Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
M
Manifest Ingestion DAG
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
OSDU
OSDU Data Platform
Data Flow
Data Ingestion
Manifest Ingestion DAG
Commits
7b9e3f0e
Commit
7b9e3f0e
authored
4 years ago
by
Yan Sushchynski (EPAM)
Committed by
Siarhei Khaletski (EPAM)
4 years ago
Browse files
Options
Downloads
Patches
Plain Diff
GONRG-1783: Valdiate entire manifest entity
parent
f77e486e
No related branches found
Branches containing commit
No related tags found
Tags containing commit
1 merge request
!24
Ingestion updates
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
src/dags/libs/validate_schema.py
+10
-55
10 additions, 55 deletions
src/dags/libs/validate_schema.py
with
10 additions
and
55 deletions
src/dags/libs/validate_schema.py
+
10
−
55
View file @
7b9e3f0e
...
@@ -110,7 +110,7 @@ class SchemaValidator(HeadersMixin):
...
@@ -110,7 +110,7 @@ class SchemaValidator(HeadersMixin):
response
=
requests
.
get
(
uri
,
headers
=
headers
,
timeout
=
60
)
response
=
requests
.
get
(
uri
,
headers
=
headers
,
timeout
=
60
)
return
response
return
response
def
_
_delete_refs
(
self
,
schema_part
:
Union
[
dict
,
list
]):
def
_delete_refs
(
self
,
schema_part
:
Union
[
dict
,
list
]):
"""
"""
Recursively clear a schema
'
s object parts containing
"
$ref
"
.
Recursively clear a schema
'
s object parts containing
"
$ref
"
.
This method is used by generic manifest validation, deleting these fields make such a
This method is used by generic manifest validation, deleting these fields make such a
...
@@ -122,10 +122,10 @@ class SchemaValidator(HeadersMixin):
...
@@ -122,10 +122,10 @@ class SchemaValidator(HeadersMixin):
schema_part
.
clear
()
schema_part
.
clear
()
else
:
else
:
for
k
in
schema_part
:
for
k
in
schema_part
:
self
.
_
_
delete_refs
(
schema_part
[
k
])
self
.
_delete_refs
(
schema_part
[
k
])
elif
isinstance
(
schema_part
,
list
):
elif
isinstance
(
schema_part
,
list
):
for
i
in
schema_part
:
for
i
in
schema_part
:
self
.
_
_
delete_refs
(
i
)
self
.
_delete_refs
(
i
)
def
get_schema_request
(
self
,
uri
:
str
)
->
dict
:
def
get_schema_request
(
self
,
uri
:
str
)
->
dict
:
"""
Get schema from Schema service. Change $id field to url.
"""
Get schema from Schema service. Change $id field to url.
...
@@ -164,9 +164,8 @@ class SchemaValidator(HeadersMixin):
...
@@ -164,9 +164,8 @@ class SchemaValidator(HeadersMixin):
"""
"""
if
not
schema
:
if
not
schema
:
schema
=
self
.
get_schema
(
entity
[
"
kind
"
])
schema
=
self
.
get_schema
(
entity
[
"
kind
"
])
data
=
entity
try
:
try
:
self
.
_validate_against_schema
(
schema
,
data
)
self
.
_validate_against_schema
(
schema
,
entity
)
logger
.
debug
(
f
"
Record successfully validated
"
)
logger
.
debug
(
f
"
Record successfully validated
"
)
return
True
return
True
except
exceptions
.
ValidationError
as
exc
:
except
exceptions
.
ValidationError
as
exc
:
...
@@ -175,17 +174,6 @@ class SchemaValidator(HeadersMixin):
...
@@ -175,17 +174,6 @@ class SchemaValidator(HeadersMixin):
logger
.
error
(
f
"
Error:
{
exc
}
"
)
logger
.
error
(
f
"
Error:
{
exc
}
"
)
return
False
return
False
def
_validate_work_product
(
self
,
work_product
:
dict
):
"""
Validate WP manifest. Raise error if manifest is not valid.
"""
for
key
,
value
in
work_product
.
items
():
if
key
!=
"
WorkProduct
"
:
for
component
in
value
:
self
.
_validate_entity
(
component
)
else
:
self
.
_validate_entity
(
value
)
def
_validate_against_schema
(
self
,
schema
:
dict
,
data
:
Any
):
def
_validate_against_schema
(
self
,
schema
:
dict
,
data
:
Any
):
"""
"""
Validate any data against schema.
Validate any data against schema.
...
@@ -203,27 +191,6 @@ class SchemaValidator(HeadersMixin):
...
@@ -203,27 +191,6 @@ class SchemaValidator(HeadersMixin):
validator
=
jsonschema
.
Draft7Validator
(
schema
=
schema
,
resolver
=
resolver
)
validator
=
jsonschema
.
