diff options
author | thegeorg <thegeorg@yandex-team.com> | 2024-02-19 02:38:52 +0300 |
---|---|---|
committer | thegeorg <thegeorg@yandex-team.com> | 2024-02-19 02:50:43 +0300 |
commit | d96fa07134c06472bfee6718b5cfd1679196fc99 (patch) | |
tree | 31ec344fa9d3ff8dc038692516b6438dfbdb8a2d /contrib/tools/python3/Lib/shelve.py | |
parent | 452cf9e068aef7110e35e654c5d47eb80111ef89 (diff) | |
download | ydb-d96fa07134c06472bfee6718b5cfd1679196fc99.tar.gz |
Sync contrib/tools/python3 layout with upstream
* Move src/ subdir contents to the top of the layout
* Rename self-written lib -> lib2 to avoid CaseFolding warning from the VCS
* Regenerate contrib/libs/python proxy-headers accordingly
4ccc62ac1511abcf0fed14ccade38e984e088f1e
Diffstat (limited to 'contrib/tools/python3/Lib/shelve.py')
-rw-r--r-- | contrib/tools/python3/Lib/shelve.py | 243 |
1 files changed, 243 insertions, 0 deletions
diff --git a/contrib/tools/python3/Lib/shelve.py b/contrib/tools/python3/Lib/shelve.py new file mode 100644 index 0000000000..e053c39734 --- /dev/null +++ b/contrib/tools/python3/Lib/shelve.py @@ -0,0 +1,243 @@ +"""Manage shelves of pickled objects. + +A "shelf" is a persistent, dictionary-like object. The difference +with dbm databases is that the values (not the keys!) in a shelf can +be essentially arbitrary Python objects -- anything that the "pickle" +module can handle. This includes most class instances, recursive data +types, and objects containing lots of shared sub-objects. The keys +are ordinary strings. + +To summarize the interface (key is a string, data is an arbitrary +object): + + import shelve + d = shelve.open(filename) # open, with (g)dbm filename -- no suffix + + d[key] = data # store data at key (overwrites old data if + # using an existing key) + data = d[key] # retrieve a COPY of the data at key (raise + # KeyError if no such key) -- NOTE that this + # access returns a *copy* of the entry! + del d[key] # delete data stored at key (raises KeyError + # if no such key) + flag = key in d # true if the key exists + list = d.keys() # a list of all existing keys (slow!) + + d.close() # close it + +Dependent on the implementation, closing a persistent dictionary may +or may not be necessary to flush changes to disk. + +Normally, d[key] returns a COPY of the entry. This needs care when +mutable entries are mutated: for example, if d[key] is a list, + d[key].append(anitem) +does NOT modify the entry d[key] itself, as stored in the persistent +mapping -- it only modifies the copy, which is then immediately +discarded, so that the append has NO effect whatsoever. To append an +item to d[key] in a way that will affect the persistent mapping, use: + data = d[key] + data.append(anitem) + d[key] = data + +To avoid the problem with mutable entries, you may pass the keyword +argument writeback=True in the call to shelve.open. When you use: + d = shelve.open(filename, writeback=True) +then d keeps a cache of all entries you access, and writes them all back +to the persistent mapping when you call d.close(). This ensures that +such usage as d[key].append(anitem) works as intended. + +However, using keyword argument writeback=True may consume vast amount +of memory for the cache, and it may make d.close() very slow, if you +access many of d's entries after opening it in this way: d has no way to +check which of the entries you access are mutable and/or which ones you +actually mutate, so it must cache, and write back at close, all of the +entries that you access. You can call d.sync() to write back all the +entries in the cache, and empty the cache (d.sync() also synchronizes +the persistent dictionary on disk, if feasible). +""" + +from pickle import DEFAULT_PROTOCOL, Pickler, Unpickler +from io import BytesIO + +import collections.abc + +__all__ = ["Shelf", "BsdDbShelf", "DbfilenameShelf", "open"] + +class _ClosedDict(collections.abc.MutableMapping): + 'Marker for a closed dict. Access attempts raise a ValueError.' + + def closed(self, *args): + raise ValueError('invalid operation on closed shelf') + __iter__ = __len__ = __getitem__ = __setitem__ = __delitem__ = keys = closed + + def __repr__(self): + return '<Closed Dictionary>' + + +class Shelf(collections.abc.MutableMapping): + """Base class for shelf implementations. + + This is initialized with a dictionary-like object. + See the module's __doc__ string for an overview of the