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
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
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
Christian Merten
haskell-gargantext
Commits
cf1206df
Commit
cf1206df
authored
Aug 26, 2020
by
Alexandre Delanoë
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[REFACT] Text -> Core
parent
2f9e26f5
Changes
86
Hide whitespace changes
Inline
Side-by-side
Showing
86 changed files
with
255 additions
and
268 deletions
+255
-268
Main.hs
bin/gargantext-adaptative-phylo/Main.hs
+6
-6
CleanCsvCorpus.hs
bin/gargantext-cli/CleanCsvCorpus.hs
+2
-2
Main.hs
bin/gargantext-cli/Main.hs
+7
-7
Main.hs
bin/gargantext-import/Main.hs
+1
-1
Main.hs
bin/gargantext-phylo/Main.hs
+6
-6
package.yaml
package.yaml
+20
-20
Gargantext.hs
src/Gargantext.hs
+0
-2
Metrics.hs
src/Gargantext/API/Metrics.hs
+1
-1
Node.hs
src/Gargantext/API/Node.hs
+1
-1
Contact.hs
src/Gargantext/API/Node/Contact.hs
+1
-1
New.hs
src/Gargantext/API/Node/Corpus/New.hs
+2
-2
Ngrams.hs
src/Gargantext/Core/Flow/Ngrams.hs
+1
-1
Types.hs
src/Gargantext/Core/Flow/Types.hs
+1
-1
Text.hs
src/Gargantext/Core/Text.hs
+2
-2
Context.hs
src/Gargantext/Core/Text/Context.hs
+4
-4
Convert.hs
src/Gargantext/Core/Text/Convert.hs
+4
-4
API.hs
src/Gargantext/Core/Text/Corpus/API.hs
+6
-6
Hal.hs
src/Gargantext/Core/Text/Corpus/API/Hal.hs
+3
-3
Isidore.hs
src/Gargantext/Core/Text/Corpus/API/Isidore.hs
+5
-5
Istex.hs
src/Gargantext/Core/Text/Corpus/API/Istex.hs
+3
-3
Pubmed.hs
src/Gargantext/Core/Text/Corpus/API/Pubmed.hs
+2
-2
Parsers.hs
src/Gargantext/Core/Text/Corpus/Parsers.hs
+8
-8
CSV.hs
src/Gargantext/Core/Text/Corpus/Parsers/CSV.hs
+4
-4
Date.hs
src/Gargantext/Core/Text/Corpus/Parsers/Date.hs
+3
-3
Attoparsec.hs
src/Gargantext/Core/Text/Corpus/Parsers/Date/Attoparsec.hs
+2
-2
Parsec.hs
src/Gargantext/Core/Text/Corpus/Parsers/Date/Parsec.hs
+2
-2
GrandDebat.hs
src/Gargantext/Core/Text/Corpus/Parsers/GrandDebat.hs
+2
-2
Isidore.hs
src/Gargantext/Core/Text/Corpus/Parsers/Isidore.hs
+2
-2
Json2Csv.hs
src/Gargantext/Core/Text/Corpus/Parsers/Json2Csv.hs
+3
-3
RIS.hs
src/Gargantext/Core/Text/Corpus/Parsers/RIS.hs
+2
-2
Presse.hs
src/Gargantext/Core/Text/Corpus/Parsers/RIS/Presse.hs
+4
-4
WOS.hs
src/Gargantext/Core/Text/Corpus/Parsers/WOS.hs
+3
-3
Wikimedia.hs
src/Gargantext/Core/Text/Corpus/Parsers/Wikimedia.hs
+3
-3
XML_hs
src/Gargantext/Core/Text/Corpus/Parsers/XML_hs
+0
-0
Examples.hs
src/Gargantext/Core/Text/Examples.hs
+8
-8
Flow.hs
src/Gargantext/Core/Text/Flow.hs
+2
-2
Learn.hs
src/Gargantext/Core/Text/Learn.hs
+10
-10
List.hs
src/Gargantext/Core/Text/List.hs
+5
-5
CSV.hs
src/Gargantext/Core/Text/List/CSV.hs
+3
-3
Learn.hs
src/Gargantext/Core/Text/List/Learn.hs
+4
-4
Metrics.hs
src/Gargantext/Core/Text/Metrics.hs
+2
-2
CharByChar.hs
src/Gargantext/Core/Text/Metrics/CharByChar.hs
+2
-2
Count.hs
src/Gargantext/Core/Text/Metrics/Count.hs
+2
-3
Freq.hs
src/Gargantext/Core/Text/Metrics/Freq.hs
+2
-2
FrequentItemSet.hs
src/Gargantext/Core/Text/Metrics/FrequentItemSet.hs
+2
-2
Hetero.purs
src/Gargantext/Core/Text/Metrics/Hetero.purs
+0
-0
TFICF.hs
src/Gargantext/Core/Text/Metrics/TFICF.hs
+2
-2
CH.hs
src/Gargantext/Core/Text/Samples/CH.hs
+2
-2
DE.hs
src/Gargantext/Core/Text/Samples/DE.hs
+2
-2
EN.hs
src/Gargantext/Core/Text/Samples/EN.hs
+2
-2
FR.hs
src/Gargantext/Core/Text/Samples/FR.hs
+2
-2
SP.hs
src/Gargantext/Core/Text/Samples/SP.hs
+2
-2
Search.hs
src/Gargantext/Core/Text/Search.hs
+5
-5
Terms.hs
src/Gargantext/Core/Text/Terms.hs
+8
-8
Eleve.hs
src/Gargantext/Core/Text/Terms/Eleve.hs
+3
-3
Mono.hs
src/Gargantext/Core/Text/Terms/Mono.hs
+3
-3
Stem.hs
src/Gargantext/Core/Text/Terms/Mono/Stem.hs
+2
-2
En.hs
src/Gargantext/Core/Text/Terms/Mono/Stem/En.hs
+2
-2
Token.hs
src/Gargantext/Core/Text/Terms/Mono/Token.hs
+3
-3
En.hs
src/Gargantext/Core/Text/Terms/Mono/Token/En.hs
+2
-2
Multi.hs
src/Gargantext/Core/Text/Terms/Multi.hs
+7
-7
Group.hs
src/Gargantext/Core/Text/Terms/Multi/Group.hs
+2
-2
En.hs
src/Gargantext/Core/Text/Terms/Multi/Lang/En.hs
+3
-3
Fr.hs
src/Gargantext/Core/Text/Terms/Multi/Lang/Fr.hs
+3
-3
PosTagging.hs
src/Gargantext/Core/Text/Terms/Multi/PosTagging.hs
+2
-2
RAKE.hs
src/Gargantext/Core/Text/Terms/Multi/RAKE.hs
+3
-3
WithList.hs
src/Gargantext/Core/Text/Terms/WithList.hs
+4
-4
Flow.hs
src/Gargantext/Database/Action/Flow.hs
+6
-15
Types.hs
src/Gargantext/Database/Action/Flow/Types.hs
+2
-2
Learn.hs
src/Gargantext/Database/Action/Learn.hs
+1
-1
Metrics.hs
src/Gargantext/Database/Action/Metrics.hs
+1
-1
Lists.hs
src/Gargantext/Database/Action/Metrics/Lists.hs
+1
-1
NgramsByNode.hs
src/Gargantext/Database/Action/Metrics/NgramsByNode.hs
+2
-3
Search.hs
src/Gargantext/Database/Action/Search.hs
+1
-1
Insert.hs
src/Gargantext/Database/Query/Table/Node/Document/Insert.hs
+1
-1
Ngrams.hs
src/Gargantext/Database/Schema/Ngrams.hs
+2
-2
IMT.hs
src/Gargantext/Ext/IMT.hs
+2
-2
AdaptativePhylo.hs
src/Gargantext/Viz/AdaptativePhylo.hs
+1
-1
Chart.hs
src/Gargantext/Viz/Chart.hs
+1
-1
Phylo.hs
src/Gargantext/Viz/Phylo.hs
+1
-1
Aggregates.hs
src/Gargantext/Viz/Phylo/Aggregates.hs
+3
-3
Example.hs
src/Gargantext/Viz/Phylo/Example.hs
+1
-1
LevelMaker.hs
src/Gargantext/Viz/Phylo/LevelMaker.hs
+1
-1
Main.hs
src/Gargantext/Viz/Phylo/Main.hs
+2
-2
PhyloExample.hs
src/Gargantext/Viz/Phylo/PhyloExample.hs
+2
-2
PhyloMaker.hs
src/Gargantext/Viz/Phylo/PhyloMaker.hs
+2
-2
No files found.
bin/gargantext-adaptative-phylo/Main.hs
View file @
cf1206df
...
...
@@ -25,11 +25,11 @@ import Data.Text (Text, unwords, unpack)
import
Gargantext.Prelude
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Corpus.Parsers.CSV
(
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.Text.Corpus.Parsers
(
FileFormat
(
..
),
parseFile
)
import
Gargantext.Text.List.CSV
(
csvMapTermList
)
import
Gargantext.Text.Terms.WithList
(
Patterns
,
buildPatterns
,
extractTermsWithList
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.
Core.
Text.Corpus.Parsers
(
FileFormat
(
..
),
parseFile
)
import
Gargantext.
Core.
Text.List.CSV
(
csvMapTermList
)
import
Gargantext.
Core.
Text.Terms.WithList
(
Patterns
,
buildPatterns
,
extractTermsWithList
)
import
Gargantext.Viz.AdaptativePhylo
import
Gargantext.Viz.Phylo.PhyloMaker
(
toPhylo
)
import
Gargantext.Viz.Phylo.PhyloTools
(
printIOMsg
,
printIOComment
)
...
...
@@ -44,7 +44,7 @@ import Control.Concurrent.Async (mapConcurrently)
import
qualified
Data.ByteString.Lazy
as
Lazy
import
qualified
Data.Vector
as
Vector
import
qualified
Gargantext.Text.Corpus.Parsers.CSV
as
Csv
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.CSV
as
Csv
---------------
...
...
bin/gargantext-cli/CleanCsvCorpus.hs
View file @
cf1206df
...
...
@@ -22,8 +22,8 @@ import Data.Vector (Vector)
import
qualified
Data.Vector
as
V
import
Gargantext.Prelude
import
Gargantext.Text.Search
import
qualified
Gargantext.Text.Corpus.Parsers.CSV
as
CSV
import
Gargantext.
Core.
Text.Search
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.CSV
as
CSV
------------------------------------------------------------------------
type
Query
=
[
S
.
Term
]
...
...
bin/gargantext-cli/Main.hs
View file @
cf1206df
...
...
@@ -49,13 +49,13 @@ import Prelude ((>>))
import
Gargantext.Prelude
import
Gargantext.Core
import
Gargantext.Core.Types
import
Gargantext.Text.Terms
import
Gargantext.Text.Context
import
Gargantext.Text.Terms.WithList
import
Gargantext.Text.Corpus.Parsers.CSV
(
readFile
,
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.Text.List.CSV
(
csvMapTermList
)
import
Gargantext.Text.Terms
(
terms
)
import
Gargantext.Text.Metrics.Count
(
coocOnContexts
,
Coocs
)
import
Gargantext.
Core.
Text.Terms
import
Gargantext.
Core.
Text.Context
import
Gargantext.
Core.
Text.Terms.WithList
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
readFile
,
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.
Core.
Text.List.CSV
(
csvMapTermList
)
import
Gargantext.
Core.
Text.Terms
(
terms
)
import
Gargantext.
Core.
Text.Metrics.Count
(
coocOnContexts
,
Coocs
)
------------------------------------------------------------------------
-- OUTPUT format
...
...
bin/gargantext-import/Main.hs
View file @
cf1206df
...
...
@@ -29,7 +29,7 @@ import Gargantext.Database.Admin.Types.Hyperdata (toHyperdataDocument)
import
Gargantext.Database.Admin.Types.Node
(
CorpusId
)
import
Gargantext.Database.Prelude
(
Cmd
)
import
Gargantext.Prelude
import
Gargantext.Text.Corpus.Parsers
(
FileFormat
(
..
))
import
Gargantext.
Core.
Text.Corpus.Parsers
(
FileFormat
(
..
))
import
Prelude
(
read
)
import
System.Environment
(
getArgs
)
import
qualified
Data.Text
as
Text
...
...
bin/gargantext-phylo/Main.hs
View file @
cf1206df
...
...
@@ -28,11 +28,11 @@ import GHC.IO (FilePath)
import
Gargantext.Database.Admin.Types.Hyperdata
import
Gargantext.Database.Admin.Types.Node
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Corpus.Parsers
(
FileFormat
(
..
),
parseFile
)
import
Gargantext.Text.Corpus.Parsers.CSV
(
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.Text.List.CSV
(
csvMapTermList
)
import
Gargantext.Text.Terms.WithList
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Corpus.Parsers
(
FileFormat
(
..
),
parseFile
)
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
csv_title
,
csv_abstract
,
csv_publication_year
)
import
Gargantext.
Core.
Text.List.CSV
(
csvMapTermList
)
import
Gargantext.
Core.
Text.Terms.WithList
import
Gargantext.Viz.Phylo
import
Gargantext.Viz.Phylo.LevelMaker
import
Gargantext.Viz.Phylo.Tools
...
...
@@ -45,7 +45,7 @@ import qualified Data.List as DL
import
qualified
Data.Map
as
DM
import
qualified
Data.Text
as
DT
import
qualified
Data.Vector
as
DV
import
qualified
Gargantext.Text.Corpus.Parsers.CSV
as
CSV
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.CSV
as
CSV
import
qualified
Prelude
as
P
...
...
package.yaml
View file @
cf1206df
...
...
@@ -58,26 +58,26 @@ library:
-
Gargantext.Database.Admin.Types.Node
-
Gargantext.Prelude
-
Gargantext.Prelude.Utils
-
Gargantext.Text
-
Gargantext.Text.Context
-
Gargantext.Text.Corpus.Parsers
-
Gargantext.Text.Corpus.Parsers.Date.Parsec
-
Gargantext.Text.Corpus.API
-
Gargantext.Text.Corpus.Parsers.CSV
-
Gargantext.Text.Examples
-
Gargantext.Text.List.CSV
-
Gargantext.Text.Metrics
-
Gargantext.Text.Metrics.TFICF
-
Gargantext.Text.Metrics.CharByChar
-
Gargantext.Text.Metrics.Count
-
Gargantext.Text.Search
-
Gargantext.Text.Terms
-
Gargantext.Text.Terms.Mono
-
Gargantext.Text.Terms.Multi.Lang.En
-
Gargantext.Text.Terms.Multi.Lang.Fr
-
Gargantext.Text.Terms.Multi.RAKE
-
Gargantext.Text.Terms.WithList
-
Gargantext.Text.Flow
-
Gargantext.
Core.
Text
-
Gargantext.
Core.
Text.Context
-
Gargantext.
Core.
Text.Corpus.Parsers
-
Gargantext.
Core.
Text.Corpus.Parsers.Date.Parsec
-
Gargantext.
Core.
Text.Corpus.API
-
Gargantext.
Core.
Text.Corpus.Parsers.CSV
-
Gargantext.
Core.
Text.Examples
-
Gargantext.
Core.
Text.List.CSV
-
Gargantext.
Core.
Text.Metrics
-
Gargantext.
Core.
Text.Metrics.TFICF
-
Gargantext.
Core.
Text.Metrics.CharByChar
-
Gargantext.
Core.
Text.Metrics.Count
-
Gargantext.
Core.
Text.Search
-
Gargantext.
Core.
Text.Terms
-
Gargantext.
Core.
Text.Terms.Mono
-
Gargantext.
Core.
Text.Terms.Multi.Lang.En
-
Gargantext.
Core.
Text.Terms.Multi.Lang.Fr
-
Gargantext.
Core.
Text.Terms.Multi.RAKE
-
Gargantext.
Core.
Text.Terms.WithList
-
Gargantext.
Core.
Text.Flow
-
Gargantext.Viz.Graph
-
Gargantext.Viz.Graph.Distances.Matrice
-
Gargantext.Viz.Graph.Index
...
...
src/Gargantext.hs
View file @
cf1206df
...
...
@@ -15,7 +15,6 @@ module Gargantext ( module Gargantext.API
,
module
Gargantext
.
Core
,
module
Gargantext
.
Database
,
module
Gargantext
.
Prelude
,
module
Gargantext
.
Text
-- , module Gargantext.Viz
)
where
...
...
@@ -23,5 +22,4 @@ import Gargantext.API
import
Gargantext.Core
import
Gargantext.Database
import
Gargantext.Prelude
import
Gargantext.Text
--import Gargantext.Viz
src/Gargantext/API/Metrics.hs
View file @
cf1206df
...
...
@@ -39,7 +39,7 @@ import Gargantext.Database.Query.Table.Node.Error (HasNodeError)
import
Gargantext.Database.Query.Table.Node.UpdateOpaleye
(
updateHyperdata
)
import
Gargantext.Database.Schema.Node
(
node_hyperdata
)
import
Gargantext.Prelude
import
Gargantext.Text.Metrics
(
Scored
(
..
))
import
Gargantext.
Core.
Text.Metrics
(
Scored
(
..
))
import
Gargantext.Viz.Chart
import
Gargantext.Viz.Types
import
qualified
Gargantext.Database.Action.Metrics
as
Metrics
...
...
src/Gargantext/API/Node.hs
View file @
cf1206df
...
...
@@ -72,7 +72,7 @@ import qualified Gargantext.Database.Action.Delete as Action (deleteNode)
import
qualified
Gargantext.Database.Query.Table.Node.Update
as
U
(
update
,
Update
(
..
))
{-
import qualified Gargantext.Text.List.Learn as Learn
import qualified Gargantext.
Core.
Text.List.Learn as Learn
import qualified Data.Vector as Vec
--}
...
...
src/Gargantext/API/Node/Contact.hs
View file @
cf1206df
...
...
@@ -42,7 +42,7 @@ import Gargantext.Database.Admin.Types.Hyperdata (HyperdataAnnuaire(..), Hyperda
import
Gargantext.Database.Admin.Types.Hyperdata.Contact
(
hyperdataContact
)
import
Gargantext.Database.Admin.Types.Node
import
Gargantext.Prelude
((
$
),
liftBase
,
(
.
),
printDebug
,
pure
)
import
Gargantext.Text.Terms
(
TermType
(
..
))
import
Gargantext.
Core.
Text.Terms
(
TermType
(
..
))
import
Servant
import
Servant.Job.Async
(
JobFunction
(
..
),
serveJobsAPI
)
import
Test.QuickCheck
(
elements
)
...
...
src/Gargantext/API/Node/Corpus/New.hs
View file @
cf1206df
...
...
@@ -58,8 +58,8 @@ import Gargantext.Database.Query.Table.Node (getNodeWith)
import
Gargantext.Database.Query.Table.Node.UpdateOpaleye
(
updateHyperdata
)
import
Gargantext.Database.Schema.Node
(
node_hyperdata
)
import
qualified
Gargantext.Prelude.Utils
as
GPU
import
qualified
Gargantext.Text.Corpus.API
as
API
import
qualified
Gargantext.Text.Corpus.Parsers
as
Parser
(
FileFormat
(
..
),
parseFormat
)
import
qualified
Gargantext.
Core.
Text.Corpus.API
as
API
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers
as
Parser
(
FileFormat
(
..
),
parseFormat
)
------------------------------------------------------------------------
{-
...
...
src/Gargantext/Core/Flow/Ngrams.hs
View file @
cf1206df
...
...
@@ -14,7 +14,7 @@ Portability : POSIX
module
Gargantext.Core.Flow.Ngrams
where
-- import Gargantext.Text.Terms.WithList (filterWith)
-- import Gargantext.
Core.
Text.Terms.WithList (filterWith)
src/Gargantext/Core/Flow/Types.hs
View file @
cf1206df
...
...
@@ -18,7 +18,7 @@ import Control.Lens (Lens')
import
Data.Map
(
Map
)
import
Data.Maybe
(
Maybe
)
-- import Control.Applicative
import
Gargantext.Text
(
HasText
(
..
))
import
Gargantext.
Core.
Text
(
HasText
(
..
))
import
Gargantext.Core.Types.Main
(
HashId
)
import
Gargantext.Database.Admin.Types.Hyperdata
import
Gargantext.Database.Admin.Types.Node
...
...
src/Gargantext/Text.hs
→
src/Gargantext/
Core/
Text.hs
View file @
cf1206df
{-|
Module : Gargantext.Text
Module : Gargantext.
Core.
Text
Description : Ngrams tools
Copyright : (c) CNRS, 2018
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Text gathers terms in unit of contexts.
-}
module
Gargantext.Text
module
Gargantext.
Core.
Text
where
import
Data.Text
(
Text
,
split
)
...
...
src/Gargantext/Text/Context.hs
→
src/Gargantext/
Core/
Text/Context.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Context
Module : Gargantext.
Core.
Text.Context
Description : How to manage contexts of texts ?
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -20,14 +20,14 @@ How to split contexts is describes in this module.
-}
module
Gargantext.Text.Context
module
Gargantext.
Core.
Text.Context
where
import
Data.Text
(
Text
,
pack
,
unpack
)
import
Data.String
(
IsString
)
import
Text.HTML.TagSoup
(
parseTags
,
isTagText
,
Tag
(
..
))
import
Gargantext.Text
import
Gargantext.
Core.
Text
import
Gargantext.Prelude
hiding
(
length
)
------------------------------------------------------------------------
...
...
@@ -49,7 +49,7 @@ data SplitContext = Chars Int | Sentences Int | Paragraphs Int
-- | splitBy contexts of Chars or Sentences or Paragraphs
-- To see some examples at a higher level (sentences and paragraph), see
-- 'Gargantext.Text.Examples.ex_terms'
-- 'Gargantext.
Core.
Text.Examples.ex_terms'
--
-- >>> splitBy (Chars 0) (pack "abcde")
-- ["a","b","c","d","e"]
...
...
src/Gargantext/Text/Convert.hs
→
src/Gargantext/
Core/
Text/Convert.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Convert
Module : Gargantext.
Core.
Text.Convert
Description : All parsers of Gargantext in one file.
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -13,13 +13,13 @@ Format Converter.
{-# LANGUAGE PackageImports #-}
module
Gargantext.Text.Convert
(
risPress2csvWrite
)
module
Gargantext.
Core.
Text.Convert
(
risPress2csvWrite
)
where
import
System.FilePath
(
FilePath
())
-- , takeExtension)
import
Gargantext.Prelude
import
Gargantext.Text.Corpus.Parsers.CSV
(
writeDocs2Csv
)
import
Gargantext.Text.Corpus.Parsers
(
parseFile
,
FileFormat
(
..
))
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
writeDocs2Csv
)
import
Gargantext.
Core.
Text.Corpus.Parsers
(
parseFile
,
FileFormat
(
..
))
risPress2csvWrite
::
FilePath
->
IO
()
...
...
src/Gargantext/Text/Corpus/API.hs
→
src/Gargantext/
Core/
Text/Corpus/API.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.API
Module : Gargantext.
Core.
Text.Corpus.API
Description : All crawlers of Gargantext in one file.
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -11,7 +11,7 @@ Portability : POSIX
{-# LANGUAGE InstanceSigs #-}
module
Gargantext.Text.Corpus.API
module
Gargantext.
Core.
Text.Corpus.API
(
ExternalAPIs
(
..
)
,
Query
,
Limit
...
...
@@ -25,10 +25,10 @@ import Gargantext.API.Admin.Orchestrator.Types (ExternalAPIs(..), externalAPIs)
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Prelude
import
qualified
Gargantext.Text.Corpus.API.Hal
as
HAL
import
qualified
Gargantext.Text.Corpus.API.Isidore
as
ISIDORE
import
qualified
Gargantext.Text.Corpus.API.Istex
as
ISTEX
import
qualified
Gargantext.Text.Corpus.API.Pubmed
as
PUBMED
import
qualified
Gargantext.
Core.
Text.Corpus.API.Hal
as
HAL
import
qualified
Gargantext.
Core.
Text.Corpus.API.Isidore
as
ISIDORE
import
qualified
Gargantext.
Core.
Text.Corpus.API.Istex
as
ISTEX
import
qualified
Gargantext.
Core.
Text.Corpus.API.Pubmed
as
PUBMED
-- | Get External API metadata main function
get
::
ExternalAPIs
...
...
src/Gargantext/Text/Corpus/API/Hal.hs
→
src/Gargantext/
Core/
Text/Corpus/API/Hal.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.API.Hal
Module : Gargantext.
Core.
Text.Corpus.API.Hal
Description : Pubmed API connection
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Corpus.API.Hal
module
Gargantext.
Core.
Text.Corpus.API.Hal
where
import
Data.Maybe
...
...
@@ -19,7 +19,7 @@ import Data.Text (Text, pack, intercalate)
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Prelude
import
qualified
Gargantext.Text.Corpus.Parsers.Date
as
Date
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.Date
as
Date
import
qualified
HAL
as
HAL
import
qualified
HAL.Client
as
HAL
import
qualified
HAL.Doc.Corpus
as
HAL
...
...
src/Gargantext/Text/Corpus/API/Isidore.hs
→
src/Gargantext/
Core/
Text/Corpus/API/Isidore.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.API.Isidore
Module : Gargantext.
Core.
Text.Corpus.API.Isidore
Description : To query French Humanities publication database from its API
Copyright : (c) CNRS, 2019-Present
License : AGPL + CECILL v3
...
...
@@ -11,7 +11,7 @@ Portability : POSIX
{-# LANGUAGE ScopedTypeVariables #-}
module
Gargantext.Text.Corpus.API.Isidore
where
module
Gargantext.
Core.
Text.Corpus.API.Isidore
where
import
System.FilePath
(
FilePath
())
import
Data.Text
(
Text
)
...
...
@@ -21,10 +21,10 @@ import Gargantext.Database.Admin.Types.Hyperdata (HyperdataDocument(..))
import
Gargantext.Prelude
import
Isidore.Client
import
Servant.Client
import
qualified
Gargantext.Text.Corpus.Parsers.Date
as
Date
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.Date
as
Date
import
qualified
Isidore
as
Isidore
import
Gargantext.Text.Corpus.Parsers.CSV
(
writeDocs2Csv
)
import
Gargantext.Text.Corpus.Parsers
(
cleanText
)
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
writeDocs2Csv
)
import
Gargantext.
Core.
Text.Corpus.Parsers
(
cleanText
)
-- | TODO work with the ServantErr
get
::
Lang
->
Maybe
Isidore
.
Limit
...
...
src/Gargantext/Text/Corpus/API/Istex.hs
→
src/Gargantext/
Core/
Text/Corpus/API/Istex.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.API.Istex
Module : Gargantext.
Core.
Text.Corpus.API.Istex
Description : Pubmed API connection
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Corpus.API.Istex
module
Gargantext.
Core.
Text.Corpus.API.Istex
where
import
Data.Either
(
either
)
...
...
@@ -22,7 +22,7 @@ import Data.Text (Text, pack)
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Prelude
import
qualified
Gargantext.Text.Corpus.Parsers.Date
as
Date
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.Date
as
Date
import
qualified
ISTEX
as
ISTEX
import
qualified
ISTEX.Client
as
ISTEX
...
...
src/Gargantext/Text/Corpus/API/Pubmed.hs
→
src/Gargantext/
Core/
Text/Corpus/API/Pubmed.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.API.Pubmed
Module : Gargantext.
Core.
Text.Corpus.API.Pubmed
Description : Pubmed API connection
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Corpus.API.Pubmed
module
Gargantext.
Core.
Text.Corpus.API.Pubmed
where
import
Data.Maybe
...
...
src/Gargantext/Text/Corpus/Parsers.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers
Module : Gargantext.
Core.
Text.Corpus.Parsers
Description : All parsers of Gargantext in one file.
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -20,7 +20,7 @@ please follow the types.
{-# LANGUAGE PackageImports #-}
module
Gargantext.Text.Corpus.Parsers
(
FileFormat
(
..
),
clean
,
parseFile
,
cleanText
,
parseFormat
)
module
Gargantext.
Core.
Text.Corpus.Parsers
(
FileFormat
(
..
),
clean
,
parseFile
,
cleanText
,
parseFormat
)
where
import
"zip"
Codec.Archive.Zip
(
withArchive
,
getEntry
,
getEntries
)
...
...
@@ -39,18 +39,18 @@ import Data.Tuple.Extra (both, first, second)
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Prelude
import
Gargantext.Text.Corpus.Parsers.CSV
(
parseHal
,
parseHal'
,
parseCsv
,
parseCsv'
)
import
Gargantext.Text.Corpus.Parsers.RIS.Presse
(
presseEnrich
)
import
Gargantext.Text.Learn
(
detectLangDefault
)
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
parseHal
,
parseHal'
,
parseCsv
,
parseCsv'
)
import
Gargantext.
Core.
Text.Corpus.Parsers.RIS.Presse
(
presseEnrich
)
import
Gargantext.
Core.
Text.Learn
(
detectLangDefault
)
import
System.FilePath
(
FilePath
(),
takeExtension
)
import
qualified
Data.ByteString
as
DB
import
qualified
Data.ByteString.Char8
as
DBC
import
qualified
Data.ByteString.Lazy
as
DBL
import
qualified
Data.Map
as
DM
import
qualified
Data.Text
as
DT
import
qualified
Gargantext.Text.Corpus.Parsers.Date
as
Date
import
qualified
Gargantext.Text.Corpus.Parsers.RIS
as
RIS
import
qualified
Gargantext.Text.Corpus.Parsers.WOS
as
WOS
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.Date
as
Date
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.RIS
as
RIS
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.WOS
as
WOS
------------------------------------------------------------------------
type
ParseError
=
String
...
...
src/Gargantext/Text/Corpus/Parsers/CSV.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/CSV.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.CSV
Module : Gargantext.
Core.
Text.Corpus.Parsers.CSV
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ CSV parser for Gargantext corpus files.
-}
module
Gargantext.Text.Corpus.Parsers.CSV
where
module
Gargantext.
Core.
Text.Corpus.Parsers.CSV
where
import
Control.Applicative
import
qualified
Data.ByteString
as
BS
...
...
@@ -30,8 +30,8 @@ import GHC.Word (Word8)
import
Gargantext.Database.Admin.Types.Hyperdata
(
HyperdataDocument
(
..
))
import
Gargantext.Prelude
hiding
(
length
)
import
Gargantext.Text
import
Gargantext.Text.Context
import
Gargantext.
Core.
Text
import
Gargantext.
Core.
Text.Context
---------------------------------------------------------------
headerCsvGargV3
::
Header
...
...
src/Gargantext/Text/Corpus/Parsers/Date.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Date.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Date
Module : Gargantext.
Core.
Text.Corpus.Parsers.Date
Description : Some utils to parse dates
Copyright : (c) CNRS 2017-present
License : AGPL + CECILL v3
...
...
@@ -10,12 +10,12 @@ Portability : POSIX
According to the language of the text, parseDateRaw returns date as Text:
TODO : Add some tests
import Gargantext.Text.Corpus.Parsers.Date as DGP
import Gargantext.
Core.
Text.Corpus.Parsers.Date as DGP
DGP.parseDateRaw DGP.FR "12 avril 2010" == "2010-04-12T00:00:00.000+00:00"
-}
module
Gargantext.Text.Corpus.Parsers.Date
(
parse
,
parseRaw
,
dateSplit
,
Year
,
Month
,
Day
)
where
module
Gargantext.
Core.
Text.Corpus.Parsers.Date
(
parse
,
parseRaw
,
dateSplit
,
Year
,
Month
,
Day
)
where
import
Data.HashMap.Strict
as
HM
hiding
(
map
)
import
Data.Text
(
Text
,
unpack
,
splitOn
,
pack
)
...
...
src/Gargantext/Text/Corpus/Parsers/Date/Attoparsec.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Date/Attoparsec.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Date.Attoparsec
Module : Gargantext.
Core.
Text.Corpus.Parsers.Date.Attoparsec
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -11,7 +11,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Corpus.Parsers.Date.Attoparsec
module
Gargantext.
Core.
Text.Corpus.Parsers.Date.Attoparsec
where
import
Control.Applicative
((
<*
))
...
...
src/Gargantext/Text/Corpus/Parsers/Date/Parsec.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Date/Parsec.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Date
Module : Gargantext.
Core.
Text.Corpus.Parsers.Date
Description : Some utils to parse dates
Copyright : (c) CNRS 2017-present
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Corpus.Parsers.Date.Parsec
module
Gargantext.
Core.
Text.Corpus.Parsers.Date.Parsec
where
import
Control.Monad
((
=<<
))
...
...
src/Gargantext/Text/Corpus/Parsers/GrandDebat.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/GrandDebat.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.GrandDebat
Module : Gargantext.
Core.
Text.Corpus.Parsers.GrandDebat
Description : Grand Debat Types
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -23,7 +23,7 @@ _flowCorpusDebat u n l fp = do
-}
module
Gargantext.Text.Corpus.Parsers.GrandDebat
module
Gargantext.
Core.
Text.Corpus.Parsers.GrandDebat
where
import
Data.Aeson
(
ToJSON
,
FromJSON
)
...
...
src/Gargantext/Text/Corpus/Parsers/Isidore.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Isidore.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Isidore
Module : Gargantext.
Core.
Text.Corpus.Parsers.Isidore
Description : To query French Humanities publication database
Copyright : (c) CNRS, 2019-Present
License : AGPL + CECILL v3
...
...
@@ -17,7 +17,7 @@ TODO:
{-# LANGUAGE ScopedTypeVariables #-}
module
Gargantext.Text.Corpus.Parsers.Isidore
where
module
Gargantext.
Core.
Text.Corpus.Parsers.Isidore
where
import
Control.Lens
hiding
(
contains
)
import
Data.ByteString.Lazy
(
ByteString
)
...
...
src/Gargantext/Text/Corpus/Parsers/Json2Csv.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Json2Csv.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Json2Csv
Module : Gargantext.
Core.
Text.Corpus.Parsers.Json2Csv
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -14,7 +14,7 @@ Json parser to export towoard CSV GargV3 format.
{-# LANGUAGE TemplateHaskell #-}
module
Gargantext.Text.Corpus.Parsers.Json2Csv
(
json2csv
,
readPatents
)
module
Gargantext.
Core.
Text.Corpus.Parsers.Json2Csv
(
json2csv
,
readPatents
)
where
import
Prelude
(
read
)
...
...
@@ -25,7 +25,7 @@ import Data.Text (Text, unpack)
import
Gargantext.Core.Utils.Prefix
(
unPrefix
)
import
Gargantext.Prelude
import
System.IO
(
FilePath
)
import
Gargantext.Text.Corpus.Parsers.CSV
(
CsvDoc
(
..
),
writeFile
,
headerCsvGargV3
)
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
(
CsvDoc
(
..
),
writeFile
,
headerCsvGargV3
)
import
Data.Vector
(
fromList
)
data
Patent
=
Patent
{
_patent_title
::
Text
...
...
src/Gargantext/Text/Corpus/Parsers/RIS.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/RIS.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.RIS
Module : Gargantext.
Core.
Text.Corpus.Parsers.RIS
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -17,7 +17,7 @@ citation programs to exchange data.
-}
module
Gargantext.Text.Corpus.Parsers.RIS
(
parser
,
onField
,
fieldWith
,
lines
)
where
module
Gargantext.
Core.
Text.Corpus.Parsers.RIS
(
parser
,
onField
,
fieldWith
,
lines
)
where
import
Data.List
(
lookup
)
import
Control.Applicative
...
...
src/Gargantext/Text/Corpus/Parsers/RIS/Presse.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/RIS/Presse.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.RIS.Presse
Module : Gargantext.
Core.
Text.Corpus.Parsers.RIS.Presse
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Presse RIS format parser for Europresse Database.
-}
module
Gargantext.Text.Corpus.Parsers.RIS.Presse
(
presseEnrich
)
where
module
Gargantext.
Core.
Text.Corpus.Parsers.RIS.Presse
(
presseEnrich
)
where
import
Data.List
(
lookup
)
import
Data.Either
(
either
)
...
...
@@ -20,9 +20,9 @@ import Data.Tuple.Extra (first, both, uncurry)
import
Data.Attoparsec.ByteString
(
parseOnly
)
import
Data.ByteString
(
ByteString
,
length
)
import
Gargantext.Prelude
hiding
(
takeWhile
,
take
,
length
)
import
Gargantext.Text.Corpus.Parsers.RIS
(
onField
)
import
Gargantext.
Core.
Text.Corpus.Parsers.RIS
(
onField
)
import
Gargantext.Core
(
Lang
(
..
))
import
qualified
Gargantext.Text.Corpus.Parsers.Date.Attoparsec
as
Date
import
qualified
Gargantext.
Core.
Text.Corpus.Parsers.Date.Attoparsec
as
Date
...
...
src/Gargantext/Text/Corpus/Parsers/WOS.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/WOS.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.WOS
Module : Gargantext.
Core.
Text.Corpus.Parsers.WOS
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -12,14 +12,14 @@ commentary with @some markup@.
-}
module
Gargantext.Text.Corpus.Parsers.WOS
(
parser
,
keys
)
where
module
Gargantext.
Core.
Text.Corpus.Parsers.WOS
(
parser
,
keys
)
where
import
Control.Applicative
import
Data.Attoparsec.ByteString
(
Parser
,
string
,
takeTill
,
take
,
manyTill
,
many1
)
import
Data.Attoparsec.ByteString.Char8
(
anyChar
,
isEndOfLine
)
import
Data.ByteString
(
ByteString
)
import
Data.ByteString.Char8
(
pack
)
import
Gargantext.Text.Corpus.Parsers.RIS
(
fieldWith
)
import
Gargantext.
Core.
Text.Corpus.Parsers.RIS
(
fieldWith
)
import
Prelude
hiding
(
takeWhile
,
take
,
concat
,
readFile
,
lines
,
concat
)
-------------------------------------------------------------
...
...
src/Gargantext/Text/Corpus/Parsers/Wikimedia.hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/Wikimedia.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Corpus.Parsers.Wikimedia
Module : Gargantext.
Core.
Text.Corpus.Parsers.Wikimedia
Description : Parser for Wikimedia dump
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -7,14 +7,14 @@ Maintainer : team@gargantext.org
Stability : experimental
Portability : POSIX
@Gargantext.Text.Corpus.Parsers.Wikimedia@:
@Gargantext.
Core.
Text.Corpus.Parsers.Wikimedia@:
This module provide a parser for wikipedia dump.
This include an xml parser for wikipedia's xml
and an wikimedia to plaintext converter for the wikipedia text field
-}
module
Gargantext.Text.Corpus.Parsers.Wikimedia
module
Gargantext.
Core.
Text.Corpus.Parsers.Wikimedia
where
import
Control.Monad.Catch
...
...
src/Gargantext/Text/Corpus/Parsers/XML_hs
→
src/Gargantext/
Core/
Text/Corpus/Parsers/XML_hs
View file @
cf1206df
File moved
src/Gargantext/Text/Examples.hs
→
src/Gargantext/
Core/
Text/Examples.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Examples
Module : Gargantext.
Core.
Text.Examples
Description : Minimal Examples to test behavior of the functions.
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -23,7 +23,7 @@ This document defines basic of Text definitions according to Gargantext..
{-# LANGUAGE BangPatterns #-}
module
Gargantext.Text.Examples
module
Gargantext.
Core.
Text.Examples
where
import
Data.Ord
(
Down
(
..
))
...
...
@@ -39,12 +39,12 @@ import Data.Tuple.Extra (both)
import
Data.Array.Accelerate
(
toList
,
Matrix
)
import
Gargantext.Prelude
import
Gargantext.Text.Metrics.Count
(
occurrences
,
cooc
)
import
Gargantext.Text.Terms
(
TermType
(
MonoMulti
),
terms
)
import
Gargantext.
Core.
Text.Metrics.Count
(
occurrences
,
cooc
)
import
Gargantext.
Core.
Text.Terms
(
TermType
(
MonoMulti
),
terms
)
import
Gargantext.Core
(
Lang
(
EN
))
import
Gargantext.Core.Types
(
Terms
(
..
),
Label
)
import
Gargantext.Text.Context
(
splitBy
,
SplitContext
(
Sentences
))
import
Gargantext.Text.Metrics.Count
(
Grouped
)
import
Gargantext.
Core.
Text.Context
(
splitBy
,
SplitContext
(
Sentences
))
import
Gargantext.
Core.
Text.Metrics.Count
(
Grouped
)
import
Gargantext.Viz.Graph.Distances.Matrice
import
Gargantext.Viz.Graph.Index
...
...
@@ -73,7 +73,7 @@ ex_paragraph :: Text
ex_paragraph
=
T
.
intercalate
" "
ex_sentences
-- | Let split sentences by Contexts of text.
-- More about 'Gargantext.Text.Context'
-- More about 'Gargantext.
Core.
Text.Context'
--
-- >>> ex_sentences == splitBy (Sentences 0) ex_paragraph
-- True
...
...
@@ -94,7 +94,7 @@ ex_occ :: IO (Map Grouped (Map Terms Int))
ex_occ
=
occurrences
<$>
L
.
concat
<$>
ex_terms
-- | Test the cooccurrences
-- Use the 'Gargantext.Text.Metrics.Count.cooc' function.
-- Use the 'Gargantext.
Core.
Text.Metrics.Count.cooc' function.
--
-- >>> cooc <$> ex_terms
-- fromList [((["glass"],["glass"]),4),((["spoon"],["glass"]),1),((["spoon"],["spoon"]),2),((["table"],["glass"]),3),((["table"],["spoon"]),2),((["table"],["table"]),4),((["wine"],["glass"]),3),((["wine"],["spoon"]),1),((["wine"],["table"]),2),((["wine"],["wine"]),3)]
...
...
src/Gargantext/Text/Flow.hs
→
src/Gargantext/
Core/
Text/Flow.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Flow
Module : Gargantext.
Core.
Text.Flow
Description : Server API
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ From text to viz, all the flow of texts in Gargantext.
-}
module
Gargantext.Text.Flow
module
Gargantext.
Core.
Text.Flow
where
import
qualified
Data.Text
as
T
...
...
src/Gargantext/Text/Learn.hs
→
src/Gargantext/
Core/
Text/Learn.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Stop
Module : Gargantext.
Core.
Text.Terms.Stop
Description : Mono Terms module
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -16,7 +16,7 @@ TODO:
{-# LANGUAGE TypeSynonymInstances #-}
module
Gargantext.Text.Learn
-- (detectLang, detectLangs, stopList)
module
Gargantext.
Core.
Text.Learn
-- (detectLang, detectLangs, stopList)
where
import
Codec.Serialise
...
...
@@ -37,14 +37,14 @@ import qualified Data.ByteString.Lazy as BSL
import
Gargantext.Prelude
import
Gargantext.Prelude.Utils
import
Gargantext.Core
(
Lang
(
..
),
allLangs
)
import
Gargantext.Text.Terms.Mono
(
words
)
import
Gargantext.Text.Metrics.Count
(
occurrencesWith
)
import
qualified
Gargantext.Text.Samples.FR
as
FR
import
qualified
Gargantext.Text.Samples.EN
as
EN
--import qualified Gargantext.Text.Samples.DE as DE
--import qualified Gargantext.Text.Samples.SP as SP
--import qualified Gargantext.Text.Samples.CH as CH
import
Gargantext.
Core.
Text.Terms.Mono
(
words
)
import
Gargantext.
Core.
Text.Metrics.Count
(
occurrencesWith
)
import
qualified
Gargantext.
Core.
Text.Samples.FR
as
FR
import
qualified
Gargantext.
Core.
Text.Samples.EN
as
EN
--import qualified Gargantext.
Core.
Text.Samples.DE as DE
--import qualified Gargantext.
Core.
Text.Samples.SP as SP
--import qualified Gargantext.
Core.
Text.Samples.CH as CH
------------------------------------------------------------------------
data
Candidate
=
Candidate
{
stop
::
Double
...
...
src/Gargantext/Text/List.hs
→
src/Gargantext/
Core/
Text/List.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams.Lists
Module : Gargantext.
Core.
Text.Ngrams.Lists
Description : Tools to build lists
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.List
module
Gargantext.
Core.
Text.List
where
-- import Data.Either (partitionEithers, Either(..))
...
...
@@ -22,12 +22,12 @@ import Gargantext.API.Ngrams (NgramsElement, mkNgramsElement, RootParent(..), mS
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Core.Types
(
ListType
(
..
),
MasterCorpusId
,
UserCorpusId
,
Ordering
(
..
))
import
Gargantext.Database.Action.Metrics.NgramsByNode
(
getTficf
,
ngramsGroup
,
getNodesByNgramsUser
,
groupNodesByNgramsWith
)
import
Gargantext.Text.Metrics.TFICF
(
sortTficf
)
import
Gargantext.
Core.
Text.Metrics.TFICF
(
sortTficf
)
import
Gargantext.Database.Prelude
(
Cmd
)
import
Gargantext.Database.Schema.Ngrams
(
NgramsType
(
..
))
import
Gargantext.Prelude
import
Gargantext.Text.List.Learn
(
Model
(
..
))
-- import Gargantext.Text.Metrics (takeScored)
import
Gargantext.
Core.
Text.List.Learn
(
Model
(
..
))
-- import Gargantext.
Core.
Text.Metrics (takeScored)
import
qualified
Data.Char
as
Char
import
qualified
Data.List
as
List
import
qualified
Data.Map
as
Map
...
...
src/Gargantext/Text/List/CSV.hs
→
src/Gargantext/
Core/
Text/List/CSV.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.List.CSV
Module : Gargantext.
Core.
Text.List.CSV
Description :
Copyright : (c) CNRS, 2018-Present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ CSV parser for Gargantext corpus files.
-}
module
Gargantext.Text.List.CSV
where
module
Gargantext.
Core.
Text.List.CSV
where
import
GHC.IO
(
FilePath
)
...
...
@@ -31,7 +31,7 @@ import Data.Vector (Vector)
import
qualified
Data.Vector
as
V
import
Gargantext.Prelude
hiding
(
length
)
import
Gargantext.Text.Context
import
Gargantext.
Core.
Text.Context
------------------------------------------------------------------------
...
...
src/Gargantext/Text/List/Learn.hs
→
src/Gargantext/
Core/
Text/List/Learn.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.List.Learn
Module : Gargantext.
Core.
Text.List.Learn
Description : Learn to make lists
Copyright : (c) CNRS, 2018-Present
License : AGPL + CECILL v3
...
...
@@ -14,7 +14,7 @@ CSV parser for Gargantext corpus files.
{-# OPTIONS_GHC -fno-warn-orphans #-}
module
Gargantext.Text.List.Learn
module
Gargantext.
Core.
Text.List.Learn
where
import
Control.Monad.Reader
(
MonadReader
)
...
...
@@ -25,7 +25,7 @@ import Data.Maybe (maybe)
import
Gargantext.Core.Types.Main
(
ListType
(
..
),
listTypeId
,
fromListTypeId
)
import
Gargantext.Prelude
import
Gargantext.Prelude.Utils
import
Gargantext.Text.Metrics.Count
(
occurrencesWith
)
import
Gargantext.
Core.
Text.Metrics.Count
(
occurrencesWith
)
import
qualified
Data.IntMap
as
IntMap
import
qualified
Data.List
as
List
import
qualified
Data.Map
as
Map
...
...
@@ -87,7 +87,7 @@ type Param = Double
grid
::
(
MonadReader
env
m
,
MonadBase
IO
m
,
HasSettings
env
)
=>
Param
->
Param
->
Train
->
[
Tests
]
->
m
(
Maybe
Model
)
grid
_
_
_
[]
=
panic
"Gargantext.Text.List.Learn.grid : empty test data"
grid
_
_
_
[]
=
panic
"Gargantext.
Core.
Text.List.Learn.grid : empty test data"
grid
s
e
tr
te
=
do
let
grid'
::
(
MonadReader
env
m
,
MonadBase
IO
m
,
HasSettings
env
)
...
...
src/Gargantext/Text/Metrics.hs
→
src/Gargantext/
Core/
Text/Metrics.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics
Module : Gargantext.
Core.
Text.Metrics
Description : All parsers of Gargantext in one file.
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -13,7 +13,7 @@ Mainly reexport functions in @Data.Text.Metrics@
{-# LANGUAGE BangPatterns #-}
module
Gargantext.Text.Metrics
module
Gargantext.
Core.
Text.Metrics
where
--import Data.Array.Accelerate ((:.)(..), Z(..))
...
...
src/Gargantext/Text/Metrics/CharByChar.hs
→
src/Gargantext/
Core/
Text/Metrics/CharByChar.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics.CharByChar
Module : Gargantext.
Core.
Text.Metrics.CharByChar
Description : All parsers of Gargantext in one file.
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Mainly reexport functions in @Data.Text.Metrics@
module
Gargantext.Text.Metrics.CharByChar
(
levenshtein
module
Gargantext.
Core.
Text.Metrics.CharByChar
(
levenshtein
,
levenshteinNorm
,
damerauLevenshtein
,
damerauLevenshteinNorm
...
...
src/Gargantext/Text/Metrics/Count.hs
→
src/Gargantext/
Core/
Text/Metrics/Count.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics.Count
Module : Gargantext.
Core.
Text.Metrics.Count
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -23,7 +23,7 @@ Source : https://en.wikipedia.org/wiki/Type%E2%80%93token_distinction#Occurrence
-}
module
Gargantext.Text.Metrics.Count
module
Gargantext.
Core.
Text.Metrics.Count
where
import
Data.Text
(
Text
)
...
...
@@ -121,7 +121,6 @@ coocOn' fun ts = DMS.fromListWith (+) xs
------------------------------------------------------------------------
coocOnContexts
::
(
a
->
[
Text
])
->
[[
a
]]
->
Map
([
Text
],
[
Text
])
Int
coocOnContexts
fun
=
DMS
.
fromListWith
(
+
)
.
List
.
concat
.
map
(
coocOnSingleContext
fun
)
...
...
src/Gargantext/Text/Metrics/Freq.hs
→
src/Gargantext/
Core/
Text/Metrics/Freq.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics.Freq
Module : Gargantext.
Core.
Text.Metrics.Freq
Description : Some functions to count.
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -10,7 +10,7 @@ Portability : POSIX
-}
module
Gargantext.Text.Metrics.Freq
where
module
Gargantext.
Core.
Text.Metrics.Freq
where
import
Gargantext.Prelude
import
Data.Bool
(
otherwise
)
...
...
src/Gargantext/Text/Metrics/FrequentItemSet.hs
→
src/Gargantext/
Core/
Text/Metrics/FrequentItemSet.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics.FrequentItemSet
Module : Gargantext.
Core.
Text.Metrics.FrequentItemSet
Description : Ngrams tools
Copyright : (c) CNRS, 2018
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Domain Specific Language to manage Frequent Item Set (FIS)
-}
module
Gargantext.Text.Metrics.FrequentItemSet
module
Gargantext.
Core.
Text.Metrics.FrequentItemSet
(
Fis
,
Size
(
..
)
,
occ_hlcm
,
cooc_hlcm
,
allFis
,
between
...
...
src/Gargantext/Text/Metrics/Hetero.purs
→
src/Gargantext/
Core/
Text/Metrics/Hetero.purs
View file @
cf1206df
File moved
src/Gargantext/Text/Metrics/TFICF.hs
→
src/Gargantext/
Core/
Text/Metrics/TFICF.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Metrics.TFICF
Module : Gargantext.
Core.
Text.Metrics.TFICF
Description : TFICF Ngrams tools
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -14,7 +14,7 @@ TFICF is a generalization of [TFIDF](https://en.wikipedia.org/wiki/Tf%E2%80%93id
-}
module
Gargantext.Text.Metrics.TFICF
(
TFICF
module
Gargantext.
Core.
Text.Metrics.TFICF
(
TFICF
,
TficfContext
(
..
)
,
Total
(
..
)
,
Count
(
..
)
...
...
src/Gargantext/Text/Samples/CH.hs
→
src/Gargantext/
Core/
Text/Samples/CH.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Samples.CH
Module : Gargantext.
Core.
Text.Samples.CH
Description : Sample of Chinese Text
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -14,7 +14,7 @@ Page : text mining
module
Gargantext.Text.Samples.CH
where
module
Gargantext.
Core.
Text.Samples.CH
where
import
Data.String
(
String
)
...
...
src/Gargantext/Text/Samples/DE.hs
→
src/Gargantext/
Core/
Text/Samples/DE.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Samples.DE
Module : Gargantext.
Core.
Text.Samples.DE
Description : Sample of German Text
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -13,7 +13,7 @@ Page : text mining
-}
module
Gargantext.Text.Samples.DE
where
module
Gargantext.
Core.
Text.Samples.DE
where
import
Data.String
(
String
)
...
...
src/Gargantext/Text/Samples/EN.hs
→
src/Gargantext/
Core/
Text/Samples/EN.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Samples.EN
Module : Gargantext.
Core.
Text.Samples.EN
Description : Sample of English Text
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -14,7 +14,7 @@ Page : text mining
module
Gargantext.Text.Samples.EN
where
module
Gargantext.
Core.
Text.Samples.EN
where
import
Data.String
(
String
)
...
...
src/Gargantext/Text/Samples/FR.hs
→
src/Gargantext/
Core/
Text/Samples/FR.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Samples.FR
Module : Gargantext.
Core.
Text.Samples.FR
Description : Sample of French Text
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -13,7 +13,7 @@ Page : text mining
-}
module
Gargantext.Text.Samples.FR
where
module
Gargantext.
Core.
Text.Samples.FR
where
import
Gargantext.Prelude
((
<>
))
import
Data.String
(
String
)
...
...
src/Gargantext/Text/Samples/SP.hs
→
src/Gargantext/
Core/
Text/Samples/SP.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Samples.SP
Module : Gargantext.
Core.
Text.Samples.SP
Description : Sample of Spanish Text
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -13,7 +13,7 @@ Page : text mining
module
Gargantext.Text.Samples.SP
where
module
Gargantext.
Core.
Text.Samples.SP
where
import
Data.String
(
String
)
...
...
src/Gargantext/Text/Search.hs
→
src/Gargantext/
Core/
Text/Search.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Search
Module : Gargantext.
Core.
Text.Search
Description : All parsers of Gargantext in one file.
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -15,7 +15,7 @@ Starting from this model, a specific Gargantext engine will be made
{-# LANGUAGE NamedFieldPuns #-}
module
Gargantext.Text.Search
where
module
Gargantext.
Core.
Text.Search
where
import
Data.SearchEngine
...
...
@@ -27,9 +27,9 @@ import Data.Ix
import
Data.Text
(
Text
)
import
Gargantext.Prelude
import
Gargantext.Text.Terms.Mono
(
monoTexts
)
import
Gargantext.Text.Terms.Mono.Stem
as
ST
import
Gargantext.Text.Corpus.Parsers.CSV
import
Gargantext.
Core.
Text.Terms.Mono
(
monoTexts
)
import
Gargantext.
Core.
Text.Terms.Mono.Stem
as
ST
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
type
DocId
=
Int
...
...
src/Gargantext/Text/Terms.hs
→
src/Gargantext/
Core/
Text/Terms.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams
Module : Gargantext.
Core.
Text.Ngrams
Description : Ngrams definition and tools
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -31,7 +31,7 @@ compute graph
{-# LANGUAGE TemplateHaskell #-}
{-# LANGUAGE ConstrainedClassMethods #-}
module
Gargantext.Text.Terms
module
Gargantext.
Core.
Text.Terms
where
import
Control.Lens
...
...
@@ -45,14 +45,14 @@ import Gargantext.Core
import
Gargantext.Core.Types
import
Gargantext.Core.Flow.Types
import
Gargantext.Prelude
import
Gargantext.Text
(
sentences
,
HasText
(
..
))
import
Gargantext.Text.Terms.Eleve
(
mainEleveWith
,
Tries
,
Token
,
buildTries
,
toToken
)
import
Gargantext.
Core.
Text
(
sentences
,
HasText
(
..
))
import
Gargantext.
Core.
Text.Terms.Eleve
(
mainEleveWith
,
Tries
,
Token
,
buildTries
,
toToken
)
import
Gargantext.Database.Schema.Ngrams
(
Ngrams
(
..
),
NgramsType
(
..
))
import
Gargantext.Text.Terms.Mono
(
monoTerms
)
import
Gargantext.
Core.
Text.Terms.Mono
(
monoTerms
)
import
Gargantext.Database.Prelude
(
Cmd
)
import
Gargantext.Text.Terms.Mono.Stem
(
stem
)
import
Gargantext.Text.Terms.Mono.Token.En
(
tokenize
)
import
Gargantext.Text.Terms.Multi
(
multiterms
)
import
Gargantext.
Core.
Text.Terms.Mono.Stem
(
stem
)
import
Gargantext.
Core.
Text.Terms.Mono.Token.En
(
tokenize
)
import
Gargantext.
Core.
Text.Terms.Multi
(
multiterms
)
import
qualified
Data.List
as
List
import
qualified
Data.Set
as
Set
import
qualified
Data.Text
as
Text
...
...
src/Gargantext/Text/Terms/Eleve.hs
→
src/Gargantext/
Core/
Text/Terms/Eleve.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Eleve
Module : Gargantext.
Core.
Text.Terms.Eleve
Description : Unsupervized Word segmentation
Copyright : (c) CNRS, 2019-Present
License : AGPL + CECILL v3
...
...
@@ -24,7 +24,7 @@ Notes for current implementation:
- TODO AD TEST: prop (Node c _e f) = c == Map.size f
- AD: Real ngrams extraction test
from Gargantext.Text.Terms import extractTermsUnsupervised
from Gargantext.
Core.
Text.Terms import extractTermsUnsupervised
docs <- runCmdRepl $ selectDocs 1004
extractTermsUnsupervised 3 $ DT.intercalate " "
$ catMaybes
...
...
@@ -35,7 +35,7 @@ Notes for current implementation:
{-# LANGUAGE TemplateHaskell #-}
{-# LANGUAGE TypeFamilies #-}
module
Gargantext.Text.Terms.Eleve
where
module
Gargantext.
Core.
Text.Terms.Eleve
where
-- import Debug.Trace (trace)
-- import Debug.SimpleReflect
...
...
src/Gargantext/Text/Terms/Mono.hs
→
src/Gargantext/
Core/
Text/Terms/Mono.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Mono
Module : Gargantext.
Core.
Text.Terms.Mono
Description : Mono Terms module
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Mono-terms are Nterms where n == 1.
-}
module
Gargantext.Text.Terms.Mono
(
monoTerms
,
monoTexts
,
monoTextsBySentence
,
words
)
module
Gargantext.
Core.
Text.Terms.Mono
(
monoTerms
,
monoTexts
,
monoTextsBySentence
,
words
)
where
import
Prelude
(
String
)
...
...
@@ -25,7 +25,7 @@ import qualified Data.Set as S
import
Gargantext.Core
import
Gargantext.Core.Types
import
Gargantext.Text.Terms.Mono.Stem
(
stem
)
import
Gargantext.
Core.
Text.Terms.Mono.Stem
(
stem
)
import
Gargantext.Prelude
--import Data.Char (isAlphaNum, isSpace)
...
...
src/Gargantext/Text/Terms/Mono/Stem.hs
→
src/Gargantext/
Core/
Text/Terms/Mono/Stem.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams.Stem
Module : Gargantext.
Core.
Text.Ngrams.Stem
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -18,7 +18,7 @@ Source : https://en.wikipedia.org/wiki/Stemming
-}
module
Gargantext.Text.Terms.Mono.Stem
(
stem
,
Lang
(
..
))
module
Gargantext.
Core.
Text.Terms.Mono.Stem
(
stem
,
Lang
(
..
))
where
import
Data.Text
(
Text
)
...
...
src/Gargantext/Text/Terms/Mono/Stem/En.hs
→
src/Gargantext/
Core/
Text/Terms/Mono/Stem/En.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams.Stem.En
Module : Gargantext.
Core.
Text.Ngrams.Stem.En
Description : Porter Algorithm Implementation purely Haskell
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -16,7 +16,7 @@ Adapted from:
-}
module
Gargantext.Text.Terms.Mono.Stem.En
(
stemIt
)
module
Gargantext.
Core.
Text.Terms.Mono.Stem.En
(
stemIt
)
where
import
Control.Monad
...
...
src/Gargantext/Text/Terms/Mono/Token.hs
→
src/Gargantext/
Core/
Text/Terms/Mono/Token.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams.Token
Module : Gargantext.
Core.
Text.Ngrams.Token
Description : Tokens and tokenizing a text
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -16,11 +16,11 @@ Source: https://en.wikipedia.org/wiki/Tokenize
-}
module
Gargantext.Text.Terms.Mono.Token
(
tokenize
)
module
Gargantext.
Core.
Text.Terms.Mono.Token
(
tokenize
)
where
import
Data.Text
(
Text
)
import
qualified
Gargantext.Text.Terms.Mono.Token.En
as
En
import
qualified
Gargantext.
Core.
Text.Terms.Mono.Token.En
as
En
-- | Contexts depend on the lang
--import Gargantext.Core (Lang(..))
...
...
src/Gargantext/Text/Terms/Mono/Token/En.hs
→
src/Gargantext/
Core/
Text/Terms/Mono/Token/En.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Ngrams.Token.Text
Module : Gargantext.
Core.
Text.Ngrams.Token.Text
Description : Tokenizer main functions
Copyright : (c) Grzegorz Chrupała first, after: CNRS, 2018-Present
License : AGPL + CECILL v3
...
...
@@ -11,7 +11,7 @@ First inspired from https://bitbucket.org/gchrupala/lingo/overview
-}
module
Gargantext.Text.Terms.Mono.Token.En
module
Gargantext.
Core.
Text.Terms.Mono.Token.En
(
EitherList
(
..
)
,
Tokenizer
,
tokenize
...
...
src/Gargantext/Text/Terms/Multi.hs
→
src/Gargantext/
Core/
Text/Terms/Multi.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi
Module : Gargantext.
Core.
Text.Terms.Multi
Description : Multi Terms module
Copyright : (c) CNRS, 2017 - present
License : AGPL + CECILL v3
...
...
@@ -12,7 +12,7 @@ Multi-terms are ngrams where n > 1.
-}
module
Gargantext.Text.Terms.Multi
(
multiterms
,
multiterms_rake
)
module
Gargantext.
Core.
Text.Terms.Multi
(
multiterms
,
multiterms_rake
)
where
import
Data.Text
hiding
(
map
,
group
,
filter
,
concat
)
...
...
@@ -23,12 +23,12 @@ import Gargantext.Prelude
import
Gargantext.Core
(
Lang
(
..
))
import
Gargantext.Core.Types
import
Gargantext.Text.Terms.Multi.PosTagging
import
Gargantext.Text.Terms.Mono.Stem
(
stem
)
import
qualified
Gargantext.Text.Terms.Multi.Lang.En
as
En
import
qualified
Gargantext.Text.Terms.Multi.Lang.Fr
as
Fr
import
Gargantext.
Core.
Text.Terms.Multi.PosTagging
import
Gargantext.
Core.
Text.Terms.Mono.Stem
(
stem
)
import
qualified
Gargantext.
Core.
Text.Terms.Multi.Lang.En
as
En
import
qualified
Gargantext.
Core.
Text.Terms.Multi.Lang.Fr
as
Fr
import
Gargantext.Text.Terms.Multi.RAKE
(
multiterms_rake
)
import
Gargantext.
Core.
Text.Terms.Multi.RAKE
(
multiterms_rake
)
multiterms
::
Lang
->
Text
->
IO
[
Terms
]
multiterms
lang
txt
=
concat
...
...
src/Gargantext/Text/Terms/Multi/Group.hs
→
src/Gargantext/
Core/
Text/Terms/Multi/Group.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi.Group
Module : Gargantext.
Core.
Text.Terms.Multi.Group
Description : English Grammar rules to group postag tokens.
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -13,7 +13,7 @@ group the tokens into extracted terms.
-}
module
Gargantext.Text.Terms.Multi.Group
(
group2
)
module
Gargantext.
Core.
Text.Terms.Multi.Group
(
group2
)
where
import
Data.Maybe
(
Maybe
(
Just
))
...
...
src/Gargantext/Text/Terms/Multi/Lang/En.hs
→
src/Gargantext/
Core/
Text/Terms/Multi/Lang/En.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi.Lang.En
Module : Gargantext.
Core.
Text.Terms.Multi.Lang.En
Description : English Grammar rules to group postag tokens.
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -13,12 +13,12 @@ the tokens into extracted terms.
-}
module
Gargantext.Text.Terms.Multi.Lang.En
(
group
)
module
Gargantext.
Core.
Text.Terms.Multi.Lang.En
(
group
)
where
import
Gargantext.Prelude
import
Gargantext.Core.Types
import
Gargantext.Text.Terms.Multi.Group
import
Gargantext.
Core.
Text.Terms.Multi.Group
------------------------------------------------------------------------
-- | Rule grammar to group tokens
...
...
src/Gargantext/Text/Terms/Multi/Lang/Fr.hs
→
src/Gargantext/
Core/
Text/Terms/Multi/Lang/Fr.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi.Lang.Fr
Module : Gargantext.
Core.
Text.Terms.Multi.Lang.Fr
Description : French Grammar rules to group postag tokens.
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -14,12 +14,12 @@ is ADJectiv in french.
-}
module
Gargantext.Text.Terms.Multi.Lang.Fr
(
group
)
module
Gargantext.
Core.
Text.Terms.Multi.Lang.Fr
(
group
)
where
import
Gargantext.Prelude
import
Gargantext.Core.Types
import
Gargantext.Text.Terms.Multi.Group
(
group2
)
import
Gargantext.
Core.
Text.Terms.Multi.Group
(
group2
)
group
::
[
TokenTag
]
->
[
TokenTag
]
group
[]
=
[]
...
...
src/Gargantext/Text/Terms/Multi/PosTagging.hs
→
src/Gargantext/
Core/
Text/Terms/Multi/PosTagging.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi.PosTagging
Module : Gargantext.
Core.
Text.Terms.Multi.PosTagging
Description : PosTagging module using Stanford java REST API
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -22,7 +22,7 @@ Source: https://en.wikipedia.org/wiki/Part-of-speech_tagging
{-# LANGUAGE TemplateHaskell #-}
{-# LANGUAGE TypeOperators #-}
module
Gargantext.Text.Terms.Multi.PosTagging
module
Gargantext.
Core.
Text.Terms.Multi.PosTagging
where
import
GHC.Generics
...
...
src/Gargantext/Text/Terms/Multi/RAKE.hs
→
src/Gargantext/
Core/
Text/Terms/Multi/RAKE.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.Multi.RAKE
Module : Gargantext.
Core.
Text.Terms.Multi.RAKE
Description : Rapid automatic keyword extraction (RAKE)
Copyright : (c) CNRS, 2017
License : AGPL + CECILL v3
...
...
@@ -28,14 +28,14 @@ list quality in time.
-}
module
Gargantext.Text.Terms.Multi.RAKE
(
multiterms_rake
,
select
,
hardStopList
)
module
Gargantext.
Core.
Text.Terms.Multi.RAKE
(
multiterms_rake
,
select
,
hardStopList
)
where
import
GHC.Real
(
round
)
import
Data.Text
(
Text
)
import
NLP.RAKE.Text
import
Gargantext.Text.Samples.EN
(
stopList
)
import
Gargantext.
Core.
Text.Samples.EN
(
stopList
)
import
Gargantext.Prelude
select
::
Double
->
[
a
]
->
[
a
]
...
...
src/Gargantext/Text/Terms/WithList.hs
→
src/Gargantext/
Core/
Text/Terms/WithList.hs
View file @
cf1206df
{-|
Module : Gargantext.Text.Terms.WithList
Module : Gargantext.
Core.
Text.Terms.WithList
Description :
Copyright : (c) CNRS, 2017-Present
License : AGPL + CECILL v3
...
...
@@ -13,14 +13,14 @@ commentary with @some markup@.
-}
{-# LANGUAGE BangPatterns #-}
module
Gargantext.Text.Terms.WithList
where
module
Gargantext.
Core.
Text.Terms.WithList
where
import
Data.List
(
null
,
concatMap
)
import
Data.Ord
import
Data.Text
(
Text
,
concat
)
import
Gargantext.Prelude
import
Gargantext.Text.Context
import
Gargantext.Text.Terms.Mono
(
monoTextsBySentence
)
import
Gargantext.
Core.
Text.Context
import
Gargantext.
Core.
Text.Terms.Mono
(
monoTextsBySentence
)
import
Prelude
(
error
)
import
qualified
Data.Algorithms.KMP
as
KMP
import
qualified
Data.IntMap.Strict
as
IntMap
...
...
src/Gargantext/Database/Action/Flow.hs
View file @
cf1206df
...
...
@@ -81,14 +81,14 @@ import Gargantext.Database.Query.Table.NodeNodeNgrams2
import
Gargantext.Ext.IMT
(
toSchoolName
)
import
Gargantext.Core.Utils.Prefix
(
unPrefix
,
unPrefixSwagger
)
import
Gargantext.Ext.IMTUser
(
deserialiseImtUsersFromFile
)
import
Gargantext.Text
import
Gargantext.
Core.
Text
import
Gargantext.Prelude
import
Gargantext.Text.Corpus.Parsers
(
parseFile
,
FileFormat
)
import
Gargantext.Text.List
(
buildNgramsLists
,
StopSize
(
..
))
import
Gargantext.Text.Terms.Mono.Stem.En
(
stemIt
)
import
Gargantext.Text.Terms
import
Gargantext.
Core.
Text.Corpus.Parsers
(
parseFile
,
FileFormat
)
import
Gargantext.
Core.
Text.List
(
buildNgramsLists
,
StopSize
(
..
))
import
Gargantext.
Core.
Text.Terms.Mono.Stem.En
(
stemIt
)
import
Gargantext.
Core.
Text.Terms
import
qualified
Gargantext.Database.Query.Table.Node.Document.Add
as
Doc
(
add
)
import
qualified
Gargantext.Text.Corpus.API
as
API
import
qualified
Gargantext.
Core.
Text.Corpus.API
as
API
------------------------------------------------------------------------
-- TODO use internal with API name (could be old data)
...
...
@@ -277,11 +277,7 @@ insertMasterDocs c lang hs = do
pure
ids'
------------------------------------------------------------------------
------------------------------------------------------------------------
viewUniqId'
::
UniqId
a
=>
a
...
...
@@ -307,14 +303,11 @@ mergeData rs = catMaybes . map toDocumentWithId . Map.toList
<*>
Just
hpd
------------------------------------------------------------------------
instance
HasText
HyperdataContact
where
hasText
=
undefined
------------------------------------------------------------------------
------------------------------------------------------------------------
documentIdWithNgrams
::
HasNodeError
err
=>
(
a
->
Cmd
err
(
Map
Ngrams
(
Map
NgramsType
Int
)))
...
...
@@ -328,8 +321,6 @@ documentIdWithNgrams f = traverse toDocumentIdWithNgrams
------------------------------------------------------------------------
instance
ExtractNgramsT
HyperdataContact
where
extractNgramsT
l
hc
=
filterNgramsT
255
<$>
extract
l
hc
...
...
src/Gargantext/Database/Action/Flow/Types.hs
View file @
cf1206df
...
...
@@ -20,8 +20,8 @@ module Gargantext.Database.Action.Flow.Types
where
import
Gargantext.Core.Flow.Types
import
Gargantext.Text
import
Gargantext.Text.Terms
import
Gargantext.
Core.
Text
import
Gargantext.
Core.
Text.Terms
import
Gargantext.API.Ngrams
(
HasRepoVar
,
RepoCmdM
)
import
Gargantext.Database.Query.Table.Node.Error
(
HasNodeError
)
import
Gargantext.Database.Prelude
(
CmdM
)
...
...
src/Gargantext/Database/Action/Learn.hs
View file @
cf1206df
...
...
@@ -24,7 +24,7 @@ import Gargantext.Database.Admin.Types.Hyperdata
import
Gargantext.Database.Admin.Types.Node
import
Gargantext.Database.Prelude
(
Cmd
)
import
Gargantext.Prelude
import
Gargantext.Text.Learn
import
Gargantext.
Core.
Text.Learn
import
qualified
Data.List
as
List
import
qualified
Data.Text
as
Text
...
...
src/Gargantext/Database/Action/Metrics.hs
View file @
cf1206df
...
...
