Remove faker from Sample-data (#1536)

* Removed Faker as a dependency

* Added ModuleNotFoundError

* Removed faker from requirements.txt

* Removed SampleData plugin from setup.py

ingestion/requirements.txt

@@ -4,7 +4,6 @@ expandvars~=0.6.5
 requests~=2.25.1
 python-dateutil~=2.8.1
 SQLAlchemy~=1.4.5
-Faker~=8.1.1
 commonregex~=1.5.4
 setuptools~=57.0.0
 PyHive~=0.6.4

ingestion/setup.py

@@ -108,7 +108,7 @@ plugins: Dict[str, Set[str]] = {
     "data-profiler": {"openmetadata-data-profiler"},
     "snowflake": {"snowflake-sqlalchemy<=1.2.4"},
     "snowflake-usage": {"snowflake-sqlalchemy<=1.2.4"},
-    "sample-data": {"faker~=8.1.1"},
+    "sample-entity": {"faker~=8.1.1"},
     "superset": {},
     "tableau": {"tableau-api-lib==0.1.22"},
     "vertica": {"sqlalchemy-vertica[vertica-python]>=0.0.5"},

ingestion/src/metadata/ingestion/source/sample_data.py

@@ -18,7 +18,6 @@ from collections import namedtuple
 from dataclasses import dataclass, field
 from typing import Any, Dict, Iterable, List, Union
 
-from faker import Faker
 from pydantic import ValidationError
 
 from metadata.config.common import ConfigModel
@@ -163,58 +162,6 @@ class SampleTableMetadataGenerator:
         return data
 
 
-class GenerateFakeSampleData:
-    def __init__(self) -> None:
-        pass
-
-    @classmethod
-    def check_columns(self, columns):
-        fake = Faker()
-        colData = []
-        colList = [column["name"] for column in columns]
-        for i in range(25):
-            row = []
-            for column in columns:
-                col_name = column["name"]
-                value = None
-                if "id" in col_name:
-                    value = uuid.uuid4()
-                elif "price" in col_name or "currency" in col_name:
-                    value = fake.pricetag()
-                elif "barcode" in col_name:
-                    value = fake.ean(length=13)
-                elif "phone" in col_name:
-                    value = fake.phone_number()
-                elif "zip" in col_name:
-                    value = fake.postcode()
-                elif "address" in col_name:
-                    value = fake.street_address()
-                elif "company" in col_name:
-                    value = fake.company()
-                elif "region" in col_name:
-                    value = fake.street_address()
-                elif "name" in col_name:
-                    value = fake.first_name()
-                elif "city" in col_name:
-                    value = fake.city()
-                elif "country" in col_name:
-                    value = fake.country()
-                if value is None:
-                    if "TIMESTAMP" in column["dataType"] or "date" in col_name:
-                        value = fake.unix_time()
-                    elif "BOOLEAN" in column["dataType"]:
-                        value = fake.pybool()
-                    elif "NUMERIC" in column["dataType"]:
-                        value = fake.pyint()
-                    elif "VARCHAR" in column["dataType"]:
-                        value = fake.text(max_nb_chars=20)
-                    else:
-                        value = None
-                row.append(value)
-            colData.append(row)
-        return {"columns": colList, "rows": colData}
-
-
 class SampleDataSource(Source):
     def __init__(
         self, config: SampleDataSourceConfig, metadata_config: MetadataServerConfig, ctx
@@ -393,10 +340,6 @@ class SampleDataSource(Source):
             ),
         )
         for table in self.tables["tables"]:
-            if not table.get("sampleData"):
-                table["sampleData"] = GenerateFakeSampleData.check_columns(
-                    table["columns"]
-                )
             table_metadata = Table(**table)
             table_and_db = OMetaDatabaseAndTable(table=table_metadata, database=db)
             self.status.scanned("table", table_metadata.name.__root__)

ingestion/src/metadata/ingestion/source/sample_entity.py

@@ -40,7 +40,6 @@ from metadata.ingestion.models.table_metadata import Chart, Dashboard
 from metadata.ingestion.ometa.client import APIError
 from metadata.ingestion.ometa.ometa_api import OpenMetadata
 from metadata.ingestion.ometa.openmetadata_rest import MetadataServerConfig
-from metadata.ingestion.processor.pii import ColumnNameScanner
 from metadata.ingestion.source.sql_source import SQLConnectionConfig
 from metadata.utils.helpers import snake_to_camel
 
@@ -91,7 +90,6 @@ class SampleEntitySource(Source):
         self.config = config
         self.metadata_config = metadata_config
         self.metadata = OpenMetadata(metadata_config)
-        self.column_scanner = ColumnNameScanner()
         self.service_name = lambda: self.faker.word()
         self.service_type = lambda: random.choice(
             ["BigQuery", "Hive", "MSSQL", "MySQL", "Postgres", "Redshift", "Snowflake"]