simpletext

package
v0.0.2 Latest Latest
Warning

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

 Go to latest Published: Jan 25, 2025 License: Apache-2.0 Imports: 24 Imported by: 11

Documentation

Index

Constants

View Source 
const (
	CODEC_NAME                    = "BKD"
	VERSION_START                 = 0
	VERSION_COMPRESSED_DOC_IDS    = 1
	VERSION_COMPRESSED_VALUES     = 2
	VERSION_IMPLICIT_SPLIT_DIM_1D = 3
	VERSION_CURRENT               = VERSION_IMPLICIT_SPLIT_DIM_1D
	DEFAULT_MAX_MB_SORT_IN_HEAP   = 16.0
)
View Source 
const (
	// POINT_EXTENSION Extension of points data file
	POINT_EXTENSION = "dim"

	// POINT_INDEX_EXTENSION Extension of points index file
	POINT_INDEX_EXTENSION = "dii"
)
View Source 
const (
	BLOCK_SIZE = 8
)
View Source 
const (
	DATA_EXTENSION = "scf"
)
View Source 
const (
	// FIELD_INFOS_EXTENSION Extension of field infos
	FIELD_INFOS_EXTENSION = "inf"
)
View Source 
const (
	NORMS_SEG_EXTENSION = "len"
)
View Source 
const (
	POSTINGS_EXTENSION = "pst"
)

Variables

View Source 
var (
	COMPOUND_FORMAT_HEADER     = []byte("cfs entry for: ")
	COMPOUND_FORMAT_TABLE      = []byte("table of contents, size: ")
	COMPOUND_FORMAT_TABLENAME  = []byte("  filename: ")
	COMPOUND_FORMAT_TABLESTART = []byte("    start: ")
	COMPOUND_FORMAT_TABLEEND   = []byte("    end: ")
	COMPOUND_FORMAT_TABLEPOS   = []byte("table of contents begins at offset: ")
	OFFSETPATTERN              = "0000000000000000000"
)
View Source 
var (
	DOC_VALUES_END   = []byte("END")
	DOC_VALUES_FIELD = []byte("field ")
	DOC_VALUES_TYPE  = []byte("  type ")
	// used for numerics
	DOC_VALUES_MINVALUE = []byte("  minvalue ")
	DOC_VALUES_PATTERN  = []byte("  pattern ")
	// used for bytes
	DOC_VALUES_LENGTH    = []byte("length ")
	DOC_VALUES_MAXLENGTH = []byte("  maxlength ")
	// used for sorted bytes
	DOC_VALUES_NUMVALUES  = []byte("  numvalues ")
	DOC_VALUES_ORDPATTERN = []byte("  ordpattern ")
)
View Source 
var (
	NUMFIELDS       = []byte("number of fields ")
	NAME            = []byte("  name ")
	NUMBER          = []byte("  number ")
	STORETV         = []byte("  term vectors ")
	STORETVPOS      = []byte("  term vector positions ")
	STORETVOFF      = []byte("  term vector offsets ")
	PAYLOADS        = []byte("  payloads ")
	NORMS           = []byte("  norms ")
	DOCVALUES       = []byte("  doc values ")
	DOCVALUES_GEN   = []byte("  doc values gen ")
	INDEXOPTIONS    = []byte("  index options ")
	NUM_ATTS        = []byte("  attributes ")
	ATT_KEY         = []byte("    key ")
	ATT_VALUE       = []byte("    value ")
	DATA_DIM_COUNT  = []byte("  data dimensional count ")
	INDEX_DIM_COUNT = []byte("  index dimensional count ")
	DIM_NUM_BYTES   = []byte("  dimensional num bytes ")
	SOFT_DELETES    = []byte("  soft-deletes ")
)
View Source 
var (
	FIELDS_END          = []byte("END")
	FIELDS_FIELD        = []byte("field ")
	FIELDS_TERM         = []byte("  term ")
	FIELDS_DOC          = []byte("    doc ")
	FIELDS_FREQ         = []byte("      freq ")
	FIELDS_POS          = []byte("      pos ")
	FIELDS_START_OFFSET = []byte("      startOffset ")
	FIELDS_END_OFFSET   = []byte("      endOffset ")
	FIELDS_PAYLOAD      = []byte("        payload ")
)
View Source 
var (
	LIVEDOCS_EXTENSION = "liv"

