red-parquet 0.0.2 → 0.12.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +5 -5
- data/Gemfile +14 -11
- data/{doc/text/apache-2.0.txt → LICENSE.txt} +0 -0
- data/NOTICE.txt +2 -0
- data/README.md +27 -29
- data/Rakefile +17 -25
- data/dependency-check/Rakefile +14 -11
- data/lib/parquet.rb +14 -11
- data/lib/parquet/arrow-table-loadable.rb +21 -15
- data/lib/parquet/arrow-table-savable.rb +19 -14
- data/lib/parquet/loader.rb +14 -11
- data/lib/parquet/version.rb +21 -12
- data/red-parquet.gemspec +29 -32
- data/test/helper.rb +14 -11
- data/test/run-test.rb +19 -12
- data/test/test-arrow-table.rb +21 -12
- metadata +13 -47
- data/.yardopts +0 -6
- data/doc/text/news.md +0 -13
- data/test/test-arrow-file-reader.rb +0 -41
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: bc5d46efc9fc652cd9c8e52345d3be7a17fe5bf22629efb0b5710baa678e8168
|
4
|
+
data.tar.gz: 185c1aadebfa2f0c38224fb2b9a925856736ea13f2084e6c6240c8e8c184a892
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 653075c4bccdf6c800d0ff52e8a37fcaf4477b59dda7dcc1b1a291f91536e0731892afda623c5c74ebf5e7358f8621a822266cc534c26e3c2ccd9a0751f5cc5f
|
7
|
+
data.tar.gz: ff57c715fd2d25cfe08f2fd6eae5f8a05d3a6a291f1e8ed505591d971768ff260cac825fccb767ab04193facb7154b6b137b9a30fea6449ffce53c5aecc638b9
|
data/Gemfile
CHANGED
@@ -1,18 +1,21 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
#
|
3
|
-
#
|
3
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4
|
+
# or more contributor license agreements. See the NOTICE file
|
5
|
+
# distributed with this work for additional information
|
6
|
+
# regarding copyright ownership. The ASF licenses this file
|
7
|
+
# to you under the Apache License, Version 2.0 (the
|
8
|
+
# "License"); you may not use this file except in compliance
|
9
|
+
# with the License. You may obtain a copy of the License at
|
4
10
|
#
|
5
|
-
#
|
6
|
-
# you may not use this file except in compliance with the License.
|
7
|
-
# You may obtain a copy of the License at
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
12
|
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
# limitations under the License.
|
13
|
+
# Unless required by applicable law or agreed to in writing,
|
14
|
+
# software distributed under the License is distributed on an
|
15
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16
|
+
# KIND, either express or implied. See the License for the
|
17
|
+
# specific language governing permissions and limitations
|
18
|
+
# under the License.
|
16
19
|
|
17
20
|
source "https://rubygems.org/"
|
18
21
|
|
File without changes
|
data/NOTICE.txt
ADDED
data/README.md
CHANGED
@@ -1,28 +1,43 @@
|
|
1
|
-
|
1
|
+
<!---
|
2
|
+
Licensed to the Apache Software Foundation (ASF) under one
|
3
|
+
or more contributor license agreements. See the NOTICE file
|
4
|
+
distributed with this work for additional information
|
5
|
+
regarding copyright ownership. The ASF licenses this file
|
6
|
+
to you under the Apache License, Version 2.0 (the
|
7
|
+
"License"); you may not use this file except in compliance
|
8
|
+
with the License. You may obtain a copy of the License at
|
2
9
|
|
3
|
-
|
10
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
4
11
|
|
5
|
-
|
12
|
+
Unless required by applicable law or agreed to in writing,
|
13
|
+
software distributed under the License is distributed on an
|
14
|
+
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
15
|
+
KIND, either express or implied. See the License for the
|
16
|
+
specific language governing permissions and limitations
|
17
|
+
under the License.
|
18
|
+
-->
|
6
19
|
|
7
|
-
|
20
|
+
# Red Parquet - Apache Parquet Ruby
|
8
21
|
|
9
|
-
Red Parquet is
|
22
|
+
Red Parquet is the Ruby bindings of Apache Parquet. Red Parquet is based on GObject Introspection.
|
10
23
|
|
11
24
|
[Apache Parquet](https://parquet.apache.org/) is a columnar storage format.
|
12
25
|
|
13
26
|
[GObject Introspection](https://wiki.gnome.org/action/show/Projects/GObjectIntrospection) is a middleware for language bindings of C library. GObject Introspection can generate language bindings automatically at runtime.
