diff --git a/doc/tutorial/Food.gf b/doc/tutorial/Food.gf new file mode 100644 index 000000000..1a2d38d1e --- /dev/null +++ b/doc/tutorial/Food.gf @@ -0,0 +1,14 @@ +abstract Food = { + + cat + S ; Item ; Kind ; Quality ; + + fun + Is : Item -> Quality -> S ; + This, That : Kind -> Item ; + QKind : Quality -> Kind -> Kind ; + Wine, Cheese, Fish : Kind ; + Very : Quality -> Quality ; + Fresh, Warm, Italian, Expensive, Delicious, Boring : Quality ; + +} \ No newline at end of file diff --git a/doc/tutorial/Food2Eng.gf b/doc/tutorial/Food2Eng.gf new file mode 100644 index 000000000..a92e426eb --- /dev/null +++ b/doc/tutorial/Food2Eng.gf @@ -0,0 +1,23 @@ +concrete Food2Eng of Food = open StringOper in { + + lincat + S, Item, Kind, Quality = SS ; + + lin + Is item quality = cc item (prefix "is" quality) ; + This = prefix "this" ; + That = prefix "that" ; + QKind = cc ; + Wine = ss "wine" ; + Cheese = ss "cheese" ; + Fish = ss "fish" ; + Very = prefix "very" ; + Fresh = ss "fresh" ; + Warm = ss "warm" ; + Italian = ss "Italian" ; + Expensive = ss "expensive" ; + Delicious = ss "delicious" ; + Boring = ss "boring" ; + +} + \ No newline at end of file diff --git a/doc/tutorial/FoodEng.gf b/doc/tutorial/FoodEng.gf new file mode 100644 index 000000000..f75727292 --- /dev/null +++ b/doc/tutorial/FoodEng.gf @@ -0,0 +1,23 @@ +concrete FoodEng of Food = { + + lincat + S, Item, Kind, Quality = {s : Str} ; + + lin + Is item quality = {s = item.s ++ "is" ++ quality.s} ; + This kind = {s = "this" ++ kind.s} ; + That kind = {s = "that" ++ kind.s} ; + QKind quality kind = {s = quality.s ++ kind.s} ; + Wine = {s = "wine"} ; + Cheese = {s = "cheese"} ; + Fish = {s = "fish"} ; + Very quality = {s = "very" ++ quality.s} ; + Fresh = {s = "fresh"} ; + Warm = {s = "warm"} ; + Italian = {s = "Italian"} ; + Expensive = {s = "expensive"} ; + Delicious = {s = "delicious"} ; + Boring = {s = "boring"} ; + +} + \ No newline at end of file diff --git a/doc/tutorial/FoodIta.gf b/doc/tutorial/FoodIta.gf new file mode 100644 index 000000000..5c565037a --- /dev/null +++ b/doc/tutorial/FoodIta.gf @@ -0,0 +1,22 @@ +concrete FoodIta of Food = { + + lincat + S, Item, Kind, Quality = {s : Str} ; + + lin + Is item quality = {s = item.s ++ "è" ++ quality.s} ; + This kind = {s = "questo" ++ kind.s} ; + That kind = {s = "quello" ++ kind.s} ; + QKind quality kind = {s = kind.s ++ quality.s} ; + Wine = {s = "vino"} ; + Cheese = {s = "formaggio"} ; + Fish = {s = "pesce"} ; + Very quality = {s = "molto" ++ quality.s} ; + Fresh = {s = "fresco"} ; + Warm = {s = "caldo"} ; + Italian = {s = "italiano"} ; + Expensive = {s = "caro"} ; + Delicious = {s = "delizioso"} ; + Boring = {s = "noioso"} ; + +} diff --git a/doc/tutorial/Foodmarket.gf b/doc/tutorial/Foodmarket.gf new file mode 100644 index 000000000..18bbe6853 --- /dev/null +++ b/doc/tutorial/Foodmarket.gf @@ -0,0 +1,5 @@ +abstract Foodmarket = Food, Fruit, Mushroom ** { + fun + FruitKind : Fruit -> Kind ; + MushroomKind : Mushroom -> Kind ; +} diff --git a/doc/tutorial/FoodmarketEng.gf b/doc/tutorial/FoodmarketEng.gf new file mode 100644 index 000000000..105cf53f6 --- /dev/null +++ b/doc/tutorial/FoodmarketEng.gf @@ -0,0 +1,5 @@ +concrete FoodmarketEng of Foodmarket = FoodEng, FruitEng, MushroomEng ** { + lin + FruitKind x = x ; + MushroomKind x = x ; +} diff --git a/doc/tutorial/Foods.gf b/doc/tutorial/Foods.gf new file mode 100644 index 000000000..985eff0c8 --- /dev/null +++ b/doc/tutorial/Foods.gf @@ -0,0 +1,14 @@ +abstract Foods = { + + cat + S ; Item ; Kind ; Quality ; + + fun + Is : Item -> Quality -> S ; + This, That, All, Most : Kind -> Item ; + QKind : Quality -> Kind -> Kind ; + Wine, Cheese, Fish : Kind ; + Very : Quality -> Quality ; + Fresh, Warm, Italian, Expensive, Delicious, Boring : Quality ; + +} \ No newline at end of file diff --git a/doc/tutorial/FoodsEng.gf b/doc/tutorial/FoodsEng.gf new file mode 100644 index 000000000..1899c0e96 --- /dev/null +++ b/doc/tutorial/FoodsEng.gf @@ -0,0 +1,35 @@ +--# -path=.:prelude + +concrete FoodsEng of Foods = open Prelude, MorphoEng in { + + lincat + S, Quality = SS ; + Kind = {s : Number => Str} ; + Item = {s : Str ; n : Number} ; + + lin + Is item quality = ss (item.s ++ (mkVerb "are" "is").s ! item.n ++ quality.s) ; + This = det Sg "this" ; + That = det Sg "that" ; + All = det Pl "all" ; + Most = det Pl "most" ; + QKind quality kind = {s = \\n => quality.s ++ kind.s ! n} ; + Wine = regNoun "wine" ; + Cheese = regNoun "cheese" ; + Fish = mkNoun "fish" "fish" ; + Very = prefixSS "very" ; + Fresh = ss "fresh" ; + Warm = ss "warm" ; + Italian = ss "Italian" ; + Expensive = ss "expensive" ; + Delicious = ss "delicious" ; + Boring = ss "boring" ; + + oper + det : Number -> Str -> Noun -> {s : Str ; n : Number} = \n,d,cn -> { + s = d ++ cn.s ! n ; + n = n + } ; + +} + \ No newline at end of file diff --git a/doc/tutorial/Fruit.gf b/doc/tutorial/Fruit.gf new file mode 100644 index 000000000..a3dc1d84a --- /dev/null +++ b/doc/tutorial/Fruit.gf @@ -0,0 +1,4 @@ +abstract Fruit = { + cat Fruit ; + fun Apple, Peach : Fruit ; +} diff --git a/doc/tutorial/FruitEng.gf b/doc/tutorial/FruitEng.gf new file mode 100644 index 000000000..15a378a1f --- /dev/null +++ b/doc/tutorial/FruitEng.gf @@ -0,0 +1,5 @@ +concrete FruitEng of Fruit = { + lin + Apple = {s = "apple"} ; + Peach = {s = "peach"} ; +} diff --git a/doc/tutorial/Morefood.gf b/doc/tutorial/Morefood.gf new file mode 100644 index 000000000..8e27e9718 --- /dev/null +++ b/doc/tutorial/Morefood.gf @@ -0,0 +1,8 @@ +abstract Morefood = Food ** { + cat + Question ; + fun + QIs : Item -> Quality -> Question ; + Pizza : Kind ; + +} diff --git a/doc/tutorial/MorefoodEng.gf b/doc/tutorial/MorefoodEng.gf new file mode 100644 index 000000000..90ff1532a --- /dev/null +++ b/doc/tutorial/MorefoodEng.gf @@ -0,0 +1,7 @@ +concrete MorefoodEng of Morefood = FoodEng ** { + lincat + Question = {s : Str} ; + lin + QIs item quality = {s = "is" ++ item.s ++ quality.s} ; + Pizza = {s = "pizza"} ; +} \ No newline at end of file diff --git a/doc/tutorial/Mushroom.gf b/doc/tutorial/Mushroom.gf new file mode 100644 index 000000000..f6b788b06 --- /dev/null +++ b/doc/tutorial/Mushroom.gf @@ -0,0 +1,4 @@ +abstract Mushroom = { + cat Mushroom ; + fun Cep, Agaric : Mushroom ; +} diff --git a/doc/tutorial/MushroomEng.gf b/doc/tutorial/MushroomEng.gf new file mode 100644 index 000000000..a029a17f3 --- /dev/null +++ b/doc/tutorial/MushroomEng.gf @@ -0,0 +1,5 @@ +concrete MushroomEng of Mushroom = { + lin + Cep = {s = "cep"} ; + Agaric = {s = "agaric"} ; +} diff --git a/doc/tutorial/StringOper.gf b/doc/tutorial/StringOper.gf new file mode 100644 index 000000000..803d957f0 --- /dev/null +++ b/doc/tutorial/StringOper.gf @@ -0,0 +1,10 @@ +resource StringOper = { + oper + SS : Type = {s : Str} ; + + ss : Str -> SS = \x -> {s = x} ; + + cc : SS -> SS -> SS = \x,y -> ss (x.s ++ y.s) ; + + prefix : Str -> SS -> SS = \p,x -> ss (p ++ x.s) ; +} \ No newline at end of file diff --git a/doc/tutorial/Tree.png b/doc/tutorial/Tree.png index 2bdaa04c8..d28f73139 100644 Binary files a/doc/tutorial/Tree.png and b/doc/tutorial/Tree.png differ diff --git a/doc/tutorial/food.cf b/doc/tutorial/food.cf new file mode 100644 index 000000000..e7d6a50a5 --- /dev/null +++ b/doc/tutorial/food.cf @@ -0,0 +1,6 @@ +S ::= Item "is" Quality ; +Item ::= "this" Kind | "that" Kind ; +Kind ::= Quality Kind ; +Kind ::= "wine" | "cheese" | "fish" ; +Quality ::= "very" Quality ; +Quality ::= "fresh" | "warm" | "Italian" | "expensive" | "delicious" | "boring" ; diff --git a/doc/tutorial/gf-tutorial2.html b/doc/tutorial/gf-tutorial2.html index bb6440ff4..42926b668 100644 --- a/doc/tutorial/gf-tutorial2.html +++ b/doc/tutorial/gf-tutorial2.html @@ -7,7 +7,7 @@

Grammatical Framework Tutorial

Author: Aarne Ranta <aarne (at) cs.chalmers.se>
-Last update: Sat Dec 17 23:19:34 2005 +Last update: Sun Dec 18 21:43:08 2005

@@ -44,76 +44,77 @@ Last update: Sat Dec 17 23:19:34 2005 -
  • Grammar architecture +
  • Grammar architecture -
  • System commands -
  • Resource modules +
  • System commands +
  • Resource modules -
  • Morphology +
  • Morphology -
  • Using morphology in concrete syntax +
  • Using morphology in concrete syntax -
  • More constructs for concrete syntax +
  • More constructs for concrete syntax -
  • More features of the module system +
  • More features of the module system -
  • More concepts of abstract syntax +
  • More concepts of abstract syntax -
  • Transfer modules -
  • Practical issues +
  • Transfer modules +
  • Practical issues -
  • Case studies +
  • Case studies @@ -156,7 +157,7 @@ GF Homepage: There you can download

    @@ -170,10 +171,29 @@ don't need to know Haskell or Java to use GF. To start the GF program, assuming you have installed it, just type 

    -    gf
+    % gf

    in the shell. You will see GF's welcome message and the prompt >. +The command +

    +
    +    > help
+
    +

    +will give you a list of available commands. +

    +

    +As a common convention in this Tutorial, we will use +

    + + +

    +Thus you should not type these prompts, but only the lines that +follow them.

    The ``.cf`` grammar format

    @@ -182,28 +202,22 @@ Now you are ready to try out your first grammar. We start with one that is not written in GF language, but in the ubiquitous BNF notation (Backus Naur Form), which GF can also understand. Type (or copy) the following lines in a file named -paleolithic.cf: +food.cf: 

    -    S   ::= NP VP ;
-    VP  ::= V | TV NP | "is" A ;
-    NP  ::= "this" CN | "that" CN | "the" CN | "a" CN ;
-    CN  ::= A CN ;
-    CN  ::= "boy" | "louse" | "snake" | "worm" ;
-    A   ::= "green" | "rotten" | "thick" | "warm" ;
-    V   ::= "laughs" | "sleeps" | "swims" ;
-    TV  ::= "eats" | "kills" | "washes" ;
+    S       ::= Item "is" Quality ;
+    Item    ::= "this" Kind | "that" Kind ;
+    Kind    ::= Quality Kind ;
+    Kind    ::= "wine" | "cheese" | "fish" ;
+    Quality ::= "very" Quality ;
+    Quality ::= "fresh" | "warm" | "Italian" | "expensive" | "delicious" | "boring" ;
    -

    -(The name paleolithic refers to a larger package -stoneage, -which implements a fragment of primitive language. This fragment -was defined by the linguist Morris Swadesh as a tool for studying -the historical relations of languages. But as suggested -in the Wiktionary article on -Swadesh list, the -fragment is also usable for basic communication between foreigners.) +This grammar defines a set of phrases usable to speak about food. +It builds sentences (S) by assigning Qualities to +Items. The grammar shows a typical character of GF grammars: +they are small grammars describing some more or less well-defined +domain, such as in this case food.

    Importing grammars and parsing strings

    @@ -212,17 +226,15 @@ The first GF command when using a grammar is to import it. The command has a long name, import, and a short name, i. You can type either

    -
    -  import paleolithic.cf
-
    -

    +

    +```> import food.cf +

    or

    -
    -  i paleolithic.cf
-
    -

    +

    +```> i food.cf +

    to get the same effect. The effect is that the GF program compiles your grammar into an internal @@ -232,16 +244,17 @@ representation, and shows a new prompt when it is ready. You can now use GF for parsing: 

    -    > parse "the boy eats a snake"
-    S_NP_VP (NP_the_CN CN_boy) (VP_TV_NP TV_eats (NP_a_CN CN_snake))
+    > parse "this cheese is delicious"
+    S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_delicious
   
-    > parse "the snake eats a boy"
-    S_NP_VP (NP_the_CN CN_snake) (VP_TV_NP TV_eats (NP_a_CN CN_boy))
+    > p "that wine is very very Italian"
+    S_Item_is_Quality (Item_that_Kind Kind_wine) 
+      (Quality_very_Quality (Quality_very_Quality Quality_Italian))

    The parse (= p) command takes a string (in double quotes) and returns an abstract syntax tree - the thing -beginning with S_NP_VP. We will see soon how to make sense +beginning with S_Item_Is_Quality. We will see soon how to make sense of the abstract syntax trees - now you should just notice that the tree is different for the two strings.

    @@ -263,8 +276,8 @@ You can also use GF for linearizing parsing, taking trees into strings: 

    -    > linearize S_NP_VP (NP_the_CN CN_boy) (VP_TV_NP TV_eats (NP_a_CN CN_snake))
-    the boy eats a snake
+    > linearize S_Item_is_Quality (Item_that_Kind Kind_wine) Quality_warm
+    that wine is warm

    What is the use of this? Typically not that you type in a tree at @@ -274,16 +287,16 @@ you can obtain a tree from somewhere else. One way to do so is 

         > generate_random
-    S_NP_VP (NP_this_CN (CN_A_CN A_thick CN_worm)) (VP_V V_sleeps)
+    S_Item_is_Quality (Item_this_Kind Kind_wine) Quality_delicious

    Now you can copy the tree and paste it to the linearize command. -Or, more efficiently, feed random generation into parsing by using +Or, more efficiently, feed random generation into linearization by using a pipe. 

         > gr | l
-    this worm is warm
+    this fresh cheese is delicious

    @@ -291,14 +304,14 @@ a pipe.

    The gibberish code with parentheses returned by the parser does not look like trees. Why is it called so? Trees are a data structure that -represent <b>nesting</b>: trees are branching entities, and the branches +represent nesting: trees are branching entities, and the branches are themselves trees. Parentheses give a linear representation of trees, useful for the computer. But the human eye may prefer to see a visualization; for this purpose, GF provides the command visualizre_tree = vt, to which parsing (and any other tree-producing command) can be piped: 

    -  parse "the green boy eats a warm snake" | vt
+  parse "this delicious cheese is very Italian" | vt

    @@ -312,16 +325,16 @@ generate ten strings with one and the same command: 

         > gr -number=10 | l
-    this boy is green
-    a snake laughs
-    the rotten boy is thick
-    a boy washes this worm
-    a boy is warm
-    this green warm boy is rotten
-    the green thick green louse is rotten
-    that boy is green
-    this thick thick boy laughs
-    a boy is green
+    that wine is boring
+    that fresh cheese is fresh
+    that cheese is very boring
+    this cheese is Italian
+    that expensive cheese is expensive
+    that fish is fresh
+    that wine is very Italian
+    this wine is Italian
+    this cheese is boring
+    this fish is boring

    @@ -332,15 +345,16 @@ can generate, use the command generate_trees = gt. 

         > generate_trees | l
-    this louse laughs
-    this louse sleeps
-    this louse swims
-    this louse is green
-    this louse is rotten
+    that cheese is very Italian
+    that cheese is very boring
+    that cheese is very delicious
+    that cheese is very expensive
+    that cheese is very fresh
     ...
-    a boy is rotten
-    a boy is thick
-    a boy is warm
+    this wine is expensive
+    this wine is fresh
+    this wine is warm
+

    You get quite a few trees but not all of them: only up to a given @@ -348,7 +362,7 @@ You get quite a few trees but not all of them: only up to a given help = h command, 

    -    help gr
+    help gt

    Quiz. If the command gt generated all @@ -369,9 +383,9 @@ want to see: 

         > gr -tr | l -tr | p
   
-    S_NP_VP (NP_the_CN CN_snake) (VP_V V_sleeps)
-    the snake sleeps
-    S_NP_VP (NP_the_CN CN_snake) (VP_V V_sleeps)
+    S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_boring
+    this cheese is boring
+    S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_boring

    This facility is good for test purposes: for instance, you @@ -413,34 +427,36 @@ with the printer flag set to cf (which means context-f 

         > print_grammar -printer=cf
   
-    V_laughs. V ::= "laughs" ;
-    V_sleeps. V ::= "sleeps" ;
-    V_swims. V ::= "swims" ;
-    VP_TV_NP. VP ::= TV NP ;
-    VP_V. VP ::= V ;
-    VP_is_A. VP ::= "is" A ;
-    TV_eats. TV ::= "eats" ;
-    TV_kills. TV ::= "kills" ;
-    TV_washes. TV ::= "washes" ;
-    S_NP_VP. S ::= NP VP ;
-    NP_a_CN. NP ::= "a" ;
-    ...
+    S_Item_is_Quality. S ::= Item "is" Quality ;
+    Quality_Italian. Quality ::= "Italian" ;
+    Quality_boring. Quality ::= "boring" ;
+    Quality_delicious. Quality ::= "delicious" ;
+    Quality_expensive. Quality ::= "expensive" ;
+    Quality_fresh. Quality ::= "fresh" ;
+    Quality_very_Quality. Quality ::= "very" Quality ;
+    Quality_warm. Quality ::= "warm" ;
+    Kind_Quality_Kind. Kind ::= Quality Kind ;
+    Kind_cheese. Kind ::= "cheese" ;
+    Kind_fish. Kind ::= "fish" ;
+    Kind_wine. Kind ::= "wine" ;
+    Item_that_Kind. Item ::= "that" Kind ;
+    Item_this_Kind. Item ::= "this" Kind ;

    A syntax tree such as 

    -    NP_this_CN (CN_A_CN A_thick CN_worm)
-    this thick worm
+    S_Item_is_Quality (Item_this_Kind Kind_wine) Quality_delicious

    encodes the sequence of grammar rules used for building the -expression. If you look at this tree, you will notice that NP_this_CN -is the label of the rule prefixing this to a common noun (CN), -thereby forming a noun phrase (NP). -A_thick is the label of the adjective thick, +tree. If you look at this tree, you will notice that Item_this_Kind +is the label of the rule prefixing this to a Kind, +thereby forming an Item. +Kind_wine is the label of the kind "wine", and so on. These labels are formed automatically when the grammar -is compiled by GF. +is compiled by GF, in a way that guarantees that different rules +get different labels.

    The labelled context-free format

    @@ -453,42 +469,32 @@ than the automatically generated ones. The following is a possible labelling of paleolithic.cf with nicer-looking labels. 

    -    PredVP.  S   ::= NP VP ;
-    UseV.    VP  ::= V ;
-    ComplTV. VP  ::= TV NP ;
-    UseA.    VP  ::= "is" A ;
-    This.    NP  ::= "this" CN ; 
-    That.    NP  ::= "that" CN ; 
-    Def.     NP  ::= "the" CN ;
-    Indef.   NP  ::= "a" CN ;  
-    ModA.    CN  ::= A CN ;
-    Boy.     CN  ::= "boy" ;
-    Louse.   CN  ::= "louse" ;
-    Snake.   CN  ::= "snake" ;
-    Worm.    CN  ::= "worm" ;
-    Green.   A   ::= "green" ;
-    Rotten.  A   ::= "rotten" ;
-    Thick.   A   ::= "thick" ;
-    Warm.    A   ::= "warm" ;
-    Laugh.   V   ::= "laughs" ;
-    Sleep.   V   ::= "sleeps" ;
-    Swim.    V   ::= "swims" ;
-    Eat.     TV  ::= "eats" ;
-    Kill.    TV  ::= "kills" 
-    Wash.    TV  ::= "washes" ;
+    Is.        S       ::= Item "is" Quality ;
+    That.      Item    ::= "that" Kind ;
+    This.      Item    ::= "this" Kind ;
+    QKind.     Kind    ::= Quality Kind ;
+    Cheese.    Kind    ::= "cheese" ;
+    Fish.      Kind    ::= "fish" ;
+    Wine.      Kind    ::= "wine" ;
+    Italian.   Quality ::= "Italian" ;
+    Boring.    Quality ::= "boring" ;
+    Delicious. Quality ::= "delicious" ;
+    Expensive. Quality ::= "expensive" ;
+    Fresh.     Quality ::= "fresh" ;
+    Very.      Quality ::= "very" Quality ;
+    Warm.      Quality ::= "warm" ;

    With this grammar, the trees look as follows: 

    -    > p "the boy eats a snake"
-    PredVP (Def Boy) (ComplTV Eat (Indef Snake))
-  
-    > gr -tr | l
-    PredVP (Indef Louse) (UseA Thick)
-    a louse is thick
+    > parse -tr "this delicious cheese is very Italian" | vt
+    Is (This (QKind Delicious Cheese)) (Very Italian)

    +

    + +

    The ``.gf`` grammar format

    @@ -510,7 +516,7 @@ how GF's own notation gives you much more expressive power than the .cf format. We will introduce the .gf format by presenting one more way of defining the same grammar as in -paleolithic.cf. +food.cf. Then we will show how the full GF grammar format enables you to do things that are not possible in the weaker formats.

    @@ -526,28 +532,28 @@ A GF grammar consists of two main parts:

    The EBNF and CF formats fuse these two things together, but it is possible -to take them apart. For instance, the verb phrase predication rule +to take them apart. For instance, the sentence formation rule 

    -    PredVP. S ::= NP VP ;
+    Is. S ::= Item "is" Quality ;

    is interpreted as the following pair of rules: 

    -    fun PredVP : NP -> VP -> S ;
-    lin PredVP x y = {s = x.s ++ y.s} ;
+    fun Is : Item -> Quality -> S ;
+    lin Is item quality = {s = item.s ++ "is" ++ quality.s} ;

    The former rule, with the keyword fun, belongs to the abstract syntax. It defines the function -PredVP which constructs syntax trees of form -(PredVP x y). +Is which constructs syntax trees of form +(Is item quality).

    The latter rule, with the keyword lin, belongs to the concrete syntax. It defines the linearization function for -syntax trees of form (PredVP x y). +syntax trees of form (Is item quality).

    Judgement forms

    @@ -682,8 +688,8 @@ denotes the empty token list.

    An abstract syntax example

    -To express the abstract syntax of paleolithic.cf in -a file Paleolithic.gf, we write two kinds of judgements: +To express the abstract syntax of food.cf in +a file Food.gf, we write two kinds of judgements: 

    -  abstract Paleolithic = {
-  cat 
-    S ; NP ; VP ; CN ; A ; V ; TV ; 
-  fun
-    PredVP  : NP -> VP -> S ;
-    UseV    : V -> VP ;
-    ComplTV : TV -> NP -> VP ;
-    UseA    : A -> VP ;
-    ModA    : A -> CN -> CN ;
-    This, That, Def, Indef : CN -> NP ; 
-    Boy, Louse, Snake, Worm : CN ;
-    Green, Rotten, Thick, Warm : A ;
-    Laugh, Sleep, Swim : V ;
-    Eat, Kill, Wash : TV ;
+  abstract Food = {
+  
+    cat
+      S ; Item ; Kind ; Quality ;
+  
+    fun
+      Is : Item -> Quality -> S ;
+      This, That : Kind -> Item ;
+      QKind : Quality -> Kind -> Kind ;
+      Wine, Cheese, Fish : Kind ;
+      Very : Quality -> Quality ;
+      Fresh, Warm, Italian, Expensive, Delicious, Boring : Quality ;
   }

    @@ -716,39 +720,32 @@ in subsequent fun judgements.

    A concrete syntax example

    -Each category introduced in Paleolithic.gf is +Each category introduced in Food.gf is given a lincat rule, and each function is given a lin rule. Similar shorthands apply as in abstract modules. 

    -  concrete PaleolithicEng of Paleolithic = {
-  lincat 
-    S, NP, VP, CN, A, V, TV = {s : Str} ; 
-  lin
-    PredVP np vp  = {s = np.s ++ vp.s} ;
-    UseV   v      = v ;
-    ComplTV tv np = {s = tv.s ++ np.s} ;
-    UseA   a   = {s = "is" ++ a.s} ;
-    This  cn   = {s = "this" ++ cn.s} ; 
-    That  cn   = {s = "that" ++ cn.s} ; 
-    Def   cn   = {s = "the" ++ cn.s} ;
-    Indef cn   = {s = "a" ++ cn.s} ; 
-    ModA  a cn = {s = a.s ++ cn.s} ;
-    Boy    = {s = "boy"} ;
-    Louse  = {s = "louse"} ;
-    Snake  = {s = "snake"} ;
-    Worm   = {s = "worm"} ;
-    Green  = {s = "green"} ;
-    Rotten = {s = "rotten"} ;
-    Thick  = {s = "thick"} ;
-    Warm   = {s = "warm"} ;
-    Laugh  = {s = "laughs"} ;
-    Sleep  = {s = "sleeps"} ;
-    Swim   = {s = "swims"} ;
-    Eat    = {s = "eats"} ;
-    Kill   = {s = "kills"} ; 
-    Wash   = {s = "washes"} ;
+  concrete FoodEng of Food = {
+  
+    lincat
+      S, Item, Kind, Quality = {s : Str} ;
+  
+    lin
+      Is item quality = {s = item.s ++ "is" ++ quality.s} ;
+      This kind = {s = "this" ++ kind.s} ;
+      That kind = {s = "that" ++ kind.s} ;
+      QKind quality kind = {s = quality.s ++ kind.s} ;
+      Wine = {s = "wine"} ;
+      Cheese = {s = "cheese"} ;
+      Fish = {s = "fish"} ;
+      Very quality = {s = "very" ++ quality.s} ;
+      Fresh = {s = "fresh"} ;
+      Warm = {s = "warm"} ;
+      Italian = {s = "Italian"} ;
+      Expensive = {s = "expensive"} ;
+      Delicious = {s = "delicious"} ;
+      Boring = {s = "boring"} ;
   }

    @@ -761,15 +758,15 @@ Module name + .gf = file name Each module is compiled into a .gfc file.

    -Import PaleolithicEng.gf and try what happens +Import FoodEng.gf and see what happens 

    -    > i PaleolithicEng.gf
+    > i FoodEng.gf

    The GF program does not only read the file -PaleolithicEng.gf, but also all other files that it -depends on - in this case, Paleolithic.gf. +FoodEng.gf, but also all other files that it +depends on - in this case, Food.gf.

    For each file that is compiled, a .gfc file @@ -789,40 +786,35 @@ A system with this property is called a multilingual grammar.

    Multilingual grammars can be used for applications such as translation. Let us buid an Italian concrete syntax for -Paleolithic and then test the resulting +Food and then test the resulting multilingual grammar.

    An Italian concrete syntax

    -  concrete PaleolithicIta of Paleolithic = {
-  lincat 
-    S, NP, VP, CN, A, V, TV = {s : Str} ; 
-  lin
-    PredVP np vp  = {s = np.s ++ vp.s} ;
-    UseV   v      = v ;
-    ComplTV tv np = {s = tv.s ++ np.s} ;
-    UseA   a   = {s = "è" ++ a.s} ;
-    This  cn   = {s = "questo" ++ cn.s} ; 
-    That  cn   = {s = "quello" ++ cn.s} ; 
-    Def   cn   = {s = "il" ++ cn.s} ;
-    Indef cn   = {s = "un" ++ cn.s} ; 
-    ModA  a cn = {s = cn.s ++ a.s} ;
-    Boy    = {s = "ragazzo"} ;
-    Louse  = {s = "pidocchio"} ;
-    Snake  = {s = "serpente"} ;
-    Worm   = {s = "verme"} ;
-    Green  = {s = "verde"} ;
-    Rotten = {s = "marcio"} ;
-    Thick  = {s = "grosso"} ;
-    Warm   = {s = "caldo"} ;
-    Laugh  = {s = "ride"} ;
-    Sleep  = {s = "dorme"} ;
-    Swim   = {s = "nuota"} ;
-    Eat    = {s = "mangia"} ;
-    Kill   = {s = "uccide"} ; 
-    Wash   = {s = "lava"} ;
+  concrete FoodIta of Food = {
+  
+    lincat
+      S, Item, Kind, Quality = {s : Str} ;
+  
+    lin
+      Is item quality = {s = item.s ++ "è" ++ quality.s} ;
+      This kind = {s = "questo" ++ kind.s} ;
+      That kind = {s = "quello" ++ kind.s} ;
+      QKind quality kind = {s = kind.s ++ quality.s} ;
+      Wine = {s = "vino"} ;
+      Cheese = {s = "formaggio"} ;
+      Fish = {s = "pesce"} ;
+      Very quality = {s = "molto" ++ quality.s} ;
+      Fresh = {s = "fresco"} ;
+      Warm = {s = "caldo"} ;
+      Italian = {s = "italiano"} ;
+      Expensive = {s = "caro"} ;
+      Delicious = {s = "delizioso"} ;
+      Boring = {s = "noioso"} ;
+  
   }
+

    @@ -831,25 +823,25 @@ multilingual grammar. Import the two grammars in the same GF session. 

    -    > i PaleolithicEng.gf
-    > i PaleolithicIta.gf
+    > i FoodEng.gf
+    > i FoodIta.gf

    Try generation now: 

         > gr | l
-    un pidocchio uccide questo ragazzo
+    quello formaggio molto noioso è italiano
   
     > gr | l -lang=PaleolithicEng
-    that louse eats a louse
+    this fish is warm

    Translate by using a pipe: 

    -    > p -lang=PaleolithicEng "the boy eats the snake" | l -lang=PaleolithicIta
-    il ragazzo mangia il serpente
+    > p -lang=FoodEng "this cheese is very delicious" | l -lang=FoodIta
+    questo formaggio è molto delizioso

    The lang flag tells GF which concrete syntax to use in parsing and @@ -859,12 +851,35 @@ To see what grammars are in scope and which is the main one, use the command 

         > print_options
-    main abstract :     Paleolithic
-    main concrete :     PaleolithicIta
-    actual concretes :  PaleolithicIta PaleolithicEng
+    main abstract :     Food
+    main concrete :     FoodIta
+    actual concretes :  FoodIta FoodEng

    +

    Translation session

    +

    +If translation is what you want to do with a set of grammars, a convenient +way to do it is to open a translation_session = ts. In this session, +you can translate between all the languages that are in scope. +A dot . terminates the translation session. +

    +
    +    > ts
+  
+    trans> that very warm cheese is boring
+    quello formaggio molto caldo è noioso
+    that very warm cheese is boring
+  
+    trans> questo vino molto italiano è molto delizioso
+    questo vino molto italiano è molto delizioso
+    this very Italian wine is very delicious
+  
+    trans> .
+    >
+
    +

    +

    Translation quiz

    This is a simple language exercise that can be automatically @@ -874,46 +889,54 @@ answer given in another language. The command translation_quiz = tq makes this in a subshell of GF. 

    -    > translation_quiz PaleolithicEng PaleolithicIta
+    > translation_quiz FoodEng FoodIta
   
     Welcome to GF Translation Quiz.
     The quiz is over when you have done at least 10 examples
     with at least 75 % success.
     You can interrupt the quiz by entering a line consisting of a dot ('.').
   
-    a green boy washes the louse
-    un ragazzo verde lava il gatto
+    this fish is warm
+    questo pesce è caldo
+    > Yes.
+    Score 1/1
   
-    No, not un ragazzo verde lava il gatto, but
-    un ragazzo verde lava il pidocchio
-    Score 0/1
+    this cheese is Italian
+    questo formaggio è noioso
+    > No, not questo formaggio è noioso, but
+    questo formaggio è italiano
+  
+    Score 1/2
+    this fish is expensive

    You can also generate a list of translation exercises and save it in a file for later use, by the command translation_list = tl 

    -    > translation_list -number=25 PaleolithicEng PaleolithicIta
+    > translation_list -number=25 FoodEng FoodIta

    The number flag gives the number of sentences generated.

    - -

    Grammar architecture

    +

    Grammar architecture

    +

    Extending a grammar

    The module system of GF makes it possible to extend a grammar in different ways. The syntax of extension is -shown by the following example. This is how language -was extended when civilization advanced from the -paleolithic to the neolithic age: +shown by the following example. We extend Food by +adding a category of questions and two new functions. 

    -    abstract Neolithic = Paleolithic ** {
+    abstract Morefood = Food ** {
+      cat
+        Question ;
       fun
-        Fire, Wheel : CN ;
-        Think : V ;
+        QIs : Item -> Quality -> Question ;
+        Pizza : Kind ;
+        
     }

    @@ -921,31 +944,32 @@ Parallel to the abstract syntax, extensions can be built for concrete syntaxes: 

    -    concrete NeolithicEng of Neolithic = PaleolithicEng ** {
+    concrete MorefoodEng of Morefood = FoodEng ** {
+      lincat
+        Question = {s : Str} ;
       lin
-        Fire  = {s = "fire"} ;
-        Wheel = {s = "wheel"} ;
-        Think = {s = "thinks"} ;
+        QIs item quality = {s = "is" ++ item.s ++ quality.s} ;
+        Pizza = {s = "pizza"} ;
     }

    The effect of extension is that all of the contents of the extended and extending module are put together.

    - +

    Multiple inheritance

    Specialized vocabularies can be represented as small grammars that only do "one thing" each. For instance, the following are grammars -for fish names and mushroom names. +for fruit and mushrooms 

    -    abstract Fish = {
-      cat Fish ;
-      fun Salmon, Perch : Fish ;
+    abstract Fruit = {
+      cat Fruit ;
+      fun Apple, Peach : Fruit ;
     }
   
-    abstract Mushrooms = {
+    abstract Mushroom = {
       cat Mushroom ;
       fun Cep, Agaric : Mushroom ;
     }
@@ -956,18 +980,22 @@ They can afterwards be combined into bigger grammars by using
 same time:
 
    
 
    -    abstract Gatherer = Paleolithic, Fish, Mushrooms ** {
+    abstract Foodmarket = Food, Fruit, Mushroom ** {
       fun 
-        FishCN     : Fish     -> CN ;
-        MushroomCN : Mushroom -> CN ;
+        FruitKind    : Fruit    -> Kind ;
+        MushroomKind : Mushroom -> Kind ;
       }
 
    
-
    
-
+
    
+At this point, you would perhaps like to go back to
+Food and take apart Wine to build a special
+Drink module.
+
    
+
 
    Visualizing module structure
    
 
    
 When you have created all the abstract syntaxes and
-one set of concrete syntaxes needed for Gatherer,
+one set of concrete syntaxes needed for Foodmarket,
 your grammar consists of eight GF modules. To see how their
 dependences look like, you can use the command 
 visualize_graph = vg,
@@ -987,25 +1015,25 @@ The graph uses
 
  • black-headed arrows for inheritance
 
  • white-headed arrows for the concrete-of-abstract relation
 
    
-
+
 
 
-
+
 
    System commands
    
 
    
 To document your grammar, you may want to print the
-graph into a file, e.g. a .gif file that
+graph into a file, e.g. a .png file that
 can be included in an HTML document. You can do this
 by first printing the graph into a file .dot and then
 processing this file with the dot program.
 
    
 
    -    > pm -printer=graph | wf Gatherer.dot
-    > ! dot -Tgif Gatherer.dot > Gatherer.gif
+    > pm -printer=graph | wf Foodmarket.dot
+    > ! dot -Tpng Foodmarket.dot > Foodmarket.png
 
    
 
    
 The latter command is a Unix command, issued from GF by using the
-shell escape symbol !. The resulting graph is shown in the next section.
+shell escape symbol !. The resulting graph was shown in the previous section.
 
    
 
    
 The command print_multi = pm is used for printing the current multilingual
@@ -1018,9 +1046,9 @@ are available:
     > help -printer

    • - -

    Resource modules

    +

    Resource modules

    +

    The golden rule of functional programming

    In comparison to the .cf format, the .gf format still looks rather @@ -1042,7 +1070,7 @@ changing parts, parameters. In functional programming languages, such as Haskell, it is possible to share muc more than in the languages such as C and Java.

    - +

    Operation definitions

    GF is a functional programming language, not only in the sense that @@ -1072,7 +1100,7 @@ its type, and an expression defining it. As for the syntax of the defining expression, notice the lambda abstraction form \x -> t of the function.

    - +

    The ``resource`` module type

    Operator definitions can be included in a concrete syntax. @@ -1103,7 +1131,7 @@ Resource modules can extend other resource modules, in the same way as modules of other types can extend modules of the same type. Thus it is possible to build resource hierarchies.

    - +

    Opening a ``resource``

    Any number of resource modules can be @@ -1137,7 +1165,7 @@ opened in a new version of PaleolithicEng. The same string operations could be use to write PaleolithicIta more concisely.

    - +

    Division of labour

    Using operations defined in resource modules is a @@ -1149,7 +1177,7 @@ available through resource grammar modules, whose users only need to pick the right operations and not to know their implementation details.

    - +

    Morphology

    Suppose we want to say, with the vocabulary included in @@ -1185,7 +1213,7 @@ many new expression forms, and a generalizarion of linearization types from strings to more complex types.

    - +

    Parameters and tables

    We define the parameter type of number in Englisn by @@ -1226,7 +1254,7 @@ operator !. For instance,

    is a selection, whose value is "boys".

    - +

    Inflection tables, paradigms, and ``oper`` definitions

    All English common nouns are inflected in number, most of them in the @@ -1260,7 +1288,7 @@ are written together to form one token. Thus, for instance, (regNoun "boy").s ! Pl ---> "boy" + "s" ---> "boys"

    - +

    Worst-case macros and data abstraction

    Some English nouns, such as louse, are so irregular that @@ -1301,7 +1329,7 @@ interface (i.e. the system of type signatures) that makes it correct to use these functions in concrete modules. In programming terms, Noun is then treated as an abstract datatype.

    - +

    A system of paradigms using ``Prelude`` operations

    In addition to the completely regular noun paradigm regNoun, @@ -1333,7 +1361,7 @@ The operator init belongs to a set of operations in the resource module Prelude, which therefore has to be opened so that init can be used.

    - +

    An intelligent noun paradigm using ``case`` expressions

    It may be hard for the user of a resource morphology to pick the right @@ -1363,7 +1391,7 @@ this, either use mkNoun or modify regNoun so that the "y" case does not apply if the second-last character is a vowel.

    - +

    Pattern matching

    Expressions of the table form are built from lists of @@ -1399,7 +1427,7 @@ programming languages are syntactic sugar for table selections: case e of {...} === table {...} ! e

    - +

    Morphological ``resource`` modules

    A common idiom is to @@ -1450,7 +1478,7 @@ module depends on. The directory prelude is a subdirectory of set the environment variable GF_LIB_PATH to point to this directory.

    - +

    Testing ``resource`` modules

    To test a resource module independently, you can import it @@ -1493,7 +1521,7 @@ Why does the command also show the operations that form Verb is first computed, and its value happens to be the same as the value of Noun.

    - +

    Using morphology in concrete syntax

    We can now enrich the concrete syntax definitions to @@ -1504,7 +1532,7 @@ parameters and linearization types are different in different languages - but this does not prevent the use of a common abstract syntax.

    - +

    Parametric vs. inherent features, agreement

    The rule of subject-verb agreement in English says that the verb @@ -1540,7 +1568,7 @@ regular only in the present tensse). The reader is invited to inspect the way in which agreement works in the formation of noun phrases and verb phrases.

    - +

    English concrete syntax with parameters

       concrete PaleolithicEng of Paleolithic = open Prelude, MorphoEng in {
@@ -1573,7 +1601,7 @@ the formation of noun phrases and verb phrases.
   }

    - +

    Hierarchic parameter types

    The reader familiar with a functional programming language such as @@ -1615,7 +1643,7 @@ the adjectival paradigm in which the two singular forms are the same, can be def }

    - +

    Morphological analysis and morphology quiz

    Even though in GF morphology @@ -1655,7 +1683,7 @@ file for later use, by the command morpho_list = ml

    The number flag gives the number of exercises generated.

    - +

    Discontinuous constituents

    A linearization type may contain more strings than one. @@ -1685,9 +1713,9 @@ the parsing and linearization commands only give reliable results for categories whose linearization type has a unique Str valued field labelled s.

    - -

    More constructs for concrete syntax

    +

    More constructs for concrete syntax

    +

    Free variation

    Sometimes there are many alternative ways to define a concrete syntax. @@ -1715,7 +1743,7 @@ user of the library has no way to choose among the variants. Moreover, even though variants admits lists of any type, its semantics for complex types can cause surprises.

    - +

    Record extension and subtyping

    Record types and records can be extended with new fields. For instance, @@ -1745,7 +1773,7 @@ be used whenever a verb is required. Contravariance means that a function taking an R as argument can also be applied to any object of a subtype T.

    - +

    Tuples and product types

    Product types and tuples are syntactic sugar for record types and records: @@ -1757,7 +1785,7 @@ Product types and tuples are syntactic sugar for record types and records:

    Thus the labels p1, p2,...` are hard-coded.

    - +

    Predefined types and operations

    GF has the following predefined categories in abstract syntax: @@ -1780,31 +1808,31 @@ they can be used as arguments. For example: -- e.g. (StreetAddress 10 "Downing Street") : Address

    - -

    More features of the module system

    +

    More features of the module system

    +

    Resource grammars and their reuse

    See resource library documentation

    - +

    Interfaces, instances, and functors

    See an example built this way

    - -

    Restricted inheritance and qualified opening

    -

    More concepts of abstract syntax

    +

    Restricted inheritance and qualified opening

    -

    Dependent types

    +

    More concepts of abstract syntax

    -

    Higher-order abstract syntax

    +

    Dependent types

    -

    Semantic definitions

    +

    Higher-order abstract syntax

    +

    Semantic definitions

    +

    Transfer modules

    Transfer means noncompositional tree-transforming operations. @@ -1823,9 +1851,9 @@ See the transfer language documentation for more information.

    - -

    Practical issues

    +

    Practical issues

    +

    Lexers and unlexers

    Lexers and unlexers can be chosen from @@ -1861,7 +1889,7 @@ Given by help -lexer, help -unlexer:

    - +

    Efficiency of grammars

    Issues: @@ -1872,7 +1900,7 @@ Issues:

  • parsing efficiency: -mcfg vs. others - +

    Speech input and output

    Thespeak_aloud = sa command sends a string to the speech @@ -1902,7 +1930,7 @@ The method words only for grammars of English. Both Flite and ATK are freely available through the links above, but they are not distributed together with GF.

    - +

    Multilingual syntax editor

    The @@ -1919,18 +1947,18 @@ Here is a snapshot of the editor: The grammars of the snapshot are from the Letter grammar package.

    - +

    Interactive Development Environment (IDE)

    Forthcoming.

    - +

    Communicating with GF

    Other processes can communicate with the GF command interpreter, and also with the GF syntax editor.

    - +

    Embedded grammars in Haskell, Java, and Prolog

    GF grammars can be used as parts of programs written in the @@ -1942,15 +1970,15 @@ following languages. The links give more documentation.

  • Prolog - +

    Alternative input and output grammar formats

    A summary is given in the following chart of GF grammar compiler phases:

    - -

    Case studies

    +

    Case studies

    +

    Interfacing formal and natural languages

    Formal and Informal Software Specifications, diff --git a/doc/tutorial/gf-tutorial2.txt b/doc/tutorial/gf-tutorial2.txt index 48383e006..696f5cbf8 100644 --- a/doc/tutorial/gf-tutorial2.txt +++ b/doc/tutorial/gf-tutorial2.txt @@ -22,8 +22,6 @@ The term GF is used for different things: - a **theory** about grammars and languages - - This tutorial is primarily about the GF program and the GF programming language. It will guide you @@ -42,27 +40,37 @@ The program is open-source free software, which you can download via the GF Homepage: [``http://www.cs.chalmers.se/~aarne/GF`` http://www.cs.chalmers.se/~aarne/GF] - - There you can download -- ready-made binaries for Linux, Solaris, Macintosh, and Windows +- binaries for Linux, Solaris, Macintosh, and Windows - source code and documentation - grammar libraries and examples - If you want to compile GF from source, you need Haskell and Java compilers. But normally you don't have to compile, and you definitely don't need to know Haskell or Java to use GF. - To start the GF program, assuming you have installed it, just type ``` - gf + % gf ``` in the shell. You will see GF's welcome message and the prompt ``>``. +The command +``` + > help +``` +will give you a list of available commands. + +As a common convention in this Tutorial, we will use + +- ``%`` as a prompt that marks system commands +- ``>`` as a prompt that marks GF commands + + +Thus you should not type these prompts, but only the lines that +follow them. %--! @@ -72,26 +80,20 @@ Now you are ready to try out your first grammar. We start with one that is not written in GF language, but in the ubiquitous BNF notation (Backus Naur Form), which GF can also understand. Type (or copy) the following lines in a file named -``paleolithic.cf``: +``food.cf``: ``` - S ::= NP VP ; - VP ::= V | TV NP | "is" A ; - NP ::= "this" CN | "that" CN | "the" CN | "a" CN ; - CN ::= A CN ; - CN ::= "boy" | "louse" | "snake" | "worm" ; - A ::= "green" | "rotten" | "thick" | "warm" ; - V ::= "laughs" | "sleeps" | "swims" ; - TV ::= "eats" | "kills" | "washes" ; + S ::= Item "is" Quality ; + Item ::= "this" Kind | "that" Kind ; + Kind ::= Quality Kind ; + Kind ::= "wine" | "cheese" | "fish" ; + Quality ::= "very" Quality ; + Quality ::= "fresh" | "warm" | "Italian" | "expensive" | "delicious" | "boring" ; ``` - -(The name ``paleolithic`` refers to a larger package -[stoneage http://www.cs.chalmers.se/~aarne/GF/examples/stoneage/], -which implements a fragment of primitive language. This fragment -was defined by the linguist Morris Swadesh as a tool for studying -the historical relations of languages. But as suggested -in the Wiktionary article on -[Swadesh list http://en.wiktionary.org/wiki/Wiktionary:Swadesh_list], the -fragment is also usable for basic communication between foreigners.) +This grammar defines a set of phrases usable to speak about food. +It builds **sentences** (``S``) by assigning ``Qualities`` to +``Item``s. The grammar shows a typical character of GF grammars: +they are small grammars describing some more or less well-defined +domain, such as in this case food. %--! @@ -101,11 +103,11 @@ The first GF command when using a grammar is to **import** it. The command has a long name, ``import``, and a short name, ``i``. You can type either -``` import paleolithic.cf +```> import food.cf or -``` i paleolithic.cf +```> i food.cf to get the same effect. The effect is that the GF program **compiles** your grammar into an internal @@ -113,15 +115,16 @@ representation, and shows a new prompt when it is ready. You can now use GF for **parsing**: ``` - > parse "the boy eats a snake" - S_NP_VP (NP_the_CN CN_boy) (VP_TV_NP TV_eats (NP_a_CN CN_snake)) + > parse "this cheese is delicious" + S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_delicious - > parse "the snake eats a boy" - S_NP_VP (NP_the_CN CN_snake) (VP_TV_NP TV_eats (NP_a_CN CN_boy)) + > p "that wine is very very Italian" + S_Item_is_Quality (Item_that_Kind Kind_wine) + (Quality_very_Quality (Quality_very_Quality Quality_Italian)) ``` The ``parse`` (= ``p``) command takes a **string** (in double quotes) and returns an **abstract syntax tree** - the thing -beginning with ``S_NP_VP``. We will see soon how to make sense +beginning with ``S_Item_Is_Quality``. We will see soon how to make sense of the abstract syntax trees - now you should just notice that the tree is different for the two strings. @@ -142,8 +145,8 @@ You can also use GF for **linearizing** (``linearize = l``). This is the inverse of parsing, taking trees into strings: ``` - > linearize S_NP_VP (NP_the_CN CN_boy) (VP_TV_NP TV_eats (NP_a_CN CN_snake)) - the boy eats a snake + > linearize S_Item_is_Quality (Item_that_Kind Kind_wine) Quality_warm + that wine is warm ``` What is the use of this? Typically not that you type in a tree at the GF prompt. The utility of linearization comes from the fact that @@ -151,14 +154,14 @@ you can obtain a tree from somewhere else. One way to do so is **random generation** (``generate_random = gr``): ``` > generate_random - S_NP_VP (NP_this_CN (CN_A_CN A_thick CN_worm)) (VP_V V_sleeps) + S_Item_is_Quality (Item_this_Kind Kind_wine) Quality_delicious ``` Now you can copy the tree and paste it to the ``linearize command``. -Or, more efficiently, feed random generation into parsing by using +Or, more efficiently, feed random generation into linearization by using a **pipe**. ``` > gr | l - this worm is warm + this fresh cheese is delicious ``` %--! @@ -166,13 +169,13 @@ a **pipe**. The gibberish code with parentheses returned by the parser does not look like trees. Why is it called so? Trees are a data structure that -represent nesting: trees are branching entities, and the branches +represent **nesting**: trees are branching entities, and the branches are themselves trees. Parentheses give a linear representation of trees, useful for the computer. But the human eye may prefer to see a visualization; for this purpose, GF provides the command ``visualizre_tree = vt``, to which parsing (and any other tree-producing command) can be piped: -``` parse "the green boy eats a warm snake" | vt +``` parse "this delicious cheese is very Italian" | vt [Tree.png] @@ -184,16 +187,16 @@ Random generation can be quite amusing. So you may want to generate ten strings with one and the same command: ``` > gr -number=10 | l - this boy is green - a snake laughs - the rotten boy is thick - a boy washes this worm - a boy is warm - this green warm boy is rotten - the green thick green louse is rotten - that boy is green - this thick thick boy laughs - a boy is green + that wine is boring + that fresh cheese is fresh + that cheese is very boring + this cheese is Italian + that expensive cheese is expensive + that fish is fresh + that wine is very Italian + this wine is Italian + this cheese is boring + this fish is boring ``` @@ -204,21 +207,22 @@ To generate //all// sentence that a grammar can generate, use the command ``generate_trees = gt``. ``` > generate_trees | l - this louse laughs - this louse sleeps - this louse swims - this louse is green - this louse is rotten + that cheese is very Italian + that cheese is very boring + that cheese is very delicious + that cheese is very expensive + that cheese is very fresh ... - a boy is rotten - a boy is thick - a boy is warm + this wine is expensive + this wine is fresh + this wine is warm + ``` You get quite a few trees but not all of them: only up to a given **depth** of trees. To see how you can get more, use the ``help = h`` command, ``` - help gr + help gt ``` **Quiz**. If the command ``gt`` generated all trees in your grammar, it would never terminate. Why? @@ -240,9 +244,9 @@ want to see: ``` > gr -tr | l -tr | p - S_NP_VP (NP_the_CN CN_snake) (VP_V V_sleeps) - the snake sleeps - S_NP_VP (NP_the_CN CN_snake) (VP_V V_sleeps) + S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_boring + this cheese is boring + S_Item_is_Quality (Item_this_Kind Kind_cheese) Quality_boring ``` This facility is good for test purposes: for instance, you may want to see if a grammar is **ambiguous**, i.e. @@ -282,31 +286,33 @@ with the ``printer`` flag set to ``cf`` (which means context-free): ``` > print_grammar -printer=cf - V_laughs. V ::= "laughs" ; - V_sleeps. V ::= "sleeps" ; - V_swims. V ::= "swims" ; - VP_TV_NP. VP ::= TV NP ; - VP_V. VP ::= V ; - VP_is_A. VP ::= "is" A ; - TV_eats. TV ::= "eats" ; - TV_kills. TV ::= "kills" ; - TV_washes. TV ::= "washes" ; - S_NP_VP. S ::= NP VP ; - NP_a_CN. NP ::= "a" ; - ... + S_Item_is_Quality. S ::= Item "is" Quality ; + Quality_Italian. Quality ::= "Italian" ; + Quality_boring. Quality ::= "boring" ; + Quality_delicious. Quality ::= "delicious" ; + Quality_expensive. Quality ::= "expensive" ; + Quality_fresh. Quality ::= "fresh" ; + Quality_very_Quality. Quality ::= "very" Quality ; + Quality_warm. Quality ::= "warm" ; + Kind_Quality_Kind. Kind ::= Quality Kind ; + Kind_cheese. Kind ::= "cheese" ; + Kind_fish. Kind ::= "fish" ; + Kind_wine. Kind ::= "wine" ; + Item_that_Kind. Item ::= "that" Kind ; + Item_this_Kind. Item ::= "this" Kind ; ``` A syntax tree such as ``` - NP_this_CN (CN_A_CN A_thick CN_worm) - this thick worm + S_Item_is_Quality (Item_this_Kind Kind_wine) Quality_delicious ``` encodes the sequence of grammar rules used for building the -expression. If you look at this tree, you will notice that ``NP_this_CN`` -is the label of the rule prefixing ``this`` to a common noun (``CN``), -thereby forming a noun phrase (``NP``). -``A_thick`` is the label of the adjective ``thick``, +tree. If you look at this tree, you will notice that ``Item_this_Kind`` +is the label of the rule prefixing ``this`` to a ``Kind``, +thereby forming an ``Item``. +``Kind_wine`` is the label of the kind ``"wine"``, and so on. These labels are formed automatically when the grammar -is compiled by GF. +is compiled by GF, in a way that guarantees that different rules +get different labels. %--! @@ -319,40 +325,29 @@ labels that you provide yourself - these may be more useful than the automatically generated ones. The following is a possible labelling of ``paleolithic.cf`` with nicer-looking labels. ``` - PredVP. S ::= NP VP ; - UseV. VP ::= V ; - ComplTV. VP ::= TV NP ; - UseA. VP ::= "is" A ; - This. NP ::= "this" CN ; - That. NP ::= "that" CN ; - Def. NP ::= "the" CN ; - Indef. NP ::= "a" CN ; - ModA. CN ::= A CN ; - Boy. CN ::= "boy" ; - Louse. CN ::= "louse" ; - Snake. CN ::= "snake" ; - Worm. CN ::= "worm" ; - Green. A ::= "green" ; - Rotten. A ::= "rotten" ; - Thick. A ::= "thick" ; - Warm. A ::= "warm" ; - Laugh. V ::= "laughs" ; - Sleep. V ::= "sleeps" ; - Swim. V ::= "swims" ; - Eat. TV ::= "eats" ; - Kill. TV ::= "kills" - Wash. TV ::= "washes" ; + Is. S ::= Item "is" Quality ; + That. Item ::= "that" Kind ; + This. Item ::= "this" Kind ; + QKind. Kind ::= Quality Kind ; + Cheese. Kind ::= "cheese" ; + Fish. Kind ::= "fish" ; + Wine. Kind ::= "wine" ; + Italian. Quality ::= "Italian" ; + Boring. Quality ::= "boring" ; + Delicious. Quality ::= "delicious" ; + Expensive. Quality ::= "expensive" ; + Fresh. Quality ::= "fresh" ; + Very. Quality ::= "very" Quality ; + Warm. Quality ::= "warm" ; ``` With this grammar, the trees look as follows: ``` - > p "the boy eats a snake" - PredVP (Def Boy) (ComplTV Eat (Indef Snake)) - - > gr -tr | l - PredVP (Indef Louse) (UseA Thick) - a louse is thick + > parse -tr "this delicious cheese is very Italian" | vt + Is (This (QKind Delicious Cheese)) (Very Italian) ``` +[Tree2.png] + %--! ==The ``.gf`` grammar format== @@ -367,14 +362,12 @@ The output is quite unreadable at this stage, and you may feel happy that you did not need to write the grammar in that notation, but that the GF grammar compiler produced it. - - However, we will now start the demonstration how GF's own notation gives you much more expressive power than the ``.cf`` format. We will introduce the ``.gf`` format by presenting one more way of defining the same grammar as in -``paleolithic.cf``. +``food.cf``. Then we will show how the full GF grammar format enables you to do things that are not possible in the weaker formats. @@ -388,27 +381,24 @@ A GF grammar consists of two main parts: - **concrete syntax**, defining how trees are linearized into strings - The