miller/pkg/transformers/group_by.go
John Kerl 570fcf0de4
Remove os.Exit callsites below the entrypoint: phase 3 (plans/exit.md) (#2204)
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>
2026-07-15 15:07:09 -04:00

138 lines
3.5 KiB
Go

package transformers
import (
"fmt"
"os"
"strings"
"github.com/johnkerl/miller/v6/pkg/cli"
"github.com/johnkerl/miller/v6/pkg/lib"
"github.com/johnkerl/miller/v6/pkg/types"
)
const verbNameGroupBy = "group-by"
var groupByOptions = []OptionSpec{}
var GroupBySetup = TransformerSetup{
Verb: verbNameGroupBy,
UsageFunc: transformerGroupByUsage,
ParseCLIFunc: transformerGroupByParseCLI,
IgnoresInput: false,
Options: groupByOptions,
}
func transformerGroupByUsage(
o *os.File,
) {
fmt.Fprintf(o, "Usage: %s %s [options] {comma-separated field names}\n", "mlr", verbNameGroupBy)
fmt.Fprintln(o, "Outputs records in batches having identical values at specified field names.")
WriteVerbOptions(o, groupByOptions)
}
func transformerGroupByParseCLI(
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
argi++
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
}
if opt == "-h" || opt == "--help" {
transformerGroupByUsage(os.Stdout)
return nil, cli.ErrHelpRequested
} else {
return nil, cli.VerbErrorf(verbNameGroupBy, "option \"%s\" not recognized", opt)
}
}
// Get the group-by field names from the command line
if argi >= argc {
return nil, cli.VerbErrorf(verbNameGroupBy, "group-by field names required")
}
groupByFieldNames := lib.SplitString(args[argi], ",")
argi++
*pargi = argi
if !doConstruct { // All transformers must do this for main command-line parsing
return nil, nil
}
transformer, err := NewTransformerGroupBy(
groupByFieldNames,
)
if err != nil {
return nil, err
}
return transformer, nil
}
type TransformerGroupBy struct {
// input
groupByFieldNames []string
// state
// map from string to record slices
recordListsByGroup *lib.OrderedMap[*[]*types.RecordAndContext]
}
func NewTransformerGroupBy(
groupByFieldNames []string,
) (*TransformerGroupBy, error) {
tr := &TransformerGroupBy{
groupByFieldNames: groupByFieldNames,
recordListsByGroup: lib.NewOrderedMap[*[]*types.RecordAndContext](),
}
return tr, nil
}
func (tr *TransformerGroupBy) 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
groupingKey, ok := inrec.GetSelectedValuesJoined(tr.groupByFieldNames)
if !ok {
return nil
}
recordListForGroup := tr.recordListsByGroup.Get(groupingKey)
if recordListForGroup == nil {
records := []*types.RecordAndContext{}
recordListForGroup = &records
tr.recordListsByGroup.Put(groupingKey, recordListForGroup)
}
*recordListForGroup = append(*recordListForGroup, inrecAndContext)
} else {
for outer := tr.recordListsByGroup.Head; outer != nil; outer = outer.Next {
*outputRecordsAndContexts = append(*outputRecordsAndContexts, *outer.Value...)
}
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext) // end-of-stream marker
}
return nil
}