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> */
32 #define BCF_VERSION "0.1.19+"
34 #define BCF_VERSION VERSION
42 typedef BGZF *bcfFile;
44 typedef gzFile bcfFile;
45 #define bgzf_open(fn, mode) gzopen(fn, mode)
46 #define bgzf_fdopen(fd, mode) gzdopen(fd, mode)
47 #define bgzf_close(fp) gzclose(fp)
48 #define bgzf_read(fp, buf, len) gzread(fp, buf, len)
49 #define bgzf_write(fp, buf, len)
50 #define bgzf_flush(fp)
54 A member in the structs below is said to "primary" if its content
55 cannot be inferred from other members in any of structs below; a
56 member is said to be "derived" if its content can be derived from
57 other members. For example, bcf1_t::str is primary as this comes from
58 the input data, while bcf1_t::info is derived as it can always be
59 correctly set if we know bcf1_t::str. Derived members are for quick
60 access to the content and must be synchronized with the primary data.
64 uint32_t fmt; // format of the block, set by bcf_str2int().
65 int len; // length of data for each individual
66 void *data; // concatenated data
67 // derived info: fmt, len (<-bcf1_t::fmt)
71 int32_t tid, pos; // refID and 0-based position
72 int32_t l_str, m_str; // length and the allocated size of ->str
73 float qual; // SNP quality
74 char *str; // concatenated string of variable length strings in VCF (from col.2 to col.7)
75 char *ref, *alt, *flt, *info, *fmt; // they all point to ->str; no memory allocation
76 int n_gi, m_gi; // number and the allocated size of geno fields
77 bcf_ginfo_t *gi; // array of geno fields
78 int n_alleles, n_smpl; // number of alleles and samples
79 // derived info: ref, alt, flt, info, fmt (<-str), n_gi (<-fmt), n_alleles (<-alt), n_smpl (<-bcf_hdr_t::n_smpl)
80 uint8_t *ploidy; // ploidy of all samples; if NULL, ploidy of 2 is assumed.
84 int32_t n_ref, n_smpl; // number of reference sequences and samples
85 int32_t l_nm; // length of concatenated sequence names; 0 padded
86 int32_t l_smpl; // length of concatenated sample names; 0 padded
87 int32_t l_txt; // length of header text (lines started with ##)
88 char *name, *sname, *txt; // concatenated sequence names, sample names and header text
89 char **ns, **sns; // array of sequence and sample names; point to name and sname, respectively
90 // derived info: n_ref (<-name), n_smpl (<-sname), ns (<-name), sns (<-sname)
94 int is_vcf; // if the file in operation is a VCF
95 void *v; // auxillary data structure for VCF
96 bcfFile fp; // file handler for BCF
100 typedef struct __bcf_idx_t bcf_idx_t;
106 // open a BCF file; for BCF file only
107 bcf_t *bcf_open(const char *fn, const char *mode);
109 int bcf_close(bcf_t *b);
110 // read one record from BCF; return -1 on end-of-file, and <-1 for errors
111 int bcf_read(bcf_t *bp, const bcf_hdr_t *h, bcf1_t *b);
112 // call this function if b->str is changed
113 int bcf_sync(bcf1_t *b);
114 // write a BCF record
115 int bcf_write(bcf_t *bp, const bcf_hdr_t *h, const bcf1_t *b);
116 // read the BCF header; BCF only
117 bcf_hdr_t *bcf_hdr_read(bcf_t *b);
118 // write the BCF header
119 int bcf_hdr_write(bcf_t *b, const bcf_hdr_t *h);
120 // set bcf_hdr_t::ns and bcf_hdr_t::sns
121 int bcf_hdr_sync(bcf_hdr_t *b);
122 // destroy the header
123 void bcf_hdr_destroy(bcf_hdr_t *h);
125 int bcf_destroy(bcf1_t *b);
126 // BCF->VCF conversion
127 char *bcf_fmt(const bcf_hdr_t *h, bcf1_t *b);
129 int bcf_append_info(bcf1_t *b, const char *info, int l);
131 int remove_tag(char *string, const char *tag, char delim);
132 // remove info tag, string is the kstring holder of bcf1_t.str
133 void rm_info(kstring_t *string, const char *key);
135 int bcf_cpy(bcf1_t *r, const bcf1_t *b);
137 // open a VCF or BCF file if "b" is set in "mode"
138 bcf_t *vcf_open(const char *fn, const char *mode);
139 // close a VCF/BCF file
140 int vcf_close(bcf_t *bp);
141 // read the VCF/BCF header
142 bcf_hdr_t *vcf_hdr_read(bcf_t *bp);
143 // read the sequence dictionary from a separate file; required for VCF->BCF conversion
144 int vcf_dictread(bcf_t *bp, bcf_hdr_t *h, const char *fn);
145 // read a VCF/BCF record; return -1 on end-of-file and <-1 for errors
146 int vcf_read(bcf_t *bp, bcf_hdr_t *h, bcf1_t *b);
147 // write the VCF header
148 int vcf_hdr_write(bcf_t *bp, const bcf_hdr_t *h);
149 // write a VCF record
150 int vcf_write(bcf_t *bp, bcf_hdr_t *h, bcf1_t *b);
152 // keep the first n alleles and discard the rest
153 int bcf_shrink_alt(bcf1_t *b, int n);
154 // keep the masked alleles and discard the rest
155 void bcf_fit_alt(bcf1_t *b, int mask);
157 int bcf_gl2pl(bcf1_t *b);
158 // if the site is an indel
159 int bcf_is_indel(const bcf1_t *b);
160 bcf_hdr_t *bcf_hdr_subsam(const bcf_hdr_t *h0, int n, char *const* samples, int *list);
161 int bcf_subsam(int n_smpl, int *list, bcf1_t *b);
162 // move GT to the first FORMAT field
163 int bcf_fix_gt(bcf1_t *b);
164 // update PL generated by old samtools
165 int bcf_fix_pl(bcf1_t *b);
166 // convert PL to GLF-like 10-likelihood GL
167 int bcf_gl10(const bcf1_t *b, uint8_t *gl);
168 // convert up to 4 INDEL alleles to GLF-like 10-likelihood GL
169 int bcf_gl10_indel(const bcf1_t *b, uint8_t *gl);
172 void *bcf_build_refhash(bcf_hdr_t *h);
173 void bcf_str2id_destroy(void *_hash);
174 void bcf_str2id_thorough_destroy(void *_hash);
175 int bcf_str2id_add(void *_hash, const char *str);
176 int bcf_str2id(void *_hash, const char *str);
177 void *bcf_str2id_init();
179 // indexing related functions
180 int bcf_idx_build(const char *fn);
181 uint64_t bcf_idx_query(const bcf_idx_t *idx, int tid, int beg);
182 int bcf_parse_region(void *str2id, const char *str, int *tid, int *begin, int *end);
183 bcf_idx_t *bcf_idx_load(const char *fn);
184 void bcf_idx_destroy(bcf_idx_t *idx);
190 static inline uint32_t bcf_str2int(const char *str, int l)
194 for (i = 0; i < l && i < 4; ++i) {
195 if (str[i] == 0) return x;