red-parquet 12.0.1 → 14.0.0
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 +4 -4
- data/lib/parquet/arrow-file-reader.rb +28 -0
- data/lib/parquet/loader.rb +1 -0
- data/lib/parquet/version.rb +1 -1
- data/test/test-arrow-file-reader.rb +66 -0
- metadata +11 -8
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8cad636ae5f27842cb134a39ae0abaabf91eadae5f4349a65b5985347e83f4dc
|
4
|
+
data.tar.gz: 486195624d0ffec4539a9475aa84635af83fd43458e9943876978345b6af9436
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 84e44b345e34097f45b9e1e463e2969e47c4d511aff640f852de3ffc285cf1c336d27c21365ec5789733f64f972c4e36e1200154737cee2e9ec7cc2e07459cca
|
7
|
+
data.tar.gz: ed680882d8e9ef23087944f9b0aba03252a7be4869d1d2ba6eff8e462f671d1462a679419859179b157df229a0b4aa37fe69d815e4c50f79932adb3e848ba0bd
|
@@ -0,0 +1,28 @@
|
|
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
|
8
|
+
#
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
10
|
+
#
|
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.
|
17
|
+
|
18
|
+
module Parquet
|
19
|
+
class ArrowFileReader
|
20
|
+
def each_row_group
|
21
|
+
return to_enum(__method__) {n_row_groups} unless block_given?
|
22
|
+
|
23
|
+
n_row_groups.times do |i|
|
24
|
+
yield(read_row_group(i))
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
data/lib/parquet/loader.rb
CHANGED
data/lib/parquet/version.rb
CHANGED
@@ -0,0 +1,66 @@
|
|
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
|
8
|
+
#
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
10
|
+
#
|
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.
|
17
|
+
|
18
|
+
class TestArrowFileReader < Test::Unit::TestCase
|
19
|
+
def setup
|
20
|
+
@schema = Arrow::Schema.new(visible: :boolean)
|
21
|
+
table = Arrow::Table.new(@schema, [[true], [false]])
|
22
|
+
Tempfile.create(["red-parquet", ".parquet"]) do |file|
|
23
|
+
@file = file
|
24
|
+
Parquet::ArrowFileWriter.open(table.schema, @file.path) do |writer|
|
25
|
+
chunk_size = 1
|
26
|
+
writer.write_table(table, chunk_size)
|
27
|
+
end
|
28
|
+
yield
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
sub_test_case("#each_row_group") do
|
33
|
+
test("block") do
|
34
|
+
Arrow::FileInputStream.open(@file.path) do |input|
|
35
|
+
reader = Parquet::ArrowFileReader.new(input)
|
36
|
+
row_groups = []
|
37
|
+
reader.each_row_group do |row_group|
|
38
|
+
row_groups << row_group
|
39
|
+
end
|
40
|
+
assert_equal([
|
41
|
+
Arrow::Table.new(@schema, [[true]]),
|
42
|
+
Arrow::Table.new(@schema, [[false]])
|
43
|
+
],
|
44
|
+
row_groups)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
test("without block") do
|
49
|
+
Arrow::FileInputStream.open(@file.path) do |input|
|
50
|
+
reader = Parquet::ArrowFileReader.new(input)
|
51
|
+
each_row_group = reader.each_row_group
|
52
|
+
assert_equal({
|
53
|
+
size: 2,
|
54
|
+
to_a: [
|
55
|
+
Arrow::Table.new(@schema, [[true]]),
|
56
|
+
Arrow::Table.new(@schema, [[false]])
|
57
|
+
],
|
58
|
+
},
|
59
|
+
{
|
60
|
+
size: each_row_group.size,
|
61
|
+
to_a: each_row_group.to_a,
|
62
|
+
})
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
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:
|
4
|
+
version: 14.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Apache Arrow Developers
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-11-08 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:
|
19
|
+
version: 14.0.0
|
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:
|
26
|
+
version: 14.0.0
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: bundler
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -81,6 +81,7 @@ files:
|
|
81
81
|
- Rakefile
|
82
82
|
- dependency-check/Rakefile
|
83
83
|
- lib/parquet.rb
|
84
|
+
- lib/parquet/arrow-file-reader.rb
|
84
85
|
- lib/parquet/arrow-table-loadable.rb
|
85
86
|
- lib/parquet/arrow-table-savable.rb
|
86
87
|
- lib/parquet/loader.rb
|
@@ -89,13 +90,14 @@ files:
|
|
89
90
|
- red-parquet.gemspec
|
90
91
|
- test/helper.rb
|
91
92
|
- test/run-test.rb
|
93
|
+
- test/test-arrow-file-reader.rb
|
92
94
|
- test/test-arrow-table.rb
|
93
95
|
- test/test-boolean-statistics.rb
|
94
96
|
homepage: https://arrow.apache.org/
|
95
97
|
licenses:
|
96
98
|
- Apache-2.0
|
97
99
|
metadata: {}
|
98
|
-
post_install_message:
|
100
|
+
post_install_message:
|
99
101
|
rdoc_options: []
|
100
102
|
require_paths:
|
101
103
|
- lib
|
@@ -110,12 +112,13 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
110
112
|
- !ruby/object:Gem::Version
|
111
113
|
version: '0'
|
112
114
|
requirements: []
|
113
|
-
rubygems_version: 3.
|
114
|
-
signing_key:
|
115
|
+
rubygems_version: 3.5.0.dev
|
116
|
+
signing_key:
|
115
117
|
specification_version: 4
|
116
118
|
summary: Red Parquet is the Ruby bindings of Apache Parquet
|
117
119
|
test_files:
|
118
120
|
- test/helper.rb
|
119
121
|
- test/run-test.rb
|
122
|
+
- test/test-arrow-file-reader.rb
|
120
123
|
- test/test-arrow-table.rb
|
121
124
|
- test/test-boolean-statistics.rb
|