/**
* build the token for operators (+ -) or separators (parens, braces) filter out comments which
* begin with two slashes
*
* @param s is the String representing the token
* @param startPosition is the column in the source file where the token begins
* @param endPosition is the column in the source file where the token ends
* @return the Token just found
*/
public Token makeToken(String s, int startPosition, int endPosition) {
if (s.equals("//")) { // filter comment
try {
int oldLine = source.getLineno();
do {
ch = source.read();
} while (oldLine == source.getLineno());
} catch (Exception e) {
atEOF = true;
}
return nextToken();
}
Symbol sym = Symbol.symbol(s, Tokens.BogusToken); // be sure it's a valid token
if (sym == null) {
System.out.println("******** illegal character: " + s + " " + "Line: " + source.getLineno());
atEOF = true;
return nextToken();
}
return new Token(startPosition, endPosition, sym);
}
public void initialize() {
venv = new Table();
tenv = new Table();
NAME nameint = new NAME(Symbol.symbol("int"));
nameint.bind(new INT());
tenv.put(nameint.name, nameint);
NAME namestring = new NAME(Symbol.symbol("string"));
namestring.bind(new STRING());
tenv.put(namestring.name, namestring);
NAME namenil = new NAME(Symbol.symbol("nil"));
namenil.bind(new NIL());
tenv.put(namenil.name, namenil);
Symbol print = Symbol.symbol("print");
RECORD printargu = new RECORD(Symbol.symbol("s"), newstring, null);
venv.put(
print,
new FunEntry(
new Level(Semant.globalLevZero, print, new BoolList(true, null)),
new Label(),
printargu,
newvoid,
true));
Symbol printi = Symbol.symbol("printi");
RECORD printiargu = new RECORD(Symbol.symbol("i"), newint, null);
venv.put(
printi,
new FunEntry(
new Level(Semant.globalLevZero, printi, new BoolList(true, null)),
new Label(),
printiargu,
newvoid,
true));
Symbol flush = Symbol.symbol("flush");
RECORD flushargu = null;
venv.put(
flush,
new FunEntry(
new Level(Semant.globalLevZero, flush, null), new Label(), flushargu, newvoid, true));
Symbol getchar = Symbol.symbol("getchar");
RECORD getcharargu = null;
venv.put(
getchar,
new FunEntry(
new Level(Semant.globalLevZero, getchar, null),
new Label(),
getcharargu,
newstring,
true));
Symbol ord = Symbol.symbol("ord");
RECORD ordargu = new RECORD(Symbol.symbol("s"), newstring, null);
venv.put(
ord,
new FunEntry(
new Level(Semant.globalLevZero, ord, new BoolList(true, null)),
new Label(),
ordargu,
newint,
true));
Symbol chr = Symbol.symbol("chr");
RECORD chrargu = new RECORD(Symbol.symbol("i"), newint, null);
venv.put(
chr,
new FunEntry(
new Level(Semant.globalLevZero, chr, new BoolList(true, null)),
new Label(),
chrargu,
newstring,
true));
Symbol size = Symbol.symbol("size");
RECORD sizeargu = new RECORD(Symbol.symbol("s"), newstring, null);
venv.put(
size,
new FunEntry(
new Level(Semant.globalLevZero, size, new BoolList(true, null)),
new Label(),
sizeargu,
newint,
true));
Symbol substring = Symbol.symbol("substring");
RECORD substringargu3 = new RECORD(Symbol.symbol("n"), newint, null);
RECORD substringargu2 = new RECORD(Symbol.symbol("first"), newint, substringargu3);
RECORD substringargu1 = new RECORD(Symbol.symbol("s"), newstring, substringargu2);
RECORD substringargu = substringargu1;
venv.put(
substring,
new FunEntry(
new Level(
Semant.globalLevZero,
substring,
new BoolList(true, new BoolList(true, new BoolList(true, null)))),
new Label(),
substringargu,
newstring,
true));
Symbol concat = Symbol.symbol("concat");
RECORD concatargu2 = new RECORD(Symbol.symbol("s2"), newstring, null);
RECORD concatargu1 = new RECORD(Symbol.symbol("s1"), newstring, concatargu2);
RECORD concatargu = concatargu1;
venv.put(
concat,
new FunEntry(
new Level(Semant.globalLevZero, concat, new BoolList(true, new BoolList(true, null))),
new Label(),
concatargu,
newstring,
true));
Symbol not = Symbol.symbol("not");
RECORD notargu = new RECORD(Symbol.symbol("i"), newint, null);
venv.put(
not,
new FunEntry(
new Level(Semant.globalLevZero, not, new BoolList(true, null)),
new Label(),
notargu,
newint,
true));
