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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188
|
# cython: embedsignature=True
# cython: profile=True
###############################################################################
###############################################################################
# Cython wrapper for access to tabix indexed files in bgzf format
###############################################################################
# The principal classes and functions defined in this module are:
#
# class TabixFile class wrapping tabix indexed files in bgzf format
#
# class asTuple Parser class for tuples
# class asGT Parser class for GTF formatted rows
# class asBed Parser class for Bed formatted rows
# class asVCF Parser class for VCF formatted rows
#
# class tabix_generic_iterator Streamed iterator of bgzf formatted files
#
# Additionally this module defines several additional classes that are part
# of the internal API. These are:
#
# class Parser base class for parsers of tab-separated rows
# class tabix_file_iterator
# class TabixIterator iterator class over rows in bgzf file
# class EmptyIterator
#
# For backwards compatibility, the following classes are also defined:
#
# class Tabixfile equivalent to TabixFile
#
###############################################################################
#
# The MIT License
#
# Copyright (c) 2015 Andreas Heger
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
#
###############################################################################
import os
import sys
from libc.stdio cimport printf, fprintf, stderr
from libc.string cimport strerror
from libc.errno cimport errno
from posix.unistd cimport dup
from cpython cimport PyErr_SetString, PyBytes_Check, \
PyUnicode_Check, PyBytes_FromStringAndSize, \
PyObject_AsFileDescriptor
from cpython.version cimport PY_MAJOR_VERSION
cimport pysam.libctabixproxies as ctabixproxies
from pysam.libchtslib cimport htsFile, hts_open, hts_close, HTS_IDX_START,\
BGZF, bgzf_open, bgzf_dopen, bgzf_close, bgzf_write, \
tbx_index_build, tbx_index_load, tbx_itr_queryi, tbx_itr_querys, \
tbx_conf_t, tbx_seqnames, tbx_itr_next, tbx_itr_destroy, \
tbx_destroy, hisremote, region_list
from pysam.libcutils cimport force_bytes, force_str, charptr_to_str
from pysam.libcutils cimport encode_filename, from_string_and_size
cdef class Parser:
def __init__(self, encoding="ascii"):
self.encoding = encoding
def set_encoding(self, encoding):
self.encoding = encoding
def get_encoding(self):
return self.encoding
cdef parse(self, char * buffer, int length):
raise NotImplementedError(
'parse method of %s not implemented' % str(self))
def __call__(self, char * buffer, int length):
return self.parse(buffer, length)
cdef class asTuple(Parser):
'''converts a :term:`tabix row` into a python tuple.
A field in a row is accessed by numeric index.
'''
cdef parse(self, char * buffer, int len):
cdef ctabixproxies.TupleProxy r
r = ctabixproxies.TupleProxy(self.encoding)
# need to copy - there were some
# persistence issues with "present"
r.copy(buffer, len)
return r
cdef class asGTF(Parser):
'''converts a :term:`tabix row` into a GTF record with the following
fields:
+----------+----------+-------------------------------+
|*Column* |*Name* |*Content* |
+----------+----------+-------------------------------+
|1 |contig |the chromosome name |
+----------+----------+-------------------------------+
|2 |feature |The feature type |
+----------+----------+-------------------------------+
|3 |source |The feature source |
+----------+----------+-------------------------------+
|4 |start |genomic start coordinate |
| | |(0-based) |
+----------+----------+-------------------------------+
|5 |end |genomic end coordinate |
| | |(0-based) |
+----------+----------+-------------------------------+
|6 |score |feature score |
+----------+----------+-------------------------------+
|7 |strand |strand |
+----------+----------+-------------------------------+
|8 |frame |frame |
+----------+----------+-------------------------------+
|9 |attributes|the attribute field |
+----------+----------+-------------------------------+
GTF formatted entries also define the following fields that
are derived from the attributes field:
+--------------------+------------------------------+
|*Name* |*Content* |
+--------------------+------------------------------+
|gene_id |the gene identifier |
