Integrate BACKBEAT SDK and resolve KACHING license validation

Major integrations and fixes:
- Added BACKBEAT SDK integration for P2P operation timing
- Implemented beat-aware status tracking for distributed operations
- Added Docker secrets support for secure license management
- Resolved KACHING license validation via HTTPS/TLS
- Updated docker-compose configuration for clean stack deployment
- Disabled rollback policies to prevent deployment failures
- Added license credential storage (CHORUS-DEV-MULTI-001)

Technical improvements:
- BACKBEAT P2P operation tracking with phase management
- Enhanced configuration system with file-based secrets
- Improved error handling for license validation
- Clean separation of KACHING and CHORUS deployment stacks

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
anthonyrawlins
2025-09-06 07:56:26 +10:00
parent 543ab216f9
commit 9bdcbe0447
4730 changed files with 1480093 additions and 1916 deletions

View File

@@ -0,0 +1,37 @@
linters:
# please, do not use `enable-all`: it's deprecated and will be removed soon.
# inverted configuration with `enable-all` and `disable` is not scalable during updates of golangci-lint
disable-all: true
enable:
- bodyclose
- deadcode
- depguard
- dogsled
- dupl
- errcheck
- goconst
- gocritic
- gocyclo
- gofmt
- goimports
- gomnd
- goprintffuncname
- gosimple
- govet
- ineffassign
- interfacer
- lll
- misspell
- nakedret
- nolintlint
- rowserrcheck
- scopelint
- staticcheck
- structcheck
- stylecheck
- typecheck
- unconvert
- unparam
- unused
- varcheck
- whitespace

202
vendor/github.com/blevesearch/bleve_index_api/LICENSE generated vendored Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

View File

@@ -0,0 +1,11 @@
# Bleve Index API
[![PkgGoDev](https://pkg.go.dev/badge/github.com/blevesearch/bleve_index_api)](https://pkg.go.dev/github.com/blevesearch/bleve_index_api)
[![Tests](https://github.com/blevesearch/bleve_index_api/workflows/Tests/badge.svg?branch=master&event=push)](https://github.com/blevesearch/bleve_index_api/actions?query=workflow%3ATests+event%3Apush+branch%3Amaster)
[![Lint](https://github.com/blevesearch/bleve_index_api/workflows/Lint/badge.svg?branch=master&event=push)](https://github.com/blevesearch/bleve_index_api/actions?query=workflow%3ALint+event%3Apush+branch%3Amaster)
Bleve supports a pluggable Index interface.
By placing these interfaces in their own, *hopefully* slowly evolving module, it frees up Bleve and the underlying index to each introduce new major versions without interfering with one another.
With that in mind, we anticipate introducing non-breaking changes only to this module, and keeping the major version at 1.x for some time.

View File

@@ -0,0 +1,53 @@
// Copyright (c) 2015 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
type AnalysisWork func()
type AnalysisQueue struct {
queue chan AnalysisWork
done chan struct{}
}
func (q *AnalysisQueue) Queue(work AnalysisWork) {
q.queue <- work
}
func (q *AnalysisQueue) Close() {
close(q.done)
}
func NewAnalysisQueue(numWorkers int) *AnalysisQueue {
rv := AnalysisQueue{
queue: make(chan AnalysisWork),
done: make(chan struct{}),
}
for i := 0; i < numWorkers; i++ {
go AnalysisWorker(rv)
}
return &rv
}
func AnalysisWorker(q AnalysisQueue) {
// read work off the queue
for {
select {
case <-q.done:
return
case w := <-q.queue:
w()
}
}
}

101
vendor/github.com/blevesearch/bleve_index_api/batch.go generated vendored Normal file
View File

