fix: make convert-to-jamo hook buffer-local

.dir-locals.el

@@ -0,0 +1,6 @@
+((nil
+  . ((eval
+      . (progn (add-to-list 'load-path (project-root (project-current)))
+               (require 'helpers)
+               (add-hook 'before-save-hook
+                         #'hangul-convert-buffer-to-jamo t))))))

.envrc

@@ -0,0 +1 @@
+use flake

.gitignore

@@ -1 +1,3 @@
-*.gfo
+*.gfo
+.gf-lsp
+.direnv

flake.lock

@@ -0,0 +1,133 @@
+{
+  "nodes": {
+    "bnfc": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1694438405,
+        "narHash": "sha256-UmrJlHrMlB4tOxQEnBA1blh3aUV28dJHFZs5LNUbNLU=",
+        "owner": "BNFC",
+        "repo": "bnfc",
+        "rev": "1ead871febe45b8adecad286a90650414e24d8a4",
+        "type": "github"
+      },
+      "original": {
+        "owner": "BNFC",
+        "ref": "master",
+        "repo": "bnfc",
+        "type": "github"
+      }
+    },
+    "gf": {
+      "inputs": {
+        "bnfc": "bnfc",
+        "gf-core": "gf-core",
+        "gf-rgl": "gf-rgl",
+        "gf-wordnet": "gf-wordnet",
+        "nixpkgs": "nixpkgs"
+      },
+      "locked": {
+        "lastModified": 1695852170,
+        "narHash": "sha256-xgA9ltioXjh5gYdgmzWACMFeFJu3w4ytMqQlb649oH8=",
+        "owner": "anka-213",
+        "repo": "cclaw-nix-stuff",
+        "rev": "bb591a7d0b6e81f5ae053d2e99a0f8dd9fb5d2a9",
+        "type": "github"
+      },
+      "original": {
+        "owner": "anka-213",
+        "ref": "nix-flakes",
+        "repo": "cclaw-nix-stuff",
+        "type": "github"
+      }
+    },
+    "gf-core": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1695655790,
+        "narHash": "sha256-de5Fk5TK5aUL1YQphoYNBrpJj8GRuPJis7komT95+q8=",
+        "owner": "GrammaticalFramework",
+        "repo": "gf-core",
+        "rev": "7d9015e2e159b376cf2ba8332093c9623375557e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "GrammaticalFramework",
+        "ref": "master",
+        "repo": "gf-core",
+        "type": "github"
+      }
+    },
+    "gf-rgl": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1695810223,
+        "narHash": "sha256-deTXlcYreUl/pHnFZbjSrZIq8L/XunLTODm7aE9LKSA=",
+        "owner": "GrammaticalFramework",
+        "repo": "gf-rgl",
+        "rev": "f19dcc01f99252feb79823830863389e6cf0fc7f",
+        "type": "github"
+      },
+      "original": {
+        "owner": "GrammaticalFramework",
+        "ref": "master",
+        "repo": "gf-rgl",
+        "type": "github"
+      }
+    },
+    "gf-wordnet": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1695803720,
+        "narHash": "sha256-LG5NVsB81Any5P/2WgEpELJKZQmySloHk1F42E7wD1k=",
+        "owner": "GrammaticalFramework",
+        "repo": "gf-wordnet",
+        "rev": "39efb2f91ccb9575c8d96bc272bd2d9f90c1eb23",
+        "type": "github"
+      },
+      "original": {
+        "owner": "GrammaticalFramework",
+        "ref": "master",
+        "repo": "gf-wordnet",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1665056165,
+        "narHash": "sha256-2C7VfNphJa0FxPoT+suMOmUDVrQ5RIE+NKfDWqElvE4=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "27a89ba43b0fb735ce867e8ab3d2442f8cc61dad",
+        "type": "github"
+      },
+      "original": {
+        "id": "nixpkgs",
+        "type": "indirect"
+      }
+    },
+    "nixpkgs_2": {
+      "locked": {
+        "lastModified": 1769170682,
+        "narHash": "sha256-oMmN1lVQU0F0W2k6OI3bgdzp2YOHWYUAw79qzDSjenU=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "c5296fdd05cfa2c187990dd909864da9658df755",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-unstable",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "gf": "gf",
+        "nixpkgs": "nixpkgs_2"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,41 @@
+{
+  inputs = {
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
+    gf.url = "github:anka-213/cclaw-nix-stuff/nix-flakes";
+  };
+
+  outputs = { self, nixpkgs, ... }@inputs:
+    let
+      supportedSystems = [
+        "aarch64-darwin"
+        "aarch64-linux"
+        "x86_64-darwin"
+        "x86_64-linux"
+      ];
+
+      each-system = f: nixpkgs.lib.genAttrs supportedSystems (system: f rec {
+	pkgs = import nixpkgs { inherit system; };
+	inherit (pkgs) lib;
+        inherit system;
+      });
+    in {
+      devShells =
+	each-system ({ pkgs, system, ... }:
+	  let
+	    gf-lsp = import
+	      (pkgs.fetchzip {
+		url = "https://github.com/anka-213/gf-lsp/archive/refs/tags/1.0.6.0.tar.gz";
+		hash = "sha256-UAI2qUslzLOWYjTirZJ0y4DZbkPZnVXTY0XtFO8+Rks=";
+	      }) {inherit system;};
+	  in {
+	    default = pkgs.mkShell {
+	      packages = [
+		inputs.gf.packages.${system}.gf-with-rgl
+		pkgs.graphviz
+		gf-lsp.gf-lsp
+		pkgs.babashka
+	      ];
+	    };
+	  });
+    };
+}

helpers.el

@@ -0,0 +1,56 @@
+(defun hangul-syllables-to-jamo (str)
+  "Convert HANGUL SYLLABLES characters in STR to their HANGUL JAMO
+equivalents."
+  (let ((result "")
+	(i 0))
+    (while (< i (length str))
+      (let ((char (aref str i)))
+	(if (and (>= char #xAC00) (<= char #xD7A3))
+	    ;; Hangul syllable
+	    (let* ((code (- char #xAC00))
+		   (lead (/ code (* 21 28)))
+		   (medial (/ (% code (* 21 28)) 28))
+		   (final (% code 28))
+		   (lead-jamo (+ #x1100 lead))
+		   (medial-jamo (+ #x1161 medial))
+		   (final-jamo (if (> final 0) (+ #x11A7 final) nil)))
+	      (setq result
+		    (concat result (char-to-string lead-jamo)
+			    (char-to-string medial-jamo)
+			    (if final-jamo (char-to-string final-jamo) ""))))
+	  ;; Not a Hangul syllable
+	  (setq result (concat result (char-to-string char)))))
+      (setq i (1+ i)))
+    result))
+
+(defun hangul-convert-region-to-jamo (beg end)
+  (interactive "r")
+  (replace-region-contents
+   beg end (lambda ()
+	     (hangul-syllables-to-jamo (buffer-substring (point-min)
+							 (point-max))))))
+
+(defun hangul-convert-buffer-to-jamo ()
+  (interactive)
+  (hangul-convert-region-to-jamo (point-min) (point-max))
+  (message "Converted Hangul Syllables in buffer to Jamo."))
+
+(require 'dash)
+
+(defconst gf-hangul/choseong
+  (cl-loop for i from #x1100 to #x1112 collect i))
+
+(defconst gf-hangul/jungseong
+  (cl-loop for i from #x1161 to #x1175 collect i))
+
+(defconst gf-hangul/batchim
+  (cl-loop for i from #x11a8 to #x11c2 collect i))
+
+(defun gf-hangul/make-pattern (name seq)
+  (format "'%s' : pattern Str = #(%s) ;"
+	  name (->> seq
+		    (--map (concat "\"" it "\""))
+		    (-interpose " | ")
+		    (apply #'concat))))
+
+(provide 'helpers)

lab1/grammar/abstract/MicroLang.gf

@@ -49,6 +49,11 @@ abstract MicroLang = {
     aPl_Det   : Det ;                   -- indefinite plural   ---s
     the_Det   : Det ;                   -- definite singular   ---s
     thePl_Det : Det ;                   -- definite plural     ---s
+    this_Det  : Det ;
+    thisPl_Det: Det ;
+    that_Det  : Det ;
+    thatPl_Det: Det ;
+
     UseN      : N -> CN ;               -- house
     AdjCN     : AP -> CN -> CN ;        -- big house
 
@@ -162,4 +167,4 @@ fun
   yellow_A : A ;
   young_A : A ;
 
