ingestr 0.10.1__tar.gz → 0.10.3__tar.gz

ingestr-0.10.3/.githooks/pre-commit-hook.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+echo "scanning for secrets ..."
+
+WORK_DIR="/root/code"
+
+secret_detected() {
+    echo "secrets detected in source code. commit aborted."
+    exit 1
+}
+
+# use gitleaks binary if available
+# else fallback to using docker for running gitleaks
+CMD="gitleaks dir -v"
+
+if [[ ! `which gitleaks`  ]]; then
+    which docker > /dev/null || (echo "gitleaks or docker is required for running secrets scan." && exit 1)
+    CMD="docker run -v $PWD:$WORK_DIR -w $WORK_DIR ghcr.io/gitleaks/gitleaks:latest dir -v"
+fi
+
+$CMD || secret_detected

ingestr-0.10.3/.github/workflows/secrets-scan.yml

@@ -0,0 +1,12 @@
+name: secrets_scan
+on: [pull_request, push, workflow_dispatch]
+jobs:
+  scan:
+    name: gitleaks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: scan for secrets (gitleaks)
+        run: docker run -v $PWD:/code -w /code ghcr.io/gitleaks/gitleaks:latest dir -v

ingestr-0.10.3/.gitleaksignore

@@ -0,0 +1,3 @@
+ingestr/src/telemetry/event.py:generic-api-key:9
+ingestr/src/testdata/fakebqcredentials.json:private-key:5
+docs/supported-sources/shopify.md:generic-api-key:26

{ingestr-0.10.1 → ingestr-0.10.3}/Makefile

@@ -1,11 +1,11 @@
 .ONESHELL:
-.PHONY: test lint format ftl test-ci lint-ci build upload-release
+.PHONY: test lint format test-ci lint-ci build upload-release setup
 
 venv: venv/touchfile
 
 venv/touchfile: requirements-dev.txt requirements.txt
 	test -d venv || python3 -m venv venv
-	. venv/bin/activate; $(MAKE) deps
+	. venv/bin/activate; pip install uv; $(MAKE) deps
 	touch venv/touchfile
 
 deps:
@@ -40,3 +40,7 @@ build:
 
 upload-release:
 	twine upload --verbose dist/*
+
+setup:
+	@echo "installing git hooks ..."
+	@install -m 755 .githooks/pre-commit-hook.sh .git/hooks/pre-commit

{ingestr-0.10.1 → ingestr-0.10.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ingestr
-Version: 0.10.1
+Version: 0.10.3
 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
@@ -26,13 +26,15 @@ Requires-Dist: pendulum==3.0.0
 Requires-Dist: psycopg2-binary==2.9.10
 Requires-Dist: py-machineid==0.6.0
 Requires-Dist: pyairtable==2.3.3
+Requires-Dist: pyarrow==18.1.0
+Requires-Dist: pyathena==3.9.0
 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: s3fs==2024.10.0
 Requires-Dist: snowflake-sqlalchemy==1.6.1
 Requires-Dist: sqlalchemy-bigquery==1.12.0
 Requires-Dist: sqlalchemy-hana==2.0.0
@@ -72,11 +74,20 @@ ingestr is a command-line app that allows you to ingest data from any source int
 ingestr takes away the complexity of managing any backend or writing any code for ingesting data, simply run the command and watch the data land on its destination.
 
 ## Installation
+We recommend using [uv](https://github.com/astral-sh/uv) to run `ingestr`.
 
 ```
-pip install ingestr
+pip install uv
+uvx ingestr
 ```
 
+Alternatively, if you'd like to install it globally:
+```
+uv pip install --system ingestr
+```
+
+While installation with vanilla `pip` is possible, it's an order of magnitude slower.
+
 ## Quickstart
 
 ```bash
@@ -102,6 +113,13 @@ You can see the full documentation [here](https://bruin-data.github.io/ingestr/g
 
 Join our Slack community [here](https://join.slack.com/t/bruindatacommunity/shared_invite/zt-2dl2i8foy-bVsuMUauHeN9M2laVm3ZVg).
 
+## Contributing
+
+Pull requests are welcome. However, please open an issue first to discuss what you would like to change. We maybe able to offer you help and feedback regarding any changes you would like to make.
+
+> [!NOTE]
+> After cloning `ingestr` make sure to run `make setup` to install githooks.
+
 ## Supported sources & destinations
 
 <table>

{ingestr-0.10.1 → ingestr-0.10.3}/README.md

@@ -21,11 +21,20 @@ ingestr is a command-line app that allows you to ingest data from any source int
 ingestr takes away the complexity of managing any backend or writing any code for ingesting data, simply run the command and watch the data land on its destination.
 
 ## Installation
+We recommend using [uv](https://github.com/astral-sh/uv) to run `ingestr`.
 