@@ -0,0 +1,101 @@
// Copyright (c) 2020 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import "fmt"
type BatchCallback func(error)
type Batch struct {
IndexOps map[string]Document
InternalOps map[string][]byte
persistedCallback BatchCallback
}
func NewBatch() *Batch {
return &Batch{
IndexOps: make(map[string]Document),
InternalOps: make(map[string][]byte),
}
}
func (b *Batch) Update(doc Document) {
b.IndexOps[doc.ID()] = doc
}
func (b *Batch) Delete(id string) {
b.IndexOps[id] = nil
}
func (b *Batch) SetInternal(key, val []byte) {
b.InternalOps[string(key)] = val
}
func (b *Batch) DeleteInternal(key []byte) {
b.InternalOps[string(key)] = nil
}
func (b *Batch) SetPersistedCallback(f BatchCallback) {
b.persistedCallback = f
}
func (b *Batch) PersistedCallback() BatchCallback {
return b.persistedCallback
}
func (b *Batch) String() string {
rv := fmt.Sprintf("Batch (%d ops, %d internal ops)\n", len(b.IndexOps), len(b.InternalOps))
for k, v := range b.IndexOps {
if v != nil {
rv += fmt.Sprintf("\tINDEX - '%s'\n", k)
} else {
rv += fmt.Sprintf("\tDELETE - '%s'\n", k)
}
}
for k, v := range b.InternalOps {
if v != nil {
rv += fmt.Sprintf("\tSET INTERNAL - '%s'\n", k)
} else {
rv += fmt.Sprintf("\tDELETE INTERNAL - '%s'\n", k)
}
}
return rv
}
func (b *Batch) Reset() {
b.IndexOps = make(map[string]Document)
b.InternalOps = make(map[string][]byte)
b.persistedCallback = nil
}
func (b *Batch) Merge(o *Batch) {
for k, v := range o.IndexOps {
b.IndexOps[k] = v
}
for k, v := range o.InternalOps {
b.InternalOps[k] = v
}
}
func (b *Batch) TotalDocSize() int {
var s int
for k, v := range b.IndexOps {
if v != nil {
s += v.Size() + sizeOfString
}
s += len(k)
}
return s
}

View File

@@ -0,0 +1,23 @@
// Copyright (c) 2021 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import (
"io"
)
type Directory interface {
GetWriter(filePath string) (io.WriteCloser, error)
}

View File

@@ -0,0 +1,126 @@
// Copyright (c) 2015 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import (
"net"
"time"
)
type Document interface {
ID() string
Size() int
VisitFields(visitor FieldVisitor)
VisitComposite(visitor CompositeFieldVisitor)
HasComposite() bool
NumPlainTextBytes() uint64
AddIDField()
StoredFieldsBytes() uint64
Indexed() bool
}
type FieldVisitor func(Field)
type Field interface {
Name() string
Value() []byte
ArrayPositions() []uint64
EncodedFieldType() byte
Analyze()
Options() FieldIndexingOptions
AnalyzedLength() int
AnalyzedTokenFrequencies() TokenFrequencies
NumPlainTextBytes() uint64
}
type CompositeFieldVisitor func(field CompositeField)
type CompositeField interface {
Field
Compose(field string, length int, freq TokenFrequencies)
}
type TextField interface {
Text() string
}
type NumericField interface {
Number() (float64, error)
}
type DateTimeField interface {
DateTime() (time.Time, string, error)
}
type BooleanField interface {
Boolean() (bool, error)
}
type GeoPointField interface {
Lon() (float64, error)
Lat() (float64, error)
}
type GeoShapeField interface {
GeoShape() (GeoJSON, error)
EncodedShape() []byte
}
type IPField interface {
IP() (net.IP, error)
}
// TokenizableSpatialField is an optional interface for fields that
// supports pluggable custom hierarchial spatial token generation.
type TokenizableSpatialField interface {
// SetSpatialAnalyzerPlugin lets the index implementations to
// initialise relevant spatial analyzer plugins for the field
// to override the spatial token generations during the analysis phase.
SetSpatialAnalyzerPlugin(SpatialAnalyzerPlugin)
}
// SynonymField represents a field that contains a list of synonyms for a set of terms.
// Each SynonymField is generated from a single synonym definition, and its name corresponds
// to the synonym source to which the synonym definition belongs.
type SynonymField interface {
Field
// IterateSynonyms iterates over the synonyms for the term in the field.
// The provided visitor function is called with each term and its corresponding synonyms.
IterateSynonyms(visitor func(term string, synonyms []string))
}
// SynonymFieldVisitor is a function type used to visit a SynonymField within a document.
type SynonymFieldVisitor func(SynonymField)
// SynonymDocument represents a special type of document that contains synonym fields.
// Each SynonymField is a field with a list of synonyms for a set of terms.
// These fields are derived from synonym definitions, and their names correspond to the synonym sources.
type SynonymDocument interface {
Document
// VisitSynonymFields allows iteration over all synonym fields in the document.
// The provided visitor function is called for each synonym field.
VisitSynonymFields(visitor SynonymFieldVisitor)
}

