Text and Keyword aggregation integration tests #176
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,258 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| package org.opensearch.sql.sql; | ||
|
|
||
| import org.junit.Test; | ||
| import org.opensearch.sql.legacy.SQLIntegTestCase; | ||
|
|
||
| import java.io.IOException; | ||
|
|
||
| import static org.opensearch.sql.legacy.TestsConstants.TEST_INDEX_TEXTKEYWORD; | ||
| import static org.opensearch.sql.util.MatcherUtils.schema; | ||
| import static org.opensearch.sql.util.MatcherUtils.verifySchema; | ||
|
|
||
| public class TextTypeIT extends SQLIntegTestCase { | ||
|
|
||
|
|
||
| @Override | ||
| public void init() throws Exception { | ||
| super.init(); | ||
| loadIndex(Index.TEXTKEYWORD); | ||
| loadIndex(Index.CALCS); | ||
|
|
||
| } | ||
|
|
||
| // Select | ||
|
|
||
| @Test | ||
| public void textKeywordTest() { | ||
| var result = executeJdbcRequest(String.format("select typeKeyword from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeKeyword", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void aggregateOnText() { | ||
| var result = executeJdbcRequest(String.format("select sum(int0) from %s GROUP BY typeText", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("sum(int0)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void aggregateOnKeyword() { | ||
| var result = executeJdbcRequest(String.format("select sum(int0) from %s GROUP BY typeKeyword", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("sum(int0)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void aggregateOnTextFieldData() { | ||
| var result = executeJdbcRequest(String.format("select sum(int0) from %s GROUP BY typeTextFieldData", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("sum(int0)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void aggregateOnKeywordFieldData() { | ||
| var result = executeJdbcRequest(String.format("select sum(int0) from %s GROUP BY typeKeywordFieldNoFieldData", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("sum(int0)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void aggregateOnTextAndFieldDataNoFields() { | ||
| var result = executeJdbcRequest(String.format("select sum(int0) from %s GROUP BY textDataFieldNoFields", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("sum(int0)", null, "integer")); | ||
| } | ||
|
|
||
| // Where like | ||
|
|
||
| @Test | ||
| public void whereLikeKeyword() { | ||
| var result = executeJdbcRequest(String.format("select typeKeyword from %s WHERE typeKeyword LIKE \\\"key*\\\"", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeKeyword", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereLikeText() { | ||
| var result = executeJdbcRequest(String.format("select typeText from %s WHERE typeText LIKE \\\"text*\\\"", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeText", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereLikeKeywordFieldNoFieldData() { | ||
| var result = executeJdbcRequest(String.format("select typeKeywordFieldNoFieldData from %s WHERE typeKeywordFieldNoFieldData LIKE \\\"keyword*\\\"", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeKeywordFieldNoFieldData", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereLikeTextFieldData() { | ||
| var result = executeJdbcRequest(String.format("select typeTextFieldData from %s WHERE typeTextFieldData LIKE \\\"keyFD*\\\"", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeTextFieldData", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereLiketextDataFieldNoFields() { | ||
| var result = executeJdbcRequest(String.format("select textDataFieldNoFields from %s WHERE textDataFieldNoFields LIKE \\\"textFDNF*\\\"", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("textDataFieldNoFields", null, "text")); | ||
| } | ||
|
|
||
| // Wildcard | ||
|
|
||
| @Test | ||
| public void whereWildcardKeyword() { | ||
| var result = executeJdbcRequest(String.format("select typeKeyword from %s WHERE wildcard_query(typeKeyword, \\\"key*\\\")", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeKeyword", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereWildcardText() { | ||
| var result = executeJdbcRequest(String.format("select typeText from %s WHERE wildcard_query(\\\"typeText\\\", \\\"text*\\\")", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeText", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereWildcardKeywordFieldNoFieldData() { | ||
| var result = executeJdbcRequest(String.format("select typeKeywordFieldNoFieldData from %s WHERE wildcard_query(\\\"typeKeywordFieldNoFieldData\\\", \\\"keyword*\\\")", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeKeywordFieldNoFieldData", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereWildcardTextFieldData() { | ||