 ```
-pip install ingestr
+pip install uv
+uvx ingestr
 ```
 
+Alternatively, if you'd like to install it globally:
+```
+uv pip install --system ingestr
+```
+
+While installation with vanilla `pip` is possible, it's an order of magnitude slower.
+
 ## Quickstart
 
 ```bash
@@ -51,6 +60,13 @@ You can see the full documentation [here](https://bruin-data.github.io/ingestr/g
 
 Join our Slack community [here](https://join.slack.com/t/bruindatacommunity/shared_invite/zt-2dl2i8foy-bVsuMUauHeN9M2laVm3ZVg).
 
+## Contributing
+
+Pull requests are welcome. However, please open an issue first to discuss what you would like to change. We maybe able to offer you help and feedback regarding any changes you would like to make.
+
+> [!NOTE]
+> After cloning `ingestr` make sure to run `make setup` to install githooks.
+
 ## Supported sources & destinations
 
 <table>

{ingestr-0.10.1 → ingestr-0.10.3}/docs/.vitepress/config.mjs

@@ -57,6 +57,7 @@ export default defineConfig({
             text: "Databases",
             collapsed: false,
             items: [
+              { text: "Athena", link: "/supported-sources/athena.md" },
               { text: "AWS Redshift", link: "/supported-sources/redshift.md" },
               { text: "Databricks", link: "/supported-sources/databricks.md" },
               { text: "DuckDB", link: "/supported-sources/duckdb.md" },

{ingestr-0.10.1 → ingestr-0.10.3}/docs/getting-started/quickstart.md

@@ -13,9 +13,19 @@ ingestr takes away the complexity of managing any backend or writing any code fo
 
 
 ## Installation
+We recommend using [uv](https://github.com/astral-sh/uv) to run `ingestr`.
+
+```
+pip install uv
+uvx ingestr
 ```
-pip install ingestr
+
+Alternatively, if you'd like to install it globally:
 ```
+uv pip install --system ingestr
+```
+
+While installation with vanilla `pip` is possible, it's an order of magnitude slower.
 
 ## Quickstart
 

ingestr-0.10.3/docs/supported-sources/athena.md

@@ -0,0 +1,36 @@
+# Athena
+[Athena](https://aws.amazon.com/athena/) is an interactive query service that allows users to analyze data directly in Amazon S3 using standard SQL.
+
+The Athena destination stores data as Parquet files in S3 buckets and creates external tables in AWS Glue Catalog.
+
+ingestr supports Athena as a destination.
+
+## URI format
+The URI format for Athena is as follows:
+
+```plaintext
+athena://?bucket=<your-destination-bucket> \
+    query_results_path=<your-query-results-location> \
+    access_key_id=<your-aws-access-key-id> \
+    secret_access_key=<your-aws-secret-access-key> \
+    region_name=<your-aws-region>
+```
+URI parameters:
+- `bucket` (required): The name of the bucket where the data will be stored, containing the Parquet files that Athena will work with, e.g. `your_bucket_name` or `s3://your_bucket_name`.
+- `access_key_id` and `secret_access_key` (required): These are AWS credentials that will be used to authenticate with AWS services like S3 and Athena.
+- `region_name` (required): The AWS region of the Athena service and S3 buckets, e.g. `eu-central-1`
+- `query_results_path` (optional): The query location path where the results of Athena queries will be saved, e.g. `dest_path` or `s3://dest_path`. If not provided, it will default to the bucket specified in the `bucket` parameter.
+- `workgroup` (optional): The name of the Athena workgroup, e.g. `my_group`
+
+## Setting up an Athena Integration
+Athena requires a `bucket`, `access_key_id`, `secret_access_key` and `region_name` to access the S3 bucket. Please follow the guide on dltHub to obtain [credentials](https://dlthub.com/docs/dlt-ecosystem/destinations/athena#2-setup-bucket-storage-and-athena-credentials). Once you've completed the guide, you should have all the above-mentioned credentials.
+```
+ingestr ingest \
+  --source-uri "stripe://?api_key=key123" \
+  --source-table 'event' \
+  --dest-uri "athena://?bucket=bucket_123&access_key_id=access_123&secret_access_key=secret_123&region_name=eu-central-1" \
+  --dest-table 'stripe.event'
+```
+This is a sample command that will copy the data from the Stripe source into Athena.
+
+<img alt="athena_img" src="../media/athena.png" />

