LuciferYang commented on code in PR #46894:
URL: https://github.com/apache/spark/pull/46894#discussion_r1634164613
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogUtils.scala:
##########
@@ -60,28 +60,42 @@ object ExternalCatalogUtils {
Array(' ', '<', '>', '|').foreach(bitSet.set(_))
}
- bitSet
+ (bitSet, bitSet.size)
}
- def needsEscaping(c: Char): Boolean = {
- c < charToEscape.size() && charToEscape.get(c)
+ private final val HEX_CHARS = "0123456789ABCDEF".toCharArray
+
+ @inline final def needsEscaping(c: Char): Boolean = {
+ c < sizeOfCharToEscape && charToEscape.get(c)
}
def escapePathName(path: String): String = {
- val builder = new StringBuilder()
- path.foreach { c =>
- if (needsEscaping(c)) {
- builder.append('%')
- builder.append(f"${c.asInstanceOf[Int]}%02X")
- } else {
- builder.append(c)
+ if (path == null || path.isEmpty) {
+ return path
+ }
+ val length = path.length
+ var firstIndex = 0
+ while (firstIndex < length && !needsEscaping(path.charAt(firstIndex))) {
+ firstIndex += 1
+ }
+ if (firstIndex == length) {
+ path
+ } else {
+ val sb = new java.lang.StringBuilder(length + 16)
+ sb.append(path, 0, firstIndex)
Review Comment:
nit: should this `append` only be executed when `firstIndex != 0`? Although
`sb.append(path, 0, 0)` won't cause an error, it could still result in some
unnecessary invocations.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogUtils.scala:
##########
@@ -60,28 +60,42 @@ object ExternalCatalogUtils {
Array(' ', '<', '>', '|').foreach(bitSet.set(_))
}
- bitSet
+ (bitSet, bitSet.size)
}
- def needsEscaping(c: Char): Boolean = {
- c < charToEscape.size() && charToEscape.get(c)
+ private final val HEX_CHARS = "0123456789ABCDEF".toCharArray
+
+ @inline final def needsEscaping(c: Char): Boolean = {
+ c < sizeOfCharToEscape && charToEscape.get(c)
}
def escapePathName(path: String): String = {
- val builder = new StringBuilder()
- path.foreach { c =>
- if (needsEscaping(c)) {
- builder.append('%')
- builder.append(f"${c.asInstanceOf[Int]}%02X")
- } else {
- builder.append(c)
+ if (path == null || path.isEmpty) {
Review Comment:
Should we directly return if `path` is a blank string? For example, `"
"`
maybe we should use `lang3.StringUtils.isBlank(path)`
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogUtilsSuite.scala:
##########
@@ -0,0 +1,37 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.catalyst.catalog
+
+import org.apache.spark.SparkFunSuite
+import
org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils.escapePathName
+
+class ExternalCatalogUtilsSuite extends SparkFunSuite {
+
+ test("SPARK-48551: escapePathName") {
+
ExternalCatalogUtils.charToEscape.stream().toArray.map(_.asInstanceOf[Char]).foreach
{ c =>
+ // Check parity with old conversion technique:
+ assert(escapePathName(c.toString) === "%" + f"$c%02X",
+ s"wrong escaping for $c")
+ }
+ assert(escapePathName("a b") === "a b")
+ assert(escapePathName("a:b") === "a%3Ab")
+ assert(escapePathName("a%b") === "a%25b")
+ assert(escapePathName("a,b") === "a,b")
+ assert(escapePathName("a/b") === "a%2Fb")
Review Comment:
I think we should add some more cases like:
1. blank string
2. the first character needs to be escaped, like ":ab"
3. only the last character needs to be escaped, like `ab%`
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/EscapePathBenchmark.scala:
##########
@@ -0,0 +1,62 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.sql.catalyst
+
+import org.apache.spark.benchmark.{Benchmark, BenchmarkBase}
+import org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils
+
+object EscapePathBenchmark extends BenchmarkBase {
Review Comment:
Like other Benchmarks, we should add a documentation related to `To run this
benchmark:`
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
