Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Cherry-pick stragglers for ksqlDB 0.10.0 docs (DOCS-4744) #5687

Merged
merged 3 commits into from
Jun 25, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 48 additions & 0 deletions docs/developer-guide/ksqldb-reference/scalar-functions.md
Original file line number Diff line number Diff line change
Expand Up @@ -400,8 +400,39 @@ SLICE(col1, from, to)
Slices a list based on the supplied indices. The indices start at 1 and
include both endpoints.

### `ARRAY_JOIN`

```sql
ARRAY_JOIN(col1, delimiter)
```

Creates a flat string representation of all the elements contained in the given array.
The elements in the resulting string are separated by the chosen `delimiter`,
which is an optional parameter that falls back to a comma `,`. The current implementation only
allows for array elements of primitive ksqlDB types.

## Strings

### `CHR`

```sql
CHR(decimal_code | utf_string)
```

Returns a single-character string representing the Unicode code-point described by the input. The input parameter can be either a decimal character code or a string representation of a UTF code.

Returns NULL if the input is NULL or does not represent a valid code-point.

Commonly used to insert control characters such as `Tab` (9), `Line Feed` (10), or `Carriage Return` (13) into strings.

Examples:
```sql
CHR(75) => 'K'
CHR('\u004b') => 'K'
CHR(22909) => '好'
CHR('\u597d') => '好'
```

### `CONCAT`

```sql
Expand Down Expand Up @@ -721,6 +752,23 @@ If the delimiter is found at the beginning or end
of the string, or there are contiguous delimiters,
then an empty space is added to the array.

### `SPLIT_TO_MAP`

```sql
SPLIT_TO_MAP(input, entryDelimiter, kvDelimiter)
```

Splits a string into key-value pairs and creates a map from them. The
`entryDelimiter` splits the string into key-value pairs which are then split by `kvDelimiter`. If the same key is present multiple times in the input, the latest value for that key is returned.

Returns NULL if the input text is NULL.
Returns NULL if either of the delimiters is NULL or an empty string.

Example:
```sql
SPLIT_TO_MAP('apple':='green'/'cherry':='red', '/', ':=') => { 'apple':'green', 'cherry':'red'}
```

### `SUBSTRING`

```sql
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,84 @@
/*
* Copyright 2020 Confluent Inc.
*
* Licensed under the Confluent Community License (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.confluent.io/confluent-community-license
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OF ANY KIND, either express or implied. See the License for the
* specific language governing permissions and limitations under the License.
*/

package io.confluent.ksql.function.udf.array;

import com.google.common.collect.ImmutableSet;
import io.confluent.ksql.function.KsqlFunctionException;
import io.confluent.ksql.function.udf.Udf;
import io.confluent.ksql.function.udf.UdfDescription;
import io.confluent.ksql.function.udf.UdfParameter;
import io.confluent.ksql.util.KsqlConstants;
import java.math.BigDecimal;
import java.util.List;
import java.util.Set;
import java.util.StringJoiner;

@SuppressWarnings("MethodMayBeStatic") // UDF methods can not be static.
@UdfDescription(
name = "ARRAY_JOIN",
description = "joins the array elements into a flat string representation",
author = KsqlConstants.CONFLUENT_AUTHOR
)
public class ArrayJoin {

private static final String DEFAULT_DELIMITER = ",";
private static final Set<Class> KSQL_PRIMITIVES = ImmutableSet.of(
Boolean.class,Integer.class,Long.class,Double.class,BigDecimal.class,String.class
);

@Udf
public <T> String join(
@UdfParameter(description = "the array to join using the default delimiter '"
+ DEFAULT_DELIMITER + "'") final List<T> array
) {
return join(array, DEFAULT_DELIMITER);
}

@Udf
public <T> String join(
@UdfParameter(description = "the array to join using the specified delimiter")
final List<T> array,
@UdfParameter(description = "the string to be used as element delimiter")
final String delimiter
) {

if (array == null) {
return null;
}

final StringJoiner sj = new StringJoiner(delimiter == null ? "" : delimiter);
array.forEach(e -> processElement(e, sj));
return sj.toString();

}

@SuppressWarnings("unchecked")
private static <T> void processElement(final T element, final StringJoiner joiner) {

if (element == null || KSQL_PRIMITIVES.contains(element.getClass())) {
handlePrimitiveType(element, joiner);
} else {
throw new KsqlFunctionException("error: hit element of type "
+ element.getClass().getTypeName() + " which is currently not supported");
}