	LIVE_DOCS_FORMAT_SIZE = []byte("size ")
	LIVE_DOCS_FORMAT_DOC  = []byte("  doc ")
	LIVE_DOCS_FORMAT_END  = []byte("END")
)
View Source 
var (
	NUM_DATA_DIMS   = []byte("num data dims ")
	NUM_INDEX_DIMS  = []byte("num index dims ")
	BYTES_PER_DIM   = []byte("bytes per dim ")
	MAX_LEAF_POINTS = []byte("max leaf points ")
	INDEX_COUNT     = []byte("index count ")
	BLOCK_COUNT     = []byte("block count ")
	BLOCK_DOC_ID    = []byte("  doc ")
	BLOCK_FP        = []byte("  block fp ")
	BLOCK_VALUE     = []byte("  block value ")
	SPLIT_COUNT     = []byte("split count ")
	SPLIT_DIM       = []byte("  split dim ")
	SPLIT_VALUE     = []byte("  split value ")
	FIELD_COUNT     = []byte("field count ")
	FIELD_FP_NAME   = []byte("  field fp name ")
	FIELD_FP        = []byte("  field fp ")
	MIN_VALUE       = []byte("min value ")
	MAX_VALUE       = []byte("max value ")
	POINT_COUNT     = []byte("point count ")
	DOC_COUNT       = []byte("doc count ")
	END             = []byte("END")
)
View Source 
var (
	SI_VERSION     = []byte("    version ")
	SI_MIN_VERSION = []byte("    min version ")
	SI_DOCCOUNT    = []byte("    number of documents ")
	SI_USECOMPOUND = []byte("    uses compound file ")
	SI_NUM_DIAG    = []byte("    diagnostics ")
	SI_DIAG_KEY    = []byte("      key ")
	SI_DIAG_VALUE  = []byte("      value ")
	SI_NUM_ATT     = []byte("    attributes ")
	SI_ATT_KEY     = []byte("      key ")
	SI_ATT_VALUE   = []byte("      value ")
	SI_NUM_FILES   = []byte("    files ")
	SI_FILE        = []byte("      file ")
	SI_ID          = []byte("    id ")
	SI_SORT        = []byte("    sort ")
	SI_SORT_TYPE   = []byte("      type ")
	SI_SORT_NAME   = []byte("      name ")
	SI_SORT_BYTES  = []byte("      bytes ")
	SI_EXTENSION   = "si"
)
View Source 
var (
	SKIP_LIST     = []byte("    skipList ")
	LEVEL_LENGTH  = []byte("      levelLength ")
	LEVEL         = []byte("      level ")
	SKIP_DOC      = []byte("        skipDoc ")
	SKIP_DOC_FP   = []byte("        skipDocFP ")
	IMPACTS       = []byte("        impacts ")
	IMPACT        = []byte("          impact ")
	FREQ          = []byte("            freq ")
	NORM          = []byte("            norm ")
	IMPACTS_END   = []byte("        impactsEnd ")
	CHILD_POINTER = []byte("        childPointer ")
)
View Source 
var (
	FIELDS_EXTENSION         = "fld"
	STORED_FIELD_TYPE_STRING = []byte("string")
	STORED_FIELD_TYPE_BINARY = []byte("binary")
	STORED_FIELD_TYPE_INT    = []byte("int")
	STORED_FIELD_TYPE_LONG   = []byte("long")
	STORED_FIELD_TYPE_FLOAT  = []byte("float")
	STORED_FIELD_TYPE_DOUBLE = []byte("double")
	STORED_FIELD_END         = []byte("END")
	STORED_FIELD_DOC         = []byte("doc ")
	STORED_FIELD_FIELD       = []byte("  field ")
	STORED_FIELD_NAME        = []byte("    name ")
	STORED_FIELD_TYPE        = []byte("    type ")
	STORED_FIELD_VALUE       = []byte("    value ")
)
View Source 
var (
	VECTORS_EXTENSION = "vec"

	VECTORS_END            = []byte("END")
	VECTORS_DOC            = []byte("doc ")
	VECTORS_NUMFIELDS      = []byte("  numfields ")
	VECTORS_FIELD          = []byte("  field ")
	VECTORS_FIELDNAME      = []byte("    name ")
	VECTORS_FIELDPOSITIONS = []byte("    positions ")
	VECTORS_FIELDOFFSETS   = []byte("    offsets   ")
	VECTORS_FIELDPAYLOADS  = []byte("    payloads  ")
	VECTORS_FIELDTERMCOUNT = []byte("    numterms ")
	VECTORS_TERMTEXT       = []byte("    term ")
	VECTORS_TERMFREQ       = []byte("      freq ")
	VECTORS_POSITION       = []byte("      position ")
	VECTORS_PAYLOAD        = []byte("        payload ")
	VECTORS_STARTOFFSET    = []byte("        startoffset ")
	VECTORS_ENDOFFSET      = []byte("        endoffset ")
)

Functions

func SortK 

func SortK(data sort.Interface, k int)

Types

type BKDReader 

type BKDReader struct {
	// contains filtered or unexported fields
}

func NewBKDReader 

func NewBKDReader(in store.IndexInput, numDims, numIndexDims, maxPointsInLeafNode, bytesPerDim int,
	leafBlockFPs []int64, splitPackedValues []byte, minPackedValue, maxPackedValue []byte,
	pointCount int, docCount int) (*BKDReader, error)

func (*BKDReader) EstimateDocCount 

func (s *BKDReader) EstimateDocCount(ctx context.Context, visitor types.IntersectVisitor) (int, error)

func (*BKDReader) EstimatePointCount 

func (s *BKDReader) EstimatePointCount(ctx context.Context, visitor types.IntersectVisitor) (int, error)

func (*BKDReader) GetBytesPerDimension 

func (s *BKDReader) GetBytesPerDimension() (int, error)

func (*BKDReader) GetDocCount 

func (s *BKDReader) GetDocCount() int

func (*BKDReader) GetMaxPackedValue 

func (s *BKDReader) GetMaxPackedValue() ([]byte, error)

func (*BKDReader) GetMinPackedValue 

func (s *BKDReader) GetMinPackedValue() ([]byte, error)

func (*BKDReader) GetNumDimensions 

func (s *BKDReader) GetNumDimensions() (int, error)

func (*BKDReader) GetNumIndexDimensions 

func (s *BKDReader) GetNumIndexDimensions() (int, error)

func (*BKDReader) Intersect 

func (s *BKDReader) Intersect(ctx context.Context, visitor types.IntersectVisitor) error

func (*BKDReader) NewIntersectState 

func (s *BKDReader) NewIntersectState(in store.IndexInput,
	numDims, packedBytesLength, maxPointsInLeafNode int,
	visitor types.IntersectVisitor) *IntersectState

func (*BKDReader) Size 

func (s *BKDReader) Size() int

type BKDWriter 

type BKDWriter struct {
	// contains filtered or unexported fields
}

func NewBKDWriter 

func NewBKDWriter(maxDoc int, tempDir store.Directory, tempFileNamePrefix string,
	config *bkd.Config, maxMBSortInHeap float64, totalPointCount int) *BKDWriter

func (*BKDWriter) Add 

func (s *BKDWriter) Add(ctx context.Context, packedValue []byte, docID int) error

func (*BKDWriter) Finish 

func (s *BKDWriter) Finish(out store.IndexOutput) (int64, error)

Finish Writes the BKD tree to the provided IndexOutput and returns the file offset where index was written.

func (*BKDWriter) GetPointCount 

func (s *BKDWriter) GetPointCount() int

GetPointCount How many points have been added so far

func (*BKDWriter) WriteField 

func (s *BKDWriter) WriteField(out store.IndexOutput, fieldName string, reader types.MutablePointValues) (int64, error)

