package com.seaofnodes.simple; import com.seaofnodes.graph.GraphObserver; import com.seaofnodes.simple.node.*; import com.seaofnodes.simple.type.*; import java.util.*; /** * The Parser converts a Simple source program to the Sea of Nodes intermediate * representation directly in one pass. There is no intermediate Abstract * Syntax Tree structure. *
* This is a simple recursive descent parser. All lexical analysis is done here as well.
*/
public class Parser {
// Current compilation context; the observer belongs to the parser.
public static Parser PARSER;
public GraphObserver
* To make the compiler multithreaded, this field will have to move into a TLS.
*/
public static StartNode START;
public StopNode STOP;
// Field identities are independent of the memory graph and Start's tuple.
private final HashMap
* Each ScopeNode contains a stack of lexical scopes, each scope is a symbol table that binds
* variable names to Nodes. The top of this stack represents current scope.
*
* We keep a list of all ScopeNodes so that we can show them in graphs.
* @see #parseIf()
* @see #_xScopes
*/
public ScopeNode _scope;
/**
* List of keywords disallowed as identifiers
*/
private static final HashSet
* '{' statements '}'
*
* Does not parse the opening or closing '{}'
* @return a {@link Node} or {@code null}
*/
private Node parseBlock() {
// Enter a new scope
_scope.push();
while (!peek('}') && !_lexer.isEOF())
parseStatement();
// Exit scope
_scope.pop();
return null;
}
/**
* Parses a statement
*
*
* returnStatement | declStatement | blockStatement | ifStatement | expressionStatement
*
* @return a {@link Node} or {@code null}
*/
private Node parseStatement() {
if( false ) return null;
else if (matchx("return") ) return parseReturn();
else if (matchx("int") ) return parseDecl(TypeInteger.BOT);
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("struct") ) return parseStruct();
else if (matchx(";") ) return null; // Empty statement
// declarations of vars with struct type are handled in parseExpressionStatement due
// to ambiguity
else return parseExpressionStatement();
}
/**
* Parse a struct field.
*
* int IDENTIFIER ;
*
*/
private Field parseField(String sname) {
if( matchx("int") ) // Currently only parsing "int" type fields
return require(Field.make(requireId().intern(),TypeInteger.BOT),";");
throw errorSyntax("A field type is expected, only type 'int' is supported at present");
}
/**
* Parse a struct declaration, and return the following statement.
* Only allowed in top level scope.
* Structs cannot be redefined.
*
* @return The statement following the struct
*/
private Node parseStruct() {
if (_xScopes.size() > 1) throw errorSyntax("struct declarations can only appear in top level scope");
String typeName = requireId();
if ( OBJS.containsKey(typeName)) throw errorSyntax("struct '" + typeName + "' cannot be redefined");
ArrayList
* while ( expression ) statement
*
* @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
// point, and second is back edge that is set after loop is parsed
// (see end_loop() call below). Note that the absence of back edge is
// used as an indicator to switch off peepholes of the region and
// associated phis; see {@code inProgress()}.
ctrl(new LoopNode(ctrl()).peephole()); // Note we set back edge to null here
// At loop head, we clone the current Scope (this includes all
// names in every nesting level within the Scope).
// We create phis eagerly for all the names we find, see dup().
// Save the current scope as the loop head
ScopeNode head = _scope.keep();
// Clone the head Scope to create a new Scope for the body.
// Create phis eagerly as part of cloning
_xScopes.push(_scope = _scope.dup(true)); // The true argument triggers creating phis
// Parse predicate
var pred = require(parseExpression(), ")");
// IfNode takes current control and predicate
Node ifNode = new IfNode(ctrl(), pred).peephole();
// Setup projection nodes
Node ifT = new ProjNode(ifNode. keep(), 0, "True" ).peephole().keep();
Node ifF = new ProjNode(ifNode.unkeep(), 1, "False").peephole();
// 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.unkeep()); // set ctrl token to ifTrue projection
parseStatement(); // Parse loop body
// 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;
}
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.ctrl(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
*
*
* if ( expression ) statement [else statement]
*
* @return a {@link Node}, never {@code null}
*/
private Node parseIf() {
require("(");
// Parse predicate
var pred = require(parseExpression(), ")").keep();
// IfNode takes current control and predicate
Node ifNode = new IfNode(ctrl(), pred).peephole();
// Setup projection nodes
Node ifT = new ProjNode(ifNode. keep(), 0, "True" ).peephole().keep();
Node ifF = new ProjNode(ifNode.unkeep(), 1, "False").peephole().keep();
// In if true branch, the ifT proj node becomes the ctrl
// But first clone the scope and set it as current
int ndefs = _scope.nIns();
ScopeNode fScope = _scope.dup(); // Duplicate current scope
fScope.ctrl(ifF); // The pending arm already starts at False
_xScopes.push(fScope); // For graph visualization we need all scopes
// Parse the true side
ctrl(ifT.unkeep()); // set ctrl token to ifTrue projection
_scope.upcast(ifT,pred,false); // Up-cast predicate
parseStatement(); // Parse true-side
ScopeNode tScope = _scope;
// Parse the false side
_scope = fScope; // Restore scope, then parse else block if any
ifF.unkeep(); // fScope already owns the false control
if (matchx("else")) {
_scope.upcast(ifF,pred,true); // Up-cast predicate
parseStatement();
fScope = _scope;
}
pred.unkeep();
if( tScope.nIns() != ndefs || fScope.nIns() != ndefs )
throw error("Cannot define a new name on one arm of an if");
// Merge results
_scope = tScope;
_xScopes.pop(); // Discard pushed from graph display
return ctrl(tScope.mergeScopes(fScope));
}
/**
* Parses a return statement; "return" already parsed.
