omnata-plugin-runtime 0.3.21a64__py3-none-any.whl → 0.3.23a69__py3-none-any.whl

omnata_plugin_runtime/omnata_plugin.py

@@ -20,6 +20,7 @@ import json
 import queue
 import threading
 import time
+import hashlib
 from abc import ABC, abstractmethod
 from decimal import Decimal
 from functools import partial, wraps, reduce
@@ -1181,29 +1182,50 @@ class InboundSyncRequest(SyncRequest):
             else:
                 results_df["APP_IDENTIFIER"] = None
             if primary_key_field is not None:
-                # the primary key field could contain a nested field, so we need to check for that
-                # we need to check that each record in the results contains the primary key field
-                if not all(
-                    primary_key_field in record["RECORD_DATA"]
-                    for record in records
-                ):
-                    if "." in primary_key_field:
-                        primary_key_field = primary_key_field.split(".")
-
-                        if not all(
-                            get_nested_value(record["RECORD_DATA"], primary_key_field)
-                            for record in records
-                        ):
+                if isinstance(primary_key_field,list) and len(primary_key_field) == 1:
+                    # don't hash it if it's just a single value
+                    primary_key_field = primary_key_field[0]
+                if isinstance(primary_key_field,list):
+                    primary_key_fields = cast(List[str],primary_key_field)
+                    primary_key_fields = sorted(primary_key_fields)
+                    # handle the sitation where the primary key is a list of fields
+                    # first, check that all records contain all of the primary key fields
+                    if not all(
+                        all(
+                            field in record["RECORD_DATA"]
+                            for field in primary_key_fields
+                        )
+                        for record in records
+                    ):
+                        raise ValueError(
+                            f"Primary key fields '{primary_key_fields}' were not present in all records for stream {stream_name}"
+                        )
+                    # hash all of the primary key fields
+                    results_df["APP_IDENTIFIER"] = results_df["RECORD_DATA"].apply(lambda x: self.get_hash([str(x[field]) for field in primary_key_fields]))
+                else:
+                    # the primary key field could contain a nested field, so we need to check for that
+                    # we need to check that each record in the results contains the primary key field
+                    if not all(
+                        primary_key_field in record["RECORD_DATA"]
+                        for record in records
+                    ):
+                        if "." in primary_key_field:
+                            primary_key_field = primary_key_field.split(".")
+
+                            if not all(
+                                get_nested_value(record["RECORD_DATA"], primary_key_field)
+                                for record in records
+                            ):
+                                raise ValueError(
+                                    f"Primary key field '{primary_key_field}' was not present in all records for stream {stream_name}"
+                                )
+                        else:
                             raise ValueError(
                                 f"Primary key field '{primary_key_field}' was not present in all records for stream {stream_name}"
                             )
-                    else:
-                        raise ValueError(
-                            f"Primary key field '{primary_key_field}' was not present in all records for stream {stream_name}"
-                        )
-                # TODO: handle the scenario where the primary key field is a list, and concatenate the values to form the APP_IDENTIFIER
-                # Currently this is only implemented in the java runtime, since it's typically databases that use composite keys
-                results_df["APP_IDENTIFIER"] = results_df["RECORD_DATA"].apply(lambda x: get_nested_value(dict(x),primary_key_field))
+                    # TODO: handle the scenario where the primary key field is a list, and concatenate the values to form the APP_IDENTIFIER
+                    # Currently this is only implemented in the java runtime, since it's typically databases that use composite keys
+                    results_df["APP_IDENTIFIER"] = results_df["RECORD_DATA"].apply(lambda x: get_nested_value(dict(x),primary_key_field))
             # ensure APP_IDENTIFIER is a string
             results_df["APP_IDENTIFIER"] = results_df["APP_IDENTIFIER"].apply(str)
             # the timestamps in Snowflake are TIMESTAMP_LTZ, so we upload in string format to ensure the
@@ -1238,6 +1260,16 @@ class InboundSyncRequest(SyncRequest):
                 ["APP_IDENTIFIER", "STREAM_NAME", "RECORD_DATA", "RETRIEVE_DATE", "IS_DELETED"]
             )
         ]
+    
+    def get_hash(self, keys:List[str]) -> str:
+        """
+        Creates a hash from a list of keys. 
+        The function will join the keys with an underscore and then create a 
+        SHA256 hash from the string. The function will return the hash as a string.
+        """
+        key_string = "_".join(keys)
+        hash_object = hashlib.sha256(key_string.encode())
+        return hash_object.hexdigest()
 
     def _apply_results_dataframe(self, stream_names: List[str], results_df: pandas.DataFrame):
         """

{omnata_plugin_runtime-0.3.21a64.dist-info → omnata_plugin_runtime-0.3.23a69.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: omnata-plugin-runtime
-Version: 0.3.21a64
+Version: 0.3.23a69
 Summary: Classes and common runtime components for building and running Omnata Plugins
 Author: James Weakley
 Author-email: james.weakley@omnata.com

{omnata_plugin_runtime-0.3.21a64.dist-info → omnata_plugin_runtime-0.3.23a69.dist-info}/RECORD

@@ -3,10 +3,10 @@ omnata_plugin_runtime/api.py,sha256=_N5ok5LN7GDO4J9n3yduXp3tpjmhpySY__U2baiygrs,
 omnata_plugin_runtime/configuration.py,sha256=7cMekoY8CeZAJHpASU6tCMidF55Hzfr7CD74jtebqIY,35742
 omnata_plugin_runtime/forms.py,sha256=pw_aKVsXSz47EP8PFBI3VDwdSN5IjvZxp8JTjO1V130,18421
 omnata_plugin_runtime/logging.py,sha256=bn7eKoNWvtuyTk7RTwBS9UARMtqkiICtgMtzq3KA2V0,3272
-omnata_plugin_runtime/omnata_plugin.py,sha256=ArEtB7LvbLBq9u39Y_2ivg24Hi1Xe-kcnzj5UG4mLP0,100971
+omnata_plugin_runtime/omnata_plugin.py,sha256=EaGIQdq_gcmH2loTluTa0T3YxuUhDNZTQIItzYXtZxE,102783
 omnata_plugin_runtime/plugin_entrypoints.py,sha256=s-SrUnXaS6FaBq1igiJhcCB3Md_a6op-dp_g1H_55QU,27736
 omnata_plugin_runtime/rate_limiting.py,sha256=se6MftQI5NrVHaLb1hByPCgAESPQhkAgIG7KIU1clDU,16562
-omnata_plugin_runtime-0.3.21a64.dist-info/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
-omnata_plugin_runtime-0.3.21a64.dist-info/METADATA,sha256=AN68hzVHcChygxFH76s7iZtvROwge5NqHDNttfkRfko,1604
-omnata_plugin_runtime-0.3.21a64.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-omnata_plugin_runtime-0.3.21a64.dist-info/RECORD,,
+omnata_plugin_runtime-0.3.23a69.dist-info/LICENSE,sha256=IMF9i4xIpgCADf0U-V1cuf9HBmqWQd3qtI3FSuyW4zE,26526
+omnata_plugin_runtime-0.3.23a69.dist-info/METADATA,sha256=u_HhdrNMZOCVn0A9Lv-u9q3KnOmxvRlJLDFAHrU8si0,1604
+omnata_plugin_runtime-0.3.23a69.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+omnata_plugin_runtime-0.3.23a69.dist-info/RECORD,,