{ingestr-0.10.1 → ingestr-0.10.3}/ingestr/main.py

@@ -288,6 +288,8 @@ def ingest(
         ),
     ] = [],  # type: ignore
 ):
+
+    # TODO(turtledev): can't we move this to the top of this file?
     import hashlib
     import tempfile
     from datetime import datetime
@@ -383,6 +385,15 @@ def ingest(
         )
 
         factory = SourceDestinationFactory(source_uri, dest_uri)
+        track(
+            "command_running", 
+            {
+                "command": "ingest",
+                "source_type": factory.source_scheme,
+                "destination_type": factory.destination_scheme,
+            },
+        )
+
         source = factory.get_source()
         destination = factory.get_destination()
 

{ingestr-0.10.1 → ingestr-0.10.3}/ingestr/src/destinations.py

@@ -5,9 +5,10 @@ import json
 import os
 import shutil
 import tempfile
-from urllib.parse import parse_qs, urlparse
+from urllib.parse import parse_qs, quote, urlparse
 
 import dlt
+from dlt.common.configuration.specs import AwsCredentials
 
 
 class GenericSqlDestination:
@@ -194,3 +195,62 @@ class CsvDestination(GenericSqlDestination):
                     csv_writer.writerow(json_obj)
 
         shutil.rmtree(self.temp_path)
+
+
+class AthenaDestination:
+    def dlt_dest(self, uri: str, **kwargs):
+        encoded_uri = quote(uri, safe=":/?&=")
+        source_fields = urlparse(encoded_uri)
+        source_params = parse_qs(source_fields.query)
+
+        bucket = source_params.get("bucket", [None])[0]
+        if not bucket:
+            raise ValueError("A bucket is required to connect to Athena.")
+
+        if not bucket.startswith("s3://"):
+            bucket = f"s3://{bucket}"
+
+        query_result_path = source_params.get("query_results_path", [None])[0]
+        if query_result_path:
+            if not query_result_path.startswith("s3://"):
+                query_result_path = f"s3://{query_result_path}"
+        else:
+            query_result_path = bucket
+
+        access_key_id = source_params.get("access_key_id", [None])[0]
+        if not access_key_id:
+            raise ValueError("The AWS access_key_id is required to connect to Athena.")
+
+        secret_access_key = source_params.get("secret_access_key", [None])[0]
+        if not secret_access_key:
+            raise ValueError("The AWS secret_access_key is required to connect Athena")
+
+        work_group = source_params.get("workgroup", [None])[0]
+
+        region_name = source_params.get("region_name", [None])[0]
+        if not region_name:
+            raise ValueError("The region_name is required to connect to Athena.")
+
+        os.environ["DESTINATION__BUCKET_URL"] = bucket
+        os.environ["DESTINATION__CREDENTIALS__AWS_ACCESS_KEY_ID"] = access_key_id
+        os.environ["DESTINATION__CREDENTIALS__AWS_SECRET_ACCESS_KEY"] = (
+            secret_access_key
+        )
+
+        credentials = AwsCredentials(
+            aws_access_key_id=access_key_id,
+            aws_secret_access_key=secret_access_key,
+            region_name=region_name,
+        )
+        return dlt.destinations.athena(
+            query_result_bucket=query_result_path,
+            athena_work_group=work_group,
+            credentials=credentials,
+            destination_name=bucket,
+        )
+
+    def dlt_run_params(self, uri: str, table: str, **kwargs) -> dict:
+        return {}
+
+    def post_load(self):
+        pass

{ingestr-0.10.1 → ingestr-0.10.3}/ingestr/src/factory.py

@@ -4,6 +4,7 @@ from urllib.parse import urlparse
 from dlt.common.destination import Destination
 
 from ingestr.src.destinations import (
+    AthenaDestination,
     BigQueryDestination,
     CsvDestination,
     DatabricksDestination,
@@ -159,6 +160,7 @@ class SourceDestinationFactory:
             "snowflake": SnowflakeDestination(),
             "synapse": SynapseDestination(),
             "csv": CsvDestination(),
+            "athena": AthenaDestination(),
         }
 
         if self.destination_scheme in match:

ingestr-0.10.3/ingestr/src/version.py

@@ -0,0 +1 @@
+__version__ = "0.10.3"