wip: unmarshall add uint handling

.gitignore

@@ -0,0 +1 @@
+/.idea/

.tool-versions

@@ -0,0 +1 @@
+golang 1.18

decode.go

@@ -0,0 +1,10 @@
+package gocsvparser
+
+type Decoder struct {
+}
+
+func NewDecoder() *Decoder {
+	decoder := new(Decoder)
+
+	return decoder
+}

default_record_handler.go

@@ -0,0 +1,182 @@
+package gocsvparser
+
+import (
+	"errors"
+	"fmt"
+	"reflect"
+	"strconv"
+	"strings"
+)
+
+type defaultRecordHandler struct {
+	fieldByTag       map[string]columnFieldBinding
+	outType          reflect.Type
+	columnNameMapped bool
+}
+
+type columnFieldBinding struct {
+	field reflect.StructField
+	index int
+}
+
+func newDefaultHandler() *defaultRecordHandler {
+	newHandler := new(defaultRecordHandler)
+	newHandler.fieldByTag = make(map[string]columnFieldBinding)
+	newHandler.columnNameMapped = false
+	return newHandler
+}
+
+func (d *defaultRecordHandler) HandleRecord(v any, record []string) error {
+	var (
+		err      error
+		strField string
+		index    int
+		ok       bool
+		binding  columnFieldBinding
+		val      reflect.Value
+	)
+
+	if d.outType == nil {
+		err = d.detType(v)
+		if err != nil {
+			return fmt.Errorf("error HandleRecord: detType: %+v", err)
+		}
+	}
+
+	if !d.columnNameMapped {
+		for index, strField = range record {
+			if binding, ok = d.fieldByTag[strField]; ok {
+				binding.index = index
+				d.fieldByTag[strField] = binding
+			}
+		}
+
+		d.columnNameMapped = true
+		return ErrHeaderRead
+	}
+
+	val = reflect.ValueOf(v)
+	if val.Kind() != reflect.Pointer {
+		return errors.New("error HandleRecord: v Kind() is not Pointer")
+	}
+
+	val = val.Elem()
+	switch val.Kind() {
+	case reflect.Struct:
+		for _, binding = range d.fieldByTag {
+			if binding.index < len(record) {
+				val, err = d.setValue(val, record[binding.index], binding.field)
+				if err != nil {
+					return fmt.Errorf("error HandleRecord: StructField SetValue: %+v", err)
+				}
+			}
+		}
+	case reflect.Map:
+		return errors.New("error HandleRecord: Map is not supported yet") //TODO: fix me
+	case reflect.Slice:
+		return errors.New("error HandleRecord: Slice is not supported yet") //TODO: fix me
+	}
+
+	return nil
+}
+
+func (d *defaultRecordHandler) setValue(val reflect.Value, strValue string, structFiled reflect.StructField) (reflect.Value, error) {
+	var (
+		fieldVal reflect.Value
+		f64      float64
+		i64      int64
+		u64      uint64
+		err      error
+		b        bool
+	)
+
+	fieldVal = val.FieldByIndex(structFiled.Index)
+	switch fieldVal.Type().Kind() {
+	case reflect.String:
