archive
archive/tar
archive/zip
bufio
bufio（緩存）
builtin
builtin（內(nèi)置包）
bytes
bytes（包字節(jié)）
compress
compress/bzip2（壓縮/bzip2）
compress/flate（壓縮/flate）
compress/gzip（壓縮/gzip）
compress/lzw（壓縮/lzw）
compress/zlib（壓縮/zlib）
container
container/heap（容器數(shù)據(jù)結(jié)構(gòu)heap）
container/list（容器數(shù)據(jù)結(jié)構(gòu)list）
container/ring（容器數(shù)據(jù)結(jié)構(gòu)ring）
context
context（上下文）
crypto
crypto（加密）
crypto/aes（加密/aes）
crypto/cipher（加密/cipher）
crypto/des（加密/des）
crypto/dsa（加密/dsa）
crypto/ecdsa（加密/ecdsa）
crypto/elliptic（加密/elliptic）
crypto/hmac（加密/hmac）
crypto/md5（加密/md5）
crypto/rand（加密/rand）
crypto/rc4（加密/rc4）
crypto/rsa（加密/rsa）
crypto/sha1（加密/sha1）
crypto/sha256（加密/sha256）
crypto/sha512（加密/sha512）
crypto/subtle（加密/subtle）
crypto/tls（加密/tls）
crypto/x509（加密/x509）
crypto/x509/pkix（加密/x509/pkix）
database
database/sql（數(shù)據(jù)庫/sql）
database/sql/driver（數(shù)據(jù)庫/sql/driver）
debug
debug/dwarf（調(diào)試/dwarf）
debug/elf（調(diào)試/elf）
debug/gosym（調(diào)試/gosym）
debug/macho（調(diào)試/macho）
debug/pe（調(diào)試/pe）
debug/plan9obj（調(diào)試/plan9obj）
encoding
encoding（編碼）
encoding/ascii85（編碼/ascii85）
encoding/asn1（編碼/asn1）
encoding/base32（編碼/base32）
encoding/base64（編碼/base64）
encoding/binary（編碼/binary）
encoding/csv（編碼/csv）
encoding/gob（編碼/gob）
encoding/hex（編碼/hex）
encoding/json（編碼/json）
encoding/pem（編碼/pem）
encoding/xml（編碼/xml）
errors
errors（錯誤）
expvar
expvar
flag
flag（命令行參數(shù)解析flag包）
fmt
fmt
go
go/ast（抽象語法樹）
go/build
go/constant（常量）
go/doc（文檔）
go/format（格式）
go/importer
go/parser
go/printer
go/scanner（掃描儀）
go/token（令牌）
go/types（類型）
hash
hash（散列）
hash/adler32
hash/crc32
hash/crc64
hash/fnv
html
html
html/template（模板）
image
image（圖像）
image/color（顏色）
image/color/palette（調(diào)色板）
image/draw（繪圖）
image/gif
image/jpeg
image/png
index
index/suffixarray
io
io
io/ioutil
log
log
log/syslog（日志系統(tǒng)）
math
math
math/big
math/big
math/bits
math/bits
math/cmplx
math/cmplx
math/rand
math/rand
mime
mime
mime/multipart（多部分）
mime/quotedprintable
net
net
net/http
net/http
net/http/cgi
net/http/cookiejar
net/http/fcgi
net/http/httptest
net/http/httptrace
net/http/httputil
net/http/internal
net/http/pprof
net/mail
net/mail
net/rpc
net/rpc
net/rpc/jsonrpc
net/smtp
net/smtp
net/textproto
net/textproto
net/url
net/url
os
os
os/exec
os/signal
os/user
path
path
path/filepath（文件路徑）
plugin
plugin（插件）
reflect
reflect（反射）
regexp
regexp（正則表達(dá)式）
regexp/syntax
runtime
runtime（運行時）
runtime/debug（調(diào)試）
runtime/internal/sys
runtime/pprof
runtime/race（競爭）
runtime/trace（執(zhí)行追蹤器）
sort
sort（排序算法）
strconv
strconv（轉(zhuǎn)換）
strings
strings（字符串）
sync
sync（同步）
sync/atomic（原子操作）
syscall
syscall（系統(tǒng)調(diào)用）
testing
testing（測試）
testing/iotest
testing/quick
text
text/scanner（掃描文本）
text/tabwriter
text/template（定義模板）
text/template/parse
time
time（時間戳）
unicode
unicode
unicode/utf16
unicode/utf8
unsafe
unsafe
?
