forked from tableau/document-api-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdatasource.py
More file actions
192 lines (148 loc) · 5.99 KB
/
datasource.py
File metadata and controls
192 lines (148 loc) · 5.99 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
###############################################################################
#
# Datasource - A class for writing datasources to Tableau files
#
###############################################################################
import collections
import itertools
import xml.etree.ElementTree as ET
import xml.sax.saxutils as sax
from tableaudocumentapi import Connection, xfile
from tableaudocumentapi import Field
from tableaudocumentapi.multilookup_dict import MultiLookupDict
from tableaudocumentapi.xfile import xml_open
########
# This is needed in order to determine if something is a string or not. It is necessary because
# of differences between python2 (basestring) and python3 (str). If python2 support is every
# dropped, remove this and change the basestring references below to str
try:
basestring
except NameError:
basestring = str
########
_ColumnObjectReturnTuple = collections.namedtuple('_ColumnObjectReturnTupleType', ['id', 'object'])
def _get_metadata_xml_for_field(root_xml, field_name):
if "'" in field_name:
field_name = sax.escape(field_name, {"'": "'"})
xpath = ".//metadata-record[@class='column'][local-name='{}']".format(field_name)
return root_xml.find(xpath)
def _is_used_by_worksheet(names, field):
return any((y for y in names if y in field.worksheets))
class FieldDictionary(MultiLookupDict):
def used_by_sheet(self, name):
# If we pass in a string, no need to get complicated, just check to see if name is in
# the field's list of worksheets
if isinstance(name, basestring):
return [x for x in self.values() if name in x.worksheets]
# if we pass in a list, we need to check to see if any of the names in the list are in
# the field's list of worksheets
return [x for x in self.values() if _is_used_by_worksheet(name, x)]
def _column_object_from_column_xml(root_xml, column_xml):
field_object = Field.from_column_xml(column_xml)
local_name = field_object.id
metadata_record = _get_metadata_xml_for_field(root_xml, local_name)
if metadata_record is not None:
field_object.apply_metadata(metadata_record)
return _ColumnObjectReturnTuple(field_object.id, field_object)
def _column_object_from_metadata_xml(metadata_xml):
field_object = Field.from_metadata_xml(metadata_xml)
return _ColumnObjectReturnTuple(field_object.id, field_object)
class ConnectionParser(object):
def __init__(self, datasource_xml, version):
self._dsxml = datasource_xml
self._dsversion = version
def _extract_federated_connections(self):
return list(map(Connection, self._dsxml.findall('.//named-connections/named-connection/*')))
def _extract_legacy_connection(self):
return list(map(Connection, self._dsxml.findall('connection')))
def get_connections(self):
if float(self._dsversion) < 10:
connections = self._extract_legacy_connection()
else:
connections = self._extract_federated_connections()
return connections
class Datasource(object):
"""
A class for writing datasources to Tableau files.
"""
###########################################################################
#
# Public API.
#
###########################################################################
def __init__(self, dsxml, filename=None):
"""
Constructor. Default is to create datasource from xml.
"""
self._filename = filename
self._datasourceXML = dsxml
self._datasourceTree = ET.ElementTree(self._datasourceXML)
self._name = self._datasourceXML.get('name') or self._datasourceXML.get(
'formatted-name') # TDS files don't have a name attribute
self._version = self._datasourceXML.get('version')
self._connection_parser = ConnectionParser(
self._datasourceXML, version=self._version)
self._connections = self._connection_parser.get_connections()
self._fields = None
@classmethod
def from_file(cls, filename):
"""Initialize datasource from file (.tds)"""
dsxml = xml_open(filename).getroot()
return cls(dsxml, filename)
def save(self):
"""
Call finalization code and save file.
Args:
None.
Returns:
Nothing.
"""
# save the file
xfile._save_file(self._filename, self._datasourceTree)
def save_as(self, new_filename):
"""
Save our file with the name provided.
Args:
new_filename: New name for the workbook file. String.
Returns:
Nothing.
"""
xfile._save_file(self._filename, self._datasourceTree, new_filename)
###########
# name
###########
@property
def name(self):
return self._name
###########
# version
###########
@property
def version(self):
return self._version
###########
# connections
###########
@property
def connections(self):
return self._connections
###########
# fields
###########
@property
def fields(self):
if not self._fields:
self._fields = self._get_all_fields()
return self._fields
def _get_all_fields(self):
column_field_objects = self._get_column_objects()
existing_column_fields = [x.id for x in column_field_objects]
metadata_only_field_objects = (x for x in self._get_metadata_objects() if x.id not in existing_column_fields)
field_objects = itertools.chain(column_field_objects, metadata_only_field_objects)
return FieldDictionary({k: v for k, v in field_objects})
def _get_metadata_objects(self):
return (_column_object_from_metadata_xml(x)
for x in self._datasourceTree.findall(".//metadata-record[@class='column']"))
def _get_column_objects(self):
return [_column_object_from_column_xml(self._datasourceTree, xml)
for xml in self._datasourceTree.findall('.//column')]