interface. + """ + + def __init__(self, dict, protocol=None, writeback=False, + keyencoding="utf-8"): + self.dict = dict + if protocol is None: + protocol = DEFAULT_PROTOCOL + self._protocol = protocol + self.writeback = writeback + self.cache = {} + self.keyencoding = keyencoding + + def __iter__(self): + for k in self.dict.keys(): + yield k.decode(self.keyencoding) + + def __len__(self): + return len(self.dict) + + def __contains__(self, key): + return key.encode(self.keyencoding) in self.dict + + def get(self, key, default=None): + if key.encode(self.keyencoding) in self.dict: + return self[key] + return default + + def __getitem__(self, key): + try: + value = self.cache[key] + except KeyError: + f = BytesIO(self.dict[key.encode(self.keyencoding)]) + value = Unpickler(f).load() + if self.writeback: + self.cache[key] = value + return value + + def __setitem__(self, key, value): + if self.writeback: + self.cache[key] = value + f = BytesIO() + p = Pickler(f, self._protocol) + p.dump(value) + self.dict[key.encode(self.keyencoding)] = f.getvalue() + + def __delitem__(self, key): + del self.dict[key.encode(self.keyencoding)] + try: + del self.cache[key] + except KeyError: + pass + + def __enter__(self): + return self + + def __exit__(self, type, value, traceback): + self.close() + + def close(self): + if self.dict is None: + return + try: + self.sync() + try: + self.dict.close() + except AttributeError: + pass + finally: + # Catch errors that may happen when close is called from __del__ + # because CPython is in interpreter shutdown. + try: + self.dict = _ClosedDict() + except: + self.dict = None + + def __del__(self): + if not hasattr(self, 'writeback'): + # __init__ didn't succeed, so don't bother closing + # see http://bugs.python.org/issue1339007 for details + return + self.close() + + def sync(self): + if self.writeback and self.cache: + self.writeback = False + for key, entry in self.cache.items(): + self[key] = entry + self.writeback = True + self.cache = {} + if hasattr(self.dict, 'sync'): + self.dict.sync() + + +class BsdDbShelf(Shelf): + """Shelf implementation using the "BSD" db interface. + + This adds methods first(), next(), previous(), last() and + set_location() that have no counterpart in [g]dbm databases. + + The actual database must be opened using one of the "bsddb" + modules "open" routines (i.e. bsddb.hashopen, bsddb.btopen or + bsddb.rnopen) and passed to the constructor. + + See the module's __doc__ string for an overview of the interface. + """ + + def __init__(self, dict, protocol=None, writeback=False, + keyencoding="utf-8"): + Shelf.__init__(self, dict, protocol, writeback, keyencoding) + + def set_location(self, key): + (key, value) = self.dict.set_location(key) + f = BytesIO(value) + return (key.decode(self.keyencoding), Unpickler(f).load()) + + def next(self): + (key, value) = next(self.dict) + f = BytesIO(value) + return (key.decode(self.keyencoding), Unpickler(f).load()) + + def previous(self): + (key, value) = self.dict.previous() + f = BytesIO(value) + return (key.decode(self.keyencoding), Unpickler(f).load()) + + def first(self): + (key, value) = self.dict.first() + f = BytesIO(value) + return (key.decode(self.keyencoding), Unpickler(f).load()) + + def last(self): + (key, value) = self.dict.last() + f = BytesIO(value) + return (key.decode(self.keyencoding), Unpickler(f).load()) + + +class DbfilenameShelf(Shelf): + """Shelf implementation using the "dbm" generic dbm interface. + + This is initialized with the filename for the dbm database. + See the module's __doc__ string for an overview of the interface. + """ + + def __init__(self, filename, flag='c', protocol=None, writeback=False): + import dbm + Shelf.__init__(self, dbm.open(filename, flag), protocol, writeback) + + +def open(filename, flag='c', protocol=None, writeback=False): + """Open a persistent dictionary for reading and writing. + + The filename parameter is the base filename for the underlying + database. As a side-effect, an extension may be added to the + filename and more than one file may be created. The optional flag + parameter has the same interpretation as the flag parameter of + dbm.open(). The optional protocol parameter specifies the + version of the pickle protocol. + + See the module's __doc__ string for an overview of the interface. + """ + + return DbfilenameShelf(filename, flag, protocol, writeback) |