This document uses PHP Chinese website manual Release
characters
import "unicode"
概觀
索引
示例
子目錄
概觀
打包unicode提供數(shù)據(jù)和函數(shù)來測試 Unicode 代碼點的一些屬性。
示例（Is）
以“Is”開頭的函數(shù)可用于檢查符文屬于哪個范圍的表格。請注意，符文可能適用于多個范圍。
package mainimport ("fmt""unicode")func main() {// constant with mixed type runesconst mixed = "\b5?g?9! ℃?G"for _, c := range mixed {
fmt.Printf("For %q:\n", c)if unicode.IsControl(c) {
fmt.Println("\tis control rune")}if unicode.IsDigit(c) {
fmt.Println("\tis digit rune")}if unicode.IsGraphic(c) {
fmt.Println("\tis graphic rune")}if unicode.IsLetter(c) {
fmt.Println("\tis letter rune")}if unicode.IsLower(c) {
fmt.Println("\tis lower case rune")}if unicode.IsMark(c) {
fmt.Println("\tis mark rune")}if unicode.IsNumber(c) {
fmt.Println("\tis number rune")}if unicode.IsPrint(c) {
fmt.Println("\tis printable rune")}if !unicode.IsPrint(c) {
fmt.Println("\tis not printable rune")}if unicode.IsPunct(c) {
fmt.Println("\tis punct rune")}if unicode.IsSpace(c) {
fmt.Println("\tis space rune")}if unicode.IsSymbol(c) {
fmt.Println("\tis symbol rune")}if unicode.IsTitle(c) {
fmt.Println("\tis title case rune")}if unicode.IsUpper(c) {
fmt.Println("\tis upper case rune")}}}索引
常量
變量
func In(r rune, ranges ...*RangeTable) bool
func Is(rangeTab *RangeTable, r rune) bool
func IsControl(r rune) bool
func IsDigit(r rune) bool
func IsGraphic(r rune) bool
func IsLetter(r rune) bool
func IsLower(r rune) bool
func IsMark(r rune) bool
func IsNumber(r rune) bool
func IsOneOf(ranges []*RangeTable, r rune) bool
func IsPrint(r rune) bool
func IsPunct(r rune) bool
func IsSpace(r rune) bool
func IsSymbol(r rune) bool
func IsTitle(r rune) bool
func IsUpper(r rune) bool
func SimpleFold(r rune) rune
func To(_case int, r rune) rune
func ToLower(r rune) rune
func ToTitle(r rune) rune
func ToUpper(r rune) rune
type CaseRange
type Range16
type Range32
type RangeTable
type SpecialCase
func (special SpecialCase) ToLower(r rune) rune
func (special SpecialCase) ToTitle(r rune) rune
func (special SpecialCase) ToUpper(r rune) rune
錯誤
示例
SimpleFold SpecialCase To ToLower ToTitle ToUpper Package (Is)
打包文件
casetables.go digit.go graphic.go letter.go tables.go
常量
const ( MaxRune = '\U0010FFFF' // Maximum valid Unicode code point. ReplacementChar = '\uFFFD' // Represents invalid code points. MaxASCII = '\u007F' // maximum ASCII value. MaxLatin1 = '\u00FF' // maximum Latin-1 value.)
CaseRanges內(nèi)的 Delta 數(shù)組索引，用于大小寫映射。
const ( UpperCase = iota LowerCase TitleCase MaxCase)
如果一個 CaseRange 的 Delta 字段是 UpperLower，則意味著這個 CaseRange 表示一個形式的序列（比如說） Upper Lower Upper Lower 。
const ( UpperLower = MaxRune + 1 // (Cannot be a valid delta.))
版本是從中派生表的 Unicode 版本。
const Version = "9.0.0"
變量
這些變量有 * RangeTable 類型。
var ( Cc = _Cc // Cc is the set of Unicode characters in category Cc. Cf = _Cf // Cf is the set of Unicode characters in category Cf. Co = _Co // Co is the set of Unicode characters in category Co. Cs = _Cs // Cs is the set of Unicode characters in category Cs. Digit = _Nd // Digit is the set of Unicode characters with the "decimal digit" property. Nd = _Nd // Nd is the set of Unicode characters in category Nd. Letter = _L // Letter/L is the set of Unicode letters, category L. L = _L Lm = _Lm // Lm is the set of Unicode characters in category Lm. Lo = _Lo // Lo is the set of Unicode characters in category Lo. Lower = _Ll // Lower is the set of Unicode lower case letters. Ll = _Ll // Ll is the set of Unicode characters in category Ll. Mark = _M // Mark/M is the set of Unicode mark characters, category M. M = _M Mc = _Mc // Mc is the set of Unicode characters in category Mc. Me = _Me // Me is the set of Unicode characters in category Me. Mn = _Mn // Mn is the set of Unicode characters in category Mn. Nl = _Nl // Nl is the set of Unicode characters in category Nl. No = _No // No is the set of Unicode characters in category No. Number = _N // Number/N is the set of Unicode number characters, category N. N = _N Other = _C // Other/C is the set of Unicode control and special characters, category C. C = _C Pc = _Pc // Pc is the set of Unicode characters in category Pc. Pd = _Pd // Pd is the set of Unicode characters in category Pd. Pe = _Pe // Pe is the set of Unicode characters in category Pe. Pf = _Pf // Pf is the set of Unicode characters in category Pf. Pi = _Pi // Pi is the set of Unicode characters in category Pi. Po = _Po // Po is the set of Unicode characters in category Po. Ps = _Ps // Ps is the set of Unicode characters in category Ps. Punct = _P // Punct/P is the set of Unicode punctuation characters, category P. P = _P Sc = _Sc // Sc is the set of Unicode characters in category Sc. Sk = _Sk // Sk is the set of Unicode characters in category Sk. Sm = _Sm // Sm is the set of Unicode characters in category Sm. So = _So // So is the set of Unicode characters in category So. Space = _Z // Space/Z is the set of Unicode space characters, category Z. Z = _Z Symbol = _S // Symbol/S is the set of Unicode symbol characters, category S. S = _S Title = _Lt // Title is the set of Unicode title case letters. Lt = _Lt // Lt is the set of Unicode characters in category Lt. Upper = _Lu // Upper is the set of Unicode upper case letters. Lu = _Lu // Lu is the set of Unicode characters in category Lu. Zl = _Zl // Zl is the set of Unicode characters in category Zl. Zp = _Zp // Zp is the set of Unicode characters in category Zp. Zs = _Zs // Zs is the set of Unicode characters in category Zs.)
