From d26ea2863b86010c8736a0ff266cbe4ec2c40c88 Mon Sep 17 00:00:00 2001
From: Daniel Roth <daniel_roth@hotmail.co.uk>
Date: Thu, 29 Jan 2026 17:19:03 +0000
Subject: [PATCH] get uprn from reference:uprn file. parsing test fails for
 now, need to fix

---
 backend/condition/local_runner.py           |  4 +-
 backend/condition/parsing/parser.py         |  3 +-
 backend/condition/parsing/peabody_parser.py | 46 ++++++++++++++-------
 3 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/backend/condition/local_runner.py b/backend/condition/local_runner.py
index fc6516cc..e39d38c7 100644
--- a/backend/condition/local_runner.py
+++ b/backend/condition/local_runner.py
@@ -20,9 +20,9 @@ def main() -> None:
         / "peabody"
         / "2026_01_06 - Peabody - Stock Condition Data - Survey Records - D  Lower.xlsx"
     )
-    # filepaths = [lbwf_path, peabody_path]
+    filepaths = [lbwf_path, peabody_path]
     # filepaths = [lbwf_path]
-    filepaths = [peabody_path]
+    # filepaths = [peabody_path]
 
     for fp in filepaths:
         with fp.open("rb") as f:
diff --git a/backend/condition/parsing/parser.py b/backend/condition/parsing/parser.py
index 105fda36..8146789f 100644
--- a/backend/condition/parsing/parser.py
+++ b/backend/condition/parsing/parser.py
@@ -1,8 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import BinaryIO, Any
 
+
 class Parser(ABC):
 
     @abstractmethod
     def parse(self, file_stream: BinaryIO) -> Any:
-        pass
\ No newline at end of file
+        pass
diff --git a/backend/condition/parsing/peabody_parser.py b/backend/condition/parsing/peabody_parser.py
index 423c0cda..0ffcb1b9 100644
--- a/backend/condition/parsing/peabody_parser.py
+++ b/backend/condition/parsing/peabody_parser.py
@@ -1,3 +1,5 @@
+import csv
+from pathlib import Path
 from typing import Any, BinaryIO, Dict, Iterator, List, Tuple, DefaultDict
 from openpyxl import Workbook, load_workbook
 from collections import defaultdict
@@ -15,17 +17,34 @@ logger = setup_logger()
 class PeabodyParser(Parser):
     def parse(self, file_stream: BinaryIO) -> Any:
         wb: Workbook = load_workbook(file_stream)
-        address_to_uprn_map: Dict[str, int] = (
-            PeabodyParser._generate_address_to_uprn_dict(wb)
+        location_ref_to_uprn_map: Dict[str, int] = (
+            PeabodyParser._build_location_ref_to_uprn_map()
         )
 
-        assets = self._parse_assets(wb)
+        assets = PeabodyParser._parse_assets(wb)
 
-        return self._group_assets_into_properties(
+        return PeabodyParser._group_assets_into_properties(
             assets=assets,
-            address_to_uprn_map=address_to_uprn_map,
+            location_ref_to_uprn_map=location_ref_to_uprn_map,
         )
 
+    @staticmethod
+    def _build_location_ref_to_uprn_map() -> Dict[str, int]:
+        location_ref_to_uprn_filepath: Path = (
+            Path(__file__).resolve().parents[1]
+            / "sample_data"
+            / "peabody"
+            / "PeabodyPropertymatched_Dec25_propref_UPRN.csv"
+        )
+        location_ref_to_uprn_map: Dict[str, int] = {}
+
+        with location_ref_to_uprn_filepath.open(newline="") as f:
+            reader: Any = csv.DictReader(f)
+            for row in reader:
+                location_ref_to_uprn_map[row["reference"]] = int(row["out_uprn"])
+
+        return location_ref_to_uprn_map
+
     @staticmethod
     def _parse_assets(wb: Workbook) -> List[PeabodyAssetCondition]:
         assets_sheet = wb["Survey Records - D & Lower"]
@@ -54,27 +73,26 @@ class PeabodyParser(Parser):
     @staticmethod
     def _group_assets_into_properties(
         assets: List[PeabodyAssetCondition],
-        address_to_uprn_map: Dict[str, int],
+        location_ref_to_uprn_map: Dict[str, int],
     ) -> List[PeabodyProperty]:
-        assets_by_address: DefaultDict[str, List[PeabodyAssetCondition]] = defaultdict(
-            list
+        assets_by_location_reference: DefaultDict[str, List[PeabodyAssetCondition]] = (
+            defaultdict(list)
         )
 
         for asset in assets:
-            if asset.full_address is None:
+            if asset.lo_reference is None:
                 continue
 
-            address = asset.full_address.strip()
-            assets_by_address[address].append(asset)
+            assets_by_location_reference[asset.lo_reference].append(asset)
 
         properties: List[PeabodyProperty] = []
 
-        for address, grouped_assets in assets_by_address.items():
+        for location_ref, grouped_assets in assets_by_location_reference.items():
 
-            uprn = address_to_uprn_map.get(address)
+            uprn = location_ref_to_uprn_map.get(location_ref)
 
             if uprn is None:
-                logger.warning(f"No UPRN found for address: {address}")
+                logger.warning(f"No UPRN found for Location Reference: {location_ref}")
                 continue
 
             properties.append(