embulk-input-oracle 0.7.2 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c21c11eb15503dc7d9b5a9622f624d31c5d61682
-  data.tar.gz: df349b10fe41bdd359ba49c7748f3726cc614516
+  metadata.gz: f54161ba3352344331934d1663a74df34f46e187
+  data.tar.gz: 91252aaba39988bab74ef588e6ca869f07d231ff
 SHA512:
-  metadata.gz: c81d15fbbeb6db3cc7681860c314075aa868290deb6622753ca63a54cec6e18a220a2609b25c8fc3f2baa9d5f776fb98ac2bbb1486362d5f94ee3151664f36cc
-  data.tar.gz: d640fe70107b0a5b218cfc7437c7bc406b300d9f87f3cbdd45788429e229db465a6491a00f6b21311c351ce94ce293734870d0ca50cde447ee34ad9fe17ffaa6
+  metadata.gz: 0a7b17cd0dfdc550f6080ec3a66e5329e3550cfba6ea99a95fb581380fa12bb1bb940391ef923752242e7dca5006145ffd01e4134bf634284ac83e6b2cbc4c14
+  data.tar.gz: 0289d93b1165f39af515bce2fffc443b4378c47f71bb686ab2f0ccff098221a409af6f9ad8f55345f5de7dd20e328405e1b801bdf561ed703235f13f7f865002

data/README.md

@@ -21,13 +21,16 @@ Oracle input plugins for Embulk loads records from Oracle.
   - **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 (used for java.sql.Statement#setFetchSize) (integer, default: 10000)
 - **connect_timeout**: timeout for establishment of a database connection. (integer (seconds), default: 300)
 - **socket_timeout**: timeout for socket read operations. (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`.
@@ -40,6 +43,43 @@ Oracle input plugins for Embulk loads records from Oracle.
 (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 incremental (SEQUENCE) 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 a primary key. Currently, only strings and integers are supported as incremental_columns.
+
+
 ## Example
 
 ```yaml
@@ -53,6 +93,16 @@ 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/OracleInputPlugin.java

@@ -87,7 +87,7 @@ public class OracleInputPlugin
         props.putAll(oracleTask.getOptions());
 
         if (oracleTask.getDriverPath().isPresent()) {
-            loadDriverJar(oracleTask.getDriverPath().get());
+            addDriverJarToClasspath(oracleTask.getDriverPath().get());
         }
 
         try {

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: embulk-input-oracle
 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 +19,8 @@ extra_rdoc_files: []
 files:
 - README.md
 - build.gradle
+- classpath/embulk-input-jdbc-0.7.3.jar
+- classpath/embulk-input-oracle-0.7.3.jar
 - lib/embulk/input/oracle.rb
 - src/main/java/org/embulk/input/OracleInputPlugin.java
 - src/main/java/org/embulk/input/oracle/OracleInputConnection.java
@@ -29,8 +31,6 @@ files:
 - src/test/resources/oracle/yml/input-query-lower.yml
 - src/test/resources/oracle/yml/input-query.yml
 - src/test/resources/oracle/yml/input.yml
-- classpath/embulk-input-jdbc-0.7.2.jar
-- classpath/embulk-input-oracle-0.7.2.jar
 homepage: https://github.com/embulk/embulk-input-jdbc
 licenses:
 - Apache 2.0
@@ -41,17 +41,17 @@ 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