這些變量有 * RangeTable 類型。
var ( Adlam = _Adlam // Adlam is the set of Unicode characters in script Adlam. Ahom = _Ahom // Ahom is the set of Unicode characters in script Ahom. Anatolian_Hieroglyphs = _Anatolian_Hieroglyphs // Anatolian_Hieroglyphs is the set of Unicode characters in script Anatolian_Hieroglyphs. Arabic = _Arabic // Arabic is the set of Unicode characters in script Arabic. Armenian = _Armenian // Armenian is the set of Unicode characters in script Armenian. Avestan = _Avestan // Avestan is the set of Unicode characters in script Avestan. Balinese = _Balinese // Balinese is the set of Unicode characters in script Balinese. Bamum = _Bamum // Bamum is the set of Unicode characters in script Bamum. Bassa_Vah = _Bassa_Vah // Bassa_Vah is the set of Unicode characters in script Bassa_Vah. Batak = _Batak // Batak is the set of Unicode characters in script Batak. Bengali = _Bengali // Bengali is the set of Unicode characters in script Bengali. Bhaiksuki = _Bhaiksuki // Bhaiksuki is the set of Unicode characters in script Bhaiksuki. Bopomofo = _Bopomofo // Bopomofo is the set of Unicode characters in script Bopomofo. Brahmi = _Brahmi // Brahmi is the set of Unicode characters in script Brahmi. Braille = _Braille // Braille is the set of Unicode characters in script Braille. Buginese = _Buginese // Buginese is the set of Unicode characters in script Buginese. Buhid = _Buhid // Buhid is the set of Unicode characters in script Buhid. Canadian_Aboriginal = _Canadian_Aboriginal // Canadian_Aboriginal is the set of Unicode characters in script Canadian_Aboriginal. Carian = _Carian // Carian is the set of Unicode characters in script Carian. Caucasian_Albanian = _Caucasian_Albanian // Caucasian_Albanian is the set of Unicode characters in script Caucasian_Albanian. Chakma = _Chakma // Chakma is the set of Unicode characters in script Chakma. Cham = _Cham // Cham is the set of Unicode characters in script Cham. Cherokee = _Cherokee // Cherokee is the set of Unicode characters in script Cherokee. Common = _Common // Common is the set of Unicode characters in script Common. Coptic = _Coptic // Coptic is the set of Unicode characters in script Coptic. Cuneiform = _Cuneiform // Cuneiform is the set of Unicode characters in script Cuneiform. Cypriot = _Cypriot // Cypriot is the set of Unicode characters in script Cypriot. Cyrillic = _Cyrillic // Cyrillic is the set of Unicode characters in script Cyrillic. Deseret = _Deseret // Deseret is the set of Unicode characters in script Deseret. Devanagari = _Devanagari // Devanagari is the set of Unicode characters in script Devanagari. Duployan = _Duployan // Duployan is the set of Unicode characters in script Duployan. Egyptian_Hieroglyphs = _Egyptian_Hieroglyphs // Egyptian_Hieroglyphs is the set of Unicode characters in script Egyptian_Hieroglyphs. Elbasan = _Elbasan // Elbasan is the set of Unicode characters in script Elbasan. Ethiopic = _Ethiopic // Ethiopic is the set of Unicode characters in script Ethiopic. Georgian = _Georgian // Georgian is the set of Unicode characters in script Georgian. Glagolitic = _Glagolitic // Glagolitic is the set of Unicode characters in script Glagolitic. Gothic = _Gothic // Gothic is the set of Unicode characters in script Gothic. Grantha = _Grantha // Grantha is the set of Unicode characters in script Grantha. Greek = _Greek // Greek is the set of Unicode characters in script Greek. Gujarati = _Gujarati // Gujarati is the set of Unicode characters in script Gujarati. Gurmukhi = _Gurmukhi // Gurmukhi is the set of Unicode characters in script Gurmukhi. Han = _Han // Han is the set of Unicode characters in script Han. Hangul = _Hangul // Hangul is the set of Unicode characters in script Hangul. Hanunoo = _Hanunoo // Hanunoo is the set of Unicode characters in script Hanunoo. Hatran = _Hatran // Hatran is the set of Unicode characters in script Hatran. Hebrew = _Hebrew // Hebrew is the set of Unicode characters in script Hebrew. Hiragana = _Hiragana // Hiragana is the set of Unicode characters in script Hiragana. Imperial_Aramaic = _Imperial_Aramaic // Imperial_Aramaic is the set of Unicode characters in script Imperial_Aramaic. Inherited = _Inherited // Inherited is the set of Unicode characters in script Inherited. Inscriptional_Pahlavi = _Inscriptional_Pahlavi // Inscriptional_Pahlavi is the set of Unicode characters in script Inscriptional_Pahlavi. Inscriptional_Parthian = _Inscriptional_Parthian // Inscriptional_Parthian is the set of Unicode characters in script Inscriptional_Parthian. Javanese = _Javanese // Javanese is the set of Unicode characters in script Javanese. Kaithi = _Kaithi // Kaithi is the set of Unicode characters in script Kaithi. Kannada = _Kannada // Kannada is the set of Unicode characters in script Kannada. Katakana = _Katakana // Katakana is the set of Unicode characters in script Katakana. Kayah_Li = _Kayah_Li // Kayah_Li is the set of Unicode characters in script Kayah_Li. Kharoshthi = _Kharoshthi // Kharoshthi is the set of Unicode characters in script Kharoshthi. Khmer = _Khmer // Khmer is the set of Unicode characters in script Khmer. Khojki = _Khojki // Khojki is the set of Unicode characters in script Khojki. Khudawadi = _Khudawadi // Khudawadi is the set of Unicode characters in script Khudawadi. Lao = _Lao // Lao is the set of Unicode characters in script Lao. Latin = _Latin // Latin is the set of Unicode characters in script Latin. Lepcha = _Lepcha // Lepcha is the set of Unicode characters in script Lepcha. Limbu = _Limbu // Limbu is the set of Unicode characters in script Limbu. Linear_A = _Linear_A // Linear_A is the set of Unicode characters in script Linear_A. Linear_B = _Linear_B // Linear_B is the set of Unicode characters in script Linear_B. Lisu = _Lisu // Lisu is the set of Unicode characters in script Lisu. Lycian = _Lycian // Lycian is the set of Unicode characters in script Lycian. Lydian = _Lydian // Lydian is the set of Unicode characters in script Lydian. Mahajani = _Mahajani // Mahajani is the set of Unicode characters in script Mahajani. Malayalam = _Malayalam // Malayalam is the set of Unicode characters in script Malayalam. Mandaic = _Mandaic // Mandaic is the set of Unicode characters in script Mandaic. Manichaean = _Manichaean // Manichaean is the set of Unicode characters in script Manichaean. Marchen = _Marchen // Marchen is the set of Unicode characters in script Marchen. Meetei_Mayek = _Meetei_Mayek // Meetei_Mayek is the set of Unicode characters in script Meetei_Mayek. Mende_Kikakui = _Mende_Kikakui // Mende_Kikakui is the set of Unicode characters in script Mende_Kikakui. Meroitic_Cursive = _Meroitic_Cursive // Meroitic_Cursive is the set of Unicode characters in script Meroitic_Cursive. Meroitic_Hieroglyphs = _Meroitic_Hieroglyphs // Meroitic_Hieroglyphs is the set of Unicode characters in script Meroitic_Hieroglyphs. Miao = _Miao // Miao is the set of Unicode characters in script Miao. Modi = _Modi // Modi is the set of Unicode characters in script Modi. Mongolian = _Mongolian // Mongolian is the set of Unicode characters in script Mongolian. Mro = _Mro // Mro is the set of Unicode characters in script Mro. Multani = _Multani // Multani is the set of Unicode characters in script Multani. Myanmar = _Myanmar // Myanmar is the set of Unicode characters in script Myanmar. Nabataean = _Nabataean // Nabataean is the set of Unicode characters in script Nabataean. New_Tai_Lue = _New_Tai_Lue // New_Tai_Lue is the set of Unicode characters in script New_Tai_Lue. Newa = _Newa // Newa is the set of Unicode characters in script Newa. Nko = _Nko // Nko is the set of Unicode characters in script Nko. Ogham = _Ogham // Ogham is the set of Unicode characters in script Ogham. Ol_Chiki = _Ol_Chiki // Ol_Chiki is the set of Unicode characters in script Ol_Chiki. Old_Hungarian = _Old_Hungarian // Old_Hungarian is the set of Unicode characters in script Old_Hungarian. Old_Italic = _Old_Italic // Old_Italic is the set of Unicode characters in script Old_Italic. Old_North_Arabian = _Old_North_Arabian // Old_North_Arabian is the set of Unicode characters in script Old_North_Arabian. Old_Permic = _Old_Permic // Old_Permic is the set of Unicode characters in script Old_Permic. Old_Persian = _Old_Persian // Old_Persian is the set of Unicode characters in script Old_Persian. Old_South_Arabian = _Old_South_Arabian // Old_South_Arabian is the set of Unicode characters in script Old_South_Arabian. Old_Turkic = _Old_Turkic // Old_Turkic is the set of Unicode characters in script Old_Turkic. Oriya = _Oriya // Oriya is the set of Unicode characters in script Oriya. Osage = _Osage // Osage is the set of Unicode characters in script Osage. Osmanya = _Osmanya // Osmanya is the set of Unicode characters in script Osmanya. Pahawh_Hmong = _Pahawh_Hmong // Pahawh_Hmong is the set of Unicode characters in script Pahawh_Hmong. Palmyrene = _Palmyrene // Palmyrene is the set of Unicode characters in script Palmyrene. Pau_Cin_Hau = _Pau_Cin_Hau // Pau_Cin_Hau is the set of Unicode characters in script Pau_Cin_Hau. Phags_Pa = _Phags_Pa // Phags_Pa is the set of Unicode characters in script Phags_Pa. Phoenician = _Phoenician // Phoenician is the set of Unicode characters in script Phoenician. Psalter_Pahlavi = _Psalter_Pahlavi // Psalter_Pahlavi is the set of Unicode characters in script Psalter_Pahlavi. Rejang = _Rejang // Rejang is the set of Unicode characters in script Rejang. Runic = _Runic // Runic is the set of Unicode characters in script Runic. Samaritan = _Samaritan // Samaritan is the set of Unicode characters in script Samaritan. Saurashtra = _Saurashtra // Saurashtra is the set of Unicode characters in script Saurashtra. Sharada = _Sharada // Sharada is the set of Unicode characters in script Sharada. Shavian = _Shavian // Shavian is the set of Unicode characters in script Shavian. Siddham = _Siddham // Siddham is the set of Unicode characters in script Siddham. SignWriting = _SignWriting // SignWriting is the set of Unicode characters in script SignWriting. Sinhala = _Sinhala // Sinhala is the set of Unicode characters in script Sinhala. Sora_Sompeng = _Sora_Sompeng // Sora_Sompeng is the set of Unicode characters in script Sora_Sompeng. Sundanese = _Sundanese // Sundanese is the set of Unicode characters in script Sundanese. Syloti_Nagri = _Syloti_Nagri // Syloti_Nagri is the set of Unicode characters in script Syloti_Nagri. Syriac = _Syriac // Syriac is the set of Unicode characters in script Syriac. Tagalog = _Tagalog // Tagalog is the set of Unicode characters in script Tagalog. Tagbanwa = _Tagbanwa // Tagbanwa is the set of Unicode characters in script Tagbanwa. Tai_Le = _Tai_Le // Tai_Le is the set of Unicode characters in script Tai_Le. Tai_Tham = _Tai_Tham // Tai_Tham is the set of Unicode characters in script Tai_Tham. Tai_Viet = _Tai_Viet // Tai_Viet is the set of Unicode characters in script Tai_Viet. Takri = _Takri // Takri is the set of Unicode characters in script Takri. Tamil = _Tamil // Tamil is the set of Unicode characters in script Tamil. Tangut = _Tangut // Tangut is the set of Unicode characters in script Tangut. Telugu = _Telugu // Telugu is the set of Unicode characters in script Telugu. Thaana = _Thaana // Thaana is the set of Unicode characters in script Thaana. Thai = _Thai // Thai is the set of Unicode characters in script Thai. Tibetan = _Tibetan // Tibetan is the set of Unicode characters in script Tibetan. Tifinagh = _Tifinagh // Tifinagh is the set of Unicode characters in script Tifinagh. Tirhuta = _Tirhuta // Tirhuta is the set of Unicode characters in script Tirhuta. Ugaritic = _Ugaritic // Ugaritic is the set of Unicode characters in script Ugaritic. Vai = _Vai // Vai is the set of Unicode characters in script Vai. Warang_Citi = _Warang_Citi // Warang_Citi is the set of Unicode characters in script Warang_Citi. Yi = _Yi // Yi is the set of Unicode characters in script Yi.)
