feat(parser): add csv document parser

components/document/parser/csv/csv_parser.go

@@ -0,0 +1,133 @@
+package csv
+
+import (
+	"encoding/csv"
+	"fmt"
+	"io"
+	"strings"
+
+	"context"
+
+	"github.com/cloudwego/eino/components/document/parser"
+	"github.com/cloudwego/eino/schema"
+)
+
+const (
+	MetaDataRow = "_row"
+	MetaDataExt = "_ext"
+)
+
+// CSVParser parses CSV content from io.Reader.
+type CSVParser struct {
+	Config *Config
+}
+
+// Config Used to configure CsvParser.
+type Config struct {
+	// NoHeader is set to false by default, which means that the first row is used as the table header
+	NoHeader bool
+	// IDPrefix is set to customize the prefix of document ID, default 1,2,3, ...
+	IDPrefix string
+	// Comma is set to ',' by default, which means that the comma is used as the field delimiter
+	Comma rune
+	// Comment is set to '#' by default, which means that the '#' character is used as the comment character
+	Comment rune
+}
+
+// NewCSVParser creates a new CSVParser
+func NewCSVParser(ctx context.Context, config *Config) (cp *CSVParser, err error) {
+	if config == nil {
+		config = &Config{}
+
+	}
+	if config.Comma == 0 {
+		config.Comma = rune(',')
+	}
+	if config.Comment == 0 {
+		config.Comment = rune('#')
+	}
+
+	cp = &CSVParser{Config: config}
+	return cp, nil
+}
+
+// generateID generates document ID based on configuration
+func (cp *CSVParser) generateID(i int) string {
+	if cp.Config.IDPrefix == "" {
+		return fmt.Sprintf("%d", i)
+	}
+	return fmt.Sprintf("%s%d", cp.Config.IDPrefix, i)
+}
+
+func (cp *CSVParser) buildRowMetaData(row []string, headers []string) map[string]any {
+	metaData := make(map[string]any)
+	if !cp.Config.NoHeader {
+		for j, header := range headers {
+			if j < len(row) {
+				metaData[header] = row[j]
+			}
+		}
+	}
+	return metaData
+}
+
+func (cp *CSVParser) Parse(ctx context.Context, reader io.Reader, opts ...parser.Option) ([]*schema.Document, error) {
+	option := parser.GetCommonOptions(&parser.Options{}, opts...)
+
+	csvFile := csv.NewReader(reader)
+
+	// get all rows
+	rows, err := csvFile.ReadAll()
+	if err != nil {
+		return nil, err
+	}
+	if len(rows) == 0 {
+		return nil, nil
+	}
+
+	var ret []*schema.Document
+
+	// Process the header
+	startIdx := 0
+	var headers []string
+	if !cp.Config.NoHeader && len(rows) > 0 {
+		headers = rows[0]
+		startIdx = 1
+	}
+
+	// Process rows of data
+	for i := startIdx; i < len(rows); i++ {
+		row := rows[i]
+		if len(row) == 0 {
+			continue
+		}
+		// Convert row data to strings
+		contentParts := make([]string, len(row))
+		for j, cell := range row {
+			contentParts[j] = strings.TrimSpace(cell)
+		}
+		content := strings.Join(contentParts, string(cp.Config.Comma))
+
+		meta := make(map[string]any)
+
+		// Build the row's Meta
+		rowMeta := cp.buildRowMetaData(row, headers)
+		meta[MetaDataRow] = rowMeta
+
+		// Get the Common ExtraMeta
+		if option.ExtraMeta != nil {
+			meta[MetaDataExt] = option.ExtraMeta
+		}
+
+		// Create New Document
+		nDoc := &schema.Document{
+			ID:       cp.generateID(i),
+			Content:  content,
+			MetaData: meta,
+		}
+
+		ret = append(ret, nDoc)
+	}
+
+	return ret, nil
+}

components/document/parser/csv/csv_parser_test.go

@@ -0,0 +1,38 @@
+package csv
+
+import (
+	"context"
+	"os"
+	"testing"
+
+	"github.com/cloudwego/eino/components/document/parser"
+)
+
+func TestCSVParser(t *testing.T) {
+	f, err := os.Open("./test.csv")
+	if err != nil {
+		t.Error(err)
+		return
+	}
+	defer f.Close()
+
+	ctx := context.Background()
+	cp, err := NewCSVParser(ctx, &Config{})
+	if err != nil {
+		t.Error(err)
+		return
+	}
+
+	docs, err := cp.Parse(ctx, f, parser.WithURI("local"), parser.WithExtraMeta(map[string]any{
+		"_extension": ".csv",
+		"_file_name": "test.csv",
+		"_source":    "local",
+	}))
+
+	if err != nil {
+		t.Error(err)
+		return
+	}
+	t.Log(docs)
+	return
+}

components/document/parser/csv/go.mod

@@ -0,0 +1,47 @@
+module github.com/cloudwego/eino-ext/components/document/parser/csv
+
+go 1.24.0
+
+toolchain go1.24.4
+
+require (
+	github.com/cloudwego/eino v0.5.13
+	golang.org/x/net v0.47.0
+)
+
+require (
+	github.com/bahlo/generic-list-go v0.2.0 // indirect
+	github.com/buger/jsonparser v1.1.1 // indirect
+	github.com/bytedance/gopkg v0.1.3 // indirect
+	github.com/bytedance/sonic v1.14.1 // indirect
+	github.com/bytedance/sonic/loader v0.3.0 // indirect
+	github.com/cloudwego/base64x v0.1.6 // indirect
+	github.com/dustin/go-humanize v1.0.1 // indirect
+	github.com/eino-contrib/jsonschema v1.0.2 // indirect
+	github.com/getkin/kin-openapi v0.118.0 // indirect
+	github.com/go-openapi/jsonpointer v0.19.5 // indirect
+	github.com/go-openapi/swag v0.19.5 // indirect
+	github.com/goph/emperror v0.17.2 // indirect
+	github.com/invopop/yaml v0.1.0 // indirect
+	github.com/josharian/intern v1.0.0 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.9 // indirect
+	github.com/mailru/easyjson v0.7.7 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 // indirect
+	github.com/nikolalohinski/gonja v1.5.3 // indirect
+	github.com/pelletier/go-toml/v2 v2.0.9 // indirect
+	github.com/perimeterx/marshmallow v1.1.4 // indirect
+	github.com/pkg/errors v0.9.1 // indirect
+	github.com/sirupsen/logrus v1.9.3 // indirect
+	github.com/slongfield/pyfmt v0.0.0-20220222012616-ea85ff4c361f // indirect
+	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
+	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
+	github.com/yargevad/filepathx v1.0.0 // indirect
+	golang.org/x/arch v0.11.0 // indirect
+	golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1 // indirect
+	golang.org/x/sys v0.38.0 // indirect
+	gopkg.in/yaml.v2 v2.4.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)