edlib 0.0.6 → 0.0.7
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/ext/edlib/edlibext.c +49 -63
- data/ext/edlib/edlibext.h +0 -27
- data/ext/edlib/extconf.rb +2 -0
- data/lib/edlib/version.rb +3 -1
- data/lib/edlib.rb +65 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 72ca7381d858e17e8ba5e2641d072cb4f391410b97ef9138504efa6851020373
|
4
|
+
data.tar.gz: 180e15f4a09149af7031536817a635be580d55afd25896341cb44cf54a9902be
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5f53003d5e12d9d55b40201f435a278b4a99d6e01569cf0f5e96a263822058257d3dd1b65c7c0f48d39a92177c271131d7752bf982c68893316e5dccbdeefc9f
|
7
|
+
data.tar.gz: 27e1ec9237c5f86fe8775100dbda7e2b9851071a9043cace94b927a65e372afa0b7cbbca741d51266b1f2a0493917eeaf1b4b60da92600def529b2e4ac724edb
|
data/ext/edlib/edlibext.c
CHANGED
@@ -1,11 +1,30 @@
|
|
1
1
|
#include "ruby.h"
|
2
2
|
#include "edlibext.h"
|
3
3
|
|
4
|
+
#define ALIGNER_GET_(name) \
|
5
|
+
static VALUE \
|
6
|
+
aligner_get_##name(VALUE self) \
|
7
|
+
{ \
|
8
|
+
EdlibAlignConfig *config = aligner_get_config(self); \
|
9
|
+
return get_##name(config); \
|
10
|
+
}
|
11
|
+
|
12
|
+
#define ALIGNER_SET_(name) \
|
13
|
+
static VALUE \
|
14
|
+
aligner_set_##name(VALUE self, VALUE value) \
|
15
|
+
{ \
|
16
|
+
EdlibAlignConfig *config = aligner_get_config(self); \
|
17
|
+
return set_##name(config, value); \
|
18
|
+
}
|
19
|
+
|
4
20
|
VALUE mEdlib;
|
5
21
|
VALUE cAligner;
|
6
22
|
|
7
23
|
// Aligner class
|
8
24
|
|
25
|
+
static size_t aligner_config_memsize(const void *ptr);
|
26
|
+
static void aligner_config_free(void *ptr);
|
27
|
+
|
9
28
|
static const rb_data_type_t config_type = {
|
10
29
|
.wrap_struct_name = "RbAlignConfig",
|
11
30
|
.function = {
|
@@ -73,12 +92,7 @@ get_k(EdlibAlignConfig *config)
|
|
73
92
|
return INT2NUM(config->k);
|
74
93
|
}
|
75
94
|
|
76
|
-
|
77
|
-
aligner_get_k(VALUE self)
|
78
|
-
{
|
79
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
80
|
-
return get_k(config);
|
81
|
-
}
|
95
|
+
ALIGNER_GET_(k)
|
82
96
|
|
83
97
|
static VALUE
|
84
98
|
set_k(EdlibAlignConfig *config, VALUE k)
|
@@ -87,35 +101,25 @@ set_k(EdlibAlignConfig *config, VALUE k)
|
|
87
101
|
return k;
|
88
102
|
}
|
89
103
|
|
90
|
-
|
91
|
-
aligner_set_k(VALUE self, VALUE k)
|
92
|
-
{
|
93
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
94
|
-
return set_k(config, k);
|
95
|
-
}
|
104
|
+
ALIGNER_SET_(k)
|
96
105
|
|
97
106
|
static VALUE
|
98
107
|
get_mode(EdlibAlignConfig *config)
|
99
108
|
{
|
100
109
|
switch (config->mode)
|
101
110
|
{
|
102
|
-
case
|
111
|
+
case EDLIB_MODE_NW:
|
103
112
|
return rb_str_new2("NW");
|
104
|
-
case
|
113
|
+
case EDLIB_MODE_SHW:
|
105
114
|
return rb_str_new2("SHW");
|
106
|
-
case
|
115
|
+
case EDLIB_MODE_HW:
|
107
116
|
return rb_str_new2("HW");
|
108
117
|
default:
|
109
118
|
return Qnil;
|
110
119
|
}
|
111
120
|
}
|
112
121
|
|
113
|
-
|
114
|
-
aligner_get_mode(VALUE self)
|
115
|
-
{
|
116
