Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
haskell-gargantext
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
195
Issues
195
List
Board
Labels
Milestones
Merge Requests
12
Merge Requests
12
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
gargantext
haskell-gargantext
Commits
56eb1b5c
Commit
56eb1b5c
authored
Dec 22, 2022
by
Przemyslaw Kaminski
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[flow] insert documents to the db in batches
parent
461124e8
Pipeline
#3493
passed with stage
in 93 minutes and 25 seconds
Changes
2
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
14 additions
and
9 deletions
+14
-9
Flow.hs
src-test/Core/Text/Flow.hs
+0
-1
Flow.hs
src/Gargantext/Database/Action/Flow.hs
+14
-8
No files found.
src-test/Core/Text/Flow.hs
View file @
56eb1b5c
...
@@ -95,4 +95,3 @@ textFlow' termType contexts = do
...
@@ -95,4 +95,3 @@ textFlow' termType contexts = do
g <- cooc2graph myCooc2
g <- cooc2graph myCooc2
pure g
pure g
-}
-}
src/Gargantext/Database/Action/Flow.hs
View file @
56eb1b5c
...
@@ -53,6 +53,7 @@ import Control.Lens ((^.), view, _Just, makeLenses, over, traverse)
...
@@ -53,6 +53,7 @@ import Control.Lens ((^.), view, _Just, makeLenses, over, traverse)
import
Control.Monad.Reader
(
MonadReader
)
import
Control.Monad.Reader
(
MonadReader
)
import
Data.Aeson.TH
(
deriveJSON
)
import
Data.Aeson.TH
(
deriveJSON
)
import
Data.Conduit.Internal
(
zipSources
)
import
Data.Conduit.Internal
(
zipSources
)
import
qualified
Data.Conduit.List
as
CList
import
Data.Either
import
Data.Either
import
Data.HashMap.Strict
(
HashMap
)
import
Data.HashMap.Strict
(
HashMap
)
import
Data.Hashable
(
Hashable
)
import
Data.Hashable
(
Hashable
)
...
@@ -111,7 +112,7 @@ import Gargantext.Prelude
...
@@ -111,7 +112,7 @@ import Gargantext.Prelude
import
Gargantext.Prelude.Crypto.Hash
(
Hash
)
import
Gargantext.Prelude.Crypto.Hash
(
Hash
)
import
qualified
Gargantext.Core.Text.Corpus.API
as
API
import
qualified
Gargantext.Core.Text.Corpus.API
as
API
import
qualified
Gargantext.Database.Query.Table.Node.Document.Add
as
Doc
(
add
)
import
qualified
Gargantext.Database.Query.Table.Node.Document.Add
as
Doc
(
add
)
import
qualified
Prelude
--
import qualified Prelude
------------------------------------------------------------------------
------------------------------------------------------------------------
-- Imports for upgrade function
-- Imports for upgrade function
...
@@ -264,7 +265,9 @@ flow :: forall env err m a c.
...
@@ -264,7 +265,9 @@ flow :: forall env err m a c.
flow
c
u
cn
la
mfslw
(
mLength
,
docsC
)
logStatus
=
do
flow
c
u
cn
la
mfslw
(
mLength
,
docsC
)
logStatus
=
do
-- TODO if public insertMasterDocs else insertUserDocs
-- TODO if public insertMasterDocs else insertUserDocs
ids
<-
runConduit
$
zipSources
(
yieldMany
[
1
..
])
docsC
ids
<-
runConduit
$
zipSources
(
yieldMany
[
1
..
])
docsC
.|
mapMC
insertDoc
.|
CList
.
chunksOf
100
.|
mapMC
insertDocs'
.|
CList
.
concat
.|
sinkList
.|
sinkList
-- ids <- traverse (\(idx, doc) -> do
-- ids <- traverse (\(idx, doc) -> do
-- id <- insertMasterDocs c la doc
-- id <- insertMasterDocs c la doc
...
@@ -278,18 +281,21 @@ flow c u cn la mfslw (mLength, docsC) logStatus = do
...
@@ -278,18 +281,21 @@ flow c u cn la mfslw (mLength, docsC) logStatus = do
flowCorpusUser
(
la
^.
tt_lang
)
u
cn
c
ids
mfslw
flowCorpusUser
(
la
^.
tt_lang
)
u
cn
c
ids
mfslw
where
where
insertDoc
::
(
Integer
,
a
)
->
m
NodeId
insertDocs'
::
[(
Integer
,
a
)]
->
m
[
NodeId
]
insertDoc
(
idx
,
doc
)
=
do
insertDocs'
[]
=
pure
[]
id
<-
insertMasterDocs
c
la
[
doc
]
insertDocs'
docs
=
do
printDebug
"[flow] calling insertDoc, ([idx], mLength) = "
(
fst
<$>
docs
,
mLength
)
ids
<-
insertMasterDocs
c
la
(
snd
<$>
docs
)
let
maxIdx
=
maximum
(
fst
<$>
docs
)
case
mLength
of
case
mLength
of
Nothing
->
pure
()
Nothing
->
pure
()
Just
len
->
do
Just
len
->
do
logStatus
JobLog
{
_scst_succeeded
=
Just
$
fromIntegral
$
1
+
i
dx
logStatus
JobLog
{
_scst_succeeded
=
Just
$
fromIntegral
$
1
+
maxI
dx
,
_scst_failed
=
Just
0
,
_scst_failed
=
Just
0
,
_scst_remaining
=
Just
$
fromIntegral
$
len
-
i
dx
,
_scst_remaining
=
Just
$
fromIntegral
$
len
-
maxI
dx
,
_scst_events
=
Just
[]
,
_scst_events
=
Just
[]
}
}
pure
$
Prelude
.
head
id
pure
ids
...
...
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