Github user tarekauel commented on a diff in the pull request:
https://github.com/apache/spark/pull/7353#discussion_r34761324
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala
---
@@ -180,4 +182,202 @@ object DateTimeUtils {
val nanos = (us % MICROS_PER_SECOND) * 1000L
(day.toInt, secondsInDay * NANOS_PER_SECOND + nanos)
}
+
+ /**
+ * Parses a given UTF8 date string to the corresponding a corresponding
[[Long]] value.
+ * The return type is [[Option]] in order to distinguish between 0L and
null. The following
+ * formats are allowed:
+ *
+ * `yyyy`
+ * `yyyy-[m]m`
+ * `yyyy-[m]m-[d]d`
+ * `yyyy-[m]m-[d]d `
+ * `yyyy-[m]m-[d]d [h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]`
+ * `yyyy-[m]m-[d]d [h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]Z`
+ * `yyyy-[m]m-[d]d [h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]-[h]h:[m]m`
+ * `yyyy-[m]m-[d]d [h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]+[h]h:[m]m`
+ * `yyyy-[m]m-[d]dT[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]`
+ * `yyyy-[m]m-[d]dT[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]Z`
+ * `yyyy-[m]m-[d]dT[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]-[h]h:[m]m`
+ * `yyyy-[m]m-[d]dT[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]+[h]h:[m]m`
+ * `[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]`
+ * `[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]Z`
+ * `[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]-[h]h:[m]m`
+ * `[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]+[h]h:[m]m`
+ * `T[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]`
+ * `T[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]Z`
+ * `T[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]-[h]h:[m]m`
+ * `T[h]h:[m]m:[s]s.[ms][ms][ms][us][us][us]+[h]h:[m]m`
+ */
+ def stringToTimestamp(s: UTF8String): Option[Long] = {
+ if (s == null) {
+ return None
+ }
+ var timeZone: Option[Byte] = None
+ val segments: Array[Int] = Array[Int](1, 1, 1, 0, 0, 0, 0, 0, 0)
+ var i = 0
+ var currentSegmentValue = 0
+ val bytes = s.getBytes
+ var j = 0
+ var digitsMilli = 0
+ var justTime = false
+ while (j < bytes.length) {
+ val b = bytes(j)
+ val parsedValue = b - '0'.toByte
+ if (parsedValue < 0 || parsedValue > 9) {
+ if (j == 0 && b == 'T') {
+ justTime = true
+ i += 3
+ } else if (i < 2) {
+ if (b == '-') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ } else if (i == 0 && b == ':') {
+ justTime = true
+ segments(3) = currentSegmentValue
+ currentSegmentValue = 0
+ i = 4
+ } else {
+ return None
+ }
+ } else if (i == 2) {
+ if (b == ' ' || b == 'T') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ } else {
+ return None
+ }
+ } else if (i == 3 || i == 4) {
+ if (b == ':') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ } else {
+ return None
+ }
+ } else if (i == 5 || i == 6) {
+ if (b == 'Z') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ timeZone = Some(43)
+ } else if (b == '-' || b == '+') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ timeZone = Some(b)
+ } else if (b == '.' && i == 5) {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ } else {
+ return None
+ }
+ if (i == 6 && b != '.') {
+ i += 1
+ }
+ } else {
+ if (b == ':' || b == ' ') {
+ segments(i) = currentSegmentValue
+ currentSegmentValue = 0
+ i += 1
+ } else {
+ return None
+ }
+ }
+ } else {
+ if (i == 6) {
+ digitsMilli += 1
+ }
+ currentSegmentValue = currentSegmentValue * 10 + parsedValue
+ }
+ j += 1
+ }
+
+ segments(i) = currentSegmentValue
+
+ while (digitsMilli < 6) {
+ segments(6) *= 10
+ digitsMilli += 1
+ }
+
+ if (!justTime && (segments(0) < 1000 || segments(0) > 9999 ||
segments(1) < 1 ||
+ segments(1) > 12 || segments(2) < 1 || segments(2) > 31)) {
+ return None
+ }
+
+ if (segments(3) < 0 || segments(3) > 23 || segments(4) < 0 ||
segments(4) > 59 ||
+ segments(5) < 0 || segments(5) > 59 || segments(6) < 0 ||
segments(6) > 999999 ||
+ segments(7) < 0 || segments(7) > 23 || segments(8) < 0 ||
segments(8) > 59) {
+ return None
+ }
+
+ val c = if (timeZone.isEmpty) {
+ Calendar.getInstance()
+ } else {
+ Calendar.getInstance(
+
TimeZone.getTimeZone(f"GMT${timeZone.get.toChar}${segments(7)}%02d:${segments(8)}%02d"))
+ }
+
+ if (justTime) {
+ c.set(Calendar.HOUR, segments(3))
+ c.set(Calendar.MINUTE, segments(4))
+ c.set(Calendar.SECOND, segments(5))
+ } else {
+ c.set(segments(0), segments(1) - 1, segments(2), segments(3),
segments(4), segments(5))
+ }
+
+ c.set(Calendar.MILLISECOND, segments(6) / 1000)
+ Some(c.getTimeInMillis * 1000 + segments(6) % 1000)
--- End diff --
It has to be: `Some(c.getTimeInMillis / 1000 * 1000000 + segments(6))`,
else we keep the "default" millis.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
