diff options
Diffstat (limited to 'src')
22 files changed, 1371 insertions, 62 deletions
diff --git a/src/main/java/com/seaofnodes/simple/GraphEvaluator.java b/src/main/java/com/seaofnodes/simple/GraphEvaluator.java new file mode 100644 index 00000000..f5694a78 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/GraphEvaluator.java @@ -0,0 +1,181 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.Arrays; +import java.util.BitSet; +import java.util.HashMap; + +public class GraphEvaluator { + + public enum ResultType { VALUE, FALLTHROUGH, TIMEOUT } + + public record Result(ResultType type, long value) {} + + /** + * Find the start node from some node in the graph or null if there is no start node + */ + private static StartNode findStart(BitSet visit, Node node) { + if (node == null) return null; + if (node instanceof StartNode start) return start; + if( visit.get(node._nid) ) return null; + visit.set(node._nid); + for( Node def : node._inputs ) { + var res = findStart(visit,def); + if( res != null ) return res; + } + for( Node use : node._outputs ) { + var res = findStart(visit,use); + if( res != null ) return res; + } + return null; + } + + /** + * Find the control output from a control node + */ + private static Node findControl(Node control) { + for( Node use : control._outputs ) { + if (use.isCFG()) return use; + } + return null; + } + + /** + * Find the projection for a node + */ + private static ProjNode findProjection(Node node, int idx) { + for( Node use : node._outputs ) { + if (use instanceof ProjNode proj && proj._idx == idx) return proj; + } + return null; + } + + /** + * Cache values for phi and parameter projection nodes. + */ + private final HashMap<Node, Long> cacheValues = new HashMap<>(); + /** + * Cache for loop phis as they can depend on itself or other loop phis + */ + private long[] loopPhiCache = new long[16]; + + private GraphEvaluator() { + } + + private long div(DivNode div) { + long in2 = getValue(div.in(2)); + return in2 == 0 ? 0 : getValue(div.in(1)) / in2; + } + + /** + * Calculate the value of a node + */ + private long getValue(Node node) { + var cache = cacheValues.get(node); + if (cache != null) return cache; + return switch (node) { + case ConstantNode cons -> ((TypeInteger)cons.compute()).value(); + case AddNode add -> getValue(add.in(1)) + getValue(add.in(2)); + case BoolNode.EQ eq -> getValue(eq.in(1)) == getValue(eq.in(2)) ? 1 : 0; + case BoolNode.LE le -> getValue(le.in(1)) <= getValue(le.in(2)) ? 1 : 0; + case BoolNode.LT lt -> getValue(lt.in(1)) < getValue(lt.in(2)) ? 1 : 0; + case DivNode div -> div(div); + case MinusNode minus -> -getValue(minus.in(1)); + case MulNode mul -> getValue(mul.in(1)) * getValue(mul.in(2)); + case NotNode not -> getValue(not.in(1)) == 0 ? 1 : 0; + case SubNode sub -> getValue(sub.in(1)) - getValue(sub.in(2)); + default -> throw Utils.TODO("Unexpected node " + node); + }; + } + + /** + * Special case of latchPhis when phis can depend on phis of the same region. + */ + private void latchLoopPhis(RegionNode region, Node prev) { + int idx = Utils.find(region._inputs, prev); + assert idx > 0; + int i = 0; + for( Node use : region._outputs ) { + if (use instanceof PhiNode phi) { + var value = getValue(phi.in(idx)); + if (i == loopPhiCache.length) loopPhiCache = Arrays.copyOf(loopPhiCache, loopPhiCache.length*2); + loopPhiCache[i++] = value; + } + } + i = 0; + for( Node use : region._outputs ) { + if (use instanceof PhiNode phi) cacheValues.put(phi, loopPhiCache[i++]); + } + } + + /** + * Calculate the values of phis of the region and caches the values. The phis are not allowed to depend on other phis of the region. + */ + private void latchPhis(RegionNode region, Node prev) { + int idx = Utils.find(region._inputs, prev); + assert idx > 0; + for( Node use : region._outputs ) { + if (use instanceof PhiNode phi) { + var value = getValue(phi.in(idx)); + cacheValues.put(phi, value); + } + } + } + + /** + * Run the graph until either a return is found or the number of loop iterations are done. + */ + private Result evaluate(StartNode start, long parameter, int loops) { + var parameter1 = findProjection(start, 1); + if (parameter1 != null) cacheValues.put(parameter1, parameter); + Node control = findProjection(start, 0); + Node prev = start; + while (control != null) { + Node next; + switch (control) { + case RegionNode region -> { + if (region instanceof LoopNode && region.in(1) != prev) { + if (loops--<=0) return new Result(ResultType.TIMEOUT, 0); + latchLoopPhis(region, prev); + } else { + latchPhis(region, prev); + } + next = findControl(region); + } + case IfNode cond -> next = findProjection(cond, getValue(cond.in(1)) != 0 ? 0 : 1); + case ReturnNode ret -> { + return new Result(ResultType.VALUE, getValue(ret.in(1))); + } + case ProjNode ignored -> next = findControl(control); + default -> throw Utils.TODO("Unexpected control node " + control); + } + prev = control; + control = next; + } + return new Result(ResultType.FALLTHROUGH, 0); + } + + public static long evaluate(Node graph) { + return evaluate(graph, 0); + } + + public static long evaluate(Node graph, long parameter) { + return evaluate(graph, parameter, 1000); + } + + public static long evaluate(Node graph, long parameter, int loops) { + var res = evaluateWithResult(graph, parameter, loops); + if (res.type==ResultType.TIMEOUT) throw new RuntimeException("Timeout"); + return res.value; + } + + public static Result evaluateWithResult(Node graph, long parameter, int loops) { + var start = findStart(new BitSet(), graph); + if (start == null) return new Result(ResultType.TIMEOUT, 0); + var evaluator = new GraphEvaluator(); + return evaluator.evaluate(start, parameter, loops); + } + +} diff --git a/src/main/java/com/seaofnodes/simple/GraphVisualizer.java b/src/main/java/com/seaofnodes/simple/GraphVisualizer.java index 07f1af21..d75e5bea 100644 --- a/src/main/java/com/seaofnodes/simple/GraphVisualizer.java +++ b/src/main/java/com/seaofnodes/simple/GraphVisualizer.java @@ -26,7 +26,7 @@ public class GraphVisualizer { // nodes in the graph. Collection<Node> all = findAll(parser); StringBuilder sb = new StringBuilder(); - sb.append("digraph chapter07 {\n"); + sb.append("digraph chapter08 {\n"); sb.append("/*\n"); sb.append(parser.src()); sb.append("\n*/\n"); @@ -212,6 +212,8 @@ public class GraphVisualizer { for( String name : syms.keySet() ) { int idx = syms.get(name); Node def = scope.in(idx); + while( def instanceof ScopeNode lazy ) + def = lazy.in(idx); if( def==null ) continue; sb.append("\t") .append(scopeName).append(":") diff --git a/src/main/java/com/seaofnodes/simple/Parser.java b/src/main/java/com/seaofnodes/simple/Parser.java index cfb4deb4..69796828 100644 --- a/src/main/java/com/seaofnodes/simple/Parser.java +++ b/src/main/java/com/seaofnodes/simple/Parser.java @@ -46,6 +46,8 @@ public class Parser { * List of keywords disallowed as