correction of comparison data show

app/services/comparison_service.py

@@ -0,0 +1,204 @@
+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)