Jac/lxml

samples/show-fields/show_fields.py

@@ -6,30 +6,34 @@
 ############################################################
 # Step 2)  Open the .tds we want to inspect
 ############################################################
-sourceTDS = Datasource.from_file('world.tds')
+datasources = [Datasource.from_file('world.tds'), Datasource.from_file('nested.tds')]
+for sourceTDS in datasources:
 
-############################################################
-# Step 3)  Print out all of the fields and what type they are
-############################################################
-print('----------------------------------------------------------')
-print('-- Info for our .tds:')
-print('--   name:\t{0}'.format(sourceTDS.name))
-print('--   version:\t{0}'.format(sourceTDS.version))
-print('----------------------------------------------------------')
-print('--- {} total fields in this datasource'.format(len(sourceTDS.fields)))
-print('----------------------------------------------------------')
-for count, field in enumerate(sourceTDS.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))
+    ############################################################
+    # Step 3)  Print out all of the fields and what type they are
+    ############################################################
+    print('----------------------------------------------------------')
+    print('-- Info for our .tds:')
+    print('--   name:\t{0}'.format(sourceTDS.name))
+    print('--   version:\t{0}'.format(sourceTDS.version))
+    print('----------------------------------------------------------')
+    print('--- {} total fields in this datasource'.format(len(sourceTDS.fields)))
+    print('----------------------------------------------------------')
+    for count, field in enumerate(sourceTDS.fields.values()):
+        blank_line = False
+        if field.calculation:
+            print('{:>4}: field named `{}` is a `{}`'.format(count+1, field.name, field.datatype))
+            print('      field id, caption, calculation: `{}`, `{}`, `{}`'.format(field.id, field.caption,
+                                                                                  field.calculation))
+            blank_line = True
+        if field.default_aggregation:
+            print('{:>4}: `{}` is a `{}`, default aggregation is `{}`'.format(count+1, field.name, field.datatype,
+                                                                              field.default_aggregation))
+
+        if field.description:
+            print('{:>4}: `{}` is a `{}`, description is `{}`'.format(count+1, field.name, field.datatype,
+                                                                      field.description))
 
-    if blank_line:
-        print('')
-print('----------------------------------------------------------')
+        if blank_line:
+            print('')
+    print('----------------------------------------------------------')

samples/show_workbook_info/show_workbook_info.py

@@ -2,7 +2,7 @@
 # Step 1)  Use Datasource object from the Document API
 ############################################################
 from tableaudocumentapi import Workbook
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 
 ############################################################
 # Step 2)  Open the .tds we want to explore

setup.py

@@ -9,5 +9,6 @@
     packages=['tableaudocumentapi'],
     license='MIT',
     description='A Python module for working with Tableau files.',
-    test_suite='test'
+    test_suite='test',
+    install_requires=['lxml']
 )

tableaudocumentapi/connection.py

@@ -1,4 +1,4 @@
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 from tableaudocumentapi.dbclass import is_valid_dbclass
 
 

tableaudocumentapi/datasource.py

@@ -1,6 +1,6 @@
 import collections
 import itertools
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 import xml.sax.saxutils as sax
 from uuid import uuid4
 

tableaudocumentapi/field.py

@@ -1,5 +1,5 @@
 import functools
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 from xml.dom import minidom
 
 from tableaudocumentapi.property_decorators import argument_is_one_of
@@ -277,7 +277,7 @@ def add_alias(self, key, value):
         # determine whether there already is an aliases-tag
         aliases = self._xml.find('aliases')
         # and create it if there isn't
-        if not aliases:
+        if not aliases:  # ignore the FutureWarning, does not apply to our usage
             aliases = ET.Element('aliases')
             self._xml.append(aliases)
 
@@ -298,7 +298,7 @@ def aliases(self):
         Returns:
             Key-value mappings of all registered aliases. Dict.
         """
-        aliases_tag = self._xml.find('aliases') or []
+        aliases_tag = self._xml.find('aliases') or []    # ignore the FutureWarning, does not apply to our usage
         return {a.get('key', 'None'): a.get('value', 'None') for a in list(aliases_tag)}
 
     ########################################

tableaudocumentapi/xfile.py

@@ -3,7 +3,7 @@
 import shutil
 import tempfile
 import zipfile
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 
 from distutils.version import LooseVersion as Version
 

test/bvt.py

@@ -1,7 +1,7 @@
 import os
 import unittest
 
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 from test.assets.index import *
 from tableaudocumentapi import Workbook, Datasource, Connection, ConnectionParser
 from tableaudocumentapi.xfile import TableauInvalidFileException, TableauVersionNotSupportedException
@@ -160,7 +160,7 @@ def test_save_has_xml_declaration(self):
         with open(self.tds_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'?>")
+                first_line, "<?xml version='1.0' encoding='UTF-8'?>")
 
 
 class DatasourceModelV10Tests(unittest.TestCase):
@@ -323,7 +323,7 @@ def test_save_has_xml_declaration(self):
         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'?>")
+                first_line, "<?xml version='1.0' encoding='UTF-8'?>")
 
 
 class WorkbookModelV10TWBXTests(unittest.TestCase):

test/test_field_change.py

@@ -2,7 +2,7 @@
 import os.path
 
 from tableaudocumentapi import Datasource
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 
 
 TEST_ASSET_DIR = os.path.join(

test/test_xfile.py

@@ -53,21 +53,10 @@ def test_save_preserves_namespace_twb(self):
         wb.save_as(new_name)
         self.assertContainsUserNamespace(new_name)
 
-    '''
     def demo_bug_ns_not_preserved_if_not_used(self):
         filename = TABLEAU_10_TDS
         self.assertContainsUserNamespace(filename)
         wb = Datasource.from_file(filename)
-        #wb.save()
         new_name = 'saved-as-tds.tds'
         wb.save_as(new_name)
-        self.assertContainsUserNamespace(new_name) <- throws
-
-    If there is no namespace in the document when you begin working with it,
-    none will be added.
-    If there is a namespace but it *is not used* in the document, it will be stripped
-
-    Fix will be something like
-    https://stackoverflow.com/questions/41937624/elementtree-why-are-my-namespace-declarations-stripped-out
-
-    '''
+        self.assertContainsUserNamespace(new_name)