style: fix ruff formatting issues in spike investigation files

- Apply ruff formatting to test_gzip_utf8_issue.py
- Apply ruff formatting to fix_gzip_parser_selection.py
- Ensure code style compliance for CI checks

Co-Authored-By: unknown <>

Author: devin-ai-integration[bot]

fix_gzip_parser_selection.py

@@ -27,13 +27,13 @@
 class ImprovedCompositeRawDecoder(CompositeRawDecoder):
     """
     Enhanced CompositeRawDecoder with better GZIP detection and error handling.
-    
+
     This addresses the StreamThreadException issue by:
     1. Auto-detecting GZIP content based on magic bytes
     2. Providing better error handling for decompression failures
     3. Falling back gracefully when parser selection fails
     """
-    
+
     def __init__(
         self,
         parser: Parser,
@@ -43,62 +43,62 @@ def __init__(
     ) -> None:
         super().__init__(parser, stream_response, parsers_by_header)
         self._auto_detect_gzip = auto_detect_gzip
-    
+
     def _detect_gzip_content(self, response: requests.Response) -> bool:
         """
         Detect if response content is GZIP-compressed by checking magic bytes.
-        
+
         Returns True if the response starts with GZIP magic number (0x1f, 0x8b).
         This helps identify GZIP content even when Content-Encoding header is missing.
         """
         if not self._auto_detect_gzip:
             return False
-            
+
         try:
-            if hasattr(response, 'raw') and response.raw:
-                current_pos = response.raw.tell() if hasattr(response.raw, 'tell') else None
-                
+            if hasattr(response, "raw") and response.raw:
+                current_pos = response.raw.tell() if hasattr(response.raw, "tell") else None
+
                 magic_bytes = response.raw.read(2)
-                
-                if current_pos is not None and hasattr(response.raw, 'seek'):
+
+                if current_pos is not None and hasattr(response.raw, "seek"):
                     response.raw.seek(current_pos)
-                elif hasattr(response.raw, 'seek'):
+                elif hasattr(response.raw, "seek"):
                     response.raw.seek(0)
-                
-                return len(magic_bytes) >= 2 and magic_bytes[0] == 0x1f and magic_bytes[1] == 0x8b
-            
-            elif hasattr(response, 'content') and len(response.content) >= 2:
-                return response.content[0] == 0x1f and response.content[1] == 0x8b
-                
+
+                return len(magic_bytes) >= 2 and magic_bytes[0] == 0x1F and magic_bytes[1] == 0x8B
+
+            elif hasattr(response, "content") and len(response.content) >= 2:
+                return response.content[0] == 0x1F and response.content[1] == 0x8B
+
         except Exception as e:
             logger.debug(f"Failed to detect GZIP content: {e}")
-            
+
         return False
-    
+
     def _select_parser(self, response: requests.Response) -> Parser:
         """
         Enhanced parser selection with GZIP auto-detection.
-        
+
         This method extends the base implementation to:
         1. Check Content-Encoding header (existing behavior)
         2. Auto-detect GZIP content by magic bytes
         3. Wrap parser with GzipParser if GZIP is detected
         """
         selected_parser = super()._select_parser(response)
-        
-        if (not isinstance(selected_parser, GzipParser) and 
-            self._detect_gzip_content(response)):
-            
-            logger.info("Auto-detected GZIP content without Content-Encoding header, wrapping parser")
-            
+
+        if not isinstance(selected_parser, GzipParser) and self._detect_gzip_content(response):
+            logger.info(
+                "Auto-detected GZIP content without Content-Encoding header, wrapping parser"
+            )
+
             return GzipParser(inner_parser=selected_parser)
-        
+
         return selected_parser
-    
+
     def decode(self, response: requests.Response):
         """
         Enhanced decode method with better error handling.
-        
+
         Provides more informative error messages and graceful fallback
         when decompression or parsing fails.
         """
@@ -113,14 +113,14 @@ def decode(self, response: requests.Response):
                     f"Original error: {e}"
                 )
                 logger.error(error_msg)
-                
+
                 if self._auto_detect_gzip and self._detect_gzip_content(response):
                     logger.info("Attempting recovery with GZIP decompression")
                     gzip_parser = GzipParser(inner_parser=self.parser)
-                    
-                    if hasattr(response, 'raw') and hasattr(response.raw, 'seek'):
+
+                    if hasattr(response, "raw") and hasattr(response.raw, "seek"):
                         response.raw.seek(0)
-                    
+
                     try:
                         if self.is_stream_response():
                             response.raw.auto_close = False
@@ -131,7 +131,7 @@ def decode(self, response: requests.Response):
                         return
                     except Exception as recovery_error:
                         logger.error(f"GZIP recovery failed: {recovery_error}")
-                
+
                 raise RuntimeError(error_msg) from e
             else:
                 raise
@@ -143,22 +143,22 @@ def decode(self, response: requests.Response):
 def create_bing_ads_compatible_decoder() -> ImprovedCompositeRawDecoder:
     """
     Create a CompositeRawDecoder configured for Bing Ads bulk streams.
-    
+
     This decoder handles the campaign_labels stream and other bulk streams
     that use GZIP compression with CSV data.
     """
     csv_parser = CsvParser(encoding="utf-8-sig", set_values_to_none=[""])
-    
+
     gzip_parser = GzipParser(inner_parser=csv_parser)
-    
+
     decoder = ImprovedCompositeRawDecoder.by_headers(
         parsers=[({"Content-Encoding"}, {"gzip"}, gzip_parser)],
         stream_response=True,
         fallback_parser=csv_parser,
     )
-    
+
     decoder._auto_detect_gzip = True
-    
+
     return decoder
 
