I am trying realize python like indent-depending grammar.
Source example:
ABC QWE
CDE EFG
EFG CDE
ABC
QWE ZXC
As i see,
Have you looked at the Python ANTLR grammar?
Edit: Added psuedo Python code for creating INDENT/DEDENT tokens
UNKNOWN_TOKEN = 0
INDENT_TOKEN = 1
DEDENT_TOKEN = 2
# filestream has already been processed so that each character is a newline and
# every tab outside of quotations is converted to 8 spaces.
def GetIndentationTokens(filestream):
# Stores (indentation_token, line, character_index)
indentation_record = list()
line = 0
character_index = 0
column = 0
counting_whitespace = true
indentations = list()
for c in filestream:
if IsNewLine(c):
character_index = 0
column = 0
line += 1
counting_whitespace = true
elif c != ' ' and counting_whitespace:
counting_whitespace = false
if(len(indentations) == 0):
indentation_record.append((token, line, character_index))
else:
while(len(indentations) > 0 and indentations[-1] != column:
if(column < indentations[-1]):
indentations.pop()
indentation_record.append((
DEDENT, line, character_index))
elif(column > indentations[-1]):
indentations.append(column)
indentation_record.append((
INDENT, line, character_index))
if not IsNewLine(c):
column += 1
character_index += 1
while(len(indentations) > 0):
indentations.pop()
indentation_record.append((DEDENT_TOKEN, line, character_index))
return indentation_record