buf=[]
token=[]
def lex():

def read():
    
    f=open('lex.txt','r')
    data=f.readline()
    data=data.split(' ')
    return data

lex=read()

def operator(i):
    
    op=[' ','-','/','*','<','>','>=','<=']
    
    if i in op:
        buf.append(i)
        token.append('RELOP')
        return True
def error(i):
    
    digit=[0,1,2,3,4,5,6,7,8,9,0]
    
    try:
    
        if i[0] in digit:
            buf.append(i)
            token.append('ERROR')
            return True
    except:
        pass
    
def keyword(i):
    
    keyword=['if','while','for']
    
    if i in keyword:
        buf.append(i)
        x=i.upper()
        token.append(x '_TOKEN')
        return True
        
def ident(i):
    
    alph=['a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','q','r','s','t','u','v','w','x','y','z']
    
    try:
        
        if i[0] in alph:
            buf.append(i)
            token.append('ID')
            return True
    
    except:
        pass
        
    
def floati(i):
    
    try:
        res = i.replace('.', '', 1).isdigit()
        if res:
            buf.append(i)
            token.append('FLOAT')
            return True
    
    except:
        pass
        
        
        
def integ(i):
    
    try:
        x=int(i)
        buf.append(i)
        token.append('INTEGER')
        return True
    except:
        pass

count=0

for i in lex:
    
    if keyword(i):
        
        print(token[count])
        
        continue
    
    elif operator(i):
        
        print(token[count])
        continue
    elif error(i):
        
        print(token[count])
        continue
    elif floati(i):
        
        print(token[count])
        continue
    elif integ(i):
        
        print(token[count])
        continue
    elif ident(i):
        
        print(token[count])
        continue
    else:
        
        print("Zaaa anan xd")
    
    count 1
    

lex()
    
  

I am trying to write a lexical analyzer in Python. I want to check an input string from a file for a float or integer, but when I use float() my code changes the string type of integer to float and returns as float. I do not want to check string using float() or int(). I want to append the string to an array without changing it.

CodePudding user response：

A simple way to check if a string is int or float:

def is_int(s):
    try:
        int(s)
        return True
    except ValueError:
        return False

Then:

>>> is_int('-73')
True

>>> is_int('2.3')
False

But note, the above is_int() only checks for int. If not, it is not necessarily a float:

>>> is_int('foo')
False

But you could easily duplicate that pattern for float.

CodePudding user response：

The str module offers the isdigit function, returning True if a string represents a digit.

str.isdigit("5")
# True
str.isdigit("five")
# False

For float type, you could write a short function using try-except:

def check_float(string):
    try:
        float(string)
        return True
    except ValueError:
        return False

CodePudding user response：

I think this does what you want, without using regexes. Notice that this handles negative numbers, which yours did not. I've removed the called to error(i), since it was pointless.

def read():
    return open('lex.txt','r').read().split()

op=[' ','-','/','*','==','!=','<','>','>=','<=']
def operator(i):
    if i in op:
        buf.append(i)
        token.append('RELOP')
        return True
    return False

# I don't know what this is doing.  `i` is a string.
def error(i):
    digit=[0,1,2,3,4,5,6,7,8,9,0]
    if i[0] in digit:
        buf.append(i)
        token.append('ERROR')
        return True
    return False
    
keywords=['if','while','for']
def keyword(i):
    if i in keywords:
        buf.append(i)
        x=i.upper()
        token.append(x '_TOKEN')
        return True
    return False
        
alph='abcdefghijklmnopqrstuvwxyz'
def ident(i):
    if i[0] in alph:
        buf.append(i)
        token.append('ID')
        return True
    return False
        
def floati(i):
    tmp = i
    if tmp[0] in " -":
        tmp = tmp[1:]
    if tmp.replace('.', '', 1).isdigit():
        buf.append(i)
        token.append('FLOAT')
        return True
    return False
        
def integ(i):
    if i.isdigit() or i[0] in " -" and i[1:].isdigit():
        buf.append(i)
        token.append('INTEGER')
        return True
    return False

def parse(lex):

    for i in lex:
        if keyword(i) or \
            operator(i) or \
            integ(i) or \
            floati(i) or \
            ident(i):
            print(i, token[-1])

        else:
            print(i, "Syntax error")

buf=[]
token=[]
parse(read())

CodePudding user response：

strs = ["x", "45", "5.4", "-33", "size33", "34RR", "if"]
from re import match
strs = ["18","18.5","s","-35"]
for s in strs:
    if match("^-{0,1}[0-9^]*(\.[0-9] ){0,1}$",s):
        if s[0] == "-":
            s = s[1:]
        if s.isdigit():
            print("int")
        else:
            print("float")
    else:
        print("other")