Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
C
core
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
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 JiHu GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Chenhao Ma
core
Commits
4a7754dd
Commit
4a7754dd
authored
9 years ago
by
Renzo Frigato
Browse files
Options
Downloads
Patches
Plain Diff
add advanced datatree search query
parent
a2e402ca
No related branches found
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
api/api.py
+2
-1
2 additions, 1 deletion
api/api.py
api/handlers/searchhandler.py
+104
-1
104 additions, 1 deletion
api/handlers/searchhandler.py
with
106 additions
and
2 deletions
api/api.py
+
2
−
1
View file @
4a7754dd
...
...
@@ -137,7 +137,8 @@ routes = [
webapp2
.
Route
(
_format
(
r
'
/api/<par_cont_name:groups>/<par_id:{group_id_re}>/<cont_name:projects>
'
),
containerhandler
.
ContainerHandler
,
name
=
'
cont_sublist_groups
'
,
handler_method
=
'
get_all
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/<par_cont_name:{cont_name_re}>/<par_id:{cid_re}>/<cont_name:{cont_name_re}>
'
),
containerhandler
.
ContainerHandler
,
name
=
'
cont_sublist
'
,
handler_method
=
'
get_all
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/search
'
),
searchhandler
.
SearchHandler
,
name
=
'
es_proxy
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/search/<cont_name:{cont_name_re}>
'
),
searchhandler
.
SearchHandler
,
name
=
'
es_proxy_1
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/search/files
'
),
searchhandler
.
SearchHandler
,
handler_method
=
'
get_datatree
'
,
name
=
'
es_data
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/search/<cont_name:{cont_name_re}>
'
),
searchhandler
.
SearchHandler
,
name
=
'
es_proxy
'
,
methods
=
[
'
GET
'
]),
webapp2
.
Route
(
_format
(
r
'
/api/schemas/<schema:{schema_re}>
'
),
schemahandler
.
SchemaHandler
,
name
=
'
schemas
'
,
methods
=
[
'
GET
'
]),
]
...
...
This diff is collapsed.
Click to expand it.
api/handlers/searchhandler.py
+
104
−
1
View file @
4a7754dd
import
bson
import
datetime
import
elasticsearch
...
...
@@ -6,8 +7,77 @@ from .. import config
log
=
config
.
log
parent_container
=
{
'
acquisitions
'
:
'
sessions
'
,
'
sessions
'
:
'
projects
'
}
def
_filter_body_by_type
(
body
,
doc_type
):
query
=
{
'
query
'
:
{
'
filtered
'
:
{
'
query
'
:
body
,
'
filter
'
:
{
'
type
'
:
{
'
value
'
:
doc_type
}
}
}
},
'
min_score
'
:
0.5
}
return
query
class
SearchHandler
(
base
.
RequestHandler
):
"""
This class allows to proxy queries to elasticsearch
The get method just wraps the body in a convenient elasticsearch query.
The get_datatree (for the special doc_type
'
files
'
) for each result build the datatree
with the containers in their hierarchy.
