Skip to content

Scalar function for url encoding and decoding #8378

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.

Sign up for GitHub

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

Merged
Jackie-Jiang merged 4 commits into from
Mar 22, 2022
Merged

Scalar function for url encoding and decoding #8378

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
71d2e7b
Add support for url encoding/decoding
jasperjiaguo Mar 17, 2022
67079a1
Adding support for url encoding/decoding
jasperjiaguo Mar 21, 2022
def6db1
Adding support for url encoding/decoding
jasperjiaguo Mar 21, 2022
6dcee76
Adding support for url encoding/decoding
jasperjiaguo Mar 21, 2022
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
32 changes: 32 additions & 0 deletions ...er/src/test/java/org/apache/pinot/broker/requesthandler/LiteralOnlyBrokerRequestTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,6 +94,15 @@ public void testLiteralOnlyTransformBrokerRequestFromSQL() {
.compileToPinotQuery("SELECT ago('PT1H'), fromDateTime('2020-01-01 UTC', 'yyyy-MM-dd z') FROM myTable")));
Assert.assertFalse(BaseBrokerRequestHandler
.isLiteralOnlyQuery(CalciteSqlParser.compileToPinotQuery("SELECT count(*) from foo where bar > ago('PT1H')")));
Assert.assertTrue(BaseBrokerRequestHandler.isLiteralOnlyQuery(CalciteSqlParser
Copy link
Contributor

@siddharthteotia siddharthteotia Mar 21, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we not use full URLs as inputs to encodeUrl / decodeUrl functions in tests ? From user perspective, they will use the full URL right ?

SELECT encodeUrl(<myURL>) FROM FOO .....

Copy link
Contributor

@siddharthteotia siddharthteotia Mar 22, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@jasperjiaguo - please add test cases with real URLs as well

Copy link
Contributor

@Jackie-Jiang Jackie-Jiang Mar 22, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry, I merged the PR too soon. @jasperjiaguo Can you please address Sidd's comments in a separate PR?

.compileToPinotQuery("SELECT encodeUrl('key1=value 1&key2=value@!$2&key3=value%3'),"
+ " decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253') FROM myTable")));
Assert.assertFalse(BaseBrokerRequestHandler.isLiteralOnlyQuery(CalciteSqlParser
.compileToPinotQuery("SELECT count(*) from foo "
+ "where bar = encodeUrl('key1=value 1&key2=value@!$2&key3=value%3')")));
Assert.assertFalse(BaseBrokerRequestHandler.isLiteralOnlyQuery(CalciteSqlParser
.compileToPinotQuery("SELECT count(*) from foo "
+ "where bar = decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253')")));
}

@Test
Expand All @@ -102,6 +111,9 @@ public void testLiteralOnlyWithAsBrokerRequestFromSQL() {
"SELECT now() AS currentTs, fromDateTime('2020-01-01 UTC', 'yyyy-MM-dd z') AS firstDayOf2020")));
Assert.assertTrue(BaseBrokerRequestHandler.isLiteralOnlyQuery(CalciteSqlParser.compileToPinotQuery(
"SELECT ago('PT1H') AS currentTs, fromDateTime('2020-01-01 UTC', 'yyyy-MM-dd z') AS firstDayOf2020")));
Assert.assertTrue(BaseBrokerRequestHandler.isLiteralOnlyQuery(CalciteSqlParser.compileToPinotQuery(
"SELECT encodeUrl('key1=value 1&key2=value@!$2&key3=value%3') AS encoded, "
+ "decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253') AS decoded")));
}

