embulk-input-redshift 0.5.0 → 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +90 -90
- data/build.gradle +6 -6
- data/classpath/{embulk-input-jdbc-0.5.0.jar → embulk-input-jdbc-0.6.0.jar} +0 -0
- data/classpath/{embulk-input-postgresql-0.5.0.jar → embulk-input-postgresql-0.6.0.jar} +0 -0
- data/classpath/embulk-input-redshift-0.6.0.jar +0 -0
- data/lib/embulk/input/redshift.rb +3 -3
- data/src/main/java/org/embulk/input/RedshiftInputPlugin.java +92 -92
- metadata +5 -5
- data/classpath/embulk-input-redshift-0.5.0.jar +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8e1f3155f45b656d818c81687eb2cb4d5ce15157
|
4
|
+
data.tar.gz: 7313ec7d41697bc3750df120b6dff3d9a59c88a3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7d1ccf37c07ffe5eb82e82e9ca45a7a721e45a27c172b1f1ee16bea565a5d55dc10555871e9aedb20c8afc782a5c09a79e65b428d7edcbe9017dab44ab0a7bae
|
7
|
+
data.tar.gz: 16ac5d172bb06a0f134d9108b0cf5f1bcf871ed0ed2a34691b9e89a1801895638bf6005860b4cef18a5338349d61437de5fc2e8e1df20d2af1dd4a2192ab927d
|
data/README.md
CHANGED
@@ -1,90 +1,90 @@
|
|
1
|
-
# Redshift input plugins for Embulk
|
2
|
-
|
3
|
-
Redshift input plugins for Embulk loads records from Redshift.
|
4
|
-
|
5
|
-
## Overview
|
6
|
-
|
7
|
-
* **Plugin type**: input
|
8
|
-
* **Resume supported**: yes
|
9
|
-
|
10
|
-
## Configuration
|
11
|
-
|
12
|
-
- **host**: database host name (string, required)
|
13
|
-
- **port**: database port number (integer, 5439)
|
14
|
-
- **user**: database login user name (string, required)
|
15
|
-
- **password**: database login password (string, default: "")
|
16
|
-
- **database**: destination database name (string, required)
|
17
|
-
- **schema**: destination schema name (string, default: "public")
|
18
|
-
- **where**: WHERE condition to filter the rows (string, default: no-condition)
|
19
|
-
- **fetch_rows**: number of rows to fetch one time (used for java.sql.Statement#setFetchSize) (integer, default: 10000)
|
20
|
-
- **options**: extra JDBC properties (hash, default: {})
|
21
|
-
- If you write SQL directly,
|
22
|
-
- **query**: SQL to run (string)
|
23
|
-
- If **query** is not set,
|
24
|
-
- **table**: destination table name (string, required)
|
25
|
-
- **select**: comma-separated list of columns to select (string, default: "*")
|
26
|
-
- **where**: WHERE condition to filter the rows (string, default: no-condition)
|
27
|
-
- **default_timezone**: If the sql type of a column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted int this default_timezone. You can overwrite timezone for each columns using column_options option. (string, default: `UTC`)
|
28
|
-
- **column_options**: advanced: a key-value pairs where key is a column name and value is options for the column.
|
29
|
-
- **value_type**: embulk get values from database as this value_type. Typically, the value_type determines `getXXX` method of `java.sql.PreparedStatement`.
|
30
|
-
(string, default: depends on the sql type of the column. Available values options are: `long`, `double`, `float`, `decimal`, `boolean`, `string`, `date`, `time`, `timestamp`)
|
31
|
-
- **type**: Column values are converted to this embulk type.
|
32
|
-
Available values options are: `boolean`, `long`, `double`, `string`, `timestamp`).
|
33
|
-
By default, the embulk type is determined according to the sql type of the column (or value_type if specified).
|
34
|
-
- **timestamp_format**: If the sql type of the column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted by this timestamp_format. And if the embulk type is `timestamp`, this timestamp_format
|
35
|
-
- **timezone**: If the sql type of the column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted in this timezone.
