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
|
#!/usr/bin/env python3
"""
Parses tab delimited database files
"""
# Info
__author__ = 'Jason Anthony Vander Heiden'
from changeo import __version__, __date__
# Imports
import csv
import os
import re
from argparse import ArgumentParser
from collections import OrderedDict
from itertools import chain
from textwrap import dedent
from time import time
# Presto and changeo imports
from presto.IO import printLog, printProgress, printMessage
from changeo.Defaults import default_id_field, default_seq_field, default_germ_field, \
default_csv_size, default_out_args
from changeo.Commandline import CommonHelpFormatter, checkArgs, getCommonArgParser, parseCommonArgs
from changeo.IO import countDbFile, getOutputHandle, splitName, TSVReader, TSVWriter
# System settings
csv.field_size_limit(default_csv_size)
# Defaults
default_index_field = 'INDEX'
# TODO: convert SQL-ish operations to modify_func() as per ParseHeaders
def splitDbFile(db_file, field, num_split=None, out_args=default_out_args):
"""
Divides a tab-delimited database file into segments by description tags
Arguments:
db_file : filename of the tab-delimited database file to split
field : the field name by which to split db_file
num_split : the numerical threshold by which to group sequences;
if None treat field as textual
out_args : common output argument dictionary from parseCommonArgs
Returns:
list : a list of output file names.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'split'
log['FILE'] = os.path.basename(db_file)
log['FIELD'] = field
log['NUM_SPLIT'] = num_split
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
out_fields = db_iter.fields
__, __, out_args['out_type'] = splitName(db_file)
# Determine total numbers of records
rec_count = countDbFile(db_file)
start_time = time()
count = 0
# Sort records into files based on textual field
if num_split is None:
# Create set of unique field tags
with open(db_file, 'rt') as tmp_handle:
tmp_iter = TSVReader(tmp_handle)
tag_list = list(set([row[field] for row in tmp_iter]))
# Forbidden characters in filename and replacements
no_good = {'\/':'f','\\':'b','?':'q','\%':'p','*':'s',':':'c',
'\|':'pi','\"':'dq','\'':'sq','<':'gt','>':'lt',' ':'_'}
# Replace forbidden characters in tag_list
tag_dict = {}
for tag in tag_list:
for c,r in no_good.items():
tag_dict[tag] = (tag_dict.get(tag, tag).replace(c,r) \
if c in tag else tag_dict.get(tag, tag))
# Create output handles
handles_dict = {tag: getOutputHandle(db_file,
out_label='%s-%s' % (field, label),
out_name=out_args['out_name'],
out_dir=out_args['out_dir'],
out_type=out_args['out_type'])
for tag, label in tag_dict.items()}
# Create Db writer instances
writers_dict = {tag: TSVWriter(handles_dict[tag], fields=out_fields)
for tag in tag_dict}
# Iterate over records
for row in db_iter:
printProgress(count, rec_count, 0.05, start_time=start_time)
count += 1
# Write row to appropriate file
tag = row[field]
writers_dict[tag].writeDict(row)
# Sort records into files based on numeric num_split
else:
num_split = float(num_split)
# Create output handles
handles_dict = {'under': getOutputHandle(db_file,
out_label='under-%.1f' % num_split,
out_name=out_args['out_name'],
out_dir=out_args['out_dir'],
out_type=out_args['out_type']),
'atleast': getOutputHandle(db_file,
out_label='atleast-%.1f' % num_split,
out_name=out_args['out_name'],
out_dir=out_args['out_dir'],
out_type=out_args['out_type'])}
# Create Db writer instances
writers_dict = {'under': TSVWriter(handles_dict['under'], fields=out_fields),
'atleast': TSVWriter(handles_dict['atleast'], fields=out_fields)}
# Iterate over records
for row in db_iter:
printProgress(count, rec_count, 0.05, start_time=start_time)
count += 1
tag = row[field]
tag = 'under' if float(tag) < num_split else 'atleast'
writers_dict[tag].writeDict(row)
# Write log
printProgress(count, rec_count, 0.05, start_time=start_time)
log = OrderedDict()
for i, k in enumerate(handles_dict):
log['OUTPUT%i' % (i + 1)] = os.path.basename(handles_dict[k].name)
log['RECORDS'] = rec_count
log['PARTS'] = len(handles_dict)
log['END'] = 'ParseDb'
printLog(log)
# Close output file handles
db_handle.close()
for t in handles_dict: handles_dict[t].close()
return [handles_dict[t].name for t in handles_dict]
def addDbFile(db_file, fields, values, out_file=None, out_args=default_out_args):
"""
Adds field and value pairs to a database file
Arguments:
db_file : the database file name.
