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
|
# Copyright 2009-2010 by Peter Cock. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Additional unit tests for Bio.SeqIO.convert(...) function."""
import os
import unittest
from StringIO import StringIO
from Bio.SeqRecord import SeqRecord
from Bio import SeqIO
from Bio.SeqIO._index import _FormatToIndexedDict
from Bio.Alphabet import generic_protein, generic_nucleotide, generic_dna
from seq_tests_common import compare_record
class IndexDictTests(unittest.TestCase):
"""Cunning unit test where methods are added at run time."""
def simple_check(self, filename, format, alphabet):
if format in SeqIO._BinaryFormats:
mode = "rb"
else :
mode = "r"
id_list = [rec.id for rec in \
SeqIO.parse(open(filename, mode), format, alphabet)]
rec_dict = SeqIO.index(filename, format, alphabet)
self.assertEqual(set(id_list), set(rec_dict.keys()))
#This is redundant, I just want to make sure len works:
self.assertEqual(len(id_list), len(rec_dict))
#Make sure boolean evaluation works
self.assertEqual(bool(id_list), bool(rec_dict))
for key in id_list:
self.assert_(key in rec_dict)
self.assertEqual(key, rec_dict[key].id)
self.assertEqual(key, rec_dict.get(key).id)
#Check non-existant keys,
try:
rec = rec_dict[chr(0)]
raise ValueError("Accessing a non-existent key should fail")
except KeyError:
pass
self.assertEqual(rec_dict.get(chr(0)), None)
self.assertEqual(rec_dict.get(chr(0), chr(1)), chr(1))
#Now check iteritems...
for key, rec in rec_dict.iteritems():
self.assert_(key in id_list)
self.assert_(isinstance(rec, SeqRecord))
self.assertEqual(rec.id, key)
#Now check non-defined methods...
self.assertRaises(NotImplementedError, rec_dict.values)
self.assertRaises(NotImplementedError, rec_dict.popitem)
self.assertRaises(NotImplementedError, rec_dict.pop, chr(0))
self.assertRaises(NotImplementedError, rec_dict.pop, chr(0), chr(1))
self.assertRaises(NotImplementedError, rec_dict.clear)
self.assertRaises(NotImplementedError, rec_dict.__setitem__, "X", None)
self.assertRaises(NotImplementedError, rec_dict.copy)
self.assertRaises(NotImplementedError, rec_dict.fromkeys, [])
#Done
def get_raw_check(self, filename, format, alphabet):
if format in SeqIO._BinaryFormats:
#This means SFF at the moment, which does not get
#implement the get_raw method
return
handle = open(filename, "rU")
raw_file = handle.read()
handle.close()
#Also checking the key_function here
id_list = [rec.id.lower() for rec in \
SeqIO.parse(filename, format, alphabet)]
rec_dict = SeqIO.index(filename, format, alphabet,
key_function = lambda x : x.lower())
self.assertEqual(set(id_list), set(rec_dict.keys()))
self.assertEqual(len(id_list), len(rec_dict))
for key in id_list:
self.assert_(key in rec_dict)
self.assertEqual(key, rec_dict[key].id.lower())
self.assertEqual(key, rec_dict.get(key).id.lower())
raw = rec_dict.get_raw(key)
self.assert_(raw.strip())
self.assert_(raw in raw_file)
if format in ["ig"]:
#These have a header structure and can't be parsed
#individually (at least, not right now).
continue
rec1 = rec_dict[key]
rec2 = SeqIO.read(StringIO(raw), format, alphabet)
self.assertEqual(True, compare_record(rec1, rec2))
#Done
tests = [
("Ace/contig1.ace", "ace", generic_dna),
("Ace/consed_sample.ace", "ace", None),
("Ace/seq.cap.ace", "ace", generic_dna),
("Quality/wrapping_original_sanger.fastq", "fastq", None),
("Quality/example.fastq", "fastq", None),
("Quality/example.fastq", "fastq-sanger", generic_dna),
("Quality/tricky.fastq", "fastq", generic_nucleotide),
("Quality/sanger_faked.fastq", "fastq-sanger", generic_dna),
("Quality/solexa_faked.fastq", "fastq-solexa", generic_dna),
("Quality/illumina_faked.fastq", "fastq-illumina", generic_dna),
("EMBL/U87107.embl", "embl", None),
("EMBL/TRBG361.embl", "embl", None),
("EMBL/A04195.imgt", "embl", None), #Not a proper EMBL file, an IMGT file
("GenBank/NC_000932.faa", "fasta", generic_protein),
("GenBank/NC_005816.faa", "fasta", generic_protein),
("GenBank/NC_005816.tsv", "tab", generic_protein),
("GenBank/NC_005816.ffn", "fasta", generic_dna),
("GenBank/NC_005816.fna", "fasta", generic_dna),
("GenBank/NC_005816.gb", "gb", None),
("GenBank/cor6_6.gb", "genbank", None),
("IntelliGenetics/vpu_nucaligned.txt", "ig", generic_nucleotide),
("IntelliGenetics/TAT_mase_nuc.txt", "ig", None),
("IntelliGenetics/VIF_mase-pro.txt", "ig", generic_protein),
("Phd/phd1", "phd", generic_dna),
("Phd/phd2", "phd", None),
("Phd/phd_solexa", "phd", generic_dna),
("Phd/phd_454", "phd", generic_dna),
("NBRF/B_nuc.pir", "pir", generic_nucleotide),
("NBRF/Cw_prot.pir", "pir", generic_protein),
("NBRF/clustalw.pir", "pir", None),
("SwissProt/sp001", "swiss", None),
("SwissProt/sp010", "swiss", None),
("SwissProt/sp016", "swiss", None),
("Roche/E3MFGYR02_random_10_reads.sff", "sff", generic_dna),
("Roche/E3MFGYR02_random_10_reads.sff", "sff-trim", generic_dna),
("Roche/E3MFGYR02_index_at_start.sff", "sff", generic_dna),
("Roche/E3MFGYR02_index_in_middle.sff", "sff", generic_dna),
("Roche/E3MFGYR02_alt_index_at_start.sff", "sff", generic_dna),
("Roche/E3MFGYR02_alt_index_in_middle.sff", "sff", generic_dna),
("Roche/E3MFGYR02_alt_index_at_end.sff", "sff", generic_dna),
("Roche/E3MFGYR02_no_manifest.sff", "sff", generic_dna),
("Roche/greek.sff", "sff", generic_nucleotide),
("Roche/greek.sff", "sff-trim", generic_nucleotide),
("Roche/paired.sff", "sff", None),
("Roche/paired.sff", "sff-trim", None),
]
for filename, format, alphabet in tests:
assert format in _FormatToIndexedDict
def funct(fn,fmt,alpha):
f = lambda x : x.simple_check(fn, fmt, alpha)
f.__doc__ = "Index %s file %s" % (fmt, fn)
return f
setattr(IndexDictTests, "test_%s_%s" \
% (filename.replace("/","_").replace(".","_"), format),
funct(filename, format, alphabet))
del funct
if format in SeqIO._BinaryFormats:
continue
def funct(fn,fmt,alpha):
f = lambda x : x.get_raw_check(fn, fmt, alpha)
f.__doc__ = "Index %s file %s get_raw" % (fmt, fn)
return f
setattr(IndexDictTests, "test_%s_%s_get_raw" \
% (filename.replace("/","_").replace(".","_"), format),
funct(filename, format, alphabet))
del funct
if __name__ == "__main__":
runner = unittest.TextTestRunner(verbosity = 2)
unittest.main(testRunner=runner)
|
