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
Roque
wendelin
Commits
5ec409e2
Commit
5ec409e2
authored
Sep 11, 2020
by
Ivan Tyagov
Browse files
Options
Browse Files
Download
Plain Diff
Roque data lake
See merge request
nexedi/wendelin!66
parents
04979895
f0dd7676
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
95 additions
and
2 deletions
+95
-2
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/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.py
...erp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.py
+30
-0
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.xml
...rp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.xml
+62
-0
bt5/erp5_wendelin_data_lake_ingestion/WorkflowTemplateItem/portal_workflow/data_set_interaction_workflow/scripts/DataSet_publishDataStreamList.py
...raction_workflow/scripts/DataSet_publishDataStreamList.py
+2
-1
No files found.
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_getDataStreamList.py
View file @
5ec409e2
...
...
@@ -17,7 +17,7 @@ except Exception as e: # fails because unauthorized access
data_stream_dict
=
{}
for
stream
in
data_set
.
DataSet_getDataStreamList
():
if
not
portal
.
ERP5Site_checkReferenceInvalidated
(
stream
)
and
stream
.
getValidationState
()
!=
"draft"
:
if
stream
and
not
portal
.
ERP5Site_checkReferenceInvalidated
(
stream
)
and
stream
.
getValidationState
()
!=
"draft"
:
data_stream_info_dict
=
{
'id'
:
'data_stream_module/'
+
stream
.
getId
(),
'size'
:
stream
.
getSize
(),
'hash'
:
stream
.
getVersion
()
}
...
...
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.py
0 → 100644
View file @
5ec409e2
"""This script invalidate all data sets (and corresponding ingestion objects) older than wendelin.io release (<= 2019)"""
portal
=
context
.
getPortalObject
()
portal_catalog
=
portal
.
portal_catalog
from
DateTime
import
DateTime
old_date
=
DateTime
(
2019
,
12
,
31
)
catalog_kw
=
{
'modification_date'
:
{
'query'
:
old_date
,
'range'
:
'<='
}}
print
"Following Dataset were invalidated:"
for
data_set
in
portal_catalog
(
portal_type
=
"Data Set"
,
**
catalog_kw
):
print
print
"DATASET: "
+
data_set
.
getReference
()
print
"state: "
+
data_set
.
getValidationState
()
print
"date: "
+
str
(
data_set
.
getModificationDate
())
print
"len of datastream list: "
+
str
(
len
(
data_set
.
DataSet_getDataStreamList
()))
for
data_stream
in
data_set
.
DataSet_getDataStreamList
():
if
data_stream
is
not
None
:
portal
.
ERP5Site_invalidateIngestionObjects
(
data_stream
.
getReference
())
try
:
data_stream
.
invalidate
()
except
:
pass
# fails if it's already invalidated, draft or if it doens't allow invalidation (e.g. DI)
portal
.
ERP5Site_invalidateReference
(
data_set
)
try
:
data_set
.
invalidate
()
except
:
pass
# fails if it's already invalidated, draft or if it doens't allow invalidation (e.g. DI)
return
printed
bt5/erp5_wendelin_data_lake_ingestion/SkinTemplateItem/portal_skins/erp5_wendelin_data_lake/ERP5Site_invalidateOldDatasets.xml
0 → 100644
View file @
5ec409e2
<?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>
ERP5Site_invalidateOldDatasets
</string>
</value>
</item>
</dictionary>
</pickle>
</record>
</ZopeData>
bt5/erp5_wendelin_data_lake_ingestion/WorkflowTemplateItem/portal_workflow/data_set_interaction_workflow/scripts/DataSet_publishDataStreamList.py
View file @
5ec409e2
...
...
@@ -3,4 +3,5 @@
"""
data_set
=
state_change
[
'object'
]
for
data_stream
in
data_set
.
DataSet_getDataStreamList
():
data_stream
.
activate
().
publish
()
if
data_stream
and
not
context
.
getPortalObject
().
ERP5Site_checkReferenceInvalidated
(
data_stream
)
and
data_stream
.
getValidationState
()
!=
'draft'
:
data_stream
.
activate
().
publish
()
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