/usr/lib/python2.7/dist-packages/tables/scripts/ptrepack.py is in python-tables 3.2.2-2.
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 | # -*- coding: utf-8 -*-
########################################################################
#
# License: BSD
# Created: February 10, 2004
# Author: Francesc Alted - faltet@pytables.com
#
# $Id$
#
########################################################################
"""This utility lets you repack your data files in a flexible way.
Pass the flag -h to this for help on usage.
"""
from __future__ import print_function
import sys
import time
import os.path
import argparse
import warnings
from tables.file import open_file
from tables.group import Group
from tables.leaf import Filters
from tables.flavor import internal_flavor
from tables.exceptions import OldIndexWarning, NoSuchNodeError, FlavorWarning
from tables._past import previous_api
# Global variables
verbose = False
regoldindexes = True
createsysattrs = True
numpy_aliases = [
'numeric',
'Numeric',
'numarray',
'NumArray',
'CharArray',
]
def newdst_group(dstfileh, dstgroup, title, filters):
group = dstfileh.root
# Now, create the new group. This works even if dstgroup == '/'
for nodename in dstgroup.split('/'):
if nodename == '':
continue
# First try if possible intermediate groups does already exist.
try:
group2 = dstfileh.get_node(group, nodename)
except NoSuchNodeError:
# The group does not exist. Create it.
group2 = dstfileh.create_group(group, nodename,
title=title,
filters=filters)
group = group2
return group
newdstGroup = previous_api(newdst_group)
def recreate_indexes(table, dstfileh, dsttable):
listoldindexes = table._listoldindexes
if listoldindexes != []:
if not regoldindexes:
if verbose:
print("[I]Not regenerating indexes for table: '%s:%s'" %
(dstfileh.filename, dsttable._v_pathname))
return
# Now, recreate the indexed columns
if verbose:
print("[I]Regenerating indexes for table: '%s:%s'" %
(dstfileh.filename, dsttable._v_pathname))
for colname in listoldindexes:
if verbose:
print("[I]Indexing column: '%s'. Please wait..." % colname)
colobj = dsttable.cols._f_col(colname)
# We don't specify the filters for the indexes
colobj.create_index(filters=None)
recreateIndexes = previous_api(recreate_indexes)
def copy_leaf(srcfile, dstfile, srcnode, dstnode, title,
filters, copyuserattrs, overwritefile, overwrtnodes, stats,
start, stop, step, chunkshape, sortby, check_CSI,
propindexes, upgradeflavors):
# Open the source file
srcfileh = open_file(srcfile, 'r')
# Get the source node (that should exist)
srcnode = srcfileh.get_node(srcnode)
# Get the destination node and its parent
last_slash = dstnode.rindex('/')
if last_slash == len(dstnode)-1:
# print("Detected a trailing slash in destination node. "
# "Interpreting it as a destination group.")
dstgroup = dstnode[:-1]
elif last_slash > 0:
dstgroup = dstnode[:last_slash]
else:
dstgroup = "/"
dstleaf = dstnode[last_slash + 1:]
if dstleaf == "":
dstleaf = srcnode.name
# Check whether the destination group exists or not
if os.path.isfile(dstfile) and not overwritefile:
dstfileh = open_file(dstfile, 'a', pytables_sys_attrs=createsysattrs)
try:
dstgroup = dstfileh.get_node(dstgroup)
except:
# The dstgroup does not seem to exist. Try creating it.
dstgroup = newdst_group(dstfileh, dstgroup, title, filters)
else:
# The node exists, but it is really a group?
if not isinstance(dstgroup, Group):
# No. Should we overwrite it?
if overwrtnodes:
parent = dstgroup._v_parent
last_slash = dstgroup._v_pathname.rindex('/')
dstgroupname = dstgroup._v_pathname[last_slash + 1:]
dstgroup.remove()
dstgroup = dstfileh.create_group(parent, dstgroupname,
title=title,
filters=filters)
else:
raise RuntimeError("Please check that the node names are "
"not duplicated in destination, and "
"if so, add the --overwrite-nodes "
"flag if desired.")
else:
# The destination file does not exist or will be overwritten.
dstfileh = open_file(dstfile, 'w', title=title, filters=filters,
pytables_sys_attrs=createsysattrs)
dstgroup = newdst_group(dstfileh, dstgroup, title="", filters=filters)
# Finally, copy srcnode to dstnode
try:
dstnode = srcnode.copy(
dstgroup, dstleaf, filters=filters,
copyuserattrs=copyuserattrs, overwrite=overwrtnodes,
stats=stats, start=start, stop=stop, step=step,
chunkshape=chunkshape,
sortby=sortby, check_CSI=check_CSI, propindexes=propindexes)
except:
(type_, value, traceback) = sys.exc_info()
print("Problems doing the copy from '%s:%s' to '%s:%s'" %
(srcfile, srcnode, dstfile, dstnode))
print("The error was --> %s: %s" % (type_, value))
print("The destination file looks like:\n", dstfileh)
# Close all the open files:
srcfileh.close()
dstfileh.close()
raise RuntimeError("Please check that the node names are not "
"duplicated in destination, and if so, add "
"the --overwrite-nodes flag if desired.")