這些變量有 * RangeTable 類型。
var ( ASCII_Hex_Digit = _ASCII_Hex_Digit // ASCII_Hex_Digit is the set of Unicode characters with property ASCII_Hex_Digit. Bidi_Control = _Bidi_Control // Bidi_Control is the set of Unicode characters with property Bidi_Control. Dash = _Dash // Dash is the set of Unicode characters with property Dash. Deprecated = _Deprecated // Deprecated is the set of Unicode characters with property Deprecated. Diacritic = _Diacritic // Diacritic is the set of Unicode characters with property Diacritic. Extender = _Extender // Extender is the set of Unicode characters with property Extender. Hex_Digit = _Hex_Digit // Hex_Digit is the set of Unicode characters with property Hex_Digit. Hyphen = _Hyphen // Hyphen is the set of Unicode characters with property Hyphen. IDS_Binary_Operator = _IDS_Binary_Operator // IDS_Binary_Operator is the set of Unicode characters with property IDS_Binary_Operator. IDS_Trinary_Operator = _IDS_Trinary_Operator // IDS_Trinary_Operator is the set of Unicode characters with property IDS_Trinary_Operator. Ideographic = _Ideographic // Ideographic is the set of Unicode characters with property Ideographic. Join_Control = _Join_Control // Join_Control is the set of Unicode characters with property Join_Control. Logical_Order_Exception = _Logical_Order_Exception // Logical_Order_Exception is the set of Unicode characters with property Logical_Order_Exception. Noncharacter_Code_Point = _Noncharacter_Code_Point // Noncharacter_Code_Point is the set of Unicode characters with property Noncharacter_Code_Point. Other_Alphabetic = _Other_Alphabetic // Other_Alphabetic is the set of Unicode characters with property Other_Alphabetic. Other_Default_Ignorable_Code_Point = _Other_Default_Ignorable_Code_Point // Other_Default_Ignorable_Code_Point is the set of Unicode characters with property Other_Default_Ignorable_Code_Point. Other_Grapheme_Extend = _Other_Grapheme_Extend // Other_Grapheme_Extend is the set of Unicode characters with property Other_Grapheme_Extend. Other_ID_Continue = _Other_ID_Continue // Other_ID_Continue is the set of Unicode characters with property Other_ID_Continue. Other_ID_Start = _Other_ID_Start // Other_ID_Start is the set of Unicode characters with property Other_ID_Start. Other_Lowercase = _Other_Lowercase // Other_Lowercase is the set of Unicode characters with property Other_Lowercase. Other_Math = _Other_Math // Other_Math is the set of Unicode characters with property Other_Math. Other_Uppercase = _Other_Uppercase // Other_Uppercase is the set of Unicode characters with property Other_Uppercase. Pattern_Syntax = _Pattern_Syntax // Pattern_Syntax is the set of Unicode characters with property Pattern_Syntax. Pattern_White_Space = _Pattern_White_Space // Pattern_White_Space is the set of Unicode characters with property Pattern_White_Space. Prepended_Concatenation_Mark = _Prepended_Concatenation_Mark // Prepended_Concatenation_Mark is the set of Unicode characters with property Prepended_Concatenation_Mark. Quotation_Mark = _Quotation_Mark // Quotation_Mark is the set of Unicode characters with property Quotation_Mark. Radical = _Radical // Radical is the set of Unicode characters with property Radical. STerm = _Sentence_Terminal // STerm is an alias for Sentence_Terminal. Sentence_Terminal = _Sentence_Terminal // Sentence_Terminal is the set of Unicode characters with property Sentence_Terminal. Soft_Dotted = _Soft_Dotted // Soft_Dotted is the set of Unicode characters with property Soft_Dotted. Terminal_Punctuation = _Terminal_Punctuation // Terminal_Punctuation is the set of Unicode characters with property Terminal_Punctuation. Unified_Ideograph = _Unified_Ideograph // Unified_Ideograph is the set of Unicode characters with property Unified_Ideograph. Variation_Selector = _Variation_Selector // Variation_Selector is the set of Unicode characters with property Variation_Selector. White_Space = _White_Space // White_Space is the set of Unicode characters with property White_Space.)
