From 8dd613caa58c016b26262028425519dac29a033a Mon Sep 17 00:00:00 2001
From: juntao <juntzhang@foxmail.com>
Date: Thu, 23 May 2024 23:45:47 +0800
Subject: [PATCH] Fixes #16235: need quote fullyQualifiedName in Ingestion
 Framework (#16273)

* Fixes #16235: need quote fullyQualifiedName in Ingestion Framework

* MINOR: fix UT issue

* revert: fix UT issue

* revert code

* revert code

* format code
---
 .../reports/web_analytic_report_data_processor.py   |  4 +++-
 .../metadata/ingestion/ometa/mixins/table_mixin.py  |  2 +-
 .../orm_profiler/test_orm_profiler_e2e.py           | 13 ++++++++++---
 .../test_web_analytic_report_processor.py           | 10 +++++-----
 4 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/ingestion/src/metadata/data_insight/processor/reports/web_analytic_report_data_processor.py b/ingestion/src/metadata/data_insight/processor/reports/web_analytic_report_data_processor.py
index 9ab1175f829..bbd78780cd5 100644
--- a/ingestion/src/metadata/data_insight/processor/reports/web_analytic_report_data_processor.py
+++ b/ingestion/src/metadata/data_insight/processor/reports/web_analytic_report_data_processor.py
@@ -108,7 +108,9 @@ class WebAnalyticEntityViewReportDataProcessor(DataProcessor):
 
             entity_obj = EntityObj(split_url[0], split_url[1])
             entity_type = entity_obj.entity_type
-            re_pattern = re.compile(f"(.*{entity_type}/{entity_obj.fqn})")
+            re_pattern = re.compile(
+                f"(.*{re.escape(entity_type)}/{re.escape(entity_obj.fqn)})"
+            )
 
             if (
                 entity_obj.fqn in refined_data
diff --git a/ingestion/src/metadata/ingestion/ometa/mixins/table_mixin.py b/ingestion/src/metadata/ingestion/ometa/mixins/table_mixin.py
index 16c968ba0c1..0096c150f74 100644
--- a/ingestion/src/metadata/ingestion/ometa/mixins/table_mixin.py
+++ b/ingestion/src/metadata/ingestion/ometa/mixins/table_mixin.py
@@ -290,7 +290,7 @@ class OMetaTableMixin:
         Returns:
             Optional[Table]: OM table object
         """
-        return self._get(Table, f"{quote(model_str(fqn))}/tableProfile/latest")
+        return self._get(Table, f"{quote(model_str(fqn), safe='')}/tableProfile/latest")
 
     def create_or_update_custom_metric(
         self, custom_metric: CreateCustomMetricRequest, table_id: str
diff --git a/ingestion/tests/integration/orm_profiler/test_orm_profiler_e2e.py b/ingestion/tests/integration/orm_profiler/test_orm_profiler_e2e.py
index 0c80fdd5305..7fb37cc00c6 100644
--- a/ingestion/tests/integration/orm_profiler/test_orm_profiler_e2e.py
+++ b/ingestion/tests/integration/orm_profiler/test_orm_profiler_e2e.py
@@ -89,8 +89,9 @@ class User(Base):
     signedup = Column(DateTime)
 
 
+# with weird characters of fqn
 class NewUser(Base):
-    __tablename__ = "new_users"
+    __tablename__ = "new/users"
     id = Column(Integer, primary_key=True)
     name = Column(String(256))
     fullname = Column(String(256))
@@ -303,7 +304,7 @@ class ProfilerWorkflowTest(TestCase):
             {
                 "type": "Profiler",
                 "profileSample": 50,
-                "tableFilterPattern": {"includes": ["new_users"]},
+                "tableFilterPattern": {"includes": ["new/users"]},
             }
         )
         workflow_config["processor"] = {"type": "orm-profiler", "config": {}}
@@ -315,13 +316,19 @@ class ProfilerWorkflowTest(TestCase):
 
         table = self.metadata.get_by_name(
             entity=Table,
-            fqn="test_sqlite.main.main.new_users",
+            fqn="test_sqlite.main.main.new/users",
             fields=["tableProfilerConfig"],
         )
         # setting sampleProfile from config has been temporarly removed
         # up until we split tests and profiling
         assert table.tableProfilerConfig is None
 
+        profile = self.metadata.get_latest_table_profile(
+            table.fullyQualifiedName
+        ).profile
+
+        assert profile is not None
+
     def test_workflow_datetime_partition(self):
         """test workflow with partition"""
         workflow_config = deepcopy(ingestion_config)
diff --git a/ingestion/tests/unit/data_insight/test_web_analytic_report_processor.py b/ingestion/tests/unit/data_insight/test_web_analytic_report_processor.py
index cbbf3c0a666..b2292a21275 100644
--- a/ingestion/tests/unit/data_insight/test_web_analytic_report_processor.py
+++ b/ingestion/tests/unit/data_insight/test_web_analytic_report_processor.py
@@ -42,8 +42,8 @@ WEB_ANALYTIC_EVENTS = [
         timestamp=1667475458757,
         eventType=WebAnalyticEventType.PageView.value,
         eventData=PageViewData(
-            fullUrl="http://localhost:8585/table/sample_data.ecommerce_db.shopify.dim_address",
-            url="/table/sample_data.ecommerce_db.shopify.dim_address",
+            fullUrl="http://localhost:8585/table/sample_data.ecommerce_db.shopify.dim(address)",
+            url="/table/sample_data.ecommerce_db.shopify.dim(address)",
             hostname="localhost",
             language="en-US",
             screenSize="2140x1273",
@@ -58,8 +58,8 @@ WEB_ANALYTIC_EVENTS = [
         timestamp=1667475458757,
         eventType=WebAnalyticEventType.PageView.value,
         eventData=PageViewData(
-            fullUrl="http://localhost:8585/table/sample_data.ecommerce_db.shopify.dim_address",
-            url="/table/sample_data.ecommerce_db.shopify.dim_address",
+            fullUrl="http://localhost:8585/table/sample_data.ecommerce_db.shopify.dim(address)",
+            url="/table/sample_data.ecommerce_db.shopify.dim(address)",
             hostname="localhost",
             language="en-US",
             screenSize="2140x1273",
@@ -111,7 +111,7 @@ class WebAnalyticEntityViewReportDataProcessorTest(unittest.TestCase):
 
         assert (
             web_analytic_entity_report_data[
-                "sample_data.ecommerce_db.shopify.dim_address"
+                "sample_data.ecommerce_db.shopify.dim(address)"
             ].views
             == 2
         )