test(bigquery-table-desc) added unit test for desc string cleaning

metadata-ingestion/src/datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -40,6 +40,9 @@
     BigQueryTableRef,
 )
 from datahub.ingestion.source.bigquery_v2.bigquery_config import BigQueryV2Config
+from datahub.ingestion.source.bigquery_v2.bigquery_helper import (
+    unquote_and_decode_unicode_escape_seq,
+)
 from datahub.ingestion.source.bigquery_v2.bigquery_report import BigQueryV2Report
 from datahub.ingestion.source.bigquery_v2.bigquery_schema import (
     BigqueryColumn,
@@ -1073,7 +1076,7 @@ def gen_dataset_workunits(
 
         dataset_properties = DatasetProperties(
             name=datahub_dataset_name.get_table_display_name(),
-            description=self.unquote_and_decode_unicode_escape_seq(table.comment)
+            description=unquote_and_decode_unicode_escape_seq(table.comment)
             if table.comment
             else "",
             qualifiedName=str(datahub_dataset_name),
@@ -1383,21 +1386,3 @@ def add_config_to_report(self):
             self.config.start_time,
             self.config.end_time,
         )
-
-    def unquote_and_decode_unicode_escape_seq(
-        self,
-        string: str,
-        leading_quote: str = '"',
-        trailing_quote: Optional[str] = None,
-    ) -> str:
-        """
-        If string starts and ends with a quote, unquote it and decode Unicode escape sequences
-        """
-        trailing_quote = trailing_quote if trailing_quote else leading_quote
-
-        if string.startswith(leading_quote) and string.endswith(trailing_quote):
-            string = string[1:-1]
-
-        cleaned_string = string.encode().decode("unicode-escape")
-
-        return cleaned_string

metadata-ingestion/src/datahub/ingestion/source/bigquery_v2/bigquery_helper.py

@@ -0,0 +1,19 @@
+from typing import Optional
+
+
+def unquote_and_decode_unicode_escape_seq(
+    string: str,
+    leading_quote: str = '"',
+    trailing_quote: Optional[str] = None,
+) -> str:
+    """
+    If string starts and ends with a quote, unquote it and decode Unicode escape sequences
+    """
+    trailing_quote = trailing_quote if trailing_quote else leading_quote
+
+    if string.startswith(leading_quote) and string.endswith(trailing_quote):
+        string = string[1:-1]
+
+    cleaned_string = string.encode().decode("unicode-escape")
+
+    return cleaned_string

metadata-ingestion/tests/unit/test_bigqueryv2_usage_source.py

@@ -8,6 +8,9 @@
     BigQueryTableRef,
 )
 from datahub.ingestion.source.bigquery_v2.bigquery_config import BigQueryV2Config
+from datahub.ingestion.source.bigquery_v2.bigquery_helper import (
+    unquote_and_decode_unicode_escape_seq,
+)
 from datahub.ingestion.source.bigquery_v2.bigquery_report import BigQueryV2Report
 from datahub.ingestion.source.bigquery_v2.usage import BigQueryUsageExtractor
 from datahub.sql_parsing.schema_resolver import SchemaResolver
@@ -176,3 +179,36 @@ def test_bigquery_table_sanitasitation():
     assert table_identifier.dataset == "dataset-4567"
     assert table_identifier.table == "foo_2016*"
     assert table_identifier.get_table_display_name() == "foo"
+
+
+def test_unquote_and_decode_unicode_escape_seq():
+
+    # Test with a string that starts and ends with quotes and has Unicode escape sequences
+    input_string = '"Hello \\u003cWorld\\u003e"'
+    expected_output = "Hello <World>"
+    result = unquote_and_decode_unicode_escape_seq(input_string)
+    assert result == expected_output
+
+    # Test with a string that does not start and end with quotes
+    input_string = "Hello \\u003cWorld\\u003e"
+    expected_output = "Hello <World>"
+    result = unquote_and_decode_unicode_escape_seq(input_string)
+    assert result == expected_output
+
+    # Test with an empty string
+    input_string = ""
+    expected_output = ""
+    result = unquote_and_decode_unicode_escape_seq(input_string)
+    assert result == expected_output
+
+    # Test with a string that does not have Unicode escape sequences
+    input_string = "No escape sequences here"
+    expected_output = "No escape sequences here"
+    result = unquote_and_decode_unicode_escape_seq(input_string)
+    assert result == expected_output
+
+    # Test with a string that starts and ends with quotes but does not have escape sequences
+    input_string = '"No escape sequences here"'
+    expected_output = "No escape sequences here"
+    result = unquote_and_decode_unicode_escape_seq(input_string)
+    assert result == expected_output