# Upgrade flavors in dstnode, if required
if upgradeflavors:
if srcfileh.format_version.startswith("1"):
# Remove original flavor in case the source file has 1.x format
dstnode.del_attr('FLAVOR')
elif srcfileh.format_version < "2.1":
if dstnode.get_attr('FLAVOR') in numpy_aliases:
dstnode.set_attr('FLAVOR', internal_flavor)
# Recreate possible old indexes in destination node
if srcnode._c_classid == "TABLE":
recreate_indexes(srcnode, dstfileh, dstnode)
# Close all the open files:
srcfileh.close()
dstfileh.close()
copyLeaf = previous_api(copy_leaf)
def copy_children(srcfile, dstfile, srcgroup, dstgroup, title,
recursive, filters, copyuserattrs, overwritefile,
overwrtnodes, stats, start, stop, step,
chunkshape, sortby, check_CSI, propindexes,
upgradeflavors, use_hardlinks=True):
"""Copy the children from source group to destination group"""
# Open the source file with srcgroup as root_uep
srcfileh = open_file(srcfile, 'r', root_uep=srcgroup)
# Assign the root to srcgroup
srcgroup = srcfileh.root
created_dstgroup = False
# Check whether the destination group exists or not
if os.path.isfile(dstfile) and not overwritefile:
dstfileh = open_file(dstfile, 'a', pytables_sys_attrs=createsysattrs)
try:
dstgroup = dstfileh.get_node(dstgroup)
except NoSuchNodeError:
# The dstgroup does not seem to exist. Try creating it.
dstgroup = newdst_group(dstfileh, dstgroup, title, filters)
created_dstgroup = True
else:
# The node exists, but it is really a group?
if not isinstance(dstgroup, Group):
# No. Should we overwrite it?
if overwrtnodes:
parent = dstgroup._v_parent
last_slash = dstgroup._v_pathname.rindex('/')
dstgroupname = dstgroup._v_pathname[last_slash + 1:]
dstgroup.remove()
dstgroup = dstfileh.create_group(parent, dstgroupname,
title=title,
filters=filters)
else:
raise RuntimeError("Please check that the node names are "
"not duplicated in destination, and "
"if so, add the --overwrite-nodes "
"flag if desired.")
else:
# The destination file does not exist or will be overwritten.
dstfileh = open_file(dstfile, 'w', title=title, filters=filters,
pytables_sys_attrs=createsysattrs)
dstgroup = newdst_group(dstfileh, dstgroup, title="", filters=filters)
created_dstgroup = True
# Copy the attributes to dstgroup, if needed
if created_dstgroup and copyuserattrs:
srcgroup._v_attrs._f_copy(dstgroup)
# Finally, copy srcgroup children to dstgroup
try:
srcgroup._f_copy_children(
dstgroup, recursive=recursive, filters=filters,
copyuserattrs=copyuserattrs, overwrite=overwrtnodes,
stats=stats, start=start, stop=stop, step=step,
chunkshape=chunkshape,
sortby=sortby, check_CSI=check_CSI, propindexes=propindexes,
use_hardlinks=use_hardlinks)
except:
(type_, value, traceback) = sys.exc_info()
print("Problems doing the copy from '%s:%s' to '%s:%s'" %
(srcfile, srcgroup, dstfile, dstgroup))
print("The error was --> %s: %s" % (type_, value))
print("The destination file looks like:\n", dstfileh)
# Close all the open files:
srcfileh.close()
dstfileh.close()
raise RuntimeError("Please check that the node names are not "
"duplicated in destination, and if so, add the "
"--overwrite-nodes flag if desired. In "
"particular, pay attention that root_uep is not "
"fooling you.")
# Upgrade flavors in dstnode, if required
if upgradeflavors:
for dstnode in dstgroup._f_walknodes("Leaf"):
if srcfileh.format_version.startswith("1"):
# Remove original flavor in case the source file has 1.x format
dstnode.del_attr('FLAVOR')
elif srcfileh.format_version < "2.1":
if dstnode.get_attr('FLAVOR') in numpy_aliases:
dstnode.set_attr('FLAVOR', internal_flavor)
# Convert the remaining tables with old indexes (if any)
for table in srcgroup._f_walknodes("Table"):
dsttable = dstfileh.get_node(dstgroup, table._v_pathname)
recreate_indexes(table, dstfileh, dsttable)
# Close all the open files:
srcfileh.close()
dstfileh.close()
copyChildren = previous_api(copy_children)
def _get_parser():
parser = argparse.ArgumentParser(
description='''This utility is very powerful and lets you copy any
leaf, group or complete subtree into another file.
