C[omp]ute

From: "andrew cooke" <andrew@...>

Date: Wed, 21 Jan 2009 09:31:23 -0300 (CLST)

It seems that the best approach is often construct an AST node that
corresponds to an error, and then later walk the tree and raise the error.
 This allows the error to be given a full context (in other words, it may
be discarded if that path subsequently fails and their is backtracking; if
it had been raised immediately the parser would never have reached a point
where it could discard the error).

Here's some example code:


from logging import basicConfig, DEBUG, INFO
from unittest import TestCase

from lepl.match import *
from lepl.node import Node, make_error, Error, throw


basicConfig(level=INFO)

class Term(Node): pass
class Factor(Node): pass
class Expression(Node): pass

expr    = Delayed()
number  = Digit()[1:,...]                          > 'number'
badChar = AnyBut(Space() | Digit() | '(')[1:,...]

with Separator(r'\s*'):

    unopen   = number ** make_error('no ( before {stream_out}') & ')'
    unclosed = ('(' & expr & Eos())
                      ** make_error('no ) for {stream_in}')

    term    = Or(
        (number | '(' & expr & ')')               > Term,
        badChar                                   ^ 'unexpected text:
{results[0]}',
        unopen                                    >> throw,
        unclosed                                  >> throw
    )
    muldiv  = Any('*/')                           > 'operator'
    factor  = (term & (muldiv & term)[:])         > Factor
    addsub  = Any('+-')                           > 'operator'
    expr   += (factor & (addsub & factor)[:])     > Expression
    line    = Empty() & Trace(expr) & Eos()

parser = line.parse_string

parser('1 + 2 * (3 + 4 - 5')[0]
#  File "<string>", line 1
#    1 + 2 * (3 + 4 - 5
#            ^
#lepl.node.Error: no ) for '(3 + 4...'

parser('1 + 2 * 3 + 4 - 5)')[0]
#  File "<string>", line 1
#    1 + 2 * 3 + 4 - 5)
#                    ^
#lepl.node.Error: no ( before ')'

parser('1 + 2 * (3 + four - 5)')[0]
#  File "<string>", line 1
#    1 + 2 * (3 + four - 5)
#                 ^
#lepl.node.Error: unexpected text: four

parser('1 + 2 ** (3 + 4 - 5)')[0]
#  File "<string>", line 1
#    1 + 2 ** (3 + 4 - 5)
#           ^
#lepl.node.Error: unexpected text: *