}

private static void handlePrimitiveType(final Object element, final StringJoiner joiner) {
joiner.add(element != null ? element.toString() : null);
}

}
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
/*
* Copyright 2020 Confluent Inc.
*
* Licensed under the Confluent Community License (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.confluent.io/confluent-community-license
*
* Unless required by applicable law or agreed to in writing, software distributed under the License
* is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and limitations under the
* License.
*/

package io.confluent.ksql.function.udf.string;

import io.confluent.ksql.function.udf.Udf;
import io.confluent.ksql.function.udf.UdfDescription;
import io.confluent.ksql.function.udf.UdfParameter;
import org.apache.commons.lang3.StringEscapeUtils;

@UdfDescription(
name = "Chr",
description = "Returns a single-character string corresponding to the input character code.")
public class Chr {

@Udf
public String chr(@UdfParameter(
description = "Decimal codepoint") final Integer decimalCode) {
if (decimalCode == null) {
return null;
}
if (!Character.isValidCodePoint(decimalCode)) {
return null;
}
final char[] resultChars = Character.toChars(decimalCode.intValue());
return String.valueOf(resultChars);
}

@Udf
public String chr(@UdfParameter(
description = "UTF16 code for the desired character e.g. '\\u004b'") final String utf16Code) {
if (utf16Code == null || utf16Code.length() < 6 || !utf16Code.startsWith("\\u")) {
return null;
}
return StringEscapeUtils.unescapeJava(utf16Code);
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
/*
* Copyright 2020 Confluent Inc.
*
* Licensed under the Confluent Community License (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.confluent.io/confluent-community-license
*
* Unless required by applicable law or agreed to in writing, software distributed under the License
* is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and limitations under the
* License.
*/

package io.confluent.ksql.function.udf.string;

import com.google.common.base.Splitter;
import io.confluent.ksql.function.udf.Udf;
import io.confluent.ksql.function.udf.UdfDescription;
import io.confluent.ksql.function.udf.UdfParameter;
import java.util.Map;
import java.util.stream.Collectors;
import java.util.stream.StreamSupport;

@UdfDescription(
name = "split_to_map",
description = "Splits a string into key-value pairs and creates a map from them. The "
+ "'entryDelimiter' splits the string into key-value pairs which are then split by "
+ "'kvDelimiter'. If the same key is present multiple times in the input, the latest "
+ "value for that key is returned. Returns NULL f the input text or either of the "
+ "delimiters is NULL.")
public class SplitToMap {
@Udf
public Map<String, String> splitToMap(
@UdfParameter(
description = "Separator string and values to join") final String input,
@UdfParameter(
description = "Separator string and values to join") final String entryDelimiter,
@UdfParameter(
description = "Separator string and values to join") final String kvDelimiter) {

if (input == null || entryDelimiter == null || kvDelimiter == null) {
return null;
}

if (entryDelimiter.isEmpty() || kvDelimiter.isEmpty() || entryDelimiter.equals(kvDelimiter)) {
return null;
}

final Iterable<String> entries = Splitter.on(entryDelimiter).omitEmptyStrings().split(input);
final Map<String, String> output = StreamSupport.stream(entries.spliterator(), false)
.filter(e -> e.contains(kvDelimiter))
.map(kv -> Splitter.on(kvDelimiter).split(kv).iterator())
.collect(Collectors.toMap(
kvIter -> kvIter.next(),
kvIter -> kvIter.next(),
(v1, v2) -> v2));

return output;
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,131 @@
/*
* Copyright 2020 Confluent Inc.
*
* Licensed under the Confluent Community License (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.confluent.io/confluent-community-license
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OF ANY KIND, either express or implied. See the License for the
* specific language governing permissions and limitations under the License.
*/

package io.confluent.ksql.function.udf.array;

import static org.hamcrest.MatcherAssert.assertThat;
import static org.hamcrest.Matchers.is;
import static org.hamcrest.Matchers.nullValue;
import static org.junit.Assert.assertThrows;

import io.confluent.ksql.function.KsqlFunctionException;
import java.math.BigDecimal;
import java.math.BigInteger;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashSet;
import org.junit.Test;

public class ArrayJoinTest {

private static final String CUSTOM_DELIMITER = "|";

private final ArrayJoin arrayJoinUDF = new ArrayJoin();

@Test
public void shouldReturnNullForNullInput() {
assertThat(arrayJoinUDF.join(null), nullValue());
assertThat(arrayJoinUDF.join(null,CUSTOM_DELIMITER), nullValue());
}

