hawk-sdk 0.0.0__py3-none-any.whl → 0.0.1__py3-none-any.whl

hawk_sdk/common/constants.py

@@ -0,0 +1 @@
+PROJECT_ID = 'wsb-hc-qasap-ae2e'

hawk_sdk/futures/main.py

@@ -2,25 +2,23 @@
 @description: Datasource API for Hawk Global Futures data access and export functions.
 @author: Rithwik Babu
 """
+from typing import List
+
+from google.cloud import bigquery
 
-from hawk_sdk.common.bigquery_connector import BigQueryConnector
+from hawk_sdk.common.constants import PROJECT_ID
 from hawk_sdk.common.data_object import DataObject
 from hawk_sdk.futures.repository import FuturesRepository
 from hawk_sdk.futures.service import FuturesService
-from typing import List
 
 
 class Futures:
     """Datasource API for fetching Futures data."""
 
-    def __init__(self, project_id: str, credentials_path: str = None) -> None:
-        """Initializes the Futures datasource with required configurations.
-
-        :param project_id: The GCP project ID.
-        :param credentials_path: Path to the Google Cloud credentials file.
-        """
-        self.connector = BigQueryConnector(project_id, credentials_path)
-        self.repository = FuturesRepository(self.connector)
+    def __init__(self, environment="production") -> None:
+        """Initializes the Futures datasource with required configurations."""
+        self.connector = bigquery.Client(project=PROJECT_ID)
+        self.repository = FuturesRepository(self.connector, environment=environment)
         self.service = FuturesService(self.repository)
 
     def get_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> DataObject:
@@ -36,4 +34,3 @@ class Futures:
             name="futures_ohlcvo",
             data=self.service.get_ohlcvo(start_date, end_date, interval, hawk_ids)
         )
-

hawk_sdk/futures/repository.py

@@ -2,58 +2,55 @@
 @description: Repository layer for fetching Futures data from BigQuery.
 @author: Rithwik Babu
 """
-
-from hawk_sdk.common.bigquery_connector import BigQueryConnector
+import logging
 from typing import Iterator, List
 
+from google.cloud import bigquery
+from google.cloud.bigquery import Client
+
 
 class FuturesRepository:
     """Repository for accessing Futures raw data."""
 
-    def __init__(self, connector: BigQueryConnector) -> None:
-        """Initializes the repository with a BigQuery connector.
+    def __init__(self, bq_client: Client, environment: str) -> None:
+        """Initializes the repository with a BigQuery client.
 
-        :param connector: An instance of BigQueryConnector.
+        :param bq_client: An instance of BigQuery Client.
+        :param environment: The environment to fetch data from (e.g., 'production', 'development').
         """
-        self.connector = connector
+        self.bq_client = bq_client
+        self.environment = environment
 
     def fetch_ohlcvo(self, start_date: str, end_date: str, interval: str, hawk_ids: List[int]) -> Iterator[dict]:
-        """Fetches raw data from BigQuery for the given date range and hawk_ids.
+        """Fetches raw data from BigQuery for the given date range and hawk_ids using query parameters."""
 