-}
+}

lab1/grammar/english/MicroLangEng.gf

@@ -30,7 +30,7 @@ concrete MicroLangEng of MicroLang = open MicroResEng, Prelude in {
     PredVPS np vp = {
       s = np.s ! Nom ++ vp.verb.s ! agr2vform np.a ++ vp.compl
       } ;
-      
+
     UseV v = {
       verb = v ;
       compl = [] ;
@@ -62,6 +62,10 @@ concrete MicroLangEng of MicroLang = open MicroResEng, Prelude in {
     aPl_Det = {s = "" ; n = Pl} ;
     the_Det = {s = "the" ; n = Sg} ;
     thePl_Det = {s = "the" ; n = Pl} ;
+    this_Det = {s = "this"; n = Sg} ;
+    thisPl_Det = {s = "these"; n = Pl} ;
+    that_Det = {s = "that"; n = Sg} ;
+    thatPl_Det = {s = "those"; n = Pl} ;
     
     UseN n = n ;
     

lab1/grammar/korean/HangulJamo.gf

@@ -0,0 +1,72 @@
+resource HangulJamo = open Prelude in {
+  flags coding=utf8 ;
+  oper
+    lemmaToStem : (lemma : Str) -> Str
+      = \lemma -> case lemma of {
+        stem + "다" => stem ;
+        _ => Predef.error ("lemmaToStem was applied to a non-lemma," ++ lemma)
+      } ;
+
+    infinitive : (stem : Str) -> Str
+      = \stem -> case stem of {
+	-- 하다 ⇒ 해
+	init + #ha => init + "해" ;
+	-- 찾다 ⇒ 찾아, 좁다 ⇒ 좁아
+        _ + #a_o + #batchim => stem + "아" ;
+	-- 가다 ⇒ 가, 
+        _ + (#a | #eo) => stem ;
+	-- 오다 ⇒ 와
+        init + #o => init + "ᅪ" ;
+	-- 따르다 ⇒ 따러
+        init + #eu => init + "ᅥ" ;
+	-- 기다리다 ⇒ 기다려
+        init + #i => init + "ᅧ" ;
+	--
+        init + #u => init + "ᅯ" ;
+	-- 맛있다 ⇒ 맛있어
+        _ => stem + "어"
+      } ;
+
+    present_haeyo : (stem : Str) -> Str
+      = \stem -> infinitive stem + "요" ;
+
+    past_haeyo : (stem : Str) -> Str
+      = \stem -> infinitive stem + "ᆻ어요" ;
+
+    vc_allomorph : (s,vowel,consonant : Str) -> Str
+      = \s,v,c -> case s of {
+	_ + #vowel => v ;
+	_ => c
+      } ;
+
+  oper
+    a_o : pattern Str = #("ᅡ" | "ᅩ") ;
+    a : pattern Str = #"ᅡ" ;
+    o : pattern Str = #"ᅩ" ;
+    eo : pattern Str = #"ᅥ" ;
+    eu : pattern Str = #"ᅳ" ;
+    i : pattern Str = #"ᅵ" ;
+    u : pattern Str = #"ᅮ" ;
+    ha : pattern Str = #"하" ;
+
+  oper
+    consonant : pattern Str =
+      #("ᄀ" | "ᄁ" | "ᄂ" | "ᄃ" | "ᄄ" | "ᄅ" | "ᄆ" | "ᄇ"
+          | "ᄈ" | "ᄉ" | "ᄊ" | "ᄋ" | "ᄌ" | "ᄍ" | "ᄎ" | "ᄏ"
+          | "ᄐ" | "ᄑ" | "ᄒ" | "ᆨ" | "ᆩ" | "ᆪ" | "ᆫ" | "ᆬ"
+          | "ᆭ" | "ᆮ" | "ᆯ" | "ᆰ" | "ᆱ" | "ᆲ" | "ᆳ" | "ᆴ"
+          | "ᆵ" | "ᆶ" | "ᆷ" | "ᆸ" | "ᆹ" | "ᆺ" | "ᆻ" | "ᆼ"
+          | "ᆽ" | "ᆾ" | "ᆿ" | "ᇀ" | "ᇁ" | "ᇂ") ;
+    batchim : pattern Str =
+      #("ᆨ" | "ᆩ" | "ᆪ" | "ᆫ" | "ᆬ" | "ᆭ" | "ᆮ" | "ᆯ" | "ᆰ"
+          | "ᆱ" | "ᆲ" | "ᆳ" | "ᆴ" | "ᆵ" | "ᆶ" | "ᆷ" | "ᆸ" | "ᆹ"
+          | "ᆺ" | "ᆻ" | "ᆼ" | "ᆽ" | "ᆾ" | "ᆿ" | "ᇀ" | "ᇁ" | "ᇂ") ;
+    choseong : pattern Str =
+      #("ᄀ" | "ᄁ" | "ᄂ" | "ᄃ" | "ᄄ" | "ᄅ" | "ᄆ" | "ᄇ" | "ᄈ"
+          | "ᄉ" | "ᄊ" | "ᄋ" | "ᄌ" | "ᄍ" | "ᄎ" | "ᄏ" | "ᄐ" | "ᄑ"
+          | "ᄒ") ;
+    vowel : pattern Str =
+      #("ᅡ" | "ᅢ" | "ᅣ" | "ᅤ" | "ᅥ" | "ᅦ" | "ᅧ" | "ᅨ" | "ᅩ"
+          | "ᅪ" | "ᅫ" | "ᅬ" | "ᅭ" | "ᅮ" | "ᅯ" | "ᅰ" | "ᅱ" | "ᅲ"
+          | "ᅳ" | "ᅴ" | "ᅵ") ;
+}

