From 6c2b96cbf697adb72fe81f2eb9391441e84fea40 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 15:03:43 +0200
Subject: [PATCH 1/8] feat: setup project

---
 .gitignore                            |  1 +
 .python-version                       |  1 +
 oc4ids_datastore_pipeline/__init__.py |  0
 oc4ids_datastore_pipeline/pipeline.py |  2 ++
 pyproject.toml                        | 16 ++++++++++++++++
 5 files changed, 20 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 .python-version
 create mode 100644 oc4ids_datastore_pipeline/__init__.py
 create mode 100644 oc4ids_datastore_pipeline/pipeline.py
 create mode 100644 pyproject.toml

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..1d17dae
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.venv
diff --git a/.python-version b/.python-version
new file mode 100644
index 0000000..e4fba21
--- /dev/null
+++ b/.python-version
@@ -0,0 +1 @@
+3.12
diff --git a/oc4ids_datastore_pipeline/__init__.py b/oc4ids_datastore_pipeline/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/oc4ids_datastore_pipeline/pipeline.py b/oc4ids_datastore_pipeline/pipeline.py
new file mode 100644
index 0000000..72d762d
--- /dev/null
+++ b/oc4ids_datastore_pipeline/pipeline.py
@@ -0,0 +1,2 @@
+def run() -> None:
+    print("Hello World!")
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..dd3bebb
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,16 @@
+[build-system]
+requires = ["flit_core >=3.2,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "oc4ids-datastore-pipeline"
+description = "OC4IDS Datastore Pipeline"
+version = "1.0.0"
+readme = "README.md"
+dependencies = []
+
+[project.optional-dependencies]
+dev = []
+
+[project.scripts]
+oc4ids-datastore-pipeline = "oc4ids_datastore_pipeline.pipeline:run"

From 2b8397d8fd149a8ad965f9e5148a717bc4049dee Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 15:08:08 +0200
Subject: [PATCH 2/8] feat: add logging

---
 .gitignore                            |  1 +
 oc4ids_datastore_pipeline/__init__.py | 10 ++++++++++
 oc4ids_datastore_pipeline/pipeline.py |  8 +++++++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index 1d17dae..033df5f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
 .venv
+__pycache__
diff --git a/oc4ids_datastore_pipeline/__init__.py b/oc4ids_datastore_pipeline/__init__.py
index e69de29..f330511 100644
--- a/oc4ids_datastore_pipeline/__init__.py
+++ b/oc4ids_datastore_pipeline/__init__.py
@@ -0,0 +1,10 @@
+import logging
+import time
+
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s:%(levelname)s:%(name)s:%(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%S",
+)
+logging.Formatter.converter = time.gmtime
diff --git a/oc4ids_datastore_pipeline/pipeline.py b/oc4ids_datastore_pipeline/pipeline.py
index 72d762d..b54c394 100644
--- a/oc4ids_datastore_pipeline/pipeline.py
+++ b/oc4ids_datastore_pipeline/pipeline.py
@@ -1,2 +1,8 @@
+import logging
+
+
+logger = logging.getLogger(__name__)
+
+
 def run() -> None:
-    print("Hello World!")
+    logger.info("Hello World!")

From 2708978bdd3f3fc455e5c99e8e9cad3d03a4cf6e Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 15:12:19 +0200
Subject: [PATCH 3/8] style: add linting and type-checking

---
 README.md                             | 11 +++++++-
 oc4ids_datastore_pipeline/__init__.py |  1 -
 oc4ids_datastore_pipeline/pipeline.py |  1 -
 pyproject.toml                        | 17 +++++++++++-
 requirements_dev.txt                  | 38 +++++++++++++++++++++++++++
 5 files changed, 64 insertions(+), 4 deletions(-)
 create mode 100644 requirements_dev.txt

diff --git a/README.md b/README.md
index cf82e6b..8d9fe46 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,10 @@
-# oc4ids-datastore-pipeline
\ No newline at end of file
+# OC4IDS Datastore Pipeline
+
+## Run linting
+
+```
+black oc4ids_datastore_pipeline/
+isort oc4ids_datastore_pipeline/
+flake8 oc4ids_datastore_pipeline/
+mypy oc4ids_datastore_pipeline/
+```
diff --git a/oc4ids_datastore_pipeline/__init__.py b/oc4ids_datastore_pipeline/__init__.py
index f330511..c3be62a 100644
--- a/oc4ids_datastore_pipeline/__init__.py
+++ b/oc4ids_datastore_pipeline/__init__.py
@@ -1,7 +1,6 @@
 import logging
 import time
 
