void CompilationEngine::compileSubroutine()
{
/* ('constructor' | 'function' | 'method')
('void' | type) subroutineName '(' parameterList ')'
subroutineBody */
tagNonTerminal("subroutineDec");
if (jt.keyword() == Keyword::kCONSTRUCTOR)
readKeyword("constructor", Keyword::kCONSTRUCTOR);
else if (jt.keyword() == Keyword::kFUNCTION)
readKeyword("function", Keyword::kFUNCTION);
else
readKeyword("method", Keyword::kMETHOD);
nextToken();
if (jt.tokenType() == TokenType::kKEYWORD && jt.keyword() == Keyword::kVOID)
readKeyword("void", Keyword::kVOID);
else
readType();
nextToken();
readIdentifier();
nextToken();
readSymbol('(');
nextToken();
compileParameterList();
readSymbol(')');
nextToken();
compileSubroutineBody();
untagNonTerminal("subroutineDec");
}
void CompilationEngine::compileClass()
{
/* 'class' className '{' classVarDec* subroutineDec* '}' */
tagNonTerminal("class");
nextToken();
readKeyword("class", Keyword::kCLASS);
nextToken();
readIdentifier();
nextToken();
readSymbol('{');
nextToken();
while (jt.tokenType() == TokenType::kKEYWORD
&& (jt.keyword() == Keyword::kFIELD || jt.keyword() == Keyword::kSTATIC))
compileClassVarDec();
while (jt.tokenType() == TokenType::kKEYWORD && (jt.keyword() == Keyword::kCONSTRUCTOR
|| jt.keyword() == Keyword::kFUNCTION || jt.keyword() == Keyword::kMETHOD))
compileSubroutine();
readSymbol('}');
untagNonTerminal("class");
if (jt.advance()) // jack language does not allow anything else beyond the class
throw CompilationException("jack language does not allow anything else beyond the class");
}
void CompilationEngine::compileSubroutineCall(string subName)
{
/*
subroutineName '(' expressionList ')' |
(className | varName) '.' subroutineName '(' expression ')'
*/
string oldTok = jt.getToken();
jt.setToken(subName);
readIdentifier();
jt.setToken(oldTok);
if (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == '(') {
readSymbol('(');
nextToken();
compileExpressionList();
readSymbol(')');
} else {
readSymbol('.');
nextToken();
readIdentifier();
nextToken();
readSymbol('(');
nextToken();
compileExpressionList();
readSymbol(')');
}
nextToken();
}
void CompilationEngine::compileClassVarDec()
{
/* ('static' | 'field') type varName (',' varName)* ';' */
tagNonTerminal("classVarDec");
if (jt.keyword() == Keyword::kFIELD)
readKeyword("field", Keyword::kFIELD);
else
readKeyword("static", Keyword::kSTATIC);
nextToken();
readType();
nextToken();
readIdentifier();
nextToken();
while (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == ',') {
readSymbol(',');
nextToken();
readIdentifier();
nextToken();
}
readSymbol(';');
untagNonTerminal("classVarDec");
nextToken();
}
void CompilationEngine::compileLet()
{
/*'let' varName('[' expression ']')? '=' expression ';' */
tagNonTerminal("letStatement");
readKeyword("let", Keyword::kLET);
nextToken();
readIdentifier();
nextToken();
if (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == '[') {
readSymbol('[');
nextToken();
compileExpression();
readSymbol(']');
nextToken();
}
readSymbol('=');
nextToken();
compileExpression();
readSymbol(';');
untagNonTerminal("letStatement");
nextToken();
}
void CompilationEngine::compileSubroutineBody()
{
/* '{' varDec* statements '}' */
tagNonTerminal("subroutineBody");
readSymbol('{');
nextToken();
while (jt.tokenType() == TokenType::kKEYWORD && jt.keyword() == Keyword::kVAR)
compileVarDec();
compileStatements();
readSymbol('}');
untagNonTerminal("subroutineBody");
nextToken();
}
void CompilationEngine::compileParameterList()
{
/* ((type varName)(',' type varName)*)? */
tagNonTerminal("parameterList");
if (jt.tokenType() != TokenType::kSYMBOL) {
readType();
nextToken();
readIdentifier();
nextToken();
while (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == ',') {
readSymbol(',');
nextToken();
readType();
nextToken();
readIdentifier();
nextToken();
}
}
untagNonTerminal("parameterList");
}
void CompilationEngine::compileWhile()
{
/* 'while' '(' expression ')' '{' statements '}' */
tagNonTerminal("whileStatement");
readKeyword("while", Keyword::kWHILE);
nextToken();
readSymbol('(');
nextToken();
compileExpression();
readSymbol(')');
nextToken();
readSymbol('{');
nextToken();
compileStatements();
readSymbol('}');
untagNonTerminal("whileStatement");
nextToken();
}
void CompilationEngine::compileDo()
{
/* 'do' subroutineCall ';' */
tagNonTerminal("doStatement");
readKeyword("do", Keyword::kDO);
nextToken();
compileSubroutineCall();
readSymbol(';');
untagNonTerminal("doStatement");
nextToken();
}
void LexicalAnalyzer::LexicalAnalyze(const string& srcCodeFilePath)
// an integrated automaton using if-else sentence
// according to current input symbol, a sub-automaton would be activated
{
FILE* fp = fopen("./test.cpp", "r");
char ch;
ch = fgetc(fp);
while(ch != EOF)
{
// cout << ch;
if(isalpha(ch) || ch == '_')
{
// cout << "will read id" << endl;
readID(fp, ch);
// cout << "read id ok" << endl;
}
else if(ch == '\'')
{
// cout << "will read character" << endl;
readCh(fp, ch);
// cout << "read character ok" << endl;
}
else if(ch == '\"')
{
// cout << "will read string" << endl;
readStr(fp, ch);
// cout << "read string ok" << endl;
}
else if(isdigit(ch))
{
// cout << "will read constant" << endl;
readConst(fp, ch);
// cout << "read constant ok" << endl;
}
else if(ch == ' ' || ch == '\t' || ch == '\n')
{
// cout << "will read space tab and newline" << endl;
readSpaceTabNewline(fp, ch);
// cout << "read space tab and newline ok" << endl;
}
else
{
// cout << "will read symbol" << endl;
readSymbol(fp, ch);
// cout << "read symbol ok" << endl;
}
}
// cout << endl;
fclose(fp);
}
static Object* ReaderReadInternal(Context* ctx, Reader* r) {
const char* token = r->tokenizer->token;
Object* result = readNumber(ctx, token);
if(!result) {
result = readList(ctx, token, r);
}
if(!result) {
result = readSymbol(ctx, token);
}
return result;
}
void CompilationEngine::compileIf()
{
/* 'if' '(' expression ')' '{' statements '}'
('else' '{' statements '}')? */
tagNonTerminal("ifStatement");
readKeyword("if", Keyword::kIF);
nextToken();
readSymbol('(');
nextToken();
compileExpression();
readSymbol(')');
nextToken();
readSymbol('{');
nextToken();
compileStatements();
readSymbol('}');
nextToken();
if (jt.tokenType() == TokenType::kKEYWORD && jt.keyword() == Keyword::kELSE) {
readKeyword("else", Keyword::kELSE);
nextToken();
readSymbol('{');
nextToken();
compileStatements();
readSymbol('}');
nextToken();
}
untagNonTerminal("ifStatement");
}
void CompilationEngine::compileVarDec()
{
/* 'var' type varName (',' varName)* ';' */
tagNonTerminal("varDec");
readKeyword("var", Keyword::kVAR);
nextToken();
readType();
nextToken();
readIdentifier();
nextToken();
while (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == ',') {
readSymbol(',');
nextToken();
readIdentifier();
nextToken();
}
readSymbol(';');
untagNonTerminal("varDec");
nextToken();
}
void CompilationEngine::compileReturn()
{
/* 'return' expression? ';' */
tagNonTerminal("returnStatement");
readKeyword("return", Keyword::kRETURN);
nextToken();
if (jt.tokenType() != TokenType::kSYMBOL || (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() != ';'))
compileExpression();
readSymbol(';');
untagNonTerminal("returnStatement");
nextToken();
}
void CompilationEngine::compileExpressionList()
{
// (expression(',' expression)*)?
