emkornfield commented on a change in pull request #11538: URL: https://github.com/apache/arrow/pull/11538#discussion_r741415194
########## File path: go/parquet/file/column_writer.go ########## @@ -0,0 +1,567 @@ +// 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 file + +import ( + "bytes" + "encoding/binary" + "io" + + "github.com/apache/arrow/go/arrow" + "github.com/apache/arrow/go/arrow/array" + "github.com/apache/arrow/go/arrow/bitutil" + "github.com/apache/arrow/go/arrow/memory" + "github.com/apache/arrow/go/parquet" + "github.com/apache/arrow/go/parquet/internal/encoding" + "github.com/apache/arrow/go/parquet/metadata" + "github.com/apache/arrow/go/parquet/schema" +) + +//go:generate go run ../../arrow/_tools/tmpl/main.go -i -data=../internal/encoding/physical_types.tmpldata column_writer_types.gen.go.tmpl + +// ColumnChunkWriter is the base interface for all columnwriters. To directly write +// data to the column, you need to assert it to the correctly typed ColumnChunkWriter +// instance, such as Int32ColumnWriter. +type ColumnChunkWriter interface { + // Close ends this column and returns the number of bytes written + Close() error + // Type returns the underlying physical parquet type for this column + Type() parquet.Type + // Descr returns the column information for this writer + Descr() *schema.Column + // RowsWritten returns the number of rows that have so far been written with this writer + RowsWritten() int64 + // TotalCompressedBytes returns the number of bytes, after compression, that have been written so far + TotalCompressedBytes() int64 + // TotalBytesWritten includes the bytes for writing dictionary pages, while TotalCompressedBytes is + // just the data and page headers + TotalBytesWritten() int64 + // Properties returns the current WriterProperties in use for this writer + Properties() *parquet.WriterProperties + + LevelInfo() LevelInfo + SetBitsBuffer(*memory.Buffer) +} + +func computeLevelInfo(descr *schema.Column) (info LevelInfo) { + info.DefLevel = descr.MaxDefinitionLevel() + info.RepLevel = descr.MaxRepetitionLevel() + + minSpacedDefLevel := descr.MaxDefinitionLevel() + n := descr.SchemaNode() + for n != nil && n.RepetitionType() != parquet.Repetitions.Repeated { + if n.RepetitionType() == parquet.Repetitions.Optional { + minSpacedDefLevel-- + } + n = n.Parent() + } + info.RepeatedAncestorDefLevel = minSpacedDefLevel + return +} + +type columnWriter struct { + metaData *metadata.ColumnChunkMetaDataBuilder + descr *schema.Column + + // scratch buffer if validity bits need to be recalculated + bitsBuffer *memory.Buffer + levelInfo LevelInfo + pager PageWriter + hasDict bool + encoding parquet.Encoding + props *parquet.WriterProperties + defEncoder encoding.LevelEncoder + repEncoder encoding.LevelEncoder + mem memory.Allocator + + pageStatistics metadata.TypedStatistics + chunkStatistics metadata.TypedStatistics + + // total number of values stored in the data page. this is the maximum Review comment: ```suggestion // total number of values stored in the data current page. this is the maximum ``` Does this make it more accurate. I wonder if adding comment dividing sections between current Page values and column writer values would make this clearer? -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
