feat: add input(es) source support

go.mod

@@ -4,6 +4,7 @@ go 1.18
 
 require (
 	github.com/elastic/go-elasticsearch/v7 v7.17.10
+	github.com/samber/lo v1.39.0
 	github.com/sirupsen/logrus v1.9.3
 	github.com/spf13/cobra v1.8.0
 )
@@ -12,5 +13,6 @@ require (
 	github.com/inconshreveable/mousetrap v1.1.0 // 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

@@ -9,6 +9,8 @@ github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLf
 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=
@@ -19,6 +21,8 @@ github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
 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 v0.14.0 h1:Vz7Qs629MkJkGyHxUlRHizWJRG2j8fbQKjELVSNhy7Q=
 golang.org/x/sys v0.14.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=

internal/cmd/cmd.go

@@ -21,6 +21,8 @@ esgo2dump --input=http://127.0.0.1:9200/some_index --output=http://192.168.1.1:9
 
 esgo2dump --input=https://username:password@127.0.0.1:9200/some_index --output=./data.json
 
+esgo2dump --input=http://127.0.0.1:9200/some_index --source='id;name;age;address' --output=./data.json
+
 esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json --query='{"match": {"name": "some_name"}}'
 
 esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json --query_file=my_queries.json`,
@@ -30,6 +32,7 @@ esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json --query_
 	f_output string
 	f_limit  int
 	f_type   string
+	f_source string
 	f_query  string
 
 	f_query_file string
@@ -45,6 +48,7 @@ func init() {
 	rootCommand.Flags().StringVarP(&f_input, "input", "i", "", "*required: input file or es url (example :data.json / http://127.0.0.1:9200/my_index)")
 	rootCommand.Flags().StringVarP(&f_output, "output", "o", "output.json", "")
 	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().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, "")

internal/cmd/run.go

@@ -7,11 +7,13 @@ import (
 	"fmt"
 	"net/url"
 	"os"
+	"strings"
 
 	"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"
 )
@@ -76,6 +78,10 @@ func run(cmd *cobra.Command, args []string) error {
 		return fmt.Errorf("with file input, query or query_file can't be supported")
 	}
 
+	if (f_source != "") && ioi.IsFile() {
+		return fmt.Errorf("with file input, source can't be supported")
+	}
+
 	switch f_type {
 	case "data":
 		if err = executeData(cmd.Context(), ioi, ioo); err != nil {
@@ -122,8 +128,15 @@ func executeData(ctx context.Context, input, output interfaces.DumpIO) error {
 		ch      = make(chan []*interfaces.ESSource, 1)
 		errCh   = make(chan error)
 		queries = make([]map[string]any, 0)
+		sources = make([]string, 0)
 	)
 
+	if f_source != "" {
+		sources = lo.Map(strings.Split(f_source, ";"), func(item string, idx int) string {
+			return strings.TrimSpace(item)
+		})
+	}
+
 	if f_query != "" {
 		query := make(map[string]any)
 		if err = json.Unmarshal([]byte(f_query), &query); err != nil {
@@ -187,7 +200,7 @@ func executeData(ctx context.Context, input, output interfaces.DumpIO) error {
 				case <-c.Done():
 					return
 				default:
-					if lines, err = input.ReadData(c, f_limit, query); err != nil {
+					if lines, err = input.ReadData(c, f_limit, query, sources); err != nil {
 						errCh <- err
 						return
 					}

internal/interfaces/dumpio.go

@@ -3,7 +3,7 @@ package interfaces
 import "context"
 
 type DumpIO interface {
-	ReadData(context.Context, int, map[string]any) ([]*ESSource, error)
+	ReadData(context.Context, int, map[string]any, []string) ([]*ESSource, error)
 	WriteData(ctx context.Context, docs []*ESSource) (int, error)
 
 	ResetOffset()

internal/xes/xes.go

@@ -201,7 +201,7 @@ func (c *client) WriteData(ctx context.Context, docs []*interfaces.ESSource) (in
 	return count, nil
 }
 
-func (c *client) ReadData(ctx context.Context, i int, query map[string]any) ([]*interfaces.ESSource, error) {
+func (c *client) ReadData(ctx context.Context, i int, query map[string]any, source []string) ([]*interfaces.ESSource, error) {
 	var (
 		err    error
 		resp   *esapi.Response
@@ -217,6 +217,10 @@ func (c *client) ReadData(ctx context.Context, i int, query map[string]any) ([]*
 			c.c.Search.WithScroll(time.Duration(opt.Timeout*2) * time.Second),
 		}
 
+		if len(source) > 0 {
+			qs = append(qs, c.c.Search.WithSourceIncludes(source...))
+		}
+
 		if query != nil && len(query) > 0 {
 			queryBs, _ := json.Marshal(map[string]any{"query": query})
 			qs = append(qs, c.c.Search.WithBody(bytes.NewReader(queryBs)))

internal/xfile/xfile.go

@@ -4,10 +4,11 @@ import (
 	"bufio"
 	"context"
 	"encoding/json"
-	"github.com/loveuer/esgo2dump/internal/opt"
 	"io"
 	"os"
 
+	"github.com/loveuer/esgo2dump/internal/opt"
+
 	"github.com/loveuer/esgo2dump/internal/interfaces"
 )
 
@@ -111,7 +112,7 @@ func (c *client) WriteData(ctx context.Context, docs []*interfaces.ESSource) (in
 	return count, nil
 }
 
-func (c *client) ReadData(ctx context.Context, i int, _ map[string]any) ([]*interfaces.ESSource, error) {
+func (c *client) ReadData(ctx context.Context, i int, _ map[string]any, _ []string) ([]*interfaces.ESSource, error) {
 	var (
 		err   error
 		count = 0