/usr/lib/python2.7/dist-packages/distlib/database.py is in python-distlib 0.1.8-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 | # -*- coding: utf-8 -*-
#
# Copyright (C) 2012-2013 The Python Software Foundation.
# See LICENSE.txt and CONTRIBUTORS.txt.
#
"""PEP 376 implementation."""
from __future__ import unicode_literals
import base64
import codecs
import contextlib
import hashlib
import logging
import os
import posixpath
import sys
import zipimport
from . import DistlibException, resources
from .compat import StringIO
from .version import get_scheme, UnsupportedVersionError
from .metadata import Metadata, METADATA_FILENAME
from .util import (parse_requirement, cached_property, parse_name_and_version,
read_exports, write_exports, CSVReader, CSVWriter)
__all__ = ['Distribution', 'BaseInstalledDistribution',
'InstalledDistribution', 'EggInfoDistribution',
'DistributionPath']
logger = logging.getLogger(__name__)
EXPORTS_FILENAME = 'pydist-exports.json'
COMMANDS_FILENAME = 'pydist-commands.json'
DIST_FILES = ('INSTALLER', METADATA_FILENAME, 'RECORD', 'REQUESTED',
'RESOURCES', EXPORTS_FILENAME, 'SHARED')
DISTINFO_EXT = '.dist-info'
class _Cache(object):
"""
A simple cache mapping names and .dist-info paths to distributions
"""
def __init__(self):
"""
Initialise an instance. There is normally one for each DistributionPath.
"""
self.name = {}
self.path = {}
self.generated = False
def clear(self):
"""
Clear the cache, setting it to its initial state.
"""
self.name.clear()
self.path.clear()
self.generated = False
def add(self, dist):
"""
Add a distribution to the cache.
:param dist: The distribution to add.
"""
if dist.path not in self.path:
self.path[dist.path] = dist
self.name.setdefault(dist.key, []).append(dist)
class DistributionPath(object):
"""
Represents a set of distributions installed on a path (typically sys.path).
"""
def __init__(self, path=None, include_egg=False):
"""
Create an instance from a path, optionally including legacy (distutils/
setuptools/distribute) distributions.
:param path: The path to use, as a list of directories. If not specified,
sys.path is used.
:param include_egg: If True, this instance will look for and return legacy
distributions as well as those based on PEP 376.
"""
if path is None:
path = sys.path
self.path = path
self._include_dist = True
self._include_egg = include_egg
self._cache = _Cache()
self._cache_egg = _Cache()
self._cache_enabled = True
self._scheme = get_scheme('default')
def _get_cache_enabled(self):
return self._cache_enabled
def _set_cache_enabled(self, value):
self._cache_enabled = value
cache_enabled = property(_get_cache_enabled, _set_cache_enabled)
def clear_cache(self):
"""
Clears the internal cache.
"""
self._cache.clear()
self._cache_egg.clear()
def _yield_distributions(self):
"""
Yield .dist-info and/or .egg(-info) distributions.
"""
# We need to check if we've seen some resources already, because on
# some Linux systems (e.g. some Debian/Ubuntu variants) there are
# symlinks which alias other files in the environment.
seen = set()
for path in self.path:
finder = resources.finder_for_path(path)
if finder is None:
continue
r = finder.find('')
if not r or not r.is_container:
continue
rset = sorted(r.resources)
for entry in rset:
r = finder.find(entry)
if not r or r.path in seen:
continue
if self._include_dist and entry.endswith(DISTINFO_EXT):
metadata_path = posixpath.join(entry, METADATA_FILENAME)
pydist = finder.find(metadata_path)
if not pydist:
continue
metadata = Metadata(fileobj=pydist.as_stream(),
scheme='legacy')
logger.debug('Found %s', r.path)
seen.add(r.path)
yield new_dist_class(r.path, metadata=metadata,
env=self)
elif self._include_egg and entry.endswith(('.egg-info',
'.egg')):
logger.debug('Found %s', r.path)
seen.add(r.path)
yield old_dist_class(r.path, self)
def _generate_cache(self):
"""
Scan the path for distributions and populate the cache with
those that are found.
"""
gen_dist = not self._cache.generated
gen_egg = self._include_egg and not self._cache_egg.generated
if gen_dist or gen_egg:
for dist in self._yield_distributions():
if isinstance(dist, InstalledDistribution):
self._cache.add(dist)
else:
self._cache_egg.add(dist)
if gen_dist:
self._cache.generated = True
if gen_egg:
self._cache_egg.generated = True
@classmethod
def distinfo_dirname(cls, name, version):
"""
The *name* and *version* parameters are converted into their
filename-escaped form, i.e. any ``'-'`` characters are replaced
with ``'_'`` other than the one in ``'dist-info'`` and the one
separating the name from the version number.
:parameter name: is converted to a standard distribution name by replacing
any runs of non- alphanumeric characters with a single
``'-'``.
:type name: string
:parameter version: is converted to a standard version string. Spaces
become dots, and all other non-alphanumeric characters
(except dots) become dashes, with runs of multiple
dashes condensed to a single dash.
:type version: string
:returns: directory name
:rtype: string"""
name = name.replace('-', '_')
return '-'.join([name, version]) + DISTINFO_EXT
def get_distributions(self):
"""
Provides an iterator that looks for distributions and returns
:class:`InstalledDistribution` or
:class:`EggInfoDistribution` instances for each one of them.
:rtype: iterator of :class:`InstalledDistribution` and
:class:`EggInfoDistribution` instances
"""
if not self._cache_enabled:
for dist in self._yield_distributions():
yield dist
else:
self._generate_cache()
for dist in self._cache.path.values():
yield dist
if self._include_egg:
for dist in self._cache_egg.path.values():
yield dist
def get_distribution(self, name):
"""
Looks for a named distribution on the path.
This function only returns the first result found, as no more than one
value is expected. If nothing is found, ``None`` is returned.
:rtype: :class:`InstalledDistribution`, :class:`EggInfoDistribution`
or ``None``
"""
result = None
name = name.lower()
if not self._cache_enabled:
for dist in self._yield_distributions():
if dist.key == name:
result = dist
break
else:
self._generate_cache()
if name in self._cache.name:
result = self._cache.name[name][0]
elif self._include_egg and name in self._cache_egg.name:
result = self._cache_egg.name[name][0]
return result
def provides_distribution(self, name, version=None):
"""
Iterates over all distributions to find which distributions provide *name*.
If a *version* is provided, it will be used to filter the results.
This function only returns the first result found, since no more than
one values are expected. If the directory is not found, returns ``None``.
:parameter version: a version specifier that indicates the version
required, conforming to the format in ``PEP-345``
:type name: string
:type version: string
"""
matcher = None
if not version is None:
try:
matcher = self._scheme.matcher('%s (%s)' % (name, version))
except ValueError:
raise DistlibException('invalid name or version: %r, %r' %
(name, version))
for dist in self.get_distributions():
provided = dist.provides
for p in provided:
p_name, p_ver = parse_name_and_version(p)
if matcher is None:
if p_name == name:
yield dist
break
else:
if p_name == name and matcher.match(p_ver):
yield dist
break
def get_file_path(self, name, relative_path):
"""
Return the path to a resource file.
"""
dist = self.get_distribution(name)
if dist is None:
raise LookupError('no distribution named %r found' % name)
return dist.get_resource_path(relative_path)
def get_exported_entries(self, category, name=None):
"""
Return all of the exported entries in a particular category.
:param category: The category to search for entries.
:param name: If specified, only entries with that name are returned.
"""
for dist in self.get_distributions():
r = dist.exports
if category in r:
d = r[category]
if name is not None:
if name in d:
yield d[name]
else:
for v in d.values():
yield v
class Distribution(object):
"""
A base class for distributions, whether installed or from indexes.
Either way, it must have some metadata, so that's all that's needed
for construction.
"""
build_time_dependency = False
"""
Set to True if it's known to be only a build-time dependency (i.e.
not needed after installation).
"""
requested = False
"""A boolean that indicates whether the ``REQUESTED`` metadata file is
present (in other words, whether the package was installed by user
request or it was installed as a dependency)."""
def __init__(self, metadata):
"""
Initialise an instance.
:param metadata: The instance of :class:`Metadata` describing this
distribution.
"""
self.metadata = metadata
self.name = metadata.name
self.key = self.name.lower() # for case-insensitive comparisons
self.version = metadata.version
self.locator = None
self.digest = None
self.extras = None # additional features requested
self.context = None # environment marker overrides
@property
def source_url(self):
"""
The source archive download URL for this distribution.
"""
return self.metadata.source_url
download_url = source_url # Backward compatibility
@property
def name_and_version(self):
"""
A utility property which displays the name and version in parentheses.
"""
return '%s (%s)' % (self.name, self.version)
@property
def provides(self):
"""
A set of distribution names and versions provided by this distribution.
:return: A set of "name (version)" strings.