|
14
27
|
|
15
|
-
Red Parquet uses [Parquet GLib](https://github.com/
|
28
|
+
Red Parquet uses [Apache Parquet GLib](https://github.com/apache/arrow/tree/master/c_glib/parquet-glib) and [gobject-introspection gem](https://rubygems.org/gems/gobject-introspection) to generate Ruby bindings of Apache Parquet.
|
16
29
|
|
17
|
-
Parquet GLib is a C wrapper for [Parquet C++](https://github.com/apache/parquet
|
30
|
+
Apache Parquet GLib is a C wrapper for [Apache Parquet C++](https://github.com/apache/arrow/tree/master/cpp/parquet). GObject Introspection can't use Apache Parquet C++ directly. Apache Parquet GLib is a bridge between Apache Parquet C++ and GObject Introspection.
|
18
31
|
|
19
32
|
gobject-introspection gem is a Ruby bindings of GObject Introspection. Red Parquet uses GObject Introspection via gobject-introspection gem.
|
20
33
|
|
21
34
|
## Install
|
22
35
|
|
23
|
-
Install Parquet GLib before install Red Parquet. Use [
|
36
|
+
Install Apache Parquet GLib before install Red Parquet. Use [packages.red-data-tools.org](https://github.com/red-data-tools/packages.red-data-tools.org) for installing Apache Parquet GLib.
|
24
37
|
|
25
|
-
|
38
|
+
Note that the Apache Parquet GLib packages are "unofficial". "Official" packages will be released in the future.
|
39
|
+
|
40
|
+
Install Red Parquet after you install Apache Parquet GLib:
|
26
41
|
|
27
42
|
```text
|
28
43
|
% gem install red-parquet
|
@@ -33,24 +48,7 @@ Install Red Parquet after you install Parquet GLib:
|
|
33
48
|
```ruby
|
34
49
|
require "parquet"
|
35
50
|
|
36
|
-
|
51
|
+
table = Arrow::Table.load("/dev/shm/data.parquet")
|
52
|
+
# Process data in table
|
53
|
+
table.save("/dev/shm/data-processed.parquet")
|
37
54
|
```
|
38
|
-
|
39
|
-
## Dependencies
|
40
|
-
|
41
|
-
* [Apache Parquet C++](https://github.com/apache/parquet-cpp) with Apache Arrow support
|
42
|
-
|
43
|
-
* [Parquet GLib](https://github.com/red-data-tools/parquet-glib)
|
44
|
-
|
45
|
-
* [Red Arrow](https://rubygems.org/gems/red-arrow)
|
46
|
-
|
47
|
-
## Authors
|
48
|
-
|
49
|
-
* Kouhei Sutou \<kou@clear-code.com\>
|
50
|
-
|
51
|
-
## License
|
52
|
-
|
53
|
-
Apache License 2.0. See doc/text/apache-2.0.txt for details.
|
54
|
-
|
55
|
-
(Kouhei Sutou has a right to change the license including contributed
|
56
|
-
patches.)