|
36
|
-
(string, value of default_timezone option is used by default)
|
37
|
-
|
38
|
-
## Example
|
39
|
-
|
40
|
-
```yaml
|
41
|
-
in:
|
42
|
-
type: redshift
|
43
|
-
host: localhost
|
44
|
-
user: myuser
|
45
|
-
password: ""
|
46
|
-
database: my_database
|
47
|
-
table: my_table
|
48
|
-
select: "col1, col2, col3"
|
49
|
-
where: "col4 != 'a'"
|
50
|
-
```
|
51
|
-
|
52
|
-
If you need a complex SQL,
|
53
|
-
|
54
|
-
```yaml
|
55
|
-
in:
|
56
|
-
type: redshift
|
57
|
-
host: localhost
|
58
|
-
user: myuser
|
59
|
-
password: ""
|
60
|
-
database: my_database
|
61
|
-
query: |
|
62
|
-
SELECT t1.id, t1.name, t2.id AS t2_id, t2.name AS t2_name
|
63
|
-
FROM table1 AS t1
|
64
|
-
LEFT JOIN table2 AS t2
|
65
|
-
ON t1.id = t2.t1_id
|
66
|
-
```
|
67
|
-
|
68
|
-
Advanced configuration:
|
69
|
-
|
70
|
-
```yaml
|
71
|
-
in:
|
72
|
-
type: redshift
|
73
|
-
host: localhost
|
74
|
-
user: myuser
|
75
|
-
password: ""
|
76
|
-
database: my_database
|
77
|
-
table: "my_table"
|
78
|
-
select: "col1, col2, col3"
|
79
|
-
where: "col4 != 'a'"
|
80
|
-
column_options:
|
81
|
-
col1: {type: long}
|
82
|
-
col3: {type: string, timestamp_format: "%Y/%m/%d", timezone: "+0900"}
|
83
|
-
|
84
|
-
```
|
85
|
-
|
86
|
-
## Build
|
87
|
-
|
88
|
-
```
|
89
|
-
$ ./gradlew gem
|
90
|
-
```
|
1
|
+
# Redshift input plugins for Embulk
|
2
|
+
|
3
|
+
Redshift input plugins for Embulk loads records from Redshift.
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: input
|
8
|
+
* **Resume supported**: yes
|
9
|
+
|
10
|
+
## Configuration
|
11
|
+
|
12
|
+
- **host**: database host name (string, required)
|
13
|
+
- **port**: database port number (integer, 5439)
|
14
|
+
- **user**: database login user name (string, required)
|
15
|
+
- **password**: database login password (string, default: "")
|
16
|
+
- **database**: destination database name (string, required)
|
17
|
+
- **schema**: destination schema name (string, default: "public")
|
18
|
+
- **where**: WHERE condition to filter the rows (string, default: no-condition)
|
19
|
+
- **fetch_rows**: number of rows to fetch one time (used for java.sql.Statement#setFetchSize) (integer, default: 10000)
|
20
|
+
- **options**: extra JDBC properties (hash, default: {})
|
21
|
+
- If you write SQL directly,
|
22
|
+
- **query**: SQL to run (string)
|
23
|
+
- If **query** is not set,
|
24
|
+
- **table**: destination table name (string, required)
|
25
|
+
- **select**: comma-separated list of columns to select (string, default: "*")
|
26
|
+
- **where**: WHERE condition to filter the rows (string, default: no-condition)
|
27
|
+
- **default_timezone**: If the sql type of a column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted int this default_timezone. You can overwrite timezone for each columns using column_options option. (string, default: `UTC`)
|
28
|
+
- **column_options**: advanced: a key-value pairs where key is a column name and value is options for the column.
|
29
|
+
- **value_type**: embulk get values from database as this value_type. Typically, the value_type determines `getXXX` method of `java.sql.PreparedStatement`.
|
30
|
+
(string, default: depends on the sql type of the column. Available values options are: `long`, `double`, `float`, `decimal`, `boolean`, `string`, `date`, `time`, `timestamp`)
|
31
|
+
- **type**: Column values are converted to this embulk type.
|
32
|
+
Available values options are: `boolean`, `long`, `double`, `string`, `timestamp`).
|
33
|
+
By default, the embulk type is determined according to the sql type of the column (or value_type if specified).
|
34
|
+
- **timestamp_format**: If the sql type of the column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted by this timestamp_format. And if the embulk type is `timestamp`, this timestamp_format may be used in the output plugin. For example, stdout plugin use the timestamp_format, but *csv formatter plugin doesn't use*. (string, default : `%Y-%m-%d` for `date`, `%H:%M:%S` for `time`, `%Y-%m-%d %H:%M:%S` for `timestamp`)
|
35
|
+
- **timezone**: If the sql type of the column is `date`/`time`/`datetime` and the embulk type is `string`, column values are formatted in this timezone.
