/* ******************************************************************************* * * Copyright (C) 2009-2010, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: unorm2.h * encoding: US-ASCII * tab size: 8 (not used) * indentation:4 * * created on: 2009dec15 * created by: Markus W. Scherer */ #ifndef __UNORM2_H__ #define __UNORM2_H__ /** * \file * \brief C API: New API for Unicode Normalization. * * Unicode normalization functionality for standard Unicode normalization or * for using custom mapping tables. * All instances of UNormalizer2 are unmodifiable/immutable. * Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller. * For more details see the Normalizer2 C++ class. */ #include "unicode/utypes.h" #include "unicode/localpointer.h" #include "unicode/uset.h" /** * Constants for normalization modes. * For details about standard Unicode normalization forms * and about the algorithms which are also used with custom mapping tables * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ typedef enum { /** * Decomposition followed by composition. * Same as standard NFC when using an "nfc" instance. * Same as standard NFKC when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_COMPOSE, /** * Map, and reorder canonically. * Same as standard NFD when using an "nfc" instance. * Same as standard NFKD when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_DECOMPOSE, /** * "Fast C or D" form. * If a string is in this form, then further decomposition without reordering * would yield the same form as DECOMPOSE. * Text in "Fast C or D" form can be processed efficiently with data tables * that are "canonically closed", that is, that provide equivalent data for * equivalent text, without having to be fully normalized. * Not a standard Unicode normalization form. * Not a unique form: Different FCD strings can be canonically equivalent. * For details see http://www.unicode.org/notes/tn5/#FCD * @stable ICU 4.4 */ UNORM2_FCD, /** * Compose only contiguously. * Also known as "FCC" or "Fast C Contiguous". * The result will often but not always be in NFC. * The result will conform to FCD which is useful for processing. * Not a standard Unicode normalization form. * For details see http://www.unicode.org/notes/tn5/#FCC * @stable ICU 4.4 */ UNORM2_COMPOSE_CONTIGUOUS } UNormalization2Mode; /** * Result values for normalization quick check functions. * For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms * @stable ICU 2.0 */ typedef enum UNormalizationCheckResult { /** * The input string is not in the normalization form. * @stable ICU 2.0 */ UNORM_NO, /** * The input string is in the normalization form. * @stable ICU 2.0 */ UNORM_YES, /** * The input string may or may not be in the normalization form. * This value is only returned for composition forms like NFC and FCC, * when a backward-combining character is found for which the surrounding text * would have to be analyzed further. * @stable ICU 2.0 */ UNORM_MAYBE } UNormalizationCheckResult; /** * Opaque C service object type for the new normalization API. * @stable ICU 4.4 */ struct UNormalizer2; typedef struct UNormalizer2 UNormalizer2; /**end=spanQuickCheckYes(s, ec); * the substring UnicodeString(s, 0, end) * will pass the quick check with a "yes" result. * * The returned end index is usually one or more characters before the * "no" or "maybe" character: The end index is at a normalization boundary. * (See the class documentation for more about normalization boundaries.) * * When the goal is a normalized string and most input strings are expected * to be normalized already, then call this method, * and if it returns a prefix shorter than the input string, * copy that prefix and use normalizeSecondAndAppend() for the remainder. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return "yes" span end index * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_spanQuickCheckYes(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Tests if the character always has a normalization boundary before it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary before it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character always has a normalization boundary after it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary after it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character is normalization-inert. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c is normalization-inert * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_isInert(const UNormalizer2 *norm2, UChar32 c); #endif /* !UCONFIG_NO_NORMALIZATION */ #endif /* __UNORM2_H__ */