+		fieldVal.SetString(strValue)
+	case reflect.Bool:
+		b, err = strconv.ParseBool(strValue)
+		if err != nil {
+			return reflect.Value{}, fmt.Errorf("ParseBool: %+v", err)
+		}
+		fieldVal.SetBool(b)
+	case reflect.Int64, reflect.Int32, reflect.Int16, reflect.Int8, reflect.Int:
+		i64, err = strconv.ParseInt(strValue, 0, 64)
+		if err != nil {
+			return reflect.Value{}, fmt.Errorf("ParseInt %s: %+v", strValue, err)
+		}
+
+		if fieldVal.OverflowInt(i64) {
+			return reflect.Value{}, fmt.Errorf("int value overflow: %s", strValue)
+		}
+
+		fieldVal.SetInt(i64)
+	case reflect.Uint64, reflect.Uint32, reflect.Uint16, reflect.Uint8, reflect.Uint:
+		u64, err = strconv.ParseUint(strValue, 0, 64)
+		if err != nil {
+			return reflect.Value{}, fmt.Errorf("ParseUint %s: %+v", strValue, err)
+		}
+
+		if fieldVal.OverflowUint(u64) {
+			return reflect.Value{}, fmt.Errorf("uint value overflow %s", strValue)
+		}
+
+		fieldVal.SetUint(u64)
+	case reflect.Float32, reflect.Float64:
+		f64, err = strconv.ParseFloat(strValue, 64)
+		if err != nil {
+			return reflect.Value{}, fmt.Errorf("ParseFloat %s: %+v", strValue, err)
+		}
+
+		if fieldVal.OverflowFloat(f64) {
+			return reflect.Value{}, fmt.Errorf("float value overflow %s", strValue)
+		}
+		fieldVal.SetFloat(f64)
+	default:
+		return reflect.Value{}, errors.New("missing implementation") //TODO: fix me
+	}
+
+	return val, nil
+}
+
+func (d *defaultRecordHandler) SetFieldConfigs(configs []FieldsConfig) {
+
+}
+
+func (d *defaultRecordHandler) detType(v any) error {
+	typ := reflect.TypeOf(v)
+	if typ.Kind() == reflect.Pointer {
+		typ = typ.Elem()
+
+		if typ.Kind() == reflect.Struct {
+			d.outType = typ
+			return d.mapStructTag()
+		} else if typ.Kind() == reflect.Map {
+			//TODO: implementation
+		} else if typ.Kind() == reflect.Slice {
+			//TODO: implementation
+		}
+	}
+	return fmt.Errorf("v should be pointer of Struct, Map, or Slice: %+v", typ)
+}
+
+func (d *defaultRecordHandler) mapStructTag() error {
+	//TODO: implementation
+	for _, field := range reflect.VisibleFields(d.outType) {
+		if csv, ok := field.Tag.Lookup(csvTag); ok {
+			s := strings.Split(csv, ",")
+			if len(s) == 0 {
+				return fmt.Errorf("invalid tag %+v", field.Tag)
+			}
+			if _, ok = d.fieldByTag[s[0]]; ok {
+				return fmt.Errorf("problem with the receiving struct, multiple field with tag %s", s[0])
+			}
+			d.fieldByTag[s[0]] = columnFieldBinding{
+				field: field,
+			}
+		} else if csvIndex, ok := field.Tag.Lookup(csvIndexTag); ok {
+			_ = csvIndex //TODO: process tag
+		}
+	}
+	return nil
+}

