BGI/SOAPsnp/sam/razf.h

   1  /*-
   2  * RAZF : Random Access compressed(Z) File
   3  * Version: 1.0
   4  * Release Date: 2008-10-27
   5  *
   6  * Copyright 2008, Jue Ruan <ruanjue@gmail.com>, Heng Li <lh3@sanger.ac.uk>
   7  *
   8  * All rights reserved.
   9  *
  10  * Redistribution and use in source and binary forms, with or without
  11  * modification, are permitted provided that the following conditions
  12  * are met:
  13  * 1. Redistributions of source code must retain the above copyright
  14  *    notice, this list of conditions and the following disclaimer.
  15  * 2. Redistributions in binary form must reproduce the above copyright
  16  *    notice, this list of conditions and the following disclaimer in the
  17  *    documentation and/or other materials provided with the distribution.
  18  *
  19  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  20  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  21  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  22  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  23  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  24  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  25  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  26  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  27  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  28  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  29  * SUCH DAMAGE.
  30  */
  31
  32
  33 #ifndef __RAZF_RJ_H
  34 #define __RAZF_RJ_H
  35
  36 #include <stdint.h>
  37 #include <stdio.h>
  38 #include "zlib.h"
  39
  40 #ifdef _USE_KNETFILE
  41 #include "knetfile.h"
  42 #endif
  43
  44 #if ZLIB_VERNUM < 0x1221
  45 #define _RZ_READONLY
  46 struct _gz_header_s;
  47 typedef struct _gz_header_s _gz_header;
  48 #define gz_header _gz_header
  49 #endif
  50
  51 #define WINDOW_BITS   15
  52
  53 #ifndef RZ_BLOCK_SIZE
  54 #define RZ_BLOCK_SIZE (1<<WINDOW_BITS)
  55 #endif
  56
  57 #ifndef RZ_BUFFER_SIZE
  58 #define RZ_BUFFER_SIZE 4096
  59 #endif
  60
  61 #ifndef RZ_COMPRESS_LEVEL
  62 #define RZ_COMPRESS_LEVEL 6
  63 #endif
  64
  65 #define RZ_BIN_SIZE ((1LLU << 32) / RZ_BLOCK_SIZE)
  66
  67 typedef struct {
  68         uint32_t *cell_offsets; // i
  69         int64_t  *bin_offsets; // i / BIN_SIZE
  70         int size;
  71         int cap;
  72 } ZBlockIndex;
  73 /* When storing index, output bytes in Big-Endian everywhere */
  74
  75 #define FILE_TYPE_RZ    1
  76 #define FILE_TYPE_PLAIN 2
  77 #define FILE_TYPE_GZ    3
  78
  79 typedef struct RandomAccessZFile  {
  80         char mode; /* 'w' : write mode; 'r' : read mode */
  81         int file_type;
  82         /* plain file or rz file, razf_read support plain file as input too, in this case, razf_read work as buffered fread */
  83 #ifdef _USE_KNETFILE
  84     union {
  85         knetFile *fpr;
  86         int fpw;
  87     } x;
  88 #else
  89         int filedes; /* the file descriptor */
  90 #endif
  91         z_stream *stream;
  92         ZBlockIndex *index;
  93         int64_t in, out, end, src_end;
  94         /* in: n bytes total in; out: n bytes total out; */
  95         /* end: the end of all data blocks, while the start of index; src_end: the true end position in uncompressed file */
  96         int buf_flush; // buffer should be flush, suspend inflate util buffer is empty
  97         int64_t block_pos, block_off, next_block_pos;
  98         /* block_pos: the start postiion of current block  in compressed file */
  99         /* block_off: tell how many bytes have been read from current block */
 100         void *inbuf, *outbuf;
 101         int header_size;
 102         gz_header *header;
 103         /* header is used to transfer inflate_state->mode from HEAD to TYPE after call inflateReset */
 104         int buf_off, buf_len;
 105         int z_err, z_eof;
 106         int seekable;
 107         /* Indice where the source is seekable */
 108         int load_index;
 109         /* set has_index to 0 in mode 'w', then index will be discarded */
 110 } RAZF;
 111
 112 #ifdef __cplusplus
 113 extern "C" {
 114 #endif
 115
 116         RAZF* razf_dopen(int data_fd, const char *mode);
 117         RAZF *razf_open(const char *fn, const char *mode);
 118         int razf_write(RAZF* rz, const void *data, int size);
 119         int razf_read(RAZF* rz, void *data, int size);
 120         int64_t razf_seek(RAZF* rz, int64_t pos, int where);
 121         void razf_close(RAZF* rz);
 122
 123 #define razf_tell(rz) ((rz)->out)
 124
 125         RAZF* razf_open2(const char *filename, const char *mode);
 126         RAZF* razf_dopen2(int fd, const char *mode);
 127         uint64_t razf_tell2(RAZF *rz);
 128         int64_t razf_seek2(RAZF *rz, uint64_t voffset, int where);
 129
 130 #ifdef __cplusplus
 131 }
 132 #endif
 133
 134 #endif