minibwa 0.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (52) hide show
  1. checksums.yaml +7 -0
  2. data/LICENSE.txt +21 -0
  3. data/README.md +119 -0
  4. data/ext/minibwa/extconf.rb +105 -0
  5. data/ext/minibwa/mb_buffer.c +113 -0
  6. data/ext/minibwa/mb_hit.c +192 -0
  7. data/ext/minibwa/mb_index.c +462 -0
  8. data/ext/minibwa/mb_index_build.c +174 -0
  9. data/ext/minibwa/mb_options.c +301 -0
  10. data/ext/minibwa/minibwa/LICENSE.txt +37 -0
  11. data/ext/minibwa/minibwa/align.c +930 -0
  12. data/ext/minibwa/minibwa/bseq.h +45 -0
  13. data/ext/minibwa/minibwa/bwt.c +715 -0
  14. data/ext/minibwa/minibwa/bwt.h +86 -0
  15. data/ext/minibwa/minibwa/cs.c +161 -0
  16. data/ext/minibwa/minibwa/format.c +356 -0
  17. data/ext/minibwa/minibwa/index.c +342 -0
  18. data/ext/minibwa/minibwa/kalloc.c +224 -0
  19. data/ext/minibwa/minibwa/kalloc.h +54 -0
  20. data/ext/minibwa/minibwa/ketopt.h +123 -0
  21. data/ext/minibwa/minibwa/kommon.c +374 -0
  22. data/ext/minibwa/minibwa/kommon.h +85 -0
  23. data/ext/minibwa/minibwa/kseq.h +256 -0
  24. data/ext/minibwa/minibwa/ksort.h +163 -0
  25. data/ext/minibwa/minibwa/ksw2.h +220 -0
  26. data/ext/minibwa/minibwa/ksw2_extd2_sse.c +403 -0
  27. data/ext/minibwa/minibwa/ksw2_extz2_sse.c +296 -0
  28. data/ext/minibwa/minibwa/ksw2_ll_sse.c +341 -0
  29. data/ext/minibwa/minibwa/kthread.h +15 -0
  30. data/ext/minibwa/minibwa/l2bit.c +479 -0
  31. data/ext/minibwa/minibwa/l2bit.h +72 -0
  32. data/ext/minibwa/minibwa/lchain.c +231 -0
  33. data/ext/minibwa/minibwa/libsais.c +6985 -0
  34. data/ext/minibwa/minibwa/libsais.h +106 -0
  35. data/ext/minibwa/minibwa/libsais64.c +7064 -0
  36. data/ext/minibwa/minibwa/libsais64.h +81 -0
  37. data/ext/minibwa/minibwa/map-algo.c +769 -0
  38. data/ext/minibwa/minibwa/mbpriv.h +148 -0
  39. data/ext/minibwa/minibwa/minibwa.h +176 -0
  40. data/ext/minibwa/minibwa/options.c +116 -0
  41. data/ext/minibwa/minibwa/pe.c +559 -0
  42. data/ext/minibwa/minibwa/s2n-lite.h +59 -0
  43. data/ext/minibwa/minibwa/seed.c +354 -0
  44. data/ext/minibwa/minibwa.c +67 -0
  45. data/ext/minibwa/minibwa.h +51 -0
  46. data/lib/minibwa/hit.rb +110 -0
  47. data/lib/minibwa/index.rb +77 -0
  48. data/lib/minibwa/options.rb +235 -0
  49. data/lib/minibwa/sam.rb +85 -0
  50. data/lib/minibwa/version.rb +6 -0
  51. data/lib/minibwa.rb +11 -0
  52. metadata +88 -0
@@ -0,0 +1,301 @@
1
+ /*
2
+ * Minibwa::Options -- wraps mb_opt_t, the alignment parameter block.
3
+ *
4
+ * The struct is stored by value inside a TypedData object, so copying an
5
+ * Options never aliases C memory. Every one of its ~50 fields is exposed as
6
+ * a reader/writer pair generated from an X-macro table, keeping the accessor
7
+ * list to one line per field as upstream adds them. Also wraps mb_opt_init()
8
+ * and mb_opt_preset() ("sr", "adap", "lr") and turns each MB_F_* bit into a
9
+ * predicate/setter pair.
