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
3cabc48d
Commit
3cabc48d
authored
Jan 27, 2020
by
Alexandre Delanoë
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[UPLOAD] adding CSV Garg v3 parser.
parent
2044f66d
Changes
3
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
15 additions
and
5 deletions
+15
-5
New.hs
src/Gargantext/API/Corpus/New.hs
+10
-4
File.hs
src/Gargantext/API/Corpus/New/File.hs
+2
-1
CSV.hs
src/Gargantext/Text/Corpus/Parsers/CSV.hs
+3
-0
No files found.
src/Gargantext/API/Corpus/New.hs
View file @
3cabc48d
...
...
@@ -43,7 +43,7 @@ import Gargantext.Database.Types.Node (CorpusId)
import
Gargantext.Database.Types.Node
(
ToHyperdataDocument
(
..
))
import
Gargantext.Database.Types.Node
(
UserId
)
import
Gargantext.Prelude
import
Gargantext.Text.Corpus.Parsers.CSV
(
parse
Hal
'
)
import
Gargantext.Text.Corpus.Parsers.CSV
(
parse
Csv'
)
--parseHal')--, parseCsv
')
import
Gargantext.Text.Terms
(
TermType
(
..
))
import
Servant
import
Servant.API.Flatten
(
Flat
)
...
...
@@ -221,11 +221,17 @@ addToCorpusWithForm :: FlowCmdM env err m
->
WithForm
->
(
ScraperStatus
->
m
()
)
->
m
ScraperStatus
addToCorpusWithForm
cid
(
WithForm
_
ft
d
)
logStatus
=
do
addToCorpusWithForm
cid
(
WithForm
ft
d
)
logStatus
=
do
let
docs
=
splitEvery
500
let
parse
=
case
ft
of
Just
CSV_HAL
->
parseHal'
Just
CSV
->
parseCsv'
_
->
parseHal'
docs
=
splitEvery
500
$
take
1000000
$
parse
Hal
'
(
cs
d
)
$
parse
Csv
'
(
cs
d
)
logStatus
ScraperStatus
{
_scst_succeeded
=
Just
1
,
_scst_failed
=
Just
0
...
...
src/Gargantext/API/Corpus/New/File.hs
View file @
3cabc48d
...
...
@@ -48,7 +48,7 @@ import Test.QuickCheck.Arbitrary (Arbitrary, arbitrary)
-------------------------------------------------------------
type
Hash
=
Text
data
FileType
=
CSV
|
PresseRIS
data
FileType
=
CSV
|
CSV_HAL
|
PresseRIS
deriving
(
Eq
,
Show
,
Generic
)
instance
ToSchema
FileType
...
...
@@ -65,6 +65,7 @@ instance ToParamSchema (MultipartData Mem) where
instance
FromHttpApiData
FileType
where
parseUrlPiece
"CSV"
=
pure
CSV
parseUrlPiece
"CSV_HAL"
=
pure
CSV_HAL
parseUrlPiece
"PresseRis"
=
pure
PresseRIS
parseUrlPiece
_
=
pure
CSV
-- TODO error here
...
...
src/Gargantext/Text/Corpus/Parsers/CSV.hs
View file @
3cabc48d
...
...
@@ -396,3 +396,6 @@ parseHal' = V.toList . V.map csvHal2doc . snd . readCsvHalLazyBS
parseCsv
::
FilePath
->
IO
[
HyperdataDocument
]
parseCsv
fp
=
V
.
toList
<$>
V
.
map
csv2doc
<$>
snd
<$>
readFile
fp
parseCsv'
::
BL
.
ByteString
->
[
HyperdataDocument
]
parseCsv'
bs
=
V
.
toList
$
V
.
map
csv2doc
$
snd
$
readCsvLazyBS
bs
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