0  0x00 NUL空

11 0x0b VT垂直制表

22 0x16 SYN空轉(zhuǎn)同步

1  0x01 SOH標(biāo)題開始

12 0x0c FF走紙控制

23 0x17 ETB信息組傳送結(jié)束

2  0x02 STX正文開始

13 0x0d CR回車

24 0x18 CAN作廢

3  0x03 ETX正文結(jié)束

14 0x0e SO移位輸出

25 0x19 EM紙盡

4  0x04 EOY傳輸結(jié)束

15 0x0f SI移位輸入

26 0x1a SUB換置

5  0x05 ENQ詢問字符

16 0x10 DLE空格

27 0x1b ESC換碼

6  0x06 ACK承認(rèn)

17 0x11 DC1設(shè)備控制1

28 0x1c FS文字分隔符

7  0x07 BEL報(bào)警

18 0x12 DC2設(shè)備控制2

29 0x1d GS組分隔符

8  0x08 BS退一格

19 0x13 DC3設(shè)備控制3

30 0x1e RS記錄分隔符

9  0x09 HT橫向列表

20 0x14 DC4設(shè)備控制4

31 0x1f US單元分隔符

10 0x0a LF換行

21 0x15 NAK否定

127 0xff DEL刪除

編碼方式

big endian

little endian

UTF-16 big endian

FE FF

FF FE（Windows）

UTF-32 bign endian

00 00 FE FF

FF FE 00 00

UTF-8 little endian （gcc）

EF BB BF

EF BB BF

源代碼的編碼

編譯器

結(jié)果

GBK

cl

1

*

mingw-g++

1

*

g++

1

UTF-8(不帶BOM)

cl

2

mingw-g++

2

g++

2

*

UTF-8(帶BOM)

cl

1

mingw-g++

2

g++

編譯失敗

源文件編碼

編譯器

"我是中文" 內(nèi)存中編碼

GBK

cl

成功轉(zhuǎn)成Unicode

gcc

失敗，編譯不過

UTF8(帶BOM)

cl

成功

gcc

成功

UTF8（不帶BOM）

cl

失敗，輸出亂碼

gcc

成功

// 下面的代碼在簡體中文Windows下的MVSC2010下，無法通過編譯

// 說明windows下源代碼保存需要BOM，不帶BOM直接當(dāng)做GBK

// utf8 encoded c++ source file without BOM

#include<iostream>

int main()

{

std::cout<<sizeof("不帶BOM是不給轉(zhuǎn)換編碼的，而使用了BOM后，會(huì)自動(dòng)將UTF-8編碼轉(zhuǎn)換成GBK。");

return0;

}

extern int utf8_mbtowc(__u16*, const __u8*, int);

extern int utf8_mbstowcs(__u16*, const __u8*, int);

extern int utf8_wctomb(__u8*, __u16,int);

extern int utf8_wcstombs(__u8*, const __u16*, int);

#include<iconv.h>

#pragma comment(lib,"iconv.lib")

int code_convert(char*from_charset,char*to_charset,constchar*inbuf, size_t inlen,char*outbuf, size_t outlen)

{

iconv_t cd;

constchar**pin=&inbuf;

char**pout=&outbuf;

cd =iconv_open(to_charset,from_charset);

if (cd==0)

return-1;

memset(outbuf,0,outlen);

if (iconv(cd, pin,&inlen,pout, &outlen)==-1)

return-1;

iconv_close(cd);

return0;

}

/* UTF-8 to GBK */

int u2g(constchar*inbuf, size_t inlen, char*outbuf, size_t outlen)

{

return code_convert("UTF-8","GBK",inbuf,inlen,outbuf,outlen);

}

/* GBK to UTF-8 */

int g2u(constchar*inbuf, size_t inlen, char*outbuf, size_t outlen)

{

return code_convert("GBK","UTF-8", inbuf, inlen, outbuf, outlen);

}

European languages

ASCII, ISO-8859-{1,2,3,4,5,7,9,10,13,14,15,16}, KOI8-R, KOI8-U, KOI8-RU,CP{1250,1251,1252,1253,1254,1257}, CP{850,866,1131}, Mac{Roman,CentralEurope,Iceland,Croatian,Romania}, Mac{Cyrillic,Ukraine,Greek,Turkish}, Macintosh

