ingestr 0.9.5__tar.gz → 0.10.0rc0__tar.gz

{ingestr-0.9.5 → ingestr-0.10.0rc0}/.github/workflows/tests.yml

@@ -20,25 +20,53 @@ env:
 
 jobs:
   tests:
-    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # I tried running stuff on macOS but it was too slow and unreliable.
+        # I also tried windows runners but couldn't get Docker to work there, so I gave up.
+        os: [ubuntu-latest]
+        python-version: ['3.10', '3.11', '3.12']
+    runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4
       - name: install Microsoft ODBC
+        if: matrix.os == 'ubuntu-latest'
         run: sudo ACCEPT_EULA=Y apt-get install msodbcsql18 -y
+      - name: install Microsoft ODBC
+        if: matrix.os == 'macos-13'
+        run: |
+          brew tap microsoft/mssql-release https://github.com/Microsoft/homebrew-mssql-release
+          brew update
+          HOMEBREW_ACCEPT_EULA=Y brew install msodbcsql18
+      - name: Install Docker on macOS
+        if: matrix.os == 'macos-13'
+        run: |
+          brew install docker
+          brew install docker-compose
+          brew install colima
+          colima start
+          # Wait for Docker daemon to be ready
+          while ! docker system info > /dev/null 2>&1; do sleep 1; done
+      - name: install Microsoft ODBC
+        if: matrix.os == 'windows-latest'
+        run: |
+          Invoke-WebRequest -Uri https://go.microsoft.com/fwlink/?linkid=2249006 -OutFile msodbcsql.msi
+          Start-Process -FilePath "msiexec.exe" -ArgumentList "/i msodbcsql.msi /qn /norestart IACCEPTMSODBCSQLLICENSETERMS=YES" -Wait
       - uses: actions/setup-python@v4
         with:
-          python-version: '3.11'
-          cache: 'pip'
-      - name: Cache dependencies
-        uses: actions/cache@v3
-        id: cache
-        with:
-          path: ${{ env.pythonLocation }}
-          key: ${{ env.pythonLocation }}-${{ hashFiles('requirements.txt') }}
+          python-version: ${{ matrix.python-version }}
+      - name: install uv
+        uses: astral-sh/setup-uv@v3
       - name: Install pip dependencies
-        if: steps.cache.outputs.cache-hit != 'true'
         run: make deps-ci
-      - name: run tests
+      - name: run tests (macOS)
+        if: matrix.os == 'macos-13'
+        run: make test-ci
+        env:
+          TESTCONTAINERS_DOCKER_SOCKET_OVERRIDE: /var/run/docker.sock
+          DOCKER_HOST: unix:///Users/runner/.colima/docker.sock
+      - name: run tests (other OS)
+        if: matrix.os != 'macos-13'
         run: make test-ci
       - name: check the formatting
         run: make lint-ci

{ingestr-0.9.5 → ingestr-0.10.0rc0}/.gitignore

@@ -5,6 +5,7 @@ venv
 !.gitkeep
 .vscode/*
 .metals/*
+.coverage.*
 .coverage
 .ruff_cache
 .pytest_cache
@@ -15,4 +16,6 @@ docs/.vitepress/dist
 docs/.vitepress/cache
 node_modules
 *.duckdb
+*.duckdb.wal
 *.db
+*.db.wal

{ingestr-0.9.5 → ingestr-0.10.0rc0}/Makefile

@@ -12,10 +12,10 @@ deps:
 	uv pip install -r requirements-dev.txt
 
 deps-ci:
-	pip install -r requirements-dev.txt
+	uv pip install --system -r requirements-dev.txt
 
 test-ci:
-	pytest -rP -vv --tb=short --cov=ingestr --no-cov-on-fail
+	pytest -n logical -x -rP -vv --tb=short --cov=ingestr --no-cov-on-fail
 
 test: venv
 	. venv/bin/activate; $(MAKE) test-ci

{ingestr-0.9.5 → ingestr-0.10.0rc0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ingestr
-Version: 0.9.5
+Version: 0.10.0rc0
 Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
 Project-URL: Homepage, https://github.com/bruin-data/ingestr
 Project-URL: Issues, https://github.com/bruin-data/ingestr/issues
@@ -13,35 +13,35 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Database
 Requires-Python: >=3.9
-Requires-Dist: confluent-kafka>=2.3.0
+Requires-Dist: confluent-kafka>=2.6.1
 Requires-Dist: databricks-sql-connector==2.9.3
-Requires-Dist: dlt==0.5.1
-Requires-Dist: duckdb-engine==0.11.5
-Requires-Dist: duckdb==0.10.2
+Requires-Dist: dlt==1.4.0
+Requires-Dist: duckdb-engine==0.13.5
+Requires-Dist: duckdb==1.1.3
 Requires-Dist: facebook-business==20.0.0
 Requires-Dist: google-api-python-client==2.130.0
 Requires-Dist: google-cloud-bigquery-storage==2.24.0
-Requires-Dist: mysql-connector-python==9.0.0
+Requires-Dist: mysql-connector-python==9.1.0
 Requires-Dist: pendulum==3.0.0
-Requires-Dist: psycopg2-binary==2.9.9
-Requires-Dist: py-machineid==0.5.1
+Requires-Dist: psycopg2-binary==2.9.10
+Requires-Dist: py-machineid==0.6.0
 Requires-Dist: pyairtable==2.3.3
-Requires-Dist: pymongo==4.6.3
-Requires-Dist: pymysql==1.1.0
-Requires-Dist: pyrate-limiter==3.6.1
-Requires-Dist: redshift-connector==2.1.0
-Requires-Dist: rich==13.7.1
-Requires-Dist: rudder-sdk-python==2.1.0
+Requires-Dist: pymongo==4.10.1
+Requires-Dist: pymysql==1.1.1
+Requires-Dist: pyrate-limiter==3.7.0
+Requires-Dist: redshift-connector==2.1.3
+Requires-Dist: rich==13.9.4
+Requires-Dist: rudder-sdk-python==2.1.4
 Requires-Dist: s3fs==2024.9.0
-Requires-Dist: snowflake-sqlalchemy==1.5.3
-Requires-Dist: sqlalchemy-bigquery==1.11.0
+Requires-Dist: snowflake-sqlalchemy==1.6.1
+Requires-Dist: sqlalchemy-bigquery==1.12.0
 Requires-Dist: sqlalchemy-hana==2.0.0
 Requires-Dist: sqlalchemy-redshift==0.8.14
 Requires-Dist: sqlalchemy2-stubs==0.0.2a38
 Requires-Dist: sqlalchemy==1.4.52
 Requires-Dist: stripe==10.7.0
-Requires-Dist: tqdm==4.66.2
-Requires-Dist: typer==0.12.3
+Requires-Dist: tqdm==4.67.0
+Requires-Dist: typer==0.13.1
 Requires-Dist: types-requests==2.32.0.20240907
 Provides-Extra: odbc
 Requires-Dist: pyodbc==5.1.0; extra == 'odbc'

{ingestr-0.9.5 → ingestr-0.10.0rc0}/ingestr/main.py

@@ -1,19 +1,13 @@
-import hashlib
-import tempfile
 from datetime import datetime
 from enum import Enum
 from typing import Optional
 
-import dlt
-import humanize
 import typer
-from dlt.common.pipeline import LoadInfo
-from dlt.common.runtime.collector import Collector, LogCollector
+from dlt.common.runtime.collector import Collector
 from rich.console import Console
 from rich.status import Status
 from typing_extensions import Annotated
 
