FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
basictz.h	8913	0644	edit dl rm
bms.h	8664	0644	edit dl rm
bmsearch.h	7316	0644	edit dl rm
brkiter.h	23001	0644	edit dl rm
bytestream.h	8531	0644	edit dl rm
calendar.h	90659	0644	edit dl rm
caniter.h	7288	0644	edit dl rm
chariter.h	24186	0644	edit dl rm
choicfmt.h	29528	0644	edit dl rm
coleitr.h	12990	0644	edit dl rm
coll.h	48468	0644	edit dl rm
colldata.h	11957	0644	edit dl rm
curramt.h	3659	0644	edit dl rm
currpinf.h	7061	0644	edit dl rm
currunit.h	3057	0644	edit dl rm
datefmt.h	27946	0644	edit dl rm
dbbi.h	966	0644	edit dl rm
dcfmtsym.h	14040	0644	edit dl rm
decimfmt.h	88612	0644	edit dl rm
docmain.h	6003	0644	edit dl rm
dtfmtsym.h	26145	0644	edit dl rm
dtintrv.h	3734	0644	edit dl rm
dtitvfmt.h	39700	0644	edit dl rm
dtitvinf.h	18704	0644	edit dl rm
dtptngen.h	17303	0644	edit dl rm
dtrule.h	8718	0644	edit dl rm
errorcode.h	4361	0644	edit dl rm
fieldpos.h	8713	0644	edit dl rm
fmtable.h	18794	0644	edit dl rm
format.h	12083	0644	edit dl rm
gregocal.h	33797	0644	edit dl rm
locid.h	30241	0644	edit dl rm
measfmt.h	1897	0644	edit dl rm
measunit.h	1635	0644	edit dl rm
measure.h	3321	0644	edit dl rm
msgfmt.h	39435	0644	edit dl rm
normlzr.h	30337	0644	edit dl rm
numfmt.h	33987	0644	edit dl rm
numsys.h	5004	0644	edit dl rm
parseerr.h	3044	0644	edit dl rm
parsepos.h	5468	0644	edit dl rm
platform.h	9961	0644	edit dl rm
plurfmt.h	23079	0644	edit dl rm
plurrule.h	9901	0644	edit dl rm
ppalmos.h	6992	0644	edit dl rm
putil.h	6686	0644	edit dl rm
pwin32.h	8668	0644	edit dl rm
rbbi.h	26993	0644	edit dl rm
rbnf.h	45681	0644	edit dl rm
rbtz.h	15695	0644	edit dl rm
regex.h	52316	0644	edit dl rm
rep.h	9559	0644	edit dl rm
resbund.h	18130	0644	edit dl rm
schriter.h	6293	0644	edit dl rm
search.h	22357	0644	edit dl rm
simpletz.h	46179	0644	edit dl rm
smpdtfmt.h	48325	0644	edit dl rm
sortkey.h	11111	0644	edit dl rm
std_string.h	1769	0644	edit dl rm
strenum.h	9888	0644	edit dl rm
stringpiece.h	5484	0644	edit dl rm
stsearch.h	22287	0644	edit dl rm
symtable.h	4199	0644	edit dl rm
tblcoll.h	38199	0644	edit dl rm
timezone.h	34584	0644	edit dl rm
tmunit.h	3454	0644	edit dl rm
tmutamt.h	4787	0644	edit dl rm
tmutfmt.h	8669	0644	edit dl rm
translit.h	54780	0644	edit dl rm
tzrule.h	36057	0644	edit dl rm
tztrans.h	6101	0644	edit dl rm
ubidi.h	83092	0644	edit dl rm
ubrk.h	17688	0644	edit dl rm
ucal.h	40177	0644	edit dl rm
ucasemap.h	16420	0644	edit dl rm
ucat.h	5371	0644	edit dl rm
uchar.h	111062	0644	edit dl rm
uchriter.h	13132	0644	edit dl rm
uclean.h	11855	0644	edit dl rm
ucnv.h	83111	0644	edit dl rm
ucnvsel.h	5630	0644	edit dl rm
ucnv_cb.h	6635	0644	edit dl rm
ucnv_err.h	21375	0644	edit dl rm
ucol.h	48826	0644	edit dl rm
ucoleitr.h	12356	0644	edit dl rm
uconfig.h	6035	0644	edit dl rm
ucsdet.h	12464	0644	edit dl rm
ucurr.h	11572	0644	edit dl rm
udat.h	34496	0644	edit dl rm
udata.h	14265	0644	edit dl rm
udatpg.h	18715	0644	edit dl rm
udeprctd.h	2284	0644	edit dl rm
udraft.h	7600	0644	edit dl rm
uenum.h	5796	0644	edit dl rm
uidna.h	15918	0644	edit dl rm
uintrnal.h	15752	0644	edit dl rm
uiter.h	23234	0644	edit dl rm
uloc.h	44548	0644	edit dl rm
ulocdata.h	9739	0644	edit dl rm
umachine.h	11360	0644	edit dl rm
umisc.h	1255	0644	edit dl rm
umsg.h	26076	0644	edit dl rm
unifilt.h	3770	0644	edit dl rm
unifunct.h	3966	0644	edit dl rm
unimatch.h	6071	0644	edit dl rm
unirepl.h	3290	0644	edit dl rm
uniset.h	61771	0644	edit dl rm
unistr.h	161321	0644	edit dl rm
unorm.h	23621	0644	edit dl rm
unum.h	32145	0644	edit dl rm
uobject.h	11393	0644	edit dl rm
uobslete.h	852	0644	edit dl rm
uregex.h	43948	0644	edit dl rm
urename.h	92538	0644	edit dl rm
urep.h	5394	0644	edit dl rm
ures.h	36348	0644	edit dl rm
uscript.h	11360	0644	edit dl rm
usearch.h	34223	0644	edit dl rm
uset.h	39868	0644	edit dl rm
usetiter.h	9606	0644	edit dl rm
ushape.h	17907	0644	edit dl rm
uspoof.h	38752	0644	edit dl rm
usprep.h	7750	0644	edit dl rm
ustdio.h	35333	0644	edit dl rm
ustream.h	1891	0644	edit dl rm
ustring.h	69383	0644	edit dl rm
usystem.h	1925	0644	edit dl rm
utext.h	58394	0644	edit dl rm
utf.h	8273	0644	edit dl rm
utf8.h	20512	0644	edit dl rm
utf16.h	18776	0644	edit dl rm
utf32.h	653	0644	edit dl rm
utf_old.h	43646	0644	edit dl rm
utmscale.h	13689	0644	edit dl rm
utrace.h	13355	0644	edit dl rm
utrans.h	23129	0644	edit dl rm
utypes.h	34513	0644	edit dl rm
uversion.h	10902	0644	edit dl rm
vtzone.h	20048	0644	edit dl rm