identifiers */ private final HashSet<String> KEYWORDS = new HashSet<>(){{ + add("break"); + add("continue"); add("else"); add("false"); add("if"); @@ -62,10 +64,14 @@ public class Parser { */ public final Stack<ScopeNode> _xScopes = new Stack<>(); + ScopeNode _continueScope; + ScopeNode _breakScope; + public Parser(String source, TypeInteger arg) { Node.reset(); _lexer = new Lexer(source); _scope = new ScopeNode(); + _continueScope = _breakScope = null; START = new StartNode(new Type[]{ Type.CONTROL, arg }); STOP = new StopNode(); } @@ -136,6 +142,8 @@ public class Parser { else if (match ("{" )) return require(parseBlock(),"}"); else if (matchx("if" )) return parseIf(); else if (matchx("while")) return parseWhile(); + else if (matchx("break")) return parseBreak(); + else if (matchx("continue")) return parseContinue(); else if (matchx("#showGraph")) return require(showGraph(),";"); else if (matchx(";")) return null; // Empty statement else return parseExpressionStatement(); @@ -150,6 +158,10 @@ public class Parser { * @return a {@link Node}, never {@code null} */ private Node parseWhile() { + + var savedContinueScope = _continueScope; + var savedBreakScope = _breakScope; + require("("); // Loop region has two control inputs, the first is the entry @@ -179,36 +191,71 @@ public class Parser { ifNode.unkeep(); Node ifF = new ProjNode(ifNode, 1, "False").peephole(); - // Clone the body Scope to create the exit Scope - // which accounts for any side effects in the predicate - // The exit Scope will be the final scope after the loop, - // And its control input is the False branch of the loop predicate - // Note that body Scope is still our current scope - var exit = _scope.dup(); - _xScopes.push(exit); - exit.ctrl(ifF); + // Clone the body Scope to create the break/exit Scope which accounts for any + // side effects in the predicate. The break/exit Scope will be the final + // scope after the loop, and its control input is the False branch of + // the loop predicate. Note that body Scope is still our current scope. + ctrl(ifF); + _xScopes.push(_breakScope = _scope.dup()); + + // No continues yet + _continueScope = null; // Parse the true side, which corresponds to loop body // Our current scope is the body Scope ctrl(ifT); // set ctrl token to ifTrue projection parseStatement(); // Parse loop body - // The true branch loops back, so whatever is current control (_scope.ctrl) gets - // added to head loop as input. endLoop() updates the head scope, - // and goes through all the phis that were created earlier. For each - // phi, it sets the second input to the corresponding input from the back edge. - // If the phi is redundant, it is replaced by its sole input. + // Merge the loop bottom into other continue statements + if (_continueScope != null) { + _continueScope = jumpTo(_continueScope); + _scope.kill(); + _scope = _continueScope; + } + + // The true branch loops back, so whatever is current _scope.ctrl gets + // added to head loop as input. endLoop() updates the head scope, and + // goes through all the phis that were created earlier. For each phi, + // it sets the second input to the corresponding input from the back + // edge. If the phi is redundant, it is replaced by its sole input. + var exit = _breakScope; head.endLoop(_scope, exit); head.unkeep().kill(); _xScopes.pop(); // Cleanup _xScopes.pop(); // Cleanup + _continueScope = savedContinueScope; + _breakScope = savedBreakScope; + // At exit the false control is the current control, and // the scope is the exit scope after the exit test. - return (_scope = exit); + return _scope = exit; + } + + private ScopeNode jumpTo(ScopeNode toScope) { + ScopeNode cur = _scope.dup(); + ctrl(new ConstantNode(Type.XCONTROL).peephole()); // Kill current scope + // Prune nested lexical scopes that have depth > than the loop head + // We use _breakScope as a proxy for the loop head scope to obtain the depth + while( cur._scopes.size() > _breakScope._scopes.size() ) + cur.pop(); + // If this is a continue then first time the target is null + // So we just use the pruned current scope as the base for the + // continue + if (toScope == null) + return cur; + // toScope is either the break scope, or a scope that was created here + assert toScope._scopes.size() <= _breakScope._scopes.size(); + toScope.mergeScopes(cur); + return toScope; } + private void checkLoopActive() { if (_breakScope == null) throw Parser.error("No active loop for a break or continue"); } + + private Node parseBreak () { checkLoopActive(); return ( _breakScope = require(jumpTo( _breakScope ),";")); } + private Node parseContinue() { checkLoopActive(); return (_continueScope = require(jumpTo( _continueScope ),";")); } + /** * Parses a statement * diff --git a/src/main/java/com/seaofnodes/simple/node/AddNode.java b/src/main/java/com/seaofnodes/simple/node/AddNode.java index 8f3e5a98..84a368fd 100644 --- a/src/main/java/com/seaofnodes/simple/node/AddNode.java +++ b/src/main/java/com/seaofnodes/simple/node/AddNode.java @@ -70,6 +70,11 @@ public class AddNode extends Node { // Now we only see (add add non) + // Dead data cycle; comes about from dead infinite loops. Do nothing, + // the loop will peep as dead after a bit. + if( lhs.in(1) == lhs ) + return null; + // Do we have (x + con1) + con2? // Replace with (x + (con1+con2) which then fold the constants if( lhs.in(2)._type.isConstant() && t2.isConstant() ) diff --git a/src/main/java/com/seaofnodes/simple/node/IfNode.java b/src/main/java/com/seaofnodes/simple/node/IfNode.java index 0f414c08..23a8fafc 100644 --- a/src/main/java/com/seaofnodes/simple/node/IfNode.java +++ b/src/main/java/com/seaofnodes/simple/node/IfNode.java @@ -46,7 +46,7 @@ public class IfNode extends MultiNode { return prior instanceof ProjNode proj // Repeated test, dominated on one side. Test result is the same. ? (proj._idx==0 ? TypeTuple.IF_TRUE : TypeTuple.IF_FALSE) - : null; // Repeated test not dominated on one side + : dom._type; // Repeated test not dominated on one side return TypeTuple.IF_BOTH; } diff --git a/src/main/java/com/seaofnodes/simple/node/LoopNode.java b/src/main/java/com/seaofnodes/simple/node/LoopNode.java index 81f707ec..c192bc20 100644 --- a/src/main/java/com/seaofnodes/simple/node/LoopNode.java +++ b/src/main/java/com/seaofnodes/simple/node/LoopNode.java @@ -16,7 +16,8 @@ public class LoopNode extends RegionNode { @Override public Type compute() { - return inProgress() ? Type.CONTROL : super.compute(); + if( inProgress() ) return Type.CONTROL; + return entry()._type; } @Override diff --git a/src/main/java/com/seaofnodes/simple/node/Node.java b/src/main/java/com/seaofnodes/simple/node/Node.java index 5759a065..234930b4 100644 --- a/src/main/java/com/seaofnodes/simple/node/Node.java +++ b/src/main/java/com/seaofnodes/simple/node/Node.java @@ -1,5 +1,6 @@ package com.seaofnodes.simple.node; +import com.seaofnodes.simple.IRPrinter; import