+--------------------+------------------------------+
|transcript_id |the transcript identifier |
+--------------------+------------------------------+
'''
cdef parse(self, char * buffer, int len):
cdef ctabixproxies.GTFProxy r
r = ctabixproxies.GTFProxy(self.encoding)
r.copy(buffer, len)
return r
cdef class asBed(Parser):
'''converts a :term:`tabix row` into a bed record
with the following fields:
+-----------+-----------+------------------------------------------+
|*Column* |*Field* |*Contents* |
| | | |
+-----------+-----------+------------------------------------------+
|1 |contig |contig |
| | | |
+-----------+-----------+------------------------------------------+
|2 |start |genomic start coordinate (zero-based) |
+-----------+-----------+------------------------------------------+
|3 |end |genomic end coordinate plus one |
| | |(zero-based) |
+-----------+-----------+------------------------------------------+
|4 |name |name of feature. |
+-----------+-----------+------------------------------------------+
|5 |score |score of feature |
+-----------+-----------+------------------------------------------+
|6 |strand |strand of feature |
+-----------+-----------+------------------------------------------+
|7 |thickStart |thickStart |
+-----------+-----------+------------------------------------------+
|8 |thickEnd |thickEnd |
+-----------+-----------+------------------------------------------+
|9 |itemRGB |itemRGB |
+-----------+-----------+------------------------------------------+
|10 |blockCount |number of bocks |
+-----------+-----------+------------------------------------------+
|11 |blockSizes |',' separated string of block sizes |
+-----------+-----------+------------------------------------------+
|12 |blockStarts|',' separated string of block genomic |
| | |start positions |
+-----------+-----------+------------------------------------------+
Only the first three fields are required. Additional
fields are optional, but if one is defined, all the preceding
need to be defined as well.
'''
cdef parse(self, char * buffer, int len):
cdef ctabixproxies.BedProxy r
r = ctabixproxies.BedProxy(self.encoding)
r.copy(buffer, len)
return r
cdef class asVCF(Parser):
'''converts a :term:`tabix row` into a VCF record with
the following fields:
+----------+---------+------------------------------------+
|*Column* |*Field* |*Contents* |
| | | |
+----------+---------+------------------------------------+
|1 |contig |chromosome |
+----------+---------+------------------------------------+
|2 |pos |chromosomal position, zero-based |
+----------+---------+------------------------------------+
|3 |id |id |
+----------+---------+------------------------------------+
|4 |ref |reference allele |
+----------+---------+------------------------------------+
|5 |alt |alternate alleles |
+----------+---------+------------------------------------+
|6 |qual |quality |
+----------+---------+------------------------------------+
|7 |filter |filter |
+----------+---------+------------------------------------+
|8 |info |info |
+----------+---------+------------------------------------+
|9 |format |format specifier. |
+----------+---------+------------------------------------+
Access to genotypes is via index::
contig = vcf.contig
first_sample_genotype = vcf[0]
second_sample_genotype = vcf[1]
'''
cdef parse(self, char * buffer, int len):
cdef ctabixproxies.VCFProxy r
r = ctabixproxies.VCFProxy(self.encoding)
r.copy(buffer, len)
return r
cdef class TabixFile:
"""Random access to bgzf formatted files that
have been indexed by :term:`tabix`.
The file is automatically opened. The index file of file
``<filename>`` is expected to be called ``<filename>.tbi``
by default (see parameter `index`).
Parameters
----------
filename : string
Filename of bgzf file to be opened.
index : string
The filename of the index. If not set, the default is to
assume that the index is called ``filename.tbi`
mode : char
The file opening mode. Currently, only ``r`` is permitted.
parser : :class:`pysam.Parser`
sets the default parser for this tabix file. If `parser`
is None, the results are returned as an unparsed string.
Otherwise, `parser` is assumed to be a functor that will return
parsed data (see for example :class:`~pysam.asTuple` and
:class:`~pysam.asGTF`).
encoding : string
The encoding passed to the parser
Raises
------
ValueError
if index file is missing.
