station_name_mapping.py

import re

def canonical_station_name(station_name):
    station_aliases = {
        "1": ["1"],
        "2": ["2"],
        "3": ["3"],
        "4": ["4"],
        "5": ["5"],
        "5.5": ["5.5"],
        "6": ["6"],
        "6.5": ["6.5"],
        "7": ["7"],
        "8": ["8"],
        "9": ["9"],
        "9.5": ["9.5"],
        "10": ["10"],
        "11": ["11"],
        "12": ["12"],
        "13": ["13"],
        "14": ["14"],
        "15": ["15"],
        "15.5": ["15.5"],
        "16": ["16"],
        "17": ["17"],
        "18": ["18"],
        "19": ["19"],
        "20": ["20"],
        "21/LK": ["21/LK", "LK", "21"],
        "21.5": ["21.5"],
        "22": ["22"],
        "22.5": ["22.5"],
        "23": ["23"],
        "24": ["24"],
        "WS": ["WS"],
        "30": ["30"],
        "30.5": ["30.5"],
        "31": ["31"],
        "32": ["32"],
        "33": ["33"],
        "34": ["34"],
        "39": ["39"],
        "40": ["40"],
        "41": ["41"],
        "42": ["42"],
        "45": ["45"],
        "46": ["46"],
        "47": ["47"],
        "48": ["48"],
        "49": ["49"],
        "50": ["50"],
        "51": ["51"],
        "52": ["52"],
        "53": ["53"],
        "54": ["54"],
        "55": ["55"],
        "56": ["56"],
        "57": ["57"],
        "57.1": ["57.1"],
        "57.2": ["57.2"],
        "57.3": ["57.3"],
        "58": ["58"],
        "59": ["59"],
        "60": ["60"],
        "61": ["61"],
        "62": ["62"],
        "63": ["63"],
        "64": ["64"],
        "65": ["65"],
        "66": ["66"],
        "67": ["67"],
        "68": ["68"],
        "69": ["69"],
        "70": ["70"],
        "AMI1": ["AMI1"],
        "AMI2": ["AMI2"],
        "AMI3": ["AMI3"],
        "AMI4": ["AMI4"],
        "AMI5": ["AMI5"],
        "AMI6": ["AMI6"],
        "AMI7": ["AMI7"],
        "AMI8": ["AMI8"],
        "AMI9": ["AMI9"],
        "BG1": ["BG1"],
        "BG2": ["BG2"],
        "BG3": ["BG3"],
        "BG4": ["BG4"],
        "CAL1": ["CAL1"],
        "CAL2": ["CAL2"],
        "CAL3": ["CAL3"],
        "CAL4": ["CAL4"],
        "CAL5": ["CAL5"],
        "CAL6": ["CAL6"],
        "CW1": ["CW1"],
        "CW2": ["CW2"],
        "CW3": ["CW3"],
        "CW4": ["CW4"],
        "EB1": ["EB1"],
        "EB2": ["EB2"],
        "EK_IN": ["EK_IN"],
        "EK_MID": ["EK_MID"],
        "EK_OFF": ["EK_OFF"],
        "GP5": ["GP5"],
        "KW1": ["KW1"],
        "KW2": ["KW2"],
        "KW3": ["KW3"],
        "KW4": ["KW4"],
        "L1": ["L1"],
        "L3": ["L3"],
        "L5": ["L5"],
        "L7": ["L7"],
        "L9": ["L9"],
        "MR": ["MR"],
        "RP1": ["RP1"],
        "RP2": ["RP2"],
        "RP3": ["RP3"],
        "RP4": ["RP4"],
        "TB1": ["TB1"],
        "TB2": ["TB2"],
        "TB3": ["TB3"],
        "TB4": ["TB4"],
        "TB5": ["TB5"],
        "TB6": ["TB6"],
        "TB7": ["TB7"],
        "TB8": ["TB8"],
        "TB9": ["TB9"],
        "TB10": ["TB10"],
        "UK_IN": ["UK_IN"],
        "UK_MID": ["UK_MID"],
        "UK_OFF": ["UK_OFF"],
        "V1": ["V1"],
        "V2": ["V2"],
        "V3": ["V3"],
        "V4": ["V4"],
        "V5": ["V5"],
        "V6": ["V6"],
        "V7": ["V7"],
        "V8": ["V8"],
        "V9": ["V9"],
        "ROME5": ["ROME5"],
        "CW7": ["CW7"],
        "BG7": ["BG7"],
        "LK": ["LK"],
        "BG10": ["BG10"],
        "BG11": ["BG11"],
        "BG12": ["BG12"],
        "BG13": ["BG13"],
        "BG14": ["BG14"],
        "BG15": ["BG15"],
        "BG15B": ["BG15B"],
        "BG16": ["BG16"],
        "BG17": ["BG17"],
        "BG17B": ["BG17B"],
        "BG18": ["BG18"],
        "BG20": ["BG20"],
        "BG6": ["BG6"],
        "BG7B": ["BG7B"],
        "BG8": ["BG8"],
        "BG9": ["BG9"],
        "BG19": ["BG19"],
        "CW5": ["CW5"],
        "CW6": ["CW6"],
        "PLUME": ["PLUME"],
        "ROME4": ["ROME4"],
        "BLANK": ["BLANK"]
    }   

    name = station_name.strip()

    # normalize by stripping leading zeros
    normalized = name.lstrip("0")

    for canonical, aliases in station_aliases.items():
        for alias in aliases:
            if normalized == alias.lstrip("0"):
                return canonical

    raise ValueError(f"Station name '{station_name}' is not recognized.")