Polish logging around git and archives to reduce noise (#4034)

* Polish logging around archives in git to reduce noise

* Log notable skipping at level 2

* Skipping based on extension happens a lot; bump the log level down to 3

* Bump empty reader log level back down to 5

* Put context check back where it was

* Revert "Put context check back where it was"

This reverts commit da710cc.

Author: camgunz

pkg/handlers/archive.go

@@ -174,22 +174,21 @@ func (h *archiveHandler) openArchive(
 // to handle nested archives or to continue processing based on the file's content and depth in the archive structure.
 func (h *archiveHandler) extractorHandler(dataOrErrChan chan DataOrErr) func(context.Context, archives.FileInfo) error {
 	return func(ctx context.Context, file archives.FileInfo) error {
+		if common.IsDone(ctx) {
+			return ctx.Err()
+		}
+
 		lCtx := logContext.WithValues(
 			logContext.AddLogger(ctx),
 			"filename", file.Name(),
 			"size", file.Size(),
 		)
-		lCtx.Logger().V(3).Info("Handling extracted file.")
 
 		if file.IsDir() || file.LinkTarget != "" {
-			lCtx.Logger().V(3).Info("skipping directory or symlink")
+			lCtx.Logger().V(4).Info("skipping directory or symlink")
 			return nil
 		}
 
-		if common.IsDone(ctx) {
-			return ctx.Err()
-		}
-
 		depth := 0
 		if ctxDepth, ok := ctx.Value(depthKey).(int); ok {
 			depth = ctxDepth
@@ -243,7 +242,7 @@ func (h *archiveHandler) extractorHandler(dataOrErrChan chan DataOrErr) func(con
 		h.metrics.incFilesProcessed()
 		h.metrics.observeFileSize(fileSize)
 
-		lCtx.Logger().V(4).Info("Processed file successfully", "filename", file.Name(), "size", file.Size())
+		lCtx.Logger().V(4).Info("Opened file successfully", "filename", file.Name(), "size", file.Size())
 		return h.openArchive(lCtx, depth, rdr, dataOrErrChan)
 	}
 }

pkg/sources/git/git.go

@@ -1296,9 +1296,11 @@ func HandleBinary(
 			)
 		}
 
-		ctx.Logger().V(3).Info(
-			"HandleFile did not consume all stdout data; excess discarded",
-			"bytes_discarded", n)
+		if n > 0 {
+			ctx.Logger().V(3).Info(
+				"HandleFile did not consume all stdout data; excess discarded",
+				"bytes_discarded", n)
+		}
 
 		// Wait for the command to finish and handle any errors.
 		waitErr := cmd.Wait()