lab1/grammar/korean/MicroLangKor.gf

@@ -0,0 +1,165 @@
+--# -path=.:../abstract
+concrete MicroLangKor of MicroLang = open MicroResKor, Prelude in {
+
+  flags coding=utf8 ;
+
+-----------------------------------------------------
+---------------- Grammar part -----------------------
+-----------------------------------------------------
+
+  lincat
+    Utt = {s : Str} ;
+
+    S  = {s : Str} ;
+    VP = {verb : Verb ; compl : Str} ; ---s special case of Mini
+    Comp = Noun ;
+    AP = Adjective ;
+    CN = Noun ;
+    NP = {s : Str} ;
+    Pron = {s : Str} ;
+    Det = {s : Str} ;
+    Prep = {s : Str} ;
+    V = Verb ;
+    V2 = Verb2 ;
+    A = Adjective ;
+    N = Noun ;
+    Adv = {s : Str} ;
+
+  lin
+    UttS s = {s = s.s} ;
+    UttNP np = {s = np.s} ;
+    PredVPS np vp = {s = np.s ++ vp.compl ++ vp.verb.s ! VPresent} ;
+    UseV v = {verb = v ; compl = []} ;
+    ComplV2 v2 np = {verb = v2 ; compl = np.s};
+    UseN n = n ;
+    DetCN det cn = {s = det.s ++ cn.s} ;
+    a_Det = {s = []} ;
+    aPl_Det = {s = []} ;
+    the_Det = {s = []} ;
+    thePl_Det = {s = []} ;
+    this_Det = {s = "이"} ;
+    thisPl_Det = {s = "이"} ;
+    that_Det = {s = "그"} ;
+    thatPl_Det = {s = "그"} ;
+    PositA a = a ;
+    AdjCN ap cn = {s = ap.s ! VAdnomial ++ cn.s} ;
+
+-----------------------------------------------------
+---------------- Lexicon part -----------------------
+-----------------------------------------------------
+
+-- lin already_Adv = mkAdv "벌써" ;
+lin animal_N = mkN "동물" ;
+lin apple_N = mkN "사과" ;
+lin baby_N = mkN "아기" ;
+lin bad_A = mkA "나쁘다" ;
+-- lin beer_N = mkN "beer" ;
+lin big_A = mkA "크다" ;
+-- lin bike_N = mkN "bike" ;
+-- lin bird_N = mkN "bird" ;
+-- lin black_A = mkA "black" ;
+lin blood_N = mkN "피" ;
+-- lin blue_A = mkA "blue" ;
+-- lin boat_N = mkN "boat" ;
+lin book_N = mkN "책" ;
+lin boy_N = mkN "소녁" ;
+lin bread_N = mkN "빵" ;
+-- lin break_V2 = mkV2 (mkV "break" "broke" "broken") ;
+lin buy_V2 = mkV2 "사다" ;
+lin car_N = mkN "자동차" ;
+lin cat_N = mkN "고양이" ;
+lin child_N = mkN "어린이" ;
+-- lin city_N = mkN "city" ;
+lin clean_A = mkA "정소하다" ;
+lin clever_A = mkA "똑똑하다" ;
+-- lin cloud_N = mkN "cloud" ;
+-- lin cold_A = mkA "차가운" ;
+lin come_V = mkV "오다" ;
+lin computer_N = mkN "컴퓨터" ;
+-- lin cow_N = mkN "cow" ;
+-- lin dirty_A = mkA "더러운" ;
+lin dog_N = mkN "개" ;
+lin drink_V2 = mkV2 "마시다" ;
+lin eat_V2 = mkV2 "먹다" ;
+lin find_V2 = mkV2 "찾다" ;
+-- lin fire_N = mkN "fire" ;
+lin fish_N = mkN "생선" ;
+-- lin flower_N = mkN "flower" ;
+lin friend_N = mkN "진구" ;
+lin girl_N = mkN "소녀" ;
+-- lin good_A = mkA "좋은" ;
+lin go_V = mkV "가다" ;
+-- lin grammar_N = mkN "grammar" ;
+-- lin green_A = mkA "green" ;
+-- lin heavy_A = mkA "heavy" ;
+-- lin horse_N = mkN "horse" ;
+-- lin hot_A = mkA "hot" ;
+lin house_N = mkN "집" ;
+-- lin john_PN = mkPN "John" ;
+-- lin jump_V = mkV "jump" ;
+lin kill_V2 = mkV2 "죽다" ;
+-- lin know_V2 = mkV "알다" ;
+lin language_N = mkN "언어" ;
+-- lin live_V = mkV "live" ;
+-- lin love_V2 = mkV2 (mkV "love") ;
+lin man_N = mkN "남자" ;
+lin milk_N = mkN "우유" ;
+lin music_N = mkN "음악" ;
+-- lin new_A = mkA "new" ;
+lin now_Adv = mkAdv "지금" ;
+-- lin old_A = mkA "낡안" ;
+-- lin paris_PN = mkPN "Paris" ;
+lin play_V = mkV "놀다" ;
+lin read_V2 = mkV2 "읽다" ;
+-- lin ready_A = mkA "ready" ;
+-- lin red_A = mkA "red" ;
+lin river_N = mkN "강" ;
+-- lin run_V = mkV "run" "ran" "run" ;
+lin sea_N = mkN "바다" ;
+lin see_V2 = mkV2 "보다" ;
+-- lin ship_N = mkN "ship" ;
+lin sleep_V = mkV "자다" ;
+-- lin small_A = mkA "작은" ;
+lin star_N = mkN "별" ;
+lin swim_V = mkV "수영하다" ;
+lin teach_V2 = mkV2 "가르치다" ;
+-- lin train_N = mkN "train" ;
+-- lin travel_V = mkV "travel" ;
+-- lin tree_N = mkN "tree" ;
+-- lin understand_V2 = mkV2 (mkV "understand" "understood" "understood") ;
+lin wait_V2 = mkV2 "기다리다" ;
+lin walk_V = mkV "걷다" ;
+-- lin warm_A = mkA "따뜻한" ;
+lin water_N = mkN "물" ;
+-- lin white_A = mkA "하얗은" ;
+-- lin wine_N = mkN "wine" ;
+lin woman_N = mkN "여자" ;
+-- lin yellow_A = mkA "yellow" ;
+-- lin young_A = mkA "young" ;
+
+---------------------------
+-- Paradigms part ---------
+---------------------------
+
+oper
+  mkN : Str -> Noun
+    = \s -> lin N {s = s} ;
+
+  mkV : Str -> V = \lemma -> lin V (regVerb lemma) ;
+
+  mkV2 = overload {
+    mkV2 : Str -> V2
+      = \lemma -> lin V2 (mkV lemma) ;
+    mkV2 : V -> V2
+      = \v -> lin V2 v ;
+    } ;
+
+  mkAdv : Str -> Adv
+    = \s -> lin Adv {s = s} ;
+
+  mkPrep : Str -> Prep
+    = \s -> lin Prep {s = s} ;
+
+  mkA : Str -> A
+    = \lemma -> lin A (regAdjective lemma) ;
+}

lab1/grammar/korean/MicroResKor.gf

@@ -0,0 +1,34 @@
+resource MicroResKor = open Prelude, HangulJamo in {
+  param
+    VForm = VLemma | VPresent | VPast | VAdnomial ;
+
+  oper
+    Noun : Type = {s : Str} ;
+    Verb : Type = {s : VForm => Str} ;
+    Verb2 : Type = Verb ;
+    Adjective : Type = Verb ;
+
+    lemmaToStem : (lemma : Str) -> Str
+      = \lemma -> case lemma of {
+	stem + "다" => stem ;
+	_ => Predef.error ("lemmaToStem was applied to a non-lemma," ++ lemma)
+      } ;
+
+    reg : (descriptive : Bool) -> (lemma : Str) -> Verb
+      = \descriptive,lemma ->
+      let stem = lemmaToStem lemma ;
+      in {
+	s = table {
+	  VLemma => lemma ;
+	  VPresent => present_haeyo stem ;
+	  VPast => past_haeyo stem ;
+	  VAdnomial =>
+	    if_then_else Str descriptive
+	      (stem + vc_allomorph stem "ᆫ" "은")
+	      (stem + "는")
+	  }
+      } ;
+
+    regVerb : (lemma : Str) -> Verb = reg False ;
+    regAdjective : (lemma : Str) -> Adjective = reg True ;
+}

lab3/README.md

@@ -12,27 +12,28 @@ Go to [universaldependencies.org](https://universaldependencies.org/) and downlo
 Choose a short (5-10 tokens) and a long (>25 words) sentence and convert it from CoNNL-U to a graphical trees by hand.
 
 ### Step 2: choose a corpus
-Choose a corpus of 25+ sentences.
+Choose one of the two corpora provided in this folder:
 
-If you want to start with __English__, you can use[`comp-syntax-corpus-english.txt`](comp-syntax-corpus-english.txt) is a combination of sentences from different sources, including [the Parallel UD treebank (PUD)](https://github.com/UniversalDependencies/UD_English-PUD/tree/master). If you want to cheat - or just check your answers - you can look for them in the official treebank. You can also compare your analyses with those of an automatic parser, such as [UDPipe](https://lindat.mff.cuni.cz/services/udpipe/), which you can try directly in your browser. These automatic analyses must of course be taken with a grain of salt. Note that the first few sentences of this corpus are pre-tokenized and POS-tagged. Each token is in the form `word:<UPOS>`.
+- [`comp-syntax-corpus-english.txt`](comp-syntax-corpus-english.txt) is a combination of __English__ sentences from different sources, including [the Parallel UD treebank (PUD)](https://github.com/UniversalDependencies/UD_English-PUD/tree/master). If you want to cheat - or just check your answers - you can look for them in the official treebank. You can also compare your analyses with those of an automatic parser, such as [UDPipe](https://lindat.mff.cuni.cz/services/udpipe/), which you can try directly in your browser. These automatic analyses must of course be taken with a grain of salt
+- [`comp-syntax-corpus-swedish.txt`](comp-syntax-corpus-swedish.txt) consists of teacher-corrected sentences from the [__Swedish__ Learner Language (SweLL) corpus](https://spraakbanken.gu.se/en/resources/swell-gold), which is currently being annotated in UD for the first time. 
+In this case, there is no "gold standard" to check your answers against, but you can still compare your solutions with [UDPipe](https://lindat.mff.cuni.cz/services/udpipe/)'s automatic analyses.
 
+In both corpora, the first few sentences are pre-tokenized and POS-tagged. Each token is in the form
 
-If you want to work with __Swedish__ and might be interested in contributing to an [official UD treebank](https://github.com/universaldependencies/UD_Swedish-SweLL), ask Arianna for [a sample of the Swedish Learner Language corpus](https://spraakbanken.gu.se/en/resources/swell).
+`word:<UPOS>`.
-
-If you have other data in mind that you think would be interesting to annotate in UD (not necessarily in English or Swedish), don't hesitate to bring it up during a lab session!
 
 ### Step 3: annotate
 For each sentence in the corpus, the annotation tasks consists in:
 
 1. analyzing the sentence in UD
-2. translating it to a language of your choice (as long as one of the two versions is in English or Swedish)
+2. translating it to a language of your choice
 3. analyzing your translation
 
 The only required fields are `ID`, `FORM`, `UPOS`, `HEAD` and `DEPREL`.
 
 In the end, you will submit two parallel CoNLL-U files, one containing the analyses of the source sentences and one for the analyses of the translations.
 
