AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-20530 Fix header issues based on test/hdrtst

Browse Source 
Remove explicit extern "C++" scope.

Remove C++ macros in C mode.

Fix issues detected by make -C test/hdrtst.

Run test/hdrtest during CI to detect future breakage.

Signed-off-by: Alon Bar-Lev <alon.barlev@gmail.com>
This commit is contained in:
Alon Bar-Lev 2019-03-30 09:59:46 +03:00 committed by Jeff Genovy
parent 693adf3987
commit 0aa19c0d22
6 changed files with 293 additions and 316 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.travis.yml
View File

@ -41,18 +41,23 @@ matrix:
# #
# Test both out-of-source and in-source builds. This one (gcc) for out-of-source, # Test both out-of-source and in-source builds. This one (gcc) for out-of-source,
# and linux clang (below) for in-source. # and linux clang (below) for in-source.
#
# Invokes test/hdrtst to check public headers compliance.
- name: "c: linux gcc" - name: "c: linux gcc"
language: cpp language: cpp
compiler: gcc compiler: gcc
env: PREFIX=/tmp/icu-prefix
before_script: before_script:
- mkdir build - mkdir build
- cd build - cd build
- ../icu4c/source/runConfigureICU --enable-debug --disable-release Linux - ../icu4c/source/runConfigureICU --enable-debug --disable-release Linux --prefix="${PREFIX}"
- make -j2 - make -j2
script: script:
- make -j2 check - make -j2 check
- ( cd ../icu4c/source/test/depstest && ./depstest.py ../../../../build/ ) - ( cd ../icu4c/source/test/depstest && ./depstest.py ../../../../build/ )
- make install
- PATH="${PREFIX}/bin:$PATH" make -C test/hdrtst check
- name: "c: linux clang" - name: "c: linux clang"
language: cpp language: cpp

39
icu4c/source/common/unicode/ucptrie.h
View File

@ -216,25 +216,6 @@ ucptrie_openFromBinary(UCPTrieType type, UCPTrieValueWidth valueWidth,
U_CAPI void U_EXPORT2 U_CAPI void U_EXPORT2
ucptrie_close(UCPTrie *trie); ucptrie_close(UCPTrie *trie);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUCPTriePointer
* "Smart pointer" class, closes a UCPTrie via ucptrie_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @draft ICU 63
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUCPTriePointer, UCPTrie, ucptrie_close);
U_NAMESPACE_END
#endif
/** /**
* Returns the trie type. * Returns the trie type.
* *
@ -642,5 +623,25 @@ ucptrie_internalU8PrevIndex(const UCPTrie *trie, UChar32 c,
U_CDECL_END U_CDECL_END
#endif // U_IN_DOXYGEN #endif // U_IN_DOXYGEN
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUCPTriePointer
* "Smart pointer" class, closes a UCPTrie via ucptrie_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @draft ICU 63
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUCPTriePointer, UCPTrie, ucptrie_close);
U_NAMESPACE_END
#endif // U_SHOW_CPLUSPLUS_API
#endif // U_HIDE_DRAFT_API #endif // U_HIDE_DRAFT_API
#endif #endif

38
icu4c/source/common/unicode/udata.h
View File

@ -264,25 +264,6 @@ udata_openChoice(const char *path, const char *type, const char *name,
U_STABLE void U_EXPORT2 U_STABLE void U_EXPORT2
udata_close(UDataMemory *pData); udata_close(UDataMemory *pData);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUDataMemoryPointer
* "Smart pointer" class, closes a UDataMemory via udata_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUDataMemoryPointer, UDataMemory, udata_close);
U_NAMESPACE_END
#endif
/** /**
* Get the pointer to the actual data inside the data memory. * Get the pointer to the actual data inside the data memory.
* The data is read-only. * The data is read-only.
@ -434,4 +415,23 @@ udata_setFileAccess(UDataFileAccess access, UErrorCode *status);
U_CDECL_END U_CDECL_END
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUDataMemoryPointer
* "Smart pointer" class, closes a UDataMemory via udata_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUDataMemoryPointer, UDataMemory, udata_close);
U_NAMESPACE_END
#endif // U_SHOW_CPLUSPLUS_API
#endif #endif

