Github user xuejianbest commented on a diff in the pull request:
https://github.com/apache/spark/pull/22048#discussion_r213537923
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ---
@@ -294,23 +294,25 @@ 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
if (!vertical) {
// Initialise the width of each column to a minimum value
val colWidths = Array.fill(numCols)(minimumColWidth)
// Compute the width of each column
for (row <- rows) {
for ((cell, i) <- row.zipWithIndex) {
- colWidths(i) = math.max(colWidths(i), cell.length)
+ colWidths(i) = math.max(colWidths(i), cell.length +
fullWidthRegex.findAllIn(cell).size)
--- End diff --
I committed a new version. See if this is appropriate please ?
@srowen
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