"""
plist = self.metadata.provides
s = '%s (%s)' % (self.name, self.version)
if s not in plist:
plist.append(s)
return plist
def _get_requirements(self, req_attr):
reqts = getattr(self.metadata, req_attr)
return set(self.metadata.get_requirements(reqts, extras=self.extras,
env=self.context))
@property
def run_requires(self):
return self._get_requirements('run_requires')
@property
def meta_requires(self):
return self._get_requirements('meta_requires')
@property
def build_requires(self):
return self._get_requirements('build_requires')
@property
def test_requires(self):
return self._get_requirements('test_requires')
@property
def dev_requires(self):
return self._get_requirements('dev_requires')
def matches_requirement(self, req):
"""
Say if this instance matches (fulfills) a requirement.
:param req: The requirement to match.
:rtype req: str
:return: True if it matches, else False.
"""
# Requirement may contain extras - parse to lose those
# from what's passed to the matcher
r = parse_requirement(req)
scheme = get_scheme(self.metadata.scheme)
try:
matcher = scheme.matcher(r.requirement)
except UnsupportedVersionError:
# XXX compat-mode if cannot read the version
logger.warning('could not read version %r - using name only',
req)
name = req.split()[0]
matcher = scheme.matcher(name)
name = matcher.key # case-insensitive
result = False
for p in self.provides:
p_name, p_ver = parse_name_and_version(p)
if p_name != name:
continue
try:
result = matcher.match(p_ver)
break
except UnsupportedVersionError:
pass
return result
def __repr__(self):
"""
Return a textual representation of this instance,
"""
if self.source_url:
suffix = ' [%s]' % self.source_url
else:
suffix = ''
return '<Distribution %s (%s)%s>' % (self.name, self.version, suffix)
def __eq__(self, other):
"""
See if this distribution is the same as another.
:param other: The distribution to compare with. To be equal to one
another. distributions must have the same type, name,
version and source_url.
:return: True if it is the same, else False.
"""
if type(other) is not type(self):
result = False
else:
result = (self.name == other.name and
self.version == other.version and
self.source_url == other.source_url)
return result
def __hash__(self):
"""
Compute hash in a way which matches the equality test.
"""
return hash(self.name) + hash(self.version) + hash(self.source_url)
class BaseInstalledDistribution(Distribution):
"""
This is the base class for installed distributions (whether PEP 376 or
legacy).
"""
hasher = None
def __init__(self, metadata, path, env=None):
"""
Initialise an instance.
:param metadata: An instance of :class:`Metadata` which describes the
distribution. This will normally have been initialised
from a metadata file in the ``path``.
:param path: The path of the ``.dist-info`` or ``.egg-info``
directory for the distribution.
:param env: This is normally the :class:`DistributionPath`
instance where this distribution was found.
"""
super(BaseInstalledDistribution, self).__init__(metadata)
self.path = path
self.dist_path = env
def get_hash(self, data, hasher=None):
"""
Get the hash of some data, using a particular hash algorithm, if
specified.
:param data: The data to be hashed.
:type data: bytes
:param hasher: The name of a hash implementation, supported by hashlib,
or ``None``. Examples of valid values are ``'sha1'``,
``'sha224'``, ``'sha384'``, '``sha256'``, ``'md5'`` and
``'sha512'``. If no hasher is specified, the ``hasher``
attribute of the :class:`InstalledDistribution` instance
is used. If the hasher is determined to be ``None``, MD5
is used as the hashing algorithm.
:returns: The hash of the data. If a hasher was explicitly specified,
the returned hash will be prefixed with the specified hasher
followed by '='.
:rtype: str
"""
if hasher is None:
hasher = self.hasher
if hasher is None:
hasher = hashlib.md5
prefix = ''
else:
hasher = getattr(hashlib, hasher)
prefix = '%s=' % self.hasher
digest = hasher(data).digest()
digest = base64.urlsafe_b64encode(digest).rstrip(b'=').decode('ascii')
return '%s%s' % (prefix, digest)
class InstalledDistribution(BaseInstalledDistribution):
"""
Created with the *path* of the ``.dist-info`` directory provided to the
constructor. It reads the metadata contained in ``pydist.json`` when it is
instantiated., or uses a passed in Metadata instance (useful for when
dry-run mode is being used).