-To produce the CoNLL-U files, you may work in your text editor (you can usually get syntax highlighting by changing the extension to `.tsv`), use a spreadsheet program and then export to TSV, or use a dedicated graphical annotation tool such as [Arborator](https://arborator.grew.fr/#/) (helpful but unstable!).
+To produce the CoNLL-U files, you may work in your text editor (if you use Visual Studio Code, you can use the [vscode-conllu](https://marketplace.visualstudio.com/items?itemName=lgrobol.vscode-conllu) to get syntax highlighting), use a spreadsheet program and then export to TSV, or use a dedicated graphical annotation tool such as [Arborator](https://arborator.grew.fr/#/).
 
 If you work in your text editor, it might be easier to first write a simplified CoNLL-U, with just the fields `ID`, `FORM`, `UPOS`, `HEAD` and `DEPREL`, separated by tabs, and then expand it to full CoNLL-U with [this script](https://gist.github.com/harisont/612a87d20f729aa3411041f873367fa2) (or similar).
 
@@ -53,7 +54,7 @@ To fully comply with the CoNLL-U standard, comment lines should consist of key-v
 # comment = your comment here
 ```
 
-but for this assignment lines like
+but for this assigment lines like
 
 ```
 # your comment here
@@ -62,14 +63,24 @@ but for this assignment lines like
 are perfectly acceptable too.
 
 ### Step 4: make sure your files match the CoNLL-U specification
-Check your treebank with the official UD validator. 
+Once you have full CoNLL, you can use [deptreepy](https://github.com/aarneranta/deptreepy/), [STUnD](https://harisont.github.io/STUnD/) or [the official online CoNNL-U viewer](https://universaldependencies.org/conllu_viewer.html) to visualize it.
+
+With deptreepy, you will need to issue the command
+
+`cat my-file.conllu | python deptreepy.py visualize_conllu > my-file.html`
+
+which creates an HTML file you can open in you web browser.
+
+If you can visualize your trees with any of these tools, that's a very good sign that your file _more or less_ matches the CoNNL-U format!
+
+As a last step, validate your treebank with the official UD validator. 
 To do that, clone or download the [UD tools repository](https://github.com/UniversalDependencies/tools), move inside the corresponding folder and run
 
 ```
-python validate.py PATH-TO-YOUR-TREEBANK.conllu --lang=2-LETTER-LANGCODE-FOR-YOUR-LANGUAGE --level=2
+python validate.py PATH-TO-YOUR-TREEBANK.conllu --lang=2-LETTER-LANGCODE-FOR-YOUR-LANGUAGE --level=1
 ```
 
-Level 2 should be enough for part 2, but you can [go up a few levels](https://harisont.github.io/gfaqs.html#ud-validator) to check for more subtle errors.
+If you want to check for more subtle errors, you can [go up a few levels](https://harisont.github.io/gfaqs.html#ud-validator).
 
 Submit the two CoNLL-U files on Canvas.
 
@@ -80,7 +91,7 @@ If you want to install MaChAmp on your own computer, keep in mind that very old
 For more information, see [here](https://github.com/machamp-nlp/machamp/issues/42). 
 
 ### Step 1: setting up MaChAmp
-1. create a Python virtual environment with the command
+1. optional, but recommended: create a Python virtual environment with the command
    ```
    python -m venv ENVNAME
    ```
@@ -113,7 +124,7 @@ python scripts/misc/cleanconl.py PATH-TO-A-DATASET-SPLIT
 This replaces the contents of your input file with a "cleaned up" version of the same treebank.
 
 ### Step 3: training
-Copy `compsyn.json` to `machamp/configs` and replace the training and development data paths with the paths to the files you selected/created in step 2.
+Copy `compsyn.json` to `machamp/configs` and replace the traning and development data paths with the paths to the files you selected/created in step 2.
 
