def outputDistrictFiles(q, i, lock, outputDir, runContextName, districtTable,
fields, starts, names, lengths, types, var_names,
outformats):
runContext = RunContext(runContextName)
dbContext = runContext.getDBContext()
while (True):
lock.acquire()
if q.empty():
lock.release()
print "Thread %s is OVER " % i + str(datetime.datetime.now())
return
else:
district = q.get()
lock.release()
fh = open(outputDir + district + ".txt", "w")
fhc = open(outputDir + district + ".csv", "w")
rows = dbContext.execute(
"SELECT {cols} FROM {districtTable} WHERE dcrxid='{district}' ORDER BY dcrxid, grade, ucrxlnm, ucrxfnm, lithocode, studentmid"
.format(cols=Joiner(var_names),
district=district,
districtTable=districtTable))
lastname = ''
for n in names:
if n != lastname:
fhc.write(n.upper() + ',')
lastname = n
fhc.write('\n')
writeToFile(rows, fh, fhc, 0, fields, starts, names, lengths, types,
var_names, outformats)
fh.close()
fhc.close()
def call_preqc(q, lock, rc, layoutFile, flat_tablename, i, row_count):
runContext = RunContext(rc)
dbContext = runContext.getDBContext()
inputFile = q.get()
x = preqc.PreQC(
runcontext=runContext,
dbcontext=dbContext,
layoutfile=layoutFile,
inputfile=inputFile,
patterns=[('[u][pcf][w]x_.*{icnt}.*', '[u][pcf][w]x__OE.*Pos.*{icnt}',
'[u][pcf][w]x_OE_.*{icnt}', 'MC_TABLE_W_' + str(i), 'W'),
('[u][pcf][c]x_.*{icnt}.*', '[u][pcf][c]x__OE.*Pos.*{icnt}',
'[u][pcf][c]x_OE_.*{icnt}', 'MC_TABLE_C_' + str(i), 'C'),
('[u][pcf][s]x_.*{icnt}.*', '[u][pcf][s]x__OE.*Pos.*{icnt}',
'[u][pcf][s]x_OE_.*{icnt}', 'MC_TABLE_S_' + str(i), 'S'),
('[u][pcf][r]x_.*{icnt}.*', '[u][pcf][r]x__OE.*Pos.*{icnt}',
'[u][pcf][r]x_OE_.*{icnt}', 'MC_TABLE_R_' + str(i), 'R'),
('[u][pcf][m]x_.*{icnt}.*', '[u][pcf][m]x__OE.*Pos.*{icnt}',
'[u][pcf][m]x_OE_.*{icnt}', 'MC_TABLE_M_' + str(i), 'M')],
flat_tablename=flat_tablename,
debug=False,
bulk_insert=False,
errorfile='c:\SAS\OGT\Error%s.txt' % i,
table_names='TABLE_NAMES_' + str(i),
output_table='Layout_Temp_' + str(i),
lock=lock,
batchfile='bcpfile%s.bat' % i,
outputsdir='c:/SAS/OGT/Joboutput%s/' % i,
row_count=row_count)
x.process()
def readTideFile(q, idx, tideDataDirectory, runContextName):
start = datetime.datetime.now()
tideDataFile = q.get()
tideDataFile = tideDataDirectory + tideDataFile
runContext = RunContext(runContextName)
dbContext = runContext.getDBContext()
server = dbContext.server
db = dbContext.db
lengths = dbContext.execute("SELECT length FROM TideLayout")
var_names = dbContext.execute("SELECT variable_name FROM TideLayout")
lengths = [l[0] for l in lengths]
var_names = [v[0] for v in var_names]
tideData = Dataset(dbms='fixed2',
lengths=lengths,
fieldnames=var_names,
open_mode='rb',
name=tideDataFile)
tideSqlTable = Dataset(dbms='pyodbc',
table='TideFile' + str(idx),
replace=True,
db=db,
server=server,
open_mode='wb')
data(tideData, tideSqlTable, unsafecopy=True)
print "thread: " + str(idx) + " ran: " + str(datetime.datetime.now() -
start)
def setUp(self):
self.saveDir = os.path.abspath('.')
