Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/6738#discussion_r32149611
--- Diff:
unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java ---
@@ -0,0 +1,198 @@
+/*
+ * 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.unsafe.types;
+
+import java.io.Serializable;
+import java.io.UnsupportedEncodingException;
+import java.util.Arrays;
+import javax.annotation.Nullable;
+
+/**
+ * A UTF-8 String for internal Spark use.
+ * <p>
+ * A String encoded in UTF-8 as an Array[Byte], which can be used for
comparison,
+ * search, see http://en.wikipedia.org/wiki/UTF-8 for details.
+ * <p>
+ * Note: This is not designed for general use cases, should not be used
outside SQL.
+ */
+public final class UTF8String implements Comparable<UTF8String>,
Serializable {
+
+ @Nullable
+ private byte[] bytes;
+
+ private int[] bytesOfCodePointInUTF8 = {2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
+ 4, 4, 4, 4, 4, 4, 4, 4,
+ 5, 5, 5, 5,
+ 6, 6, 6, 6};
+
+ public static UTF8String fromBytes(byte[] bytes) {
+ return (bytes != null) ? new UTF8String().set(bytes) : null;
+ }
+
+ public static UTF8String fromString(String str) {
+ return (str != null) ? new UTF8String().set(str) : null;
+ }
+
+ /**
+ * Updates the UTF8String with String.
+ */
+ public UTF8String set(final String str) {
+ bytes = str.getBytes();
+ return this;
+ }
+
+ /**
+ * Updates the UTF8String with byte[], which should be encoded in UTF-8.
+ */
+ public UTF8String set(final byte[] bytes) {
+ this.bytes = bytes;
+ return this;
+ }
+
+ /**
+ * Returns the number of bytes for a code point with the first byte as
`b`
+ * @param b The first byte of a code point
+ */
+ public int numBytes(final byte b) {
+ final int offset = (b & 0xFF) - 192;
+ return (offset >= 0) ? bytesOfCodePointInUTF8[offset] : 1;
+ }
+
+ /**
+ * Returns the number of code points in it.
+ *
+ * This is only used by Substring() when `start` is negative.
+ */
+ public int length() {
+ int len = 0;
+ for (int i = 0; i < bytes.length; i+= numBytes(bytes[i])) {
+ len += 1;
+ }
+ return len;
+ }
+
+ public byte[] getBytes() {
+ return bytes;
+ }
+
+ /**
+ * Returns a substring of this.
+ * @param start the position of first code point
+ * @param until the position after last code point
+ */
+ public UTF8String slice(final int start, final int until) {
+ if (until <= start || start >= bytes.length) {
+ return new UTF8String();
+ }
+
+ int i = 0;
+ int c = 0;
+ for (; i < bytes.length && c < start; i += numBytes(bytes[i])) {
+ c += 1;
+ }
+
+ int j = i;
+ for (; j < bytes.length && c < until; j += numBytes(bytes[i])) {
+ c += 1;
+ }
+
+ return UTF8String.fromBytes(Arrays.copyOfRange(bytes, i, j));
+ }
+
+ public boolean contains(final UTF8String substring) {
+ final byte[] b = substring.getBytes();
+ if (b.length == 0) {
+ return true;
+ }
+
+ for (int i = 0; i <= bytes.length - b.length; i++) {
+ // TODO: Avoid copying.
+ if (bytes[i] == b[0] && Arrays.equals(Arrays.copyOfRange(bytes, i, i
+ b.length), b)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ public boolean startsWith(final UTF8String prefix) {
+ final byte[] b = prefix.getBytes();
+ // TODO: Avoid copying.
+ return b.length > bytes.length &&
Arrays.equals(Arrays.copyOfRange(bytes, 0, b.length), b);
+ }
+
+ public boolean endsWith(final UTF8String suffix) {
+ final byte[] b = suffix.getBytes();
+ return b.length > bytes.length &&
+ Arrays.equals(Arrays.copyOfRange(bytes, bytes.length - b.length,
bytes.length), b);
+ }
+
+ public UTF8String toUpperCase() {
+ return UTF8String.fromString(toString().toUpperCase());
+ }
+
+ public UTF8String toLowerCase() {
+ return UTF8String.fromString(toString().toLowerCase());
+ }
+
+ @Override
+ public String toString() {
+ try {
+ return new String(bytes, "utf-8");
+ } catch (UnsupportedEncodingException e) {
+ e.printStackTrace();
+ return "unsupported encoding";
--- End diff --
Should we raise the exception?
---
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]
