def createNewFile(
self,
fileName, # name of the new file
force=False, # should we check to see if this is a wise move?
):
"""Create a new MacaronDB database file"""
# make a basic file
BaseFile.createNewFile(self,
fileName,
type="MacaronDB_DB",
version=__MACARONDB_DB_VERSION__,
force=force)
def createNewFile(
self,
fileName, # name of the new file
force=False, # should we check to see if this is a wise move?
):
"""Create a new FootballDB database file"""
# make a basic file
BaseFile.createNewFile(self,
fileName,
type="FootballDB_DB",
version=__FOOTBALLDB_DB_VERSION__,
force=force)
self._addTable('results', {
"season": "INT",
"week": "INT",
"team_a": "TEXT",
"team_b": "TEXT",
"score_a": "INT",
"score_b": "INT",
},
force=True)
def createNewFile(self,
fileName, # name of the new file
force=False, # should we check to see if this is a wise move?
):
"""Create a new FootballDB database file"""
# make a basic file
BaseFile.createNewFile(self,
fileName,
type="FootballDB_DB",
version=__FOOTBALLDB_DB_VERSION__,
force=force)
self._addTable('results',
{
"season" : "INT",
"week" : "INT",
"team_a" : "TEXT",
"team_b" : "TEXT",
"score_a" : "INT",
"score_b" : "INT",
},
force=True)
def __init__(self, verbosity=0):
BaseFile.__init__(self, verbosity)
class BaseFileTests(unittest.TestCase):
BF = BaseFile(verbosity=-1)
def open(self):
self.done()
self.BF.openFile("test.dp")
def done(self):
if self.BF.isOpen():
self.BF.closeFile()
def testCreation(self):
self.BF.createNewFile("test.dp", "testing_db", "1.0", force=True)
self.done()
def testFileType(self):
self.open()
self.assertTrue(self.BF.getFileType() == "testing_db")
self.done()
def testVersioning(self):
self.open()
self.assertTrue(self.BF.getVersion() == "1.0")
self.BF.logVersion("1.1")
self.assertTrue(self.BF.getVersion() == "1.1")
self.done()
def testHistory(self):
self.open()
self.BF.logMessage("test message")
(message, message_time) = self.BF.getMessages()[-1]
self.assertTrue(message == "test message")
time.sleep(1)
self.BF.logMessage("test message2")
messages = self.BF.getMessages(fromTime=message_time + 1)
self.assertTrue(len(messages) == 1)
(message, message_time) = messages[0]
self.assertTrue(message == "test message2")
self.done()
def testAddTable(self):
self.open()
self.BF._addTable("testing", {
"time": "INT",
"thing": "TEXT",
"size": "INT"
},
force=True)
self.done()
def testInsert(self):
self.open()
IF = Interface("test.dp")
IF.db = self.BF
to_db = [(1, "cat", 5), (2, "dog", 6), (2, "fish", 8), (4, "goat", 0),
(5, "fish", 12)]
IF.insert('testing', ['time', 'thing', 'size'], to_db)
self.done()
def testSelect(self):
self.open()
IF = Interface("test.dp")
IF.db = self.BF
C = Condition("thing", "=", "'fish'")
rows = IF.select("testing", ['time'], condition=C)
self.assertTrue(len(rows) == 2)
C = Condition("thing", "=", "'dog'")
rows = IF.select("testing", ['time'], condition=C)
self.assertTrue(len(rows) == 1)
self.done()
def testSelectCondition(self):
"""
DB looks like:
1 cat 5
2 dog 6
3 fish 8
4 goat 0
5 fish 12
"""
self.open()
IF = Interface("test.dp")
IF.db = self.BF
C = Condition(Condition("thing", "="), "or", Condition("size", "<"))
values = ("fish", 6)
rows = IF.select("testing", ['*'], condition=C, values=values)
self.assertTrue(len(rows) == 4)
self.done()
def testUpdate(self):
self.open()
IF = Interface("test.dp")
IF.db = self.BF
to_db = [("frog", 18, 2), ("yak", 20, 5)]
C = Condition("time", "=")
IF.update('testing', ['thing', 'size'], to_db, C)
"""
DB looks like:
1 cat 5
2 frog 18
2 frog 18
4 goat 0
5 yak 20
"""
C = Condition("thing", "=", "'fish'")
rows = IF.select("testing", ['time'], condition=C)
self.assertTrue(len(rows) == 0)
C = Condition("size", ">=", "'18'")
rows = IF.select("testing", ['time'], condition=C)
self.assertTrue(len(rows) == 3)
# more complex updates (proxy as test for more complex selects
s1 = Condition("size", ">=", "'18'")
s2 = Condition("thing", "!=")
C = Condition(s1, "and", s2)
data = [(7, 'frog')]
IF.update('testing', ['time'], data, C)
C = Condition("thing", "=", "'yak'")
rows = IF.select("testing", ['time'], condition=C)
# should affect 1 row
self.assertTrue(len(rows) == 1)
# should be the yak row which should now have time = 7
self.assertTrue(rows[0][0] == 7)
data = [(7, 8, "pig")]
IF.update('testing', ['time', 'size', 'thing'], data, 1)
C = Condition("time", "=", 7)
rows = IF.select("testing", ['time'], condition=C)
# should affect 1 row
self.assertTrue(len(rows) == 5)
self.done()
def createNewFile(self,
fileName, # name of the new file
force=False, # should we check to see if this is a wise move?
