binary.read 返回"unexpected EOF"无论我使用什么 dBase (.dbf) 文件

Question

func main() {
        file, err := os.Open("example.dbf") // For read access.
        if err != nil {
            log.Fatal(err)
        }
        dBaseioReader, err := NewReader(file)
        if err != nil {
            log.Fatal(err)
        }
        return nil
}
type dbHeader struct {
    Version             byte
    LastUpdate          [3]byte
    NumRecords          int32
    NumBytesInHeader    int16
    NumBytesInRecord    int16
    _                   [2]byte //reserved
    IncompatFlag        byte
    EncryptionFlag      byte
    MultiUserProcessing [12]byte
    MDXProductionFlag   byte
    LangDriverId        byte
    _                   [2]byte //reserved
    LangDriverName      [32]byte
    _                   [4]byte //reserved
}

type dbFieldDescriptor struct {
    FieldName         [32]byte
    FieldType         byte
    FieldLen          byte
    FieldDec          byte
    _                 [2]byte
    MDXProductionFlag byte
    _                 [2]byte
    NextAutoIncrement [4]byte
    _                 [4]byte
}

type DBaseReader struct {
    rawInput *bufio.Reader
    Header   *dbHeader
    Fields   []*dbFieldDescriptor
    recordsLeft int
}
func NewReader(input io.Reader) (dbr *DBaseReader, err error) {
    dbr = &DBaseReader{
        rawInput: bufio.NewReaderSize(input, 32*1024),
        Header:   &dbHeader{},
    }
    err = binary.Read(dbr.rawInput, binary.LittleEndian, dbr.Header)
    if err != nil{
        return
    }
    dbr.recordsLeft = int(dbr.Header.NumRecords)
    headerBytesLeft := dbr.Header.NumBytesInHeader
    headerBytesLeft -= dbHeaderSize
    // read field descriptors until 0x0D termination byte
    var term []byte
    for {
        field := &dbFieldDescriptor{}
        err = binary.Read(dbr.rawInput, binary.LittleEndian, field)
        if err != nil{
            //FIRST CRASH HAPPENS HERE.
            return
        }
        dbr.Fields = append(dbr.Fields, field)
        headerBytesLeft -= dbFieldDescriptorSize
        // check for terminator byte
        term, err = dbr.rawInput.Peek(1)
        if err != nil{
            return
        }
        if term[0] == 0x0D {
            break
        }
    }
    // read the terminator
    _, err = dbr.rawInput.ReadByte()
    if err != nil {
        return
    }
    headerBytesLeft -= 1
    if headerBytesLeft > 0 {
        err = fmt.Errorf("Error: Header Bytes Left: %d.. Read Properties?!..n", headerBytesLeft)
        return
        // headerLeftOver := make([]byte, headerBytesLeft)
        // err = binary.Read(dbr.rawInput, binary.LittleEndian, headerLeftOver)
        // if err != nil {
        //  return
        // }
        // props := &dbFieldProperties{}
        // err = binary.Read(dbr.rawInput, binary.LittleEndian, props)
        // if err != nil {
        //  return
        // }
        // fmt.Printf("Props: %#vn", props)
    }
    // read until first record marker
    _, err = dbr.rawInput.ReadBytes(' ')
    if err != nil {
        return
    }
    return dbr, nil
}

以上是相关代码。无论我使用什么示例dbf文件，程序都会崩溃。我不知道为什么我一直得到"意外的EOF"错误。在过去的几天里，我一直在试图弄清楚这个问题，但不幸的是没有运气。

Answer 1

您没有提供证据证明您的文件格式是正确的。在编写程序之前，您应该确认文件的格式是否正确。

文件的前256个字节是多少?例如,

hex.go:

package main
import (
    "encoding/hex"
    "fmt"
    "io/ioutil"
    "os"
    "strconv"
)
func main() {
    if len(os.Args) <= 1 {
        fmt.Fprintln(os.Stderr, "usage: hex filename [bytes]")
        return
    }
    data, err := ioutil.ReadFile(os.Args[1])
    if err != nil {
        fmt.Fprintln(os.Stderr, "filename:", err)
        return
    }
    n := len(data)
    if len(os.Args) > 2 {
        i, err := strconv.Atoi(os.Args[2])
        if err != nil {
            fmt.Fprintln(os.Stderr, "bytes:", err)
            return
        }
        if n > i {
            n = i
        }
    }
    fmt.Print(hex.Dump(data[:n]))
}

输出:

$ go run hex.go example.dbf 256
00000000  03 01 04 18 01 00 00 00  41 07 d0 05 00 00 00 00  |........A.......|
00000010  00 00 00 00 00 00 00 00  00 00 00 00 00 03 00 00  |................|
00000020  54 52 41 43 4b 5f 49 44  00 00 00 43 01 00 00 00  |TRACK_ID...C....|
00000030  0b 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
00000040  4c 4d 55 4c 54 00 00 00  00 00 00 4c 0c 00 00 00  |LMULT......L....|
00000050  01 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
00000060  4e 54 41 58 59 45 41 52  00 00 00 4e 0d 00 00 00  |NTAXYEAR...N....|
00000070  04 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
00000080  4e 43 4f 55 4e 54 59 43  4f 44 00 4e 11 00 00 00  |NCOUNTYCOD.N....|
00000090  02 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
000000a0  43 50 52 4f 50 41 44 44  00 00 00 43 13 00 00 00  |CPROPADD...C....|
000000b0  3c 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |<...............|
000000c0  4c 43 4f 4d 4d 49 4e 44  00 00 00 4c 4f 00 00 00  |LCOMMIND...LO...|
000000d0  01 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
000000e0  4c 56 41 43 4c 41 4e 44  00 00 00 4c 50 00 00 00  |LVACLAND...LP...|
000000f0  01 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
$

表级别

但是表的级别是多少呢?关卡意味着它的版本。的dBASE表格式是一种随着时间的推移而发展的标准。当一个新版本的dBASE对该格式做了一些改进，一个新的格式级别编号，与新的dBASE版本相同。为例如，我们有3、4、5和7级对应于dBASE III，dBASE IV, dBASE 5和Visual dBASE 7。没有第6级，因为没有Visual dBASE 6.

第7级带来了许多改进。字段名最多可以有31个字符(以前最多10个)。一些新的字段类型具有出现(例如，AutoIncrement字段使近不可能给同一个表中的两个记录相同的数字)。如果您的表必须由其他软件使用，那么您可能必须这样做为了兼容性而牺牲这些优点，尽可能少应用程序可以使用7级表。

。dbf文件格式

文件头字节0,0-2表示版本号:3表示dBASE Level 5, 4表示dBASE Level 7。

5级DOS报头

数据文件(*.dbf)