def test_can_open_twbx_and_save_changes(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].server = 'newdb'
original_wb.save()
new_wb = Workbook(self.workbook_file.name)
self.assertEqual(new_wb.datasources[0].connections[0].server, 'newdb')
def test_can_update_datasource_connection_and_save(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].dbname = 'newdb'
original_wb.save()
new_wb = Workbook(self.workbook_file.name)
self.assertEqual(new_wb.datasources[0].connections[0].dbname, 'newdb')
def test_can_update_datasource_connection_and_save(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].dbname = 'newdb'
original_wb.save()
new_wb = Workbook(self.workbook_file.name)
self.assertEqual(new_wb.datasources[0].connections[
0].dbname, 'newdb')
def test_can_open_twbx_and_save_changes(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].server = 'newdb'
original_wb.save()
new_wb = Workbook(self.workbook_file.name)
self.assertEqual(new_wb.datasources[0].connections[
0].server, 'newdb')
def test_save_has_xml_declaration(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].dbname = 'newdb'
original_wb.save()
with open(self.workbook_file.name) as f:
first_line = f.readline().strip() # first line should be xml tag
self.assertEqual(
first_line, "<?xml version='1.0' encoding='utf-8'?>")
def test_can_open_twbx_and_save_as_changes(self):
new_twbx_filename = 'newtwbx.twbx'
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].server = 'newdb'
original_wb.save_as(new_twbx_filename)
new_wb = Workbook(new_twbx_filename)
self.assertEqual(new_wb.datasources[0].connections[0].server, 'newdb')
os.unlink(new_twbx_filename)
def test_save_has_xml_declaration(self):
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].dbname = 'newdb.test.tsi.lan'
original_wb.save()
with open(self.workbook_file.name) as f:
first_line = f.readline().strip() # first line should be xml tag
self.assertEqual(first_line,
"<?xml version='1.0' encoding='utf-8'?>")
def test_can_open_twbx_and_save_as_changes(self):
new_twbx_filename = 'newtwbx.twbx'
original_wb = Workbook(self.workbook_file.name)
original_wb.datasources[0].connections[0].server = 'newdb'
original_wb.save_as(new_twbx_filename)
new_wb = Workbook(new_twbx_filename)
self.assertEqual(new_wb.datasources[0].connections[
0].server, 'newdb')
os.unlink(new_twbx_filename)
def test_can_mixed_connections_workbook(self):
wb = Workbook(self.twb_file.name)
self.assertTrue(len(wb.datasources), 2)
self.assertTrue(len(wb.datasources[1].connections), 2)
self.assertEqual(wb.datasources[0].connections[0].dbclass, 'sqlproxy')
self.assertEqual(wb.datasources[1].connections[0].dbclass, 'mysql')
self.assertEqual(wb.datasources[1].connections[1].dbclass, 'sqlserver')
def test_can_extract_datasourceV10(self):
wb = Workbook(self.workbook_file.name)
self.assertEqual(len(wb.datasources), 1)
self.assertEqual(len(wb.datasources[0].connections), 2)
self.assertIsInstance(wb.datasources[0].connections, list)
self.assertIsInstance(wb.datasources[0], Datasource)
self.assertEqual(wb.datasources[0].name,
'federated.1s4nxn20cywkdv13ql0yk0g1mpdx')
def print_info_workbook(file_name):
############################################################
# Step 2) Open the .twb or .twbx we want to inspect
############################################################
sourceWB = Workbook(file_name)
############################################################
# Step 3) Print out all of the datasources on this workbook
############################################################
print('----------------------------------------------------------')
print('--- {} total datasources in this workbook'.format(
len(sourceWB.datasources)))
print('----------------------------------------------------------')
############################################################
# Step 4) Print the total field using on each datasource,
# the fields and what type they are
############################################################
for key, value in enumerate(sourceWB.datasources):
print('----------------------------------------------------------')
print('--- {0} total fields in {1} datasource'.format(
len(value.fields.values()), value.name))
print('----------------------------------------------------------')
print('----------------------------------------------------------')
print('-- Info for our .tds:')
print('-- name:\t{0}'.format(value.name))
print('-- version:\t{0}'.format(value.version))
print('----------------------------------------------------------')
for connKey, connInfo in enumerate(value.connections):
print('-------Connection #{0} - {1} ----------------------------'.