Edit: /usr/include/unicode/uidna.h (15918B)

/*
 *******************************************************************************
 *
 *   Copyright (C) 2003-2007, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *******************************************************************************
 *   file name:  uidna.h
 *   encoding:   US-ASCII
 *   tab size:   8 (not used)
 *   indentation:4
 *
 *   created on: 2003feb1
 *   created by: Ram Viswanadha
 */

#ifndef __UIDNA_H__
#define __UIDNA_H__

#include "unicode/utypes.h"

#if !UCONFIG_NO_IDNA

#include "unicode/parseerr.h"
  
/**
 * \file
 * \brief C API: Internationalized Domain Names in Applications Tranformation
 *
 * UIDNA API implements the IDNA protocol as defined in the IDNA RFC 
 * (http://www.ietf.org/rfc/rfc3490.txt).
 * The RFC defines 2 operations: ToASCII and ToUnicode. Domain labels 
 * containing non-ASCII code points are required to be processed by
 * ToASCII operation before passing it to resolver libraries. Domain names
 * that are obtained from resolver libraries are required to be processed by
 * ToUnicode operation before displaying the domain name to the user.
 * IDNA requires that implementations process input strings with Nameprep
 * (http://www.ietf.org/rfc/rfc3491.txt), 
 * which is a profile of Stringprep (http://www.ietf.org/rfc/rfc3454.txt), 
 * and then with Punycode (http://www.ietf.org/rfc/rfc3492.txt). 
 * Implementations of IDNA MUST fully implement Nameprep and Punycode; 
 * neither Nameprep nor Punycode are optional.
 * The input and output of ToASCII and ToUnicode operations are Unicode 
 * and are designed to be chainable, i.e., applying ToASCII or ToUnicode operations
 * multiple times to an input string will yield the same result as applying the operation
 * once.
 * ToUnicode(ToUnicode(ToUnicode...(ToUnicode(string)))) == ToUnicode(string) 
 * ToASCII(ToASCII(ToASCII...(ToASCII(string))) == ToASCII(string).
 *
 */

