ingestr 0.14.92__tar.gz → 0.14.93__tar.gz

{ingestr-0.14.92 → ingestr-0.14.93}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.14.92
+Version: 0.14.93
 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

ingestr-0.14.93/docs/supported-sources/allium.md

@@ -0,0 +1,164 @@
+# Allium
+
+[Allium](https://allium.so/) is a blockchain data platform that provides access to indexed blockchain data through a powerful query interface.
+
+ingestr supports Allium as a source.
+
+## URI format
+
+The URI format for Allium is as follows:
+
+```plaintext
+allium://?api_key=<api-key>
+```
+
+URI parameters:
+
+- `api_key`: The API key used for authentication with the Allium API (required)
+
+The URI is used to connect to the Allium API for extracting blockchain data.
+
+Query parameters should be passed using ingestr's `--interval-start` and `--interval-end` flags.
+
+## Setting up an Allium Integration
+
+To get your Allium API credentials:
+
+1. Sign up for an Allium account at [allium.so](https://allium.so/)
+2. Navigate to your account settings
+3. Generate an API key
+4. Find your query ID from the Allium explorer interface
+
+Once you have your credentials, here's a sample command that will copy the data from Allium into a DuckDB database:
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:your_query_id' \
+  --interval-start '2025-02-01' \
+  --interval-end '2025-02-02' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.query_results'
+```
+
+The result of this command will be a table in the `allium.duckdb` database.
+
+## Query ID Format
+
+Allium source uses query IDs to identify which query to execute. The query ID should be passed as the `--source-table` parameter with the `query:` prefix.
+
+| Format | Example | Description |
+|--------|---------|-------------|
+| `query:<query_id>` | `query:abc123def456` | The query ID from Allium explorer |
+| `query:<query_id>:<params>` | `query:abc123def456:network=ethereum&min_value=1000` | Query ID with custom parameters |
+| `query:<query_id>:<params>` | `query:abc123def456:limit=5000&compute_profile=standard` | Query ID with run_config parameters |
+
+Each query ID represents a specific blockchain data query that you've created in the Allium explorer.
+
+### Run Config Parameters
+
+Special parameters that control query execution (part of `run_config`):
+
+- `limit`: Limit the number of rows in the result (max 250,000)
+- `compute_profile`: Compute profile identifier
+
+These parameters are passed in the same format as custom parameters but are used for query execution control.
+
+### Custom Query Parameters
+
+You can pass additional custom parameters to your Allium query using the format:
+```
+query:<query_id>:param1=value1&param2=value2
+```
+
+These custom parameters will be merged with the default date parameters. If a custom parameter has the same name as a default parameter, the custom value will take precedence.
+
+## How it works
+
+The Allium source connector:
+
+1. **Starts an async query execution** using your query ID and parameters
+2. **Polls for completion status** every 5 seconds (max 12 hours)
+3. **Fetches and returns the results** once the query completes successfully
+
+## Examples
+
+### Basic Query Ingestion (without date filters)
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:abc123def456' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.transactions'
+```
+
+### Query with Date Parameters
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:abc123def456' \
+  --interval-start '2025-02-01' \
+  --interval-end '2025-02-02' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.daily_transactions'
+```
+
+### Query with Custom Parameters
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:abc123def456:network=ethereum&min_value=1000' \
+  --interval-start '2025-02-01' \
+  --interval-end '2025-02-02' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.filtered_transactions'
+```
+
+In this example, the query will receive both the default date parameters and the custom parameters `network` and `min_value`.
+
+### Query with Run Config Parameters
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:abc123def456:limit=5000&compute_profile=standard' \
+  --interval-start '2025-02-01' \
+  --interval-end '2025-02-02' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.query_results'
+```
+
+This example limits the result to 5000 rows and uses the 'standard' compute profile.
+
+### Query with Both Custom and Run Config Parameters
+
+```sh
+ingestr ingest \
+  --source-uri 'allium://?api_key=your_api_key' \
+  --source-table 'query:abc123def456:network=ethereum&limit=10000&compute_profile=large' \
+  --interval-start '2025-02-01' \
+  --interval-end '2025-02-02' \
+  --dest-uri duckdb:///allium.duckdb \
+  --dest-table 'allium.filtered_transactions'
+```
+
+This example combines custom query parameters (`network`) with run config parameters (`limit` and `compute_profile`).
+
+## Notes
+
+> [!NOTE]
+> - Query execution is asynchronous and may take time depending on the complexity of your query
+> - The connector will wait up to 12 hours for query completion
+> - Use `--interval-start` and `--interval-end` flags to pass date parameters to your Allium query
+> - The dates will be automatically converted to:
+>   - `start_date` and `end_date` parameters in the format `YYYY-MM-DD`
+>   - `start_timestamp` and `end_timestamp` parameters as Unix timestamps (seconds since epoch)
+> - **Default dates**: If not specified, defaults to 2 days ago (00:00) to yesterday (00:00)
+> - Custom parameters can be added to the source table format: `query:your_query_id:param1=value1&param2=value2`
+> - Run config parameters (`limit`, `compute_profile`) are also passed in the source table format
+> - Custom parameters will override default parameters if they have the same name
+> - The `limit` parameter has a maximum value of 250,000 rows
+> - Make sure your query ID is valid and accessible with your API key

