Python SqliteDict.terminate方法代码示例

# 需要导入模块: from sqlitedict import SqliteDict [as 别名]
# 或者: from sqlitedict.SqliteDict import terminate [as 别名]
class SqliteDictTerminateFailTest(unittest.TestCase):
    """Provide Coverage for SqliteDict.terminate()."""

    def setUp(self):
        self.fname = norm_file('tests/db-permdenied/sqlitedict.sqlite')
        self.db = SqliteDict(filename=self.fname)
        os.chmod(self.fname, 0o000)
        os.chmod(os.path.dirname(self.fname), 0o000)

    def tearDown(self):
        os.chmod(os.path.dirname(self.fname), 0o700)
        os.chmod(self.fname, 0o600)
        os.unlink(self.fname)
        os.rmdir(os.path.dirname(self.fname))

    def test_terminate_cannot_delete(self):
        # exercise,
        self.db.terminate()  # deletion failed, but no exception raised!

        # verify,
        os.chmod(os.path.dirname(self.fname), 0o700)
        os.chmod(self.fname, 0o600)
        self.assertTrue(os.path.exists(self.fname))

# 需要导入模块: from sqlitedict import SqliteDict [as 别名]
# 或者: from sqlitedict.SqliteDict import terminate [as 别名]
class SimIndex(gensim.utils.SaveLoad):
    """
    An index of documents. Used internally by SimServer.

    It uses the Similarity class to persist all document vectors to disk (via mmap).
    """
    def __init__(self, fname, num_features, shardsize=SHARD_SIZE, topsims=TOP_SIMS):
        """
        Spill index shards to disk after every `shardsize` documents.
        In similarity queries, return only the `topsims` most similar documents.
        """
        self.fname = fname
        self.shardsize = int(shardsize)
        self.topsims = int(topsims)
        self.id2pos = {} # map document id (string) to index position (integer)
        self.pos2id = {} # reverse mapping for id2pos; redundant, for performance
        self.id2sims = SqliteDict(self.fname + '.id2sims', journal_mode=JOURNAL_MODE) # precomputed top similar: document id -> [(doc_id, similarity)]
        self.qindex = gensim.similarities.Similarity(self.fname + '.idx', corpus=None,
            num_best=None, num_features=num_features, shardsize=shardsize)
        self.length = 0

    def save(self, fname):
        tmp, self.id2sims = self.id2sims, None
        super(SimIndex, self).save(fname)
        self.id2sims = tmp


    @staticmethod
    def load(fname):
        result = gensim.utils.SaveLoad.load(fname)
        result.fname = fname
        result.check_moved()
        result.id2sims = SqliteDict(fname + '.id2sims', journal_mode=JOURNAL_MODE)
        return result


    def check_moved(self):
        output_prefix = self.fname + '.idx'
        if self.qindex.output_prefix != output_prefix:
            logger.info("index seems to have moved from %s to %s; updating locations" %
                (self.qindex.output_prefix, output_prefix))
            self.qindex.output_prefix = output_prefix
            self.qindex.check_moved()


    def close(self):
        "Explicitly release important resources (file handles, db, ...)"
        try:
            self.id2sims.close()
        except:
            pass
        try:
            del self.qindex
        except:
            pass


    def terminate(self):
        """Delete all files created by this index, invalidating `self`. Use with care."""
        try:
            self.id2sims.terminate()
        except:
            pass
        import glob
        for fname in glob.glob(self.fname + '*'):
            try:
                os.remove(fname)
                logger.info("deleted %s" % fname)
            except Exception, e:
                logger.warning("failed to delete %s: %s" % (fname, e))
        for val in self.__dict__.keys():
            try:
                delattr(self, val)
            except:
                pass

# 需要导入模块: from sqlitedict import SqliteDict [as 别名]
# 或者: from sqlitedict.SqliteDict import terminate [as 别名]
class SimServer(object):
    """
    Top-level functionality for similarity services. A similarity server takes
    care of::

    1. creating semantic models
    2. indexing documents using these models
    3. finding the most similar documents in an index.

    An object of this class can be shared across network via Pyro, to answer remote
    client requests. It is thread safe. Using a server concurrently from multiple
    processes is safe for reading = answering similarity queries. Modifying
    (training/indexing) is realized via locking = serialized internally.
    """
    def __init__(self, basename, use_locks=False):
        """
        All data will be stored under directory `basename`. If there is a server
        there already, it will be loaded (resumed).

        The server object is stateless in RAM -- its state is defined entirely by its location.
        There is therefore no need to store the server object.
        """
        if not os.path.isdir(basename):
            raise ValueError("%r must be a writable directory" % basename)
        self.basename = basename
        self.use_locks = use_locks
        self.lock_update = threading.RLock() if use_locks else gensim.utils.nocm
        try:
            self.fresh_index = SimIndex.load(self.location('index_fresh'))
        except:
            logger.debug("starting a new fresh index")
            self.fresh_index = None
        try:
            self.opt_index = SimIndex.load(self.location('index_opt'))
        except:
            logger.debug("starting a new optimized index")
            self.opt_index = None
        try:
            self.model = SimModel.load(self.location('model'))
        except:
            self.model = None
        self.payload = SqliteDict(self.location('payload'), autocommit=True, journal_mode=JOURNAL_MODE)
        self.flush(save_index=False, save_model=False, clear_buffer=True)
        logger.info("loaded %s" % self)


    def location(self, name):
        return os.path.join(self.basename, name)


    @gensim.utils.synchronous('lock_update')
    def flush(self, save_index=False, save_model=False, clear_buffer=False):
        """Commit all changes, clear all caches."""
        if save_index:
            if self.fresh_index is not None:
                self.fresh_index.save(self.location('index_fresh'))
            if self.opt_index is not None:
                self.opt_index.save(self.location('index_opt'))
        if save_model:
            if self.model is not None:
                self.model.save(self.location('model'))
        self.payload.commit()
        if clear_buffer:
            if hasattr(self, 'fresh_docs'):
                try:
                    self.fresh_docs.terminate() # erase all buffered documents + file on disk
                except:
                    pass
            self.fresh_docs = SqliteDict(journal_mode=JOURNAL_MODE) # buffer defaults to a random location in temp
        self.fresh_docs.sync()


    def close(self):
        """Explicitly close open file handles, databases etc."""
        try:
            self.payload.close()
        except:
            pass
        try:
            self.model.close()
        except:
            pass
        try:
            self.fresh_index.close()
        except:
            pass
        try:
            self.opt_index.close()
        except:
            pass
        try:
            self.fresh_docs.terminate()
        except:
            pass

    def __del__(self):
        """When the server went out of scope, make an effort to close its DBs."""
        self.close()

    @gensim.utils.synchronous('lock_update')
#.........这里部分代码省略.........