 You can now train your model by running
 
@@ -141,4 +152,4 @@ Then, use the `machamp/scripts/misc/conll18_ud_eval.py` script to evaluate the s
 python scripts/misc/conll18_ud_eval.py PATH-TO-YOUR-PART1-TREEBANK predictions/OUTPUT-FILE-NAME.conllu
 ```
 
-On Canvas, submit the training logs, the predictions and the output of `conll18_ud_eval.py`, along with a short text summarizing your considerations on the performance of the parser, based on the predictions themselves and on the automatic evaluation.
+On Canvas, submit the training logs, the predictions and the output of `conll18_ud_eval.py`, along with a short text summarizing your considerations on the performance of the parser, based on the predictions themselves and on the output of the results of the evaluation.

lab3/comp-syntax-corpus-english.txt

@@ -6,7 +6,7 @@ The:<DET> study:<NOUN> of:<ADP> volcanoes:<NOUN> is:<AUX> called:<VERB> volcanol
 It:<PRON> was:<AUX> conducted:<VERB> just:<ADV> off:<ADP> the:<DET> Mexican:<ADJ> coast:<NOUN> from:<ADP> April:<PROPN> to:<ADP> June:<PROPN> .:<PUNCT>
 ":<PUNCT> Her:<PRON> voice:<NOUN> literally:<ADV> went:<VERB> around:<ADP> the:<DET> world:<NOUN> ,:<PUNCT> ":<PUNCT> Leive:<PROPN> said:<VERB> .:<PUNCT>
 A:<DET> witness:<NOUN> told:<VERB> police:<NOUN> that:<SCONJ> the:<DET> victim:<NOUN> had:<AUX> attacked:<VERB> the:<DET> suspect:<NOUN> in:<ADP> April:<PROPN> .:<PUNCT>
-It:<PRON> 's:<AUX> most:<ADV> obvious:<ADJ> when:<SCONJ> a:<DET> celebrity:<NOUN> 's:<PART> name:<NOUN> is:<AUX> initially:<ADV> quite:<ADV> rare:<ADJ> .:<PUNCT>
+It:<PRON> 's:<AUX> most:<ADV> obvious:<ADJ> when:<SSUBJ> a:<DET> celebrity:<NOUN> 's:<PART> name:<NOUN> is:<AUX> initially:<ADV> quite:<ADV> rare:<ADJ> .:<PUNCT>
 This:<PRON> has:<AUX> not:<PART> stopped:<VERB> investors:<NOUN> flocking:<VERB> to:<PART> put:<VERB> their:<PRON> money:<NOUN> in:<ADP> the:<DET> funds:<NOUN> .:<PUNCT>
 This:<DET> discordance:<NOUN> between:<ADP> economic:<ADJ> data:<NOUN> and:<CCONJ> political:<ADJ> rhetoric:<NOUN> is:<AUX> familiar:<ADJ> ,:<PUNCT> or:<CCONJ> should:<AUX> be:<AUX> .:<PUNCT>
 The:<DET> feasibility:<NOUN> study:<NOUN> estimates:<VERB> that:<SCONJ> it:<PRON> would:<AUX> take:<VERB> passengers:<NOUN> about:<ADV> four:<NUM> minutes:<NOUN> to:<PART> cross:<VERB> the:<DET> Potomac:<PROPN> River:<PROPN> on:<ADP> the:<DET> gondola:<NOUN> .:<PUNCT>

lab3/comp-syntax-corpus-swedish.txt

@@ -0,0 +1,24 @@
+Jag:<PRON> tycker:<VERB> att:<SCONJ> du:<PRON> ska:<AUX> börja:<VERB> med:<ADP> en:<DET> språkkurs:<NOUN>.:<PUNCT>
+Flerspråkighet:<NOUN> gynnar:<VERB> oss:<PRON> även:<ADV> på:<ADP> arbetsmarknaden:<NOUN>.:<PUNCT>
+Språket:<NOUN> är:<AUX> lätt:<ADJ> och:<CCONJ> jag:<PRON> kan:<AUX> läsa:<VERB> utan:<ADP> något:<DET> problem:<PRON>.:<PUNCT>
+Man:<PRON> känner:<VERB> sig:<PRON> ensam:<ADJ> när:<SCONJ> man:<PRON> inte:<PART> kan:<AUX> prata:<VERB> språket:<NOUN> bra:<ADV>.:<PUNCT>
+Det:<PRON> kan:<AUX> vara:<AUX> kroppsspråk:<NOUN> men:<CCONJ> främst:<ADV> sker:<VERB> det:<PRON> genom:<ADP> talet:<NOUN>.
+Språket:<NOUN> är:<AUX> nyckeln:<NOUN> till:<ADP> alla:<DET> låsta:<ADJ> dörrar:<NOUN>,:<PUNCT> har:<AUX> vi:<PRON> hört:<VERB> flera:<ADJ> gånger:<NOUN>.:<PUNCT>
+Att:<PART> kunna:<VERB> ett:<DET> språk:<NOUN> är:<AUX> en:<DET> av:<ADP> de:<DET> viktigaste:<ADJ> och:<CCONJ> värdefullaste:<ADJ> egenskaper:<NOUN> en:<DET> människa:<NOUN> kan:<AUX> ha:<VERB> så:<SCONJ> det:<PRON> är:<AUX> värt:<ADJ> mer:<ADV> än:<ADP> vad:<PRON> man:<PRON> tror:<VERB>.:<PUNCT>
+Med:<ADP> andra:<ADJ> ord:<NOUN>,:<PUNCT> språket:<NOUN> är:<AUX> nyckeln:<NOUN> till:<ADP> alla:<DET> låsta:<ADJ> dörrar:<NOUN>,:<PUNCT> men:<CCONJ> det:<PRON> finns:<VERB> viktigare:<ADJ> saker:<NOUN> att:<PART> satsa:<VERB> på:<ADP> som:<PRON> jag:<PRON> kommer:<AUX> att:<PART> nämna:<VERB> längre:<ADV> ner:<ADV>.:<PUNCT>
+Han:<PRON> kom:<VERB> till:<ADP> Sverige:<PROPN> för:<ADP> 4:<NUM> år:<NOUN> sedan:<ADV>,:<PUNCT> han:<PRON> kunde:<AUX> inte:<PART> tala:<VERB> svenska:<ADJ> språket:<NOUN>,<PUNCT> ingen:<DET> engelska:<NOUN>,:<PUNCT> han:<PRON> kunde:<AUX> i:<ADP> princip:<NOUN> inte:<PART> kommunicera:<VERB> med:<ADP> någon:<PRON> här<ADV>.:<PUNCT>
+För:<ADP> det:<DET> första:<ADJ> hänger:<VERB> språket:<NOUN> ihop:<ADV> med:<ADP> tillhörighet:<NOUN>,:<PUNCT> särskilt:<ADV> för:<ADP> de:<DET> nya:<ADJ> invandrare:<NOUN> som:<PRON> har:<AUX> bestämt:<VERB> sig:<PRON> för:<ADP> att:<PART> flytta:<VERB> och:<CCONJ> bosätta:<VERB> sig:<PRON> i:<ADP> Sverige:<PROPN>.:<PUNCT>
+Om:<SCONJ> alla:<PRON> hade:<AUX> talat:<VERB> samma:<DET> språk:<NOUN> hade:<AUX> det:<PRON> förmodligen:<ADV> inte:<PART> funnits:<VERB> något:<DET> utanförskap:<NOUN>,:<PUNCT> utan:<CCONJ> man:<PRON> hade:<AUX> fått:<VERB> en:<DET> typ:<NOUN> av:<ADP> gemenskap:<NOUN> där:<ADV> man:<PRON> delar:<VERB> samma:<DET> kultur:<NOUN>.:<PUNCT>
+Att:<PART> lära:<VERB> sig:<PRON> ett:<DET> språk:<NOUN> är:<AUX> väldigt:<ADV> svårt:<ADJ>,:<PUNCT> speciellt:<ADV> för:<ADP> vuxna:<ADJ> människor:<NOUN>,:<PUNCT> och:<CCONJ> eftersom:<SCONJ> majoritetsspråket:<NOUN> blir:<VERB> en:<DET> viktig:<ADJ> del:<NOUN> i:<ADP> en:<DET> persons:<NOUN> liv:<NOUN> räcker:<VERB> det:<PRON> inte:<PART> att:<PART> tala:<VERB> det:<PRON> på:<ADP> söndagar:<NOUN> utan:<CCONJ> det:<PRON> måste:<AUX> läras:<VERB> in:<PART> som:<SCONJ> ett:<DET> modersmål:<NOUN>,:<PUNCT> vilket:<PRON> finansieras:<VERB> av:<ADP> oss:<PRON> skattebetalare:<NOUN>.:<PUNCT>
+Avslutningsvis så vill jag förmedla att vi bör rädda världen innan språken.
+Språket är ganska enkelt, och det är lätt att förstå vad romanen handlar om.
+Det är även kostsamt för staten att se till att dessa minoritetsspråk lever kvar.
+Låt mig säga att det är inte för sent att rädda de små språken, vi måste ta steget nu.
+Att hålla dessa minoritetsspråk vid liv är både slöseri med tid och mycket ekonomiskt krävande.
+Jag tackar alla lärare på Sfi som hjälper oss för att vi ska kunna bli bättre på svenska språket.
+Språk skapades för flera tusen år sedan och vissa språk har tynat bort medan några nya har skapats.
+Samhället behöver flerspråkiga och vägen till kommunikation och till att begripa andras kulturer är ett språk.
+Om man kan fler språk har man fler möjligheter att använda sig av dem vilket leder till utveckling.
+Därför tycker jag att vi bör införa ett förbud mot främmande språk i statliga myndigheter och föreningar.
+Men jag anser först och främst att språket är som själen, det som ger oss livskraft, säregenhet och karaktär.
+På Sveriges riksdags hemsida kan man läsa om hur Sverige bidrar med att skydda dessa språk med hjälp av statligt bidrag.

lectures/lecture01/nano.cf

@@ -1,13 +0,0 @@
-S ::= NP VP ;
-VP ::= V NP ;
-NP ::= Det CN ;
-CN ::= A CN ;
-CN ::= N ;
-NP ::= Pron ;
-
-Det ::= "the" ;
-A ::= "black" ;
-N ::= "cat" ;
-V ::= "sees" ;
-Pron ::= "us" ;
-

lectures/lecture01/nanopar.cf