106
vendor/github.com/blevesearch/bleve_index_api/freq.go generated vendored Normal file
View File

@@ -0,0 +1,106 @@
// Copyright (c) 2020 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import "reflect"
var reflectStaticSizeTokenLocation int
var reflectStaticSizeTokenFreq int
func init() {
var tl TokenLocation
reflectStaticSizeTokenLocation = int(reflect.TypeOf(tl).Size())
var tf TokenFreq
reflectStaticSizeTokenFreq = int(reflect.TypeOf(tf).Size())
}
// TokenLocation represents one occurrence of a term at a particular location in
// a field. Start, End and Position have the same meaning as in analysis.Token.
// Field and ArrayPositions identify the field value in the source document.
// See document.Field for details.
type TokenLocation struct {
Field string
ArrayPositions []uint64
Start int
End int
Position int
}
func (tl *TokenLocation) Size() int {
rv := reflectStaticSizeTokenLocation
rv += len(tl.ArrayPositions) * sizeOfUint64
return rv
}
// TokenFreq represents all the occurrences of a term in all fields of a
// document.
type TokenFreq struct {
Term []byte
Locations []*TokenLocation
frequency int
}
func (tf *TokenFreq) Size() int {
rv := reflectStaticSizeTokenFreq
rv += len(tf.Term)
for _, loc := range tf.Locations {
rv += loc.Size()
}
return rv
}
func (tf *TokenFreq) Frequency() int {
return tf.frequency
}
func (tf *TokenFreq) SetFrequency(frequency int) {
tf.frequency = frequency
}
// TokenFrequencies maps document terms to their combined frequencies from all
// fields.
type TokenFrequencies map[string]*TokenFreq
func (tfs TokenFrequencies) Size() int {
rv := sizeOfMap
rv += len(tfs) * (sizeOfString + sizeOfPtr)
for k, v := range tfs {
rv += len(k)
rv += v.Size()
}
return rv
}
func (tfs TokenFrequencies) MergeAll(remoteField string, other TokenFrequencies) {
// walk the new token frequencies
for tfk, tf := range other {
// set the remoteField value in incoming token freqs
for _, l := range tf.Locations {
l.Field = remoteField
}
existingTf, exists := tfs[tfk]
if exists {
existingTf.Locations = append(existingTf.Locations, tf.Locations...)
existingTf.frequency += tf.frequency
} else {
tfs[tfk] = &TokenFreq{
Term: tf.Term,
frequency: tf.frequency,
Locations: make([]*TokenLocation, len(tf.Locations)),
}
copy(tfs[tfk].Locations, tf.Locations)
}
}
}

354
vendor/github.com/blevesearch/bleve_index_api/index.go generated vendored Normal file
View File

@@ -0,0 +1,354 @@
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import (
"bytes"
"context"
"reflect"
)
var reflectStaticSizeTermFieldDoc int
var reflectStaticSizeTermFieldVector int
func init() {
var tfd TermFieldDoc
reflectStaticSizeTermFieldDoc = int(reflect.TypeOf(tfd).Size())
var tfv TermFieldVector
reflectStaticSizeTermFieldVector = int(reflect.TypeOf(tfv).Size())
}
type Index interface {
Open() error
Close() error
Update(doc Document) error
Delete(id string) error
Batch(batch *Batch) error
SetInternal(key, val []byte) error
DeleteInternal(key []byte) error
// Reader returns a low-level accessor on the index data. Close it to
// release associated resources.
Reader() (IndexReader, error)
StatsMap() map[string]interface{}
}
// CopyIndex is an extended index that supports copying to a new location online.
// Use the CopyReader method to obtain a reader for initiating the copy operation.
type CopyIndex interface {
Index
// Obtain a copy reader for the online copy/backup operation,
// to handle necessary bookkeeping, instead of using the regular IndexReader.
CopyReader() CopyReader
}
// EventIndex is an optional interface for exposing the support for firing event
// callbacks for various events in the index.
type EventIndex interface {
// FireIndexEvent is used to fire an event callback when Index() is called,
// to notify the caller that a document has been added to the index.
FireIndexEvent()
}
type IndexReader interface {
TermFieldReader(ctx context.Context, term []byte, field string, includeFreq, includeNorm, includeTermVectors bool) (TermFieldReader, error)
// DocIDReader returns an iterator over all doc ids
// The caller must close returned instance to release associated resources.
DocIDReaderAll() (DocIDReader, error)
DocIDReaderOnly(ids []string) (DocIDReader, error)
FieldDict(field string) (FieldDict, error)
// FieldDictRange is currently defined to include the start and end terms
FieldDictRange(field string, startTerm []byte, endTerm []byte) (FieldDict, error)
FieldDictPrefix(field string, termPrefix []byte) (FieldDict, error)
Document(id string) (Document, error)
DocValueReader(fields []string) (DocValueReader, error)
Fields() ([]string, error)
GetInternal(key []byte) ([]byte, error)
DocCount() (uint64, error)
ExternalID(id IndexInternalID) (string, error)
InternalID(id string) (IndexInternalID, error)
Close() error
}
type BM25Reader interface {
IndexReader
FieldCardinality(field string) (int, error)
}
// CopyReader is an extended index reader for backup or online copy operations, replacing the regular index reader.
type CopyReader interface {
IndexReader
// CopyTo performs an online copy or backup of the index to the specified directory.
CopyTo(d Directory) error
// CloseCopyReader must be used instead of Close() to close the copy reader.
CloseCopyReader() error
}
// RegexAutomaton abstracts an automaton built using a regex pattern.
type RegexAutomaton interface {
// MatchesRegex returns true if the given string matches the regex pattern
// used to build the automaton.
MatchesRegex(string) bool
}
// IndexReaderRegexp provides functionality to work with regex-based field dictionaries.
type IndexReaderRegexp interface {
// FieldDictRegexp returns a FieldDict for terms matching the specified regex pattern
// in the dictionary of the given field.
FieldDictRegexp(field string, regex string) (FieldDict, error)
// FieldDictRegexpAutomaton returns a FieldDict and a RegexAutomaton that can be used
// to match strings against the regex pattern.
FieldDictRegexpAutomaton(field string, regex string) (FieldDict, RegexAutomaton, error)
}
// FuzzyAutomaton abstracts a Levenshtein automaton built using a term and a fuzziness value.
type FuzzyAutomaton interface {
// MatchAndDistance checks if the given string is within the fuzziness distance
// of the term used to build the automaton. It also returns the edit (Levenshtein)
// distance between the string and the term.
MatchAndDistance(term string) (bool, uint8)
}
// IndexReaderFuzzy provides functionality to work with fuzzy matching in field dictionaries.
type IndexReaderFuzzy interface {
// FieldDictFuzzy returns a FieldDict for terms that are within the specified fuzziness
// distance of the given term and match the specified prefix in the given field.
FieldDictFuzzy(field string, term string, fuzziness int, prefix string) (FieldDict, error)
// FieldDictFuzzyAutomaton returns a FieldDict and a FuzzyAutomaton that can be used
// to calculate the edit distance between the term and other strings.
FieldDictFuzzyAutomaton(field string, term string, fuzziness int, prefix string) (FieldDict, FuzzyAutomaton, error)
}
type IndexReaderContains interface {
FieldDictContains(field string) (FieldDictContains, error)
}
// SpatialIndexPlugin is an optional interface for exposing the
// support for any custom analyzer plugins that are capable of
// generating hierarchial spatial tokens for both indexing and
// query purposes from the geo location data.
type SpatialIndexPlugin interface {
GetSpatialAnalyzerPlugin(typ string) (SpatialAnalyzerPlugin, error)
}
type TermFieldVector struct {
Field string
ArrayPositions []uint64
Pos uint64
Start uint64
End uint64
}
func (tfv *TermFieldVector) Size() int {
return reflectStaticSizeTermFieldVector + sizeOfPtr +
len(tfv.Field) + len(tfv.ArrayPositions)*sizeOfUint64
}
// IndexInternalID is an opaque document identifier interal to the index impl
type IndexInternalID []byte
func (id IndexInternalID) Equals(other IndexInternalID) bool {
return id.Compare(other) == 0