| var result = executeJdbcRequest(String.format("select typeTextFieldData from %s WHERE wildcard_query(\\\"typeTextFieldData\\\", \\\"keyFD*\\\")", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeTextFieldData", null, "text")); | ||
| } | ||
|
|
||
| @Test | ||
| public void whereWildcardtextDataFieldNoFields() { | ||
| var result = executeJdbcRequest(String.format("select textDataFieldNoFields from %s WHERE wildcard_query(\\\"textDataFieldNoFields\\\", \\\"textFDNF*\\\")", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("textDataFieldNoFields", null, "text")); | ||
| } | ||
|
|
||
| // Locate | ||
|
|
||
| @Test | ||
| public void selectLocateKeyword() { | ||
| var result = executeJdbcRequest(String.format("select locate(\\\"key*\\\", typeKeyword) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("locate(\"key*\", typeKeyword)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectLocateText() { | ||
| var result = executeJdbcRequest(String.format("select locate(\\\"text*\\\", typeText) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("locate(\"text*\", typeText)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectLocateTextKeywordFieldNoFieldData() { | ||
| var result = executeJdbcRequest(String.format("select locate(\\\"keyword*\\\", typeKeywordFieldNoFieldData) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("locate(\"keyword*\", typeKeywordFieldNoFieldData)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectLocateTypeTextFieldData() { | ||
| var result = executeJdbcRequest(String.format("select locate(\\\"keyFD*\\\", typeTextFieldData) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("locate(\"keyFD*\", typeTextFieldData)", null, "integer")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectLocateTextDataFieldNoFields() { | ||
| var result = executeJdbcRequest(String.format("select locate(\\\"textFDNF*\\\", textDataFieldNoFields) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("locate(\"textFDNF*\", textDataFieldNoFields)", null, "integer")); | ||
| } | ||
|
|
||
| // Position | ||
|
|
||
| @Test | ||
| public void selectPositionKeyword() { | ||
| var result = executeJdbcRequest(String.format("select POSITION(\\\"key\\\" IN typeKeyword) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("LOCATE('key', typeKeyword)", null, "double")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectPositionText() throws IOException { | ||
| var result = executeQuery(String.format("select POSITION(\\\"text\\\" IN typeText) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("typeText", null, "double")); | ||
|
|
||
| // } | ||
| } | ||
|
|
||
| @Test | ||
| public void selectPositionTextKeywordFieldNoFieldData() { | ||
| var result = executeJdbcRequest(String.format("select POSITION(\\\"keyword\\\" IN typeKeywordFieldNoFieldData) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("LOCATE('keyword', typeKeywordFieldNoFieldData)", null, "double")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectPositionTypeTextFieldData() throws IOException { | ||
| var result = executeQuery(String.format("select POSITION(\\\"keyFD\\\" IN typeTextFieldData) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("LOCATE('keyFD', typeTextFieldData)", null, "double")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectPositionTextDataFieldNoFields() { | ||
| var result = executeJdbcRequest(String.format("select POSITION(\\\"textFDNF\\\" IN textDataFieldNoFields) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("LOCATE('textFDNF', textDataFieldNoFields)", null, "double")); | ||
| } | ||
|
|
||
| // Substring | ||
|
|
||
| @Test | ||
| public void selectSubstringKeyword() { | ||
| var result = executeJdbcRequest(String.format("select SUBSTRING(typeKeyword, 1, 1) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("SUBSTRING(typeKeyword, 1, 1)", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectSubstringText() { | ||
| var result = executeJdbcRequest(String.format("select SUBSTRING(typeText, 1, 1) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("SUBSTRING(typeText, 1, 1)", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectSubstringTextKeywordFieldNoFieldData() { | ||
| var result = executeJdbcRequest(String.format("select SUBSTRING(typeKeywordFieldNoFieldData, 1, 1) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("SUBSTRING(typeKeywordFieldNoFieldData, 1, 1)", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectSubstringTypeTextFieldData() { | ||
| var result = executeJdbcRequest(String.format("select SUBSTRING(typeTextFieldData, 1, 1) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("SUBSTRING(typeTextFieldData, 1, 1)", null, "keyword")); | ||
