/usr/include/io_lib/cram_io.h is in libstaden-read-dev 1.14.9-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 | /*
* Copyright (c) 2013, 2014, 2015 Genome Research Ltd.
* Author(s): James Bonfield
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials provided
* with the distribution.
*
* 3. Neither the names Genome Research Ltd and Wellcome Trust Sanger
* Institute nor the names of its contributors may be used to endorse
* or promote products derived from this software without specific
* prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY GENOME RESEARCH LTD AND CONTRIBUTORS "AS
* IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
* TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
* PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL GENOME RESEARCH
* LTD OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/*
* Author: James Bonfield, Wellcome Trust Sanger Institute. 2013
*/
/*! \file
* Include cram.h instead.
*
* This is an internal part of the CRAM system and is automatically included
* when you #include cram.h.
*
* Implements the low level CRAM I/O primitives.
* This includes basic data types such as byte, int, ITF-8,
* maps, bitwise I/O, etc.
*/
#ifndef _CRAM_IO_H_
#define _CRAM_IO_H_
#ifdef __cplusplus
extern "C" {
#endif
#define ITF8_MACROS
#include <stdint.h>
#include <io_lib/misc.h>
#include <io_lib/bam.h>
/**@{ ----------------------------------------------------------------------
* ITF8 encoding and decoding.
*
* Also see the itf8_get and itf8_put macros.
*/
/*! INTERNAL: Converts two characters into an integer for use in switch{} */
#define CRAM_KEY(a,b) (((a)<<8)|((b)))
/*! Reads an integer in ITF-8 encoding from 'fd' and stores it in
* *val.
*
* @return
* Returns the number of bytes read on success;
* -1 on failure
*/
int itf8_decode(cram_fd *fd, int32_t *val);
#ifndef ITF8_MACROS
/*! Reads an integer in ITF-8 encoding from 'cp' and stores it in
* *val.
*
* @return
* Returns the number of bytes read on success;
* -1 on failure
*/
int itf8_get(char *cp, int32_t *val_p);
/*! Stores a value to memory in ITF-8 format.
*
* @return
* Returns the number of bytes required to store the number.
* This is a maximum of 5 bytes.
*/
int itf8_put(char *cp, int32_t val);
#else
/*
* Macro implementations of the above
*/
#define itf8_get(c,v) (((uc)(c)[0]<0x80)?(*(v)=(uc)(c)[0],1):(((uc)(c)[0]<0xc0)?(*(v)=(((uc)(c)[0]<<8)|(uc)(c)[1])&0x3fff,2):(((uc)(c)[0]<0xe0)?(*(v)=(((uc)(c)[0]<<16)|((uc)(c)[1]<<8)|(uc)(c)[2])&0x1fffff,3):(((uc)(c)[0]<0xf0)?(*(v)=(((uc)(c)[0]<<24)|((uc)(c)[1]<<16)|((uc)(c)[2]<<8)|(uc)(c)[3])&0x0fffffff,4):(*(v)=(((uc)(c)[0]&0x0f)<<28)|((uc)(c)[1]<<20)|((uc)(c)[2]<<12)|((uc)(c)[3]<<4)|((uc)(c)[4]&0x0f),5)))))
#define itf8_put(c,v) ((!((v)&~0x7f))?((c)[0]=(v),1):(!((v)&~0x3fff))?((c)[0]=((v)>>8)|0x80,(c)[1]=(v)&0xff,2):(!((v)&~0x1fffff))?((c)[0]=((v)>>16)|0xc0,(c)[1]=((v)>>8)&0xff,(c)[2]=(v)&0xff,3):(!((v)&~0xfffffff))?((c)[0]=((v)>>24)|0xe0,(c)[1]=((v)>>16)&0xff,(c)[2]=((v)>>8)&0xff,(c)[3]=(v)&0xff,4):((c)[0]=0xf0|(((v)>>28)&0xff),(c)[1]=((v)>>20)&0xff,(c)[2]=((v)>>12)&0xff,(c)[3]=((v)>>4)&0xff,(c)[4]=(v)&0xf,5))
#define itf8_size(v) ((!((v)&~0x7f))?1:(!((v)&~0x3fff))?2:(!((v)&~0x1fffff))?3:(!((v)&~0xfffffff))?4:5)
#endif
int ltf8_put(char *cp, int64_t val);
/* Version of itf8_get that checks it hasn't run out of input */
extern const int itf8_bytes[16];
extern const int ltf8_bytes[256];
static inline int safe_itf8_get(const char *cp, const char *endp,
int32_t *val_p) {
const unsigned char *up = (unsigned char *)cp;
if (endp - cp < 5 &&
(cp >= endp || endp - cp < itf8_bytes[up[0]>>4])) {
*val_p = 0;
return 0;
}
if (up[0] < 0x80) {
*val_p = up[0];
return 1;
} else if (up[0] < 0xc0) {
*val_p = ((up[0] <<8) | up[1]) & 0x3fff;
return 2;
} else if (up[0] < 0xe0) {
*val_p = ((up[0]<<16) | (up[1]<< 8) | up[2]) & 0x1fffff;
return 3;
} else if (up[0] < 0xf0) {
*val_p = ((up[0]<<24) | (up[1]<<16) | (up[2]<<8) | up[3]) & 0x0fffffff;
return 4;
} else {
*val_p = ((up[0] & 0x0f)<<28) | (up[1]<<20) | (up[2]<<12) | (up[3]<<4) | (up[4] & 0x0f);
return 5;
}
}
static inline int safe_ltf8_get(const char *cp, const char *endp,
int64_t *val_p) {
unsigned char *up = (unsigned char *)cp;
if (endp - cp < 9 &&
(cp >= endp || endp - cp < ltf8_bytes[up[0]])) return 0;
if (up[0] < 0x80) {
*val_p = up[0];
return 1;
} else if (up[0] < 0xc0) {
*val_p = (((uint64_t)up[0]<< 8) |
(uint64_t)up[1]) & (((1LL<<(6+8)))-1);
return 2;
} else if (up[0] < 0xe0) {
*val_p = (((uint64_t)up[0]<<16) |
((uint64_t)up[1]<< 8) |
(uint64_t)up[2]) & ((1LL<<(5+2*8))-1);
return 3;
} else if (up[0] < 0xf0) {
*val_p = (((uint64_t)up[0]<<24) |
((uint64_t)up[1]<<16) |
((uint64_t)up[2]<< 8) |
(uint64_t)up[3]) & ((1LL<<(4+3*8))-1);
return 4;
} else if (up[0] < 0xf8) {
*val_p = (((uint64_t)up[0]<<32) |
((uint64_t)up[1]<<24) |
((uint64_t)up[2]<<16) |
((uint64_t)up[3]<< 8) |
(uint64_t)up[4]) & ((1LL<<(3+4*8))-1);
return 5;
} else if (up[0] < 0xfc) {
*val_p = (((uint64_t)up[0]<<40) |
((uint64_t)up[1]<<32) |
((uint64_t)up[2]<<24) |
((uint64_t)up[3]<<16) |
((uint64_t)up[4]<< 8) |
(uint64_t)up[5]) & ((1LL<<(2+5*8))-1);
return 6;
} else if (up[0] < 0xfe) {
*val_p = (((uint64_t)up[0]<<48) |
((uint64_t)up[1]<<40) |
((uint64_t)up[2]<<32) |
((uint64_t)up[3]<<24) |
((uint64_t)up[4]<<16) |
((uint64_t)up[5]<< 8) |
(uint64_t)up[6]) & ((1LL<<(1+6*8))-1);
return 7;
} else if (up[0] < 0xff) {
*val_p = (((uint64_t)up[1]<<48) |
((uint64_t)up[2]<<40) |
((uint64_t)up[3]<<32) |
((uint64_t)up[4]<<24) |
((uint64_t)up[5]<<16) |
((uint64_t)up[6]<< 8) |
(uint64_t)up[7]) & ((1LL<<(7*8))-1);
return 8;
} else {
*val_p = (((uint64_t)up[1]<<56) |
((uint64_t)up[2]<<48) |
((uint64_t)up[3]<<40) |
((uint64_t)up[4]<<32) |
((uint64_t)up[5]<<24) |
((uint64_t)up[6]<<16) |
((uint64_t)up[7]<< 8) |
(uint64_t)up[8]);
return 9;
}
}
/*! Pushes a value in ITF8 format onto the end of a block.
