Merge pull request #16 from gdcc/migrate-to-httpx

Migrate to `httpx`

.github/workflows/codespell.yml

@@ -0,0 +1,21 @@
+# Codespell configuration is within .codespellrc
+---
+name: Codespell
+
+on:
+  - push
+  - pull_request
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

.github/workflows/lint.yml

@@ -0,0 +1,8 @@
+name: Ruff
+on: [push, pull_request]
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1

.gitignore

@@ -150,3 +150,15 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Ruff
+.ruff_cache/
+
+# Pyright
+pyrightconfig.json
+
+# MacOS
+.DS_Store
+
+# Poetry
+poetry.lock

README.md

@@ -1,7 +1,7 @@
 <h1 align="center">
   Dataverse Uploader</br>
   <a href="https://badge.fury.io/py/dvuploader"><img src="https://badge.fury.io/py/dvuploader.svg" alt="PyPI version" height="18"></a>
-  <img src="https://img.shields.io/badge/python-3.8 | 3.9 | 3.10 | 3.11-blue.svg" alt="Build Badge">
+  <img src="https://img.shields.io/badge/python-3.9 | 3.10 | 3.11-blue.svg" alt="Build Badge">
   <img src="https://github.com/gdcc/python-dvuploader/actions/workflows/test.yml/badge.svg" alt="Build Badge">
 </h1>
 
@@ -81,7 +81,7 @@ dvuploader my_file.txt my_other_file.txt \
 
 #### Using a config file
 
-Alternatively, you can also supply a `config` file that contains all necessary informations for the uploader. The `config` file is a JSON/YAML file that contains the following keys:
+Alternatively, you can also supply a `config` file that contains all necessary information for the uploader. The `config` file is a JSON/YAML file that contains the following keys:
 
 * `persistent_id`: Persistent identifier of the dataset to upload to.
 * `dataverse_url`: URL of the Dataverse instance.
@@ -114,3 +114,48 @@ The `config` file can then be used as follows:
 ```bash
 dvuploader --config-path config.yml
 ```
+
+## Development
+
+To install the development dependencies, run the following command:
+
+```bash
+pip install poetry
+poetry install --with test
+```
+
+### Running tests locally
+
+In order to test the DVUploader, you need to have a Dataverse instance running. You can start a local Dataverse instance by following these steps:
+
+**1. Start the Dataverse instance**
+
+```bash
+docker compose \
+    -f ./docker/docker-compose-base.yml \
+    --env-file local-test.env \
+    up -d
+```
+
+**2. Set up the environment variables**
+
+```bash
+export BASE_URL=http://localhost:8080
+export $(grep "API_TOKEN" "dv/bootstrap.exposed.env")
+export DVUPLOADER_TESTING=true
+```
+
+**3. Run the test(s) with pytest**
+
+```bash
+python -m pytest -v
+```
+
+### Linting
+
+This repository uses `ruff` to lint the code and `codespell` to check for spelling mistakes. You can run the linters with the following command:
+
+```bash
+python -m ruff
+python -m codespell --check-filenames
+```

