3 Copyright (c) 2008 Broad Institute / Massachusetts Institute of Technology
4 2011 Attractive Chaos <attractor@live.co.uk>
6 Permission is hereby granted, free of charge, to any person obtaining a copy
7 of this software and associated documentation files (the "Software"), to deal
8 in the Software without restriction, including without limitation the rights
9 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
10 copies of the Software, and to permit persons to whom the Software is
11 furnished to do so, subject to the following conditions:
13 The above copyright notice and this permission notice shall be included in
14 all copies or substantial portions of the Software.
16 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
25 /* The BGZF library was originally written by Bob Handsaker from the Broad
26 * Institute. It was later improved by the SAMtools developers. */
35 #define BGZF_BLOCK_SIZE 0x10000 // 64k
37 #define BGZF_ERR_ZLIB 1
38 #define BGZF_ERR_HEADER 2
40 #define BGZF_ERR_MISUSE 8
43 int open_mode:8, compress_level:8, errcode:16;
45 int block_length, block_offset;
46 int64_t block_address;
47 void *uncompressed_block, *compressed_block;
48 void *cache; // a pointer to a hash table
49 void *fp; // actual file handler; FILE* on writing; FILE* or knetFile* on reading
53 #define KSTRING_T kstring_t
54 typedef struct __kstring_t {
69 * Open an existing file descriptor for reading or writing.
71 * @param fd file descriptor
72 * @param mode mode matching /[rwu0-9]+/: 'r' for reading, 'w' for writing and a digit specifies
73 * the zlib compression level; if both 'r' and 'w' are present, 'w' is ignored.
74 * @return BGZF file handler; 0 on error
76 BGZF* bgzf_dopen(int fd, const char *mode);
79 * Open the specified file for reading or writing.
81 BGZF* bgzf_open(const char* path, const char *mode);
84 * Close the BGZF and free all associated resources.
86 * @param fp BGZF file handler
87 * @return 0 on success and -1 on error
89 int bgzf_close(BGZF *fp);
92 * Read up to _length_ bytes from the file storing into _data_.
94 * @param fp BGZF file handler
95 * @param data data array to read into
96 * @param length size of data to read
97 * @return number of bytes actually read; 0 on end-of-file and -1 on error
99 ssize_t bgzf_read(BGZF *fp, void *data, ssize_t length);
102 * Write _length_ bytes from _data_ to the file.
104 * @param fp BGZF file handler
105 * @param data data array to write
106 * @param length size of data to write
107 * @return number of bytes actually written; -1 on error
109 ssize_t bgzf_write(BGZF *fp, const void *data, ssize_t length);
112 * Write the data in the buffer to the file.
114 int bgzf_flush(BGZF *fp);
117 * Return a virtual file pointer to the current location in the file.
118 * No interpetation of the value should be made, other than a subsequent
119 * call to bgzf_seek can be used to position the file at the same point.
120 * Return value is non-negative on success.
122 #define bgzf_tell(fp) ((fp->block_address << 16) | (fp->block_offset & 0xFFFF))
125 * Set the file to read from the location specified by _pos_.
127 * @param fp BGZF file handler
128 * @param pos virtual file offset returned by bgzf_tell()
129 * @param whence must be SEEK_SET
130 * @return 0 on success and -1 on error
132 int64_t bgzf_seek(BGZF *fp, int64_t pos, int whence);
135 * Check if the BGZF end-of-file (EOF) marker is present
137 * @param fp BGZF file handler opened for reading
138 * @return 1 if EOF is present; 0 if not or on I/O error
140 int bgzf_check_EOF(BGZF *fp);
143 * Check if a file is in the BGZF format
145 * @param fn file name
146 * @return 1 if _fn_ is BGZF; 0 if not or on I/O error
148 int bgzf_is_bgzf(const char *fn);
150 /*********************
151 * Advanced routines *
152 *********************/
155 * Set the cache size. Only effective when compiled with -DBGZF_CACHE.
157 * @param fp BGZF file handler
158 * @param size size of cache in bytes; 0 to disable caching (default)
160 void bgzf_set_cache_size(BGZF *fp, int size);
163 * Flush the file if the remaining buffer size is smaller than _size_
165 int bgzf_flush_try(BGZF *fp, ssize_t size);
168 * Read one byte from a BGZF file. It is faster than bgzf_read()
169 * @param fp BGZF file handler
170 * @return byte read; -1 on end-of-file or error
172 int bgzf_getc(BGZF *fp);
175 * Read one line from a BGZF file. It is faster than bgzf_getc()
177 * @param fp BGZF file handler
178 * @param delim delimitor
179 * @param str string to write to; must be initialized
180 * @return length of the string; 0 on end-of-file; negative on error
182 int bgzf_getline(BGZF *fp, int delim, kstring_t *str);
185 * Read the next BGZF block.
187 int bgzf_read_block(BGZF *fp);