DBsExcel_con_UDT/S7_DBParser.py

import re
import os
import json

def clean_line(line):
    """Clean line from BOM and extra spaces or quotes."""
    # Remove UTF-8 BOM if exists and strip trailing/leading whitespace
    line = line.replace("\ufeff", "").strip()
    # Standardize TYPE and DATA_BLOCK definitions to ensure they're properly captured
    line = re.sub(r'\s*TYPE\s+"?', 'TYPE "', line)
    line = re.sub(r'\s*DATA_BLOCK\s+"?', 'DATA_BLOCK "', line)
    line = remove_text_inside_brackets(line)
    return line

def remove_text_inside_brackets(text):
    # Define the pattern to find text inside brackets
    pattern = r"\{.*?\}"
    # Use re.sub to replace the found text with an empty string
    cleaned_text = re.sub(pattern, '', text)
    return cleaned_text

def extract_name(line):
    """Extract the name from TYPE or DATA_BLOCK definition line."""
    # Attempt to find a quoted name first
    match = re.search(r'(TYPE|DATA_BLOCK)\s+"([^"]+)"', line)
    if match:
        return match.group(2).strip()  # The name is within quotes

    # If no quoted name, find an unquoted name
    match = re.search(r"(TYPE|DATA_BLOCK)\s+(\S+)", line)
    if match:
        return match.group(2).strip()  # The name is without quotes


def parse_udts(lines):
    udt_json = {}
    udt_name = None
    nested_structs = []
    current_struct = None
    is_within_struct = False

    for line in lines:
        line = clean_line(line)
        if "TYPE" in line and "END_TYPE" not in line:
            udt_name = extract_name(line)
            udt_json[udt_name] = {}
            current_struct = udt_json[udt_name]
            print(f"Created UDT: {udt_name}")
        elif "END_TYPE" in line:
            print(f"Completed UDT: {udt_name}")
            udt_name = None
            nested_structs = []
            current_struct = None
            is_within_struct = False
        elif "STRUCT" in line and "END_STRUCT" not in line and udt_name is not None:
            struct_name = (
                "Struct" if "STRUCT" == line.strip() else line.split(":")[0].strip()
            )
            new_struct = {}
            current_struct[struct_name] = new_struct
            nested_structs.append(current_struct)
            current_struct = new_struct
            is_within_struct = True
            print(f"Created STRUCT: {struct_name}")
        elif "END_STRUCT" in line and udt_name is not None:
            current_struct = nested_structs.pop() if nested_structs else None
            is_within_struct = bool(nested_structs)
            print(f"Closed STRUCT in UDT '{udt_name}'")
        elif udt_name and ":" in line and is_within_struct:
            parts = line.split(":")
            field_name = parts[0].strip()
            field_details = parts[1].strip().split("//")
            field_type = (
                field_details[0].replace(";", "").strip()
            )  # Removing ';' from field type
            field_comment = parts[1].split("//")[1].strip() if "//" in parts[1] else ""
            if "Struct" in field_type:
                new_struct = {}
                current_struct[field_name] = new_struct
                nested_structs.append(current_struct)
                current_struct = new_struct
                print(f"Opened inline STRUCT at field '{field_name}'")
            else:
                current_struct[field_name] = {
                    "type": field_type,
                    "comment": field_comment,
                }
                print(
                    f"Added field '{field_name}' to STRUCT: Type={field_type}, Comment={field_comment}"
                )

    return udt_json


def parse_dbs(lines, udts):
    db_json = {}
    db_name = None
    nested_structs = []
    current_struct = None
    is_within_struct = False

    for line in lines:
        line = clean_line(line)
        if "DATA_BLOCK" in line and "END_DATA_BLOCK" not in line:
            db_name = extract_name(line)
            db_json[db_name] = {}
            current_struct = db_json[db_name]
            print(f"Created DATA_BLOCK: {db_name}")
        elif "END_DATA_BLOCK" in line:
            print(f"Completed DATA_BLOCK: {db_name}")
            db_name = None
            nested_structs = []
            current_struct = None
            is_within_struct = False
        elif "STRUCT" in line and "END_STRUCT" not in line and db_name is not None:
            struct_name = (
                "Struct" if "STRUCT" == line.strip() else line.split(":")[0].strip()
            )
            new_struct = {}
            current_struct[struct_name] = new_struct
            nested_structs.append(current_struct)
            current_struct = new_struct
            is_within_struct = True
            print(f"Created STRUCT in DB '{db_name}': {struct_name}")
        elif "END_STRUCT" in line and db_name is not None:
            current_struct = nested_structs.pop() if nested_structs else None
            is_within_struct = bool(nested_structs)
            print(f"Closed STRUCT in DB '{db_name}'")
        elif db_name and ":" in line and is_within_struct:
            parts = line.split(":")
            field_name = parts[0].strip()
            field_details = parts[1].strip().split("//")
            field_type = (
                field_details[0].replace(";", "").strip()
            )  # Removing ';' from field type
            field_comment = parts[1].split("//")[1].strip() if "//" in parts[1] else ""
            if "Struct" in field_type:
                new_struct = {}
                current_struct[field_name] = new_struct
                nested_structs.append(current_struct)
                current_struct = new_struct
                print(f"Opened inline STRUCT at field '{field_name}' in DB '{db_name}'")
            else:
                current_struct[field_name] = {
                    "type": field_type,
                    "comment": field_comment,
                }
                print(
                    f"Added field '{field_name}' to STRUCT in DB '{db_name}': Type={field_type}, Comment={field_comment}"
                )

    return db_json