format(connKey, connInfo))
print('Server: {}'.format(connInfo.server))
print('DbName: {}'.format(connInfo.dbname))
print('Username: {}'.format(connInfo.username))
print('----------------------------------------------------------')
for count, field in enumerate(value.fields.values()):
print('{:>4}: {} is a {}'.format(count + 1, field.name,
field.datatype))
blank_line = False
if field.calculation:
print(' the formula is {}'.format(field.calculation))
blank_line = True
if field.default_aggregation:
print(' the default aggregation is {}'.format(
field.default_aggregation))
blank_line = True
if field.description:
print(' the description is {}'.format(field.description))
if blank_line:
print('')
print('----------------------------------------------------------')
def get_workbook_info(wbds):
# Make a temp file for downloading the workbook
temp = tempfile.NamedTemporaryFile(delete=False)
try:
# Downlaod the workbook into a temp file, without the extract
server.workbooks.download(wb.id, temp.name, include_extract=False)
# Open the workbook in the doc api and pull the info we need
parsed = Workbook(temp.name)
return parsed
except Exception as e:
print(e)
finally:
temp.close()
os.remove(temp.name)
def initial(filename):
wb = Workbook(os.path.join('twbx', filename))
data = []
for datasource in wb.datasources:
fields = []
for field in datasource.fields.values():
fields.append({
'name': field.name,
'role': field.role,
'datatype': field.datatype,
# 'Number Type': field.type,
'caption': field.caption,
'calculation': field.calculation == '1',
})
data.append({
'name': datasource.name,
'caption': datasource.caption or datasource.name,
'fields': fields
})
return data
def setUp(self):
self.wb = Workbook(TEST_TWB_FILE)
self.ds = self.wb.datasources[
0] # Assume the first datasource in the file
def test_exception_when_workbook_given_tdsx(self):
with self.assertRaises(TableauInvalidFileException):
wb = Workbook(TABLEAU_10_TDSX)
def test_82_workbook_throws_exception(self):
with self.assertRaises(TableauVersionNotSupportedException):
wb = Workbook(TABLEAU_82_TWB)
cur = db.cursor()
cur.execute(
"SELECT uniqueField, schema, DB_Username, DB_Password, Server_Username FROM tablename"
)
for row in cur.fetchall():
uniqueField.append(row[0])
schema.append(row[1])
db_username.append(row[2])
db_password.append(row[3])
server_username.append(row[4])
counter = counter + 1
db.close()
###Creating duplicate copies of workbooks###
sourceWB = Workbook('Base.twbx')
sourceDS = Datasource.from_file('Base.tdsx')
for i in range(0, len(uniqueField)):
for x in sourceWB.datasources:
for j in x.connections:
j.dbname = schema[i]
j.username = db_username[i]
for j in sourceDS.connections:
j.dbname = schema[i]
j.username = db_username[i]
#Saving the workbook and datasource
Workbook.save_as(sourceWB, uniqueField[i] + '.twbx')
Datasource.save_as(sourceDS, uniqueField[i] + '.tdsx')
###Creating sites, projects and users if they don't exist, and publishing the workbooks###
import csv # so we can work with our database list (in a CSV file)
############################################################
# Step 1) Use Workbook object from the Document API
############################################################
from tableaudocumentapi import Workbook
############################################################
# Step 2) Open the .twb we want to replicate
############################################################
sourceWB = Workbook('sample-superstore.twb')
############################################################
# Step 3) Use a database list (in CSV), loop thru and
# create new .twb's with their settings
############################################################
with open('databases.csv') as csvfile:
databases = csv.DictReader(csvfile, delimiter=',', quotechar='"')
for row in databases:
# Set our unique values for this database
sourceWB.datasources[0].connections[0].server = row['Server']
sourceWB.datasources[0].connections[0].dbname = row['Database']
sourceWB.datasources[0].connections[0].username = row['User']
# Save our newly created .twb with the new file name
sourceWB.save_as(row['DBFriendlyName'] + ' - Superstore' + '.twb')
def main():
parser = argparse.ArgumentParser(
description='Connect and publish a workbook to a server.')