|
36
|
+
(string, value of default_timezone option is used by default)
|
37
|
+
|
38
|
+
## Example
|
39
|
+
|
40
|
+
```yaml
|
41
|
+
in:
|
42
|
+
type: redshift
|
43
|
+
host: localhost
|
44
|
+
user: myuser
|
45
|
+
password: ""
|
46
|
+
database: my_database
|
47
|
+
table: my_table
|
48
|
+
select: "col1, col2, col3"
|
49
|
+
where: "col4 != 'a'"
|
50
|
+
```
|
51
|
+
|
52
|
+
If you need a complex SQL,
|
53
|
+
|
54
|
+
```yaml
|
55
|
+
in:
|
56
|
+
type: redshift
|
57
|
+
host: localhost
|
58
|
+
user: myuser
|
59
|
+
password: ""
|
60
|
+
database: my_database
|
61
|
+
query: |
|
62
|
+
SELECT t1.id, t1.name, t2.id AS t2_id, t2.name AS t2_name
|
63
|
+
FROM table1 AS t1
|
64
|
+
LEFT JOIN table2 AS t2
|
65
|
+
ON t1.id = t2.t1_id
|
66
|
+
```
|
67
|
+
|
68
|
+
Advanced configuration:
|
69
|
+
|
70
|
+
```yaml
|
71
|
+
in:
|
72
|
+
type: redshift
|
73
|
+
host: localhost
|
74
|
+
user: myuser
|
75
|
+
password: ""
|
76
|
+
database: my_database
|
77
|
+
table: "my_table"
|
78
|
+
select: "col1, col2, col3"
|
79
|
+
where: "col4 != 'a'"
|
80
|
+
column_options:
|
81
|
+
col1: {type: long}
|
82
|
+
col3: {type: string, timestamp_format: "%Y/%m/%d", timezone: "+0900"}
|
83
|
+
|
84
|
+
```
|
85
|
+
|
86
|
+
## Build
|
87
|
+
|
88
|
+
```
|
89
|
+
$ ./gradlew gem
|
90
|
+
```
|
data/build.gradle
CHANGED
@@ -1,6 +1,6 @@
|
|
1
|
-
dependencies {
|
2
|
-
compile project(':embulk-input-jdbc')
|
3
|
-
compile project(':embulk-input-postgresql')
|
4
|
-
|
5
|
-
testCompile project(':embulk-input-jdbc').sourceSets.test.output
|
6
|
-
}
|
1
|
+
dependencies {
|
2
|
+
compile project(':embulk-input-jdbc')
|
3
|
+
compile project(':embulk-input-postgresql')
|
4
|
+
|
5
|
+
testCompile project(':embulk-input-jdbc').sourceSets.test.output
|
6
|
+
}
|
Binary file
|
Binary file
|
Binary file
|
@@ -1,3 +1,3 @@
|
|
1
|
-
Embulk::JavaPlugin.register_input(
|
2
|
-
:redshift, "org.embulk.input.RedshiftInputPlugin",
|
3
|
-
File.expand_path('../../../../classpath', __FILE__))
|
1
|
+
Embulk::JavaPlugin.register_input(
|
2
|
+
:redshift, "org.embulk.input.RedshiftInputPlugin",
|
3
|
+
File.expand_path('../../../../classpath', __FILE__))
|
@@ -1,92 +1,92 @@
|
|
1
|
-
package org.embulk.input;
|
2
|
-
|
3
|
-
import java.util.Properties;
|
4
|
-
import java.sql.Connection;
|
5
|
-
import java.sql.Driver;
|
6
|
-
import java.sql.SQLException;
|
7
|
-
import com.google.common.base.Throwables;
|
8
|
-
import org.embulk.config.Config;
|
9
|
-
import org.embulk.config.ConfigDefault;
|
10
|
-
import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
|
11
|
-
import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
|
12
|
-
import org.embulk.input.postgresql.PostgreSQLInputConnection;
|
13
|
-
|
14
|
-
public class RedshiftInputPlugin
|
15
|
-
extends AbstractJdbcInputPlugin
|
16
|
-
{
|
17
|
-
private static final Driver driver = new org.postgresql.Driver();
|
18
|
-
|
19
|
-
public interface RedshiftPluginTask
|
20
|
-
extends PluginTask
|
21
|
-
{
|
22
|
-
@Config("host")
|
23
|
-
public String getHost();
|
24
|
-
|
25
|
-
@Config("port")
|
26
|
-
@ConfigDefault("5439")
|
27
|
