Comparison_Project/app/services/comparison_service.py

from collections import defaultdict
import pandas as pd
from app.utils.regex_utils import RegularExpression


class ComparisonService:
    
    TRENCH_MAPPING = [
        {
            "label": "Marshi 0 to 1.5",
            "client": "Client_Marshi_Muddy_Slushy_0_to_1_5_total",
            "sub": None
        },
        {
            "label": "Marshi 1.5 to 3.0",
            "client": "Client_Marshi_Muddy_Slushy_1_5_to_3_0_total",
            "sub": None
        },
        {
            "label": "Marshi 3.0 to 4.5",
            "client": "Client_Marshi_Muddy_Slushy_3_0_to_4_5_total",
            "sub": None
        },
        {
            "label": "Soft Murum 0 to 1.5",
            "client": "Client_Soft_Murum_0_to_1_5_total",
            "sub": "Sub_Soft_Murum_0_to_1_5_total"
        },
        {
            "label": "Soft Murum 1.5 to 3.0",
            "client": "Client_Soft_Murum_1_5_to_3_0_total",
            "sub": "Sub_Soft_Murum_1_5_to_3_0_total"
        },
        {
            "label": "Soft Murum 3.0 to 4.5",
            "client": "Client_Soft_Murum_3_0_to_4_5_total",
            "sub": "Sub_Soft_Murum_3_0_to_4_5_total"
        },
        {
            "label": "Hard Murum 0 to 1.5",
            "client": "Client_Hard_Murum_0_to_1_5_total",
            "sub": "Sub_Hard_Murum_0_to_1_5_total"
        },
        {
            "label": "Hard Murum 1.5+",
            "client": "Client_Hard_Murum_1_5_to_3_0_total",
            "sub": "Sub_Hard_Murum_1_5_and_above_total"
        },
        {
            "label": "Soft Rock 0 to 1.5",
            "client": "Client_Soft_Rock_0_to_1_5_total",
            "sub": "Sub_Soft_Rock_0_to_1_5_total"
        },
        {
            "label": "Soft Rock 1.5+",
            "client": "Client_Soft_Rock_1_5_to_3_0_total",
            "sub": "Sub_Soft_Rock_1_5_and_above_total"
        },
        {
            "label": "Hard Rock 0 to 1.5",
            "client": "Client_Hard_Rock_0_to_1_5_total",
            "sub": "Sub_Hard_Rock_0_to_1_5_total"
        },
        {
            "label": "Hard Rock 1.5 to 3.0",
            "client": "Client_Hard_Rock_1_5_to_3_0_total",
            "sub": "Sub_Hard_Rock_1_5_to_3_0_total"
        },
        {
            "label": "Hard Rock 3.0 to 4.5",
            "client": "Client_Hard_Rock_3_0_to_4_5_total",
            "sub": "Sub_Hard_Rock_3_0_to_4_5_total"
        },
        {
            "label": "Hard Rock 4.5 to 6.0",
            "client": "Client_Hard_Rock_4_5_to_6_0_total",
            "sub": "Sub_Hard_Rock_4_5_to_6_0_total"
        },
        {
            "label": "Hard Rock 6.0 to 7.5",
            "client": "Client_Hard_Rock_6_0_to_7_5_total",
            "sub": "Sub_Hard_Rock_6_0_to_7_5_total"
        }
    ]
    
    

    @staticmethod
    def normalize_key(value):
        if value is None:
            return ""
        return str(value).strip().upper()

    @classmethod
    def make_lookup(cls, rows, key_field):
        """
        Create lookup dictionary using:
        (Location, MH_NO)
        """

        lookup = defaultdict(list)

        for row in rows:

            location = cls.normalize_key(row.get("Location"))
            key = cls.normalize_key(row.get(key_field))

            if location and key:
                lookup[(location, key)].append(row)

        return lookup

    @classmethod
    def build_comparison(cls, client_rows, subcontractor_rows, key_field="MH_NO"):

        subcontractor_lookup = cls.make_lookup(
            subcontractor_rows,
            key_field
        )

        used = defaultdict(int)

        output = []

        for client in client_rows:

            location = cls.normalize_key(client.get("Location"))
            key = cls.normalize_key(client.get(key_field))

            if not location or not key:
                continue

            rows = subcontractor_lookup.get((location, key))

            if not rows:
                continue

            index = used[(location, key)]

            if index >= len(rows):
                continue

            subcontractor = rows[index]

            used[(location, key)] += 1

            client_total = sum(
                float(v or 0)
                for k, v in client.items()
                if k.endswith("_total")
                or RegularExpression.D_RANGE_PATTERN.match(k)
                or RegularExpression.PIPE_MM_PATTERN.match(k)
            )

            subcontractor_total = sum(
                float(v or 0)
                for k, v in subcontractor.items()
                if k.endswith("_total")
                or RegularExpression.D_RANGE_PATTERN.match(k)
                or RegularExpression.PIPE_MM_PATTERN.match(k)
            )

            row = {

                "Location": location,

                key_field: key,

                "Client_Total": round(client_total, 2),

                "Subcontractor_Total": round(subcontractor_total, 2),

                "Difference": round(
                    client_total - subcontractor_total,
                    2
                )
            }

            # Client Columns
            for column, value in client.items():

                if column in [
                    "id",
                    "created_at"
                ]:
                    continue

                row[f"Client_{column}"] = value

            # Subcontractor Columns
            for column, value in subcontractor.items():

                if column in [
                    "id",
                    "created_at",
                    "subcontractor_id"
                ]:
                    continue

                row[f"Sub_{column}"] = value

            output.append(row)

        return pd.DataFrame(output)