[
https://issues.apache.org/jira/browse/ASTERIXDB-3529?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Savyasach Reddy Enukonda updated ASTERIXDB-3529:
------------------------------------------------
Description:
[^0001-0000000000000000000.csv]
^Create an external dataset using the csv files above,^
{code:java}
CREATE TYPE ColumnType AS {
id: bigint,
name: string,
amount: float,
accountNumber: double
};
CREATE EXTERNAL DATASET DatasetCopy(ColumnType) USING hdfs (
("hdfs"="hdfs://localhost:31888"),
("header"="true"),
("escape"="|"),
("input-format"="text-input-format"),
("path"="/asterix/csvfiles"),
("format" = "csv"),
("requireVersionChangeDetection"="false"),
("include"="*.csv")
);{code}
^The query^
{code:java}
SELECT id, name, amount, accountNumber
FROM DatasetCopy d order by d.id;
{code}
^can return either^
{code:java}
{"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
{"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9}
{"id":4,"name":"Mac|,book4","amount":234.5,"accountNumber":567.89} {code}
^or^
{code:java}
{"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
{"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9} {code}
was:
[^0001-0000000000000000000.csv]
^Create an external dataset using the csv files above,^
{code:java}
CREATE TYPE ColumnType AS {
id: bigint,
name: string,
amount: float,
accountNumber: double
};
CREATE EXTERNAL DATASET DatasetCopy(ColumnType) USING HDFS (
("hdfs"="hdfs://localhost:31888"),
("header"="true"),
("escape"="|"),
("input-format"="text-input-format"),
("path"="/asterix/csvfiles"),
("format" = "csv"),
("requireVersionChangeDetection"="false"),
("include"="*.csv")
);{code}
^The query^
{code:java}
SELECT id, name, amount, accountNumber
FROM DatasetCopy d order by d.id;
{code}
^can return either^
{code:java}
{"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
{"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9}
{"id":4,"name":"Mac|,book4","amount":234.5,"accountNumber":567.89} {code}
^or^
{code:java}
{"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
{"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9} {code}
> Missing record when read from HDFS
> ----------------------------------
>
> Key: ASTERIXDB-3529
> URL: https://issues.apache.org/jira/browse/ASTERIXDB-3529
> Project: Apache AsterixDB
> Issue Type: Bug
> Components: EXT - External data
> Reporter: Savyasach Reddy Enukonda
> Priority: Major
> Attachments: 0001-0000000000000000000.csv,
> 0003-0000000000000000000.csv
>
>
> [^0001-0000000000000000000.csv]
> ^Create an external dataset using the csv files above,^
> {code:java}
> CREATE TYPE ColumnType AS {
> id: bigint,
> name: string,
> amount: float,
> accountNumber: double
> };
> CREATE EXTERNAL DATASET DatasetCopy(ColumnType) USING hdfs (
> ("hdfs"="hdfs://localhost:31888"),
> ("header"="true"),
> ("escape"="|"),
> ("input-format"="text-input-format"),
> ("path"="/asterix/csvfiles"),
> ("format" = "csv"),
> ("requireVersionChangeDetection"="false"),
> ("include"="*.csv")
> );{code}
> ^The query^
> {code:java}
> SELECT id, name, amount, accountNumber
> FROM DatasetCopy d order by d.id;
> {code}
> ^can return either^
> {code:java}
> {"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
> {"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9}
> {"id":4,"name":"Mac|,book4","amount":234.5,"accountNumber":567.89} {code}
> ^or^
> {code:java}
> {"id":1,"name":"Macbook1","amount":123.2,"accountNumber":345.34}
> {"id":3,"name":"Macbook3","amount":789.1,"accountNumber":678.9} {code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