-        :param start_date: The start date for the data query (YYYY-MM-DD).
-        :param end_date: The end date for the data query (YYYY-MM-DD).
-        :param interval: The interval for the data query (e.g., '1d', '1h', '1m').
-        :param hawk_ids: A list of specific hawk_ids to filter by.
-        :return: An iterator over raw data rows.
-        """
-        hawk_ids_str = ', '.join(map(str, hawk_ids))
-        query = f"""
+        query = """
         WITH records_data AS (
           SELECT 
             r.record_timestamp AS date,
             hi.value AS ticker,
-            MAX(CASE WHEN f.field_name = 'open_{interval}' THEN r.double_value END) AS open,
-            MAX(CASE WHEN f.field_name = 'high_{interval}' THEN r.double_value END) AS high,
-            MAX(CASE WHEN f.field_name = 'low_{interval}' THEN r.double_value END) AS low,
-            MAX(CASE WHEN f.field_name = 'close_{interval}' THEN r.double_value END) AS close,
-            MAX(CASE WHEN f.field_name = 'volume_{interval}' THEN r.int_value END) AS volume,
-            MAX(CASE WHEN f.field_name = 'open_interest_{interval}' THEN r.double_value END) AS open_interest
+            MAX(CASE WHEN f.field_name = @open_field THEN r.double_value END) AS open,
+            MAX(CASE WHEN f.field_name = @high_field THEN r.double_value END) AS high,
+            MAX(CASE WHEN f.field_name = @low_field THEN r.double_value END) AS low,
+            MAX(CASE WHEN f.field_name = @close_field THEN r.double_value END) AS close,
+            MAX(CASE WHEN f.field_name = @volume_field THEN r.int_value END) AS volume,
+            MAX(CASE WHEN f.field_name = @open_interest_field THEN r.double_value END) AS open_interest
           FROM 
-            `wsb-hc-qasap-ae2e.development.records` AS r
+            `wsb-hc-qasap-ae2e.@environment.records` AS r
           JOIN 
-            `wsb-hc-qasap-ae2e.development.fields` AS f
+            `wsb-hc-qasap-ae2e.@environment.fields` AS f
             ON r.field_id = f.field_id
           JOIN 
-            `wsb-hc-qasap-ae2e.development.hawk_identifiers` AS hi
+            `wsb-hc-qasap-ae2e.@environment.hawk_identifiers` AS hi
             ON r.hawk_id = hi.hawk_id
           WHERE 
-            r.hawk_id IN ({hawk_ids_str})
-            AND f.field_name IN ('open_1d', 'high_1d', 'low_1d', 'close_1d', 'volume_1d', 'open_interest_1d')
-            AND r.record_timestamp BETWEEN '{start_date}' AND '{end_date}'
+            r.hawk_id IN UNNEST(@hawk_ids)
+            AND f.field_name IN (@open_field, @high_field, @low_field, @close_field, @volume_field, @open_interest_field)
+            AND r.record_timestamp BETWEEN @start_date AND @end_date
           GROUP BY 
             date, ticker
         )
-        SELECT 
+        SELECT DISTINCT
           date,
           ticker,
           open,
@@ -67,4 +64,25 @@ class FuturesRepository:
         ORDER BY 
           date;
         """
-        return self.connector.run_query(query)
+
+        query_params = [
+            bigquery.ArrayQueryParameter("hawk_ids", "INT64", hawk_ids),
+            bigquery.ScalarQueryParameter("start_date", "STRING", start_date),
+            bigquery.ScalarQueryParameter("end_date", "STRING", end_date),
+            bigquery.ScalarQueryParameter("open_field", "STRING", f"open_{interval}"),
+            bigquery.ScalarQueryParameter("high_field", "STRING", f"high_{interval}"),
+            bigquery.ScalarQueryParameter("low_field", "STRING", f"low_{interval}"),
+            bigquery.ScalarQueryParameter("close_field", "STRING", f"close_{interval}"),
+            bigquery.ScalarQueryParameter("volume_field", "STRING", f"volume_{interval}"),
+            bigquery.ScalarQueryParameter("open_interest_field", "STRING", f"open_interest_{interval}"),
+            bigquery.ScalarQueryParameter("environment", "string", self.environment),
+        ]
+
+        job_config = bigquery.QueryJobConfig(query_parameters=query_params)
+
+        try:
+            query_job = self.bq_client.query(query, job_config=job_config)
+            return query_job.result()
+        except Exception as e:
+            logging.error(f"Failed to fetch OHLCVO data: {e}")
+            raise

hawk_sdk/system/main.py

@@ -0,0 +1,33 @@
+"""
+@description: Datasource API for Hawk Global System data access and export functions.
+@author: Rithwik Babu
+"""
+from typing import List
+
+from google.cloud import bigquery
+
+from hawk_sdk.common.constants import PROJECT_ID
+from hawk_sdk.common.data_object import DataObject
+from hawk_sdk.system.repository import SystemRepository
+from hawk_sdk.system.service import SystemService
+
+
+class System:
+    """Datasource API for fetching System data."""
+
+    def __init__(self, environment="production") -> None:
+        """Initializes the System datasource with required configurations."""
+        self.connector = bigquery.Client(project=PROJECT_ID)
+        self.repository = SystemRepository(self.connector, environment=environment)
+        self.service = SystemService(self.repository)
+
+    def get_hawk_ids(self, tickers: List[str]) -> DataObject:
+        """Fetch hawk_ids for the given list of tickers.
+
+        :param tickers: A list of specific tickers to filter by.
+        :return: A hawk DataObject containing the hawk ID data.
+        """
+        return DataObject(
+            name="system_hawk_id_mappings",
+            data=self.service.get_hawk_ids(tickers)
+        )