10
+ */
11
+
12
+ #include "minibwa.h"
13
+
14
+ const rb_data_type_t rb_minibwa_options_type = {
15
+ .wrap_struct_name = "Minibwa::Options",
16
+ .function = { NULL, RUBY_DEFAULT_FREE, NULL },
17
+ .flags = RUBY_TYPED_FREE_IMMEDIATELY
18
+ };
19
+
20
+ /* ------------------------------------------------------------------ */
21
+ /* X-macro: field name, C type, Ruby wrap/unwrap macros */
22
+ /* ------------------------------------------------------------------ */
23
+
24
+ #define INT32_FIELD(name) FIELD(name, int32_t, NUM2INT, INT2NUM)
25
+ #define INT64_FIELD(name) FIELD(name, int64_t, NUM2LL, LL2NUM)
26
+ #define UINT64_FIELD(name) FIELD(name, uint64_t, NUM2ULL, ULL2NUM)
27
+ #define FLOAT_FIELD(name) FIELD(name, float, NUM2DBL, DBL2NUM)
28
+
29
+ #define FIELD(name, ctype, unwrap, wrap) \
30
+ static VALUE \
31
+ mb_opt_get_##name(VALUE self) \
32
+ { \
33
+ mb_opt_t *opt = rb_minibwa_get_opt(self); \
34
+ return wrap(opt->name); \
35
+ } \
36
+ static VALUE \
37
+ mb_opt_set_##name(VALUE self, VALUE val) \
38
+ { \
39
+ mb_opt_t *opt = rb_minibwa_get_opt(self); \
40
+ opt->name = (ctype)unwrap(val); \
41
+ return val; \
42
+ }
43
+
44
+ /* ---- flag (uint64_t, special: also has bit predicates/setters) ---- */
45
+ UINT64_FIELD(flag)
46
+
47
+ /* ---- seeding options ---- */
48
+ INT32_FIELD(min_len)
49
+ INT32_FIELD(max_sub_occ)
50
+ INT32_FIELD(max_occ)
51
+
52
+ /* ---- general algorithm options ---- */
53
+ INT32_FIELD(bw)
54
+ INT32_FIELD(bw_long)
55
+ INT32_FIELD(max_gap)
56
+ INT32_FIELD(max_sr_len)
57
+
58
+ /* ---- chaining options ---- */
59
+ INT32_FIELD(max_chain_skip)
60
+ INT32_FIELD(max_chain_iter)
61
+ INT32_FIELD(min_chain_score)
62
+ FLOAT_FIELD(chain_gap_scale)
63
+
64
+ /* ---- hit processing options ---- */
65
+ FLOAT_FIELD(mask_level)
66
+ INT32_FIELD(mask_len)
67
+ FLOAT_FIELD(pri_ratio)
68
+ INT32_FIELD(best_n)
69
+
70
+ /* ---- alignment options ---- */
71
+ INT32_FIELD(a)
72
+ INT32_FIELD(b)
73
+ INT32_FIELD(b_ts)
74
+ INT32_FIELD(b_ambi)
75
+ INT32_FIELD(q)
76
+ INT32_FIELD(q2)
77
+ INT32_FIELD(e)
78
+ INT32_FIELD(e2)
79
+ INT32_FIELD(end_bonus)
80
+ INT32_FIELD(min_dp_max)
81
+ INT32_FIELD(zdrop)
82
+ INT32_FIELD(zdrop_inv)
83
+ INT32_FIELD(min_ksw_len)
84
+
85
+ /* ---- pairing options ---- */
86
+ INT32_FIELD(max_pe_ins)
87
+ INT32_FIELD(max_rescue)
88
+ INT32_FIELD(pen_unpair)
89
+ INT32_FIELD(pe_avg)
90
+ INT32_FIELD(pe_std)
91
+ INT32_FIELD(pe_lo)
92
+ INT32_FIELD(pe_hi)
93
+
94
+ /* ---- input/output options ---- */
