feat: read,write data with buffered

v0.0.3 beta

.github/workflows/build.yml

@@ -13,10 +13,13 @@ jobs:
       pull-requests: write
       repository-projects: write
     steps:
+      - name: checkout repository
+        uses: actions/checkout@v4
+
       - name: install golang
         uses: actions/setup-go@v4
         with:
-          go-version: '1.20'
+          go-version: '1.18'
 
       - name: build linux amd64
         run: CGO_ENABLE=0 GOOS=linux GOARCH=amd64 go build -ldflags='-s -w' -o dist/esgo2dump_${{ github.ref_name }}_linux_amd64 .
@@ -27,6 +30,9 @@ jobs:
       - name: build windows amd64
         run: CGO_ENABLE=0 GOOS=windows GOARCH=amd64 go build -ldflags='-s -w' -o dist/esgo2dump_${{ github.ref_name }}_windows_amd64.exe .
 
+      - name: build windows arm64
+        run: CGO_ENABLE=0 GOOS=windows GOARCH=arm64 go build -ldflags='-s -w' -o dist/esgo2dump_${{ github.ref_name }}_windows_arm64.exe .
+
       - name: build darwin amd64
         run: CGO_ENABLE=0 GOOS=darwin GOARCH=amd64 go build -ldflags='-s -w' -o dist/esgo2dump_${{ github.ref_name }}_darwin_amd64 .
 
@@ -34,7 +40,7 @@ jobs:
         run: CGO_ENABLE=0 GOOS=darwin GOARCH=arm64 go build -ldflags='-s -w' -o dist/esgo2dump_${{ github.ref_name }}_darwin_arm64 .
 
       - name: create releases
-        id: create_release
+        id: create_releases
         uses: "marvinpinto/action-automatic-releases@latest"
         with:
           repo_token: "${{ secrets.GITHUB_TOKEN }}"
@@ -43,6 +49,7 @@ jobs:
             dist/esgo2dump_${{ github.ref_name }}_linux_amd64
             dist/esgo2dump_${{ github.ref_name }}_linux_arm64
             dist/esgo2dump_${{ github.ref_name }}_windows_amd64.exe
+            dist/esgo2dump_${{ github.ref_name }}_windows_arm64.exe
             dist/esgo2dump_${{ github.ref_name }}_darwin_amd64
             dist/esgo2dump_${{ github.ref_name }}_darwin_amd64
             dist/esgo2dump_${{ github.ref_name }}_darwin_arm64

.gitignore

@@ -5,4 +5,5 @@ data.json
 mapping.json
 setting.json
 output.json
-*.txt
+*.txt
+dist

go.mod

@@ -1,4 +1,4 @@
-module esgo2dump
+module github.com/loveuer/esgo2dump
 
 go 1.18
 

internal/cmd/cmd.go

@@ -2,7 +2,8 @@ package cmd
 
 import (
 	"context"
-	"esgo2dump/internal/opt"
+
+	"github.com/loveuer/esgo2dump/internal/opt"
 	"github.com/spf13/cobra"
 )
 

internal/cmd/run.go

@@ -3,17 +3,16 @@ package cmd
 import (
 	"context"
 	"encoding/json"
-	"errors"
-	"esgo2dump/internal/interfaces"
-	"esgo2dump/internal/opt"
-	"esgo2dump/internal/xes"
-	"esgo2dump/internal/xfile"
 	"fmt"
-	"github.com/sirupsen/logrus"
-	"github.com/spf13/cobra"
-	"io"
 	"net/url"
 	"os"
+
+	"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/sirupsen/logrus"
+	"github.com/spf13/cobra"
 )
 
 func run(cmd *cobra.Command, args []string) error {
@@ -27,6 +26,10 @@ func run(cmd *cobra.Command, args []string) error {
 		logrus.SetLevel(logrus.DebugLevel)
 	}
 
