openmetadata-ingestion 1.5.5.0__py3-none-any.whl → 1.5.7.0__py3-none-any.whl

metadata/ingestion/source/pipeline/gluepipeline/metadata.py

@@ -25,6 +25,7 @@ from metadata.generated.schema.entity.data.pipeline import (
     Task,
     TaskStatus,
 )
+from metadata.generated.schema.entity.data.table import Table
 from metadata.generated.schema.entity.services.connections.pipeline.gluePipelineConnection import (
     GluePipelineConnection,
 )
@@ -40,14 +41,25 @@ from metadata.generated.schema.type.basic import (
     SourceUrl,
     Timestamp,
 )
+from metadata.generated.schema.type.entityLineage import EntitiesEdge, LineageDetails
+from metadata.generated.schema.type.entityLineage import Source as LineageSource
+from metadata.generated.schema.type.entityReference import EntityReference
 from metadata.ingestion.api.models import Either
 from metadata.ingestion.api.steps import InvalidSourceException
 from metadata.ingestion.models.pipeline_status import OMetaPipelineStatus
 from metadata.ingestion.ometa.ometa_api import OpenMetadata
+from metadata.ingestion.source.pipeline.gluepipeline.models import (
+    AmazonRedshift,
+    CatalogSource,
+    JDBCSource,
+    JobNodeResponse,
+    S3Source,
+    S3Target,
+)
 from metadata.ingestion.source.pipeline.pipeline_service import PipelineServiceSource
 from metadata.utils import fqn
 from metadata.utils.logger import ingestion_logger
-from metadata.utils.time_utils import convert_timestamp_to_milliseconds
+from metadata.utils.time_utils import datetime_to_timestamp
 
 logger = ingestion_logger()
 
@@ -63,6 +75,28 @@ STATUS_MAP = {
     "incomplete": StatusType.Failed,
     "pending": StatusType.Pending,
 }
+TABLE_MODEL_MAP = {
+    "AmazonRedshiftSource": AmazonRedshift,
+    "AmazonRedshiftTarget": AmazonRedshift,
+    "AthenaConnectorSource": JDBCSource,
+    "JDBCConnectorSource": JDBCSource,
+    "JDBCConnectorTarget": JDBCSource,
+    "DirectJDBCSource": CatalogSource,
+    "RedshiftSource": CatalogSource,
+    "RedshiftTarget": CatalogSource,
+    "DirectJDBC": CatalogSource,
+}
+STORAGE_MODEL_MAP = {
+    "S3CsvSource": S3Source,
+    "S3JsonSource": S3Source,
+    "S3ParquetSource": S3Source,
+    "S3HudiSource": S3Source,
+    "S3DeltaSource": S3Source,
+    "S3DirectTarget": S3Target,
+    "S3DeltaDirectTarget": S3Target,
+    "S3GlueParquetTarget": S3Target,
+    "S3HudiDirectTarget": S3Target,
+}
 
 
 class GluepipelineSource(PipelineServiceSource):
@@ -145,9 +179,88 @@ class GluepipelineSource(PipelineServiceSource):
                 downstream_tasks.append(self.task_id_mapping[edges["DestinationId"]])
         return downstream_tasks
 
