Update _process_stdout within SlingResource to handle Emojis

python_modules/libraries/dagster-sling/dagster_sling/resources.py

@@ -238,9 +238,27 @@ def _clean_line(self, line: str) -> str:
 
     def _process_stdout(self, stdout: IO[AnyStr], encoding="utf8") -> Iterator[str]:
         """Process stdout from the Sling CLI."""
+        emoji_pattern = re.compile(
+            "["
+            "\U0001f600-\U0001f64f"  # emoticons
+            "\U0001f300-\U0001f5ff"  # symbols & pictographs
+            "\U0001f680-\U0001f6ff"  # transport & map symbols
+            "\U0001f700-\U0001f77f"  # alchemical symbols
+            "\U0001f780-\U0001f7ff"  # Geometric Shapes Extended
+            "\U0001f800-\U0001f8ff"  # Supplemental Arrows-C
+            "\U0001f900-\U0001f9ff"  # Supplemental Symbols and Pictographs
+            "\U0001fa00-\U0001fa6f"  # Chess Symbols
+            "\U0001fa70-\U0001faff"  # Symbols and Pictographs Extended-A
+            "\U00002702-\U000027b0"  # Dingbats
+            "\U000024c2-\U0001f251"
+            "]+",
+            flags=re.UNICODE,
+        )
+
         for line in stdout:
             assert isinstance(line, bytes)
             fmt_line = bytes.decode(line, encoding=encoding, errors="replace")
+            fmt_line = emoji_pattern.sub(r"", fmt_line)
             yield self._clean_line(fmt_line)
 
     def _exec_sling_cmd(

python_modules/libraries/dagster-sling/dagster_sling_tests/test_dagster_sling_translator.py

@@ -1,5 +1,8 @@
+import io
+
 import pytest
 from dagster import AssetKey, AutoMaterializePolicy, FreshnessPolicy, JsonMetadataValue
+from dagster_sling import SlingResource
 from dagster_sling.dagster_sling_translator import DagsterSlingTranslator
 
 
@@ -152,3 +155,23 @@ def test_freshness_policy_from_get_asset_spec(stream, expected):
 def test_auto_materialize_policy_from_get_asset_spec(stream, expected):
     translator = DagsterSlingTranslator()
     assert translator.get_asset_spec(stream).auto_materialize_policy == expected
+
+
+def test_process_stdout():
+    # Example stdout containing a variety of emojis and text
+    example_stdout = io.BytesIO(
+        b"Hello World\xf0\x9f\x91\x8b\n"  # Wave emoji
+        b"Does this line have an emoji?\xf0\x9f\x91\x94\n"  # Thinking emoji
+        b"It should not have one if you ask me\xf0\x9f\x99\x87\n"  # Shrugging emoji
+        b"It was the pointing finger emoji that caused trouble!\xf0\x9f\x91\x89\n"  # Pointing right emoji
+    )
+
+    sling_resource = SlingResource(connections=[])
+    processed_lines = [line.strip() for line in sling_resource._process_stdout(example_stdout)]  # noqa: SLF001
+
+    assert processed_lines == [
+        "Hello World",
+        "Does this line have an emoji?",
+        "It should not have one if you ask me",
+        "It was the pointing finger emoji that caused trouble!",
+    ]