schema

Documentation

Index

• type Item
  • func NewItem() *Item
• type JSONSchemaItemType
  • func NewJSONSchemaItem() *JSONSchemaItemType
• type PathMapType
  • func NewPathMap(path string) *PathMapType
  • func (self *PathMapType) Add(path []string)
• type SchemaHandler
  • func NewSchemaHandlerFromJSON(str string) (sh *SchemaHandler, err error)
  • func NewSchemaHandlerFromMetadata(mds []string) *SchemaHandler
  • func NewSchemaHandlerFromSchemaList(schemas []*parquet.SchemaElement) *SchemaHandler
  • func NewSchemaHandlerFromStruct(obj interface{}) (sh *SchemaHandler, err error)
  • func (self *SchemaHandler) CreateInExMap()
  • func (self *SchemaHandler) GetColumnNum() int64
  • func (self *SchemaHandler) GetRepetitionType(path []string) (parquet.FieldRepetitionType, error)
  • func (self *SchemaHandler) GetRootName() string
  • func (self *SchemaHandler) MaxDefinitionLevel(path []string) (int32, error)
  • func (self *SchemaHandler) MaxRepetitionLevel(path []string) (int32, error)

Types

type Item

type Item struct {
	GoType reflect.Type
	Info   *common.Tag
}

func NewItem

func NewItem() *Item

type JSONSchemaItemType

type JSONSchemaItemType struct {
	Tag    string
	Fields []*JSONSchemaItemType
}

func NewJSONSchemaItem

func NewJSONSchemaItem() *JSONSchemaItemType

type PathMapType

type PathMapType struct {
	Path     string
	Children map[string]*PathMapType
}

PathMapType records the path and its children; This is used in Marshal for improve performance.

func NewPathMap

func NewPathMap(path string) *PathMapType

func (*PathMapType) Add

func (self *PathMapType) Add(path []string)

type SchemaHandler

type SchemaHandler struct {
	SchemaElements []*parquet.SchemaElement
	MapIndex       map[string]int32
	IndexMap       map[int32]string
	PathMap        *PathMapType
	Infos          []*common.Tag

	InPathToExPath map[string]string
	ExPathToInPath map[string]string

	ValueColumns []string
}

SchemaHandler stores the schema data

func NewSchemaHandlerFromJSON

func NewSchemaHandlerFromJSON(str string) (sh *SchemaHandler, err error)

func NewSchemaHandlerFromMetadata

func NewSchemaHandlerFromMetadata(mds []string) *SchemaHandler

Create a schema handler from CSV metadata

func NewSchemaHandlerFromSchemaList

func NewSchemaHandlerFromSchemaList(schemas []*parquet.SchemaElement) *SchemaHandler

NewSchemaHandlerFromSchemaList creates schema handler from schema list

func NewSchemaHandlerFromStruct

func NewSchemaHandlerFromStruct(obj interface{}) (sh *SchemaHandler, err error)

Create schema handler from a object

func (*SchemaHandler) CreateInExMap

func (self *SchemaHandler) CreateInExMap()

func (*SchemaHandler) GetColumnNum

func (self *SchemaHandler) GetColumnNum() int64

func (*SchemaHandler) GetRepetitionType

func (self *SchemaHandler) GetRepetitionType(path []string) (parquet.FieldRepetitionType, error)

GetRepetitionType returns the repetition type of a column by it's schema path

func (*SchemaHandler) GetRootName

func (self *SchemaHandler) GetRootName() string

Get root name from the schema handler

func (*SchemaHandler) MaxDefinitionLevel

func (self *SchemaHandler) MaxDefinitionLevel(path []string) (int32, error)

MaxDefinitionLevel returns the max definition level type of a column by it's schema path

func (*SchemaHandler) MaxRepetitionLevel

func (self *SchemaHandler) MaxRepetitionLevel(path []string) (int32, error)

MaxRepetitionLevel returns the max repetition level type of a column by it's schema path