"""
hasher = 'sha256'
def __init__(self, path, metadata=None, env=None):
self.finder = finder = resources.finder_for_path(path)
if finder is None:
import pdb; pdb.set_trace ()
if env and env._cache_enabled and path in env._cache.path:
metadata = env._cache.path[path].metadata
elif metadata is None:
r = finder.find(METADATA_FILENAME)
# Temporary - for legacy support
if r is None:
r = finder.find('METADATA')
if r is None:
raise ValueError('no %s found in %s' % (METADATA_FILENAME,
path))
with contextlib.closing(r.as_stream()) as stream:
metadata = Metadata(fileobj=stream, scheme='legacy')
super(InstalledDistribution, self).__init__(metadata, path, env)
if env and env._cache_enabled:
env._cache.add(self)
try:
r = finder.find('REQUESTED')
except AttributeError:
import pdb; pdb.set_trace ()
self.requested = r is not None
def __repr__(self):
return '<InstalledDistribution %r %s at %r>' % (
self.name, self.version, self.path)
def __str__(self):
return "%s %s" % (self.name, self.version)
def _get_records(self):
"""
Get the list of installed files for the distribution
:return: A list of tuples of path, hash and size. Note that hash and
size might be ``None`` for some entries. The path is exactly
as stored in the file (which is as in PEP 376).
"""
results = []
r = self.get_distinfo_resource('RECORD')
with contextlib.closing(r.as_stream()) as stream:
with CSVReader(stream=stream) as record_reader:
# Base location is parent dir of .dist-info dir
#base_location = os.path.dirname(self.path)
#base_location = os.path.abspath(base_location)
for row in record_reader:
missing = [None for i in range(len(row), 3)]
path, checksum, size = row + missing
#if not os.path.isabs(path):
# path = path.replace('/', os.sep)
# path = os.path.join(base_location, path)
results.append((path, checksum, size))
return results
@cached_property
def exports(self):
"""
Return the information exported by this distribution.
:return: A dictionary of exports, mapping an export category to a dict
of :class:`ExportEntry` instances describing the individual
export entries, and keyed by name.
"""
result = {}
r = self.get_distinfo_resource(EXPORTS_FILENAME)
if r:
result = self.read_exports()
return result
def read_exports(self):
"""
Read exports data from a file in .ini format.
:return: A dictionary of exports, mapping an export category to a list
of :class:`ExportEntry` instances describing the individual
export entries.
"""
result = {}
r = self.get_distinfo_resource(EXPORTS_FILENAME)
if r:
with contextlib.closing(r.as_stream()) as stream:
result = read_exports(stream)
return result
def write_exports(self, exports):
"""
Write a dictionary of exports to a file in .ini format.
:param exports: A dictionary of exports, mapping an export category to
a list of :class:`ExportEntry` instances describing the
individual export entries.
"""
rf = self.get_distinfo_file(EXPORTS_FILENAME)
with open(rf, 'w') as f:
write_exports(exports, f)
def get_resource_path(self, relative_path):
"""
NOTE: This API may change in the future.
Return the absolute path to a resource file with the given relative
path.
:param relative_path: The path, relative to .dist-info, of the resource
of interest.
:return: The absolute path where the resource is to be found.
"""
r = self.get_distinfo_resource('RESOURCES')
with contextlib.closing(r.as_stream()) as stream:
with CSVReader(stream=stream) as resources_reader:
for relative, destination in resources_reader:
if relative == relative_path:
return destination
raise KeyError('no resource file with relative path %r '
'is installed' % relative_path)
def list_installed_files(self):
"""
Iterates over the ``RECORD`` entries and returns a tuple
``(path, hash, size)`` for each line.
:returns: iterator of (path, hash, size)
"""
for result in self._get_records():
yield result
def write_installed_files(self, paths, prefix, dry_run=False):
"""
Writes the ``RECORD`` file, using the ``paths`` iterable passed in. Any
existing ``RECORD`` file is silently overwritten.
prefix is used to determine when to write absolute paths.
"""
prefix = os.path.join(prefix, '')
base = os.path.dirname(self.path)
base_under_prefix = base.startswith(prefix)
base = os.path.join(base, '')
record_path = self.get_distinfo_file('RECORD')
logger.info('creating %s', record_path)
if dry_run:
return None
with CSVWriter(record_path) as writer:
for path in paths:
if os.path.isdir(path) or path.endswith(('.pyc', '.pyo')):
# do not put size and hash, as in PEP-376
hash_value = size = ''
else:
size = '%d' % os.path.getsize(path)
with open(path, 'rb') as fp:
hash_value = self.get_hash(fp.read())
if path.startswith(base) or (base_under_prefix and
path.startswith(prefix)):
path = os.path.relpath(path, base)
writer.writerow((path, hash_value, size))
# add the RECORD file itself
if record_path.startswith(base):
record_path = os.path.relpath(record_path, base)
writer.writerow((record_path, '', ''))
return record_path
def check_installed_files(self):
"""
Checks that the hashes and sizes of the files in ``RECORD`` are
matched by the files themselves. Returns a (possibly empty) list of
mismatches. Each entry in the mismatch list will be a tuple consisting
of the path, 'exists', 'size' or 'hash' according to what didn't match
(existence is checked first, then size, then hash), the expected
value and the actual value.