95
+ INT32_FIELD(sb_len)
96
+ INT32_FIELD(sb_seq)
97
+ INT32_FIELD(n_thread)
98
+ INT32_FIELD(out_n)
99
+ FLOAT_FIELD(out_s)
100
+ INT32_FIELD(seed)
101
+ INT32_FIELD(xa_max)
102
+ INT64_FIELD(mb_size)
103
+ INT64_FIELD(max_mb_size)
104
+ INT64_FIELD(max_sw_mat)
105
+ INT64_FIELD(cap_kalloc)
106
+
107
+ #undef FIELD
108
+ #undef INT32_FIELD
109
+ #undef INT64_FIELD
110
+ #undef UINT64_FIELD
111
+ #undef FLOAT_FIELD
112
+
113
+ /* ------------------------------------------------------------------ */
114
+ /* Flag bit predicates and setters */
115
+ /* ------------------------------------------------------------------ */
116
+
117
+ #define FLAG_BIT(name, bit) \
118
+ static VALUE \
119
+ mb_opt_##name##_p(VALUE self) \
120
+ { \
121
+ mb_opt_t *opt = rb_minibwa_get_opt(self); \
122
+ return (opt->flag & bit) ? Qtrue : Qfalse; \
123
+ } \
124
+ static VALUE \
125
+ mb_opt_set_##name(VALUE self, VALUE val) \
126
+ { \
127
+ mb_opt_t *opt = rb_minibwa_get_opt(self); \
128
+ if (RTEST(val)) opt->flag |= bit; \
129
+ else opt->flag &= ~bit; \
130
+ return val; \
131
+ }
132
+
133
+ FLAG_BIT(paf, MB_F_PAF)
134
+ FLAG_BIT(no_unmap, MB_F_NO_UNMAP)
135
+ FLAG_BIT(copy_comment, MB_F_COPY_COMMENT)
136
+ FLAG_BIT(pe, MB_F_PE)
137
+ FLAG_BIT(long_mode, MB_F_LONG)
138
+ FLAG_BIT(eqx, MB_F_EQX)
139
+ FLAG_BIT(no_kalloc, MB_F_NO_KALLOC)
140
+ FLAG_BIT(no_aln, MB_F_NO_ALN)
141
+ FLAG_BIT(pe_predef, MB_F_PE_PREDEF)
142
+ FLAG_BIT(write_ds, MB_F_WRITE_DS)
143
+ FLAG_BIT(write_cs, MB_F_WRITE_CS)
144
+ FLAG_BIT(write_md, MB_F_WRITE_MD)
145
+ FLAG_BIT(second_seq, MB_F_2ND_SEQ)
146
+ FLAG_BIT(supp_soft, MB_F_SUPP_SOFT)
147
+ FLAG_BIT(adap, MB_F_ADAP)
148
+ FLAG_BIT(primary5, MB_F_PRIMARY5)
149
+ FLAG_BIT(no_pairing, MB_F_NO_PAIRING)
150
+ FLAG_BIT(meth, MB_F_METH)
151
+
152
+ #undef FLAG_BIT
153
+
154
+ /* ------------------------------------------------------------------ */
155
+ /* Constructor, init, preset */
156
+ /* ------------------------------------------------------------------ */
157
+
158
+ static VALUE
159
+ mb_opt_alloc(VALUE klass)
160
+ {
161
+ mb_opt_t *opt;
162
+ VALUE obj = TypedData_Make_Struct(klass, mb_opt_t,
163
+ &rb_minibwa_options_type, opt);
164
+ mb_opt_init(opt);
165
+ return obj;
166
+ }
167
+
168
+ /*
169
+ * call-seq:
170
+ * Options.new(**kwargs) -> Options
171
+ *
172
+ * Returns a new Options initialised with mb_opt_init() (adaptive paired-end
173
+ * defaults). Pass keyword arguments to override individual fields, e.g.
174
+ *
175
+ * Options.new(bw: 500, min_len: 19)
176
+ */
177
+ static VALUE
178
+ mb_opt_initialize(int argc, VALUE *argv, VALUE self)
179
+ {
180
+ VALUE kwargs;
181
+ rb_scan_args(argc, argv, ":", &kwargs);
182
+
183
+ if (!NIL_P(kwargs)) {
184
+ static ID id_keyword_new;
185
+ if (!id_keyword_new)
186
+ id_keyword_new = rb_intern("__keyword_new__");
187
+ /* Delegate to Ruby-side keyword handling in lib/minibwa/options.rb */
188
+ rb_funcall(self, id_keyword_new, 1, kwargs);
189
+ }
190
+ return Qnil;
191
+ }
192
+
193
+ /*
194
+ * call-seq:
195
+ * preset!(name) -> true or false
196
+ *
197
+ * Applies a named preset. Returns +true+ on success, +false+ if the preset
198
+ * name is unknown. Known presets: "sr", "adap", "lr".
199
+ */
200
+ static VALUE
201
+ rb_minibwa_opt_preset(VALUE self, VALUE name)
202
+ {
203
+ mb_opt_t *opt = rb_minibwa_get_opt(self);
204
+ const char *s = StringValueCStr(name);
205
+ return mb_opt_preset(opt, s) == 0 ? Qtrue : Qfalse;
206
+ }
207
+
208
+ /* ------------------------------------------------------------------ */
209
+ /* Registration */
210
+ /* ------------------------------------------------------------------ */
211
+
212
+ #define DEF_ACCESSOR(klass, name) \
213
+ rb_define_method(klass, #name, mb_opt_get_##name, 0); \
214
+ rb_define_method(klass, #name "=", mb_opt_set_##name, 1);
215
+
216
+ #define DEF_FLAG(klass, name) \
217
+ rb_define_method(klass, #name "?", mb_opt_##name##_p, 0); \
218
+ rb_define_method(klass, #name "=", mb_opt_set_##name, 1);
219
+
220
+ void
221
+ rb_minibwa_init_options(void)
222
+ {
223
+ VALUE klass = rb_define_class_under(rb_mMinibwa, "Options", rb_cObject);
224
+ rb_cMinibwaOptions = klass;
225
+
226
+ rb_define_alloc_func(klass, mb_opt_alloc);
227
+ rb_define_method(klass, "initialize", mb_opt_initialize, -1);
228
+ rb_define_method(klass, "preset!", rb_minibwa_opt_preset, 1);
229
+
230
+ /* ---- scalar fields ---- */
231
+ DEF_ACCESSOR(klass, flag)
232
+ DEF_ACCESSOR(klass, min_len)
233
+ DEF_ACCESSOR(klass, max_sub_occ)
234
+ DEF_ACCESSOR(klass, max_occ)
235
+ DEF_ACCESSOR(klass, bw)
236
+ DEF_ACCESSOR(klass, bw_long)
237
+ DEF_ACCESSOR(klass, max_gap)
238
+ DEF_ACCESSOR(klass, max_sr_len)
239
+ DEF_ACCESSOR(klass, max_chain_skip)
240
+ DEF_ACCESSOR(klass, max_chain_iter)
241
+ DEF_ACCESSOR(klass, min_chain_score)
242
+ DEF_ACCESSOR(klass, chain_gap_scale)
243
+ DEF_ACCESSOR(klass, mask_level)
244
+ DEF_ACCESSOR(klass, mask_len)
245
+ DEF_ACCESSOR(klass, pri_ratio)
246
+ DEF_ACCESSOR(klass, best_n)
247
+ DEF_ACCESSOR(klass, a)
248
+ DEF_ACCESSOR(klass, b)
249
+ DEF_ACCESSOR(klass, b_ts)
250
+ DEF_ACCESSOR(klass, b_ambi)
251
+ DEF_ACCESSOR(klass, q)
252
+ DEF_ACCESSOR(klass, q2)
253
+ DEF_ACCESSOR(klass, e)
254
+ DEF_ACCESSOR(klass, e2)
255
+ DEF_ACCESSOR(klass, end_bonus)
256
+ DEF_ACCESSOR(klass, min_dp_max)
257
+ DEF_ACCESSOR(klass, zdrop)
258
+ DEF_ACCESSOR(klass, zdrop_inv)
259
+ DEF_ACCESSOR(klass, min_ksw_len)
260
+ DEF_ACCESSOR(klass, max_pe_ins)
261
+ DEF_ACCESSOR(klass, max_rescue)
262
+ DEF_ACCESSOR(klass, pen_unpair)
263
+ DEF_ACCESSOR(klass, pe_avg)
264
+ DEF_ACCESSOR(klass, pe_std)
265
+ DEF_ACCESSOR(klass, pe_lo)
266
+ DEF_ACCESSOR(klass, pe_hi)
267
+ DEF_ACCESSOR(klass, sb_len)
268
+ DEF_ACCESSOR(klass, sb_seq)
269
+ DEF_ACCESSOR(klass, n_thread)
270
+ DEF_ACCESSOR(klass, out_n)
271
+ DEF_ACCESSOR(klass, out_s)
272
+ DEF_ACCESSOR(klass, seed)
273
+ DEF_ACCESSOR(klass, xa_max)
274
+ DEF_ACCESSOR(klass, mb_size)
275
+ DEF_ACCESSOR(klass, max_mb_size)
276
+ DEF_ACCESSOR(klass, max_sw_mat)
277
+ DEF_ACCESSOR(klass, cap_kalloc)
278
+
279
+ /* ---- flag bits ---- */
280
+ DEF_FLAG(klass, paf)
281
+ DEF_FLAG(klass, no_unmap)
282
+ DEF_FLAG(klass, copy_comment)
283
+ DEF_FLAG(klass, pe)
284
+ DEF_FLAG(klass, long_mode)
285
+ DEF_FLAG(klass, eqx)
286
+ DEF_FLAG(klass, no_kalloc)
287
+ DEF_FLAG(klass, no_aln)
288
+ DEF_FLAG(klass, pe_predef)
289
+ DEF_FLAG(klass, write_ds)
290
+ DEF_FLAG(klass, write_cs)
291
+ DEF_FLAG(klass, write_md)
292
+ DEF_FLAG(klass, second_seq)
293
+ DEF_FLAG(klass, supp_soft)
294
+ DEF_FLAG(klass, adap)
295
+ DEF_FLAG(klass, primary5)
296
+ DEF_FLAG(klass, no_pairing)
297
+ DEF_FLAG(klass, meth)
298
+ }
299
+
300
+ #undef DEF_ACCESSOR
301
+ #undef DEF_FLAG
@@ -0,0 +1,37 @@
1
+ The MIT License
2
+
3
+ Copyright (c) 2025- Dana-Farber Cancer Institute
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining
6
+ a copy of this software and associated documentation files (the
7
+ "Software"), to deal in the Software without restriction, including
8
+ without limitation the rights to use, copy, modify, merge, publish,
9
+ distribute, sublicense, and/or sell copies of the Software, and to
10
+ permit persons to whom the Software is furnished to do so, subject to
11
+ the following conditions:
12
+
13
+ The above copyright notice and this permission notice shall be
14
+ included in all copies or substantial portions of the Software.
15
+
16
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
17
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
19
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
20
+ BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
21
+ ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
22
+ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
23
+ SOFTWARE.
24
+
25
+ ---
26
+
27
+ THIRD-PARTY SOFTWARE NOTICES
28
+
29
+ This project includes the source code from the following projects:
30
+
31
+ * libsais: Apache 2 License. Copyright (c) 2021-2025 Ilya Grebnov <ilya.grebnov@gmail.com>
32
+ * mimalloc: MIT License. Copyright (c) 2018-2026 Microsoft Corporation, Daan Leijen
33
+
34
+ It is optionally built on the following projects (disabled with "make gpl=0"):
35
+
36
+ * QSufSort: HPND License. Copyright (c) 1999 N. Jesper Larsson
37
+ * bwtgen: GPL 2 License. Copyright (c) 2004 Wong Chi Kwong