docker/docker-compose-base.yml

@@ -0,0 +1,137 @@
+version: "2.4"
+name: pydataverse
+services:
+  dataverse:
+    container_name: "dataverse"
+    hostname: dataverse
+    image: ${DATAVERSE_IMAGE}
+    restart: on-failure
+    user: payara
+    environment:
+      - DATAVERSE_DB_HOST=postgres
+      - DATAVERSE_DB_USER=${DATAVERSE_DB_USER}
+      - DATAVERSE_DB_PASSWORD=${DATAVERSE_DB_PASSWORD}
+      - JVM_ARGS=-Ddataverse.pid.providers=fake
+        -Ddataverse.pid.default-provider=fake
+        -Ddataverse.pid.fake.type=FAKE
+        -Ddataverse.pid.fake.label=FakeDOIProvider
+        -Ddataverse.pid.fake.authority=10.5072
+        -Ddataverse.pid.fake.shoulder=FK2/
+    ports:
+      - "8080:8080"
+    networks:
+      - dataverse
+    depends_on:
+      postgres:
+        condition: service_started
+      solr:
+        condition: service_started
+      dv_initializer:
+        condition: service_completed_successfully
+    volumes:
+      - ${PWD}/dv/data:/dv
+      - ${PWD}:/secrets
+    tmpfs:
+      - /dumps:mode=770,size=2052M,uid=1000,gid=1000
+      - /tmp:mode=770,size=2052M,uid=1000,gid=1000
+    mem_limit: 2147483648 # 2 GiB
+    mem_reservation: 1024m
+    privileged: false
+    healthcheck:
+      test: curl --fail http://dataverse:8080/api/info/version || exit 1
+      interval: 10s
+      retries: 20
+      start_period: 20s
+      timeout: 240s
+
+  dv_initializer:
+    container_name: "dv_initializer"
+    image: ${CONFIGBAKER_IMAGE}
+    restart: "no"
+    command:
+      - sh
+      - -c
+      - "fix-fs-perms.sh dv"
+    volumes:
+      - ${PWD}/dv/data:/dv
+
+  postgres:
+    container_name: "postgres"
+    hostname: postgres
+    image: postgres:${POSTGRES_VERSION}
+    restart: on-failure
+    environment:
+      - POSTGRES_USER=${DATAVERSE_DB_USER}
+      - POSTGRES_PASSWORD=${DATAVERSE_DB_PASSWORD}
+    ports:
+      - "5432:5432"
+    networks:
+      - dataverse
+
+  solr_initializer:
+    container_name: "solr_initializer"
+    image: ${CONFIGBAKER_IMAGE}
+    restart: "no"
+    command:
+      - sh
+      - -c
+      - "fix-fs-perms.sh solr && cp -a /template/* /solr-template"
+    volumes:
+      - ${PWD}/solr/data:/var/solr
+      - ${PWD}/solr/conf:/solr-template
+
+  solr:
+    container_name: "solr"
+    hostname: "solr"
+    image: solr:${SOLR_VERSION}
+    depends_on:
+      solr_initializer:
+        condition: service_completed_successfully
+    restart: on-failure
+    ports:
+      - "8983:8983"
+    networks:
+      - dataverse
+    command:
+      - "solr-precreate"
+      - "collection1"
+      - "/template"
+    volumes:
+      - ${PWD}/solr/data:/var/solr
+      - ${PWD}/solr/conf:/template
+
+  smtp:
+    container_name: "smtp"
+    hostname: "smtp"
+    image: maildev/maildev:2.0.5
+    restart: on-failure
+    expose:
+      - "25" # smtp server
+    environment:
+      - MAILDEV_SMTP_PORT=25
+      - MAILDEV_MAIL_DIRECTORY=/mail
+    networks:
+      - dataverse
+    tmpfs:
+      - /mail:mode=770,size=128M,uid=1000,gid=1000
+
+  bootstrap:
+    container_name: "bootstrap"
+    hostname: "bootstrap"
+    image: ${CONFIGBAKER_IMAGE}
+    restart: "no"
+    networks:
+      - dataverse
+    volumes:
+      - ${PWD}/dv/bootstrap.exposed.env:/.env
+    command:
+      - sh
+      - -c
+      - "bootstrap.sh -e /.env dev"
+    depends_on:
+      dataverse:
+        condition: service_healthy
+
+networks:
+  dataverse:
+    driver: bridge

docker/docker-compose-test-all.yml

@@ -0,0 +1,31 @@
+version: "2.4"
+services:
+  unit-tests:
+    container_name: unit-tests
+    image: python:${PYTHON_VERSION}-slim
+    environment:
+      BASE_URL: http://dataverse:8080
+      DV_VERSION: 6.2
+    networks:
+      - dataverse
+    volumes:
+      - ${PWD}:/pydataverse
+      - ../dv:/dv
+    command:
+      - sh
+      - -c
+      - |
+        # Fetch the API Token from the local file
+        export $(grep "API_TOKEN" "dv/bootstrap.exposed.env")
+        export API_TOKEN_SUPERUSER=$$API_TOKEN
+        cd /pydataverse
+
+        # Run the unit tests
+        python3 -m pip install --upgrade pip
+        python3 -m pip install pytest pytest-cov
+        python3 -m pip install -e .
+        python3 -m pytest > /dv/unit-tests.log
+
+    depends_on:
+      bootstrap:
+        condition: service_completed_successfully

dvuploader/__init__.py

@@ -1,6 +1,6 @@
-from .dvuploader import DVUploader
-from .file import File
-from .utils import add_directory
+from .dvuploader import DVUploader  # noqa: F401
+from .file import File  # noqa: F401
+from .utils import add_directory  # noqa: F401
 
 import nest_asyncio
 

dvuploader/checksum.py

@@ -1,13 +1,10 @@
 import hashlib
 from enum import Enum
-import os
 from typing import IO, Callable
 
 from pydantic import BaseModel, ConfigDict, Field
 
 
-from enum import Enum
-import hashlib
 
 
 class ChecksumTypes(Enum):