-
Notifications
You must be signed in to change notification settings - Fork 135
lib/logstorage: add pipe json_array_concat #1408
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
cuongleqq
wants to merge
4
commits into
VictoriaMetrics:master
Choose a base branch
from
cuongleqq:add-pipe-json-array-concat
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
faccd78
lib/logstorage: add json_array_concat pipe
cuongleqq 593ce95
docs: add json_array_concat pipe documentation
cuongleqq 8824246
lib/logstorage: improve test coverage for json_array_concat pipe
cuongleqq d0dccc7
lib/logstorage: trim JSON whitespace in json_array_concat pipe
cuongleqq File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,212 @@ | ||
| package logstorage | ||
|
|
||
| import ( | ||
| "fmt" | ||
|
|
||
| "github.com/valyala/fastjson" | ||
|
|
||
| "github.com/VictoriaMetrics/VictoriaMetrics/lib/atomicutil" | ||
| "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" | ||
|
|
||
| "github.com/VictoriaMetrics/VictoriaLogs/lib/prefixfilter" | ||
| ) | ||
|
|
||
| // pipeJSONArrayConcat processes '| json_array_concat ...' pipe. | ||
| // | ||
| // See https://docs.victoriametrics.com/victorialogs/logsql/#json_array_concat-pipe | ||
| type pipeJSONArrayConcat struct { | ||
| delimiter string | ||
| fromField string | ||
| resultField string | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) String() string { | ||
| s := "json_array_concat" | ||
| if pc.delimiter != "" { | ||
| s += " " + quoteTokenIfNeeded(pc.delimiter) | ||
| } | ||
| if !isMsgFieldName(pc.fromField) { | ||
| s += " from " + quoteTokenIfNeeded(pc.fromField) | ||
| } | ||
| if pc.resultField != pc.fromField { | ||
| s += " as " + quoteTokenIfNeeded(pc.resultField) | ||
| } | ||
| return s | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) splitToRemoteAndLocal(_ int64) (pipe, []pipe) { | ||
| return pc, nil | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) canLiveTail() bool { | ||
| return true | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) canReturnLastNResults() bool { | ||
| return pc.resultField != "_time" | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) isFixedOutputFieldsOrder() bool { | ||
| return false | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) updateNeededFields(pf *prefixfilter.Filter) { | ||
| if pf.MatchString(pc.resultField) { | ||
| pf.AddDenyFilter(pc.resultField) | ||
| pf.AddAllowFilter(pc.fromField) | ||
| } | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) hasFilterInWithQuery() bool { | ||
| return false | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) initFilterInValues(_ *inValuesCache, _ getFieldValuesFunc) (pipe, error) { | ||
| return pc, nil | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) visitSubqueries(_ func(q *Query)) { | ||
| // nothing to do | ||
| } | ||
|
|
||
| func (pc *pipeJSONArrayConcat) newPipeProcessor(_ int, _ <-chan struct{}, _ func(), ppNext pipeProcessor) pipeProcessor { | ||
| pcp := &pipeJSONArrayConcatProcessor{ | ||
| pc: pc, | ||
| ppNext: ppNext, | ||
| } | ||
| pcp.shards.Init = func(shard *pipeJSONArrayConcatProcessorShard) { | ||
| shard.reset() | ||
| } | ||
| return pcp | ||
| } | ||
|
|
||
| type pipeJSONArrayConcatProcessor struct { | ||
| pc *pipeJSONArrayConcat | ||
| ppNext pipeProcessor | ||
|
|
||
| shards atomicutil.Slice[pipeJSONArrayConcatProcessorShard] | ||
| } | ||
|
|
||