CaseRanges 是描述具有非自映射的所有字母的大小寫映射的表格。
var CaseRanges = _CaseRanges
類別是一組 Unicode 類別表。
var Categories = map[string]*RangeTable{ "C": C, "Cc": Cc, "Cf": Cf, "Co": Co, "Cs": Cs, "L": L, "Ll": Ll, "Lm": Lm, "Lo": Lo, "Lt": Lt, "Lu": Lu, "M": M, "Mc": Mc, "Me": Me, "Mn": Mn, "N": N, "Nd": Nd, "Nl": Nl, "No": No, "P": P, "Pc": Pc, "Pd": Pd, "Pe": Pe, "Pf": Pf, "Pi": Pi, "Po": Po, "Ps": Ps, "S": S, "Sc": Sc, "Sk": Sk, "Sm": Sm, "So": So, "Z": Z, "Zl": Zl, "Zp": Zp, "Zs": Zs,}FoldCategory 將類別名稱映射到類別外的代碼點表，這些代碼點在簡單大小寫折疊的情況下等同于類別內(nèi)的代碼點。如果沒有類別名稱的條目，則不存在這樣的點。
var FoldCategory = map[string]*RangeTable{ "L": foldL, "Ll": foldLl, "Lt": foldLt, "Lu": foldLu, "M": foldM, "Mn": foldMn,}FoldScript 將腳本名稱映射到腳本外的代碼點表，這些代碼點在簡單案例折疊到腳本內(nèi)的代碼點之后是等同的。如果沒有條目名稱的條目，則沒有這樣的條目。
var FoldScript = map[string]*RangeTable{ "Common": foldCommon, "Greek": foldGreek, "Inherited": foldInherited,}GraphicRanges 根據(jù) Unicode 定義了一組圖形字符。
var GraphicRanges = []*RangeTable{
L, M, N, P, S, Zs,}PrintRanges 根據(jù) Go 定義一組可打印的字符。ASCII 空間 U+0020 分開處理。
var PrintRanges = []*RangeTable{
L, M, N, P, S,}屬性是 Unicode 屬性表的集合。
var Properties = map[string]*RangeTable{ "ASCII_Hex_Digit": ASCII_Hex_Digit, "Bidi_Control": Bidi_Control, "Dash": Dash, "Deprecated": Deprecated, "Diacritic": Diacritic, "Extender": Extender, "Hex_Digit": Hex_Digit, "Hyphen": Hyphen, "IDS_Binary_Operator": IDS_Binary_Operator, "IDS_Trinary_Operator": IDS_Trinary_Operator, "Ideographic": Ideographic, "Join_Control": Join_Control, "Logical_Order_Exception": Logical_Order_Exception, "Noncharacter_Code_Point": Noncharacter_Code_Point, "Other_Alphabetic": Other_Alphabetic, "Other_Default_Ignorable_Code_Point": Other_Default_Ignorable_Code_Point, "Other_Grapheme_Extend": Other_Grapheme_Extend, "Other_ID_Continue": Other_ID_Continue, "Other_ID_Start": Other_ID_Start, "Other_Lowercase": Other_Lowercase, "Other_Math": Other_Math, "Other_Uppercase": Other_Uppercase, "Pattern_Syntax": Pattern_Syntax, "Pattern_White_Space": Pattern_White_Space, "Prepended_Concatenation_Mark": Prepended_Concatenation_Mark, "Quotation_Mark": Quotation_Mark, "Radical": Radical, "Sentence_Terminal": Sentence_Terminal, "STerm": Sentence_Terminal, "Soft_Dotted": Soft_Dotted, "Terminal_Punctuation": Terminal_Punctuation, "Unified_Ideograph": Unified_Ideograph, "Variation_Selector": Variation_Selector, "White_Space": White_Space,}腳本是一組 Unicode 腳本表。
var Scripts = map[string]*RangeTable{ "Adlam": Adlam, "Ahom": Ahom, "Anatolian_Hieroglyphs": Anatolian_Hieroglyphs, "Arabic": Arabic, "Armenian": Armenian, "Avestan": Avestan, "Balinese": Balinese, "Bamum": Bamum, "Bassa_Vah": Bassa_Vah, "Batak": Batak, "Bengali": Bengali, "Bhaiksuki": Bhaiksuki, "Bopomofo": Bopomofo, "Brahmi": Brahmi, "Braille": Braille, "Buginese": Buginese, "Buhid": Buhid, "Canadian_Aboriginal": Canadian_Aboriginal, "Carian": Carian, "Caucasian_Albanian": Caucasian_Albanian, "Chakma": Chakma, "Cham": Cham, "Cherokee": Cherokee, "Common": Common, "Coptic": Coptic, "Cuneiform": Cuneiform, "Cypriot": Cypriot, "Cyrillic": Cyrillic, "Deseret": Deseret, "Devanagari": Devanagari, "Duployan": Duployan, "Egyptian_Hieroglyphs": Egyptian_Hieroglyphs, "Elbasan": Elbasan, "Ethiopic": Ethiopic, "Georgian": Georgian, "Glagolitic": Glagolitic, "Gothic": Gothic, "Grantha": Grantha, "Greek": Greek, "Gujarati": Gujarati, "Gurmukhi": Gurmukhi, "Han": Han, "Hangul": Hangul, "Hanunoo": Hanunoo, "Hatran": Hatran, "Hebrew": Hebrew, "Hiragana": Hiragana, "Imperial_Aramaic": Imperial_Aramaic, "Inherited": Inherited, "Inscriptional_Pahlavi": Inscriptional_Pahlavi, "Inscriptional_Parthian": Inscriptional_Parthian, "Javanese": Javanese, "Kaithi": Kaithi, "Kannada": Kannada, "Katakana": Katakana, "Kayah_Li": Kayah_Li, "Kharoshthi": Kharoshthi, "Khmer": Khmer, "Khojki": Khojki, "Khudawadi": Khudawadi, "Lao": Lao, "Latin": Latin, "Lepcha": Lepcha, "Limbu": Limbu, "Linear_A": Linear_A, "Linear_B": Linear_B, "Lisu": Lisu, "Lycian": Lycian, "Lydian": Lydian, "Mahajani": Mahajani, "Malayalam": Malayalam, "Mandaic": Mandaic, "Manichaean": Manichaean, "Marchen": Marchen, "Meetei_Mayek": Meetei_Mayek, "Mende_Kikakui": Mende_Kikakui, "Meroitic_Cursive": Meroitic_Cursive, "Meroitic_Hieroglyphs": Meroitic_Hieroglyphs, "Miao": Miao, "Modi": Modi, "Mongolian": Mongolian, "Mro": Mro, "Multani": Multani, "Myanmar": Myanmar, "Nabataean": Nabataean, "New_Tai_Lue": New_Tai_Lue, "Newa": Newa, "Nko": Nko, "Ogham": Ogham, "Ol_Chiki": Ol_Chiki, "Old_Hungarian": Old_Hungarian, "Old_Italic": Old_Italic, "Old_North_Arabian": Old_North_Arabian, "Old_Permic": Old_Permic, "Old_Persian": Old_Persian, "Old_South_Arabian": Old_South_Arabian, "Old_Turkic": Old_Turkic, "Oriya": Oriya, "Osage": Osage, "Osmanya": Osmanya, "Pahawh_Hmong": Pahawh_Hmong, "Palmyrene": Palmyrene, "Pau_Cin_Hau": Pau_Cin_Hau, "Phags_Pa": Phags_Pa, "Phoenician": Phoenician, "Psalter_Pahlavi": Psalter_Pahlavi, "Rejang": Rejang, "Runic": Runic, "Samaritan": Samaritan, "Saurashtra": Saurashtra, "Sharada": Sharada, "Shavian": Shavian, "Siddham": Siddham, "SignWriting": SignWriting, "Sinhala": Sinhala, "Sora_Sompeng": Sora_Sompeng, "Sundanese": Sundanese, "Syloti_Nagri": Syloti_Nagri, "Syriac": Syriac, "Tagalog": Tagalog, "Tagbanwa": Tagbanwa, "Tai_Le": Tai_Le, "Tai_Tham": Tai_Tham, "Tai_Viet": Tai_Viet, "Takri": Takri, "Tamil": Tamil, "Tangut": Tangut, "Telugu": Telugu, "Thaana": Thaana, "Thai": Thai, "Tibetan": Tibetan, "Tifinagh": Tifinagh, "Tirhuta": Tirhuta, "Ugaritic": Ugaritic, "Vai": Vai, "Warang_Citi": Warang_Citi, "Yi": Yi,}func In
func In(r rune, ranges ...*RangeTable) bool
在報告中，符文是否是其中一個范圍的成員。
func Is
func Is(rangeTab *RangeTable, r rune) bool
Is 報告符文是否在指定的范圍表中。
func IsControl
func IsControl(r rune) bool
IsControl 報告符文是否是控制角色。C（其他）Unicode 類別包含更多代碼點，例如代理; 使用 Is(C, r) 來測試它們。
func IsDigit
func IsDigit(r rune) bool
IsDigit 報告符文是否為十進(jìn)制數(shù)字。
func IsGraphic
func IsGraphic(r rune) bool
IsGraphic 報告符文是否被Unicode定義為Graphic。這些字符包括類別 L，M，N，P，S，Zs 中的字母，標(biāo)記，數(shù)字，標(biāo)點，符號和空格。
func IsLetter
func IsLetter(r rune) bool
IsLetter 報告符文是否為字母（L類）。
func IsLower
func IsLower(r rune) bool
IsLower 報告符文是否是小寫字母。
func IsMark
func IsMark(r rune) bool
IsMark 報告符文是否為標(biāo)記符（M類）。
func IsNumber
func IsNumber(r rune) bool
IsNumber 報告符文是否是一個數(shù)字（類別N）。
func IsOneOf
func IsOneOf(ranges []*RangeTable, r rune) bool
IsOneOf 報告符文是否是其中一個范圍的成員。函數(shù)“In”提供了更好的簽名，應(yīng)優(yōu)先使用 IsOneOf。
func IsPrint
func IsPrint(r rune) bool
IsPrint 報告符文是否被 Go 定義為可打印。這些字符包括類別 L，M，N，P，S 和 ASCII 空格字符中的字母，標(biāo)記，數(shù)字，標(biāo)點，符號和 ASCII 空格字符。除了唯一的空格字符是 ASCII 空格 U+0020 之外，該分類與 IsGraphic 相同。
func IsPunct
func IsPunct(r rune) bool
IsPunct 報告符文是否是 Unicode 標(biāo)點符號（類別 P）。
func IsSpace
func IsSpace(r rune) bool
IsSpace 報告符文是否是由 Unicode 的空白屬性定義的空格字符; 在拉丁美洲1空間
'\t', '\n', '\v', '\f', '\r', ' ', U+0085 (NEL), U+00A0 (NBSP).
間距字符的其他定義由類別 Z 和屬性 Pattern_White_Space 設(shè)置。
func IsSymbol
func IsSymbol(r rune) bool
IsSymbol 報告符文是否是一個象征性的特征。
func IsTitle
func IsTitle(r rune) bool
IsTitle 報告符文是否是一個標(biāo)題大小寫字母。
func IsUpper
func IsUpper(r rune) bool
IsUpper 報告符文是否是大寫字母。
func SimpleFold
func SimpleFold(r rune) rune
SimpleFold 在 Unicode 定義的簡單大小寫折疊下迭代 Unicode 代碼點。在相當(dāng)于符文的代碼點（包括符文本身）中，SimpleFold返回最小的符文> r，否則最小的符文> = 0.如果r不是有效的 Unicode 代碼點，則 SimpleFold（r） 返回 r。
例如：
SimpleFold('A') = 'a'SimpleFold('a') = 'A'SimpleFold('K') = 'k'SimpleFold('k') = '\u212A' (Kelvin symbol, ?)SimpleFold('\u212A') = 'K'SimpleFold('1') = '1'SimpleFold(-2) = -2示例
package mainimport ("fmt""unicode")func main() {
fmt.Printf("%#U\n", unicode.SimpleFold('A')) // 'a'
fmt.Printf("%#U\n", unicode.SimpleFold('a')) // 'A'
fmt.Printf("%#U\n", unicode.SimpleFold('K')) // 'k'
fmt.Printf("%#U\n", unicode.SimpleFold('k')) // '\u212A' (Kelvin symbol, ?)