| } | ||
|
|
||
| @Test | ||
| public void selectSubstringTextDataFieldNoFields() { | ||
| var result = executeJdbcRequest(String.format("select SUBSTRING(textDataFieldNoFields, 1, 1) from %s", TEST_INDEX_TEXTKEYWORD)); | ||
| verifySchema(result, | ||
| schema("SUBSTRING(textDataFieldNoFields, 1, 1)", null, "keyword")); | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -20,7 +20,7 @@ | |
| "type" : "double" | ||
| }, | ||
| "str0" : { | ||
| "type" : "integer" | ||
| }, | ||
| "str1" : { | ||
| "type" : "keyword" | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,37 @@ | ||
| { | ||
| "mappings" : { | ||
| "properties" : { | ||
| "typeKeyword" : { | ||
| "type" : "keyword" | ||
| }, | ||
| "typeText" : { | ||
| "type" : "text" | ||
| }, | ||
| "typeKeywordFieldNoFieldData" : { | ||
| "type": "text", | ||
| "fields": { | ||
| "keyword": { | ||
| "type": "keyword", | ||
| "ignore_above": 10 | ||
|
There was a problem hiding this comment. Try adding a row with more than 10 words. Interesting to test this too. |
||
| } | ||
| } }, | ||
| "typeTextFieldData" : { | ||
| "type": "text", | ||
| "fielddata": true, | ||
|
There was a problem hiding this comment. it would be interesting to know how it works if we have a There was a problem hiding this comment. Added in 2a8fbac. It passes. |
||
| "fields": { | ||
| "keyword": { | ||
| "type": "keyword", | ||
| "ignore_above": 10 | ||
| } | ||
| } | ||
| }, | ||
| "textDataFieldNoFields" : { | ||
| "type": "text", | ||
| "fielddata": true | ||
| }, | ||
| "int0" : { | ||
| "type": "integer" | ||
| } | ||
| } | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| {"index": {"_id":"1"}} | ||
| {"typeKeyword": "key00", "typeText": "text00", "typeKeywordFieldNoFieldData": "keyword00","typeTextFieldData": "keyFD00", "typeKeywordFieldData": "textFD00", "textDataFieldNoFields": "textFDNF00","int0": 0} | ||
| {"index": {"_id":"2"}} | ||
| {"typeKeyword": "key01", "typeText": "text01", "typeKeywordFieldNoFieldData": "keyword01", "typeTextFieldData": "keyFD01", "typeKeywordFieldData": "textFD01OverTen", "textDataFieldNoFields": "textFDNF01", "int0": 1} | ||
| {"index": {"_id":"3"}} | ||
| {"typeKeyword": "key02", "typeText": "text02", "typeKeywordFieldNoFieldData": "keyword02", "typeTextFieldData": "keyFD02", "typeKeywordFieldData": "textFD02", "textDataFieldNoFields": "textFDNF02", "int0": 2} | ||
| {"index": {"_id":"4"}} | ||
| {"typeKeyword": "key03", "typeText": "text03", "typeKeywordFieldNoFieldData": "keyword03", "typeTextFieldData": "keyFD03OverTen", "typeKeywordFieldData": "textFD03", "textDataFieldNoFields": "textFDNF03", "int0": 3} | ||
| {"index": {"_id":"5"}} | ||
| {"typeKeyword": "key04", "typeText": "text04", "typeKeywordFieldNoFieldData": "keyword04", "typeTextFieldData": "keyFD04", "typeKeywordFieldData": "textFD04", "textDataFieldNoFields": "textFDNF04", "int0": 4} | ||
| {"index": {"_id":"6"}} | ||
| {"typeKeyword": "key05", "typeText": "text05", "typeKeywordFieldNoFieldData": "keyword05", "typeTextFieldData": "keyFD05", "typeKeywordFieldData": "textFD0OverTen5", "textDataFieldNoFields": "textFDNF05", "int0": 5} | ||
| {"index": {"_id":"7"}} | ||
| {"typeKeyword": "key06", "typeText": "text06", "typeKeywordFieldNoFieldData": "keyword06", "typeTextFieldData": "keyFD06OverTen", "typeKeywordFieldData": "textFD06", "textDataFieldNoFields": "textFDNF06", "int0": 6} | ||
| {"index": {"_id":"8"}} | ||
| {"typeKeyword": "key07", "typeText": "text07", "typeKeywordFieldNoFieldData": "keyword07", "typeTextFieldData": "keyFD07", "typeKeywordFieldData": "textFD07", "textDataFieldNoFields": "textFDNF07", "int0": 7} |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Are there any other tests that you tried? These only look like aggregation tests, but it would be good to know if some of the following would also work:
WHERE field LIKE "keyFD??"WHERE wildcard("field", "keyFD??")SELECT field LIKE "keyFD??"and maybe a couple of string-like functions:
SELECT LOCATE("FD", field)SELECT SUBSTRING(field, 3, 2)There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also try
SELECT POSITION(substring IN field)since it seems to fail for text fields (as Margarit demonstrated)There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
SELECT POSITION(substring IN field)
Passed:
Failed:
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you check selectPositionTextDataFieldNoFields - its giving you a parser error.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Otherwise, this looks exclusively like an issue with aggregation on text fields.
Strangely, I thought POSITION was going to fail on text fields, since it was failing for Margarit earlier.