sour

package module
v0.1.0 Latest Latest
Warning

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

 Go to latest Published: Dec 5, 2021 License: Apache-2.0 Imports: 8 Imported by: 0

README

sour

PkgGoDev Tests Lint License

Will this bluge.Document match this bluge.Query? This library allows you to efficiently answer this question.

	s := sour.New(bluge.InMemoryOnlyConfig())

	s.Reset(bluge.NewDocument("id").
		AddField(bluge.NewKeywordField("name", "sour")))

	dmi, err := s.Search(context.Background(),
		bluge.NewTopNSearch(0, bluge.NewTermQuery("sour").SetField("name")).
		WithStandardAggregations())
	if err != nil {
		panic(err)
	}
	if dmi.Aggregations().Count() > 0 {
		fmt.Println("matches name sour")
	} else {
		fmt.Println("does not match name sour")
	}

Details

  • This implementation is NOT thread-safe. If you need to run multiple queries concurrently, you must use separate Sour instances.
  • Loading stored fields is not supported

Approach

  • Single document, data sizes are small.
  • Therefore, avoid heavy document analysis and complex data structures.
  • After regular document analysis is complete, use this structure in place.
  • Do not build more complicated structures like vellums or roaring bitmaps.
  • If additional structure is needed, prefer arrays which have good cache locality, and can be reused.
  • Avoid copying data, prefer sub-slicing, and brute-force processing over arrays.
  • Cache reusable parts of the query, as we expect the same query to be run over multiple documents.

License

Apache License Version 2.0

Documentation

Overview

Example 
package main

import (
	"context"
	"fmt"

	"github.com/blugelabs/bluge"
	"github.com/blugelabs/sour"
)

func main() {
	s := sour.New(bluge.InMemoryOnlyConfig())

	s.Reset(bluge.NewDocument("id").
		AddField(bluge.NewKeywordField("name", "sour")))

	dmi, err := s.Search(context.Background(),
		bluge.NewTopNSearch(0, bluge.NewTermQuery("sour").SetField("name")).
			WithStandardAggregations())
	if err != nil {
		panic(err)
	}
	if dmi.Aggregations().Count() > 0 {
		fmt.Println("matches name sour")
	} else {
		fmt.Println("does not match name sour")
	}
}

Output:

matches name sour

Index

Examples

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type CollectionStats 

type CollectionStats struct{}

func (*CollectionStats) DocumentCount 

func (c *CollectionStats) DocumentCount() uint64

DocumentCount returns the number of documents with at least one term for this field

func (*CollectionStats) Merge 

func (c *CollectionStats) Merge(segment.CollectionStats)

func (*CollectionStats) SumTotalTermFrequency 

func (c *CollectionStats) SumTotalTermFrequency() uint64

SumTotalTermFrequency returns to total number of tokens across all documents

func (*CollectionStats) TotalDocumentCount 

func (c *CollectionStats) TotalDocumentCount() uint64

type DictEntry 

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

func (*DictEntry) Count 

func (d *DictEntry) Count() uint64

func (*DictEntry) Term 

func (d *DictEntry) Term() string

type Dictionary 

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

func (*Dictionary) Close 

func (d *Dictionary) Close() error

func (*Dictionary) Contains 

func (d *Dictionary) Contains(key []byte) (bool, error)

type DictionaryIterator 

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

func NewDictionaryIteratorWithTerms 

func NewDictionaryIteratorWithTerms(terms []string, include func(string) bool) *DictionaryIterator

func NewFieldDictEmpty 

func NewFieldDictEmpty() *DictionaryIterator

func (*DictionaryIterator) Close 

func (d *DictionaryIterator) Close() error

func (*DictionaryIterator) Next 

func (d *DictionaryIterator) Next() (segment.DictionaryEntry, error)

type DocValueReader 

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

func (*DocValueReader) VisitDocumentValues 

func (d *DocValueReader) VisitDocumentValues(number uint64, visitor segment.DocumentValueVisitor) error

type Location 

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

func (Location) End 

func (l Location) End() int

func (Location) Field 

func (l Location) Field() string

func (Location) Pos 

func (l Location) Pos() int

func (Location) Size 

func (l Location) Size() int

func (Location) Start 

func (l Location) Start() int

type Posting 

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

func (*Posting) Frequency 

func (p *Posting) Frequency() int

func (*Posting) Locations 

func (p *Posting) Locations() []segment.Location

func (*Posting) Norm 

func (p *Posting) Norm() float64

func (*Posting) Number 

func (p *Posting) Number() uint64

func (*Posting) SetNumber 

func (p *Posting) SetNumber(num uint64)

func (*Posting) Size 

func (p *Posting) Size() int

type Sour 

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

func New 

func New(cfg bluge.Config) *Sour

func NewWithDocument 

func NewWithDocument(cfg bluge.Config, doc *bluge.Document) *Sour

func (*Sour) Close 

func (s *Sour) Close() error

func (*Sour) CollectionStats 

func (s *Sour) CollectionStats(field string) (segment.CollectionStats, error)

func (*Sour) DictionaryIterator 

func (s *Sour) DictionaryIterator(field string, automaton segment.Automaton, start,
	end []byte) (segment.DictionaryIterator, error)

DictionaryIterator provides a way to explore the terms used in the specified field. You can optionally filter these terms by the provided Automaton, or start/end terms.

func (*Sour) DictionaryLookup 

func (s *Sour) DictionaryLookup(field string) (segment.DictionaryLookup, error)

func (*Sour) DocumentValueReader 

func (s *Sour) DocumentValueReader(fields []string) (segment.DocumentValueReader, error)

func (*Sour) Fields 

func (s *Sour) Fields() []string

func (*Sour) PostingsIterator 

func (s *Sour) PostingsIterator(term []byte, field string, includeFreq, includeNorm,
	includeTermVectors bool) (segment.PostingsIterator, error)

PostingsIterator provides a way to find information about all documents that use the specified term in the specified field.

func (*Sour) Reset 

func (s *Sour) Reset(doc *bluge.Document)

func (*Sour) Search 

func (s *Sour) Search(ctx context.Context, req bluge.SearchRequest) (search.DocumentMatchIterator, error)

func (*Sour) SortedTermsForField 

func (s *Sour) SortedTermsForField(fieldName string) ([]string, error)

func (*Sour) TokenFreqsAndLen 

func (s *Sour) TokenFreqsAndLen(fieldName string) (analysis.TokenFrequencies, int, error)

func (*Sour) VisitStoredFields 

func (s *Sour) VisitStoredFields(number uint64, visitor segment.StoredFieldVisitor) error

type TermFieldReader 

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

func NewTermFieldReaderEmpty 

func NewTermFieldReaderEmpty() *TermFieldReader

func NewTermFieldReaderFromTokenFreqAndLen 

func NewTermFieldReaderFromTokenFreqAndLen(tf *analysis.TokenFreq, l int, includeFreq, includeNorm,
	includeTermVectors bool) *TermFieldReader

func (*TermFieldReader) Advance 

func (t *TermFieldReader) Advance(docNum uint64) (segment.Posting, error)

Advance resets the enumeration at specified document or its immediate follower.

func (*TermFieldReader) Close 

func (t *TermFieldReader) Close() error

func (*TermFieldReader) Count 

func (t *TermFieldReader) Count() uint64

func (*TermFieldReader) Empty 

func (t *TermFieldReader) Empty() bool

func (*TermFieldReader) Next 

func (t *TermFieldReader) Next() (segment.Posting, error)

func (*TermFieldReader) Size 

func (t *TermFieldReader) Size() int

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.