32
icu4c/source/common/unicode/uversion.h
View File

@ -62,26 +62,22 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
/* C++ namespace if supported. Versioned unless versioning is disabled. */ /* C++ namespace if supported. Versioned unless versioning is disabled. */
/*===========================================================================*/ /*===========================================================================*/
/* Define C++ namespace symbols. */
#ifdef __cplusplus
/** /**
* \def U_NAMESPACE_BEGIN * \def U_NAMESPACE_BEGIN
* This is used to begin a declaration of a public ICU C++ API. * This is used to begin a declaration of a public ICU C++ API within
* When not compiling for C++, it does nothing. * versioned-ICU-namespace block.
* When compiling for C++, it begins an extern "C++" linkage block (to protect
* against cases in which an external client includes ICU header files inside
* an extern "C" linkage block).
* *
* It also begins a versioned-ICU-namespace block.
* @stable ICU 2.4 * @stable ICU 2.4
*/ */
/** /**
* \def U_NAMESPACE_END * \def U_NAMESPACE_END
* This is used to end a declaration of a public ICU C++ API. * This is used to end a declaration of a public ICU C++ API.
* When not compiling for C++, it does nothing. * It ends the versioned-ICU-namespace block begun by U_NAMESPACE_BEGIN.
* When compiling for C++, it ends the extern "C++" block begun by
* U_NAMESPACE_BEGIN.
* *
* It also ends the versioned-ICU-namespace block begun by U_NAMESPACE_BEGIN.
* @stable ICU 2.4 * @stable ICU 2.4
*/ */
@ -89,9 +85,6 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
* \def U_NAMESPACE_USE * \def U_NAMESPACE_USE
* This is used to specify that the rest of the code uses the * This is used to specify that the rest of the code uses the
* public ICU C++ API namespace. * public ICU C++ API namespace.
* This is invoked by default; we recommend that you turn it off:
* See the "Recommended Build Options" section of the ICU4C readme
* (http://source.icu-project.org/repos/icu/icu/trunk/readme.html#RecBuild)
* @stable ICU 2.4 * @stable ICU 2.4
*/ */
@ -105,8 +98,6 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
* @stable ICU 2.4 * @stable ICU 2.4
*/ */
/* Define C++ namespace symbols. */
#ifdef __cplusplus
# if U_DISABLE_RENAMING # if U_DISABLE_RENAMING
# define U_ICU_NAMESPACE icu # define U_ICU_NAMESPACE icu
namespace U_ICU_NAMESPACE { } namespace U_ICU_NAMESPACE { }
@ -116,8 +107,8 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
namespace icu = U_ICU_NAMESPACE; namespace icu = U_ICU_NAMESPACE;
# endif # endif
# define U_NAMESPACE_BEGIN extern "C++" { namespace U_ICU_NAMESPACE { # define U_NAMESPACE_BEGIN namespace U_ICU_NAMESPACE {
# define U_NAMESPACE_END } } # define U_NAMESPACE_END }
# define U_NAMESPACE_USE using namespace U_ICU_NAMESPACE; # define U_NAMESPACE_USE using namespace U_ICU_NAMESPACE;
# define U_NAMESPACE_QUALIFIER U_ICU_NAMESPACE:: # define U_NAMESPACE_QUALIFIER U_ICU_NAMESPACE::
@ -133,12 +124,7 @@ typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
# if U_USING_ICU_NAMESPACE # if U_USING_ICU_NAMESPACE
U_NAMESPACE_USE U_NAMESPACE_USE
# endif # endif
#else #endif /* __cplusplus */
# define U_NAMESPACE_BEGIN
# define U_NAMESPACE_END
# define U_NAMESPACE_USE
# define U_NAMESPACE_QUALIFIER
#endif
/*===========================================================================*/ /*===========================================================================*/
/* General version helper functions. Definitions in putil.c */ /* General version helper functions. Definitions in putil.c */

1
icu4c/source/i18n/unicode/reldatefmt.h
View File

@ -246,6 +246,7 @@ class SharedPluralRules;
class SharedBreakIterator; class SharedBreakIterator;
class NumberFormat; class NumberFormat;
class UnicodeString; class UnicodeString;
class FormattedRelativeDateTime;
class FormattedRelativeDateTimeData; class FormattedRelativeDateTimeData;
#ifndef U_HIDE_DRAFT_API #ifndef U_HIDE_DRAFT_API

492
icu4c/source/i18n/unicode/uspoof.h
View File

@ -353,6 +353,8 @@
* @stable ICU 4.6 * @stable ICU 4.6
*/ */
U_CDECL_BEGIN
struct USpoofChecker; struct USpoofChecker;
/** /**
* @stable ICU 4.2 * @stable ICU 4.2
@ -674,25 +676,6 @@ uspoof_openFromSource(const char *confusables, int32_t confusablesLen,
U_STABLE void U_EXPORT2 U_STABLE void U_EXPORT2
uspoof_close(USpoofChecker *sc); uspoof_close(USpoofChecker *sc);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUSpoofCheckerPointer
* "Smart pointer" class, closes a USpoofChecker via uspoof_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSpoofCheckerPointer, USpoofChecker, uspoof_close);
U_NAMESPACE_END
#endif
/** /**
* Clone a Spoof Checker. The clone will be set to perform the same checks * Clone a Spoof Checker. The clone will be set to perform the same checks
* as the original source. * as the original source.
@ -901,54 +884,6 @@ U_STABLE const USet * U_EXPORT2
uspoof_getAllowedChars(const USpoofChecker *sc, UErrorCode *status); uspoof_getAllowedChars(const USpoofChecker *sc, UErrorCode *status);
#if U_SHOW_CPLUSPLUS_API
/**
* Limit the acceptable characters to those specified by a Unicode Set.
* Any previously specified character limit is
* is replaced by the new settings. This includes limits on
* characters that were set with the uspoof_setAllowedLocales() function.
*
* The USPOOF_CHAR_LIMIT test is automatically enabled for this
* USoofChecker by this function.
*
* @param sc The USpoofChecker
* @param chars A Unicode Set containing the list of
* characters that are permitted. Ownership of the set
* remains with the caller. The incoming set is cloned by
* this function, so there are no restrictions on modifying
* or deleting the UnicodeSet after calling this function.
* @param status The error code, set if this function encounters a problem.
* @stable ICU 4.2
*/
U_STABLE void U_EXPORT2
uspoof_setAllowedUnicodeSet(USpoofChecker *sc, const icu::UnicodeSet *chars, UErrorCode *status);
/**
* Get a UnicodeSet for the characters permitted in an identifier.
* This corresponds to the limits imposed by the Set Allowed Characters /
* UnicodeSet functions. Limitations imposed by other checks will not be
* reflected in the set returned by this function.
*
* The returned set will be frozen, meaning that it cannot be modified
* by the caller.
*
* Ownership of the returned set remains with the Spoof Detector. The
* returned set will become invalid if the spoof detector is closed,
* or if a new set of allowed characters is specified.
*
*
* @param sc The USpoofChecker
* @param status The error code, set if this function encounters a problem.
* @return A UnicodeSet containing the characters that are permitted by
* the USPOOF_CHAR_LIMIT test.
* @stable ICU 4.2
*/
U_STABLE const icu::UnicodeSet * U_EXPORT2
uspoof_getAllowedUnicodeSet(const USpoofChecker *sc, UErrorCode *status);
#endif
/** /**
* Check the specified string for possible security issues. * Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort. * The text to be checked will typically be an identifier of some sort.
@ -1027,43 +962,6 @@ uspoof_checkUTF8(const USpoofChecker *sc,
UErrorCode *status); UErrorCode *status);
#if U_SHOW_CPLUSPLUS_API
/**
* Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort.
* The set of checks to be performed is specified with uspoof_setChecks().
*
* \note
* Consider using the newer API, {@link uspoof_check2UnicodeString}, instead.
* The newer API exposes additional information from the check procedure
* and is otherwise identical to this method.
*
* @param sc The USpoofChecker
* @param id A identifier to be checked for possible security issues.
* @param position Deprecated in ICU 51. Always returns zero.
* Originally, an out parameter for the index of the first
