ryukobayashi commented on code in PR #5624:
URL: https://github.com/apache/hive/pull/5624#discussion_r2178943575
##########
ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSubstr.java:
##########
@@ -96,53 +97,51 @@ private Text evaluateInternal(Text t, int pos, int len) {
return r;
}
- String s = t.toString();
- int[] index = makeIndex(pos, len, s.length());
- if (index == null) {
+ byte[] utf8String = t.toString().getBytes();
+ StringSubstrColStartLen.populateSubstrOffsets(utf8String, 0,
utf8String.length, adjustStartPos(pos), len, index);
+ if (index[0] == -1) {
return r;
}
- r.set(s.substring(index[0], index[1]));
+ r.set(new String(utf8String, index[0], index[1]));
return r;
}
- private int[] makeIndex(int pos, int len, int inputLen) {
- if ((Math.abs(pos) > inputLen)) {
- return null;
- }
-
- int start, end;
+ private Text evaluateInternal(Text t, int pos) {
+ r.clear();
- if (pos > 0) {
- start = pos - 1;
- } else if (pos < 0) {
- start = inputLen + pos;
- } else {
- start = 0;
+ byte[] utf8String = t.toString().getBytes();
Review Comment:
fixed.
##########
ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSubstr.java:
##########
@@ -96,53 +97,51 @@ private Text evaluateInternal(Text t, int pos, int len) {
return r;
}
- String s = t.toString();
- int[] index = makeIndex(pos, len, s.length());
- if (index == null) {
+ byte[] utf8String = t.toString().getBytes();
+ StringSubstrColStartLen.populateSubstrOffsets(utf8String, 0,
utf8String.length, adjustStartPos(pos), len, index);
+ if (index[0] == -1) {
return r;
}
- r.set(s.substring(index[0], index[1]));
+ r.set(new String(utf8String, index[0], index[1]));
return r;
}
- private int[] makeIndex(int pos, int len, int inputLen) {
- if ((Math.abs(pos) > inputLen)) {
- return null;
- }
-
- int start, end;
+ private Text evaluateInternal(Text t, int pos) {
+ r.clear();
- if (pos > 0) {
- start = pos - 1;
- } else if (pos < 0) {
- start = inputLen + pos;
- } else {
- start = 0;
+ byte[] utf8String = t.toString().getBytes();
+ int offset = StringSubstrColStart.getSubstrStartOffset(utf8String, 0,
utf8String.length, adjustStartPos(pos));
+ if (offset == -1) {
+ return r;
}
- if ((inputLen - start) < len) {
- end = inputLen;
- } else {
- end = start + len;
- }
- index[0] = start;
- index[1] = end;
- return index;
+ r.set(new String(utf8String, offset, utf8String.length - offset));
Review Comment:
fixed
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For additional commands, e-mail: gitbox-h...@hive.apache.org