During the copy process you are allowed to change the filter
properties if you want so. Also, in the case of duplicated pathnames,
you can decide if you want to overwrite already existing nodes on the
destination file. Generally speaking, ptrepack can be useful in may
situations, like replicating a subtree in another file, change the
filters in objects and see how affect this to the compression degree
or I/O performance, consolidating specific data in repositories or
even *importing* generic HDF5 files and create true PyTables
counterparts.''')
parser.add_argument(
'-v', '--verbose', action='store_true',
help='show verbose information',
)
parser.add_argument(
'-o', '--overwrite', action='store_true', dest='overwritefile',
help='overwrite destination file',
)
parser.add_argument(
'-R', '--range', dest='rng', metavar='RANGE',
help='''select a RANGE of rows (in the form "start,stop,step")
during the copy of *all* the leaves.
Default values are "None,None,1", which means a copy of all the
rows.''',
)
parser.add_argument(
'--non-recursive', action='store_false', default=True,
dest='recursive',
help='do not do a recursive copy. Default is to do it',
)
parser.add_argument(
'--dest-title', dest='title', default='',
help='title for the new file (if not specified, the source is copied)',
)
parser.add_argument(
'--dont-create-sysattrs', action='store_false', default=True,
dest='createsysattrs',
help='do not create sys attrs (default is to do it)',
)
parser.add_argument(
'--dont-copy-userattrs', action='store_false', default=True,
dest='copyuserattrs',
help='do not copy the user attrs (default is to do it)',
)
parser.add_argument(
'--overwrite-nodes', action='store_true', dest='overwrtnodes',
help='''overwrite destination nodes if they exist.
Default is to not overwrite them''',
)
parser.add_argument(
'--complevel', type=int, default=0,
help='''set a compression level (0 for no compression, which is the
default)''',
)
parser.add_argument(
'--complib', choices=(
"zlib", "lzo", "bzip2", "blosc", "blosc:blosclz",
"blosc:lz4", "blosc:lz4hc", "blosc:snappy",
"blosc:zlib"), default='zlib',
help='''set the compression library to be used during the copy.
Defaults to %(default)s''',
)
parser.add_argument(
'--shuffle', type=int, choices=(0, 1),
help='''activate or not the shuffling filter (default is active if
complevel > 0)''',
)
parser.add_argument(
'--fletcher32', type=int, choices=(0, 1),
help='''whether to activate or not the fletcher32 filter (not active
by default)''',
)
parser.add_argument(
'--keep-source-filters', action='store_true', dest='keepfilters',
help='''use the original filters in source files.
The default is not doing that if any of --complevel, --complib,
--shuffle or --fletcher32 option is specified''',
)
parser.add_argument(
'--chunkshape', default='keep',
help='''set a chunkshape.
Possible options are: "keep" | "auto" | int | tuple.
A value of "auto" computes a sensible value for the chunkshape of the
leaves copied. The default is to "keep" the original value''',
)
parser.add_argument(
'--upgrade-flavors', action='store_true', dest='upgradeflavors',
help='''when repacking PyTables 1.x or PyTables 2.x files, the flavor
of leaves will be unset. With this, such a leaves will be serialized
as objects with the internal flavor ('numpy' for 3.x series)''',
)
parser.add_argument(
'--dont-regenerate-old-indexes', action='store_false', default=True,
dest='regoldindexes',
help='''disable regenerating old indexes.
The default is to regenerate old indexes as they are found''',
)
parser.add_argument(
'--sortby', metavar='COLUMN',
help='''do a table copy sorted by the index in "column".
For reversing the order, use a negative value in the "step" part of
"RANGE" (see "-r" flag). Only applies to table objects''',
)
parser.add_argument(
'--checkCSI', action='store_true',
help='Force the check for a CSI index for the --sortby column',
)
parser.add_argument(
'--propindexes', action='store_true',
help='''propagate the indexes existing in original tables. The default
is to not propagate them. Only applies to table objects''',
)
parser.add_argument(
'src', metavar='sourcefile:sourcegroup', help='source file/group',
)
parser.add_argument(
'dst', metavar='destfile:destgroup', help='destination file/group',
)
return parser
def main():
global verbose
global regoldindexes
global createsysattrs
parser = _get_parser()
args = parser.parse_args()
# check arguments
if args.rng:
try:
args.rng = eval("slice(" + args.rng + ")")
except Exception:
parser.error("Error when getting the range parameter.")
