embulk-input-redshift 0.9.2 → 0.9.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f1b87a75bee192f78b6a9c9486811c59ef5f58b3
-  data.tar.gz: c1cf3328329376cc1b5aeb561fb47912f8956c09
+  metadata.gz: 6e8c344685265804a7323eab781eaf7bf87653bf
+  data.tar.gz: 95dd684c86cbc4fd44a10839a1949e7c44245053
 SHA512:
-  metadata.gz: 176fa8df4324c4d527abc80a0c6045f1dd53111ae391015aeb741140e5a69002c10b932d3ae5e1f7a79aa9ae59db830142385371dfca13fb4511eb5b82c7518a
-  data.tar.gz: 912cadb712b4c113e9d6e637098fb442bef885b917169aba0cacf269d342c76c91f6d0fd062e90f2ac7b7e94f70760069fc165fc26e4e39b14ab34a963fdfe89
+  metadata.gz: c18d9405bbfb2609223c193679704bfcf6cfbc594d948603b9609b321a9b06e7710daf0e677287c9f972a1216790de77d6713b5d50158177531e558150762d4a
+  data.tar.gz: 71011ae9e8f7077807a73b3c3d72785c624a4336fae8a5e33e9a2695ea2ba87cd9f71f1ea4a74e549ec32444956ac6e6f49a99e079f9884044d1c2b1750d4397

data/README.md

@@ -23,6 +23,7 @@ Redshift input plugin for Embulk loads records from Redshift.
 - **options**: extra JDBC properties (hash, default: {})
 - If you write SQL directly,
   - **query**: SQL to run (string)
+  - **use_raw_query_with_incremental**: If true, you can write optimized query using prepared statement by yourself. See [Use incremental loading with raw query](#use-incremental-loading-with-raw-query) for more detail (boolean, default: false)
 - If **query** is not set,
   - **table**: destination table name (string, required)
   - **select**: expression of select (e.g. `id, created_at`) (string, default: "*")
@@ -79,6 +80,38 @@ 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 (IDENTITY) primary key. Currently, only strings and integers are supported as incremental_columns.
 
+### Use incremental loading with raw query
+
+**IMPORTANT**: This is an advanced feature and assume you have an enough knowledge about incremental loading using Embulk and this plugin
+
+Normally, you can't write your own query for incremental loading.
+`use_raw_query_with_incremental` option allow you to write raw query for incremental loading. It might be well optimized and faster than SQL statement which is automatically generated by plugin.
+
+Prepared statement starts with `:` is available instead of fixed value.
+`last_record` value is necessary when you use this option.
+Please use prepared statement that is well distinguishable in SQL statement. Using too simple prepared statement like `:a` might cause SQL parse failure.
+
+In the following example, prepared statement `:foo_id` will be replaced with value "1" which is specified in `last_record`.
+
+```yaml
+in:
+  type: redshift
+  query:
+    SELECT
+      foo.id as foo_id, bar.name
+    FROM
+      foo LEFT JOIN bar ON foo.id = bar.id
+    WHERE
+      foo.hoge IS NOT NULL
+      AND foo.id > :foo_id
+    ORDER BY
+      foo.id ASC
+  use_raw_query_with_incremental: true
+  incremental_columns:
+    - foo_id
+  incremental: true
+  last_record: [1]
+```
 
 ## Example
 

data/src/test/java/org/embulk/input/redshift/IncrementalTest.java

@@ -140,4 +140,68 @@ public class IncrementalTest
                 result2.getConfigDiff(),
                 is((ConfigDiff) loadYamlResource(embulk, "timestamptz/expected_2.diff")));
     }
+
+    @Test
+    public void simpleQueryWithPlaceholder() throws Exception
+    {
+        // setup first rows
+        execute(readResource("query/setup.sql"));
+
+        Path out1 = embulk.createTempFile("csv");
+        RunResult result1 = embulk.runInput(
+                baseConfig.merge(loadYamlResource(embulk, "query/config_1.yml")),
+                out1);
+        assertThat(
+                readSortedFile(out1),
+                is(readResource("query/expected_1.csv")));
+        assertThat(
+                result1.getConfigDiff(),
+                is((ConfigDiff) loadYamlResource(embulk, "query/expected_1.diff")));
+
+        // insert more rows
+        execute(readResource("query/insert_more.sql"));
+
+        Path out2 = embulk.createTempFile("csv");
+        RunResult result2 = embulk.runInput(
+                baseConfig.merge(loadYamlResource(embulk, "query/config_2.yml")),
+                out2);
+        assertThat(
+                readSortedFile(out2),
+                is(readResource("query/expected_2.csv")));
+        assertThat(
+                result2.getConfigDiff(),
+                is((ConfigDiff) loadYamlResource(embulk, "query/expected_2.diff")));
+    }
+
+    @Test
+    public void simpleQueryWithPlaceholderAndMultiColumns() throws Exception
+    {
+        // setup first rows
+        execute(readResource("query/setup.sql"));
+
+        Path out1 = embulk.createTempFile("csv");
+        RunResult result1 = embulk.runInput(
+                baseConfig.merge(loadYamlResource(embulk, "query/multi_columns_config_1.yml")),
+                out1);
+        assertThat(
+                readSortedFile(out1),
+                is(readResource("query/multi_columns_expected_1.csv")));
+        assertThat(
+                result1.getConfigDiff(),
+                is((ConfigDiff) loadYamlResource(embulk, "query/multi_columns_expected_1.diff")));
+
+        // insert more rows
+        execute(readResource("query/insert_more.sql"));
+
+        Path out2 = embulk.createTempFile("csv");
+        RunResult result2 = embulk.runInput(
+                baseConfig.merge(loadYamlResource(embulk, "query/multi_columns_config_2.yml")),
+                out2);
+        assertThat(
+                readSortedFile(out2),
+                is(readResource("query/multi_columns_expected_2.csv")));
+        assertThat(
+                result2.getConfigDiff(),
+                is((ConfigDiff) loadYamlResource(embulk, "query/multi_columns_expected_2.diff")));
+    }
 }

