/* ********************************************************************** * Copyright (C) 1999-2002, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * * File USC_IMPL.H * * Modification History: * * Date Name Description * 07/08/2002 Eric Mader Creation. ****************************************************************************** */ #ifndef USC_IMPL_H #define USC_IMPL_H #include "unicode/utypes.h" #include "unicode/uscript.h" /** * Gets the script code associated with the given codepoint. * Returns USCRIPT_MALAYALAM given 0x0D02 * @param codepoint UChar32 codepoint * @param err the error status code. * @return The UScriptCode * @draft ICU 2.0 */ U_CAPI UScriptCode U_EXPORT2 uscript_getScript(UChar32 codepoint, UErrorCode *err); /** * UScriptRun is used to find runs of characters in * the same script. It implements a simple iterator over an array * of characters. The iterator will resolve script-neutral characters * like punctuation into the script of the surrounding characters. * * The iterator will try to match paired punctuation. If it sees an * opening punctuation character, it will remember the script that * was assigned to that character, and assign the same script to the * matching closing punctuation. * * Scripts are chosen based on the UScriptCode enumeration. * No attempt is made to combine related scripts into a single run. In * particular, Hiragana, Katakana, and Han characters will appear in seperate * runs. * Here is an example of how to iterate over script runs: *
 * \code
 * void printScriptRuns(const UChar *text, int32_t length)
 * {
 *     UErrorCode error = U_ZERO_ERROR;
 *     UScriptRun *scriptRun = uscript_openRun(text, testLength, &error);
 *     int32_t start = 0, limit = 0;
 *     UScriptCode code = USCRIPT_INVALID_CODE;
 *
 *     while (uscript_nextRun(&start, &limit, &code)) {
 *         printf("Script '%s' from %d to %d.\n", uscript_getName(code), start, limit);
 *     }
 *
 *     uscript_closeRun(scriptRun);
 *  }
 * 
* * @draft ICU 2.2 */ struct UScriptRun; typedef struct UScriptRun UScriptRun; /** * Create a UScriptRun object for iterating over the given text. This object must * be freed using uscript_closeRun(). Note that this object does not copy the source text, * only the pointer to it. You must make sure that the pointer remains valid until you call * uscript_closeRun() or uscript_setRunText(). * * @param src is the address of the array of characters over which to iterate. * if src == NULL and length == 0, * an empty UScriptRun object will be returned. * * @param length is the number of characters over which to iterate. * * @param pErrorCode is a pointer to a valid UErrorCode value. If this value * indicates a failure on entry, the function will immediately return. * On exit the value will indicate the success of the operation. * * @return the address of UScriptRun object which will iterate over the text, * or NULL if the operation failed. * * @draft ICU 2.2 */ U_CAPI UScriptRun * U_EXPORT2 uscript_openRun(const UChar *src, int32_t length, UErrorCode *pErrorCode); /** * Frees the given UScriptRun object and any storage associated with it. * On return, scriptRun no longer points to a valid UScriptRun object. * * @param scriptRun is the UScriptRun object which will be freed. * * @draft ICU 2.2 */ U_CAPI void U_EXPORT2 uscript_closeRun(UScriptRun *scriptRun); /** * Reset the UScriptRun object so that it will start iterating from * the beginning. * * @param scriptRun is the address of the UScriptRun object to be reset. * * @draft ICU 2.2 */ U_CAPI void U_EXPORT2 uscript_resetRun(UScriptRun *scriptRun); /** * Change the text over which the given UScriptRun object iterates. * * @param scriptRun is the UScriptRun object which will be changed. * * @param src is the address of the new array of characters over which to iterate. * If src == NULL and length == 0, * the UScriptRun object will become empty. * * @param length is the new number of characters over which to iterate * * @param pErrorCode is a pointer to a valid UErrorCode value. If this value * indicates a failure on entry, the function will immediately return. * On exit the value will indicate the success of the operation. * * @draft ICU 2.2 */ U_CAPI void U_EXPORT2 uscript_setRunText(UScriptRun *scriptRun, const UChar *src, int32_t length, UErrorCode *pErrorCode); /** * Advance the UScriptRun object to the next script run, return the start and limit * offsets, and the script of the run. * * @param scriptRun is the address of the UScriptRun object. * * @param pRunStart is a pointer to the variable to receive the starting offset of the next run. * This pointer can be NULL if the value is not needed. * * @param pRunLimit is a pointer to the variable to receive the limit offset of the next run. * This pointer can be NULL if the value is not needed. * * @param pRunScript is a pointer to the variable to receive the UScriptCode for the * script of the current run. This pointer can be NULL if the value is not needed. * * @return true if there was another script run. * * @draft ICU 2.2 */ U_CAPI UBool U_EXPORT2 uscript_nextRun(UScriptRun *scriptRun, int32_t *pRunStart, int32_t *pRunLimit, UScriptCode *pRunScript); #endif