Der Scanner zerlegt eine Eingabe in ihre Token.

a = 23
b = 5

q = 0
r = a
while r>=b:
    r = r-b
    q = q+1
#end
 
print(q)

Der Minipython-Scanner

import ply.lex as lex

reserved = {'while' : 'WHILE',
            'if'    : 'IF',
            'else'  : 'ELSE',
            'pass'  : 'PASS'}

tokens = ['VAR','NUM','END','OP'] + list(reserved.values())                       
literals = "=:+-"
    
def t_IGN(t):
    r'print\(.*'
    # kein return, damit die Zeile vom Parser nicht gesehen wird
   
def t_VAR(t):
    r'[a-zA-Z_][a-zA-Z_0-9]*'
    t.type = reserved.get(t.value,'VAR')
    return t                             

def t_NUM(t):
    r'\d+'
    t.value = int(t.value)
    return t

def t_END(t):
    r'\#end'
    return t

def t_OP(t):
    r'=?|==|!='
    return t

def t_newline(t):
    r'\n+'
    t.lexer.lineno = t.lexer.lineno + len(t.value)

t_ignore  = ' \t'

def t_error(t):
    print('Unerwartetes Zeichen:',t.value[0],',Zeile:',s.lineno)
    t.lexer.skip(1)

s = lex.lex()

Test

>>> s.input("""
a = 23
b = 5

q = 0
r = a
while r>=b:
    r = r-b
    q = q+1
#end
 
print(q)
print(r)""")
>>> while True:
	t = s.token()
	print(t)
	if t == None: break

	
LexToken(VAR,'a',2,1)
LexToken(=,'=',2,3)
LexToken(NUM,23,2,5)
LexToken(VAR,'b',3,8)
LexToken(=,'=',3,10)
LexToken(NUM,5,3,12)
LexToken(VAR,'q',5,15)
LexToken(=,'=',5,17)
LexToken(NUM,0,5,19)
LexToken(VAR,'r',6,21)
LexToken(=,'=',6,23)
LexToken(VAR,'a',6,25)
LexToken(WHILE,'while',7,27)
LexToken(VAR,'r',7,33)
LexToken(OP,'>=',7,34)
LexToken(VAR,'b',7,36)
LexToken(:,':',7,37)
LexToken(VAR,'r',8,43)
LexToken(=,'=',8,45)
LexToken(VAR,'r',8,47)
LexToken(-,'-',8,48)
LexToken(VAR,'b',8,49)
LexToken(VAR,'q',9,55)
LexToken(=,'=',9,57)
LexToken(VAR,'q',9,59)
LexToken(+,'+',9,60)
LexToken(NUM,1,9,61)
LexToken(END,'#end',10,63)
None
>>> 

Aufgabe

Teste weitere Eingaben, z.B.

a=17b=345if b=7 #end while :

oder

JamesBond 007

oder

42;otto

oder

...