hawk_sdk/system/repository.py

@@ -0,0 +1,53 @@
+"""
+@description: Repository layer for fetching System data from BigQuery.
+@author: Rithwik Babu
+"""
+import logging
+from typing import Iterator, List
+
+from google.cloud import bigquery
+from google.cloud.bigquery import Client
+
+
+class SystemRepository:
+    """Repository for accessing System data."""
+
+    def __init__(self, bq_client: Client, environment: str) -> None:
+        """Initializes the repository with a BigQuery client.
+
+        :param bq_client: An instance of BigQuery Client.
+        :param environment: The environment to fetch data from (e.g., 'production', 'development').
+        """
+        self.bq_client = bq_client
+        self.environment = environment
+
+    def fetch_hawk_ids(self, tickers: List[str]) -> Iterator[dict]:
+        """Fetches hawk_ids for the given list of tickers from BigQuery.
+
+        :param tickers: A list of ticker strings to filter by.
+        :return: An iterator over raw data rows.
+        """
+        query = """
+        SELECT 
+            value AS ticker, 
+            hawk_id
+        FROM 
+            `wsb-hc-qasap-ae2e.@environment.hawk_identifiers`
+        WHERE 
+            id_type = 'TICKER'
+            AND value IN UNNEST(@ticker_list)
+        """
+
+        query_params = [
+            bigquery.ArrayQueryParameter("ticker_list", "STRING", tickers),
+            bigquery.ScalarQueryParameter("environment", "string", self.environment),
+        ]
+
+        job_config = bigquery.QueryJobConfig(query_parameters=query_params)
+
+        try:
+            query_job = self.bq_client.query(query, job_config=job_config)
+            return query_job.result()
+        except Exception as e:
+            logging.error(f"Failed to fetch hawk_ids: {e}")
+            raise

hawk_sdk/system/service.py

@@ -0,0 +1,39 @@
+"""
+@description: Service layer for processing and normalizing System data.
+@author: Rithwik Babu
+"""
+
+from typing import List, Iterator
+
+import pandas as pd
+
+from hawk_sdk.system.repository import SystemRepository
+
+
+class SystemService:
+    """Service class for System business logic."""
+
+    def __init__(self, repository: SystemRepository) -> None:
+        """Initializes the service with a repository.
+
+        :param repository: An instance of SystemRepository for data access.
+        """
+        self.repository = repository
+
+    def get_hawk_ids(self, tickers: List[str]) -> pd.DataFrame:
+        """Fetches and normalizes hawk IDs into a pandas DataFrame.
+
+        :param tickers: A list of specific tickers to filter by.
+        :return: A pandas DataFrame containing the normalized hawk ID data.
+        """
+        raw_data = self.repository.fetch_hawk_ids(tickers)
+        return self._normalize_data(raw_data)
+
+    @staticmethod
+    def _normalize_data(data: Iterator[dict]) -> pd.DataFrame:
+        """Converts raw data into a normalized pandas DataFrame.
+
+        :param data: An iterator over raw data rows.
+        :return: A pandas DataFrame containing normalized data.
+        """
+        return pd.DataFrame([dict(row) for row in data])

{hawk_sdk-0.0.0.dist-info → hawk_sdk-0.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hawk-sdk
-Version: 0.0.0
+Version: 0.0.1
 Requires-Dist: google-cloud-bigquery
 Requires-Dist: pandas
 

hawk_sdk-0.0.1.dist-info/RECORD

@@ -0,0 +1,16 @@
+hawk_sdk/__init__.py,sha256=prH_sfjYeRZpBvyYYe5xV8lyn8auj1whvyftpBEHz_Y,37
+hawk_sdk/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+hawk_sdk/common/constants.py,sha256=KmsNfRVCwGeXEBHfo3TzSaDYJDMtnL-YEQKsO1DnWV8,33
+hawk_sdk/common/data_object.py,sha256=qXsnDf__ePw4DbeF9Pe82B2DY05xsID9uU8vyfCUIe0,977
+hawk_sdk/futures/__init__.py,sha256=g0TubD9lrU2xoF1YvHSkNDjn3XehRT6zrIiSdX8C4no,42
+hawk_sdk/futures/main.py,sha256=d12PdblMz79iBexaBfcdUHN5xdMmVZYqHDJHioT-XBk,1535
+hawk_sdk/futures/repository.py,sha256=LRB2SGGrObjce4UbPNn5FHXAmeoY-ZlOWxpNzg6RlBY,3658
+hawk_sdk/futures/service.py,sha256=LaLbNWJMw6kJEjl2SC3eKSCWSGwpKK2JBTnPCHHlL3k,1559
+hawk_sdk/system/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+hawk_sdk/system/main.py,sha256=wXycZyIUMNlbQXD8b57edq642gqinD3sdKabsFyzlu4,1180
+hawk_sdk/system/repository.py,sha256=7SEuZgjhaweO7jFdfv1KybLWCHbJsgbPwdn7n74Pcj8,1721
+hawk_sdk/system/service.py,sha256=1QxvONep7E5-oN1Tiq8xoS-gyt4FVJQUed2ZTw_O0TM,1258
+hawk_sdk-0.0.1.dist-info/METADATA,sha256=a-t1OpVDr10ezom4mb4wDx4wvPfmtXIELsHUDelWEHs,112
+hawk_sdk-0.0.1.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+hawk_sdk-0.0.1.dist-info/top_level.txt,sha256=aSjbudHcWSYsKXH9Wg0L1ltJfDOHXzjYFPO3v3cP-SE,9
+hawk_sdk-0.0.1.dist-info/RECORD,,

