ceph/src/arrow/c_glib/test/parquet/test-arrow-file-reader.rb

   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 TestParquetArrowFileReader < Test::Unit::TestCase
  19   include Helper::Buildable
  20
  21   def setup
  22     omit("Parquet is required") unless defined?(::Parquet)
  23     @file = Tempfile.open(["data", ".parquet"])
  24     @a_array = build_string_array(["foo", "bar"])
  25     @b_array = build_int32_array([123, 456])
  26     @table = build_table("a" => @a_array,
  27                          "b" => @b_array)
  28     writer = Parquet::ArrowFileWriter.new(@table.schema, @file.path)
  29     chunk_size = 1
  30     writer.write_table(@table, chunk_size)
  31     writer.close
  32     @reader = Parquet::ArrowFileReader.new(@file.path)
  33   end
  34
  35   def test_schema
  36     assert_equal(<<-SCHEMA.chomp, @reader.schema.to_s)
  37 a: string
  38 b: int32
  39     SCHEMA
  40   end
  41
  42   sub_test_case("#read_row_group") do
  43     test("with column indices") do
  44       assert_equal(build_table("b" => @b_array.slice(0, 1)),
  45                    @reader.read_row_group(0, [-1]))
  46     end
  47
  48     test("without column indices") do
  49       assert_equal(build_table("a" => @a_array.slice(1, 1),
  50                                "b" => @b_array.slice(1, 1)),
  51                    @reader.read_row_group(1))
  52     end
  53   end
  54
  55   def test_read_column
  56     assert_equal([
  57                    Arrow::ChunkedArray.new([@a_array]),
  58                    Arrow::ChunkedArray.new([@b_array]),
  59                  ],
  60                  [
  61                    @reader.read_column_data(0),
  62                    @reader.read_column_data(-1),
  63                  ])
  64   end
  65
  66   def test_n_rows
  67     assert_equal(2, @reader.n_rows)
  68   end
  69 end