Spaces:
Running
Running
File size: 66,595 Bytes
b72ab63 |
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 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 |
from __future__ import annotations
import io
import logging
import os
import threading
import warnings
import weakref
from errno import ESPIPE
from glob import has_magic
from hashlib import sha256
from typing import ClassVar
from .callbacks import DEFAULT_CALLBACK
from .config import apply_config, conf
from .dircache import DirCache
from .transaction import Transaction
from .utils import (
_unstrip_protocol,
glob_translate,
isfilelike,
other_paths,
read_block,
stringify_path,
tokenize,
)
logger = logging.getLogger("fsspec")
def make_instance(cls, args, kwargs):
return cls(*args, **kwargs)
class _Cached(type):
"""
Metaclass for caching file system instances.
Notes
-----
Instances are cached according to
* The values of the class attributes listed in `_extra_tokenize_attributes`
* The arguments passed to ``__init__``.
This creates an additional reference to the filesystem, which prevents the
filesystem from being garbage collected when all *user* references go away.
A call to the :meth:`AbstractFileSystem.clear_instance_cache` must *also*
be made for a filesystem instance to be garbage collected.
"""
def __init__(cls, *args, **kwargs):
super().__init__(*args, **kwargs)
# Note: we intentionally create a reference here, to avoid garbage
# collecting instances when all other references are gone. To really
# delete a FileSystem, the cache must be cleared.
if conf.get("weakref_instance_cache"): # pragma: no cover
# debug option for analysing fork/spawn conditions
cls._cache = weakref.WeakValueDictionary()
else:
cls._cache = {}
cls._pid = os.getpid()
def __call__(cls, *args, **kwargs):
kwargs = apply_config(cls, kwargs)
extra_tokens = tuple(
getattr(cls, attr, None) for attr in cls._extra_tokenize_attributes
)
token = tokenize(
cls, cls._pid, threading.get_ident(), *args, *extra_tokens, **kwargs
)
skip = kwargs.pop("skip_instance_cache", False)
if os.getpid() != cls._pid:
cls._cache.clear()
cls._pid = os.getpid()
if not skip and cls.cachable and token in cls._cache:
cls._latest = token
return cls._cache[token]
else:
obj = super().__call__(*args, **kwargs)
# Setting _fs_token here causes some static linters to complain.
obj._fs_token_ = token
obj.storage_args = args
obj.storage_options = kwargs
if obj.async_impl and obj.mirror_sync_methods:
from .asyn import mirror_sync_methods
mirror_sync_methods(obj)
if cls.cachable and not skip:
cls._latest = token
cls._cache[token] = obj
return obj
class AbstractFileSystem(metaclass=_Cached):
"""
An abstract super-class for pythonic file-systems
Implementations are expected to be compatible with or, better, subclass
from here.
"""
cachable = True # this class can be cached, instances reused
_cached = False
blocksize = 2**22
sep = "/"
protocol: ClassVar[str | tuple[str, ...]] = "abstract"
_latest = None
async_impl = False
mirror_sync_methods = False
root_marker = "" # For some FSs, may require leading '/' or other character
transaction_type = Transaction
#: Extra *class attributes* that should be considered when hashing.
_extra_tokenize_attributes = ()
def __init__(self, *args, **storage_options):
"""Create and configure file-system instance
Instances may be cachable, so if similar enough arguments are seen
a new instance is not required. The token attribute exists to allow
implementations to cache instances if they wish.
A reasonable default should be provided if there are no arguments.
Subclasses should call this method.
Parameters
----------
use_listings_cache, listings_expiry_time, max_paths:
passed to ``DirCache``, if the implementation supports
directory listing caching. Pass use_listings_cache=False
to disable such caching.
skip_instance_cache: bool
If this is a cachable implementation, pass True here to force
creating a new instance even if a matching instance exists, and prevent
storing this instance.
asynchronous: bool
loop: asyncio-compatible IOLoop or None
"""
if self._cached:
# reusing instance, don't change
return
self._cached = True
self._intrans = False
self._transaction = None
self._invalidated_caches_in_transaction = []
self.dircache = DirCache(**storage_options)
if storage_options.pop("add_docs", None):
warnings.warn("add_docs is no longer supported.", FutureWarning)
if storage_options.pop("add_aliases", None):
warnings.warn("add_aliases has been removed.", FutureWarning)
# This is set in _Cached
self._fs_token_ = None
@property
def fsid(self):
"""Persistent filesystem id that can be used to compare filesystems
across sessions.
"""
raise NotImplementedError
@property
def _fs_token(self):
return self._fs_token_
def __dask_tokenize__(self):
return self._fs_token
def __hash__(self):
return int(self._fs_token, 16)
def __eq__(self, other):
return isinstance(other, type(self)) and self._fs_token == other._fs_token
def __reduce__(self):
return make_instance, (type(self), self.storage_args, self.storage_options)
@classmethod
def _strip_protocol(cls, path):
"""Turn path from fully-qualified to file-system-specific
May require FS-specific handling, e.g., for relative paths or links.
"""
if isinstance(path, list):
return [cls._strip_protocol(p) for p in path]
path = stringify_path(path)
protos = (cls.protocol,) if isinstance(cls.protocol, str) else cls.protocol
for protocol in protos:
if path.startswith(protocol + "://"):
path = path[len(protocol) + 3 :]
elif path.startswith(protocol + "::"):
path = path[len(protocol) + 2 :]
path = path.rstrip("/")
# use of root_marker to make minimum required path, e.g., "/"
return path or cls.root_marker
def unstrip_protocol(self, name: str) -> str:
"""Format FS-specific path to generic, including protocol"""
protos = (self.protocol,) if isinstance(self.protocol, str) else self.protocol
for protocol in protos:
if name.startswith(f"{protocol}://"):
return name
return f"{protos[0]}://{name}"
@staticmethod
def _get_kwargs_from_urls(path):
"""If kwargs can be encoded in the paths, extract them here
This should happen before instantiation of the class; incoming paths
then should be amended to strip the options in methods.
Examples may look like an sftp path "sftp://user@host:/my/path", where
the user and host should become kwargs and later get stripped.
"""
# by default, nothing happens
return {}
@classmethod
def current(cls):
"""Return the most recently instantiated FileSystem
If no instance has been created, then create one with defaults
"""
if cls._latest in cls._cache:
return cls._cache[cls._latest]
return cls()
@property
def transaction(self):
"""A context within which files are committed together upon exit
Requires the file class to implement `.commit()` and `.discard()`
for the normal and exception cases.
"""
if self._transaction is None:
self._transaction = self.transaction_type(self)
return self._transaction
def start_transaction(self):
"""Begin write transaction for deferring files, non-context version"""
self._intrans = True
self._transaction = self.transaction_type(self)
return self.transaction
def end_transaction(self):
"""Finish write transaction, non-context version"""
self.transaction.complete()
self._transaction = None
# The invalid cache must be cleared after the transaction is completed.
for path in self._invalidated_caches_in_transaction:
self.invalidate_cache(path)
self._invalidated_caches_in_transaction.clear()
def invalidate_cache(self, path=None):
"""
Discard any cached directory information
Parameters
----------
path: string or None
If None, clear all listings cached else listings at or under given
path.
"""
# Not necessary to implement invalidation mechanism, may have no cache.
# But if have, you should call this method of parent class from your
# subclass to ensure expiring caches after transacations correctly.
# See the implementation of FTPFileSystem in ftp.py
if self._intrans:
self._invalidated_caches_in_transaction.append(path)
def mkdir(self, path, create_parents=True, **kwargs):
"""
Create directory entry at path
For systems that don't have true directories, may create an for
this instance only and not touch the real filesystem
Parameters
----------
path: str
location
create_parents: bool
if True, this is equivalent to ``makedirs``
kwargs:
may be permissions, etc.
"""
pass # not necessary to implement, may not have directories
def makedirs(self, path, exist_ok=False):
"""Recursively make directories
Creates directory at path and any intervening required directories.
Raises exception if, for instance, the path already exists but is a
file.
Parameters
----------
path: str
leaf directory name
exist_ok: bool (False)
If False, will error if the target already exists
"""
pass # not necessary to implement, may not have directories
def rmdir(self, path):
"""Remove a directory, if empty"""
pass # not necessary to implement, may not have directories
def ls(self, path, detail=True, **kwargs):
"""List objects at path.
This should include subdirectories and files at that location. The
difference between a file and a directory must be clear when details
are requested.
The specific keys, or perhaps a FileInfo class, or similar, is TBD,
but must be consistent across implementations.
Must include:
- full path to the entry (without protocol)
- size of the entry, in bytes. If the value cannot be determined, will
be ``None``.
- type of entry, "file", "directory" or other
Additional information
may be present, appropriate to the file-system, e.g., generation,
checksum, etc.
May use refresh=True|False to allow use of self._ls_from_cache to
check for a saved listing and avoid calling the backend. This would be
common where listing may be expensive.
Parameters
----------
path: str
detail: bool
if True, gives a list of dictionaries, where each is the same as
the result of ``info(path)``. If False, gives a list of paths
(str).
kwargs: may have additional backend-specific options, such as version
information
Returns
-------
List of strings if detail is False, or list of directory information
dicts if detail is True.
"""
raise NotImplementedError
def _ls_from_cache(self, path):
"""Check cache for listing
Returns listing, if found (may be empty list for a directly that exists
but contains nothing), None if not in cache.
"""
parent = self._parent(path)
try:
return self.dircache[path.rstrip("/")]
except KeyError:
pass
try:
files = [
f
for f in self.dircache[parent]
if f["name"] == path
or (f["name"] == path.rstrip("/") and f["type"] == "directory")
]
if len(files) == 0:
# parent dir was listed but did not contain this file
raise FileNotFoundError(path)
return files
except KeyError:
pass
def walk(self, path, maxdepth=None, topdown=True, on_error="omit", **kwargs):
"""Return all files belows path
List all files, recursing into subdirectories; output is iterator-style,
like ``os.walk()``. For a simple list of files, ``find()`` is available.
When topdown is True, the caller can modify the dirnames list in-place (perhaps
using del or slice assignment), and walk() will
only recurse into the subdirectories whose names remain in dirnames;
this can be used to prune the search, impose a specific order of visiting,
or even to inform walk() about directories the caller creates or renames before
it resumes walk() again.
Modifying dirnames when topdown is False has no effect. (see os.walk)
Note that the "files" outputted will include anything that is not
a directory, such as links.
Parameters
----------
path: str
Root to recurse into
maxdepth: int
Maximum recursion depth. None means limitless, but not recommended
on link-based file-systems.
topdown: bool (True)
Whether to walk the directory tree from the top downwards or from
the bottom upwards.
on_error: "omit", "raise", a collable
if omit (default), path with exception will simply be empty;
If raise, an underlying exception will be raised;
if callable, it will be called with a single OSError instance as argument
kwargs: passed to ``ls``
"""
if maxdepth is not None and maxdepth < 1:
raise ValueError("maxdepth must be at least 1")
path = self._strip_protocol(path)
full_dirs = {}
dirs = {}
files = {}
detail = kwargs.pop("detail", False)
try:
listing = self.ls(path, detail=True, **kwargs)
except (FileNotFoundError, OSError) as e:
if on_error == "raise":
raise
elif callable(on_error):
on_error(e)
if detail:
return path, {}, {}
return path, [], []
for info in listing:
# each info name must be at least [path]/part , but here
# we check also for names like [path]/part/
pathname = info["name"].rstrip("/")
name = pathname.rsplit("/", 1)[-1]
if info["type"] == "directory" and pathname != path:
# do not include "self" path
full_dirs[name] = pathname
dirs[name] = info
elif pathname == path:
# file-like with same name as give path
files[""] = info
else:
files[name] = info
if not detail:
dirs = list(dirs)
files = list(files)
if topdown:
# Yield before recursion if walking top down
yield path, dirs, files
if maxdepth is not None:
maxdepth -= 1
if maxdepth < 1:
if not topdown:
yield path, dirs, files
return
for d in dirs:
yield from self.walk(
full_dirs[d],
maxdepth=maxdepth,
detail=detail,
topdown=topdown,
**kwargs,
)
if not topdown:
# Yield after recursion if walking bottom up
yield path, dirs, files
def find(self, path, maxdepth=None, withdirs=False, detail=False, **kwargs):
"""List all files below path.
Like posix ``find`` command without conditions
Parameters
----------
path : str
maxdepth: int or None
If not None, the maximum number of levels to descend
withdirs: bool
Whether to include directory paths in the output. This is True
when used by glob, but users usually only want files.
kwargs are passed to ``ls``.