fields : a list of fields to add.
values : a list of values to assign to all rows of each field.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'add'
log['FILE'] = os.path.basename(db_file)
log['FIELDS'] = ','.join(fields)
log['VALUES'] = ','.join(values)
printLog(log)
# Open inut
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
__, __, out_args['out_type'] = splitName(db_file)
# Add fields
out_fields = list(db_iter.fields)
out_fields.extend(fields)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-add', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Define fields and values to append
add_dict = {k:v for k,v in zip(fields, values) if k not in db_iter.fields}
# Iterate over records
start_time = time()
rec_count = 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Write updated row
rec.update(add_dict)
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def indexDbFile(db_file, field=default_index_field, out_file=None, out_args=default_out_args):
"""
Adds an index column to a database file
Arguments:
db_file : the database file name.
field : the name of the index field to add.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'index'
log['FILE'] = os.path.basename(db_file)
log['FIELD'] = field
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
__, __, out_args['out_type'] = splitName(db_file)
# Append index field
out_fields = list(db_iter.fields)
out_fields.append(field)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-index', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count = 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Add count and write updated row
rec.update({field:rec_count})
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def dropDbFile(db_file, fields, out_file=None, out_args=default_out_args):
"""
Deletes entire fields from a database file
Arguments:
db_file : the database file name.
fields : a list of fields to drop.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs
Returns:
str : output file name.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'add'
log['FILE'] = os.path.basename(db_file)
log['FIELDS'] = ','.join(fields)
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
__, __, out_args['out_type'] = splitName(db_file)
# Exclude dropped field from output
out_fields = [f for f in db_iter.fields if f not in fields]
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-drop', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count = 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Write row
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
return pass_handle.name
def deleteDbFile(db_file, fields, values, logic='any', regex=False,
out_file=None, out_args=default_out_args):
"""
Deletes records from a database file
Arguments:
db_file : the database file name.
fields : a list of fields to check for deletion criteria.
values : a list of values defining deletion targets.
logic : one of 'any' or 'all' defining whether one or all fields must have a match.
regex : if False do exact full string matches; if True allow partial regex matches.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name.
"""
# Define string match function
if regex:
def _match_func(x, patterns): return any([re.search(p, x) for p in patterns])
else:
def _match_func(x, patterns): return x in patterns
# Define logic function
if logic == 'any':
_logic_func = any
elif logic == 'all':
_logic_func = all
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'delete'
log['FILE'] = os.path.basename(db_file)
log['FIELDS'] = ','.join(fields)
log['VALUES'] = ','.join(values)
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
out_fields = db_iter.fields
__, __, out_args['out_type'] = splitName(db_file)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-delete', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count, pass_count, fail_count = 0, 0, 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Check for deletion values in all fields
delete = _logic_func([_match_func(rec.get(f, False), values) for f in fields])
# Write sequences
if not delete:
pass_count += 1
pass_writer.writeDict(rec)
else:
fail_count += 1
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['KEPT'] = pass_count
log['DELETED'] = fail_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def renameDbFile(db_file, fields, names, out_file=None, out_args=default_out_args):
"""
Renames fields in a database file
Arguments:
db_file : the database file name.
fields : a list of fields to rename.
values : a list of new names for fields.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'rename'
log['FILE'] = os.path.basename(db_file)
log['FIELDS'] = ','.join(fields)
log['NAMES'] = ','.join(names)
printLog(log)
# Open file handles
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
__, __, out_args['out_type'] = splitName(db_file)
# Get header and rename fields
out_fields = list(db_iter.fields)
for f, n in zip(fields, names):
i = out_fields.index(f)
out_fields[i] = n
# Open writer
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-rename', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count = 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# TODO: repeating renaming is unnecessary.
# Rename fields
for f, n in zip(fields, names):
rec[n] = rec.pop(f)
# Write
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def selectDbFile(db_file, fields, values, logic='any', regex=False,
out_file=None, out_args=default_out_args):
"""
Selects records from a database file
Arguments:
db_file : the database file name
fields : a list of fields to check for selection criteria
values : a list of values defining selection targets
logic : one of 'any' or 'all' defining whether one or all fields must have a match.
regex : if False do exact full string matches; if True allow partial regex matches.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs
Returns:
str : output file name.