parser.add_argument('--server', '-s', required=True, help='server address')
parser.add_argument('--username',
'-u',
required=True,
help='username to sign into server')
parser.add_argument('--password',
'-p',
required=True,
help='password for the user')
parser.add_argument('--dest',
'-D',
required=True,
help='destination server address')
parser.add_argument('-U',
required=True,
help='username to sign into destination server')
parser.add_argument('-P',
required=True,
help='password for the user on the destination server')
parser.add_argument('--source', '-S', default=None)
parser.add_argument('--target', '-T', default=None)
parser.add_argument('--directory', '-d', default='migrated')
parser.add_argument('--logging-level',
'-l',
choices=['debug', 'info', 'error'],
default='error',
help='desired logging level (set to error by default)')
parser.add_argument('workbook',
help='one or more workbooks to publish',
nargs='+')
args = parser.parse_args()
# Set logging level based on user input, or error by default
logging_level = getattr(logging, args.logging_level.upper())
logging.basicConfig(level=logging_level)
# Step 1: Sign in to server.
server, server_auth = connect(args.server, args.username, args.password)
dest, dest_auth = connect(args.dest, args.U, args.P)
overwrite_true = TSC.Server.PublishMode.Overwrite
os.makedirs(args.directory, exist_ok=True)
with server.auth.sign_in(server_auth) and dest.auth.sign_in(dest_auth):
# Step 2: Get the project on server.
source = filter_project(args.source, server)
target = filter_project(args.target, dest)
print("source: {0} [{1}]".format(server.baseurl, source.name))
print("destination: {0} [{1}]".format(dest.baseurl, target.name))
# Step 4: If project is found, build lookup tables.
if source is not None and target is not None:
# Step 3: Build a list of datasources.
ds_source = extract_ds(server, source)
ds_target = extract_ds(dest, target)
dbnames_from_to = map_content_url_from_to(ds_source, ds_target)
# Step 4: Form a new workbook item and publish.
for wb in args.workbook:
pub = Workbook(wb)
for ds in pub.datasources:
value = ''
if len(ds.connections
) == 1 and ds.connections[0].dbclass == 'sqlproxy':
try:
if len(ds.caption) == 0 and ds.name in ds_target:
value = ds.name
ds.connections[0] = ds_target[
value].connections[0]
elif ds.connections[0].dbname in dbnames_from_to:
value = dbnames_from_to[
ds.connections[0].dbname]
ds.connections[0].dbname = value
else:
value = clean_name(ds.caption)
ds.connections[0] = ds_target[
value].connections[0]
except LookupError as e:
raise LookupError(
"lookup information between target and source is inconsistent, datasource caption: {0}, connection: {1}"
.format(ds.caption, ds.connections[0].dbname))
print("{0}, {1} --> {2}".format(ds.caption, ds.name,
value))
wb_migrated = os.path.join(args.directory, wb)
pub.save_as(wb_migrated)
new_workbook = TSC.WorkbookItem(target.id)
try:
new_workbook = dest.workbooks.publish(
new_workbook, wb_migrated, overwrite_true)
except TSC.server.endpoint.exceptions.ServerResponseError:
dest.version = '2.4'
new_workbook = dest.workbooks.publish(
new_workbook, wb_migrated, overwrite_true)
print("workbook published ID: {0}".format(new_workbook.id))
def test_no_exceptions_thrown(self):
wb = Workbook(EMPTY_WORKBOOK)
self.assertIsNotNone(wb)
tableau_auth = TSC.TableauAuth('login', 'password',site.content_url)
server.auth.sign_in(tableau_auth)
all_workbooks = list(TSC.Pager(server.workbooks))
##For Each Workbook
for workbook in all_workbooks:
if workbook.id=="54fb14ca-7395-47fa-b6db-af568699bd92":
try:
##Download Workbook
workbooks.append([workbook.id,workbook.name,workbook.owner_id,workbook.project_id,workbook.project_name,site.name])
file_path = server.workbooks.download(workbook.id,no_extract=True)
print("Downloaded the file to {0}".format(file_path))
extension=file_path.split(".")[len(file_path.split("."))-1]
tree=""
##Manage extenssion
if extension == "twb":
wb = Workbook(file_path)
tree = ET.parse(file_path)
os.remove(file_path)
else:
mzip = os.rename(file_path,"temp.zip" )
zip = zipfile.ZipFile("temp.zip")
zip=zip.extractall('temp')
name=""
for f in glob.glob('temp/*.twb'):
name=f
wb = Workbook(name)
tree = ET.parse(name)
os.remove("temp.zip")
shutil.rmtree("temp")
root = tree.getroot()
##Get Data for Dashboards
def test_can_get_worksheets(self):
wb = Workbook(self.workbook_file.name)
self.assertIsNotNone(wb.worksheets)
from tableaudocumentapi import Workbook
from tableaudocumentapi import Connection
sourceWB = Workbook('TestCase3.twbx')
#Allowing the user to choose whether to replace the datasource with an embedded or published connection
user_login = ""
print "The workbook is currently connected to a flat file and a published datasource but can be replaced by an alternative embedded or published connection respectively. The embedded connection will fail due to differences in table names but the published connection will not. The published connection can be found in the Presales site. Choose the type of datasource you would like to replace the existing connection with : "
user_login = raw_input("Please enter your demoapac.tableau.com username: "******"sqlproxy":
j.server = "sql.databender.net, 14333"
j.dbname = "Superstore"
j.dbclass = "sqlserver"
j.username = "******"
elif j.dbclass == "sqlproxy":
j.server = "https://demoapac.tableau.com"
j.dbname = "TestCase3-destination"
j.username = "******"
#Saving the workbook
Workbook.save_as(sourceWB, 'TestCase3 output.twbx')
print ""
print "The workbook connections have been updated. Please open the newly created workbook to test."