ingestr-0.14.93/ingestr/src/allium/__init__.py

@@ -0,0 +1,128 @@
+"""
+Allium source for data extraction via REST API.
+
+This source provides access to Allium blockchain data via asynchronous query execution.
+"""
+
+import time
+from typing import Any, Iterator
+
+import dlt
+
+from ingestr.src.http_client import create_client
+
+
+@dlt.source(max_table_nesting=0, name="allium_source")
+def allium_source(
+    api_key: str,
+    query_id: str,
+    parameters: dict[str, Any] | None = None,
+    limit: int | None = None,
+    compute_profile: str | None = None,
+) -> Any:
+    """
+    Allium data source for blockchain data extraction.
+
+    This source connects to Allium API, runs async queries, and fetches results.
+
+    Args:
+        api_key: Allium API key for authentication
+        query_id: The query ID to execute (e.g., 'abc123')
+        parameters: Optional parameters for the query (e.g., {'start_date': '2025-02-01', 'end_date': '2025-02-02'})
+        limit: Limit the number of rows in the result (max 250,000)
+        compute_profile: Compute profile identifier
+
+    Yields:
+        DltResource: Data resources for Allium query results
+    """
+    base_url = "https://api.allium.so/api/v1/explorer"
+    session = create_client()
+    headers = {"X-API-Key": api_key}
+
+    @dlt.resource(
+        name="query_results",
+        write_disposition="replace",
+    )
+    def fetch_query_results() -> Iterator[dict[str, Any]]:
+        """
+        Fetch query results from Allium.
+
+        This function:
+        1. Starts an async query execution
+        2. Polls for completion status
+        3. Fetches and yields the results
+        """
+        # Step 1: Start async query execution
+        run_config: dict[str, Any] = {}
+        if limit is not None:
+            run_config["limit"] = limit
+        if compute_profile is not None:
+            run_config["compute_profile"] = compute_profile
+
+        run_payload = {"parameters": parameters or {}, "run_config": run_config}
+
+        run_response = session.post(
+            f"{base_url}/queries/{query_id}/run-async",
+            json=run_payload,
+            headers=headers,
+        )
+
+        run_data = run_response.json()
+
+        if "run_id" not in run_data:
+            raise ValueError(f"Failed to start query execution: {run_data}")
+
+        run_id = run_data["run_id"]
+
+        # Step 2: Poll for completion
+        max_retries = 8640  # Max 12 hours with 5-second intervals
+        retry_count = 0
+        poll_interval = 5  # seconds
+
+        while retry_count < max_retries:
+            status_response = session.get(
+                f"{base_url}/query-runs/{run_id}/status",
+                headers=headers,
+            )
+            status_response.raise_for_status()
+            status_data = status_response.json()
+
+            # Handle both string and dict responses
+            if isinstance(status_data, str):
+                status = status_data
+            else:
+                status = status_data.get("status")
+
+            if status == "success":
+                break
+            elif status == "failed":
+                error_msg = (
+                    status_data.get("error", "Unknown error")
+                    if isinstance(status_data, dict)
+                    else "Unknown error"
+                )
+                raise ValueError(f"Query execution failed: {error_msg}")
+            elif status in ["pending", "running", "queued"]:
+                time.sleep(poll_interval)
+                retry_count += 1
+            else:
+                raise ValueError(f"Unknown status: {status}")
+
+        if retry_count >= max_retries:
+            raise TimeoutError(
+                f"Query execution timed out after {max_retries * poll_interval} seconds"
+            )
+
+        # Step 3: Fetch results
+        results_response = session.get(
+            f"{base_url}/query-runs/{run_id}/results",
+            headers=headers,
+            params={"f": "json"},
+        )
+        results_response.raise_for_status()
+        query_output = results_response.json()
+
+        # Extract and yield all data
+        yield query_output.get("data", [])
+
+    return (fetch_query_results,)

