3 # Copyright 2011 GRNET S.A. All rights reserved.
5 # Redistribution and use in source and binary forms, with or
6 # without modification, are permitted provided that the following
9 # 1. Redistributions of source code must retain the above
10 # copyright notice, this list of conditions and the following
13 # 2. Redistributions in binary form must reproduce the above
14 # copyright notice, this list of conditions and the following
15 # disclaimer in the documentation and/or other materials
16 # provided with the distribution.
18 # THIS SOFTWARE IS PROVIDED BY GRNET S.A. ``AS IS'' AND ANY EXPRESS
19 # OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
20 # WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
21 # PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL GRNET S.A OR
22 # CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
25 # USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
26 # AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 # LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
28 # ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
29 # POSSIBILITY OF SUCH DAMAGE.
31 # The views and conclusions contained in the software and
32 # documentation are those of the authors and should not be
33 # interpreted as representing official policies, either expressed
34 # or implied, of GRNET S.A.
36 from binascii import hexlify
38 from sqlalchemy import create_engine
39 from sqlalchemy import Table, Column, String, MetaData
40 from sqlalchemy.sql import select
42 from pithos import settings
43 from pithos.backends.modular import ModularBackend
45 from lib.hashmap import HashMap
46 from lib.migrate import Migration
48 class DataMigration(Migration):
49 def __init__(self, pithosdb, db):
50 Migration.__init__(self, pithosdb)
51 # XXX Need more columns for primary key - last modified timestamp...
52 engine = create_engine(db)
53 metadata = MetaData(engine)
56 columns.append(Column('path', String(2048), primary_key=True))
57 columns.append(Column('hash', String(255)))
58 self.files = Table('files', metadata, *columns)
59 metadata.create_all(engine)
61 def cache_put(self, path, hash):
63 s = self.files.delete().where(self.files.c.path==path)
64 r = self.conn.execute(s)
66 s = self.files.insert()
67 r = self.conn.execute(s, {'path': path, 'hash': hash})
70 def cache_get(self, path):
71 s = select([self.files.c.hash], self.files.c.path == path)
72 r = self.conn.execute(s)
80 blocksize = self.backend.block_size
81 blockhash = self.backend.hash_algorithm
83 # Loop for all available files.
84 filebody = Table('filebody', self.metadata, autoload=True)
85 s = select([filebody.c.storedfilepath])
86 rp = self.conn.execute(s)
91 map = HashMap(blocksize, blockhash)
93 hash = hexlify(map.hash())
95 if hash != self.cache_get(path):
96 missing = self.backend.blocker.block_ping(map) # XXX Backend hack...
97 status = '[>] ' + path
99 status += ' - %d block(s) missing' % len(missing)
100 with open(path) as fp:
102 offset = map.index(h) * blocksize
104 block = fp.read(blocksize)
105 self.backend.put_block(block)
107 status += ' - no blocks missing'
108 self.cache_put(path, hash)
110 status = '[-] ' + path
113 if __name__ == "__main__":
115 db = 'sqlite:///migrate.db'
117 dt = DataMigration(pithosdb, db)