WriteField Write a field from a MutablePointValues. This way of writing points is faster than regular writes with add since there is opportunity for reordering points before writing them to disk. This method does not use transient disk in order to reorder points.

type BytesOutput 

type BytesOutput struct {
	*store.BaseDataOutput
	// contains filtered or unexported fields
}

func NewBytesOutput 

func NewBytesOutput() *BytesOutput

func (*BytesOutput) Write 

func (b *BytesOutput) Write(bs []byte) (n int, err error)

func (*BytesOutput) WriteByte 

func (b *BytesOutput) WriteByte(c byte) error

type Codec 

type Codec struct {
	// contains filtered or unexported fields
}

Codec plain text index format. FOR RECREATIONAL USE ONLY lucene.experimental

func NewCodec 

func NewCodec() *Codec

func (*Codec) CompoundFormat 

func (s *Codec) CompoundFormat() index.CompoundFormat

func (*Codec) DocValuesFormat 

func (s *Codec) DocValuesFormat() index.DocValuesFormat

func (*Codec) FieldInfosFormat 

func (s *Codec) FieldInfosFormat() index.FieldInfosFormat

func (*Codec) GetName 

func (s *Codec) GetName() string

func (*Codec) LiveDocsFormat 

func (s *Codec) LiveDocsFormat() index.LiveDocsFormat

func (*Codec) NormsFormat 

func (s *Codec) NormsFormat() index.NormsFormat

func (*Codec) PointsFormat 

func (s *Codec) PointsFormat() index.PointsFormat

func (*Codec) PostingsFormat 

func (s *Codec) PostingsFormat() index.PostingsFormat

func (*Codec) SegmentInfoFormat 

func (s *Codec) SegmentInfoFormat() index.SegmentInfoFormat

func (*Codec) StoredFieldsFormat 

func (s *Codec) StoredFieldsFormat() index.StoredFieldsFormat

func (*Codec) TermVectorsFormat 

func (s *Codec) TermVectorsFormat() index.TermVectorsFormat

type CompoundFormat 

type CompoundFormat struct {
}

CompoundFormat plain text compound format. FOR RECREATIONAL USE ONLY lucene.experimental

func NewCompoundFormat 

func NewCompoundFormat() *CompoundFormat

func (*CompoundFormat) GetCompoundReader 

func (s *CompoundFormat) GetCompoundReader(ctx context.Context, dir store.Directory, si index.SegmentInfo, context *store.IOContext) (index.CompoundDirectory, error)

func (*CompoundFormat) Write 

func (s *CompoundFormat) Write(ctx context.Context, dir store.Directory, si index.SegmentInfo, ioContext *store.IOContext) error

type DocValuesFormat 

type DocValuesFormat struct {
	// contains filtered or unexported fields
}

DocValuesFormat * plain text doc values format. FOR RECREATIONAL USE ONLY the .dat file contains the data. for numbers this is a "fixed-width" file, for example a single byte range: 

field myField
  type NUMERIC
  minvalue 0
  pattern 000
005
T
234
T
123
T
...

so a document's value (delta encoded from minvalue) can be retrieved by seeking to startOffset + (1+pattern.length()+2)*docid. The extra 1 is the newline. The extra 2 is another newline and 'T' or 'F': true if the value is real, false if missing. for bytes this is also a "fixed-width" file, for example: 

field myField
  type BINARY
  maxlength 6
  pattern 0
length 6
foobar[space][space]
T
length 3
baz[space][space][space][space][space]
T
...

so a doc's value can be retrieved by seeking to startOffset + (9+pattern.length+maxlength+2)*doc the extra 9 is 2 newlines, plus "length " itself. the extra 2 is another newline and 'T' or 'F': true if the value is real, false if missing. for sorted bytes this is a fixed-width file, for example: 

field myField
  type SORTED
  numvalues 10
  maxLength 8
  pattern 0
  ordpattern 00
length 6
foobar[space][space]
length 3
baz[space][space][space][space][space]
...
03
06
01
10
...

so the "ord section" begins at startOffset + (9+pattern.length+maxlength)*numValues. a document's ord can be retrieved by seeking to "ord section" + (1+ordpattern.length())*docid an ord's value can be retrieved by seeking to startOffset + (9+pattern.length+maxlength)*ord for sorted set this is a fixed-width file very similar to the SORTED case, for example: 

  field myField
    type SORTED_SET
    numvalues 10
    maxLength 8
    pattern 0
    ordpattern XXXXX
  length 6
  foobar[space][space]
  length 3
  baz[space][space][space][space][space]
  ...
  0,3,5
  1,2

  10
  ...

so the "ord section" begins at startOffset + (9+pattern.length+maxlength)*numValues.
a document's ord list can be retrieved by seeking to "ord section" + (1+ordpattern.length())*docid
this is a comma-separated list, and it's padded with spaces to be fixed width. so trim() and split() it.
and beware the empty string! an ord's value can be retrieved by seeking to
startOffset + (9+pattern.length+maxlength)*ord for sorted numerics, it's encoded (not very creatively)
as a comma-separated list of strings the same as binary. beware the empty string! the reader can just
scan this file when it opens, skipping over the data blocks and saving the offset/etc for each field.