Semitic languages

ISO-8859-{6,8}, CP{1255,1256}, CP862, Mac{Hebrew,Arabic}

Japanese

EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP, ISO-2022-JP-2, ISO-2022-JP-1

Chinese

EUC-CN, HZ, GBK, CP936, GB18030, EUC-TW,BIG5, CP950, BIG5-HKSCS, BIG5-HKSCS:2001, BIG5-HKSCS:1999, ISO-2022-CN, ISO-2022-CN-EXT

Korean

EUC?KR, CP949, ISO?2022?KR, JOHAB

Armenian

ARMSCII-8

Georgian

Georgian-Academy, Georgian-PS

Tajik

KOI8-T

Kazakh

PT154, RK1048

Thai

TIS-620, CP874, MacThai

Laotian

MuleLao-1, CP1133

Vietnamese

VISCII, TCVN, CP1258

Platform specifics

HP-ROMAN8, NEXTSTEP

Full Unicode

UTF-8,UCS-2, UCS-2BE,UCS-2LE,UCS-4, UCS-4BE, UCS-4LE,UTF-16, UTF-16BE, UTF-16LE,UTF-32, UTF-32BE, UTF-32LE,UTF-7,C99,JAVA

Full Unicode, in terms of uint16_t or uint32_t

UCS-2-INTERNAL, UCS-4-INTERNAL

(with machine dependent endianness and alignment)

Locale dependent, in terms of char or wchar_t

char, wchar_t

(with machine dependent endianness and alignment, and with semantics depending on the OS and the current LC_CTYPE locale facet)

When configured with the option --enable-extra-encodings,

it also provides support for a few extra encodings:

European languages

CP{437,737,775,852,853,855,857,858,860,861,863,865,869,1125}

Semitic languages

CP864

Japanese

EUC-JISX0213, Shift_JISX0213, ISO-2022-JP-3

Chinese

BIG5-2003 (experimental)

Turkmen

TDS565

Platform specifics

ATARIST, RISCOS-LATIN1

The empty encoding name "" is equivalent to"char":

it denotes the locale dependent character encoding.

int ToUCS(unsignedchar*p,wchar_t* pUCS,int codepage)

{

int len=0;

if(pUCS== NULL || p == NULL)

return-1;

len =MultiByteToWideChar(codepage,0,p,-1,NULL,0);

MultiByteToWideChar(codepage,0,p,-1,pUCS,len);

return len;

}

int UCSTo(wchar_t* pUCS,char*p,int codepage)

{

int len=0;

if(pUCS== NULL || pBIG5 == NULL)

return-1;

len =WideCharToMultiByte(codepage,0,pUCS,-1,NULL,0,NULL,NULL);

WideCharToMultiByte(codepage,0,pUCS,-1,p,len,NULL,NULL);

len--;

return len;

}

WINBASEAPI int WINAPI

MultiByteToWideChar(

    __in UINT     CodePage,

    __in DWORD    dwFlags,

    __in_bcount(cbMultiByte) LPCSTR   lpMultiByteStr,

    __in int      cbMultiByte,

    __out_ecount_opt(cchWideChar) __transfer(lpMultiByteStr) LPWSTR  lpWideCharStr,

    __in int      cchWideChar);

WINBASEAPI int WINAPI

WideCharToMultiByte(

    __in UINT     CodePage,

    __in DWORD    dwFlags,

    __in_ecount(cchWideChar) LPCWSTR  lpWideCharStr,

    __in int      cchWideChar,

    __out_bcount_opt(cbMultiByte) __transfer(lpWideCharStr) LPSTR   lpMultiByteStr,

    __in int      cbMultiByte,

    __in_opt LPCSTR   lpDefaultChar,

    __out_opt LPBOOL  lpUsedDefaultChar);

Bit

Code page

Description

ANSI

0

1252

Latin 1

1

1250

Latin 2: Eastern Europe

2

1251

Cyrillic

3

1253

Greek

4

1254

Turkish

5

1255

Hebrew

6

1256

Arabic

7

1257

Baltic

8

1258

VietNam

9 - 15

Reserved for ANSI

ANSI and OEM

16

874

Thai

17

932

Japanese, Shift-JIS

18

936

Chinese: Simplified chars—PRC and Singapore

ASCII、GB2312、GBK到GB18030 兼容

19

949

Korean Unified Hangeul Code (Hangeul TongHabHyung Code)

20

950

Chinese: Traditional chars—Hong Kong SAR, PRC and Taiwan

BIG5

21

1361

Korean (Johab)

22 - 29

Reserved for alternate ANSI and OEM

30 - 31

Reserved by system.

