Versions in this module Expand all Collapse all v8 v8.0.1 Jul 14, 2022 v8.0.0 May 3, 2022 Changes in this version + var DefaultCompressionType = compress.Codecs.Uncompressed + var Parquet816FixedVersion = NewAppVersionExplicit("parquet-mr", 1, 2, 9) + func GetStatValue(typ parquet.Type, val []byte) interface + type AppVersion struct + App string + Build string + Version struct{ ... } + func NewAppVersion(createdby string) *AppVersion + func NewAppVersionExplicit(app string, major, minor, patch int) *AppVersion + func (v AppVersion) Equal(other *AppVersion) bool + func (v AppVersion) HasCorrectStatistics(coltype parquet.Type, logicalType schema.LogicalType, stats EncodedStatistics, ...) bool + func (v AppVersion) LessThan(other *AppVersion) bool + type BooleanStatistics struct + func NewBooleanStatistics(descr *schema.Column, mem memory.Allocator) *BooleanStatistics + func NewBooleanStatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *BooleanStatistics + func (s *BooleanStatistics) Descr() *schema.Column + func (s *BooleanStatistics) DistinctCount() int64 + func (s *BooleanStatistics) Encode() (enc EncodedStatistics, err error) + func (s *BooleanStatistics) EncodeMax() []byte + func (s *BooleanStatistics) EncodeMin() []byte + func (s *BooleanStatistics) Equals(other TypedStatistics) bool + func (s *BooleanStatistics) HasDistinctCount() bool + func (s *BooleanStatistics) HasMinMax() bool + func (s *BooleanStatistics) HasNullCount() bool + func (s *BooleanStatistics) Max() bool + func (s *BooleanStatistics) Merge(other TypedStatistics) + func (s *BooleanStatistics) Min() bool + func (s *BooleanStatistics) MinMaxEqual(rhs *BooleanStatistics) bool + func (s *BooleanStatistics) NullCount() int64 + func (s *BooleanStatistics) NumValues() int64 + func (s *BooleanStatistics) Reset() + func (s *BooleanStatistics) SetMinMax(argMin, argMax bool) + func (s *BooleanStatistics) Type() parquet.Type + func (s *BooleanStatistics) Update(values []bool, numNull int64) + func (s *BooleanStatistics) UpdateSpaced(values []bool, validBits []byte, validBitsOffset, numNull int64) + type ByteArrayStatistics struct + func NewByteArrayStatistics(descr *schema.Column, mem memory.Allocator) *ByteArrayStatistics + func NewByteArrayStatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *ByteArrayStatistics + func (s *ByteArrayStatistics) Descr() *schema.Column + func (s *ByteArrayStatistics) DistinctCount() int64 + func (s *ByteArrayStatistics) Encode() (enc EncodedStatistics, err error) + func (s *ByteArrayStatistics) EncodeMax() []byte + func (s *ByteArrayStatistics) EncodeMin() []byte + func (s *ByteArrayStatistics) Equals(other TypedStatistics) bool + func (s *ByteArrayStatistics) HasDistinctCount() bool + func (s *ByteArrayStatistics) HasMinMax() bool + func (s *ByteArrayStatistics) HasNullCount() bool + func (s *ByteArrayStatistics) Max() parquet.ByteArray + func (s *ByteArrayStatistics) Merge(other TypedStatistics) + func (s *ByteArrayStatistics) Min() parquet.ByteArray + func (s *ByteArrayStatistics) MinMaxEqual(rhs *ByteArrayStatistics) bool + func (s *ByteArrayStatistics) NullCount() int64 + func (s *ByteArrayStatistics) NumValues() int64 + func (s *ByteArrayStatistics) Reset() + func (s *ByteArrayStatistics) SetMinMax(argMin, argMax parquet.ByteArray) + func (s *ByteArrayStatistics) Type() parquet.Type + func (s *ByteArrayStatistics) Update(values []parquet.ByteArray, numNull int64) + func (s *ByteArrayStatistics) UpdateSpaced(values []parquet.ByteArray, validBits []byte, validBitsOffset, numNull int64) + type ChunkMetaInfo struct + CompressedSize int64 + DataPageOffset int64 + DictPageOffset int64 + IndexPageOffset int64 + NumValues int64 + UncompressedSize int64 + type ColumnChunkMetaData struct + func NewColumnChunkMetaData(column *format.ColumnChunk, descr *schema.Column, writerVersion *AppVersion, ...) (*ColumnChunkMetaData, error) + func (c *ColumnChunkMetaData) BloomFilterOffset() int64 + func (c *ColumnChunkMetaData) Compression() compress.Compression + func (c *ColumnChunkMetaData) CryptoMetadata() *format.ColumnCryptoMetaData + func (c *ColumnChunkMetaData) DataPageOffset() int64 + func (c *ColumnChunkMetaData) DictionaryPageOffset() int64 + func (c *ColumnChunkMetaData) EncodingStats() []PageEncodingStats + func (c *ColumnChunkMetaData) Encodings() []parquet.Encoding + func (c *ColumnChunkMetaData) Equals(other *ColumnChunkMetaData) bool + func (c *ColumnChunkMetaData) FileOffset() int64 + func (c *ColumnChunkMetaData) FilePath() string + func (c *ColumnChunkMetaData) HasDictionaryPage() bool + func (c *ColumnChunkMetaData) HasIndexPage() bool + func (c *ColumnChunkMetaData) IndexPageOffset() int64 + func (c *ColumnChunkMetaData) NumValues() int64 + func (c *ColumnChunkMetaData) PathInSchema() parquet.ColumnPath + func (c *ColumnChunkMetaData) Statistics() (TypedStatistics, error) + func (c *ColumnChunkMetaData) StatsSet() (bool, error) + func (c *ColumnChunkMetaData) TotalCompressedSize() int64 + func (c *ColumnChunkMetaData) TotalUncompressedSize() int64 + func (c *ColumnChunkMetaData) Type() parquet.Type + type ColumnChunkMetaDataBuilder struct + func NewColumnChunkMetaDataBuilder(props *parquet.WriterProperties, column *schema.Column) *ColumnChunkMetaDataBuilder + func NewColumnChunkMetaDataBuilderWithContents(props *parquet.WriterProperties, column *schema.Column, ...) *ColumnChunkMetaDataBuilder + func (c *ColumnChunkMetaDataBuilder) Contents() *format.ColumnChunk + func (c *ColumnChunkMetaDataBuilder) Descr() *schema.Column + func (c *ColumnChunkMetaDataBuilder) Finish(info ChunkMetaInfo, hasDict, dictFallback bool, encStats EncodingStats, ...) error + func (c *ColumnChunkMetaDataBuilder) SetFilePath(val string) + func (c *ColumnChunkMetaDataBuilder) SetStats(val EncodedStatistics) + func (c *ColumnChunkMetaDataBuilder) TotalCompressedSize() int64 + func (c *ColumnChunkMetaDataBuilder) WriteTo(w io.Writer) (int64, error) + type EncodedStatistics struct + DistinctCount int64 + HasDistinctCount bool + HasMax bool + HasMin bool + HasNullCount bool + Max []byte + Min []byte + NullCount int64 + Signed bool + func (e *EncodedStatistics) ApplyStatSizeLimits(length int) + func (e *EncodedStatistics) IsSet() bool + func (e *EncodedStatistics) SetDistinctCount(val int64) *EncodedStatistics + func (e *EncodedStatistics) SetMax(val []byte) *EncodedStatistics + func (e *EncodedStatistics) SetMin(val []byte) *EncodedStatistics + func (e *EncodedStatistics) SetNullCount(val int64) *EncodedStatistics + func (e *EncodedStatistics) ToThrift() (stats *format.Statistics) + type EncodingStats struct + DataEncodingStats map[parquet.Encoding]int32 + DictEncodingStats map[parquet.Encoding]int32 + type FileCryptoMetadata struct + func NewFileCryptoMetaData(metadata []byte) (ret FileCryptoMetadata, err error) + func (fc FileCryptoMetadata) EncryptionAlgorithm() parquet.Algorithm + func (fc FileCryptoMetadata) KeyMetadata() []byte + func (fc FileCryptoMetadata) Len() int + func (fc FileCryptoMetadata) WriteTo(w io.Writer) (int64, error) + type FileMetaData struct + FileDecryptor encryption.FileDecryptor + Schema *schema.Schema + func NewFileMetaData(data []byte, fileDecryptor encryption.FileDecryptor) (*FileMetaData, error) + func (f *FileMetaData) AppendRowGroups(other *FileMetaData) error + func (f *FileMetaData) EncryptionAlgorithm() parquet.Algorithm + func (f *FileMetaData) Equals(other *FileMetaData) bool + func (f *FileMetaData) KeyValueMetadata() KeyValueMetadata + func (f *FileMetaData) NumSchemaElements() int + func (f *FileMetaData) RowGroup(i int) *RowGroupMetaData + func (f *FileMetaData) Serialize(ctx context.Context) ([]byte, error) + func (f *FileMetaData) SerializeString(ctx context.Context) (string, error) + func (f *FileMetaData) SetFilePath(path string) + func (f *FileMetaData) Size() int + func (f *FileMetaData) Subset(rowGroups []int) (*FileMetaData, error) + func (f *FileMetaData) VerifySignature(signature []byte) bool + func (f *FileMetaData) Version() parquet.Version + func (f *FileMetaData) WriteTo(w io.Writer, encryptor encryption.Encryptor) (int64, error) + func (f *FileMetaData) WriterVersion() *AppVersion + type FileMetaDataBuilder struct + func NewFileMetadataBuilder(schema *schema.Schema, props *parquet.WriterProperties, ...) *FileMetaDataBuilder + func (f *FileMetaDataBuilder) AppendRowGroup() *RowGroupMetaDataBuilder + func (f *FileMetaDataBuilder) Finish() (*FileMetaData, error) + func (f *FileMetaDataBuilder) GetFileCryptoMetaData() *FileCryptoMetadata + type FixedLenByteArrayStatistics struct + func NewFixedLenByteArrayStatistics(descr *schema.Column, mem memory.Allocator) *FixedLenByteArrayStatistics + func NewFixedLenByteArrayStatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *FixedLenByteArrayStatistics + func (s *FixedLenByteArrayStatistics) Descr() *schema.Column + func (s *FixedLenByteArrayStatistics) DistinctCount() int64 + func (s *FixedLenByteArrayStatistics) Encode() (enc EncodedStatistics, err error) + func (s *FixedLenByteArrayStatistics) EncodeMax() []byte + func (s *FixedLenByteArrayStatistics) EncodeMin() []byte + func (s *FixedLenByteArrayStatistics) Equals(other TypedStatistics) bool + func (s *FixedLenByteArrayStatistics) HasDistinctCount() bool + func (s *FixedLenByteArrayStatistics) HasMinMax() bool + func (s *FixedLenByteArrayStatistics) HasNullCount() bool + func (s *FixedLenByteArrayStatistics) Max() parquet.FixedLenByteArray + func (s *FixedLenByteArrayStatistics) Merge(other TypedStatistics) + func (s *FixedLenByteArrayStatistics) Min() parquet.FixedLenByteArray + func (s *FixedLenByteArrayStatistics) MinMaxEqual(rhs *FixedLenByteArrayStatistics) bool + func (s *FixedLenByteArrayStatistics) NullCount() int64 + func (s *FixedLenByteArrayStatistics) NumValues() int64 + func (s *FixedLenByteArrayStatistics) Reset() + func (s *FixedLenByteArrayStatistics) SetMinMax(argMin, argMax parquet.FixedLenByteArray) + func (s *FixedLenByteArrayStatistics) Type() parquet.Type + func (s *FixedLenByteArrayStatistics) Update(values []parquet.FixedLenByteArray, numNull int64) + func (s *FixedLenByteArrayStatistics) UpdateSpaced(values []parquet.FixedLenByteArray, validBits []byte, ...) + type Float32Statistics struct + func NewFloat32Statistics(descr *schema.Column, mem memory.Allocator) *Float32Statistics + func NewFloat32StatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *Float32Statistics + func (s *Float32Statistics) Descr() *schema.Column + func (s *Float32Statistics) DistinctCount() int64 + func (s *Float32Statistics) Encode() (enc EncodedStatistics, err error) + func (s *Float32Statistics) EncodeMax() []byte + func (s *Float32Statistics) EncodeMin() []byte + func (s *Float32Statistics) Equals(other TypedStatistics) bool + func (s *Float32Statistics) HasDistinctCount() bool + func (s *Float32Statistics) HasMinMax() bool + func (s *Float32Statistics) HasNullCount() bool + func (s *Float32Statistics) Max() float32 + func (s *Float32Statistics) Merge(other TypedStatistics) + func (s *Float32Statistics) Min() float32 + func (s *Float32Statistics) MinMaxEqual(rhs *Float32Statistics) bool + func (s *Float32Statistics) NullCount() int64 + func (s *Float32Statistics) NumValues() int64 + func (s *Float32Statistics) Reset() + func (s *Float32Statistics) SetMinMax(argMin, argMax float32) + func (s *Float32Statistics) Type() parquet.Type + func (s *Float32Statistics) Update(values []float32, numNull int64) + func (s *Float32Statistics) UpdateSpaced(values []float32, validBits []byte, validBitsOffset, numNull int64) + type Float64Statistics struct + func NewFloat64Statistics(descr *schema.Column, mem memory.Allocator) *Float64Statistics + func NewFloat64StatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *Float64Statistics + func (s *Float64Statistics) Descr() *schema.Column + func (s *Float64Statistics) DistinctCount() int64 + func (s *Float64Statistics) Encode() (enc EncodedStatistics, err error) + func (s *Float64Statistics) EncodeMax() []byte + func (s *Float64Statistics) EncodeMin() []byte + func (s *Float64Statistics) Equals(other TypedStatistics) bool + func (s *Float64Statistics) HasDistinctCount() bool + func (s *Float64Statistics) HasMinMax() bool + func (s *Float64Statistics) HasNullCount() bool + func (s *Float64Statistics) Max() float64 + func (s *Float64Statistics) Merge(other TypedStatistics) + func (s *Float64Statistics) Min() float64 + func (s *Float64Statistics) MinMaxEqual(rhs *Float64Statistics) bool + func (s *Float64Statistics) NullCount() int64 + func (s *Float64Statistics) NumValues() int64 + func (s *Float64Statistics) Reset() + func (s *Float64Statistics) SetMinMax(argMin, argMax float64) + func (s *Float64Statistics) Type() parquet.Type + func (s *Float64Statistics) Update(values []float64, numNull int64) + func (s *Float64Statistics) UpdateSpaced(values []float64, validBits []byte, validBitsOffset, numNull int64) + type Int32Statistics struct + func NewInt32Statistics(descr *schema.Column, mem memory.Allocator) *Int32Statistics + func NewInt32StatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *Int32Statistics + func (s *Int32Statistics) Descr() *schema.Column + func (s *Int32Statistics) DistinctCount() int64 + func (s *Int32Statistics) Encode() (enc EncodedStatistics, err error) + func (s *Int32Statistics) EncodeMax() []byte + func (s *Int32Statistics) EncodeMin() []byte + func (s *Int32Statistics) Equals(other TypedStatistics) bool + func (s *Int32Statistics) HasDistinctCount() bool + func (s *Int32Statistics) HasMinMax() bool + func (s *Int32Statistics) HasNullCount() bool + func (s *Int32Statistics) Max() int32 + func (s *Int32Statistics) Merge(other TypedStatistics) + func (s *Int32Statistics) Min() int32 + func (s *Int32Statistics) MinMaxEqual(rhs *Int32Statistics) bool + func (s *Int32Statistics) NullCount() int64 + func (s *Int32Statistics) NumValues() int64 + func (s *Int32Statistics) Reset() + func (s *Int32Statistics) SetMinMax(argMin, argMax int32) + func (s *Int32Statistics) Type() parquet.Type + func (s *Int32Statistics) Update(values []int32, numNull int64) + func (s *Int32Statistics) UpdateSpaced(values []int32, validBits []byte, validBitsOffset, numNull int64) + type Int64Statistics struct + func NewInt64Statistics(descr *schema.Column, mem memory.Allocator) *Int64Statistics + func NewInt64StatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *Int64Statistics + func (s *Int64Statistics) Descr() *schema.Column + func (s *Int64Statistics) DistinctCount() int64 + func (s *Int64Statistics) Encode() (enc EncodedStatistics, err error) + func (s *Int64Statistics) EncodeMax() []byte + func (s *Int64Statistics) EncodeMin() []byte + func (s *Int64Statistics) Equals(other TypedStatistics) bool + func (s *Int64Statistics) HasDistinctCount() bool + func (s *Int64Statistics) HasMinMax() bool + func (s *Int64Statistics) HasNullCount() bool + func (s *Int64Statistics) Max() int64 + func (s *Int64Statistics) Merge(other TypedStatistics) + func (s *Int64Statistics) Min() int64 + func (s *Int64Statistics) MinMaxEqual(rhs *Int64Statistics) bool + func (s *Int64Statistics) NullCount() int64 + func (s *Int64Statistics) NumValues() int64 + func (s *Int64Statistics) Reset() + func (s *Int64Statistics) SetMinMax(argMin, argMax int64) + func (s *Int64Statistics) Type() parquet.Type + func (s *Int64Statistics) Update(values []int64, numNull int64) + func (s *Int64Statistics) UpdateSpaced(values []int64, validBits []byte, validBitsOffset, numNull int64) + type Int96Statistics struct + func NewInt96Statistics(descr *schema.Column, mem memory.Allocator) *Int96Statistics + func NewInt96StatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) *Int96Statistics + func (s *Int96Statistics) Descr() *schema.Column + func (s *Int96Statistics) DistinctCount() int64 + func (s *Int96Statistics) Encode() (enc EncodedStatistics, err error) + func (s *Int96Statistics) EncodeMax() []byte + func (s *Int96Statistics) EncodeMin() []byte + func (s *Int96Statistics) Equals(other TypedStatistics) bool + func (s *Int96Statistics) HasDistinctCount() bool + func (s *Int96Statistics) HasMinMax() bool + func (s *Int96Statistics) HasNullCount() bool + func (s *Int96Statistics) Max() parquet.Int96 + func (s *Int96Statistics) Merge(other TypedStatistics) + func (s *Int96Statistics) Min() parquet.Int96 + func (s *Int96Statistics) MinMaxEqual(rhs *Int96Statistics) bool + func (s *Int96Statistics) NullCount() int64 + func (s *Int96Statistics) NumValues() int64 + func (s *Int96Statistics) Reset() + func (s *Int96Statistics) SetMinMax(argMin, argMax parquet.Int96) + func (s *Int96Statistics) Type() parquet.Type + func (s *Int96Statistics) Update(values []parquet.Int96, numNull int64) + func (s *Int96Statistics) UpdateSpaced(values []parquet.Int96, validBits []byte, validBitsOffset, numNull int64) + type KeyValueMetadata []*format.KeyValue + func NewKeyValueMetadata() KeyValueMetadata + func (k *KeyValueMetadata) Append(key, value string) error + func (k KeyValueMetadata) Equals(other KeyValueMetadata) bool + func (k KeyValueMetadata) FindValue(key string) *string + func (k KeyValueMetadata) Keys() (ret []string) + func (k KeyValueMetadata) Len() int + func (k KeyValueMetadata) Values() (ret []string) + type PageEncodingStats struct + Encoding parquet.Encoding + PageType format.PageType + type RowGroupMetaData struct + Schema *schema.Schema + func NewRowGroupMetaData(rg *format.RowGroup, sc *schema.Schema, version *AppVersion, ...) *RowGroupMetaData + func (r *RowGroupMetaData) ColumnChunk(i int) (*ColumnChunkMetaData, error) + func (r *RowGroupMetaData) Equals(other *RowGroupMetaData) bool + func (r *RowGroupMetaData) FileOffset() int64 + func (r *RowGroupMetaData) NumColumns() int + func (r *RowGroupMetaData) NumRows() int64 + func (r *RowGroupMetaData) Ordinal() int16 + func (r *RowGroupMetaData) TotalByteSize() int64 + func (r *RowGroupMetaData) TotalCompressedSize() int64 + type RowGroupMetaDataBuilder struct + func NewRowGroupMetaDataBuilder(props *parquet.WriterProperties, schema *schema.Schema, rg *format.RowGroup) *RowGroupMetaDataBuilder + func (r *RowGroupMetaDataBuilder) CurrentColumn() int + func (r *RowGroupMetaDataBuilder) Finish(totalBytesWritten int64, ordinal int16) error + func (r *RowGroupMetaDataBuilder) NextColumnChunk() *ColumnChunkMetaDataBuilder + func (r *RowGroupMetaDataBuilder) NumColumns() int + func (r *RowGroupMetaDataBuilder) NumRows() int64 + func (r *RowGroupMetaDataBuilder) SetNumRows(nrows int) + type StatProvider interface + GetDistinctCount func() int64 + GetMax func() []byte + GetMin func() []byte + GetNullCount func() int64 + IsSetDistinctCount func() bool + IsSetMax func() bool + IsSetMin func() bool + IsSetNullCount func() bool + type TypedStatistics interface + Descr func() *schema.Column + DistinctCount func() int64 + Encode func() (EncodedStatistics, error) + EncodeMax func() []byte + EncodeMin func() []byte + HasDistinctCount func() bool + HasMinMax func() bool + HasNullCount func() bool + Merge func(TypedStatistics) + NullCount func() int64 + NumValues func() int64 + Reset func() + Type func() parquet.Type + func NewStatistics(descr *schema.Column, mem memory.Allocator) TypedStatistics + func NewStatisticsFromEncoded(descr *schema.Column, mem memory.Allocator, nvalues int64, ...) TypedStatistics Other modules containing this package github.com/apache/arrow/go/v10 github.com/apache/arrow/go/v11 github.com/apache/arrow/go/v12 github.com/apache/arrow/go/v13 github.com/apache/arrow/go/v14 github.com/apache/arrow/go/v15 github.com/apache/arrow/go/v16 github.com/apache/arrow/go/v17 github.com/apache/arrow/go/v6 github.com/apache/arrow/go/v7 github.com/apache/arrow/go/v9
Go to main page