shelve.py: database of persistent objects, on top of pickle.py and anydbm.py

pickle.py: new low-level persistency module (used to be called flatten)
dbmac.py: stupid dbm clone for the Mac
anydbm.py: generic dbm interface (should be extended to support gdbm)

Lib/anydbm.py

+"""A generic interface to all dbm clones."""
+
+try:
+	import dbm
+	def open(file, mode = 'rw'):
+		return dbm.open(file, mode, 0666)
+except ImportError:
+	import dbmac
+	open = dbmac.open

Lib/shelve.py

+"""Manage shelves of pickled objects."""
+
+import pickle
+import StringIO
+
+class Shelf:
+
+	def __init__(self, dict):
+		self.dict = dict
+	
+	def keys(self):
+		return self.dict.keys()
+	
+	def __len__(self):
+		return self.dict.len()
+	
+	def has_key(self, key):
+		return self.dict.has_key(key)
+	
+	def __getitem__(self, key):
+		return pickle.Unpickler(StringIO.StringIO(self.dict[key])).load()
+	
+	def __setitem__(self, key, value):
+		f = StringIO.StringIO()
+		p = pickle.Pickler(f)
+		p.dump(value)
+		self.dict[key] = f.getvalue()
+	
+	def __delitem__(self, key):
+		del self.dict[key]
+	
+	def close(self):
+		self.db.close()
+		self.db = None
+
+class DbShelf(Shelf):
+	
+	def __init__(self, file):
+		import anydbm
+		Shelf.__init__(self, anydbm.open(file))
+
+def open(file):
+	return DbShelf(file)

Mac/Lib/dbmac.py

+"""A slow but simple dbm clone for the Mac.
+
+For database spam, spam.dir contains the index (a text file),
+spam.bak *may* contain a backup of the index (also a text file),
+while spam.dat contains the data (a binary file).
+
+XXX TO DO:
+
+- reclaim free space (currently, space once occupied by deleted or expanded
+items is never reused)
+
+- support concurrent access (currently, if two processes take turns making
+updates, they can mess up the index)
+
+- support efficient access to large databases (currently, the whole index
+is read when the database is opened, and some updates rewrite the whole index)
+"""
+
+_os = __import__('os')
+import __builtin__
+
+_open = __builtin__.open
+
+_BLOCKSIZE = 512
+
+class _Database:
+
+	def __init__(self, file):
+		self._dirfile = file + '.dir'
+		self._datfile = file + '.dat'
+		self._bakfile = file + '.bak'
+		self._update()
+	
+	def _update(self):
+		self._index = {}
+		try:
+			f = _open(self._dirfile)
+		except IOError:
+			pass
+		else:
+			while 1:
+				line = f.readline()
+				if not line: break
+				key, (pos, siz) = eval(line)
+				self._index[key] = (pos, siz)
+			f.close()
+
+	def _commit(self):
+		try: _os.unlink(self._bakfile)
+		except _os.error: pass
+		try: _os.rename(self._dirfile, self._bakfile)
+		except _os.error: pass
+		f = _open(self._dirfile, 'w')
+		for key, (pos, siz) in self._index.items():
+			f.write("%s, (%s, %s)\n" % (`key`, `pos`, `siz`))
+		f.close()
+	
+	def __getitem__(self, key):
+		pos, siz = self._index[key]	# may raise KeyError
+		f = _open(self._datfile, 'rb')
+		f.seek(pos)
+		dat = f.read(siz)
+		f.close()
+		return dat
+	
+	def _addval(self, val):
+		f = _open(self._datfile, 'rb+')
+		f.seek(0, 2)
+		pos = f.tell()
+		pos = ((pos + _BLOCKSIZE - 1) / _BLOCKSIZE) * _BLOCKSIZE
+		f.seek(pos)
+		f.write(val)
+		f.close()
+		return (pos, len(val))
+	
+	def _setval(self, pos, val):
+		f = _open(self._datfile, 'rb+')
+		f.seek(pos)
+		f.write(val)
+		f.close()
+		return pos, (val)
+	
+	def _addkey(self, key, (pos, siz)):
+		self._index[key] = (pos, siz)
+		f = _open(self._dirfile, 'a')
+		f.write("%s, (%s, %s)\n" % (`key`, `pos`, `siz`))
+		f.close()
+	
+	def __setitem__(self, key, val):
+		if not type(key) == type('') == type(val):
+			raise TypeError, "dbmac keys and values must be strings"
+		if not self._index.has_key(key):
+			(pos, siz) = self._addval(val)
+			self._addkey(key, (pos, siz))
+		else:
+			pos, siz = self._index[key]
+			oldblocks = (siz + _BLOCKSIZE - 1) / _BLOCKSIZE
+			newblocks = (len(val) + _BLOCKSIZE - 1) / _BLOCKSIZE
+			if newblocks <= oldblocks:
+				pos, siz = self._setval(pos, val)
+				self._index[key] = pos, siz
+			else:
+				pos, siz = self._addval(val)
+				self._index[key] = pos, siz
+			self._addkey(key, (pos, siz))
+	
+	def __delitem__(self, key):
+		del self._index[key]
+		self._commit()
+	
+	def keys(self):
+		return self._index.keys()
+	
+	def has_key(self, key):
+		return self._index.has_key(key)
+	
+	def __len__(self):
+		return len(self._index)
+	
+	def close(self):
+		self._index = self._datfile = self._dirfile = self._bakfile = None
+
+
+def open(file, mode = None):
+	return _Database(file)