output example:
[
{
"
mimetype
"
:
"
application/zip
"
,
"
hash
"
:
"
v0-sha384-8607a3c17008ff24d0cb9e1ccd60f5c7bcc1810b8c1dc9ee0f14ee91b7b1f897b78fcb035ff0135520a58bebfcdbd78b
"
,
"
name
"
:
"
8613_6_1_t1.zip
"
,
"
project
"
: {
"
group
"
:
"
scitran
"
,
"
created
"
:
"
2016-03-08T22:46:01.941000+00:00
"
,
"
modified
"
:
"
2016-03-08T22:46:33.030000+00:00
"
,
"
label
"
:
"
Neuroscience
"
,
"
_id
"
:
"
56df5629b13d67a9cbfca1ea
"
,
"
public
"
: false
},
"
session
"
: {
"
group
"
:
"
scitran
"
,
"
created
"
:
"
2016-03-08T22:46:16.221000+00:00
"
,
"
modified
"
:
"
2016-03-08T22:46:18.822000+00:00
"
,
"
label
"
:
"
1.2.840.113619.6.353.50113891957665820485497041858168751557
"
,
"
project
"
:
"
56df5629b13d67a9cbfca1ea
"
,
"
_id
"
:
"
56df5638b13d67a9cbfca1f7
"
,
"
public
"
: false,
"
subject
"
: {
"
code
"
:
"
ex8613
"
}
},
"
container_name
"
:
"
acquisitions
"
,
"
type
"
:
"
dicom
"
,
"
acquisition
"
: {
"
created
"
:
"
2016-03-08T22:46:17.164000
"
,
"
timestamp
"
:
"
2015-01-07T17:38:09
"
,
"
modified
"
:
"
2016-03-08T22:46:17.164000
"
,
"
label
"
:
"
T1_high-res_inplane_Ret_knk
"
,
"
instrument
"
:
"
MRI
"
,
"
session
"
:
"
56df5638b13d67a9cbfca1f7
"
,
"
measurement
"
:
"
anatomical
"
,
"
timezone
"
:
"
America/Los_Angeles
"
,
"
_id
"
:
"
56df5639b13d67a9cbfca1f9
"
,
"
public
"
: false
},
"
size
"
: 3216386
},
...
]
"""
def
__init__
(
self
,
request
=
None
,
response
=
None
):
super
(
SearchHandler
,
self
).
__init__
(
request
,
response
)
...
...
@@ -17,8 +87,41 @@ class SearchHandler(base.RequestHandler):
self
.
abort
(
403
,
'
search is available only for authenticated users
'
)
size
=
self
.
get_param
(
'
size
'
)
body
=
self
.
request
.
json_body
query
=
_filter_body_by_type
(
body
,
cont_name
)
try
:
results
=
config
.
es
.
search
(
index
=
'
scitran
'
,
doc_type
=
cont_name
,
body
=
body
,
_source
=
[
'
_id
'
],
size
=
size
or
10
)
results
=
config
.
es
.
search
(
index
=
'
scitran
'
,
body
=
body
,
_source
=
[
'
_id
'
],
size
=
size
or
10
)
except
elasticsearch
.
exceptions
.
ConnectionError
as
e
:
self
.
abort
(
503
,
'
elasticsearch is not available
'
)
return
results
[
'
hits
'
][
'
hits
'
]
def
get_datatree
(
self
,
**
kwargs
):
if
self
.
public_request
:
self
.
abort
(
403
,
'
search is available only for authenticated users
'
)
size
=
self
.
get_param
(
'
size
'
)
body
=
self
.
request
.
json_body
query
=
_filter_body_by_type
(
body
,
'
files
'
)
try
:
es_results
=
config
.
es
.
search
(
index
=
'
scitran
'
,
body
=
query
,
size
=
size
or
10
)
## elastic search results are wrapped in subkey ['hits']['hits']
es_results
=
es_results
[
'
hits
'
][
'
hits
'
]
results
=
[]
for
result
in
es_results
:
# extract the source of the result
result
=
result
[
'
_source
'
]
# add to the result the container hierarchy references
container
=
result
.
pop
(
'
container
'
)
container
.
pop
(
'
permissions
'
)
cont_name
=
result
[
'
container_name
'
]
result
[
cont_name
[:
-
1
]]
=
container
while
parent_container
.
get
(
cont_name
):
parent_cont_name
=
parent_container
[
cont_name
]
parent_id
=
bson
.
objectid
.
ObjectId
(
container
[
parent_cont_name
[:
-
1
]])
container
=
config
.
db
[
parent_cont_name
].
find_one
({
'
_id
'
:
parent_id
})
container
.
pop
(
'
permissions
'
)
result
[
parent_cont_name
[:
-
1
]]
=
container
cont_name
=
parent_cont_name
results
.
append
(
result
)
except
elasticsearch
.
exceptions
.
ConnectionError
as
e
:
self
.
abort
(
503
,
'
elasticsearch is not available
'
)
return
results
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