| func (plp *pipeJSONArrayConcatProcessor) writeBlock(workerID uint, br *blockResult) { | ||
| if br.rowsLen == 0 { | ||
| return | ||
| } | ||
|
|
||
| shard := plp.shards.Get(workerID) | ||
| shard.rc.name = plp.pc.resultField | ||
|
|
||
| c := br.getColumnByName(plp.pc.fromField) | ||
| delimiter := plp.pc.delimiter | ||
| if c.isConst { | ||
| // Fast path for const column | ||
| v := c.valuesEncoded[0] | ||
| out := shard.concat(v, delimiter) | ||
| shard.rc.addValue(out) | ||
| br.addResultColumnConst(shard.rc) | ||
| } else { | ||
| // Slow path for other columns | ||
| values := c.getValues(br) | ||
| prevOut := "" | ||
| for rowIdx := range values { | ||
| if rowIdx == 0 || values[rowIdx] != values[rowIdx-1] { | ||
| prevOut = shard.concat(values[rowIdx], delimiter) | ||
| } | ||
| shard.rc.addValue(prevOut) | ||
| } | ||
| br.addResultColumn(shard.rc) | ||
| } | ||
|
|
||
| plp.ppNext.writeBlock(workerID, br) | ||
|
|
||
| shard.reset() | ||
| } | ||
|
|
||
| type pipeJSONArrayConcatProcessorShard struct { | ||
| a arena | ||
| rc resultColumn | ||
| } | ||
|
|
||
| func (shard *pipeJSONArrayConcatProcessorShard) reset() { | ||
| shard.a.reset() | ||
| shard.rc.reset() | ||
| } | ||
|
|
||
| func (shard *pipeJSONArrayConcatProcessorShard) concat(arrayStr, delimiter string) string { | ||
| if len(arrayStr) == 0 || arrayStr[0] != '[' { | ||
| return "" | ||
| } | ||
|
|
||
| p := jspp.Get() | ||
| defer jspp.Put(p) | ||
|
|
||
| jsv, err := p.Parse(arrayStr) | ||
| if err != nil { | ||
| return "" | ||
| } | ||
| jsa, err := jsv.Array() | ||
| if err != nil || len(jsa) == 0 { | ||
| return "" | ||
| } | ||
|
|
||
| bLen := len(shard.a.b) | ||
| for i, item := range jsa { | ||
| if i > 0 { | ||
| shard.a.b = append(shard.a.b, delimiter...) | ||
| } | ||
| if item.Type() == fastjson.TypeString { | ||
| sb, _ := item.StringBytes() | ||
| shard.a.b = append(shard.a.b, sb...) | ||
| } else { | ||
| shard.a.b = item.MarshalTo(shard.a.b) | ||
| } | ||
| } | ||
| return bytesutil.ToUnsafeString(shard.a.b[bLen:]) | ||
| } | ||
|
|
||
| func (plp *pipeJSONArrayConcatProcessor) flush() error { | ||
| return nil | ||
| } | ||
|
|
||
| func parsePipeJSONArrayConcat(lex *lexer) (pipe, error) { | ||
| if !lex.isKeyword("json_array_concat") { | ||
| return nil, fmt.Errorf("unexpected token: %q; want %q", lex.token, "json_array_concat") | ||
| } | ||
| lex.nextToken() | ||
|
|
||
| delimiter := "" | ||
| if !lex.isKeyword("from", "as", "|", ")", "") { | ||
| s, err := lex.nextCompoundToken() | ||
| if err != nil { | ||
| return nil, fmt.Errorf("cannot parse delimiter for 'json_array_concat': %w", err) | ||
| } | ||
| delimiter = s | ||
| } | ||
|
|
||
| fromField := "_msg" | ||
| if lex.isKeyword("from") { | ||
| lex.nextToken() | ||
| f, err := parseFieldName(lex) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("cannot parse 'from' field for 'json_array_concat': %w", err) | ||
| } | ||
| fromField = f | ||
| } | ||
|
|
||
| resultField := fromField | ||
| if lex.isKeyword("as") { | ||
| lex.nextToken() | ||
| } | ||
| if !lex.isKeyword("|", ")", "") { | ||
| f, err := parseFieldName(lex) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("cannot parse result field for 'json_array_concat': %w", err) | ||
| } | ||
| resultField = f | ||
| } | ||
|
|
||
| return &pipeJSONArrayConcat{ | ||
| delimiter: delimiter, | ||
| fromField: fromField, | ||
| resultField: resultField, | ||
| }, nil | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.