[
https://issues.apache.org/jira/browse/PHOENIX-4237?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16203799#comment-16203799
]
ASF GitHub Bot commented on PHOENIX-4237:
-----------------------------------------
Github user JamesRTaylor commented on a diff in the pull request:
https://github.com/apache/phoenix/pull/275#discussion_r144600094
--- Diff:
phoenix-core/src/main/java/org/apache/phoenix/expression/function/CollationKeyFunction.java
---
@@ -0,0 +1,233 @@
+package org.apache.phoenix.expression.function;
+
+import java.sql.SQLException;
+import java.text.Collator;
+import java.util.Arrays;
+import java.util.List;
+import java.util.Locale;
+
+import org.apache.commons.lang.BooleanUtils;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
+import org.apache.phoenix.expression.Expression;
+import org.apache.phoenix.parse.FunctionParseNode;
+import org.apache.phoenix.schema.tuple.Tuple;
+import org.apache.phoenix.schema.types.PBoolean;
+import org.apache.phoenix.schema.types.PDataType;
+import org.apache.phoenix.schema.types.PInteger;
+import org.apache.phoenix.schema.types.PIntegerArray;
+import org.apache.phoenix.schema.types.PUnsignedIntArray;
+import org.apache.phoenix.schema.types.PVarbinary;
+import org.apache.phoenix.schema.types.PVarchar;
+import org.apache.phoenix.schema.types.PhoenixArray;
+
+import com.force.db.i18n.LinguisticSort;
+import com.force.i18n.LocaleUtils;
+
+import com.ibm.icu.impl.jdkadapter.CollatorICU;
+import com.ibm.icu.util.ULocale;
+
+/**
+ * A Phoenix Function that calculates a collation key for an input string
based
+ * on a caller-provided locale and collator strength and decomposition
settings.
+ *
+ * It uses the open-source grammaticus and i18n packages to obtain the
collators
+ * it needs.
+ *
+ * @author snakhoda
+ *
+ */
[email protected](name = CollationKeyFunction.NAME, args
= {
+ // input string
+ @FunctionParseNode.Argument(allowedTypes = { PVarchar.class }),
+ // ISO Code for Locale
+ @FunctionParseNode.Argument(allowedTypes = { PVarchar.class },
isConstant = true),
+ // whether to use special upper case collator
+ @FunctionParseNode.Argument(allowedTypes = { PBoolean.class },
defaultValue = "false", isConstant = true),
+ // collator strength
+ @FunctionParseNode.Argument(allowedTypes = { PInteger.class },
defaultValue = "null", isConstant = true),
+ // collator decomposition
+ @FunctionParseNode.Argument(allowedTypes = { PInteger.class },
defaultValue = "null", isConstant = true) })
+public class CollationKeyFunction extends ScalarFunction {
+
+ private static final Log LOG =
LogFactory.getLog(CollationKeyFunction.class);
+
+ public static final String NAME = "COLLKEY";
+
+ public CollationKeyFunction() {
+ }
+
+ public CollationKeyFunction(List<Expression> children) throws
SQLException {
+ super(children);
+ }
+
+ @Override
+ public boolean evaluate(Tuple tuple, ImmutableBytesWritable ptr) {
+ try {
+ String inputValue = getInputValue(tuple, ptr);
+ String localeISOCode = getLocaleISOCode(tuple, ptr);
+ Boolean useSpecialUpperCaseCollator =
getUseSpecialUpperCaseCollator(tuple, ptr);
+ Integer collatorStrength = getCollatorStrength(tuple,
ptr);
+ Integer collatorDecomposition =
getCollatorDecomposition(tuple, ptr);
+
+ Locale locale =
LocaleUtils.get().getLocaleByIsoCode(localeISOCode);
+
+ if(LOG.isDebugEnabled()) {
+ LOG.debug(String.format("Locale: " +
locale.toLanguageTag()));
+ }
+
+ LinguisticSort linguisticSort =
LinguisticSort.get(locale);
+
+ Collator collator =
BooleanUtils.isTrue(useSpecialUpperCaseCollator)
+ ?
linguisticSort.getUpperCaseCollator(false) : linguisticSort.getCollator();
+
+ if (collatorStrength != null) {
+ collator.setStrength(collatorStrength);
+ }
+
+ if (collatorDecomposition != null) {
+
collator.setDecomposition(collatorDecomposition);
+ }
+
+ if(LOG.isDebugEnabled()) {
+ LOG.debug(String.format("Collator: [strength:
%d, decomposition: %d], Special-Upper-Case: %s",
+ collator.getStrength(),
collator.getDecomposition(), BooleanUtils.isTrue(useSpecialUpperCaseCollator)));
+ }
+
+ byte[] collationKeyByteArray =
collator.getCollationKey(inputValue).toByteArray();
+
+ if(LOG.isDebugEnabled()) {
+ LOG.debug("Collation key bytes:" +
Arrays.toString(collationKeyByteArray));
+ }
+
+ // byte is signed in Java, but we need unsigned values
for comparison
+ //
https://www.programcreek.com/java-api-examples/index.php?api=java.text.CollationKey
+ // Byte.toUnsignedInt will convert a byte value between
[-128,127] to an int value
+ // between [0,255]
--- End diff --
> doing a Java comparison on them with regular operators (which is
presumably what Phoenix does) produces incorrect results
That's not what Phoenix does. That's what I tried to explain in my previous
comment. In your unit tests, the best way to confirm this is through an
end-to-end integration test that uses an ORDER BY COLLKEY(my_varchar_col):
* Create a simple table CREATE TABLE t (k INTEGER PRIMARY KEY, v VARCHAR)
* Populate the table with some multi-byte string values:
UPSERT INTO t VALUES(1,'ണഫɰɸ')
UPSERT INTO t VALUES(2,'ɚɦ')
* Execute an ORDER BY on the table: SELECT * FROM t ORDER BY COLLKEY(v)
* Confirm that the rows are ordered as expected by a linguistic sort
The above test is a must-have. We can also have lower level unit tests that
don't need to run as an integration test to test the sorting. You'd need to
manually create an OrderedResultIterator. See OrderedResultIteratorTest as an
example.
> Allow sorting on (Java) collation keys for non-English locales
> --------------------------------------------------------------
>
> Key: PHOENIX-4237
> URL: https://issues.apache.org/jira/browse/PHOENIX-4237
> Project: Phoenix
> Issue Type: Improvement
> Reporter: Shehzaad Nakhoda
> Fix For: 4.12.0
>
>
> Strings stored via Phoenix can be composed from a subset of the entire set of
> Unicode characters. The natural sort order for strings for different
> languages often differs from the order dictated by the binary representation
> of the characters of these strings. Java provides the idea of a Collator
> which given an input string and a (language) locale can generate a Collation
> Key which can then be used to compare strings in that natural order.
> Salesforce has recently open-sourced grammaticus. IBM has open-sourced ICU4J
> some time ago. These technologies can be combined to provide a robust new
> Phoenix function that can be used in an ORDER BY clause to sort strings
> according to the user's locale.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