os.chdir( _THIS_DIR )
self.OUT = RunContext( 'runcontexttest' )
self.log_main = get_list( 'main' )
del self.log_main[:]
self.log_root = get_list( 'root' )
del self.log_root[:]
self.log_sql = get_list( 'sql' )
del self.log_sql[:]
def __init__(self,filename,sheet_name='sheet1',output_table='temp1',get_names=True, delimiter=','):
'''
Constructor:This init step will take the following inputs -
Layout filename- The Input file name
sheet name (defaults to sheet1)- The Name of the sheet that will be loaded
Output_table name- The Output table name that will be created in the sqlserver
delimiter- Delimiter
Get_names_indicator - Indicate to load the first column or not
'''
self.RC = RunContext('unittest')
self.dbcontext = self.RC.getDBContext()
self.filename = filename
self.sheet_name = sheet_name
self.output_table = output_table
self.get_names = get_names
self.delimiter = delimiter
self.layoutdict ={}
self.maxmindict ={}
self.recodingsdict ={}
def test_logger_isolation(self):
rc_independent = RunContext( 'independent' )
self.OUT.info( "Message 1" )
rc_independent.info( "Message 2" )
expected_list = [
r'INFO runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 1',
]
for expected, actual in zip( expected_list, get_list( 'main' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
expected_list = [
r'INFO independent ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 2',
]
for expected, actual in zip( expected_list, get_list( 'independent' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
def outputStateFile(i, outputDir, runContextName, stateTable, fields, starts,
names, lengths, types, var_names, outformats):
runContext = RunContext(runContextName)
dbContext = runContext.getDBContext()
num_rows = dbContext.execute(
"SELECT count(*) FROM {stateTable}".format(stateTable=stateTable))
length = num_rows[0][0] / NUM_PROCESSES
print 'starting to make wholestate' + str(datetime.datetime.now())
fh = open(outputDir + "WholeState%s.txt" % i, "w")
rows = dbContext.execute(
"SELECT {cols} FROM {stateTable} ORDER BY dcrxid, grade, ucrxlnm, ucrxfnm, lithocode, studentmid"
.format(cols=Joiner(var_names), stateTable=stateTable))
#writeToFile(rows, fh, None, 1, fields, starts, names, lengths, types, var_names, outformats)
if i == NUM_PROCESSES - 1:
writeToFile(rows[(length * i):], fh, None, 1, fields, starts, names,
lengths, types, var_names, outformats)
else:
writeToFile(rows[(length * i):(length * i + length)], fh, None, 1,
fields, starts, names, lengths, types, var_names,
outformats)
fh.close()
class Test(unittest.TestCase):
def setUp(self):
self.context = RunContext('unittest')
self.db_context = self.context.getDBContext(tag='unittest')
def tearDown(self):
pass
def testCRUD(self):
ctx = self.db_context
ctx.executeNoResults("CREATE TABLE testtable( col1 VARCHAR(255) )")
ctx.executeNoResults(
"INSERT INTO testtable( col1 ) VALUES ( 'ABCDE' )")
results = [row[0] for row in ctx.execute("SELECT col1 FROM testtable")]
n = len(results)
self.assertEquals(n, 1, "Wrong number of results {0}".format(n))
self.assertEquals(results[0], "ABCDE",
"Wrong result {0}".format(results[0]))
ctx.executeNoResults("DROP TABLE testtable")
var_names, outformats)
fh.close()
fhc.close()
if __name__ == '__main__':
basepath = "C:\\CVS Projects\\ScoreReportMacros\\UnitTested\\"
inputFile = "C:\\CVS Projects\\CSSC Score Reporting\\OGT Spring 2012\\Code\\Development\\DownloadableFiles\\LongformatSP12.xls"
dataFile1 = "C:\\CVS Projects\\CSSC Score Reporting\\OGT Fall 2008\\code\\ODE downloadable files\\longformat\\Copy of JVSschool.xls"
#outputDir = "H:\share\Ohio Graduation Tests\Technical\2013 March\ScoreReports\ODEdownloadleFiles"
