You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2019/10/28 16:09:24 UTC

[GitHub] [incubator-iceberg] Fokko opened a new pull request #587: Improve docs on converting the Avro schema

Fokko opened a new pull request #587: Improve docs on converting the Avro schema
URL: https://github.com/apache/incubator-iceberg/pull/587
 
 
   Small improvements on:
   
   - Add Apache prefix at some places
   - Fix the import of the Apache Avro Parse
   - Add example on how to add the spark-runtime-jars to the --jars
   
   The `AvroSchemaUtil` wants to have the shaded Avro schema:
   ```
   C02VF05JHV2T:incubator-iceberg fdriesprong$ spark-shell --jars runtime/build/libs/iceberg-spark-runtime-fa64197.jar 
   Welcome to
         ____              __
        / __/__  ___ _____/ /__
       _\ \/ _ \/ _ `/ __/  '_/
      /___/ .__/\_,_/_/ /_/\_\   version 2.4.4
         /_/
            
   Using Scala version 2.11.12 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_192)
   Type in expressions to have them evaluated.
   Type :help for more information.
   
   scala> import org.apache.iceberg.avro.AvroSchemaUtil
   import org.apache.iceberg.avro.AvroSchemaUtil
   
   scala> import scala.io.Source
   import scala.io.Source
   
   scala> import org.apache.avro.Schema.Parser
   import org.apache.avro.Schema.Parser
   
   scala> val strSchema = Source.fromFile("/Users/fdriesprong/Desktop/fpa-aws-poc/acid-fs/data/beers.avsc").getLines.mkString
   strSchema: String = {  "type" : "record",  "name" : "topLevelRecord",  "fields" : [ {    "name" : "seq",    "type" : [ "string", "null" ]  }, {    "name" : "abv",    "type" : [ "string", "null" ]  }, {    "name" : "ibu",    "type" : [ "string", "null" ]  }, {    "name" : "id",    "type" : [ "string", "null" ]  }, {    "name" : "name",    "type" : [ "string", "null" ]  }, {    "name" : "style",    "type" : [ "string", "null" ]  }, {    "name" : "brewery_id",    "type" : [ "string", "null" ]  }, {    "name" : "ounces",    "type" : [ "string", "null" ]  } ]}
   
   scala> val avroSchema = new Parser().parse(strSchema)
   avroSchema: org.apache.avro.Schema = {"type":"record","name":"topLevelRecord","fields":[{"name":"seq","type":["string","null"]},{"name":"abv","type":["string","null"]},{"name":"ibu","type":["string","null"]},{"name":"id","type":["string","null"]},{"name":"name","type":["string","null"]},{"name":"style","type":["string","null"]},{"name":"brewery_id","type":["string","null"]},{"name":"ounces","type":["string","null"]}]}
   
   scala> val schema = AvroSchemaUtil.convert(avroSchema)
   <console>:28: error: overloaded method value convert with alternatives:
     (x$1: org.apache.iceberg.shaded.org.apache.avro.Schema)org.apache.iceberg.types.Type <and>
     (x$1: org.apache.iceberg.types.Type)org.apache.iceberg.shaded.org.apache.avro.Schema
    cannot be applied to (org.apache.avro.Schema)
          val schema = AvroSchemaUtil.convert(avroSchema)
   ```
   
   Passing the shaded version is bueno:
   ```
   C02VF05JHV2T:incubator-iceberg fdriesprong$ spark-shell --jars runtime/build/libs/iceberg-spark-runtime-fa64197.jar 
   Welcome to
         ____              __
        / __/__  ___ _____/ /__
       _\ \/ _ \/ _ `/ __/  '_/
      /___/ .__/\_,_/_/ /_/\_\   version 2.4.4
         /_/
            
   Using Scala version 2.11.12 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_192)
   Type in expressions to have them evaluated.
   Type :help for more information.
   
   scala> import scala.io.Source
   import scala.io.Source
   
   scala> import org.apache.iceberg.shaded.org.apache.avro.Schema.Parser
   import org.apache.iceberg.shaded.org.apache.avro.Schema.Parser
   
   scala> import org.apache.iceberg.avro.AvroSchemaUtil
   import org.apache.iceberg.avro.AvroSchemaUtil
   
   scala> val strSchema = Source.fromFile("/Users/fdriesprong/Desktop/fpa-aws-poc/acid-fs/data/beers.avsc").getLines.mkString
   strSchema: String = {  "type" : "record",  "name" : "topLevelRecord",  "fields" : [ {    "name" : "seq",    "type" : [ "string", "null" ]  }, {    "name" : "abv",    "type" : [ "string", "null" ]  }, {    "name" : "ibu",    "type" : [ "string", "null" ]  }, {    "name" : "id",    "type" : [ "string", "null" ]  }, {    "name" : "name",    "type" : [ "string", "null" ]  }, {    "name" : "style",    "type" : [ "string", "null" ]  }, {    "name" : "brewery_id",    "type" : [ "string", "null" ]  }, {    "name" : "ounces",    "type" : [ "string", "null" ]  } ]}
   
   scala> val avroSchema = new Parser().parse(strSchema)
   avroSchema: org.apache.iceberg.shaded.org.apache.avro.Schema = {"type":"record","name":"topLevelRecord","fields":[{"name":"seq","type":["string","null"]},{"name":"abv","type":["string","null"]},{"name":"ibu","type":["string","null"]},{"name":"id","type":["string","null"]},{"name":"name","type":["string","null"]},{"name":"style","type":["string","null"]},{"name":"brewery_id","type":["string","null"]},{"name":"ounces","type":["string","null"]}]}
   
   scala> val schema = AvroSchemaUtil.convert(avroSchema)
   schema: org.apache.iceberg.types.Type = struct<0: seq: optional string, 1: abv: optional string, 2: ibu: optional string, 3: id: optional string, 4: name: optional string, 5: style: optional string, 6: brewery_id: optional string, 7: ounces: optional string>
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org