Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
W
wendelin
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Xiaowu Zhang
wendelin
Commits
b0be31a9
Commit
b0be31a9
authored
Mar 08, 2021
by
Roque
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
erp5_wendelin_data_lake_ingestion: drop obsolete script and use new name
parent
7357b3db
Changes
5
Show whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
4 additions
and
79 deletions
+4
-79
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/DataSet_getDataStreamList.py
...kins/erp5_wendelin_data_lake/DataSet_getDataStreamList.py
+0
-13
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/DataSet_getDataStreamList.xml
...ins/erp5_wendelin_data_lake/DataSet_getDataStreamList.xml
+0
-62
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_getDataStreamCount.py
...ns/erp5_wendelin_data_lake/ERP5Site_getDataStreamCount.py
+1
-1
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_getDataStreamList.py
...ins/erp5_wendelin_data_lake/ERP5Site_getDataStreamList.py
+1
-1
bt5/erp5_wendelin_data_lake_ingestion/TestTemplateItem/portal_components/test.erp5.testDataLakeIngestion.py
...Item/portal_components/test.erp5.testDataLakeIngestion.py
+2
-2
No files found.
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/DataSet_getDataStreamList.py
deleted
100644 → 0
View file @
7357b3db
"""
Return list of Data Streams belonging to a Date Set.
Data Ingestion line aggregates both Data Set and Data Stream.
Note: This code is quite computationally costly (for Data Streams having thousands of iles) as it needs to:
1. Query MariaDB to find ingestion lines
2. Read from ZODB both Data Ingestion Lines and Data Streams (which itself can be big too)
"""
data_ingestion_line_list
=
context
.
portal_catalog
(
portal_type
=
"Data Ingestion Line"
,
aggregate_uid
=
context
.
getUid
())
return
[
x
.
getAggregateValue
(
portal_type
=
"Data Stream"
)
\
for
x
in
data_ingestion_line_list
]
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/DataSet_getDataStreamList.xml
deleted
100644 → 0
View file @
7357b3db
<?xml version="1.0"?>
<ZopeData>
<record
id=
"1"
aka=
"AAAAAAAAAAE="
>
<pickle>
<global
name=
"PythonScript"
module=
"Products.PythonScripts.PythonScript"
/>
</pickle>
<pickle>
<dictionary>
<item>
<key>
<string>
Script_magic
</string>
</key>
<value>
<int>
3
</int>
</value>
</item>
<item>
<key>
<string>
_bind_names
</string>
</key>
<value>
<object>
<klass>
<global
name=
"NameAssignments"
module=
"Shared.DC.Scripts.Bindings"
/>
</klass>
<tuple/>
<state>
<dictionary>
<item>
<key>
<string>
_asgns
</string>
</key>
<value>
<dictionary>
<item>
<key>
<string>
name_container
</string>
</key>
<value>
<string>
container
</string>
</value>
</item>
<item>
<key>
<string>
name_context
</string>
</key>
<value>
<string>
context
</string>
</value>
</item>
<item>
<key>
<string>
name_m_self
</string>
</key>
<value>
<string>
script
</string>
</value>
</item>
<item>
<key>
<string>
name_subpath
</string>
</key>
<value>
<string>
traverse_subpath
</string>
</value>
</item>
</dictionary>
</value>
</item>
</dictionary>
</state>
</object>
</value>
</item>
<item>
<key>
<string>
_params
</string>
</key>
<value>
<string></string>
</value>
</item>
<item>
<key>
<string>
id
</string>
</key>
<value>
<string>
DataSet_getDataStreamList
</string>
</value>
</item>
</dictionary>
</pickle>
</record>
</ZopeData>
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_getDataStreamCount.py
View file @
b0be31a9
...
@@ -14,6 +14,6 @@ except Exception as e:
...
