Merge branch 'devel' into rfix/extracts-list-of-resources-single-source

.github/weaviate-compose.yml

@@ -11,8 +11,6 @@ services:
     image: semitechnologies/weaviate:1.21.1
     ports:
     - 8080:8080
-    volumes:
-    - weaviate_data
     restart: on-failure:0
     environment:
       QUERY_DEFAULTS_LIMIT: 25

.github/workflows/test_common.yml

@@ -15,6 +15,10 @@ env:
   RUNTIME__LOG_LEVEL: ERROR
   RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
 
+  # we need the secrets only for the rest_api_pipeline tests which are in tests/sources
+  # so we inject them only at the end
+  SOURCES__GITHUB__ACCESS_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
 jobs:
   get_docs_changes:
     name: docs changes
@@ -87,11 +91,11 @@ jobs:
         run: poetry install --no-interaction --with sentry-sdk
 
       - run: |
-          poetry run pytest tests/common tests/normalize tests/reflection tests/sources tests/load/test_dummy_client.py tests/extract/test_extract.py tests/extract/test_sources.py tests/pipeline/test_pipeline_state.py
+          poetry run pytest tests/common tests/normalize tests/reflection tests/load/test_dummy_client.py tests/extract/test_extract.py tests/extract/test_sources.py tests/pipeline/test_pipeline_state.py
         if: runner.os != 'Windows'
         name: Run common tests with minimum dependencies Linux/MAC
       - run: |
-          poetry run pytest tests/common tests/normalize tests/reflection tests/sources tests/load/test_dummy_client.py tests/extract/test_extract.py tests/extract/test_sources.py tests/pipeline/test_pipeline_state.py -m "not forked"
+          poetry run pytest tests/common tests/normalize tests/reflection tests/load/test_dummy_client.py tests/extract/test_extract.py tests/extract/test_sources.py tests/pipeline/test_pipeline_state.py -m "not forked"
         if: runner.os == 'Windows'
         name: Run common tests with minimum dependencies Windows
         shell: cmd
@@ -122,15 +126,29 @@ jobs:
         name: Run pipeline tests with pyarrow but no pandas installed Windows
         shell: cmd
 
-      - name: Install pipeline dependencies
-        run: poetry install --no-interaction -E duckdb -E cli -E parquet --with sentry-sdk --with pipeline -E deltalake
+      - name: Install pipeline and sources dependencies
+        run: poetry install --no-interaction -E duckdb -E cli -E parquet -E deltalake -E sql_database --with sentry-sdk,pipeline,sources
+
+      - run: |
+          poetry run pytest tests/extract tests/pipeline tests/libs tests/cli/common tests/destinations tests/sources
+        if: runner.os != 'Windows'
+        name: Run extract and pipeline tests Linux/MAC
+      - run: |
+          poetry run pytest tests/extract tests/pipeline tests/libs tests/cli/common tests/destinations tests/sources -m "not forked"
+        if: runner.os == 'Windows'
+        name: Run extract tests Windows
+        shell: cmd
+
+      # here we upgrade sql alchemy to 2 an run the sql_database tests again
+      - name: Upgrade sql alchemy
+        run: poetry run pip install sqlalchemy==2.0.32
 
       - run: |
-          poetry run pytest tests/extract tests/pipeline tests/libs tests/cli/common tests/destinations
+          poetry run pytest tests/sources/sql_database
         if: runner.os != 'Windows'
         name: Run extract and pipeline tests Linux/MAC
       - run: |
-          poetry run pytest tests/extract tests/pipeline tests/libs tests/cli/common tests/destinations  -m "not forked"
+          poetry run pytest tests/sources/sql_database
         if: runner.os == 'Windows'
         name: Run extract tests Windows
         shell: cmd