+	if f_limit == 0 || f_limit > 10000 {
+		return fmt.Errorf("invalid limit(1 - 10000)")
+	}
+
 	switch f_type {
 	case "data", "mapping", "setting":
 	default:
@@ -55,14 +58,26 @@ func run(cmd *cobra.Command, args []string) error {
 			return err
 		}
 
-		return ioo.WriteMapping(cmd.Context(), mapping)
+		if err = ioo.WriteMapping(cmd.Context(), mapping); err != nil {
+			return err
+		}
+
+		logrus.Info("Dump: write mapping succeed!!!")
+
+		return nil
 	case "setting":
 		var setting map[string]any
 		if setting, err = ioi.ReadSetting(cmd.Context()); err != nil {
 			return err
 		}
 
-		return ioo.WriteSetting(cmd.Context(), setting)
+		if err = ioo.WriteSetting(cmd.Context(), setting); err != nil {
+			return err
+		}
+
+		logrus.Info("Dump: write setting succeed!!!")
+
+		return nil
 	default:
 		return fmt.Errorf("unknown type=%s", f_type)
 	}
@@ -70,35 +85,74 @@ func run(cmd *cobra.Command, args []string) error {
 
 func executeData(ctx context.Context, input, output interfaces.DumpIO) error {
 	var (
-		err     error
-		lines   []*interfaces.ESSource
+		err   error
+		ch    = make(chan []*interfaces.ESSource, 1)
+		errCh = make(chan error)
+	)
+
+	// write goroutine
+	go func(c context.Context) {
+		var (
+			lines []*interfaces.ESSource
+		)
+
+		defer func() {
+			close(ch)
+		}()
+
+		for {
+			select {
+			case <-c.Done():
+				return
+			default:
+				if lines, err = input.ReadData(c, f_limit); err != nil {
+					errCh <- err
+					return
+				}
+
+				if len(lines) == 0 {
+					ch <- lines
+					return
+				}
+
+				ch <- lines
+			}
+		}
+	}(ctx)
+
+	var (
 		succeed int
+		total   int
+		docs    []*interfaces.ESSource
+		ok      bool
 	)
 
 	for {
+		select {
+		case <-ctx.Done():
+		case err = <-errCh:
+			return err
+		case docs, ok = <-ch:
+			if !ok {
+				return err
+			}
 
-		if lines, err = input.ReadData(ctx, f_limit); err != nil {
-			if errors.Is(err, io.EOF) {
+			if len(docs) == 0 {
 				return nil
 			}
 
-			return err
+			if succeed, err = output.WriteData(ctx, docs); err != nil {
+				return err
+			}
+
+			if succeed != len(docs) {
+				return fmt.Errorf("cmd.run: got lines=%d, only succeed=%d", len(docs), succeed)
+			}
+
+			total += succeed
+
+			logrus.Infof("Dump: succeed=%d total=%d docs succeed!!!", succeed, total)
 		}
-
-		if len(lines) == 0 {
-			return nil
-		}
-
-		if succeed, err = output.WriteData(ctx, lines); err != nil {
-			return err
-		}
-
-		if succeed != len(lines) {
-			return fmt.Errorf("cmd.run: got lines=%d, only succeed=%d", len(lines), succeed)
-		}
-
-		logrus.Infof("Dump: %d docs succeed!!!", succeed)
-
 	}
 }
 

internal/xes/xes.go

@@ -5,18 +5,20 @@ import (
 	"context"
 	"crypto/tls"
 	"encoding/json"
-	"esgo2dump/internal/interfaces"
-	"esgo2dump/internal/opt"
-	"esgo2dump/internal/util"
 	"fmt"
-	elastic "github.com/elastic/go-elasticsearch/v7"
-	"github.com/elastic/go-elasticsearch/v7/esapi"
-	"github.com/elastic/go-elasticsearch/v7/esutil"
-	"github.com/sirupsen/logrus"
+	"net"
 	"net/http"
 	"net/url"
 	"strings"
 	"time"
+
+	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/sirupsen/logrus"
 )
 