lucene.experimental

func NewSimpleTextDocValuesFormat 

func NewSimpleTextDocValuesFormat() *DocValuesFormat

func (*DocValuesFormat) FieldsConsumer 

func (s *DocValuesFormat) FieldsConsumer(ctx context.Context, state *index.SegmentWriteState) (index.DocValuesConsumer, error)

func (*DocValuesFormat) FieldsProducer 

func (s *DocValuesFormat) FieldsProducer(ctx context.Context, state *index.SegmentReadState) (index.DocValuesProducer, error)

func (*DocValuesFormat) GetName 

func (s *DocValuesFormat) GetName() string

type DocValuesIterator 

type DocValuesIterator interface {
	types.DocIdSetIterator

	AdvanceExact(target int) (bool, error)
}

type DocValuesReader 

type DocValuesReader struct {
	// contains filtered or unexported fields
}

func NewDocValuesReader 

func NewDocValuesReader(ctx context.Context, state *index.SegmentReadState, ext string) (*DocValuesReader, error)

func (*DocValuesReader) CheckIntegrity 

func (s *DocValuesReader) CheckIntegrity() error

func (*DocValuesReader) Close 

func (s *DocValuesReader) Close() error

func (*DocValuesReader) GetBinary 

func (s *DocValuesReader) GetBinary(ctx context.Context, fieldInfo *document.FieldInfo) (index.BinaryDocValues, error)

func (*DocValuesReader) GetMergeInstance 

func (s *DocValuesReader) GetMergeInstance() index.DocValuesProducer

func (*DocValuesReader) GetNumeric 

func (s *DocValuesReader) GetNumeric(ctx context.Context, fieldInfo *document.FieldInfo) (index.NumericDocValues, error)

func (*DocValuesReader) GetSorted 

func (s *DocValuesReader) GetSorted(ctx context.Context, fieldInfo *document.FieldInfo) (index.SortedDocValues, error)

func (*DocValuesReader) GetSortedNumeric 

func (s *DocValuesReader) GetSortedNumeric(ctx context.Context, fieldInfo *document.FieldInfo) (index.SortedNumericDocValues, error)

func (*DocValuesReader) GetSortedSet 

func (s *DocValuesReader) GetSortedSet(ctx context.Context, fieldInfo *document.FieldInfo) (index.SortedSetDocValues, error)

type DocValuesWriter 

type DocValuesWriter struct {
	// contains filtered or unexported fields
}

func NewDocValuesWriter 

func NewDocValuesWriter(ctx context.Context, state *index.SegmentWriteState, ext string) (*DocValuesWriter, error)

func (*DocValuesWriter) AddBinaryField 

func (s *DocValuesWriter) AddBinaryField(ctx context.Context, field *document.FieldInfo, valuesProducer index.DocValuesProducer) error

func (*DocValuesWriter) AddNumericField 

func (s *DocValuesWriter) AddNumericField(ctx context.Context, field *document.FieldInfo, valuesProducer index.DocValuesProducer) error

func (*DocValuesWriter) AddSortedField 

func (s *DocValuesWriter) AddSortedField(ctx context.Context, field *document.FieldInfo, valuesProducer index.DocValuesProducer) error

func (*DocValuesWriter) AddSortedNumericField 

func (s *DocValuesWriter) AddSortedNumericField(ctx context.Context, field *document.FieldInfo, valuesProducer index.DocValuesProducer) error

func (*DocValuesWriter) AddSortedSetField 

func (s *DocValuesWriter) AddSortedSetField(ctx context.Context, field *document.FieldInfo, valuesProducer index.DocValuesProducer) error

func (*DocValuesWriter) Close 

func (s *DocValuesWriter) Close() error

type DocsEnum 

type DocsEnum struct {
	// contains filtered or unexported fields
}

func (*DocsEnum) Advance 

func (s *DocsEnum) Advance(ctx context.Context, target int) (int, error)

func (*DocsEnum) AdvanceShallow 

func (s *DocsEnum) AdvanceShallow(ctx context.Context, target int) error

func (*DocsEnum) CanReuse 

func (s *DocsEnum) CanReuse(in store.IndexInput) bool

func (*DocsEnum) Cost 

func (s *DocsEnum) Cost() int64

func (*DocsEnum) DocID 

func (s *DocsEnum) DocID() int

func (*DocsEnum) EndOffset 

func (s *DocsEnum) EndOffset() (int, error)

func (*DocsEnum) Freq 

func (s *DocsEnum) Freq() (int, error)

func (*DocsEnum) GetImpacts 

func (s *DocsEnum) GetImpacts() (index.Impacts, error)

func (*DocsEnum) GetPayload 

func (s *DocsEnum) GetPayload() ([]byte, error)

func (*DocsEnum) NextDoc 

func (s *DocsEnum) NextDoc(ctx context.Context) (int, error)

func (*DocsEnum) NextPosition 

func (s *DocsEnum) NextPosition() (int, error)

func (*DocsEnum) SlowAdvance 

func (s *DocsEnum) SlowAdvance(ctx context.Context, target int) (int, error)

func (*DocsEnum) StartOffset 

func (s *DocsEnum) StartOffset() (int, error)

type FieldInfosFormat 

type FieldInfosFormat struct {
}

FieldInfosFormat plaintext field infos format FOR RECREATIONAL USE ONLY lucene.experimental

func NewSimpleTextFieldInfosFormat 

func NewSimpleTextFieldInfosFormat() *FieldInfosFormat

func (*FieldInfosFormat) Read 

func (s *FieldInfosFormat) Read(ctx context.Context, directory store.Directory, segmentInfo index.SegmentInfo, segmentSuffix string, ioContext *store.IOContext) (index.FieldInfos, error)

func (*FieldInfosFormat) Write 

func (s *FieldInfosFormat) Write(ctx context.Context, directory store.Directory, segmentInfo index.SegmentInfo, segmentSuffix string, infos index.FieldInfos, ioContext *store.IOContext) error

type FieldsReader 

type FieldsReader struct {
	// contains filtered or unexported fields
}

func NewSimpleTextFieldsReader 

func NewSimpleTextFieldsReader(state *index.SegmentReadState) (*FieldsReader, error)

func (*FieldsReader) CheckIntegrity 

func (s *FieldsReader) CheckIntegrity() error

func (*FieldsReader) Close 

func (s *FieldsReader) Close() error

func (*FieldsReader) GetMergeInstance 

func (s *FieldsReader) GetMergeInstance() index.FieldsProducer

func (*FieldsReader) Names 

func (s *FieldsReader) Names() []string

func (*FieldsReader) NewSimpleTextDocsEnum 

func (s *FieldsReader) NewSimpleTextDocsEnum() *DocsEnum

func (*FieldsReader) Size 

func (s *FieldsReader) Size() int

func (*FieldsReader) Terms 

func (s *FieldsReader) Terms(field string) (index.Terms, error)

type IntersectState 

type IntersectState struct {
	// contains filtered or unexported fields
}

IntersectState Used to track all state for a single call to intersect.

