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>
266 lines
7 KiB
Go
266 lines
7 KiB
Go
package transformers
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"golang.org/x/text/cases"
|
|
"golang.org/x/text/language"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/cli"
|
|
"github.com/johnkerl/miller/v6/pkg/lib"
|
|
"github.com/johnkerl/miller/v6/pkg/mlrval"
|
|
"github.com/johnkerl/miller/v6/pkg/types"
|
|
)
|
|
|
|
const verbNameCase = "case"
|
|
|
|
var caseOptions = []OptionSpec{
|
|
{Flag: "-k", Type: "bool", Desc: "Case only keys, not keys and values."},
|
|
{Flag: "-v", Type: "bool", Desc: "Case only values, not keys and values."},
|
|
{Flag: "-f", Arg: "{a,b,c}", Type: "csv-list", Desc: "Specify which field names to case (default: all)."},
|
|
{Flag: "-u", Type: "bool", Desc: "Convert to uppercase."},
|
|
{Flag: "-l", Type: "bool", Desc: "Convert to lowercase."},
|
|
{Flag: "-s", Type: "bool", Desc: "Convert to sentence case (capitalize first letter)."},
|
|
{Flag: "-t", Type: "bool", Desc: "Convert to title case (capitalize words)."},
|
|
}
|
|
|
|
var CaseSetup = TransformerSetup{
|
|
Verb: verbNameCase,
|
|
UsageFunc: transformerCaseUsage,
|
|
ParseCLIFunc: transformerCaseParseCLI,
|
|
IgnoresInput: false,
|
|
Options: caseOptions,
|
|
}
|
|
|
|
const (
|
|
e_UNSPECIFIED_CASE = iota
|
|
e_UPPER_CASE
|
|
e_LOWER_CASE
|
|
e_SENTENCE_CASE
|
|
e_TITLE_CASE
|
|
)
|
|
|
|
func transformerCaseUsage(
|
|
o *os.File,
|
|
) {
|
|
fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameCase)
|
|
fmt.Fprintf(o, "Uppercases strings in record keys and/or values.\n")
|
|
WriteVerbOptions(o, caseOptions)
|
|
}
|
|
|
|
func transformerCaseParseCLI(
|
|
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++
|
|
|
|
var err error
|
|
which := "keys_and_values"
|
|
style := e_UNSPECIFIED_CASE
|
|
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":
|
|
transformerCaseUsage(os.Stdout)
|
|
return nil, cli.ErrHelpRequested
|
|
|
|
case "-k":
|
|
which = "keys_only"
|
|
|
|
case "-v":
|
|
which = "values_only"
|
|
|
|
case "-f":
|
|
fieldNames, err = cli.VerbGetStringArrayArg(verb, opt, args, &argi, argc)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
case "-u":
|
|
style = e_UPPER_CASE
|
|
case "-l":
|
|
style = e_LOWER_CASE
|
|
case "-s":
|
|
style = e_SENTENCE_CASE
|
|
case "-t":
|
|
style = e_TITLE_CASE
|
|
|
|
default:
|
|
return nil, cli.VerbErrorf(verb, "option \"%s\" not recognized", opt)
|
|
}
|
|
}
|
|
|
|
*pargi = argi
|
|
if !doConstruct { // All transformers must do this for main command-line parsing
|
|
return nil, nil
|
|
}
|
|
|
|
transformer, err := NewTransformerCase(which, fieldNames, style)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return transformer, nil
|
|
}
|
|
|
|
type caserFuncT func(input string) string
|
|
|
|
type TransformerCase struct {
|
|
recordTransformerFunc RecordTransformerFunc
|
|
fieldNameSet map[string]bool
|
|
caserFunc caserFuncT
|
|
}
|
|
|
|
func NewTransformerCase(
|
|
which string,
|
|
fieldNames []string,
|
|
style int,
|
|
) (*TransformerCase, error) {
|
|
tr := &TransformerCase{}
|
|
|
|
switch which {
|
|
case "keys_only":
|
|
tr.recordTransformerFunc = tr.transformKeysOnly
|
|
case "values_only":
|
|
tr.recordTransformerFunc = tr.transformValuesOnly
|
|
default:
|
|
tr.recordTransformerFunc = tr.transformKeysAndValues
|
|
}
|
|
|
|
if fieldNames != nil {
|
|
tr.fieldNameSet = lib.StringListToSet(fieldNames)
|
|
}
|
|
|
|
switch style {
|
|
case e_UPPER_CASE:
|
|
tr.caserFunc = cases.Upper(language.Und).String
|
|
case e_LOWER_CASE:
|
|
tr.caserFunc = cases.Lower(language.Und).String
|
|
case e_SENTENCE_CASE:
|
|
tr.caserFunc = caseSentenceFunc
|
|
case e_TITLE_CASE:
|
|
tr.caserFunc = cases.Title(language.Und).String
|
|
default:
|
|
return nil, fmt.Errorf(
|
|
"mlr %s: case option must be specified using one of -u, -l, -s, -t",
|
|
verbNameCase,
|
|
)
|
|
}
|
|
|
|
return tr, nil
|
|
}
|
|
|
|
func caseSentenceFunc(input string) string {
|
|
runes := []rune(input)
|
|
if len(runes) == 0 {
|
|
return input
|
|
}
|
|
first := string(runes[0])
|
|
rest := string(runes[1:])
|
|
return strings.ToUpper(first) + strings.ToLower(rest)
|
|
}
|
|
|
|
func (tr *TransformerCase) Transform(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) error {
|
|
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
if !inrecAndContext.EndOfStream {
|
|
return tr.recordTransformerFunc(
|
|
inrecAndContext,
|
|
outputRecordsAndContexts,
|
|
inputDownstreamDoneChannel,
|
|
outputDownstreamDoneChannel,
|
|
)
|
|
} else { // end of record stream
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (tr *TransformerCase) transformKeysOnly(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
_ <-chan bool,
|
|
__ chan<- bool,
|
|
) error {
|
|
inrec := inrecAndContext.Record
|
|
newrec := mlrval.NewMlrmapAsRecord()
|
|
for pe := inrec.Head; pe != nil; pe = pe.Next {
|
|
if tr.fieldNameSet == nil || tr.fieldNameSet[pe.Key] {
|
|
newkey := tr.caserFunc(pe.Key)
|
|
// Reference not copy since this is ownership transfer of the value from the now-abandoned inrec
|
|
newrec.PutReference(newkey, pe.Value)
|
|
} else {
|
|
newrec.PutReference(pe.Key, pe.Value)
|
|
}
|
|
}
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(newrec, &inrecAndContext.Context))
|
|
return nil
|
|
}
|
|
|
|
func (tr *TransformerCase) transformValuesOnly(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
_ <-chan bool,
|
|
__ chan<- bool,
|
|
) error {
|
|
inrec := inrecAndContext.Record
|
|
for pe := inrec.Head; pe != nil; pe = pe.Next {
|
|
if tr.fieldNameSet == nil || tr.fieldNameSet[pe.Key] {
|
|
stringval, ok := pe.Value.GetStringValue()
|
|
if ok {
|
|
pe.Value = mlrval.FromString(tr.caserFunc(stringval))
|
|
}
|
|
}
|
|
}
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(inrec, &inrecAndContext.Context))
|
|
return nil
|
|
}
|
|
|
|
func (tr *TransformerCase) transformKeysAndValues(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
_ <-chan bool,
|
|
__ chan<- bool,
|
|
) error {
|
|
inrec := inrecAndContext.Record
|
|
newrec := mlrval.NewMlrmapAsRecord()
|
|
for pe := inrec.Head; pe != nil; pe = pe.Next {
|
|
if tr.fieldNameSet == nil || tr.fieldNameSet[pe.Key] {
|
|
newkey := tr.caserFunc(pe.Key)
|
|
stringval, ok := pe.Value.GetStringValue()
|
|
if ok {
|
|
stringval = tr.caserFunc(stringval)
|
|
newrec.PutReference(newkey, mlrval.FromString(stringval))
|
|
} else {
|
|
newrec.PutReference(newkey, pe.Value)
|
|
}
|
|
} else {
|
|
newrec.PutReference(pe.Key, pe.Value)
|
|
}
|
|
}
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(newrec, &inrecAndContext.Context))
|
|
return nil
|
|
}
|