如何用python写一个简单的词法分析器

#保留字
key_word = [\'abstract\',\'assert\',\'boolean\',\'break\',\'byte\',
      \'case\',\'catch\',\'char\',\'class\',\'const\',
      \'continue\',\'default\',\'do\',\'double\',\'else\',
      \'enum\',\'extends\',\'final\',\'finally\',\'float\',
      \'for\',\'goto\',\'if\',\'implements\',\'import\',
      \'instanceof\',\'int\',\'interface\',\'long\',\'native\',
      \'new\',\'package\',\'private\',\'protected\',\'public\',
      \'return\',\'short\',\'static\',\'strictfp\',\'super\',
      \'switch\',\'synchronized\',\'this\',\'throw\',\'throws\',
      \'transient\',\'try\',\'void\',\'volatile\',\'while\']

#运算符
operator = [\'+\',\'-\',\'*\',\'/\',\'%\',\'++\',\'--\',\'+=\',\'-=\',\'+=\',\'/=\',#算术运算符
      \'==\',\'!=\',\'>\',\'<\',\'>=\',\'<=\',#关系运算符
      \'&\',\'|\',\'^\',\'~\',\'<<\',\'>>\',\'>>>\',#位运算符
      \'&&\',\'||\',\'!\',#逻辑运算符
      \'=\',\'+=\',\'-=\',\'*=\',\'/=\',\'%=\',\'<<=\',\'>>=\',\'&=\',\'^=\',\'|=\',#赋值运算符
      \'?:\']#条件运算符

#界符
delimiters = [\'{\',\'}\',\'[\',\']\',\'(\',\')\',\'.\',\',\',\':\',\';\']

#预处理
def filterResource(file,new_file):
  f2 = open(new_file,\'w+\')
  txt = \'\'.join(open(file,\'r\').readlines())
  deal_txt = re.sub(r\'\\/\\*[\\s\\S]*\\*\\/|\\/\\/.*\',\'\',txt) 
  for line in deal_txt.split(\'\\n\'):
      line = line.strip()
      line = line.replace(\'\\\\t\',\'\')
      line = line.replace(\'\\\\n\',\'\')
      if not line:
        continue
      else:
        f2.write(line+\'\\n\')
  f2.close()
  return sys.path[0]+\'\\\\\'+ new_file

def Scan(file):
  lines = open(file,\'r\').readlines()
  for line in lines:
    word = \'\'
    word_line = []
    i = 0
    while i <len(line):
      word +=line[i]
      if line[i]==\' \' or line[i] in delimiters or line[i] in operator:
        if word[0].isalpha() or word[0]==\'$\' or word[0]==\'_\':
          word = word[:-1]
          if searchReserve(word):
            # 保留字
            word_line.append({word[:-1]:key_word.index(word)})
          else:
            # 标识符
            identifier.append({word:-2})
            word_line.append({word:-2})
        # 常数
        elif word[:-1].isdigit():
          word_line.append({word:-1})
        #else:
          #error_word.append(word)
        # 字符是界符
        if line[i] in delimiters:
          word_line.append({line[i]:len(key_word)+delimiters.index(line[i])})
        # 字符是运算符
        elif line[i] in operator:
          s = line[i] +line[i+1]
          if s in operator:
            word_line.append({s:len(key_word)+len(delimiters)+operator.index(s)})
            i +=1
          else:
            word_line.append({line[i]:len(key_word)+len(delimiters)+operator.index(line[i])})
        word = \'\'
      i+=1
    token.append(word_line)

def check(number):
  hanzi = \'\'
  q = len(key_word)
  w = len(delimiters)
  e = len(operator)
  if 0<number<=q:
    hanzi = \'保留字\'
  elif q<number <= q+w:
    hanzi = \'界符\'
  elif q+w<number <=q+w+e:
    hanzi = \'运算符\'
  elif number == -1:
    hanzi =\'常数\'
  elif number == -2:
    hanzi =\'标识符\'
  return hanzi

from tkinter import * 
from tkinter.filedialog import askdirectory,askopenfilename

root = Tk()
  root. (\'词法分析\')
  root.resizable(0, 0)
  path = StringVar() 
  Label(root,text = \"目标路径:\").grid(row = 0, column = 0) 
  Entry(root, textvariable = path).grid(row = 0, column = 1) 
  Button(root, text = \"路径选择\", command = openfiles).grid(row = 0, column = 2)
  Button(root,text=\'词法分析\',command= open_excel).grid(row = 0,column = 3)
  root.mainloop()

def openfiles():
  fname = askopenfilename( =\'打开文件\', filetypes=[(\'All Files\', \'*\')])
  path.set(fname)

pip install xwings

import xlwings as xw

def open_excel():
  # 预处理
  row,col=0,0
  if path.get()!=\'\':

    txt = java_analysis.filterResource(path.get(),new_file)
    print(txt)
    #扫描
    java_analysis.Scan(txt)
    app = xw.App(visible=True,add_book=False)
    wb =app.books.open(sys.path[0]+\'\\\\\'+\'test.xlsx\')
    sheet = wb.sheets.active
    sheet.clear() 
    print(java_analysis.token)
    for i in range(len(java_analysis.token)):
      sheet[row,0].value = \'第\'+str(i+1)+\'行\'
      row +=1
      for word in java_analysis.token[i]:
        for k,w in word.items():
          sheet[row,3].value = k
          sheet[row,5].value = w
          sheet[row,7].value = java_analysis.check(w)
        row +=1
    sheet.autofit()#整个sheet自动调整
    #wb.save()