@Test
public void shouldReturnEmptyStringForEmptyArrays() {
assertThat(arrayJoinUDF.join(Collections.emptyList()).isEmpty(),is(true));
assertThat(arrayJoinUDF.join(Collections.emptyList(),CUSTOM_DELIMITER).isEmpty(),is(true));
}

@Test
public void shouldReturnCorrectStringForFlatArraysWithPrimitiveTypes() {

assertThat(arrayJoinUDF.join(Arrays.asList(true, null, false),""),
is("truenullfalse")
);
assertThat(arrayJoinUDF.join(Arrays.asList(true, null, false)),
is("true,null,false")
);
assertThat(arrayJoinUDF.join(Arrays.asList(true,null,false),CUSTOM_DELIMITER),
is("true"+CUSTOM_DELIMITER+"null"+CUSTOM_DELIMITER+"false")
);

assertThat(arrayJoinUDF.join(Arrays.asList(1,23,-42,0),null), is("123-420"));
assertThat(arrayJoinUDF.join(Arrays.asList(1,23,-42,0)), is("1,23,-42,0"));
assertThat(arrayJoinUDF.join(Arrays.asList(1,23,-42,0),CUSTOM_DELIMITER),
is("1"+CUSTOM_DELIMITER+"23"+CUSTOM_DELIMITER+"-42"+CUSTOM_DELIMITER+"0")
);

assertThat(arrayJoinUDF.join(Arrays.asList(-4294967297L, 8589934592L),""),
is("-42949672978589934592")
);
assertThat(arrayJoinUDF.join(Arrays.asList(-4294967297L, 8589934592L)),
is("-4294967297,8589934592")
);
assertThat(arrayJoinUDF.join(Arrays.asList(-4294967297L, 8589934592L), CUSTOM_DELIMITER),
is("-4294967297"+CUSTOM_DELIMITER+"8589934592")
);

assertThat(arrayJoinUDF.join(Arrays.asList(1.23,-23.42,0.0),null),
is("1.23-23.420.0")
);
assertThat(arrayJoinUDF.join(Arrays.asList(1.23,-23.42,0.0)),
is("1.23,-23.42,0.0")
);
assertThat(arrayJoinUDF.join(Arrays.asList(1.23,-23.42,0.0),CUSTOM_DELIMITER),
is("1.23"+CUSTOM_DELIMITER+"-23.42"+CUSTOM_DELIMITER+"0.0")
);

assertThat(arrayJoinUDF.join(
Arrays.asList(new BigDecimal("123.45"), new BigDecimal("987.65")),null
),
is("123.45987.65")
);
assertThat(arrayJoinUDF.join(Arrays.asList(new BigDecimal("123.45"), new BigDecimal("987.65"))),
is("123.45,987.65")
);
assertThat(arrayJoinUDF.join(
Arrays.asList(new BigDecimal("123.45"), new BigDecimal("987.65")),CUSTOM_DELIMITER),
is("123.45"+CUSTOM_DELIMITER+"987.65")
);

assertThat(arrayJoinUDF.join(Arrays.asList("Hello","From","","Ksqldb","Udf"),""),
is("HelloFromKsqldbUdf")
);
assertThat(arrayJoinUDF.join(Arrays.asList("Hello","From","","Ksqldb","Udf")),
is("Hello,From,,Ksqldb,Udf")
);
assertThat(
arrayJoinUDF.join(Arrays.asList("hello","from","","ksqldb","udf",null),CUSTOM_DELIMITER),
is("hello"+CUSTOM_DELIMITER+"from"+CUSTOM_DELIMITER+CUSTOM_DELIMITER
+"ksqldb"+CUSTOM_DELIMITER+"udf"+CUSTOM_DELIMITER+"null")
);

}

@Test
public void shouldThrowExceptionForExamplesOfUnsupportedElementTypes() {
assertThrows(KsqlFunctionException.class,
() -> arrayJoinUDF.join(Arrays.asList('a','b')));
assertThrows(KsqlFunctionException.class,
() -> arrayJoinUDF.join(Arrays.asList(BigInteger.ONE,BigInteger.ZERO)));
assertThrows(KsqlFunctionException.class,
() -> arrayJoinUDF.join(Arrays.asList(-23.0f,42.42f,0.0f)));
assertThrows(KsqlFunctionException.class,
() -> arrayJoinUDF.join(Arrays.asList(
new HashSet<>(Arrays.asList("foo", "blah")),
new HashSet<>(Arrays.asList("ksqlDB", "UDF"))
))
);
}

}
Loading