outputDir = "C:\\out\\"
#runContext = RunContext('sharedtest')
runContextName = 'OGT_12SP'
runContext = RunContext(runContextName)
dbContext = runContext.getDBContext()
#studentTable = 'StudentOGT_2012P_'
studentTable = 'sas_student_'
#dasitesTable = 'OGT_dasites'
dasitesTable = 'sas_dasites'
sql_s = datetime.datetime.now()
if True:
print "downloadable files start: " + str(datetime.datetime.now())
drop_tables(['OGT_DL_Vars', 'OGT_DL_Data'], dbContext)
reader = SafeExcelReader(runContext)
reader.db_context = dbContext
reader.filename = inputFile
'''
from airassessmentreporting.airutility import RunContext, TableSpec, FieldSpec
from airassessmentreporting.airutility.dbutilities import table_exists, drop_table_if_exists, get_column_names, get_table_spec
from airassessmentreporting.airutility.formatutilities import Joiner, db_identifier_unquote
import layoutcheck
_TABLE_NAMES = [
'MC_TABLE_W_1', 'MC_TABLE_C_1', 'MC_TABLE_S_1', 'MC_TABLE_R_1',
'MC_TABLE_M_1'
]
_ID_COLUMNS = ['ID', 'FLAT_TABLE_ID']
_LAYOUTFILE = 'C:\CVS Projects\CSSC Score Reporting\OGT Spring 2012\Input Layout\OGT_SP12_Op_DataLayout_IntakeLayout.xls'
runcontext = RunContext('unittest')
dbcontext = runcontext.getDBContext()
def prepare_update(fieldnames, table):
# print table
# print fieldnames
LC = layoutcheck.LayoutCheck(runcontext=runcontext,
dbcontext=dbcontext,
layoutfile=_LAYOUTFILE)
layoutdict, maxmindict, recodingsdict = LC.process()
format_list = []
for each in fieldnames:
position_value = each + '_1'
# print 'each=', each
value = recodingsdict.get(position_value)
class Test(unittest.TestCase):
def setUp(self):
self.saveDir = os.path.abspath('.')
os.chdir( _THIS_DIR )
self.OUT = RunContext( 'runcontexttest' )
self.log_main = get_list( 'main' )
del self.log_main[:]
self.log_root = get_list( 'root' )
del self.log_root[:]
self.log_sql = get_list( 'sql' )
del self.log_sql[:]
def tearDown(self):
os.chdir( self.saveDir )
def test_config_read(self):
config = self.OUT.config
self.assertEqual( 'THIS IS NOT A REAL SERVER',
config.get( 'DB', 'default_server' ),
'Wrong default server value' )
self.assertEqual( 'NOTADB',
config.get( 'DB', 'default_database'),
'Wrong default db value' )
level = logging.getLevelName( self.OUT.get_logger().level )
self.assertEqual( 'DEBUG',
level,
'Wrong logging level: found {}'.format( level ) )
def test_logger_setup(self):
logger = self.OUT.logger
self.assertEquals( 'DEBUG',
logging.getLevelName( logger.level ),
'Wrong logging level on logger' )
self.assertEqual( 'runcontexttest',
logger.name,
'Wrong logger name' )
def test_logger_main1(self):
self.OUT.debug( 'Message 1' )
self.OUT.info( 'Message 2' )
self.OUT.warning( 'Message 3' )
self.OUT.error( 'This error is only a drill. In the event of a real error, the unit test would fail.' )
expected_list = [
r'DEBUG runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 1',
r'INFO runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 2',
r'WARNING runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 3',
r'ERROR runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: This error is only a drill\. In the event of a real error, the unit test would fail\.',
]
for expected, actual in zip( expected_list, get_list( 'main' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
def test_logger_SQL1(self):
logger = self.OUT.get_sql_logger()
logger.debug( 'Message 1' )
logger.info( 'Message 2' )
logger.warning( 'Message 3' )
logger.error( 'This error is only a drill. In the event of a real error, the unit test would fail.' )
expected_list = [