IOError
if file could not be opened
"""
def __cinit__(self,
filename,
mode='r',
parser=None,
index=None,
encoding="ascii",
*args,
**kwargs ):
self.htsfile = NULL
self.is_remote = False
self.is_stream = False
self.parser = parser
self._open(filename, mode, index, *args, **kwargs)
self.encoding = encoding
def _open( self,
filename,
mode='r',
index=None,
):
'''open a :term:`tabix file` for reading.'''
if mode != 'r':
raise ValueError("invalid file opening mode `%s`" % mode)
if self.htsfile != NULL:
self.close()
self.htsfile = NULL
filename_index = index or (filename + ".tbi")
# encode all the strings to pass to tabix
self.filename = encode_filename(filename)
self.filename_index = encode_filename(filename_index)
self.is_stream = self.filename == b'-'
self.is_remote = hisremote(self.filename)
if not self.is_remote:
if not os.path.exists(filename):
raise IOError("file `%s` not found" % filename)
if not os.path.exists(filename_index):
raise IOError("index `%s` not found" % filename_index)
# open file
cdef char *cfilename = self.filename
with nogil:
self.htsfile = hts_open(cfilename, 'r')
if self.htsfile == NULL:
raise IOError("could not open file `%s`" % filename)
#if self.htsfile.format.category != region_list:
# raise ValueError("file does not contain region data")
cfilename = self.filename_index
with nogil:
self.index = tbx_index_load(cfilename)
if self.index == NULL:
raise IOError("could not open index for `%s`" % filename)
if not self.is_stream:
self.start_offset = self.tell()
def _dup(self):
'''return a copy of this tabix file.
The file is being re-opened.
'''
return TabixFile(self.filename,
mode="r",
parser=self.parser,
index=self.filename_index,
encoding=self.encoding)
def fetch(self,
reference=None,
start=None,
end=None,
region=None,
parser=None,
multiple_iterators=False):
'''fetch one or more rows in a :term:`region` using 0-based
indexing. The region is specified by :term:`reference`,
*start* and *end*. Alternatively, a samtools :term:`region`
string can be supplied.
Without *reference* or *region* all entries will be fetched.
If only *reference* is set, all reads matching on *reference*
will be fetched.
If *parser* is None, the default parser will be used for
parsing.
Set *multiple_iterators* to true if you will be using multiple
iterators on the same file at the same time. The iterator
returned will receive its own copy of a filehandle to the file
effectively re-opening the file. Re-opening a file creates
some overhead, so beware.
'''
if not self.is_open():
raise ValueError("I/O operation on closed file")
# convert coordinates to region string, which is one-based
if reference:
if end is not None:
if end < 0:
raise ValueError("end out of range (%i)" % end)
if start is None:
start = 0
if start < 0:
raise ValueError("start out of range (%i)" % end)
elif start > end:
raise ValueError(
'start (%i) >= end (%i)' % (start, end))
elif start == end:
return EmptyIterator()
else:
region = '%s:%i-%i' % (reference, start + 1, end)
elif start is not None:
if start < 0:
raise ValueError("start out of range (%i)" % end)
region = '%s:%i' % (reference, start + 1)
else:
region = reference
# get iterator
cdef hts_itr_t * itr
cdef char *cstr
cdef TabixFile fileobj
# reopen the same file if necessary
if multiple_iterators:
fileobj = self._dup()
else:
fileobj = self
if region is None:
# without region or reference - iterate from start
with nogil:
itr = tbx_itr_queryi(fileobj.index,
HTS_IDX_START,
0,
0)
else:
s = force_bytes(region, encoding=fileobj.encoding)
cstr = s
with nogil:
itr = tbx_itr_querys(fileobj.index, cstr)
if itr == NULL:
if region is None:
if len(self.contigs) > 0:
# when accessing a tabix file created prior tabix 1.0
# the full-file iterator is empty.
raise ValueError(
"could not create iterator, possible "
"tabix version mismatch")
else:
# possible reason is that the file is empty -
# return an empty iterator
return EmptyIterator()
else:
raise ValueError(
"could not create iterator for region '%s'" %
region)
# use default parser if no parser is specified
if parser is None:
parser = fileobj.parser
cdef TabixIterator a
if parser is None:
a = TabixIterator(encoding=fileobj.encoding)
else:
parser.set_encoding(fileobj.encoding)
a = TabixIteratorParsed(parser)
a.tabixfile = fileobj
a.iterator = itr
return a
###############################################################
###############################################################
###############################################################
## properties
###############################################################
property header:
'''the file header.
The file header consists of the lines at the beginning of a
file that are prefixed by the comment character ``#``.