*
* This shouldn't be used for high-volume data as it is not the fastest
* method.
*
* @return
* Returns the number of bytes written
*/
int itf8_put_blk(cram_block *blk, int val);
/**@}*/
/**@{ ----------------------------------------------------------------------
* CRAM blocks - the dynamically growable data block. We have code to
* create, update, (un)compress and read/write.
*
* These are derived from the deflate_interlaced.c blocks, but with the
* CRAM extension of content types and IDs.
*/
/*! Allocates a new cram_block structure with a specified content_type and
* id.
*
* @return
* Returns block pointer on success;
* NULL on failure
*/
cram_block *cram_new_block(enum cram_content_type content_type,
int content_id);
/*! Reads a block from a cram file.
*
* @return
* Returns cram_block pointer on success;
* NULL on failure
*/
cram_block *cram_read_block(cram_fd *fd);
/*! Writes a CRAM block.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_write_block(cram_fd *fd, cram_block *b);
/*! Frees a CRAM block, deallocating internal data too.
*/
void cram_free_block(cram_block *b);
/*! Uncompresses a CRAM block, if compressed.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_uncompress_block(cram_block *b);
/*! Compresses a block.
*
* Compresses a block using one of two different zlib strategies. If we only
* want one choice set strat2 to be -1.
*
* The logic here is that sometimes Z_RLE does a better job than Z_FILTERED
* or Z_DEFAULT_STRATEGY on quality data. If so, we'd rather use it as it is
* significantly faster.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_compress_block(cram_fd *fd, cram_block *b, cram_metrics *metrics,
int method, int level);
cram_metrics *cram_new_metrics(void);
char *cram_block_method2str(enum cram_block_method m);
char *cram_content_type2str(enum cram_content_type t);
/*
* Find an external block by its content_id
*/
static inline cram_block *cram_get_block_by_id(cram_slice *slice, int id) {
if (slice->block_by_id && id >= 0 && id < 1024) {
return slice->block_by_id[id];
} else {
int i;
for (i = 0; i < slice->hdr->num_blocks; i++) {
cram_block *b = slice->block[i];
if (b && b->content_type == EXTERNAL && b->content_id == id)
return b;
}
}
return NULL;
}
/* --- Accessor macros for manipulating blocks on a byte by byte basis --- */
/* Block size and data pointer. */
#define BLOCK_SIZE(b) ((b)->byte)
#define BLOCK_DATA(b) ((b)->data)
/* Returns the address one past the end of the block */
#define BLOCK_END(b) (&(b)->data[(b)->byte])
/* Request block to be at least 'l' bytes long */
#define BLOCK_RESIZE(b,l) \
do { \
while((b)->alloc <= (l)) { \
(b)->alloc = (b)->alloc ? (b)->alloc*1.5 : 1024; \
(b)->data = realloc((b)->data, (b)->alloc); \
} \
} while(0)
/* Make block exactly 'l' bytes long */
#define BLOCK_RESIZE_EXACT(b,l) \
do { \
(b)->alloc = (l); \
(b)->data = realloc((b)->data, (b)->alloc); \
} while(0)
/* Ensure the block can hold at least another 'l' bytes */
