hanguleam

-module(hanguleam@extractor).
-compile([no_auto_import, nowarn_unused_vars, nowarn_unused_function, nowarn_nomatch]).
-define(FILEPATH, "src/hanguleam/extractor.gleam").
-export([get_choseong/1]).

-if(?OTP_RELEASE >= 27).
-define(MODULEDOC(Str), -moduledoc(Str)).
-define(DOC(Str), -doc(Str)).
-else.
-define(MODULEDOC(Str), -compile([])).
-define(DOC(Str), -compile([])).
-endif.

-file("src/hanguleam/extractor.gleam", 68).
-spec get_choseong_index(integer()) -> integer().
get_choseong_index(Codepoint) ->
    Base = Codepoint - 16#AC00,
    case (21 * 28) of
        0 -> 0;
        Gleam@denominator -> Base div Gleam@denominator
    end.

-file("src/hanguleam/extractor.gleam", 73).
-spec get_choseong_by_index(integer()) -> gleam@option:option(binary()).
get_choseong_by_index(Index) ->
    _pipe = hanguleam@internal@utils:get_value_by_index(
        Index,
        [<<"ㄱ"/utf8>>,
            <<"ㄲ"/utf8>>,
            <<"ㄴ"/utf8>>,
            <<"ㄷ"/utf8>>,
            <<"ㄸ"/utf8>>,
            <<"ㄹ"/utf8>>,
            <<"ㅁ"/utf8>>,
            <<"ㅂ"/utf8>>,
            <<"ㅃ"/utf8>>,
            <<"ㅅ"/utf8>>,
            <<"ㅆ"/utf8>>,
            <<"ㅇ"/utf8>>,
            <<"ㅈ"/utf8>>,
            <<"ㅉ"/utf8>>,
            <<"ㅊ"/utf8>>,
            <<"ㅋ"/utf8>>,
            <<"ㅌ"/utf8>>,
            <<"ㅍ"/utf8>>,
            <<"ㅎ"/utf8>>]
    ),
    gleam@option:from_result(_pipe).

-file("src/hanguleam/extractor.gleam", 56).
-spec extract_from_complete_hangul(binary()) -> gleam@option:option(binary()).
extract_from_complete_hangul(Char) ->
    case hanguleam@internal@unicode:get_codepoint_result_from_char(Char) of
        {ok, Codepoint} ->
            case hanguleam@internal@unicode:is_complete_hangul(Codepoint) of
                true ->
                    _pipe = get_choseong_index(Codepoint),
                    get_choseong_by_index(_pipe);

                false ->
                    none
            end;

        {error, _} ->
            none
    end.

-file("src/hanguleam/extractor.gleam", 49).
-spec extract_choseong_from_char(binary()) -> gleam@option:option(binary()).
extract_choseong_from_char(Char) ->
    case gleam@list:contains(
        [<<"ㄱ"/utf8>>,
            <<"ㄲ"/utf8>>,
            <<"ㄴ"/utf8>>,
            <<"ㄷ"/utf8>>,
            <<"ㄸ"/utf8>>,
            <<"ㄹ"/utf8>>,
            <<"ㅁ"/utf8>>,
            <<"ㅂ"/utf8>>,
            <<"ㅃ"/utf8>>,
            <<"ㅅ"/utf8>>,
            <<"ㅆ"/utf8>>,
            <<"ㅇ"/utf8>>,
            <<"ㅈ"/utf8>>,
            <<"ㅉ"/utf8>>,
            <<"ㅊ"/utf8>>,
            <<"ㅋ"/utf8>>,
            <<"ㅌ"/utf8>>,
            <<"ㅍ"/utf8>>,
            <<"ㅎ"/utf8>>],
        Char
    ) of
        true ->
            {some, Char};

        false ->
            extract_from_complete_hangul(Char)
    end.

-file("src/hanguleam/extractor.gleam", 30).
-spec do_get_choseong(binary(), binary()) -> binary().
do_get_choseong(Word, Accumulator) ->
    case gleam_stdlib:string_pop_grapheme(Word) of
        {ok, {Head, Tail}} ->
            Extracted = case Head of
                <<" "/utf8>> ->
                    <<" "/utf8>>;

                <<"\t"/utf8>> ->
                    <<"\t"/utf8>>;

                <<"\n"/utf8>> ->
                    <<"\n"/utf8>>;

                _ ->
                    case extract_choseong_from_char(Head) of
                        {some, Choseong} ->
                            Choseong;

                        none ->
                            <<""/utf8>>
                    end
            end,
            do_get_choseong(Tail, <<Accumulator/binary, Extracted/binary>>);

        {error, _} ->
            Accumulator
    end.

-file("src/hanguleam/extractor.gleam", 26).
?DOC(
    " Extracts the initial consonants (choseong) from Korean Hangul characters in a string.\n"
    " Non-Korean characters are filtered out, while whitespace characters (spaces, tabs, newlines)\n"
    " are preserved in their original positions.\n"
    "\n"
    " ## Examples\n"
    "\n"
    " ```gleam\n"
    " get_choseong(\"사과\")\n"
    " // -> \"ㅅㄱ\"\n"
    "\n"
    " get_choseong(\"띄어 쓰기\")\n"
    " // -> \"ㄸㅇ ㅆㄱ\"\n"
    "\n"
    " get_choseong(\"안녕hello\")\n"
    " // -> \"ㅇㄴ\"\n"
    " ```\n"
).
-spec get_choseong(binary()) -> binary().
get_choseong(Word) ->
    do_get_choseong(Word, <<""/utf8>>).