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/config_1.yml

@@ -0,0 +1,14 @@
+last_record: [0]
+incremental: true
+incremental_columns: [num]
+use_raw_query_with_incremental: true
+query: |
+  SELECT
+    num,note
+  FROM
+    query_load
+  WHERE
+    num IS NOT NULL
+    AND num > :num
+  ORDER BY
+    num ASC

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/config_2.yml

@@ -0,0 +1,14 @@
+last_record: [4]
+incremental: true
+incremental_columns: [num]
+use_raw_query_with_incremental: true
+query: |
+  SELECT
+    num,note
+  FROM
+    query_load
+  WHERE
+    num IS NOT NULL
+    AND num > :num
+  ORDER BY
+    num ASC

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_1.csv

@@ -0,0 +1,4 @@
+1,first
+2,first
+3,first
+4,first

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_1.diff

@@ -0,0 +1,3 @@
+in:
+  last_record: [4]
+out: {}

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_2.csv

@@ -0,0 +1,2 @@
+5,more_load
+9,more_load

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_2.diff

@@ -0,0 +1,3 @@
+in:
+  last_record: [9]
+out: {}

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/insert_more.sql

@@ -0,0 +1,6 @@
+
+insert into query_load (num, num2, note) values
+(0, 100, 'more_skip'),
+(4, 104, 'more_skip'),
+(9, 109, 'more_load'),
+(5, 105, 'more_load');

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_config_1.yml

@@ -0,0 +1,16 @@
+last_record: [0,0]
+incremental: true
+incremental_columns: [num,num2]
+use_raw_query_with_incremental: true
+query: |
+  SELECT
+    *
+  FROM
+    query_load
+  WHERE
+    num IS NOT NULL
+    AND num > :num
+    OR (num = :num AND num2 > :num2)
+  ORDER BY
+    num ASC,
+    num2 ASC

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_config_2.yml

@@ -0,0 +1,16 @@
+last_record: [4,104]
+incremental: true
+incremental_columns: [num,num2]
+use_raw_query_with_incremental: true
+query: |
+  SELECT
+    *
+  FROM
+    query_load
+  WHERE
+    num IS NOT NULL
+    AND num > :num
+    OR (num = :num AND num2 > :num2)
+  ORDER BY
+    num ASC,
+    num2 ASC

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_1.csv

@@ -0,0 +1,4 @@
+1,101,first
+2,102,first
+3,103,first
+4,104,first

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_1.diff

@@ -0,0 +1,3 @@
+in:
+  last_record: [4,104]
+out: {}

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_2.csv

@@ -0,0 +1,2 @@
+5,105,more_load
+9,109,more_load

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_2.diff

@@ -0,0 +1,3 @@
+in:
+  last_record: [9,109]
+out: {}

data/src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/setup.sql

@@ -0,0 +1,13 @@
+drop table if exists query_load;
+
+create table query_load (
+    num int not null,
+    num2 int not null,
+    note text
+);
+
+insert into query_load (num, num2, note) values
+(3, 103, 'first'),
+(4, 104, 'first'),
+(2, 102, 'first'),
+(1, 101, 'first');

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: embulk-input-redshift
 version: !ruby/object:Gem::Version
-  version: 0.9.2
+  version: 0.9.3
 platform: ruby
 authors:
 - Sadayuki Furuhashi
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-07-03 00:00:00.000000000 Z
+date: 2018-08-10 00:00:00.000000000 Z
 dependencies: []
 description: Selects records from a table.
 email:
@@ -19,9 +19,9 @@ extra_rdoc_files: []
 files:
 - README.md
 - build.gradle
-- classpath/embulk-input-jdbc-0.9.2.jar
-- classpath/embulk-input-postgresql-0.9.2.jar
-- classpath/embulk-input-redshift-0.9.2.jar
+- classpath/embulk-input-jdbc-0.9.3.jar
+- classpath/embulk-input-postgresql-0.9.3.jar
+- classpath/embulk-input-redshift-0.9.3.jar
 - classpath/postgresql-9.4-1205-jdbc41.jar
 - lib/embulk/input/redshift.rb
 - src/main/java/org/embulk/input/RedshiftInputPlugin.java
@@ -36,6 +36,20 @@ files:
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/int/expected_2.diff
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/int/insert_more.sql
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/int/setup.sql
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/config_1.yml
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/config_2.yml
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_1.csv
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_1.diff
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_2.csv
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/expected_2.diff
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/insert_more.sql
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_config_1.yml
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_config_2.yml
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_1.csv
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_1.diff
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_2.csv
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/multi_columns_expected_2.diff
+- src/test/resources/org/embulk/input/redshift/test/expect/incremental/query/setup.sql
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/timestamp/config_1.yml
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/timestamp/config_2.yml
 - src/test/resources/org/embulk/input/redshift/test/expect/incremental/timestamp/expected_1.csv