fmt.Printf("%#U\n", unicode.SimpleFold('\u212A')) // 'K'
fmt.Printf("%#U\n", unicode.SimpleFold('1')) // '1'}func To
func To(_case int, r rune) rune
將符號映射到指定的情況：UpperCase， LowerCase 或 TitleCase。
示例
package mainimport ("fmt""unicode")func main() {const lcG = 'g'
fmt.Printf("%#U\n", unicode.To(unicode.UpperCase, lcG))
fmt.Printf("%#U\n", unicode.To(unicode.LowerCase, lcG))
fmt.Printf("%#U\n", unicode.To(unicode.TitleCase, lcG))const ucG = 'G'
fmt.Printf("%#U\n", unicode.To(unicode.UpperCase, ucG))
fmt.Printf("%#U\n", unicode.To(unicode.LowerCase, ucG))
fmt.Printf("%#U\n", unicode.To(unicode.TitleCase, ucG))}func ToLower
func ToLower(r rune) rune
ToLower 將符文映射為小寫字母。
示例
package mainimport ("fmt""unicode")func main() {const ucG = 'G'
fmt.Printf("%#U\n", unicode.ToLower(ucG))}func ToTitle
func ToTitle(r rune) rune
ToTitle 將符文映射到標(biāo)題大小寫。
示例
package mainimport ("fmt""unicode")func main() {const ucG = 'g'
fmt.Printf("%#U\n", unicode.ToTitle(ucG))}func ToUpper
func ToUpper(r rune) rune
ToUpper 將符文映射為大寫。
示例
package mainimport ("fmt""unicode")func main() {const ucG = 'g'
fmt.Printf("%#U\n", unicode.ToUpper(ucG))}鍵入 CaseRange
CaseRange 表示簡單（一個代碼點到一個代碼點）大小寫轉(zhuǎn)換的一系列 Unicode 代碼點。范圍從 Lo 到 Hi 包含，固定步幅為 1. Deltas 是要添加到代碼點以達(dá)到該角色不同情況的代碼點的數(shù)字。他們可能是消極的。如果為零，則表示該角色處于相應(yīng)的情況。有一個特殊情況代表交替對應(yīng)的上和下對的序列。它與一個固定的 Delta 相似
{UpperLower, UpperLower, UpperLower}常數(shù) UpperLower 具有不可能的增量值。
type CaseRange struct {
Lo uint32
Hi uint32
Delta d}鍵入 Range16
Range16 表示一系列16位 Unicode 代碼點。范圍從 Lo 到 Hi 包含并且具有指定的步幅。
type Range16 struct {
Lo uint16
Hi uint16
Stride uint16}鍵入 Range32
Range32 代表一系列 Unicode 代碼點，當(dāng)一個或多個值不適合16位時使用。范圍從 Lo 到 Hi 包含并且具有指定的步幅。 Lo 和 Hi 必須始終> = 1 << 16。
type Range32 struct {
Lo uint32
Hi uint32
Stride uint32}鍵入 RangeTable
RangeTable 通過列出集合中代碼點的范圍來定義一組 Unicode 代碼點。范圍在兩個切片中列出以節(jié)省空間：16位范圍片段和32位范圍片段。這兩個切片必須按排序順序且不重疊。另外，R32 應(yīng)該只包含 > = 0x10000（1 << 16） 的值。
type RangeTable struct {
R16 []Range16
R32 []Range32
LatinOffset int // number of entries in R16 with Hi <= MaxLatin1}鍵入 SpecialCase
SpecialCase 代表語言特定的案例映射，如土耳其語。SpecialCase 的方法自定義（通過覆蓋）標(biāo)準(zhǔn)映射。
type SpecialCase []CaseRange
var AzeriCase SpecialCase = _TurkishCase
var TurkishCase SpecialCase = _TurkishCase
示例
package mainimport ("fmt""unicode")func main() {
t := unicode.TurkishCaseconst lci = 'i'
fmt.Printf("%#U\n", t.ToLower(lci))
fmt.Printf("%#U\n", t.ToTitle(lci))
fmt.Printf("%#U\n", t.ToUpper(lci))const uci = '?'
fmt.Printf("%#U\n", t.ToLower(uci))
fmt.Printf("%#U\n", t.ToTitle(uci))
fmt.Printf("%#U\n", t.ToUpper(uci))}func (SpecialCase) ToLower
func (special SpecialCase) ToLower(r rune) rune
ToLower 將符文映射為小寫，優(yōu)先考慮特殊映射。
func (SpecialCase) ToTitle
func (special SpecialCase) ToTitle(r rune) rune
ToTitle 將符文映射為標(biāo)題情況，優(yōu)先考慮特殊映射。
func (SpecialCase) ToUpper
func (special SpecialCase) ToUpper(r rune) rune
ToUpper 將符文映射為大寫，優(yōu)先考慮特殊映射。
錯誤
? 沒有完整大小寫折疊的機(jī)制，也就是說，對于在輸入或輸出中涉及多個符文的字符。
子目錄
名稱 | 概要 |
|---|
| .. |
| utf16 | 打包 utf16 實現(xiàn) UTF-16 序列的編碼和解碼。|
| utf8 | 打包 utf8 實現(xiàn)函數(shù)和常量以支持以 UTF-8 編碼的文本。|