EBNF and CF formats fuse these two things together, but it is possible -to take them apart. For instance, the verb phrase predication rule +to take them apart. For instance, the sentence formation rule ``` - PredVP. S ::= NP VP ; + Is. S ::= Item "is" Quality ; ``` is interpreted as the following pair of rules: ``` - fun PredVP : NP -> VP -> S ; - lin PredVP x y = {s = x.s ++ y.s} ; + fun Is : Item -> Quality -> S ; + lin Is item quality = {s = item.s ++ "is" ++ quality.s} ; ``` The former rule, with the keyword ``fun``, belongs to the abstract syntax. It defines the **function** -``PredVP`` which constructs syntax trees of form -(``PredVP`` //x// //y//). - - +``Is`` which constructs syntax trees of form +(``Is`` //item// //quality//). The latter rule, with the keyword ``lin``, belongs to the concrete syntax. It defines the **linearization function** for -syntax trees of form (``PredVP`` //x// //y//). +syntax trees of form (``Is`` //item// //quality//). %--! @@ -498,8 +488,8 @@ denotes the empty token list. %--! ===An abstract syntax example=== -To express the abstract syntax of ``paleolithic.cf`` in -a file ``Paleolithic.gf``, we write two kinds of judgements: +To express the abstract syntax of ``food.cf`` in +a file ``Food.gf``, we write two kinds of judgements: - Each category is introduced by a ``cat`` judgement. - Each rule label is introduced by a ``fun`` judgement, @@ -507,20 +497,18 @@ a file ``Paleolithic.gf``, we write two kinds of judgements: ``` -abstract Paleolithic = { -cat - S ; NP ; VP ; CN ; A ; V ; TV ; -fun - PredVP : NP -> VP -> S ; - UseV : V -> VP ; - ComplTV : TV -> NP -> VP ; - UseA : A -> VP ; - ModA : A -> CN -> CN ; - This, That, Def, Indef : CN -> NP ; - Boy, Louse, Snake, Worm : CN ; - Green, Rotten, Thick, Warm : A ; - Laugh, Sleep, Swim : V ; - Eat, Kill, Wash : TV ; +abstract Food = { + + cat + S ; Item ; Kind ; Quality ; + + fun + Is : Item -> Quality -> S ; + This, That : Kind -> Item ; + QKind : Quality -> Kind -> Kind ; + Wine, Cheese, Fish : Kind ; + Very : Quality -> Quality ; + Fresh, Warm, Italian, Expensive, Delicious, Boring : Quality ; } ``` Notice the use of shorthands permitting the sharing of @@ -531,38 +519,31 @@ in subsequent ``fun`` judgements. %--! ===A concrete syntax example=== -Each category introduced in ``Paleolithic.gf`` is +Each category introduced in ``Food.gf`` is given a ``lincat`` rule, and each function is given a ``lin`` rule. Similar shorthands apply as in ``abstract`` modules. ``` -concrete PaleolithicEng of Paleolithic = { -lincat - S, NP, VP, CN, A, V, TV = {s : Str} ; -lin - PredVP np vp = {s = np.s ++ vp.s} ; - UseV v = v ; - ComplTV tv np = {s = tv.s ++ np.s} ; - UseA a = {s = "is" ++ a.s} ; - This cn = {s = "this" ++ cn.s} ; - That cn = {s = "that" ++ cn.s} ; - Def cn = {s = "the" ++ cn.s} ; - Indef cn = {s = "a" ++ cn.s} ; - ModA a cn = {s = a.s ++ cn.s} ; - Boy = {s = "boy"} ; - Louse = {s = "louse"} ; - Snake = {s = "snake"} ; - Worm = {s = "worm"} ; - Green = {s = "green"} ; - Rotten = {s = "rotten"} ; - Thick = {s = "thick"} ; - Warm = {s = "warm"} ; - Laugh = {s = "laughs"} ; - Sleep = {s = "sleeps"} ; - Swim = {s = "swims"} ; - Eat = {s = "eats"} ; - Kill = {s = "kills"} ; - Wash = {s = "washes"} ; +concrete FoodEng of Food = { + + lincat + S, Item, Kind, Quality = {s : Str} ; + + lin + Is item quality = {s = item.s ++ "is" ++ quality.s} ; + This kind = {s = "this" ++ kind.s} ; + That kind = {s = "that" ++ kind.s} ; + QKind quality kind = {s = quality.s ++ kind.s} ; + Wine = {s = "wine"} ; + Cheese = {s = "cheese"} ; + Fish = {s = "fish"} ; + Very quality = {s = "very" ++ quality.s} ; + Fresh = {s = "fresh"} ; + Warm = {s = "warm"} ; + Italian = {s = "Italian"} ; + Expensive = {s = "expensive"} ; + Delicious = {s = "delicious"} ; + Boring = {s = "boring"} ; } ``` @@ -572,19 +553,15 @@ lin Module name + ``.gf`` = file name - - Each module is compiled into a ``.gfc`` file. - - -Import ``PaleolithicEng.gf`` and try what happens +Import ``FoodEng.gf`` and see what happens ``` - > i PaleolithicEng.gf + > i FoodEng.gf ``` The GF program does not only read the file -``PaleolithicEng.gf``, but also all other files that it -depends on - in this case, ``Paleolithic.gf``. +``FoodEng.gf``, but also all other files that it +depends on - in this case, ``Food.gf``. For each file that is compiled, a ``.gfc`` file is generated. The GFC format (="GF Canonical") is the @@ -604,7 +581,7 @@ A system with this property is called a **multilingual grammar**. Multilingual grammars can be used for applications such as translation. Let us buid an Italian concrete syntax for -``Paleolithic`` and then test the resulting +``Food`` and then test the resulting multilingual grammar. @@ -614,34 +591,29 @@ multilingual grammar. ===An Italian concrete syntax=== ``` -concrete PaleolithicIta of Paleolithic = { -lincat - S, NP, VP, CN, A, V, TV = {s : Str} ; -lin - PredVP np vp = {s = np.s ++ vp.s} ; - UseV v = v ; - ComplTV tv np = {s = tv.s ++ np.s} ; - UseA a = {s = "è" ++ a.s} ; - This cn = {s = "questo" ++ cn.s} ; - That cn = {s = "quello" ++ cn.s} ; - Def cn = {s = "il" ++ cn.s} ; - Indef cn = {s = "un" ++ cn.s} ; - ModA a cn = {s = cn.s ++ a.s} ; - Boy = {s = "ragazzo"} ; - Louse = {s = "pidocchio"} ; - Snake = {s = "serpente"} ; - Worm = {s = "verme"} ; - Green = {s = "verde"} ; - Rotten = {s = "marcio"} ; - Thick = {s = "grosso"} ; - Warm = {s = "caldo"} ; - Laugh = {s = "ride"} ; - Sleep = {s = "dorme"} ; - Swim = {s = "nuota"} ; - Eat = {s = "mangia"} ; - Kill = {s = "uccide"} ; - Wash = {s = "lava"} ; +concrete FoodIta of Food = { + + lincat + S, Item, Kind, Quality = {s : Str} ; + + lin + Is item quality = {s = item.s ++ "è" ++ quality.s} ; + This kind = {s = "questo" ++ kind.s} ; + That kind = {s = "quello" ++ kind.s} ; + QKind quality kind = {s = kind.s ++ quality.s} ; + Wine = {s = "vino"} ; + Cheese = {s = "formaggio"} ; + Fish = {s = "pesce"} ; + Very quality = {s = "molto" ++ quality.s} ; + Fresh = {s = "fresco"} ; + Warm = {s = "caldo"} ; + Italian = {s = "italiano"} ; + Expensive = {s = "caro"} ; + Delicious = {s = "delizioso"} ; + Boring = {s = "noioso"} ; + } + ``` %--! @@ -649,21 +621,21 @@ lin Import the two grammars in the same GF session. ``` - > i PaleolithicEng.gf - > i PaleolithicIta.gf + > i FoodEng.gf + > i FoodIta.gf ``` Try generation now: ``` > gr | l - un pidocchio uccide questo ragazzo + quello formaggio molto noioso è italiano - > gr | l -lang=PaleolithicEng - that louse eats a louse + > gr | l -lang=FoodEng + this fish is warm ``` Translate by using a pipe: ``` - > p -lang=PaleolithicEng "the boy eats the snake" | l -lang=PaleolithicIta - il ragazzo mangia il serpente + > p -lang=FoodEng "this cheese is very delicious" | l -lang=FoodIta + questo formaggio è molto delizioso ``` The ``lang`` flag tells GF which concrete syntax to use in parsing and linearization. By default, the flag is set to the last-imported grammar. @@ -671,12 +643,36 @@ To see what grammars are in scope and which is the main one, use the command ``print_options = po``: ``` > print_options - main abstract : Paleolithic - main concrete : PaleolithicIta - actual concretes : PaleolithicIta PaleolithicEng + main abstract : Food + main concrete : FoodIta + actual concretes : FoodIta FoodEng ``` +%--! +===Translation session=== + +If translation is what you want to do with a set of grammars, a convenient +way to do it is to open a ``translation_session = ts``. In this session, +you can translate between all the languages that are in scope. +A dot ``.`` terminates the translation session. +``` + > ts + + trans> that very warm cheese is boring + quello formaggio molto caldo è noioso + that very warm cheese is boring + + trans> questo vino molto italiano è molto delizioso + questo vino molto italiano è molto delizioso + this very Italian wine is very delicious + + trans> . + > +``` + + + %--! ===Translation quiz=== @@ -686,24 +682,30 @@ random sentences, displays them in one language, and checks the user's answer given in another language. The command ``translation_quiz = tq`` makes this in a subshell of GF. ``` - > translation_quiz PaleolithicEng PaleolithicIta + > translation_quiz FoodEng FoodIta Welcome to GF Translation Quiz. The quiz is over when you have done at least 10 examples with at least 75 % success. You can interrupt the quiz by entering a line consisting of a dot ('.'). - a green boy washes the louse - un ragazzo verde lava il gatto + this fish is warm + questo pesce è caldo + > Yes. + Score 1/1 - No, not un ragazzo verde lava il gatto, but - un ragazzo verde lava il pidocchio - Score 0/1 + this cheese is Italian + questo formaggio è noioso + > No, not questo formaggio è noioso, but + questo formaggio è italiano + + Score 1/2 + this fish is expensive ``` You can also generate a list of translation exercises and save it in a file for later use, by the command ``translation_list = tl`` ``` - > translation_list -number=25 PaleolithicEng PaleolithicIta + > translation_list -number=25 FoodEng FoodIta ``` The ``number`` flag gives the number of sentences generated. @@ -716,24 +718,27 @@ The ``number`` flag gives the number of sentences generated. The module system of GF makes it possible to **extend** a grammar in different ways. The syntax of extension is -shown by the following example. This is how language -was extended when civilization advanced from the -paleolithic to the neolithic age: +shown by the following example. We extend ``Food`` by +adding a category of questions and two new functions. ``` - abstract Neolithic = Paleolithic ** { + abstract Morefood = Food ** { + cat + Question ; fun - Fire, Wheel : CN ; - Think : V ; + QIs : Item -> Quality -> Question ; + Pizza : Kind ; + } ``` Parallel to the abstract syntax, extensions can be built for concrete syntaxes: ``` - concrete NeolithicEng of Neolithic = PaleolithicEng ** { + concrete MorefoodEng of Morefood = FoodEng ** { + lincat + Question = {s : Str} ; lin - Fire = {s = "fire"} ; - Wheel = {s = "wheel"} ; - Think = {s = "thinks"} ; + QIs item quality = {s = "is" ++ item.s ++ quality.s} ; + Pizza = {s = "pizza"} ; } ``` The effect of extension is that all of the contents of the extended @@ -746,14 +751,14 @@ and extending module are put together. Specialized vocabularies can be represented as small grammars that only do "one thing" each. For instance, the following are grammars -for fish names and mushroom names. +for fruit and mushrooms ``` - abstract Fish = { - cat Fish ; - fun Salmon, Perch : Fish ; + abstract Fruit = { + cat Fruit ; + fun Apple, Peach : Fruit ; } - abstract Mushrooms = { + abstract Mushroom = { cat Mushroom ; fun Cep, Agaric : Mushroom ; } @@ -762,20 +767,22 @@ They can afterwards be combined into bigger grammars by using **multiple inheritance**, i.e. extension of several grammars at the same time: ``` - abstract Gatherer = Paleolithic, Fish, Mushrooms ** { + abstract Foodmarket = Food, Fruit, Mushroom ** { fun - FishCN : Fish -> CN ; - MushroomCN : Mushroom -> CN ; + FruitKind : Fruit -> Kind ; + MushroomKind : Mushroom -> Kind ; } ``` - +At this point, you would perhaps like to go back to +``Food`` and take apart ``Wine`` to build a special +``Drink`` module. %--! ===Visualizing module structure=== When you have created all the abstract syntaxes and -one set of concrete syntaxes needed for ``Gatherer``, +one set of concrete syntaxes needed for ``Foodmarket``, your grammar consists of eight GF modules. To see how their dependences look like, you can use the command ``visualize_graph = vg``, @@ -791,7 +798,7 @@ The graph uses - black-headed arrows for inheritance - white-headed arrows for the concrete-of-abstract relation -[Gatherer.gif] +[Foodmarket.png] @@ -799,17 +806,16 @@ The graph uses ==System commands== To document your grammar, you may want to print the -graph into a file, e.g. a ``.gif`` file that +graph into a file, e.g. a ``.png`` file that can be included in an HTML document. You can do this by first printing the graph into a file ``.dot`` and then processing this file with the ``dot`` program. ``` - > pm -printer=graph | wf Gatherer.dot - > ! dot -Tgif Gatherer.dot > Gatherer.gif + > pm -printer=graph | wf Foodmarket.dot + > ! dot -Tpng Foodmarket.dot > Foodmarket.png ``` The latter command is a Unix command, issued from GF by using the -shell escape symbol ``!``. The resulting graph is shown in the next section. - +shell escape symbol ``!