Various cleanups and refactoring

README.md

@@ -30,10 +30,14 @@ The project is under development and subject to change. At this point in time, w
 
 ## How can you contribute?
 
-Obviously firstly any contributions that improve the implementation and/or fix bugs are welcome. I am not keen on language extensions at this stage, but eventually
-we will be extending the language to explore more advanced features.
+The project is educational, with a focus on exploring various compiler algorithms and data structures.
+Clarity and simplicity is preferred over a coding style that attempts to do micro optimizations.
 
-I am also interested in creating implementations of this project in C++, Go, Rust, Swift, D, C, etc. If you are interested in working on such a 
+Contributions that improve the quality of the implementation, add test cases / documentation or fix bugs, are very welcome. 
+I am not keen on language extensions at this stage, but eventually we will be extending the language to explore more 
+advanced features.
+
+I am also interested in porting this project to C++, Go, Rust, Swift, D, C, etc. If you are interested in working on such a 
 port please contact me via [Discussions](https://github.com/orgs/CompilerProgramming/discussions).
 
 ## Community Discussions

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/BasicBlock.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/BasicBlock.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import com.compilerprogramming.ezlang.types.Register;
 

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/BytecodeFunction.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/CompiledFunction.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import com.compilerprogramming.ezlang.exceptions.CompilerException;
 import com.compilerprogramming.ezlang.parser.AST;
@@ -10,7 +10,7 @@
 import java.util.ArrayList;
 import java.util.List;
 
-public class BytecodeFunction {
+public class CompiledFunction {
 
     public BasicBlock entry;
     public BasicBlock exit;
@@ -41,7 +41,7 @@ public class BytecodeFunction {
      */
     private List<Operand> virtualStack = new ArrayList<>();
 
-    public BytecodeFunction(Symbol.FunctionTypeSymbol functionSymbol) {
+    public CompiledFunction(Symbol.FunctionTypeSymbol functionSymbol) {
         AST.FuncDecl funcDecl = (AST.FuncDecl) functionSymbol.functionDecl;
         setVirtualRegisters(funcDecl.scope);
         this.numLocalRegs = this.nextReg; // Before assigning temps

optvm/src/main/java/com/compilerprogramming/ezlang/compiler/Compiler.java

@@ -0,0 +1,45 @@
+package com.compilerprogramming.ezlang.compiler;
+
+import com.compilerprogramming.ezlang.lexer.Lexer;
+import com.compilerprogramming.ezlang.parser.Parser;
+import com.compilerprogramming.ezlang.semantic.SemaAssignTypes;
+import com.compilerprogramming.ezlang.semantic.SemaDefineTypes;
+import com.compilerprogramming.ezlang.types.Symbol;
+import com.compilerprogramming.ezlang.types.Type;
+import com.compilerprogramming.ezlang.types.TypeDictionary;
+
+import java.util.BitSet;
+
+public class Compiler {
+
+    private void compile(TypeDictionary typeDictionary) {
+        for (Symbol symbol: typeDictionary.getLocalSymbols()) {
+            if (symbol instanceof Symbol.FunctionTypeSymbol functionSymbol) {
+                Type.TypeFunction functionType = (Type.TypeFunction) functionSymbol.type;
+                functionType.code = new CompiledFunction(functionSymbol);
+            }
+        }
+    }
+    public TypeDictionary compileSrc(String src) {
+        Parser parser = new Parser();
+        var program = parser.parse(new Lexer(src));
+        var typeDict = new TypeDictionary();
+        var sema = new SemaDefineTypes(typeDict);
+        sema.analyze(program);
+        var sema2 = new SemaAssignTypes(typeDict);
+        sema2.analyze(program);
+        compile(typeDict);
+        return typeDict;
+    }
+    public String dumpIR(TypeDictionary typeDictionary) {
+        StringBuilder sb = new StringBuilder();
+        for (Symbol s: typeDictionary.bindings.values()) {
+            if (s instanceof Symbol.FunctionTypeSymbol f) {
+                var functionBuilder = (CompiledFunction) f.code();
+                BasicBlock.toStr(sb, functionBuilder.entry, new BitSet());
+            }
+        }
+        return sb.toString();
+    }
+
+}

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/DominatorTree.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/DominatorTree.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import java.util.ArrayList;
 import java.util.Comparator;

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/Instruction.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/Instruction.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import com.compilerprogramming.ezlang.types.Register;
 import com.compilerprogramming.ezlang.types.Type;

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/LoopFinder.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/LoopFinder.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import java.util.*;
 import java.util.stream.Collectors;

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/LoopNest.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/LoopNest.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import java.util.*;
 

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/Operand.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/Operand.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import com.compilerprogramming.ezlang.types.Register;
 import com.compilerprogramming.ezlang.types.Type;

optvm/src/main/java/com/compilerprogramming/ezlang/bytecode/SSATransform.java → optvm/src/main/java/com/compilerprogramming/ezlang/compiler/SSATransform.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import com.compilerprogramming.ezlang.types.Register;
 
