embulk-input-mysql 0.7.2 → 0.7.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +52 -2
- data/classpath/embulk-input-jdbc-0.7.3.jar +0 -0
- data/classpath/embulk-input-mysql-0.7.3.jar +0 -0
- data/src/main/java/org/embulk/input/mysql/MySQLInputConnection.java +15 -3
- metadata +8 -8
- data/classpath/embulk-input-jdbc-0.7.2.jar +0 -0
- data/classpath/embulk-input-mysql-0.7.2.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: df7e77fb9710e59a758f75ecb6a799d1c70f138a
|
4
|
+
data.tar.gz: f0ca6f0272e329eefbf63730cd70060b1aa4f6b0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a2d992492d49c4c0bcbc58424a130e85514fc9e79cd2ac9d9180cdc0b09ef8c341cd7b1d4d57cec4af41399eec54ff39477938a7a10bcf40c499396cc081a4c7
|
7
|
+
data.tar.gz: ab3fc7378700e980c9ccf4cfcb3a907abfba3ae17873fb0c572e6682e3e807ce088e96a604caa31ef76226dbbf5512499b83ccc457833d2ac4b2230096d880f2
|
data/README.md
CHANGED
@@ -18,9 +18,9 @@ MySQL input plugins for Embulk loads records from MySQL.
|
|
18
18
|
- **query**: SQL to run (string)
|
19
19
|
- If **query** is not set,
|
20
20
|
- **table**: destination table name (string, required)
|
21
|
-
- **select**:
|
21
|
+
- **select**: expression of select (e.g. `id, created_at`) (string, default: "*")
|
22
22
|
- **where**: WHERE condition to filter the rows (string, default: no-condition)
|
23
|
-
- **order_by**:
|
23
|
+
- **order_by**: expression of ORDER BY to sort rows (e.g. `created_at DESC, id ASC`) (string, default: not sorted)
|
24
24
|
- **fetch_rows**: number of rows to fetch one time (integer, default: 10000)
|
25
25
|
- If this value is set to > 1:
|
26
26
|
- It uses a server-side prepared statement and fetches rows by chunks.
|
@@ -34,6 +34,9 @@ MySQL input plugins for Embulk loads records from MySQL.
|
|
34
34
|
- **connect_timeout**: timeout for socket connect. 0 means no timeout. (integer (seconds), default: 300)
|
35
35
|
- **socket_timeout**: timeout on network socket operations. 0 means no timeout. (integer (seconds), default: 1800)
|
36
36
|
- **options**: extra JDBC properties (hash, default: {})
|
37
|
+
- **incremental**: if true, enables incremental loading. See next section for details (boolean, default: false)
|
38
|
+
- **incremental_columns**: column names for incremental loading (array of strings, default: use primary keys)
|
39
|
+
- **last_record**: values of the last record for incremental loading (array of objects, default: load all records)
|
37
40
|
- **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`)
|
38
41
|
- **column_options**: advanced: a key-value pairs where key is a column name and value is options for the column.
|
39
42
|
- **value_type**: embulk get values from database as this value_type. Typically, the value_type determines `getXXX` method of `java.sql.PreparedStatement`.
|
@@ -46,6 +49,43 @@ MySQL input plugins for Embulk loads records from MySQL.
|
|
46
49
|
(string, value of default_timezone option is used by default)
|
47
50
|
- **after_select**: if set, this SQL will be executed after the SELECT query in the same transaction.
|
48
51
|
|
52
|
+
|
53
|
+
## Incremental loading
|
54
|
+
|
55
|
+
Incremental loading uses monotonically increasing unique columns (such as AUTO_INCREMENT column) to load records inserted (or updated) after last execution.
|
56
|
+
|
57
|
+
First, if `incremental: true` is set, this plugin loads all records with additional ORDER BY. For example, if `incremental_columns: [updated_at, id]` option is set, query will be as following:
|
58
|
+
|
59
|
+
```
|
60
|
+
SELECT * FROM (
|
61
|
+
...original query is here...
|
62
|
+
)
|
63
|
+
ORDER BY updated_at, id
|
64
|
+
```
|
65
|
+
|
66
|
+
When bulk data loading finishes successfully, it outputs `last_record: ` paramater as config-diff so that next execution uses it.
|
67
|
+
|
68
|
+
At the next execution, when `last_record: ` is also set, this plugin generates additional WHERE conditions to load records larger than the last record. For example, if `last_record: ["2017-01-01 00:32:12", 5291]` is set,
|
69
|
+
|
70
|
+
```
|
71
|
+
SELECT * FROM (
|
72
|
+
...original query is here...
|
73
|
+
)
|
74
|
+
WHERE created_at > '2017-01-01 00:32:12' OR (created_at = '2017-01-01 00:32:12' AND id > 5291)
|
75
|
+
ORDER BY updated_at, id
|
76
|
+
```
|
77
|
+
|
78
|
+
Then, it updates `last_record: ` so that next execution uses the updated last_record.
|
79
|
+
|
80
|
+
**IMPORTANT**: If you set `incremental_columns: ` option, make sure that there is an index on the columns to avoid full table scan. For this example, following index should be created:
|
81
|
+
|
82
|
+
```
|
83
|
+
CREATE INDEX embulk_incremental_loading_index ON table (updated_at, id);
|
84
|
+
```
|
85
|
+
|
86
|
+
Recommended usage is to leave `incremental_columns` unset and let this plugin automatically finds an AUTO_INCREMENT primary key. Currently, only strings and integers are supported as incremental_columns.