r'ERROR runcontexttest\.sql ....-..-.. ..:..:..,... test_runcontext.py \[... ]: This error is only a drill\. In the event of a real error, the unit test would fail\.',
]
for expected, actual in zip( expected_list, get_list( 'sql' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
def test_logger_another(self):
logger = self.OUT.get_logger( 'some.class' )
self.assertEqual( 'runcontexttest.some.class', logger.name,
"Expected logger named runcontexttest.some.class, found {}".format( logger.name ) )
logger.debug( 'Message 1' )
logger.info( 'Message 2' )
logger.warning( 'Message 3' )
logger.error( 'This error is only a drill. In the event of a real error, the unit test would fail.' )
expected_list = [
r'DEBUG runcontexttest\.some\.class ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 1',
r'INFO runcontexttest\.some\.class ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 2',
r'WARNING runcontexttest\.some\.class ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 3',
r'ERROR runcontexttest\.some\.class ....-..-.. ..:..:..,... test_runcontext.py \[... ]: This error is only a drill\. In the event of a real error, the unit test would fail\.',
]
for expected, actual in zip( expected_list, get_list( 'main' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
def test_logger_isolation(self):
rc_independent = RunContext( 'independent' )
self.OUT.info( "Message 1" )
rc_independent.info( "Message 2" )
expected_list = [
r'INFO runcontexttest ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 1',
]
for expected, actual in zip( expected_list, get_list( 'main' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
expected_list = [
r'INFO independent ....-..-.. ..:..:..,... test_runcontext.py \[... ]: Message 2',
]
for expected, actual in zip( expected_list, get_list( 'independent' ) ):
if not re.match(expected, actual):
self.fail( "Expected message \"{}\", found \"{}\"".format( expected, actual ) )
def test_db_context_cache(self):
rc = RunContext( 'unittest' )
dbc1 = rc.getDBContext( 'unittest' )
dbc2 = rc.getDBContext( 'unittest', 'second' )
dbc3 = rc.getDBContext( 'unittest', cached=False )
self.assertIsNot( dbc1, dbc2, 'Returned same dbContext in spite of different instance name' )
self.assertIsNot( dbc1, dbc3, 'Returned same dbContext in spite of different instance name' )
self.assertIsNot( dbc2, dbc3, 'Returned same dbContext in spite of different instance name' )
self.assertIs( rc.getDBContext( 'unittest' ), dbc1, 'Did not return same dbContext' )
self.assertIs( rc.getDBContext( 'unittest', 'second' ), dbc2, 'Did not return same dbContext' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc1, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc2, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc3, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc1, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc2, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc3, 'Returned same dbContext even though cached=False' )
def test_db_context_cache(self):
rc = RunContext( 'unittest' )
dbc1 = rc.getDBContext( 'unittest' )
dbc2 = rc.getDBContext( 'unittest', 'second' )
dbc3 = rc.getDBContext( 'unittest', cached=False )
self.assertIsNot( dbc1, dbc2, 'Returned same dbContext in spite of different instance name' )
self.assertIsNot( dbc1, dbc3, 'Returned same dbContext in spite of different instance name' )
self.assertIsNot( dbc2, dbc3, 'Returned same dbContext in spite of different instance name' )
self.assertIs( rc.getDBContext( 'unittest' ), dbc1, 'Did not return same dbContext' )
