From 5b677dedbec75d85faa0dad510be4c15d91b7741 Mon Sep 17 00:00:00 2001
From: Jun-te Kim <juntekim@googlemail.com>
Date: Fri, 22 May 2026 08:15:11 +0000
Subject: [PATCH] SAL

---
 applications/SAL/Dockerfile                   | 34 ++++++++++++++
 applications/SAL/handler.py                   | 46 +++++++++++++++++++
 .../SAL/local_handler/.env.local.example      |  5 ++
 .../SAL/local_handler/docker-compose.yml      |  9 ++++
 .../SAL/local_handler/invoke_local_lambda.py  | 16 +++++++
 applications/SAL/local_handler/run_local.sh   | 12 +++++
 applications/SAL/requirements.txt             |  4 ++
 orchestration/sal_orchestrator.py             | 23 ++++++++++
 8 files changed, 149 insertions(+)
 create mode 100644 applications/SAL/Dockerfile
 create mode 100644 applications/SAL/handler.py
 create mode 100644 applications/SAL/local_handler/.env.local.example
 create mode 100644 applications/SAL/local_handler/docker-compose.yml
 create mode 100755 applications/SAL/local_handler/invoke_local_lambda.py
 create mode 100755 applications/SAL/local_handler/run_local.sh
 create mode 100644 applications/SAL/requirements.txt
 create mode 100644 orchestration/sal_orchestrator.py

diff --git a/applications/SAL/Dockerfile b/applications/SAL/Dockerfile
new file mode 100644
index 00000000..e2456b81
--- /dev/null
+++ b/applications/SAL/Dockerfile
@@ -0,0 +1,34 @@
+FROM public.ecr.aws/lambda/python:3.11
+
+# Postgres host/port/database are baked into the image at build time from
+# the deploy workflow's --build-arg values (GitHub Actions DEV_DB_* secrets),
+# mirroring backend/postcode_splitter/handler/Dockerfile. They map onto the
+# POSTGRES_* names PostgresConfig.from_env reads. Username/password are NOT
+# baked in -- Terraform injects those as Lambda env vars from Secrets Manager.
+ARG DEV_DB_HOST
+ARG DEV_DB_PORT
+ARG DEV_DB_NAME
+
+ENV POSTGRES_HOST=${DEV_DB_HOST}
+ENV POSTGRES_PORT=${DEV_DB_PORT}
+ENV POSTGRES_DATABASE=${DEV_DB_NAME}
+
+WORKDIR /var/task
+
+COPY applications/postcode_splitter/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the layered source the handler imports from. The new splitter pulls
+# only DDD-shaped packages — no pandas, no legacy backend/.
+COPY domain/ domain/
+COPY infrastructure/ infrastructure/
+COPY orchestration/ orchestration/
+COPY repositories/ repositories/
+COPY utilities/ utilities/
+COPY applications/ applications/
+
+# Place the handler at the Lambda task root so the runtime can resolve
+# ``main.handler`` without an extra package prefix.
+COPY applications/landlord_description_overrides/handler.py /var/task/main.py
+
+CMD ["main.handler"]
diff --git a/applications/SAL/handler.py b/applications/SAL/handler.py
new file mode 100644
index 00000000..73dffd5a
--- /dev/null
+++ b/applications/SAL/handler.py
@@ -0,0 +1,46 @@
+from typing import Any
+import boto3
+from orchestration.landlord_description_overrides_orchestrator import (
+    SALOrchestrator,
+)
+from infrastructure.csv_s3_client import CsvS3Client
+from repositories.raw_address.raw_address_csv_s3_repository import (
+    RawAddressCsvS3Repository,
+)
+from domain.addresses.raw_address import AddressList
+
+
+def handler(
+    body: dict[str, Any],
+    context: Any,
+) -> dict[str, list[str]]:
+
+    s3_uri = "s3://retrofit-data-dev/bulk_onboarding_inputs/hyde2 (1).csv"
+    bucket = "retrofit-data-dev"
+
+    # boto3.client is overloaded per-service in the installed stubs; cast
+    # to Any so the strict-mode checker treats it as opaque.