+    def get_lineage_details(self, job) -> Optional[dict]:
+        """
+        Get the Lineage Details of the pipeline
+        """
+        lineage_details = {"sources": [], "targets": []}
+        try:
+            job_details = JobNodeResponse.model_validate(
+                self.glue.get_job(JobName=job)
+            ).Job
+            if job_details and job_details.config_nodes:
+                nodes = job_details.config_nodes
+                for _, node in nodes.items():
+                    for key, entity in node.items():
+                        table_model, storage_model = None, None
+                        if key in TABLE_MODEL_MAP:
+                            table_model = TABLE_MODEL_MAP[key].model_validate(entity)
+                        elif "Catalog" in key:
+                            table_model = CatalogSource.model_validate(entity)
+                        elif key in STORAGE_MODEL_MAP:
+                            storage_model = STORAGE_MODEL_MAP[key].model_validate(
+                                entity
+                            )
+                        if table_model:
+                            for db_service_name in self.get_db_service_names():
+                                table_entity = self.metadata.get_entity_reference(
+                                    entity=Table,
+                                    fqn=fqn.build(
+                                        metadata=self.metadata,
+                                        entity_type=Table,
+                                        table_name=table_model.table_name,
+                                        database_name=table_model.database_name,
+                                        schema_name=table_model.schema_name,
+                                        service_name=db_service_name,
+                                    ),
+                                )
+                                if table_entity:
+                                    if key.endswith("Source"):
+                                        lineage_details["sources"].append(table_entity)
+                                    else:
+                                        lineage_details["targets"].append(table_entity)
+                                    break
+                        if storage_model:
+                            for path in storage_model.Paths or [storage_model.Path]:
+                                container = self.metadata.es_search_container_by_path(
+                                    full_path=path
+                                )
+                                if container and container[0]:
+                                    storage_entity = EntityReference(
+                                        id=container[0].id,
+                                        type="container",
+                                        name=container[0].name.root,
+                                        fullyQualifiedName=container[
+                                            0
+                                        ].fullyQualifiedName.root,
+                                    )
+                                    if storage_entity:
+                                        if key.endswith("Source"):
+                                            lineage_details["sources"].append(
+                                                storage_entity
+                                            )
+                                        else:
+                                            lineage_details["targets"].append(
+                                                storage_entity
+                                            )
+                                        break
+
+        except Exception as exc:
+            logger.debug(traceback.format_exc())
+            logger.warning(
+                f"Failed to get lineage details for job : {job} due to : {exc}"
+            )
+        return lineage_details
+
     def yield_pipeline_status(
         self, pipeline_details: Any
     ) -> Iterable[Either[OMetaPipelineStatus]]:
+        pipeline_fqn = fqn.build(
+            metadata=self.metadata,
+            entity_type=Pipeline,
+            service_name=self.context.get().pipeline_service,
+            pipeline_name=self.context.get().pipeline,
+        )
         for job in self.job_name_list:
             try:
                 runs = self.glue.get_job_runs(JobName=job)
@@ -161,13 +274,13 @@ class GluepipelineSource(PipelineServiceSource):
                                 attempt["JobRunState"].lower(), StatusType.Pending
                             ).value,
                             startTime=Timestamp(
-                                convert_timestamp_to_milliseconds(
-                                    attempt["StartedOn"].timestamp()
+                                datetime_to_timestamp(
+                                    attempt["StartedOn"], milliseconds=True
                                 )
                             ),
                             endTime=Timestamp(
-                                convert_timestamp_to_milliseconds(
-                                    attempt["CompletedOn"].timestamp()
+                                datetime_to_timestamp(
+                                    attempt["CompletedOn"], milliseconds=True
                                 )
                             ),
                         )
@@ -175,20 +288,14 @@ class GluepipelineSource(PipelineServiceSource):
                     pipeline_status = PipelineStatus(
                         taskStatus=task_status,
                         timestamp=Timestamp(
-                            convert_timestamp_to_milliseconds(
-                                attempt["StartedOn"].timestamp()
+                            datetime_to_timestamp(
+                                attempt["StartedOn"], milliseconds=True
                             )
                         ),
                         executionStatus=STATUS_MAP.get(
                             attempt["JobRunState"].lower(), StatusType.Pending
                         ).value,
                     )
-                    pipeline_fqn = fqn.build(
-                        metadata=self.metadata,
-                        entity_type=Pipeline,
-                        service_name=self.context.get().pipeline_service,
-                        pipeline_name=self.context.get().pipeline,
-                    )
                     yield Either(
                         right=OMetaPipelineStatus(
                             pipeline_fqn=pipeline_fqn,
@@ -199,7 +306,7 @@ class GluepipelineSource(PipelineServiceSource):
                 yield Either(
                     left=StackTraceError(
                         name=pipeline_fqn,
-                        error=f"Failed to yield pipeline status: {exc}",
+                        error=f"Failed to yield pipeline status for job {job}: {exc}",
                         stackTrace=traceback.format_exc(),
                     )
                 )
@@ -210,3 +317,42 @@ class GluepipelineSource(PipelineServiceSource):
         """
         Get lineage between pipeline and data sources
         """
+        try:
+            pipeline_fqn = fqn.build(
+                metadata=self.metadata,
+                entity_type=Pipeline,
+                service_name=self.context.get().pipeline_service,
+                pipeline_name=self.context.get().pipeline,
+            )
+
+            pipeline_entity = self.metadata.get_by_name(
+                entity=Pipeline, fqn=pipeline_fqn
+            )
+
+            lineage_details = LineageDetails(
+                pipeline=EntityReference(id=pipeline_entity.id.root, type="pipeline"),
+                source=LineageSource.PipelineLineage,
+            )
+
+            for job in self.job_name_list:
+                lineage_enities = self.get_lineage_details(job)
+                for source in lineage_enities.get("sources"):
+                    for target in lineage_enities.get("targets"):
+                        yield Either(
+                            right=AddLineageRequest(
+                                edge=EntitiesEdge(
+                                    fromEntity=source,
+                                    toEntity=target,
+                                    lineageDetails=lineage_details,
+                                )
+                            )
+                        )
+
+        except Exception as exc:
+            yield Either(
+                left=StackTraceError(
+                    name=pipeline_details.get(NAME),
+                    error=f"Wild error ingesting pipeline lineage {pipeline_details} - {exc}",
+                    stackTrace=traceback.format_exc(),
+                )
+            )

