ext/ply/ply/lex.py: ext/ply/ply/yacc.py: ext/ply/CHANGES: ext/ply/README: ext/ply/TODO: ext/ply/doc/ply.html: ext/ply/example/ansic/clex.py: ext/ply/example/ansic/cparse.py: ext/ply/example/calc/calc.py: ext/ply/example/hedit/hedit.py: ext/ply/example/optcalc/calc.py: ext/ply/test/README: ext/ply/test/calclex.py: ext/ply/test/lex_doc1.exp: ext/ply/test/lex_doc1.py: ext/ply/test/lex_dup1.exp: ext/ply/test/lex_dup1.py: ext/ply/test/lex_dup2.exp: ext/ply/test/lex_dup2.py: ext/ply/test/lex_dup3.exp: ext/ply/test/lex_dup3.py: ext/ply/test/lex_empty.py: ext/ply/test/lex_error1.py: ext/ply/test/lex_error2.py: ext/ply/test/lex_error3.exp: ext/ply/test/lex_error3.py: ext/ply/test/lex_error4.exp: ext/ply/test/lex_error4.py: ext/ply/test/lex_hedit.exp: ext/ply/test/lex_hedit.py: ext/ply/test/lex_ignore.exp: ext/ply/test/lex_ignore.py: ext/ply/test/lex_re1.exp: ext/ply/test/lex_re1.py: ext/ply/test/lex_rule1.py: ext/ply/test/lex_token1.py: ext/ply/test/lex_token2.py: ext/ply/test/lex_token3.py: ext/ply/test/lex_token4.py: ext/ply/test/lex_token5.exp: ext/ply/test/lex_token5.py: ext/ply/test/yacc_badargs.exp: ext/ply/test/yacc_badargs.py: ext/ply/test/yacc_badprec.exp: ext/ply/test/yacc_badprec.py: ext/ply/test/yacc_badprec2.exp: ext/ply/test/yacc_badprec2.py: ext/ply/test/yacc_badrule.exp: ext/ply/test/yacc_badrule.py: ext/ply/test/yacc_badtok.exp: ext/ply/test/yacc_badtok.py: ext/ply/test/yacc_dup.exp: ext/ply/test/yacc_dup.py: ext/ply/test/yacc_error1.exp: ext/ply/test/yacc_error1.py: ext/ply/test/yacc_error2.exp: ext/ply/test/yacc_error2.py: ext/ply/test/yacc_error3.exp: ext/ply/test/yacc_error3.py: ext/ply/test/yacc_inf.exp: ext/ply/test/yacc_inf.py: ext/ply/test/yacc_missing1.exp: ext/ply/test/yacc_missing1.py: ext/ply/test/yacc_nodoc.exp: ext/ply/test/yacc_nodoc.py: ext/ply/test/yacc_noerror.exp: ext/ply/test/yacc_noerror.py: ext/ply/test/yacc_nop.exp: ext/ply/test/yacc_nop.py: ext/ply/test/yacc_notfunc.exp: ext/ply/test/yacc_notfunc.py: ext/ply/test/yacc_notok.exp: ext/ply/test/yacc_notok.py: ext/ply/test/yacc_rr.exp: ext/ply/test/yacc_rr.py: ext/ply/test/yacc_simple.exp: ext/ply/test/yacc_simple.py: ext/ply/test/yacc_sr.exp: ext/ply/test/yacc_sr.py: ext/ply/test/yacc_term1.exp: ext/ply/test/yacc_term1.py: ext/ply/test/yacc_unused.exp: ext/ply/test/yacc_unused.py: ext/ply/test/yacc_uprec.exp: ext/ply/test/yacc_uprec.py: Import patch ply.diff src/arch/isa_parser.py: everything is now within the ply package --HG-- rename : ext/ply/lex.py => ext/ply/ply/lex.py rename : ext/ply/yacc.py => ext/ply/ply/yacc.py extra : convert_revision : fca8deabd5c095bdeabd52a1f236ae1404ef106e
164 lines
3.8 KiB
Python
164 lines
3.8 KiB
Python
# ----------------------------------------------------------------------
|
|
# clex.py
|
|
#
|
|
# A lexer for ANSI C.
|
|
# ----------------------------------------------------------------------
|
|
|
|
import sys
|
|
sys.path.insert(0,"../..")
|
|
|
|
import ply.lex as lex
|
|
|
|
# Reserved words
|
|
reserved = (
|
|
'AUTO', 'BREAK', 'CASE', 'CHAR', 'CONST', 'CONTINUE', 'DEFAULT', 'DO', 'DOUBLE',
|
|
'ELSE', 'ENUM', 'EXTERN', 'FLOAT', 'FOR', 'GOTO', 'IF', 'INT', 'LONG', 'REGISTER',
|
|
'RETURN', 'SHORT', 'SIGNED', 'SIZEOF', 'STATIC', 'STRUCT', 'SWITCH', 'TYPEDEF',
|
|
'UNION', 'UNSIGNED', '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', 'RSHIFT',
|
|
'LOR', 'LAND', 'LNOT',
|
|
'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',
|
|
|
|
# Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, &=, ^=, |=)
|
|
'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL',
|
|
'LSHIFTEQUAL','RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL', 'OREQUAL',
|
|
|
|
# Increment/decrement (++,--)
|
|
'PLUSPLUS', 'MINUSMINUS',
|
|
|
|
# Structure dereference (->)
|
|
'ARROW',
|
|
|
|
# Conditional operator (?)
|
|
'CONDOP',
|
|
|
|
# Delimeters ( ) [ ] { } , . ; :
|
|
'LPAREN', 'RPAREN',
|
|
'LBRACKET', 'RBRACKET',
|
|
'LBRACE', 'RBRACE',
|
|
'COMMA', 'PERIOD', 'SEMI', 'COLON',
|
|
|
|
# Ellipsis (...)
|
|
'ELLIPSIS',
|
|
)
|
|
|
|
# Completely ignored characters
|
|
t_ignore = ' \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_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_RSHIFTEQUAL = r'>>='
|
|
t_ANDEQUAL = r'&='
|
|
t_OREQUAL = r'\|='
|
|
t_XOREQUAL = r'^='
|
|
|
|
# Increment/decrement
|
|
t_PLUSPLUS = r'\+\+'
|
|
t_MINUSMINUS = r'--'
|
|
|
|
# ->
|
|
t_ARROW = 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':'
|
|
t_ELLIPSIS = 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.lineno += t.value.count('\n')
|
|
|
|
# Preprocessor directive (ignored)
|
|
def t_preprocessor(t):
|
|
r'\#(.)*?\n'
|
|
t.lineno += 1
|
|
|
|
def t_error(t):
|
|
print "Illegal character %s" % repr(t.value[0])
|
|
t.lexer.skip(1)
|
|
|
|
lexer = lex.lex(optimize=1)
|
|
if __name__ == "__main__":
|
|
lex.runmain(lexer)
|
|
|
|
|
|
|
|
|
|
|