for field in datasource.fields.values():
field_attributes = [
field.id, field.caption, field.alias, field.datatype, field.role,
field.is_quantitative, field.is_ordinal, field.is_nominal,
field.calculation, field.default_aggregation, field.description
]
print(field_attributes)
# file_name = "C:\\Users\\jj2362\\Desktop\\docs in\\standard frequent flyer.tds"
file_name = "C:\\Users\\jj2362\\Desktop\\Sheet1 (Visual_Analytics_TOC_DataSimulated).tds"
# file_name = "C:\\Users\\jj2362\\Desktop\\docs in\\Master.twb"
file_type = xml_open(file_name)
base = file_type.getroot()
print(base.tag)
if base.tag == 'datasource':
document = tableaudocumentapi.Datasource.from_file(file_name)
process_datasources(document)
else:
document = Workbook(file_name)
for datasource in document.datasources:
process_datasources(datasource)
print("")
# for datasource in workbook.datasources:
test = Field()
print(test._attributes)
from tableaudocumentapi import Workbook
from tableaudocumentapi import Datasource
from tableaudocumentapi import Field
from tableaudocumentapi import Connection
import pprint as pp
sourceWB = Workbook('ZenoWorkbook.twb')
sourceDB = Datasource.from_file('Beatlog (BeatlogV1).tdsx')
print("Filename: " + sourceWB.filename)
print(sourceWB.worksheets)
pp.pprint(sourceWB.datasources)
def listTDS(sourceTDS):
print('----------------------------------------------------------')
print('-- Info for our .tds:')
print('-- name:\t{0}'.format(sourceTDS.name))
print('-- version:\t{0}'.format(sourceTDS.version))
print('----------------------------------------------------------')
return
pp.pprint(sourceDB.connections)
pp.pprint(sourceDB.fields)
def showFields(sourceTDS):
print('----------------------------------------------------------')
from tableaudocumentapi import Workbook
sourceWB = Workbook('workbook__31__5ebd2e77c610660027445090_output.twbx')
for i in range(0, (len(sourceWB.datasources))):
sourceWB.datasources[i].connections[
0].server = "sandbox3.opexanalytics.com"
sourceWB.datasources[i].connections[
0].dbname = "qa_tableau_test_app_5ed5fba9c966080027ea792a"
sourceWB.datasources[i].connections[
0].username = "******"
sourceWB.datasources[i].connections[0].password = "******"
print("Updated for : ", (sourceWB.datasources[i].caption))
sourceWB.save()
from tableaudocumentapi import Workbook, Datasource
import os
import pandas as pd
baseLoc = "../../data/"
baseTab = os.path.join(baseLoc, 'tableau')
baseTabout = os.path.join(baseLoc, 'tableauout')
Details = []
print(baseTab)
for file in os.listdir(baseTab):
if file.endswith(".twbx"):
# print(file)
sourceWB = Workbook(os.path.join(baseTab, file))
worksheets = sourceWB.worksheets
for worksheet in worksheets:
for datasource in sourceWB.datasources:
for count, field in enumerate(datasource.fields.values()):
for fieldWorksheet in field.worksheets:
if worksheet == fieldWorksheet:
# print(file,worksheet, "==", fieldWorksheet, "|", count, field.name, "-", field.caption)
Details.append([
file, worksheet, datasource.caption, count,
field.name, field.caption, field.role
])
detailsdc = []
for file in os.listdir(baseTab):
def test_can_extract_datasource(self):
wb = Workbook(self.workbook_file.name)
self.assertEqual(len(wb.datasources), 1)
self.assertIsInstance(wb.datasources[0], Datasource)
self.assertEqual(wb.datasources[0].name,
'sqlserver.17u3bqc16tjtxn14e2hxh19tyvpo')
def test_has_filename(self):
wb = Workbook(self.workbook_file.name)
self.assertEqual(wb.filename, self.workbook_file.name)
from pathlib import Path
import requests
from tableaudocumentapi import Workbook
import os
import sys
filename = Path('metadata.pdf')
url = 'https://www.echr.coe.int/Documents/Application_Form_ENG.pdf'
response = requests.get(url)
filename.write_bytes(response.content)
sourceWB = Workbook(file_name)
sourceWB.save_as(os.path.join(os.path.dirname(filename)))
def file_save_as(self):
fout = asksaveasfilename(defaultextension='.pdf')
try:
with open(fout, 'w') as output:
for x in self.entries:
output.write(x.get())
except FileNotFoundError:
print("Cancelled save or error in filename")
