miller/pkg/transformers/cat.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 verbNameCat = "cat"

var catOptions = []OptionSpec{
	{Flag: "-n", Type: "bool", Desc: "Prepend field \"n\" to each record with record-counter starting at 1."},
	{Flag: "-N", Arg: "{name}", Type: "string", Desc: "Prepend field {name} to each record with record-counter starting at 1."},
	{Flag: "-g", Arg: "{a,b,c}", Type: "csv-list", Desc: "Optional group-by-field names for counters, e.g. a,b,c."},
	{Flag: "--filename", Type: "bool", Desc: "Prepend current filename to each record."},
	{Flag: "--filenum", Type: "bool", Desc: "Prepend current filenum (1-up) to each record."},
}

var CatSetup = TransformerSetup{
	Verb:         verbNameCat,
	UsageFunc:    transformerCatUsage,
	ParseCLIFunc: transformerCatParseCLI,
	IgnoresInput: false,
	Options:      catOptions,
}

func transformerCatUsage(
	o *os.File,
) {
	fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameCat)
	fmt.Fprintf(o, "Passes input records directly to output. Most useful for format conversion.\n")
	WriteVerbOptions(o, catOptions)
}

func transformerCatParseCLI(
	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
	// Parse local flags
	doCounters := false
	counterFieldName := ""
	var groupByFieldNames []string = nil
	doFileName := false
	doFileNum := false

	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":
			transformerCatUsage(os.Stdout)
			return nil, cli.ErrHelpRequested

		case "-n":
			counterFieldName = "n"

		case "-N":
			counterFieldName, err = cli.VerbGetStringArg(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
			}

		case "--filename":
			doFileName = true

		case "--filenum":
			doFileNum = true

		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 := NewTransformerCat(
		doCounters,
		counterFieldName,
		groupByFieldNames,
		doFileName,
		doFileNum,
	)
	if err != nil {
		return nil, err
	}

	return transformer, nil
}

type TransformerCat struct {
	doCounters        bool
	groupByFieldNames []string

	counter          int64
	countsByGroup    map[string]int64
	counterFieldName string

	doFileName bool
	doFileNum  bool

	recordTransformerFunc RecordTransformerFunc
}

func NewTransformerCat(
	doCounters bool,
	counterFieldName string,
	groupByFieldNames []string,
	doFileName bool,
	doFileNum bool,
) (*TransformerCat, error) {

	if counterFieldName != "" {
		doCounters = true
	}

	tr := &TransformerCat{
		doCounters:        doCounters,
		groupByFieldNames: groupByFieldNames,
		counter:           0,
		countsByGroup:     make(map[string]int64),
		counterFieldName:  counterFieldName,
		doFileName:        doFileName,
		doFileNum:         doFileNum,
	}

	if !doCounters {
		tr.recordTransformerFunc = tr.simpleCat
	} else {
		if groupByFieldNames == nil {
			tr.recordTransformerFunc = tr.countersUngrouped
		} else {
			tr.recordTransformerFunc = tr.countersGrouped
		}
	}

	return tr, nil
}

func (tr *TransformerCat) 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 *TransformerCat) simpleCat(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) error {
	if !inrecAndContext.EndOfStream {
		if tr.doFileName {
			inrecAndContext.Record.PrependCopy("filename", mlrval.FromString(inrecAndContext.Context.FILENAME))
		}
		if tr.doFileNum {
			inrecAndContext.Record.PrependCopy("filenum", mlrval.FromInt(inrecAndContext.Context.FILENUM))
		}
	}
	*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
	return nil
}

func (tr *TransformerCat) countersUngrouped(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) error {
	if !inrecAndContext.EndOfStream {
		inrec := inrecAndContext.Record
		tr.counter++
		key := tr.counterFieldName
		inrec.PrependCopy(key, mlrval.FromInt(tr.counter))

		if tr.doFileName {
			inrec.PrependCopy("filename", mlrval.FromString(inrecAndContext.Context.FILENAME))
		}
		if tr.doFileNum {
			inrec.PrependCopy("filenum", mlrval.FromInt(inrecAndContext.Context.FILENUM))
		}
	}
	*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
	return nil
}

func (tr *TransformerCat) countersGrouped(
	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)
		var counter int64
		if !ok {
			// Treat as unkeyed
			tr.counter++
			counter = tr.counter
		} else {
			counter, ok = tr.countsByGroup[groupingKey]
			if ok {
				counter++
			} else {
				counter = 1
			}
			tr.countsByGroup[groupingKey] = counter
		}

		key := tr.counterFieldName
		inrec.PrependCopy(key, mlrval.FromInt(counter))

		if tr.doFileName {
			inrec.PrependCopy("filename", mlrval.FromString(inrecAndContext.Context.FILENAME))
		}
		if tr.doFileNum {
			inrec.PrependCopy("filenum", mlrval.FromInt(inrecAndContext.Context.FILENUM))
		}
	}
	*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
	return nil
}