com.seaofnodes.simple.Utils; import com.seaofnodes.simple.type.Type; @@ -100,6 +101,7 @@ public abstract class Node { public final String print() { return _print0(new StringBuilder(), new BitSet()).toString(); } + // This is the common print: check for repeats, check for DEAD and print // "DEAD" else call the per-Node print1. final StringBuilder _print0(StringBuilder sb, BitSet visited) { @@ -138,6 +140,8 @@ public abstract class Node { sb.append("\n"); } + public String p(int depth) { return IRPrinter.prettyPrint(this,depth); } + public boolean isMultiHead() { return false; } public boolean isMultiTail() { return false; } @@ -153,8 +157,6 @@ public abstract class Node { public int nIns() { return _inputs.size(); } - public Node out(int i) { return _outputs.get(i); } - public int nOuts() { return _outputs.size(); } public boolean isUnused() { return nOuts() == 0; } @@ -443,7 +445,10 @@ public abstract class Node { * Used to allow repeating tests in the same JVM. This just resets the * Node unique id generator, and is done as part of making a new Parser. */ - public static void reset() { UNIQUE_ID = 1; _disablePeephole=false; } + public static void reset() { + UNIQUE_ID = 1; + _disablePeephole=false; + } /** * Debugging utility to find a Node by index diff --git a/src/main/java/com/seaofnodes/simple/node/PhiNode.java b/src/main/java/com/seaofnodes/simple/node/PhiNode.java index 2a4ff52a..c7b5b357 100644 --- a/src/main/java/com/seaofnodes/simple/node/PhiNode.java +++ b/src/main/java/com/seaofnodes/simple/node/PhiNode.java @@ -85,10 +85,13 @@ public class PhiNode extends Node { */ private Node singleUniqueInput() { Node live = null; - for( int i=1; i<nIns(); i++ ) + for( int i=1; i<nIns(); i++ ) { + if( region() instanceof LoopNode loop && loop.entry()._type == Type.XCONTROL ) + return null; // Dead entry loops just ignore and let the loop collapse if( region().in(i)._type != Type.XCONTROL && in(i) != this ) if( live == null || live == in(i) ) live = in(i); else return null; + } return live; } diff --git a/src/main/java/com/seaofnodes/simple/node/RegionNode.java b/src/main/java/com/seaofnodes/simple/node/RegionNode.java index acaadaf1..453d028f 100644 --- a/src/main/java/com/seaofnodes/simple/node/RegionNode.java +++ b/src/main/java/com/seaofnodes/simple/node/RegionNode.java @@ -3,6 +3,7 @@ package com.seaofnodes.simple.node; import com.seaofnodes.simple.Utils; import com.seaofnodes.simple.type.Type; +import java.util.Collection; import java.util.BitSet; public class RegionNode extends Node { diff --git a/src/main/java/com/seaofnodes/simple/node/ScopeNode.java b/src/main/java/com/seaofnodes/simple/node/ScopeNode.java index a4fcbe65..e5d03d93 100644 --- a/src/main/java/com/seaofnodes/simple/node/ScopeNode.java +++ b/src/main/java/com/seaofnodes/simple/node/ScopeNode.java @@ -39,6 +39,10 @@ public class ScopeNode extends Node { for( int j=0; j<nIns(); j++ ) { sb.append(names[j]).append(":"); Node n = in(j); + while( n instanceof ScopeNode loop ) { + sb.append("Lazy_"); + n = loop.in(j); + } n._print0(sb, visited).append(" "); } sb.setLength(sb.length()-1); @@ -107,8 +111,18 @@ public class ScopeNode extends Node { var idx = syms.get(name); if( idx == null ) return update(name,n,nestingLevel-1); // Not found in this scope, recursively look in parent scope Node old = in(idx); - // If n is null we are looking up rather than updating, hence return existing value - return n==null ? old : setDef(idx,n); + if( old instanceof ScopeNode loop ) { + // Lazy Phi! + old = loop.in(idx) instanceof PhiNode phi && loop.ctrl()==phi.region() + // Loop already has a real Phi, use it + ? loop.in(idx) + // Set real Phi in the loop head + // The phi takes its one input (no backedge yet) from a recursive + // lookup, which might have insert a Phi in every loop nest. + : loop.setDef(idx,new PhiNode(name,loop.ctrl(),loop.update(name,null,nestingLevel),null).peephole()); + setDef(idx,old); + } + return n==null ? old : setDef(idx,n); // Not lazy, so this is the answer } public Node ctrl() { return in(0); } @@ -131,6 +145,11 @@ public class ScopeNode extends Node { * tables), nor deep (would dup the Scope, the HashMap tables, but then * also the program Nodes). * <p> + * If the {@code loop} flag is set, the edges are filled in as the original + * Scope, as a indication of Lazy Phis at loop heads. The goal here is to + * not make Phis at loop heads for variables which are never touched in the + * loop body. + * <p> * The new Scope is a full-fledged Node with proper use<->def edges. */ public ScopeNode dup() { return dup(false); } @@ -144,17 +163,10 @@ public class ScopeNode extends Node { dup._scopes.push(new HashMap<>(syms)); dup.addDef(ctrl()); // Control input is just copied - for( int i=1; i<nIns(); i++ ) { - if ( !loop ) { dup.addDef(in(i)); } - else { - String[] names = reverseNames(); // Get the variable names - // Create a phi node with second input as null - to be filled in - // by endLoop() below - dup.addDef(new PhiNode(names[i], ctrl(), in(i), null).peephole()); - // Ensure our node has the same phi in case we created one - setDef(i, dup.in(i)); - } - } + for( int i=1; i<nIns(); i++ ) + // For lazy phis on loops we use a sentinel + // that will trigger phi creation on update + dup.addDef(loop ? this : in(i)); return dup; } @@ -172,7 +184,9 @@ public class ScopeNode extends Node { // Note that we skip i==0, which is bound to '$ctrl' for (int i = 1; i < nIns(); i++) if( in(i) != that.in(i) ) // No need for redundant Phis - setDef(i, new PhiNode(ns[i], r, in(i), that.in(i)).peephole()); + // If we are in lazy phi mode we need to a lookup + // by name as it will trigger a phi creation + setDef(i, new PhiNode(ns[i], r, this.lookup(ns[i]), that.lookup(ns[i])).peephole()); that.kill(); // Kill merged scope return r.unkeep().peephole(); } @@ -184,14 +198,26 @@ public class ScopeNode extends Node { assert ctrl instanceof LoopNode loop && loop.inProgress(); ctrl.setDef(2,back.ctrl()); for( int i=1; i<nIns(); i++ ) { - PhiNode phi = (PhiNode)in(i); - assert phi.region()==ctrl && phi.in(2)==null; - phi.setDef(2,back.in(i)); - // Do an eager useless-phi removal - Node in = phi.peephole(); - if( in != phi ) - phi.subsume(in); + if( back.in(i) != this ) { + PhiNode phi = (PhiNode)in(i); + assert phi.region()==ctrl && phi.in(2)==null; + phi.setDef(2,back.in(i)); + } + if( exit.in(i) == this ) // Replace a lazy-phi on the exit path also + exit.setDef(i,in(i)); } back.kill(); // Loop backedge is dead + // Now one-time do a useless-phi removal + for( int i=1; i<nIns(); i++ ) { + if( in(i) instanceof PhiNode phi ) { + // Do an eager useless-phi removal + Node in = phi.peephole(); + if( in != phi ) { + phi.subsume(in); + setDef(i,in); // Set the update back into Scope + } + } + } + } } diff --git a/src/test/java/com/seaofnodes/simple/Chapter01Test.java b/src/test/java/com/seaofnodes/simple/Chapter01Test.java index 547c36f8..13b42f96 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter01Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter01Test.java @@ -31,7 +31,7 @@ public class Chapter01Test { parser.parse(); StartNode start = Parser.START; for( Node use : start._outputs ) - if( use instanceof ConstantNode con ) + if( use instanceof ConstantNode con && con._type instanceof TypeInteger ) assertEquals(TypeInteger.constant(0),con._type); } diff --git a/src/test/java/com/seaofnodes/simple/Chapter03Test.java b/src/test/java/com/seaofnodes/simple/Chapter03Test.java index 1e67cef5..64ff153e 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter03Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter03Test.java @@ -31,7 +31,7 @@ public class Chapter03Test { @Test public void testVarScopeNoPeephole() { - Parser parser = new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b; } return c;"); + Parser parser = new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b; } return c; "); Node._disablePeephole = true; StopNode ret = parser.parse(); Node._disablePeephole = false; @@ -40,7 +40,7 @@ public class Chapter03Test { @Test public void testVarDist() { - Parser parser = new Parser("int x0=1; int y0=2; int x1=3; int y1=4; return (x0-x1)*(x0-x1) + (y0-y1)*(y0-y1);"); + Parser parser = new Parser("int x0=1; int y0=2; int x1=3; int y1=4; return (x0-x1)*(x0-x1) + (y0-y1)*(y0-y1); "); StopNode ret = parser.parse(); assertEquals("return 8;", ret.print()); } @@ -54,7 +54,7 @@ public class Chapter03Test { assertEquals("Undefined name 'a'",e.getMessage()); } } - + @Test public void testRedeclareVar() { try { diff --git a/src/test/java/com/seaofnodes/simple/Chapter04Test.java b/src/test/java/com/seaofnodes/simple/Chapter04Test.java index 98878ca6..2e2abb25 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter04Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter04Test.java @@ -10,7 +10,7 @@ public class Chapter04Test { @Test public void testPeephole() { - Parser parser = new Parser("return 1+arg+2;"); + Parser parser = new Parser("return 1+arg+2; "); StopNode ret = parser.parse(); assertEquals("return (arg+3);", ret.print()); } @@ -38,7 +38,7 @@ public class Chapter04Test { @Test public void testPeephole3() { - Parser parser = new Parser("return 1+arg+2+arg+3;"); + Parser parser = new Parser("return 1+arg+2+arg+3; "); StopNode ret = parser.parse(); assertEquals("return ((arg*2)+6);", ret.print()); } @@ -52,7 +52,7 @@ public class Chapter04Test { @Test public void testVarArg() { - Parser parser = new Parser("return arg;"); + Parser parser = new Parser("return arg; "); StopNode stop = parser.parse(); ReturnNode ret = stop.ret(); assertTrue(ret.in(0) instanceof ProjNode); @@ -61,49 +61,49 @@ public class Chapter04Test { @Test public void testConstantArg() { - Parser parser = new Parser("return arg;", TypeInteger.constant(2)); + Parser parser = new Parser("return arg; ", TypeInteger.constant(2)); StopNode ret = parser.parse(); assertEquals("return 2;", ret.print()); } @Test public void testCompEq() { - Parser parser = new Parser("return 3==3;"); + Parser parser = new Parser("return 3==3; "); StopNode ret = parser.parse(); assertEquals("return 1;", ret.print()); } @Test public void testCompEq2() { - Parser parser = new Parser("return 3==4;"); + Parser parser = new Parser("return 3==4; "); StopNode ret = parser.parse(); assertEquals("return 0;", ret.print()); } @Test public void testCompNEq() { - Parser parser = new Parser("return 3!=3;"); + Parser parser = new Parser("return 3!=3; "); StopNode ret = parser.parse(); assertEquals("return 0;", ret.print()); } @Test public void testCompNEq2() { - Parser parser = new Parser("return 3!=4;"); + Parser parser = new Parser("return 3!=4; "); StopNode ret = parser.parse(); assertEquals("return 1;", ret.print()); } @Test public void testBug1() { - Parser parser = new Parser("int a=arg+1; int b=a; b=1; return a+2;"); + Parser parser = new Parser("int a=arg+1; int b=a; b=1; return a+2; "); StopNode ret = parser.parse(); assertEquals("return (arg+3);", ret.print()); } @Test public void testBug2() { - Parser parser = new Parser("int a=arg+1; a=a; return a;"); + Parser parser = new Parser("int a=arg+1; a=a; return a; "); StopNode ret = parser.parse(); assertEquals("return (arg+1);", ret.print()); } diff --git a/src/test/java/com/seaofnodes/simple/Chapter05Test.java b/src/test/java/com/seaofnodes/simple/Chapter05Test.java index 5bb67817..68d379a1 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter05Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter05Test.java @@ -17,7 +17,9 @@ if (arg == 1) a = arg+2; else { a = arg-3; + } + return a;"""); StopNode ret = parser.parse(); assertEquals("return Phi(Region17,(arg+2),(arg-3));", ret.toString()); diff --git a/src/test/java/com/seaofnodes/simple/Chapter06Test.java b/src/test/java/com/seaofnodes/simple/Chapter06Test.java index 00d725bc..b858b83e 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter06Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter06Test.java @@ -29,7 +29,7 @@ if (arg) a = 2; return (arg < a) < 3; """); - StopNode stop = parser.parse(); + StopNode stop = parser.parse(false); assertEquals("return ((arg<Phi(Region12,2,1))<3);", stop.toString()); } diff --git a/src/test/java/com/seaofnodes/simple/Chapter07Test.java b/src/test/java/com/seaofnodes/simple/Chapter07Test.java index 189fcf66..d691672e 100644 --- a/src/test/java/com/seaofnodes/simple/Chapter07Test.java +++ b/src/test/java/com/seaofnodes/simple/Chapter07Test.java @@ -37,7 +37,7 @@ if(arg){}else{ return a; """); StopNode stop = parser.parse(); - assertEquals("return Phi(Region23,1,Phi(Loop11,1,(Phi_a+1)));", stop.toString()); + assertEquals("return Phi(Region22,1,Phi(Loop11,1,(Phi_a+1)));", stop.toString()); } @Test @@ -57,7 +57,7 @@ while(i < arg) { return sum; """); StopNode stop = parser.parse(); - assertEquals("return Phi(Loop8,0,Phi(Loop21,Phi_sum,(Phi(Loop,0,(Phi_j+1))+Phi_sum)));", stop.toString()); + assertEquals("return Phi(Loop8,0,Phi(Loop20,Phi_sum,(Phi_sum+Phi(Loop,0,(Phi_j+1)))));", stop.toString()); } @Test @@ -74,7 +74,7 @@ return b; """); Node._disablePeephole = true; StopNode stop = parser.parse(); - assertEquals("return Phi(Loop8,2,Phi(Region27,Phi_b,4));", stop.toString()); + assertEquals("return Phi(Loop8,2,Phi(Region26,Phi_b,4));", stop.toString()); assertTrue(stop.ret().ctrl() instanceof ProjNode); Node._disablePeephole = false; } @@ -94,7 +94,7 @@ while(a < 10) { return b; """); StopNode stop = parser.parse(); - assertEquals("return Phi(Loop8,2,(Phi(Region27,Phi_b,4)+1));", stop.toString()); + assertEquals("return Phi(Loop8,2,(Phi(Region26,Phi_b,4)+1));", stop.toString()); assertTrue(stop.ret().ctrl() instanceof ProjNode); } @@ -156,7 +156,7 @@ int a = 1; while(arg) a = 2; return a; """); - StopNode stop = parser.parse(); + StopNode stop = parser.parse(false); assertEquals("return Phi(Loop7,1,2);", stop.toString()); assertTrue(stop.ret().ctrl() instanceof ProjNode); } diff --git a/src/test/java/com/seaofnodes/simple/Chapter08Test.java b/src/test/java/com/seaofnodes/simple/Chapter08Test.java new file mode 100644 index 00000000..5d9d1545 --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/Chapter08Test.java @@ -0,0 +1,218 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Assert; +import org.junit.Test; +import org.junit.Ignore; + +import static org.junit.Assert.*; + +public class Chapter08Test { + + @Test + @Ignore + public void testJig() { + Parser parser = new Parser(""" +// Insert test case here +"""); + StopNode stop = parser.parse(); + } + + @Test + public void testEx6() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + break; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Region36,Phi(Region25,Phi(Loop6,arg,(Phi_arg+1)),Add),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + Assert.assertEquals(5, GraphEvaluator.evaluate(stop, 1)); + Assert.assertEquals(10, GraphEvaluator.evaluate(stop, 6)); + } + + + @Test + public void testEx5() { + Parser parser = new Parser( + """ +int a = 1; +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 7) + continue; + a = a + 1; +} +return a; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop7,1,Phi(Region42,Phi_a,(Phi_a+1)));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + + @Test + public void testEx4() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Region34,Phi(Loop6,arg,(Phi_arg+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + @Test + public void testEx3() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Region25,Phi(Loop6,arg,(Phi_arg+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + + @Test + public void testEx2() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 6) + continue; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop6,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + + @Test + public void testEx1() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop6,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testRegress1() { + Parser parser = new Parser( + """ +while( arg < 10 ) { + int a = arg+2; + if( a > 4 ) + break; +} +return arg; + """); + StopNode stop = parser.parse(); + assertEquals("return arg;", stop.toString()); + } + + @Test + public void testRegress2() { + Parser parser = new Parser("if(1) return 0; else while(arg>--arg) arg=arg+1; return 0;"); + StopNode stop = parser.parse(); + assertEquals("Stop[ return 0; return 0; ]", stop.toString()); + } + + @Test + public void testBreakOutsideLoop() { + try { + new Parser(""" +if(arg <= 10) { + break; + arg = arg + 1; +} +return arg; +""").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("No active loop for a break or continue",e.getMessage()); + } + } + + @Test + public void testRegress3() { + Parser parser = new Parser(""" +while(arg < 10) { + break; +} +return arg; +"""); + StopNode stop = parser.parse(); + assertEquals("return arg;", stop.toString()); + } + + @Test + public void testRegress4() { + Parser parser = new Parser(""" +int a = 1; +while(arg < 10) { + a = a + 1; + if (arg > 2) { + int a = 17; + break; + } +} +return a; +"""); + StopNode stop = parser.parse(); + assertEquals("return Phi(Region28,Phi(Loop7,1,(Phi_a+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + @Test + public void testRegress5() { + Parser parser = new Parser(""" +int a = 1; +while(1) { + a = a + 1; + if (a<10) continue; + break; +} +return a; +"""); + StopNode stop = parser.parse(); + assertEquals("return (Phi(Loop7,1,Add)+1);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + +} diff --git a/src/test/java/com/seaofnodes/simple/FuzzerWrap.java b/src/test/java/com/seaofnodes/simple/FuzzerWrap.java new file mode 100644 index 00000000..82a6a472 --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/FuzzerWrap.java @@ -0,0 +1,26 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.fuzzer.Fuzzer; +import org.junit.Ignore; +import org.junit.Test; + + +import static org.junit.Assert.assertTrue; + +/** + * To use the fuzzer run the <code>fuzzPeeps</code> methods. + * This can be done from IntelliJ Gui or remove the `@Ignore` annotation and start the test case from the command line + * via <code>mvn clean test -Dtest=com.seaofnodes.simple.FuzzerWrap#fuzzPeeps</code> + */ +public class FuzzerWrap { + + @Test + @Ignore + public void fuzzPeeps() { + var fuzzer = new Fuzzer(); + for (int i=0; i<100000; i++) + fuzzer.fuzzPeeps(i); + assertTrue(fuzzer.noExceptions()); + } + +} diff --git a/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java b/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java new file mode 100644 index 00000000..5fcd8764 --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java @@ -0,0 +1,128 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.GraphEvaluator; +import com.seaofnodes.simple.node.StopNode; + +import java.util.ArrayList; +import java.util.Random; +import java.util.function.Consumer; + +/** + * Implementation of the fuzzer. + * Random testcases are generated using the ScriptGenerator. + * This will generate a script similar to how the parser parses it but instead of parsing it will + * randomly choose a variation the parser would parse and generate it. + * These scripts are the parsed by the parser and all exceptions are caught and filtered + * to only show one occurrence of one problem. This includes script which generate different + * results when the compiled graph with and without peeps is executed. + * To aid debugging scripts that cause errors are then reduced by applying rules and checking + * that the same issue persists. + */ +public class Fuzzer { + + private static final int EVAL_TIMEOUT = 1000; + + /** + * List of exceptions already encountered. + * This is used to filter new exceptions and discard them if they are already found. + */ + private final ArrayList<Throwable> exceptions = new ArrayList<>(); + + /** + * Filter and record an exception in a script. + * @param e The exception caused by the script + * @param script The script causing the exception + * @param reproducer Reproducer which should be used to reproduce the test case. + */ + private void recordException(Throwable e, String script, Consumer<String> reproducer) { + for (var ex : exceptions) { + if (FuzzerUtils.isExceptionFromSameCause(ex, e)) return; + } + exceptions.add(e); + System.out.println("========== Stack =========="); + e.printStackTrace(System.out); + System.out.println("========== Code ==========="); + System.out.println(script); + System.out.println("========= Reduced ========="); + System.out.println(Reducer.reduce(script, e, reproducer)); + System.out.println("==========================="); + System.out.flush(); + } + + /** + * Check that two graphs result in the same output when supplied with a value + * @param stop1 Stop node of the first graph + * @param stop2 Stop node of the second graph + * @param in The input value to both graphs to test for an equal output + */ + private static void checkGraphs(StopNode stop1, StopNode stop2, long in) { + var e1 = GraphEvaluator.evaluateWithResult(stop1, in, EVAL_TIMEOUT); + var e2 = GraphEvaluator.evaluateWithResult(stop2, in, EVAL_TIMEOUT); + if (e1.type() == GraphEvaluator.ResultType.TIMEOUT || e2.type() == GraphEvaluator.ResultType.TIMEOUT) return; + if (e1.type() != e2.type()) + throw new RuntimeException("Different calculations types " + e1.type() + " vs " + e2.type()); + if (e1.value() != e2.value()) + throw new RuntimeException("Different calculations values " + e1.value() + " vs " + e2.value()); + } + + /** + * Run checks for script. Compile the script with peeps enabled and disabled. + * Check that exceptions raised in the parser by both methods are the same and only happens if the script may be invalid. + * If the script was successfully parsed check that both version behave the same. + * @param script The script to test + * @param valid If the script is definitely valid. If not some exceptions may be suppressed. + */ + private static void runCheck(String script, boolean valid) { + StopNode stop1; + try { + stop1 = FuzzerUtils.parse(script, false); + } catch (RuntimeException e1) { + try { + FuzzerUtils.parse(script, true); + } catch (RuntimeException e2) { + if (FuzzerUtils.isExceptionFromSameCause(e1, e2)) { + if (!valid || e1.getClass() == RuntimeException.class) return; + } else { + e1.addSuppressed(e2); + } + } + throw e1; + } + var stop2 = FuzzerUtils.parse(script, true); + checkGraphs(stop1, stop2, 0); + checkGraphs(stop1, stop2, 1); + checkGraphs(stop1, stop2, 10); + } + + /** + * Check that the script does not result in exceptions. + * @param script The script to test. + * @param valid If the script is valid or if it might contain syntax errors. + */ + private void check(String script, boolean valid) { + try { + runCheck(script, valid); + } catch (Throwable e) { + recordException(e, script, s->runCheck(s, valid)); + } + } + + /** + * Run one test with the given seed. + * @param seed The seed to use for generating this test case + */ + public void fuzzPeeps(long seed) { + var rand = new Random(seed); + var sb = new StringBuilder(); + var valid = new ScriptGenerator(rand, sb, false).genProgram(); + check(sb.toString(), valid); + } + + /** + * Check that no exceptions happened. + * @return true if no exception happened + */ + public boolean noExceptions() { + return exceptions.isEmpty(); + } +} diff --git a/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java b/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java new file mode 100644 index 00000000..37a57e11 --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java @@ -0,0 +1,58 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.node.Node; +import com.seaofnodes.simple.node.StopNode; + +/** + * Some utilities for the fuzzer. + */ +class FuzzerUtils { + + /** + * Check that eiter one of the objects is null or that both are equal. + */ + private static boolean equalOrNull(Object a, Object b) { + if (a == null || b == null) return true; + return a.equals(b); + } + + /** + * Check if both stack traces have the same first entry. Empty stack traces can happen with NPE optimization + * and allow the other to be any stack trace. + */ + private static boolean sameStackTraceOrigin(StackTraceElement[] a, StackTraceElement[] b) { + if (a == null || a.length == 0 || b == null || b.length == 0) return true; // One or both stack traces are missing. + return a[0].equals(b[0]); + } + + /** + * Checks if two exceptions are caused by the same problem. + */ + public static boolean isExceptionFromSameCause(Throwable a, Throwable b) { + if (a == null || b == null) return a == b; // Handle the null case + if (a.getClass() != b.getClass()) return false; // Different classes + if (!equalOrNull(a.getMessage(), b.getMessage())) return false; // Different messages. Null is allowed as wildcard + var s1 = a.getStackTrace(); + var s2 = b.getStackTrace(); + if (!sameStackTraceOrigin(s1, s2)) return false; // Different stack trace origins + if (!isExceptionFromSameCause(a.getCause(), b.getCause())) return false; // Different causes + var o1 = a.getSuppressed(); + var o2 = b.getSuppressed(); + if (o1 == null || o2 == null || o1.length != o2.length) return o1 == o2; // Different suppression + for (int i=0; i<o1.length; i++) { + if (!isExceptionFromSameCause(o1[i], o2[i])) return false; // Different suppression + } + return true; + } + + /** + * Parse script with peepholes enabled or disabled + */ + public static StopNode parse(String script, boolean runPeeps) { + var parser = new Parser(script); + Node._disablePeephole = !runPeeps; + return parser.parse(); + } + +} diff --git a/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java b/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java new file mode 100644 index 00000000..b7fc18ec --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java @@ -0,0 +1,144 @@ +package com.seaofnodes.simple.fuzzer; + +import java.util.function.Consumer; +import java.util.function.Predicate; +import java.util.regex.Pattern; + +/** + * This class is used to reduce test cases created by the fuzzer. + * It applies rewrite rules to the test case and checks that the + * test still produces the same exception. + * This is done in a fixpoint iteration until every rewrite produces + * no or a different exception. + */ +public class Reducer { + + /** + * Holder for the rewrite rules + */ + private record Replace(Pattern p, String r) {} + + /** + * List of rewrite rules. + */ + private static final Replace[] REPLACEMENTS = { + new Replace(Pattern.compile("(?<=[+\\-*/<>=(])--"), ""), + new Replace(Pattern.compile("\\b--"), "+"), + new Replace(Pattern.compile("\\b\\+-"), "-"), + new Replace(Pattern.compile("\\bfalse\\b"), "0"), + new Replace(Pattern.compile("\\btrue\\b"), "1"), + new Replace(Pattern.compile("-"), ""), + new Replace(Pattern.compile("(?<![+\\-*/<>=])(?:-|\\*|/|>=|<=|>|<|!=|==)(?![+\\-*/<>=])"), "+"), + new Replace(Pattern.compile("\\{(?:[^{}]|\\{})+}"), "{}"), + new Replace(Pattern.compile("\\{((?:[^{}]|\\{})+)}"), "$1"), + new Replace(Pattern.compile("\\(([^()]+)\\)"), "$1"), + new Replace(Pattern.compile("\\b\\w+\\b"), "1"), + new Replace(Pattern.compile("\\b\\w+\\b"), "0"), + new Replace(Pattern.compile("\\d+\\+"), ""), + new Replace(Pattern.compile("\\+\\d+"), ""), + new Replace(Pattern.compile("(?<=\\n|^)[^\\n]*(?=\\n|$)"), "\n"), + new Replace(Pattern.compile("\\n+"), "\n"), + new Replace(Pattern.compile("^\\n+|\\n+$"), ""), + new Replace(Pattern.compile("else *"), ""), + new Replace(Pattern.compile("\\bif\\([^()]+\\) *"), ""), + new Replace(Pattern.compile("\\bwhile\\([^()]+\\) *"), ""), + }; + + /** + * Predicate to test if the reduced script generates the same error. + */ + private final Predicate<String> tester; + + /** + * Create a reducer with a test function. + * @param tester Test function which returns true when the same issue is found in the script. + */ + private Reducer(Predicate<String> tester) { + this.tester = tester; + } + + /** + * Rewrites the script with one rewrite rule. + */ + private String doReplacement(String script, Pattern pattern, String with) { + var matcher = pattern.matcher(script); + var sb = new StringBuilder(); + int last = 0; + while (matcher.find()) { + var pos = sb.length(); + matcher.appendReplacement(sb, with); + var tail = sb.length(); + matcher.appendTail(sb); + if (tester.test(sb.toString())) { + sb.setLength(tail); + } else { + sb.setLength(pos); + sb.append(script, last, matcher.end()); + } + last = matcher.end(); + } + matcher.appendTail(sb); + return sb.toString(); + } + + /** + * Clean up variable names from the random ones generated by the fuzzer. + */ + private String cleanVariables(String script) { + var matcher = Pattern.compile("\\bint ([0-9a-zA-Z_]+)").matcher(script); + int num = 0; + while (matcher.find()) { + var var = matcher.group(1); + if (var.matches("v\\d+")) continue; + while (script.contains("v"+num)) num++; + var n = script.replaceAll("\\b"+var+"\\b", "v" + num); + if (tester.test(n)) { + script = n; + } + } + return script; + } + + /** + * Run all rewrite rules once. + */ + private String doAllReplacements(String script) { + for (var replace: REPLACEMENTS) { + script = doReplacement(script, replace.p, replace.r); + } + return script; + } + + /** + * Reduce the script to a minimal version which produces the same problem with a test function. + * @param tester Test function which returns true when the same issue is found in the script. + */ + public static String reduce(String script, Predicate<String> tester) { + var reducer = new Reducer(tester); + String old; + do { + old = script; + script = reducer.doAllReplacements(script); + script = reducer.cleanVariables(script); + } while (!script.equals(old)); + return script; + } + + /** + * Reduce the script to a minimal version which produces the same problem with a reproducer. + * @param ex The exception originally caused by the script + * @param reproducer Test function which throws an exception which will be checked against ex. + */ + public static String reduce(String script, Throwable ex, Consumer<String> reproducer) { + return reduce(script, s->{ + Throwable nex = null; + try { + reproducer.accept(s); + } catch (Throwable e) { + nex = e; + } + return FuzzerUtils.isExceptionFromSameCause(nex, ex); + }); + } + +} diff --git a/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java b/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java new file mode 100644 index 00000000..148c2319 --- /dev/null +++ b/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java @@ -0,0 +1,462 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.node.ScopeNode; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.Random; + +/** + * Generate a pseudo random script. + * This generator will generate the same script for two random number generators initialized with the same seed. + * To generate valid code it implements the parser but instead of parsing it emits the statements and expressions. + * It is guaranteed to terminate. + */ +public class ScriptGenerator { + + /** + * Get the list of keywords from the parser. + */ + @SuppressWarnings("unchecked") + private static HashSet<String> getKeywords() { + try { + var field = Parser.class.getDeclaredField("KEYWORDS"); + field.setAccessible(true); + return (HashSet<String>) field.get(new Parser("")); + } catch (Throwable e) { + throw new ExceptionInInitializerError(e); + } + } + + /** + * Number of spaces per indentation + */ + private static final int INDENTATION = 4; + /** + * Valid characters for identifiers. The last 10 are not valid for the first character. + */ + private static final String VAR_CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_0123456789"; + /** + * List of keywords not valid for identifiers. + */ + private static final HashSet<String> KEYWORDS = getKeywords(); + + /** + * Flag for a statement that it does not pass on control flow to the next statement. + */ + private static final int FLAG_STOP = 0x01; + /** + * Flag for a statement that it contains a final if statement without an else branch. + */ + private static final int FLAG_IF_WITHOUT_ELSE = 0x02; + /** + * Binary operators. + */ + private static final String[] BINARY_OP = {"==", "!=", "<", "<=", ">", ">=", "+", "-", "*", "/"}; + /** + * Unary operators. + */ + private static final String[] UNARY_OP = {"-"}; + + + /** + * The random number generator used for random decisions. + */ + private final Random random; + /** + * Indentation depth. + */ + private int indentation = 0; + /** + * Output string builder + */ + private final StringBuilder sb; + /** + * Number of nested loops + */ + private int loopDepth = 0; + /** + * Current scope start in the variables list. + */ + private int currScopeStart = 0; + /** + * The depth of blocks allowed. + */ + private int depth = 7; + /** + * The depth of expressions allowed. + */ + private int exprDepth = 3; + /** + * Current variables in scope. + */ + private final ArrayList<String> variables = new ArrayList<>(); + /** + * If this needs to generate valid scripts or is also allowed to generate invalid ones. + */ + private final boolean generateValid; + /** + * If this script might be invalid. + */ + private boolean maybeInvalid = false; + + /** + * + * @param random the random number generator. + * @param sb the script will be written to this string builder. + * @param generateValid if the script should be guaranteed valid or if it is allowed to contain bugs. + */ + public ScriptGenerator(Random random, StringBuilder sb, boolean generateValid) { + this.random = random; + this.sb = sb; + this.generateValid = generateValid; + } + + /** + * Random number with log distribution + * @param max The maximum value + * @return A random number in the range [0, max) with higher numbers being more uncommon. + */ + private int randLog(int max) { + max--; + int n = 1<<max; + var num = random.nextInt(n); + for (int i=max-1; i>=0; i--) { + if ((num & (1<<i))!=0) return max-i-1; + } + return max; + } + + /** + * Helper function to print indentation. + * @return sb for chaining + */ + private StringBuilder printIndentation() { + return sb.repeat(' ', indentation); + } + + /** + * Generate a random name for variables. This might be invalid when it is a keyword. + * @return The random name generated + */ + private StringBuilder getRandomName() { + int len = random.nextInt(10) + 1; + StringBuilder sb = new StringBuilder(len); + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()-10))); + for (int i=1; i<len; i++) + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()))); + return sb; + } + + /** + * Generate a variable name. This might be new random name or a name from an outer scope. + * If the program is allowed to be invalid this can return keywords and already used variable names in the current scope. + * @return The variable name. + */ + private String getVarName() { + if (currScopeStart > 0 && random.nextInt(10) > 7) { + // Use a variable outside the current scope. + var v = variables.get(random.nextInt(currScopeStart)); + if (variables.lastIndexOf(v) < currScopeStart) return v; + if (!generateValid) { + maybeInvalid = true; + return v; + } + } + // Generate a new random variable name + StringBuilder sb = getRandomName(); + var v = sb.toString(); + if (!generateValid && (KEYWORDS.contains(v) || variables.lastIndexOf(v) >= currScopeStart)) { + maybeInvalid = true; + return v; + } + while (KEYWORDS.contains(v) || variables.lastIndexOf(v) >= currScopeStart) { + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()))); + v = sb.toString(); + } + return v; + } + + + + /** + * Generates a program and writes it into the string builder supplied in the constructor. + * @return If the program is allowed to be invalid returns if something potentially invalid was generated. + */ + public boolean genProgram() { + this.maybeInvalid = false; + variables.add(ScopeNode.ARG0); + currScopeStart = variables.size(); + if ((genStatements() & FLAG_STOP) == 0) { + if (generateValid || random.nextInt(10)<7) { + genReturn(); + } else { + this.maybeInvalid = true; + } + } + return !this.maybeInvalid; + } + + /** + * Generate a list of statements. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the last statement generated + */ + public int genStatements() { + var num = random.nextInt(10); + for (int i=0; i<num; i++) { + printIndentation(); + var stop = genStatement(); + sb.append("\n"); + if ((stop & FLAG_STOP) != 0) return stop; + } + return 0; + } + + /** + * Generate a single statement + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genStatement() { + return switch (random.nextInt(10)) { + case 1 -> genBlock(); + case 2 -> genIf(); + case 3 -> genWhile(); + case 4, 5 -> genDecl(); + case 6, 7, 8 -> genAssignment(); + default -> genExit(); + }; + } + + /** + * Generate a statement for if, else and while blocks. + * This is special since it disallows declarations and prefers to generate blocks. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genStatementBlock() { + indentation += INDENTATION; + int res; + if (depth == 0) { + res = random.nextBoolean() ? genAssignment() : genExit(); + } else { + depth--; + res = switch (random.nextInt(10)) { + case 1, 2, 3, 4, 5 -> { + depth++; + indentation -= INDENTATION; + var ret = genBlock(); + indentation += INDENTATION; + depth--; + yield ret; + } + case 6 -> genIf(); + case 7 -> genWhile(); + case 8 -> genAssignment(); + default -> genExit(); + }; + depth++; + } + indentation -= INDENTATION; + return res; + } + + /** + * Generate an exit. This can be return or break and continue when in a loop. + * @return FLAG_STOP + */ + public int genExit() { + if (loopDepth == 0 && generateValid) return genReturn(); + return switch (random.nextInt(7)) { + case 0,1,2 -> { + if (loopDepth == 0) maybeInvalid = true; + sb.append("continue;"); + yield FLAG_STOP; + } + case 3,4,5 -> { + if (loopDepth == 0) maybeInvalid = true; + sb.append("break;"); + yield FLAG_STOP; + } + default -> genReturn(); + }; + } + + /** + * Generate a block statement. After a certain depth only empty blocks are generated to ensure termination of the generator. + * @return flag FLAG_STOP for the generated statement + */ + public int genBlock() { + if (depth == 0) { + sb.append("{}"); + return 0; + } + depth--; + int oldCSS = currScopeStart; + currScopeStart = variables.size(); + sb.append("{\n"); + indentation += INDENTATION; + var stop = genStatements(); + indentation -= INDENTATION; + printIndentation().append("}"); + while (variables.size() > currScopeStart) + variables.removeLast(); + currScopeStart = oldCSS; + depth++; + return stop & ~FLAG_IF_WITHOUT_ELSE; + } + + /** + * Generate an if statement with an optional else block. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genIf() { + sb.append("if("); + genExpression(); + sb.append(") "); + var stop = genStatementBlock(); + if ((stop & FLAG_IF_WITHOUT_ELSE) == 0 && random.nextInt(10) > 3) { + sb.append("\n"); + printIndentation().append("else "); + stop &= genStatementBlock(); + } else { + stop = FLAG_IF_WITHOUT_ELSE; + } + return stop; + } + + /** + * Generate a while loop. + * @return 0 + */ + public int genWhile() { + sb.append("while("); + genExpression(); + sb.append(") "); + loopDepth++; + genStatementBlock(); + loopDepth--; + return 0; + } + + /** + * Generate a declaration statement. + * @return 0 + */ + public int genDecl() { + String name = getVarName(); + sb.append("int ").append(name).append("="); + genExpression(); + sb.append(";"); + variables.add(name); + return 0; + } + + /** + * Generate an assignment statement. + * @return 0 + */ + public int genAssignment() { + if (variables.isEmpty()) return genDecl(); + genVariable(); + sb.append("="); + genExpression(); + sb.append(";"); + return 0; + } + + /** + * Generate a return statement. + * @return FLAG_STOP + */ + public int genReturn() { + sb.append("return "); + genExpression(); + sb.append(";"); + return FLAG_STOP; + } + + + /** + * Generate a binary expression. + * This method does not care about operator precedence. + */ + public void genExpression() { + var num = randLog(10); + while(num-->0) { + genUnary(); + sb.append(BINARY_OP[random.nextInt(BINARY_OP.length)]); + } + genUnary(); + } + + /** + * Generate a unary expression. + */ + public void genUnary() { + var num = randLog(6); + while(num-->0) { + sb.append(UNARY_OP[random.nextInt(UNARY_OP.length)]); + } + genPrimary(); + } + + /** + * Generate a primary expression. + */ + public void genPrimary() { + switch (random.nextInt(10)) { + case 0: + sb.append("true"); + break; + case 1: + sb.append("false"); + break; + case 2: + if (exprDepth == 0) { + // Ensure termination of the generator. + if (random.nextBoolean()) { + genNumber(); + } else { + genVariable(); + } + } else { + sb.append("("); + exprDepth--; + genExpression(); + exprDepth++; + sb.append(")"); + } + break; + case 3, 4, 5, 6: + genNumber(); + break; + default: + genVariable(); + } + } + + /** + * Generate a number. + */ + public void genNumber() { + sb.append(random.nextInt(100)); + } + + /** + * Generate a variable. If there are none generate a number instead. + * If the program is allowed to be invalid a random name can be generated in some cases. + */ + public void genVariable() { + if (!generateValid && random.nextInt(100)>97) { + sb.append(getRandomName()); + maybeInvalid = true; + return; + } + if (variables.isEmpty()) { + genNumber(); + } else { + sb.append(variables.get(random.nextInt(variables.size()))); + } + } + +} |