/** 
 * Option to prohibit processing of unassigned codepoints in the input and
 * do not check if the input conforms to STD-3 ASCII rules.
 * 
 * @see  uidna_toASCII uidna_toUnicode
 * @stable ICU 2.6
 */
#define UIDNA_DEFAULT          0x0000
/** 
 * Option to allow processing of unassigned codepoints in the input
 * 
 * @see  uidna_toASCII uidna_toUnicode
 * @stable ICU 2.6
 */
#define UIDNA_ALLOW_UNASSIGNED 0x0001
/** 
 * Option to check if input conforms to STD-3 ASCII rules
 * 
 * @see  uidna_toASCII uidna_toUnicode
 * @stable ICU 2.6
 */
#define UIDNA_USE_STD3_RULES   0x0002

/**
 * This function implements the ToASCII operation as defined in the IDNA RFC.
 * This operation is done on single labels before sending it to something that expects
 * ASCII names. A label is an individual part of a domain name. Labels are usually
 * separated by dots; e.g." "www.example.com" is composed of 3 labels 
 * "www","example", and "com".
 *
 *
 * @param src Input UChar array containing label in Unicode.
 * @param srcLength Number of UChars in src, or -1 if NUL-terminated.
 * @param dest Output UChar array with ASCII (ACE encoded) label.
 * @param destCapacity Size of dest.
 * @param options A bit set of options:
 *
 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points
 * and do not use STD3 ASCII rules
 * If unassigned code points are found the operation fails with 
 * U_UNASSIGNED_ERROR error code.
 *
 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations
 * If this option is set, the unassigned code points are in the input 
 * are treated as normal Unicode code points.
 * 
 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions
 * If this option is set and the input does not satisfy STD3 rules, 
 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR
 *
 * @param parseError Pointer to UParseError struct to receive information on position 
 * of error if an error is encountered. Can be NULL.
 * @param status ICU in/out error code parameter.
 * U_INVALID_CHAR_FOUND if src contains
 * unmatched single surrogates.
 * U_INDEX_OUTOFBOUNDS_ERROR if src contains
 * too many code points.
 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
 * @return The length of the result string, if successful - or in case of a buffer overflow,
 * in which case it will be greater than destCapacity.
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
uidna_toASCII(const UChar* src, int32_t srcLength, 
 UChar* dest, int32_t destCapacity,
 int32_t options,
 UParseError* parseError,
 UErrorCode* status);

/**
 * This function implements the ToUnicode operation as defined in the IDNA RFC.
 * This operation is done on single labels before sending it to something that expects
 * Unicode names. A label is an individual part of a domain name. Labels are usually
 * separated by dots; for e.g." "www.example.com" is composed of 3 labels 
 * "www","example", and "com".
 *
 * @param src Input UChar array containing ASCII (ACE encoded) label.
 * @param srcLength Number of UChars in src, or -1 if NUL-terminated.
 * @param dest Output Converted UChar array containing Unicode equivalent of label.
 * @param destCapacity Size of dest.
 * @param options A bit set of options:
 * 
 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points
 * and do not use STD3 ASCII rules
 * If unassigned code points are found the operation fails with 
 * U_UNASSIGNED_ERROR error code.
 *
 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations
 * If this option is set, the unassigned code points are in the input 
 * are treated as normal Unicode code points. Note: This option is 
 * required on toUnicode operation because the RFC mandates 
 * verification of decoded ACE input by applying toASCII and comparing
 * its output with source
 *
 * 
 * 
 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions
 * If this option is set and the input does not satisfy STD3 rules, 
 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR
 *
 * @param parseError Pointer to UParseError struct to receive information on position 
 * of error if an error is encountered. Can be NULL.
 * @param status ICU in/out error code parameter.
 * U_INVALID_CHAR_FOUND if src contains
 * unmatched single surrogates.
 * U_INDEX_OUTOFBOUNDS_ERROR if src contains
 * too many code points.
 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
 * @return The length of the result string, if successful - or in case of a buffer overflow,
 * in which case it will be greater than destCapacity.
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
uidna_toUnicode(const UChar* src, int32_t srcLength,
 UChar* dest, int32_t destCapacity,
 int32_t options,
 UParseError* parseError,
 UErrorCode* status);