* The $ctrl edge is killed.
*
*
* 'return' expr ;
*
* @return an expression {@link Node}, never {@code null}
*/
private Node parseReturn() {
var expr = require(parseExpression(), ";");
Node ret = STOP.addReturn(new ReturnNode(ctrl(), expr, _scope).peephole());
ctrl(new ConstantNode(Type.XCONTROL).peephole()); // Kill control
return ret;
}
/**
* Parses an expression statement or a declaration statement where type is a struct
*
*
* name; // Error
* type name; // Define name with default initial value
* type name = expr; // Define name with given initial value
* name = expr; // Reassign existing
* expr // Something else
*
* @return an expression {@link Node}, never {@code null}
*/
private Node parseExpressionStatement() {
int old = _lexer._position;
Type t = type();
String name = requireId();
Node expr;
if( match(";") ) { // Assign a default value
// No type and no expr is an error
if( t==null ) throw errorSyntax("expression");
expr = new ConstantNode(t.makeInit()).peephole();
} else if( match("=") ) { // Assign "= expr;"
expr = require(parseExpression(), ";");
} else { // Neither, so just a normal expression parse
_lexer._position = old;
return require(parseExpression(),";");
}
// Defining a new variable vs updating an old one
if( t != null ) {
if( _scope.define(name,t,expr) == null )
throw error("Redefining name '" + name + "'");
} else {
Node n = _scope.lookup(name);
t = _scope.lookupDeclaredType(name);
if( n==null )
throw error("Undefined name '" + name + "'");
_scope.update(name,expr);
}
if( !expr._type.isa(t) )
throw error("Type " + expr._type.str() + " is not of declared type " + t.str());
return expr;
}
// Parse a type-or-null
private Type type() {
int old = _lexer._position;
String tname = _lexer.matchId();
if( tname==null ) return null;
if( tname.equals("int") ) return TypeInteger.BOT;
TypeStruct obj = OBJS.get(tname);
if( obj != null )
return TypeMemPtr.make(obj,match("?"));
// Not a type; unwind the parse
_lexer._position = old;
return null;
}
/**
* Parses a declStatement
*
*
* type name = expression ';'
*
* @return an expression {@link Node}
*/
private Node parseDecl(Type t) {
var name = requireId();
var expr = match(";")
// Assign a null value
? new ConstantNode(t.makeInit()).peephole()
// Assign "= expr;"
: require(require("=").parseExpression(), ";");
if( !expr._type.isa(t) )
throw error("Type " + expr._type.str() + " is not of declared type " + t.str());
if( _scope.define(name,t,expr) == null )
throw error("Redefining name '" + name + "'");
return expr;
}
/**
* Parse an expression of the form:
*
*
* expr : compareExpr
*
* @return an expression {@link Node}, never {@code null}
*/
private Node parseExpression() { return parseComparison(); }
/**
* Parse an expression of the form:
*
*
* expr : additiveExpr op additiveExpr
*
* @return an comparator expression {@link Node}, never {@code null}
*/
private Node parseComparison() {
var lhs = parseAddition();
while( true ) {
int idx=0; boolean negate=false;
// Test for any local nodes made, and "keep" lhs during peepholes
if( false ) ;
else if( match("==") ) { idx=2; lhs = new BoolNode.EQ(lhs, null); }
else if( match("!=") ) { idx=2; lhs = new BoolNode.EQ(lhs, null); negate=true; }
else if( match("<=") ) { idx=2; lhs = new BoolNode.LE(lhs, null); }
else if( match("<" ) ) { idx=2; lhs = new BoolNode.LT(lhs, null); }
else if( match(">=") ) { idx=1; lhs = new BoolNode.LE(null, lhs); }
else if( match(">" ) ) { idx=1; lhs = new BoolNode.LT(null, lhs); }
else break;
// Peepholes can fire, but lhs is already "hooked", kept alive
lhs.setDef(idx,parseAddition());
lhs = lhs.peephole();
if( negate ) // Extra negate for !=
lhs = new NotNode(lhs).peephole();
}
return lhs;
}
/**
* Parse an additive expression
*
*
* additiveExpr : multiplicativeExpr (('+' | '-') multiplicativeExpr)*
*
* @return an add expression {@link Node}, never {@code null}
*/
private Node parseAddition() {
Node lhs = parseMultiplication();
while( true ) {
if( false ) ;
else if( match("+") ) lhs = new AddNode(lhs,null);
else if( match("-") ) lhs = new SubNode(lhs,null);
else break;
lhs.setDef(2,parseMultiplication());
lhs = lhs.peephole();
}
return lhs;
}
/**
* Parse an multiplicativeExpr expression
*
*
* multiplicativeExpr : unaryExpr (('*' | '/') unaryExpr)*
*
* @return a multiply expression {@link Node}, never {@code null}
*/
private Node parseMultiplication() {
var lhs = parseUnary();
while( true ) {
if( false ) ;
else if( match("*") ) lhs = new MulNode(lhs,null);
else if( match("/") ) lhs = new DivNode(lhs,null);
else break;
lhs.setDef(2,parseUnary());
lhs = lhs.peephole();
}
return lhs;
}
/**
* Parse a unary minus expression.
*
*
* unaryExpr : ('-') | '!') unaryExpr | postfixExpr | primaryExpr
*
* @return a unary expression {@link Node}, never {@code null}
*/
private Node parseUnary() {
if (match("-")) return new MinusNode(parseUnary()).peephole();
if (match("!")) return new NotNode(parseUnary()).peephole();
return parsePostfix(parsePrimary());
}
/**
* Parse a primary expression:
*
*
* primaryExpr : integerLiteral | Identifier | true | false | null | new Identifier | '(' expression ')'
*
* @return a primary {@link Node}, never {@code null}
*/
private Node parsePrimary() {
if( _lexer.isNumber() ) return parseIntegerLiteral();
if( match("(") ) return require(parseExpression(), ")");
if( matchx("true" ) ) return new ConstantNode(TypeInteger.constant(1)).peephole();
if( matchx("false") ) return new ConstantNode(TypeInteger.constant(0)).peephole();
if( matchx("null" ) ) return new ConstantNode(TypeMemPtr.NULLPTR).peephole();
if( matchx("new") ) {
String structName = requireId();
TypeStruct obj = OBJS.get(structName);
if( obj == null) throw errorSyntax("Unknown struct type '" + structName + "'");
return newStruct(obj);
}
String name = _lexer.matchId();
if( name == null) throw errorSyntax("an identifier or expression");
Node n = _scope.lookup(name);
if( n!=null ) return n;
throw error("Undefined name '" + name + "'");
}
/**
* Return a NewNode but also generate instructions to initialize it.
*/
private Node newStruct( TypeStruct obj ) {
Node n = new NewNode(TypeMemPtr.make(obj), ctrl()).peephole().keep();
Node initValue = new ConstantNode(TypeInteger.constant(0)).peephole();
int alias = _aliases.get(obj._name);
for( Field field : obj._fields ) {
store(field._fname,alias,n,initValue);
alias++;
}
return n.unkeep();
}
// Memory is one hidden SSA variable, including across branches and loops.
private Node mem() { return _scope.lookup("$mem"); }
private Node mem(Node n) { return _scope.update("$mem",n); }
private void store(String name, int alias, Node ptr, Node val) {
Node prior = mem().keep();
Node st = new StoreNode(name,alias,prior,ptr,val).peephole();
mem(new MemMergeNode(prior,alias,st).peephole());
prior.unkeep();
}
/**
* Parse postfix expression. For now this is just a field
* expression, but in future could be array index too.
*
*
* expr ('.' IDENTIFIER)* [ = expr ]
*
*/
private Node parsePostfix(Node expr) {
if( !match(".") ) return expr;
if( !(expr._type instanceof TypeMemPtr ptr) )
throw error("Expected struct reference but got " + expr._type.str());
String name = requireId().intern();
int idx = ptr._obj==null ? -1 : ptr._obj.find(name);
if( idx == -1 ) throw error("Accessing unknown field '" + name + "' from '" + ptr.str() + "'");
int alias = _aliases.get(ptr._obj._name)+idx;
if( match("=") ) {
// Disambiguate "obj.fld==x" boolean test from "obj.fld=x" field assignment
if( peek('=') ) _lexer._position--;
else {
Node val = parseExpression();
store(name,alias,expr,val);
return expr; // "obj.a = expr" returns the expression while updating memory
}
}
Type declaredType = ptr._obj._fields[idx]._type;
return parsePostfix(new LoadNode(name, alias, declaredType, mem(), expr).peephole());
}
/**
* Parse integer literal
*
*
* integerLiteral: [1-9][0-9]* | [0]
*
*/
private ConstantNode parseIntegerLiteral() {
return (ConstantNode) new ConstantNode(_lexer.parseNumber()).peephole();
}
//////////////////////////////////
// Utilities for lexical analysis
// Return true and skip if "syntax" is next in the stream.
private boolean match (String syntax) { return _lexer.match (syntax); }
// Match must be "exact", not be followed by more id letters
private boolean matchx(String syntax) { return _lexer.matchx(syntax); }
// Return true and do NOT skip if 'ch' is next
private boolean peek(char ch) { return _lexer.peek(ch); }
private boolean peekIsId() { return _lexer.peekIsId(); }
// Require and return an identifier
private String requireId() {
String id = _lexer.matchId();
if (id != null && !KEYWORDS.contains(id) ) return id;
throw error("Expected an identifier, found '"+id+"'");
}
// Require an exact match
private Parser require(String syntax) { require(null, syntax); return this; }
private