Draft7Validator
(
schema
=
schema
,
resolver
=
resolver
)
validator
.
validate
(
data
)
validator
.
validate
(
data
)
def
_validate_data_group
(
self
,
entities
:
list
):
"""
Validate each entity from a list of entities.
:param entities:
:return:
"""
if
isinstance
(
entities
,
list
):
for
entity
in
entities
:
self
.
_validate_entity
(
entity
)
def
_validate_whole_manifest
(
self
,
manifest
:
dict
):
"""
Validate any manifest in general.
Also at this step verify that MasterData, ReferenceData, WorkProduct, WorkProductComponents,
Files entities correspond their generic schemas, because references to those schemas are in
a Manifest schema.
"""
schema
=
self
.
get_schema
(
manifest
[
"
kind
"
])
logger
.
debug
(
f
"
Validating kind
{
manifest
[
'
kind
'
]
}
"
)
self
.
_validate_against_schema
(
schema
,
manifest
)
def
validate_common_schema
(
self
,
manifest
:
dict
)
->
dict
:
def
validate_common_schema
(
self
,
manifest
:
dict
)
->
dict
:
"""
"""
This is a preliminary validation of a manifest that verifies that a manifest corresponds
This is a preliminary validation of a manifest that verifies that a manifest corresponds
...
@@ -237,29 +204,19 @@ class SchemaValidator(HeadersMixin):
...
@@ -237,29 +204,19 @@ class SchemaValidator(HeadersMixin):
schema
=
self
.
get_schema
(
manifest
[
"
manifest
"
][
"
kind
"
])
schema
=
self
.
get_schema
(
manifest
[
"
manifest
"
][
"
kind
"
])
schema_without_refs
=
copy
.
deepcopy
(
schema
)
schema_without_refs
=
copy
.
deepcopy
(
schema
)
if
schema_without_refs
.
get
(
"
properties
"
):
if
schema_without_refs
.
get
(
"
properties
"
):
self
.
_
_
delete_refs
(
schema_without_refs
[
"
properties
"
])
self
.
_delete_refs
(
schema_without_refs
[
"
properties
"
])
else
:
else
:
self
.
_
_
delete_refs
(
schema_without_refs
)
self
.
_delete_refs
(
schema_without_refs
)
logger
.
debug
(
"
Schema without refs
"
)
logger
.
debug
(
"
Schema without refs
"
)
logger
.
debug
(
f
"
{
schema_without_refs
}
"
)
logger
.
debug
(
f
"
{
schema_without_refs
}
"
)
self
.
_validate_against_schema
(
schema
,
manifest
)
self
.
_validate_against_schema
(
schema
,
manifest
)
return
schema
return
schema
def
_validate_against_generic_schema
(
self
,
schema
:
str
,
entity
:
Any
)
->
bool
:
try
:
self
.
_validate_against_schema
(
schema
,
entity
)
logger
.
debug
(
f
"
Record successfully validated against generic schema.
"
)
return
True
except
exceptions
.
ValidationError
as
exc
:
logger
.
error
(
"
Schema validation error.
"
)
logger
.
error
(
f
"
Manifest kind:
{
entity
[
'
kind
'
]
}
"
)
logger
.
error
(
f
"
Manifest:
{
entity
}
"
)
logger
.
error
(
f
"
Error:
{
exc
}
"
)
return
False
def
validate_manifest
(
self
,
manifest_records
:
List
[
dict
])
->
List
[
dict
]:
def
validate_manifest
(
self
,
manifest_records
:
List
[
dict
])
->
List
[
dict
]:
"""
"""
Validate manifest. Raise error if manifest is not valid.
Validate manifest
'
s entities one-by-one. Return list of
:param manifest_records: List of manifest
'
s records
:return: List of entities passed the validation
"""
"""
validated_records
=
[]
validated_records
=
[]
if
not
manifest_records
:
if
not
manifest_records
:
...
@@ -267,9 +224,7 @@ class SchemaValidator(HeadersMixin):
...
@@ -267,9 +224,7 @@ class SchemaValidator(HeadersMixin):
for
manifest_record
in
manifest_records
:
for
manifest_record
in
manifest_records
:
manifest
=
manifest_record
.
get
(
"
entity
"
)
manifest
=
manifest_record
.
get
(
"
entity
"
)
if
isinstance
(
manifest
,
dict
)
and
manifest
.
get
(
"
kind
"
):
if
isinstance
(
manifest
,
dict
)
and
manifest
.
get
(
"
kind
"
):
generic_schema
=
self
.
get_schema
(
manifest_record
.
get
(
"
schema
"
))
validation_result
=
self
.
_validate_entity
(
manifest
)
validation_result
=
self
.
_validate_against_generic_schema
(
generic_schema
,
manifest
)
\
and
self
.
_validate_entity
(
manifest
)
if
validation_result
:
if
validation_result
:
validated_records
.
append
(
manifest_record
)
validated_records
.
append
(
manifest_record
)
else
:
else
:
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment