Commit 9b8bd4b5 authored by Alexandre Delanoë's avatar Alexandre Delanoë

[BIN/PHYLO] first draft, needs phylo connection.

parent 1223b2b1
...@@ -241,6 +241,29 @@ executables: ...@@ -241,6 +241,29 @@ executables:
- unordered-containers - unordered-containers
- full-text-search - full-text-search
gargantext-phylo:
main: Main.hs
source-dirs: bin/gargantext-phylo
ghc-options:
- -threaded
- -rtsopts
- -with-rtsopts=-N
- -O2
- -Wmissing-signatures
dependencies:
- aeson
- async
- base
- bytestring
- containers
- gargantext
- vector
- cassava
- ini
- optparse-generic
- split
- unordered-containers
gargantext-import: gargantext-import:
main: Main.hs main: Main.hs
source-dirs: bin/gargantext-import source-dirs: bin/gargantext-import
......
...@@ -18,7 +18,7 @@ commentary with @some markup@. ...@@ -18,7 +18,7 @@ commentary with @some markup@.
module Gargantext.Text.Terms.WithList where module Gargantext.Text.Terms.WithList where
import qualified Data.Algorithms.KMP as KMP import qualified Data.Algorithms.KMP as KMP
import Data.Text (Text) import Data.Text (Text, concat, unpack)
import qualified Data.IntMap.Strict as IntMap import qualified Data.IntMap.Strict as IntMap
import Gargantext.Text.Context import Gargantext.Text.Context
...@@ -75,3 +75,12 @@ buildPatterns = sortWith (Down . _pat_length) . concatMap buildPattern ...@@ -75,3 +75,12 @@ buildPatterns = sortWith (Down . _pat_length) . concatMap buildPattern
extractTermsWithList :: Patterns -> Text -> Corpus [Text] extractTermsWithList :: Patterns -> Text -> Corpus [Text]
extractTermsWithList pats = map (replaceTerms pats) . monoTextsBySentence extractTermsWithList pats = map (replaceTerms pats) . monoTextsBySentence
-- | Extract terms
-- >>> let termList = [(["chat blanc"], [["chat","blanc"]])] :: TermList
-- extractTermsWithList' (buildPatterns termList) "Le chat blanc"["chat blanc"]
-- ["chat blanc"]
extractTermsWithList' :: Patterns -> Text -> [Text]
extractTermsWithList' pats = map (concat . map concat . replaceTerms pats) . monoTextsBySentence
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment