miller/pkg/transformers/tee.go

package transformers

import (
	"fmt"
	"os"
	"strings"

	"github.com/johnkerl/miller/v6/pkg/cli"
	"github.com/johnkerl/miller/v6/pkg/output"
	"github.com/johnkerl/miller/v6/pkg/types"
)

const verbNameTee = "tee"

var teeOptions = []OptionSpec{
	{Flag: "-a", Type: "bool", Desc: "Append to existing file, if any, rather than overwriting."},
	{Flag: "-p", Type: "bool", Desc: "Treat filename as a pipe-to command."},
}

var TeeSetup = TransformerSetup{
	Verb:         verbNameTee,
	UsageFunc:    transformerTeeUsage,
	ParseCLIFunc: transformerTeeParseCLI,
	IgnoresInput: false,
	Options:      teeOptions,
}

func transformerTeeUsage(
	o *os.File,
) {
	fmt.Fprintf(o, "Usage: %s %s [options] {filename}\n", "mlr", verbNameTee)
	WriteVerbOptions(o, teeOptions)
	fmt.Fprintf(o,
		`Any of the output-format command-line flags (see mlr -h). Example: using
  mlr --icsv --opprint put '...' then tee --ojson ./mytap.dat then stats1 ...
the input is CSV, the output is pretty-print tabular, but the tee-file output
is written in JSON format.
`)
}

func transformerTeeParseCLI(
	pargi *int,
	argc int,
	args []string,
	mainOptions *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++

	filenameOrCommand := ""
	appending := false
	piping := false
	// TODO: make sure this is a full nested-struct copy.
	var localOptions *cli.TOptions = nil
	if mainOptions != nil {
		copyThereof := *mainOptions // struct copy
		localOptions = &copyThereof
	}

	// Parse local flags.

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

		case "-a":
			appending = true
			piping = false

		case "-p":
			appending = false
			piping = true

		default:
			// This is inelegant. For error-proofing we advance argi already in our
			// loop (so individual if-statements don't need to). However,
			// ParseWriterOptions expects it unadvanced.
			largi := argi - 1
			handled, err := cli.FLAG_TABLE.Parse(args, argc, &largi, localOptions)
			if err != nil {
				return nil, err
			}
			if handled {
				// This lets mlr main and mlr tee have different output formats.
				// Nothing else to handle here.
				argi = largi
			} else {
				return nil, cli.VerbErrorf(verbNameTee, "option \"%s\" not recognized", opt)
			}
		}
	}

	if err := cli.FinalizeWriterOptions(&localOptions.WriterOptions); err != nil {
		return nil, cli.VerbErrorf(verbNameTee, "%v", err)
	}

	// Get the filename/command from the command line, after the flags
	if argi >= argc {
		return nil, cli.VerbErrorf(verbNameTee, "filename or command required")
	}
	filenameOrCommand = args[argi]
	argi++

	*pargi = argi
	if !doConstruct { // All transformers must do this for main command-line parsing
		return nil, nil
	}

	transformer, err := NewTransformerTee(
		appending,
		piping,
		filenameOrCommand,
		&localOptions.WriterOptions,
	)
	if err != nil {
		return nil, err
	}

	return transformer, nil
}

type TransformerTee struct {
	filenameOrCommandForDisplay string
	fileOutputHandler           *output.FileOutputHandler
}

func NewTransformerTee(
	appending bool,
	piping bool,
	filenameOrCommand string,
	recordWriterOptions *cli.TWriterOptions,
) (*TransformerTee, error) {
	var fileOutputHandler *output.FileOutputHandler
	var err error
	var filenameOrCommandForDisplay string
	if piping {
		fileOutputHandler, err = output.NewPipeWriteOutputHandler(filenameOrCommand, recordWriterOptions)
		filenameOrCommandForDisplay = "| " + filenameOrCommand
	} else if appending {
		fileOutputHandler, err = output.NewFileAppendOutputHandler(filenameOrCommand, recordWriterOptions)
		filenameOrCommandForDisplay = ">> " + filenameOrCommand
	} else {
		fileOutputHandler, err = output.NewFileWriteOutputHandler(filenameOrCommand, recordWriterOptions)
		filenameOrCommandForDisplay = "> " + filenameOrCommand
	}
	if err != nil {
		return nil, err
	}

	return &TransformerTee{
		filenameOrCommandForDisplay: filenameOrCommandForDisplay,
		fileOutputHandler:           fileOutputHandler,
	}, nil
}

func (tr *TransformerTee) Transform(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) error {

	// If we receive a downstream-done flag from a transformer downstream from
	// us, read it to unblock their goroutine but -- unlike most other verbs --
	// do not forward the flag farther upstream.
	//
	// For example, 'mlr cut -f foo then head -n 10' on million-line input:
	// head can signal it's got 10 records, then write downStreamDone <- true,
	// then cut and record-reader can stop sending any more data. This makes
	// the UX response for head on huge files.
	//
	// But 'mlr cut -f foo then tee bar.txt then head -n 10' -- one does expect
	// bar.txt to have all the output from cut.
	select {
	case <-inputDownstreamDoneChannel:
		// Do not write this to the coutputDownstreamDoneChannel, as other transformers do
		break
	default:
		break
	}

	if !inrecAndContext.EndOfStream {
		// The file-output handler writes records asynchronously on another
		// goroutine, and buffering formats like pprint/json can hold onto them
		// even longer. Meanwhile we also forward the same record downstream,
		// where subsequent verbs may mutate it in place. Give the tee output
		// its own copy so downstream mutations can't leak into it (issue
		// #1671).
		err := tr.fileOutputHandler.WriteRecordAndContext(inrecAndContext.Copy())
		if err != nil {
			return fmt.Errorf(
				"%s: error writing to tee \"%s\":\n%v",
				"mlr", tr.filenameOrCommandForDisplay, err,
			)
		}

		*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
	} else {
		err := tr.fileOutputHandler.Close()
		if err != nil {
			return fmt.Errorf(
				"%s: error closing tee \"%s\":\n%v",
				"mlr", tr.filenameOrCommandForDisplay, err,
			)
		}
		*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
	}
	return nil
}