@@ -9,15 +9,15 @@
  */
 public class SSATransform {
 
-    BytecodeFunction function;
+    CompiledFunction function;
     DominatorTree domTree;
     Register[] globals;
     BBSet[] blockSets;
     List<BasicBlock> blocks;
     int[] counters;
     VersionStack[] stacks;
 
-    public SSATransform(BytecodeFunction bytecodeFunction) {
+    public SSATransform(CompiledFunction bytecodeFunction) {
         this.function = bytecodeFunction;
         setupGlobals();
         computeDomTreeAndDominanceFrontiers();

optvm/src/main/java/com/compilerprogramming/ezlang/interpreter/Interpreter.java

@@ -1,9 +1,9 @@
 package com.compilerprogramming.ezlang.interpreter;
 
-import com.compilerprogramming.ezlang.bytecode.BasicBlock;
-import com.compilerprogramming.ezlang.bytecode.BytecodeFunction;
-import com.compilerprogramming.ezlang.bytecode.Instruction;
-import com.compilerprogramming.ezlang.bytecode.Operand;
+import com.compilerprogramming.ezlang.compiler.BasicBlock;
+import com.compilerprogramming.ezlang.compiler.CompiledFunction;
+import com.compilerprogramming.ezlang.compiler.Instruction;
+import com.compilerprogramming.ezlang.compiler.Operand;
 import com.compilerprogramming.ezlang.exceptions.CompilerException;
 import com.compilerprogramming.ezlang.exceptions.InterpreterException;
 import com.compilerprogramming.ezlang.types.Symbol;
@@ -31,7 +31,7 @@ public Value run(String functionName) {
     }
 
     public Value interpret(ExecutionStack execStack, Frame frame) {
-        BytecodeFunction currentFunction = frame.bytecodeFunction;
+        CompiledFunction currentFunction = frame.bytecodeFunction;
         BasicBlock currentBlock = currentFunction.entry;
         int ip = -1;
         int base = frame.base;
@@ -239,18 +239,18 @@ else if (setFieldInst.sourceOperand instanceof Operand.RegisterOperand registerO
     static class Frame {
         Frame caller;
         int base;
-        BytecodeFunction bytecodeFunction;
+        CompiledFunction bytecodeFunction;
 
         public Frame(Symbol.FunctionTypeSymbol functionSymbol) {
             this.caller = null;
             this.base = 0;
-            this.bytecodeFunction = (BytecodeFunction) functionSymbol.code();
+            this.bytecodeFunction = (CompiledFunction) functionSymbol.code();
         }
 
         Frame(Frame caller, int base, Type.TypeFunction functionType) {
             this.caller = caller;
             this.base = base;
-            this.bytecodeFunction = (BytecodeFunction) functionType.code;
+            this.bytecodeFunction = (CompiledFunction) functionType.code;
         }
     }
 }

optvm/src/test/java/com/compilerprogramming/ezlang/bytecode/TestCompiler.java → optvm/src/test/java/com/compilerprogramming/ezlang/compiler/TestCompiler.java

@@ -1,36 +1,14 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
-import com.compilerprogramming.ezlang.lexer.Lexer;
-import com.compilerprogramming.ezlang.parser.Parser;
-import com.compilerprogramming.ezlang.semantic.SemaAssignTypes;
-import com.compilerprogramming.ezlang.semantic.SemaDefineTypes;
-import com.compilerprogramming.ezlang.types.Symbol;
-import com.compilerprogramming.ezlang.types.TypeDictionary;
 import org.junit.Assert;
 import org.junit.Test;
 
-import java.util.BitSet;
-
 public class TestCompiler {
 
     String compileSrc(String src) {
-        Parser parser = new Parser();
-        var program = parser.parse(new Lexer(src));
-        var typeDict = new TypeDictionary();
-        var sema = new SemaDefineTypes(typeDict);
-        sema.analyze(program);
-        var sema2 = new SemaAssignTypes(typeDict);
-        sema2.analyze(program);
-        var byteCodeCompiler = new BytecodeCompiler();
-        byteCodeCompiler.compile(typeDict);
-        StringBuilder sb = new StringBuilder();
-        for (Symbol s : typeDict.bindings.values()) {
-            if (s instanceof Symbol.FunctionTypeSymbol f) {
-                var functionBuilder = (BytecodeFunction) f.code();
-                BasicBlock.toStr(sb, functionBuilder.entry, new BitSet());
-            }
-        }
-        return sb.toString();
+        var compiler = new Compiler();
+        var typeDict = compiler.compileSrc(src);
+        return compiler.dumpIR(typeDict);
     }
 
     @Test

optvm/src/test/java/com/compilerprogramming/ezlang/bytecode/TestDominators.java → optvm/src/test/java/com/compilerprogramming/ezlang/compiler/TestDominators.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import org.junit.Assert;
 import org.junit.Test;

optvm/src/test/java/com/compilerprogramming/ezlang/bytecode/TestSSATransform.java → optvm/src/test/java/com/compilerprogramming/ezlang/compiler/TestSSATransform.java

@@ -1,11 +1,6 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
-import com.compilerprogramming.ezlang.lexer.Lexer;
-import com.compilerprogramming.ezlang.parser.Parser;
-import com.compilerprogramming.ezlang.semantic.SemaAssignTypes;
-import com.compilerprogramming.ezlang.semantic.SemaDefineTypes;
 import com.compilerprogramming.ezlang.types.Symbol;
-import com.compilerprogramming.ezlang.types.TypeDictionary;
 import org.junit.Assert;
 import org.junit.Test;
 
@@ -14,19 +9,12 @@
 public class TestSSATransform {
 
     String compileSrc(String src) {
-        Parser parser = new Parser();
-        var program = parser.parse(new Lexer(src));
-        var typeDict = new TypeDictionary();
-        var sema = new SemaDefineTypes(typeDict);
-        sema.analyze(program);
-        var sema2 = new SemaAssignTypes(typeDict);
-        sema2.analyze(program);
-        var byteCodeCompiler = new BytecodeCompiler();
-        byteCodeCompiler.compile(typeDict);
+        var compiler = new Compiler();
+        var typeDict = compiler.compileSrc(src);
         StringBuilder sb = new StringBuilder();
         for (Symbol s : typeDict.bindings.values()) {
             if (s instanceof Symbol.FunctionTypeSymbol f) {
-                var functionBuilder = (BytecodeFunction) f.code();
+                var functionBuilder = (CompiledFunction) f.code();
                 sb.append("func ").append(f.name).append("\n");
                 sb.append("Before SSA\n");
                 sb.append("==========\n");

optvm/src/test/java/com/compilerprogramming/ezlang/bytecode/TestInterpreter.java → optvm/src/test/java/com/compilerprogramming/ezlang/interpreter/TestInterpreter.java

@@ -1,38 +1,16 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.interpreter;
 
-import com.compilerprogramming.ezlang.interpreter.Interpreter;
-import com.compilerprogramming.ezlang.interpreter.Value;
-import com.compilerprogramming.ezlang.lexer.Lexer;
-import com.compilerprogramming.ezlang.parser.Parser;
-import com.compilerprogramming.ezlang.semantic.SemaAssignTypes;
-import com.compilerprogramming.ezlang.semantic.SemaDefineTypes;
-import com.compilerprogramming.ezlang.types.Symbol;
-import com.compilerprogramming.ezlang.types.TypeDictionary;
+import com.compilerprogramming.ezlang.compiler.Compiler;
 import org.junit.Assert;
 import org.junit.Test;
 
-import java.util.BitSet;
-
 public class TestInterpreter {
 
     Value compileAndRun(String src, String mainFunction) {
-        Parser parser = new Parser();
-        var program = parser.parse(new Lexer(src));
-        var typeDict = new TypeDictionary();
-        var sema = new SemaDefineTypes(typeDict);
-        sema.analyze(program);
-        var sema2 = new SemaAssignTypes(typeDict);
-        sema2.analyze(program);
-        var byteCodeCompiler = new BytecodeCompiler();
-        byteCodeCompiler.compile(typeDict);
-        StringBuilder sb = new StringBuilder();
-        for (Symbol s : typeDict.bindings.values()) {
-            if (s instanceof Symbol.FunctionTypeSymbol f) {
-                var functionBuilder = (BytecodeFunction) f.code();
-                BasicBlock.toStr(sb, functionBuilder.entry, new BitSet());
-            }
-        }
-        System.out.println(sb.toString());
+        var compiler = new Compiler();
+        var typeDict = compiler.compileSrc(src);
+        var compiled = compiler.dumpIR(typeDict);
+        System.out.println(compiled);
         var interpreter = new Interpreter(typeDict);
         return interpreter.run(mainFunction);
     }

registervm/src/main/java/com/compilerprogramming/ezlang/bytecode/BasicBlock.java → registervm/src/main/java/com/compilerprogramming/ezlang/compiler/BasicBlock.java

@@ -1,4 +1,4 @@
-package com.compilerprogramming.ezlang.bytecode;
+package com.compilerprogramming.ezlang.compiler;
 
 import java.util.ArrayList;
 import java.util.BitSet;
@@ -25,6 +25,7 @@ public void addSuccessor(BasicBlock successor) {
         successors.add(successor);
         successor.predecessors.add(this);
     }
+
     public static StringBuilder toStr(StringBuilder sb, BasicBlock bb, BitSet visited)
     {
         if (visited.get(bb.bid))