 func NewClient(url *url.URL, iot interfaces.IO, qm map[string]any) (interfaces.DumpIO, error) {
@@ -55,6 +57,7 @@ func NewClient(url *url.URL, iot interfaces.IO, qm map[string]any) (interfaces.D
 			RetryBackoff:  nil,
 			Transport: &http.Transport{
 				TLSClientConfig: &tls.Config{InsecureSkipVerify: true},
+				DialContext:     (&net.Dialer{Timeout: 5 * time.Second}).DialContext,
 			},
 		},
 	); err != nil {
@@ -108,6 +111,7 @@ func (c *client) WriteData(ctx context.Context, docs []*interfaces.ESSource) (in
 		err     error
 		indexer esutil.BulkIndexer
 		count   int
+		be      error
 	)
 	if indexer, err = esutil.NewBulkIndexer(esutil.BulkIndexerConfig{
 		Client:  c.c,
@@ -131,6 +135,9 @@ func (c *client) WriteData(ctx context.Context, docs []*interfaces.ESSource) (in
 			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
 		}
@@ -141,9 +148,13 @@ func (c *client) WriteData(ctx context.Context, docs []*interfaces.ESSource) (in
 		return 0, err
 	}
 
+	if be != nil {
+		return 0, be
+	}
+
 	stats := indexer.Stats()
 	if stats.NumFailed > 0 {
-		return count, fmt.Errorf("write to xes failed=%d", stats.NumFailed)
+		return count, fmt.Errorf("write to xes failed_count=%d bulk_count=%d", stats.NumFailed, count)
 	}
 
 	return count, nil

internal/xes/xes_test.go

@@ -1,9 +1,10 @@
 package xes
 
 import (
-	"esgo2dump/internal/util"
-	elastic "github.com/elastic/go-elasticsearch/v7"
 	"testing"
+
+	elastic "github.com/elastic/go-elasticsearch/v7"
+	"github.com/loveuer/esgo2dump/internal/util"
 )
 
 func TestGetESMapping(t *testing.T) {

internal/xfile/xfile.go

@@ -4,10 +4,11 @@ import (
 	"bufio"
 	"context"
 	"encoding/json"
-	"esgo2dump/internal/interfaces"
-	"github.com/sirupsen/logrus"
 	"io"
 	"os"
+
+	"github.com/loveuer/esgo2dump/internal/interfaces"
+	"github.com/sirupsen/logrus"
 )
 
 type client struct {

main.go

@@ -2,10 +2,11 @@ package main
 
 import (
 	"context"
-	"esgo2dump/internal/cmd"
 	"os/signal"
 	"syscall"
 
+	"github.com/loveuer/esgo2dump/internal/cmd"
+
 	"github.com/sirupsen/logrus"
 )
 

readme.md

@@ -15,24 +15,28 @@
 
 - download pre-build release:
 
-  [release](https://github.com/loveuer/esgo2dump/releases)
+  [releases](https://github.com/loveuer/esgo2dump/releases)
 
 ### usage
 
 `esgo2dump -h`
 
+```bash
+esgo2dump --input=http://127.0.0.1:9200/some_index --output=./data.json
+
+esgo2dump --input=http://127.0.0.1:9200/some_index --output=http://192.168.1.1:9200/some_index --limit=5000
+
+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 --output=./data.json --query='{"match": {"name": "some_name"}}'`,
+```
+
 ### roadmap
 
-[*] data dump
-
-[*] mapping dump
-
-[*] es to file
-
-[*] es to es
-
-[*] auto create index with mapping
-
-[ ] auto create index with mapping,setting
-
-[ ] support es8
+- [x] data dump
+- [x] mapping dump
+- [x] es to file
+- [x] es to es
+- [x] auto create index with mapping
+- [ ] auto create index with mapping,setting
+- [ ] support es8