mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-17 16:38:54 +00:00
Phase 3 of plans/exit.md: the streaming-interface change, the load-bearing piece for #341 (DSL exit statement) and #440 (strict mode). - RecordTransformer.Transform and RecordTransformerFunc now return error. All 69 Transform implementations and their dispatch helpers updated (mechanical rewrite, compiler- and errcheck-verified). - runSingleTransformerBatch, on a Transform error, forwards any output produced before the failure plus an end-of-stream marker downstream, so the rest of the chain and the record-writer drain and finish cleanly; runSingleTransformer then surfaces the error to stream.Stream's select loop (non-blocking send; first error wins) and signals upstream-done so the record-reader stops. This is exactly the flush-then-exit sequencing a future DSL 'exit N' needs. - dataProcessingErrorChannel and FileOutputHandler.recordErroredChannel are now chan error instead of chan bool; ChannelWriter still prints write- error details at the site and sends the 'exiting due to data error' sentinel, preserving the exact stderr shape pinned by regression cases. - Mid-stream os.Exit sites converted to returned errors: put/filter DSL begin/main/end-block errors and the non-boolean filter-expression case, tee write/close failures, split write/open/close failures, join left-file ingest failures (both half-streaming and sorted paths, with full error plumbing through JoinBucketKeeper), histogram/stats2 ingest errors, surv fit errors, and step stepper allocation (tStepperAllocator now returns (tStepper, error); bad EWMA coefficients propagate; negative slwin parameters are reported by the CLI parser via the existing bad-stepper-name pattern). - The two genuinely internal join-bucket-keeper states now use lib.InternalCodingErrorWithMessageIf instead of hand-rolled print+exit. - pkg/transformers is now os.Exit-free. Behavior notes: the non-boolean filter message gains the standard 'mlr: ' prefix and a newline (it previously printed with neither); tee errors now include the underlying cause. All 4779 regression cases pass unchanged; mlr head early-out latency is unaffected (0.02s over 50M records). Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
199 lines
5.1 KiB
Go
199 lines
5.1 KiB
Go
package transformers
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/cli"
|
|
"github.com/johnkerl/miller/v6/pkg/mlrval"
|
|
"github.com/johnkerl/miller/v6/pkg/types"
|
|
)
|
|
|
|
const verbNameGap = "gap"
|
|
|
|
var gapOptions = []OptionSpec{
|
|
{Flag: "-g", Arg: "{a,b,c}", Type: "csv-list", Desc: "Print a gap whenever values of these fields (e.g. a,b,c) changes."},
|
|
{Flag: "-n", Arg: "{n}", Type: "int", Desc: "Print a gap every n records. Ignored if -g is present."},
|
|
}
|
|
|
|
var GapSetup = TransformerSetup{
|
|
Verb: verbNameGap,
|
|
UsageFunc: transformerGapUsage,
|
|
ParseCLIFunc: transformerGapParseCLI,
|
|
IgnoresInput: false,
|
|
Options: gapOptions,
|
|
}
|
|
|
|
func transformerGapUsage(
|
|
o *os.File,
|
|
) {
|
|
fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameGap)
|
|
fmt.Fprint(o, "Emits an empty record every n records, or when certain values change.\n")
|
|
fmt.Fprintf(o, "One of -n or -g is required.\n")
|
|
WriteVerbOptions(o, gapOptions)
|
|
}
|
|
|
|
func transformerGapParseCLI(
|
|
pargi *int,
|
|
argc int,
|
|
args []string,
|
|
_ *cli.TOptions,
|
|
doConstruct bool, // false for first pass of CLI-parse, true for second pass
|
|
) (RecordTransformer, error) {
|
|
|
|
// Skip the verb name from the current spot in the mlr command line
|
|
argi := *pargi
|
|
verb := args[argi]
|
|
argi++
|
|
|
|
gapCount := int64(-1)
|
|
var groupByFieldNames []string = nil
|
|
|
|
var err error
|
|
for argi < argc /* variable increment: 1 or 2 depending on flag */ {
|
|
opt := args[argi]
|
|
if !strings.HasPrefix(opt, "-") {
|
|
break // No more flag options to process
|
|
}
|
|
if args[argi] == "--" {
|
|
break // All transformers must do this so main-flags can follow verb-flags
|
|
}
|
|
argi++
|
|
|
|
switch opt {
|
|
case "-h", "--help":
|
|
transformerGapUsage(os.Stdout)
|
|
return nil, cli.ErrHelpRequested
|
|
|
|
case "-n":
|
|
gapCount, err = cli.VerbGetIntArg(verb, opt, args, &argi, argc)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
case "-g":
|
|
groupByFieldNames, err = cli.VerbGetStringArrayArg(verb, opt, args, &argi, argc)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
default:
|
|
return nil, cli.VerbErrorf(verb, "option \"%s\" not recognized", opt)
|
|
}
|
|
}
|
|
|
|
if gapCount == -1 && groupByFieldNames == nil {
|
|
transformerGapUsage(os.Stderr)
|
|
return nil, cli.ErrUsagePrinted
|
|
}
|
|
|
|
*pargi = argi
|
|
if !doConstruct { // All transformers must do this for main command-line parsing
|
|
return nil, nil
|
|
}
|
|
|
|
transformer, err := NewTransformerGap(
|
|
gapCount,
|
|
groupByFieldNames,
|
|
)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return transformer, nil
|
|
}
|
|
|
|
type TransformerGap struct {
|
|
// input
|
|
gapCount int64
|
|
groupByFieldNames []string
|
|
|
|
// state
|
|
recordTransformerFunc RecordTransformerFunc
|
|
recordCount int64
|
|
previousGroupingKey string
|
|
}
|
|
|
|
func NewTransformerGap(
|
|
gapCount int64,
|
|
groupByFieldNames []string,
|
|
) (*TransformerGap, error) {
|
|
|
|
tr := &TransformerGap{
|
|
gapCount: gapCount,
|
|
groupByFieldNames: groupByFieldNames,
|
|
|
|
recordCount: 0,
|
|
previousGroupingKey: "",
|
|
}
|
|
|
|
if groupByFieldNames == nil {
|
|
tr.recordTransformerFunc = tr.transformUnkeyed
|
|
} else {
|
|
tr.recordTransformerFunc = tr.transformKeyed
|
|
}
|
|
|
|
return tr, nil
|
|
}
|
|
|
|
func (tr *TransformerGap) Transform(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) error {
|
|
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
return tr.recordTransformerFunc(inrecAndContext, outputRecordsAndContexts, inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
}
|
|
|
|
func (tr *TransformerGap) transformUnkeyed(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) error {
|
|
if !inrecAndContext.EndOfStream {
|
|
if tr.recordCount > 0 && tr.recordCount%tr.gapCount == 0 {
|
|
newrec := mlrval.NewMlrmapAsRecord()
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(newrec, &inrecAndContext.Context))
|
|
}
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
|
|
tr.recordCount++
|
|
|
|
} else {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (tr *TransformerGap) transformKeyed(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) error {
|
|
if !inrecAndContext.EndOfStream {
|
|
inrec := inrecAndContext.Record
|
|
|
|
groupingKey, ok := inrec.GetSelectedValuesJoined(tr.groupByFieldNames)
|
|
if !ok {
|
|
groupingKey = ""
|
|
}
|
|
|
|
if groupingKey != tr.previousGroupingKey && tr.recordCount > 0 {
|
|
newrec := mlrval.NewMlrmapAsRecord()
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(newrec, &inrecAndContext.Context))
|
|
}
|
|
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
|
|
tr.previousGroupingKey = groupingKey
|
|
tr.recordCount++
|
|
|
|
} else {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
return nil
|
|
}
|