Skip to content

NIFI-8269 - Add support for schema inference in ForkRecord processor when extracting array records #10167

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

NIFI-8269 - Add support for schema inference in ForkRecord processor when extracting array records #10167

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 4 additions & 0 deletions nifi-extension-bundles/nifi-standard-bundle/nifi-standard-processors/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -624,6 +624,10 @@
<exclude>src/test/resources/TestExtractGrok/simple_text.log</exclude>
<exclude>src/test/resources/TestExtractRecordSchema/name_age_schema.avsc</exclude>
<exclude>src/test/resources/TestForkRecord/input/complex-input-json.json</exclude>
<exclude>src/test/resources/TestForkRecord/input/complex-input-json-for-inference.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/extract-address-without-parents.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/extract-address-with-parents.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/extract-bank-accounts-with-parents.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/extract-transactions.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/split-address.json</exclude>
<exclude>src/test/resources/TestForkRecord/output/split-transactions.json</exclude>
Expand Down
245 changes: 180 additions & 65 deletions ...ifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/ForkRecord.java
View file
Open in desktop

Large diffs are not rendered by default.

90 changes: 90 additions & 0 deletions ...standard-processors/src/test/java/org/apache/nifi/processors/standard/TestForkRecord.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -451,6 +451,96 @@ public void testExtractMode() throws InitializationException, IOException {
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertAttributeEquals("record.count", "6");
}

@Test
public void testExtractWithParentFieldsAndInferredSchema() throws Exception {
TestRunner runner = TestRunners.newTestRunner(new ForkRecord());

final JsonTreeReader jsonReader = new JsonTreeReader();
runner.addControllerService("record-reader", jsonReader);
runner.enableControllerService(jsonReader);

final JsonRecordSetWriter jsonWriter = new JsonRecordSetWriter();
runner.addControllerService("record-writer", jsonWriter);
runner.setProperty(jsonWriter, "Pretty Print JSON", "true");
runner.enableControllerService(jsonWriter);

runner.setProperty(ForkRecord.RECORD_READER, "record-reader");
runner.setProperty(ForkRecord.RECORD_WRITER, "record-writer");
runner.setProperty(ForkRecord.MODE, ForkRecord.MODE_EXTRACT);
runner.setProperty(ForkRecord.INCLUDE_PARENT_FIELDS, "true");
runner.setProperty("bankAccounts", "/bankAccounts");

runner.enqueue(Paths.get("src/test/resources/TestForkRecord/input/complex-input-json-for-inference.json"));
runner.run();

runner.assertTransferCount(ForkRecord.REL_ORIGINAL, 1);
runner.assertTransferCount(ForkRecord.REL_FORK, 1);

final String expectedOutput = new String(Files.readAllBytes(Paths.get("src/test/resources/TestForkRecord/output/extract-bank-accounts-with-parents.json")));
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertAttributeEquals("record.count", "5");
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertContentEquals(expectedOutput);
}

@Test
public void testExtractFieldsAndInferredSchema() throws Exception {
TestRunner runner = TestRunners.newTestRunner(new ForkRecord());

final JsonTreeReader jsonReader = new JsonTreeReader();
runner.addControllerService("record-reader", jsonReader);
runner.enableControllerService(jsonReader);

final JsonRecordSetWriter jsonWriter = new JsonRecordSetWriter();
runner.addControllerService("record-writer", jsonWriter);
runner.setProperty(jsonWriter, "Pretty Print JSON", "true");
runner.enableControllerService(jsonWriter);

runner.setProperty(ForkRecord.RECORD_READER, "record-reader");
runner.setProperty(ForkRecord.RECORD_WRITER, "record-writer");
runner.setProperty(ForkRecord.MODE, ForkRecord.MODE_EXTRACT);
runner.setProperty(ForkRecord.INCLUDE_PARENT_FIELDS, "false");
runner.setProperty("address", "/address");

runner.enqueue(Paths.get("src/test/resources/TestForkRecord/input/complex-input-json-for-inference.json"));
runner.run();

runner.assertTransferCount(ForkRecord.REL_ORIGINAL, 1);
runner.assertTransferCount(ForkRecord.REL_FORK, 1);

final String expectedOutput = new String(Files.readAllBytes(Paths.get("src/test/resources/TestForkRecord/output/extract-address-without-parents.json")));
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertAttributeEquals("record.count", "5");
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertContentEquals(expectedOutput);
}

@Test
public void testExtractFieldsWithParentsAndFieldConflictAndInferredSchema() throws Exception {
TestRunner runner = TestRunners.newTestRunner(new ForkRecord());

final JsonTreeReader jsonReader = new JsonTreeReader();
runner.addControllerService("record-reader", jsonReader);
runner.enableControllerService(jsonReader);

final JsonRecordSetWriter jsonWriter = new JsonRecordSetWriter();
runner.addControllerService("record-writer", jsonWriter);
runner.setProperty(jsonWriter, "Pretty Print JSON", "true");
runner.enableControllerService(jsonWriter);

runner.setProperty(ForkRecord.RECORD_READER, "record-reader");
runner.setProperty(ForkRecord.RECORD_WRITER, "record-writer");
runner.setProperty(ForkRecord.MODE, ForkRecord.MODE_EXTRACT);
runner.setProperty(ForkRecord.INCLUDE_PARENT_FIELDS, "true");
runner.setProperty("address", "/address");

runner.enqueue(Paths.get("src/test/resources/TestForkRecord/input/complex-input-json-for-inference.json"));
runner.run();

runner.assertTransferCount(ForkRecord.REL_ORIGINAL, 1);
runner.assertTransferCount(ForkRecord.REL_FORK, 1);

