feat: support multi endpoints(format: scheme://user:passwd@ip1:port1,ip2:port2...)

Bugfix: the response  elasticsearch6 and 7 are a little different

.gitignore

@@ -7,4 +7,5 @@
 *output.json
 *test.json
 *.txt
-dist
+dist
+xtest

go.mod

@@ -7,7 +7,6 @@ require (
 	github.com/elastic/go-elasticsearch/v7 v7.17.10
 	github.com/fatih/color v1.16.0
 	github.com/samber/lo v1.39.0
-	github.com/sirupsen/logrus v1.9.3
 	github.com/spf13/cobra v1.8.0
 )
 
@@ -16,7 +15,6 @@ require (
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
-	github.com/stretchr/testify v1.8.4 // indirect
 	golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17 // indirect
 	golang.org/x/sys v0.14.0 // indirect
 )

go.sum

@@ -1,7 +1,4 @@
 github.com/cpuguy83/go-md2man/v2 v2.0.3/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
-github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
-github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/elastic/go-elasticsearch/v6 v6.8.10 h1:2lN0gJ93gMBXvkhwih5xquldszpm8FlUwqG5sPzr6a8=
 github.com/elastic/go-elasticsearch/v6 v6.8.10/go.mod h1:UwaDJsD3rWLM5rKNFzv9hgox93HoX8utj1kxD9aFUcI=
 github.com/elastic/go-elasticsearch/v7 v7.17.10 h1:TCQ8i4PmIJuBunvBS6bwT2ybzVFxxUhhltAs3Gyu1yo=
@@ -15,29 +12,18 @@ github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovk
 github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
-github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/samber/lo v1.39.0 h1:4gTz1wUhNYLhFSKl6O+8peW0v2F4BCY034GRpU9WnuA=
 github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXnEA=
-github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
-github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/spf13/cobra v1.8.0 h1:7aJaZx1B85qltLMc546zn58BxxfZdR/W22ej9CFoEf0=
 github.com/spf13/cobra v1.8.0/go.mod h1:WXLWApfZ71AjXPya3WOlMsY9yMs7YeiHhFVlvLyhcho=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
-github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
-github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
-github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17 h1:3MTrJm4PyNL9NBqvYDSj3DHl46qQakyfqfWo4jgfaEM=
 golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17/go.mod h1:lgLbSvA5ygNOMpwM/9anMpWVlVJ7Z+cHWq/eFuinpGE=
-golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.14.0 h1:Vz7Qs629MkJkGyHxUlRHizWJRG2j8fbQKjELVSNhy7Q=
 golang.org/x/sys v0.14.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

internal/cmd/cmd.go

@@ -34,9 +34,10 @@ esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json --query_
 
 	f_input  string
 	f_output string
-	f_limit  int
+	f_limit  uint64
 	f_type   string
 	f_source string
+	f_sort   string
 	f_query  string
 
 	f_query_file string
@@ -57,9 +58,10 @@ func init() {
 	rootCommand.Flags().StringVar(&es_oversion, "o-version", "7", "output(es) version")
 	rootCommand.Flags().StringVarP(&f_type, "type", "t", "data", "data/mapping/setting")
 	rootCommand.Flags().StringVarP(&f_source, "source", "s", "", "query source, use ';' to separate")
+	rootCommand.Flags().StringVar(&f_sort, "sort", "", "sort, <field>:<direction> format, for example: time:desc or name:asc")
 	rootCommand.Flags().StringVarP(&f_query, "query", "q", "", `query dsl, example: {"bool":{"must":[{"term":{"name":{"value":"some_name"}}}],"must_not":[{"range":{"age":{"gte":18,"lt":60}}}]}}`)
 	rootCommand.Flags().StringVar(&f_query_file, "query_file", "", `query json file (will execute line by line)`)
-	rootCommand.Flags().IntVarP(&f_limit, "limit", "l", 100, "")
+	rootCommand.Flags().Uint64VarP(&f_limit, "limit", "l", 100, "")
 }
 
 func Start(ctx context.Context) error {

internal/cmd/run.go

@@ -11,13 +11,13 @@ import (
 	"net/url"
 	"os"
 	"strings"
+	"sync"
 
 	"github.com/loveuer/esgo2dump/internal/interfaces"
 	"github.com/loveuer/esgo2dump/internal/opt"
 	"github.com/loveuer/esgo2dump/internal/xes"
 	"github.com/loveuer/esgo2dump/internal/xfile"
 	"github.com/samber/lo"
-	"github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
 )
 
@@ -52,9 +52,7 @@ func run(cmd *cobra.Command, args []string) error {
 	)
 
 	if opt.Debug {
-		logrus.SetLevel(logrus.DebugLevel)
+		log.SetLogLevel(log.LogLevelDebug)
-		logrus.SetReportCaller(true)
-		logrus.SetFormatter(&logrus.JSONFormatter{})
 	}
 
 	if f_version {
@@ -188,54 +186,61 @@ func executeData(ctx context.Context, input, output interfaces.DumpIO) error {
 	}
 
 	var (
-		dch <-chan []*model.ESSource
+		ok   bool
-		ech <-chan error
+		docs []*model.ESSource
+		dch  <-chan []*model.ESSource
+		ech  <-chan error
 
-		succeed int
+		e2ch = make(chan error)
-		total   int
+		wch  = make(chan []*model.ESSource)
-		docs    []*model.ESSource
+		wg   = sync.WaitGroup{}
-		ok      bool
 	)
 
