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.

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

Jump to bottom

Updating default parsing in AvscParser #546

Merged
merged 5 commits into from
Feb 5, 2024
Merged

Updating default parsing in AvscParser #546

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1a273ef
Default for a node can be processed if its type is union and first el…
li-ukumar Feb 2, 2024
d710f78
Updated processing of defaults to be done after resolution of schemas…
li-ukumar Feb 3, 2024
1cea21a
fix checkstyle
li-ukumar Feb 3, 2024
65801b1
refactor logic
li-ukumar Feb 5, 2024
7a73bdd
unnecessary continue removed
li-ukumar Feb 5, 2024
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
47 changes: 33 additions & 14 deletions parser/src/main/java/com/linkedin/avroutil1/parser/avsc/AvscFileParseContext.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,39 @@ public void resolveReferences() {
for (AvroSchema schema : definedSchemas) {
resolveReferences(schema);
}

// Once all schemas are resolved for this file, we can process the defaults for fields
for (AvroSchema schema : definedSchemas) {
processAllDefaults(schema);
}
}

private void processAllDefaults(AvroSchema schema) {
AvroType type = schema.type();
if (type == AvroType.RECORD) {
AvroRecordSchema recordSchema = (AvroRecordSchema) schema;
List<AvroSchemaField> fields = recordSchema.getFields();
for (AvroSchemaField field : fields) {
SchemaOrRef fieldSchema = field.getSchemaOrRef();
boolean hasDefault = field.hasDefaultValue();
boolean wasDefinedBefore = fieldSchema.isFullyDefined();
if (!wasDefinedBefore) {
if (!fieldSchema.isFullyDefined()) {
if (hasDefault) {
Copy link
Collaborator

Choose a reason for hiding this comment

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

line 197 and 198 are same. duplicate check.

fieldsWithUnparsedDefaults.add(field);
}
continue;
}
}
//fully defined if we're here
if (!hasDefault) {
continue;
}
if (field.getDefaultValue() instanceof AvscUnparsedLiteral) {
AvscParseUtil.lateParseFieldDefault(field, this);
}
}
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think we can refactor these code to remove these two continue to make the logic more clear.

The logic is like:
for (AvroSchemaField field : fields) {
SchemaOrRef fieldSchema = field.getSchemaOrRef();
boolean hasDefault = field.hasDefaultValue();
boolean wasDefinedBefore = fieldSchema.isFullyDefined();
if (!wasDefinedBefore) {
if (hasDefault) {
fieldsWithUnparsedDefaults.add(field);
}
} else {
if (!hasDefault) {
if (field.getDefaultValue() instanceof AvscUnparsedLiteral) {
AvscParseUtil.lateParseFieldDefault(field, this);
}
}
}
}

Or you can move the the check if (hasDefault) ahead:

for (AvroSchemaField field : fields) {
if (!field.hasDefaultValue()) {
continue;
}

SchemaOrRef fieldSchema = field.getSchemaOrRef();
boolean wasDefinedBefore = fieldSchema.isFullyDefined();
if (!wasDefinedBefore) {
fieldsWithUnparsedDefaults.add(field);
} else if (field.getDefaultValue() instanceof AvscUnparsedLiteral) {
AvscParseUtil.lateParseFieldDefault(field, this);
}
}

}
}

private void resolveReferences(AvroSchema schema) {
Expand All @@ -188,23 +221,9 @@ private void resolveReferences(AvroSchema schema) {
List<AvroSchemaField> fields = recordSchema.getFields();
for (AvroSchemaField field : fields) {
SchemaOrRef fieldSchema = field.getSchemaOrRef();
boolean hasDefault = field.hasDefaultValue();
boolean wasDefinedBefore = fieldSchema.isFullyDefined();
if (!wasDefinedBefore) {
resolveReferences(fieldSchema);
if (!fieldSchema.isFullyDefined()) {
if (hasDefault) {
fieldsWithUnparsedDefaults.add(field);
}
continue;
}
}
//fully defined if we're here
if (!hasDefault) {
continue;
}
if (field.getDefaultValue() instanceof AvscUnparsedLiteral) {
AvscParseUtil.lateParseFieldDefault(field, this);
}
}
break;
Expand Down
35 changes: 35 additions & 0 deletions parser/src/test/java/com/linkedin/avroutil1/parser/avsc/AvscParserTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import com.linkedin.avroutil1.parser.exceptions.JsonParseException;
import com.linkedin.avroutil1.parser.exceptions.UnresolvedReferenceException;
import com.linkedin.avroutil1.testcommon.TestUtil;
import com.linkedin.avroutil1.writer.avsc.AvscSchemaWriter;
import java.io.IOException;
import java.util.stream.Collectors;
import org.apache.avro.Schema;
Expand Down Expand Up @@ -688,6 +689,40 @@ public void testSomething() throws Exception {
Assert.assertEquals(recordParseResult.getIssues().size(), 1);
}

@Test
public void testRecursiveReferenceUnionWithDefault() throws Exception {
String recordAvsc = TestUtil.load("schemas/RecursiveRefUnion.avsc");
AvscParser avscParser = new AvscParser();

AvscParseResult recordParseResult = avscParser.parse(recordAvsc);
AvroRecordSchema topLevelSchema = (AvroRecordSchema) recordParseResult.getTopLevelSchema();

// Tests we don't have unparsed default values in for of AvscUnparsedLiteral.
new AvscSchemaWriter().writeSingle(topLevelSchema);

Assert.assertFalse(hasUnparsedDefault(topLevelSchema));
Assert.assertEquals(recordParseResult.getIssues().size(), 0);
}

/**
* Recursively goes through all fields and their schemas to check if any field has an unparsed default value
* @param schema
* @return
*/
private boolean hasUnparsedDefault(AvroRecordSchema schema) {
for(AvroSchemaField field : schema.getFields()) {
if (field.getDefaultValue() instanceof AvscUnparsedLiteral) {
return true;
}
if (field.getSchema().type() == AvroType.RECORD) {
if (hasUnparsedDefault((AvroRecordSchema) field.getSchema())) {
return true;
}
}
}
return false;
}

private Schema vanillaParse(String resource) throws Exception {
String avsc = TestUtil.load(resource);
Schema.Parser vanillaParser = new Schema.Parser();
Expand Down
89 changes: 89 additions & 0 deletions parser/src/test/resources/schemas/RecursiveRefUnion.avsc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
{
"type": "record",
"name": "RecursiveRefUnion",
"namespace": "com.test",
"doc": "Top record",
"fields": [
{
"name": "innerField2",
"type": [
"null",
{
"type": "record",
"name": "NestedType2",
"doc": "",
"fields": [
{
"name": "innerField3",
"type": {
"type": "record",
"name": "NestedType3",
"fields": [
{
"name": "innerField4",
"type": [
"null",
"NestedType2"
],
"doc": "",
"default": null
},
{
"name": "innerField5",
"type": {
"type": "record",
"name": "NestedType4",
"fields": [
{
"name": "innerField6",
"type": [
"null",
"NestedType2"
],
"doc": "!!!!",
"default": null
},
{
"name": "innerField7",
"type": [
"null",
{
"type": "record",
"name": "NestedType5",
"doc": "",
"fields": [
{
"name": "field",
"type": "string"
}
]
}
],
"doc": "",
"default": null
}
]
},
"doc": "."
},
{
"name": "innerField8",
"type": [
"null",
"NestedType5"
],
"doc": "!!!!",
"default": null
}
]
},
"doc": "."
}
]
}
],
"doc": "",
"default": null
}
]
}
Loading