# Stephanie Taylor
# CS333
# Spring 2026
# Tokenizer for simple examples in lecture

# T -> 0 | ... | 9
# "+"		{ echo (); return new Token (TokenClass . PLUS); }
# "-"		{ echo (); return new Token (TokenClass . MINUS); }

# The value field will always be a string. This makes it easier for the parsing.s

class Token:
    def __init__( self, value ):
        self.value = value
    def __str__( self ):
        return str(self.value)
        
class Tokenizer:

    def __init__( self, filename=None, lines=None ):
        """
        If a filename is given, open it and store the lines as a list of strings.
        else if lines is not None, store the lines
        else don't really do anything (not useful)
        """
        if filename is not None:
            fobj = open( filename )
            self.lines = fobj.readlines()
            fobj.close()
        elif lines is not None:
            self.lines = lines
        self.cur_line = 0
        self.cur_index = 0
        
    # Increment the line and column indices until they indicate the
    # beginning of a token.
    def passWhitespace(self):
        if self.cur_line == len(self.lines):
            return
        if self.cur_index == len(self.lines[self.cur_line]):
            self.cur_line += 1
            self.cur_index = 0
            self.passWhitespace()
            return
        foundIt = False
        # search this line for a non-whitespace character
        for self.cur_index in range(self.cur_index,len(self.lines[self.cur_line])):
            if self.lines[self.cur_line][self.cur_index] not in " \t\n\r":
                foundIt = True
                break
        # if we are still in whitespace, go on to the next line
        if self.cur_index == len(self.lines[self.cur_line])-1 and not foundIt:
            self.cur_line += 1
            self.cur_index = 0
            self.passWhitespace()
        # If we find a comment, then we need to skip the rest of the line
        # and go on to the next.
        elif self.lines[self.cur_line][self.cur_index:self.cur_index+2] == '//':
            self.cur_line += 1
            self.cur_index = 0
            self.passWhitespace()
                
    def getToken(self):
        self.passWhitespace()
        if self.cur_line == len(self.lines):
            # We are at the end of the file. No more tokens
            return None
        cur_char  = self.lines[self.cur_line][self.cur_index]
        if cur_char in "+-":
            self.cur_index += 1
            return Token( cur_char )
        elif cur_char in "0123456789":
            self.cur_index += 1
            return Token( cur_char )
        else:
            print( "Problem - can't identify", cur_char )
        
if __name__ == '__main__':
    t = Tokenizer( lines=['3 - 4+5 '])
    while True:
        tok = t.getToken()
        if tok is None:
            break
        print( tok )