+	go func() {
+		wg.Add(1)
+		if err = output.WriteData(ctx, wch); err != nil {
+			e2ch <- err
+		}
+
+		wg.Done()
+	}()
+
+	log.Info("Query: got queries=%d", len(queries))
+
 Loop:
-	for _, query := range queries {
+	for qi, query := range queries {
-		dch, ech = input.ReadData(ctx, f_limit, query, sources)
+		bs, _ := json.Marshal(query)
+
+		log.Debug("Query[%d]: %s", qi, string(bs))
+
+		dch, ech = input.ReadData(ctx, f_limit, query, sources, []string{f_sort})
+
 		for {
 			select {
 			case <-ctx.Done():
 				return ctx.Err()
-			case err = <-ech:
+			case err, ok = <-ech:
-				return err
+				if err != nil {
-			case docs, ok = <-dch:
-				logrus.
-					WithField("action", "run.ExecuteData").
-					WithField("read.docs", len(docs)).
-					WithField("read.ok", ok).
-					Debug()
-
-				if !ok {
-					continue Loop
-				}
-
-				if len(docs) == 0 {
-					continue Loop
-				}
-
-				if succeed, err = output.WriteData(ctx, docs); err != nil {
 					return err
 				}
 
-				if succeed != len(docs) {
+				continue Loop
-					return fmt.Errorf("output got lines=%d, only succeed=%d", len(docs), succeed)
+			case err, _ = <-e2ch:
+				return err
+			case docs, ok = <-dch:
+				if !ok || len(docs) == 0 {
+					continue Loop
 				}
 
-				total += succeed
+				wch <- docs
-
-				log.Info("Dump: succeed=%d total=%d docs succeed!!!", succeed, total)
 			}
 		}
 	}
 
+	close(wch)
+
+	wg.Wait()
+
 	return nil
 }
 
@@ -247,50 +252,26 @@ func newIO(source string, ioType interfaces.IO, esv string) (interfaces.DumpIO,
 		qm   = make(map[string]any)
 	)
 
-	logrus.
+	log.Debug("action=%s, type=%s, source=%s, es_version=%s", "new_io", ioType.Code(), source, esv)
-		WithField("action", "new_io").
-		WithField("type", ioType.Code()).
-		WithField("source", source).
-		WithField("es_version", esv).
-		Debug()
 
 	if iurl, err = url.Parse(source); err != nil {
-		logrus.
+		log.Debug("action=%s, type=%s, source=%s, err=%s", "new_io url parse err", ioType.Code(), source, err.Error())
-			WithField("action", "new_io url parse error").
-			WithField("type", ioType.Code()).
-			WithField("source", source).
-			WithField("err", err).
-			Debug()
 		goto ClientByFile
 	}
 
 	if !(iurl.Scheme == "http" || iurl.Scheme == "https") {
-		logrus.
+		log.Debug("action=%s, type=%s, source=%s, scheme=%s", "new_io url scheme error", ioType.Code(), source, iurl.Scheme)
-			WithField("action", "new_io url scheme error").
-			WithField("type", ioType.Code()).
-			WithField("source", source).
-			WithField("scheme", iurl.Scheme).
-			Debug()
 		goto ClientByFile
 	}
 
 	if iurl.Host == "" {
-		logrus.
+		log.Debug("action=%s, type=%s, source=%s", "new_io url host empty", ioType.Code(), source)
-			WithField("action", "new_io url host empty").
-			WithField("type", ioType.Code()).
-			WithField("source", source).
-			Debug()
 		goto ClientByFile
 	}
 
 	if ioType == interfaces.IOInput && f_query != "" {
 		if err = json.Unmarshal([]byte(f_query), &qm); err != nil {
-			logrus.
+			log.Debug("action=%s, type=%s, source=%s, query=%s", "new_io query string invalid", ioType.Code(), source, f_query)
-				WithField("action", "new_io query string invalid").
-				WithField("type", ioType.Code()).
-				WithField("source", source).
-				WithField("query", f_query).
-				Debug()
 			return nil, fmt.Errorf("invalid query err=%v", err)
 		}
 	}

internal/interfaces/dumpio.go

@@ -6,8 +6,8 @@ import (
 )
 
 type DumpIO interface {
-	ReadData(ctx context.Context, size int, query map[string]any, includeFields []string) (<-chan []*model.ESSource, <-chan error)
+	ReadData(ctx context.Context, size uint64, query map[string]any, includeFields []string, sort []string) (<-chan []*model.ESSource, <-chan error)
-	WriteData(ctx context.Context, docs []*model.ESSource) (int, error)
+	WriteData(ctx context.Context, docsCh <-chan []*model.ESSource) error
 
 	ReadMapping(context.Context) (map[string]any, error)
 	WriteMapping(context.Context, map[string]any) error

internal/util/min.go

@@ -0,0 +1,9 @@
+package util
+
+func Min[T ~string | ~int | ~int64 | ~uint64 | ~float64 | ~float32 | ~int32 | ~uint32 | ~int16 | ~uint16 | ~int8 | ~uint8](a, b T) T {
+	if a <= b {
+		return a
+	}
+
+	return b
+}

internal/xes/xes6.go

@@ -6,6 +6,7 @@ import (
 	"crypto/tls"
 	"encoding/json"
 	"fmt"
+	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
 	"github.com/loveuer/esgo2dump/xes/es6"
 	"net"
@@ -16,11 +17,9 @@ import (
 
 	elastic "github.com/elastic/go-elasticsearch/v6"
 	"github.com/elastic/go-elasticsearch/v6/esapi"
-	"github.com/elastic/go-elasticsearch/v6/esutil"
 	"github.com/loveuer/esgo2dump/internal/interfaces"
 	"github.com/loveuer/esgo2dump/internal/opt"
 	"github.com/loveuer/esgo2dump/internal/util"
-	"github.com/sirupsen/logrus"
 )
 
 func NewClientV6(url *url.URL, iot interfaces.IO) (interfaces.DumpIO, error) {
@@ -41,13 +40,7 @@ func NewClientV6(url *url.URL, iot interfaces.IO) (interfaces.DumpIO, error) {
 		}
 	}
 
-	logrus.
+	log.Debug("action=%s, endpoint=%s, index=%s, username=%s, password=%s", "new es client v6", address, urlIndex, urlUsername, urlPassword)
-		WithField("action", "new es client v6").
-		WithField("endpoint", address).
-		WithField("index", urlIndex).
-		WithField("username", urlUsername).
-		WithField("password", urlPassword).
-		Debug()
 
 	if urlIndex == "" {
 		return nil, fmt.Errorf("please specify index name: (like => http://127.0.0.1:9200/my_index)")
@@ -75,30 +68,20 @@ func NewClientV6(url *url.URL, iot interfaces.IO) (interfaces.DumpIO, error) {
 				},
 			},
 		); err != nil {
-			logrus.
+			log.Debug("action=%s, endpoints=%v, err=%s", "new es client v6 error", endpoints, err.Error())
-				WithField("action", "new es client v6 error").
-				WithField("endpoints", endpoints).
-				WithField("err", err).
-				Debug()
 			errCh <- err
 			return
 		}
 
 		if infoResp, err = cli.Info(); err != nil {
-			logrus.
+			log.Debug("action=%s, endpoints=%v, err=%s", "new es client v6 info error", endpoints, err.Error())
-				WithField("action", "es client v6 ping error").
-				WithField("err", err).
-				Debug()
 			errCh <- err
 			return
 		}
 
 		if infoResp.StatusCode != 200 {
 			err = fmt.Errorf("info xes status=%d", infoResp.StatusCode)
-			logrus.
+			log.Debug("action=%s, endpoints=%v, err=%s", "es client v6 ping status error", endpoints, err.Error())
-				WithField("action", "es client v6 ping status error").
-				WithField("status", infoResp.StatusCode).
-				Debug()
 			errCh <- err
 			return
 		}
@@ -124,6 +107,14 @@ type clientv6 struct {
 	index  string
 }
 
+func (c *clientv6) Info(msg string, data ...any) {
+	log.Info(msg, data...)
+}
+
+func (c *clientv6) WriteData(ctx context.Context, docsCh <-chan []*model.ESSource) error {
+	return es6.WriteData(ctx, c.client, c.index, docsCh, c)
+}
+
 func (c *clientv6) checkResponse(r *esapi.Response) error {
 	if r.StatusCode == 200 {
 		return nil
@@ -144,63 +135,8 @@ func (c *clientv6) Close() error {
 	return nil
 }
 
-func (c *clientv6) WriteData(ctx context.Context, docs []*model.ESSource) (int, error) {
+func (c *clientv6) ReadData(ctx context.Context, size uint64, query map[string]any, source []string, sort []string) (<-chan []*model.ESSource, <-chan error) {
-	var (
+	dch, ech := es6.ReadData(ctx, c.client, c.index, size, 0, query, source, sort)
-		err     error
-		indexer esutil.BulkIndexer
-		count   int
-		be      error
-	)
-	if indexer, err = esutil.NewBulkIndexer(esutil.BulkIndexerConfig{
-		Client:       c.client,
-		Index:        c.index,
-		DocumentType: "_doc",
-		ErrorTrace:   true,
-	}); err != nil {
-		return 0, err
-	}
-
-	for _, doc := range docs {
-		var bs []byte
-
-		if bs, err = json.Marshal(doc.Content); err != nil {
-			return 0, err
-		}
-
-		logrus.WithField("raw", string(bs)).Debug()
-
-		if err = indexer.Add(context.Background(), esutil.BulkIndexerItem{
-			Action:     "index",
-			Index:      c.index,
-			DocumentID: doc.DocId,
-			Body:       bytes.NewReader(bs),
-			OnFailure: func(ctx context.Context, item esutil.BulkIndexerItem, item2 esutil.BulkIndexerResponseItem, bulkErr error) {
-				be = bulkErr
-			},
-		}); err != nil {
-			return 0, err
-		}
-		count++
-	}
-
-	if err = indexer.Close(util.TimeoutCtx(ctx, opt.Timeout)); err != nil {
-		return 0, err
-	}
-
-	if be != nil {
-		return 0, be
-	}
-
-	stats := indexer.Stats()
-	if stats.NumFailed > 0 {
-		return count, fmt.Errorf("write to xes failed_count=%d bulk_count=%d", stats.NumFailed, count)
-	}
-
-	return count, nil
-}
-
-func (c *clientv6) ReadData(ctx context.Context, size int, query map[string]any, source []string) (<-chan []*model.ESSource, <-chan error) {
-	dch, ech := es6.ReadData(ctx, c.client, c.index, size, 0, query, source)
 
 	return dch, ech
 }

internal/xes/xes7.go

@@ -7,10 +7,10 @@ import (
 	"fmt"
 	elastic "github.com/elastic/go-elasticsearch/v7"
 	"github.com/elastic/go-elasticsearch/v7/esapi"
-	"github.com/elastic/go-elasticsearch/v7/esutil"
 	"github.com/loveuer/esgo2dump/internal/interfaces"
 	"github.com/loveuer/esgo2dump/internal/opt"
 	"github.com/loveuer/esgo2dump/internal/util"
+	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
 	"github.com/loveuer/esgo2dump/xes/es7"
 	"net/url"
@@ -23,6 +23,14 @@ type client struct {
 	index  string
 }
 
+func (c *client) Info(msg string, data ...any) {
+	log.Info(msg, data...)
+}
+
+func (c *client) WriteData(ctx context.Context, docsCh <-chan []*model.ESSource) error {
+	return es7.WriteData(ctx, c.client, c.index, docsCh, c)
+}
+
 func NewClient(url *url.URL, iot interfaces.IO) (interfaces.DumpIO, error) {
 
 	var (
@@ -62,63 +70,8 @@ func (c *client) Close() error {
 	return nil
 }
 
-func (c *client) WriteData(ctx context.Context, docs []*model.ESSource) (int, error) {
+func (c *client) ReadData(ctx context.Context, size uint64, query map[string]any, source []string, sort []string) (<-chan []*model.ESSource, <-chan error) {
-	var (
+	dch, ech := es7.ReadDataV2(ctx, c.client, c.index, size, 0, query, source, sort)
-		err     error
-		indexer esutil.BulkIndexer
-		count   int
-		be      error
-	)
-	if indexer, err = esutil.NewBulkIndexer(esutil.BulkIndexerConfig{
-		Client:     c.client,
-		Index:      c.index,
-		ErrorTrace: true,
-		OnError: func(ctx context.Context, err error) {
-
-		},
-	}); err != nil {
-		return 0, err
-	}
-
-	for _, doc := range docs {
-		var bs []byte
-
-		if bs, err = json.Marshal(doc.Content); err != nil {
-			return 0, err
-		}
-
-		if err = indexer.Add(context.Background(), esutil.BulkIndexerItem{
-			Action:     "index",
-			Index:      c.index,
-			DocumentID: doc.DocId,
-			Body:       bytes.NewReader(bs),
-			OnFailure: func(ctx context.Context, item esutil.BulkIndexerItem, item2 esutil.BulkIndexerResponseItem, bulkErr error) {
-				be = bulkErr
-			},
-		}); err != nil {
-			return 0, err
-		}
-		count++
-	}
-
-	if err = indexer.Close(util.TimeoutCtx(ctx, opt.Timeout)); err != nil {
-		return 0, err
-	}
-
-	if be != nil {
-		return 0, be
-	}
-
-	stats := indexer.Stats()
-	if stats.NumFailed > 0 {
-		return count, fmt.Errorf("write to xes failed_count=%d bulk_count=%d", stats.NumFailed, count)
-	}
-
-	return count, nil
-}
-
-func (c *client) ReadData(ctx context.Context, size int, query map[string]any, source []string) (<-chan []*model.ESSource, <-chan error) {
-	dch, ech := es7.ReadData(ctx, c.client, c.index, size, 0, query, source)
 
 	return dch, ech
 }

internal/xfile/xfile.go

@@ -5,6 +5,7 @@ import (
 	"context"
 	"encoding/json"
 	"github.com/loveuer/esgo2dump/internal/opt"
+	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
 	"io"
 	"os"
@@ -18,6 +19,29 @@ type client struct {
 	scanner *bufio.Scanner
 }
 
+func (c *client) WriteData(ctx context.Context, docsCh <-chan []*model.ESSource) error {
+	total := 0
+	for line := range docsCh {
+		for _, doc := range line {
+			bs, err := json.Marshal(doc)
+			if err != nil {
+				return err
+			}
+
+			if _, err = c.f.Write(append(bs, '\n')); err != nil {
+				return err
+			}
+		}
+
+		count := len(line)
+		total += count
+
+		log.Info("Dump: succeed=%d total=%d docs succeed!!!", count, total)
+	}
+
+	return nil
+}
+
 func (c *client) ReadMapping(ctx context.Context) (map[string]any, error) {
 	var (
 		err error
@@ -86,38 +110,14 @@ func (c *client) IsFile() bool {
 	return true
 }
 
-func (c *client) WriteData(ctx context.Context, docs []*model.ESSource) (int, error) {
+func (c *client) ReadData(ctx context.Context, size uint64, _ map[string]any, _ []string, _ []string) (<-chan []*model.ESSource, <-chan error) {
 	var (
 		err   error
-		bs    []byte
+		count uint64 = 0
-		count = 0
+		list         = make([]*model.ESSource, 0, size)
-	)
+		dch          = make(chan []*model.ESSource)
-
+		ech          = make(chan error)
-	for _, doc := range docs {
+		ready        = make(chan bool)
-		if bs, err = json.Marshal(doc); err != nil {
-			return count, err
-		}
-
-		bs = append(bs, '\n')
-
-		if _, err = c.f.Write(bs); err != nil {
-			return count, err
-		}
-
-		count++
-	}
-
-	return count, nil
-}
-
-func (c *client) ReadData(ctx context.Context, size int, _ map[string]any, _ []string) (<-chan []*model.ESSource, <-chan error) {
-	var (
-		err   error
-		count = 0
-		list  = make([]*model.ESSource, 0, size)
-		dch   = make(chan []*model.ESSource)
-		ech   = make(chan error)
-		ready = make(chan bool)
 	)
 
 	go func(ctx context.Context) {

log/default.go

@@ -0,0 +1,67 @@
+package log
+
+import (
+	"fmt"
+	"os"
+	"sync"
+)
+
+var (
+	nilLogger    = func(prefix, timestamp, msg string, data ...any) {}
+	normalLogger = func(prefix, timestamp, msg string, data ...any) {
+		fmt.Printf(prefix+"| "+timestamp+" | "+msg+"\n", data...)
+	}
+
+	panicLogger = func(prefix, timestamp, msg string, data ...any) {
+		panic(fmt.Sprintf(prefix+"| "+timestamp+" | "+msg+"\n", data...))
+	}
+
+	fatalLogger = func(prefix, timestamp, msg string, data ...any) {
+		fmt.Printf(prefix+"| "+timestamp+" | "+msg+"\n", data...)
+		os.Exit(1)
+	}
+
+	defaultLogger = &logger{
+		Mutex:      sync.Mutex{},
+		timeFormat: "2006-01-02T15:04:05",
+		writer:     os.Stdout,
+		level:      LogLevelInfo,
+		debug:      nilLogger,
+		info:       normalLogger,
+		warn:       normalLogger,
+		error:      normalLogger,
+		panic:      panicLogger,
+		fatal:      fatalLogger,
+	}
+)
+
+func SetTimeFormat(format string) {
+	defaultLogger.SetTimeFormat(format)
+}
+
+func SetLogLevel(level LogLevel) {
+	defaultLogger.SetLogLevel(level)
+}
+
+func Debug(msg string, data ...any) {
+	defaultLogger.Debug(msg, data...)
+}
+func Info(msg string, data ...any) {
+	defaultLogger.Info(msg, data...)
+}
+
+func Warn(msg string, data ...any) {
+	defaultLogger.Warn(msg, data...)
+}
+
+func Error(msg string, data ...any) {
+	defaultLogger.Error(msg, data...)
+}
+
+func Panic(msg string, data ...any) {
+	defaultLogger.Panic(msg, data...)
+}
+
+func Fatal(msg string, data ...any) {
+	defaultLogger.Fatal(msg, data...)
+}

log/log.go

@@ -1,50 +1,115 @@
 package log
 
 import (
-	"bytes"
-	"fmt"
 	"github.com/fatih/color"
+	"io"
 	"sync"
 	"time"
 )
 
-var (
+type LogLevel uint32
-	red    = color.New(color.FgRed)
-	green  = color.New(color.FgGreen)
-	yellow = color.New(color.FgYellow)
 
-	locker = &sync.Mutex{}
+const (
-
+	LogLevelDebug = iota
-	timeFormat = "06-01-02T15:04:05"
+	LogLevelInfo
+	LogLevelWarn
+	LogLevelError
+	LogLevelPanic
+	LogLevelFatal
 )
 
-func SetTimeFormat(format string) {
+type logger struct {
-	locker.Lock()
+	sync.Mutex
-	defer locker.Unlock()
+	timeFormat string
-
+	writer     io.Writer
-	timeFormat = format
+	level      LogLevel
+	debug      func(prefix, timestamp, msg string, data ...any)
+	info       func(prefix, timestamp, msg string, data ...any)
+	warn       func(prefix, timestamp, msg string, data ...any)
+	error      func(prefix, timestamp, msg string, data ...any)
+	panic      func(prefix, timestamp, msg string, data ...any)
+	fatal      func(prefix, timestamp, msg string, data ...any)
 }
 
-func Info(msg string, data ...any) {
+var (
-	buf := &bytes.Buffer{}
+	red    = color.New(color.FgRed)
-	_, _ = green.Fprint(buf, "Info  ")
+	hired  = color.New(color.FgHiRed)
-	_, _ = fmt.Fprintf(buf, "| %s | ", time.Now().Format(timeFormat))
+	green  = color.New(color.FgGreen)
-	_, _ = fmt.Fprintf(buf, msg, data...)
+	yellow = color.New(color.FgYellow)
-	fmt.Println(buf.String())
+	white  = color.New(color.FgWhite)
+)
+
+func (l *logger) SetTimeFormat(format string) {
+	l.Lock()
+	defer l.Unlock()
+	l.timeFormat = format
 }
 
-func Warn(msg string, data ...any) {
+func (l *logger) SetLogLevel(level LogLevel) {
-	buf := &bytes.Buffer{}
+	l.Lock()
-	_, _ = yellow.Fprint(buf, "Warn  ")
+	defer l.Unlock()
-	_, _ = fmt.Fprintf(buf, "| %s | ", time.Now().Format(timeFormat))
+
-	_, _ = fmt.Fprintf(buf, msg, data...)
+	if level > LogLevelDebug {
-	fmt.Println(buf.String())
+		l.debug = nilLogger
+	} else {
+		l.debug = normalLogger
+	}
+
+	if level > LogLevelInfo {
+		l.info = nilLogger
+	} else {
+		l.info = normalLogger
+	}
+
+	if level > LogLevelWarn {
+		l.warn = nilLogger
+	} else {
+		l.warn = normalLogger
+	}
+
+	if level > LogLevelError {
+		l.error = nilLogger
+	} else {
+		l.error = normalLogger
+	}
+
+	if level > LogLevelPanic {
+		l.panic = nilLogger
+	} else {
+		l.panic = panicLogger
+	}
+
+	if level > LogLevelFatal {
+		l.fatal = nilLogger
+	} else {
+		l.fatal = fatalLogger
+	}
 }
 
-func Error(msg string, data ...any) {
+func (l *logger) Debug(msg string, data ...any) {
-	buf := &bytes.Buffer{}
+	l.debug(white.Sprint("Debug "), time.Now().Format(l.timeFormat), msg, data...)
-	_, _ = red.Fprint(buf, "Error ")
+}
-	_, _ = fmt.Fprintf(buf, "| %s | ", time.Now().Format(timeFormat))
+
-	_, _ = fmt.Fprintf(buf, msg, data...)
+func (l *logger) Info(msg string, data ...any) {
-	fmt.Println(buf.String())
+	l.info(green.Sprint("Info  "), time.Now().Format(l.timeFormat), msg, data...)
+}
+
+func (l *logger) Warn(msg string, data ...any) {
+	l.warn(yellow.Sprint("Warn  "), time.Now().Format(l.timeFormat), msg, data...)
+}
+
+func (l *logger) Error(msg string, data ...any) {
+	l.error(red.Sprint("Error "), time.Now().Format(l.timeFormat), msg, data...)
+}
+
+func (l *logger) Panic(msg string, data ...any) {
+	l.panic(hired.Sprint("Panic "), time.Now().Format(l.timeFormat), msg, data...)
+}
+
+func (l *logger) Fatal(msg string, data ...any) {
+	l.fatal(hired.Sprint("Fatal "), time.Now().Format(l.timeFormat), msg, data...)
+}
+
+type WroteLogger interface {
+	Info(msg string, data ...any)
 }

log/new.go

@@ -0,0 +1,21 @@
+package log
+
+import (
+	"os"
+	"sync"
+)
+
+func New() *logger {
+	return &logger{
+		Mutex:      sync.Mutex{},
+		timeFormat: "2006-01-02T15:04:05",
+		writer:     os.Stdout,
+		level:      LogLevelInfo,
+		debug:      nilLogger,
+		info:       normalLogger,
+		warn:       normalLogger,
+		error:      normalLogger,
+		panic:      panicLogger,
+		fatal:      fatalLogger,
+	}
+}

model/es.go

@@ -4,9 +4,27 @@ type ESSource struct {
 	DocId   string         `json:"_id"`
 	Index   string         `json:"_index"`
 	Content map[string]any `json:"_source"`
+	Sort    []any          `json:"sort"`
 }
 
-type ESResponse struct {
+type ESResponseV6 struct {
+	ScrollId string `json:"_scroll_id"`
+	Took     int    `json:"took"`
+	TimedOut bool   `json:"timed_out"`
+	Shards   struct {
+		Total      int `json:"total"`
+		Successful int `json:"successful"`
+		Skipped    int `json:"skipped"`
+		Failed     int `json:"failed"`
+	} `json:"_shards"`
+	Hits struct {
+		Total    int         `json:"total"`
+		MaxScore float64     `json:"max_score"`
+		Hits     []*ESSource `json:"hits"`
+	} `json:"hits"`
+}
+
+type ESResponseV7 struct {
 	ScrollId string `json:"_scroll_id"`
 	Took     int    `json:"took"`
 	TimedOut bool   `json:"timed_out"`

readme.md

@@ -53,7 +53,8 @@ esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json --query_
 - [x] es to file
 - [x] es to es
 - [x] auto create index with mapping
+- [x] support es6
+- [ ] [Feature Request #1](https://github.com/loveuer/esgo2dump/issues/1): Supports more than 10,000 lines of query_file
 - [ ] args: split_size (auto split json output file)
 - [ ] auto create index with mapping,setting
-- [x] support es6
 - [ ] support es8

xes/es6/read.go

@@ -10,10 +10,11 @@ import (
 	"github.com/loveuer/esgo2dump/internal/util"
 	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
+	"github.com/samber/lo"
 	"time"
 )
 
-func ReadData(ctx context.Context, client *elastic.Client, index string, size, max int, query map[string]any, source []string) (<-chan []*model.ESSource, <-chan error) {
+func ReadData(ctx context.Context, client *elastic.Client, index string, size, max uint64, query map[string]any, source []string, sort []string) (<-chan []*model.ESSource, <-chan error) {
 	var (
 		dataCh = make(chan []*model.ESSource)
 		errCh  = make(chan error)
@@ -23,9 +24,9 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 		var (
 			err      error
 			resp     *esapi.Response
-			result   = new(model.ESResponse)
+			result   = new(model.ESResponseV6)
 			scrollId string
-			total    int
+			total    uint64
 		)
 
 		defer func() {
@@ -62,7 +63,7 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 		qs := []func(*esapi.SearchRequest){
 			client.Search.WithContext(util.TimeoutCtx(ctx, 20)),
 			client.Search.WithIndex(index),
-			client.Search.WithSize(size),
+			client.Search.WithSize(int(size)),
 			client.Search.WithFrom(0),
 			client.Search.WithScroll(time.Duration(120) * time.Second),
 		}
@@ -71,6 +72,16 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 			qs = append(qs, client.Search.WithSourceIncludes(source...))
 		}
 
