# -*- coding: cp1251 -*-
# HJava Programming Language, 2008 © nerezus


import sys
import ply.lex as lex

# Reserved words
reserved = (
    'PUBLIC', 'PRIVATE', 'PROTECTED', 'ABSTRACT', 'FINAL',
    'SYNCHRONIZED', 'TRANSIENT', 'NATIVE',
    'ASSERT', 'PACKAGE', 'NEW', 'THIS', 'IMPLEMENTS', 'EXTENDS', 'INSTANCEOF',
    'IMPORT', 'SUPER','STRICTFP',
    'TRY', 'CATCH', 'FINALLY', 'THROWS', 'THROW', 
            
    'BREAK', 'CASE', 'CHAR', 'CONST', 'CONTINUE', 'DEFAULT', 'DO', 'DOUBLE',
    'ELSE', 'ENUM', 'FLOAT', 'FOR', 'GOTO', 'IF', 'INT', 'LONG',
    'RETURN', 'SHORT', 'STATIC', 'SWITCH',
    'VOID', 'VOLATILE', 'WHILE',
    )

tokens = reserved + (
    # Literals (identifier, integer constant, float constant, string constant, char const)
    'ID', 'TYPEID', 'ICONST', 'FCONST', 'SCONST', 'CCONST',

    # Operators (+,-,*,/,%,|,&,~,^,<<,>>,>>>, ||, &&, !, <, <=, >, >=, ==, !=)
    'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD',
    'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFTRSHIFT','RSHIFT',
    'LOR', 'LAND', 'LNOT',
    'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',
    
    # Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, >>>=, &=, ^=, |=)
    'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL',
    'LSHIFTEQUAL', 'RSHIFTRSHIFTEQUAL', 'RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL',
    'OREQUAL',

    # Increment/decrement (++,--)
    'PLUSPLUS', 'MINUSMINUS',

    # Conditional operator (?)
    'CONDOP',
    
    # Delimeters ( ) [ ] { } , . ; :
    'LPAREN', 'RPAREN',
    'LBRACKET', 'RBRACKET',
    'LBRACE', 'RBRACE',
    'COMMA', 'PERIOD', 'SEMI', 'COLON'
    
    )

# Completely ignored characters
t_ignore           = ' \r\t\x0c'

# Newlines
def t_NEWLINE(t):
    r'\n+'
    t.lexer.lineno += t.value.count("\n")
    
# Operators
t_PLUS             = r'\+'
t_MINUS            = r'-'
t_TIMES            = r'\*'
t_DIVIDE           = r'/'
t_MOD              = r'%'
t_OR               = r'\|'
t_AND              = r'&'
t_NOT              = r'~'
t_XOR              = r'\^'
t_LSHIFT           = r'<<'
t_RSHIFTRSHIFT     = r'>>>'
t_RSHIFT           = r'>>'
t_LOR              = r'\|\|'
t_LAND             = r'&&'
t_LNOT             = r'!'
t_LT               = r'<'
t_GT               = r'>'
t_LE               = r'<='
t_GE               = r'>='
t_EQ               = r'=='
t_NE               = r'!='

# Assignment operators

t_EQUALS           = r'='
t_TIMESEQUAL       = r'\*='
t_DIVEQUAL         = r'/='
t_MODEQUAL         = r'%='
t_PLUSEQUAL        = r'\+='
t_MINUSEQUAL       = r'-='
t_LSHIFTEQUAL      = r'<<='
t_RSHIFTRSHIFTEQUAL= r'>>>='
t_RSHIFTEQUAL      = r'>>='
t_ANDEQUAL         = r'&='
t_OREQUAL          = r'\|='
t_XOREQUAL         = r'^='

# Increment/decrement
t_PLUSPLUS         = r'\+\+'
t_MINUSMINUS       = r'--'


# ?
t_CONDOP           = r'\?'

# Delimeters
t_LPAREN           = r'\('
t_RPAREN           = r'\)'
t_LBRACKET         = r'\['
t_RBRACKET         = r'\]'
t_LBRACE           = r'\{'
t_RBRACE           = r'\}'
t_COMMA            = r','
t_PERIOD           = r'\.'
t_SEMI             = r';'
t_COLON            = r':'

# Identifiers and reserved words

reserved_map = { }
for r in reserved:
    reserved_map[r.lower()] = r

def t_ID(t):
    r'[A-Za-z_][\w_]*'
    t.type = reserved_map.get(t.value,"ID")
    return t

# Integer literal
t_ICONST = r'\d+([uU]|[lL]|[uU][lL]|[lL][uU])?'

# Floating literal
t_FCONST = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?'

# String literal
t_SCONST = r'\"([^\\\n]|(\\.))*?\"'

# Character constant 'c' or L'c'
t_CCONST = r'(L)?\'([^\\\n]|(\\.))*?\''

# Comments
def t_comment(t):
    r'/\*(.|\n)*?\*/'
    t.lexer.lineno += t.value.count('\n')

# Preprocessor directive (ignored)
def t_preprocessor(t):
    r'\#(.)*?\n'
    t.lexer.lineno += 1
    
def t_error(t):
    print "Illegal character %s" % repr(t.value[0])
    t.lexer.skip(1)
    
input = """public class Test {

    /**
     * @param args
     */
    public static void main(String[] args) {
    int a = -8;
    int b = a >>> 1;
    System.out.println(b);

    }

}"""

lexer = lex.lex(optimize = 1)
lexer.input(input)
while 1:
    tok = lexer.token()
    if not tok: break
    print "    " + str(tok)