"""
mismatches = []
base = os.path.dirname(self.path)
record_path = self.get_distinfo_file('RECORD')
for path, hash_value, size in self.list_installed_files():
if not os.path.isabs(path):
path = os.path.join(base, path)
if path == record_path:
continue
if not os.path.exists(path):
mismatches.append((path, 'exists', True, False))
elif os.path.isfile(path):
actual_size = str(os.path.getsize(path))
if size and actual_size != size:
mismatches.append((path, 'size', size, actual_size))
elif hash_value:
if '=' in hash_value:
hasher = hash_value.split('=', 1)[0]
else:
hasher = None
with open(path, 'rb') as f:
actual_hash = self.get_hash(f.read(), hasher)
if actual_hash != hash_value:
mismatches.append((path, 'hash', hash_value, actual_hash))
return mismatches
@cached_property
def shared_locations(self):
"""
A dictionary of shared locations whose keys are in the set 'prefix',
'purelib', 'platlib', 'scripts', 'headers', 'data' and 'namespace'.
The corresponding value is the absolute path of that category for
this distribution, and takes into account any paths selected by the
user at installation time (e.g. via command-line arguments). In the
case of the 'namespace' key, this would be a list of absolute paths
for the roots of namespace packages in this distribution.
The first time this property is accessed, the relevant information is
read from the SHARED file in the .dist-info directory.
"""
result = {}
shared_path = os.path.join(self.path, 'SHARED')
if os.path.isfile(shared_path):
with codecs.open(shared_path, 'r', encoding='utf-8') as f:
lines = f.read().splitlines()
for line in lines:
key, value = line.split('=', 1)
if key == 'namespace':
result.setdefault(key, []).append(value)
else:
result[key] = value
return result
def write_shared_locations(self, paths, dry_run=False):
"""
Write shared location information to the SHARED file in .dist-info.
:param paths: A dictionary as described in the documentation for
:meth:`shared_locations`.
:param dry_run: If True, the action is logged but no file is actually
written.
:return: The path of the file written to.
"""
shared_path = os.path.join(self.path, 'SHARED')
logger.info('creating %s', shared_path)
if dry_run:
return None
lines = []
for key in ('prefix', 'lib', 'headers', 'scripts', 'data'):
path = paths[key]
if os.path.isdir(paths[key]):
lines.append('%s=%s' % (key, path))
for ns in paths.get('namespace', ()):
lines.append('namespace=%s' % ns)
with codecs.open(shared_path, 'w', encoding='utf-8') as f:
f.write('\n'.join(lines))
return shared_path
def get_distinfo_resource(self, path):
if path not in DIST_FILES:
raise DistlibException('invalid path for a dist-info file: '
'%r at %r' % (path, self.path))
finder = resources.finder_for_path(self.path)
if finder is None:
raise DistlibException('Unable to get a finder for %s' % self.path)
return finder.find(path)
def get_distinfo_file(self, path):
"""
Returns a path located under the ``.dist-info`` directory. Returns a
string representing the path.
:parameter path: a ``'/'``-separated path relative to the
``.dist-info`` directory or an absolute path;
If *path* is an absolute path and doesn't start
with the ``.dist-info`` directory path,
a :class:`DistlibException` is raised
:type path: str
:rtype: str
"""
# Check if it is an absolute path # XXX use relpath, add tests
if path.find(os.sep) >= 0:
# it's an absolute path?
distinfo_dirname, path = path.split(os.sep)[-2:]
if distinfo_dirname != self.path.split(os.sep)[-1]:
raise DistlibException(
'dist-info file %r does not belong to the %r %s '
'distribution' % (path, self.name, self.version))
# The file must be relative
if path not in DIST_FILES:
raise DistlibException('invalid path for a dist-info file: '
'%r at %r' % (path, self.path))
return os.path.join(self.path, path)
def list_distinfo_files(self):
"""
Iterates over the ``RECORD`` entries and returns paths for each line if
the path is pointing to a file located in the ``.dist-info`` directory
or one of its subdirectories.