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
117
|
-
return get_mode(config);
|
118
|
-
}
|
122
|
+
ALIGNER_GET_(mode)
|
119
123
|
|
120
124
|
static VALUE
|
121
125
|
set_mode(EdlibAlignConfig *config, VALUE mode)
|
@@ -127,18 +131,19 @@ set_mode(EdlibAlignConfig *config, VALUE mode)
|
|
127
131
|
switch (TYPE(mode))
|
128
132
|
{
|
129
133
|
case T_STRING:;
|
130
|
-
|
131
|
-
|
134
|
+
VALUE mode_str = rb_funcall(mode, rb_intern("upcase"), 0);
|
135
|
+
char *mode_s = RSTRING_PTR(mode_str);
|
136
|
+
if (strcmp(mode_s, "NW") == 0)
|
132
137
|
{
|
133
|
-
config->mode =
|
138
|
+
config->mode = EDLIB_MODE_NW;
|
134
139
|
}
|
135
|
-
else if (strcmp(
|
140
|
+
else if (strcmp(mode_s, "SHW") == 0)
|
136
141
|
{
|
137
|
-
config->mode =
|
142
|
+
config->mode = EDLIB_MODE_SHW;
|
138
143
|
}
|
139
|
-
else if (strcmp(
|
144
|
+
else if (strcmp(mode_s, "HW") == 0)
|
140
145
|
{
|
141
|
-
config->mode =
|
146
|
+
config->mode = EDLIB_MODE_HW;
|
142
147
|
}
|
143
148
|
else
|
144
149
|
{
|
@@ -159,35 +164,25 @@ set_mode(EdlibAlignConfig *config, VALUE mode)
|
|
159
164
|
return mode;
|
160
165
|
}
|
161
166
|
|
162
|
-
|
163
|
-
aligner_set_mode(VALUE self, VALUE mode)
|
164
|
-
{
|
165
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
166
|
-
return set_mode(config, mode);
|
167
|
-
}
|
167
|
+
ALIGNER_SET_(mode)
|
168
168
|
|
169
169
|
static VALUE
|
170
170
|
get_task(EdlibAlignConfig *config)
|
171
171
|
{
|
172
172
|
switch (config->task)
|
173
173
|
{
|
174
|
-
case
|
174
|
+
case EDLIB_TASK_DISTANCE:
|
175
175
|
return rb_str_new2("DISTANCE");
|
176
|
-
case
|
176
|
+
case EDLIB_TASK_LOC:
|
177
177
|
return rb_str_new2("LOC");
|
178
|
-
case
|
178
|
+
case EDLIB_TASK_PATH:
|
179
179
|
return rb_str_new2("PATH");
|
180
180
|
default:
|
181
181
|
return Qnil;
|
182
182
|
}
|
183
183
|
}
|
184
184
|
|
185
|
-
|
186
|
-
aligner_get_task(VALUE self)
|
187
|
-
{
|
188
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
189
|
-
return get_task(config);
|
190
|
-
}
|
185
|
+
ALIGNER_GET_(task)
|
191
186
|
|
192
187
|
static VALUE
|
193
188
|
set_task(EdlibAlignConfig *config, VALUE task)
|
@@ -199,18 +194,19 @@ set_task(EdlibAlignConfig *config, VALUE task)
|
|
199
194
|
switch (TYPE(task))
|
200
195
|
{
|
201
196
|
case T_STRING:;
|
202
|
-
rb_funcall(task, rb_intern("upcase
|
203
|
-
|
197
|
+
VALUE task_str = rb_funcall(task, rb_intern("upcase"), 0);
|
198
|
+
char *task_s = RSTRING_PTR(task_str);
|
199
|
+
if (strcmp(task_s, "DISTANCE") == 0)
|
204
200
|
{
|
205
|
-
config->task =
|
201
|
+
config->task = EDLIB_TASK_DISTANCE;
|
206
202
|
}
|
207
|
-
else if (strcmp(
|
203
|
+
else if (strcmp(task_s, "LOC") == 0)
|
208
204
|
{
|
209
|
-
config->task =
|
205
|
+
config->task = EDLIB_TASK_LOC;
|
210
206
|
}
|
211
|
-
else if (strcmp(
|
207
|
+
else if (strcmp(task_s, "PATH") == 0)
|
212
208
|
{
|
213
|
-
config->task =
|
209
|
+
config->task = EDLIB_TASK_PATH;
|
214
210
|
}
|
215
211
|
else
|
216
212
|
{
