zeroshade commented on a change in pull request #9817: URL: https://github.com/apache/arrow/pull/9817#discussion_r604351891
########## File path: go/parquet/compress/compress_test.go ########## @@ -0,0 +1,128 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package compress_test + +import ( + "bytes" + "io/ioutil" + "math/rand" + "testing" + + "github.com/apache/arrow/go/parquet/compress" + "github.com/stretchr/testify/assert" +) + +const ( + RandomDataSize = 3 * 1024 * 1024 + CompressibleDataSize = 8 * 1024 * 1024 +) + +func makeRandomData(size int) []byte { + ret := make([]byte, size) + r := rand.New(rand.NewSource(1234)) + r.Read(ret) + return ret +} + +func makeCompressibleData(size int) []byte { + const base = "Apache Arrow is a cross-language development platform for in-memory data" + + data := make([]byte, size) + n := copy(data, base) + for i := n; i < len(data); i *= 2 { + copy(data[i:], data[:i]) + } + return data +} + +func TestCompressDataOneShot(t *testing.T) { + tests := []struct { + c compress.Compression + }{ + {compress.Codecs.Uncompressed}, + {compress.Codecs.Snappy}, + {compress.Codecs.Gzip}, + // {compress.Codecs.Lzo}, + {compress.Codecs.Brotli}, + {compress.Codecs.Lz4}, + {compress.Codecs.Zstd}, + } + + for _, tt := range tests { + t.Run(tt.c.String(), func(t *testing.T) { + codec := compress.GetCodec(tt.c) + data := makeCompressibleData(CompressibleDataSize) + + buf := make([]byte, codec.CompressBound(int64(len(data)))) + compressed := codec.Encode(buf, data) + assert.Same(t, &buf[0], &compressed[0]) + + out := make([]byte, len(data)) + uncompressed := codec.Decode(out, compressed) + assert.Same(t, &out[0], &uncompressed[0]) + + assert.Exactly(t, data, uncompressed) + }) + } +} + +func TestCompressReaderWriter(t *testing.T) { + tests := []struct { + c compress.Compression + }{ + {compress.Codecs.Uncompressed}, + {compress.Codecs.Snappy}, + {compress.Codecs.Gzip}, + // {compress.Codecs.Lzo}, + {compress.Codecs.Brotli}, + {compress.Codecs.Lz4}, + {compress.Codecs.Zstd}, + } + + for _, tt := range tests { + t.Run(tt.c.String(), func(t *testing.T) { + var buf bytes.Buffer + codec := compress.GetCodec(tt.c) + data := makeRandomData(RandomDataSize) + + wr := codec.NewWriter(&buf) + + const chunkSize = 1111 Review comment: pulled this test from the C++ implementation tests. Ultimately it's because it's a number that is small enough to make sure we'll have multiple chunks but large enough that it'll have some compression it can do :) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
