1 #include "bcftools.pysam.h"
2
3 /* The MIT License
4
5 Copyright (c) 2016-2020 Genome Research Ltd.
6
7 Author: Petr Danecek <pd3@sanger.ac.uk>
8
9 Permission is hereby granted, free of charge, to any person obtaining a copy
10 of this software and associated documentation files (the "Software"), to deal
11 in the Software without restriction, including without limitation the rights
12 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
13 copies of the Software, and to permit persons to whom the Software is
14 furnished to do so, subject to the following conditions:
15
16 The above copyright notice and this permission notice shall be included in
17 all copies or substantial portions of the Software.
18
19 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
20 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
21 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
22 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
23 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
24 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
25 THE SOFTWARE.
26
27 */
28
29 #include <stdio.h>
30 #include <stdlib.h>
31 #include <math.h>
32 #include <string.h>
33 #include <assert.h>
34 #include "dist.h"
35
36 extern void error(const char *format, ...);
37
38 struct _dist_t
39 {
40 uint64_t *bins, nvalues;
41 int nbins;
42 int npow; // the number of orders of magnitude to represent exactly
43 int nexact; // pow(10,npow)
44 int nlevel;
45 };
46
dist_init(int npow)47 dist_t *dist_init(int npow)
48 {
49 dist_t *dist = (dist_t*) calloc(1,sizeof(dist_t));
50 dist->npow = npow;
51 dist->nexact = pow(10,npow);
52 dist->nlevel = dist->nexact - pow(10,npow-1);
53 return dist;
54 }
55
dist_destroy(dist_t * dist)56 void dist_destroy(dist_t *dist)
57 {
58 if ( !dist ) return;
59 free(dist->bins);
60 free(dist);
61 }
62
dist_nbins(dist_t * dist)63 int dist_nbins(dist_t *dist)
64 {
65 return dist->nbins;
66 }
67
dist_nvalues(dist_t * dist)68 int dist_nvalues(dist_t *dist)
69 {
70 return dist->nvalues;
71 }
72
dist_insert(dist_t * dist,uint32_t value)73 uint32_t dist_insert(dist_t *dist, uint32_t value)
74 {
75 int ibin;
76
77 if ( value <= dist->nexact )
78 ibin = value;
79 else
80 {
81 int npow = (int) log10(value);
82 int level = npow - dist->npow + 1;
83 uint32_t step = pow(10, level);
84 ibin = dist->nexact + dist->nlevel*(level-1) + (value - pow(10,npow)) / step;
85 }
86
87 if ( ibin >= dist->nbins )
88 {
89 dist->bins = (uint64_t*) realloc(dist->bins, sizeof(*dist->bins)*(ibin+1));
90 memset(dist->bins + dist->nbins, 0, (ibin+1 - dist->nbins)*sizeof(*dist->bins));
91 dist->nbins = ibin+1;
92 }
93 dist->bins[ibin]++;
94 dist->nvalues++;
95 return ibin;
96 }
dist_insert_n(dist_t * dist,uint32_t value,uint32_t cnt)97 uint32_t dist_insert_n(dist_t *dist, uint32_t value, uint32_t cnt)
98 {
99 if ( !cnt ) return 0;
100 int ibin = dist_insert(dist, value);
101 dist->bins[ibin] += cnt - 1;
102 dist->nvalues += cnt;
103 return ibin;
104 }
105
dist_get(dist_t * dist,uint32_t idx,uint32_t * beg,uint32_t * end)106 uint64_t dist_get(dist_t *dist, uint32_t idx, uint32_t *beg, uint32_t *end)
107 {
108 if ( idx < dist->nexact )
109 {
110 if ( beg ) *beg = idx;
111 if ( end ) *end = idx + 1;
112 }
113 else
114 {
115 int level = (idx - dist->nexact) / dist->nlevel + 1;
116 int bin = idx - dist->nexact - dist->nlevel*(level-1);
117
118 uint32_t step = pow(10, level);
119 uint32_t value = pow(10, level + dist->npow - 1) + step*bin;
120
121 if ( beg ) *beg = value;
122 if ( end ) *end = value + step;
123 }
124 return dist->bins[idx];
125 }
126
127