Github user maropu commented on a diff in the pull request: https://github.com/apache/spark/pull/22048#discussion_r213537424 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala --- @@ -294,23 +294,29 @@ class Dataset[T] private[sql]( // We set a minimum column width at '3' val minimumColWidth = 3 + // Regular expression matching full width characters + val fullWidthRegex = """[\u1100-\u115F\u2E80-\uA4CF\uAC00-\uD7A3\uF900-\uFAFF\uFE10-\uFE19\uFE30-\uFE6F\uFF00-\uFF60\uFFE0-\uFFE6]""".r + // The number of half width of a string + def stringHalfWidth = (str: String) => { + str.length + fullWidthRegex.findAllIn(str).size + } --- End diff -- better to move this method into `util.Utils` or something as a helper function?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org