if args.chunkshape.isdigit() or args.chunkshape.startswith('('):
args.chunkshape = eval(args.chunkshape)
if args.complevel < 0 or args.complevel > 9:
parser.error(
'invalid "complevel" value, it sould be in te range [0, 9]'
)
# Catch the files passed as the last arguments
src = args.src.split(':')
dst = args.dst.split(':')
if len(src) == 1:
srcfile, srcnode = src[0], "/"
else:
srcfile, srcnode = src
if len(dst) == 1:
dstfile, dstnode = dst[0], "/"
else:
dstfile, dstnode = dst
if srcnode == "":
# case where filename == "filename:" instead of "filename:/"
srcnode = "/"
if dstnode == "":
# case where filename == "filename:" instead of "filename:/"
dstnode = "/"
# Ignore the warnings for tables that contains oldindexes
# (these will be handled by the copying routines)
warnings.filterwarnings("ignore", category=OldIndexWarning)
# Ignore the flavors warnings during upgrading flavor operations
if args.upgradeflavors:
warnings.filterwarnings("ignore", category=FlavorWarning)
# Build the Filters instance
filter_params = (
args.complevel,
args.complib,
args.shuffle,
args.fletcher32,
)
if (filter_params == (None,) * 4 or args.keepfilters):
filters = None
else:
if args.complevel is None:
args.complevel = 0
if args.shuffle is None:
if args.complevel > 0:
args.shuffle = True
else:
args.shuffle = False
if args.complib is None:
args.complib = "zlib"
if args.fletcher32 is None:
args.fletcher32 = False
filters = Filters(complevel=args.complevel, complib=args.complib,
shuffle=args.shuffle, fletcher32=args.fletcher32)
# The start, stop and step params:
start, stop, step = None, None, 1 # Defaults
if args.rng:
start, stop, step = args.rng.start, args.rng.stop, args.rng.step
# Set globals
verbose = args.verbose
regoldindexes = args.regoldindexes
createsysattrs = args.createsysattrs
# Some timing
t1 = time.time()
cpu1 = time.clock()
# Copy the file
if verbose:
print("+=+" * 20)
print("Recursive copy:", args.recursive)
print("Applying filters:", filters)
if args.sortby is not None:
print("Sorting table(s) by column:", args.sortby)
print("Forcing a CSI creation:", args.checkCSI)
if args.propindexes:
print("Recreating indexes in copied table(s)")
print("Start copying %s:%s to %s:%s" % (srcfile, srcnode,
dstfile, dstnode))
print("+=+" * 20)
# Check whether the specified source node is a group or a leaf
h5srcfile = open_file(srcfile, 'r')
srcnodeobject = h5srcfile.get_node(srcnode)
# Close the file again
h5srcfile.close()
stats = {'groups': 0, 'leaves': 0, 'links': 0, 'bytes': 0, 'hardlinks': 0}
if isinstance(srcnodeobject, Group):
copy_children(
srcfile, dstfile, srcnode, dstnode,
title=args.title, recursive=args.recursive, filters=filters,
copyuserattrs=args.copyuserattrs, overwritefile=args.overwritefile,
overwrtnodes=args.overwrtnodes, stats=stats,
start=start, stop=stop, step=step, chunkshape=args.chunkshape,
sortby=args.sortby, check_CSI=args.checkCSI,
propindexes=args.propindexes,
upgradeflavors=args.upgradeflavors,
use_hardlinks=True)
else:
# If not a Group, it should be a Leaf
copy_leaf(
srcfile, dstfile, srcnode, dstnode,
title=args.title, filters=filters,
copyuserattrs=args.copyuserattrs,
overwritefile=args.overwritefile, overwrtnodes=args.overwrtnodes,
stats=stats, start=start, stop=stop, step=step,
chunkshape=args.chunkshape,
sortby=args.sortby, check_CSI=args.checkCSI,
propindexes=args.propindexes,
upgradeflavors=args.upgradeflavors)
# Gather some statistics
t2 = time.time()
cpu2 = time.clock()
tcopy = round(t2 - t1, 3)
cpucopy = round(cpu2 - cpu1, 3)
tpercent = int(round(cpucopy / tcopy, 2) * 100)
if verbose:
ngroups = stats['groups']
nleaves = stats['leaves']
nlinks = stats['links']
nhardlinks = stats['hardlinks']
nbytescopied = stats['bytes']
nnodes = ngroups + nleaves + nlinks + nhardlinks
print(
"Groups copied:", ngroups,
", Leaves copied:", nleaves,
", Links copied:", nlinks,
", Hard links copied:", nhardlinks,
)
if args.copyuserattrs:
print("User attrs copied")
else:
print("User attrs not copied")
print("KBytes copied:", round(nbytescopied / 1024., 3))
print("Time copying: %s s (real) %s s (cpu) %s%%" % (
tcopy, cpucopy, tpercent))
print("Copied nodes/sec: ", round((nnodes) / float(tcopy), 1))
print("Copied KB/s :", int(nbytescopied / (tcopy * 1024)))
|