|
87
|
+
|
88
|
+
|
49
89
|
## Example
|
50
90
|
|
51
91
|
```yaml
|
@@ -58,6 +98,16 @@ in:
|
|
58
98
|
table: my_table
|
59
99
|
select: "col1, col2, col3"
|
60
100
|
where: "col4 != 'a'"
|
101
|
+
order_by: "col1 DESC"
|
102
|
+
```
|
103
|
+
|
104
|
+
This configuration will generate following SQL:
|
105
|
+
|
106
|
+
```
|
107
|
+
SELECT col1, col2, col3
|
108
|
+
FROM `my_table`
|
109
|
+
WHERE col4 != 'a'
|
110
|
+
ORDER BY col1 DESC
|
61
111
|
```
|
62
112
|
|
63
113
|
If you need a complex SQL,
|
Binary file
|
Binary file
|
@@ -1,10 +1,13 @@
|
|
1
1
|
package org.embulk.input.mysql;
|
2
2
|
|
3
|
+
import java.util.List;
|
3
4
|
import java.sql.Connection;
|
4
5
|
import java.sql.PreparedStatement;
|
5
6
|
import java.sql.SQLException;
|
6
7
|
import java.sql.ResultSet;
|
7
8
|
import org.embulk.input.jdbc.JdbcInputConnection;
|
9
|
+
import org.embulk.input.jdbc.JdbcLiteral;
|
10
|
+
import org.embulk.input.jdbc.getter.ColumnGetter;
|
8
11
|
|
9
12
|
public class MySQLInputConnection
|
10
13
|
extends JdbcInputConnection
|
@@ -16,10 +19,19 @@ public class MySQLInputConnection
|
|
16
19
|
}
|
17
20
|
|
18
21
|
@Override
|
19
|
-
protected BatchSelect newBatchSelect(
|
22
|
+
protected BatchSelect newBatchSelect(PreparedQuery preparedQuery,
|
23
|
+
List<ColumnGetter> getters,
|
24
|
+
int fetchRows, int queryTimeout) throws SQLException
|
20
25
|
{
|
21
|
-
|
22
|
-
|
26
|
+
String query = preparedQuery.getQuery();
|
27
|
+
List<JdbcLiteral> params = preparedQuery.getParameters();
|
28
|
+
|
29
|
+
logger.info("SQL: " + query);
|
30
|
+
PreparedStatement stmt = connection.prepareStatement(query, ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY); // TYPE_FORWARD_ONLY and CONCUR_READ_ONLY are default
|
31
|
+
if (!params.isEmpty()) {
|
32
|
+
logger.info("Parameters: {}", params);
|
33
|
+
prepareParameters(stmt, getters, params);
|
34
|
+
}
|
23
35
|
if (fetchRows == 1) {
|
24
36
|
// See MySQLInputPlugin.newConnection doesn't set useCursorFetch=true when fetchRows=1
|
25
37
|
// MySQL Connector/J keeps the connection opened and process rows one by one with Integer.MIN_VALUE.
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: embulk-input-mysql
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.7.
|
4
|
+
version: 0.7.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Sadayuki Furuhashi
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-
|
11
|
+
date: 2016-08-26 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Selects records from a table.
|
14
14
|
email:
|
@@ -19,6 +19,9 @@ extra_rdoc_files: []
|
|
19
19
|
files:
|
20
20
|
- README.md
|
21
21
|
- build.gradle
|
22
|
+
- classpath/embulk-input-jdbc-0.7.3.jar
|
23
|
+
- classpath/embulk-input-mysql-0.7.3.jar
|
24
|
+
- classpath/mysql-connector-java-5.1.34.jar
|
22
25
|
- lib/embulk/input/mysql.rb
|
23
26
|
- src/main/java/org/embulk/input/MySQLInputPlugin.java
|
24
27
|
- src/main/java/org/embulk/input/mysql/MySQLInputConnection.java
|
@@ -33,9 +36,6 @@ files:
|
|
33
36
|
- src/test/resources/mysql/yml/input-valuetype-decimal.yml
|
34
37
|
- src/test/resources/mysql/yml/input-valuetype-string.yml
|
35
38
|
- src/test/resources/mysql/yml/input.yml
|
36
|
-
- classpath/embulk-input-jdbc-0.7.2.jar
|
37
|
-
- classpath/embulk-input-mysql-0.7.2.jar
|
38
|
-
- classpath/mysql-connector-java-5.1.34.jar
|
39
39
|
homepage: https://github.com/embulk/embulk-input-jdbc
|
40
40
|
licenses:
|
41
41
|
- Apache 2.0
|
@@ -46,17 +46,17 @@ require_paths:
|
|
46
46
|
- lib
|
47
47
|
required_ruby_version: !ruby/object:Gem::Requirement
|
48
48
|
requirements:
|
49
|
-
- -
|
49
|
+
- - ">="
|
50
50
|
- !ruby/object:Gem::Version
|
51
51
|
version: '0'
|
52
52
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
53
53
|
requirements:
|
54
|
-
- -
|
54
|
+
- - ">="
|
55
55
|
- !ruby/object:Gem::Version
|
56
56
|
version: '0'
|
57
57
|
requirements: []
|
58
58
|
rubyforge_project:
|
59
|
-
rubygems_version: 2.
|
59
|
+
rubygems_version: 2.4.8
|
60
60
|
signing_key:
|
61
61
|
specification_version: 4
|
62
62
|
summary: JDBC input plugin for Embulk
|
Binary file
|
Binary file
|