"""
# Define string match function
if regex:
def _match_func(x, patterns): return any([re.search(p, x) for p in patterns])
else:
def _match_func(x, patterns): return x in patterns
# Define logic function
if logic == 'any':
_logic_func = any
elif logic == 'all':
_logic_func = all
# Print console log
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'select'
log['FILE'] = os.path.basename(db_file)
log['FIELDS'] = ','.join(fields)
log['VALUES'] = ','.join(values)
log['REGEX'] =regex
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
out_fields = db_iter.fields
__, __, out_args['out_type'] = splitName(db_file)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-select', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count, pass_count, fail_count = 0, 0, 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Check for selection values in all fields
select = _logic_func([_match_func(rec.get(f, False), values) for f in fields])
# Write sequences
if select:
pass_count += 1
pass_writer.writeDict(rec)
else:
fail_count += 1
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['SELECTED'] = pass_count
log['DISCARDED'] = fail_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def sortDbFile(db_file, field, numeric=False, descend=False,
out_file=None, out_args=default_out_args):
"""
Sorts records by values in an annotation field
Arguments:
db_file : the database filename
field : the field name to sort by
numeric : if True sort field numerically;
if False sort field alphabetically
descend : if True sort in descending order;
if False sort in ascending order
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs
Returns:
str : output file name
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'sort'
log['FILE'] = os.path.basename(db_file)
log['FIELD'] = field
log['NUMERIC'] = numeric
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
out_fields = db_iter.fields
__, __, out_args['out_type'] = splitName(db_file)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-sort', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Store all records in a dictionary
start_time = time()
printMessage("Indexing: Running", start_time=start_time)
db_dict = {i:r for i, r in enumerate(db_iter)}
result_count = len(db_dict)
# Sort db_dict by field values
tag_dict = {k:v[field] for k, v in db_dict.items()}
if numeric: tag_dict = {k:float(v or 0) for k, v in tag_dict.items()}
sorted_keys = sorted(tag_dict, key=tag_dict.get, reverse=descend)
printMessage("Indexing: Done", start_time=start_time, end=True)
# Iterate over records
start_time = time()
rec_count = 0
for key in sorted_keys:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Write records
pass_writer.writeDict(db_dict[key])
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def updateDbFile(db_file, field, values, updates, out_file=None, out_args=default_out_args):
"""
Updates field and value pairs to a database file
Arguments:
db_file : the database file name.
field : the field to update.
values : a list of values to specifying which rows to update.
updates : a list of values to update each value with.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'update'
log['FILE'] = os.path.basename(db_file)
log['FIELD'] = field
log['VALUES'] = ','.join(values)
log['UPDATES'] = ','.join(updates)
printLog(log)
# Open input
db_handle = open(db_file, 'rt')
db_iter = TSVReader(db_handle)
out_fields = db_iter.fields
__, __, out_args['out_type'] = splitName(db_file)
# Open output
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
pass_handle = getOutputHandle(db_file, out_label='parse-update', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Count records
result_count = countDbFile(db_file)
# Iterate over records
start_time = time()
rec_count, pass_count = 0, 0
for rec in db_iter:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Updated values if found
for x, y in zip(values, updates):
if rec[field] == x:
rec[field] = y
pass_count += 1
# Write records
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['UPDATED'] = pass_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
db_handle.close()
return pass_handle.name
def mergeDbFiles(db_files, drop=False, out_file=None, out_args=default_out_args):
"""
Updates field and value pairs to a database file
Arguments:
db_files : list of database file names.
drop : if True drop columns not present in all files.
out_file : output file name. Automatically generated from the input file if None.
out_args : common output argument dictionary from parseCommonArgs.
Returns:
str : output file name.
"""
log = OrderedDict()
log['START'] = 'ParseDb'
log['COMMAND'] = 'merge'
log['FILES'] = ','.join([os.path.basename(f) for f in db_files])
log['DROP'] = drop
printLog(log)
# Open input
db_handles = [open(f, 'rt') for f in db_files]
db_iters = [TSVReader(x) for x in db_handles]
result_count = sum([countDbFile(f) for f in db_files])
# Define output fields
field_list = [x.fields for x in db_iters]
if drop:
field_set = set.intersection(*map(set, field_list))
else:
field_set = set.union(*map(set, field_list))
field_order = OrderedDict([(f, None) for f in chain(*field_list)])
out_fields = [f for f in field_order if f in field_set]
# Open output file
if out_file is not None:
pass_handle = open(out_file, 'w')
else:
__, __, out_args['out_type'] = splitName(db_files[0])
pass_handle = getOutputHandle(db_files[0], out_label='parse-merge', out_dir=out_args['out_dir'],
out_name=out_args['out_name'], out_type=out_args['out_type'])
pass_writer = TSVWriter(pass_handle, out_fields)
# Iterate over records
start_time = time()
rec_count = 0
for db in db_iters:
for rec in db:
# Print progress for previous iteration
printProgress(rec_count, result_count, 0.05, start_time=start_time)
rec_count += 1
# Write records
pass_writer.writeDict(rec)
# Print counts
printProgress(rec_count, result_count, 0.05, start_time=start_time)
log = OrderedDict()
log['OUTPUT'] = os.path.basename(pass_handle.name)
log['RECORDS'] = rec_count
log['END'] = 'ParseDb'
printLog(log)
# Close file handles
pass_handle.close()
for x in db_handles: x.close()
return pass_handle.name
def getArgParser():
"""
Defines the ArgumentParser
Arguments:
None
Returns:
an ArgumentParser object
"""
# Define input and output field help message
fields = dedent(
'''
output files:
sequences
FASTA formatted sequences output from the subcommands fasta and clip.