OEM

32 - 46

Reserved for OEM

47

1258

VietNam

48

869

IBM Greek

49

866

MS-DOS Russian

50

865

MS-DOS Nordic

51

864

Arabic

52

863

MS-DOS Canadian French

53

862

Hebrew

54

861

MS-DOS Icelandic

55

860

MS-DOS Portuguese

56

857

IBM Turkish

57

855

IBM Cyrillic; primarily Russian

58

852

Latin 2

59

775

Baltic

60

737

Greek; former 437 G

61

708

Arabic; ASMO 708

62

850

Western European/Latin 1

63

437

US

#include<unicode/ucnv.h>

#ifdef _WIN32

#pragmacomment(lib,"icuuc.lib")

#endif

//返回0為成功，錯(cuò)誤代碼定義見后面

intconvert(constchar* toConverterName,

constchar* fromConverterName,

char* target,

int32_t targetCapacity,

constchar* source,

int32_t sourceLength)

{

UErrorCode errorcode= U_ZERO_ERROR;

ucnv_convert(toConverterName,fromConverterName,target, targetCapacity, source, sourceLength,&errorcode );

return errorcode;

}

int _tmain(int argc, _TCHAR* argv[])

{

wchar_t aaa[]= L"中國人的系統(tǒng)上123323";

int alen= wcslen(aaa);

int blen=alen*2+sizeof(int);

char*abuff=newchar[blen];

int result= convert( "gb2312", "utf-16le", abuff, blen, (constchar*)aaa, alen);

cout<< abuff<< endl<<strlen(abuff)<<endl;

delete []abuff;

return0;

}

typedef enum UErrorCode{ 

    /* The ordering of U_ERROR_INFO_START Vs U_USING_FALLBACK_WARNING looks weird

     * and is that way because VC++ debugger displays first encountered constant,

     * which is not the what the code is used for

     */ 

U_USING_FALLBACK_WARNING  = -128,   /**< A resource bundle lookup returned a fallback result (not an error) */ 

U_ERROR_WARNING_START     = -128,   /**< Start of information results (semantically successful) */ 

U_USING_DEFAULT_WARNING   = -127,   /**< A resource bundle lookup returned a result from the root locale (not an error) */ 

U_SAFECLONE_ALLOCATED_WARNING = -126, /**< A SafeClone operation required allocating memory (informational only) */ 

U_STATE_OLD_WARNING       = -125,   /**< ICU has to use compatibility layer to construct the service. Expect performance/memory usage degradation. Consider upgrading */ 

U_STRING_NOT_TERMINATED_WARNING = -124,/**< An output string could not be NUL-terminated because output length==destCapacity. */ 

U_SORT_KEY_TOO_SHORT_WARNING = -123, /**< Number of levels requested in getBound is higher than the number of levels in the sort key */ 

U_AMBIGUOUS_ALIAS_WARNING = -122,   /**< This converter alias can go to different converter implementations */ 

U_DIFFERENT_UCA_VERSION = -121,     /**< ucol_open encountered a mismatch between UCA version and collator image version, so the collator was constructed from rules. No impact to further function */ 

U_PLUGIN_CHANGED_LEVEL_WARNING = -120, /**< A plugin caused a level change. May not be an error, but later plugins may not load. */ 

U_ERROR_WARNING_LIMIT,              /**< This must always be the last warning value to indicate the limit for UErrorCode warnings (last warning code +1) */ 

    U_ZERO_ERROR              =  0,     /**< No error, no warning. */ 

    U_ILLEGAL_ARGUMENT_ERROR  =  1,     /**< Start of codes indicating failure */ 

    U_MISSING_RESOURCE_ERROR  =  2,     /**< The requested resource cannot be found */ 