example/example_test.go

@@ -0,0 +1,38 @@
+package example
+
+import (
+	"testing"
+
+	"gitea.suyono.dev/suyono/gocsvparser"
+)
+
+type mtcarsFlat struct {
+	Model            string  `csv:"model"`
+	MilesPerGalon    float64 `csv:"mpg"`
+	Cylinder         int     `csv:"cyl"`
+	Displacement     float64 `csv:"disp"`
+	Horsepower       int     `csv:"hp"`
+	DriveShaftRatio  float64 `csv:"drat"`
+	Weight           float64 `csv:"wt"`
+	QuerterMileTime  float64 `csv:"qsec"`
+	VEngine          bool    `csv:"vs"`
+	AutoTransmission bool    `csv:"am"`
+	Gear             int     `csv:"gear"`
+	Carburetors      int     `csv:"carb"`
+}
+
+func TestMtcars(t *testing.T) {
+	var (
+		cars []mtcarsFlat
+		err  error
+	)
+
+	err = gocsvparser.Unmarshal(MtcarsCsv, &cars)
+	if err != nil {
+		t.Fatalf("unexpected error %+v", err)
+	}
+
+	for _, c := range cars {
+		t.Logf("%+v", c)
+	}
+}

example/mtcars.go

@@ -0,0 +1,37 @@
+package example
+
+var (
+	MtcarsCsv = []byte(`model,mpg,cyl,disp,hp,drat,wt,qsec,vs,am,gear,carb
+Mazda RX4,21,6,160,110,3.9,2.62,16.46,0,1,4,4
+Mazda RX4 Wag,21,6,160,110,3.9,2.875,17.02,0,1,4,4
+Datsun 710,22.8,4,108,93,3.85,2.32,18.61,1,1,4,1
+Hornet 4 Drive,21.4,6,258,110,3.08,3.215,19.44,1,0,3,1
+Hornet Sportabout,18.7,8,360,175,3.15,3.44,17.02,0,0,3,2
+Valiant,18.1,6,225,105,2.76,3.46,20.22,1,0,3,1
+Duster 360,14.3,8,360,245,3.21,3.57,15.84,0,0,3,4
+Merc 240D,24.4,4,146.7,62,3.69,3.19,20,1,0,4,2
+Merc 230,22.8,4,140.8,95,3.92,3.15,22.9,1,0,4,2
+Merc 280,19.2,6,167.6,123,3.92,3.44,18.3,1,0,4,4
+Merc 280C,17.8,6,167.6,123,3.92,3.44,18.9,1,0,4,4
+Merc 450SE,16.4,8,275.8,180,3.07,4.07,17.4,0,0,3,3
+Merc 450SL,17.3,8,275.8,180,3.07,3.73,17.6,0,0,3,3
+Merc 450SLC,15.2,8,275.8,180,3.07,3.78,18,0,0,3,3
+Cadillac Fleetwood,10.4,8,472,205,2.93,5.25,17.98,0,0,3,4
+Lincoln Continental,10.4,8,460,215,3,5.424,17.82,0,0,3,4
+Chrysler Imperial,14.7,8,440,230,3.23,5.345,17.42,0,0,3,4
+Fiat 128,32.4,4,78.7,66,4.08,2.2,19.47,1,1,4,1
+Honda Civic,30.4,4,75.7,52,4.93,1.615,18.52,1,1,4,2
+Toyota Corolla,33.9,4,71.1,65,4.22,1.835,19.9,1,1,4,1
+Toyota Corona,21.5,4,120.1,97,3.7,2.465,20.01,1,0,3,1
+Dodge Challenger,15.5,8,318,150,2.76,3.52,16.87,0,0,3,2
+AMC Javelin,15.2,8,304,150,3.15,3.435,17.3,0,0,3,2
+Camaro Z28,13.3,8,350,245,3.73,3.84,15.41,0,0,3,4
+Pontiac Firebird,19.2,8,400,175,3.08,3.845,17.05,0,0,3,2
+Fiat X1-9,27.3,4,79,66,4.08,1.935,18.9,1,1,4,1
+Porsche 914-2,26,4,120.3,91,4.43,2.14,16.7,0,1,5,2
+Lotus Europa,30.4,4,95.1,113,3.77,1.513,16.9,1,1,5,2
+Ford Pantera L,15.8,8,351,264,4.22,3.17,14.5,0,1,5,4
+Ferrari Dino,19.7,6,145,175,3.62,2.77,15.5,0,1,5,6
+Maserati Bora,15,8,301,335,3.54,3.57,14.6,0,1,5,8
+Volvo 142E,21.4,4,121,109,4.11,2.78,18.6,1,1,4,2`)
+)

ext_test.go

@@ -0,0 +1,25 @@
+package gocsvparser_test
+
+import (
+	"testing"
+
+	"gitea.suyono.dev/suyono/gocsvparser"
+)
+
+type testDirect struct {
+}
+
+func (t *testDirect) SetFieldConfigs(configs []gocsvparser.FieldsConfig) {
+
+}
+
+func (t *testDirect) HandleRecord(v any, records []string) error {
+	return nil
+}
+
+func TestExt(t *testing.T) {
+	// _, err := gocsvparser.NewUnmarshaler().WithRecordHandler(new(testDirect))
+	// if err != nil {
+	// 	t.Fatalf("unexpected error %v", err)
+	// }
+}

go.mod

@@ -0,0 +1,3 @@
+module gitea.suyono.dev/suyono/gocsvparser
+
+go 1.18

gocsvparser.go

@@ -0,0 +1,6 @@
+package gocsvparser
+
+const (
+	csvTag      string = "csv"
+	csvIndexTag string = "csv.index"
+)