@@ -27,7 +27,7 @@ import Gargantext.Database.Admin.Types.Node (ListId, CorpusId)
import
Gargantext.Database.Query.Table.Node
(
defaultList
)
import
Gargantext.Database.Query.Table.Node.Select
import
Gargantext.Prelude
import
Gargantext.Text.Metrics
(
scored
,
Scored
(
..
),
{-localMetrics, toScored-}
)
import
Gargantext.
Core.
Text.Metrics
(
scored
,
Scored
(
..
),
{-localMetrics, toScored-}
)
import
qualified
Data.Map
as
Map
getMetrics
::
FlowCmdM
env
err
m
...
...
src/Gargantext/Database/Action/Metrics/Lists.hs
View file @
cf1206df
...
...
@@ -23,7 +23,7 @@ import Gargantext.API.Ngrams (TabType(..))
import
Gargantext.Core.Types
-- (NodePoly(..), NodeCorpus, ListId)
import
Gargantext.Database.Action.Flow
(
FlowCmdM
)
import
Gargantext.Prelude
hiding
(
sum
,
head
)
import
Gargantext.Text.Metrics
(
Scored
(
..
))
import
Gargantext.
Core.
Text.Metrics
(
Scored
(
..
))
import
Prelude
hiding
(
null
,
id
,
map
,
sum
)
import
qualified
Data.Map
as
Map
import
qualified
Data.Vector
as
Vec
...
...
src/Gargantext/Database/Action/Metrics/NgramsByNode.hs
View file @
cf1206df
...
...
@@ -30,8 +30,8 @@ import Gargantext.Database.Admin.Types.Node -- (ListId, CorpusId, NodeId)
import
Gargantext.Database.Prelude
(
Cmd
,
runPGSQuery
)
import
Gargantext.Database.Schema.Ngrams
(
ngramsTypeId
,
NgramsType
(
..
))
import
Gargantext.Prelude
import
Gargantext.Text.Metrics.TFICF
import
Gargantext.Text.Terms.Mono.Stem
(
stem
)
import
Gargantext.
Core.
Text.Metrics.TFICF
import
Gargantext.
Core.
Text.Terms.Mono.Stem
(
stem
)
import
qualified
Data.List
as
List
import
qualified
Data.Map.Strict
as
Map
import
qualified
Data.Set
as
Set
...
...
@@ -56,7 +56,6 @@ ngramsGroup l _m _n = Text.intercalate " "
.
Text
.
replace
"-"
" "
getTficf
::
UserCorpusId
->
MasterCorpusId
->
NgramsType
...
...
src/Gargantext/Database/Action/Search.hs
View file @
cf1206df
...
...
@@ -34,7 +34,7 @@ import Gargantext.Database.Query.Table.Node
import
Gargantext.Database.Query.Table.NodeNode
import
Gargantext.Database.Schema.Node
import
Gargantext.Prelude
import
Gargantext.Text.Terms.Mono.Stem.En
(
stemIt
)
import
Gargantext.
Core.
Text.Terms.Mono.Stem.En
(
stemIt
)
import
Opaleye
hiding
(
Query
,
Order
)
import
Data.Profunctor.Product
(
p4
)
import
qualified
Opaleye
as
O
hiding
(
Order
)
...
...
src/Gargantext/Database/Query/Table/Node/Document/Insert.hs
View file @
cf1206df
...
...
@@ -14,7 +14,7 @@ Enabling "common goods" of text data and respecting privacy.
Gargantext shares as "common good" the links between context of texts
and terms / words / ngrams.
Basically a context of text can be defined as a document (see 'Gargantext.Text').
Basically a context of text can be defined as a document (see 'Gargantext.
Core.
Text').
Issue to tackle in that module: each global document of Gargantext has
to be unique, then shared, but how to respect privacy if needed ?
...
...
src/Gargantext/Database/Schema/Ngrams.hs
View file @
cf1206df
...
...
@@ -142,7 +142,7 @@ fromNgramsTypeId id = lookup id
]
------------------------------------------------------------------------
-- | TODO put it in Gargantext.Text.Ngrams
-- | TODO put it in Gargantext.
Core.
Text.Ngrams
data
Ngrams
=
Ngrams
{
_ngramsTerms
::
Text
,
_ngramsSize
::
Int
}
deriving
(
Generic
,
Show
,
Eq
,
Ord
)
...
...
@@ -155,7 +155,7 @@ text2ngrams :: Text -> Ngrams
text2ngrams
txt
=
Ngrams
txt
$
length
$
splitOn
" "
txt
-------------------------------------------------------------------------
-- | TODO put it in Gargantext.Text.Ngrams
-- | TODO put it in Gargantext.
Core.
Text.Ngrams
-- Named entity are typed ngrams of Terms Ngrams
data
NgramsT
a
=
NgramsT
{
_ngramsType
::
NgramsType
...
...
src/Gargantext/Ext/IMT.hs
View file @
cf1206df
...
...
@@ -20,8 +20,8 @@ import qualified Data.List as DL
import
qualified
Data.Vector
as
DV
import
qualified
Data.Map
as
M
import
Gargantext.Text.Metrics.Freq
as
F
import
Gargantext.Text.Corpus.Parsers.CSV
as
CSV
import
Gargantext.
Core.
Text.Metrics.Freq
as
F
import
Gargantext.
Core.
Text.Corpus.Parsers.CSV
as
CSV
data
School
=
School
{
school_shortName
::
Text
,
school_longName
::
Text
...
...
src/Gargantext/Viz/AdaptativePhylo.hs
View file @
cf1206df
...
...
@@ -34,7 +34,7 @@ import Data.Map (Map)
import
Gargantext.Core.Utils.Prefix
(
unPrefix
)
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
GHC.Generics
import
GHC.IO
(
FilePath
)
...
...
src/Gargantext/Viz/Chart.hs
View file @
cf1206df
...
...
@@ -30,7 +30,7 @@ import Gargantext.Database.Query.Table.Node.Select
import
Gargantext.Database.Query.Table.NodeNode
(
selectDocsDates
)
import
Gargantext.Database.Schema.Node
import
Gargantext.Prelude
import
Gargantext.Text.Metrics.Count
(
occurrencesWith
)
import
Gargantext.
Core.
Text.Metrics.Count
(
occurrencesWith
)
-- Pie Chart
import
Gargantext.API.Ngrams.NTree
...
...
src/Gargantext/Viz/Phylo.hs
View file @
cf1206df
...
...
@@ -39,7 +39,7 @@ import Data.Vector (Vector)
import
GHC.Generics
(
Generic
)
import
Gargantext.Core.Utils.Prefix
(
unPrefix
,
unPrefixSwagger
)
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Prelude
(
Bounded
)
--------------------
...
...
src/Gargantext/Viz/Phylo/Aggregates.hs
View file @
cf1206df
...
...
@@ -16,9 +16,9 @@ module Gargantext.Viz.Phylo.Aggregates
import
Control.Parallel.Strategies
import
Gargantext.Prelude
hiding
(
elem
)
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Metrics.FrequentItemSet
(
fisWithSizePolyMap
,
Size
(
..
))
import
Gargantext.Text.Terms.Mono
(
monoTexts
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Metrics.FrequentItemSet
(
fisWithSizePolyMap
,
Size
(
..
))
import
Gargantext.
Core.
Text.Terms.Mono
(
monoTexts
)
import
Gargantext.Viz.Phylo
import
Gargantext.Viz.Phylo.Tools
...
...
src/Gargantext/Viz/Phylo/Example.hs
View file @
cf1206df
...
...
@@ -33,7 +33,7 @@ import Data.Map (Map,empty)
import
Data.Tuple
(
fst
)
import
Data.Vector
(
Vector
)
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.Viz.Phylo
import
Gargantext.Viz.Phylo.Cluster
import
Gargantext.Viz.Phylo.Aggregates
...
...
src/Gargantext/Viz/Phylo/LevelMaker.hs
View file @
cf1206df
...
...
@@ -30,7 +30,7 @@ import Gargantext.Viz.Phylo.Cluster
import
Gargantext.Viz.Phylo.BranchMaker
import
Gargantext.Viz.Phylo.LinkMaker
import
Gargantext.Viz.Phylo.Tools
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
qualified
Data.Vector.Storable
as
VS
import
qualified
Data.Set
as
Set
...
...
src/Gargantext/Viz/Phylo/Main.hs
View file @
cf1206df
...
...
@@ -33,8 +33,8 @@ import Gargantext.Database.Query.Table.Node(defaultList)
import
Gargantext.Database.Query.Table.NodeNode
(
selectDocs
)
import
Gargantext.Database.Schema.Ngrams
(
NgramsType
(
..
))
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Terms.WithList
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Terms.WithList
import
Gargantext.Viz.Phylo
hiding
(
Svg
,
Dot
)
import
Gargantext.Viz.Phylo.LevelMaker
import
Gargantext.Viz.Phylo.Tools
...
...
src/Gargantext/Viz/Phylo/PhyloExample.hs
View file @
cf1206df
...
...
@@ -20,8 +20,8 @@ import Data.Map (Map)
import
Data.Text
(
Text
,
toLower
)
import
Gargantext.Prelude
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Terms.Mono
(
monoTexts
)
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Terms.Mono
(
monoTexts
)
import
Gargantext.Viz.AdaptativePhylo
import
Gargantext.Viz.Phylo.PhyloTools
import
Gargantext.Viz.Phylo.PhyloMaker
...
...
src/Gargantext/Viz/Phylo/PhyloMaker.hs
View file @
cf1206df
...
...
@@ -20,8 +20,8 @@ import Gargantext.Viz.AdaptativePhylo
import
Gargantext.Viz.Phylo.PhyloTools
import
Gargantext.Viz.Phylo.TemporalMatching
(
adaptativeTemporalMatching
,
constanteTemporalMatching
,
getNextPeriods
,
filterDocs
,
filterDiago
,
reduceDiagos
,
toProximity
)
import
Gargantext.Viz.Phylo.SynchronicClustering
(
synchronicClustering
)
import
Gargantext.Text.Context
(
TermList
)
import
Gargantext.Text.Metrics.FrequentItemSet
(
fisWithSizePolyMap
,
Size
(
..
))
import
Gargantext.
Core.
Text.Context
(
TermList
)
import
Gargantext.
Core.
Text.Metrics.FrequentItemSet
(
fisWithSizePolyMap
,
Size
(
..
))
import
Gargantext.Viz.Graph.MaxClique
(
getMaxCliques
)
import
Gargantext.Viz.Graph.Distances
(
Distance
(
Conditional
))
...
...
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