|
data/Rakefile
CHANGED
@@ -1,40 +1,32 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
#
|
3
|
-
#
|
3
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4
|
+
# or more contributor license agreements. See the NOTICE file
|
5
|
+
# distributed with this work for additional information
|
6
|
+
# regarding copyright ownership. The ASF licenses this file
|
7
|
+
# to you under the Apache License, Version 2.0 (the
|
8
|
+
# "License"); you may not use this file except in compliance
|
9
|
+
# with the License. You may obtain a copy of the License at
|
4
10
|
#
|
5
|
-
#
|
6
|
-
# you may not use this file except in compliance with the License.
|
7
|
-
# You may obtain a copy of the License at
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
12
|
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
# limitations under the License.
|
13
|
+
# Unless required by applicable law or agreed to in writing,
|
14
|
+
# software distributed under the License is distributed on an
|
15
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16
|
+
# KIND, either express or implied. See the License for the
|
17
|
+
# specific language governing permissions and limitations
|
18
|
+
# under the License.
|
16
19
|
|
17
20
|
require "rubygems"
|
18
21
|
require "bundler/gem_helper"
|
19
|
-
require "packnga"
|
20
22
|
|
21
|
-
base_dir = File.join(
|
23
|
+
base_dir = File.join(__dir__)
|
22
24
|
|
23
25
|
helper = Bundler::GemHelper.new(base_dir)
|
24
|
-
def helper.version_tag
|
25
|
-
version
|
26
|
-
end
|
27
|
-
|
28
26
|
helper.install
|
29
|
-
spec = helper.gemspec
|
30
27
|
|
31
|
-
|
32
|
-
|
33
|
-
task.translate_language = "ja"
|
34
|
-
end
|
35
|
-
|
36
|
-
Packnga::ReleaseTask.new(spec) do
|
37
|
-
end
|
28
|
+
release_task = Rake::Task["release"]
|
29
|
+
release_task.prerequisites.replace(["build", "release:rubygem_push"])
|
38
30
|
|
39
31
|
desc "Run tests"
|
40
32
|
task :test do
|
data/dependency-check/Rakefile
CHANGED
@@ -1,18 +1,21 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
#
|
3
|
-
#
|
3
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4
|
+
# or more contributor license agreements. See the NOTICE file
|
5
|
+
# distributed with this work for additional information
|
6
|
+
# regarding copyright ownership. The ASF licenses this file
|
7
|
+
# to you under the Apache License, Version 2.0 (the
|
8
|
+
# "License"); you may not use this file except in compliance
|
9
|
+
# with the License. You may obtain a copy of the License at
|
4
10
|
#
|
5
|
-
#
|
6
|
-
# you may not use this file except in compliance with the License.
|
7
|
-
# You may obtain a copy of the License at
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
12
|
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
# limitations under the License.
|
13
|
+
# Unless required by applicable law or agreed to in writing,
|
14
|
+
# software distributed under the License is distributed on an
|
15
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16
|
+
# KIND, either express or implied. See the License for the
|
17
|
+
# specific language governing permissions and limitations
|
18
|
+
# under the License.
|
16
19
|
|
17
20
|
require "pkg-config"
|
18
21
|
require "native-package-installer"
|
data/lib/parquet.rb
CHANGED
@@ -1,16 +1,19 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
require "arrow"
|
16
19
|
|
@@ -1,24 +1,30 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
module Parquet
|
16
19
|
module ArrowTableLoadable
|
17
20
|
private
|
18
|
-
def load_as_parquet
|
19
|
-
|
20
|
-
reader
|
21
|
-
reader.
|
21
|
+
def load_as_parquet
|
22
|
+
input = open_input_stream
|
23
|
+
reader = Parquet::ArrowFileReader.new(input)
|
24
|
+
reader.use_threads = (@options[:use_threads] != false)
|
25
|
+
table = reader.read_table
|
26
|
+
table.instance_variable_set(:@input, input)
|
27
|
+
table
|
22
28
|
end
|
23
29
|
end
|
24
30
|
end
|
@@ -1,24 +1,29 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
module Parquet
|
16
19
|
module ArrowTableSavable
|
17
20
|
private
|
18
|
-
def save_as_parquet
|
21
|
+
def save_as_parquet
|
19
22
|
chunk_size = @options[:chunk_size] || 1024 # TODO
|
20
|
-
|
21
|
-
|
23
|
+
open_output_stream do |output|
|
24
|
+
Parquet::ArrowFileWriter.open(@table.schema, output) do |writer|
|
25
|
+
writer.write_table(@table, chunk_size)
|
26
|
+
end
|
22
27
|
end
|
23
28
|
end
|
24
29
|
end
|
data/lib/parquet/loader.rb
CHANGED
@@ -1,16 +1,19 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
module Parquet
|
16
19
|
class Loader < GObjectIntrospection::Loader
|
data/lib/parquet/version.rb
CHANGED
@@ -1,17 +1,26 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
module Parquet
|
16
|
-
VERSION = "0.0
|
19
|
+
VERSION = "0.12.0"
|
20
|
+
|
21
|
+
module Version
|
22
|
+
numbers, TAG = VERSION.split("-")
|
23
|
+
MAJOR, MINOR, MICRO = numbers.split(".").collect(&:to_i)