@@ -1,19 +0,0 @@
-S ::= NP_nom_sg VP_sg ;
-S ::= NP_nom_pl VP_pl ;
-VP_sg ::= V_sg NP_acc ;
-VP_pl ::= V_pl NP_acc ;
-NP_nom_sg ::= Det CN ;
-NP_acc ::= Det CN ;
-CN ::= A CN ;
-CN ::= N ;
-NP_nom_pl ::= Pron_nom_pl ;
-NP_acc ::= Pron_acc ;
-
-Det ::= "the" ;
-A ::= "black" ;
-N ::= "cat" ;
-V_sg ::= "sees" ;
-V_pl ::= "see" ;
-Pron_nom_pl ::= "we" ;
-Pron_acc ::= "us" ;
-

lectures/lecture02/Nano.gf

@@ -1,21 +0,0 @@
-abstract Nano = {
-
-cat
-  S ; NP ; VP ; CN ;
-  Det ; Pron ; A ; N ; V2 ;
-
-fun
-  PredVPS : NP -> VP -> S ;
-  ComplV2 : V2 -> NP -> VP ;
-  DetCN : Det -> CN -> NP ;
-  AdjCN : A -> CN -> CN ;
-  UseCN : N -> CN ;
-  UsePron : Pron -> NP ;
-
-  the_Det : Det ;
-  black_A : A ;
-  cat_N : N ;
-  see_V2 : V2 ;
-  we_Pron : Pron ;
-
-}

lectures/lecture02/NanoEng.gf

@@ -1,33 +0,0 @@
-concrete NanoEng of Nano = {
-
-lincat
-  S = Str ;
-  NP, Pron = {s : Case => Str ; n : Number} ;
-  VP, V2 = Number => Str ;
-  CN, Det = Str ;
-  A, N = Str ;
-
-lin
-  PredVPS np vp = np.s ! Nom  ++ vp ! np.n ;
-  ComplV2 v2 np = table {n => v2 ! n ++ np.s ! Acc} ;
-  DetCN det cn =
-    {s = table {c => det ++ cn} ; n = Sg} ;
-  AdjCN a cn = a ++ cn ;
-  UseCN n = n ;
-  UsePron pron = pron ;
-
-  the_Det = "the" ;
-  black_A = "black" ;
-  cat_N = "cat" ;
-  see_V2 =
-    table {Sg => "sees" ; Pl => "see"} ;
-  we_Pron = {
-    s = table {Nom => "we" ; Acc => "us"} ;
-    n = Pl
-    } ;
-
-param
-  Number = Sg | Pl ;
-  Case = Nom | Acc ;
-
-}

lectures/lecture02/NanoIta.gf

@@ -1,21 +0,0 @@
-concrete NanoIta of Nano = {
-
-lincat
-  S, NP, VP, CN,
-  Det, Pron, A, N, V2 = Str ;
-
-lin
-  PredVPS np vp = np ++ vp ;
-  ComplV2 v2 np = np ++ v2 ;
-  DetCN det cn = det ++ cn ;
-  AdjCN a cn = cn ++ a ;
-  UseCN n = n ;
-  UsePron pron = pron ;
-
-  the_Det = "il" ;
-  black_A = "nero" ;
-  cat_N = "gatto" ;
-  see_V2 = "vede" ;
-  we_Pron = "ci" ;
-
-}

lectures/lecture03/MorphologyEng.gf

@@ -1,82 +0,0 @@
-resource MorphologyEng = {
-
--- to use:
---  i -retain MorphologyEng.gf
---  cc -table dog_N
-
-param
-  Number = Sg | Pl ;
-
-  VerbForm = Inf | Pres3Sg | Past | PastPart | PresPart ;
-
-oper
-  Noun : Type = {s : Number => Str} ;
-
-  -- constructor
-  mkNoun : (dog, dogs : Str) -> Noun
-    = \dog, dogs -> {
-      s = table {Sg => dog ; Pl => dogs}
-      } ;
-
-  regNoun : (dog : Str) -> Noun
-    = \dog -> mkNoun dog (dog + "s") ;
-
-  smartNoun : (noun : Str) -> Noun
-    = \noun -> case noun of {
-       b + ("a" | "e" | "o" | "u") + "y" => regNoun noun ;
-       bab + "y" => mkNoun noun (bab + "ies") ;
-       _ => regNoun noun
-      } ;
-
-  Verb : Type = {s : VerbForm => Str} ;
-  
-  -- constructor; worst case paradigm
-  mkVerb : (sing, sings, sang, sung, singing : Str) -> Verb
-     = \sing, sings, sang, sung, singing -> {
-       s = table {
-         Inf => sing ;
-	 Pres3Sg => sings ;
-	 Past => sang ;
-	 PastPart => sung ;
-	 PresPart => singing
-         }
-       } ;
-
-   regVerb : (walk : Str) -> Verb
-     = \walk ->
-       mkVerb walk (walk + "s") (walk + "ed")
-                   (walk + "ed")  (walk + "ing") ;
-
-   smartVerb : (verb : Str) -> Verb
-     = \verb -> case verb of {
-         b + ("a" | "e" | "o" | "u") + "y" => regVerb verb ;
-	 cr + "y" => mkVerb verb (cr + "ies")
-	               (cr + "ied") (cr + "ied") (cr + "ying") ;
-         us + "e" => let used = us + "ed" in
-	             mkVerb verb (verb + "s") used used (us + "ing") ;
-         wa + ("ch" | "sh" | "s" | "z" | "x") =>
-	     mkVerb verb (verb + "es") (verb + "ed") (verb + "ed")
-	       (verb + "ing") ; 
-         _ => regVerb verb
-         } ;
-
-    irregVerb : (sing, sang, sung : Str) -> Verb
-      = \sing, sang, sung -> {s =
-        table {
-	  Past => sang ;
-	  PastPart => sung ;
-	  x => (smartVerb sing).s ! x
-	  }
-	} ;
-
-
--- lexicon
-
-  dog_N = mkNoun "dog" "dogs" ;
-  girl_N = mkNoun "girl" "girls" ;
-  house_N = regNoun "house" ;
-
-
-
-
-}

lectures/lecture04/MicroLangMyeng.gf

@@ -1,105 +0,0 @@
---# -path=.:../abstract
-
-concrete MicroLangMyeng of MicroLang = open MicroResMyeng, Prelude in {
-
-  lincat
-    V = Verb ;
-    V2 = Verb2 ;
-    A = Adjective ;
-    N = Noun ;
-    Adv = Adverb ;
-
------------------------------------------------------
----------------- Lexicon part -----------------------
------------------------------------------------------
-
-lin already_Adv = mkAdv "already" ;
-lin animal_N = mkN "animal" ;
-lin apple_N = mkN "apple" ;
-lin baby_N = mkN "baby" ;
-lin bad_A = mkA "bad" ;
-lin beer_N = mkN "beer" ;
-lin big_A = mkA "big" ;
-lin bike_N = mkN "bike" ;
-lin bird_N = mkN "bird" ;
-lin black_A = mkA "black" ;
-lin blood_N = mkN "blood" ;
-lin blue_A = mkA "blue" ;
-lin boat_N = mkN "boat" ;
-lin book_N = mkN "book" ;
-lin boy_N = mkN "boy" ;
-lin bread_N = mkN "bread" ;
-lin break_V2 = mkV2 (mkV "break" "broke" "broken") ;
-lin buy_V2 = mkV2 (mkV "buy" "bought" "bought") ;
-lin car_N = mkN "car" ;
-lin cat_N = mkN "cat" ;
-lin child_N = mkN "child" "children" ;
-lin city_N = mkN "city" ;
-lin clean_A = mkA "clean" ;
-lin clever_A = mkA "clever" ;
-lin cloud_N = mkN "cloud" ;
-lin cold_A = mkA "cold" ;
-lin come_V = mkV "come" "came" "come" ;
-lin computer_N = mkN "computer" ;
-lin cow_N = mkN "cow" ;
-lin dirty_A = mkA "dirty" ;
-lin dog_N = mkN "dog" ;
-lin drink_V2 = mkV2 (mkV "drink" "drank" "drunk") ;
-lin eat_V2 = mkV2 (mkV "eat" "ate" "eaten") ;
-lin find_V2 = mkV2 (mkV "find" "found" "found") ;
-lin fire_N = mkN "fire" ;
-lin fish_N = mkN "fish" "fish" ;
-lin flower_N = mkN "flower" ;
-lin friend_N = mkN "friend" ;
-lin girl_N = mkN "girl" ;
-lin good_A = mkA "good" ;
-lin go_V = mkV "go" "goes" "went" "gone" "going" ;
-lin grammar_N = mkN "grammar" ;
-lin green_A = mkA "green" ;
-lin heavy_A = mkA "heavy" ;
-lin horse_N = mkN "horse" ;
-lin hot_A = mkA "hot" ;
-lin house_N = mkN "house" ;
--- lin john_PN = mkPN "John" ;
-lin jump_V = mkV "jump" ;
-lin kill_V2 = mkV2 "kill" ;
--- lin know_VS = mkVS (mkV "know" "knew" "known") ;
-lin language_N = mkN "language" ;
-lin live_V = mkV "live" ;
-lin love_V2 = mkV2 (mkV "love") ;
-lin man_N = mkN "man" "men" ;
-lin milk_N = mkN "milk" ;
-lin music_N = mkN "music" ;
-lin new_A = mkA "new" ;
-lin now_Adv = mkAdv "now" ;
-lin old_A = mkA "old" ;
--- lin paris_PN = mkPN "Paris" ;
-lin play_V = mkV "play" ;
-lin read_V2 = mkV2 (mkV "read" "read" "read") ;
-lin ready_A = mkA "ready" ;
-lin red_A = mkA "red" ;
-lin river_N = mkN "river" ;
-lin run_V = mkV "run" "runs" "ran" "run" "running" ;
-lin sea_N = mkN "sea" ;
-lin see_V2 = mkV2 (mkV "see" "saw" "seen") ;
-lin ship_N = mkN "ship" ;
-lin sleep_V = mkV "sleep" "slept" "slept" ;
-lin small_A = mkA "small" ;
-lin star_N = mkN "star" ;
-lin swim_V = mkV "swim" "swims" "swam" "swum" "swimming" ;
-lin teach_V2 = mkV2 (mkV "teach" "taught" "taught") ;
-lin train_N = mkN "train" ;
-lin travel_V = mkV "travel" ;
-lin tree_N = mkN "tree" ;
-lin understand_V2 = mkV2 (mkV "understand" "understood" "understood") ;
-lin wait_V2 = mkV2 "wait" "for" ;
-lin walk_V = mkV "walk" ;
-lin warm_A = mkA "warm" ;
-lin water_N = mkN "water" ;
-lin white_A = mkA "white" ;
-lin wine_N = mkN "wine" ;
-lin woman_N = mkN "woman" "women" ;
-lin yellow_A = mkA "yellow" ;
-lin young_A = mkA "young" ;
-
-}

lectures/lecture04/MicroResMyeng.gf

@@ -1,115 +0,0 @@
-resource MicroResMyeng = {
-
-------------------------------
--- API: overloaded paradigms
-
-oper
-  mkN = overload {
-    mkN : (baby : Str) -> Noun
-      = \baby -> smartNoun baby ;
-    mkN : (man, men : Str) -> Noun
-      = \man, men -> mkNoun man men ;
-    } ;
-
-  mkA : Str -> Adjective
-    = \adj -> {s = adj} ;
-    
-  mkAdv : Str -> Adverb
-    = \adv -> {s = adv} ;
-
-  mkV = overload {
-    mkV : (try : Str) -> Verb
-      = \try -> smartVerb try ;
-    mkV : (go, went, gone : Str) -> Verb
-      = \go, went, gone -> irregVerb go went gone ;
-    mkV : (sing, sings, sang, sung, singing : Str) -> Verb
-     = \sing, sings, sang, sung, singing ->
-       mkVerb sing sings sang sung singing ;
-    } ;
-
-  mkV2 = overload {
-    mkV2 : (kill : Str) -> Verb2
-      = \kill -> mkV kill ** {prep = ""} ;
-    mkV2 : (wait, for : Str) -> Verb2
-      = \wait, for -> mkV wait ** {prep = for} ;
-    mkV2 : Verb -> Verb2
-      = \verb -> verb ** {prep = ""} ;
-    } ;
-    
-  
-
-------------------------------
-param
-  Number = Sg | Pl ;
-
-  VerbForm = Inf | Pres3Sg | Past | PastPart | PresPart ;
-
-oper
-  Noun : Type = {s : Number => Str} ;
-
-  -- constructor
-  mkNoun : (dog, dogs : Str) -> Noun
-    = \dog, dogs -> {
-      s = table {Sg => dog ; Pl => dogs}
-      } ;
-
-  regNoun : (dog : Str) -> Noun
-    = \dog -> mkNoun dog (dog + "s") ;
-
-  smartNoun : (noun : Str) -> Noun
-    = \noun -> case noun of {
-       b + ("a" | "e" | "o" | "u") + "y" => regNoun noun ;
-       bab + "y" => mkNoun noun (bab + "ies") ;
-       _ => regNoun noun
-      } ;
-
-  Adjective : Type = {s : Str} ;
-
-  Adverb : Type = {s : Str} ;
-
-  Verb : Type = {s : VerbForm => Str} ;
-  
-  -- constructor; worst case paradigm
-  mkVerb : (sing, sings, sang, sung, singing : Str) -> Verb
-     = \sing, sings, sang, sung, singing -> {
-       s = table {
-         Inf => sing ;
-	 Pres3Sg => sings ;
-	 Past => sang ;
-	 PastPart => sung ;
-	 PresPart => singing
-         }
-       } ;
-
-   regVerb : (walk : Str) -> Verb
-     = \walk ->
-       mkVerb walk (walk + "s") (walk + "ed")
-                   (walk + "ed")  (walk + "ing") ;
-
-   smartVerb : (verb : Str) -> Verb
-     = \verb -> case verb of {
-         b + ("a" | "e" | "o" | "u") + "y" => regVerb verb ;
-	 cr + "y" => mkVerb verb (cr + "ies")
-	               (cr + "ied") (cr + "ied") (cr + "ying") ;
-         refer + "ee" => let refereed = refer + "eed" in
-	             mkVerb verb (verb + "s") refereed refereed (verb + "ing") ;
-         us + "e" => let used = us + "ed" in
-	             mkVerb verb (verb + "s") used used (us + "ing") ;
-         wa + ("ch" | "sh" | "s" | "z" | "x") =>
-	     mkVerb verb (verb + "es") (verb + "ed") (verb + "ed")
-	       (verb + "ing") ; 
-         _ => regVerb verb
-         } ;
-
-    irregVerb : (sing, sang, sung : Str) -> Verb
-      = \sing, sang, sung -> {s =
-        table {
-	  Past => sang ;
-	  PastPart => sung ;
-	  x => (smartVerb sing).s ! x
-	  }
-	} ;
-
-  Verb2 : Type = {s : VerbForm => Str ; prep : Str} ;
-
-}

lectures/lecture05/MicroLangMyeng.gf

@@ -1,160 +0,0 @@
---# -path=.:../abstract
-
-concrete MicroLangMyeng of MicroLang = open MicroResMyeng, Prelude in {
-
-  lincat
-    Utt = {s : Str} ;
-    S = {s : Str} ;
-
-    NP = {s : Case => Str ; n : Number} ;
-    VP = {s : Number => Str} ;
-    CN = {s : Number => Str} ;
-    Comp = {s : Str} ;
-    AP = {s : Str} ;
-    Det = {s : Str ; n : Number} ;
-    Prep = {s : Str} ;
-    Pron = {s : Case => Str ; n : Number} ;
-    
-    V = Verb ;
-    V2 = Verb2 ;
-    A = Adjective ;
-    N = Noun ;
-    Adv = Adverb ;
-
-lin
-    UttS s = s ;
-    UttNP np = {s = np.s ! Nom} ;
-
-    PredVPS np vp = {s = np.s ! Nom ++ vp.s ! np.n} ;
-
--- Verb
-    UseV verb = {s = \\n => presentVerb verb n} ;
-
-    ComplV2 verb np = {s = \\n => presentVerb verb n ++ verb.prep ++ np.s ! Acc} ;
-
-    UseComp comp = {s = \\n => copula n ++ comp.s} ;
-    CompAP ap = ap ;
-    AdvVP vp adv = {s = \\n => vp.s ! n ++ adv.s} ;
-
--- Noun
-    DetCN det cn = {s = \\c => det.s ++ cn.s ! det.n ; n = det.n} ;
-    UsePron pron = pron ;
-
-    a_Det = {s = "a" ; n = Sg} ;
-    aPl_Det = {s = "" ; n = Pl} ;
-    the_Det = {s = "the" ; n = Sg} ;
-    thePl_Det = {s = "the" ; n = Pl} ;
-    UseN noun = noun ;
-    AdjCN ap cn = {s = \\n => ap.s ++ cn.s ! n} ;
-
--- Adjective
-    PositA adj = adj ;
-
-{-
--- Adverb
-    PrepNP    : Prep -> NP -> Adv ;     -- in the house
-
--- Structural
-    in_Prep   : Prep ;
-    on_Prep   : Prep ;
-    with_Prep : Prep ;
--}
-    he_Pron = {s = table {Nom => "he" ; Acc => "him"} ; n = Sg} ;
-    she_Pron = {s = table {Nom => "she" ; Acc => "her"} ; n = Sg} ;
-    they_Pron = {s = table {Nom => "they" ; Acc => "them"} ; n = Pl} ;
- 
-
------------------------------------------------------
----------------- Lexicon part -----------------------
------------------------------------------------------
-
-lin already_Adv = mkAdv "already" ;
-lin animal_N = mkN "animal" ;
-lin apple_N = mkN "apple" ;
-lin baby_N = mkN "baby" ;
-lin bad_A = mkA "bad" ;
-lin beer_N = mkN "beer" ;
-lin big_A = mkA "big" ;
-lin bike_N = mkN "bike" ;
-lin bird_N = mkN "bird" ;
-lin black_A = mkA "black" ;
-lin blood_N = mkN "blood" ;
-lin blue_A = mkA "blue" ;
-lin boat_N = mkN "boat" ;
-lin book_N = mkN "book" ;
-lin boy_N = mkN "boy" ;
-lin bread_N = mkN "bread" ;
-lin break_V2 = mkV2 (mkV "break" "broke" "broken") ;
-lin buy_V2 = mkV2 (mkV "buy" "bought" "bought") ;
-lin car_N = mkN "car" ;
-lin cat_N = mkN "cat" ;
-lin child_N = mkN "child" "children" ;
-lin city_N = mkN "city" ;
-lin clean_A = mkA "clean" ;
-lin clever_A = mkA "clever" ;
-lin cloud_N = mkN "cloud" ;
-lin cold_A = mkA "cold" ;
-lin come_V = mkV "come" "came" "come" ;
-lin computer_N = mkN "computer" ;
-lin cow_N = mkN "cow" ;
-lin dirty_A = mkA "dirty" ;
-lin dog_N = mkN "dog" ;
-lin drink_V2 = mkV2 (mkV "drink" "drank" "drunk") ;
-lin eat_V2 = mkV2 (mkV "eat" "ate" "eaten") ;
-lin find_V2 = mkV2 (mkV "find" "found" "found") ;
-lin fire_N = mkN "fire" ;
-lin fish_N = mkN "fish" "fish" ;
-lin flower_N = mkN "flower" ;
-lin friend_N = mkN "friend" ;
-lin girl_N = mkN "girl" ;
-lin good_A = mkA "good" ;
-lin go_V = mkV "go" "goes" "went" "gone" "going" ;
-lin grammar_N = mkN "grammar" ;
-lin green_A = mkA "green" ;
-lin heavy_A = mkA "heavy" ;
-lin horse_N = mkN "horse" ;