@Test
Expand Down Expand Up @@ -178,6 +190,26 @@ public void testBrokerRequestHandlerWithAsFunction()
.assertTrue(Long.parseLong(brokerResponse.getResultTable().getRows().get(0)[0].toString()) <= oneHourAgoTsMax);
Assert.assertEquals(brokerResponse.getResultTable().getRows().get(0)[1], 1577836800000L);
Assert.assertEquals(brokerResponse.getTotalDocs(), 0);

request = new ObjectMapper().readTree(
"{\"sql\":\"SELECT encodeUrl('key1=value 1&key2=value@!$2&key3=value%3') AS encoded, "
+ "decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253') AS decoded\"}");
requestStats = new RequestStatistics();
brokerResponse = requestHandler.handleRequest(request, null, requestStats);
System.out.println(brokerResponse.getResultTable());
Assert.assertEquals(brokerResponse.getResultTable().getDataSchema().getColumnName(0), "encoded");
Assert.assertEquals(brokerResponse.getResultTable().getDataSchema().getColumnDataType(0),
DataSchema.ColumnDataType.STRING);
Assert.assertEquals(brokerResponse.getResultTable().getDataSchema().getColumnName(1), "decoded");
Assert.assertEquals(brokerResponse.getResultTable().getDataSchema().getColumnDataType(1),
DataSchema.ColumnDataType.STRING);
Assert.assertEquals(brokerResponse.getResultTable().getRows().size(), 1);
Assert.assertEquals(brokerResponse.getResultTable().getRows().get(0).length, 2);
Assert.assertEquals(brokerResponse.getResultTable().getRows().get(0)[0].toString(),
"key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253");
Assert.assertEquals(brokerResponse.getResultTable().getRows().get(0)[1].toString(),
"key1=value 1&key2=value@!$2&key3=value%3");
Assert.assertEquals(brokerResponse.getTotalDocs(), 0);
}

/** Tests for EXPLAIN PLAN for literal only queries. */
Expand Down
27 changes: 27 additions & 0 deletions pinot-common/src/main/java/org/apache/pinot/common/function/scalar/StringFunctions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,9 @@
*/
package org.apache.pinot.common.function.scalar;

import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import java.text.Normalizer;
import java.util.regex.Matcher;
Expand Down Expand Up @@ -443,4 +446,28 @@ public static boolean contains(String input, String substring) {
public static int strcmp(String input1, String input2) {
return input1.compareTo(input2);
}

/**
*
* @param input plaintext string
* @return url encoded string
* @throws UnsupportedEncodingException
*/
@ScalarFunction
public static String encodeUrl(String input)
throws UnsupportedEncodingException {
return URLEncoder.encode(input, StandardCharsets.UTF_8.toString());
}

/**
*
* @param input url encoded string
* @return plaintext string
* @throws UnsupportedEncodingException
*/
@ScalarFunction
public static String decodeUrl(String input)
throws UnsupportedEncodingException {
return URLDecoder.decode(input, StandardCharsets.UTF_8.toString());
}
}
61 changes: 61 additions & 0 deletions pinot-common/src/test/java/org/apache/pinot/sql/parsers/CalciteSqlCompilerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -444,6 +444,31 @@ public void testBrokerConverterWithLiteral() {
pinotQuery = CalciteSqlParser.compileToPinotQuery("SELECT count(*) from mytable where bar > ago('PT1H')");
literal = pinotQuery.getSelectList().get(0).getLiteral();
Assert.assertNull(literal);

pinotQuery = CalciteSqlParser
.compileToPinotQuery("select encodeUrl('key1=value 1&key2=value@!$2&key3=value%3'), "
+ "decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253') from mytable");
Literal literal1 = pinotQuery.getSelectList().get(0).getLiteral();
Literal literal2 = pinotQuery.getSelectList().get(1).getLiteral();
Assert.assertNotNull(literal1);
Assert.assertNotNull(literal2);
converter = new PinotQuery2BrokerRequestConverter();
tempBrokerRequest = converter.convert(pinotQuery);
Assert.assertEquals(tempBrokerRequest.getQuerySource().getTableName(), "mytable");
Assert.assertEquals(tempBrokerRequest.getSelections().getSelectionColumns().get(0),
String.format("'%s'", literal1.getFieldValue().toString()));
Assert.assertEquals(tempBrokerRequest.getSelections().getSelectionColumns().get(1),
String.format("'%s'", literal2.getFieldValue().toString()));

