dumbdbm.py 4.4 KB
Newer Older
Guido van Rossum's avatar
Guido van Rossum committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
"""A dumb and slow but simple dbm clone.

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:

- seems to contain a bug when updating...

- 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)

- support opening for read-only (flag = 'm')

"""

24
import os as _os
Guido van Rossum's avatar
Guido van Rossum committed
25 26 27 28 29 30
import __builtin__

_open = __builtin__.open

_BLOCKSIZE = 512

Tim Peters's avatar
Tim Peters committed
31
error = IOError                         # For anydbm
32

Guido van Rossum's avatar
Guido van Rossum committed
33 34
class _Database:

35 36
    def __init__(self, file, mode):
        self._mode = mode
37 38 39
        self._dirfile = file + _os.extsep + 'dir'
        self._datfile = file + _os.extsep + 'dat'
        self._bakfile = file + _os.extsep + 'bak'
Tim Peters's avatar
Tim Peters committed
40 41 42 43
        # Mod by Jack: create data file if needed
        try:
            f = _open(self._datfile, 'r')
        except IOError:
44
            f = _open(self._datfile, 'w', self._mode)
Tim Peters's avatar
Tim Peters committed
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
        f.close()
        self._update()

    def _update(self):
        self._index = {}
        try:
            f = _open(self._dirfile)
        except IOError:
            pass
        else:
            while 1:
                line = f.readline().rstrip()
                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
67
        f = _open(self._dirfile, 'w', self._mode)
Tim Peters's avatar
Tim Peters committed
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83
        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 = int(f.tell())
Guido van Rossum's avatar
Guido van Rossum committed
84
## Does not work under MW compiler
Tim Peters's avatar
Tim Peters committed
85 86
##              pos = ((pos + _BLOCKSIZE - 1) / _BLOCKSIZE) * _BLOCKSIZE
##              f.seek(pos)
87
        npos = ((pos + _BLOCKSIZE - 1) // _BLOCKSIZE) * _BLOCKSIZE
Tim Peters's avatar
Tim Peters committed
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103
        f.write('\0'*(npos-pos))
        pos = npos

        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, len(val))

    def _addkey(self, key, (pos, siz)):
        self._index[key] = (pos, siz)
104
        f = _open(self._dirfile, 'a', self._mode)
Tim Peters's avatar
Tim Peters committed
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
        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, "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

    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)

135 136 137 138 139 140 141
    def __contains__(self, key):
        return self._index.has_key(key)

    def iterkeys(self):
        return self._index.iterkeys()
    __iter__ = iterkeys

Tim Peters's avatar
Tim Peters committed
142 143 144 145
    def __len__(self):
        return len(self._index)

    def close(self):
146
        self._commit()
Tim Peters's avatar
Tim Peters committed
147 148
        self._index = None
        self._datfile = self._dirfile = self._bakfile = None
Guido van Rossum's avatar
Guido van Rossum committed
149

150 151 152
    def __del__(self):
        if self._index is not None:
            self._commit()
Tim Peters's avatar
Tim Peters committed
153

154

Guido van Rossum's avatar
Guido van Rossum committed
155

156
def open(file, flag=None, mode=0666):
Tim Peters's avatar
Tim Peters committed
157
    # flag, mode arguments are currently ignored
158
    return _Database(file, mode)