self.assertIs( rc.getDBContext( 'unittest', 'second' ), dbc2, 'Did not return same dbContext' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc1, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc2, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', cached=False ), dbc3, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc1, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc2, 'Returned same dbContext even though cached=False' )
self.assertIsNot( rc.getDBContext( 'unittest', 'second', cached=False ), dbc3, 'Returned same dbContext even though cached=False' )
self.c.drawString(80,
self.startval - (self._incr_val() * self.linediff),
"")
self.c.setFont("Helvetica", 10)
self.c.drawString(
160, self.startval - (self._incr_val() * self.linediff),
"Number of variables in {0} and not in {1}".format(
self.TableNm1, self.TableNm2))
self.c.setFont("Helvetica", 10)
self.c.drawString(80,
self.startval - (self._incr_val() * self.linediff),
"FIELD")
self.c.drawString(300, self.startval - (self.incr * self.linediff),
"TYPE")
self.c.drawString(400, self.startval - (self.incr * self.linediff),
"LENGTH")
if __name__ == '__main__':
context = RunContext('unittest')
x = Compare(context,
TableNm1='Employee1',
TableNm2='Employee2',
Keyfields=['EMP_NO', 'EMP_FNAME'],
tag='CSSC',
num_of_errors=50,
tolerance=0)
# x = Compare(TableNm1='dbo.compare1',TableNm2='dbo.compare2',Keyfields=['SSID'],db='Share',num_of_errors=50,tolerance=0)
# x = Compare(TableNm1='dbo.read_gr04_1',TableNm2='dbo.read_gr04_2',Keyfields=['SSID'])
x.process()
self.where_list_1 = self.where_list_1 + ' A.' + self.Keyfields[x] + ' is null'
else:
self.where_list_1 = self.where_list_1 + ' OR A.' + self.Keyfields[x] + ' = B.' + self.Keyfields[x]
collist1 = ','.join(['TB1.' + x + ' AS TB1' + x for x in self.table_Schema])
collist2 = ','.join(['TB2.' + x + ' AS TB2' + x for x in self.table_Schema])
self.qry = """Select {cols1},{cols2} from {table_nm1} TB1
full outer join
{table_nm2} TB2
on {keys} where {where_list} """.format(table_nm1=self.TableNm1,table_nm2=self.TableNm2,keys=self.keys,where_list=self.where_list,cols1=collist1,cols2=collist2)
self.runContext.debug( 'self.qry=' + self.qry )
if __name__ == '__main__':
RC = RunContext('sharedtest')
dbcontext = RC.getDBContext()
# x = SqlCompare( run_context=RC, dbcontext= dbcontext,TableNm1='dbo.pre_qctable_table_SAS',TableNm2='dbo.pre_qc_flat_table',Keyfields=['STUDENTID'],db_tag='CSSC',num_of_errors=50,tolerance=0.000001,
# excludefields=['id'],output_file='c:/compare.pdf')
# x = SqlCompare(TableNm1='Employee1',TableNm2='Employee2',Keyfields=['EMP_NO','EMP_FNAME'],db='CSSC',num_of_errors=50,tolerance=0)
x = SqlCompare( run_context=RC,
dbcontext= dbcontext,
TableNm1='school_repnum_Ascii',
TableNm2='school_repnum_Ascii',
Keyfields=['GRADE'],
db_tag='ScoreReportingTestData',
print eachcol
self.grid.SetCellValue(i, 0, eachcol)
i += 1
print 'i=', i
# self.grid.SetCellValue(0,0,'Hi')
# self.grid.SetCellValue(1,0,'Hiii')
print self.grid.NumberCols
vbox.Add(self.grid, 1, wx.EXPAND, 5)
panel.SetSizer(vbox)
def OnButtonClicked(self, e):
print 'Button clicked'
if __name__ == '__main__':
RC = RunContext('unittest')
dbcontext = RC.getDBContext()
app = wx.PySimpleApp()
frame = ScrollbarFrame(
title='LayoutMapper',
runcontext=RC,
dbcontext=dbcontext,
layoutfile=
'C:\CVS Projects\CSSC Score Reporting\OGT Spring 2012\Input Layout\OGT_SP12_Op_DataLayout_IntakeLayout.xls'
)
frame.Show()
app.MainLoop()
def setUp(self):
self.context = RunContext('unittest')
self.db_context = self.context.getDBContext(tag='unittest')
#query = "Select name from sys.columns where object_id = OBJECT_ID(?) order by column_id"
query = """SELECT A.NAME FROM SYS.COLUMNS A,SYS.COLUMNS B WHERE A.NAME = B.NAME AND a.object_id = OBJECT_ID(?) AND b.object_id = OBJECT_ID(?)"""