.github/workflows/test_destination_athena.yml

@@ -22,7 +22,7 @@ env:
   RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
   ACTIVE_DESTINATIONS: "[\"athena\"]"
   ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
-  EXCLUDED_DESTINATION_CONFIGURATIONS: "[\"athena-parquet-staging-iceberg\", \"athena-parquet-no-staging-iceberg\"]"
+  EXCLUDED_DESTINATION_CONFIGURATIONS: "[\"athena-parquet-iceberg-no-staging-iceberg\", \"athena-parquet-iceberg-staging-iceberg\"]"
 
 jobs:
   get_docs_changes:
@@ -73,11 +73,11 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || !github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_athena_iceberg.yml

@@ -73,11 +73,11 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_bigquery.yml

@@ -72,5 +72,5 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux

.github/workflows/test_destination_clickhouse.yml

@@ -1,4 +1,3 @@
-
 name: test | clickhouse
 
 on:
@@ -8,7 +7,7 @@ on:
       - devel
   workflow_dispatch:
   schedule:
-    - cron:  '0 2 * * *'
+    - cron: '0 2 * * *'
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@@ -20,7 +19,7 @@ env:
   DLT_SECRETS_TOML: ${{ secrets.DLT_SECRETS_TOML }}
 
   ACTIVE_DESTINATIONS: "[\"clickhouse\"]"
-  ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
+  ALL_FILESYSTEM_DRIVERS: "[\"memory\", \"file\"]"
 
 jobs:
   get_docs_changes:
@@ -67,12 +66,51 @@ jobs:
       - name: create secrets.toml
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
+      # OSS ClickHouse
       - run: |
-          poetry run pytest tests/load -m "essential"
-        name: Run essential tests Linux
+          docker compose -f "tests/load/clickhouse/clickhouse-compose.yml" up -d
+          echo "Waiting for ClickHouse to be healthy..."
+          timeout 30s bash -c 'until docker compose -f "tests/load/clickhouse/clickhouse-compose.yml" ps | grep -q "healthy"; do sleep 1; done'
+          echo "ClickHouse is up and running"
+        name: Start ClickHouse OSS
+
+
+      - run: poetry run pytest tests/load --ignore tests/load/sources -m "essential"
+        name: Run essential tests Linux (ClickHouse OSS)
+        if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
+        env:
+          DESTINATION__CLICKHOUSE__CREDENTIALS__HOST: localhost
+          DESTINATION__CLICKHOUSE__CREDENTIALS__DATABASE: dlt_data
+          DESTINATION__CLICKHOUSE__CREDENTIALS__USERNAME: loader
+          DESTINATION__CLICKHOUSE__CREDENTIALS__PASSWORD: loader
+          DESTINATION__CLICKHOUSE__CREDENTIALS__PORT: 9000
+          DESTINATION__CLICKHOUSE__CREDENTIALS__HTTP_PORT: 8123
+          DESTINATION__CLICKHOUSE__CREDENTIALS__SECURE: 0
+
+      - run: poetry run pytest tests/load --ignore tests/load/sources
+        name: Run all tests Linux (ClickHouse OSS)
+        if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}
+        env:
+          DESTINATION__CLICKHOUSE__CREDENTIALS__HOST: localhost
+          DESTINATION__CLICKHOUSE__CREDENTIALS__DATABASE: dlt_data
+          DESTINATION__CLICKHOUSE__CREDENTIALS__USERNAME: loader
+          DESTINATION__CLICKHOUSE__CREDENTIALS__PASSWORD: loader
+          DESTINATION__CLICKHOUSE__CREDENTIALS__PORT: 9000
+          DESTINATION__CLICKHOUSE__CREDENTIALS__HTTP_PORT: 8123
+          DESTINATION__CLICKHOUSE__CREDENTIALS__SECURE: 0
+
+      - name: Stop ClickHouse OSS
+        if: always()
+        run: docker compose -f "tests/load/clickhouse/clickhouse-compose.yml" down -v
+
+      # ClickHouse Cloud
+      - run: |
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
+        name: Run essential tests Linux (ClickHouse Cloud)
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
-        name: Run all tests Linux
+          poetry run pytest tests/load --ignore tests/load/sources
+        name: Run all tests Linux (ClickHouse Cloud)
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}
+

.github/workflows/test_destination_databricks.yml

@@ -70,11 +70,11 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_dremio.yml