marshal.go

@@ -0,0 +1 @@
+package gocsvparser

options.go

@@ -0,0 +1,178 @@
+package gocsvparser
+
+import (
+	"encoding/csv"
+	"errors"
+	"fmt"
+)
+
+type csvOptionsType int
+
+type CsvOption interface {
+	getType() csvOptionsType
+}
+
+const (
+	comma csvOptionsType = iota
+	comment
+	fieldsPerRecord
+	lazyQuotes
+	trimLeadingSpace
+	reuseRecord
+	useCrlf
+	columnHeader
+	recordHandler
+	csvReader
+)
+
+type csvReaderOption struct {
+	reader *csv.Reader
+}
+
+func CsvReader(reader *csv.Reader) csvReaderOption {
+	return csvReaderOption{
+		reader: reader,
+	}
+}
+
+func (csvReaderOption) getType() csvOptionsType {
+	return csvReader
+}
+
+type recordHandlerOption struct {
+	handlerType         recordHandlerType
+	recordHandler       RecordHandler
+	recordFieldsHandler RecordFieldsHandler
+}
+
+func RecordHandlerOption(handler any) (*recordHandlerOption, error) {
+	var rho *recordHandlerOption
+	if d, ok := handler.(RecordHandler); ok {
+		if d == nil {
+			return nil, errors.New("handler value is nil")
+		}
+
+		rho = &recordHandlerOption{
+			handlerType:   direct,
+			recordHandler: d,
+		}
+	} else if s, ok := handler.(RecordFieldsHandler); ok {
+		if s == nil {
+			return nil, errors.New("handler value is nil")
+		}
+
+		rho = &recordHandlerOption{
+			handlerType:         fieldsSpecific,
+			recordFieldsHandler: s,
+		}
+	} else {
+		return nil, fmt.Errorf("invalid handler type %T", handler)
+	}
+
+	return rho, nil
+}
+
+func (r *recordHandlerOption) getType() csvOptionsType {
+	return recordHandler
+}
+
+type columnHeaderOption struct {
+	header []string
+}
+
+func ColumnHeader(header ...string) columnHeaderOption {
+	columnHeader := columnHeaderOption{}
+	if len(header) > 0 {
+		columnHeader.header = make([]string, len(header))
+		copy(columnHeader.header, header)
+	}
+	return columnHeader
+}
+
+func (c columnHeaderOption) getType() csvOptionsType {
+	return columnHeader
+}
+
+type commaOption struct {
+	comma rune
+}
+
+func CommaOption(comma rune) commaOption {
+	return commaOption{
+		comma: comma,
+	}
+}
+
+func (c commaOption) getType() csvOptionsType {
+	return comma
+}
+
+type commentOption struct {
+	comment rune
+}
+
+func CommentOption(comment rune) commentOption {
+	return commentOption{
+		comment: comment,
+	}
+}
+
+func (c commentOption) getType() csvOptionsType {
+	return comment
+}
+
+type fieldsPerRecordOption struct {
+	fieldsPerRecord int
+}
+
+func FieldPerRecordOption(i int) fieldsPerRecordOption {
+	return fieldsPerRecordOption{
+		fieldsPerRecord: i,
+	}
+}
+
+func (f fieldsPerRecordOption) getType() csvOptionsType {
+	return fieldsPerRecord
+}
+
+type lazyQuotesOption struct {
+	lazyQuotes bool
+}
+
+func LazyQuotesOption(b bool) lazyQuotesOption {
+	return lazyQuotesOption{
+		lazyQuotes: b,
+	}
+}
+
+func (l lazyQuotesOption) getType() csvOptionsType {
+	return lazyQuotes
+}
+
+type trimLeadingSpaceOption struct {
+	trimLeadingSpace bool
+}
+
+func TrimLeadingSpaceOption(b bool) trimLeadingSpaceOption {
+	return trimLeadingSpaceOption{
+		trimLeadingSpace: b,
+	}
+}
+
+func (t trimLeadingSpaceOption) getType() csvOptionsType {
+	return trimLeadingSpace
+}
+
+type reuseRecordOption struct {
+	reuseRecord bool
+}
+
+func ReuseRecordOption(b bool) reuseRecordOption {
+	return reuseRecordOption{
+		reuseRecord: b,
+	}
+}
+
+func (r reuseRecordOption) getType() csvOptionsType {
+	return reuseRecord
+}