|
24
|
+
STRING = VERSION
|
25
|
+
end
|
17
26
|
end
|
data/red-parquet.gemspec
CHANGED
@@ -1,52 +1,49 @@
|
|
1
1
|
# -*- ruby -*-
|
2
2
|
#
|
3
|
-
#
|
3
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4
|
+
# or more contributor license agreements. See the NOTICE file
|
5
|
+
# distributed with this work for additional information
|
6
|
+
# regarding copyright ownership. The ASF licenses this file
|
7
|
+
# to you under the Apache License, Version 2.0 (the
|
8
|
+
# "License"); you may not use this file except in compliance
|
9
|
+
# with the License. You may obtain a copy of the License at
|
4
10
|
#
|
5
|
-
#
|
6
|
-
# you may not use this file except in compliance with the License.
|
7
|
-
# You may obtain a copy of the License at
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
12
|
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
# limitations under the License.
|
16
|
-
|
17
|
-
clean_white_space = lambda do |entry|
|
18
|
-
entry.gsub(/(\A\n+|\n+\z)/, '') + "\n"
|
19
|
-
end
|
13
|
+
# Unless required by applicable law or agreed to in writing,
|
14
|
+
# software distributed under the License is distributed on an
|
15
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16
|
+
# KIND, either express or implied. See the License for the
|
17
|
+
# specific language governing permissions and limitations
|
18
|
+
# under the License.
|
20
19
|
|
21
|
-
|
22
|
-
require "parquet/version"
|
20
|
+
require_relative "lib/parquet/version"
|
23
21
|
|
24
22
|
Gem::Specification.new do |spec|
|
25
23
|
spec.name = "red-parquet"
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
24
|
+
version_components = [
|
25
|
+
Parquet::Version::MAJOR.to_s,
|
26
|
+
Parquet::Version::MINOR.to_s,
|
27
|
+
Parquet::Version::MICRO.to_s,
|
28
|
+
Parquet::Version::TAG,
|
29
|
+
]
|
30
|
+
spec.version = version_components.compact.join(".")
|
31
|
+
spec.homepage = "https://arrow.apache.org/"
|
32
|
+
spec.authors = ["Apache Arrow Developers"]
|
33
|
+
spec.email = ["dev@arrow.apache.org"]
|
30
34
|
|
31
|
-
|
32
|
-
|
33
|
-
entries = readme.split(/^\#\#\s(.*)$/)
|
34
|
-
clean_white_space.call(entries[entries.index("Description") + 1])
|
35
|
-
description = clean_white_space.call(entries[entries.index("Description") + 1])
|
36
|
-
spec.summary, spec.description, = description.split(/\n\n+/, 3)
|
35
|
+
spec.summary = "Red Parquet is the Ruby bindings of Apache Parquet"
|
36
|
+
spec.description = "Apache Parquet is a columnar storage format."
|
37
37
|
spec.license = "Apache-2.0"
|
38
38
|
spec.files = ["README.md", "Rakefile", "Gemfile", "#{spec.name}.gemspec"]
|
39
|
-
spec.files += [".
|
39
|
+
spec.files += ["LICENSE.txt", "NOTICE.txt"]
|
40
40
|
spec.files += Dir.glob("lib/**/*.rb")
|
41
|
-
spec.files += Dir.glob("doc/text/*")
|
42
41
|
spec.test_files += Dir.glob("test/**/*")
|
43
42
|
spec.extensions = ["dependency-check/Rakefile"]
|
44
43
|
|
45
|
-
spec.add_runtime_dependency("red-arrow"
|
44
|
+
spec.add_runtime_dependency("red-arrow")
|
46
45
|
|
47
46
|
spec.add_development_dependency("bundler")
|
48
47
|
spec.add_development_dependency("rake")
|
49
48
|
spec.add_development_dependency("test-unit")
|
50
|
-
spec.add_development_dependency("packnga")
|
51
|
-
spec.add_development_dependency("kramdown")
|
52
49
|
end
|
data/test/helper.rb
CHANGED
@@ -1,16 +1,19 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
require "parquet"