/**
 * Convenience function that implements the IDNToASCII operation as defined in the IDNA RFC.
 * This operation is done on complete domain names, e.g: "www.example.com". 
 * It is important to note that this operation can fail. If it fails, then the input 
 * domain name cannot be used as an Internationalized Domain Name and the application
 * should have methods defined to deal with the failure.
 * 
 * Note: IDNA RFC specifies that a conformant application should divide a domain name
 * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, 
 * and then convert. This function does not offer that level of granularity. The options once 
 * set will apply to all labels in the domain name
 *
 * @param src Input UChar array containing IDN in Unicode.
 * @param srcLength Number of UChars in src, or -1 if NUL-terminated.
 * @param dest Output UChar array with ASCII (ACE encoded) IDN.
 * @param destCapacity Size of dest.
 * @param options A bit set of options:
 * 
 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points
 * and do not use STD3 ASCII rules
 * If unassigned code points are found the operation fails with 
 * U_UNASSIGNED_CODE_POINT_FOUND error code.
 *
 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations
 * If this option is set, the unassigned code points are in the input 
 * are treated as normal Unicode code points.
 * 
 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions
 * If this option is set and the input does not satisfy STD3 rules, 
 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR
 * 
 * @param parseError Pointer to UParseError struct to receive information on position 
 * of error if an error is encountered. Can be NULL.
 * @param status ICU in/out error code parameter.
 * U_INVALID_CHAR_FOUND if src contains
 * unmatched single surrogates.
 * U_INDEX_OUTOFBOUNDS_ERROR if src contains
 * too many code points.
 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
 * @return The length of the result string, if successful - or in case of a buffer overflow,
 * in which case it will be greater than destCapacity.
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
uidna_IDNToASCII( const UChar* src, int32_t srcLength,
 UChar* dest, int32_t destCapacity,
 int32_t options,
 UParseError* parseError,
 UErrorCode* status);

/**
 * Convenience function that implements the IDNToUnicode operation as defined in the IDNA RFC.
 * This operation is done on complete domain names, e.g: "www.example.com". 
 *
 * Note: IDNA RFC specifies that a conformant application should divide a domain name
 * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, 
 * and then convert. This function does not offer that level of granularity. The options once 
 * set will apply to all labels in the domain name
 *
 * @param src Input UChar array containing IDN in ASCII (ACE encoded) form.
 * @param srcLength Number of UChars in src, or -1 if NUL-terminated.
 * @param dest Output UChar array containing Unicode equivalent of source IDN.
 * @param destCapacity Size of dest.
 * @param options A bit set of options:
 * 
 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points
 * and do not use STD3 ASCII rules
 * If unassigned code points are found the operation fails with 
 * U_UNASSIGNED_CODE_POINT_FOUND error code.
 *
 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations
 * If this option is set, the unassigned code points are in the input 
 * are treated as normal Unicode code points.
 * 
 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions
 * If this option is set and the input does not satisfy STD3 rules, 
 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR
 *
 * @param parseError Pointer to UParseError struct to receive information on position 
 * of error if an error is encountered. Can be NULL.
 * @param status ICU in/out error code parameter.
 * U_INVALID_CHAR_FOUND if src contains
 * unmatched single surrogates.
 * U_INDEX_OUTOFBOUNDS_ERROR if src contains
 * too many code points.
 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
 * @return The length of the result string, if successful - or in case of a buffer overflow,
 * in which case it will be greater than destCapacity.
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
uidna_IDNToUnicode( const UChar* src, int32_t srcLength,
 UChar* dest, int32_t destCapacity,
 int32_t options,
 UParseError* parseError,
 UErrorCode* status);

/**
 * Compare two IDN strings for equivalence.
 * This function splits the domain names into labels and compares them.
 * According to IDN RFC, whenever two labels are compared, they are 
 * considered equal if and only if their ASCII forms (obtained by 
 * applying toASCII) match using an case-insensitive ASCII comparison.
 * Two domain names are considered a match if and only if all labels 
 * match regardless of whether label separators match.
 *
 * @param s1 First source string.
 * @param length1 Length of first source string, or -1 if NUL-terminated.
 *
 * @param s2 Second source string.
 * @param length2 Length of second source string, or -1 if NUL-terminated.
 * @param options A bit set of options:
 * 
 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points
 * and do not use STD3 ASCII rules
 * If unassigned code points are found the operation fails with 
 * U_UNASSIGNED_CODE_POINT_FOUND error code.
 *
 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations
 * If this option is set, the unassigned code points are in the input 
 * are treated as normal Unicode code points.
 * 
 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions
 * If this option is set and the input does not satisfy STD3 rules, 
 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR
 *
 * @param status ICU error code in/out parameter.
 * Must fulfill U_SUCCESS before the function call.
 * @return <0 or 0 or >0 as usual for string comparisons
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
uidna_compare( const UChar *s1, int32_t length1,
 const UChar *s2, int32_t length2,
 int32_t options,
 UErrorCode* status);

#endif /* #if !UCONFIG_NO_IDNA */

#endif

cmd: