Golang encoding-csv.Reader类(方法)实例源码

func (mfr *MicrophoneFileReader) LoadMicrophones(reader *csv.Reader) (bool, error) {
	records, err := reader.ReadAll()

	if err != nil {
		fmt.Println(err)
		return false, err
	}

	for i := 0; i < len(records); i++ {
		price, err := strconv.ParseFloat(records[i][3], 64)

		if err != nil {
			return false, errors.New("Not able to parse price to float")
		}

		mic := Microphone{
			name:        records[i][0],
			brand:       records[i][1],
			description: records[i][2],
			price:       price,
			url:         records[i][4],
			micType:     records[i][5],
			micStyle:    records[i][6],
		}
		mfr.microphoneList = append(mfr.microphoneList, mic)
	}

	return true, nil
}

// Read takes a CSV reader and reads it into a typed List of structs. Each row gets read into a struct named structName, described by headers. If the original data contained headers it is expected that the input reader has already read those and are pointing at the first data row.
// If kinds is non-empty, it will be used to type the fields in the generated structs; otherwise, they will be left as string-fields.
// In addition to the list, Read returns the typeRef for the structs in the list, and last the typeDef of the structs.
func Read(r *csv.Reader, structName string, headers []string, kinds KindSlice, vrw types.ValueReadWriter) (l types.List, typeRef, typeDef types.Type) {
	typeRef, typeDef = MakeStructTypeFromHeaders(headers, structName, kinds)
	valueChan := make(chan types.Value, 128) // TODO: Make this a function param?
	listType := types.MakeCompoundType(types.ListKind, typeRef)
	listChan := types.NewStreamingTypedList(listType, vrw, valueChan)

	structFields := typeDef.Desc.(types.StructDesc).Fields

	for {
		row, err := r.Read()
		if err == io.EOF {
			close(valueChan)
			break
		} else if err != nil {
			panic(err)
		}

		fields := make(map[string]types.Value)
		for i, v := range row {
			if i < len(headers) {
				f := structFields[i]
				fields[f.Name] = StringToType(v, f.T.Kind())
			}
		}
		valueChan <- types.NewStruct(typeRef, typeDef, fields)
	}

	return <-listChan, typeRef, typeDef
}

// streamCsv
//  Streams a CSV Reader into a returned channel.  Each CSV row is streamed along with the header.
//  "true" is sent to the `done` channel when the file is finished.
//
// Args
//  csv    - The csv.Reader that will be read from.
//  buffer - The "lines" buffer factor.  Send "0" for an unbuffered channel.
func streamCsv(csv *csv.Reader, buffer int) (lines chan *CsvLine) {
	lines = make(chan *CsvLine, buffer)

	go func() {
		// get Header
		header, err := csv.Read()
		if err != nil {
			close(lines)
			return
		}

		i := 0

		for {
			line, err := csv.Read()

			if len(line) > 0 {
				i++
				lines <- &CsvLine{Header: header, Line: line}
			}

			if err != nil {
				fmt.Printf("Sent %d lines\n", i)
				close(lines)
				return
			}
		}
	}()

	return
}

// Reads the census CSV data from files
func unmarshalCensusData(reader *csv.Reader, v interface{}) error {
	record, err := reader.Read()
	if err != nil {
		return err
	}
	s := reflect.ValueOf(v).Elem()
	if s.NumField() != len(record) {
		return &csvFieldMismatch{s.NumField(), len(record)}
	}
	for i := 0; i < s.NumField(); i++ {
		f := s.Field(i)
		switch f.Type().String() {
		case "string":
			f.SetString(record[i])
		case "int":
			ival, err := strconv.ParseInt(record[i], 10, 0)
			if err != nil {
				return err
			}
			f.SetInt(ival)
		case "float64":
			fval, err := strconv.ParseFloat(record[i], 64)
			if err != nil {
				return err
			}
			f.SetFloat(fval)
		default:
			return &csvUnsupportedType{f.Type().String()}
		}
	}
	return nil
}

// Get is to get OTC csv data.
func (o *OTCLists) Get(category string) ([][]string, error) {
	var (
		csvArrayContent []string
		csvReader       *csv.Reader
		data            []byte
		err             error
		rawData         [][]string
		url             string
	)

	url = fmt.Sprintf("%s%s", utils.OTCHOST, fmt.Sprintf(utils.OTCLISTCSV, fmt.Sprintf("%d/%02d/%02d", o.Date.Year()-1911, o.Date.Month(), o.Date.Day()), category))

	if data, err = hCache.Get(url, false); err == nil {
		csvArrayContent = strings.Split(string(data), "\n")
		if len(csvArrayContent) > 5 {
			csvReader = csv.NewReader(strings.NewReader(strings.Join(csvArrayContent[4:len(csvArrayContent)-1], "\n")))
			if rawData, err = csvReader.ReadAll(); err == nil {
				o.categoryRawData[category] = rawData
				o.formatData(category)
				return rawData, nil
			}
		}
	}
	return nil, err
}

// Get return csv data in array.
func (d *Data) Get() ([][]string, error) {
	if len(d.UnixMapData[d.Date.Unix()]) == 0 {
		data, err := hCache.Get(d.URL(), true)
		if err != nil {
			return nil, fmt.Errorf(errorNetworkFail.Error(), err)
		}
		csvArrayContent := strings.Split(string(data), "\n")
		for i := range csvArrayContent {
			csvArrayContent[i] = strings.TrimSpace(csvArrayContent[i])
		}
		var csvReader *csv.Reader
		if (d.exchange == "tse" && len(csvArrayContent) > 2) || (d.exchange == "otc" && len(csvArrayContent) > 5) {
			if d.exchange == "tse" {
				if d.Name == "" {
					d.Name = strings.Split(csvArrayContent[0], " ")[2]
				}
				csvReader = csv.NewReader(strings.NewReader(strings.Join(csvArrayContent[2:], "\n")))
			} else if d.exchange == "otc" {
				if d.Name == "" {
					d.Name = strings.Split(csvArrayContent[2], ":")[1]
				}
				csvReader = csv.NewReader(strings.NewReader(strings.Join(csvArrayContent[5:len(csvArrayContent)-1], "\n")))
			}
			allData, err := csvReader.ReadAll()
			d.RawData = append(allData, d.RawData...)
			d.UnixMapData[d.Date.Unix()] = allData
			d.clearCache()
			return allData, err
		}
		return nil, errorNotEnoughData
	}
	return d.UnixMapData[d.Date.Unix()], nil
}

func RecsFromCSVReader(r *csv.Reader, recs map[string][]RepoRelation) error {
	for {
		record, err := r.Read()
		if err == io.EOF {
			break
		}
		if err != nil {
			return fmt.Errorf("failed to read csv record: %v", err)
		}
		if len(record[0]) < prefixLen {
			log.Printf("not valid rec record %v", record)
			continue
		}
		sp1 := ShortPathFromURL(record[0])
		sp2 := ShortPathFromURL(record[1])
		c, err := strconv.ParseFloat(record[2], 64)
		if err != nil {
			log.Printf("Failed to ParseFloat(%q, 64): %v", record[2], err)
		}
		recs[sp1] = append(recs[sp1], RepoRelation{sp2, c})
	}
	for k, _ := range recs {
		sort.Sort(ByScore(recs[k]))
	}
	log.Printf("%v recs has been loaded", len(recs))
	return nil
}

func (t *table) start(reader *csv.Reader) {
	defer t.Stop()
	defer close(t.rows)

	headers, err := reader.Read()
	if err != nil {
		if perr, ok := err.(*csv.ParseError); ok {
			// Modifies the underlying err
			perr.Err = fmt.Errorf("%s. %s", perr.Err, "This can happen when the CSV is malformed, or when the wrong delimiter is used")
		}
		t.handleErr(err)
		return
	}

	reader.FieldsPerRecord = len(headers)
	for {
		if t.stopped {
			break
		}
		line, err := reader.Read()
		if err != nil {
			t.handleErr(err)
			return
		}
		t.rows <- convertLineToRow(line, headers)
	}
}

// Read takes a CSV reader and reads it into a typed List of structs. Each row gets read into a struct named structName, described by headers. If the original data contained headers it is expected that the input reader has already read those and are pointing at the first data row.
// If kinds is non-empty, it will be used to type the fields in the generated structs; otherwise, they will be left as string-fields.
// In addition to the list, Read returns the typeRef for the structs in the list, and last the typeDef of the structs.
func ReadToList(r *csv.Reader, structName string, headers []string, kinds KindSlice, vrw types.ValueReadWriter) (l types.List, t *types.Type) {
	t, fieldOrder, kindMap := MakeStructTypeFromHeaders(headers, structName, kinds)
	valueChan := make(chan types.Value, 128) // TODO: Make this a function param?
	listChan := types.NewStreamingList(vrw, valueChan)

	for {
		row, err := r.Read()
		if err == io.EOF {
			close(valueChan)
			break
		} else if err != nil {
			panic(err)
		}

		fields := make(types.ValueSlice, len(headers))
		for i, v := range row {
			if i < len(headers) {
				fieldOrigIndex := fieldOrder[i]
				val, err := StringToValue(v, kindMap[fieldOrigIndex])
				if err != nil {
					d.Chk.Fail(fmt.Sprintf("Error parsing value for column '%s': %s", headers[i], err))
				}
				fields[fieldOrigIndex] = val
			}
		}
		valueChan <- types.NewStructWithType(t, fields)
	}

	return <-listChan, t
}

func read_record(csv_reader *csv.Reader) (loadedRecord, error) {
	row, err := csv_reader.Read()
	if err != nil {
		return loadedRecord{}, err
	}
	if err != nil {
		panic(err)
	}
	var id, key string
	if len(row) == 2 {
		id, key = row[0], row[1]
	} else {
		key = row[0]
	}

	numeric, _ := regexp.Compile("[0-9]")
	new_key := numeric.ReplaceAllString(key, "")
	new_key = strings.ToLower(new_key)

	record := loadedRecord{
		id:           id,
		key:          new_key,
		original_key: key,
		length:       len(new_key) - 2,
	}
	record.trigrams = create_trigram(new_key, record.length)

	return record, nil
}

//LoadCases will load data stored case by case from a cvs reader into a
//feature matrix that has allready been filled with the coresponding empty
//features. It is a lower level method generally called after inital setup to parse
//a fm, arff, csv etc.
func (fm *FeatureMatrix) LoadCases(data *csv.Reader, rowlabels bool) {
	count := 0
	for {
		record, err := data.Read()
		if err == io.EOF {
			break
		} else if err != nil {
			log.Print("Error:", err)
			break
		}

		caselabel := fmt.Sprintf("%v", count)
		if rowlabels {
			caselabel = record[0]
			record = record[1:]
		}
		fm.CaseLabels = append(fm.CaseLabels, caselabel)

		for i, v := range record {
			fm.Data[i].Append(v)
		}

		count++
	}

}

// Parse columns from first header row or from flags
func parseColumns(reader *csv.Reader, skipHeader bool, fields string) ([]string, error) {
	var err error
	var columns []string
	if fields != "" {
		columns = strings.Split(fields, ",")

		if skipHeader {
			reader.Read() //Force consume one row
		}
	} else {
		columns, err = reader.Read()
		if err != nil {
			return nil, err
		}
	}

	for _, col := range columns {
		if containsDelimiter(col) {
			return columns, errors.New("Please specify the correct delimiter with -d.\nHeader column contains a delimiter character: " + col)
		}
	}

	for i, col := range columns {
		columns[i] = postgresify(col)
	}

	return columns, nil
}

func processFile(reader *csv.Reader, keyIndex, valueIndex int, headerRow bool) ([]MapEntry, error) {
	entries := []MapEntry{}
	for i := 0; true; i++ {
		row, err := reader.Read()
		if err == io.EOF {
			break
		}

		if err != nil {
			return nil, err
		}

		if headerRow && i == 0 {
			continue
		}

		numFields := len(row)
		if keyIndex > numFields {
			return nil, fmt.Errorf("key index '%d' > number of fields '%d'", keyIndex, numFields)
		}
		if valueIndex > numFields {
			return nil, fmt.Errorf("value index '%d' > number of fields '%d'", valueIndex, numFields)
		}

		key := row[keyIndex-1]
		value := row[valueIndex-1]
		entries = append(entries, MapEntry{key, value})
	}
	return entries, nil
}

//Read read csv for handle
func ReadLines(file string, isGbk bool) (lines [][]string, err error) {
	//catch panic
	defer func() {
		if rerr := recover(); rerr != nil {
			err = errors.New(fmt.Sprintf("read csv file: %v, error: %v", file, rerr))
		}
	}()

	//open file
	fi, err := os.Open(file)
	if err != nil {
		return nil, err
	}
	defer fi.Close()
	//get reader
	var reader *csv.Reader
	if !isGbk {
		reader = csv.NewReader(fi)
	} else {
		//transform gbk to utf8
		r := transform.NewReader(fi, simplifiedchinese.GBK.NewDecoder())
		reader = csv.NewReader(r)
	}
	lines, err = reader.ReadAll()
	return
}

// User CSV
// Fields are stored in the sequence as they appear in the struct, with arrays
// being represented as semicolon separated lists.
// Create a new user read from a CSV reader
func NewUserFromCSV(reader *csv.Reader) (user *User, done bool) {
	line, err := reader.Read()
	if err != nil {
		return nil, true
	}
	if len(line) != 7 {
		return nil, false
	}
	// comment
	firstElement := strings.TrimSpace(line[0])
	if len(firstElement) > 0 && firstElement[0] == '#' {
		return nil, false
	}
	level := line[2]
	ValidFrom, _ := time.Parse("2006-01-02 15:04", line[4])
	ValidTo, _ := time.Parse("2006-01-02 15:04", line[5])
	if !isValidLevel(level) {
		log.Printf("Got invalid level '%s'", level)
		return nil, false
	}
	return &User{
			Name:        line[0],
			ContactInfo: line[1],
			UserLevel:   Level(level),
			Sponsors:    strings.Split(line[3], ";"),
			ValidFrom:   ValidFrom, // field 4
			ValidTo:     ValidTo,   // field 5
			Codes:       strings.Split(line[6], ";")},
		false
}

func (d *Data) readFeatures(in csv.Reader) {
	for {
		record, err := in.Read()

		if err == io.EOF {
			break
		}

		if err != nil {
			fmt.Println("ERROR: ", err)
		}

		x := len(record)
		conv := make([]float64, x, x)
		correctData := true

		for i := 0; i < x; i++ {
			conv[i], err = strconv.ParseFloat(record[i], 64)
			if err != nil {
				fmt.Println("ERROR: ", err)
				correctData = false
			}
		}
		if correctData {
			d.AppendRow(conv)
		}
	}
}

func (d *Data) readHeader(r csv.Reader) {
	record, err := r.Read()

	if err != nil {
		fmt.Println("ERROR: ", err)
	}

	d.setFeatures(record)
}

func readOneRecordAtaTime(reader *csv.Reader) {

	for {
		row, err := reader.Read()
		if err != nil {
			break
		}
		printRow(row)
	}
}

func readAllRecord(reader *csv.Reader) {

	recs, err := reader.ReadAll()
	if err != nil {
		log.Fatal(err)
	}

	for _, row := range recs {
		printRow(row)
	}

}

func read(r *csv.Reader, f func(record []string)) {
	for {
		record, err := r.Read()
		if err == io.EOF {
			break
		} else if err != nil && err != io.EOF {
			log.Fatal("Error reading defects file ", err)
		}
		if record[1] != "Id" {
			f(record)
		}
	}
}