result = self.conn.execute(query, (self.tablenm1, self.tablenm2))
print 'query result=', result
if result:
select_collist = ','.join(elem[0] for elem in result)
match_collist = [str(each[0]).upper() for each in result]
print 'match_collist=', match_collist
if self.Keyfields:
key_collist = ','.join(elem for elem in self.Keyfields)
print 'QUERY result=', result
table1_qry = "Select {select_collist} from {table_nm} order by {key_collist}".format(
select_collist=select_collist,
table_nm=self.tablenm1,
key_collist=key_collist)
table2_qry = "Select {select_collist} from {table_nm} order by {key_collist}".format(
select_collist=select_collist,
table_nm=self.tablenm2,
key_collist=key_collist)
return table1_qry, table2_qry, match_collist
if __name__ == '__main__':
x = Query(RunContext("unittest"),
'dbo.compare1',
'dbo.compare2', ['ssid'], [],
db='Share')
x.process()
class LayoutCheck(object):
'''
classdocs
'''
def __init__(self,filename,sheet_name='sheet1',output_table='temp1',get_names=True, delimiter=','):
'''
Constructor:This init step will take the following inputs -
Layout filename- The Input file name
sheet name (defaults to sheet1)- The Name of the sheet that will be loaded
Output_table name- The Output table name that will be created in the sqlserver
delimiter- Delimiter
Get_names_indicator - Indicate to load the first column or not
'''
self.RC = RunContext('unittest')
self.dbcontext = self.RC.getDBContext()
self.filename = filename
self.sheet_name = sheet_name
self.output_table = output_table
self.get_names = get_names
self.delimiter = delimiter
self.layoutdict ={}
self.maxmindict ={}
self.recodingsdict ={}
def process(self):
"""This is the main process that controls the flow of this module"""
SE = SafeExcelReader(self.RC, self.filename, self.sheet_name, self.output_table, db_context=self.dbcontext,get_names=True, delimiter=',', import_order='import_order')
SE.createTable()
try:
self._checktypes()
self._checkemptyrows()
self._checkinvalidvariables()
self._checkvalidranges()
self._recodings_and_create_dicts()
except Exception as error:
print 'Module:LAYOUT_CHECK Error=',error
return self.layoutdict, self.maxmindict, self.recodingsdict
def _checktypes(self):
"""This function checks for the type of the following fields-START,END,NOMINAL_VALUES & AIR_STD_CODE"""
typechecksql="""SELECT TB1.NAME as COLUMN_NAME ,TB2.NAME as COLUMN_TYPE
from sys.columns tb1
inner join sys.types tb2
on tb1.system_type_id = tb2.system_type_id
where tb1.object_id = object_id(?) and
tb2.name <>'sysname'"""
result=self.dbcontext.execute(query=typechecksql,parameters=[self.output_table])
columns = [str(getattr(each,'COLUMN_NAME').upper()) for each in result if getattr(each,'COLUMN_NAME').upper() not in COLUMN_LIST and getattr(each,'COLUMN_NAME').upper() not in IGNORE_LIST ]
if columns:
error= "The following columns {0} are missing from the Input file".format(columns)
raise Exception(error)
for each in result:
if getattr(each,'COLUMN_NAME').upper() == 'START':
if getattr(each,'COLUMN_TYPE').upper() <> 'FLOAT':
raise Exception('The START Column must be of type FLOAT')
if getattr(each,'COLUMN_NAME').upper() == 'END':
if getattr(each,'COLUMN_TYPE').upper() <> 'FLOAT':
raise Exception('The END Column must be of type FLOAT')
if getattr(each,'COLUMN_NAME').upper() == 'NOMINAL_VALUES':
if getattr(each,'COLUMN_TYPE').upper() <> 'NVARCHAR':
raise Exception('The NOMINAL_VALUES Column must be of type NVARCHAR')
if getattr(each,'COLUMN_NAME').upper() == 'AIR_STD_CODE':
if getattr(each,'COLUMN_TYPE').upper() <> 'NVARCHAR':
raise Exception('The AIR_STD_CODE Column must be of type NVARCHAR')
def _checkemptyrows(self):
"""This functions checks for any blank row in the table and flags it"""
qrytemplate="""select import_order from {tablename} where start='' and nominal_values='' and comments='' """.format(tablename=self.output_table)
result = self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows= {0} are blank in the table, Check and correct ".format(result)
raise Exception(error)
def _checkinvalidvariables(self):
"""This function validates the variable names in following ways
1.Checks for any space in variable name
2.Checks for variable length more than 28 characters
3.Flags variable name that starts with bad_
4.Flags variable name that ends with _tmp
5.Checks for duplicate variable names
"""
#Checks for any space in the variable names
qrytemplate="""select variable_name
FROM {tablename}
where Variable_name <> ''
