embulk-input-mysql 0.7.2 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ce1cc0bda9fc6b7d3274330e039a3cc8eed4bab5
-  data.tar.gz: bbd9954bd61e347fbd46fcad186f301e43bb75e7
+  metadata.gz: df7e77fb9710e59a758f75ecb6a799d1c70f138a
+  data.tar.gz: f0ca6f0272e329eefbf63730cd70060b1aa4f6b0
 SHA512:
-  metadata.gz: 110b37febae29f93ec4eb6e6336428356c1a2108474cb3b62b96e542596cd69fd3b6d2a7bb14c520e98c9fada48b0a23ac954e671912bffc3e403282efa4dfb5
-  data.tar.gz: 24112e432d231826a3adb77963314af742ab7632345cfe8ea1693d04a0b9b7183e099d806176193833f222335c251201d354f9a267a3ae2ce0493d34b1aafcf2
+  metadata.gz: a2d992492d49c4c0bcbc58424a130e85514fc9e79cd2ac9d9180cdc0b09ef8c341cd7b1d4d57cec4af41399eec54ff39477938a7a10bcf40c499396cc081a4c7
+  data.tar.gz: ab3fc7378700e980c9ccf4cfcb3a907abfba3ae17873fb0c572e6682e3e807ce088e96a604caa31ef76226dbbf5512499b83ccc457833d2ac4b2230096d880f2

data/README.md

@@ -18,9 +18,9 @@ MySQL input plugins for Embulk loads records from MySQL.
   - **query**: SQL to run (string)
 - If **query** is not set,
   - **table**: destination table name (string, required)
-  - **select**: comma-separated list of columns to select (string, default: "*")
+  - **select**: expression of select (e.g. `id, created_at`) (string, default: "*")
   - **where**: WHERE condition to filter the rows (string, default: no-condition)
-  - **order_by**: name of the column that rows are sorted by (string, default: not sorted)
+  - **order_by**: expression of ORDER BY to sort rows (e.g. `created_at DESC, id ASC`) (string, default: not sorted)
 - **fetch_rows**: number of rows to fetch one time (integer, default: 10000)
   - If this value is set to > 1:
     - 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.
 - **connect_timeout**: timeout for socket connect. 0 means no timeout. (integer (seconds), default: 300)
 - **socket_timeout**: timeout on network socket operations. 0 means no timeout. (integer (seconds), default: 1800)
 - **options**: extra JDBC properties (hash, default: {})
+- **incremental**: if true, enables incremental loading. See next section for details (boolean, default: false)
+- **incremental_columns**: column names for incremental loading (array of strings, default: use primary keys)
+- **last_record**: values of the last record for incremental loading (array of objects, default: load all records)
 - **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`)
 - **column_options**: advanced: a key-value pairs where key is a column name and value is options for the column.
   - **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.
 (string, value of default_timezone option is used by default)
 - **after_select**: if set, this SQL will be executed after the SELECT query in the same transaction.
 
+
+## Incremental loading
+
+Incremental loading uses monotonically increasing unique columns (such as AUTO_INCREMENT column) to load records inserted (or updated) after last execution.
+
+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:
+
+```
+SELECT * FROM (
+  ...original query is here...
+)
+ORDER BY updated_at, id
+```
+
+When bulk data loading finishes successfully, it outputs `last_record: ` paramater as config-diff so that next execution uses it.
+
+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,
+
+```
+SELECT * FROM (
+  ...original query is here...
+)
+WHERE created_at > '2017-01-01 00:32:12' OR (created_at = '2017-01-01 00:32:12' AND id > 5291)
+ORDER BY updated_at, id
+```
+
+Then, it updates `last_record: ` so that next execution uses the updated last_record.
+
+**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:
+
+```
+CREATE INDEX embulk_incremental_loading_index ON table (updated_at, id);
+```
+
+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.
+
+
 ## Example
 
 ```yaml
@@ -58,6 +98,16 @@ in:
   table: my_table
   select: "col1, col2, col3"
   where: "col4 != 'a'"
+  order_by: "col1 DESC"
+```
+
+This configuration will generate following SQL:
+
+```
+SELECT col1, col2, col3
+FROM `my_table`
+WHERE col4 != 'a'
+ORDER BY col1 DESC
 ```
 
 If you need a complex SQL,

data/src/main/java/org/embulk/input/mysql/MySQLInputConnection.java

@@ -1,10 +1,13 @@
 package org.embulk.input.mysql;
 
+import java.util.List;
 import java.sql.Connection;
 import java.sql.PreparedStatement;
 import java.sql.SQLException;
 import java.sql.ResultSet;
 import org.embulk.input.jdbc.JdbcInputConnection;
+import org.embulk.input.jdbc.JdbcLiteral;
+import org.embulk.input.jdbc.getter.ColumnGetter;
 
 public class MySQLInputConnection
         extends JdbcInputConnection
@@ -16,10 +19,19 @@ public class MySQLInputConnection
     }
 
     @Override
-    protected BatchSelect newBatchSelect(String select, int fetchRows, int queryTimeout) throws SQLException
+    protected BatchSelect newBatchSelect(PreparedQuery preparedQuery,
+            List<ColumnGetter> getters,
+            int fetchRows, int queryTimeout) throws SQLException
     {
-        logger.info("SQL: " + select);
-        PreparedStatement stmt = connection.prepareStatement(select, ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY);  // TYPE_FORWARD_ONLY and CONCUR_READ_ONLY are default
+        String query = preparedQuery.getQuery();
+        List<JdbcLiteral> params = preparedQuery.getParameters();
+
+        logger.info("SQL: " + query);
+        PreparedStatement stmt = connection.prepareStatement(query, ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY);  // TYPE_FORWARD_ONLY and CONCUR_READ_ONLY are default
+        if (!params.isEmpty()) {
+            logger.info("Parameters: {}", params);
+            prepareParameters(stmt, getters, params);
+        }
         if (fetchRows == 1) {
             // See MySQLInputPlugin.newConnection doesn't set useCursorFetch=true when fetchRows=1
             // MySQL Connector/J keeps the connection opened and process rows one by one with Integer.MIN_VALUE.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: embulk-input-mysql
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.7.3
 platform: ruby
 authors:
 - Sadayuki Furuhashi
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2016-06-24 00:00:00.000000000 Z
+date: 2016-08-26 00:00:00.000000000 Z
 dependencies: []
 description: Selects records from a table.
 email:
@@ -19,6 +19,9 @@ extra_rdoc_files: []
 files:
 - README.md
 - build.gradle
+- classpath/embulk-input-jdbc-0.7.3.jar
+- classpath/embulk-input-mysql-0.7.3.jar
+- classpath/mysql-connector-java-5.1.34.jar
 - lib/embulk/input/mysql.rb
 - src/main/java/org/embulk/input/MySQLInputPlugin.java
 - src/main/java/org/embulk/input/mysql/MySQLInputConnection.java
@@ -33,9 +36,6 @@ files:
 - src/test/resources/mysql/yml/input-valuetype-decimal.yml
 - src/test/resources/mysql/yml/input-valuetype-string.yml
 - src/test/resources/mysql/yml/input.yml
-- classpath/embulk-input-jdbc-0.7.2.jar
-- classpath/embulk-input-mysql-0.7.2.jar
-- classpath/mysql-connector-java-5.1.34.jar
 homepage: https://github.com/embulk/embulk-input-jdbc
 licenses:
 - Apache 2.0
@@ -46,17 +46,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.1.9
+rubygems_version: 2.4.8
 signing_key:
 specification_version: 4
 summary: JDBC input plugin for Embulk