@@ -14,6 +14,6 @@ except Exception as e:
return
{
"status_code"
:
1
,
"error_message"
:
"401 - Unauthorized access. Please check your user credentials and try again."
}
return
{
"status_code"
:
1
,
"error_message"
:
"401 - Unauthorized access. Please check your user credentials and try again."
}
data_set_uid
=
data_set
.
getUid
()
data_set_uid
=
data_set
.
getUid
()
data_stream_list
=
context
.
ERP5Site
_getDataStreamList
(
data_set_uid
)
data_stream_list
=
context
.
DataSet
_getDataStreamList
(
data_set_uid
)
return
{
"status_code"
:
0
,
"result"
:
len
(
data_stream_list
)
}
return
{
"status_code"
:
0
,
"result"
:
len
(
data_stream_list
)
}
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_getDataStreamList.py
View file @
b0be31a9
...
@@ -19,7 +19,7 @@ except Exception as e: # fails because unauthorized access
...
@@ -19,7 +19,7 @@ except Exception as e: # fails because unauthorized access
return
json
.
dumps
({
"status_code"
:
1
,
"error_message"
:
"401 - Unauthorized access. Please check your user credentials and try again."
})
return
json
.
dumps
({
"status_code"
:
1
,
"error_message"
:
"401 - Unauthorized access. Please check your user credentials and try again."
})
data_set_uid
=
data_set
.
getUid
()
data_set_uid
=
data_set
.
getUid
()
data_stream_list
=
context
.
ERP5Site
_getDataStreamList
(
data_set_uid
,
limit
)
data_stream_list
=
context
.
DataSet
_getDataStreamList
(
data_set_uid
,
limit
)
data_stream_dict
=
{}
data_stream_dict
=
{}
for
stream_brain
in
data_stream_list
:
for
stream_brain
in
data_stream_list
:
...
...
bt5/erp5_wendelin_data_lake_ingestion/TestTemplateItem/portal_components/test.erp5.testDataLakeIngestion.py
View file @
b0be31a9
...
@@ -227,7 +227,7 @@ class TestDataIngestion(SecurityTestCase):
...
@@ -227,7 +227,7 @@ class TestDataIngestion(SecurityTestCase):
self
.
tic
()
self
.
tic
()
# check data relation between Data Set and Data Streams work
# check data relation between Data Set and Data Streams work
self
.
assertSameSet
(
data_stream_list
,
data_set
.
DataSet_getDataStreamList
())
self
.
assertSameSet
(
data_stream_list
,
data_set
.
DataSet_getDataStreamList
(
data_set
.
getUid
()
))
# check data set and all Data Streams states
# check data set and all Data Streams states
self
.
assertEqual
(
'validated'
,
data_set
.
getValidationState
())
self
.
assertEqual
(
'validated'
,
data_set
.
getValidationState
())
...
@@ -359,6 +359,6 @@ class TestDataIngestion(SecurityTestCase):
...
@@ -359,6 +359,6 @@ class TestDataIngestion(SecurityTestCase):
select_list
=
[
'reference'
,
'relative_url'
,
'versioning.size'
,
'versioning.version'
])
select_list
=
[
'reference'
,
'relative_url'
,
'versioning.size'
,
'versioning.version'
])
data_stream_list
=
[
x
.
getObject
()
for
x
in
data_stream_list
]
data_stream_list
=
[
x
.
getObject
()
for
x
in
data_stream_list
]
# assert that the list from the search is the same as DataSet_getDataStreamList
# assert that the list from the search is the same as DataSet_getDataStreamList
self
.
assertSameSet
(
data_stream_list
,
data_set
.
DataSet_getDataStreamList
())
self
.
assertSameSet
(
data_stream_list
,
data_set
.
DataSet_getDataStreamList
(
data_set
.
getUid
()
))
# XXX: new test which simulates download / upload of Data Set and increase DS version
# XXX: new test which simulates download / upload of Data Set and increase DS version
\ No newline at end of file
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment