Merge pull request #122 from billhails/tidy

Tidy
billhails · Oct 20, 2024 · 8404755 · 8404755
2 parents 8ace092 + 7c9d3d6
commit 8404755
Show file tree

Hide file tree

Showing 19 changed files with 35 additions and 69,748 deletions.
diff --git a/Makefile b/Makefile
@@ -51,7 +51,8 @@ EXTRA_TARGETS= \
     $(EXTRA_H_TARGETS) \
     $(EXTRA_OBJTYPES_H_TARGETS) \
     $(EXTRA_DEBUG_H_TARGETS) \
-    $(EXTRA_DEBUG_C_TARGETS)
+    $(EXTRA_DEBUG_C_TARGETS) \
+	generated/UnicodeData.inc
 
 MAIN=src/main.c
 PREAMBLE=generated/preamble.c
@@ -178,8 +179,10 @@ unicode/UnicodeData.csv: unicode/UnicodeData.txt ./tools/convertCsv.py
 	$(PYTHON) ./tools/convertCsv.py
 
 unicode/UnicodeData.txt: | unicode
-	wget https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-	mv UnicodeData.txt $@
+	wget -P unicode https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
+
+generated/UnicodeData.inc: unicode/UnicodeData.txt tools/analyzeCsv.py | generated
+	$(PYTHON) ./tools/analyzeCsv.py > $@
 
 realclean: clean
 	rm -rf tags unicode

diff --git a/README.md b/README.md
@@ -68,10 +68,12 @@ the $step$ function: one to deal with `amb` and one to deal with `back`.
 flowchart TD
 classDef process fill:#aef;
 source(Source) -->
-parser([Parser]):::process -->
-ast(AST) -->
+parser([Parser]):::process
+parser <--> oi([Operator Inlining]):::process
+parser --> ast(AST) -->
 lc([Lambda Conversion]):::process --> tpmc([Pattern Matching Compiler]):::process
 lc <---> pg([Print Function Generator]):::process
+lc <---> me([Macro Expansion]):::process
 tpmc --> vs([Variable Substitution]):::process
 vs --> lc
 lc <--> des([Desugaring]):::process

diff --git a/docs/TODO.md b/docs/TODO.md
@@ -4,14 +4,12 @@ More of a wish-list than a hard and fast plan.
 
 * Over-application i.e. `fn (a) { fn (b) { a + b } }(2, 3)`.
 * Unpacking function return values (tuples only).
-* Error function.
-* Macro support (see [MACROS](./MACROS.md) for initial thoughts).
 * More numbers:
    * NaN.
 * Improve arithmetic.
    * General overhaul.
    * move to [libgmp](https://gmplib.org/)?
-   * trig functions.
+   * trig and log functions.
    * Pre-compute constant values at compile time.
    * allow numeric (not symbolic) arithmetic expressions in patterns.
    * allow unpacking of numerator and denominator variables in patterns.
@@ -25,25 +23,7 @@ More of a wish-list than a hard and fast plan.
    * allow unpacking of the real and imaginary parts of a complex number in patterns.
       * another special case: `a + b`, `b` would be bound to `0i` if the actual
         argument is not complex.
-* Much better error reporting.
-* `--expression="..."` to execute a snippet from the command line.
-* Error recovery.
-* User definable operators.
-   * With precedence and associativity.
-   * `infix 55 left ">>=" fn(l, r) { ... }`
-   * `prefix 45 "$" fn(a) { ... }`
-   * `suffix 60 "!" factorial`
-   * `infix 40 "and" and` - where `and` would have to be a macro.
-   * precedence of prefix and postfix operators matters, i.e. `-2**2` is `-(2**2)` not `(-2)**2`.
-   * looks like this is a biggie and would involve replacing the existing parser (and probably lexer)
-     with a
-     [Pratt Parser](https://journal.stuffwithstuff.com/2011/03/19/pratt-parsers-expression-parsing-made-easy/). 
-     However this may be the right thing to do as it also opens up a much better approach to
-     [macros](https://journal.stuffwithstuff.com/2011/02/13/extending-syntax-from-within-a-language/).
 * Curried binary operators `(2+)` etc.
-* Aliases
-   * `alias some = maybe.some;`
-   * `alias string = list(char);`
 * (internal) have a NEWZ variant of NEW that bzero's its result.
 * Builtins
    * `now()` builtin returns current time in milliseconds.
diff --git a/src/anf.yaml b/src/anf.yaml
@@ -100,7 +100,7 @@ structs:
         next: CexpIntCondCases
 