#define BLOCK_GROW(b,l) BLOCK_RESIZE((b), BLOCK_SIZE((b)) + (l))
/* Append string 's' of length 'l' */
#define BLOCK_APPEND(b,s,l) \
do { \
BLOCK_GROW((b),(l)); \
memcpy(BLOCK_END((b)), (s), (l)); \
BLOCK_SIZE((b)) += (l); \
} while (0)
/* Append as single character 'c' */
#define BLOCK_APPEND_CHAR(b,c) \
do { \
BLOCK_GROW((b),1); \
(b)->data[(b)->byte++] = (c); \
} while (0)
/* Append a single unsigned integer */
#define BLOCK_APPEND_UINT(b,i) \
do { \
unsigned char *cp; \
BLOCK_GROW((b),11); \
cp = &(b)->data[(b)->byte]; \
(b)->byte += append_uint(cp, (i)) - cp; \
} while (0)
static inline unsigned char *append_uint32(unsigned char *cp, uint32_t i) {
uint32_t j;
if (i == 0) {
*cp++ = '0';
return cp;
}
if (i < 100) goto b1;
if (i < 10000) goto b3;
if (i < 1000000) goto b5;
if (i < 100000000) goto b7;
if ((j = i / 1000000000)) {*cp++ = j + '0'; i -= j*1000000000; goto x8;}
if ((j = i / 100000000)) {*cp++ = j + '0'; i -= j*100000000; goto x7;}
b7:if ((j = i / 10000000)) {*cp++ = j + '0'; i -= j*10000000; goto x6;}
if ((j = i / 1000000)) {*cp++ = j + '0', i -= j*1000000; goto x5;}
b5:if ((j = i / 100000)) {*cp++ = j + '0', i -= j*100000; goto x4;}
if ((j = i / 10000)) {*cp++ = j + '0', i -= j*10000; goto x3;}
b3:if ((j = i / 1000)) {*cp++ = j + '0', i -= j*1000; goto x2;}
if ((j = i / 100)) {*cp++ = j + '0', i -= j*100; goto x1;}
b1:if ((j = i / 10)) {*cp++ = j + '0', i -= j*10; goto x0;}
if (i) *cp++ = i + '0';
return cp;
x8: *cp++ = i / 100000000 + '0', i %= 100000000;
x7: *cp++ = i / 10000000 + '0', i %= 10000000;
x6: *cp++ = i / 1000000 + '0', i %= 1000000;
x5: *cp++ = i / 100000 + '0', i %= 100000;
x4: *cp++ = i / 10000 + '0', i %= 10000;
x3: *cp++ = i / 1000 + '0', i %= 1000;
x2: *cp++ = i / 100 + '0', i %= 100;
x1: *cp++ = i / 10 + '0', i %= 10;
x0: *cp++ = i + '0';
return cp;
}
static inline unsigned char *append_sub32(unsigned char *cp, uint32_t i) {
*cp++ = i / 100000000 + '0', i %= 100000000;
*cp++ = i / 10000000 + '0', i %= 10000000;
*cp++ = i / 1000000 + '0', i %= 1000000;
*cp++ = i / 100000 + '0', i %= 100000;
*cp++ = i / 10000 + '0', i %= 10000;
*cp++ = i / 1000 + '0', i %= 1000;
*cp++ = i / 100 + '0', i %= 100;
*cp++ = i / 10 + '0', i %= 10;
*cp++ = i + '0';
return cp;
}
static inline unsigned char *append_uint64(unsigned char *cp, uint64_t i) {
uint64_t j;
if (i <= 0xffffffff)
return append_uint32(cp, i);
if ((j = i/1000000000) > 1000000000) {
cp = append_uint32(cp, j/1000000000);
j %= 1000000000;
cp = append_sub32(cp, j);
} else {
cp = append_uint32(cp, i / 1000000000);
}
cp = append_sub32(cp, i % 1000000000);
return cp;
}
#define BLOCK_UPLEN(b) \
(b)->comp_size = (b)->uncomp_size = BLOCK_SIZE((b))
/**@}*/
/**@{ ----------------------------------------------------------------------
* Reference sequence handling
*/
/*! Loads a reference set from fn and stores in the cram_fd.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_load_reference(cram_fd *fd, char *fn);
/*! Generates a lookup table in refs based on the SQ headers in SAM_hdr.
