Github user sarutak commented on a diff in the pull request:
https://github.com/apache/spark/pull/12199#discussion_r58697136
--- Diff:
sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/parser/ParseUtils.java
---
@@ -1,135 +0,0 @@
-/**
- * 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.parser;
-
-import java.nio.charset.StandardCharsets;
-
-/**
- * A couple of utility methods that help with parsing ASTs.
- *
- * The 'unescapeSQLString' method in this class was take from the
SemanticAnalyzer in Hive:
- * ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
- */
-public final class ParseUtils {
- private ParseUtils() {
- super();
- }
-
- private static final int[] multiplier = new int[] {1000, 100, 10, 1};
-
- @SuppressWarnings("nls")
- public static String unescapeSQLString(String b) {
- Character enclosure = null;
-
- // Some of the strings can be passed in as unicode. For example, the
- // delimiter can be passed in as \002 - So, we first check if the
- // string is a unicode number, else go back to the old behavior
- StringBuilder sb = new StringBuilder(b.length());
- for (int i = 0; i < b.length(); i++) {
-
- char currentChar = b.charAt(i);
- if (enclosure == null) {
- if (currentChar == '\'' || b.charAt(i) == '\"') {
- enclosure = currentChar;
- }
- // ignore all other chars outside the enclosure
- continue;
- }
-
- if (enclosure.equals(currentChar)) {
- enclosure = null;
- continue;
- }
-
- if (currentChar == '\\' && (i + 6 < b.length()) && b.charAt(i + 1)
== 'u') {
- int code = 0;
- int base = i + 2;
- for (int j = 0; j < 4; j++) {
- int digit = Character.digit(b.charAt(j + base), 16);
- code += digit * multiplier[j];
--- End diff --
Yes, I'm thinking about reporting this issue.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