-lin hot_A = mkA "hot" ;
-lin house_N = mkN "house" ;
--- lin john_PN = mkPN "John" ;
-lin jump_V = mkV "jump" ;
-lin kill_V2 = mkV2 "kill" ;
--- lin know_VS = mkVS (mkV "know" "knew" "known") ;
-lin language_N = mkN "language" ;
-lin live_V = mkV "live" ;
-lin love_V2 = mkV2 (mkV "love") ;
-lin man_N = mkN "man" "men" ;
-lin milk_N = mkN "milk" ;
-lin music_N = mkN "music" ;
-lin new_A = mkA "new" ;
-lin now_Adv = mkAdv "now" ;
-lin old_A = mkA "old" ;
--- lin paris_PN = mkPN "Paris" ;
-lin play_V = mkV "play" ;
-lin read_V2 = mkV2 (mkV "read" "read" "read") ;
-lin ready_A = mkA "ready" ;
-lin red_A = mkA "red" ;
-lin river_N = mkN "river" ;
-lin run_V = mkV "run" "runs" "ran" "run" "running" ;
-lin sea_N = mkN "sea" ;
-lin see_V2 = mkV2 (mkV "see" "saw" "seen") ;
-lin ship_N = mkN "ship" ;
-lin sleep_V = mkV "sleep" "slept" "slept" ;
-lin small_A = mkA "small" ;
-lin star_N = mkN "star" ;
-lin swim_V = mkV "swim" "swims" "swam" "swum" "swimming" ;
-lin teach_V2 = mkV2 (mkV "teach" "taught" "taught") ;
-lin train_N = mkN "train" ;
-lin travel_V = mkV "travel" ;
-lin tree_N = mkN "tree" ;
-lin understand_V2 = mkV2 (mkV "understand" "understood" "understood") ;
-lin wait_V2 = mkV2 "wait" "for" ;
-lin walk_V = mkV "walk" ;
-lin warm_A = mkA "warm" ;
-lin water_N = mkN "water" ;
-lin white_A = mkA "white" ;
-lin wine_N = mkN "wine" ;
-lin woman_N = mkN "woman" "women" ;
-lin yellow_A = mkA "yellow" ;
-lin young_A = mkA "young" ;
-
-}

lectures/lecture05/MicroResMyeng.gf

@@ -1,131 +0,0 @@
-resource MicroResMyeng = {
-
-------------------------------
--- API: overloaded paradigms
-
-oper
-  mkN = overload {
-    mkN : (baby : Str) -> Noun
-      = \baby -> smartNoun baby ;
-    mkN : (man, men : Str) -> Noun
-      = \man, men -> mkNoun man men ;
-    } ;
-
-  mkA : Str -> Adjective
-    = \adj -> {s = adj} ;
-    
-  mkAdv : Str -> Adverb
-    = \adv -> {s = adv} ;
-
-  mkV = overload {
-    mkV : (try : Str) -> Verb
-      = \try -> smartVerb try ;
-    mkV : (go, went, gone : Str) -> Verb
-      = \go, went, gone -> irregVerb go went gone ;
-    mkV : (sing, sings, sang, sung, singing : Str) -> Verb
-     = \sing, sings, sang, sung, singing ->
-       mkVerb sing sings sang sung singing ;
-    } ;
-
-  mkV2 = overload {
-    mkV2 : (kill : Str) -> Verb2
-      = \kill -> mkV kill ** {prep = ""} ;
-    mkV2 : (wait, for : Str) -> Verb2
-      = \wait, for -> mkV wait ** {prep = for} ;
-    mkV2 : Verb -> Verb2
-      = \verb -> verb ** {prep = ""} ;
-    } ;
-    
-  
-
-------------------------------
-param
-  Number = Sg | Pl ;
-
-  VerbForm = Inf | Pres3Sg | Past | PastPart | PresPart ;
-
-  Case = Nom | Acc ;
-
-oper
-  Noun : Type = {s : Number => Str} ;
-
-  -- constructor
-  mkNoun : (dog, dogs : Str) -> Noun
-    = \dog, dogs -> {
-      s = table {Sg => dog ; Pl => dogs}
-      } ;
-
-  regNoun : (dog : Str) -> Noun
-    = \dog -> mkNoun dog (dog + "s") ;
-
-  smartNoun : (noun : Str) -> Noun
-    = \noun -> case noun of {
-       b + ("a" | "e" | "o" | "u") + "y" => regNoun noun ;
-       bab + "y" => mkNoun noun (bab + "ies") ;
-       _ => regNoun noun
-      } ;
-
-  Adjective : Type = {s : Str} ;
-
-  Adverb : Type = {s : Str} ;
-
-  Verb : Type = {s : VerbForm => Str} ;
-
-  -- constructor; worst case paradigm
-  mkVerb : (sing, sings, sang, sung, singing : Str) -> Verb
-     = \sing, sings, sang, sung, singing -> {
-       s = table {
-         Inf => sing ;
-	 Pres3Sg => sings ;
-	 Past => sang ;
-	 PastPart => sung ;
-	 PresPart => singing
-         }
-       } ;
-
-   regVerb : (walk : Str) -> Verb
-     = \walk ->
-       mkVerb walk (walk + "s") (walk + "ed")
-                   (walk + "ed")  (walk + "ing") ;
-
-   smartVerb : (verb : Str) -> Verb
-     = \verb -> case verb of {
-         b + ("a" | "e" | "o" | "u") + "y" => regVerb verb ;
-	 cr + "y" => mkVerb verb (cr + "ies")
-	               (cr + "ied") (cr + "ied") (cr + "ying") ;
-         refer + "ee" => let refereed = refer + "eed" in
-	             mkVerb verb (verb + "s") refereed refereed (verb + "ing") ;
-         us + "e" => let used = us + "ed" in
-	             mkVerb verb (verb + "s") used used (us + "ing") ;
-         wa + ("ch" | "sh" | "s" | "z" | "x") =>
-	     mkVerb verb (verb + "es") (verb + "ed") (verb + "ed")
-	       (verb + "ing") ; 
-         _ => regVerb verb
-         } ;
-
-    irregVerb : (sing, sang, sung : Str) -> Verb
-      = \sing, sang, sung -> {s =
-        table {
-	  Past => sang ;
-	  PastPart => sung ;
-	  x => (smartVerb sing).s ! x
-	  }
-	} ;
-
-  Verb2 : Type = {s : VerbForm => Str ; prep : Str} ;
-
--- auxiliary for syntax
-  presentVerb : Verb -> Number -> Str = \verb, n ->
-    case n of {
-      Sg => verb.s ! Pres3Sg ;
-      Pl => verb.s ! Inf
-      } ;
-
-  copula : Number -> Str = \n ->
-    case n of {
-      Sg => "is" ;
-      Pl => "are"
-      } ;
-
-
-}

scripts/search-hangul

@@ -0,0 +1,12 @@
+#!/usr/bin/env bb
+
+(require '[babashka.fs :as fs]
+         '[clojure.string :as str])
+
+(doseq [f (fs/glob "lab1/grammar/korean" "**.gf")
+        [line-number line] (map-indexed (fn [i x] [i x])
+                                        (-> f str slurp str/split-lines))]
+  (when (re-find #"\p{block=HangulJamo}" line)
+    (printf "JAMO: %s:%d: %s\n" (str f) line-number line))
+  (when (re-find #"\p{block=HangulSyllables}" line)
+    (printf "SYLLABLE: %s:%d: %s\n" (str f) line-number line)))

scripts/syllables-to-jamo

@@ -0,0 +1,44 @@
+#!/usr/bin/env bb
+
+(require '[babashka.fs :as fs]
+         '[clojure.string :as str])
+
+(defn syllables->jamo [s]
+  "Convert Hangul syllables in string S to their jamo components."
+  (->> s
+       (map int)
+       (mapcat
+        (fn [c]
+          (if (<= 0xAC00 c 0xD7A3)
+            ;; Hangul syllable - decompose
+            (let [code (- c 0xAC00)
+                  lead (quot code (* 21 28))
+                  medial (quot (mod code (* 21 28)) 28)
+                  final (mod code 28)
+                  lead-jamo (+ 0x1100 lead)
+                  medial-jamo (+ 0x1161 medial)
+                  final-jamo (if (> final 0) (+ 0x11A7 final) nil)]
+              (remove nil? [lead-jamo medial-jamo final-jamo]))
+            ;; Not a Hangul syllable
+            [c])))
+       (map char)
+       (apply str)))
+
+
+(defn -main [& args]
+  (if (seq args)
+    (doseq [f args]
+      (let [x (-> (slurp f)
+                  (str/replace #"\p{block=HangulSyllables}+"
+                               syllables->jamo))]
+        (spit f x)))
+    (loop [line (read-line)]
+      (when line
+        (-> line
+            (str/replace #"\p{block=HangulSyllables}+"
+                         syllables->jamo)
+            println)
+        (recur (read-line))))))
+
+(when (= *file* (System/getProperty "babashka.file"))
+  (apply -main *command-line-args*))