ingestr-0.14.93/ingestr/src/buildinfo.py

@@ -0,0 +1 @@
+version = "v0.14.93"

{ingestr-0.14.92 → ingestr-0.14.93}/ingestr/src/factory.py

@@ -28,6 +28,7 @@ from ingestr.src.destinations import (
 from ingestr.src.sources import (
     AdjustSource,
     AirtableSource,
+    AlliumSource,
     AnthropicSource,
     AppleAppStoreSource,
     ApplovinMaxSource,
@@ -156,6 +157,7 @@ class SourceDestinationFactory:
     source_scheme: str
     destination_scheme: str
     sources: Dict[str, Type[SourceProtocol]] = {
+        "allium": AlliumSource,
         "anthropic": AnthropicSource,
         "csv": LocalCsvSource,
         "docebo": DoceboSource,

{ingestr-0.14.92 → ingestr-0.14.93}/ingestr/src/sources.py

@@ -3997,3 +3997,72 @@ class MailchimpSource:
             ).with_resources(table)
         except ResourcesNotFoundError:
             raise UnsupportedResourceError(table, "Mailchimp")
+
+
+class AlliumSource:
+    def handles_incrementality(self) -> bool:
+        return False
+
+    def dlt_source(self, uri: str, table: str, **kwargs):
+        parsed_uri = urlparse(uri)
+        query_params = parse_qs(parsed_uri.query)
+        api_key = query_params.get("api_key")
+
+        if api_key is None:
+            raise MissingValueError("api_key", "Allium")
+
+        # Extract query_id and custom parameters from table parameter
+        # Format: query_id or query:query_id or query:query_id:param1=value1&param2=value2
+        query_id = table
+        custom_params = {}
+        limit = None
+        compute_profile = None
+
+        if ":" in table:
+            parts = table.split(":", 2)  # Split into max 3 parts
+            if len(parts) >= 2:
+                query_id = parts[1]
+            if len(parts) == 3:
+                # Parse custom parameters from query string format
+                param_string = parts[2]
+                for param in param_string.split("&"):
+                    if "=" in param:
+                        key, value = param.split("=", 1)
+                        # Extract run_config parameters
+                        if key == "limit":
+                            limit = int(value)
+                        elif key == "compute_profile":
+                            compute_profile = value
+                        else:
+                            custom_params[key] = value
+
+        # Extract parameters from interval_start and interval_end
+        # Default: 2 days ago 00:00 to yesterday 00:00
+        now = pendulum.now()
+        default_start = now.subtract(days=2).start_of("day")
+        default_end = now.subtract(days=1).start_of("day")
+
+        parameters = {}
+        interval_start = kwargs.get("interval_start")
+        interval_end = kwargs.get("interval_end")
+
+        start_date = interval_start if interval_start is not None else default_start
+        end_date = interval_end if interval_end is not None else default_end
+
+        parameters["start_date"] = start_date.strftime("%Y-%m-%d")
+        parameters["end_date"] = end_date.strftime("%Y-%m-%d")
+        parameters["start_timestamp"] = str(int(start_date.timestamp()))
+        parameters["end_timestamp"] = str(int(end_date.timestamp()))
+
+        # Merge custom parameters (they override default parameters)
+        parameters.update(custom_params)
+
+        from ingestr.src.allium import allium_source
+
+        return allium_source(
+            api_key=api_key[0],
+            query_id=query_id,
+            parameters=parameters if parameters else None,
+            limit=limit,
+            compute_profile=compute_profile,
+        )

ingestr-0.14.92/ingestr/src/buildinfo.py

@@ -1 +0,0 @@
-version = "v0.14.92"