@@ -43,7 +43,7 @@ jobs:
         uses: actions/checkout@master
 
       - name: Start dremio
-        run: docker-compose -f "tests/load/dremio/docker-compose.yml" up -d
+        run: docker compose -f "tests/load/dremio/docker-compose.yml" up -d
 
       - name: Setup Python
         uses: actions/setup-python@v4
@@ -68,7 +68,7 @@ jobs:
         run: poetry install --no-interaction -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         if: runner.os != 'Windows'
         name: Run tests Linux/MAC
         env:
@@ -80,11 +80,11 @@ jobs:
           DESTINATION__MINIO__CREDENTIALS__ENDPOINT_URL: http://127.0.0.1:9010
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         if: runner.os == 'Windows'
         name: Run tests Windows
         shell: cmd
 
       - name: Stop dremio
         if: always()
-        run: docker-compose -f "tests/load/dremio/docker-compose.yml" down -v
+        run: docker compose -f "tests/load/dremio/docker-compose.yml" down -v

.github/workflows/test_destination_lancedb.yml

@@ -71,11 +71,11 @@ jobs:
         run: poetry run pip install openai
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_motherduck.yml

@@ -0,0 +1,80 @@
+
+name: dest | motherduck
+
+on:
+  pull_request:
+    branches:
+      - master
+      - devel
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 2 * * *'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+env:
+  DLT_SECRETS_TOML: ${{ secrets.DLT_SECRETS_TOML }}
+
+  RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752
+  RUNTIME__LOG_LEVEL: ERROR
+  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}
+
+  ACTIVE_DESTINATIONS: "[\"motherduck\"]"
+  ALL_FILESYSTEM_DRIVERS: "[\"memory\"]"
+
+jobs:
+  get_docs_changes:
+    name: docs changes
+    uses: ./.github/workflows/get_docs_changes.yml
+    if: ${{ !github.event.pull_request.head.repo.fork || contains(github.event.pull_request.labels.*.name, 'ci from fork')}}
+
+  run_loader:
+    name: dest | motherduck tests
+    needs: get_docs_changes
+    if: needs.get_docs_changes.outputs.changes_outside_docs == 'true'
+    defaults:
+      run:
+        shell: bash
+    runs-on: "ubuntu-latest"
+
+    steps:
+
+      - name: Check out
+        uses: actions/checkout@master
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10.x"
+
+      - name: Install Poetry
+        uses: snok/[email protected]
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v3
+        with:
+          path: .venv
+          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-motherduck
+
+      - name: Install dependencies
+        run: poetry install --no-interaction -E motherduck -E s3 -E gs -E az -E parquet --with sentry-sdk --with pipeline
+
+      - name: create secrets.toml
+        run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
+
+      - run: |
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
+        name: Run essential tests Linux
+        if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
+
+      - run: |
+          poetry run pytest tests/load --ignore tests/load/sources
+        name: Run all tests Linux
+        if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_mssql.yml

@@ -75,5 +75,5 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       # always run full suite, also on branches
-      - run: poetry run pytest tests/load
+      - run: poetry run pytest tests/load --ignore tests/load/sources
         name: Run tests Linux

.github/workflows/test_destination_qdrant.yml

@@ -69,11 +69,11 @@ jobs:
         run: poetry install --no-interaction -E qdrant -E parquet --with sentry-sdk --with pipeline
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_snowflake.yml

@@ -70,11 +70,11 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}

.github/workflows/test_destination_synapse.yml

@@ -73,11 +73,11 @@ jobs:
         run: pwd && echo "$DLT_SECRETS_TOML" > tests/.dlt/secrets.toml
 
       - run: |
-          poetry run pytest tests/load -m "essential"
+          poetry run pytest tests/load --ignore tests/load/sources -m "essential"
         name: Run essential tests Linux
         if: ${{ ! (contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule')}}
 
       - run: |
-          poetry run pytest tests/load
+          poetry run pytest tests/load --ignore tests/load/sources
         name: Run all tests Linux
         if: ${{ contains(github.event.pull_request.labels.*.name, 'ci full') || github.event_name == 'schedule'}}