fix/pyingest-pgsql-mount: Fix Postgres volume mount and healthcheck for postgres:18-alpine+ (#176)

* Fix volume mount from `/var/lib/postgresql/data` to `/var/lib/postgresql`
   to avoid breakage due to PGDATA change in postgres:18-alpine+
* Use `$$POSTGRES_USER` env var in healthcheck instead of hardcoded username
* Pin default image tag to `postgres:18-alpine` floating tag
* Renames tlc-db to nyc-tlc-db - (updates service/container_name/volume)
* Updates running instructions on README

This addresses a breaking change introduced in [docker-library/postgres#1394](docker-library/postgres#1394).

Author: iobruno

module1-data-ingestion/python-ingest/Dockerfile

@@ -16,11 +16,11 @@ FROM python:3.14-slim AS runner
 WORKDIR /ntlcli/
 
 COPY --from=builder /usr/local/lib/python3.14/site-packages /usr/local/lib/python3.14/site-packages
-COPY --from=builder /usr/local/bin /usr/local/bin
+COPY --from=builder /usr/local/bin/tlc /usr/local/bin/tlc
 COPY --from=builder /app /ntlcli/
 COPY datasets.yaml ./
 
 ENV PYTHONPATH=/ntlcli \
     PYTHONUNBUFFERED=1
 
-CMD ["tlc", "ingest", "-zygf", "--use-polars"]
+CMD ["tlc", "ingest", "-zygf", "--use-polars"]

module1-data-ingestion/python-ingest/README.md

@@ -31,7 +31,7 @@ pre-commit install
 
 **3.** Spin-up the nyc-tlc-db:
 ```shell
-docker compose up -d tlc-db
+docker compose up -d nyc-tlc-db
 ```
 
 **4.** Export ENV VARS to connect to DB:
@@ -69,7 +69,7 @@ You can use any combination of options above to fetch more than dataset group at
 
 **1.** Build the Docker Image with:
 ```shell
-docker build -t iobruno/tlc-cli:latest . --no-cache
+docker build -t nyc-tlc-cli:latest . --no-cache
 ```
 
 **2.** Start a container with it:
@@ -92,4 +92,3 @@ docker run -d --rm \
 - [x] Re-Implement the pipeline with Polars
 - [x] Containerize it and run app on `Docker`
 - [x] Fix Dockerfile to add support for `Podman`
-- [x] Code format/lint with `ruff`

module1-data-ingestion/python-ingest/compose.yaml

@@ -1,41 +1,42 @@
-x-postgres-image: &postgres-image postgres:${POSTGRES_VERSION:-18.1-alpine}
+x-postgres-image: &postgres-image postgres:${POSTGRES_VERSION:-18-alpine}
 
 services:
-  tlc-db:
+  nyc-tlc-db:
     image: *postgres-image
-    container_name: tlc-db
+    container_name: nyc-tlc-db
     environment:
       POSTGRES_USER: 'postgres'
       POSTGRES_PASSWORD: 'postgres'
       POSTGRES_DB: 'nyc_tlc'
     ports:
       - '5432:5432'
     volumes:
-      - vol-tlc-db:/var/lib/postgresql/data
+      - vol-nyc-tlc-db:/var/lib/postgresql
     healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      test: ["CMD-SHELL", "pg_isready -U $$POSTGRES_USER"]
       interval: 5s
       timeout: 5s
       retries: 5
     restart: on-failure
 
-  tlc-cli:
-    image: iobruno/tlc-cli:latest
-    container_name: tlc-cli
-    pull_policy: build
+  nyc-tlc-cli:
+    image: nyc-tlc-cli:latest
+    container_name: nyc-tlc-cli
     build:
-      dockerfile: ./Dockerfile
+      context: .
+      dockerfile: Dockerfile
+    pull_policy: build
     environment:
-      DB_HOST: 'tlc-db'
-      DB_NAME: 'nyc_tlc'
+      DB_HOST: 'nyc-tlc-db'
       DB_USERNAME: 'postgres'
       DB_PASSWORD: 'postgres'
+      DB_NAME: 'nyc_tlc'
     volumes:
       - ./datasets.yml:/app/datasets.yml
     depends_on:
-      tlc-db:
+      nyc-tlc-db:
         condition: service_healthy
 
 volumes:
-  vol-tlc-db:
-    name: vol-tlc-db
+  vol-nyc-tlc-db:
+    name: vol-nyc-tlc-db