enumerate(src_filenames):
# print(src_idx, src_filename)
src_path = pathmap.char_source_path(src_filename)
self.verify_get_from(
matrix_type=dendropy.ContinuousCharacterMatrix,
src_filepath=src_path,
schema="nexus",
factory_kwargs={},
check_taxon_annotations=False,
check_matrix_annotations=False,
check_sequence_annotations=False,
check_column_annotations=False,
check_cell_annotations=False)
class NexusStandardCharacters01234TestCase(
standard_file_test_chars.Standard01234TestChecker,
dendropytest.ExtendedTestCase):
@classmethod
def setUpClass(cls):
cls.build()
def test_basic_nexus(self):
src_filenames = [
"standard-test-chars-generic.simple.nexus",
"standard-test-chars-generic.basic.nexus",
"standard-test-chars-generic.dotted.nexus",
"standard-test-chars-generic.interleaved.nexus",
]
for src_idx, src_filename in enumerate(src_filenames):
# print(src_idx, src_filename)
src_path = pathmap.char_source_path(src_filename)
self.verify_get_from(
matrix_type=dendropy.StandardCharacterMatrix,
src_filepath=src_path,
schema="nexus",
factory_kwargs={},
check_taxon_annotations=False,
check_matrix_annotations=False,
check_sequence_annotations=False,
check_column_annotations=False,
check_cell_annotations=False)
class NexusTooManyTaxaTest(
dendropytest.ExtendedTestCase):
def testTooManyTaxaNonInterleaved(self):
data_str = """\
#NEXUS
BEGIN TAXA;
DIMENSIONS NTAX=2;
TAXLABELS AAA BBB ;
END;
BEGIN CHARACTERS;
DIMENSIONS NCHAR=8;
FORMAT DATATYPE=DNA GAP=- MISSING=? MATCHCHAR=.;
MATRIX
AAA ACGTACGT
BBB ACGTACGT
CCC ACGTACGT
;
END;
"""
self.assertRaises(nexusreader.NexusReader.TooManyTaxaError,
dendropy.DnaCharacterMatrix.get_from_string,
data_str,
'nexus')
class NexusCharsSubsetsTest(
compare_and_validate.Comparator,
dendropytest.ExtendedTestCase):
def verify_subsets(self, src_filename, expected_sets):
"""
``src_filename`` -- name of file containing full data and charsets
statement
``expected_sets`` -- dictionary with keys = label of charset, and values
= name of file with subset of characters correspond
to the charset.
"""
src_data = dendropy.DnaCharacterMatrix.get_from_path(
pathmap.char_source_path(src_filename),
'nexus')
state_alphabet = src_data.default_state_alphabet
self.assertEqual(len(src_data.character_subsets), len(expected_sets))
for label, expected_data_file in expected_sets.items():
_LOG.debug(label)
self.assertTrue(label in src_data.character_subsets)
result_subset = src_data.export_character_subset(label)
expected_subset = dendropy.DnaCharacterMatrix.get_from_path(
pathmap.char_source_path(expected_data_file),
'nexus')
# confirm subset is correct
self.compare_distinct_char_matrix(
result_subset,
expected_subset,
taxon_namespace_scoped=False,
)
# mutate new and confirm that old remains unchanged
e1_symbols = src_data[0].symbols_as_string()
r1 = result_subset[0]
dummy_state = state_alphabet["A"]
for idx in range(len(r1)):
r1[idx].value = dummy_state
self.assertEqual(e1_symbols, src_data[0].symbols_as_string())
# mutate old and confirm that new remains unchanged
r2_symbols = result_subset[1].symbols_as_string()
e2 = src_data[1]
dummy_state = state_alphabet["A"]
for idx in range(len(e2)):
e2[idx].value = dummy_state
self.assertEqual(r2_symbols, result_subset[1].symbols_as_string())
def testNonInterleaved(self):
"""
Charsets here go through all forms of position specification.
"""
expected_sets = {
"coding" : "primates.chars.subsets-coding.nexus",
"noncoding" : "primates.chars.subsets-noncoding.nexus",
"1stpos" : "primates.chars.subsets-1stpos.nexus",
"2ndpos" : "primates.chars.subsets-2ndpos.nexus",
"3rdpos" : "primates.chars.subsets-3rdpos.nexus",
}
self.verify_subsets('primates.chars.subsets-all.nexus', expected_sets)
def testInterleaved(self):
"""
A bug in DendroPy resulted in the block immediately following an
interleaved character matrix DATA or CHARACTERS block being skipped.
This tests for it by ensuring that the ASSUMPTIONS block following an
interleaved CHARACTERS block is parsed. A better test would approach
the issue more directly, by checking to see if block parsing left the
stream reader in the correct position.
"""
expected_sets = {
"c1" : "interleaved-charsets-c1.nex",
"c2" : "interleaved-charsets-c2.nex",
"c3" : "interleaved-charsets-c3.nex",
}
self.verify_subsets('interleaved-charsets-all.nex', expected_sets)
if __name__ == "__main__":
unittest.main()
|