    U_INVALID_FORMAT_ERROR    =  3,     /**< Data format is not what is expected */ 

    U_FILE_ACCESS_ERROR       =  4,     /**< The requested file cannot be found */ 

    U_INTERNAL_PROGRAM_ERROR  =  5,     /**< Indicates a bug in the library code */ 

    U_MESSAGE_PARSE_ERROR     =  6,     /**< Unable to parse a message (message format) */ 

    U_MEMORY_ALLOCATION_ERROR =  7,     /**< Memory allocation error */ 

    U_INDEX_OUTOFBOUNDS_ERROR =  8,     /**< Trying to access the index that is out of bounds */ 

    U_PARSE_ERROR             =  9,     /**< Equivalent to Java ParseException */ 

    U_INVALID_CHAR_FOUND      = 10,     /**< Character conversion: Unmappable input sequence. In other APIs: Invalid character. */ 

    U_TRUNCATED_CHAR_FOUND    = 11,     /**< Character conversion: Incomplete input sequence. */ 

    U_ILLEGAL_CHAR_FOUND      = 12,     /**< Character conversion: Illegal input sequence/combination of input units. */ 

    U_INVALID_TABLE_FORMAT    = 13,     /**< Conversion table file found, but corrupted */ 

    U_INVALID_TABLE_FILE      = 14,     /**< Conversion table file not found */ 

    U_BUFFER_OVERFLOW_ERROR   = 15,     /**< A result would not fit in the supplied buffer */ 

    U_UNSUPPORTED_ERROR       = 16,     /**< Requested operation not supported in current context */ 

    U_RESOURCE_TYPE_MISMATCH  = 17,     /**< an operation is requested over a resource that does not support it */ 

    U_ILLEGAL_ESCAPE_SEQUENCE = 18,     /**< ISO-2022 illlegal escape sequence */ 

    U_UNSUPPORTED_ESCAPE_SEQUENCE = 19, /**< ISO-2022 unsupported escape sequence */ 

    U_NO_SPACE_AVAILABLE      = 20,     /**< No space available for in-buffer expansion for Arabic shaping */ 

    U_CE_NOT_FOUND_ERROR      = 21,     /**< Currently used only while setting variable top, but can be used generally */ 

    U_PRIMARY_TOO_LONG_ERROR  = 22,     /**< User tried to set variable top to a primary that is longer than two bytes */ 

    U_STATE_TOO_OLD_ERROR     = 23,     /**< ICU cannot construct a service from this state, as it is no longer supported */ 

    U_TOO_MANY_ALIASES_ERROR  = 24,     /**< There are too many aliases in the path to the requested resource.

                                             It is very possible that a circular alias definition has occured */ 

    U_ENUM_OUT_OF_SYNC_ERROR  = 25,     /**< UEnumeration out of sync with underlying collection */ 

    U_INVARIANT_CONVERSION_ERROR = 26,  /**< Unable to convert a UChar* string to char* with the invariant converter. */ 

    U_INVALID_STATE_ERROR     = 27,     /**< Requested operation can not be completed with ICU in its current state */ 

    U_COLLATOR_VERSION_MISMATCH = 28,   /**< Collator version is not compatible with the base version */ 

    U_USELESS_COLLATOR_ERROR  = 29,     /**< Collator is options only and no base is specified */ 

    U_NO_WRITE_PERMISSION     = 30,     /**< Attempt to modify read-only or constant data. */ 

U_STANDARD_ERROR_LIMIT,             /**< This must always be the last value to indicate the limit for standard errors */ 

    /*

     * the error code range 0x10000 0x10100 are reserved for Transliterator

     */ 

    U_BAD_VARIABLE_DEFINITION=0x10000,/**< Missing '</p> or duplicate variable name */ 