type LiveDocsFormat 

type LiveDocsFormat struct {
}

LiveDocsFormat reads/writes plaintext live docs FOR RECREATIONAL USE ONLY lucene.experimental

func NewLiveDocsFormat 

func NewLiveDocsFormat() *LiveDocsFormat

func (*LiveDocsFormat) Files 

func (s *LiveDocsFormat) Files(ctx context.Context, info index.SegmentCommitInfo, files map[string]struct{}) (map[string]struct{}, error)

func (*LiveDocsFormat) ReadLiveDocs 

func (s *LiveDocsFormat) ReadLiveDocs(ctx context.Context, dir store.Directory, info index.SegmentCommitInfo, ioContext *store.IOContext) (util.Bits, error)

func (*LiveDocsFormat) WriteLiveDocs 

func (s *LiveDocsFormat) WriteLiveDocs(ctx context.Context, bits util.Bits, dir store.Directory, info index.SegmentCommitInfo, newDelCount int, ioContext *store.IOContext) error

type NormsFormat 

type NormsFormat struct {
}

NormsFormat plain-text norms format. FOR RECREATIONAL USE ONLY

func NewNormsFormat 

func NewNormsFormat() *NormsFormat

func (*NormsFormat) NormsConsumer 

func (s *NormsFormat) NormsConsumer(ctx context.Context, state *index.SegmentWriteState) (index.NormsConsumer, error)

func (*NormsFormat) NormsProducer 

func (s *NormsFormat) NormsProducer(ctx context.Context, state *index.SegmentReadState) (index.NormsProducer, error)

type OneField 

type OneField struct {
	// contains filtered or unexported fields
}

func NewOneField 

func NewOneField() *OneField

type PointsFormat 

type PointsFormat struct {
}

PointsFormat For debugging, curiosity, transparency only!! Do not use this codec in production. This codec stores all dimensional data in a single human-readable text file (_N.dim). You can view this in any text editor, and even edit it to alter your index. lucene.experimental

func NewPointsFormat 

func NewPointsFormat() *PointsFormat

func (*PointsFormat) FieldsReader 

func (s *PointsFormat) FieldsReader(ctx context.Context, state *index.SegmentReadState) (index.PointsReader, error)

func (*PointsFormat) FieldsWriter 

func (s *PointsFormat) FieldsWriter(ctx context.Context, state *index.SegmentWriteState) (index.PointsWriter, error)

type PointsReader 

type PointsReader struct {
	// contains filtered or unexported fields
}

func NewPointsReader 

func NewPointsReader(ctx context.Context, readState *index.SegmentReadState) (*PointsReader, error)

func (*PointsReader) CheckIntegrity 

func (s *PointsReader) CheckIntegrity() error

func (*PointsReader) Close 

func (s *PointsReader) Close() error

func (*PointsReader) GetMergeInstance 

func (s *PointsReader) GetMergeInstance() index.PointsReader

func (*PointsReader) GetValues 

func (s *PointsReader) GetValues(ctx context.Context, field string) (types.PointValues, error)

type PointsWriter 

type PointsWriter struct {
	*coreIndex.BasePointsWriter
	// contains filtered or unexported fields
}

func NewPointsWriter 

func NewPointsWriter(ctx context.Context, writeState *index.SegmentWriteState) (*PointsWriter, error)

func (*PointsWriter) Close 

func (s *PointsWriter) Close() error

func (*PointsWriter) Finish 

func (s *PointsWriter) Finish() error

func (*PointsWriter) WriteField 

func (s *PointsWriter) WriteField(ctx context.Context, fieldInfo *document.FieldInfo, reader index.PointsReader) error

type PostingsEnum 

type PostingsEnum struct {
	// contains filtered or unexported fields
}

func (*PostingsEnum) Advance 

func (s *PostingsEnum) Advance(ctx context.Context, target int) (int, error)

func (*PostingsEnum) AdvanceShallow 

func (s *PostingsEnum) AdvanceShallow(ctx context.Context, target int) error

func (*PostingsEnum) Cost 

func (s *PostingsEnum) Cost() int64

func (*PostingsEnum) DocID 

func (s *PostingsEnum) DocID() int

func (*PostingsEnum) EndOffset 

func (s *PostingsEnum) EndOffset() (int, error)

func (*PostingsEnum) Freq 

func (s *PostingsEnum) Freq() (int, error)

func (*PostingsEnum) GetImpacts 

func (s *PostingsEnum) GetImpacts() (index.Impacts, error)

func (*PostingsEnum) GetPayload 

func (s *PostingsEnum) GetPayload() ([]byte, error)

func (*PostingsEnum) NextDoc 

func (s *PostingsEnum) NextDoc(ctx context.Context) (int, error)

func (*PostingsEnum) NextPosition 

func (s *PostingsEnum) NextPosition() (int, error)

func (*PostingsEnum) SlowAdvance 

func (s *PostingsEnum) SlowAdvance(ctx context.Context, target int) (int, error)

func (*PostingsEnum) StartOffset 

func (s *PostingsEnum) StartOffset() (int, error)

type PostingsFormat 

type PostingsFormat struct {
	// contains filtered or unexported fields
}

PostingsFormat For debugging, curiosity, transparency only!! Do not use this codec in production. This codec stores all postings data in a single human-readable text file (_N.pst). You can view this in any text editor, and even edit it to alter your index. lucene.experimental

func NewPostingsFormat 

func NewPostingsFormat() *PostingsFormat

func (*PostingsFormat) FieldsConsumer 

func (s *PostingsFormat) FieldsConsumer(ctx context.Context, state *index.SegmentWriteState) (index.FieldsConsumer, error)