unmarshal.go

@@ -0,0 +1,218 @@
+package gocsvparser
+
+import (
+	"bytes"
+	"encoding/csv"
+	"errors"
+	"fmt"
+	"io"
+	"reflect"
+)
+
+var (
+	ErrHeaderRead = errors.New("column headers successfully read")
+)
+
+type FieldsConfig struct {
+	Name string
+	Num  int
+}
+
+type FieldsHandlerByName interface {
+	FieldName() string
+	FieldByName(name, field string) error
+	FieldsHandler
+}
+
+type FieldsHandlerByIndices interface {
+	FieldsIndices() []int
+	FieldByIndex(index int, field string) error
+	FieldsHandler
+}
+
+type FieldsHandler interface {
+	Fields(fields ...string) error
+	NumFields() int
+}
+
+type RecordFieldsHandler interface {
+	FieldsHandlers() []FieldsHandler
+	Out(v any) error
+}
+
+type RecordHandler interface {
+	// SetFieldConfigs is only effective if a Map is passed to HandleRecord
+	SetFieldConfigs(configs []FieldsConfig)
+	HandleRecord(v any, record []string) error
+}
+
+type recordHandlerType int
+
+const (
+	direct         recordHandlerType = 1
+	fieldsSpecific recordHandlerType = 2
+)
+
+type Unmarshaler struct {
+	options            []CsvOption
+	header             []string
+	recordHandler      RecordHandler
+	recordFieldHandler RecordFieldsHandler
+	handlerType        recordHandlerType
+	csvReader          *csv.Reader
+}
+
+func NewUnmarshaler(options ...CsvOption) *Unmarshaler {
+	unmarshaler := &Unmarshaler{
+		handlerType: direct,
+		options:     []CsvOption{nil},
+	}
+
+	if len(options) > 0 {
+		unmarshaler.options = append(unmarshaler.options, options...)
+	}
+
+	return unmarshaler
+}
+
+func (u *Unmarshaler) processOptions(options ...CsvOption) {
+	for _, option := range options {
+		if option == nil {
+			continue
+		}
+
+		switch option.getType() {
+		case csvReader:
+			if u.csvReader != nil {
+				continue
+			}
+			o := option.(csvReaderOption)
+			u.csvReader = o.reader
+		case comma:
+			o := option.(commaOption)
+			u.csvReader.Comma = o.comma
+		case comment:
+			o := option.(commentOption)
+			u.csvReader.Comment = o.comment
+		case fieldsPerRecord:
+			o := option.(fieldsPerRecordOption)
+			u.csvReader.FieldsPerRecord = o.fieldsPerRecord
+		case lazyQuotes:
+			o := option.(lazyQuotesOption)
+			u.csvReader.LazyQuotes = o.lazyQuotes
+		case trimLeadingSpace:
+			o := option.(trimLeadingSpaceOption)
+			u.csvReader.TrimLeadingSpace = o.trimLeadingSpace
+		case reuseRecord:
+			o := option.(reuseRecordOption)
+			u.csvReader.ReuseRecord = o.reuseRecord
+		case columnHeader:
+			headerOption := option.(columnHeaderOption)
+			u.header = headerOption.header
+		case recordHandler:
+			rho := option.(*recordHandlerOption)
+			u.handlerType = rho.handlerType
+			switch rho.handlerType {
+			case direct:
+				u.recordHandler = rho.recordHandler
+			case fieldsSpecific:
+				u.recordFieldHandler = rho.recordFieldsHandler
+			}
+		}
+	}
+}
+
+func (u *Unmarshaler) Unmarshal(data []byte, v any, options ...CsvOption) error {
+	var (
+		typ        reflect.Type
+		val, slice reflect.Value
+		record     []string
+		err        error
+	)
+
+	if len(options) > 0 {
+		u.options = append(u.options, options...)
+	}
+
+	u.options[0] = CsvReader(csv.NewReader(bytes.NewReader(data)))
+	u.processOptions(u.options...)
+
+	if u.handlerType == direct {
+		if u.recordHandler == nil {
+			u.recordHandler = newDefaultHandler()
+		}
+
+		slice, typ, err = u.detOutputType(v)
+		if err != nil {
+			return fmt.Errorf("error Unmarshal: detOutputType: %+v", err)
+		}
+
+		for {
+			record, err = u.csvReader.Read()
+			if err != nil {
+				if err == io.EOF {
+					break
+				}
+				return fmt.Errorf("error Unmarshal: csv.Reader.Read: %+v", err)
+			}
+
+			val, err = u.newElem(typ)
+			if err != nil {
+				return fmt.Errorf("error Unmarshal: newElem: %+v", err)
+			}
+
+			err = u.recordHandler.HandleRecord(val.Interface(), record)
+			if err != nil {
+				if err == ErrHeaderRead {
+					continue
+				}
+				return fmt.Errorf("error Unmarshal: RecordHandler.HandleRecord: %+v", err)
+			}
+
+			slice.Set(reflect.Append(slice, val.Elem()))
+		}
+	} else {
+		//TODO: implementation
+	}
+
+	return nil
+}
+
+func (u *Unmarshaler) detOutputType(v any) (reflect.Value, reflect.Type, error) {
+	var typ reflect.Type
+
+	if v == nil {
+		return reflect.Value{}, nil, errors.New("the output parameter is nil")
+	}
+
+	val := reflect.ValueOf(v)
+	if val.Kind() != reflect.Pointer {
+		return reflect.Value{}, nil, errors.New("invalid output parameter type")
+	}
+
+	val = val.Elem()
+	if val.Kind() != reflect.Slice {
+		return reflect.Value{}, nil, errors.New("invalid output parameter type")
+	}
+
+	typ = val.Type().Elem()
+
+	return val, typ, nil
+}
+
+func Unmarshal(data []byte, v any, options ...CsvOption) error {
+	return NewUnmarshaler().Unmarshal(data, v, options...)
+}
+
+func (u *Unmarshaler) newElem(typ reflect.Type) (reflect.Value, error) {
+	switch typ.Kind() {
+	case reflect.Struct:
+		return reflect.New(typ), nil
+	case reflect.Map:
+		//TODO: implementation
+	case reflect.Slice:
+		//TODO: implementation
+	}
+
+	return reflect.Zero(typ), errors.New("invalid implementation") //TODO: placeholder; update me
+}

