taking a new approach using tuples and atoms for compilation, it's working out a lot better

lang/common.go

@@ -0,0 +1,18 @@
+package lang
+
+// Commonly used Terms
+var (
+	// Language structure types
+	AAtom  = Atom("atom")
+	AConst = Atom("const")
+	ATuple = Atom("tup")
+	AList  = Atom("list")
+
+	// Match shortcuts
+	AUnder    = Atom("_")
+	TDblUnder = Tuple{AUnder, AUnder}
+
+	// VM commands
+	AInt = Atom("int")
+	AAdd = Atom("add")
+)

lang/lang.go

@@ -0,0 +1,105 @@
+package lang
+
+import (
+	"fmt"
+	"reflect"
+	"strings"
+)
+
+// Term is a unit of language which carries some meaning. Some Terms are
+// actually comprised of multiple sub-Terms.
+type Term interface {
+	fmt.Stringer // for debugging
+
+	// Type returns a Term which describes the type of this Term, i.e.  the
+	// components this Term is comprised of.
+	Type() Term
+}
+
+// Equal returns whether or not two Terms are of equal value
+func Equal(t1, t2 Term) bool {
+	return reflect.DeepEqual(t1, t2)
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+// Atom is a constant with no other meaning than that it can be equal or not
+// equal to another Atom.
+type Atom string
+
+func (a Atom) String() string {
+	return string(a)
+}
+
+// Type implements the method for Term
+func (a Atom) Type() Term {
+	return Atom("atom")
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+// Const is a constant whose meaning depends on the context in which it is used
+type Const string
+
+func (a Const) String() string {
+	return string(a)
+}
+
+// Type implements the method for Term
+func (a Const) Type() Term {
+	return Const("const")
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+// Tuple is a compound Term of zero or more sub-Terms, each of which may have a
+// different Type. Both the length of the Tuple and the Type of each of it's
+// sub-Terms are components in the Tuple's Type.
+type Tuple []Term
+
+func (t Tuple) String() string {
+	ss := make([]string, len(t))
+	for i := range t {
+		ss[i] = t[i].String()
+	}
+	return "(" + strings.Join(ss, " ") + ")"
+}
+
+// Type implements the method for Term
+func (t Tuple) Type() Term {
+	tt := make(Tuple, len(t))
+	for i := range t {
+		tt[i] = t[i].Type()
+	}
+	return Tuple{Atom("tup"), tt}
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+type list struct {
+	typ Term
+	ll  []Term
+}
+
+// List is a compound Term of zero or more sub-Terms, each of which must have
+// the same Type (the one given as the first argument to this function). Only
+// the Type of the sub-Terms is a component in the List's Type.
+func List(typ Term, elems ...Term) Term {
+	return list{
+		typ: typ,
+		ll:  elems,
+	}
+}
+
+func (l list) String() string {
+	ss := make([]string, len(l.ll))
+	for i := range l.ll {
+		ss[i] = l.ll[i].String()
+	}
+	return "[" + strings.Join(ss, " ") + "]"
+}
+
+// Type implements the method for Term
+func (l list) Type() Term {
+	return Tuple{Atom("list"), l.typ}
+}

lang/match.go

@@ -0,0 +1,54 @@
+package lang
+
+import "fmt"
+
+// Match is used to pattern match an arbitrary Term against a pattern. A pattern
+// is a 2-tuple of the type (as an atom, e.g. AAtom, AConst) and a matching
+// value.
+//
+// If the value is AUnder the pattern will match all Terms of the type,
+// regardless of their value. If the pattern's type and value are both AUnder
+// the pattern will match all Terms.
+//
+// If the pattern's value is a Tuple or a List, each of its values will be used
+// as a sub-pattern to match against the corresponding value in the value.
+func Match(pat Tuple, t Term) bool {
+	if len(pat) != 2 {
+		return false
+	}
+	pt, pv := pat[0], pat[1]
+
+	switch pt {
+	case AAtom:
+		a, ok := t.(Atom)
+		return ok && (Equal(pv, AUnder) || Equal(pv, a))
+	case AConst:
+		c, ok := t.(Const)
+		return ok && (Equal(pv, AUnder) || Equal(pv, c))
+	case ATuple:
+		tt, ok := t.(Tuple)
+		if !ok {
+			return false
+		} else if Equal(pv, AUnder) {
+			return true
+		}
+
+		pvt := pv.(Tuple)
+		if len(tt) != len(pvt) {
+			return false
+		}
+		for i := range tt {
+			pvti, ok := pvt[i].(Tuple)
+			if !ok || !Match(pvti, tt[i]) {
+				return false
+			}
+		}
+		return true
+	case AList:
+		panic("TODO")
+	case AUnder:
+		return true
+	default:
+		panic(fmt.Sprintf("unknown type %T", pt))
+	}
+}