and charindex(' ',Variable_name) > 0 """.format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following variables contain spaces in between them - {tablename}".format(tablename=self.output_table)
raise Exception(error)
#Checks for variable names greater than 28
qrytemplate="""select variable_name
from {tablename}
where Variable_name <> ''
and len(variable_name) > 28 group by variable_name""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following variables length is too long, it should be less than 28 characters - {0}".format(result)
raise Exception(error)
#Checks for variable name that starts with bad_
qrytemplate="""select variable_name
from {tablename}
where Variable_name <> ''
and substring(variable_name,1,4) = 'bad_' """.format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following variables cannot start with bad_ {0}".format(result)
raise Exception(error)
#Checks for variable name that ends with _tmp
qrytemplate="""select variable_name
from {tablename}
where Variable_name <> ''
and substring(variable_name,len(variable_name) -3,4) = '_tmp'""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following variables cannot end with _tmp {0}".format(result)
raise Exception(error)
#Checks for duplicate variable names
qrytemplate="""select variable_name, count(*)
from {tablename}
where variable_name <> ' '
group by variable_name having count(*) > 1""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following variables are duplicate -[VARIABLE_NAME,COUNT]{0}".format(result)
raise Exception(error)
def _checkvalidranges(self):
"""This function does the following checks
1.START value but no END value.
2.START value greater than END.
3.START value is negative.
4.No TYPE value defined.
5.TYPE values are not defined correctly- ONLY valid types are allowed.
6.Check for any overlapping for START & END.
"""
#Checks for START but no END value
qrytemplate="""select import_order,start,[end]
from {tablename}
where variable_name <> ' '
and start is not null
and ([end] is null or [end] =0)""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows-[rowmnum,start,end] {0} has a START VALUE but no END".format(result)
raise Exception(error)
#Checks for START greater than END
qrytemplate="""select import_order,start,[end]
from {tablename}
where variable_name <> ' '
and start is not null
and [end] is not null
and start - [end] > 0""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows-[rowmnum,start,end] {0} has START greater than END".format(result)
raise Exception(error)
#Checks for negative values in START
qrytemplate=""" select import_order,start,[end]
from {tablename}
where variable_name <> ' '
and start is not null
and start < 0""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows-[rowmnum,start,end] {0} has START that has negative values".format(result)
raise Exception(error)
#Checks for rows with no TYPE values
qrytemplate=""" select import_order,start,[end]
from {tablename}
where start is not null
and type is null""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows-[rowmnum,start,end] {0} has NO TYPE values".format(result)
raise Exception(error)
#Checks for rows with invalid TYPE values
qrytemplate=""" select import_order,start,[end]
from {tablename}
where start is not null
and (UPPER(type) not in ('INTEGER','STRING','REAL','NOMINAL','NOMINAL_N')
and UPPER(type) not like 'ID[0-9]' and UPPER(type) not like 'NOMINAL_ID[0-9]')""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if result:
error= "The following rows-[rowmnum,start,end] {0} has wrong TYPES defined ONLY- integer, string, real, nominal, nominal_n or ID1, ID2, ID3, ... allowed".format(result)
raise Exception(error)
#Checks for rows with overlapping START and END
qrytemplate="""SELECT TB1.START,TB1.[END] FROM
(
select START,[END],ROW_NUMBER() over(order by import_order) as rownum from
{tablename}
where variable_name <> ' '
) TB1
INNER JOIN
(
select START,[END],ROW_NUMBER() over(order by import_order) as rownum from
{tablename}
where variable_name <> ' '
) TB2
ON TB1.rownum + 1 = TB2.rownum
WHERE TB1.[END] > TB2.START""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
if len(result):
error= "The following rows-[start,end] {0} has overlappings".format(result)
raise Exception(error)
def _recodings_and_create_dicts(self):
"""This method iterates over all the rows in the Layout table and peforms the following
1.Checks if any variable name contains bad characters- The rules are in the regular expression.