"""
# TODO: allow equivalent of -name parameter
path = self._strip_protocol(path)
out = {}
# Add the root directory if withdirs is requested
# This is needed for posix glob compliance
if withdirs and path != "" and self.isdir(path):
out[path] = self.info(path)
for _, dirs, files in self.walk(path, maxdepth, detail=True, **kwargs):
if withdirs:
files.update(dirs)
out.update({info["name"]: info for name, info in files.items()})
if not out and self.isfile(path):
# walk works on directories, but find should also return [path]
# when path happens to be a file
out[path] = {}
names = sorted(out)
if not detail:
return names
else:
return {name: out[name] for name in names}
def du(self, path, total=True, maxdepth=None, withdirs=False, **kwargs):
"""Space used by files and optionally directories within a path
Directory size does not include the size of its contents.
Parameters
----------
path: str
total: bool
Whether to sum all the file sizes
maxdepth: int or None
Maximum number of directory levels to descend, None for unlimited.
withdirs: bool
Whether to include directory paths in the output.
kwargs: passed to ``find``
Returns
-------
Dict of {path: size} if total=False, or int otherwise, where numbers
refer to bytes used.
"""
sizes = {}
if withdirs and self.isdir(path):
# Include top-level directory in output
info = self.info(path)
sizes[info["name"]] = info["size"]
for f in self.find(path, maxdepth=maxdepth, withdirs=withdirs, **kwargs):
info = self.info(f)
sizes[info["name"]] = info["size"]
if total:
return sum(sizes.values())
else:
return sizes
def glob(self, path, maxdepth=None, **kwargs):
"""
Find files by glob-matching.
If the path ends with '/', only folders are returned.
We support ``"**"``,
``"?"`` and ``"[..]"``. We do not support ^ for pattern negation.
The `maxdepth` option is applied on the first `**` found in the path.
kwargs are passed to ``ls``.
"""
if maxdepth is not None and maxdepth < 1:
raise ValueError("maxdepth must be at least 1")
import re
seps = (os.path.sep, os.path.altsep) if os.path.altsep else (os.path.sep,)
ends_with_sep = path.endswith(seps) # _strip_protocol strips trailing slash
path = self._strip_protocol(path)
append_slash_to_dirname = ends_with_sep or path.endswith(
tuple(sep + "**" for sep in seps)
)
idx_star = path.find("*") if path.find("*") >= 0 else len(path)
idx_qmark = path.find("?") if path.find("?") >= 0 else len(path)
idx_brace = path.find("[") if path.find("[") >= 0 else len(path)
min_idx = min(idx_star, idx_qmark, idx_brace)
detail = kwargs.pop("detail", False)
if not has_magic(path):
if self.exists(path, **kwargs):
if not detail:
return [path]
else:
return {path: self.info(path, **kwargs)}
else:
if not detail:
return [] # glob of non-existent returns empty
else:
return {}
elif "/" in path[:min_idx]:
min_idx = path[:min_idx].rindex("/")
root = path[: min_idx + 1]
depth = path[min_idx + 1 :].count("/") + 1
else:
root = ""
depth = path[min_idx + 1 :].count("/") + 1
if "**" in path:
if maxdepth is not None:
idx_double_stars = path.find("**")
depth_double_stars = path[idx_double_stars:].count("/") + 1
depth = depth - depth_double_stars + maxdepth
else:
depth = None
allpaths = self.find(root, maxdepth=depth, withdirs=True, detail=True, **kwargs)
pattern = glob_translate(path + ("/" if ends_with_sep else ""))
pattern = re.compile(pattern)
out = {
p: info
for p, info in sorted(allpaths.items())
if pattern.match(
(
p + "/"
if append_slash_to_dirname and info["type"] == "directory"
else p
)
)
}
if detail:
return out
else:
return list(out)
def exists(self, path, **kwargs):
"""Is there a file at the given path"""
try:
self.info(path, **kwargs)
return True
except: # noqa: E722
# any exception allowed bar FileNotFoundError?
return False
def lexists(self, path, **kwargs):
"""If there is a file at the given path (including
broken links)"""
return self.exists(path)
def info(self, path, **kwargs):
"""Give details of entry at path
Returns a single dictionary, with exactly the same information as ``ls``
would with ``detail=True``.
The default implementation should calls ls and could be overridden by a
shortcut. kwargs are passed on to ```ls()``.
Some file systems might not be able to measure the file's size, in
which case, the returned dict will include ``'size': None``.
Returns
-------
dict with keys: name (full path in the FS), size (in bytes), type (file,
directory, or something else) and other FS-specific keys.
"""
path = self._strip_protocol(path)
out = self.ls(self._parent(path), detail=True, **kwargs)
out = [o for o in out if o["name"].rstrip("/") == path]
if out:
return out[0]
out = self.ls(path, detail=True, **kwargs)
path = path.rstrip("/")
out1 = [o for o in out if o["name"].rstrip("/") == path]
if len(out1) == 1:
if "size" not in out1[0]:
out1[0]["size"] = None
return out1[0]
elif len(out1) > 1 or out:
return {"name": path, "size": 0, "type": "directory"}
else:
raise FileNotFoundError(path)
def checksum(self, path):
"""Unique value for current version of file
If the checksum is the same from one moment to another, the contents
are guaranteed to be the same. If the checksum changes, the contents
*might* have changed.
This should normally be overridden; default will probably capture
creation/modification timestamp (which would be good) or maybe
access timestamp (which would be bad)
"""
return int(tokenize(self.info(path)), 16)
def size(self, path):
"""Size in bytes of file"""
return self.info(path).get("size", None)
def sizes(self, paths):
"""Size in bytes of each file in a list of paths"""
return [self.size(p) for p in paths]
def isdir(self, path):
"""Is this entry directory-like?"""
try:
return self.info(path)["type"] == "directory"
except OSError:
return False
def isfile(self, path):
"""Is this entry file-like?"""
try:
return self.info(path)["type"] == "file"
except: # noqa: E722
return False
def read_text(self, path, encoding=None, errors=None, newline=None, **kwargs):
"""Get the contents of the file as a string.
Parameters
----------
path: str
URL of file on this filesystems
encoding, errors, newline: same as `open`.