|
@@ -231,12 +227,7 @@ set_task(EdlibAlignConfig *config, VALUE task)
|
|
231
227
|
return task;
|
232
228
|
}
|
233
229
|
|
234
|
-
|
235
|
-
aligner_set_task(VALUE self, VALUE task)
|
236
|
-
{
|
237
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
238
|
-
return set_task(config, task);
|
239
|
-
}
|
230
|
+
ALIGNER_SET_(task)
|
240
231
|
|
241
232
|
static VALUE
|
242
233
|
get_additional_equalities(EdlibAlignConfig *config)
|
@@ -255,12 +246,7 @@ get_additional_equalities(EdlibAlignConfig *config)
|
|
255
246
|
return equalities;
|
256
247
|
}
|
257
248
|
|
258
|
-
|
259
|
-
aligner_get_additional_equalities(VALUE self)
|
260
|
-
{
|
261
|
-
EdlibAlignConfig *config = aligner_get_config(self);
|
262
|
-
return get_additional_equalities(config);
|
263
|
-
}
|
249
|
+
ALIGNER_GET_(additional_equalities)
|
264
250
|
|
265
251
|
static VALUE
|
266
252
|
set_additional_equalities(EdlibAlignConfig *config, EdlibEqualityPair *eqpairs, VALUE equalities)
|
@@ -455,5 +441,5 @@ void Init_edlibext(void)
|
|
455
441
|
rb_define_method(cAligner, "additional_equalities", aligner_get_additional_equalities, 0);
|
456
442
|
rb_define_method(cAligner, "additional_equalities=", aligner_set_additional_equalities, 1);
|
457
443
|
rb_define_method(cAligner, "config", aligner_config_hash, 0);
|
458
|
-
rb_define_method(cAligner, "
|
444
|
+
rb_define_method(cAligner, "align_raw", aligner_align, 2);
|
459
445
|
}
|
data/ext/edlib/edlibext.h
CHANGED
@@ -9,34 +9,7 @@ typedef struct
|
|
9
9
|
EdlibEqualityPair *equalityPairs;
|
10
10
|
} RbAlignConfig;
|
11
11
|
|
12
|
-
static VALUE aligner_config_allocate(VALUE klass);
|
13
|
-
static size_t aligner_config_memsize(const void *ptr);
|
14
|
-
static void aligner_config_free(void *ptr);
|
15
|
-
|
16
12
|
static EdlibAlignConfig *aligner_get_config(VALUE self);
|
17
13
|
static EdlibEqualityPair *aligner_get_equalityPairs(VALUE self);
|
18
14
|
|
19
|
-
static VALUE get_k(EdlibAlignConfig *config);
|
20
|
-
static VALUE aligner_get_k(VALUE self);
|
21
|
-
static VALUE set_k(EdlibAlignConfig *config, VALUE k);
|
22
|
-
static VALUE aligner_set_k(VALUE self, VALUE k);
|
23
|
-
static VALUE get_mode(EdlibAlignConfig *config);
|
24
|
-
static VALUE aligner_get_mode(VALUE self);
|
25
|
-
static VALUE set_mode(EdlibAlignConfig *config, VALUE mode);
|
26
|
-
static VALUE aligner_set_mode(VALUE self, VALUE mode);
|
27
|
-
static VALUE get_task(EdlibAlignConfig *config);
|
28
|
-
static VALUE aligner_get_task(VALUE self);
|
29
|
-
static VALUE set_task(EdlibAlignConfig *config, VALUE task);
|
30
|
-
static VALUE aligner_set_task(VALUE self, VALUE task);
|
31
|
-
static VALUE get_additional_equalities(EdlibAlignConfig *config);
|
32
|
-
static VALUE aligner_get_additional_equalities(VALUE self);
|
33
|
-
static VALUE set_additional_equalities(EdlibAlignConfig *config, EdlibEqualityPair *eqpairs, VALUE equalities);
|
34
|
-
static VALUE aligner_set_additional_equalities(VALUE self, VALUE equalities);