+		if len(sort) > 0 {
+			sorts := lo.Filter(sort, func(item string, index int) bool {
+				return item != ""
+			})
+
+			if len(sorts) > 0 {
+				qs = append(qs, client.Search.WithSort(sorts...))
+			}
+		}
+
 		if query != nil && len(query) > 0 {
 			queryBs, _ := json.Marshal(map[string]any{"query": query})
 			qs = append(qs, client.Search.WithBody(bytes.NewReader(queryBs)))
@@ -95,9 +106,9 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 		scrollId = result.ScrollId
 
 		dataCh <- result.Hits.Hits
-		total += len(result.Hits.Hits)
+		total += uint64(len(result.Hits.Hits))
 
-		if len(result.Hits.Hits) < size || (max > 0 && total >= max) {
+		if uint64(len(result.Hits.Hits)) < size || (max > 0 && total >= max) {
 			return
 		}
 
@@ -110,7 +121,7 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 				return
 			}
 
-			result = new(model.ESResponse)
+			result = new(model.ESResponseV6)
 
 			decoder = json.NewDecoder(resp.Body)
 			if err = decoder.Decode(result); err != nil {
@@ -124,9 +135,9 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 			}
 
 			dataCh <- result.Hits.Hits
-			total += len(result.Hits.Hits)
+			total += uint64(len(result.Hits.Hits))
 
-			if len(result.Hits.Hits) < size || (max > 0 && total >= max) {
+			if uint64(len(result.Hits.Hits)) < size || (max > 0 && total >= max) {
 				break
 			}
 		}

xes/es6/write.go

@@ -7,13 +7,15 @@ import (
 	"fmt"
 	elastic "github.com/elastic/go-elasticsearch/v6"
 	"github.com/elastic/go-elasticsearch/v6/esutil"
+	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
 )
 
-func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh <-chan []*model.ESSource) error {
+func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh <-chan []*model.ESSource, logs ...log.WroteLogger) error {
 	var (
 		err     error
 		indexer esutil.BulkIndexer
+		total   = 0
 	)
 
 	for {
@@ -64,6 +66,8 @@ func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh
 				count++
 			}
 
+			total += count
+
 			if err = indexer.Close(ctx); err != nil {
 				return err
 			}
@@ -72,6 +76,10 @@ func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh
 			if stats.NumFailed > 0 {
 				return fmt.Errorf("write to es failed_count=%d bulk_count=%d", stats.NumFailed, count)
 			}
+
+			if len(logs) > 0 && logs[0] != nil {
+				logs[0].Info("Dump: succeed=%d total=%d docs succeed!!!", count, total)
+			}
 		}
 	}
 }

xes/es7/client.go

@@ -7,9 +7,11 @@ import (
 	elastic "github.com/elastic/go-elasticsearch/v7"
 	"github.com/elastic/go-elasticsearch/v7/esapi"
 	"github.com/loveuer/esgo2dump/internal/util"
+	"github.com/samber/lo"
 	"net"
 	"net/http"
 	"net/url"
+	"strings"
 	"time"
 )
 
@@ -21,7 +23,12 @@ func NewClient(ctx context.Context, url *url.URL) (*elastic.Client, error) {
 		client      *elastic.Client
 		errCh       = make(chan error)
 		cliCh       = make(chan *elastic.Client)
-		address     = fmt.Sprintf("%s://%s", url.Scheme, url.Host)
+		endpoints   = lo.Map(
+			strings.Split(url.Host, ","),
+			func(item string, index int) string {
+				return fmt.Sprintf("%s://%s", url.Scheme, item)
+			},
+		)
 	)
 
 	if url.User != nil {
@@ -71,12 +78,12 @@ func NewClient(ctx context.Context, url *url.URL) (*elastic.Client, error) {
 		cliCh <- cli
 	}
 
-	go ncFunc([]string{address}, urlUsername, urlPassword)
+	go ncFunc(endpoints, urlUsername, urlPassword)
 	timeout := util.TimeoutCtx(ctx, 10)
 
 	select {
 	case <-timeout.Done():
-		return nil, fmt.Errorf("dial es=%s err=%v", address, context.DeadlineExceeded)
+		return nil, fmt.Errorf("dial es=%v err=%v", endpoints, context.DeadlineExceeded)
 	case client = <-cliCh:
 		return client, nil
 	case err = <-errCh:

xes/es7/client_test.go

@@ -0,0 +1,20 @@
+package es7
+
+import (
+	"github.com/loveuer/esgo2dump/internal/util"
+	"net/url"
+	"testing"
+)
+
+func TestNewClient(t *testing.T) {
+	uri := "http://es1.dev:9200,es2.dev:9200"
+	ins, _ := url.Parse(uri)
+
+	c, err := NewClient(util.Timeout(5), ins)
+	if err != nil {
+		t.Fatal(err.Error())
+	}
+
+	t.Log("success!!!")
+	_ = c
+}

xes/es7/read.go

@@ -10,10 +10,15 @@ import (
 	"github.com/loveuer/esgo2dump/internal/util"
 	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
+	"github.com/samber/lo"
 	"time"
 )
 
-func ReadData(ctx context.Context, client *elastic.Client, index string, size, max int, query map[string]any, source []string) (<-chan []*model.ESSource, <-chan error) {
+// ReadData
+// Deprecated
+// @param[source]: a list of include fields to extract and return from the _source field.
+// @param[sort]:   a list of <field>:<direction> pairs.
+func ReadData(ctx context.Context, client *elastic.Client, index string, size, max int, query map[string]any, source []string, sort []string) (<-chan []*model.ESSource, <-chan error) {
 	var (
 		dataCh = make(chan []*model.ESSource)
 		errCh  = make(chan error)
@@ -23,7 +28,7 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 		var (
 			err      error
 			resp     *esapi.Response
-			result   = new(model.ESResponse)
+			result   = new(model.ESResponseV7)
 			scrollId string
 			total    int
 		)
@@ -71,6 +76,16 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 			qs = append(qs, client.Search.WithSourceIncludes(source...))
 		}
 
+		if len(sort) > 0 {
+			sorts := lo.Filter(sort, func(item string, index int) bool {
+				return item != ""
+			})
+
+			if len(sorts) > 0 {
+				qs = append(qs, client.Search.WithSort(sorts...))
+			}
+		}
+
 		if query != nil && len(query) > 0 {
 			queryBs, _ := json.Marshal(map[string]any{"query": query})
 			qs = append(qs, client.Search.WithBody(bytes.NewReader(queryBs)))
@@ -110,7 +125,7 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 				return
 			}
 
-			result = new(model.ESResponse)
+			result = new(model.ESResponseV7)
 
 			decoder = json.NewDecoder(resp.Body)
 			if err = decoder.Decode(result); err != nil {
@@ -134,3 +149,113 @@ func ReadData(ctx context.Context, client *elastic.Client, index string, size, m
 
 	return dataCh, errCh
 }
+
+// ReadDataV2 es7 read data
+/*
+	- @param[source]: a list of include fields to extract and return from the _source field.
+    - @param[sort]:   a list of <field>:<direction> pairs.
+*/
+func ReadDataV2(
+	ctx context.Context,
+	client *elastic.Client,
+	index string,
+	size, max uint64,
+	query map[string]any,
+	source []string,
+	sort []string,
+) (<-chan []*model.ESSource, <-chan error) {
+	var (
+		dataCh = make(chan []*model.ESSource)
+		errCh  = make(chan error)
+	)
+
+	go func() {
+		var (
+			err         error
+			bs          []byte
+			resp        *esapi.Response
+			searchAfter        = make([]any, 0)
+			total       uint64 = 0
+			body               = make(map[string]any)
+			qs          []func(request *esapi.SearchRequest)
+		)
+
+		if sort == nil {
+			sort = []string{}
+		}
+
+		if query != nil && len(query) > 0 {
+			body["query"] = query
+		}
+
+		sort = append(sort, "_id:ASC")
+
+		sorts := lo.Filter(sort, func(item string, index int) bool {
+			return item != ""
+		})
+
+		defer func() {
+			close(dataCh)
+			close(errCh)
+		}()
+
+		for {
+			qs = []func(*esapi.SearchRequest){
+				client.Search.WithContext(util.TimeoutCtx(ctx, 30)),
+				client.Search.WithIndex(index),
+				client.Search.WithSize(int(util.Min(size, max-total))),
+				client.Search.WithSort(sorts...),
+			}
+
+			if len(source) > 0 {
+				qs = append(qs, client.Search.WithSourceIncludes(source...))
+			}
+
+			delete(body, "search_after")
+			if len(searchAfter) > 0 {
+				body["search_after"] = searchAfter
+			}
+
+			if bs, err = json.Marshal(body); err != nil {
+				errCh <- err
+				return
+			}
+
+			qs = append(qs, client.Search.WithBody(bytes.NewReader(bs)))
+			if resp, err = client.Search(qs...); err != nil {
+				errCh <- err
+				return
+			}
+
+			if resp.StatusCode != 200 {
+				errCh <- fmt.Errorf("resp status=%d, resp=%s", resp.StatusCode, resp.String())
+				return
+			}
+
+			var result = new(model.ESResponseV7)
+			decoder := json.NewDecoder(resp.Body)
+			if err = decoder.Decode(result); err != nil {
+				errCh <- err
+				return
+			}
+
+			if resp.StatusCode != 200 {
+				errCh <- fmt.Errorf("resp status=%d, resp=%s", resp.StatusCode, resp.String())
+				return
+			}
+
+			dataCh <- result.Hits.Hits
+			total += uint64(len(result.Hits.Hits))
+
+			if uint64(len(result.Hits.Hits)) < size || (max > 0 && total >= max) {
+				break
+			}
+
+			searchAfter = result.Hits.Hits[len(result.Hits.Hits)-1].Sort
+		}
+
+	}()
+
+	return dataCh, errCh
+
+}

xes/es7/write.go

@@ -7,13 +7,15 @@ import (
 	"fmt"
 	elastic "github.com/elastic/go-elasticsearch/v7"
 	"github.com/elastic/go-elasticsearch/v7/esutil"
+	"github.com/loveuer/esgo2dump/log"
 	"github.com/loveuer/esgo2dump/model"
 )
 
-func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh <-chan []*model.ESSource) error {
+func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh <-chan []*model.ESSource, logs ...log.WroteLogger) error {
 	var (
 		err     error
 		indexer esutil.BulkIndexer
+		total   int
 	)
 
 	for {
@@ -63,6 +65,8 @@ func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh
 				count++
 			}
 
+			total += count
+
 			if err = indexer.Close(ctx); err != nil {
 				return err
 			}
@@ -71,6 +75,10 @@ func WriteData(ctx context.Context, client *elastic.Client, index string, docsCh
 			if stats.NumFailed > 0 {
 				return fmt.Errorf("write to es failed_count=%d bulk_count=%d", stats.NumFailed, count)
 			}
+
+			if len(logs) > 0 && logs[0] != nil {
+				logs[0].Info("Dump: succeed=%d total=%d docs succeed!!!", count, total)
+			}
 		}
 	}
 }