func (*PostingsFormat) FieldsProducer 

func (s *PostingsFormat) FieldsProducer(ctx context.Context, state *index.SegmentReadState) (index.FieldsProducer, error)

func (*PostingsFormat) GetName 

func (s *PostingsFormat) GetName() string

type SegmentInfoFormat 

type SegmentInfoFormat struct {
}

func NewSegmentInfoFormat 

func NewSegmentInfoFormat() *SegmentInfoFormat

func (*SegmentInfoFormat) Read 

func (s *SegmentInfoFormat) Read(ctx context.Context, dir store.Directory,
	segmentName string, segmentID []byte, ioContext *store.IOContext) (index.SegmentInfo, error)

func (*SegmentInfoFormat) Write 

func (s *SegmentInfoFormat) Write(ctx context.Context, dir store.Directory, si index.SegmentInfo, ioContext *store.IOContext) error

type SimpleTVDocsEnum 

type SimpleTVDocsEnum struct {
	// contains filtered or unexported fields
}

SimpleTVDocsEnum note: these two enum classes are exactly like the Default impl...

func NewSimpleTVDocsEnum 

func NewSimpleTVDocsEnum() *SimpleTVDocsEnum

func (*SimpleTVDocsEnum) Advance 

func (s *SimpleTVDocsEnum) Advance(ctx context.Context, target int) (int, error)

func (*SimpleTVDocsEnum) Cost 

func (s *SimpleTVDocsEnum) Cost() int64

func (*SimpleTVDocsEnum) DocID 

func (s *SimpleTVDocsEnum) DocID() int

func (*SimpleTVDocsEnum) EndOffset 

func (s *SimpleTVDocsEnum) EndOffset() (int, error)

func (*SimpleTVDocsEnum) Freq 

func (s *SimpleTVDocsEnum) Freq() (int, error)

func (*SimpleTVDocsEnum) GetPayload 

func (s *SimpleTVDocsEnum) GetPayload() ([]byte, error)

func (*SimpleTVDocsEnum) NextDoc 

func (s *SimpleTVDocsEnum) NextDoc(ctx context.Context) (int, error)

func (*SimpleTVDocsEnum) NextPosition 

func (s *SimpleTVDocsEnum) NextPosition() (int, error)

func (*SimpleTVDocsEnum) Reset 

func (s *SimpleTVDocsEnum) Reset(freq int)

func (*SimpleTVDocsEnum) SlowAdvance 

func (s *SimpleTVDocsEnum) SlowAdvance(ctx context.Context, target int) (int, error)

func (*SimpleTVDocsEnum) StartOffset 

func (s *SimpleTVDocsEnum) StartOffset() (int, error)

type SimpleTVFields 

type SimpleTVFields struct {
	// contains filtered or unexported fields
}

func NewSimpleTVFields 

func NewSimpleTVFields(fields *treemap.Map[string, index.Terms]) *SimpleTVFields

func (*SimpleTVFields) Names 

func (s *SimpleTVFields) Names() []string

func (*SimpleTVFields) Size 

func (s *SimpleTVFields) Size() int

func (*SimpleTVFields) Terms 

func (s *SimpleTVFields) Terms(field string) (index.Terms, error)

type SimpleTVPostings 

type SimpleTVPostings struct {
	// contains filtered or unexported fields
}

func NewSimpleTVPostings 

func NewSimpleTVPostings() *SimpleTVPostings

type SimpleTVPostingsEnum 

type SimpleTVPostingsEnum struct {
	// contains filtered or unexported fields
}

func NewSimpleTVPostingsEnum 

func NewSimpleTVPostingsEnum() *SimpleTVPostingsEnum

func (*SimpleTVPostingsEnum) Advance 

func (s *SimpleTVPostingsEnum) Advance(ctx context.Context, target int) (int, error)

func (*SimpleTVPostingsEnum) Cost 

func (s *SimpleTVPostingsEnum) Cost() int64

func (*SimpleTVPostingsEnum) DocID 

func (s *SimpleTVPostingsEnum) DocID() int

func (*SimpleTVPostingsEnum) EndOffset 

func (s *SimpleTVPostingsEnum) EndOffset() (int, error)

func (*SimpleTVPostingsEnum) Freq 

func (s *SimpleTVPostingsEnum) Freq() (int, error)

func (*SimpleTVPostingsEnum) GetPayload 

func (s *SimpleTVPostingsEnum) GetPayload() ([]byte, error)

func (*SimpleTVPostingsEnum) NextDoc 

func (s *SimpleTVPostingsEnum) NextDoc(ctx context.Context) (int, error)

func (*SimpleTVPostingsEnum) NextPosition 

func (s *SimpleTVPostingsEnum) NextPosition() (int, error)

func (*SimpleTVPostingsEnum) Reset 

func (s *SimpleTVPostingsEnum) Reset(positions, startOffsets, endOffsets []int, payloads [][]byte)

func (*SimpleTVPostingsEnum) SlowAdvance 

func (s *SimpleTVPostingsEnum) SlowAdvance(ctx context.Context, target int) (int, error)

func (*SimpleTVPostingsEnum) StartOffset 

func (s *SimpleTVPostingsEnum) StartOffset() (int, error)

type SimpleTVTerms 

type SimpleTVTerms struct {
	*coreIndex.BaseTerms
	// contains filtered or unexported fields
}

func NewSimpleTVTerms 

func NewSimpleTVTerms(hasOffsets, hasPositions, hasPayloads bool) *SimpleTVTerms

func (*SimpleTVTerms) GetDocCount 

func (s *SimpleTVTerms) GetDocCount() (int, error)

func (*SimpleTVTerms) GetSumDocFreq 

func (s *SimpleTVTerms) GetSumDocFreq() (int64, error)

func (*SimpleTVTerms) GetSumTotalTermFreq 

func (s *SimpleTVTerms) GetSumTotalTermFreq() (int64, error)

