model for resource

This commit is contained in:
aarne
2007-02-28 15:49:13 +00:00
parent b789031396
commit 6248b4a1c7
11 changed files with 798 additions and 0 deletions

8
examples/model/Lex.gf Normal file
View File

@@ -0,0 +1,8 @@
interface Lex = open Grammar in {
oper
even_A : A ;
odd_A : A ;
zero_PN : PN ;
}

8
examples/model/LexEng.gf Normal file
View File

@@ -0,0 +1,8 @@
instance LexEng of Lex = open GrammarEng, ParadigmsEng in {
oper
even_A = regA "even" ;
odd_A = regA "odd" ;
zero_PN = regPN "zero" ;
}

8
examples/model/LexFre.gf Normal file
View File

@@ -0,0 +1,8 @@
instance LexFre of Lex = open GrammarFre, ParadigmsFre in {
oper
even_A = regA "pair" ;
odd_A = regA "impair" ;
zero_PN = regPN "zéro" ;
}

17
examples/model/Makefile Normal file
View File

@@ -0,0 +1,17 @@
all: gf hs run
gf:
echo "pm | wf math.gfcm" | gf MathEng.gf MathFre.gf
hs: gf
echo "pg -printer=haskell | wf GSyntax.hs" | gf math.gfcm
run: hs
ghc --make -o math Run.hs
clean:
rm -f *.gfc *.gfr *.o *.hi
distclean:
rm -f GSyntax.hs math math.gfcm *.gfc *.gfr *.o *.hi

11
examples/model/Math.gf Normal file
View File

@@ -0,0 +1,11 @@
abstract Math = {
cat Prop ; Elem ;
fun
And : Prop -> Prop -> Prop ;
Even : Elem -> Prop ;
Odd : Elem -> Prop ;
Zero : Elem ;
}

View File

@@ -0,0 +1,7 @@
--# -path=.:api:present:prelude:mathematical
concrete MathEng of Math = MathI with
(Grammar = GrammarEng),
(Combinators = CombinatorsEng),
(Predication = PredicationEng),
(Lex = LexEng) ;

View File

@@ -0,0 +1,7 @@
--# -path=.:api:present:prelude:mathematical
concrete MathFre of Math = MathI with
(Grammar = GrammarFre),
(Combinators = CombinatorsFre),
(Predication = PredicationFre),
(Lex = LexFre) ;

16
examples/model/MathI.gf Normal file
View File

@@ -0,0 +1,16 @@
incomplete concrete MathI of Math =
open Grammar, Combinators, Predication, Lex in {
flags startcat = Prop ;
lincat
Prop = S ;
Elem = NP ;
lin
And x y = coord and_Conj x y ;
Even x = PosCl (pred even_A x) ;
Odd x = PosCl (pred odd_A x) ;
Zero = UsePN zero_PN ;
}

33
examples/model/Run.hs Normal file
View File

@@ -0,0 +1,33 @@
module Main where
import GSyntax
import GF.Embed.EmbedAPI
main :: IO ()
main = do
gr <- file2grammar "math.gfcm"
loop gr
loop :: MultiGrammar -> IO ()
loop gr = do
s <- getLine
interpret gr s
loop gr
interpret :: MultiGrammar -> String -> IO ()
interpret gr s = do
let tss = parseAll gr "Prop" s
case (concat tss) of
[] -> putStrLn "no parse"
t:_ -> print $ answer $ fg t
answer :: GProp -> Bool
answer p = case p of
(GOdd x1) -> odd (value x1)
(GEven x1) -> even (value x1)
(GAnd x1 x2) -> answer x1 && answer x2
value :: GElem -> Int
value e = case e of
GZero -> 0

View File

@@ -0,0 +1,382 @@
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML>
<HEAD>
<META NAME="generator" CONTENT="http://txt2tags.sf.net">
<TITLE>A Tutorial on Resource Grammar Applications</TITLE>
</HEAD><BODY BGCOLOR="white" TEXT="black">
<P ALIGN="center"><CENTER><H1>A Tutorial on Resource Grammar Applications</H1>
<FONT SIZE="4">
<I>Aarne Ranta</I><BR>
28 February 2007
</FONT></CENTER>
<P></P>
<HR NOSHADE SIZE=1>
<P></P>
<UL>
<LI><A HREF="#toc1">Writing GF grammars</A>
<UL>
<LI><A HREF="#toc2">Creating the first grammar</A>
<LI><A HREF="#toc3">Testing</A>
<LI><A HREF="#toc4">Adding a new language</A>
<LI><A HREF="#toc5">Extending the language</A>
</UL>
<LI><A HREF="#toc6">Building a user program</A>
<UL>
<LI><A HREF="#toc7">Producing a compiled grammar package</A>
<LI><A HREF="#toc8">Writing the Haskell application</A>
<LI><A HREF="#toc9">Compiling the Haskell grammar</A>
<LI><A HREF="#toc10">Building a distribution</A>
<LI><A HREF="#toc11">Using a Makefile</A>
</UL>
</UL>
<P></P>
<HR NOSHADE SIZE=1>
<P></P>
<P>
In this directory, we have a minimal resource grammar
application whose architecture scales up to much
larger applications. The application is run from the
shell by the command
</P>
<PRE>
math
</PRE>
<P>
whereafter it reads user input in English and French.
To each input line, it answers by the truth value of
the sentence.
</P>
<PRE>
./math
zéro est pair
True
zero is odd
False
zero is even and zero is odd
False
</PRE>
<P>
The source of the application consists of the following
files:
</P>
<PRE>
LexEng.gf -- English instance of Lex
LexFre.gf -- French instance of Lex
Lex.gf -- lexicon interface
Makefile -- a makefile
MathEng.gf -- English instantiation of MathI
MathFre.gf -- French instantiation of MathI
Math.gf -- abstract syntax
MathI.gf -- concrete syntax functor for Math
Run.hs -- Haskell Main module
</PRE>
<P>
The system was built in 22 steps explained below.
</P>
<A NAME="toc1"></A>
<H2>Writing GF grammars</H2>
<A NAME="toc2"></A>
<H3>Creating the first grammar</H3>
<P>
1. Write <CODE>Math.gf</CODE>, which defines what you want to say.
</P>
<PRE>
abstract Math = {
cat Prop ; Elem ;
fun
And : Prop -&gt; Prop -&gt; Prop ;
Even : Elem -&gt; Prop ;
Zero : Elem ;
}
</PRE>
<P>
2. Write <CODE>Lex.gf</CODE>, which defines which language-dependent
parts are needed in the concrete syntax. These are mostly
words (lexicon), but can in fact be any operations. The definitions
only use resource abstract syntax, which is opened.
</P>
<PRE>
interface Lex = open Grammar in {
oper
even_A : A ;
zero_PN : PN ;
}
</PRE>
<P>
3. Write <CODE>LexEng.gf</CODE>, the English implementation of <CODE>Lex.gf</CODE>
This module uses English resource libraries.
</P>
<PRE>
instance LexEng of Lex = open GrammarEng, ParadigmsEng in {
oper
even_A = regA "even" ;
zero_PN = regPN "zero" ;
}
</PRE>
<P>
4. Write <CODE>MathI.gf</CODE>, a language-independent concrete syntax of
<CODE>Math.gf</CODE>. It opens interfaces can resource abstract syntaxes,
which makes it an incomplete module, aka. parametrized module, aka.
functor.
</P>
<PRE>
incomplete concrete MathI of Math =
open Grammar, Combinators, Predication, Lex in {
flags startcat = Prop ;
lincat
Prop = S ;
Elem = NP ;
lin
And x y = coord and_Conj x y ;
Even x = PosCl (pred even_A x) ;
Zero = UsePN zero_PN ;
}
</PRE>
<P>
5. Write <CODE>MathEng.gf</CODE>, which is just an instatiation of <CODE>MathI.gf</CODE>,
replacing the interfaces by their English instances. This is the module
that will be used as a top module in GF, so it contains a path to
the libraries.
</P>
<PRE>
--# -path=.:api:present:prelude:mathematical
concrete MathEng of Math = MathI with
(Grammar = GrammarEng),
(Combinators = CombinatorsEng),
(Predication = PredicationEng),
(Lex = LexEng) ;
</PRE>
<P></P>
<A NAME="toc3"></A>
<H3>Testing</H3>
<P>
6. Test the grammar in GF by random generation and parsing.
</P>
<PRE>
$ gf
&gt; i MathEng.gf
&gt; gr -tr | l -tr | p
And (Even Zero) (Even Zero)
zero is evenand zero is even
And (Even Zero) (Even Zero)
</PRE>
<P>
When importing the grammar, you will fail if you haven't
</P>
<UL>
<LI>correctly defined your <CODE>GF_LIB_PATH</CODE> as <CODE>GF/lib</CODE>
<LI>compiled the resourcec by <CODE>make</CODE> in <CODE>GF/lib/resource-1.0</CODE>
</UL>
<A NAME="toc4"></A>
<H3>Adding a new language</H3>
<P>
7. Now it is time to add a new language. Write a French lexicon <CODE>LexFre.gf</CODE>:
</P>
<PRE>
instance LexFre of Lex = open GrammarFre, ParadigmsFre in {
oper
even_A = regA "pair" ;
zero_PN = regPN "zéro" ;
}
</PRE>
<P>
8. You also need a French concrete syntax, <CODE>MathFre.gf</CODE>:
</P>
<PRE>
--# -path=.:api:present:prelude:mathematical
concrete MathFre of Math = MathI with
(Grammar = GrammarFre),
(Combinators = CombinatorsFre),
(Predication = PredicationFre),
(Lex = LexFre) ;
</PRE>
<P>
9. This time, you can test multilingual generation:
</P>
<PRE>
&gt; i MathFre.gf
&gt; gr -tr | l -multi
Even Zero
zéro est pair
zero is even
</PRE>
<P></P>
<A NAME="toc5"></A>
<H3>Extending the language</H3>
<P>
10. You want to add a predicate saying that a number is odd.
It is first added to <CODE>Math.gf</CODE>:
</P>
<PRE>
fun Odd : Elem -&gt; Prop ;
</PRE>
<P>
11. You need a new word in <CODE>Lex.gf</CODE>.
</P>
<PRE>
oper odd_A : A ;
</PRE>
<P>
12. Then you can give a language-independent concrete syntax in
<CODE>MathI.gf</CODE>:
</P>
<PRE>
lin Odd x = PosCl (pred odd_A x) ;
</PRE>
<P>
13. The new word is implemented in <CODE>LexEng.gf</CODE>.
</P>
<PRE>
oper odd_A = regA "odd" ;
</PRE>
<P>
14. The new word is implemented in <CODE>LexFre.gf</CODE>.
</P>
<PRE>
oper odd_A = regA "impair" ;
</PRE>
<P>
15. Now you can test with the extended lexicon. First empty
the environment to get rid of the old abstract syntax, then
import the new versions of the grammars.
</P>
<PRE>
&gt; e
&gt; i MathEng.gf
&gt; i MathFre.gf
&gt; gr -tr | l -multi
And (Odd Zero) (Even Zero)
zéro est impair et zéro est pair
zero is odd and zero is even
</PRE>
<P></P>
<A NAME="toc6"></A>
<H2>Building a user program</H2>
<A NAME="toc7"></A>
<H3>Producing a compiled grammar package</H3>
<P>
16. Your grammar is going to be used by persons wh<CODE>MathEng.gf</CODE>o do not need
to compile it again. They may not have access to the resource library,
either. Therefore it is advisable to produce a multilingual grammar
package in a single file. We call this package <CODE>math.gfcm</CODE> and
produce it, when we have <CODE>MathEng.gf</CODE> and
<CODE>MathEng.gf</CODE> in the GF state, by the command
</P>
<PRE>
&gt; pm | wf math.gfcm
</PRE>
<P></P>
<A NAME="toc8"></A>
<H3>Writing the Haskell application</H3>
<P>
17. Write the Haskell main file <CODE>Run.hs</CODE>. It uses the <CODE>EmbeddedAPI</CODE>
module defining some basic functionalities such as parsing.
The answer is produced by an interpreter of trees returned by the parser.
</P>
<PRE>
module Main where
import GSyntax
import GF.Embed.EmbedAPI
main :: IO ()
main = do
gr &lt;- file2grammar "math.gfcm"
loop gr
loop :: MultiGrammar -&gt; IO ()
loop gr = do
s &lt;- getLine
interpret gr s
loop gr
interpret :: MultiGrammar -&gt; String -&gt; IO ()
interpret gr s = do
let tss = parseAll gr "Prop" s
case (concat tss) of
[] -&gt; putStrLn "no parse"
t:_ -&gt; print $ answer $ fg t
answer :: GProp -&gt; Bool
answer p = case p of
(GOdd x1) -&gt; odd (value x1)
(GEven x1) -&gt; even (value x1)
(GAnd x1 x2) -&gt; answer x1 &amp;&amp; answer x2
value :: GElem -&gt; Int
value e = case e of
GZero -&gt; 0
</PRE>
<P></P>
<P>
18. The syntax trees manipulated by the interpreter are not raw
GF trees, but objects of the Haskell datatype <CODE>GProp</CODE>.
From any GF grammar, a file <CODE>GFSyntax.hs</CODE> with
datatypes corresponding to its abstract
syntax can be produced by the command
</P>
<PRE>
&gt; pg -printer=haskell | wf GSyntax.hs
</PRE>
<P>
The module also defines the overloaded functions
<CODE>gf</CODE> and <CODE>fg</CODE> for translating from these types to
raw trees and back.
</P>
<A NAME="toc9"></A>
<H3>Compiling the Haskell grammar</H3>
<P>
19. Before compiling <CODE>Run.hs</CODE>, you must check that the
embedded GF modules are found. The easiest way to do this
is by two symbolic links to your GF source directories:
</P>
<PRE>
$ ln -s /home/aarne/GF/src/GF
$ ln -s /home/aarne/GF/src/Transfer/
</PRE>
<P></P>
<P>
20. Now you can run the GHC Haskell compiler to produce the program.
</P>
<PRE>
$ ghc --make -o math Run.hs
</PRE>
<P>
The program can be tested with the command <CODE>./math</CODE>.
</P>
<A NAME="toc10"></A>
<H3>Building a distribution</H3>
<P>
21. For a stand-alone binary-only distribution, only
the two files <CODE>math</CODE> and <CODE>math.gfcm</CODE> are needed.
For a source distribution, the files mentioned in
the beginning of this documents are needed.
</P>
<A NAME="toc11"></A>
<H3>Using a Makefile</H3>
<P>
22. As a part of the source distribution, a <CODE>Makefile</CODE> is
essential. The <CODE>Makefile</CODE> is also useful when developing the
application. It should always be possible to build an executable
from source by typing <CODE>make</CODE>.
</P>
<!-- html code generated by txt2tags 2.3 (http://txt2tags.sf.net) -->
<!-- cmdline: txt2tags -thtml -\-toc model-resource-app.txt -->
</BODY></HTML>