"""
with self.open(
path,
mode="r",
encoding=encoding,
errors=errors,
newline=newline,
**kwargs,
) as f:
return f.read()
def write_text(
self, path, value, encoding=None, errors=None, newline=None, **kwargs
):
"""Write the text to the given file.
An existing file will be overwritten.
Parameters
----------
path: str
URL of file on this filesystems
value: str
Text to write.
encoding, errors, newline: same as `open`.
"""
with self.open(
path,
mode="w",
encoding=encoding,
errors=errors,
newline=newline,
**kwargs,
) as f:
return f.write(value)
def cat_file(self, path, start=None, end=None, **kwargs):
"""Get the content of a file
Parameters
----------
path: URL of file on this filesystems
start, end: int
Bytes limits of the read. If negative, backwards from end,
like usual python slices. Either can be None for start or
end of file, respectively
kwargs: passed to ``open()``.
"""
# explicitly set buffering off?
with self.open(path, "rb", **kwargs) as f:
if start is not None:
if start >= 0:
f.seek(start)
else:
f.seek(max(0, f.size + start))
if end is not None:
if end < 0:
end = f.size + end
return f.read(end - f.tell())
return f.read()
def pipe_file(self, path, value, **kwargs):
"""Set the bytes of given file"""
with self.open(path, "wb", **kwargs) as f:
f.write(value)
def pipe(self, path, value=None, **kwargs):
"""Put value into path
(counterpart to ``cat``)
Parameters
----------
path: string or dict(str, bytes)
If a string, a single remote location to put ``value`` bytes; if a dict,
a mapping of {path: bytesvalue}.
value: bytes, optional
If using a single path, these are the bytes to put there. Ignored if
``path`` is a dict
"""
if isinstance(path, str):
self.pipe_file(self._strip_protocol(path), value, **kwargs)
elif isinstance(path, dict):
for k, v in path.items():
self.pipe_file(self._strip_protocol(k), v, **kwargs)
else:
raise ValueError("path must be str or dict")
def cat_ranges(
self, paths, starts, ends, max_gap=None, on_error="return", **kwargs
):
"""Get the contents of byte ranges from one or more files
Parameters
----------
paths: list
A list of of filepaths on this filesystems
starts, ends: int or list
Bytes limits of the read. If using a single int, the same value will be
used to read all the specified files.
"""
if max_gap is not None:
raise NotImplementedError
if not isinstance(paths, list):
raise TypeError
if not isinstance(starts, list):
starts = [starts] * len(paths)
if not isinstance(ends, list):
ends = [ends] * len(paths)
if len(starts) != len(paths) or len(ends) != len(paths):
raise ValueError
out = []
for p, s, e in zip(paths, starts, ends):
try:
out.append(self.cat_file(p, s, e))
except Exception as e:
if on_error == "return":
out.append(e)
else:
raise
return out
def cat(self, path, recursive=False, on_error="raise", **kwargs):
"""Fetch (potentially multiple) paths' contents
Parameters
----------
recursive: bool
If True, assume the path(s) are directories, and get all the
contained files
on_error : "raise", "omit", "return"
If raise, an underlying exception will be raised (converted to KeyError
if the type is in self.missing_exceptions); if omit, keys with exception
will simply not be included in the output; if "return", all keys are
included in the output, but the value will be bytes or an exception
instance.
kwargs: passed to cat_file
Returns
-------
dict of {path: contents} if there are multiple paths
or the path has been otherwise expanded
"""
paths = self.expand_path(path, recursive=recursive)
if (
len(paths) > 1
or isinstance(path, list)
or paths[0] != self._strip_protocol(path)
):
out = {}
for path in paths:
try:
out[path] = self.cat_file(path, **kwargs)
except Exception as e:
if on_error == "raise":
raise
if on_error == "return":
out[path] = e
return out
else:
return self.cat_file(paths[0], **kwargs)
def get_file(self, rpath, lpath, callback=DEFAULT_CALLBACK, outfile=None, **kwargs):
"""Copy single remote file to local"""
from .implementations.local import LocalFileSystem
if isfilelike(lpath):
outfile = lpath
elif self.isdir(rpath):
os.makedirs(lpath, exist_ok=True)
return None
fs = LocalFileSystem(auto_mkdir=True)
fs.makedirs(fs._parent(lpath), exist_ok=True)
with self.open(rpath, "rb", **kwargs) as f1:
if outfile is None:
outfile = open(lpath, "wb")
try:
callback.set_size(getattr(f1, "size", None))
data = True
while data:
data = f1.read(self.blocksize)
segment_len = outfile.write(data)
if segment_len is None:
segment_len = len(data)
callback.relative_update(segment_len)
finally:
if not isfilelike(lpath):
outfile.close()
def get(
self,
rpath,
lpath,
recursive=False,
callback=DEFAULT_CALLBACK,
maxdepth=None,
**kwargs,
):
"""Copy file(s) to local.
Copies a specific file or tree of files (if recursive=True). If lpath
ends with a "/", it will be assumed to be a directory, and target files
will go within. Can submit a list of paths, which may be glob-patterns
and will be expanded.
Calls get_file for each source.
"""
if isinstance(lpath, list) and isinstance(rpath, list):
# No need to expand paths when both source and destination
# are provided as lists
rpaths = rpath
lpaths = lpath
else:
from .implementations.local import (
LocalFileSystem,
make_path_posix,
trailing_sep,
)
source_is_str = isinstance(rpath, str)
rpaths = self.expand_path(rpath, recursive=recursive, maxdepth=maxdepth)
if source_is_str and (not recursive or maxdepth is not None):
# Non-recursive glob does not copy directories
rpaths = [p for p in rpaths if not (trailing_sep(p) or self.isdir(p))]
if not rpaths:
return
if isinstance(lpath, str):
lpath = make_path_posix(lpath)
source_is_file = len(rpaths) == 1
dest_is_dir = isinstance(lpath, str) and (
trailing_sep(lpath) or LocalFileSystem().isdir(lpath)
)
exists = source_is_str and (
(has_magic(rpath) and source_is_file)
or (not has_magic(rpath) and dest_is_dir and not trailing_sep(rpath))
)
lpaths = other_paths(
rpaths,
lpath,
exists=exists,
flatten=not source_is_str,
)
callback.set_size(len(lpaths))
for lpath, rpath in callback.wrap(zip(lpaths, rpaths)):
with callback.branched(rpath, lpath) as child:
self.get_file(rpath, lpath, callback=child, **kwargs)
def put_file(self, lpath, rpath, callback=DEFAULT_CALLBACK, **kwargs):
"""Copy single file to remote"""
if os.path.isdir(lpath):
self.makedirs(rpath, exist_ok=True)
return None
with open(lpath, "rb") as f1:
size = f1.seek(0, 2)
callback.set_size(size)
f1.seek(0)
self.mkdirs(self._parent(os.fspath(rpath)), exist_ok=True)
with self.open(rpath, "wb", **kwargs) as f2:
while f1.tell() < size:
data = f1.read(self.blocksize)
segment_len = f2.write(data)
if segment_len is None:
segment_len = len(data)
callback.relative_update(segment_len)
def put(
self,
lpath,
rpath,
recursive=False,
callback=DEFAULT_CALLBACK,
maxdepth=None,
**kwargs,
):
"""Copy file(s) from local.