-
public int getPort();
|
28
|
-
|
29
|
-
@Config("user")
|
30
|
-
public String getUser();
|
31
|
-
|
32
|
-
@Config("password")
|
33
|
-
@ConfigDefault("\"\"")
|
34
|
-
public String getPassword();
|
35
|
-
|
36
|
-
@Config("database")
|
37
|
-
public String getDatabase();
|
38
|
-
|
39
|
-
@Config("schema")
|
40
|
-
@ConfigDefault("\"public\"")
|
41
|
-
public String getSchema();
|
42
|
-
}
|
43
|
-
|
44
|
-
@Override
|
45
|
-
protected Class<? extends PluginTask> getTaskClass()
|
46
|
-
{
|
47
|
-
return RedshiftPluginTask.class;
|
48
|
-
}
|
49
|
-
|
50
|
-
@Override
|
51
|
-
protected PostgreSQLInputConnection newConnection(PluginTask task) throws SQLException
|
52
|
-
{
|
53
|
-
RedshiftPluginTask t = (RedshiftPluginTask) task;
|
54
|
-
|
55
|
-
String url = String.format("jdbc:postgresql://%s:%d/%s",
|
56
|
-
t.getHost(), t.getPort(), t.getDatabase());
|
57
|
-
|
58
|
-
Properties props = new Properties();
|
59
|
-
props.setProperty("user", t.getUser());
|
60
|
-
props.setProperty("password", t.getPassword());
|
61
|
-
props.setProperty("loginTimeout", "300"); // seconds
|
62
|
-
props.setProperty("socketTimeout", "1800"); // seconds
|
63
|
-
|
64
|
-
// Enable keepalive based on tcp_keepalive_time, tcp_keepalive_intvl and tcp_keepalive_probes kernel parameters.
|
65
|
-
// Socket options TCP_KEEPCNT, TCP_KEEPIDLE, and TCP_KEEPINTVL are not configurable.
|
66
|
-
props.setProperty("tcpKeepAlive", "true");
|
67
|
-
|
68
|
-
// TODO
|
69
|
-
//switch t.getSssl() {
|
70
|
-
//when "disable":
|
71
|
-
// break;
|
72
|
-
//when "enable":
|
73
|
-
// props.setProperty("sslfactory", "org.postgresql.ssl.NonValidatingFactory"); // disable server-side validation
|
74
|
-
//when "verify":
|
75
|
-
// props.setProperty("ssl", "true");
|
76
|
-
// break;
|
77
|
-
//}
|
78
|
-
|
79
|
-
props.putAll(t.getOptions());
|
80
|
-
|
81
|
-
Connection con = driver.connect(url, props);
|
82
|
-
try {
|
83
|
-
PostgreSQLInputConnection c = new PostgreSQLInputConnection(con, t.getSchema());
|
84
|
-
con = null;
|
85
|
-
return c;
|
86
|
-
} finally {
|
87
|
-
if (con != null) {
|
88
|
-
con.close();
|
89
|
-
}
|
90
|
-
}
|
91
|
-
}
|
92
|
-
}
|
1
|
+
package org.embulk.input;
|
2
|
+
|
3
|
+
import java.util.Properties;
|
4
|
+
import java.sql.Connection;
|
5
|
+
import java.sql.Driver;
|
6
|
+
import java.sql.SQLException;
|
7
|
+
import com.google.common.base.Throwables;
|
8
|
+
import org.embulk.config.Config;
|
9
|
+
import org.embulk.config.ConfigDefault;
|
10
|
+
import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
|
11
|
+
import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
|
12
|
+
import org.embulk.input.postgresql.PostgreSQLInputConnection;
|
13
|
+
|
14
|
+
public class RedshiftInputPlugin
|
15
|
+
extends AbstractJdbcInputPlugin
|
16
|
+
{
|
17
|
+
private static final Driver driver = new org.postgresql.Driver();
|
18
|
+
|
19
|
+
public interface RedshiftPluginTask
|
20
|
+
extends PluginTask
|
21
|
+
{
|
22
|
+
@Config("host")
|
23
|
+
public String getHost();
|
24
|
+
|
25
|
+
@Config("port")
|
26
|
+
@ConfigDefault("5439")
|
27
|
+
public int getPort();