|
35
|
-
|
36
|
-
static VALUE aligner_config_hash(VALUE self);
|
37
|
-
|
38
|
-
static VALUE aligner_initialize_raw(VALUE self, VALUE k, VALUE mode, VALUE task, VALUE additional_equalities);
|
39
|
-
static VALUE aligner_align(VALUE self, VALUE query, VALUE target);
|
40
|
-
void Init_edlibext(void);
|
41
|
-
|
42
15
|
#endif // EDLIBEXT_H
|
data/ext/edlib/extconf.rb
CHANGED
data/lib/edlib/version.rb
CHANGED
data/lib/edlib.rb
CHANGED
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'edlib/edlibext'
|
2
4
|
|
3
5
|
module Edlib
|
@@ -9,5 +11,68 @@ module Edlib
|
|
9
11
|
task = task.upcase if task.is_a? String
|
10
12
|
initialize_raw(k, mode, task, additional_equalities)
|
11
13
|
end
|
14
|
+
|
15
|
+
def align(query, target, nice: false)
|
16
|
+
if nice
|
17
|
+
align_nice(query, target)
|
18
|
+
else
|
19
|
+
align_raw(query, target)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def align_nice(query, target)
|
26
|
+
result = align(query, target)
|
27
|
+
result.merge(nice(result, query, target))
|
28
|
+
end
|
29
|
+
|
30
|
+
def nice(result, query, target, gap_symbol: '-')
|
31
|
+
raise 'result does not have :locations and :cigar' unless result.key?(:locations) && result.key?(:cigar)
|
32
|
+
|
33
|
+
target_pos = result[:locations][0][0]
|
34
|
+
query_pos = 0
|
35
|
+
query_aln = String.new
|
36
|
+
match_aln = String.new
|
37
|
+
target_aln = String.new
|
38
|
+
cigar = result[:cigar]
|
39
|
+
cigar.scan(/(\d+)(\D)/).each do |num, op|
|
40
|
+
num = num.to_i
|
41
|
+
case op
|
42
|
+
when '='
|
43
|
+
target_aln << target[target_pos, num]
|
44
|
+
target_pos += num
|
45
|
+
query_aln << query[query_pos, num]
|
46
|
+
query_pos += num
|
47
|
+
match_aln << '|' * num
|
48
|
+
when 'X'
|
49
|
+
target_aln << target[target_pos, num]
|
50
|
+
target_pos += num
|
51
|
+
query_aln << query[query_pos, num]
|
52
|
+
query_pos += num
|
53
|
+
match_aln << '.' * num
|
54
|
+
when 'D'
|
55
|
+
target_aln << target[target_pos, num]
|
56
|
+
target_pos += num
|
57
|
+
query_aln << gap_symbol * num
|
58
|
+
query_pos += 0
|
59
|
+
match_aln << gap_symbol * num
|
60
|
+
when 'I'
|
61
|
+
target_aln << gap_symbol * num
|
62
|
+
target_pos += 0
|
63
|
+
query_aln << query[query_pos, num]
|
64
|
+
query_pos += num
|
65
|
+
match_aln << gap_symbol * num
|
66
|
+
else
|
67
|
+
raise "Unknown CIGAR operation: #{op}"
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
{
|
72
|
+
query_aligned: query_aln,
|
73
|
+
match_aligned: match_aln,
|
74
|
+
target_aligned: target_aln
|
75
|
+
}
|
76
|
+
end
|
12
77
|
end
|
13
78
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: edlib
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- kojix2
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2022-11-
|
11
|
+
date: 2022-11-07 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: 'Lightweight, super fast C/C++ library for sequence alignment using edit
|
14
14
|
(Levenshtein) distance. '
|