Symbol exit = Symbol.symbol("exit");
RECORD exitargu = new RECORD(Symbol.symbol("i"), newint, null);
venv.put(
exit,
new FunEntry(
new Level(Semant.globalLevZero, exit, new BoolList(true, null)),
new Label(),
exitargu,
newvoid,
true));
}
public Token newCharToken(String number, int startPosition2, int endPosition2) {
return new Token(startPosition, endPosition, Symbol.symbol(number, Tokens.Char));
}
public Token newSciToken(String number, int startPosition2, int endPosition2) {
return new Token(startPosition, endPosition, Symbol.symbol(number, Tokens.ScientificN));
}
public Token newFloatToken(String number, int startPosition, int endPosition) {
return new Token(startPosition, endPosition, Symbol.symbol(number, Tokens.Float));
}
/**
* number tokens are inserted in the symbol table; we don't convert the numeric strings to numbers
* until we load the bytecodes for interpreting; this ensures that any machine numeric
* dependencies are deferred until we actually run the program; i.e. the numeric constraints of
* the hardware used to compile the source program are not used
*
* @param number is the int String just scanned
* @param startPosition is the column in the source file where the int begins
* @param endPosition is the column in the source file where the int ends
* @return the int Token
*/
public Token newNumberToken(String number, int startPosition, int endPosition) {
return new Token(startPosition, endPosition, Symbol.symbol(number, Tokens.INTeger));
}
/**
* newIdTokens are either ids or reserved words; new id's will be inserted in the symbol table
* with an indication that they are id's
*
* @param id is the String just scanned - it's either an id or reserved word
* @param startPosition is the column in the source file where the token begins
* @param endPosition is the column in the source file where the token ends
* @return the Token; either an id or one for the reserved words
*/
public Token newIdToken(String id, int startPosition, int endPosition) {
return new Token(startPosition, endPosition, Symbol.symbol(id, Tokens.Identifier));
}
/** @return the next Token found in the source file */
public Token nextToken() { // ch is always the next char to process
if (atEOF) {
if (source != null) {
source.close();
source = null;
}
return null;
}
try {
while (Character.isWhitespace(ch)) { // scan past whitespace
ch = source.read();
}
} catch (Exception e) {
atEOF = true;
return nextToken();
}
startPosition = source.getPosition();
endPosition = startPosition - 1;
if (Character.isJavaIdentifierStart(ch)) {
// return tokens for ids and reserved words
String id = "";
try {
do {
endPosition++;
id += ch;
ch = source.read();
} while (Character.isJavaIdentifierPart(ch));
} catch (Exception e) {
atEOF = true;
}
return newIdToken(id, startPosition, endPosition);
}
// This block is a translation of state diagram that I drew
// case number starts with digit
if (Character.isDigit(ch)) {
try {
String number = "";
// Read the second item
endPosition++;
number += ch;
ch = source.read();
// check if the second item is digit, decimal or neither
// second item is digit
if (Character.isDigit(ch)) {
// move to section 1 then checke for decimal
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
if (ch == '.') {
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
return newFloatToken(number, startPosition, endPosition);
} else {
return newNumberToken(number, startPosition, endPosition);
}
} // second item is decimal
else if (ch == '.') {
// move to section 2 check for scientific notaiton
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
if (ch == 'E' || ch == 'e') {
// move to scientific notation
endPosition++;
number += ch;
ch = source.read();
if (ch == '+' || ch == '-') {
endPosition++;
number += ch;
ch = source.read();
if (Character.isDigit(ch)) {
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
return newSciToken(number, startPosition, endPosition);
} else {
return newErrorToken(number, startPosition, endPosition);
}
} else if (Character.isDigit(ch)) {