file_save_as()
# import sys
# import os
# import pathlib
def main():
parser = argparse.ArgumentParser(description='dump output from workbooks')
parser.add_argument('--server', '-s', required=True, help='server address')
parser.add_argument('--site', '-S', default='')
parser.add_argument('--project', required=True, default=None)
parser.add_argument('--username',
'-u',
help='username to sign into server')
parser.add_argument('-p', '--password', default=None)
parser.add_argument('--filepath',
'-f',
required=True,
help='filepath to save the image(s) returned')
parser.add_argument('--logging-level',
'-l',
choices=['debug', 'info', 'error'],
default='error',
help='desired logging level (set to error by default)')
parser.add_argument(
'workbook',
help='one or more workbooks to process, "all" means all workbooks',
nargs='+')
args = parser.parse_args()
if args.password is None:
password = getpass.getpass("Password: "******"2.5"
with server.auth.sign_in(tableau_auth):
server.use_server_version()
calculations = dict()
# Step 2: Query for the workbook that we want info on
for wb in TSC.Pager(server.workbooks):
if (args.workbook[0] == "all" or wb.name
in args.workbook) and wb.project_name == args.project:
filename = server.workbooks.download(wb.id,
filepath=args.filepath,
include_extract=False)
contents = Workbook(filename)
print("workbook [{0}]: {1}".format(wb.name, contents.filename))
for ds in contents.datasources:
for name in ds.fields:
field = ds.fields[name]
if field.calculation is not None and 'false' != field.calculation:
calculations[field.id] = field
for ds in contents.datasources:
for name in ds.fields:
field = ds.fields[name]
s = substitute_calculations(calculations,
field.calculation)
if len(field.worksheets) > 0:
print('field [{1}]({0}): {3}; "{4}":"{5}"'.format(
field.datatype, field.name, field.caption,
", ".join(field.worksheets), field.calculation,
s))
def test_can_open_twbx(self):
wb = Workbook(self.workbook_file.name)
self.assertTrue(wb.datasources)
self.assertTrue(wb.datasources[0].connections)
import csv # so we can work with our database list (in a CSV file)
############################################################
# Step 1) Use Workbook object from the Document API
############################################################
from tableaudocumentapi import Workbook
############################################################
# Step 2) Open the .twb we want to replicate
############################################################
sourceWB = Workbook('sample-superstore.twb')
############################################################
# Step 3) Use a database list (in CSV), loop thru and
# create new .twb's with their settings
############################################################
with open('databases.csv') as csvfile:
databases = csv.DictReader(csvfile, delimiter=',', quotechar='"')
for row in databases:
# Set our unique values for this database
sourceWB.datasources[0].connections[0].server = row['Server']
sourceWB.datasources[0].connections[0].dbname = row['Database']
sourceWB.datasources[0].connections[0].username = row['User']
# Save our newly created .twb with the new file name
sourceWB.save_as(row['DBFriendlyName'] + ' - Superstore' + '.twb')
def view_conn_info(adv_dir, file_name):
source = Workbook(adv_dir + '/' + file_name)
for ds in source.datasources:
for conn in ds.connections:
# print conn
write_log('output/run.log', conn, print_log_value=True)
from tableaudocumentapi import Workbook
from tableaudocumentapi import Connection
sourceWB = Workbook('TestCase1.twbx')
#Printing workbook information
print "Workbook Name : "
print sourceWB.filename
print "Sheet Names : "
print sourceWB.worksheets
#Printing data connection information
for x in sourceWB.datasources:
print "Datasource details in following order (Server name, database name, user name, database type, port, authentication) :"
for j in x.connections:
print j.server
print j.dbname
print j.username
print j.dbclass
print j.port
print j.authentication
print " "