/*
*******************************************************************************
*
-* Copyright (C) 2009-2010, International Business Machines
+* Copyright (C) 2009-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
#if !UCONFIG_NO_NORMALIZATION
+#ifndef U_HIDE_DRAFT_API
+/**
+ * Returns a UNormalizer2 instance for Unicode NFC normalization.
+ * Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode).
+ * Returns an unmodifiable singleton instance. Do not delete it.
+ * @param errorCode 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 the requested Normalizer2, if successful
+ * @draft ICU 49
+ */
+U_DRAFT const UNormalizer2 * U_EXPORT2
+unorm2_getNFCInstance(UErrorCode *pErrorCode);
+
+/**
+ * Returns a UNormalizer2 instance for Unicode NFD normalization.
+ * Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode).
+ * Returns an unmodifiable singleton instance. Do not delete it.
+ * @param errorCode 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 the requested Normalizer2, if successful
+ * @draft ICU 49
+ */
+U_DRAFT const UNormalizer2 * U_EXPORT2
+unorm2_getNFDInstance(UErrorCode *pErrorCode);
+
+/**
+ * Returns a UNormalizer2 instance for Unicode NFKC normalization.
+ * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode).
+ * Returns an unmodifiable singleton instance. Do not delete it.
+ * @param errorCode 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 the requested Normalizer2, if successful
+ * @draft ICU 49
+ */
+U_DRAFT const UNormalizer2 * U_EXPORT2
+unorm2_getNFKCInstance(UErrorCode *pErrorCode);
+
+/**
+ * Returns a UNormalizer2 instance for Unicode NFKD normalization.
+ * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode).
+ * Returns an unmodifiable singleton instance. Do not delete it.
+ * @param errorCode 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 the requested Normalizer2, if successful
+ * @draft ICU 49
+ */
+U_DRAFT const UNormalizer2 * U_EXPORT2
+unorm2_getNFKDInstance(UErrorCode *pErrorCode);
+
+/**
+ * Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization.
+ * Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode).
+ * Returns an unmodifiable singleton instance. Do not delete it.
+ * @param errorCode 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 the requested Normalizer2, if successful
+ * @draft ICU 49
+ */
+U_DRAFT const UNormalizer2 * U_EXPORT2
+unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode);
+#endif /* U_HIDE_DRAFT_API */
+
/**
* Returns a UNormalizer2 instance which uses the specified data file
* (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle)
UErrorCode *pErrorCode);
/**
- * Gets the decomposition mapping of c. Equivalent to unorm2_normalize(string(c))
- * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster.
+ * Gets the decomposition mapping of c.
+ * Roughly equivalent to normalizing the String form of c
+ * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function
+ * returns a negative value and does not write a string
+ * if c does not have a decomposition mapping in this instance's data.
* This function is independent of the mode of the UNormalizer2.
* @param norm2 UNormalizer2 instance
* @param c code point
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the non-negative length of c's decomposition, if there is one; otherwise a negative value
- * @draft ICU 4.6
+ * @stable ICU 4.6
*/
U_DRAFT int32_t U_EXPORT2
unorm2_getDecomposition(const UNormalizer2 *norm2,
UChar32 c, UChar *decomposition, int32_t capacity,
UErrorCode *pErrorCode);
+#ifndef U_HIDE_DRAFT_API
+/**
+ * Gets the raw decomposition mapping of c.
+ *
+ * This is similar to the unorm2_getDecomposition() function but returns the
+ * raw decomposition mapping as specified in UnicodeData.txt or
+ * (for custom data) in the mapping files processed by the gennorm2 tool.
+ * By contrast, unorm2_getDecomposition() returns the processed,
+ * recursively-decomposed version of this mapping.
+ *
+ * When used on a standard NFKC Normalizer2 instance,
+ * unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property.
+ *
+ * When used on a standard NFC Normalizer2 instance,
+ * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can);
+ * in this case, the result contains either one or two code points (=1..4 UChars).
+ *
+ * This function is independent of the mode of the UNormalizer2.
+ * @param norm2 UNormalizer2 instance
+ * @param c code point
+ * @param decomposition String buffer which will be set to c's
+ * raw decomposition mapping, if there is one.
+ * @param capacity number of UChars that can be written to decomposition
+ * @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 the non-negative length of c's raw decomposition, if there is one; otherwise a negative value
+ * @draft ICU 49
+ */
+U_DRAFT int32_t U_EXPORT2
+unorm2_getRawDecomposition(const UNormalizer2 *norm2,
+ UChar32 c, UChar *decomposition, int32_t capacity,
+ UErrorCode *pErrorCode);
+
+/**
+ * Performs pairwise composition of a & b and returns the composite if there is one.
+ *
+ * Returns a composite code point c only if c has a two-way mapping to a+b.
+ * In standard Unicode normalization, this means that
+ * c has a canonical decomposition to a+b
+ * and c does not have the Full_Composition_Exclusion property.
+ *
+ * This function is independent of the mode of the UNormalizer2.
+ * @param norm2 UNormalizer2 instance
+ * @param a A (normalization starter) code point.
+ * @param b Another code point.
+ * @return The non-negative composite code point if there is one; otherwise a negative value.
+ * @draft ICU 49
+ */
+U_DRAFT UChar32 U_EXPORT2
+unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b);
+
+/**
+ * Gets the combining class of c.
+ * The default implementation returns 0
+ * but all standard implementations return the Unicode Canonical_Combining_Class value.
+ * @param norm2 UNormalizer2 instance
+ * @param c code point
+ * @return c's combining class
+ * @draft ICU 49
+ */
+U_DRAFT uint8_t U_EXPORT2
+unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c);
+#endif /* U_HIDE_DRAFT_API */
+
/**
* Tests if the string is normalized.
* Internally, in cases where the quickCheck() method would return "maybe"
projects / apple / icu.git / blobdiff