bikoret/shoresh-engine/src/Shoresh/Kriah.hs

{-# LANGUAGE OverloadedStrings #-}

-- | Kriah — naming and identification.
--
-- Architecture §3.1:
--   kriah :: [(Category, Content)] -> [(Name, Category, Content)]
--   "Assign stable names to distinguished categories"
--
-- After havdalah separates, kriah names what was separated.
-- The names come from the roots themselves — a category's name
-- is derived from the dominant root or domain within it.
module Shoresh.Kriah
  ( kriah
  , nameCategory
  , NamedCategory(..)
  ) where

import Shoresh.Types
import Data.Text (Text)
import qualified Data.Text as T

-- | A named category — the result of kriah.
data NamedCategory = NamedCategory
  { ncName     :: !Text
  , ncDomain   :: !SemanticDomain
  , ncEntries  :: ![ShoreshEntry]
  } deriving (Show)

-- | Assign stable names to distinguished categories.
kriah :: [(SemanticDomain, [ShoreshEntry])] -> [NamedCategory]
kriah = map nameCategory

-- | Name a single category from its domain and entries.
-- The name is the domain name plus the most frequent root.
nameCategory :: (SemanticDomain, [ShoreshEntry]) -> NamedCategory
nameCategory (domain, entries) =
  let domName = T.pack (show domain)
      rootSuffix = case entries of
        (e:_) -> " (" <> shoreshToText (seShoresh e) <> ")"
        []    -> ""
  in NamedCategory
    { ncName    = domName <> rootSuffix
    , ncDomain  = domain
    , ncEntries = entries
    }