    U_PARSE_ERROR_START = 0x10000,    /**< Start of Transliterator errors */ 

    U_MALFORMED_RULE,                 /**< Elements of a rule are misplaced */ 

    U_MALFORMED_SET,                  /**< A UnicodeSet pattern is invalid*/ 

    U_MALFORMED_SYMBOL_REFERENCE,     /**< UNUSED as of ICU 2.4 */ 

    U_MALFORMED_UNICODE_ESCAPE,       /**< A Unicode escape pattern is invalid*/ 

    U_MALFORMED_VARIABLE_DEFINITION,  /**< A variable definition is invalid */ 

    U_MALFORMED_VARIABLE_REFERENCE,   /**< A variable reference is invalid */ 

    U_MISMATCHED_SEGMENT_DELIMITERS,  /**< UNUSED as of ICU 2.4 */ 

    U_MISPLACED_ANCHOR_START,         /**< A start anchor appears at an illegal position */ 

    U_MISPLACED_CURSOR_OFFSET,        /**< A cursor offset occurs at an illegal position */ 

    U_MISPLACED_QUANTIFIER,           /**< A quantifier appears after a segment close delimiter */ 

    U_MISSING_OPERATOR,               /**< A rule contains no operator */ 

    U_MISSING_SEGMENT_CLOSE,          /**< UNUSED as of ICU 2.4 */ 

    U_MULTIPLE_ANTE_CONTEXTS,         /**< More than one ante context */ 

    U_MULTIPLE_CURSORS,               /**< More than one cursor */ 

    U_MULTIPLE_POST_CONTEXTS,         /**< More than one post context */ 

    U_TRAILING_BACKSLASH,             /**< A dangling backslash */ 

    U_UNDEFINED_SEGMENT_REFERENCE,    /**< A segment reference does not correspond to a defined segment */ 

    U_UNDEFINED_VARIABLE,             /**< A variable reference does not correspond to a defined variable */ 

    U_UNQUOTED_SPECIAL,               /**< A special character was not quoted or escaped */ 

    U_UNTERMINATED_QUOTE,             /**< A closing single quote is missing */ 

    U_RULE_MASK_ERROR,                /**< A rule is hidden by an earlier more general rule */ 

    U_MISPLACED_COMPOUND_FILTER,      /**< A compound filter is in an invalid location */ 

    U_MULTIPLE_COMPOUND_FILTERS,      /**< More than one compound filter */ 

    U_INVALID_RBT_SYNTAX,             /**< A "::id" rule was passed to the RuleBasedTransliterator parser */ 

    U_INVALID_PROPERTY_PATTERN,       /**< UNUSED as of ICU 2.4 */ 

    U_MALFORMED_PRAGMA,               /**< A 'use' pragma is invlalid */ 

    U_UNCLOSED_SEGMENT,               /**< A closing ')' is missing */ 

    U_ILLEGAL_CHAR_IN_SEGMENT,        /**< UNUSED as of ICU 2.4 */ 

    U_VARIABLE_RANGE_EXHAUSTED,       /**< Too many stand-ins generated for the given variable range */ 

    U_VARIABLE_RANGE_OVERLAP,         /**< The variable range overlaps characters used in rules */ 

    U_ILLEGAL_CHARACTER,              /**< A special character is outside its allowed context */ 

    U_INTERNAL_TRANSLITERATOR_ERROR,  /**< Internal transliterator system error */ 

    U_INVALID_ID,                     /**< A "::id" rule specifies an unknown transliterator */ 

    U_INVALID_FUNCTION,               /**< A "&fn()" rule specifies an unknown transliterator */ 

    U_PARSE_ERROR_LIMIT,              /**< The limit for Transliterator errors */ 

    /*

     * the error code range 0x10100 0x10200 are reserved for formatting API parsing error

     */ 

    U_UNEXPECTED_TOKEN=0x10100,       /**< Syntax error in format pattern */ 

    U_FMT_PARSE_ERROR_START=0x10100,  /**< Start of format library errors */ 

    U_MULTIPLE_DECIMAL_SEPARATORS,    /**< More than one decimal separator in number pattern */ 

    U_MULTIPLE_DECIMAL_SEPERATORS = U_MULTIPLE_DECIMAL_SEPARATORS, /**< Typo: kept for backward compatibility. Use U_MULTIPLE_DECIMAL_SEPARATORS */ 

    U_MULTIPLE_EXPONENTIAL_SYMBOLS,   /**< More than one exponent symbol in number pattern */ 