+    boto3_client: Any = boto3.client  # noqa
+    boto_s3: Any = boto3_client("s3")
+
+    csv_client = CsvS3Client(boto_s3, bucket)
+    raw_address_repo = RawAddressCsvS3Repository(csv_client, bucket)
+
+    orchestrator = SALOrchestrator(
+        raw_address_repo=raw_address_repo,
+    )
+
+    list_of_raw_address: AddressList = orchestrator.get_raw_addresses(
+        input_s3_uri=s3_uri
+    )
+
+    col_to_desc_map = orchestrator.get_col_to_description_mappings(
+        list_of_raw_address=list_of_raw_address
+    )
+
+    # Read csv of user input
+    # get the column and unique variations of each description
+    # { walls: "wall variation 1", "wall varition 2"}
+    # Call chatgpt(input from landlord, our way of understanding the mapping) Retrun -> lanlordMapped
+
+    return {"hello world": ["hello world"]}
diff --git a/applications/SAL/local_handler/.env.local.example b/applications/SAL/local_handler/.env.local.example
new file mode 100644
index 00000000..a78a797f
--- /dev/null
+++ b/applications/SAL/local_handler/.env.local.example
@@ -0,0 +1,5 @@
+POSTGRES_HOST=
+POSTGRES_PORT=5432
+POSTGRES_USERNAME=
+POSTGRES_PASSWORD=
+POSTGRES_DATABASE=
\ No newline at end of file
diff --git a/applications/SAL/local_handler/docker-compose.yml b/applications/SAL/local_handler/docker-compose.yml
new file mode 100644
index 00000000..6ead2e33
--- /dev/null
+++ b/applications/SAL/local_handler/docker-compose.yml
@@ -0,0 +1,9 @@
+services:
+  landlord_overrides:
+    build:
+      context: ../../../
+      dockerfile: applications/landlord_description_overrides/Dockerfile
+    ports:
+      - "9002:8080"
+    env_file:
+      - .env.local
diff --git a/applications/SAL/local_handler/invoke_local_lambda.py b/applications/SAL/local_handler/invoke_local_lambda.py
new file mode 100755
index 00000000..4514495f
--- /dev/null
+++ b/applications/SAL/local_handler/invoke_local_lambda.py
@@ -0,0 +1,16 @@
+#!/usr/bin/env python3
+import json
+import requests
+
+HOST = "localhost"
+PORT = "9002"
+
+LAMBDA_URL = f"http://{HOST}:{PORT}/2015-03-31/functions/function/invocations"
+
+payload = {"Records": [{"body": json.dumps({})}]}
+
+response = requests.post(LAMBDA_URL, json=payload)
+
+print("Status code:", response.status_code)
+print("Response:")
+print(response.text)
diff --git a/applications/SAL/local_handler/run_local.sh b/applications/SAL/local_handler/run_local.sh
new file mode 100755
index 00000000..345b60ee
--- /dev/null
+++ b/applications/SAL/local_handler/run_local.sh
@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")"
+
+if [ ! -f .env.local ]; then
+  cp .env.local.example .env.local
+  echo "Created .env.local from the template — fill it in, then re-run." >&2
+  exit 1
+fi
+
+docker compose build --no-cache
+docker compose up --force-recreate
diff --git a/applications/SAL/requirements.txt b/applications/SAL/requirements.txt
new file mode 100644
index 00000000..6a85a255
--- /dev/null
+++ b/applications/SAL/requirements.txt
@@ -0,0 +1,4 @@
+boto3
+pydantic
+sqlmodel
+psycopg2-binary
diff --git a/orchestration/sal_orchestrator.py b/orchestration/sal_orchestrator.py
new file mode 100644
index 00000000..e9584aa1
--- /dev/null
+++ b/orchestration/sal_orchestrator.py
@@ -0,0 +1,23 @@
+from repositories.raw_address.raw_address_repository import RawAddressRepository
+from domain.addresses.raw_address import AddressList
+
+
+class SALOrchestrator:
+    def __init__(self, raw_address_repo: RawAddressRepository) -> None:
+        self._raw_address_repo = raw_address_repo
+
+    def get_raw_addresses(
+        self,
+        input_s3_uri: str,
+    ) -> AddressList:
+        return self._raw_address_repo.load_batch(input_s3_uri)
+
+    def get_col_to_description_mappings(
+        self, list_of_raw_address: AddressList
+    ) -> dict[str, set[str]]:
+        mappings: dict[str, set[str]] = {}
+        for raw_address in list_of_raw_address:
+            for key, value in raw_address.additional_info.items():
+                # Lower-case so case-only typos collapse to one variant.
+                mappings.setdefault(key, set()).add(value.lower())
+        return mappings