Re: [Pyparsing] fixed-length field preceded by length?

[John W. S. <jo...@nm...>]

#!/usr/bin/env python3
#================================================================
# countedtext: Using pyparsing for a string preceded by a count
#----------------------------------------------------------------
# Author: John W. Shipman (jo...@nm...)
#         New Mexico Tech Computer Center
#         Socorro, NM 87801
#
# Problem: Sanjay Ghemawat's venerable 'ical' calendar utility
# (http://en.wikipedia.org/wiki/Ical_%28Unix%29) saves events
# in a .calendar file, in which the description of an event
# is saved in a line like this:
#
#   Text [6 [Easter]]
#
# The problem is to write a pyparsing pattern that parses the
# count and the bracketed string.  The shortcut method is to
# use QuotedString(quoteChar='[', endQuoteChar=']'), but this
# fails if the literal string contains a ']' character.
#
# Paul McGuire responded immediately to my post on the pyparsing
# mailing list, suggesting that I study the implementation of the
# countedArray() helper.  Based on this advice, I offer this
# implementation of a countedText() pattern that matches an
# integer followed by a literal string in brackets, complete
# with a test driver.
#----------------------------------------------------------------

import sys
import pyparsing as pp

def countedText():
     '''Defines a pattern of the form:
          int "[" char* "]"
        where int is an integer that specifies the length of the
        following bracketed string literal.
        Example: "6 [Easter]"
     '''
     stringExpr = pp.Forward()

     def countedParseAction(s, l, t):
         '''Parse action that sets up the count in stringExpr.
         '''
         n = int(t[0])

         #--
         # CharsNotIn does not like exact=0.  We use Combine so that
         # whichever pattern represents the contents, the result is
         # a single string.
         #--
         if n > 0:
             contents = pp.CharsNotIn('', exact=n)
         else:
             contents = pp.Empty()
         stringExpr << pp.Combine(pp.Literal("[").suppress() +
                                  contents +
                                  pp.Literal("]").suppress())
         return []

     #--
     # The first parse action converts the count to an int.
     #--
     intExpr = pp.Word(pp.nums).setParseAction(lambda t: int(t[0]))

     #--
     # The second parse action uses the count to define the
     # stringExpr pattern using the actual value of the count.
     #--
     intExpr.addParseAction(countedParseAction)
     return (intExpr + stringExpr)

linePat = countedText()

# - - - - -   m a i n

testLines = [                # Test output
     "0 []",                  # ['']
     "11 [abcdefghijk]",      # ['abcdefghijk']
     "6 [Easter]",            # ['Easter']
     "4 [[[]]]",              # ['[[]]']
     "6 []]]]]]]",            # [']]]]]]']
     "6 [ abcdef]"            # Fails (leading whitespace not skipped)
     ]

def main():
     """Main
     """
     for line in testLines:
         test(line)

def test(line):
     '''Test one line
     '''
     print("\n", line, sep='')
     try:
         result = linePat.parseString(line, parseAll=True)
         print(result)
     except pp.ParseException as x:
         print("{}^".format(" "*(x.column-1)))
         print("No")

# - - - - -   E p i l o g u e

if __name__ == "__main__":
     main()