metadata/ingestion/source/pipeline/gluepipeline/models.py

@@ -0,0 +1,78 @@
+#  Copyright 2021 Collate
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#  http://www.apache.org/licenses/LICENSE-2.0
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""
+Glue Pipeline Source Model module
+"""
+
+from typing import List, Optional
+
+from pydantic import BaseModel, Field
+
+
+class EntityDetails(BaseModel):
+    Value: str
+
+
+class SourceDetails(BaseModel):
+    schema_details: EntityDetails = Field(alias="Schema")
+    table_details: EntityDetails = Field(alias="Table")
+
+
+class AmazonRedshift(BaseModel):
+    Name: str
+    Data: SourceDetails
+    database_name: Optional[str] = None
+
+    @property
+    def table_name(self):
+        if self.Data:
+            return self.Data.table_details.Value
+        return None
+
+    @property
+    def schema_name(self):
+        if self.Data:
+            return self.Data.schema_details.Value
+        return None
+
+
+class CatalogSource(BaseModel):
+    Name: str
+    database_name: str = Field(alias="Database")
+    schema_name: Optional[str] = None
+    table_name: str = Field(alias="Table")
+
+
+class JDBCSource(BaseModel):
+    Name: str
+    schema_name: Optional[str] = Field(default=None, alias="SchemaName")
+    database_name: Optional[str] = None
+    table_name: str = Field(alias="ConnectionTable")
+
+
+class S3Source(BaseModel):
+    Name: str
+    Paths: List[str]
+
+
+class S3Target(BaseModel):
+    Name: str
+    Path: str
+    Paths: Optional[str] = None
+
+
+class JobNodes(BaseModel):
+    config_nodes: Optional[dict] = Field(alias="CodeGenConfigurationNodes")
+
+
+class JobNodeResponse(BaseModel):
+    Job: Optional[JobNodes] = None

metadata/ingestion/source/pipeline/pipeline_service.py

@@ -285,6 +285,16 @@ class PipelineServiceSource(TopologyRunnerMixin, Source, ABC):
             else []
         )
 
+    def get_storage_service_names(self) -> List[str]:
+        """
+        Get the list of storage service names
+        """
+        return (
+            self.source_config.lineageInformation.storageServiceNames or []
+            if self.source_config.lineageInformation
+            else []
+        )
+
     def prepare(self):
         """
         Method to implement any required logic before starting the ingestion process

metadata/profiler/metrics/composed/null_ratio.py

@@ -50,8 +50,9 @@ class NullRatio(ComposedMetric):
         results of other Metrics
         """
 
-        count = res.get(Count.name())
-        null_count = res.get(NullCount.name())
-        if count + null_count == 0:
+        count = res.get(Count.name(), 0)
+        null_count = res.get(NullCount.name(), 0)
+        total = count + null_count
+        if total == 0:
             return None
-        return null_count / (null_count + count)
+        return null_count / total

metadata/profiler/orm/functions/table_metric_computer.py

@@ -176,6 +176,8 @@ class SnowflakeTableMetricComputer(BaseTableMetricComputer):
         )
 
         rest = self._runner._session.execute(query).first()
+        if not rest:
+            return None
         if rest.rowCount is None:
             # if we don't have any row count, fallback to the base logic
             return super().compute()

metadata/profiler/orm/types/custom_hex_byte_string.py

@@ -22,6 +22,7 @@ from sqlalchemy.sql.sqltypes import String, TypeDecorator
 from metadata.utils.logger import ingestion_logger
 
 logger = ingestion_logger()
+NULL_BYTE = "\x00"
 
 
 class HexByteString(TypeDecorator):
@@ -63,10 +64,22 @@ class HexByteString(TypeDecorator):
         detected_encoding = chardet.detect(bytes_value).get("encoding")
         if detected_encoding:
             try:
-                value = bytes_value.decode(encoding=detected_encoding)
-                return value
+                # Decode the bytes value with the detected encoding and replace errors with "?"
+                # if bytes cannot be decoded e.g. b"\x66\x67\x67\x9c", if detected_encoding="utf-8"
+                # will result in 'foo�' (instead of failing)
+                str_value = bytes_value.decode(
+                    encoding=detected_encoding, errors="replace"
+                )
+                # Replace NULL_BYTE with empty string to avoid errors with
+                # the database client (should be O(n))
+                str_value = (
+                    str_value.replace(NULL_BYTE, "")
+                    if NULL_BYTE in str_value
+                    else str_value
+                )
+                return str_value
             except Exception as exc:
-                logger.debug("Failed to parse bytes valud as string: %s", exc)
+                logger.debug("Failed to parse bytes value as string: %s", exc)
                 logger.debug(traceback.format_exc())
 
         return value.hex()

metadata/utils/collections.py

@@ -0,0 +1,27 @@
+"""
+Uility classes for collections
+"""
+
+
+class CaseInsensitiveString(str):
+    """
+    A case-insensitive string. Useful for case-insensitive comparisons like SQL.
+    """
+
+    def __eq__(self, other):
+        return self.casefold() == other.casefold()
+
+    def __hash__(self):
+        return hash(self.casefold())
+
+
+class CaseInsensitiveList(list):
+    """A case-insensitive list that treats all its string elements as case-insensitive.
+    Non-string elements are treated with default behavior."""
+
+    def __contains__(self, item):
+        return (
+            any(CaseInsensitiveString(x) == item for x in self)
+            if isinstance(item, str)
+            else any(x == item for x in self)
+        )