Copies a specific file or tree of files (if recursive=True). If rpath
ends with a "/", it will be assumed to be a directory, and target files
will go within.
Calls put_file for each source.
"""
if isinstance(lpath, list) and isinstance(rpath, list):
# No need to expand paths when both source and destination
# are provided as lists
rpaths = rpath
lpaths = lpath
else:
from .implementations.local import (
LocalFileSystem,
make_path_posix,
trailing_sep,
)
source_is_str = isinstance(lpath, str)
if source_is_str:
lpath = make_path_posix(lpath)
fs = LocalFileSystem()
lpaths = fs.expand_path(lpath, recursive=recursive, maxdepth=maxdepth)
if source_is_str and (not recursive or maxdepth is not None):
# Non-recursive glob does not copy directories
lpaths = [p for p in lpaths if not (trailing_sep(p) or fs.isdir(p))]
if not lpaths:
return
source_is_file = len(lpaths) == 1
dest_is_dir = isinstance(rpath, str) and (
trailing_sep(rpath) or self.isdir(rpath)
)
rpath = (
self._strip_protocol(rpath)
if isinstance(rpath, str)
else [self._strip_protocol(p) for p in rpath]
)
exists = source_is_str and (
(has_magic(lpath) and source_is_file)
or (not has_magic(lpath) and dest_is_dir and not trailing_sep(lpath))
)
rpaths = other_paths(
lpaths,
rpath,
exists=exists,
flatten=not source_is_str,
)
callback.set_size(len(rpaths))
for lpath, rpath in callback.wrap(zip(lpaths, rpaths)):
with callback.branched(lpath, rpath) as child:
self.put_file(lpath, rpath, callback=child, **kwargs)
def head(self, path, size=1024):
"""Get the first ``size`` bytes from file"""
with self.open(path, "rb") as f:
return f.read(size)
def tail(self, path, size=1024):
"""Get the last ``size`` bytes from file"""
with self.open(path, "rb") as f:
f.seek(max(-size, -f.size), 2)
return f.read()
def cp_file(self, path1, path2, **kwargs):
raise NotImplementedError
def copy(
self, path1, path2, recursive=False, maxdepth=None, on_error=None, **kwargs
):
"""Copy within two locations in the filesystem
on_error : "raise", "ignore"
If raise, any not-found exceptions will be raised; if ignore any
not-found exceptions will cause the path to be skipped; defaults to
raise unless recursive is true, where the default is ignore
"""
if on_error is None and recursive:
on_error = "ignore"
elif on_error is None:
on_error = "raise"
if isinstance(path1, list) and isinstance(path2, list):
# No need to expand paths when both source and destination
# are provided as lists
paths1 = path1
paths2 = path2
else:
from .implementations.local import trailing_sep
source_is_str = isinstance(path1, str)
paths1 = self.expand_path(path1, recursive=recursive, maxdepth=maxdepth)
if source_is_str and (not recursive or maxdepth is not None):
# Non-recursive glob does not copy directories
paths1 = [p for p in paths1 if not (trailing_sep(p) or self.isdir(p))]
if not paths1:
return
source_is_file = len(paths1) == 1
dest_is_dir = isinstance(path2, str) and (
trailing_sep(path2) or self.isdir(path2)
)
exists = source_is_str and (
(has_magic(path1) and source_is_file)
or (not has_magic(path1) and dest_is_dir and not trailing_sep(path1))
)
paths2 = other_paths(
paths1,
path2,
exists=exists,
flatten=not source_is_str,
)
for p1, p2 in zip(paths1, paths2):
try:
self.cp_file(p1, p2, **kwargs)
except FileNotFoundError:
if on_error == "raise":
raise
def expand_path(self, path, recursive=False, maxdepth=None, **kwargs):
"""Turn one or more globs or directories into a list of all matching paths
to files or directories.
kwargs are passed to ``glob`` or ``find``, which may in turn call ``ls``
"""
if maxdepth is not None and maxdepth < 1:
raise ValueError("maxdepth must be at least 1")
if isinstance(path, (str, os.PathLike)):
out = self.expand_path([path], recursive, maxdepth)
else:
out = set()
path = [self._strip_protocol(p) for p in path]
for p in path:
if has_magic(p):
bit = set(self.glob(p, maxdepth=maxdepth, **kwargs))
out |= bit
if recursive:
# glob call above expanded one depth so if maxdepth is defined
# then decrement it in expand_path call below. If it is zero
# after decrementing then avoid expand_path call.
if maxdepth is not None and maxdepth <= 1:
continue
out |= set(
self.expand_path(
list(bit),
recursive=recursive,
maxdepth=maxdepth - 1 if maxdepth is not None else None,
**kwargs,
)
)
continue
elif recursive:
rec = set(
self.find(
p, maxdepth=maxdepth, withdirs=True, detail=False, **kwargs
)
)
out |= rec
if p not in out and (recursive is False or self.exists(p)):
# should only check once, for the root
out.add(p)
if not out:
raise FileNotFoundError(path)
return sorted(out)
def mv(self, path1, path2, recursive=False, maxdepth=None, **kwargs):
"""Move file(s) from one location to another"""
if path1 == path2:
logger.debug("%s mv: The paths are the same, so no files were moved.", self)
else:
# explicitly raise exception to prevent data corruption
self.copy(
path1, path2, recursive=recursive, maxdepth=maxdepth, onerror="raise"
)
self.rm(path1, recursive=recursive)
def rm_file(self, path):
"""Delete a file"""
self._rm(path)
def _rm(self, path):
"""Delete one file"""
# this is the old name for the method, prefer rm_file
raise NotImplementedError
def rm(self, path, recursive=False, maxdepth=None):
"""Delete files.
Parameters
----------
path: str or list of str
File(s) to delete.
recursive: bool
If file(s) are directories, recursively delete contents and then
also remove the directory
maxdepth: int or None
Depth to pass to walk for finding files to delete, if recursive.
If None, there will be no limit and infinite recursion may be
possible.
"""
path = self.expand_path(path, recursive=recursive, maxdepth=maxdepth)
for p in reversed(path):
self.rm_file(p)
@classmethod
def _parent(cls, path):
path = cls._strip_protocol(path)
if "/" in path:
parent = path.rsplit("/", 1)[0].lstrip(cls.root_marker)
return cls.root_marker + parent
else:
return cls.root_marker
def _open(
self,
path,
mode="rb",
block_size=None,
autocommit=True,
cache_options=None,
**kwargs,
):
"""Return raw bytes-mode file-like from the file-system"""
return AbstractBufferedFile(
self,
path,
mode,
block_size,
autocommit,
cache_options=cache_options,
**kwargs,
)
def open(
self,
path,
mode="rb",
block_size=None,
cache_options=None,
compression=None,
**kwargs,
):
"""
Return a file-like object from the filesystem
The resultant instance must function correctly in a context ``with``
block.
Parameters
----------
path: str
Target file
mode: str like 'rb', 'w'
See builtin ``open()``
block_size: int
Some indication of buffering - this is a value in bytes
cache_options : dict, optional
Extra arguments to pass through to the cache.
compression: string or None
If given, open file using compression codec. Can either be a compression
name (a key in ``fsspec.compression.compr``) or "infer" to guess the
compression from the filename suffix.
encoding, errors, newline: passed on to TextIOWrapper for text mode
"""
import io
path = self._strip_protocol(path)
if "b" not in mode:
mode = mode.replace("t", "") + "b"
text_kwargs = {
k: kwargs.pop(k)
for k in ["encoding", "errors", "newline"]
if k in kwargs
}
return io.TextIOWrapper(
self.open(
path,
mode,
block_size=block_size,
cache_options=cache_options,
compression=compression,
**kwargs,
),
**text_kwargs,
)
else:
ac = kwargs.pop("autocommit", not self._intrans)
f = self._open(
path,
mode=mode,
block_size=block_size,
autocommit=ac,
cache_options=cache_options,
**kwargs,
)
if compression is not None:
from fsspec.compression import compr
from fsspec.core import get_compression
compression = get_compression(path, compression)
compress = compr[compression]
f = compress(f, mode=mode[0])
if not ac and "r" not in mode:
self.transaction.files.append(f)
return f
def touch(self, path, truncate=True, **kwargs):
"""Create empty file, or update timestamp
Parameters
----------
path: str
file location
truncate: bool
If True, always set file size to 0; if False, update timestamp and
leave file unchanged, if backend allows this
"""
if truncate or not self.exists(path):
with self.open(path, "wb", **kwargs):
pass
else:
raise NotImplementedError # update timestamp, if possible
def ukey(self, path):
"""Hash of file properties, to tell if it has changed"""
return sha256(str(self.info(path)).encode()).hexdigest()
def read_block(self, fn, offset, length, delimiter=None):
"""Read a block of bytes from
Starting at ``offset`` of the file, read ``length`` bytes. If
``delimiter`` is set then we ensure that the read starts and stops at
delimiter boundaries that follow the locations ``offset`` and ``offset
+ length``. If ``offset`` is zero then we start at zero. The
bytestring returned WILL include the end delimiter string.
If offset+length is beyond the eof, reads to eof.
Parameters
----------
fn: string
Path to filename
offset: int
Byte offset to start read
length: int
Number of bytes to read. If None, read to end.
delimiter: bytes (optional)
Ensure reading starts and stops at delimiter bytestring
Examples
--------
>>> fs.read_block('data/file.csv', 0, 13) # doctest: +SKIP
b'Alice, 100\\nBo'
>>> fs.read_block('data/file.csv', 0, 13, delimiter=b'\\n') # doctest: +SKIP
b'Alice, 100\\nBob, 200\\n'
Use ``length=None`` to read to the end of the file.
>>> fs.read_block('data/file.csv', 0, None, delimiter=b'\\n') # doctest: +SKIP
b'Alice, 100\\nBob, 200\\nCharlie, 300'
See Also
--------
:func:`fsspec.utils.read_block`
"""
with self.open(fn, "rb") as f:
size = f.size
if length is None:
length = size
if size is not None and offset + length > size:
length = size - offset
return read_block(f, offset, length, delimiter)
def to_json(self):
"""
JSON representation of this filesystem instance
Returns
-------
str: JSON structure with keys cls (the python location of this class),
protocol (text name of this class's protocol, first one in case of
multiple), args (positional args, usually empty), and all other
kwargs as their own keys.
"""
import json
cls = type(self)
cls = ".".join((cls.__module__, cls.__name__))
proto = (
self.protocol[0]
if isinstance(self.protocol, (tuple, list))
else self.protocol
)
return json.dumps(
dict(
cls=cls,
protocol=proto,
args=self.storage_args,
**self.storage_options,
)
)
@staticmethod
def from_json(blob):
"""
Recreate a filesystem instance from JSON representation
See ``.to_json()`` for the expected structure of the input
Parameters
----------
blob: str
Returns
-------
file system instance, not necessarily of this particular class.
"""
import json
from .registry import _import_class, get_filesystem_class
dic = json.loads(blob)
protocol = dic.pop("protocol")
try:
cls = _import_class(dic.pop("cls"))
except (ImportError, ValueError, RuntimeError, KeyError):
cls = get_filesystem_class(protocol)
return cls(*dic.pop("args", ()), **dic)
def _get_pyarrow_filesystem(self):
"""
Make a version of the FS instance which will be acceptable to pyarrow
"""
# all instances already also derive from pyarrow
return self
def get_mapper(self, root="", check=False, create=False, missing_exceptions=None):
"""Create key/value store based on this file-system
Makes a MutableMapping interface to the FS at the given root path.
See ``fsspec.mapping.FSMap`` for further details.
"""
from .mapping import FSMap
return FSMap(
root,
self,
check=check,
create=create,
missing_exceptions=missing_exceptions,
)
@classmethod
def clear_instance_cache(cls):
"""
Clear the cache of filesystem instances.
Notes
-----
Unless overridden by setting the ``cachable`` class attribute to False,
the filesystem class stores a reference to newly created instances. This
prevents Python's normal rules around garbage collection from working,
since the instances refcount will not drop to zero until
``clear_instance_cache`` is called.
"""
cls._cache.clear()
def created(self, path):
"""Return the created timestamp of a file as a datetime.datetime"""
raise NotImplementedError
def modified(self, path):
"""Return the modified timestamp of a file as a datetime.datetime"""
raise NotImplementedError
# ------------------------------------------------------------------------
# Aliases
def read_bytes(self, path, start=None, end=None, **kwargs):
"""Alias of `AbstractFileSystem.cat_file`."""
return self.cat_file(path, start=start, end=end, **kwargs)
def write_bytes(self, path, value, **kwargs):
"""Alias of `AbstractFileSystem.pipe_file`."""
self.pipe_file(path, value, **kwargs)
def makedir(self, path, create_parents=True, **kwargs):
"""Alias of `AbstractFileSystem.mkdir`."""
return self.mkdir(path, create_parents=create_parents, **kwargs)
def mkdirs(self, path, exist_ok=False):
"""Alias of `AbstractFileSystem.makedirs`."""
return self.makedirs(path, exist_ok=exist_ok)
def listdir(self, path, detail=True, **kwargs):
"""Alias of `AbstractFileSystem.ls`."""
return self.ls(path, detail=detail, **kwargs)
def cp(self, path1, path2, **kwargs):
"""Alias of `AbstractFileSystem.copy`."""
return self.copy(path1, path2, **kwargs)
def move(self, path1, path2, **kwargs):
"""Alias of `AbstractFileSystem.mv`."""
return self.mv(path1, path2, **kwargs)
def stat(self, path, **kwargs):
"""Alias of `AbstractFileSystem.info`."""
return self.info(path, **kwargs)
def disk_usage(self, path, total=True, maxdepth=None, **kwargs):
"""Alias of `AbstractFileSystem.du`."""
return self.du(path, total=total, maxdepth=maxdepth, **kwargs)
def rename(self, path1, path2, **kwargs):
"""Alias of `AbstractFileSystem.mv`."""
return self.mv(path1, path2, **kwargs)
def delete(self, path, recursive=False, maxdepth=None):
"""Alias of `AbstractFileSystem.rm`."""
return self.rm(path, recursive=recursive, maxdepth=maxdepth)
def upload(self, lpath, rpath, recursive=False, **kwargs):
"""Alias of `AbstractFileSystem.put`."""
return self.put(lpath, rpath, recursive=recursive, **kwargs)
def download(self, rpath, lpath, recursive=False, **kwargs):
"""Alias of `AbstractFileSystem.get`."""
return self.get(rpath, lpath, recursive=recursive, **kwargs)
def sign(self, path, expiration=100, **kwargs):
"""Create a signed URL representing the given path
Some implementations allow temporary URLs to be generated, as a
way of delegating credentials.
Parameters
----------
path : str
The path on the filesystem
expiration : int
Number of seconds to enable the URL for (if supported)
Returns
-------
URL : str
The signed URL
Raises
------
NotImplementedError : if method is not implemented for a filesystem
"""
raise NotImplementedError("Sign is not implemented for this filesystem")
def _isfilestore(self):
# Originally inherited from pyarrow DaskFileSystem. Keeping this
# here for backwards compatibility as long as pyarrow uses its
# legacy fsspec-compatible filesystems and thus accepts fsspec
# filesystems as well
return False
class AbstractBufferedFile(io.IOBase):
"""Convenient class to derive from to provide buffering
In the case that the backend does not provide a pythonic file-like object
already, this class contains much of the logic to build one. The only
methods that need to be overridden are ``_upload_chunk``,
``_initiate_upload`` and ``_fetch_range``.
"""
DEFAULT_BLOCK_SIZE = 5 * 2**20
_details = None
def __init__(
self,
fs,
path,
mode="rb",
block_size="default",
autocommit=True,
cache_type="readahead",
cache_options=None,
size=None,
**kwargs,
):
"""
Template for files with buffered reading and writing
Parameters
----------
fs: instance of FileSystem
path: str
location in file-system
mode: str
Normal file modes. Currently only 'wb', 'ab' or 'rb'. Some file
systems may be read-only, and some may not support append.
block_size: int
Buffer size for reading or writing, 'default' for class default
autocommit: bool
Whether to write to final destination; may only impact what
happens when file is being closed.
cache_type: {"readahead", "none", "mmap", "bytes"}, default "readahead"
Caching policy in read mode. See the definitions in ``core``.
cache_options : dict
Additional options passed to the constructor for the cache specified
by `cache_type`.
size: int
If given and in read mode, suppressed having to look up the file size
kwargs:
Gets stored as self.kwargs
"""
from .core import caches
self.path = path
self.fs = fs
self.mode = mode
self.blocksize = (
self.DEFAULT_BLOCK_SIZE if block_size in ["default", None] else block_size
)
self.loc = 0
self.autocommit = autocommit
self.end = None
self.start = None
self.closed = False
if cache_options is None:
cache_options = {}
if "trim" in kwargs:
warnings.warn(
"Passing 'trim' to control the cache behavior has been deprecated. "
"Specify it within the 'cache_options' argument instead.",
FutureWarning,
)
cache_options["trim"] = kwargs.pop("trim")
self.kwargs = kwargs
if mode not in {"ab", "rb", "wb"}:
raise NotImplementedError("File mode not supported")
if mode == "rb":
if size is not None:
self.size = size
else:
self.size = self.details["size"]
self.cache = caches[cache_type](
self.blocksize, self._fetch_range, self.size, **cache_options
)
else:
self.buffer = io.BytesIO()
self.offset = None
self.forced = False
self.location = None
@property
def details(self):
if self._details is None:
self._details = self.fs.info(self.path)
return self._details
@details.setter
def details(self, value):
self._details = value
self.size = value["size"]
@property
def full_name(self):
return _unstrip_protocol(self.path, self.fs)
@property
def closed(self):
# get around this attr being read-only in IOBase
# use getattr here, since this can be called during del
return getattr(self, "_closed", True)
@closed.setter
def closed(self, c):
self._closed = c
def __hash__(self):
if "w" in self.mode:
return id(self)
else:
return int(tokenize(self.details), 16)
def __eq__(self, other):
"""Files are equal if they have the same checksum, only in read mode"""
if self is other:
return True
return (
isinstance(other, type(self))
and self.mode == "rb"
and other.mode == "rb"
and hash(self) == hash(other)
)
def commit(self):
"""Move from temp to final destination"""
def discard(self):
"""Throw away temporary file"""
def info(self):
"""File information about this path"""
if "r" in self.mode:
return self.details
else:
raise ValueError("Info not available while writing")
def tell(self):
"""Current file location"""
return self.loc
def seek(self, loc, whence=0):
"""Set current file location
Parameters
----------
loc: int
byte location
whence: {0, 1, 2}
from start of file, current location or end of file, resp.
"""
loc = int(loc)
if not self.mode == "rb":
raise OSError(ESPIPE, "Seek only available in read mode")
if whence == 0:
nloc = loc
elif whence == 1:
nloc = self.loc + loc
elif whence == 2:
nloc = self.size + loc
else:
raise ValueError(f"invalid whence ({whence}, should be 0, 1 or 2)")
if nloc < 0:
raise ValueError("Seek before start of file")
self.loc = nloc
return self.loc
def write(self, data):
"""
Write data to buffer.
Buffer only sent on flush() or if buffer is greater than
or equal to blocksize.
Parameters
----------
data: bytes
Set of bytes to be written.
"""
if self.mode not in {"wb", "ab"}:
raise ValueError("File not in write mode")
if self.closed:
raise ValueError("I/O operation on closed file.")
if self.forced:
raise ValueError("This file has been force-flushed, can only close")
out = self.buffer.write(data)
self.loc += out
if self.buffer.tell() >= self.blocksize:
self.flush()
return out
def flush(self, force=False):
"""
Write buffered data to backend store.
Writes the current buffer, if it is larger than the block-size, or if
the file is being closed.
Parameters
----------
force: bool
When closing, write the last block even if it is smaller than
blocks are allowed to be. Disallows further writing to this file.
"""
if self.closed:
raise ValueError("Flush on closed file")
if force and self.forced:
raise ValueError("Force flush cannot be called more than once")
if force:
self.forced = True
if self.mode not in {"wb", "ab"}:
# no-op to flush on read-mode
return
if not force and self.buffer.tell() < self.blocksize:
# Defer write on small block
return
if self.offset is None:
# Initialize a multipart upload
self.offset = 0
try:
self._initiate_upload()
except: # noqa: E722
self.closed = True
raise
if self._upload_chunk(final=force) is not False:
self.offset += self.buffer.seek(0, 2)
self.buffer = io.BytesIO()
def _upload_chunk(self, final=False):
"""Write one part of a multi-block file upload
Parameters
==========
final: bool
This is the last block, so should complete file, if
self.autocommit is True.
"""
# may not yet have been initialized, may need to call _initialize_upload
def _initiate_upload(self):
"""Create remote file/upload"""
pass
def _fetch_range(self, start, end):
"""Get the specified set of bytes from remote"""
raise NotImplementedError
def read(self, length=-1):
"""
Return data from cache, or fetch pieces as necessary
Parameters
----------
length: int (-1)
Number of bytes to read; if <0, all remaining bytes.
"""
length = -1 if length is None else int(length)
if self.mode != "rb":
raise ValueError("File not in read mode")
if length < 0:
length = self.size - self.loc
if self.closed:
raise ValueError("I/O operation on closed file.")
if length == 0:
# don't even bother calling fetch
return b""
out = self.cache._fetch(self.loc, self.loc + length)
logger.debug(
"%s read: %i - %i %s",
self,
self.loc,
self.loc + length,
self.cache._log_stats(),
)
self.loc += len(out)
return out
def readinto(self, b):
"""mirrors builtin file's readinto method
https://docs.python.org/3/library/io.html#io.RawIOBase.readinto
"""
out = memoryview(b).cast("B")
data = self.read(out.nbytes)
out[: len(data)] = data
return len(data)
def readuntil(self, char=b"\n", blocks=None):
"""Return data between current position and first occurrence of char
char is included in the output, except if the end of the tile is
encountered first.
Parameters
----------
char: bytes
Thing to find
blocks: None or int
How much to read in each go. Defaults to file blocksize - which may
mean a new read on every call.
"""
out = []
while True:
start = self.tell()
part = self.read(blocks or self.blocksize)
if len(part) == 0:
break
found = part.find(char)
if found > -1:
out.append(part[: found + len(char)])
self.seek(start + found + len(char))
break
out.append(part)
return b"".join(out)
def readline(self):
"""Read until first occurrence of newline character
Note that, because of character encoding, this is not necessarily a
true line ending.
"""
return self.readuntil(b"\n")
def __next__(self):
out = self.readline()
if out:
return out
raise StopIteration
def __iter__(self):
return self
def readlines(self):
"""Return all data, split by the newline character"""
data = self.read()
lines = data.split(b"\n")
out = [l + b"\n" for l in lines[:-1]]
if data.endswith(b"\n"):
return out
else:
return out + [lines[-1]]
# return list(self) ???
def readinto1(self, b):
return self.readinto(b)
def close(self):
"""Close file
Finalizes writes, discards cache
"""
if getattr(self, "_unclosable", False):
return
if self.closed:
return
if self.mode == "rb":
self.cache = None
else:
if not self.forced:
self.flush(force=True)
if self.fs is not None:
self.fs.invalidate_cache(self.path)
self.fs.invalidate_cache(self.fs._parent(self.path))
self.closed = True
def readable(self):
"""Whether opened for reading"""
return self.mode == "rb" and not self.closed
def seekable(self):
"""Whether is seekable (only in read mode)"""
return self.readable()
def writable(self):
"""Whether opened for writing"""
return self.mode in {"wb", "ab"} and not self.closed
def __del__(self):
if not self.closed:
self.close()
def __str__(self):
return f"<File-like object {type(self.fs).__name__}, {self.path}>"
__repr__ = __str__
def __enter__(self):
return self
def __exit__(self, *args):
self.close()
|