ceph/src/arrow/cpp/src/parquet/properties_test.cc

   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 #include <gtest/gtest.h>
  19
  20 #include <string>
  21
  22 #include "arrow/buffer.h"
  23 #include "arrow/io/memory.h"
  24
  25 #include "parquet/file_reader.h"
  26 #include "parquet/properties.h"
  27
  28 namespace parquet {
  29
  30 using schema::ColumnPath;
  31
  32 namespace test {
  33
  34 TEST(TestReaderProperties, Basics) {
  35   ReaderProperties props;
  36
  37   ASSERT_EQ(props.buffer_size(), kDefaultBufferSize);
  38   ASSERT_FALSE(props.is_buffered_stream_enabled());
  39 }
  40
  41 TEST(TestWriterProperties, Basics) {
  42   std::shared_ptr<WriterProperties> props = WriterProperties::Builder().build();
  43
  44   ASSERT_EQ(kDefaultDataPageSize, props->data_pagesize());
  45   ASSERT_EQ(DEFAULT_DICTIONARY_PAGE_SIZE_LIMIT, props->dictionary_pagesize_limit());
  46   ASSERT_EQ(ParquetVersion::PARQUET_1_0, props->version());
  47   ASSERT_EQ(ParquetDataPageVersion::V1, props->data_page_version());
  48 }
  49
  50 TEST(TestWriterProperties, AdvancedHandling) {
  51   WriterProperties::Builder builder;
  52   builder.compression("gzip", Compression::GZIP);
  53   builder.compression("zstd", Compression::ZSTD);
  54   builder.compression(Compression::SNAPPY);
  55   builder.encoding(Encoding::DELTA_BINARY_PACKED);
  56   builder.encoding("delta-length", Encoding::DELTA_LENGTH_BYTE_ARRAY);
  57   builder.data_page_version(ParquetDataPageVersion::V2);
  58   std::shared_ptr<WriterProperties> props = builder.build();
  59
  60   ASSERT_EQ(Compression::GZIP, props->compression(ColumnPath::FromDotString("gzip")));
  61   ASSERT_EQ(Compression::ZSTD, props->compression(ColumnPath::FromDotString("zstd")));
  62   ASSERT_EQ(Compression::SNAPPY,
  63             props->compression(ColumnPath::FromDotString("delta-length")));
  64   ASSERT_EQ(Encoding::DELTA_BINARY_PACKED,
  65             props->encoding(ColumnPath::FromDotString("gzip")));
  66   ASSERT_EQ(Encoding::DELTA_LENGTH_BYTE_ARRAY,
  67             props->encoding(ColumnPath::FromDotString("delta-length")));
  68   ASSERT_EQ(ParquetDataPageVersion::V2, props->data_page_version());
  69 }
  70
  71 TEST(TestReaderProperties, GetStreamInsufficientData) {
  72   // ARROW-6058
  73   std::string data = "shorter than expected";
  74   auto buf = std::make_shared<Buffer>(data);
  75   auto reader = std::make_shared<::arrow::io::BufferReader>(buf);
  76
  77   ReaderProperties props;
  78   try {
  79     ARROW_UNUSED(props.GetStream(reader, 12, 15));
  80     FAIL() << "No exception raised";
  81   } catch (const ParquetException& e) {
  82     std::string ex_what =
  83         ("Tried reading 15 bytes starting at position 12"
  84          " from file but only got 9");
  85     ASSERT_EQ(ex_what, e.what());
  86   }
  87 }
  88
  89 }  // namespace test
  90 }  // namespace parquet