* string position that failed a check.
* This parameter may be NULL.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Spoofing or security issues detected with the input string are
* not reported here, but through the function's return value.
* @return An integer value with bits set for any potential security
* or spoofing issues detected. The bits are defined by
* enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS)
* will be zero if the input string passes all of the
* enabled checks.
* @see uspoof_check2UnicodeString
* @stable ICU 4.2
*/
U_STABLE int32_t U_EXPORT2
uspoof_checkUnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &id,
int32_t *position,
UErrorCode *status);
#endif
/** /**
* Check the specified string for possible security issues. * Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort. * The text to be checked will typically be an identifier of some sort.
@ -1135,39 +1033,6 @@ uspoof_check2UTF8(const USpoofChecker *sc,
USpoofCheckResult* checkResult, USpoofCheckResult* checkResult,
UErrorCode *status); UErrorCode *status);
#if U_SHOW_CPLUSPLUS_API
/**
* Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort.
* The set of checks to be performed is specified with uspoof_setChecks().
*
* @param sc The USpoofChecker
* @param id A identifier to be checked for possible security issues.
* @param checkResult An instance of USpoofCheckResult to be filled with
* details about the identifier. Can be NULL.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Spoofing or security issues detected with the input string are
* not reported here, but through the function's return value.
* @return An integer value with bits set for any potential security
* or spoofing issues detected. The bits are defined by
* enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS)
* will be zero if the input string passes all of the
* enabled checks. Any information in this bitmask will be
* consistent with the information saved in the optional
* checkResult parameter.
* @see uspoof_openCheckResult
* @see uspoof_check2
* @see uspoof_check2UTF8
* @stable ICU 58
*/
U_STABLE int32_t U_EXPORT2
uspoof_check2UnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &id,
USpoofCheckResult* checkResult,
UErrorCode *status);
#endif
/** /**
* Create a USpoofCheckResult, used by the {@link uspoof_check2} class of functions to return * Create a USpoofCheckResult, used by the {@link uspoof_check2} class of functions to return
* information about the identifier. Information includes: * information about the identifier. Information includes:
@ -1199,32 +1064,6 @@ uspoof_openCheckResult(UErrorCode *status);
U_STABLE void U_EXPORT2 U_STABLE void U_EXPORT2
uspoof_closeCheckResult(USpoofCheckResult *checkResult); uspoof_closeCheckResult(USpoofCheckResult *checkResult);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUSpoofCheckResultPointer
* "Smart pointer" class, closes a USpoofCheckResult via `uspoof_closeCheckResult()`.
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 58
*/
/**
* \cond
* Note: Doxygen is giving a bogus warning on this U_DEFINE_LOCAL_OPEN_POINTER.
* For now, suppress with a Doxygen cond
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSpoofCheckResultPointer, USpoofCheckResult, uspoof_closeCheckResult);
/** \endcond */
U_NAMESPACE_END
#endif
/** /**
* Indicates which of the spoof check(s) have failed. The value is a bitwise OR of the constants for the tests * Indicates which of the spoof check(s) have failed. The value is a bitwise OR of the constants for the tests
* in question: USPOOF_RESTRICTION_LEVEL, USPOOF_CHAR_LIMIT, and so on. * in question: USPOOF_RESTRICTION_LEVEL, USPOOF_CHAR_LIMIT, and so on.
@ -1355,36 +1194,6 @@ uspoof_areConfusableUTF8(const USpoofChecker *sc,
#if U_SHOW_CPLUSPLUS_API
/**
* A version of {@link uspoof_areConfusable} accepting UnicodeStrings.
*
* @param sc The USpoofChecker
* @param s1 The first of the two identifiers to be compared for
* confusability. The strings are in UTF-8 format.
* @param s2 The second of the two identifiers to be compared for
* confusability. The strings are in UTF-8 format.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Confusability of the identifiers is not reported here,