lang/match_test.go

@@ -0,0 +1,66 @@
+package lang
+
+import (
+	. "testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestMatch(t *T) {
+	pat := func(typ, val Term) Tuple {
+		return Tuple{typ, val}
+	}
+
+	tests := []struct {
+		pattern Tuple
+		t       Term
+		exp     bool
+	}{
+		{pat(AAtom, Atom("foo")), Atom("foo"), true},
+		{pat(AAtom, Atom("foo")), Atom("bar"), false},
+		{pat(AAtom, Atom("foo")), Const("foo"), false},
+		{pat(AAtom, Atom("foo")), Tuple{Atom("a"), Atom("b")}, false},
+		{pat(AAtom, Atom("_")), Atom("bar"), true},
+		{pat(AAtom, Atom("_")), Const("bar"), false},
+
+		{pat(AConst, Const("foo")), Const("foo"), true},
+		{pat(AConst, Const("foo")), Atom("foo"), false},
+		{pat(AConst, Const("foo")), Const("bar"), false},
+		{pat(AConst, Atom("_")), Const("bar"), true},
+		{pat(AConst, Atom("_")), Atom("foo"), false},
+
+		{
+			pat(ATuple, Tuple{
+				pat(AAtom, Atom("foo")),
+				pat(AAtom, Atom("bar")),
+			}),
+			Tuple{Atom("foo"), Atom("bar")},
+			true,
+		},
+		{
+			pat(ATuple, Tuple{
+				pat(AAtom, Atom("_")),
+				pat(AAtom, Atom("bar")),
+			}),
+			Tuple{Atom("foo"), Atom("bar")},
+			true,
+		},
+		{
+			pat(ATuple, Tuple{
+				pat(AAtom, Atom("_")),
+				pat(AAtom, Atom("_")),
+				pat(AAtom, Atom("_")),
+			}),
+			Tuple{Atom("foo"), Atom("bar")},
+			false,
+		},
+
+		{pat(AUnder, AUnder), Atom("foo"), true},
+		{pat(AUnder, AUnder), Const("foo"), true},
+		{pat(AUnder, AUnder), Tuple{Atom("a"), Atom("b")}, true},
+	}
+
+	for _, testCase := range tests {
+		assert.Equal(t, testCase.exp, Match(testCase.pattern, testCase.t), "%#v", testCase)
+	}
+}

main.go

@@ -2,13 +2,30 @@ package main
 
 import (
 	"fmt"
-	"log"
 
-	"github.com/mediocregopher/ginger/expr"
+	"github.com/mediocregopher/ginger/lang"
-
+	"github.com/mediocregopher/ginger/vm"
-	"llvm.org/llvm/bindings/go/llvm"
 )
 
+func main() {
+	t := lang.Tuple{lang.AAdd, lang.Tuple{
+		lang.Tuple{lang.AInt, lang.Const("1")},
+		lang.Tuple{lang.AInt, lang.Const("2")},
+	}}
+
+	mod, err := vm.Build(t)
+	if err != nil {
+		panic(err)
+	}
+	defer mod.Dispose()
+
+	mod.Dump()
+
+	out, err := mod.Run()
+	fmt.Printf("\n\n########\nout: %v %v\n", out, err)
+}
+
+/*
 func main() {
 	//ee, err := expr.Parse(os.Stdin)
 	//if err != nil {
@@ -73,3 +90,4 @@ func main() {
 	funcResult := engine.RunFunction(bctx.M.NamedFunction("main"), []llvm.GenericValue{})
 	fmt.Printf("\nOUTPUT:\n%d\n", funcResult.Int(false))
 }
+*/

