uros-db commented on code in PR #46040:
URL: https://github.com/apache/spark/pull/46040#discussion_r1565412168


##########
sql/core/src/test/scala/org/apache/spark/sql/CollationStringExpressionsSuite.scala:
##########
@@ -163,6 +163,169 @@ class CollationStringExpressionsSuite
     })
   }
 
+  test("substring check output type on explicitly collated string") {
+    case class SubstringTestCase[R](args: Seq[String], collation: String, 
result: R)
+    val checks = Seq(
+      SubstringTestCase(Seq("Spark", "2"), "UTF8_BINARY", "park"),
+      SubstringTestCase(Seq("Spark", "2"), "UTF8_BINARY_LCASE", "park")
+    )
+    checks.foreach(ct => {
+      val query = s"SELECT substr(collate('${ct.args.head}', 
'${ct.collation}')," +
+        s" ${ct.args.tail.head})"
+      // Result & data type
+      checkAnswer(sql(query), Row(ct.result))
+      
assert(sql(query).schema.fields.head.dataType.sameType(StringType(ct.collation)))
+    })
+  }
+
+  test("left/right/substr on implicitly collated string returns proper value 
and type") {
+    case class QTestCase(query: String, collation: String, result: Row)
+    val longString = "In the course of human events"
+    val checks = Seq("utf8_binary_lcase", "utf8_binary", "unicode", 
"unicode_ci").flatMap(
+      c => Seq(
+        QTestCase(s"select left(left('$longString' collate " + c + ", 5), 1)", 
c, Row("I")),
+        QTestCase(s"select right(right('$longString' collate " + c + ", 5), 
1)", c, Row("s")),
+        QTestCase(
+          s"select substr(substr('$longString' collate " + c + ", 4), 2)", c,
+          Row("he course of human events"))
+      )
+    )
+
+    checks.foreach { check =>
+      // Result & data type
+      checkAnswer(sql(check.query), check.result)
+      
assert(sql(check.query).schema.fields.head.dataType.sameType(StringType(check.collation)))
+    }
+  }
+
+  test("left/right/substr on explicitly collated proper string returns proper 
value and type") {
+    case class QTestCase(query: String, collation: String, result: Row)
+    val checks = Seq("utf8_binary_lcase", "utf8_binary", "unicode", 
"unicode_ci").flatMap(
+      c => Seq(
+        QTestCase("select left('abc' collate " + c + ", 1)", c, Row("a")),
+        QTestCase("select right('def' collate " + c + ", 1)", c, Row("f")),
+        QTestCase("select substr('abc' collate " + c + ", 2)", c, Row("bc")),
+        QTestCase("select substr('example' collate " + c + ", 0, 2)", c, 
Row("ex")),
+        QTestCase("select substr('example' collate " + c + ", 1, 2)", c, 
Row("ex")),
+        QTestCase("select substr('example' collate " + c + ", 0, 7)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 1, 7)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 0, 100)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 1, 100)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 2, 2)", c, 
Row("xa")),
+        QTestCase("select substr('example' collate " + c + ", 1, 6)", c, 
Row("exampl")),
+        QTestCase("select substr('example' collate " + c + ", 2, 100)", c, 
Row("xample")),
+        QTestCase("select substr('example' collate " + c + ", 0, 0)", c, 
Row("")),
+        QTestCase("select substr('example' collate " + c + ", 100, 4)", c, 
Row("")),
+        QTestCase("select substr('example' collate " + c + ", 0, 100)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 1, 100)", c, 
Row("example")),
+        QTestCase("select substr('example' collate " + c + ", 2, 100)", c, 
Row("xample")),
+        QTestCase("select substr('example' collate " + c + ", -3, 2)", c, 
Row("pl")),
+        QTestCase("select substr('example' collate " + c + ", -100, 4)", c, 
Row("")),
+        QTestCase("select substr('example' collate " + c + ", -2147483648, 
6)", c, Row("")),
+        QTestCase("select substr(' a世a ' collate " + c + ", 2, 3)", c, 
Row("a世a")), // scalastyle:ignore
+        QTestCase("select left(' a世a ' collate " + c + ", 3)", c, Row(" a世")), 
// scalastyle:ignore
+        QTestCase("select right(' a世a ' collate " + c + ", 3)", c, Row("世a 
")), // scalastyle:ignore
+        QTestCase("select substr('AaAaAaAa000000' collate " + c + ", 2, 3)", 
c, Row("aAa")),
+        QTestCase("select left('AaAaAaAa000000' collate " + c + ", 3)", c, 
Row("AaA")),
+        QTestCase("select right('AaAaAaAa000000' collate " + c + ", 3)", c, 
Row("000")),
+        QTestCase("select substr('' collate " + c + ", 1, 1)", c, Row("")),
+        QTestCase("select left('' collate " + c + ", 1)", c, Row("")),
+        QTestCase("select right('' collate " + c + ", 1)", c, Row("")),
+        QTestCase("select left('ghi' collate " + c + ", 1)", c, Row("g"))

Review Comment:
   I don't think we need this many test cases here, if you didn't modify the 
way Substring/Left/Right expressions behave when given collated strings (i.e. 
you didn't introduce any collation awareness to nullSafeEval/doCodeGen), then 
there should be no need to go this deep - a couple of test cases should do the 
trick just fine



-- 
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: reviews-unsubscr...@spark.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to