Documentation
¶
Index ¶
- Constants
- Variables
- func GetDefaultCollation(charset string) (string, error)
- func GetDefaultCollationLegacy(charset string) (string, error)
- func HackSlice(s string) (b []byte)
- func HackString(b []byte) (s string)
- func MySQLDefaultCollation(cs string) (string, bool)
- func ValidCharsetAndCollation(cs string, co string) bool
- type Charset
- type Collation
- type Encoding
- type EncodingTp
- type Op
Constants ¶
const ( // CollationBin is the default collation for CharsetBin. CollationBin = "binary" // CollationUTF8 is the default collation for CharsetUTF8. CollationUTF8 = "utf8_bin" // CollationUTF8MB4 is the default collation for CharsetUTF8MB4. CollationUTF8MB4 = "utf8mb4_bin" // CollationASCII is the default collation for CharsetACSII. CollationASCII = "ascii_bin" // CollationLatin1 is the default collation for CharsetLatin1. CollationLatin1 = "latin1_bin" // CollationGBKBin is the default collation for CharsetGBK when new collation is disabled. CollationGBKBin = "gbk_bin" // CollationGBKChineseCI is the default collation for CharsetGBK when new collation is enabled. CollationGBKChineseCI = "gbk_chinese_ci" // CollationGB18030Bin is the default collation for CharsetGB18030 when new collation is disabled. CollationGB18030Bin = "gb18030_bin" // CollationGB18030ChineseCI is the default collation for CharsetGB18030 when new collation is enabled. CollationGB18030ChineseCI = "gb18030_chinese_ci" )
const ( // CharsetASCII is a subset of UTF8. CharsetASCII = "ascii" // CharsetBin is used for marking binary charset. CharsetBin = "binary" // CharsetLatin1 is a single byte charset. CharsetLatin1 = "latin1" // CharsetUTF8 is the default charset for string types. CharsetUTF8 = "utf8" // CharsetUTF8MB3 is 3 bytes utf8, a MySQL legacy encoding. "utf8" and "utf8mb3" are aliases. CharsetUTF8MB3 = "utf8mb3" // CharsetUTF8MB4 represents 4 bytes utf8, which works the same way as utf8 in Go. CharsetUTF8MB4 = "utf8mb4" // CharsetGB18030 represents 4 bytes gb18030. CharsetGB18030 = "gb18030" //revive:disable:exported CharsetARMSCII8 = "armscii8" CharsetBig5 = "big5" CharsetCP1250 = "cp1250" CharsetCP1251 = "cp1251" CharsetCP1256 = "cp1256" CharsetCP1257 = "cp1257" CharsetCP850 = "cp850" CharsetCP852 = "cp852" CharsetCP866 = "cp866" CharsetCP932 = "cp932" CharsetDEC8 = "dec8" CharsetEUCJPMS = "eucjpms" CharsetEUCKR = "euckr" CharsetGB2312 = "gb2312" CharsetGBK = "gbk" CharsetGEOSTD8 = "geostd8" CharsetGreek = "greek" CharsetHebrew = "hebrew" CharsetHP8 = "hp8" CharsetKEYBCS2 = "keybcs2" CharsetKOI8R = "koi8r" CharsetKOI8U = "koi8u" CharsetLatin2 = "latin2" CharsetLatin5 = "latin5" CharsetLatin7 = "latin7" CharsetMacCE = "macce" CharsetMacRoman = "macroman" CharsetSJIS = "sjis" CharsetSWE7 = "swe7" CharsetTIS620 = "tis620" CharsetUCS2 = "ucs2" CharsetUJIS = "ujis" CharsetUTF16 = "utf16" CharsetUTF16LE = "utf16le" CharsetUTF32 = "utf32" )
const ( // OpReplaceNoErr is used to replace invalid bytes with '?'. OpReplaceNoErr = opFromUTF8 | opTruncateReplace | opCollectFrom | opSkipError OpReplace = opFromUTF8 | opTruncateReplace | opCollectFrom OpEncode = opFromUTF8 | opTruncateTrim | opCollectTo OpEncodeNoErr = OpEncode | opSkipError OpEncodeReplace = opFromUTF8 | opTruncateReplace | opCollectTo OpDecode = opToUTF8 | opTruncateTrim | opCollectTo OpDecodeNoErr = OpDecode | opSkipError OpDecodeReplace = opToUTF8 | opTruncateReplace | opCollectTo )
Variables ¶
var ( // ErrUnknownCollation is unknown collation. ErrUnknownCollation = mysql.NewStdErr("ddl", mysql.ErrUnknownCollation) // ErrCollationCharsetMismatch is collation charset mismatch. ErrCollationCharsetMismatch = mysql.NewStdErr("ddl", mysql.ErrCollationCharsetMismatch) )
var ( // PadSpace is to mark that trailing spaces are insignificant in comparisons PadSpace = "PAD SPACE" // PadNone is to mark that trailing spaces are significant in comparisons PadNone = "NO PAD" )
var CharacterSetInfos = map[string]*Charset{ CharsetUTF8: {CharsetUTF8, CollationUTF8, make(map[string]*Collation), "UTF-8 Unicode", 3}, CharsetUTF8MB4: {CharsetUTF8MB4, CollationUTF8MB4, make(map[string]*Collation), "UTF-8 Unicode", 4}, CharsetASCII: {CharsetASCII, CollationASCII, make(map[string]*Collation), "US ASCII", 1}, CharsetLatin1: {CharsetLatin1, CollationLatin1, make(map[string]*Collation), "Latin1", 1}, CharsetBin: {CharsetBin, CollationBin, make(map[string]*Collation), "binary", 1}, CharsetGBK: {CharsetGBK, CollationGBKBin, make(map[string]*Collation), "Chinese Internal Code Specification", 2}, CharsetGB18030: {CharsetGB18030, CollationGB18030Bin, make(map[string]*Collation), "China National Standard GB18030", 4}, }
CharacterSetInfos contains all the supported charsets.
var EncodingASCIIImpl = &encodingASCII{encodingBase{enc: encoding.Nop}}
EncodingASCIIImpl is the instance of encodingASCII
var EncodingBinImpl = &encodingBin{encodingBase{enc: encoding.Nop}}
EncodingBinImpl is the instance of encodingBin.
var EncodingLatin1Impl = &encodingLatin1{encodingUTF8{encodingBase{enc: encoding.Nop}}}
EncodingLatin1Impl is the instance of encodingLatin1. latin1 is handled with the utf8 implementation (a no-op transform) for backward compatibility.
var EncodingUTF8Impl = &encodingUTF8{encodingBase{enc: encoding.Nop}}
EncodingUTF8Impl is the instance of encodingUTF8.
var EncodingUTF8MB3StrictImpl = &encodingUTF8MB3Strict{ encodingUTF8{ encodingBase{ enc: encoding.Nop, }, }, }
EncodingUTF8MB3StrictImpl is the instance of encodingUTF8MB3Strict.
var ErrInvalidCharacterString = mysql.NewStdErr("parser", mysql.ErrInvalidCharacterString)
ErrInvalidCharacterString returns when the string is invalid in the specific charset.
Functions ¶
func GetDefaultCollation ¶
GetDefaultCollation returns the default collation for charset.
func GetDefaultCollationLegacy ¶
GetDefaultCollationLegacy is compatible with the charset support in old version parser.
func HackString ¶
HackString converts slice to string without copy. Use it at your own risk.
func MySQLDefaultCollation ¶
MySQLDefaultCollation returns the collation MySQL 8.0+ applies to a charset that is used without an explicit COLLATE clause, and whether cs is a charset this parser knows.
It deliberately does not go through GetCharsetInfo/GetDefaultCollation: those consult CharacterSetInfos first, which carries the *_bin defaults inherited from this parser's upstream (utf8mb4 -> utf8mb4_bin). MySQL's own default for utf8mb4 is utf8mb4_0900_ai_ci, which is what the charsets registry records, so callers that need to reason about what a live server would do must read that registry directly. Legacy utf8_* spellings are returned as-is; see utf8Alias.
func ValidCharsetAndCollation ¶
ValidCharsetAndCollation checks the charset and the collation validity and returns a boolean.
Types ¶
type Charset ¶
type Charset struct {
Name string
DefaultCollation string
Collations map[string]*Collation
Desc string
Maxlen int
}
Charset is a charset. Now we only support MySQL.
func GetCharsetInfo ¶
GetCharsetInfo returns charset and collation for cs as name.
type Collation ¶
type Collation struct {
ID int
CharsetName string
Name string
IsDefault bool
Sortlen int
PadAttribute string
}
Collation is a collation. Now we only support MySQL.
func GetCollationByName ¶
GetCollationByName returns the collation by name.
type Encoding ¶
type Encoding interface {
// Name is the name of the encoding.
Name() string
// Tp is the type of the encoding.
Tp() EncodingTp
// Peek returns the next char.
Peek(src []byte) []byte
// MbLen returns multiple byte length, if the next character is single byte, return 0.
MbLen(string) int
// IsValid checks whether the utf-8 bytes can be convert to valid string in current encoding.
IsValid(src []byte) bool
// Foreach iterates the characters in current encoding.
Foreach(src []byte, op Op, fn func(from, to []byte, ok bool) bool)
// Transform map the bytes in src to dest according to Op.
// **the caller should initialize the dest if it wants to avoid memory alloc every time,
// or else it will always make a new one**
//
// **the returned array may be the alias of `src`, edit the returned array on your own risk**
Transform(dest *bytes.Buffer, src []byte, op Op) ([]byte, error)
// ToUpper change a string to uppercase.
ToUpper(src string) string
// ToLower change a string to lowercase.
ToLower(src string) string
}
Encoding provide encode/decode functions for a string with a specific charset.
func FindEncoding ¶
FindEncoding finds the encoding according to charset.
type EncodingTp ¶
type EncodingTp int8
EncodingTp is the type of the encoding.
const ( EncodingTpNone EncodingTp = iota EncodingTpUTF8 EncodingTpUTF8MB3Strict EncodingTpASCII EncodingTpLatin1 EncodingTpBin )
Source Files