``. The resulting graph was shown in the previous section. The command ``print_multi = pm`` is used for printing the current multilingual grammar in various formats, of which the format ``-printer=graph`` just @@ -821,6 +827,7 @@ are available: ``` + %--! ==Resource modules== @@ -908,28 +915,32 @@ Any number of ``resource`` modules can be makes definitions contained in the resource usable in the concrete syntax. Here is an example, where the resource ``StringOper`` is -opened in a new version of ``PaleolithicEng``. +opened in a new version of ``FoodEng``. ``` -concrete PalEng of Paleolithic = open StringOper in { - lincat - S, NP, VP, CN, A, V, TV = SS ; + concrete Food2Eng of Food = open StringOper in { + + lincat + S, Item, Kind, Quality = SS ; + lin - PredVP = cc ; - UseV v = v ; - ComplTV = cc ; - UseA = prefix "is" ; - This = prefix "this" ; - That = prefix "that" ; - Def = prefix "the" ; - Indef = prefix "a" ; - ModA = cc ; - Boy = ss "boy" ; - Louse = ss "louse" ; - Snake = ss "snake" ; - -- etc -} + Is item quality = cc item (prefix "is" quality) ; + This = prefix "this" ; + That = prefix "that" ; + QKind = cc ; + Wine = ss "wine" ; + Cheese = ss "cheese" ; + Fish = ss "fish" ; + Very = prefix "very" ; + Fresh = ss "fresh" ; + Warm = ss "warm" ; + Italian = ss "Italian" ; + Expensive = ss "expensive" ; + Delicious = ss "delicious" ; + Boring = ss "boring" ; + + } ``` -The same string operations could be use to write ``PaleolithicIta`` +The same string operations could be use to write ``FoodIta`` more concisely. @@ -952,13 +963,12 @@ details. ==Morphology== Suppose we want to say, with the vocabulary included in -``Paleolithic.gf``, things like +``Food.gf``, things like ``` - the boy eats two snakes - all boys sleep + all Italian wines are delicious ``` The new grammatical facility we need are the plural forms -of nouns and verbs (//boys, sleep//), as opposed to their +of nouns and verbs (//wines, are//), as opposed to their singular forms. The introduction of plural forms requires two things: @@ -973,9 +983,9 @@ For instance, Italian has also agreement in gender (masculine vs. feminine). We want to express such special features of languages in the concrete syntax while ignoring them in the abstract syntax. -To be able to do all this, we need one new judgement form, -many new expression forms, -and a generalizarion of linearization types +To be able to do all this, we need one new judgement form +and many new expression forms. +We also need to generalize linearization types from strings to more complex types. @@ -987,11 +997,11 @@ using a new form of judgement: ``` param Number = Sg | Pl ; ``` -To express that nouns in English have a linearization +To express that ``Kind`` expressions in English have a linearization depending on number, we replace the linearization type ``{s : Str}`` with a type where the ``s`` field is a **table** depending on number: ``` - lincat CN = {s : Number => Str} ; + lincat Kind = {s : Number => Str} ; ``` The **table type** ``Number => Str`` is in many respects similar to a function type (``Number -> Str``). The main difference is that the @@ -999,18 +1009,18 @@ argument type of a table type must always be a parameter type. This means that the argument-value pairs can be listed in a finite table. The following example shows such a table: ``` - lin Boy = {s = table { - Sg => "boy" ; - Pl => "boys" + lin Cheese = {s = table { + Sg => "cheese" ; + Pl => "cheeses" } } ; ``` The application of a table to a parameter is done by the **selection** operator ``!``. For instance, ``` - Boy.s ! Pl + Cheese.s ! Pl ``` -is a selection, whose value is ``"boys"``. +is a selection, whose value is ``"cheeses"``. %--! @@ -1036,11 +1046,11 @@ The following operation defines the regular noun paradigm of English: } } ; ``` -The **glueing** operator ``+`` tells that +The **gluing** operator ``+`` tells that the string held in the variable ``x`` and the ending ``"s"`` are written together to form one **token**. Thus, for instance, ``` - (regNoun "boy").s ! Pl ---> "boy" + "s" ---> "boys" + (regNoun "cheese").s ! Pl ---> "cheese" + "s" ---> "cheeses" ``` @@ -1048,7 +1058,7 @@ are written together to form one **token**. Thus, for instance, %--! ===Worst-case macros and data abstraction=== -Some English nouns, such as ``louse``, are so irregular that +Some English nouns, such as ``mouse``, are so irregular that it makes no sense to see them as instances of a paradigm. Even then, it is useful to perform **data abstraction** from the definition of the type ``Noun``, and introduce a constructor @@ -1061,9 +1071,9 @@ operation, a **worst-case macro** for nouns: } } ; ``` -Thus we define +Thus we could define ``` - lin Louse = mkNoun "louse" "lice" ; + lin Mouse = mkNoun "mouse" "mice" ; ``` and ``` @@ -1129,7 +1139,7 @@ This definition displays many GF expression forms not shown befores; these forms are explained in the next section. The paradigms ``regNoun`` does not give the correct forms for -all nouns. For instance, //louse - lice// and +all nouns. For instance, //mouse - mice// and //fish - fish// must be given by using ``mkNoun``. Also the word //boy// would be inflected incorrectly; to prevent this, either use ``mkNoun`` or modify @@ -1276,7 +1286,7 @@ means that a noun phrase (functioning as a subject), inherently //has// a number, which it passes to the verb. The verb does not //have// a number, but must be able to receive whatever number the subject has. This distinction is nicely represented by the -different linearization types of noun phrases and verb phrases: +different linearization types of **noun phrases** and **verb phrases**: ``` lincat NP = {s : Str ; n : Number} ; lincat VP = {s : Number => Str} ; @@ -1289,49 +1299,53 @@ the predication structure: ``` lin PredVP np vp = {s = np.s ++ vp.s ! np.n} ; ``` -The following section will present a new version of -``PaleolithingEng``, assuming an abstract syntax -xextended with ``All`` and ``Two``. -It also assumes that ``MorphoEng`` has a paradigm -``regVerb`` for regular verbs (which need only be -regular only in the present tensse). +The following section will present +``FoodsEng``, assuming the abstract syntax ``Foods`` +that is similar to ``Food`` but also has the +plural determiners ``All`` and ``Most``. The reader is invited to inspect the way in which agreement works in -the formation of noun phrases and verb phrases. +the formation of sentences. %--! ===English concrete syntax with parameters=== ``` -concrete PaleolithicEng of Paleolithic = open Prelude, MorphoEng in { -lincat - S, A = SS ; - VP, CN, V, TV = {s : Number => Str} ; - NP = {s : Str ; n : Number} ; -lin - PredVP np vp = ss (np.s ++ vp.s ! np.n) ; - UseV v = v ; - ComplTV tv np = {s = \\n => tv.s ! n ++ np.s} ; - UseA a = {s = \\n => case n of {Sg => "is" ; Pl => "are"} ++ a.s} ; - This = det Sg "this" ; - Indef = det Sg "a" ; - All = det Pl "all" ; - Two = det Pl "two" ; - ModA a cn = {s = \\n => a.s ++ cn.s ! n} ; - Louse = mkNoun "louse" "lice" ; - Snake = regNoun "snake" ; - Green = ss "green" ; - Warm = ss "warm" ; - Laugh = regVerb "laugh" ; - Sleep = regVerb "sleep" ; - Kill = regVerb "kill" ; -oper - det : Number -> Str -> Noun -> {s : Str ; n : Number} = \n,d,cn -> { - s = d ++ n.s ! n ; - n = n - } ; +--# -path=.:prelude + +concrete FoodsEng of Foods = open Prelude, MorphoEng in { + + lincat + S, Quality = SS ; + Kind = {s : Number => Str} ; + Item = {s : Str ; n : Number} ; + + lin + Is item quality = ss (item.s ++ (mkVerb "are" "is").s ! item.n ++ quality.s) ; + This = det Sg "this" ; + That = det Sg "that" ; + All = det Pl "all" ; + Most = det Pl "most" ; + QKind quality kind = {s = \\n => quality.s ++ kind.s ! n} ; + Wine = regNoun "wine" ; + Cheese = regNoun "cheese" ; + Fish = mkNoun "fish" "fish" ; + Very = prefixSS "very" ; + Fresh = ss "fresh" ; + Warm = ss "warm" ; + Italian = ss "Italian" ; + Expensive = ss "expensive" ; + Delicious = ss "delicious" ; + Boring = ss "boring" ; + + oper + det : Number -> Str -> Noun -> {s : Str ; n : Number} = \n,d,cn -> { + s = d ++ cn.s ! n ; + n = n + } ; + } -``` + ``` @@ -1503,6 +1517,31 @@ Product types and tuples are syntactic sugar for record types and records: Thus the labels ``p1, p2,...``` are hard-coded. +%--! +===Prefix-dependent choices=== + +The construct exemplified in +``` + oper artIndef : Str = + pre {"a" ; "an" / strs {"a" ; "e" ; "i" ; "o"}} ; +``` +Thus +``` + artIndef ++ "cheese" ---> "a" ++ "cheese" + artIndef ++ "apple" ---> "an" ++ "cheese" +``` +This very example does not work in all situations: the prefix +//u// has no general rules, and some problematic words are +//euphemism, one-eyed, n-gram//. It is possible to write +``` + oper artIndef : Str = + pre {"a" ; + "a" / strs {"eu" ; "one"} ; + "an" / strs {"a" ; "e" ; "i" ; "o" ; "n-"} + } ; +``` + + ===Predefined types and operations=== diff --git a/doc/tutorial/Fish.gf b/doc/tutorial/old/Fish.gf similarity index 100% rename from doc/tutorial/Fish.gf rename to doc/tutorial/old/Fish.gf diff --git a/doc/tutorial/FishEng.gf b/doc/tutorial/old/FishEng.gf similarity index 100% rename from doc/tutorial/FishEng.gf rename to doc/tutorial/old/FishEng.gf diff --git a/doc/tutorial/Gatherer.gf b/doc/tutorial/old/Gatherer.gf similarity index 100% rename from doc/tutorial/Gatherer.gf rename to doc/tutorial/old/Gatherer.gf diff --git a/doc/tutorial/Gatherer.gif b/doc/tutorial/old/Gatherer.gif similarity index 100% rename from doc/tutorial/Gatherer.gif rename to doc/tutorial/old/Gatherer.gif diff --git a/doc/tutorial/GathererEng.gf b/doc/tutorial/old/GathererEng.gf similarity index 100% rename from doc/tutorial/GathererEng.gf rename to doc/tutorial/old/GathererEng.gf diff --git a/doc/tutorial/Mushrooms.gf b/doc/tutorial/old/Mushrooms.gf similarity index 100% rename from doc/tutorial/Mushrooms.gf rename to doc/tutorial/old/Mushrooms.gf diff --git a/doc/tutorial/MushroomsEng.gf b/doc/tutorial/old/MushroomsEng.gf similarity index 100% rename from doc/tutorial/MushroomsEng.gf rename to doc/tutorial/old/MushroomsEng.gf diff --git a/doc/tutorial/Neolithic.gf b/doc/tutorial/old/Neolithic.gf similarity index 100% rename from doc/tutorial/Neolithic.gf rename to doc/tutorial/old/Neolithic.gf diff --git a/doc/tutorial/NeolithicEng.gf b/doc/tutorial/old/NeolithicEng.gf similarity index 100% rename from doc/tutorial/NeolithicEng.gf rename to doc/tutorial/old/NeolithicEng.gf diff --git a/doc/tutorial/Paleolithic.gf b/doc/tutorial/old/Paleolithic.gf similarity index 100% rename from doc/tutorial/Paleolithic.gf rename to doc/tutorial/old/Paleolithic.gf diff --git a/doc/tutorial/PaleolithicEng.gf b/doc/tutorial/old/PaleolithicEng.gf similarity index 100% rename from doc/tutorial/PaleolithicEng.gf rename to doc/tutorial/old/PaleolithicEng.gf diff --git a/doc/tutorial/PaleolithicIta.gf b/doc/tutorial/old/PaleolithicIta.gf similarity index 100% rename from doc/tutorial/PaleolithicIta.gf rename to doc/tutorial/old/PaleolithicIta.gf diff --git a/doc/tutorial/old/paleolithic.cf b/doc/tutorial/old/paleolithic.cf new file mode 100644 index 000000000..08496c800 --- /dev/null +++ b/doc/tutorial/old/paleolithic.cf @@ -0,0 +1,23 @@ +PredVP. S ::= NP VP ; +UseV. VP ::= V ; +ComplTV. VP ::= TV NP ; +UseA. VP ::= "is" A ; +This. NP ::= "this" CN ; +That. NP ::= "that" CN ; +Def. NP ::= "the" CN ; +Indef. NP ::= "a" CN ; +ModA. CN ::= A CN ; +Boy. CN ::= "boy" ; +Louse. CN ::= "louse" ; +Snake. CN ::= "snake" ; +Worm. CN ::= "worm" ; +Green. A ::= "green" ; +Rotten. A ::= "rotten" ; +Thick. A ::= "thick" ; +Warm. A ::= "warm" ; +Laugh. V ::= "laughs" ; +Sleep. V ::= "sleeps" ; +Swim. V ::= "swims" ; +Eat. TV ::= "eats" ; +Kill. TV ::= "kills" +Wash. TV ::= "washes" ; diff --git a/doc/tutorial/paleolithic.ebnf b/doc/tutorial/old/paleolithic.ebnf similarity index 100% rename from doc/tutorial/paleolithic.ebnf rename to doc/tutorial/old/paleolithic.ebnf diff --git a/doc/tutorial/paleolithic.cf b/doc/tutorial/paleolithic.cf deleted file mode 100644 index 97da4447f..000000000 --- a/doc/tutorial/paleolithic.cf +++ /dev/null @@ -1,8 +0,0 @@ -S ::= NP VP ; -VP ::= V | TV NP | "is" A ; -NP ::= "this" CN | "that" CN | "the" CN | "a" CN ; -CN ::= A CN ; -CN ::= "boy" | "louse" | "snake" | "worm" ; -A ::= "green" | "rotten" | "thick" | "warm" ; -V ::= "laughs" | "sleeps" | "swims" ; -TV ::= "eats" | "kills" | "washes" ;