Merge branch '202409-loadRules' of https://github.com/implydata/learn…

…-druid into 202409-loadRules

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.4.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-json
+-   repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+    -   id: codespell
+        name: codespell
+        description: Checks for common misspellings in text files.
+        entry: codespell --ignore-words=ignore-spelling-words.txt
+        language: python
+        types: [text]

README.md

@@ -29,7 +29,7 @@ It contains:
 Suggestions or comments? Call into the [discussions](https://github.com/implydata/learn-druid/discussions). Found a problem or want to request a notebook? Raise an [issue](https://github.com/implydata/learn-druid/issues). Want to contribute? Raise a [PR](https://github.com/implydata/learn-druid/pulls).
 
 [Contributions](contributing.md) to this community resource are welcome! Contribute your own notebook on a topic that's not listed here, and check out the [issue](https://github.com/implydata/learn-druid/issues) list, where you'll find bugs and enhancement requests.
- 
+
 Come meet your friendly Apache Druid [community](https://druid.apache.org/community) if you have any questions about the functionality you see here.
 
 ## Pre-requisites
@@ -48,7 +48,7 @@ To use the "Learn Druid" Docker Compose, you need:
 To get started quickly:
 
 1. Clone the repository:
-    
+
    ```bash
    git clone https://github.com/implydata/learn-druid
    ```

contributing.md

@@ -11,14 +11,21 @@ Here are some general guidelines on making a notebook.
 The [contributing](https://github.com/implydata/learn-druid/tree/main/notebooks/99-contributing) folder contains a notebook template as a starting point. You'll find boilerplate elements including:
 
 * Setting the connection to Druid, Kafka, and the data generator.
-* Starter elements for ingesting from example datas sets or the data generator.
+* Starter elements for ingesting from example data sets or the data generator.
 * Clean-up elements, like dropping tables, stopping streaming ingestion, and halting data generator jobs.
-* Re-usable code elements that other contributors have found useful.
+* Reusable code elements that other contributors have found useful.
 
 And don't forget that the template itself is open to contribution!
 
 ### Raise a PR
 
+Please install and run the [pre-commit](https://pre-commit.com/) before raising PRs.
+
+```bash
+pip install pre-commit
+pre-commit install
+```
+
 When you have a notebook and you're ready for feedback, it's a good idea to raise a draft PR first. Feel free to use the comments section to ask for initial feedback, or drop into the docs channel in the official Apache Druid Slack channel.
 
 And when it's ready to go, finalize your PR. Add reviewers, get formal feedback, make any necessary changes, etc. in the usual way.
@@ -39,12 +46,12 @@ Use the same route to run a locally-built Docker image by using the appropriate
 
 ### Run automated tests on notebooks
 
-Make sure that docker compose is down and all volumes have been deleted, then start tests with: 
+Make sure that docker compose is down and all volumes have been deleted, then start tests with:
 
    ```shell
    cd tests
    ./test-notebooks.sh
-   ``` 
+   ```
 
 To test single notebook:
 

docker-compose.yaml

@@ -34,7 +34,7 @@ services:
   postgres:
     image: postgres:alpine3.20
     container_name: postgres
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - metadata_data:/var/lib/postgresql/data
     environment:
@@ -46,11 +46,11 @@ services:
   zookeeper:
     image: zookeeper:3.9.2
     container_name: zookeeper
-    profiles: ["druid-jupyter", "kafka-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "kafka-jupyter", "all-services", "tiered-druid-jupyter"]
     environment:
       - ZOO_MY_ID=1
       - ALLOW_ANONYMOUS_LOGIN=yes
-  
+
   kafka:
     image: bitnami/kafka:3.6.2
     container_name: kafka-broker
@@ -74,11 +74,11 @@ services:
   coordinator:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: coordinator
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - druid_shared:/opt/shared
       - coordinator_var:/opt/druid/var
-    depends_on: 
+    depends_on:
       - zookeeper
       - postgres
     ports:
@@ -91,11 +91,11 @@ services:
   broker:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: broker
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - broker_var:/opt/druid/var
       - druid_shared:/opt/shared
-    depends_on: 
+    depends_on:
       - zookeeper
       - postgres
       - coordinator
@@ -109,11 +109,11 @@ services:
   historical:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: historical
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - druid_shared:/opt/shared
       - historical_var:/opt/druid/var
-    depends_on: 
+    depends_on:
       - zookeeper
       - postgres
       - coordinator
@@ -127,11 +127,11 @@ services:
   historical_slow:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: historical_slow
-    profiles: ["druid-jupyter-tiered-hist"]
+    profiles: ["tiered-druid-jupyter"]
     volumes:
       - druid_shared:/opt/shared
       - historical_2_var:/opt/druid/var
-    depends_on: 
+    depends_on:
       - zookeeper
       - postgres
       - coordinator
@@ -150,11 +150,11 @@ services:
   middlemanager:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: middlemanager
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - druid_shared:/opt/shared
       - middle_var:/opt/druid/var
-    depends_on: 
+    depends_on:
       - zookeeper
       - postgres
       - coordinator
@@ -169,7 +169,7 @@ services:
   router:
     image: imply/druid:${DRUID_VERSION:-30.0.0}
     container_name: router
-    profiles: ["druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["druid-jupyter", "all-services", "tiered-druid-jupyter"]
     volumes:
       - router_var:/opt/druid/var
     depends_on:
@@ -186,7 +186,7 @@ services:
   jupyter:
     image: imply/druid-notebook:latest
     container_name: jupyter
-    profiles: ["jupyter", "kafka-jupyter", "druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["jupyter", "kafka-jupyter", "druid-jupyter", "all-services", "tiered-druid-jupyter"]
     environment:
       JUPYTER_ENABLE_LAB: "yes"
       JUPYTER_TOKEN: "docker"
@@ -203,7 +203,7 @@ services:
   datagen:
     image: imply/datagen:latest
     container_name: datagen
-    profiles: ["jupyter", "kafka-jupyter", "druid-jupyter", "all-services", "druid-jupyter-tiered-hist"]
+    profiles: ["jupyter", "kafka-jupyter", "druid-jupyter", "all-services", "tiered-druid-jupyter"]
     ports:
       - "${DATAGEN_PORT:-9999}:9999"
     volumes:

ignore-spelling-words.txt

@@ -0,0 +1,8 @@
+EGE
+MKE
+MOT
+SAV
+AGS
+
+Rouge
+Nome