}
func (id IndexInternalID) Compare(other IndexInternalID) int {
return bytes.Compare(id, other)
}
type TermFieldDoc struct {
Term string
ID IndexInternalID
Freq uint64
Norm float64
Vectors []*TermFieldVector
}
func (tfd *TermFieldDoc) Size() int {
sizeInBytes := reflectStaticSizeTermFieldDoc + sizeOfPtr +
len(tfd.Term) + len(tfd.ID)
for _, entry := range tfd.Vectors {
sizeInBytes += entry.Size()
}
return sizeInBytes
}
// Reset allows an already allocated TermFieldDoc to be reused
func (tfd *TermFieldDoc) Reset() *TermFieldDoc {
// remember the []byte used for the ID
id := tfd.ID
vectors := tfd.Vectors
// idiom to copy over from empty TermFieldDoc (0 allocations)
*tfd = TermFieldDoc{}
// reuse the []byte already allocated (and reset len to 0)
tfd.ID = id[:0]
tfd.Vectors = vectors[:0]
return tfd
}
// TermFieldReader is the interface exposing the enumeration of documents
// containing a given term in a given field. Documents are returned in byte
// lexicographic order over their identifiers.
type TermFieldReader interface {
// Next returns the next document containing the term in this field, or nil
// when it reaches the end of the enumeration. The preAlloced TermFieldDoc
// is optional, and when non-nil, will be used instead of allocating memory.
Next(preAlloced *TermFieldDoc) (*TermFieldDoc, error)
// Advance resets the enumeration at specified document or its immediate
// follower.
Advance(ID IndexInternalID, preAlloced *TermFieldDoc) (*TermFieldDoc, error)
// Count returns the number of documents contains the term in this field.
Count() uint64
Close() error
Size() int
}
type DictEntry struct {
Term string
Count uint64
EditDistance uint8
}
type FieldDict interface {
Next() (*DictEntry, error)
Close() error
Cardinality() int
BytesRead() uint64
}
type FieldDictContains interface {
Contains(key []byte) (bool, error)
BytesRead() uint64
}
// DocIDReader is the interface exposing enumeration of documents identifiers.
// Close the reader to release associated resources.
type DocIDReader interface {
// Next returns the next document internal identifier in the natural
// index order, nil when the end of the sequence is reached.
Next() (IndexInternalID, error)
// Advance resets the iteration to the first internal identifier greater than
// or equal to ID. If ID is smaller than the start of the range, the iteration
// will start there instead. If ID is greater than or equal to the end of
// the range, Next() call will return io.EOF.
Advance(ID IndexInternalID) (IndexInternalID, error)
Size() int
Close() error
}
type DocValueVisitor func(field string, term []byte)
type DocValueReader interface {
VisitDocValues(id IndexInternalID, visitor DocValueVisitor) error
BytesRead() uint64
}
// IndexBuilder is an interface supported by some index schemes
// to allow direct write-only index building
type IndexBuilder interface {
Index(doc Document) error
Close() error
}
// ThesaurusTermReader is an interface for enumerating synonyms of a term in a thesaurus.
type ThesaurusTermReader interface {
// Next returns the next synonym of the term, or an error if something goes wrong.
// Returns nil when the enumeration is complete.
Next() (string, error)
// Close releases any resources associated with the reader.
Close() error
Size() int
}
// ThesaurusEntry represents a term in the thesaurus for which synonyms are stored.
type ThesaurusEntry struct {
Term string
}
// ThesaurusKeys is an interface for enumerating terms (keys) in a thesaurus.
type ThesaurusKeys interface {
// Next returns the next key in the thesaurus, or an error if something goes wrong.
// Returns nil when the enumeration is complete.
Next() (*ThesaurusEntry, error)
// Close releases any resources associated with the reader.
Close() error
}
// ThesaurusReader is an interface for accessing a thesaurus in the index.
type ThesaurusReader interface {
IndexReader
// ThesaurusTermReader returns a reader for the synonyms of a given term in the
// specified thesaurus.
ThesaurusTermReader(ctx context.Context, name string, term []byte) (ThesaurusTermReader, error)
// ThesaurusKeys returns a reader for all terms in the specified thesaurus.
ThesaurusKeys(name string) (ThesaurusKeys, error)
// ThesaurusKeysFuzzy returns a reader for terms in the specified thesaurus that
// match the given prefix and are within the specified fuzziness distance from
// the provided term.
ThesaurusKeysFuzzy(name string, term string, fuzziness int, prefix string) (ThesaurusKeys, error)
// ThesaurusKeysRegexp returns a reader for terms in the specified thesaurus that
// match the given regular expression pattern.
ThesaurusKeysRegexp(name string, regex string) (ThesaurusKeys, error)
// ThesaurusKeysPrefix returns a reader for terms in the specified thesaurus that
// start with the given prefix.
ThesaurusKeysPrefix(name string, termPrefix []byte) (ThesaurusKeys, error)
}
// EligibleDocumentSelector filters documents based on specific eligibility criteria.
// It can be extended with additional methods for filtering and retrieval.
type EligibleDocumentSelector interface {
// AddEligibleDocumentMatch marks a document as eligible for selection.
// id is the internal identifier of the document to be added.
AddEligibleDocumentMatch(id IndexInternalID) error
// SegmentEligibleDocs returns a list of eligible document IDs within a given segment.
// segmentID identifies the segment for which eligible documents are retrieved.
// This must be called after all eligible documents have been added.
SegmentEligibleDocs(segmentID int) []uint64
}

