Re: [Pyparsing] more refinement but still lost

[Paul M. <pt...@au...>]

all_tests = {
       "test_1": "some plain text",
       "test_2": "[simple ]",
       "test_3": "[simple_text some plain text]",
       "test_4": "[onearg [one ]]",
       "test_5": "[twoarg [one ] [two ]]",
       "test_6": "[onearg_text [one some plain text]]",
       "test_7": "[twoarg_text [one ] [two some plain text arg]]",
       "test_8": "[nested_text some [not plain] text]",
       "test_9": "[nested_text [one text] some [not [very ] plain] text]",
       "test_10": "[nested_text_escaped [one text] some [not [very ] plain]
bracketed \[text\]]",
       "test_11": """[nested_text_escaped_indented 
                            [one text] some 
                            [not 
                                   [very ] 
                                   plain
                            ] 
                            bracked \[text\]
                     ]""",

}

# a simple BNF:
#
# listExpr     ::= '[' listContent ']'
# listContent  ::= (contentsWord | escapedChar | listExpr)*
# contentsWord ::= printableCharacter+
#
#
# Some notes:
# 1. listContent could be empty, "[]" is a valid listExpr
# 2. contentsWord cannot contain '\', '[' or ']' characters, or
#    else we couldn't distinguish delimiters from contents, or 
#    detect escapes
#

from pyparsing import *

# start with the basics
LBRACK,RBRACK = map(Suppress,"[]")
escapedChar = Combine('\\' + oneOf(list(printables)))
contentsWord = Word(printables,excludeChars=r"\[]")

# define a placeholder for a nested list, since we need to 
# reference it before it is fully defined
listExpr = Forward()

# the contents of a list is one or more contents words or lists
listContent = ZeroOrMore(contentsWord | escapedChar | listExpr)

# a list is a listContent enclosed in []'s - enclose
# in a Group so that pyparsing will maintain the nested structure
#
# since listExpr was already defined as a Forward, we use '<<' to
# "inject" the definition into the already defined Forward
listExpr << Group(LBRACK + listContent + RBRACK)

# parse the test string - note that the results no longer contain 
# the parsed '[' and ']' characters, but they do retain the 
# nesting of the original string in nested lists
for name,testStr in all_tests.items():
    print name, listContent.parseString(testStr).asList()

# pyparsing includes a short-cut to simplify defining nested
# structures like this
print nestedExpr('[',']').parseString(all_tests['test_9']).asList()