pinotQuery = CalciteSqlParser.compileToPinotQuery("SELECT count(*) from mytable "
+ "where bar = encodeUrl('key1=value 1&key2=value@!$2&key3=value%3')");
literal = pinotQuery.getSelectList().get(0).getLiteral();
Assert.assertNull(literal);

pinotQuery = CalciteSqlParser.compileToPinotQuery("SELECT count(*) from mytable "
+ "where bar = decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253')");
literal = pinotQuery.getSelectList().get(0).getLiteral();
Assert.assertNull(literal);
}

@Test
Expand Down Expand Up @@ -1855,6 +1880,23 @@ public void testCompilationInvokedFunction() {
upperBound = System.currentTimeMillis() - ONE_HOUR_IN_MS;
Assert.assertTrue(nowTs >= lowerBound);
Assert.assertTrue(nowTs <= upperBound);

query = "select encodeUrl('key1=value 1&key2=value@!$2&key3=value%3'), "
+ "decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253') from mytable";
pinotQuery = CalciteSqlParser.compileToPinotQuery(query);
String encoded = pinotQuery.getSelectList().get(0).getLiteral().getStringValue();
String decoded = pinotQuery.getSelectList().get(1).getLiteral().getStringValue();
Assert.assertEquals(encoded, "key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253");
Assert.assertEquals(decoded, "key1=value 1&key2=value@!$2&key3=value%3");

query = "select a from mytable where foo=encodeUrl('key1=value 1&key2=value@!$2&key3=value%3') and"
+ " bar=decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253')";
pinotQuery = CalciteSqlParser.compileToPinotQuery(query);
Function and = pinotQuery.getFilterExpression().getFunctionCall();
encoded = and.getOperands().get(0).getFunctionCall().getOperands().get(1).getLiteral().getStringValue();
decoded = and.getOperands().get(1).getFunctionCall().getOperands().get(1).getLiteral().getStringValue();
Assert.assertEquals(encoded, "key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253");
Assert.assertEquals(decoded, "key1=value 1&key2=value@!$2&key3=value%3");
}

@Test
Expand Down Expand Up @@ -1926,6 +1968,25 @@ public void testCompileTimeExpression() {
Assert.assertEquals(expression.getFunctionCall().getOperands().get(0).getIdentifier().getName(),
"millisSinceEpoch");

expression = CalciteSqlParser.compileToExpression("encodeUrl('key1=value 1&key2=value@!$2&key3=value%3')");
Assert.assertNotNull(expression.getFunctionCall());
pinotQuery.setFilterExpression(expression);
pinotQuery = compileTimeFunctionsInvoker.rewrite(pinotQuery);
expression = pinotQuery.getFilterExpression();
Assert.assertNotNull(expression.getLiteral());
Assert.assertEquals(expression.getLiteral().getFieldValue(),
"key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253");

expression = CalciteSqlParser
.compileToExpression("decodeUrl('key1%3Dvalue+1%26key2%3Dvalue%40%21%242%26key3%3Dvalue%253')");
Assert.assertNotNull(expression.getFunctionCall());
pinotQuery.setFilterExpression(expression);
pinotQuery = compileTimeFunctionsInvoker.rewrite(pinotQuery);
expression = pinotQuery.getFilterExpression();
Assert.assertNotNull(expression.getLiteral());
Assert.assertEquals(expression.getLiteral().getFieldValue(),
"key1=value 1&key2=value@!$2&key3=value%3");

expression = CalciteSqlParser.compileToExpression("reverse(playerName)");
Assert.assertNotNull(expression.getFunctionCall());
pinotQuery.setFilterExpression(expression);
Expand Down
Loading