View File

@@ -0,0 +1,92 @@
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
type FieldIndexingOptions int
const (
IndexField FieldIndexingOptions = 1 << iota
StoreField
IncludeTermVectors
DocValues
SkipFreqNorm
)
const (
BM25Scoring = "bm25"
TFIDFScoring = "tfidf"
)
// Scoring model indicates the algorithm used to rank documents fetched
// for a query performed on a text field.
const DefaultScoringModel = TFIDFScoring
// Supported similarity models
var SupportedScoringModels = map[string]struct{}{
BM25Scoring: {},
TFIDFScoring: {},
}
func (o FieldIndexingOptions) IsIndexed() bool {
return o&IndexField != 0
}
func (o FieldIndexingOptions) IsStored() bool {
return o&StoreField != 0
}
func (o FieldIndexingOptions) IncludeTermVectors() bool {
return o&IncludeTermVectors != 0
}
func (o FieldIndexingOptions) IncludeDocValues() bool {
return o&DocValues != 0
}
func (o FieldIndexingOptions) SkipFreqNorm() bool {
return o&SkipFreqNorm != 0
}
func (o FieldIndexingOptions) String() string {
rv := ""
if o.IsIndexed() {
rv += "INDEXED"
}
if o.IsStored() {
if rv != "" {
rv += ", "
}
rv += "STORE"
}
if o.IncludeTermVectors() {
if rv != "" {
rv += ", "
}
rv += "TV"
}
if o.IncludeDocValues() {
if rv != "" {
rv += ", "
}
rv += "DV"
}
if !o.SkipFreqNorm() {
if rv != "" {
rv += ", "
}
rv += "FN"
}
return rv
}