* but through this function's return value.
* @return An integer value with bit(s) set corresponding to
* the type of confusability found, as defined by
* enum USpoofChecks. Zero is returned if the identifiers
* are not confusable.
*
* @stable ICU 4.2
*
* @see uspoof_areConfusable
*/
U_STABLE int32_t U_EXPORT2
uspoof_areConfusableUnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &s1,
const icu::UnicodeString &s2,
UErrorCode *status);
#endif
/** /**
* Get the "skeleton" for an identifier. * Get the "skeleton" for an identifier.
* Skeletons are a transformation of the input identifier; * Skeletons are a transformation of the input identifier;
@ -1463,38 +1272,6 @@ uspoof_getSkeletonUTF8(const USpoofChecker *sc,
char *dest, int32_t destCapacity, char *dest, int32_t destCapacity,
UErrorCode *status); UErrorCode *status);
#if U_SHOW_CPLUSPLUS_API
/**
* Get the "skeleton" for an identifier.
* Skeletons are a transformation of the input identifier;
* Two identifiers are confusable if their skeletons are identical.
* See Unicode UAX #39 for additional information.
*
* Using skeletons directly makes it possible to quickly check
* whether an identifier is confusable with any of some large
* set of existing identifiers, by creating an efficiently
* searchable collection of the skeletons.
*
* @param sc The USpoofChecker.
* @param type Deprecated in ICU 58. You may pass any number.
* Originally, controlled which of the Unicode confusable data
* tables to use.
* @param id The input identifier whose skeleton will be computed.
* @param dest The output identifier, to receive the skeleton string.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* @return A reference to the destination (skeleton) string.
*
* @stable ICU 4.2
*/
U_I18N_API icu::UnicodeString & U_EXPORT2
uspoof_getSkeletonUnicodeString(const USpoofChecker *sc,
uint32_t type,
const icu::UnicodeString &id,
icu::UnicodeString &dest,
UErrorCode *status);
#endif /* U_SHOW_CPLUSPLUS_API */
/** /**
* Get the set of Candidate Characters for Inclusion in Identifiers, as defined * Get the set of Candidate Characters for Inclusion in Identifiers, as defined
* in http://unicode.org/Public/security/latest/xidmodifications.txt * in http://unicode.org/Public/security/latest/xidmodifications.txt
@ -1525,8 +1302,243 @@ uspoof_getInclusionSet(UErrorCode *status);
U_STABLE const USet * U_EXPORT2 U_STABLE const USet * U_EXPORT2
uspoof_getRecommendedSet(UErrorCode *status); uspoof_getRecommendedSet(UErrorCode *status);
/**
* Serialize the data for a spoof detector into a chunk of memory.
* The flattened spoof detection tables can later be used to efficiently
* instantiate a new Spoof Detector.
*
* The serialized spoof checker includes only the data compiled from the
* Unicode data tables by uspoof_openFromSource(); it does not include
* include any other state or configuration that may have been set.
*
* @param sc the Spoof Detector whose data is to be serialized.
* @param data a pointer to 32-bit-aligned memory to be filled with the data,
* can be NULL if capacity==0
* @param capacity the number of bytes available at data,
* or 0 for preflighting
* @param status an in/out ICU UErrorCode; possible errors include:
* - U_BUFFER_OVERFLOW_ERROR if the data storage block is too small for serialization
* - U_ILLEGAL_ARGUMENT_ERROR the data or capacity parameters are bad
* @return the number of bytes written or needed for the spoof data
*
* @see utrie2_openFromSerialized()
* @stable ICU 4.2
*/
U_STABLE int32_t U_EXPORT2
uspoof_serialize(USpoofChecker *sc,
void *data, int32_t capacity,
UErrorCode *status);
U_CDECL_END
#if U_SHOW_CPLUSPLUS_API #if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUSpoofCheckerPointer
* "Smart pointer" class, closes a USpoofChecker via uspoof_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
/**
* \cond
* Note: Doxygen is giving a bogus warning on this U_DEFINE_LOCAL_OPEN_POINTER.
* For now, suppress with a Doxygen cond
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSpoofCheckerPointer, USpoofChecker, uspoof_close);
/** \endcond */
/**
* \class LocalUSpoofCheckResultPointer