-
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s:%(levelname)s:%(name)s:%(message)s",
diff --git a/oc4ids_datastore_pipeline/pipeline.py b/oc4ids_datastore_pipeline/pipeline.py
index b54c394..56081a4 100644
--- a/oc4ids_datastore_pipeline/pipeline.py
+++ b/oc4ids_datastore_pipeline/pipeline.py
@@ -1,6 +1,5 @@
 import logging
 
-
 logger = logging.getLogger(__name__)
 
 
diff --git a/pyproject.toml b/pyproject.toml
index dd3bebb..7313347 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,7 +10,22 @@ readme = "README.md"
 dependencies = []
 
 [project.optional-dependencies]
-dev = []
+dev = [
+  "black",
+  "isort",
+  "flake8",
+  "Flake8-pyproject",
+  "mypy",
+]
 
 [project.scripts]
 oc4ids-datastore-pipeline = "oc4ids_datastore_pipeline.pipeline:run"
+
+[tool.isort]
+profile = "black"
+
+[tool.flake8]
+max-line-length = 88
+
+[tool.mypy]
+strict = true
diff --git a/requirements_dev.txt b/requirements_dev.txt
new file mode 100644
index 0000000..561fb72
--- /dev/null
+++ b/requirements_dev.txt
@@ -0,0 +1,38 @@
+#
+# This file is autogenerated by pip-compile with Python 3.12
+# by the following command:
+#
+#    pip-compile --extra=dev --output-file=requirements_dev.txt pyproject.toml
+#
+black==25.1.0
+    # via oc4ids-datastore-pipeline (pyproject.toml)
+click==8.1.8
+    # via black
+flake8==7.1.1
+    # via
+    #   flake8-pyproject
+    #   oc4ids-datastore-pipeline (pyproject.toml)
+flake8-pyproject==1.2.3
+    # via oc4ids-datastore-pipeline (pyproject.toml)
+isort==6.0.0
+    # via oc4ids-datastore-pipeline (pyproject.toml)
+mccabe==0.7.0
+    # via flake8
+mypy==1.14.1
+    # via oc4ids-datastore-pipeline (pyproject.toml)
+mypy-extensions==1.0.0
+    # via
+    #   black
+    #   mypy
+packaging==24.2
+    # via black
+pathspec==0.12.1
+    # via black
+platformdirs==4.3.6
+    # via black
+pycodestyle==2.12.1
+    # via flake8
+pyflakes==3.2.0
+    # via flake8
+typing-extensions==4.12.2
+    # via mypy

From 31f9d648c3cb0e4306a64c553325897219748370 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 15:15:34 +0200
Subject: [PATCH 4/8] test: add pytest boilerplate

---
 pyproject.toml         |  1 +
 requirements_dev.txt   | 10 +++++++++-
 tests/test_pipeline.py |  2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_pipeline.py

diff --git a/pyproject.toml b/pyproject.toml
index 7313347..a4a59d0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -16,6 +16,7 @@ dev = [
   "flake8",
   "Flake8-pyproject",
   "mypy",
+  "pytest",
 ]
 
 [project.scripts]
diff --git a/requirements_dev.txt b/requirements_dev.txt
index 561fb72..b1ce205 100644
--- a/requirements_dev.txt
+++ b/requirements_dev.txt
@@ -14,6 +14,8 @@ flake8==7.1.1
     #   oc4ids-datastore-pipeline (pyproject.toml)
 flake8-pyproject==1.2.3
     # via oc4ids-datastore-pipeline (pyproject.toml)
+iniconfig==2.0.0
+    # via pytest
 isort==6.0.0
     # via oc4ids-datastore-pipeline (pyproject.toml)
 mccabe==0.7.0
@@ -25,14 +27,20 @@ mypy-extensions==1.0.0
     #   black
     #   mypy
 packaging==24.2
-    # via black
+    # via
+    #   black
+    #   pytest
 pathspec==0.12.1
     # via black
 platformdirs==4.3.6
     # via black
+pluggy==1.5.0
+    # via pytest
 pycodestyle==2.12.1
     # via flake8
 pyflakes==3.2.0
     # via flake8
+pytest==8.3.4
+    # via oc4ids-datastore-pipeline (pyproject.toml)
 typing-extensions==4.12.2
     # via mypy
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
new file mode 100644
index 0000000..af8ff9f
--- /dev/null
+++ b/tests/test_pipeline.py
@@ -0,0 +1,2 @@
+def test_hello_world() -> None:
+    pass