|
16
19
|
|
data/test/run-test.rb
CHANGED
@@ -1,28 +1,35 @@
|
|
1
1
|
#!/usr/bin/env ruby
|
2
2
|
#
|
3
|
-
#
|
3
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4
|
+
# or more contributor license agreements. See the NOTICE file
|
5
|
+
# distributed with this work for additional information
|
6
|
+
# regarding copyright ownership. The ASF licenses this file
|
7
|
+
# to you under the Apache License, Version 2.0 (the
|
8
|
+
# "License"); you may not use this file except in compliance
|
9
|
+
# with the License. You may obtain a copy of the License at
|
4
10
|
#
|
5
|
-
#
|
6
|
-
# you may not use this file except in compliance with the License.
|
7
|
-
# You may obtain a copy of the License at
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
12
|
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
#
|
15
|
-
# limitations under the License.
|
13
|
+
# Unless required by applicable law or agreed to in writing,
|
14
|
+
# software distributed under the License is distributed on an
|
15
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16
|
+
# KIND, either express or implied. See the License for the
|
17
|
+
# specific language governing permissions and limitations
|
18
|
+
# under the License.
|
16
19
|
|
17
20
|
$VERBOSE = true
|
18
21
|
|
19
22
|
require "pathname"
|
20
23
|
|
21
|
-
base_dir = Pathname.new(
|
24
|
+
base_dir = Pathname.new(__dir__).parent.expand_path
|
25
|
+
arrow_base_dir = base_dir.parent + "red-arrow"
|
22
26
|
|
23
27
|
lib_dir = base_dir + "lib"
|
24
28
|
test_dir = base_dir + "test"
|
25
29
|
|
30
|
+
arrow_lib_dir = arrow_base_dir + "lib"
|
31
|
+
|
32
|
+
$LOAD_PATH.unshift(arrow_lib_dir.to_s)
|
26
33
|
$LOAD_PATH.unshift(lib_dir.to_s)
|
27
34
|
|
28
35
|
require_relative "helper"
|
data/test/test-arrow-table.rb
CHANGED
@@ -1,16 +1,19 @@
|
|
1
|
-
#
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one
|
2
|
+
# or more contributor license agreements. See the NOTICE file
|
3
|
+
# distributed with this work for additional information
|
4
|
+
# regarding copyright ownership. The ASF licenses this file
|
5
|
+
# to you under the Apache License, Version 2.0 (the
|
6
|
+
# "License"); you may not use this file except in compliance
|
7
|
+
# with the License. You may obtain a copy of the License at
|
2
8
|
#
|
3
|
-
#
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
10
|
#
|
7
|
-
#
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
11
|
-
#
|
12
|
-
#
|
13
|
-
# limitations under the License.
|
11
|
+
# Unless required by applicable law or agreed to in writing,
|
12
|
+
# software distributed under the License is distributed on an
|
13
|
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
14
|
+
# KIND, either express or implied. See the License for the
|
15
|
+
# specific language governing permissions and limitations
|
16
|
+
# under the License.
|
14
17
|
|
15
18
|
class TestArrowTableReader < Test::Unit::TestCase
|
16
19
|
def setup
|
@@ -37,9 +40,15 @@ class TestArrowTableReader < Test::Unit::TestCase
|
|
37
40
|
@table = Arrow::Table.new(schema, [@count_column, @visible_column])
|
38
41
|
end
|
39
42
|
|
40
|
-
def
|
43
|
+
def test_save_load_path
|
41
44
|
tempfile = Tempfile.open(["red-parquet", ".parquet"])
|
42
45
|
@table.save(tempfile.path)
|
43
46
|
assert_equal(@table, Arrow::Table.load(tempfile.path))
|
44
47
|
end
|
48
|
+
|
49
|
+
def test_save_load_buffer
|
50
|
+
buffer = Arrow::ResizableBuffer.new(1024)
|
51
|
+
@table.save(buffer, format: :parquet)
|
52
|
+
assert_equal(@table, Arrow::Table.load(buffer, format: :parquet))
|
53
|
+
end
|
45
54
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: red-parquet
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.12.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
|
-
-
|
7
|
+
- Apache Arrow Developers
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2019-01-19 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: red-arrow
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 0
|
19
|
+
version: '0'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: 0
|
26
|
+
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: bundler
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -66,50 +66,20 @@ dependencies:
|
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '0'
|
69
|
-
|
70
|
-
name: packnga
|
71
|
-
requirement: !ruby/object:Gem::Requirement
|
72
|
-
requirements:
|
73
|
-
- - ">="
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
version: '0'
|
76
|
-
type: :development
|
77
|
-
prerelease: false
|
78
|
-
version_requirements: !ruby/object:Gem::Requirement
|
79
|
-
requirements:
|
80
|
-
- - ">="
|
81
|
-
- !ruby/object:Gem::Version
|
82
|
-
version: '0'
|
83
|
-
- !ruby/object:Gem::Dependency
|
84
|
-
name: kramdown
|
85
|
-
requirement: !ruby/object:Gem::Requirement
|
86
|
-
requirements:
|
87
|
-
- - ">="
|
88
|
-
- !ruby/object:Gem::Version
|
89
|
-
version: '0'
|
90
|
-
type: :development
|
91
|
-
prerelease: false
|
92
|
-
version_requirements: !ruby/object:Gem::Requirement
|
93
|
-
requirements:
|
94
|
-
- - ">="
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
version: '0'
|
97
|
-
description: "[Apache Parquet](https://parquet.apache.org/) is a columnar storage
|
98
|
-
format."