final String expectedOutput = new String(Files.readAllBytes(Paths.get("src/test/resources/TestForkRecord/output/extract-address-with-parents.json")));
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertAttributeEquals("record.count", "5");
runner.getFlowFilesForRelationship(ForkRecord.REL_FORK).get(0).assertContentEquals(expectedOutput);
}

private class JsonRecordReader extends AbstractControllerService implements RecordReaderFactory {

private static final JsonParserFactory jsonParserFactory = new JsonParserFactory();
Expand Down
116 changes: 116 additions & 0 deletions ...-processors/src/test/resources/TestForkRecord/input/complex-input-json-for-inference.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,116 @@
[
{
"id": 1,
"name": {
"last": "Doe",
"first": "John"
},
"address": [
{
"id": "home",
"street": "1 nifi street",
"city": "nifi city"
}
],
"bankAccounts": [
{
"bankID": "OneBank",
"IBAN": "OneIBAN",
"last5Transactions": [
{
"comment": "food",
"amount": "-450"
}
]
}
]
}, {
"id": 2,
"name": {
"last": "Smith",
"first": "John"
},
"address": [null],
"bankAccounts": null
}, {
"id": 3,
"name": {
"last": "Smith",
"first": "Jane"
},
"address": [
{
"id": "home",
"street": "1 nifi street",
"city": "nifi city"
}, {
"id": "work",
"street": "1 nifi avenue",
"city": "apache city"
}
],
"bankAccounts": [
{
"bankID": "nifi bank",
"IBAN": "myIBAN",
"last5Transactions": null
}, {
"bankID": "apache bank",
"IBAN": "myIBAN",
"last5Transactions": [
{
"comment": "gas station",
"amount": "-45"
}, {
"comment": "hair cut",
"amount": "-19"
}
]
}
]
}, {
"id": 4,
"name": {
"last": "Clark",
"first": "Jane"
},
"address": [
{
"id": "home",
"street": "10 nifi street",
"city": "nifi city"
}, {
"id": "work",
"street": "10 nifi avenue",
"city": "apache city"
}
],
"bankAccounts": [
{
"bankID": "nifi bank",
"IBAN": "myIBAN",
"last5Transactions": [
{
"comment": "gift",
"amount": "+100"
}, {
"comment": "flights",
"amount": "-190"
}
]
}, {
"bankID": "apache bank",
"IBAN": "myIBAN",
"last5Transactions": [
{
"comment": "nifi tshirt",
"amount": "0"
}, {
"comment": "theatre",
"amount": "-19"
}
]
}
]
}
]
121 changes: 121 additions & 0 deletions ...ard-processors/src/test/resources/TestForkRecord/output/extract-address-with-parents.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,121 @@
[ {
"id" : "home",
"street" : "1 nifi street",
"city" : "nifi city",
"name" : {
"last" : "Doe",
"first" : "John"
},
"bankAccounts" : [ {
"bankID" : "OneBank",
"IBAN" : "OneIBAN",
"last5Transactions" : [ {
"comment" : "food",
"amount" : "-450"
} ]
} ]
}, {
"id" : "home",
"street" : "1 nifi street",
"city" : "nifi city",
"name" : {
"last" : "Smith",
"first" : "Jane"
},
"bankAccounts" : [ {
"bankID" : "nifi bank",
"IBAN" : "myIBAN",
"last5Transactions" : null
}, {
"bankID" : "apache bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "gas station",
"amount" : "-45"
}, {
"comment" : "hair cut",
"amount" : "-19"
} ]
} ]
}, {
"id" : "work",
"street" : "1 nifi avenue",
"city" : "apache city",
"name" : {
"last" : "Smith",
"first" : "Jane"
},
"bankAccounts" : [ {
"bankID" : "nifi bank",
"IBAN" : "myIBAN",
"last5Transactions" : null
}, {
"bankID" : "apache bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "gas station",
"amount" : "-45"
}, {
"comment" : "hair cut",
"amount" : "-19"
} ]
} ]
}, {
"id" : "home",
"street" : "10 nifi street",
"city" : "nifi city",
"name" : {
"last" : "Clark",
"first" : "Jane"
},
"bankAccounts" : [ {
"bankID" : "nifi bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "gift",
"amount" : "+100"
}, {
"comment" : "flights",
"amount" : "-190"
} ]
}, {
"bankID" : "apache bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "nifi tshirt",
"amount" : "0"
}, {
"comment" : "theatre",
"amount" : "-19"
} ]
} ]
}, {
"id" : "work",
"street" : "10 nifi avenue",
"city" : "apache city",
"name" : {
"last" : "Clark",
"first" : "Jane"
},
"bankAccounts" : [ {
"bankID" : "nifi bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "gift",
"amount" : "+100"
}, {
"comment" : "flights",
"amount" : "-190"
} ]
}, {
"bankID" : "apache bank",
"IBAN" : "myIBAN",
"last5Transactions" : [ {
"comment" : "nifi tshirt",
"amount" : "0"
}, {
"comment" : "theatre",
"amount" : "-19"
} ]
} ]
} ]
21 changes: 21 additions & 0 deletions ...-processors/src/test/resources/TestForkRecord/output/extract-address-without-parents.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
[ {
"id" : "home",
"street" : "1 nifi street",
"city" : "nifi city"
}, {
"id" : "home",
"street" : "1 nifi street",
"city" : "nifi city"
}, {
"id" : "work",
"street" : "1 nifi avenue",
"city" : "apache city"
}, {
"id" : "home",
"street" : "10 nifi street",
"city" : "nifi city"
}, {
"id" : "work",
"street" : "10 nifi avenue",
"city" : "apache city"
} ]
Loading
Loading