     CexpCharCondCases:
-        option: char
+        option: character
         body: Exp
         next: CexpCharCondCases
 
@@ -146,15 +146,12 @@ unions:
         intCases: CexpIntCondCases
 
     Aexp:
-        t: void_ptr
-        f: void_ptr
-        v: void_ptr
         lam: AexpLam
         var: HashSymbol
         annotatedVar: AexpAnnotatedVar
         biginteger: MaybeBigInt
         littleinteger: int
-        character: char
+        character: character
         prim: AexpPrimApp
         unary: AexpUnaryApp
         makeVec: AexpMakeVec

diff --git a/src/anf_pp.c b/src/anf_pp.c
@@ -378,15 +378,6 @@ void ppAexp(Aexp *x) {
         case AEXP_TYPE_ANNOTATEDVAR:
             ppAexpAnnotatedVar(x->val.annotatedVar);
             break;
-        case AEXP_TYPE_T:
-            eprintf("#t");
-            break;
-        case AEXP_TYPE_F:
-            eprintf("#f");
-            break;
-        case AEXP_TYPE_V:
-            eprintf("nil");
-            break;
         case AEXP_TYPE_BIGINTEGER:
             fprintMaybeBigInt(errout, x->val.biginteger);
             break;

diff --git a/src/annotate.c b/src/annotate.c
@@ -380,12 +380,9 @@ static CTEnv *annotateAexp(Aexp *x, CTEnv *env) {
         case AEXP_TYPE_ANNOTATEDVAR:
             cant_happen("annotateAexp called on annotated var %s",
                         x->val.annotatedVar->var->name);
-        case AEXP_TYPE_T:
-        case AEXP_TYPE_F:
         case AEXP_TYPE_BIGINTEGER:
         case AEXP_TYPE_LITTLEINTEGER:
         case AEXP_TYPE_CHARACTER:
-        case AEXP_TYPE_V:
             return env;
         case AEXP_TYPE_PRIM:
             return annotateAexpPrimApp(x->val.prim, env);

diff --git a/src/ast.yaml b/src/ast.yaml
@@ -215,7 +215,7 @@ unions:
         unpack: AstUnpack
         unpackStruct: AstUnpackStruct
         number: MaybeBigInt
-        character: char
+        character: character
         tuple: AstArgList
 
     AstExpression:
@@ -227,7 +227,7 @@ unions:
         symbol: HashSymbol
         gensym: HashSymbol
         number: MaybeBigInt
-        character: char
+        character: character
         fun: AstCompositeFunction
         nest: AstNest
         iff: AstIff
@@ -243,10 +243,6 @@ hashes:
         entries: int
 
 arrays:
-    AstCharArray:
-        dimension: 1
-        entries: char
-
     AstNamespaceArray:
         dimension: 1
         entries: AstNamespaceImpl

diff --git a/src/bytecode.c b/src/bytecode.c
@@ -619,18 +619,6 @@ void writeAexp(Aexp *x, ByteCodeArray *b) {
                 writeAexpAnnotatedVar(x->val.annotatedVar, b);
             }
             break;
-        case AEXP_TYPE_T:{
-                addByte(b, BYTECODES_TYPE_TRUE);
-            }
-            break;
-        case AEXP_TYPE_F:{
-                addByte(b, BYTECODES_TYPE_FALSE);
-            }
-            break;
-        case AEXP_TYPE_V:{
-                addByte(b, BYTECODES_TYPE_VOID);
-            }
-            break;
         case AEXP_TYPE_LITTLEINTEGER:{
                 addByte(b, BYTECODES_TYPE_STDINT);
                 addInteger(b, x->val.littleinteger);

diff --git a/src/cekf.c b/src/cekf.c
@@ -229,8 +229,8 @@ void restoreFail(Stack *s, Fail *source) {
     copyAllStackEntries(s, source->S);
 }
 
-CharArray *listToCharArray(Value list) {
-    CharArray *chars = newCharArray();
+CharacterArray *listToCharArray(Value list) {
+    CharacterArray *chars = newCharacterArray();
     int save = PROTECT(chars);
     while (list.val.vec) {
 #ifdef SAFETY_CHECKS
@@ -251,18 +251,18 @@ CharArray *listToCharArray(Value list) {
                 cant_happen("unexpected %s", valueTypeName(character.type));
             }
 #endif
-            pushCharArray(chars, character.val.character);
+            pushCharacterArray(chars, character.val.character);
             list = v->entries[2];
         } else {
             list.val.vec = NULL;
         }
     }
-    pushCharArray(chars, (Character) 0); // null terminated
+    pushCharacterArray(chars, (Character) 0); // null terminated
     UNPROTECT(save);
     return chars;
 }
 
