bio-cgranges 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.
@@ -0,0 +1,87 @@
1
+ /* The MIT License
2
+
3
+ Copyright (c) 2019 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
+ #ifndef CRANGES_H
26
+ #define CRANGES_H
27
+
28
+ #include <stdint.h>
29
+
30
+ typedef struct { // a contig
31
+ char *name; // name of the contig
32
+ int32_t len; // max length seen in data
33
+ int32_t root_k;
34
+ int64_t n, off; // sum of lengths of previous contigs
35
+ } cr_ctg_t;
36
+
37
+ typedef struct { // an interval
38
+ uint64_t x; // prior to cr_index(), x = ctg_id<<32|start_pos; after: x = start_pos<<32|end_pos
39
+ uint32_t y:31, rev:1;
40
+ int32_t label; // NOT used
41
+ } cr_intv_t;
42
+
43
+ typedef struct {
44
+ int64_t n_r, m_r; // number and max number of intervals
45
+ cr_intv_t *r; // list of intervals (of size _n_r_)
46
+ int32_t n_ctg, m_ctg; // number and max number of contigs
47
+ cr_ctg_t *ctg; // list of contigs (of size _n_ctg_)
48
+ void *hc; // dictionary for converting contig names to integers
49
+ } cgranges_t;
50
+
51
+ #ifdef __cplusplus
52
+ extern "C" {
53
+ #endif
54
+
55
+ // retrieve start and end positions from a cr_intv_t object
56
+ static inline int32_t cr_st(const cr_intv_t *r) { return (int32_t)(r->x>>32); }
57
+ static inline int32_t cr_en(const cr_intv_t *r) { return (int32_t)r->x; }
58
+ static inline int32_t cr_start(const cgranges_t *cr, int64_t i) { return cr_st(&cr->r[i]); }
59
+ static inline int32_t cr_end(const cgranges_t *cr, int64_t i) { return cr_en(&cr->r[i]); }
60
+ static inline int32_t cr_label(const cgranges_t *cr, int64_t i) { return cr->r[i].label; }
61
+
62
+ // Initialize
63
+ cgranges_t *cr_init(void);
64
+
65
+ // Deallocate
66
+ void cr_destroy(cgranges_t *cr);
67
+
68
+ // Add an interval
69
+ cr_intv_t *cr_add(cgranges_t *cr, const char *ctg, int32_t st, int32_t en, int32_t label_int);
70
+
71
+ // Sort and index intervals
72
+ void cr_index(cgranges_t *cr);
73
+
74
+ int64_t cr_overlap(const cgranges_t *cr, const char *ctg, int32_t st, int32_t en, int64_t **b_, int64_t *m_b_);
75
+ int64_t cr_contain(const cgranges_t *cr, const char *ctg, int32_t st, int32_t en, int64_t **b_, int64_t *m_b_);
76
+
77
+ // Add a contig and length. Call this for desired contig ordering. _len_ can be 0.
78
+ int32_t cr_add_ctg(cgranges_t *cr, const char *ctg, int32_t len);
79
+
80
+ // Get the contig ID given its name
81
+ int32_t cr_get_ctg(const cgranges_t *cr, const char *ctg);
82
+
83
+ #ifdef __cplusplus
84
+ }
85
+ #endif
86
+
87
+ #endif