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
return newSciToken(number, startPosition, endPosition);
} else {
return newErrorToken(number, startPosition, endPosition);
}
} else {
return newFloatToken(number, startPosition, endPosition);
}
} // second item is none
else {
return newNumberToken(number, startPosition, endPosition);
}
} catch (IOException e) {
e.printStackTrace();
}
}
// case number starts with decimal
if (ch == '.') {
try {
String number = "";
endPosition++;
number += ch;
ch = source.read();
// digit followed by decimal
if (Character.isDigit(ch)) {
do {
endPosition++;
number += ch;
ch = source.read();
} while (Character.isDigit(ch));
return newFloatToken(number, startPosition, endPosition);
} else {
return newErrorToken(number, startPosition, endPosition);
}
} catch (IOException e) {
e.printStackTrace();
}
}
// Check for char, if it is followed by '
if (ch == '\'') {
try {
String character = "";
// Read the second item
endPosition++;
character += ch;
ch = source.read();
if (ch == '\'') // quote followed by qoute is error
{
return newErrorToken(character, startPosition, endPosition);
} else {
endPosition++;
character += ch;
ch = source.read();
if (ch == '\'') // quote followed by a char followed by a qoute
{
endPosition++;
character += ch;
ch = source.read();
return newCharToken(character, startPosition, endPosition);
} else // quote followed by no closing qoute after 1 letter throws an error token
{
return newErrorToken(character, startPosition, endPosition);
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
// At this point the only tokens to check for are one or two
// characters; we must also check for comments that begin with
// 2 slashes
String charOld = "" + ch;
String op = charOld;
Symbol sym;
try {
endPosition++;
ch = source.read();
op += ch;
// check if valid 2 char operator; if it's not in the symbol
// table then don't insert it since we really have a one char
// token
sym = Symbol.symbol(op, Tokens.BogusToken);
if (sym == null) { // it must be a one char token
return makeToken(charOld, startPosition, endPosition); // return error token
}
endPosition++;
ch = source.read();
return makeToken(op, startPosition, endPosition);
} catch (Exception e) {
}
atEOF = true;
if (startPosition == endPosition) {
op = charOld;
}
return makeToken(op, startPosition, endPosition);
}
Env(ErrorMsg err) {
errorMsg = err;
fenv = new Table();
tenv = new Table();
Symbol i, s;
i = Symbol.symbol("int");
s = Symbol.symbol("string");
// Types.RECORD trec=null;
// Label lab;
// BoolList formals;
tenv.put(i, new Types.INT());
tenv.put(s, new Types.STRING());
fenv.put(Symbol.symbol("print"), new Types.VOID());
fenv.put(Symbol.symbol("printi"), new Types.VOID());
fenv.put(Symbol.symbol("flush"), new Types.VOID());
fenv.put(Symbol.symbol("getchar"), new Types.STRING());
fenv.put(Symbol.symbol("ord"), new Types.INT());
fenv.put(Symbol.symbol("chr"), new Types.STRING());
fenv.put(Symbol.symbol("size"), new Types.INT());
fenv.put(Symbol.symbol("substring"), new Types.STRING());
fenv.put(Symbol.symbol("concat"), new Types.STRING());
fenv.put(Symbol.symbol("not"), new Types.INT());
fenv.put(Symbol.symbol("exit"), new Types.VOID());
}
public static void main(String[] args) {
Table<Integer> t = new Table<Integer>();
t.put(Symbol.symbol("abc"), new Integer(1));
t.put(Symbol.symbol("efg"), new Integer(2));
System.out.println(t.get(Symbol.symbol("efg")));
System.out.println(t.get(Symbol.symbol("")));
t.put(Symbol.symbol("efg"), new Integer(3));
System.out.println(t.get(Symbol.symbol("efg")));
t.beginScope();
System.out.println(t.get(Symbol.symbol("efg")));
t.put(Symbol.symbol("efg"), new Integer(4));
System.out.println(t.get(Symbol.symbol("efg")));
t.put(Symbol.symbol("efg"), new Integer(5));
System.out.println(t.get(Symbol.symbol("efg")));
t.put(Symbol.symbol("new"), new Integer(6));
System.out.println(t.get(Symbol.symbol("d")));
System.out.println(t.get(Symbol.symbol("new")));
t.endScope();
System.out.println(t.get(Symbol.symbol("efg")));
System.out.println(t.get(Symbol.symbol("new")));
}