:returns: iterator of paths
"""
base = os.path.dirname(self.path)
for path, checksum, size in self._get_records():
# XXX add separator or use real relpath algo
if not os.path.isabs(path):
path = os.path.join(base, path)
if path.startswith(self.path):
yield path
def __eq__(self, other):
return (isinstance(other, InstalledDistribution) and
self.path == other.path)
# See http://docs.python.org/reference/datamodel#object.__hash__
__hash__ = object.__hash__
class EggInfoDistribution(BaseInstalledDistribution):
"""Created with the *path* of the ``.egg-info`` directory or file provided
to the constructor. It reads the metadata contained in the file itself, or
if the given path happens to be a directory, the metadata is read from the
file ``PKG-INFO`` under that directory."""
requested = True # as we have no way of knowing, assume it was
shared_locations = {}
def __init__(self, path, env=None):
def set_name_and_version(s, n, v):
s.name = n
s.key = n.lower() # for case-insensitive comparisons
s.version = v
self.path = path
self.dist_path = env
if env and env._cache_enabled and path in env._cache_egg.path:
metadata = env._cache_egg.path[path].metadata
set_name_and_version(self, metadata.name, metadata.version)
else:
metadata = self._get_metadata(path)
# Need to be set before caching
set_name_and_version(self, metadata.name, metadata.version)
if env and env._cache_enabled:
env._cache_egg.add(self)
super(EggInfoDistribution, self).__init__(metadata, path, env)
def _get_metadata(self, path):
requires = None
def parse_requires_data(data):
"""Create a list of dependencies from a requires.txt file.
*data*: the contents of a setuptools-produced requires.txt file.
"""
reqs = []
lines = data.splitlines()
for line in lines:
line = line.strip()
if line.startswith('['):
logger.warning('Unexpected line: quitting requirement scan: %r',
line)
break
r = parse_requirement(line)
if not r:
logger.warning('Not recognised as a requirement: %r', line)
continue
if r.extras:
logger.warning('extra requirements in requires.txt are '
'not supported')
if not r.constraints:
reqs.append(r.name)
else:
cons = ', '.join('%s%s' % c for c in r.constraints)
reqs.append('%s (%s)' % (r.name, cons))
return reqs
def parse_requires_path(req_path):
"""Create a list of dependencies from a requires.txt file.
*req_path*: the path to a setuptools-produced requires.txt file.
"""
reqs = []
try:
with codecs.open(req_path, 'r', 'utf-8') as fp:
reqs = parse_requires_data(fp.read())
except IOError:
pass
return reqs
if path.endswith('.egg'):
if os.path.isdir(path):
meta_path = os.path.join(path, 'EGG-INFO', 'PKG-INFO')
metadata = Metadata(path=meta_path, scheme='legacy')
req_path = os.path.join(path, 'EGG-INFO', 'requires.txt')
requires = parse_requires_path(req_path)
else:
# FIXME handle the case where zipfile is not available
zipf = zipimport.zipimporter(path)
fileobj = StringIO(
zipf.get_data('EGG-INFO/PKG-INFO').decode('utf8'))
metadata = Metadata(fileobj=fileobj, scheme='legacy')
try:
data = zipf.get_data('EGG-INFO/requires.txt')
requires = parse_requires_data(data.decode('utf-8'))
except IOError:
requires = None
elif path.endswith('.egg-info'):
if os.path.isdir(path):
path = os.path.join(path, 'PKG-INFO')
req_path = os.path.join(path, 'requires.txt')
requires = parse_requires_path(req_path)
metadata = Metadata(path=path, scheme='legacy')
else:
raise DistlibException('path must end with .egg-info or .egg, '
'got %r' % path)
if requires:
metadata.add_requirements(requires)
return metadata
def __repr__(self):
return '<EggInfoDistribution %r %s at %r>' % (
self.name, self.version, self.path)
def __str__(self):
return "%s %s" % (self.name, self.version)
def check_installed_files(self):
"""
Checks that the hashes and sizes of the files in ``RECORD`` are
matched by the files themselves. Returns a (possibly empty) list of
mismatches. Each entry in the mismatch list will be a tuple consisting
of the path, 'exists', 'size' or 'hash' according to what didn't match
(existence is checked first, then size, then hash), the expected
value and the actual value.
"""
mismatches = []
record_path = os.path.join(self.path, 'installed-files.txt')
if os.path.exists(record_path):
for path, _, _ in self.list_installed_files():
if path == record_path:
continue
if not os.path.exists(path):
mismatches.append((path, 'exists', True, False))
return mismatches
def list_installed_files(self):
"""
Iterates over the ``installed-files.txt`` entries and returns a tuple
``(path, hash, size)`` for each line.