|
28
|
+
|
29
|
+
@Config("user")
|
30
|
+
public String getUser();
|
31
|
+
|
32
|
+
@Config("password")
|
33
|
+
@ConfigDefault("\"\"")
|
34
|
+
public String getPassword();
|
35
|
+
|
36
|
+
@Config("database")
|
37
|
+
public String getDatabase();
|
38
|
+
|
39
|
+
@Config("schema")
|
40
|
+
@ConfigDefault("\"public\"")
|
41
|
+
public String getSchema();
|
42
|
+
}
|
43
|
+
|
44
|
+
@Override
|
45
|
+
protected Class<? extends PluginTask> getTaskClass()
|
46
|
+
{
|
47
|
+
return RedshiftPluginTask.class;
|
48
|
+
}
|
49
|
+
|
50
|
+
@Override
|
51
|
+
protected PostgreSQLInputConnection newConnection(PluginTask task) throws SQLException
|
52
|
+
{
|
53
|
+
RedshiftPluginTask t = (RedshiftPluginTask) task;
|
54
|
+
|
55
|
+
String url = String.format("jdbc:postgresql://%s:%d/%s",
|
56
|
+
t.getHost(), t.getPort(), t.getDatabase());
|
57
|
+
|
58
|
+
Properties props = new Properties();
|
59
|
+
props.setProperty("user", t.getUser());
|
60
|
+
props.setProperty("password", t.getPassword());
|
61
|
+
props.setProperty("loginTimeout", "300"); // seconds
|
62
|
+
props.setProperty("socketTimeout", "1800"); // seconds
|
63
|
+
|
64
|
+
// Enable keepalive based on tcp_keepalive_time, tcp_keepalive_intvl and tcp_keepalive_probes kernel parameters.
|
65
|
+
// Socket options TCP_KEEPCNT, TCP_KEEPIDLE, and TCP_KEEPINTVL are not configurable.
|
66
|
+
props.setProperty("tcpKeepAlive", "true");
|
67
|
+
|
68
|
+
// TODO
|
69
|
+
//switch t.getSssl() {
|
70
|
+
//when "disable":
|
71
|
+
// break;
|
72
|
+
//when "enable":
|
73
|
+
// props.setProperty("sslfactory", "org.postgresql.ssl.NonValidatingFactory"); // disable server-side validation
|
74
|
+
//when "verify":
|
75
|
+
// props.setProperty("ssl", "true");
|
76
|
+
// break;
|
77
|
+
//}
|
78
|
+
|
79
|
+
props.putAll(t.getOptions());
|
80
|
+
|
81
|
+
Connection con = driver.connect(url, props);
|
82
|
+
try {
|
83
|
+
PostgreSQLInputConnection c = new PostgreSQLInputConnection(con, t.getSchema());
|
84
|
+
con = null;
|
85
|
+
return c;
|
86
|
+
} finally {
|
87
|
+
if (con != null) {
|
88
|
+
con.close();
|
89
|
+
}
|
90
|
+
}
|
91
|
+
}
|
92
|
+
}
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: embulk-input-redshift
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.6.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Sadayuki Furuhashi
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-07-07 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Selects records from a table.
|
14
14
|
email:
|
@@ -21,9 +21,9 @@ files:
|
|
21
21
|
- build.gradle
|
22
22
|
- lib/embulk/input/redshift.rb
|
23
23
|
- src/main/java/org/embulk/input/RedshiftInputPlugin.java
|
24
|
-
- classpath/embulk-input-jdbc-0.
|
25
|
-
- classpath/embulk-input-postgresql-0.
|
26
|
-
- classpath/embulk-input-redshift-0.
|
24
|
+
- classpath/embulk-input-jdbc-0.6.0.jar
|
25
|
+
- classpath/embulk-input-postgresql-0.6.0.jar
|
26
|
+
- classpath/embulk-input-redshift-0.6.0.jar
|
27
27
|
- classpath/jna-4.1.0.jar
|
28
28
|
- classpath/jna-platform-4.1.0.jar
|
29
29
|
- classpath/postgresql-9.4-1200-jdbc41.jar
|
Binary file
|