.. note::
The header is returned as an iterator presenting lines
without the newline character.
.. note::
The header is only available for local files. For remote
files an Attribute Error is raised.
'''
def __get__(self):
if self.is_remote:
raise AttributeError(
"the header is not available for remote files")
return GZIteratorHead(self.filename)
property contigs:
'''list of chromosome names'''
def __get__(self):
cdef char ** sequences
cdef int nsequences
with nogil:
sequences = tbx_seqnames(self.index, &nsequences)
cdef int x
result = []
for x from 0 <= x < nsequences:
result.append(force_str(sequences[x]))
# htslib instructions:
# only free container, not the sequences themselves
free(sequences)
return result
def close(self):
'''
closes the :class:`pysam.TabixFile`.'''
if self.htsfile != NULL:
hts_close(self.htsfile)
self.htsfile = NULL
if self.index != NULL:
tbx_destroy(self.index)
self.index = NULL
def __dealloc__( self ):
# remember: dealloc cannot call other python methods
# note: no doc string
# note: __del__ is not called.
if self.htsfile != NULL:
hts_close(self.htsfile)
self.htsfile = NULL
if self.index != NULL:
tbx_destroy(self.index)
cdef class TabixIterator:
"""iterates over rows in *tabixfile* in region
given by *tid*, *start* and *end*.
"""
def __init__(self, encoding="ascii"):
self.encoding = encoding
def __iter__(self):
self.buffer.s = NULL
self.buffer.l = 0
self.buffer.m = 0
return self
cdef int __cnext__(self):
'''iterate to next element.
Return -5 if file has been closed when this function
was called.
'''
if self.tabixfile.htsfile == NULL:
return -5
cdef int retval
while 1:
with nogil:
retval = tbx_itr_next(
self.tabixfile.htsfile,
self.tabixfile.index,
self.iterator,
&self.buffer)
if retval < 0:
break
if self.buffer.s[0] != '#':
break
return retval
def __next__(self):
"""python version of next().
pyrex uses this non-standard name instead of next()
"""
cdef int retval = self.__cnext__()
if retval == -5:
raise IOError("iteration on closed file")
elif retval < 0:
raise StopIteration
return charptr_to_str(self.buffer.s, self.encoding)
def next(self):
return self.__next__()
def __dealloc__(self):
if <void*>self.iterator != NULL:
tbx_itr_destroy(self.iterator)
if self.buffer.s != NULL:
free(self.buffer.s)
class EmptyIterator:
'''empty iterator'''
def __iter__(self):
return self
def next(self):
raise StopIteration()
def __next__(self):
raise StopIteration()
cdef class TabixIteratorParsed(TabixIterator):
"""iterates over mapped reads in a region.
The *parser* determines the encoding.
Returns parsed data.
"""
def __init__(self,
Parser parser):
TabixIterator.__init__(self)
self.parser = parser
def __next__(self):
"""python version of next().
pyrex uses this non-standard name instead of next()
"""
cdef int retval = self.__cnext__()
if retval == -5:
raise IOError("iteration on closed file")
elif retval < 0:
raise StopIteration
return self.parser.parse(self.buffer.s,
self.buffer.l)
cdef class GZIterator:
def __init__(self, filename, int buffer_size=65536, encoding="ascii"):
'''iterate line-by-line through gzip (or bgzip)
compressed file.
'''
if not os.path.exists(filename):
raise IOError("No such file or directory: %s" % filename)
filename = encode_filename(filename)
cdef char *cfilename = filename
with nogil:
self.gzipfile = bgzf_open(cfilename, "r")
self._filename = filename
self.kstream = ks_init(self.gzipfile)
self.encoding = encoding
self.buffer.l = 0
self.buffer.m = 0
self.buffer.s = <char*>malloc(buffer_size)
def __dealloc__(self):
'''close file.'''
if self.gzipfile != NULL:
bgzf_close(self.gzipfile)
self.gzipfile = NULL
if self.buffer.s != NULL:
free(self.buffer.s)
if self.kstream != NULL:
ks_destroy(self.kstream)
def __iter__(self):
return self
cdef int __cnext__(self):
cdef int dret = 0
cdef int retval = 0
while 1:
with nogil:
retval = ks_getuntil(self.kstream, '\n', &self.buffer, &dret)
if retval < 0:
break
return dret
return -1
def __next__(self):
"""python version of next().
"""
cdef int retval = self.__cnext__()
if retval < 0:
raise StopIteration
return force_str(self.buffer.s, self.encoding)
cdef class GZIteratorHead(GZIterator):
'''iterate line-by-line through gzip (or bgzip)
compressed file returning comments at top of file.
'''
def __next__(self):
"""python version of next().
"""
cdef int retval = self.__cnext__()
if retval < 0:
raise StopIteration
if self.buffer.s[0] == '#':
return self.buffer.s
else:
raise StopIteration
cdef class GZIteratorParsed(GZIterator):
'''iterate line-by-line through gzip (or bgzip)
compressed file returning comments at top of file.
'''
def __init__(self, parser):
self.parser = parser
def __next__(self):
"""python version of next().
"""
cdef int retval = self.__cnext__()
if retval < 0:
raise StopIteration
return self.parser.parse(self.buffer.s,
self.buffer.l)
def tabix_compress(filename_in,
filename_out,
force=False):
'''compress *filename_in* writing the output to *filename_out*.
Raise an IOError if *filename_out* already exists, unless *force*
is set.
'''
if not force and os.path.exists(filename_out):
raise IOError(
"Filename '%s' already exists, use *force* to "
"overwrite" % filename_out)
cdef int WINDOW_SIZE
cdef int c, r
cdef void * buffer
cdef BGZF * fp
cdef int fd_src
cdef bint is_empty = True
cdef int O_RDONLY
O_RDONLY = os.O_RDONLY
WINDOW_SIZE = 64 * 1024
fn = encode_filename(filename_out)
cdef char *cfn = fn
with nogil:
fp = bgzf_open(cfn, "w")
if fp == NULL:
raise IOError("could not open '%s' for writing" % filename_out)
fn = encode_filename(filename_in)
fd_src = open(fn, O_RDONLY)
if fd_src == 0:
raise IOError("could not open '%s' for reading" % filename_in)
buffer = malloc(WINDOW_SIZE)
c = 1
while c > 0:
with nogil:
c = read(fd_src, buffer, WINDOW_SIZE)
if c > 0:
is_empty = False
r = bgzf_write(fp, buffer, c)
if r < 0:
free(buffer)
raise OSError("writing failed")
free(buffer)
r = bgzf_close(fp)
if r < 0:
raise OSError("error %i when writing to file %s" % (r, filename_out))
r = close(fd_src)
# an empty file will return with -1, thus ignore this.
if r < 0:
if not (r == -1 and is_empty):
raise OSError("error %i when closing file %s" % (r, filename_in))
def tabix_index( filename,
force = False,
seq_col = None,
start_col = None,
end_col = None,
preset = None,
meta_char = "#",
zerobased = False,
int min_shift = -1,
):
'''index tab-separated *filename* using tabix.
An existing index will not be overwritten unless
*force* is set.
The index will be built from coordinates
in columns *seq_col*, *start_col* and *end_col*.
The contents of *filename* have to be sorted by
contig and position - the method does not check
if the file is sorted.
Column indices are 0-based. Coordinates in the file
are assumed to be 1-based.
If *preset* is provided, the column coordinates
are taken from a preset. Valid values for preset
are "gff", "bed", "sam", "vcf", psltbl", "pileup".
Lines beginning with *meta_char* and the first
*line_skip* lines will be skipped.
If *filename* does not end in ".gz", it will be automatically
compressed. The original file will be removed and only the
compressed file will be retained.
If *filename* ends in *gz*, the file is assumed to be already
compressed with bgzf.
*min-shift* sets the minimal interval size to 1<<INT; 0 for the
old tabix index. The default of -1 is changed inside htslib to
the old tabix default of 0.
returns the filename of the compressed data
'''
if not os.path.exists(filename):
raise IOError("No such file '%s'" % filename)
if preset is None and \
(seq_col is None or start_col is None or end_col is None):
raise ValueError(
"neither preset nor seq_col,start_col and end_col given")
if not filename.endswith(".gz"):
tabix_compress(filename, filename + ".gz", force=force)
os.unlink( filename )
filename += ".gz"
if not force and os.path.exists(filename + ".tbi"):
raise IOError(
"Filename '%s.tbi' already exists, use *force* to overwrite")
# columns (1-based):
# preset-code, contig, start, end, metachar for
# comments, lines to ignore at beginning
# 0 is a missing column
preset2conf = {
'gff' : (0, 1, 4, 5, ord('#'), 0),
'bed' : (0x10000, 1, 2, 3, ord('#'), 0),
'psltbl' : (0x10000, 15, 17, 18, ord('#'), 0),
'sam' : (1, 3, 4, 0, ord('@'), 0),
'vcf' : (2, 1, 2, 0, ord('#'), 0),
'pileup': (3, 1, 2, 0, ord('#'), 0),
}
if preset:
try:
conf_data = preset2conf[preset]
except KeyError:
raise KeyError(
"unknown preset '%s', valid presets are '%s'" %
(preset, ",".join(preset2conf.keys())))
else:
if end_col == None:
end_col = -1
preset = 0
# note that tabix internally works with 0-based coordinates
# and open/closed intervals. When using a preset, conversion
# is automatically taken care of. Otherwise, the coordinates
# are assumed to be 1-based closed intervals and -1 is
# subtracted from the start coordinate. To avoid doing this,
# set the TI_FLAG_UCSC=0x10000 flag:
if zerobased:
preset = preset | 0x10000
conf_data = (preset, seq_col+1, start_col+1, end_col+1, ord(meta_char), 0)
cdef tbx_conf_t conf
conf.preset, conf.sc, conf.bc, conf.ec, conf.meta_char, conf.line_skip = conf_data
fn = encode_filename(filename)
cdef char *cfn = fn
with nogil:
tbx_index_build(cfn, min_shift, &conf)
return filename
# #########################################################
# cdef class tabix_file_iterator_old:
# '''iterate over ``infile``.
# This iterator is not safe. If the :meth:`__next__()` method is called
# after ``infile`` is closed, the result is undefined (see ``fclose()``).
# The iterator might either raise a StopIteration or segfault.
# '''
# def __cinit__(self,
# infile,
# Parser parser,
# int buffer_size = 65536 ):
# cdef int fd = PyObject_AsFileDescriptor( infile )
# if fd == -1: raise ValueError( "I/O operation on closed file." )
# self.infile = fdopen( fd, 'r')
# if self.infile == NULL: raise ValueError( "I/O operation on closed file." )
# self.buffer = <char*>malloc( buffer_size )
# self.size = buffer_size
# self.parser = parser
# def __iter__(self):
# return self
# cdef __cnext__(self):
# cdef char * b
# cdef size_t nbytes
# b = self.buffer
# while not feof( self.infile ):
# nbytes = getline( &b, &self.size, self.infile)
# # stop at first error or eof
# if (nbytes == -1): break
# # skip comments
# if (b[0] == '#'): continue
# # skip empty lines
# if b[0] == '\0' or b[0] == '\n' or b[0] == '\r': continue
# # make sure that entry is complete
# if b[nbytes-1] != '\n' and b[nbytes-1] != '\r':
# result = b
# raise ValueError( "incomplete line at %s" % result )
# # make sure that this goes fully through C
# # otherwise buffer is copied to/from a
# # Python object causing segfaults as
# # the wrong memory is freed
# return self.parser.parse( b, nbytes )
# raise StopIteration
# def __dealloc__(self):
# free(self.buffer)
# def __next__(self):
# return self.__cnext__()
#########################################################
#########################################################
#########################################################
## Iterators for parsing through unindexed files.
#########################################################
# cdef buildGzipError(void *gzfp):
# cdef int errnum = 0
# cdef char *s = gzerror(gzfp, &errnum)
# return "error (%d): %s (%d: %s)" % (errno, strerror(errno), errnum, s)
cdef class tabix_file_iterator:
'''iterate over a compressed or uncompressed ``infile``.
'''
def __cinit__(self,
infile,
Parser parser,
int buffer_size=65536):
if infile.closed:
raise ValueError("I/O operation on closed file.")
self.infile = infile
cdef int fd = PyObject_AsFileDescriptor(infile)
if fd == -1:
raise ValueError("I/O operation on closed file.")
self.duplicated_fd = dup(fd)
# From the manual:
# gzopen can be used to read a file which is not in gzip format;
# in this case gzread will directly read from the file without decompression.
# When reading, this will be detected automatically by looking
# for the magic two-byte gzip header.
self.fh = bgzf_dopen(self.duplicated_fd, 'r')
if self.fh == NULL:
raise IOError('%s' % strerror(errno))
self.kstream = ks_init(self.fh)
self.buffer.s = <char*>malloc(buffer_size)
#if self.buffer == NULL:
# raise MemoryError( "tabix_file_iterator: could not allocate %i bytes" % buffer_size)
#self.size = buffer_size
self.parser = parser
def __iter__(self):
return self
cdef __cnext__(self):
cdef char * b
cdef int dret = 0
cdef int retval = 0
while 1:
with nogil:
retval = ks_getuntil(self.kstream, '\n', &self.buffer, &dret)
if retval < 0:
break
#raise IOError('gzip error: %s' % buildGzipError( self.fh ))
b = self.buffer.s
# skip comments
if (b[0] == '#'):
continue
# skip empty lines
if b[0] == '\0' or b[0] == '\n' or b[0] == '\r':
continue
# gzgets terminates at \n, no need to test
# parser creates a copy
return self.parser.parse(b, self.buffer.l)
raise StopIteration
def __dealloc__(self):
free(self.buffer.s)
ks_destroy(self.kstream)
bgzf_close(self.fh)
def __next__(self):
return self.__cnext__()
def next(self):
return self.__cnext__()
class tabix_generic_iterator:
'''iterate over ``infile``.
Permits the use of file-like objects for example from the gzip module.
'''
def __init__(self, infile, parser):
self.infile = infile
if self.infile.closed:
raise ValueError("I/O operation on closed file.")
self.parser = parser
def __iter__(self):
return self
# cython version - required for python 3
def __next__(self):
cdef char * b
cdef char * cpy
cdef size_t nbytes
encoding = self.parser.get_encoding()
# note that GzipFile.close() does not close the file
# reading is still possible.
if self.infile.closed:
raise ValueError("I/O operation on closed file.")
while 1:
line = self.infile.readline()
if not line:
break
s = force_bytes(line, encoding)
b = s
nbytes = len(line)
assert b[nbytes] == '\0'
# skip comments
if b[0] == '#':
continue
# skip empty lines
if b[0] == '\0' or b[0] == '\n' or b[0] == '\r':
continue
# make sure that entry is complete
if b[nbytes-1] != '\n' and b[nbytes-1] != '\r':
raise ValueError("incomplete line at %s" % line)
bytes_cpy = <bytes> b
cpy = <char *> bytes_cpy
return self.parser(cpy, nbytes)
raise StopIteration
# python version - required for python 2.7
def next(self):
return self.__next__()
def tabix_iterator(infile, parser):
"""return an iterator over all entries in a file.
Results are returned parsed as specified by the *parser*. If
*parser* is None, the results are returned as an unparsed string.
Otherwise, *parser* is assumed to be a functor that will return
parsed data (see for example :class:`~pysam.asTuple` and
:class:`~pysam.asGTF`).
"""
if PY_MAJOR_VERSION >= 3:
return tabix_generic_iterator(infile, parser)
else:
return tabix_file_iterator(infile, parser)
# file objects can use C stdio
# used to be: isinstance( infile, file):
# if PY_MAJOR_VERSION >= 3:
# if isinstance( infile, io.IOBase ):
# return tabix_copy_iterator( infile, parser )
# else:
# return tabix_generic_iterator( infile, parser )
# else:
# if isinstance( infile, file ):
# return tabix_copy_iterator( infile, parser )
# else:
# return tabix_generic_iterator( infile, parser )
cdef class Tabixfile(TabixFile):
"""Tabixfile is deprecated: use TabixFile instead"""
pass
__all__ = [
"tabix_index",
"tabix_compress",
"TabixFile",
"Tabixfile",
"asTuple",
"asGTF",
"asVCF",
"asBed",
"GZIterator",
"GZIteratorHead",
"tabix_iterator",
"tabix_generic_iterator",
"tabix_file_iterator",
]
|