python pretty printer for Tokenizer class

[ollydbg]

Hi, this is my draft forTokenizer class, see the code:

Code

import gdb
import re

class TokenizerPrinter(object):
    '''Print a Tokenizer object'''
    def __init__(self, val):
        self.val = val

    def to_string(self):
        # This add a new line here, so we can align the buffer and the token line
        print ("The Tokenizer object")
        buffer = self.val['m_Buffer']
        length = int(self.val['m_BufferLen'])
        curr_index = int(self.val['m_TokenIndex'])
        undo_index = int(self.val['m_UndoTokenIndex'])
        peek_index = int(self.val['m_PeekTokenIndex'])
        curr = self.val['m_Token']
        peek = self.val['m_PeekToken']
        #print (buffer)
        dir(buffer)
        dataAsCharPointer = buffer['m_pchData']
        start = curr_index - 30
        end = curr_index + 30
        #print (start)
        #print (end)
        #print (dataAsCharPointer)
        s = dataAsCharPointer.string()
        cut_s_left  = s[start:curr_index].encode("ascii")
        cut_s_right = s[curr_index:end].encode("ascii")
        #print (cut_s_left)
        #print (cut_s_right)
        #print (repr(cut_s_left))
        #print (repr(cut_s_right))
        left = repr(cut_s_left)
        right = repr(cut_s_right)
        # remove the single quote
        left = left[1:-1]
        right = right[1:-1]
        buffer_line = "Buffer: " + left + right
        print (str(buffer_line))
        t_left_space = " "* len(left)
        token = curr['m_pchData'].string()
        left_space = token.rjust(len(left), ' ')
        token_line =  "Token : " + left_space + "^"
        print (str(token_line))
        have_peek = self.val['m_PeekAvailable']
        if have_peek == True:
            cut_p_left = s[curr_index:peek_index].encode("ascii")
            p_left = repr(cut_p_left)
            p_left = p_left[1:-1]
            s_peek = peek['m_pchData'].string()
            #print (len(p_left))
            p_space_left = s_peek.rjust(len(p_left), ' ')
            #print (len(p_space_left))
            peek_line =  "Peek  : " + t_left_space + p_space_left + "^"
            print (peek_line)
        return None

    def display_hint (self):
        return 'string'

def lookup_function (val):
    "Look-up and return a pretty-printer that can print val."
    typename = val.type.tag
    if typename == None:
        return None
    regex = re.compile('^Tokenizer$') 
    if regex.match(typename):
        return  TokenizerPrinter(val)
    return None

def register_my_printers (obj):
    if obj == None:
        obj = gdb
    obj.pretty_printers.append (lookup_function)

register_my_printers(None)

So, when you debugging, you can have the following gdb output in the command line:

Code

$35 = The Tokenizer object
Buffer: /Category.hh"\r\n\r\n\r\n    int abc;\r\n    int def;\r\n    int abc;\r
Token :                                  abc^
Peek  :                                     ;^

or

Code

$36 = The Tokenizer object
Buffer: hh"\r\n\r\n\r\n    int abc;\r\n    int def;\r\n    int abc;\r\n    int d
Token :                                    int^
Peek  :                                        def^

When you type the "p *this" when you inside the Tokenizer member function, or "p m_Tokenizer" in upper layer class.
The source code may be a bit hard to understand, so it need some refactoring (such as variable name change)