*
* Indexes references by the order they appear in a BAM file. This may not
* necessarily be the same order they appear in the fasta reference file.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int refs2id(refs_t *r, SAM_hdr *bfd);
refs_t *refs_load_fai(refs_t *r_orig, char *fn, int is_err);
char *load_ref_portion(bzi_FILE *fp, ref_entry *e, int start, int end);
void refs_free(refs_t *r);
/*! Returns a portion of a reference sequence from start to end inclusive.
*
* The returned pointer is owned by the cram_file fd and should not be freed
* by the caller. It is valid only until the next cram_get_ref is called
* with the same fd parameter (so is thread-safe if given multiple files).
*
* To return the entire reference sequence, specify start as 1 and end
* as 0.
*
* @return
* Returns reference on success;
* NULL on failure
*/
char *cram_get_ref(cram_fd *fd, int id, int start, int end);
void cram_ref_incr(refs_t *r, int id);
void cram_ref_decr(refs_t *r, int id);
/**@}*/
/**@{ ----------------------------------------------------------------------
* Containers
*/
/*! Creates a new container, specifying the maximum number of slices
* and records permitted.
*
* @return
* Returns cram_container ptr on success;
* NULL on failure
*/
cram_container *cram_new_container(int nrec, int nslice);
void cram_free_container(cram_container *c);
/*! Reads a container header.
*
* @return
* Returns cram_container on success;
* NULL on failure or no container left (fd->err == 0).
*/
cram_container *cram_read_container(cram_fd *fd);
/*! Writes a container structure.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_write_container(cram_fd *fd, cram_container *h);
/*! Flushes a container to disk.
*
* Flushes a completely or partially full container to disk, writing
* container structure, header and blocks. This also calls the encoder
* functions.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_flush_container(cram_fd *fd, cram_container *c);
int cram_flush_container_mt(cram_fd *fd, cram_container *c);
/**@}*/
/**@{ ----------------------------------------------------------------------
* Compression headers; the first part of the container
*/
/*! Creates a new blank container compression header
*
* @return
* Returns header ptr on success;
* NULL on failure
*/
cram_block_compression_hdr *cram_new_compression_header(void);
/*! Frees a cram_block_compression_hdr */
void cram_free_compression_header(cram_block_compression_hdr *hdr);
/**@}*/
/**@{ ----------------------------------------------------------------------
* Slices and slice headers
*/
/*! Frees a slice header */
void cram_free_slice_header(cram_block_slice_hdr *hdr);
/*! Frees a slice */
void cram_free_slice(cram_slice *s);
/*! Creates a new empty slice in memory, for subsequent writing to
* disk.
*
* @return
* Returns cram_slice ptr on success;
* NULL on failure
*/
cram_slice *cram_new_slice(enum cram_content_type type, int nrecs);
/*! Loads an entire slice.
*
* FIXME: In 1.0 the native unit of slices within CRAM is broken
* as slices contain references to objects in other slices.
* To work around this while keeping the slice oriented outer loop
* we read all slices and stitch them together into a fake large
* slice instead.
*
* @return
* Returns cram_slice ptr on success;
* NULL on failure
*/
cram_slice *cram_read_slice(cram_fd *fd);
/**@}*/
/**@{ ----------------------------------------------------------------------
* CRAM file definition (header)
*/
/*! Reads a CRAM file definition structure.