):
"""Create a new TrackM database file"""
# make a basic file
BaseFile.createNewFile(self,
fileName,
type="TrackM_DB",
version=__TRACKM_DB_VERSION__,
force=force)
# add TrackM specific tables
self._addTable("ids", # housekeeping information about highest ids
{
"sqid" : "INT", # highest sqid in the seqs table (-1 for None)
"hid" : "INT", # highest hid in the hits table (-1 for None)
"cid" : "INT", # highest cid in the contigs table (-1 for None)
"oid" : "INT", # highest oid in the orfs table (-1 for None)
},
force=True)
self._addTable("paths", # information about the location of genome files
{
"gid" : "TEXT", # genomeTree compatible ID for genome 1 (primary key)
"path" : "TEXT" # absolute path to fasta file
},
force=True)
self._addTable("pairs", # information about comparisons to make
{
"pid" : "INT", # unique ID describing this pair (primary key)
"gid_1" : "TEXT", # genomeTree compatible ID for genome 1 (foreign key)
"gid_2" : "TEXT", # genomeTree compatible ID for genome 2 (gid_2 > gid_1) (foreign key)
"ani_1" : "REAL", # ANI from gid_1 -> gid_2
"ani_2" : "REAL", # ANI from gid_2 -> gid_1
"ident_tree" : "REAL", # GTDB (83 marker) identity
"ident_16S" : "REAL", # 16S pairwise identity
"batch" : "INT", # batch processed in
"ani_comp" : "REAL" # which ani has this pair been processed as?
},
force=True)
self._addTable("hits", # information about hits between genome pairs
{
"hid" : "INT", # unique ID for this hit (primary key)
"pid" : "INT", # pair ID from pairs table (foreign key)
"cid_1" : "INT", # ID of the contig for this hit
"start_1" : "INT", # start position for this hit in gid_1
"len_1" : "INT", # length of this hit in gid_1
"strand_1" : "INT", # strand of the hit in gid_1
"sqid_1" : "INT", # sequence ID for this hit from seqs table (foreign key)
"cid_2" : "TEXT",
"start_2" : "INT",
"len_2" : "INT",
"strand_2" : "INT",
"sqid_2" : "INT",
"ident" : "REAL", # percent identity for this hit
},
force=True)
self._addTable("contigs", # store contig headers once
{
"cid" : "INT", # unique ID for this contig (primary key)
"header" : "TEXT", # contig header
},
force=True)
self._addTable("seqs", # information about orfs found on hits
{
"sqid" : "INT", # unique ID for this sequence (primary key)
"seq" : "TEXT", # nucelotide sequence
},
force=True)
self._addTable("orfs", # information about orfs found on hits
{
"oid" : "INT", # unique ID for this orf (primary key)
"sqid" : "INT", # hit ID for this orf from in hits table (foreign key)
"start" : "INT", # start of the ORF
"len" : "INT", # length of the orf
"strand" : "INT", # strand of the orf
"seq_nucl" : "TEXT", # nucelotide sequence
"seq_prot" : "TEXT" # protein sequence
},
force=True)
self._addTable("ann_kegg", # kegg annotatations for orfs
{
"oid" : "INT", # orf id for this hit (foreign key)
"hit_1" : "TEXT", # best hit
"hit_1" : "TEXT", # second best hit
"hit_1" : "TEXT" # third best hit
},
force=True)
self._addTable("ann_nog", # eggnog annotations for orfs
{
"oid" : "INT", # orf id for this hit (foreign key)
"hit_1" : "TEXT", # best hit
"hit_1" : "TEXT", # second best hit
"hit_1" : "TEXT" # third best hit
},
force=True)
self._addTable("ann_nr", # nr annotations for orfs
{
"oid" : "INT", # orf id for this hit (foreign key)
"hit_1" : "TEXT", # best hit
"hit_1" : "TEXT", # second best hit
"hit_1" : "TEXT" # third best hit
},
force=True)
def __init__(self, verbosity=0):
BaseFile.__init__(self, verbosity)