tagNonTerminal("expressionList");
if (jt.tokenType() != TokenType::kSYMBOL || (jt.symbol() == '(' ))
compileExpression();
while (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == ',') {
readSymbol(',');
nextToken();
compileExpression();
}
untagNonTerminal("expressionList");
}
static void findAsmTags (void)
{
vString *name = vStringNew ();
vString *operator = vStringNew ();
const unsigned char *line;
boolean inCComment = FALSE;
while ((line = readLineFromInputFile ()) != NULL)
{
const unsigned char *cp = line;
boolean labelCandidate = (boolean) (! isspace ((int) *cp));
boolean nameFollows = FALSE;
const boolean isComment = (boolean)
(*cp != '\0' && strchr (";*@", *cp) != NULL);
/* skip comments */
if (strncmp ((const char*) cp, "/*", (size_t) 2) == 0)
{
inCComment = TRUE;
cp += 2;
}
if (inCComment)
{
do
{
if (strncmp ((const char*) cp, "*/", (size_t) 2) == 0)
{
inCComment = FALSE;
cp += 2;
break;
}
++cp;
} while (*cp != '\0');
}
if (isComment || inCComment)
continue;
/* read preprocessor defines */
if (*cp == '#')
{
++cp;
readPreProc (cp);
continue;
}
/* skip white space */
while (isspace ((int) *cp))
++cp;
/* read symbol */
cp = readSymbol (cp, name);
if (vStringLength (name) > 0 && *cp == ':')
{
labelCandidate = TRUE;
++cp;
}
if (! isspace ((int) *cp) && *cp != '\0')
continue;
/* skip white space */
while (isspace ((int) *cp))
++cp;
/* skip leading dot */
#if 0
if (*cp == '.')
++cp;
#endif
cp = readOperator (cp, operator);
/* attempt second read of symbol */
if (vStringLength (name) == 0)
{
while (isspace ((int) *cp))
++cp;
cp = readSymbol (cp, name);
nameFollows = TRUE;
}
makeAsmTag (name, operator, labelCandidate, nameFollows);
}
vStringDelete (name);
vStringDelete (operator);
}
llvm::Expected<IndexFileIn> readRIFF(llvm::StringRef Data) {
auto RIFF = riff::readFile(Data);
if (!RIFF)
return RIFF.takeError();
if (RIFF->Type != riff::fourCC("CdIx"))
return makeError("wrong RIFF type");
llvm::StringMap<llvm::StringRef> Chunks;
for (const auto &Chunk : RIFF->Chunks)
Chunks.try_emplace(llvm::StringRef(Chunk.ID.data(), Chunk.ID.size()),
Chunk.Data);
for (llvm::StringRef RequiredChunk : {"meta", "stri"})
if (!Chunks.count(RequiredChunk))
return makeError("missing required chunk " + RequiredChunk);
Reader Meta(Chunks.lookup("meta"));
if (Meta.consume32() != Version)
return makeError("wrong version");
auto Strings = readStringTable(Chunks.lookup("stri"));
if (!Strings)
return Strings.takeError();
IndexFileIn Result;
if (Chunks.count("srcs")) {
Reader SrcsReader(Chunks.lookup("srcs"));
Result.Sources.emplace();
while (!SrcsReader.eof()) {
auto IGN = readIncludeGraphNode(SrcsReader, Strings->Strings);
auto Entry = Result.Sources->try_emplace(IGN.URI).first;
Entry->getValue() = std::move(IGN);
// We change all the strings inside the structure to point at the keys in
// the map, since it is the only copy of the string that's going to live.
Entry->getValue().URI = Entry->getKey();
for (auto &Include : Entry->getValue().DirectIncludes)
Include = Result.Sources->try_emplace(Include).first->getKey();
}
if (SrcsReader.err())
return makeError("malformed or truncated include uri");
}
if (Chunks.count("symb")) {
Reader SymbolReader(Chunks.lookup("symb"));
SymbolSlab::Builder Symbols;
while (!SymbolReader.eof())
Symbols.insert(readSymbol(SymbolReader, Strings->Strings));
if (SymbolReader.err())
return makeError("malformed or truncated symbol");
Result.Symbols = std::move(Symbols).build();
}
if (Chunks.count("refs")) {
Reader RefsReader(Chunks.lookup("refs"));
RefSlab::Builder Refs;
while (!RefsReader.eof()) {
auto RefsBundle = readRefs(RefsReader, Strings->Strings);
for (const auto &Ref : RefsBundle.second) // FIXME: bulk insert?
Refs.insert(RefsBundle.first, Ref);
}
if (RefsReader.err())
return makeError("malformed or truncated refs");
Result.Refs = std::move(Refs).build();
}
return std::move(Result);
}
static void findAsmTags (void)
{
vString *name = vStringNew ();
vString *operator = vStringNew ();
const unsigned char *line;
cppInit (false, false, false, false,
KIND_GHOST_INDEX, 0, KIND_GHOST_INDEX, 0, 0);
unsigned int lastMacroCorkIndex = CORK_NIL;
while ((line = asmReadLineFromInputFile ()) != NULL)
{
const unsigned char *cp = line;
bool labelCandidate = (bool) (! isspace ((int) *cp));
bool nameFollows = false;
bool directive = false;
const bool isComment = (bool)
(*cp != '\0' && strchr (";*@", *cp) != NULL);
/* skip comments */
if (isComment)
continue;
/* skip white space */
while (isspace ((int) *cp))
++cp;
/* read symbol */
if (*cp == '.')
{
directive = true;
labelCandidate = false;
++cp;
}
cp = readSymbol (cp, name);
if (vStringLength (name) > 0 && *cp == ':')
{
labelCandidate = true;
++cp;
}
if (! isspace ((int) *cp) && *cp != '\0')
continue;
/* skip white space */
while (isspace ((int) *cp))
++cp;
/* skip leading dot */
#if 0
if (*cp == '.')
++cp;
#endif
cp = readOperator (cp, operator);
/* attempt second read of symbol */
if (vStringLength (name) == 0)
{
while (isspace ((int) *cp))
++cp;
cp = readSymbol (cp, name);
nameFollows = true;
}
makeAsmTag (name, operator, labelCandidate, nameFollows, directive,
&lastMacroCorkIndex);
}
cppTerminate ();
vStringDelete (name);
vStringDelete (operator);
}
OBJ
js_read(OBJ inStream){
OBJ retVal;
prompt_off();
char ch = skipWhiteSpace(inStream);
if( ch == -1){
retVal = js_eof;
unreadChar(inStream, ch);
}
else if(ch == '('){
retVal = readList(inStream);
}
else if(ch =='\''){
OBJ expr = js_read(inStream);
// (quote (expr* (nil))) -> expr must be a cons
return newCons(symbolTableGetOrAdd("quote"),
newCons(expr, js_nil));
}
else if(ch == '"'){
retVal = readString(inStream);
}
else if(isDigit(ch)){
retVal = readNumber(inStream, ch, 0);
}else if(ch == '-'){
/*
* TO-DO refactor: implement proper read ahead solution
*/
// simple read ahead to catch negative numbers
char nextCh = nextChar(inStream);
if(isDigit(nextCh)){
retVal = readNumber(inStream, nextCh, 1);
}else{
unreadChar(inStream, nextCh);
retVal = readSymbol(inStream, ch);
}
}
#ifdef DEBUG
else if(ch == '%'){
ch = nextChar(inStream);
OBJ debugOption;
if(ch == '\n' ){
unreadChar(inStream, ch);
debugOption = newSymbol("");
}else{
debugOption = readSymbol(inStream, ch);
}
switchDebugOptions( debugOption );
retVal = js_void;
}
#endif
else {
retVal = readSymbol(inStream, ch);
}
if(thisIsTheEnd(inStream)){
prompt_on();
};
return retVal;
}
void CompilationEngine::compileTerm() // 362
{
// integerConst | stringConst | keywordConst |
// varName | varName '[' expression ']' | subroutineCall |
// '(' expression ')' | unaryOp term
tagNonTerminal("term");
string id;
string oldTok;
switch(jt.tokenType()) {
case TokenType::kINT_CONST:
readIntConst();
break;
case TokenType::kSTRING_CONST:
readStringConst();
break;
case TokenType::kKEYWORD:
readKeywordConstant();
break;
case TokenType::kIDENTIFIER:
id = jt.getToken(); // save current token
nextToken();
if (jt.tokenType() == TokenType::kSYMBOL && jt.symbol() == '[') {
oldTok = jt.getToken();
jt.setToken(id);
readIdentifier();
jt.setToken(oldTok);
readSymbol('[');
nextToken();
compileExpression();
readSymbol(']');
nextToken();
} else if (jt.tokenType() == TokenType::kSYMBOL && (jt.symbol() == '.' || jt.symbol() == '(')) {
compileSubroutineCall(id);
} else {
oldTok = jt.getToken();
jt.setToken(id);
readIdentifier();
jt.setToken(oldTok);
}
untagNonTerminal("term");
return; // has already advanced
break;
case TokenType::kSYMBOL:
if (jt.symbol() == '(') { // '(' expression ')'
readSymbol('(');
nextToken();
compileExpression();
readSymbol(')');
} else { // unaryOp term
readUnaryOp();
nextToken();
compileTerm();
untagNonTerminal("term");
return; // has already advanced
}
break;
default:
break;
}
nextToken();
untagNonTerminal("term");
}