|
69
|
+
description: Apache Parquet is a columnar storage format.
|
99
70
|
email:
|
100
|
-
-
|
71
|
+
- dev@arrow.apache.org
|
101
72
|
executables: []
|
102
73
|
extensions:
|
103
74
|
- dependency-check/Rakefile
|
104
75
|
extra_rdoc_files: []
|
105
76
|
files:
|
106
|
-
- ".yardopts"
|
107
77
|
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- NOTICE.txt
|
108
80
|
- README.md
|
109
81
|
- Rakefile
|
110
82
|
- dependency-check/Rakefile
|
111
|
-
- doc/text/apache-2.0.txt
|
112
|
-
- doc/text/news.md
|
113
83
|
- lib/parquet.rb
|
114
84
|
- lib/parquet/arrow-table-loadable.rb
|
115
85
|
- lib/parquet/arrow-table-savable.rb
|
@@ -118,9 +88,8 @@ files:
|
|
118
88
|
- red-parquet.gemspec
|
119
89
|
- test/helper.rb
|
120
90
|
- test/run-test.rb
|
121
|
-
- test/test-arrow-file-reader.rb
|
122
91
|
- test/test-arrow-table.rb
|
123
|
-
homepage: https://
|
92
|
+
homepage: https://arrow.apache.org/
|
124
93
|
licenses:
|
125
94
|
- Apache-2.0
|
126
95
|
metadata: {}
|
@@ -139,14 +108,11 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
139
108
|
- !ruby/object:Gem::Version
|
140
109
|
version: '0'
|
141
110
|
requirements: []
|
142
|
-
|
143
|
-
rubygems_version: 2.5.2.2
|
111
|
+
rubygems_version: 3.0.2
|
144
112
|
signing_key:
|
145
113
|
specification_version: 4
|
146
|
-
summary: Red Parquet is
|
147
|
-
GObject Introspection.
|
114
|
+
summary: Red Parquet is the Ruby bindings of Apache Parquet
|
148
115
|
test_files:
|
149
116
|
- test/helper.rb
|
150
|
-
- test/run-test.rb
|
151
|
-
- test/test-arrow-file-reader.rb
|
152
117
|
- test/test-arrow-table.rb
|
118
|
+
- test/run-test.rb
|
data/.yardopts
DELETED
data/doc/text/news.md
DELETED
@@ -1,41 +0,0 @@
|
|
1
|
-
# Copyright 2017 Kouhei Sutou <kou@clear-code.com>
|
2
|
-
#
|
3
|
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
-
# you may not use this file except in compliance with the License.
|
5
|
-
# You may obtain a copy of the License at
|
6
|
-
#
|
7
|
-
# http://www.apache.org/licenses/LICENSE-2.0
|
8
|
-
#
|
9
|
-
# Unless required by applicable law or agreed to in writing, software
|
10
|
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
-
# See the License for the specific language governing permissions and
|
13
|
-
# limitations under the License.
|
14
|
-
|
15
|
-
class TestArrowFileReader < Test::Unit::TestCase
|
16
|
-
def test_read_write
|
17
|
-
tempfile = Tempfile.open(["data", ".parquet"])
|
18
|
-
|
19
|
-
values = [true, nil, false, true]
|
20
|
-
chunk_size = 2
|
21
|
-
|
22
|
-
field = Arrow::Field.new("enabled", Arrow::BooleanDataType.new)
|
23
|
-
schema = Arrow::Schema.new([field])
|
24
|
-
Parquet::ArrowFileWriter.open(schema, tempfile.path) do |writer|
|
25
|
-
columns = [
|
26
|
-
Arrow::Column.new(field, Arrow::BooleanArray.new(values)),
|
27
|
-
]
|
28
|
-
table = Arrow::Table.new(schema, columns)
|
29
|
-
writer.write_table(table, chunk_size)
|
30
|
-
end
|
31
|
-
|
32
|
-
reader = Parquet::ArrowFileReader.new(tempfile.path)
|
33
|
-
reader.n_threads = 4
|
34
|
-
assert_equal(chunk_size, reader.n_row_groups)
|
35
|
-
table = reader.read_table
|
36
|
-
table_data = table.each_column.collect do |column|
|
37
|
-
[column.name, column.to_a]
|
38
|
-
end
|
39
|
-
assert_equal([["enabled", values]], table_data)
|
40
|
-
end
|
41
|
-
end
|