    U_MALFORMED_EXPONENTIAL_PATTERN,  /**< Grouping symbol in exponent pattern */ 

    U_MULTIPLE_PERCENT_SYMBOLS,       /**< More than one percent symbol in number pattern */ 

    U_MULTIPLE_PERMILL_SYMBOLS,       /**< More than one permill symbol in number pattern */ 

    U_MULTIPLE_PAD_SPECIFIERS,        /**< More than one pad symbol in number pattern */ 

    U_PATTERN_SYNTAX_ERROR,           /**< Syntax error in format pattern */ 

    U_ILLEGAL_PAD_POSITION,           /**< Pad symbol misplaced in number pattern */ 

    U_UNMATCHED_BRACES,               /**< Braces do not match in message pattern */ 

    U_UNSUPPORTED_PROPERTY,           /**< UNUSED as of ICU 2.4 */ 

    U_UNSUPPORTED_ATTRIBUTE,          /**< UNUSED as of ICU 2.4 */ 

    U_ARGUMENT_TYPE_MISMATCH,         /**< Argument name and argument index mismatch in MessageFormat functions */ 

    U_DUPLICATE_KEYWORD,              /**< Duplicate keyword in PluralFormat */ 

    U_UNDEFINED_KEYWORD,              /**< Undefined Plural keyword */ 

    U_DEFAULT_KEYWORD_MISSING,        /**< Missing DEFAULT rule in plural rules */ 

    U_DECIMAL_NUMBER_SYNTAX_ERROR,    /**< Decimal number syntax error */ 

    U_FMT_PARSE_ERROR_LIMIT,          /**< The limit for format library errors */ 

    /*

     * the error code range 0x10200 0x102ff are reserved for Break Iterator related error

     */ 

    U_BRK_INTERNAL_ERROR=0x10200,          /**< An internal error (bug) was detected.             */ 

    U_BRK_ERROR_START=0x10200,             /**< Start of codes indicating Break Iterator failures */ 

    U_BRK_HEX_DIGITS_EXPECTED,             /**< Hex digits expected as part of a escaped char in a rule. */ 

    U_BRK_SEMICOLON_EXPECTED,              /**< Missing ';' at the end of a RBBI rule.            */ 

    U_BRK_RULE_SYNTAX,                     /**< Syntax error in RBBI rule.                        */ 

    U_BRK_UNCLOSED_SET,                    /**< UnicodeSet witing an RBBI rule missing a closing ']'.  */ 

    U_BRK_ASSIGN_ERROR,                    /**< Syntax error in RBBI rule assignment statement.   */ 

    U_BRK_VARIABLE_REDFINITION,            /**< RBBI rule $Variable redefined.                    */ 

    U_BRK_MISMATCHED_PAREN,                /**< Mis-matched parentheses in an RBBI rule.          */ 

    U_BRK_NEW_LINE_IN_QUOTED_STRING,       /**< Missing closing quote in an RBBI rule.            */ 

    U_BRK_UNDEFINED_VARIABLE,              /**< Use of an undefined $Variable in an RBBI rule.    */ 

    U_BRK_INIT_ERROR,                      /**< Initialization failure.  Probable missing ICU Data. */ 

    U_BRK_RULE_EMPTY_SET,                  /**< Rule contains an empty Unicode Set.               */ 

    U_BRK_UNRECOGNIZED_OPTION,             /**< !!option in RBBI rules not recognized.            */ 

    U_BRK_MALFORMED_RULE_TAG,              /**< The {nnn} tag on a rule is mal formed             */ 

    U_BRK_ERROR_LIMIT,                     /**< This must always be the last value to indicate the limit for Break Iterator failures */ 

    /*

     * The error codes in the range 0x10300-0x103ff are reserved for regular expression related errrs

     */ 

    U_REGEX_INTERNAL_ERROR=0x10300,       /**< An internal error (bug) was detected.              */ 

    U_REGEX_ERROR_START=0x10300,          /**< Start of codes indicating Regexp failures          */ 

    U_REGEX_RULE_SYNTAX,                  /**< Syntax error in regexp pattern.                    */ 

    U_REGEX_INVALID_STATE,                /**< RegexMatcher in invalid state for requested operation */ 

    U_REGEX_BAD_ESCAPE_SEQUENCE,          /**< Unrecognized backslash escape sequence in pattern  */ 

    U_REGEX_PROPERTY_SYNTAX,              /**< Incorrect Unicode property                         */ 

    U_REGEX_UNIMPLEMENTED,                /**< Use of regexp feature that is not yet implemented. */ 

    U_REGEX_MISMATCHED_PAREN,             /**< Incorrectly nested parentheses in regexp pattern.  */ 

    U_REGEX_NUMBER_TOO_BIG,               /**< Decimal number is too large.                       */ 

    U_REGEX_BAD_INTERVAL,                 /**< Error in {min,max} interval                        */ 

    U_REGEX_MAX_LT_MIN,                   /**< In {min,max}, max is less than min.                */ 

    U_REGEX_INVALID_BACK_REF,             /**< Back-reference to a non-existent capture group.    */ 

    U_REGEX_INVALID_FLAG,                 /**< Invalid value for match mode flags.                */ 

    U_REGEX_LOOK_BEHIND_LIMIT,            /**< Look-Behind pattern matches must have a bounded maximum length.    */ 

    U_REGEX_SET_CONTAINS_STRING,          /**< Regexps cannot have UnicodeSets containing strings.*/ 

    U_REGEX_OCTAL_TOO_BIG,                /**< Octal character constants must be <= 0377.         */ 

    U_REGEX_MISSING_CLOSE_BRACKET,        /**< Missing closing bracket on a bracket expression.   */ 

    U_REGEX_INVALID_RANGE,                /**< In a character range [x-y], x is greater than y.   */ 

    U_REGEX_STACK_OVERFLOW,               /**< Regular expression backtrack stack overflow.       */ 

    U_REGEX_TIME_OUT,                     /**< Maximum allowed match time exceeded                */ 

    U_REGEX_STOPPED_BY_CALLER,            /**< Matching operation aborted by user callback fn.    */ 

    U_REGEX_ERROR_LIMIT,                  /**< This must always be the last value to indicate the limit for regexp errors */ 

    /*

     * The error code in the range 0x10400-0x104ff are reserved for IDNA related error codes

     */ 

    U_IDNA_PROHIBITED_ERROR=0x10400, 

    U_IDNA_ERROR_START=0x10400, 

    U_IDNA_UNASSIGNED_ERROR, 

    U_IDNA_CHECK_BIDI_ERROR, 

    U_IDNA_STD3_ASCII_RULES_ERROR, 

    U_IDNA_ACE_PREFIX_ERROR, 

    U_IDNA_VERIFICATION_ERROR, 

    U_IDNA_LABEL_TOO_LONG_ERROR, 

    U_IDNA_ZERO_LENGTH_LABEL_ERROR, 

    U_IDNA_DOMAIN_NAME_TOO_LONG_ERROR, 

    U_IDNA_ERROR_LIMIT, 

    /*

     * Aliases for StringPrep

     */ 

    U_STRINGPREP_PROHIBITED_ERROR = U_IDNA_PROHIBITED_ERROR, 

    U_STRINGPREP_UNASSIGNED_ERROR = U_IDNA_UNASSIGNED_ERROR, 

    U_STRINGPREP_CHECK_BIDI_ERROR = U_IDNA_CHECK_BIDI_ERROR, 

    /*

     * The error code in the range 0x10500-0x105ff are reserved for Plugin related error codes

     */ 

    U_PLUGIN_ERROR_START=0x10500,         /**< Start of codes indicating plugin failures */ 

    U_PLUGIN_TOO_HIGH=0x10500,            /**< The plugin's level is too high to be loaded right now. */ 

    U_PLUGIN_DIDNT_SET_LEVEL,             /**< The plugin didn't call uplug_setPlugLevel in response to a QUERY */ 

    U_PLUGIN_ERROR_LIMIT,                 /**< This must always be the last value to indicate the limit for plugin errors */ 

    U_ERROR_LIMIT=U_PLUGIN_ERROR_LIMIT      /**< This must always be the last value to indicate the limit for UErrorCode (last error code +1) */ 

} UErrorCode;