Add "log4j" input format

Only works for the most common "bracketed style" format:

2024-01-19 15:04:23,456 [main] INFO [com.example.Class] - Message

klp.py

@@ -127,7 +127,10 @@
         "timestamp_key": "off",
         "levels": {
             "trace": "cyan",
+            "finest": "cyan",
             "debug": "bright_cyan",
+            "finer": "bright_cyan",
+            "config": "bright_cyan",
             "info": "bright_green",
             "notice": "bright_green",
             "warn": "bright_yellow",
@@ -141,6 +144,7 @@
             "critical": "bright_red",
             "emerg": "bright_red",
             "emergency": "bright_red",
+            "severe": "bright_red",
         },
         "context_prefix": {
             "before": "blue",
@@ -342,6 +346,7 @@ def build_globals_dict(modules: List[Any]) -> Dict[str, Any]:
         parse_jsonl,
         parse_clf,
         parse_combined,
+        parse_log4j,
         parse_unix,
         parse_line,
         parse_data,
@@ -771,6 +776,7 @@ def identity(x):
         "jsonl": parse_jsonl,
         "clf": parse_clf,
         "combined": parse_combined,
+        "log4j": parse_log4j,
         "unix": parse_unix,
         "line": parse_line,
         "ts1m": parse_ts1m,
@@ -1150,6 +1156,29 @@ def parse_combined(line):
         return {}
 
 
+def parse_log4j(line: str) -> dict:
+    """Parse a Log4j formatted line into dictionary with string values.
+
+    Examples:
+    2024-01-19 15:04:23,456 [main] SEVERE [com.example.CustomerService] - Failed to connect
+    19-Jan-2024 15:04:23.456 [main] ERROR [com.example] - Message
+    """
+    pattern = r"""
+        ^\s*(?P<timestamp>[^\[]+?)\s+    # Timestamp (any non-bracket chars until whitespace)
+        \[(?P<thread>[^\]]+)\]\s+        # Thread name in brackets
+        (?P<level>[\w_]+)\s+             # Log level (word chars and underscore)
+        \[(?P<logger>[^\]]+)\]\s+-\s+    # Logger name in brackets
+        (?P<message>.+?)                  # Message (non-greedy)
+        \s*$                             # Optional trailing whitespace
+    """
+
+    match = re.match(pattern, line.strip(), re.VERBOSE)
+    if not match:
+        return {}
+
+    return {k: v.strip() for k, v in match.groupdict().items()}
+
+
 def parse_unix(line: str) -> Dict[str, str]:
     """
     Parse a line of log data in typical Unix server format into structured components.
@@ -3730,6 +3759,7 @@ def parse_args():
             "table",
             "clf",
             "combined",
+            "log4j",
             "unix",
             "line",
             "data",

tests/test_parsers.py

@@ -3,6 +3,7 @@
     parse_jsonl,
     parse_clf,
     parse_combined,
+    parse_log4j,
     parse_unix,
 )
 
@@ -77,6 +78,52 @@ def test_parse_combined():
     assert parse_combined("Invalid line") == {}
 
 
+def test_parse_log4j():
+    """Test Log4j format parsing with various cases."""
+    # Standard line
+    line = "2024-01-19 15:04:23,456 [main] INFO [com.example.Service] - Started successfully"
+    result = parse_log4j(line)
+    assert result["timestamp"] == "2024-01-19 15:04:23,456"
+    assert result["thread"] == "main"
+    assert result["level"] == "INFO"
+    assert result["logger"] == "com.example.Service"
+    assert result["message"] == "Started successfully"
+
+    # Different timestamp format
+    line = "19-Jan-2024 15:04:23.456 [main] ERROR [com.example] - Failed to start"
+    result = parse_log4j(line)
+    assert result["timestamp"] == "19-Jan-2024 15:04:23.456"
+    assert result["level"] == "ERROR"
+
+    # Complex thread name
+    line = "2024-01-19 15:04:23,456 [http-nio-8080-exec-1] DEBUG [com.example] - Processing request"
+    result = parse_log4j(line)
+    assert result["thread"] == "http-nio-8080-exec-1"
+    assert result["level"] == "DEBUG"
+
+    # Complex logger name with version
+    line = (
+        "2024-01-19 15:04:23,456 [main] INFO [com.example.v2.api.Service] - API ready"
+    )
+    result = parse_log4j(line)
+    assert result["logger"] == "com.example.v2.api.Service"
+
+    # Message with special characters
+    line = '2024-01-19 15:04:23,456 [main] WARN [com.example] - User "john.doe" failed auth: error=Invalid credentials'
+    result = parse_log4j(line)
+    assert result["message"] == 'User "john.doe" failed auth: error=Invalid credentials'
+
+    # With extra whitespace
+    line = (
+        "  2024-01-19 15:04:23,456  [main]   INFO   [com.example]  -   Extra spaces  "
+    )
+    result = parse_log4j(line)
+    assert result["message"] == "Extra spaces"
+
+    # Invalid format
+    assert parse_log4j("Invalid line") == {}
+
+
 def test_parse_unix():
     """Test Unix syslog format parsing."""
     # Standard format with PID