def getJoinColUniqueOneLink(self, first_table, second_table):
general_links = generalLinksDB([first_table, second_table], self)
links = general_links.getLinks()
edge = links[0]
first_node = edge[0]
[first_table, join_col] = first_node.split(':')
return join_col
def test_Two_Tables_One_Link_Case3(self):
first_table = "./ks_filehandler/ks_filehandler/data/Sales.csv"
second_table = "./ks_filehandler/ks_filehandler/data/CountryRegion.csv"
ks_merge = merge(self.db)
ks_merge.reset()
ks_merge.addTable(first_table,"Sales")
ks_merge.addTable(second_table,"CountryRegion")
general_links = generalLinksDB(["Sales","CountryRegion"], ks_merge)
self.assertEqual(False, general_links.isEdge('Sales.csv:Cou ntryCode', 'CountryRegion.csv:CountryCode'))
self.db.commit()
def getJoinColUniqueTwoLinks(self, first_table, second_table):
general_links = generalLinksDB([first_table, second_table],self)
links = general_links.getLinks()
edge1 = links[0]
first_node = edge1[0]
[first_table, join_col1] = first_node.split(':')
edge2 = links[1]
second_node = edge2[0]
[first_table, join_col2] = second_node.split(':')
return [join_col1, join_col2]
def isUniqueTwoLinks(self, first_table, second_table):
general_links = generalLinksDB([first_table, second_table],self)
if len(general_links.getLinks()) == 2:
[join_col1, join_col2] = self.getJoinColUniqueTwoLinks(first_table, second_table)
is_unique_table1 = self.isUniqueColTwo(first_table, join_col1, join_col2)
is_unique_table2 = self.isUniqueColTwo(second_table, join_col1, join_col2)
if is_unique_table1 or is_unique_table2:
return True
else:
return False
else:
return False
def isUniqueOneLink(self, first_table, second_table):
general_links = generalLinksDB([first_table, second_table],self)
links = general_links.getLinks()
print len(links)
print links
if len(links) == 1:
edge = links[0]
first_node = edge[0]
second_node = edge[1]
[first_table, first_col] = first_node.split(':')
[second_table, second_col] = second_node.split(':')
if (self.isUniqueCol(first_table, first_col)) or (self.isUniqueCol(second_table, second_col)):
return True
else:
return False
else:
return False
def test_Four_Tables_Five_Links(self):
first_table = "./ks_filehandler/ks_filehandler/data/Sales.csv"
second_table = "./ks_filehandler/ks_filehandler/data/graph/CountryRegion.csv"
third_table = "./ks_filehandler/ks_filehandler/data/ComissionTax.csv"
fourth_table = "./ks_filehandler/ks_filehandler/data/graph/Currencyv2.csv"
ks_merge = merge(self.db)
ks_merge.reset()
ks_merge.addTable(first_table,"Sales")
ks_merge.addTable(second_table,"CountryRegion")
ks_merge.addTable(third_table,"ComissionTax")
ks_merge.addTable(fourth_table,"Currencyv2")
general_links = generalLinksDB(["Sales","Currencyv2","ComissionTax","CountryRegion"], ks_merge)
print ("Links:")
print(general_links.getLinks())
self.assertEqual(True, general_links.isEdge('ComissionTax:Region', 'CountryRegion:Region'))
self.assertEqual(True, general_links.isEdge('ComissionTax:VendorId', 'Sales:VendorId'))
self.assertEqual(True, general_links.isEdge('Sales:CountryCode', 'CountryRegion:CountryCode'))
self.assertEqual(True, general_links.isEdge('Sales:DownloadDate', 'Currencyv2:DownloadDate'))
self.assertEqual(True, general_links.isEdge('Currencyv2:CustomerCurrency', 'Sales:CustomerCurrency'))
self.db.commit()
def getLinks(self):
general_links = generalLinksDB(self.getTables(),self)
links = general_links.getLinks()
return links
