{-# LANGUAGE OverloadedStrings #-}

-- | Havdalah — separation and distinction.
--
-- Architecture §3.1:
--   havdalah :: Input -> [(Category, Content)]
--   "Separate an input into distinguished categories"
--
-- Havdalah is the act of making distinctions. In the processing
-- pipeline, it takes the output of vayomer (structured symbolic output)
-- and separates it into categories that can be named (kriah).
--
-- Te'amim inform the separation — the text's own divisions guide havdalah.
module Shoresh.Havdalah
  ( havdalah
  , separateByDomain
  , separateByTeamim
  ) where

import Shoresh.Types
import Shoresh.Teamim (ParsedVerse(..), AnnotatedWord(..), primaryDivision)
import Data.Text (Text)
import qualified Data.Text as T
import Data.Map.Strict (Map)
import qualified Data.Map.Strict as Map

-- | Separate input into distinguished categories.
-- Uses both semantic domain analysis and te'amim structure.
havdalah :: [(Shoresh, SemanticDomain)] -> [(Text, [(Shoresh, SemanticDomain)])]
havdalah items =
  let grouped = Map.toList $ Map.fromListWith (++)
                  [ (domainName d, [(sh, d)]) | (sh, d) <- items ]
  in grouped
  where
    domainName :: SemanticDomain -> Text
    domainName d = T.pack (show d)

-- | Separate roots by their semantic domain.
separateByDomain :: [ShoreshEntry] -> Map SemanticDomain [ShoreshEntry]
separateByDomain entries =
  Map.fromListWith (++) [ (sePrimaryDomain e, [e]) | e <- entries ]

-- | Separate using te'amim structure.
-- The te'amim parse tree tells us where the text itself
-- draws its divisions. Havdalah follows the text's own structure.
separateByTeamim :: ParsedVerse -> ([Text], [Text])
separateByTeamim verse =
  let (left, right) = primaryDivision verse
  in (collectWords left, collectWords right)
  where
    collectWords :: ParsedVerse -> [Text]
    collectWords (Leaf w) = [awWord w]
    collectWords (Branch _ l r) = collectWords l ++ collectWords r