3 Copyright (c) 2010 Broad Institute
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:
13 The above copyright notice and this permission notice shall be
14 included in all copies or substantial portions of the Software.
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
26 /* Contact: Heng Li <lh3@live.co.uk> */
31 #define BCF_VERSION "0.1.17-dev (r973:277)"
38 typedef BGZF *bcfFile;
40 typedef gzFile bcfFile;
41 #define bgzf_open(fn, mode) gzopen(fn, mode)
42 #define bgzf_fdopen(fd, mode) gzdopen(fd, mode)
43 #define bgzf_close(fp) gzclose(fp)
44 #define bgzf_read(fp, buf, len) gzread(fp, buf, len)
45 #define bgzf_write(fp, buf, len)
46 #define bgzf_flush(fp)
50 A member in the structs below is said to "primary" if its content
51 cannot be inferred from other members in any of structs below; a
52 member is said to be "derived" if its content can be derived from
53 other members. For example, bcf1_t::str is primary as this comes from
54 the input data, while bcf1_t::info is derived as it can always be
55 correctly set if we know bcf1_t::str. Derived members are for quick
56 access to the content and must be synchronized with the primary data.
60 uint32_t fmt; // format of the block, set by bcf_str2int().
61 int len; // length of data for each individual
62 void *data; // concatenated data
63 // derived info: fmt, len (<-bcf1_t::fmt)
67 int32_t tid, pos; // refID and 0-based position
68 int32_t l_str, m_str; // length and the allocated size of ->str
69 float qual; // SNP quality
70 char *str; // concatenated string of variable length strings in VCF (from col.2 to col.7)
71 char *ref, *alt, *flt, *info, *fmt; // they all point to ->str; no memory allocation
72 int n_gi, m_gi; // number and the allocated size of geno fields
73 bcf_ginfo_t *gi; // array of geno fields
74 int n_alleles, n_smpl; // number of alleles and samples
75 // derived info: ref, alt, flt, info, fmt (<-str), n_gi (<-fmt), n_alleles (<-alt), n_smpl (<-bcf_hdr_t::n_smpl)
79 int32_t n_ref, n_smpl; // number of reference sequences and samples
80 int32_t l_nm; // length of concatenated sequence names; 0 padded
81 int32_t l_smpl; // length of concatenated sample names; 0 padded
82 int32_t l_txt; // length of header text (lines started with ##)
83 char *name, *sname, *txt; // concatenated sequence names, sample names and header text
84 char **ns, **sns; // array of sequence and sample names; point to name and sname, respectively
85 // derived info: n_ref (<-name), n_smpl (<-sname), ns (<-name), sns (<-sname)
89 int is_vcf; // if the file in operation is a VCF
90 void *v; // auxillary data structure for VCF
91 bcfFile fp; // file handler for BCF
95 typedef struct __bcf_idx_t bcf_idx_t;
101 // open a BCF file; for BCF file only
102 bcf_t *bcf_open(const char *fn, const char *mode);
104 int bcf_close(bcf_t *b);
105 // read one record from BCF; return -1 on end-of-file, and <-1 for errors
106 int bcf_read(bcf_t *bp, const bcf_hdr_t *h, bcf1_t *b);
107 // call this function if b->str is changed
108 int bcf_sync(bcf1_t *b);
109 // write a BCF record
110 int bcf_write(bcf_t *bp, const bcf_hdr_t *h, const bcf1_t *b);
111 // read the BCF header; BCF only
112 bcf_hdr_t *bcf_hdr_read(bcf_t *b);
113 // write the BCF header
114 int bcf_hdr_write(bcf_t *b, const bcf_hdr_t *h);
115 // set bcf_hdr_t::ns and bcf_hdr_t::sns
116 int bcf_hdr_sync(bcf_hdr_t *b);
117 // destroy the header
118 void bcf_hdr_destroy(bcf_hdr_t *h);
120 int bcf_destroy(bcf1_t *b);
121 // BCF->VCF conversion
122 char *bcf_fmt(const bcf_hdr_t *h, bcf1_t *b);
124 int bcf_append_info(bcf1_t *b, const char *info, int l);
126 int bcf_cpy(bcf1_t *r, const bcf1_t *b);
128 // open a VCF or BCF file if "b" is set in "mode"
129 bcf_t *vcf_open(const char *fn, const char *mode);
130 // close a VCF/BCF file
131 int vcf_close(bcf_t *bp);
132 // read the VCF/BCF header
133 bcf_hdr_t *vcf_hdr_read(bcf_t *bp);
134 // read the sequence dictionary from a separate file; required for VCF->BCF conversion
135 int vcf_dictread(bcf_t *bp, bcf_hdr_t *h, const char *fn);
136 // read a VCF/BCF record; return -1 on end-of-file and <-1 for errors
137 int vcf_read(bcf_t *bp, bcf_hdr_t *h, bcf1_t *b);
138 // write the VCF header
139 int vcf_hdr_write(bcf_t *bp, const bcf_hdr_t *h);
140 // write a VCF record
141 int vcf_write(bcf_t *bp, bcf_hdr_t *h, bcf1_t *b);
143 // keep the first n alleles and discard the rest
144 int bcf_shrink_alt(bcf1_t *b, int n);
146 int bcf_gl2pl(bcf1_t *b);
147 // if the site is an indel
148 int bcf_is_indel(const bcf1_t *b);
149 bcf_hdr_t *bcf_hdr_subsam(const bcf_hdr_t *h0, int n, char *const* samples, int *list);
150 int bcf_subsam(int n_smpl, int *list, bcf1_t *b);
151 // move GT to the first FORMAT field
152 int bcf_fix_gt(bcf1_t *b);
153 // update PL generated by old samtools
154 int bcf_fix_pl(bcf1_t *b);
155 // convert PL to GLF-like 10-likelihood GL
156 int bcf_gl10(const bcf1_t *b, uint8_t *gl);
157 // convert up to 4 INDEL alleles to GLF-like 10-likelihood GL
158 int bcf_gl10_indel(const bcf1_t *b, uint8_t *gl);
161 void *bcf_build_refhash(bcf_hdr_t *h);
162 void bcf_str2id_destroy(void *_hash);
163 void bcf_str2id_thorough_destroy(void *_hash);
164 int bcf_str2id_add(void *_hash, const char *str);
165 int bcf_str2id(void *_hash, const char *str);
166 void *bcf_str2id_init();
168 // indexing related functions
169 int bcf_idx_build(const char *fn);
170 uint64_t bcf_idx_query(const bcf_idx_t *idx, int tid, int beg);
171 int bcf_parse_region(void *str2id, const char *str, int *tid, int *begin, int *end);
172 bcf_idx_t *bcf_idx_load(const char *fn);
173 void bcf_idx_destroy(bcf_idx_t *idx);
179 static inline uint32_t bcf_str2int(const char *str, int l)
183 for (i = 0; i < l && i < 4; ++i) {
184 if (str[i] == 0) return x;