func (*SimpleTVTerms) HasFreqs 

func (s *SimpleTVTerms) HasFreqs() bool

func (*SimpleTVTerms) HasOffsets 

func (s *SimpleTVTerms) HasOffsets() bool

func (*SimpleTVTerms) HasPayloads 

func (s *SimpleTVTerms) HasPayloads() bool

func (*SimpleTVTerms) HasPositions 

func (s *SimpleTVTerms) HasPositions() bool

func (*SimpleTVTerms) Iterator 

func (s *SimpleTVTerms) Iterator() (index.TermsEnum, error)

func (*SimpleTVTerms) Size 

func (s *SimpleTVTerms) Size() (int, error)

type SimpleTVTermsEnum 

type SimpleTVTermsEnum struct {
	*coreIndex.BaseTermsEnum
	// contains filtered or unexported fields
}

func NewSimpleTVTermsEnum 

func NewSimpleTVTermsEnum(terms *treemap.Map[[]byte, *SimpleTVPostings]) *SimpleTVTermsEnum

func (*SimpleTVTermsEnum) DocFreq 

func (s *SimpleTVTermsEnum) DocFreq() (int, error)

func (*SimpleTVTermsEnum) Impacts 

func (s *SimpleTVTermsEnum) Impacts(flags int) (index.ImpactsEnum, error)

func (*SimpleTVTermsEnum) Next 

func (s *SimpleTVTermsEnum) Next(context.Context) ([]byte, error)

func (*SimpleTVTermsEnum) Ord 

func (s *SimpleTVTermsEnum) Ord() (int64, error)

func (*SimpleTVTermsEnum) Postings 

func (s *SimpleTVTermsEnum) Postings(reuse index.PostingsEnum, flags int) (index.PostingsEnum, error)

func (*SimpleTVTermsEnum) SeekCeil 

func (s *SimpleTVTermsEnum) SeekCeil(ctx context.Context, text []byte) (index.SeekStatus, error)

func (*SimpleTVTermsEnum) SeekExactByOrd 

func (s *SimpleTVTermsEnum) SeekExactByOrd(ctx context.Context, ord int64) error

func (*SimpleTVTermsEnum) Term 

func (s *SimpleTVTermsEnum) Term() ([]byte, error)

func (*SimpleTVTermsEnum) TotalTermFreq 

func (s *SimpleTVTermsEnum) TotalTermFreq() (int64, error)

type SimpleTextNormsConsumer 

type SimpleTextNormsConsumer struct {
	*coreIndex.NormsConsumerDefault
	// contains filtered or unexported fields
}

SimpleTextNormsConsumer Writes plain-text norms. FOR RECREATIONAL USE ONLY

func NewSimpleTextNormsConsumer 

func NewSimpleTextNormsConsumer(ctx context.Context, state *index.SegmentWriteState) (*SimpleTextNormsConsumer, error)

func (*SimpleTextNormsConsumer) AddNormsField 

func (s *SimpleTextNormsConsumer) AddNormsField(ctx context.Context, field *document.FieldInfo, normsProducer index.NormsProducer) error

func (*SimpleTextNormsConsumer) Close 

func (s *SimpleTextNormsConsumer) Close() error

type SimpleTextNormsProducer 

type SimpleTextNormsProducer struct {
	// contains filtered or unexported fields
}

func NewSimpleTextNormsProducer 

func NewSimpleTextNormsProducer(state *index.SegmentReadState) (*SimpleTextNormsProducer, error)

func (*SimpleTextNormsProducer) CheckIntegrity 

func (s *SimpleTextNormsProducer) CheckIntegrity() error

func (*SimpleTextNormsProducer) Close 

func (s *SimpleTextNormsProducer) Close() error

func (*SimpleTextNormsProducer) GetMergeInstance 

func (s *SimpleTextNormsProducer) GetMergeInstance() index.NormsProducer

func (*SimpleTextNormsProducer) GetNorms 

func (s *SimpleTextNormsProducer) GetNorms(field *document.FieldInfo) (index.NumericDocValues, error)

type SkipReader 

type SkipReader struct {
	// contains filtered or unexported fields
}

func NewSkipReader 

func NewSkipReader(skipStream store.IndexInput) *SkipReader

func (*SkipReader) GetImpacts 

func (s *SkipReader) GetImpacts() index.Impacts

func (*SkipReader) GetNextSkipDoc 

func (s *SkipReader) GetNextSkipDoc() int

func (*SkipReader) GetNextSkipDocFP 

func (s *SkipReader) GetNextSkipDocFP() int64

func (*SkipReader) Reset 

func (s *SkipReader) Reset(ctx context.Context, skipPointer int64, docFreq int) error

func (*SkipReader) SkipTo 

func (s *SkipReader) SkipTo(ctx context.Context, target int) (int, error)

type SkipWriter 

type SkipWriter struct {
	// contains filtered or unexported fields
}

func NewSkipWriter 

func NewSkipWriter(writeState *index.SegmentWriteState) (*SkipWriter, error)

func (*SkipWriter) BufferSkip 

func (s *SkipWriter) BufferSkip(ctx context.Context, doc int, docFilePointer int64, numDocs int,
	accumulator *coreIndex.CompetitiveImpactAccumulator) error

func (*SkipWriter) ResetSkip 

func (s *SkipWriter) ResetSkip() error

func (*SkipWriter) WriteSkip 

func (s *SkipWriter) WriteSkip(ctx context.Context, out store.IndexOutput) (int64, error)

type StoredFieldsFormat 

type StoredFieldsFormat struct {
}

func NewStoredFieldsFormat 

func NewStoredFieldsFormat() *StoredFieldsFormat

func (*StoredFieldsFormat) FieldsReader 

func (s *StoredFieldsFormat) FieldsReader(ctx context.Context, directory store.Directory, si index.SegmentInfo, fn index.FieldInfos, ioContext *store.IOContext) (index.StoredFieldsReader, error)

func (*StoredFieldsFormat) FieldsWriter 

func (s *StoredFieldsFormat) FieldsWriter(ctx context.Context, directory store.Directory, si index.SegmentInfo, ioContext *store.IOContext) (index.StoredFieldsWriter, error)