View File

@@ -0,0 +1,39 @@
// Copyright (c) 2020 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
// Optimizable represents an optional interface that implementable by
// optimizable resources (e.g., TermFieldReaders, Searchers). These
// optimizable resources are provided the same OptimizableContext
// instance, so that they can coordinate via dynamic interface
// casting.
type Optimizable interface {
Optimize(kind string, octx OptimizableContext) (OptimizableContext, error)
}
// Represents a result of optimization -- see the Finish() method.
type Optimized interface{}
type OptimizableContext interface {
// Once all the optimzable resources have been provided the same
// OptimizableContext instance, the optimization preparations are
// finished or completed via the Finish() method.
//
// Depending on the optimization being performed, the Finish()
// method might return a non-nil Optimized instance. For example,
// the Optimized instance might represent an optimized
// TermFieldReader instance.
Finish() (Optimized, error)
}

35
vendor/github.com/blevesearch/bleve_index_api/sizes.go generated vendored Normal file
View File

@@ -0,0 +1,35 @@
// Copyright (c) 2020 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
import (
"reflect"
)
func init() {
var m map[int]int
sizeOfMap = int(reflect.TypeOf(m).Size())
var ptr *int
sizeOfPtr = int(reflect.TypeOf(ptr).Size())
var str string
sizeOfString = int(reflect.TypeOf(str).Size())
var u64 uint64
sizeOfUint64 = int(reflect.TypeOf(u64).Size())
}
var sizeOfMap int
var sizeOfPtr int
var sizeOfString int
var sizeOfUint64 int

View File

@@ -0,0 +1,47 @@
// Copyright (c) 2022 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package index
// SpatialAnalyzerPlugin is an interface for the custom spatial
// tokenizer implementations that supports the generation of spatial
// hierarchial tokens for both indexing and querying of geoJSON data.
type SpatialAnalyzerPlugin interface {
// Type returns the plugin type. eg: "s2".
Type() string
// GetIndexTokens returns the tokens to be indexed for the
// given GeoJSON type data in the document.
GetIndexTokens(GeoJSON) []string
// GetQueryTokens returns the tokens to be queried for the
// given GeoJSON type data in the document.
GetQueryTokens(GeoJSON) []string
}
// GeoJSON is generic interface for any geoJSON shapes like
// points, polygon etc.
type GeoJSON interface {
// Returns the type of geoJSON shape.
Type() string
// Checks whether the given shape intersects with current shape.
Intersects(GeoJSON) (bool, error)
// Checks whether the given shape resides within the current shape.
Contains(GeoJSON) (bool, error)
// Value returns the byte value for the shape.
Value() ([]byte, error)
}

View File

@@ -0,0 +1,70 @@
// Copyright (c) 2023 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//go:build vectors
// +build vectors
package index
type VectorField interface {
Vector() []float32
// Dimensionality of the vector
Dims() int
// Similarity metric to be used for scoring the vectors
Similarity() string
// nlist/nprobe config (recall/latency) the index is optimized for
IndexOptimizedFor() string
}
// -----------------------------------------------------------------------------
const (
EuclideanDistance = "l2_norm"
InnerProduct = "dot_product"
CosineSimilarity = "cosine"
)
const DefaultVectorSimilarityMetric = EuclideanDistance
// Supported similarity metrics for vector fields
var SupportedVectorSimilarityMetrics = map[string]struct{}{
EuclideanDistance: {},
InnerProduct: {},
CosineSimilarity: {},
}
// -----------------------------------------------------------------------------
const (
IndexOptimizedForRecall = "recall"
IndexOptimizedForLatency = "latency"
IndexOptimizedForMemoryEfficient = "memory-efficient"
)
const DefaultIndexOptimization = IndexOptimizedForRecall
var SupportedVectorIndexOptimizations = map[string]int{
IndexOptimizedForRecall: 0,
IndexOptimizedForLatency: 1,
IndexOptimizedForMemoryEfficient: 2,
}
// Reverse maps vector index optimizations': int -> string
var VectorIndexOptimizationsReverseLookup = map[int]string{
0: IndexOptimizedForRecall,
1: IndexOptimizedForLatency,
2: IndexOptimizedForMemoryEfficient,
}

View File

@@ -0,0 +1,87 @@
// Copyright (c) 2023 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//go:build vectors
// +build vectors
package index
import (
"context"
"encoding/json"
"reflect"
)
var reflectStaticSizeVectorDoc int
func init() {
var vd VectorDoc
reflectStaticSizeVectorDoc = int(reflect.TypeOf(vd).Size())
}
type VectorReader interface {
// Next returns the next document similar to the vector, in this field, or nil
// when it reaches the end of the enumeration. The preAlloced VectorDoc
// is optional, and when non-nil, will be used instead of allocating memory.
Next(preAlloced *VectorDoc) (*VectorDoc, error)
// Advance resets the enumeration at specified document or its immediate
// follower.
Advance(ID IndexInternalID, preAlloced *VectorDoc) (*VectorDoc, error)
// Count returns the number of documents similar to the vector, in this field.
Count() uint64
Close() error
Size() int
}
// VectorIndexReader is an index reader that can retrieve similar vectors from a vector-based index.
type VectorIndexReader interface {
// NewEligibleDocumentSelector returns an instance of an eligible document selector.
// This selector filters documents for KNN search based on a pre-filter query.
NewEligibleDocumentSelector() EligibleDocumentSelector
// VectorReader creates a new vector reader for performing KNN search.
// - vector: the query vector
// - field: the field to search in
// - k: the number of similar vectors to return
// - searchParams: additional search parameters
// - selector: an eligible document selector to filter documents before KNN search
VectorReader(ctx context.Context, vector []float32, field string, k int64,
searchParams json.RawMessage, selector EligibleDocumentSelector) (
VectorReader, error)
}
type VectorDoc struct {
Vector []float32
ID IndexInternalID
Score float64
}
func (vd *VectorDoc) Size() int {
return reflectStaticSizeVectorDoc + sizeOfPtr + len(vd.Vector) +
len(vd.ID)
}
// Reset allows an already allocated VectorDoc to be reused
func (vd *VectorDoc) Reset() *VectorDoc {
// remember the []byte used for the ID
id := vd.ID
// idiom to copy over from empty VectorDoc (0 allocations)
*vd = VectorDoc{}
// reuse the []byte already allocated (and reset len to 0)
vd.ID = id[:0]
return vd
}

View File

@@ -0,0 +1,38 @@
// Copyright (c) 2023 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//go:build vectors
// +build vectors
package index
import "context"
// VectorOptimizable represents an optional interface that implementable by
// optimizable resources (e.g., VectorReaders, Searchers). These
// optimizable resources are provided the same OptimizableContext
// instance, so that they can coordinate via dynamic interface
// casting.
// To avoid KNNSearchers' OptimizableContext being casted to ones used for
// TFRs, term searchers, etc.
type VectorOptimizable interface {
VectorOptimize(ctx context.Context, octx VectorOptimizableContext) (VectorOptimizableContext, error)
}
type VectorOptimizableContext interface {
// Once all the optimzable resources have been provided the same
// OptimizableContext instance, the optimization preparations are
// finished or completed via the Finish() method.
Finish() error
}