 

test_gzip_utf8_issue.py

@@ -22,40 +22,42 @@
 def test_gzip_utf8_decoding_issue():
     """
     Reproduce the issue where GZIP data is incorrectly treated as UTF-8.
-    
+
     This simulates the scenario in Bing Ads campaign_labels stream where:
     1. Response contains GZIP-compressed CSV data
     2. Parser selection fails to detect GZIP content-encoding
     3. Compressed data is passed to UTF-8 decoder
     4. UTF-8 decoder fails with byte 0x8b error
     """
     csv_data = "Account Id,Campaign,Client Id\n123,Test Campaign,456\n"
-    
-    compressed_data = gzip.compress(csv_data.encode('utf-8'))
-    
-    assert compressed_data[1] == 0x8b, f"Expected GZIP magic number 0x8b, got {hex(compressed_data[1])}"
-    
+
+    compressed_data = gzip.compress(csv_data.encode("utf-8"))
+
+    assert (
+        compressed_data[1] == 0x8B
+    ), f"Expected GZIP magic number 0x8b, got {hex(compressed_data[1])}"
+
     mock_response = Mock(spec=requests.Response)
     mock_response.content = compressed_data
     mock_response.raw = io.BytesIO(compressed_data)
     mock_response.headers = {}  # Missing Content-Encoding: gzip header
-    
+
     csv_parser = CsvParser(encoding="utf-8")
     decoder = CompositeRawDecoder(parser=csv_parser, stream_response=False)
-    
+
     try:
         list(decoder.decode(mock_response))
         assert False, "Expected UTF-8 decoding error but none occurred"
     except UnicodeDecodeError as e:
         assert "can't decode byte 0x8b" in str(e)
         assert "invalid start byte" in str(e)
         print(f"✓ Reproduced the issue: {e}")
-    
+
     gzip_parser = GzipParser(inner_parser=csv_parser)
     correct_decoder = CompositeRawDecoder(parser=gzip_parser, stream_response=False)
-    
+
     mock_response.raw = io.BytesIO(compressed_data)
-    
+
     records = list(correct_decoder.decode(mock_response))
     assert len(records) == 1
     assert records[0]["Account Id"] == "123"
@@ -69,22 +71,22 @@ def test_header_based_parser_selection():
     when Content-Encoding header is present.
     """
     csv_data = "Account Id,Campaign\n123,Test\n"
-    compressed_data = gzip.compress(csv_data.encode('utf-8'))
-    
+    compressed_data = gzip.compress(csv_data.encode("utf-8"))
+
     mock_response = Mock(spec=requests.Response)
     mock_response.content = compressed_data
     mock_response.raw = io.BytesIO(compressed_data)
     mock_response.headers = {"Content-Encoding": "gzip"}
-    
+
     gzip_parser = GzipParser(inner_parser=CsvParser(encoding="utf-8"))
     fallback_parser = CsvParser(encoding="utf-8")
-    
+
     decoder = CompositeRawDecoder.by_headers(
         parsers=[({"Content-Encoding"}, {"gzip"}, gzip_parser)],
         stream_response=False,
         fallback_parser=fallback_parser,
     )
-    
+
     records = list(decoder.decode(mock_response))
     assert len(records) == 1
     assert records[0]["Account Id"] == "123"