*
* @return
* Returns file_def ptr on success;
* NULL on failure
*/
cram_file_def *cram_read_file_def(cram_fd *fd);
/*! Writes a cram_file_def structure to cram_fd.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_write_file_def(cram_fd *fd, cram_file_def *def);
/*! Frees a cram_file_def structure. */
void cram_free_file_def(cram_file_def *def);
/**@}*/
/**@{ ----------------------------------------------------------------------
* SAM header I/O
*/
/*! Reads the SAM header from the first CRAM data block.
*
* Also performs minimal parsing to extract read-group
* and sample information.
*
* @return
* Returns SAM hdr ptr on success;
* NULL on failure
*/
SAM_hdr *cram_read_SAM_hdr(cram_fd *fd);
/*! Writes a CRAM SAM header.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_write_SAM_hdr(cram_fd *fd, SAM_hdr *hdr);
/**@}*/
/**@{ ----------------------------------------------------------------------
* The top-level cram opening, closing and option handling
*/
/*! Opens a CRAM file for read (mode "rb") or write ("wb").
*
* The filename may be "-" to indicate stdin or stdout.
*
* @return
* Returns file handle on success;
* NULL on failure.
*/
cram_fd *cram_open(const char *filename, const char *mode);
/*! Closes a CRAM file.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_close(cram_fd *fd);
/*
* Flushes a CRAM file.
* Useful for when writing to stdout without wishing to close the stream.
*
* Returns 0 on success
* -1 on failure
*/
int cram_flush(cram_fd *fd);
/*
* Writes an EOF block to a CRAM file.
*
* Returns 0 on success
* -1 on failure
*/
int cram_write_eof_block(cram_fd *fd);
/*! Checks for end of file on a cram_fd stream.
*
* @return
* Returns 0 if not at end of file
* 1 if we hit an expected EOF (end of range or EOF block)
* 2 for other EOF (end of stream without EOF block)
*/
int cram_eof(cram_fd *fd);
/*! Sets options on the cram_fd.
*
* See CRAM_OPT_* definitions in cram_structs.h.
* Use this immediately after opening.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_set_option(cram_fd *fd, enum cram_option opt, ...);
/*! Sets options on the cram_fd.
*
* See CRAM_OPT_* definitions in cram_structs.h.
* Use this immediately after opening.
*
* @return
* Returns 0 on success;
* -1 on failure
*/
int cram_set_voption(cram_fd *fd, enum cram_option opt, va_list args);
#if defined(CRAM_IO_CUSTOM_BUFFERING)
/*
* Opens a CRAM file for input via callbacks
*
* Returns file handle on success
* NULL on failure.
*/
extern cram_fd *cram_open_by_callbacks(
char const * filename,
cram_io_allocate_read_input_t callback_allocate_function,
cram_io_deallocate_read_input_t callback_deallocate_function,
size_t const bufsize
);
extern cram_fd * cram_openw_by_callbacks(
char const * filename,
cram_io_allocate_write_output_t callback_allocate_function,
cram_io_deallocate_write_output_t callback_deallocate_function,
size_t const bufsize
);
extern cram_fd * cram_io_open(
char const * filename,
char const * mode,
char const * fmode
);
extern cram_fd * cram_io_open_by_callbacks(
char const * filename,
cram_io_allocate_read_input_t callback_allocate_function,
cram_io_deallocate_read_input_t callback_deallocate_function,
size_t const bufsize,
int const decompress
);
extern cram_fd * cram_io_openw_by_callbacks(
char const * filename,
cram_io_allocate_write_output_t callback_allocate_function,
cram_io_deallocate_write_output_t callback_deallocate_function,
size_t const bufsize
);
extern cram_fd * cram_io_close(cram_fd * fd, int * fclose_result);
extern cram_fd_output_buffer *
cram_io_deallocate_output_buffer(cram_fd_output_buffer * buffer);
extern cram_fd_output_buffer *
cram_io_allocate_output_buffer(size_t const bufsize);
#endif
char *zlib_mem_inflate(char *cdata, size_t csize, size_t *size);
/**@}*/
#ifdef __cplusplus
}
#endif
#endif /* _CRAM_IO_H_ */
|