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>
183 lines
4.8 KiB
Go
183 lines
4.8 KiB
Go
package transformers
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/bifs"
|
|
"github.com/johnkerl/miller/v6/pkg/cli"
|
|
"github.com/johnkerl/miller/v6/pkg/mlrval"
|
|
"github.com/johnkerl/miller/v6/pkg/types"
|
|
)
|
|
|
|
const verbNameSparkline = "sparkline"
|
|
|
|
var sparklineOptions = []OptionSpec{
|
|
{Flag: "-f", Arg: "{a,b,c}", Type: "csv-list", Desc: "Field names to sparkline."},
|
|
}
|
|
|
|
var SparklineSetup = TransformerSetup{
|
|
Verb: verbNameSparkline,
|
|
UsageFunc: transformerSparklineUsage,
|
|
ParseCLIFunc: transformerSparklineParseCLI,
|
|
IgnoresInput: false,
|
|
Options: sparklineOptions,
|
|
}
|
|
|
|
func transformerSparklineUsage(
|
|
o *os.File,
|
|
) {
|
|
fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameSparkline)
|
|
fmt.Fprintf(o, "Reduces numeric field(s), across all records in input order, to a compact\n")
|
|
fmt.Fprintf(o, "Unicode sparkline -- one block character per record -- for visualizing\n")
|
|
fmt.Fprintf(o, "trends. Emits one output record per field. Holds all records in memory\n")
|
|
fmt.Fprintf(o, "before producing any output.\n")
|
|
WriteVerbOptions(o, sparklineOptions)
|
|
}
|
|
|
|
func transformerSparklineParseCLI(
|
|
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++
|
|
|
|
// Parse local flags
|
|
var err error
|
|
var fieldNames []string = nil
|
|
|
|
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":
|
|
transformerSparklineUsage(os.Stdout)
|
|
return nil, cli.ErrHelpRequested
|
|
|
|
case "-f":
|
|
fieldNames, 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 fieldNames == nil {
|
|
return nil, cli.VerbErrorf(verb, "-f field names required")
|
|
}
|
|
|
|
*pargi = argi
|
|
if !doConstruct { // All transformers must do this for main command-line parsing
|
|
return nil, nil
|
|
}
|
|
|
|
transformer, err := NewTransformerSparkline(fieldNames)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return transformer, nil
|
|
}
|
|
|
|
type TransformerSparkline struct {
|
|
fieldNames []string
|
|
valuesByField map[string][]*mlrval.Mlrval
|
|
}
|
|
|
|
func NewTransformerSparkline(
|
|
fieldNames []string,
|
|
) (*TransformerSparkline, error) {
|
|
valuesByField := make(map[string][]*mlrval.Mlrval)
|
|
for _, fieldName := range fieldNames {
|
|
valuesByField[fieldName] = make([]*mlrval.Mlrval, 0)
|
|
}
|
|
return &TransformerSparkline{
|
|
fieldNames: fieldNames,
|
|
valuesByField: valuesByField,
|
|
}, nil
|
|
}
|
|
|
|
func (tr *TransformerSparkline) Transform(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) error {
|
|
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
|
|
if !inrecAndContext.EndOfStream {
|
|
inrec := inrecAndContext.Record
|
|
for _, fieldName := range tr.fieldNames {
|
|
mvalue := inrec.Get(fieldName)
|
|
if mvalue != nil {
|
|
tr.valuesByField[fieldName] = append(tr.valuesByField[fieldName], mvalue.Copy())
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// Else, end of stream: emit one summary record per field.
|
|
for _, fieldName := range tr.fieldNames {
|
|
values := tr.valuesByField[fieldName]
|
|
|
|
outrec := mlrval.NewMlrmapAsRecord()
|
|
outrec.PutReference("field", mlrval.FromString(fieldName))
|
|
outrec.PutReference("n", mlrval.FromInt(int64(len(values))))
|
|
|
|
sparkline := bifs.BIF_sparkline(mlrval.FromArray(values))
|
|
if !sparkline.IsError() {
|
|
lo, hi, haveLoHi := floatRangeOf(values)
|
|
if haveLoHi {
|
|
outrec.PutReference("lo", mlrval.FromFloat(lo))
|
|
outrec.PutReference("hi", mlrval.FromFloat(hi))
|
|
}
|
|
}
|
|
outrec.PutReference("sparkline", sparkline)
|
|
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(outrec, &inrecAndContext.Context))
|
|
}
|
|
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext) // Emit the end-of-stream marker
|
|
return nil
|
|
}
|
|
|
|
// floatRangeOf returns the min and max of the numeric values, and whether
|
|
// any were found.
|
|
func floatRangeOf(values []*mlrval.Mlrval) (lo float64, hi float64, haveLoHi bool) {
|
|
for _, value := range values {
|
|
floatValue, isFloat := value.GetNumericToFloatValue()
|
|
if !isFloat {
|
|
continue
|
|
}
|
|
if !haveLoHi {
|
|
lo = floatValue
|
|
hi = floatValue
|
|
haveLoHi = true
|
|
} else {
|
|
if floatValue < lo {
|
|
lo = floatValue
|
|
}
|
|
if floatValue > hi {
|
|
hi = floatValue
|
|
}
|
|
}
|
|
}
|
|
return lo, hi, haveLoHi
|
|
}
|