{hawk_sdk-0.0.0.dist-info → hawk_sdk-0.0.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.2)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

hawk_sdk/common/bigquery_connector.py

@@ -1,47 +0,0 @@
-"""
-@description: Handles the connection and interaction with Google BigQuery.
-@author: Rithwik Babu
-"""
-
-import os
-from typing import Iterator
-
-from google.cloud import bigquery
-
-
-class BigQueryConnector:
-    """Handles authentication and querying BigQuery."""
-
-    def __init__(self, project_id: str, credentials_path: str = None) -> None:
-        """Initializes BigQuery client and sets up authentication.
-
-        :param project_id: The GCP project ID.
-        :param credentials_path: Path to the Google Cloud credentials file.
-        """
-        if credentials_path:
-            os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path
-
-        if not self._validate_credentials_exists():
-            raise ValueError("Credentials not found. Set GOOGLE_APPLICATION_CREDENTIALS environment variable.")
-
-        self.client = bigquery.Client(project=project_id)
-
-    def run_query(self, query: str) -> Iterator[bigquery.Row]:
-        """Runs a SQL query on BigQuery and returns an iterator over rows.
-
-        :param query: The SQL query to execute.
-        :return: An iterator over the result rows.
-        """
-        query_job = self.client.query(query)
-        return query_job.result()
-
-    def _validate_credentials_exists(self) -> bool:
-        """Validates if the GOOGLE_APPLICATION_CREDENTIALS environment variable is set.
-
-        :return: True if the environment variable is set, False otherwise.
-        """
-        if "GOOGLE_APPLICATION_CREDENTIALS" in os.environ:
-            return True
-        else:
-            print("Environment variable for credentials is not set.")
-            return False

hawk_sdk-0.0.0.dist-info/RECORD

@@ -1,12 +0,0 @@
-hawk_sdk/__init__.py,sha256=prH_sfjYeRZpBvyYYe5xV8lyn8auj1whvyftpBEHz_Y,37
-hawk_sdk/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-hawk_sdk/common/bigquery_connector.py,sha256=QRwd6PW3G2l8d9m114gDCL6PkGCvehu0VKYblHGAlIU,1625
-hawk_sdk/common/data_object.py,sha256=qXsnDf__ePw4DbeF9Pe82B2DY05xsID9uU8vyfCUIe0,977
-hawk_sdk/futures/__init__.py,sha256=g0TubD9lrU2xoF1YvHSkNDjn3XehRT6zrIiSdX8C4no,42
-hawk_sdk/futures/main.py,sha256=yziRSZYlZMNr6UyR03vc9uZJiYtsgT7Q0gv2aNky6Bc,1658
-hawk_sdk/futures/repository.py,sha256=1hoLxO0w46FYWXt8R9mp1pkm2pXGcb3e_Wqp839pDH4,2733
-hawk_sdk/futures/service.py,sha256=LaLbNWJMw6kJEjl2SC3eKSCWSGwpKK2JBTnPCHHlL3k,1559
-hawk_sdk-0.0.0.dist-info/METADATA,sha256=gW5KFDfJ_v5SGT4uM1x_0SOvixrLNHutjYfp_g-UEpQ,112
-hawk_sdk-0.0.0.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-hawk_sdk-0.0.0.dist-info/top_level.txt,sha256=aSjbudHcWSYsKXH9Wg0L1ltJfDOHXzjYFPO3v3cP-SE,9
-hawk_sdk-0.0.0.dist-info/RECORD,,