I get in trouble with the definitions of precedence.
I am trying to parse this file content :
HOSTNAMES
HOST 1 "Name_a" "ctrla2" END
HOST 4 "NameC" "ctrl4" "ctrl25" END
END
using this code that I wrote to experience PLY:
#---------------------------------------------------------------------------------------------------
# -*- coding: utf-8 -*-
"""Module basic_lexyacc : """
# imports
import sys
import lex
import yacc
tokens =
( 'CONTROL_STR','END','HOST','HOSTNAMES','NAME','NUMBER','PLUS', )
# Tokens
t_CONTROL_STR = r'("[^"]*")|(\'[^\']*\')'
t_END = 'END'
t_HOST = 'HOST'
t_HOSTNAMES = 'HOSTNAMES'
#t_NAME = r'[a-zA-Z_][a-zA-Z0-9_]*'
def t_NUMBER(t):
r'\d+'
t.value = int(t.value)
return t
t_ignore = " \t"
def t_newline(t):
r'\n+'
t.lexer.lineno += t.value.count("\n")
def t_error(t):
print("Illegal character '%s'" % t.value[0])
t.lexer.skip(1)
# Build the lexer
lex.lex()
# Parsing rules
precedence = (
('left', 'NAME'),
('left','END','HOST','HOSTNAMES','NUMBER'),
('left', 'CONTROL_STR'),
)
# Init global variables as support to the parsing function
control_str_lst = []
def p_expression_UNIX_FileGrammar(p):
'''expression : hostnames'''
def p_hostnames(p):
'''hostnames : HOSTNAMES host_def_lst END
| HOSTNAMES END'''
# an other way to declare 'host' optional in one shot
def p_host_def_lst(p):
'''host_def_lst : host_def_lst host_def
| host_def'''
def p_host_def(p):
'''host_def : HOST NUMBER CONTROL_STR control_str_lst END'''
print "HOST number %d :" % p[2]
print "\tName is %s" % p[3]
print "\tlist of controls is %",control_str_lst
def p_control_str_lst(p):
'''control_str_lst : control_str_lst CONTROL_STR
| CONTROL_STR'''
if len(p) == 2:
# Make sure the list is empty at the first pass when building
it
del control_str_lst[0:len(control_str_lst)]
control_str_lst.append(p[len(p)-1])
def p_expression_number(p):
"expression : NUMBER"
p[0] = p[1]
def p_error(p):
if p:
print("Syntax error at '%s'" % p.value)
else:
print("Syntax error at EOF")
yacc.yacc()
filePath = ""
f = open('C:\FileToParse.txt','r')
text_to_parse = f.read()
f.close()
yacc.parse(text_to_parse)
#------------------------------------------------------------------------------------------------------
The problem is that code does not work anymore if I uncomment the
line :
#t_NAME = r'[a-zA-Z_][a-zA-Z0-9_]*'
I understand there is a conflict with the other token but I don't
understand how to set my precedence then to fix this problem ?
(to be honnest I didn't know lex and yacc but have to use them)
Thank you...
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups
"ply-hack" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/ply-hack?hl=en
-~----------~----~----~----~------~----~------~--~---
