simpleparse parsing problem

[Paul McGuire]

"David Hirschfield" <davidh at ilm.com> wrote in message 
news:mailman.10272.1157163438.27775.python-list at python.org...
> Anyone out there use simpleparse? If so, I have a problem that I can't 
> seem to solve...I need to be able to parse this line:
>
> """Cen2 = Cen(OUT, "Cep", "ies", wh, 544, (wh/ht));"""
>
> with this grammar:
>
> grammar = r'''
> declaration := ws, line, (ws, line)*, ws
> line        := (statement / assignment), ';', ws
> assignment  := identifier, ws, '=', ws, statement
> statement   := identifier, '(', arglist?, ')', chars?
> identifier  := ([a-zA-Z0-9_.:])+
> arglist     := arg, (',', ws, arg)*
> arg         := expr/ statement / identifier / num / str /
>               curve / spline / union / conditional / definition
> definition  := typedef?, ws, identifier, ws, '=', ws, arg
> typedef     := ([a-zA-Z0-9_])+
> expr        := termlist, ( operator, termlist )+
> termlist    := ( '(', expr, ')' ) / term
> term        := call / identifier / num
> call        := identifier, '(', arglist?, ')'
> union       := '{{', ws, (arg, ws, ';', ws)*, arg, ws, '}}'
> operator    := ( '+' / '-' / '/' / '*' /
>                 '==' / '>=' / '<=' / '>' / '<' )
> conditional := termlist, ws, '?', ws, termlist, ws, ':', ws, termlist
> curve       := (list / num), '@', num
> spline      := (cv, ',')*, cv
> cv          := identifier, '@', num
> list        := '[', arg, (',', ws, arg)*, ']'
> str         := '"', ([;] / chars)*, '"'
> num         := ( scinot / float / int )
> <chars>     := ('-' / '/' / '?' / [a-zA-Z0-9_.!@#$%^&\*\+=<> :])+
> <int>       := ([-+]?, [0-9]+)
> <float>     := ([-+]?, [0-9\.]+)
> <scinot>    := (float, 'e', int)
> <ws>        := [ \t\n]*
> '''
<snip>
>

David -

I converted your simpleparse grammar to pyparsing, which I could then 
troubleshoot.  Here is a working pyparsing grammar, perhaps you can convert 
it back to simpleparse form and see if you make any better progress.

-- Paul


test = """Cen2 = Cen(OUT, "Cep", "ies", wh, 544, (wh/ht));"""


from pyparsing import *

# recursive items need forward decl - assign contents later using '<<' 
operator
arg = Forward()
expr = Forward()
statement = Forward()

float_ = Regex (r"[-+]?[0-9]+\.[0-9]*")
int_   = Regex (r"[-+]?[0-9]+")
scinot = Combine(float_ + oneOf(list("eE")) + int_)
num = scinot | float_ | int_
str_ = dblQuotedString
list_ = "[" + delimitedList(arg) + "]"
identifier = Word(alphas, srange("[a-zA-Z0-9_.:]"))
cv = identifier + "@" + num
spline = delimitedList(cv)
curve = (list_ | num) + "@" + num
conditional = expr + "?" + expr + ":" + expr
operator = oneOf( ('+', '-', '/', '*', '==', '>=', '<=', '>', '<') )
union = "{{" + delimitedList( arg, delim=";" ) + "}}"
call = identifier + "(" + delimitedList(arg) + ")"
term = call | identifier | num | Group( "(" + expr + ")" )
expr << (term + ZeroOrMore( operator+term ) )
typedef = Word( alphas, alphanums )
definition = ( (typedef + identifier) | identifier ) + "=" + arg
arg << (expr | statement | identifier | num | str_ | "." |
               curve | spline | union | conditional | definition)
assignment = identifier + "=" + statement
statement << ( call | assignment )
line_ = statement + ';'
declaration = OneOrMore(line_)

print declaration.parseString(test)

Prints:
['Cen2', '=', 'Cen', '(', 'OUT', '"Cep"', '"ies"', 'wh', '544', ['(', 'wh', 
'/', 'ht', ')'], ')', ';']