[
https://issues.apache.org/jira/browse/AVRO-2299?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16742948#comment-16742948
]
Rumeshkrishnan commented on AVRO-2299:
--------------------------------------
[~cutting] Nice, the SchemaNormalization will be helpful. But it keeps only
attributes that are relevant to parsing data, which are: type, name, fields,
symbols, items, values, size. I was expecting `default` value along with that.
Example Code:
{code:java}
import scala.collection.JavaConverters._
import org.apache.avro._
import org.apache.avro.Schema.Parser
import scala.util.Try
object Test extends App {
val schemaOne: String =
"""{
| "name": "testSchema",
| "namespace": "com.avro",
| "type": "record",
| "fields": [
| {
| "name": "email",
| "type": "string",
| "doc": "email id",
| "user_field_prop": "xxxxx"
| }
| ],
| "user_schema_prop": "xxxxxx"
|}""".stripMargin
val schemaTwo: String =
"""{
| "name": "testSchema",
| "namespace": "com.avro",
| "type": "record",
| "fields": [
| {
| "name": "email",
| "type": "string",
| "doc": "email id",
| "user_field_prop": "xxxxx"
| },
| {
| "name": "country",
| "type": "string",
| "doc": "country",
| "user_field_prop": "xxxxx",
| "default": "IN"
| }
| ],
| "user_schema_prop": "xxxxxx"
|}""".stripMargin
def getSchema(schemaString: String): Schema = new Parser().parse(schemaString)
def normalize(schema: Schema): Schema =
getSchema(SchemaNormalization.toParsingForm(schema))
// Validator to check full compatibility on two schema versions
val getFullValidator = new
SchemaValidatorBuilder().mutualReadStrategy().validateLatest()
def fullCompatibilityCheck(oldSchema: Schema, newSchema: Schema): Boolean =
Try {
getFullValidator.validate(newSchema, List(oldSchema).asJava)
true
}.toOption.getOrElse(false)
val schema1: Schema = getSchema(schemaOne)
val schema2: Schema = getSchema(schemaTwo)
val normSchema1 = normalize(schema1)
val normSchema2 = normalize(schema2)
val compatibilityResultBeforeNormalization = fullCompatibilityCheck(schema1,
schema2)
val compatibilityResultAfterNormalization =
fullCompatibilityCheck(normSchema1, normSchema2)
// display result
println(compatibilityResultBeforeNormalization)
println(compatibilityResultAfterNormalization)
}{code}
Result :
{code:java}
true
false{code}
When I am trying to do compatibility check before and after normalisation,
results are different due to `default` property missing.
Is it possible to add the parsing logic not strip `default` if exist. ?
> Get Plain Schema
> ----------------
>
> Key: AVRO-2299
> URL: https://issues.apache.org/jira/browse/AVRO-2299
> Project: Apache Avro
> Issue Type: Improvement
> Components: java
> Affects Versions: 1.8.2
> Reporter: Rumeshkrishnan
> Priority: Minor
> Labels: features
> Fix For: 1.9.0, 1.8.3, 1.8.4
>
>
> {panel:title=Avro Schema Reserved Keys:}
> "doc", "fields", "items", "name", "namespace",
> "size", "symbols", "values", "type", "aliases", "default"
> {panel}
> AVRO also supports user defined properties for both Schema and Field.
> Is there way to get the schema with reserved property (key, value)?
> Input Schema:
> {code:java}
> {
> "name": "testSchema",
> "namespace": "com.avro",
> "type": "record",
> "fields": [
> {
> "name": "email",
> "type": "string",
> "doc": "email id",
> "user_field_prop": "xxxxx"
> }
> ],
> "user_schema_prop": "xxxxxx"
> }{code}
> Expected Plain Schema:
> {code:java}
> {
> "name": "testSchema",
> "namespace": "com.avro",
> "type": "record",
> "fields": [
> {
> "name": "email",
> "type": "string",
> "doc": "email id"
> }
> ]
> }
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