* "Smart pointer" class, closes a USpoofCheckResult via `uspoof_closeCheckResult()`.
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 58
*/
/**
* \cond
* Note: Doxygen is giving a bogus warning on this U_DEFINE_LOCAL_OPEN_POINTER.
* For now, suppress with a Doxygen cond
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSpoofCheckResultPointer, USpoofCheckResult, uspoof_closeCheckResult);
/** \endcond */
U_NAMESPACE_END
/**
* Limit the acceptable characters to those specified by a Unicode Set.
* Any previously specified character limit is
* is replaced by the new settings. This includes limits on
* characters that were set with the uspoof_setAllowedLocales() function.
*
* The USPOOF_CHAR_LIMIT test is automatically enabled for this
* USoofChecker by this function.
*
* @param sc The USpoofChecker
* @param chars A Unicode Set containing the list of
* characters that are permitted. Ownership of the set
* remains with the caller. The incoming set is cloned by
* this function, so there are no restrictions on modifying
* or deleting the UnicodeSet after calling this function.
* @param status The error code, set if this function encounters a problem.
* @stable ICU 4.2
*/
U_STABLE void U_EXPORT2
uspoof_setAllowedUnicodeSet(USpoofChecker *sc, const icu::UnicodeSet *chars, UErrorCode *status);
/**
* Get a UnicodeSet for the characters permitted in an identifier.
* This corresponds to the limits imposed by the Set Allowed Characters /
* UnicodeSet functions. Limitations imposed by other checks will not be
* reflected in the set returned by this function.
*
* The returned set will be frozen, meaning that it cannot be modified
* by the caller.
*
* Ownership of the returned set remains with the Spoof Detector. The
* returned set will become invalid if the spoof detector is closed,
* or if a new set of allowed characters is specified.
*
*
* @param sc The USpoofChecker
* @param status The error code, set if this function encounters a problem.
* @return A UnicodeSet containing the characters that are permitted by
* the USPOOF_CHAR_LIMIT test.
* @stable ICU 4.2
*/
U_STABLE const icu::UnicodeSet * U_EXPORT2
uspoof_getAllowedUnicodeSet(const USpoofChecker *sc, UErrorCode *status);
/**
* Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort.
* The set of checks to be performed is specified with uspoof_setChecks().
*
* \note
* Consider using the newer API, {@link uspoof_check2UnicodeString}, instead.
* The newer API exposes additional information from the check procedure
* and is otherwise identical to this method.
*
* @param sc The USpoofChecker
* @param id A identifier to be checked for possible security issues.
* @param position Deprecated in ICU 51. Always returns zero.
* Originally, an out parameter for the index of the first
* string position that failed a check.
* This parameter may be NULL.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Spoofing or security issues detected with the input string are
* not reported here, but through the function's return value.
* @return An integer value with bits set for any potential security
* or spoofing issues detected. The bits are defined by
* enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS)
* will be zero if the input string passes all of the
* enabled checks.
* @see uspoof_check2UnicodeString
* @stable ICU 4.2
*/
U_STABLE int32_t U_EXPORT2
uspoof_checkUnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &id,
int32_t *position,
UErrorCode *status);
/**
* Check the specified string for possible security issues.
* The text to be checked will typically be an identifier of some sort.
* The set of checks to be performed is specified with uspoof_setChecks().
*
* @param sc The USpoofChecker
* @param id A identifier to be checked for possible security issues.
* @param checkResult An instance of USpoofCheckResult to be filled with
* details about the identifier. Can be NULL.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Spoofing or security issues detected with the input string are
* not reported here, but through the function's return value.
* @return An integer value with bits set for any potential security
* or spoofing issues detected. The bits are defined by
* enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS)
* will be zero if the input string passes all of the
* enabled checks. Any information in this bitmask will be
* consistent with the information saved in the optional
* checkResult parameter.
* @see uspoof_openCheckResult
* @see uspoof_check2
* @see uspoof_check2UTF8
* @stable ICU 58
*/
U_STABLE int32_t U_EXPORT2
uspoof_check2UnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &id,
USpoofCheckResult* checkResult,
UErrorCode *status);
/**
* A version of {@link uspoof_areConfusable} accepting UnicodeStrings.
*
* @param sc The USpoofChecker
* @param s1 The first of the two identifiers to be compared for
* confusability. The strings are in UTF-8 format.
* @param s2 The second of the two identifiers to be compared for
* confusability. The strings are in UTF-8 format.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* Confusability of the identifiers is not reported here,
* but through this function's return value.
* @return An integer value with bit(s) set corresponding to
* the type of confusability found, as defined by
* enum USpoofChecks. Zero is returned if the identifiers
* are not confusable.
*
* @stable ICU 4.2
*
* @see uspoof_areConfusable
*/
U_STABLE int32_t U_EXPORT2
uspoof_areConfusableUnicodeString(const USpoofChecker *sc,
const icu::UnicodeString &s1,
const icu::UnicodeString &s2,
UErrorCode *status);
/**
* Get the "skeleton" for an identifier.
* Skeletons are a transformation of the input identifier;
* Two identifiers are confusable if their skeletons are identical.
* See Unicode UAX #39 for additional information.
*
* Using skeletons directly makes it possible to quickly check
* whether an identifier is confusable with any of some large
* set of existing identifiers, by creating an efficiently
* searchable collection of the skeletons.
*
* @param sc The USpoofChecker.
* @param type Deprecated in ICU 58. You may pass any number.
* Originally, controlled which of the Unicode confusable data
* tables to use.
* @param id The input identifier whose skeleton will be computed.
* @param dest The output identifier, to receive the skeleton string.
* @param status The error code, set if an error occurred while attempting to
* perform the check.
* @return A reference to the destination (skeleton) string.
*
* @stable ICU 4.2
*/
U_I18N_API icu::UnicodeString & U_EXPORT2
uspoof_getSkeletonUnicodeString(const USpoofChecker *sc,
uint32_t type,
const icu::UnicodeString &id,
icu::UnicodeString &dest,
UErrorCode *status);
/** /**
* Get the set of Candidate Characters for Inclusion in Identifiers, as defined * Get the set of Candidate Characters for Inclusion in Identifiers, as defined
* in http://unicode.org/Public/security/latest/xidmodifications.txt * in http://unicode.org/Public/security/latest/xidmodifications.txt
@ -1559,34 +1571,6 @@ uspoof_getRecommendedUnicodeSet(UErrorCode *status);
#endif /* U_SHOW_CPLUSPLUS_API */ #endif /* U_SHOW_CPLUSPLUS_API */
/** #endif /* UCONFIG_NO_NORMALIZATION */
* Serialize the data for a spoof detector into a chunk of memory.
* The flattened spoof detection tables can later be used to efficiently
* instantiate a new Spoof Detector.
*
* The serialized spoof checker includes only the data compiled from the
* Unicode data tables by uspoof_openFromSource(); it does not include
* include any other state or configuration that may have been set.
*
* @param sc the Spoof Detector whose data is to be serialized.
* @param data a pointer to 32-bit-aligned memory to be filled with the data,
* can be NULL if capacity==0
* @param capacity the number of bytes available at data,
* or 0 for preflighting
* @param status an in/out ICU UErrorCode; possible errors include:
* - U_BUFFER_OVERFLOW_ERROR if the data storage block is too small for serialization
* - U_ILLEGAL_ARGUMENT_ERROR the data or capacity parameters are bad
* @return the number of bytes written or needed for the spoof data
*
* @see utrie2_openFromSerialized()
* @stable ICU 4.2
*/
U_STABLE int32_t U_EXPORT2
uspoof_serialize(USpoofChecker *sc,
void *data, int32_t capacity,
UErrorCode *status);
#endif
#endif /* USPOOF_H */ #endif /* USPOOF_H */