document

package
v0.0.0-...-73d4566 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Feb 15, 2025 License: GPL-3.0 Imports: 13 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func AddTypeID 

func AddTypeID[WordID, VariantID comparable](id uint32)

func Parse 

func Parse(str string) (string, []string)

func Root 

func Root(str string) string

Root find the prefix of the string containing letters and numbers.

Types

type ChangeSet 

type ChangeSet[T any] struct {
	Added, Removed slice.Slice[T]
}

ChangeSet shows the IDs that were added and removed from a Document.

type Decoder 

type Decoder[WordID, VariantID any] interface {
	IDToWord(WordID) string
	IDToVariant(VariantID) Variant
}

Encoder supplies the necessary decoding information to translate IDs into strings.

type Document 

type Document[WordID, VariantID comparable] struct {
	ID
	entity.Key
	Start            string
	ByteLen, WordLen int
	// Words holds the root words present in the document. This slice can
	// be reordered without effecting the encoding.
	Words    []Locations[WordID]
	Variants *huffslice.Slice[VariantID]
	// contains filtered or unexported fields
}

Document is a string encoded as the root words. This makes identifying which words are in a document fast.

func (*Document[WordID, VariantID]) Bale 

func (doc *Document[WordID, VariantID]) Bale() *DocumentBale[WordID, VariantID]

func (*Document[WordID, VariantID]) EntLoad 

func (doc *Document[WordID, VariantID]) EntLoad(k entity.Key, data []byte) error

func (*Document[WordID, VariantID]) EntVal 

func (doc *Document[WordID, VariantID]) EntVal(buf []byte) ([]byte, error)

func (*Document[WordID, VariantID]) Save 

func (doc *Document[WordID, VariantID]) Save() (*entity.Ref[Document[WordID, VariantID], *Document[WordID, VariantID]], error)

func (*Document[WordID, VariantID]) WordIDs 

func (doc *Document[WordID, VariantID]) WordIDs() []WordID

WordIDs returns a slice with all the WordIDs in the document.

type DocumentBale 

type DocumentBale[WordID, VariantID comparable] struct {
	ID
	Start            string
	ByteLen, WordLen int
	// Words holds the root words present in the document. This slice can
	// be reordered without effecting the encoding.
	Words    []Locations[WordID]
	Variants *huffslice.SliceBale[VariantID]
}

func (*DocumentBale[WordID, VariantID]) EntRefs 

func (bale *DocumentBale[WordID, VariantID]) EntRefs() []entity.Key

func (*DocumentBale[WordID, VariantID]) TypeID32 

func (bale *DocumentBale[WordID, VariantID]) TypeID32() uint32

func (*DocumentBale[WordID, VariantID]) UnbaleTo 

func (bale *DocumentBale[WordID, VariantID]) UnbaleTo(doc *Document[WordID, VariantID])

type DocumentDecoder 

type DocumentDecoder[WordID, VariantID comparable] struct {
	Decoder[WordID, VariantID]
	WordSingleToken WordID
	VarSingleToken  VariantID
}

DocumentDecoder can decode a Document into a string.

func (DocumentDecoder[WordID, VariantID]) Decode 

func (dec DocumentDecoder[WordID, VariantID]) Decode(doc *Document[WordID, VariantID]) string

Decode a Document to a string

type DocumentEncoder 

type DocumentEncoder[WordID, VariantID comparable] struct {
	Encoder[WordID, VariantID]
	Splitter        func(string) (string, []string)
	RootVariant     func(string) (string, Variant)
	WordSingleToken WordID
	VarSingleToken  VariantID
}

DocumentEncoder can encode a string into a Document.

func (DocumentEncoder[WordID, VariantID]) AddTypeID 

func (enc DocumentEncoder[WordID, VariantID]) AddTypeID(id uint32)

func (DocumentEncoder[WordID, VariantID]) Build 

func (enc DocumentEncoder[WordID, VariantID]) Build(str string) *Document[WordID, VariantID]

Build takes a stirng and encodes it to a Document.

func (DocumentEncoder[WordID, VariantID]) Update 

func (enc DocumentEncoder[WordID, VariantID]) Update(doc *Document[WordID, VariantID], str string) *ChangeSet[WordID]

Update a document updates the encoding and returns a ChangeSet.

type Encoder 

type Encoder[WordID, VariantID any] interface {
	WordToID(string) WordID
	VariantToID(Variant) VariantID
}

Encoder supplies the necessary encoding information to translate strings into IDs.

type ID 

type ID uint32

func (ID) DocID 

func (id ID) DocID() ID

ID fullfils DocIDer

type Locations 

type Locations[T comparable] struct {
	ID   T
	Idxs []uint32
}

Locations hold an ID and the index locations where that ID occures.

type Variant 

type Variant []byte

Variant encodes the casing of a word and the non-alphanumeric characters that follow the word.

func RootVariant 

func RootVariant(str string) (string, Variant)

RootVariant find the prefix of the string containing letters and numbers and the Variant to convert the root back to the original input.

func (Variant) Apply 

func (v Variant) Apply(root string, buf []byte) []byte

Apply a variant to a word. It is expected that the root is all lower case. The casing will be changed according the variant and non-alphanumeric runes will be appended.

Source Files

View all Source files

Directories

Path Synopsis

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.