-from ingestr.src.factory import SourceDestinationFactory
 from ingestr.src.telemetry.event import track
 
 app = typer.Typer(
@@ -181,6 +175,20 @@ def ingest(
             envvar="PRIMARY_KEY",
         ),
     ] = None,  # type: ignore
+    partition_by: Annotated[
+        Optional[str],
+        typer.Option(
+            help="The partition key to be used for partitioning the destination table",
+            envvar="PARTITION_BY",
+        ),
+    ] = None,  # type: ignore
+    cluster_by: Annotated[
+        Optional[str],
+        typer.Option(
+            help="The clustering key to be used for clustering the destination table, not every destination supports clustering.",
+            envvar="CLUSTER_BY",
+        ),
+    ] = None,  # type: ignore
     yes: Annotated[
         Optional[bool],
         typer.Option(
@@ -252,6 +260,66 @@ def ingest(
         ),
     ] = 5,  # type: ignore
 ):
+    import hashlib
+    import tempfile
+    from datetime import datetime
+
+    import dlt
+    import humanize
+    import typer
+    from dlt.common.destination import Destination
+    from dlt.common.pipeline import LoadInfo
+    from dlt.common.runtime.collector import Collector, LogCollector
+    from dlt.common.schema.typing import TColumnSchema
+
+    from ingestr.src.factory import SourceDestinationFactory
+    from ingestr.src.telemetry.event import track
+
+    def report_errors(run_info: LoadInfo):
+        for load_package in run_info.load_packages:
+            failed_jobs = load_package.jobs["failed_jobs"]
+            if len(failed_jobs) == 0:
+                continue
+
+            print()
+            print("[bold red]Failed jobs:[/bold red]")
+            print()
+            for job in failed_jobs:
+                print(f"[bold red]  {job.job_file_info.job_id()}[/bold red]")
+                print(f"    [bold yellow]Error:[/bold yellow] {job.failed_message}")
+
+            raise typer.Exit(1)
+
+    def validate_source_dest_tables(
+        source_table: str, dest_table: str
+    ) -> tuple[str, str]:
+        if not dest_table:
+            if len(source_table.split(".")) != 2:
+                print(
+                    "[red]Table name must be in the format schema.table for source table when dest-table is not given.[/red]"
+                )
+                raise typer.Abort()
+
+            print()
+            print(
+                "[yellow]Destination table is not given, defaulting to the source table.[/yellow]"
+            )
+            dest_table = source_table
+        return (source_table, dest_table)
+
+    def validate_loader_file_format(
+        dlt_dest: Destination, loader_file_format: Optional[LoaderFileFormat]
+    ):
+        if (
+            loader_file_format
+            and loader_file_format.value
+            not in dlt_dest.capabilities().supported_loader_file_formats
+        ):
+            print(
+                f"[red]Loader file format {loader_file_format.value} is not supported by the destination.[/red]"
+            )
+            raise typer.Abort()
+
     track(
         "command_triggered",
         {
@@ -267,29 +335,23 @@ def ingest(
         dlt.config["schema.naming"] = schema_naming.value
 
     try:
-        if not dest_table:
-            if len(source_table.split(".")) != 2:
-                print(
-                    "[red]Table name must be in the format schema.table for source table when dest-table is not given.[/red]"
-                )
-                raise typer.Abort()
-
-            print()
-            print(
-                "[yellow]Destination table is not given, defaulting to the source table.[/yellow]"
-            )
-            dest_table = source_table
+        (source_table, dest_table) = validate_source_dest_tables(
+            source_table, dest_table
+        )
 
         factory = SourceDestinationFactory(source_uri, dest_uri)
         source = factory.get_source()
         destination = factory.get_destination()
 
+        column_hints: dict[str, TColumnSchema] = {}
         original_incremental_strategy = incremental_strategy
 
         merge_key = None
         if incremental_strategy == IncrementalStrategy.delete_insert:
             merge_key = incremental_key
             incremental_strategy = IncrementalStrategy.merge
+            if incremental_key:
+                column_hints[incremental_key] = {"merge_key": True}
 
         m = hashlib.sha256()
         m.update(dest_table.encode("utf-8"))
@@ -303,11 +365,31 @@ def ingest(
             pipelines_dir = tempfile.mkdtemp()
             is_pipelines_dir_temp = True
 
