Exercises for Section 2.6
2.6.1
Extend the lexical analyzer in Section 2.6.5 to remove comments, defined as
follows:
- A comment begins with // and includes all characters until the end of that line.
- A comment begins with /* and includes all characters through the next occurrence of the character sequence */.
2.6.2
Extend the lexical analyzer in Section 2.6.5 to recognize the relational operators <, <=, ==, ! =, >=, >.
2.6.3
Extend the lexical analyzer in Section 2.6.5 to recognize floating point numbers
such as 2., 3.14, and . 5.
Answer
Source code: commit 8dd1a9a
Code snippet(src/lexer/Lexer.java):
public Token scan() throws IOException, SyntaxException{
for(;;peek = (char)stream.read()){
if(peek == ' ' || peek == '\t'){
continue;
}else if(peek == '\n'){
line = line + 1;
}else{
break;
}
}
// handle comment
if(peek == '/'){
peek = (char) stream.read();
if(peek == '/'){
// single line comment
for(;;peek = (char)stream.read()){
if(peek == '\n'){
break;
}
}
}else if(peek == '*'){
// block comment
char prevPeek = ' ';
for(;;prevPeek = peek, peek = (char)stream.read()){
if(prevPeek == '*' && peek == '/'){
break;
}
}
}else{
throw new SyntaxException();
}
}
// handle relation sign
if("<=!>".indexOf(peek) > -1){
StringBuffer b = new StringBuffer();
b.append(peek);
peek = (char)stream.read();
if(peek == '='){
b.append(peek);
}
return new Rel(b.toString());
}
// handle number, no type sensitive
if(Character.isDigit(peek) || peek == '.'){
Boolean isDotExist = false;
StringBuffer b = new StringBuffer();
do{
if(peek == '.'){
isDotExist = true;
}
b.append(peek);
peek = (char)stream.read();
}while(isDotExist == true ? Character.isDigit(peek) : Character.isDigit(peek) || peek == '.');
return new Num(new Float(b.toString()));
}
// handle word
if(Character.isLetter(peek)){
StringBuffer b = new StringBuffer();
do{
b.append(peek);
peek = (char)stream.read();
}while(Character.isLetterOrDigit(peek));
String s = b.toString();
Word w = words.get(s);
if(w == null){
w = new Word(Tag.ID, s);
words.put(s, w);
}
return w;
}
Token t = new Token(peek);
peek = ' ';
return t;
}