Add is_tor plumbing from collector->aggregator->frontend/cli

cmd/collector/parser.go

@@ -6,22 +6,25 @@ import (
 	"strings"
 )
 
-// LogRecord holds the four dimensions extracted from a single nginx log line.
+// LogRecord holds the dimensions extracted from a single nginx log line.
 type LogRecord struct {
 	Website      string
 	ClientPrefix string
 	URI          string
 	Status       string
+	IsTor        bool
 }
 
 // ParseLine parses a tab-separated logtail log line:
 //
-//	$host \t $remote_addr \t $msec \t $request_method \t $request_uri \t $status \t $body_bytes_sent \t $request_time
+//	$host \t $remote_addr \t $msec \t $request_method \t $request_uri \t $status \t $body_bytes_sent \t $request_time \t $is_tor
 //
+// The is_tor field (0 or 1) is optional for backward compatibility with
+// older log files that omit it; it defaults to false when absent.
 // Returns false for lines with fewer than 8 fields.
 func ParseLine(line string, v4bits, v6bits int) (LogRecord, bool) {
-	// SplitN caps allocations; we need exactly 8 fields.
-	fields := strings.SplitN(line, "\t", 8)
+	// SplitN caps allocations; we need up to 9 fields.
+	fields := strings.SplitN(line, "\t", 9)
 	if len(fields) < 8 {
 		return LogRecord{}, false
 	}
@@ -36,11 +39,14 @@ func ParseLine(line string, v4bits, v6bits int) (LogRecord, bool) {
 		return LogRecord{}, false
 	}
 
+	isTor := len(fields) == 9 && fields[8] == "1"
+
 	return LogRecord{
 		Website:      fields[0],
 		ClientPrefix: prefix,
 		URI:          uri,
 		Status:       fields[5],
+		IsTor:        isTor,
 	}, true
 }