+        dlt_dest = destination.dlt_dest(uri=dest_uri)
+        validate_loader_file_format(dlt_dest, loader_file_format)
+
+        if partition_by:
+            if partition_by not in column_hints:
+                column_hints[partition_by] = {}
+
+            column_hints[partition_by]["partition"] = True
+
+        if cluster_by:
+            if cluster_by not in column_hints:
+                column_hints[cluster_by] = {}
+
+            column_hints[cluster_by]["cluster"] = True
+
+        if primary_key:
+            for key in primary_key:
+                if key not in column_hints:
+                    column_hints[key] = {}
+
+                column_hints[key]["primary_key"] = True
+
         pipeline = dlt.pipeline(
             pipeline_name=m.hexdigest(),
-            destination=destination.dlt_dest(
-                uri=dest_uri,
-            ),
+            destination=dlt_dest,
             progress=progressInstance,
             pipelines_dir=pipelines_dir,
             refresh="drop_resources" if full_refresh else None,
@@ -400,27 +482,17 @@ def ingest(
             loader_file_format=loader_file_format.value
             if loader_file_format is not None
             else None,  # type: ignore
+            columns=column_hints,
         )
 
-        for load_package in run_info.load_packages:
-            failed_jobs = load_package.jobs["failed_jobs"]
-            if len(failed_jobs) > 0:
-                print()
-                print("[bold red]Failed jobs:[/bold red]")
-                print()
-                for job in failed_jobs:
-                    print(f"[bold red]  {job.job_file_info.job_id()}[/bold red]")
-                    print(f"    [bold yellow]Error:[/bold yellow] {job.failed_message}")
-
-                raise typer.Exit(1)
+        report_errors(run_info)
 
         destination.post_load()
 
         end_time = datetime.now()
         elapsedHuman = ""
-        if run_info.started_at:
-            elapsed = end_time - start_time
-            elapsedHuman = f"in {humanize.precisedelta(elapsed)}"
+        elapsed = end_time - start_time
+        elapsedHuman = f"in {humanize.precisedelta(elapsed)}"
 
         # remove the pipelines_dir folder if it was created by ingestr
         if is_pipelines_dir_temp:

{ingestr-0.9.5 → ingestr-0.10.0rc0}/ingestr/src/gorgias/__init__.py

@@ -99,12 +99,12 @@ def gorgias_source(
                 "description": "When the user was last updated.",
             },
             "meta": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Meta information associated with the user.",
             },
             "data": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Additional data associated with the user.",
             },
@@ -185,17 +185,17 @@ def gorgias_source(
                 "description": "Indicates if the ticket was created by an agent",
             },
             "customer": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": False,
                 "description": "The customer linked to the ticket.",
             },
             "assignee_user": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "User assigned to the ticket",
             },
             "assignee_team": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Team assigned to the ticket",
             },
@@ -210,17 +210,17 @@ def gorgias_source(
                 "description": "Excerpt of the ticket",
             },
             "integrations": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": False,
                 "description": "Integration information related to the ticket",
             },
             "meta": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Meta information related to the ticket",
             },
             "tags": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": False,
                 "description": "Tags associated with the ticket",
             },
@@ -354,7 +354,7 @@ def gorgias_source(
                 "description": "How the message has been received, or sent from Gorgias.",
             },
             "sender": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": False,
                 "description": "The person who sent the message. It can be a user or a customer.",
             },
@@ -364,7 +364,7 @@ def gorgias_source(
                 "description": "ID of the integration that either received or sent the message.",
             },
             "intents": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "",
             },
@@ -379,7 +379,7 @@ def gorgias_source(
                 "description": "Whether the message was sent by your company to a customer, or the opposite.",
             },
             "receiver": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "The primary receiver of the message. It can be a user or a customer. Optional when the source type is 'internal-note'.",
             },
@@ -414,27 +414,27 @@ def gorgias_source(
                 "description": "",
             },
             "headers": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Headers of the message",
             },
             "attachments": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "A list of files attached to the message.",
             },
             "actions": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "A list of actions performed on the message.",
             },
             "macros": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "A list of macros",
             },
             "meta": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Message metadata",
             },
@@ -526,7 +526,7 @@ def gorgias_source(
                 "description": "ID of the customer linked to the survey.",
             },
             "meta": {
-                "data_type": "complex",
+                "data_type": "json",
                 "nullable": True,
                 "description": "Meta information associated with the survey.",
             },