type StoredFieldsReader 

type StoredFieldsReader struct {
	// contains filtered or unexported fields
}

StoredFieldsReader reads plaintext stored fields FOR RECREATIONAL USE ONLY lucene.experimental

func NewStoredFieldsReader 

func NewStoredFieldsReader(ctx context.Context, directory store.Directory,
	si index.SegmentInfo, fn index.FieldInfos, ioContext *store.IOContext) (*StoredFieldsReader, error)

func (*StoredFieldsReader) CheckIntegrity 

func (s *StoredFieldsReader) CheckIntegrity() error

func (*StoredFieldsReader) Clone 

func (s *StoredFieldsReader) Clone(context.Context) index.StoredFieldsReader

func (*StoredFieldsReader) Close 

func (s *StoredFieldsReader) Close() error

func (*StoredFieldsReader) GetMergeInstance 

func (s *StoredFieldsReader) GetMergeInstance() index.StoredFieldsReader

func (*StoredFieldsReader) VisitDocument 

func (s *StoredFieldsReader) VisitDocument(ctx context.Context, docID int, visitor document.StoredFieldVisitor) error

type StoredFieldsWriter 

type StoredFieldsWriter struct {
	// contains filtered or unexported fields
}

func NewStoredFieldsWriter 

func NewStoredFieldsWriter(ctx context.Context, dir store.Directory, segment string, ioContext *store.IOContext) (*StoredFieldsWriter, error)

func (*StoredFieldsWriter) Close 

func (s *StoredFieldsWriter) Close() error

func (*StoredFieldsWriter) Finish 

func (s *StoredFieldsWriter) Finish(ctx context.Context, fis index.FieldInfos, numDocs int) error

func (*StoredFieldsWriter) FinishDocument 

func (s *StoredFieldsWriter) FinishDocument(ctx context.Context) error

func (*StoredFieldsWriter) StartDocument 

func (s *StoredFieldsWriter) StartDocument(ctx context.Context) error

func (*StoredFieldsWriter) WriteField 

func (s *StoredFieldsWriter) WriteField(ctx context.Context, info *document.FieldInfo, field document.IndexableField) error

type TermVectorsFormat 

type TermVectorsFormat struct {
}

func NewTermVectorsFormat 

func NewTermVectorsFormat() *TermVectorsFormat

func (*TermVectorsFormat) VectorsReader 

func (s *TermVectorsFormat) VectorsReader(ctx context.Context, dir store.Directory, segmentInfo index.SegmentInfo, fieldInfos index.FieldInfos, ioContext *store.IOContext) (index.TermVectorsReader, error)

func (*TermVectorsFormat) VectorsWriter 

func (s *TermVectorsFormat) VectorsWriter(ctx context.Context, dir store.Directory, segmentInfo index.SegmentInfo, ioContext *store.IOContext) (index.TermVectorsWriter, error)

type TermVectorsReader 

type TermVectorsReader struct {
	// contains filtered or unexported fields
}

TermVectorsReader Reads plain-text term vectors. FOR RECREATIONAL USE ONLY lucene.experimental

func NewTermVectorsReader 

func NewTermVectorsReader(ctx context.Context, directory store.Directory, si index.SegmentInfo, ioContext *store.IOContext) (*TermVectorsReader, error)

func (*TermVectorsReader) CheckIntegrity 

func (s *TermVectorsReader) CheckIntegrity() error

func (*TermVectorsReader) Clone 

func (s *TermVectorsReader) Clone(context.Context) index.TermVectorsReader

func (*TermVectorsReader) Close 

func (s *TermVectorsReader) Close() error

func (*TermVectorsReader) Get 

func (s *TermVectorsReader) Get(ctx context.Context, doc int) (index.Fields, error)

func (*TermVectorsReader) GetMergeInstance 

func (s *TermVectorsReader) GetMergeInstance() index.TermVectorsReader

type TermVectorsWriter 

type TermVectorsWriter struct {
	// contains filtered or unexported fields
}

TermVectorsWriter Writes plain-text term vectors. FOR RECREATIONAL USE ONLY lucene.experimental

func NewTermVectorsWriter 

func NewTermVectorsWriter(ctx context.Context, dir store.Directory, segment string, ioContext *store.IOContext) (*TermVectorsWriter, error)

func (*TermVectorsWriter) AddPosition 

func (s *TermVectorsWriter) AddPosition(ctx context.Context, position, startOffset, endOffset int, payload []byte) error

func (*TermVectorsWriter) Close 

func (s *TermVectorsWriter) Close() error

func (*TermVectorsWriter) Finish 

func (s *TermVectorsWriter) Finish(ctx context.Context, fis index.FieldInfos, numDocs int) error

func (*TermVectorsWriter) FinishDocument 

func (s *TermVectorsWriter) FinishDocument(context.Context) error

func (*TermVectorsWriter) FinishField 

func (s *TermVectorsWriter) FinishField(context.Context) error

func (*TermVectorsWriter) FinishTerm 

func (s *TermVectorsWriter) FinishTerm(context.Context) error

func (*TermVectorsWriter) StartDocument 

func (s *TermVectorsWriter) StartDocument(ctx context.Context, numVectorFields int) error

func (*TermVectorsWriter) StartField 

func (s *TermVectorsWriter) StartField(ctx context.Context, info *document.FieldInfo, numTerms int, positions, offsets, payloads bool) error

func (*TermVectorsWriter) StartTerm 

func (s *TermVectorsWriter) StartTerm(ctx context.Context, term []byte, freq int) error

type TextFieldsWriter 

type TextFieldsWriter struct {
	// contains filtered or unexported fields
}

func NewFieldsWriter 

func NewFieldsWriter(ctx context.Context, writeState *index.SegmentWriteState) (*TextFieldsWriter, error)

func (*TextFieldsWriter) Close 

func (s *TextFieldsWriter) Close() error

func (*TextFieldsWriter) Write 

func (s *TextFieldsWriter) Write(ctx context.Context, fields index.Fields, norms index.NormsProducer) error

Source Files

View all Source files

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.