View File

@@ -0,0 +1,301 @@
A Tutorial on Resource Grammar Applications
Aarne Ranta
28 February 2007
In this directory, we have a minimal resource grammar
application whose architecture scales up to much
larger applications. The application is run from the
shell by the command
```
math
```
whereafter it reads user input in English and French.
To each input line, it answers by the truth value of
the sentence.
```
./math
zéro est pair
True
zero is odd
False
zero is even and zero is odd
False
```
The source of the application consists of the following
files:
```
LexEng.gf -- English instance of Lex
LexFre.gf -- French instance of Lex
Lex.gf -- lexicon interface
Makefile -- a makefile
MathEng.gf -- English instantiation of MathI
MathFre.gf -- French instantiation of MathI
Math.gf -- abstract syntax
MathI.gf -- concrete syntax functor for Math
Run.hs -- Haskell Main module
```
The system was built in 22 steps explained below.
==Writing GF grammars==
===Creating the first grammar===
1. Write ``Math.gf``, which defines what you want to say.
```
abstract Math = {
cat Prop ; Elem ;
fun
And : Prop -> Prop -> Prop ;
Even : Elem -> Prop ;
Zero : Elem ;
}
```
2. Write ``Lex.gf``, which defines which language-dependent
parts are needed in the concrete syntax. These are mostly
words (lexicon), but can in fact be any operations. The definitions
only use resource abstract syntax, which is opened.
```
interface Lex = open Grammar in {
oper
even_A : A ;
zero_PN : PN ;
}
```
3. Write ``LexEng.gf``, the English implementation of ``Lex.gf``
This module uses English resource libraries.
```
instance LexEng of Lex = open GrammarEng, ParadigmsEng in {
oper
even_A = regA "even" ;
zero_PN = regPN "zero" ;
}
```
4. Write ``MathI.gf``, a language-independent concrete syntax of
``Math.gf``. It opens interfaces can resource abstract syntaxes,
which makes it an incomplete module, aka. parametrized module, aka.
functor.
```
incomplete concrete MathI of Math =
open Grammar, Combinators, Predication, Lex in {
flags startcat = Prop ;
lincat
Prop = S ;
Elem = NP ;
lin
And x y = coord and_Conj x y ;
Even x = PosCl (pred even_A x) ;
Zero = UsePN zero_PN ;
}
```
5. Write ``MathEng.gf``, which is just an instatiation of ``MathI.gf``,
replacing the interfaces by their English instances. This is the module
that will be used as a top module in GF, so it contains a path to
the libraries.
```
--# -path=.:api:present:prelude:mathematical
concrete MathEng of Math = MathI with
(Grammar = GrammarEng),
(Combinators = CombinatorsEng),
(Predication = PredicationEng),
(Lex = LexEng) ;
```
===Testing===
6. Test the grammar in GF by random generation and parsing.
```
$ gf
> i MathEng.gf
> gr -tr | l -tr | p
And (Even Zero) (Even Zero)
zero is evenand zero is even
And (Even Zero) (Even Zero)
```
When importing the grammar, you will fail if you haven't
- correctly defined your ``GF_LIB_PATH`` as ``GF/lib``
- compiled the resourcec by ``make`` in ``GF/lib/resource-1.0``
===Adding a new language===
7. Now it is time to add a new language. Write a French lexicon ``LexFre.gf``:
```
instance LexFre of Lex = open GrammarFre, ParadigmsFre in {
oper
even_A = regA "pair" ;
zero_PN = regPN "zéro" ;
}
```
8. You also need a French concrete syntax, ``MathFre.gf``:
```
--# -path=.:api:present:prelude:mathematical
concrete MathFre of Math = MathI with
(Grammar = GrammarFre),
(Combinators = CombinatorsFre),
(Predication = PredicationFre),
(Lex = LexFre) ;
```
9. This time, you can test multilingual generation:
```
> i MathFre.gf
