lark_parser_demo

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Filename: lark_parser_demo.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
This script demonstrates parsing behavior using Lark grammar with and without a question mark.

Requirements:
- Python 3.x
- Lark library

Functions:
- line(): A utility function to print divider lines for better readability.
- parse_and_print(grammar, grammar_type): Parses the input string using the provided grammar and prints the parsed results.

Usage:
1. Run the script using Python 3.x interpreter.
2. The script will parse an input string using two different grammars and print the parsed results.

Additional Notes:
- The script defines two grammars: one without a question mark and another with rules starting with a question mark.
- It parses an input string using both grammars and displays the parsed results.
- It's recommended to have Python 3.x and the Lark library installed to run the script.
"""

import lark

# Define grammars with different rules
grammar_first = """
start:   rule1   rule2

rule1:      /\w+/  /\w+/
   |  "("  /\w+/  ")"

rule2:      /\w+/  /\w+/
   |  "("  /\w+/  ")"

%ignore " "
"""

grammar_second = """
start:   rule1   rule2

?rule1:      /\w+/  /\w+/
   |  "("  /\w+/  ")"

?rule2:      /\w+/  /\w+/
   |  "("  /\w+/  ")"

%ignore " "
"""


def line():
    print("-" * 40)


def parse_and_print(grammar, grammar_type):
    print(f"Parsing with {grammar_type} grammar:\n")
    print("Grammar:")
    print(grammar)
    line()

    parser = lark.Lark(grammar)
    parsed = parser.parse("example sample (another_example)")
    print()

    for idx, ch in enumerate(parsed.children, start=1):
        if isinstance(ch, lark.Tree):
            print(f"Tree {idx} with name {ch.data}:")
            for sub_ch in ch.children:
                print(f"   {sub_ch.value}")
            print()
        elif isinstance(ch, lark.Token):
            print(f"Token {idx} with value {ch.value}")

    line()


# Test with different grammars
parse_and_print(grammar_first, "First Grammar")
parse_and_print(grammar_second, "Second Grammar")