:returns: a list of (path, hash, size)
"""
def _md5(path):
f = open(path, 'rb')
try:
content = f.read()
finally:
f.close()
return hashlib.md5(content).hexdigest()
def _size(path):
return os.stat(path).st_size
record_path = os.path.join(self.path, 'installed-files.txt')
result = []
if os.path.exists(record_path):
with codecs.open(record_path, 'r', encoding='utf-8') as f:
for line in f:
line = line.strip()
p = os.path.normpath(os.path.join(self.path, line))
# "./" is present as a marker between installed files
# and installation metadata files
if not os.path.exists(p):
logger.warning('Non-existent file: %s', p)
if p.endswith(('.pyc', '.pyo')):
continue
#otherwise fall through and fail
if not os.path.isdir(p):
result.append((p, _md5(p), _size(p)))
result.append((record_path, None, None))
return result
def list_distinfo_files(self, absolute=False):
"""
Iterates over the ``installed-files.txt`` entries and returns paths for
each line if the path is pointing to a file located in the
``.egg-info`` directory or one of its subdirectories.
:parameter absolute: If *absolute* is ``True``, each returned path is
transformed into a local absolute path. Otherwise the
raw value from ``installed-files.txt`` is returned.
:type absolute: boolean
:returns: iterator of paths
"""
record_path = os.path.join(self.path, 'installed-files.txt')
skip = True
with codecs.open(record_path, 'r', encoding='utf-8') as f:
for line in f:
line = line.strip()
if line == './':
skip = False
continue
if not skip:
p = os.path.normpath(os.path.join(self.path, line))
if p.startswith(self.path):
if absolute:
yield p
else:
yield line
def __eq__(self, other):
return (isinstance(other, EggInfoDistribution) and
self.path == other.path)
# See http://docs.python.org/reference/datamodel#object.__hash__
__hash__ = object.__hash__
new_dist_class = InstalledDistribution
old_dist_class = EggInfoDistribution
class DependencyGraph(object):
"""
Represents a dependency graph between distributions.
The dependency relationships are stored in an ``adjacency_list`` that maps
distributions to a list of ``(other, label)`` tuples where ``other``
is a distribution and the edge is labeled with ``label`` (i.e. the version
specifier, if such was provided). Also, for more efficient traversal, for
every distribution ``x``, a list of predecessors is kept in
``reverse_list[x]``. An edge from distribution ``a`` to
distribution ``b`` means that ``a`` depends on ``b``. If any missing
dependencies are found, they are stored in ``missing``, which is a
dictionary that maps distributions to a list of requirements that were not
provided by any other distributions.
"""
def __init__(self):
self.adjacency_list = {}
self.reverse_list = {}
self.missing = {}
def add_distribution(self, distribution):
"""Add the *distribution* to the graph.
:type distribution: :class:`distutils2.database.InstalledDistribution`
or :class:`distutils2.database.EggInfoDistribution`
"""
self.adjacency_list[distribution] = []
self.reverse_list[distribution] = []
#self.missing[distribution] = []
def add_edge(self, x, y, label=None):
"""Add an edge from distribution *x* to distribution *y* with the given
*label*.
:type x: :class:`distutils2.database.InstalledDistribution` or
:class:`distutils2.database.EggInfoDistribution`
:type y: :class:`distutils2.database.InstalledDistribution` or
:class:`distutils2.database.EggInfoDistribution`
:type label: ``str`` or ``None``
"""
self.adjacency_list[x].append((y, label))
# multiple edges are allowed, so be careful
if x not in self.reverse_list[y]:
self.reverse_list[y].append(x)
def add_missing(self, distribution, requirement):
"""
Add a missing *requirement* for the given *distribution*.
:type distribution: :class:`distutils2.database.InstalledDistribution`
or :class:`distutils2.database.EggInfoDistribution`
:type requirement: ``str``
"""
logger.debug('%s missing %r', distribution, requirement)
self.missing.setdefault(distribution, []).append(requirement)
def _repr_dist(self, dist):
return '%s %s' % (dist.name, dist.version)
def repr_node(self, dist, level=1):
"""Prints only a subgraph"""
output = [self._repr_dist(dist)]
for other, label in self.adjacency_list[dist]:
dist = self._repr_dist(other)
if label is not None:
dist = '%s [%s]' % (dist, label)
output.append(' ' * level + str(dist))
suboutput = self.repr_node(other, level + 1)
subs = suboutput.split('\n')
output.extend(subs[1:])
return '\n'.join(output)
def to_dot(self, f, skip_disconnected=True):
"""Writes a DOT output for the graph to the provided file *f*.
If *skip_disconnected* is set to ``True``, then all distributions
that are not dependent on any other distribution are skipped.