2.Checks if the recoded values are in the proper format.
3.Prepares 3 dicts-Layoutdicts-['variablename':[start,end,type], Maxmindicts-[max,min] and recordingsdict-[nominal_Values,air_std_value]
"""
qrytemplate="""SELECT type,air_std_code,import_order, variable_name, start, [end],max,min,nominal_values, air_std_code
from {tablename} order by import_order""".format(tablename=self.output_table)
result=self.dbcontext.execute(query=qrytemplate,parameters=[])
for each in result:
#Check to make sure the variable names has valid names
if getattr(each,'variable_name') is not None and getattr(each,'variable_name') <> ' ':
if not re.search(r"^[a-zA-Z][a-zA-Z0-9_]*$",getattr(each,'variable_name')):
error= "The variable {0} in line number - {1} - contains bad characters ".format(getattr(each,'variable_name'),getattr(each,'import_order'))
raise Exception(error)
#Check to make sure the recorded values are in the proper format
if getattr(each,'type') is not None:
vartype = getattr(each,'type')
cnt = 1
else:
cnt+=1
if ((vartype == 'integer' or vartype =='real' or vartype[0:2] == 'id') and cnt > 1) or vartype =='nominal_n':
if not re.search(r"^(-?\d+(\.\d*)?|\.[A-Z]?)$",str(getattr(each,'air_std_code'))):
error= "The recoded value '{0}' must be numeric (or a period followed by a single uppercase letter) for the following [import_order=] {1}".format(getattr(each,'air_std_code'),getattr(each,'import_order'))
raise Exception(error)
t1 = datetime.datetime.now()
if (getattr(each,'start') not in ['',None] and getattr(each,'end') not in ['',None]):
self.layoutdict[str(getattr(each,'variable_name'))] = [int(getattr(each,'start')),int(getattr(each,'end')),str(getattr(each,'type'))]
if (getattr(each,'max') not in ['',None] and getattr(each,'min') not in ['',None]):
self.maxmindict[str(getattr(each,'variable_name'))] = [int(str(getattr(each,'min'))),int(str(getattr(each,'max')))]
#The check for missed values on variable_name & nominal_values is not done as missing values comes with dot(.)
self.recodingsdict[str(getattr(each,'variable_name'))] = [[str(getattr(each,'nominal_values'))],[str(getattr(each,'air_std_code'))]]
# print 'Last Added variable name=',getattr(each,'variable_name')
variable_name_cache = str(getattr(each,'variable_name'))
else:
# print 'recodingsdict=',recodingsdict
# print 'str(getattr(each,nominal_values))=',str(getattr(each,'nominal_values'))
# print 'str(getattr(each,air_std_code))=',str(getattr(each,'air_std_code'))
# print 'variable_name_cache=',variable_name_cache
self.recodingsdict[variable_name_cache][0].append(str(getattr(each,'nominal_values')))
self.recodingsdict[variable_name_cache][1].append(str(getattr(each,'air_std_code')))
t2 = datetime.datetime.now()
print 'len-layoutdict=',len(self.layoutdict)
print 'len-maxmindict=',len(self.maxmindict)
print 'len-recodngsdict=',len(self.recodingsdict)
self._writereports()
def _writereports(self):
import os
import operator
result = sorted(self.layoutdict.iteritems(),key=operator.itemgetter(1))
f = open('c:/layoutdict', "w")
for (variablename,startend) in result:
str1 = "Variable Name=" + variablename + ' ' + "StartEnd=" + str(startend)
f.write(str1 + '\n')
f.close()
result = sorted(self.maxmindict.iteritems(),key=operator.itemgetter(1))
f = open('c:/maxmindict', "w")
for (variablename,startend) in result:
str1 = "Variable Name=" + variablename + ' ' + "StartEnd=" + str(startend)
f.write(str1 + '\n')
f.close()
result = sorted(self.recodingsdict.iteritems(),key=operator.itemgetter(1))
f = open('c:/recodingsdict', "w")
for (variablename,startend) in result:
str1 = "Variable Name=" + variablename + ' ' + "StartEnd=" + str(startend)
f.write(str1 + '\n')
f.close()