From 27d2c039181bd0f05acd2c2418d700c0483981e1 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 15:21:17 +0200
Subject: [PATCH 5/8] ci: add lint and test checks

---
 .github/workflows/ci.yml | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 .github/workflows/ci.yml

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..b4a8868
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,23 @@
+name: CI
+on: [push]
+
+jobs:
+  ci:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install dev requirements
+        run: pip install -r requirements_dev.txt
+      - name: Check black
+        run: black --check oc4ids_datastore_pipeline/
+      - name: Check isort
+        run: isort --check-only oc4ids_datastore_pipeline/
+      - name: Check flake8
+        run: flake8 oc4ids_datastore_pipeline/
+      - name: Check mypy
+        run: mypy oc4ids_datastore_pipeline/
+      - name: Run tests
+        run: pytest

From c44b4ba828d5b563da6bf5e4e0211222106bda45 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Wed, 29 Jan 2025 16:25:08 +0200
Subject: [PATCH 6/8] docs: add running instructions to readme

---
 README.md | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 8d9fe46..a4f1bf6 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,29 @@
 # OC4IDS Datastore Pipeline
 
-## Run linting
+A Python application to validate and store published OC4IDS datasets.
+
+## Local Development
+
+### Prerequisites
+
+- Python 3.12
+
+### Install Python requirements
+
+```
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements_dev.txt
+```
+
+### Run app
+
+```
+pip install -e .
+oc4ids-datastore-pipeline
+```
+
+### Run linting and type checking
 
 ```
 black oc4ids_datastore_pipeline/
@@ -8,3 +31,9 @@ isort oc4ids_datastore_pipeline/
 flake8 oc4ids_datastore_pipeline/
 mypy oc4ids_datastore_pipeline/
 ```
+
+### Run tests
+
+```
+pytest
+```

From 4319e126bb49898af867cb8c9eaaec4b3da7dd43 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Tue, 4 Feb 2025 10:39:49 +0200
Subject: [PATCH 7/8] build: update version number

---
 pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyproject.toml b/pyproject.toml
index a4a59d0..603c4ba 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -5,7 +5,7 @@ build-backend = "flit_core.buildapi"
 [project]
 name = "oc4ids-datastore-pipeline"
 description = "OC4IDS Datastore Pipeline"
-version = "1.0.0"
+version = "0.1.0"
 readme = "README.md"
 dependencies = []
 

From 2b6b9ba5f7d345f706802b4e6f31125bd0d46307 Mon Sep 17 00:00:00 2001
From: Tilly Woodfield <22456167+tillywoodfield@users.noreply.github.com>
Date: Tue, 4 Feb 2025 10:41:36 +0200
Subject: [PATCH 8/8] ci: run linters on test directory

---
 .github/workflows/ci.yml | 8 ++++----
 README.md                | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index b4a8868..6beb13e 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -12,12 +12,12 @@ jobs:
       - name: Install dev requirements
         run: pip install -r requirements_dev.txt
       - name: Check black
-        run: black --check oc4ids_datastore_pipeline/
+        run: black --check oc4ids_datastore_pipeline/ tests/
       - name: Check isort
-        run: isort --check-only oc4ids_datastore_pipeline/
+        run: isort --check-only oc4ids_datastore_pipeline/ tests/
       - name: Check flake8
-        run: flake8 oc4ids_datastore_pipeline/
+        run: flake8 oc4ids_datastore_pipeline/ tests/
       - name: Check mypy
-        run: mypy oc4ids_datastore_pipeline/
+        run: mypy oc4ids_datastore_pipeline/ tests/
       - name: Run tests
         run: pytest
diff --git a/README.md b/README.md
index a4f1bf6..3fac6a2 100644
--- a/README.md
+++ b/README.md
@@ -26,10 +26,10 @@ oc4ids-datastore-pipeline
 ### Run linting and type checking
 
 ```
-black oc4ids_datastore_pipeline/
-isort oc4ids_datastore_pipeline/
-flake8 oc4ids_datastore_pipeline/
-mypy oc4ids_datastore_pipeline/
+black oc4ids_datastore_pipeline/ tests/
+isort oc4ids_datastore_pipeline/ tests/
+flake8 oc4ids_datastore_pipeline/ tests/
+mypy oc4ids_datastore_pipeline/ tests/
 ```
 
 ### Run tests