> gr -tr | l -multi
Even Zero
zéro est pair
zero is even
```
===Extending the language===
10. You want to add a predicate saying that a number is odd.
It is first added to ``Math.gf``:
```
fun Odd : Elem -> Prop ;
```
11. You need a new word in ``Lex.gf``.
```
oper odd_A : A ;
```
12. Then you can give a language-independent concrete syntax in
``MathI.gf``:
```
lin Odd x = PosCl (pred odd_A x) ;
```
13. The new word is implemented in ``LexEng.gf``.
```
oper odd_A = regA "odd" ;
```
14. The new word is implemented in ``LexFre.gf``.
```
oper odd_A = regA "impair" ;
```
15. Now you can test with the extended lexicon. First empty
the environment to get rid of the old abstract syntax, then
import the new versions of the grammars.
```
> e
> i MathEng.gf
> i MathFre.gf
> gr -tr | l -multi
And (Odd Zero) (Even Zero)
zéro est impair et zéro est pair
zero is odd and zero is even
```
==Building a user program==
===Producing a compiled grammar package===
16. Your grammar is going to be used by persons wh``MathEng.gf``o do not need
to compile it again. They may not have access to the resource library,
either. Therefore it is advisable to produce a multilingual grammar
package in a single file. We call this package ``math.gfcm`` and
produce it, when we have ``MathEng.gf`` and
``MathEng.gf`` in the GF state, by the command
```
> pm | wf math.gfcm
```
===Writing the Haskell application===
17. Write the Haskell main file ``Run.hs``. It uses the ``EmbeddedAPI``
module defining some basic functionalities such as parsing.
The answer is produced by an interpreter of trees returned by the parser.
```
module Main where
import GSyntax
import GF.Embed.EmbedAPI
main :: IO ()
main = do
gr <- file2grammar "math.gfcm"
loop gr
loop :: MultiGrammar -> IO ()
loop gr = do
s <- getLine
interpret gr s
loop gr
interpret :: MultiGrammar -> String -> IO ()
interpret gr s = do
let tss = parseAll gr "Prop" s
case (concat tss) of
[] -> putStrLn "no parse"
t:_ -> print $ answer $ fg t
answer :: GProp -> Bool
answer p = case p of
(GOdd x1) -> odd (value x1)
(GEven x1) -> even (value x1)
(GAnd x1 x2) -> answer x1 && answer x2
value :: GElem -> Int
value e = case e of
GZero -> 0
```
18. The syntax trees manipulated by the interpreter are not raw
GF trees, but objects of the Haskell datatype ``GProp``.
From any GF grammar, a file ``GFSyntax.hs`` with
datatypes corresponding to its abstract
syntax can be produced by the command
```
> pg -printer=haskell | wf GSyntax.hs
```
The module also defines the overloaded functions
``gf`` and ``fg`` for translating from these types to
raw trees and back.
===Compiling the Haskell grammar===
19. Before compiling ``Run.hs``, you must check that the
embedded GF modules are found. The easiest way to do this
is by two symbolic links to your GF source directories:
```
$ ln -s /home/aarne/GF/src/GF
$ ln -s /home/aarne/GF/src/Transfer/
```
20. Now you can run the GHC Haskell compiler to produce the program.
```
$ ghc --make -o math Run.hs
```
The program can be tested with the command ``./math``.
===Building a distribution===
21. For a stand-alone binary-only distribution, only
the two files ``math`` and ``math.gfcm`` are needed.
For a source distribution, the files mentioned in
the beginning of this documents are needed.
===Using a Makefile===
22. As a part of the source distribution, a ``Makefile`` is
essential. The ``Makefile`` is also useful when developing the
application. It should always be possible to build an executable
from source by typing ``make``.