-Value charArrayToList(CharArray *c) {
+Value charArrayToList(CharacterArray *c) {
     Vec *nullByte = newVec(1);
     nullByte->entries[0] = value_Stdint(0); // tag=null
     Value v = value_Vec(nullByte);

diff --git a/src/cekf.h b/src/cekf.h
@@ -63,8 +63,8 @@ void markVec(Vec *x);
 void dumpStack(Stack *stack);
 void dumpFrame(Frame *frame);
 
-CharArray *listToCharArray(Value list);
-Value charArrayToList(CharArray *c);
+CharacterArray *listToCharArray(Value list);
+Value charArrayToList(CharacterArray *c);
 Value makeNull(void);
 Value makePair(Value car, Value cdr);
 

diff --git a/src/cekfs.yaml b/src/cekfs.yaml
@@ -72,7 +72,7 @@ inline:
             rational_imag: Vec
             irrational_imag: double
             complex: Vec
-            character: char
+            character: character
             clo: Clo
             pclo: Clo
             kont: Kont
@@ -86,8 +86,8 @@ inline:
             entries: byte
 
 arrays:
-    CharArray:
-        entries: char
+    CharacterArray:
+        entries: character
 
     ByteArray:
         entries: byte
@@ -136,9 +136,6 @@ enums:
     - BACK
     - LET
     - CALLCC
-    - "TRUE"
-    - "FALSE"
-    - VOID
     - STDINT
     - BIGINT
     - IRRATIONAL

diff --git a/src/debug.c b/src/debug.c
@@ -222,18 +222,6 @@ void dumpByteCode(ByteCodeArray *bca) {
                     eprintf("CALLCC\n");
                 }
                 break;
-            case BYTECODES_TYPE_TRUE:{
-                    eprintf("TRUE\n");
-                }
-                break;
-            case BYTECODES_TYPE_FALSE:{
-                    eprintf("FALSE\n");
-                }
-                break;
-            case BYTECODES_TYPE_VOID:{
-                    eprintf("VOID\n");
-                }
-                break;
             case BYTECODES_TYPE_STDINT_IMAG:{
                     int val = readInteger(bca, &i);
                     eprintf("STDINT_IMAG [%d]\n", val);

diff --git a/src/lambda.yaml b/src/lambda.yaml
@@ -110,7 +110,7 @@ structs:
         next: LamIntCondCases
 
     LamCharCondCases:
-        constant: char
+        constant: character
         body: LamExp
         next: LamCharCondCases
 
@@ -264,7 +264,7 @@ unions:
         cond: LamCond
         amb: LamAmb
         print: LamPrint
-        character: char
+        character: character
         back: void_ptr
         error: void_ptr
         cond_default: void_ptr

diff --git a/src/pratt.yaml b/src/pratt.yaml
@@ -132,7 +132,7 @@ arrays:
         entries: uchar
 
     PrattUnicode:
-        entries: char
+        entries: character
 
 primitives: !include primitives.yaml
 

diff --git a/src/primitives.yaml b/src/primitives.yaml
@@ -66,7 +66,7 @@ bool:
     printf: "%d"
     valued: true
 
-char:
+character:
     cname: Character
     printf: "%lc"
     valued: true

diff --git a/src/step.c b/src/step.c
@@ -1037,27 +1037,6 @@ static void step() {
                 }
                 break;
 
-            case BYTECODES_TYPE_TRUE:{
-                    // push true
-                    DEBUGPRINTF("TRUE\n");
-                    push(vTrue);
-                }
-                break;
-
-            case BYTECODES_TYPE_FALSE:{
-                    // push false
-                    DEBUGPRINTF("FALSE\n");
-                    push(vFalse);
-                }
-                break;
-
-            case BYTECODES_TYPE_VOID:{
-                    // push void
-                    DEBUGPRINTF("VOID\n");
-                    push(vVoid);
-                }
-                break;
-
             case BYTECODES_TYPE_IRRATIONAL:{
                     // push literal Double
                     Double f = readCurrentIrrational();

diff --git a/src/tpmc.yaml b/src/tpmc.yaml
@@ -94,7 +94,7 @@ unions:
         comparison: TpmcComparisonPattern
         assignment: TpmcAssignmentPattern
         wildcard: void_ptr
-        character: char
+        character: character
         biginteger: MaybeBigInt
         constructor: TpmcConstructorPattern
         tuple: TpmcPatternArray