<field>-<value>
database files partitioned by annotation <field> and <value>.
parse-<command>
output of the database modification functions where <command> is one of
the subcommands add, index, drop, delete, rename, select, sort or update.
required fields:
SEQUENCE_ID
optional fields:
JUNCTION, SEQUENCE_IMGT, SEQUENCE_VDJ, GERMLINE_IMGT, GERMLINE_VDJ,
GERMLINE_IMGT_D_MASK, GERMLINE_VDJ_D_MASK,
GERMLINE_IMGT_V_REGION, GERMLINE_VDJ_V_REGION
''')
# Define ArgumentParser
parser = ArgumentParser(description=__doc__, epilog=fields,
formatter_class=CommonHelpFormatter, add_help=False)
group_help = parser.add_argument_group('help')
group_help.add_argument('--version', action='version',
version='%(prog)s:' + ' %s %s' %(__version__, __date__))
group_help.add_argument('-h', '--help', action='help', help='show this help message and exit')
subparsers = parser.add_subparsers(title='subcommands', dest='command', metavar='',
help='Database operation')
# TODO: This is a temporary fix for Python issue 9253
subparsers.required = True
# Define parent parsers
default_parent = getCommonArgParser(failed=False, log=False, format=False)
multi_parent = getCommonArgParser(out_file=False, failed=False, log=False, format=False)
# Subparser to add records
parser_add = subparsers.add_parser('add', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Adds field and value pairs.',
description='Adds field and value pairs.')
group_add = parser_add.add_argument_group('parsing arguments')
group_add.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to add.')
group_add.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='The value to assign to all rows for each field.')
parser_add.set_defaults(func=addDbFile)
# Subparser to delete records
parser_delete = subparsers.add_parser('delete', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Deletes specific records.',
description='Deletes specific records.')
group_delete = parser_delete.add_argument_group('parsing arguments')
group_delete.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to check for deletion criteria.')
group_delete.add_argument('-u', nargs='+', action='store', dest='values', default=['', 'NA'],
help='''The values defining which records to delete. A value
may appear in any of the fields specified with -f.''')
group_delete.add_argument('--logic', action='store', dest='logic',
choices=('any', 'all'), default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).''')
group_delete.add_argument('--regex', action='store_true', dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_delete.set_defaults(func=deleteDbFile)
# Subparser to drop fields
parser_drop = subparsers.add_parser('drop', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Deletes entire fields.',
description='Deletes entire fields.')
group_drop = parser_drop.add_argument_group('parsing arguments')
group_drop.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to delete from the database.')
parser_drop.set_defaults(func=dropDbFile)
# Subparser to index fields
parser_index = subparsers.add_parser('index', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Adds a numeric index field.',
description='Adds a numeric index field.')
group_index = parser_index.add_argument_group('parsing arguments')
group_index.add_argument('-f', action='store', dest='field',
default=default_index_field,
help='The name of the index field to add to the database.')
parser_index.set_defaults(func=indexDbFile)
# Subparser to rename fields
parser_rename = subparsers.add_parser('rename', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Renames fields.',
description='Renames fields.')
group_rename = parser_rename.add_argument_group('parsing arguments')
group_rename.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='List of fields to rename.')
group_rename.add_argument('-k', nargs='+', action='store', dest='names', required=True,
help='List of new names for each field.')
parser_rename.set_defaults(func=renameDbFile)
# Subparser to select records
parser_select = subparsers.add_parser('select', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Selects specific records.',
description='Selects specific records.')
group_select = parser_select.add_argument_group('parsing arguments')
group_select.add_argument('-f', nargs='+', action='store', dest='fields', required=True,
help='The name of the fields to check for selection criteria.')
group_select.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='''The values defining with records to select. A value
may appear in any of the fields specified with -f.''')
group_select.add_argument('--logic', action='store', dest='logic',
choices=('any', 'all'), default='any',
help='''Defines whether a value may appear in any field (any)
or whether it must appear in all fields (all).''')
group_select.add_argument('--regex', action='store_true', dest='regex',
help='''If specified, treat values as regular expressions
and allow partial string matches.''')
parser_select.set_defaults(func=selectDbFile)
# Subparser to sort file by records
parser_sort = subparsers.add_parser('sort', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Sorts records by field values.',
description='Sorts records by field values.')
group_sort = parser_sort.add_argument_group('parsing arguments')
group_sort.add_argument('-f', action='store', dest='field', type=str, required=True,
help='The annotation field by which to sort records.')
group_sort.add_argument('--num', action='store_true', dest='numeric', default=False,
help='''Specify to define the sort column as numeric rather
than textual.''')
group_sort.add_argument('--descend', action='store_true', dest='descend',
help='''If specified, sort records in descending, rather
than ascending, order by values in the target field.''')
parser_sort.set_defaults(func=sortDbFile)
# Subparser to update records
parser_update = subparsers.add_parser('update', parents=[default_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Updates field and value pairs.',
description='Updates field and value pairs.')
group_update = parser_update.add_argument_group('parsing arguments')
group_update.add_argument('-f', action='store', dest='field', required=True,
help='The name of the field to update.')
group_update.add_argument('-u', nargs='+', action='store', dest='values', required=True,
help='The values that will be replaced.')
group_update.add_argument('-t', nargs='+', action='store', dest='updates', required=True,
help='''The new value to assign to each selected row.''')
parser_update.set_defaults(func=updateDbFile)
# Subparser to merge files
parser_merge = subparsers.add_parser('merge', parents=[multi_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Merges files.',
description='Merges files.')
group_merge = parser_merge.add_argument_group('parsing arguments')
group_merge.add_argument('-o', action='store', dest='out_file', default=None,
help='''Explicit output file name. Note, this argument cannot be used with
the --failed, --outdir or --outname arguments.''')
group_merge.add_argument('--drop', action='store_true', dest='drop',
help='''If specified, drop fields that do not exist in all input files.
Otherwise, include all columns in all files and fill missing data
with empty strings.''')
parser_merge.set_defaults(func=mergeDbFiles)
# Subparser to partition files by annotation values
parser_split = subparsers.add_parser('split', parents=[multi_parent],
formatter_class=CommonHelpFormatter, add_help=False,
help='Splits database files by field values.',
description='Splits database files by field values')
group_split = parser_split.add_argument_group('parsing arguments')
group_split.add_argument('-f', action='store', dest='field', type=str, required=True,
help='Annotation field by which to split database files.')
group_split.add_argument('--num', action='store', dest='num_split', type=float, default=None,
help='''Specify to define the field as numeric and group
records by whether they are less than or at least
(greater than or equal to) the specified value.''')
parser_split.set_defaults(func=splitDbFile)
return parser
if __name__ == '__main__':
"""
Parses command line arguments and calls main function
"""
# Parse arguments
parser = getArgParser()
checkArgs(parser)
args = parser.parse_args()
if args.command == 'merge':
args_dict = parseCommonArgs(args, in_list=True)
else:
args_dict = parseCommonArgs(args)
# Delete command declaration from argument dictionary
del args_dict['command']
del args_dict['func']
# Check argument pairs
if args.command == 'add' and len(args_dict['fields']) != len(args_dict['values']):
parser.error('You must specify exactly one value (-u) per field (-f)')
elif args.command == 'rename' and len(args_dict['fields']) != len(args_dict['names']):
parser.error('You must specify exactly one new name (-k) per field (-f)')
elif args.command == 'update' and len(args_dict['values']) != len(args_dict['updates']):
parser.error('You must specify exactly one value (-u) per replacement (-t)')
# Call parser function for each database file
if args.command == 'merge':
args.func(**args_dict)
elif args.command == 'split':
del args_dict['db_files']
for f in args.__dict__['db_files']:
args_dict['db_file'] = f
args.func(**args_dict)
else:
del args_dict['db_files']
del args_dict['out_files']
for i, f in enumerate(args.__dict__['db_files']):
args_dict['db_file'] = f
args_dict['out_file'] = args.__dict__['out_files'][i] \
if args.__dict__['out_files'] else None
args.func(**args_dict)
|