vm/vm.go

@@ -0,0 +1,154 @@
+package vm
+
+import (
+	"fmt"
+	"strconv"
+	"sync"
+
+	"github.com/mediocregopher/ginger/lang"
+
+	"llvm.org/llvm/bindings/go/llvm"
+)
+
+// Val holds onto a value which has been created within the VM
+type Val struct {
+	v llvm.Value
+}
+
+// Module contains a compiled set of code which can be run, dumped in IR form,
+// or compiled. A Module should be Dispose()'d of once it's no longer being
+// used.
+type Module struct {
+	b      llvm.Builder
+	m      llvm.Module
+	mainFn llvm.Value
+}
+
+var initOnce sync.Once
+
+// Build creates a new Module by compiling the given Term as code
+func Build(t lang.Term) (*Module, error) {
+	initOnce.Do(func() {
+		llvm.LinkInMCJIT()
+		llvm.InitializeNativeTarget()
+		llvm.InitializeNativeAsmPrinter()
+	})
+	mod := &Module{
+		b: llvm.NewBuilder(),
+		m: llvm.NewModule(""),
+	}
+
+	// TODO figure out types
+	mod.mainFn = llvm.AddFunction(mod.m, "", llvm.FunctionType(llvm.Int64Type(), []llvm.Type{}, false))
+	block := llvm.AddBasicBlock(mod.mainFn, "")
+	mod.b.SetInsertPoint(block, block.FirstInstruction())
+
+	out, err := mod.build(t)
+	if err != nil {
+		mod.Dispose()
+		return nil, err
+	}
+	mod.b.CreateRet(out.v)
+
+	if err := llvm.VerifyModule(mod.m, llvm.ReturnStatusAction); err != nil {
+		mod.Dispose()
+		return nil, fmt.Errorf("could not verify module: %s", err)
+	}
+
+	return mod, nil
+}
+
+// Dispose cleans up all resources held by the Module
+func (mod *Module) Dispose() {
+	// TODO this panics for some reason...
+	//mod.m.Dispose()
+	//mod.b.Dispose()
+}
+
+func (mod *Module) build(t lang.Term) (Val, error) {
+	aPat := func(a lang.Atom) lang.Tuple {
+		return lang.Tuple{lang.AAtom, a}
+	}
+	cPat := func(t lang.Term) lang.Tuple {
+		return lang.Tuple{lang.AConst, t}
+	}
+	tPat := func(el ...lang.Term) lang.Tuple {
+		return lang.Tuple{lang.ATuple, lang.Tuple(el)}
+	}
+	match := func(a lang.Atom, b lang.Tuple) bool {
+		return lang.Match(tPat(aPat(a), b), t)
+	}
+
+	switch {
+	// (int 42)
+	case match(lang.AInt, cPat(lang.AUnder)):
+		con := t.(lang.Tuple)[1].(lang.Const)
+		coni, err := strconv.ParseInt(string(con), 10, 64)
+		if err != nil {
+			return Val{}, err
+		}
+		return Val{
+			// TODO why does this have to be cast?
+			v: llvm.ConstInt(llvm.Int64Type(), uint64(coni), false),
+		}, nil
+
+	// (tup ((atom foo) (const 10)))
+	case match(lang.ATuple, lang.Tuple{lang.ATuple, lang.AUnder}):
+		tup := t.(lang.Tuple)[1].(lang.Tuple)
+		// if the tuple is empty then it is a void
+		if len(tup) == 0 {
+			return Val{v: llvm.Undef(llvm.VoidType())}, nil
+		}
+
+		var err error
+		vals := make([]Val, len(tup))
+		typs := make([]llvm.Type, len(tup))
+		for i := range tup {
+			if vals[i], err = mod.build(tup[i]); err != nil {
+				return Val{}, err
+			}
+			typs[i] = vals[i].v.Type()
+		}
+
+		str := llvm.Undef(llvm.StructType(typs, false))
+		for i := range vals {
+			str = mod.b.CreateInsertValue(str, vals[i].v, i, "")
+		}
+		return Val{v: str}, nil
+
+	// (add ((const 5) (var foo)))
+	case match(lang.AAdd, tPat(lang.TDblUnder, lang.TDblUnder)):
+		tup := t.(lang.Tuple)[1].(lang.Tuple)
+		v1, err := mod.build(tup[0])
+		if err != nil {
+			return Val{}, err
+		}
+		v2, err := mod.build(tup[1])
+		if err != nil {
+			return Val{}, err
+		}
+		return Val{v: mod.b.CreateAdd(v1.v, v2.v, "")}, nil
+
+	default:
+		return Val{}, fmt.Errorf("unknown compiler command %v", t)
+	}
+}
+
+// Dump dumps the Module's IR to stdout
+func (mod *Module) Dump() {
+	mod.m.Dump()
+}
+
+// Run executes the Module
+// TODO input and output?
+func (mod *Module) Run() (interface{}, error) {
+	engine, err := llvm.NewExecutionEngine(mod.m)
+	if err != nil {
+		return nil, err
+	}
+	defer engine.Dispose()
+
+	funcResult := engine.RunFunction(mod.mainFn, []llvm.GenericValue{})
+	defer funcResult.Dispose()
+	return funcResult.Int(false), nil
+}