unmarshal_test.go

@@ -0,0 +1,73 @@
+package gocsvparser
+
+import (
+	"reflect"
+	"testing"
+)
+
+type Coba struct {
+	Name    string `csv:"name"`
+	Address string `csv:"address,omitempty"`
+	Mile    int64  `csv:"mile"`
+	anon
+}
+
+type anon struct {
+	FieldX  int64 `csv:"x"`
+	OutputY int64 `csv:"y"`
+}
+
+func TestParse(t *testing.T) {
+	newDefaultHandler().detType(&Coba{})
+}
+
+func TestRead(t *testing.T) {
+	var coba []Coba
+
+	Read(&coba, t)
+
+	t.Logf("outside %+v", coba)
+
+	// type args struct {
+	// 	i interface{}
+	// }
+	// tests := []struct {
+	// 	name string
+	// 	args args
+	// }{
+	// 	// TODO: Add test cases.
+	// }
+	// for _, tt := range tests {
+	// 	t.Run(tt.name, func(t *testing.T) {
+	// 		Read(tt.args.i)
+	// 	})
+	// }
+}
+
+func Read(i interface{}, t *testing.T) {
+	var val reflect.Value
+
+	val = reflect.ValueOf(i)
+	if val.Kind() == reflect.Pointer {
+		val = val.Elem()
+
+		if val.Kind() == reflect.Slice {
+			vslice := val
+			typ := val.Type().Elem()
+
+			if typ.Kind() == reflect.Struct {
+				for _, x := range reflect.VisibleFields(typ) {
+					t.Logf("test: %+v", x)
+				}
+
+				nv := reflect.New(typ).Elem()
+				nv.FieldByName("Name").SetString("hello")
+				nv.FieldByName("Mile").SetInt(72)
+				// vslice = reflect.Append(vslice, nv)
+				vslice.Set(reflect.Append(vslice, nv))
+
+				t.Logf("inside: %+v", vslice)
+			}
+		}
+	}
+}