:type f: has to support ``file``-like operations
:type skip_disconnected: ``bool``
"""
disconnected = []
f.write("digraph dependencies {\n")
for dist, adjs in self.adjacency_list.items():
if len(adjs) == 0 and not skip_disconnected:
disconnected.append(dist)
for other, label in adjs:
if not label is None:
f.write('"%s" -> "%s" [label="%s"]\n' %
(dist.name, other.name, label))
else:
f.write('"%s" -> "%s"\n' % (dist.name, other.name))
if not skip_disconnected and len(disconnected) > 0:
f.write('subgraph disconnected {\n')
f.write('label = "Disconnected"\n')
f.write('bgcolor = red\n')
for dist in disconnected:
f.write('"%s"' % dist.name)
f.write('\n')
f.write('}\n')
f.write('}\n')
def topological_sort(self):
"""
Perform a topological sort of the graph.
:return: A tuple, the first element of which is a topologically sorted
list of distributions, and the second element of which is a
list of distributions that cannot be sorted because they have
circular dependencies and so form a cycle.
"""
result = []
# Make a shallow copy of the adjacency list
alist = {}
for k, v in self.adjacency_list.items():
alist[k] = v[:]
while True:
# See what we can remove in this run
to_remove = []
for k, v in list(alist.items())[:]:
if not v:
to_remove.append(k)
del alist[k]
if not to_remove:
# What's left in alist (if anything) is a cycle.
break
# Remove from the adjacency list of others
for k, v in alist.items():
alist[k] = [(d, r) for d, r in v if d not in to_remove]
logger.debug('Moving to result: %s',
['%s (%s)' % (d.name, d.version) for d in to_remove])
result.extend(to_remove)
return result, list(alist.keys())
def __repr__(self):
"""Representation of the graph"""
output = []
for dist, adjs in self.adjacency_list.items():
output.append(self.repr_node(dist))
return '\n'.join(output)
def make_graph(dists, scheme='default'):
"""Makes a dependency graph from the given distributions.
:parameter dists: a list of distributions
:type dists: list of :class:`distutils2.database.InstalledDistribution` and
:class:`distutils2.database.EggInfoDistribution` instances
:rtype: a :class:`DependencyGraph` instance
"""
scheme = get_scheme(scheme)
graph = DependencyGraph()
provided = {} # maps names to lists of (version, dist) tuples
# first, build the graph and find out what's provided
for dist in dists:
graph.add_distribution(dist)
for p in dist.provides:
name, version = parse_name_and_version(p)
logger.debug('Add to provided: %s, %s, %s', name, version, dist)
provided.setdefault(name, []).append((version, dist))
# now make the edges
for dist in dists:
requires = (dist.run_requires | dist.meta_requires |
dist.build_requires | dist.dev_requires)
for req in requires:
try:
matcher = scheme.matcher(req)
except UnsupportedVersionError:
# XXX compat-mode if cannot read the version
logger.warning('could not read version %r - using name only',
req)
name = req.split()[0]
matcher = scheme.matcher(name)
name = matcher.key # case-insensitive
matched = False
if name in provided:
for version, provider in provided[name]:
try:
match = matcher.match(version)
except UnsupportedVersionError:
match = False
if match:
graph.add_edge(dist, provider, req)
matched = True
break
if not matched:
graph.add_missing(dist, req)
return graph
def get_dependent_dists(dists, dist):
"""Recursively generate a list of distributions from *dists* that are
dependent on *dist*.
:param dists: a list of distributions
:param dist: a distribution, member of *dists* for which we are interested
"""
if dist not in dists:
raise DistlibException('given distribution %r is not a member '
'of the list' % dist.name)
graph = make_graph(dists)
dep = [dist] # dependent distributions
todo = graph.reverse_list[dist] # list of nodes we should inspect
while todo:
d = todo.pop()
dep.append(d)
for succ in graph.reverse_list[d]:
if succ not in dep:
todo.append(succ)
dep.pop(0) # remove dist from dep, was there to prevent infinite loops
return dep
def get_required_dists(dists, dist):
"""Recursively generate a list of distributions from *dists* that are
required by *dist*.
:param dists: a list of distributions
:param dist: a distribution, member of *dists* for which we are interested
"""
if dist not in dists:
raise DistlibException('given distribution %r is not a member '
'of the list' % dist.name)
graph = make_graph(dists)
req = [] # required distributions
todo = graph.adjacency_list[dist] # list of nodes we should inspect
while todo:
d = todo.pop()[0]
req.append(d)
for pred in graph.adjacency_list[d]:
if pred not in req:
todo.append(pred)
return req
def make_dist(name, version, **kwargs):
"""
A convenience method for making a dist given just a name and version.
"""
summary = kwargs.pop('summary', 'Placeholder for summary')
md = Metadata(**kwargs)
md.name = name
md.version = version
md.summary = summary or 'Plaeholder for summary'
return Distribution(md)
|