// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ********************************************************************** * Copyright (C) 1997-2016, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * * File USCRIPT.H * * Modification History: * * Date Name Description * 07/06/2001 Ram Creation. ****************************************************************************** */ #ifndef USCRIPT_H #define USCRIPT_H #include "unicode/utypes.h" /** * \file * \brief C API: Unicode Script Information */ /** * Constants for ISO 15924 script codes. * * The current set of script code constants supports at least all scripts * that are encoded in the version of Unicode which ICU currently supports. * The names of the constants are usually derived from the * Unicode script property value aliases. * See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/) * and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt . * * In addition, constants for many ISO 15924 script codes * are included, for use with language tags, CLDR data, and similar. * Some of those codes are not used in the Unicode Character Database (UCD). * For example, there are no characters that have a UCD script property value of * Hans or Hant. All Han ideographs have the Hani script property value in Unicode. * * Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR. * * Starting with ICU 55, script codes are only added when their scripts * have been or will certainly be encoded in Unicode, * and have been assigned Unicode script property value aliases, * to ensure that their script names are stable and match the names of the constants. * Script codes like Latf and Aran that are not subject to separate encoding * may be added at any time. * * @stable ICU 2.2 */ UScriptCode; /** * Gets the script codes associated with the given locale or ISO 15924 abbreviation or name. * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". * Fills in USCRIPT_LATIN given "en" OR "en_US" * If the required capacity is greater than the capacity of the destination buffer, * then the error code is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned. * * <p>Note: To search by short or long script alias only, use * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. That does * a fast lookup with no access of the locale data. * * @param nameOrAbbrOrLocale name of the script, as given in * PropertyValueAliases.txt, or ISO 15924 code or locale * @param fillIn the UScriptCode buffer to fill in the script code * @param capacity the capacity (size) of UScriptCode buffer passed in. * @param err the error status code. * @return The number of script codes filled in the buffer passed in * @stable ICU 2.4 */ U_CAPI int32_t U_EXPORT2 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); /** * Returns the long Unicode script name, if there is one. * Otherwise returns the 4-letter ISO 15924 script code. * Returns "Malayam" given USCRIPT_MALAYALAM. * * @param scriptCode UScriptCode enum * @return long script name as given in PropertyValueAliases.txt, or the 4-letter code, * or NULL if scriptCode is invalid * @stable ICU 2.4 */ U_CAPI const char* U_EXPORT2 uscript_getName(UScriptCode scriptCode); /** * Returns the 4-letter ISO 15924 script code, * which is the same as the short Unicode script name if Unicode has names for the script. * Returns "Mlym" given USCRIPT_MALAYALAM. * * @param scriptCode UScriptCode enum * @return short script name (4-letter code), or NULL if scriptCode is invalid * @stable ICU 2.4 */ U_CAPI const char* U_EXPORT2 uscript_getShortName(UScriptCode scriptCode); /** * 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, or 0 if codepoint is invalid * @stable ICU 2.4 */ U_CAPI UScriptCode U_EXPORT2 uscript_getScript(UChar32 codepoint, UErrorCode *err); /** * Do the Script_Extensions of code point c contain script sc? * If c does not have explicit Script_Extensions, then this tests whether * c has the Script property value sc. * * Some characters are commonly used in multiple scripts. * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. * @param c code point * @param sc script code * @return true if sc is in Script_Extensions(c) * @stable ICU 49 */ U_CAPI UBool U_EXPORT2 uscript_hasScript(UChar32 c, UScriptCode sc); /** * Writes code point c's Script_Extensions as a list of UScriptCode values * to the output scripts array and returns the number of script codes. * - If c does have Script_Extensions, then the Script property value * (normally Common or Inherited) is not included. * - If c does not have Script_Extensions, then the one Script code is written to the output array. * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written. * In other words, if the return value is 1, * then the output array contains exactly c's single Script code. * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes. * * Some characters are commonly used in multiple scripts. * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. * * If there are more than capacity script codes to be written, then * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. * (Usual ICU buffer handling behavior.) * * @param c code point * @param scripts output script code array * @param capacity capacity of the scripts array * @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 number of script codes in c's Script_Extensions, or 1 for the single Script value, * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity * @stable ICU 49 */ U_CAPI int32_t U_EXPORT2 uscript_getScriptExtensions(UChar32 c, UScriptCode *scripts, int32_t capacity, UErrorCode *errorCode); /** * Script usage constants. * See UAX #31 Unicode Identifier and Pattern Syntax. * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers * * @stable ICU 51 */ UScriptUsage; /** * Writes the script sample character string. * This string normally consists of one code point but might be longer. * The string is empty if the script is not encoded. * * @param script script code * @param dest output string array * @param capacity number of UChars in the dest array * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input * @return the string length, even if U_BUFFER_OVERFLOW_ERROR * @stable ICU 51 */ U_CAPI int32_t U_EXPORT2 uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); #if U_SHOW_CPLUSPLUS_API U_NAMESPACE_BEGIN class UnicodeString; U_NAMESPACE_END /** * Returns the script sample character string. * This string normally consists of one code point but might be longer. * The string is empty if the script is not encoded. * * @param script script code * @return the sample character string * @stable ICU 51 */ U_COMMON_API icu::UnicodeString U_EXPORT2 uscript_getSampleUnicodeString(UScriptCode script); #endif /** * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode. * * @param script script code * @return script usage * @see UScriptUsage * @stable ICU 51 */ U_CAPI UScriptUsage U_EXPORT2 uscript_getUsage(UScriptCode script); /** * Returns true if the script is written right-to-left. * For example, Arab and Hebr. * * @param script script code * @return true if the script is right-to-left * @stable ICU 51 */ U_CAPI UBool U_EXPORT2 uscript_isRightToLeft(UScriptCode script); /** * Returns true if the script allows line breaks between letters (excluding hyphenation). * Such a script typically requires dictionary-based line breaking. * For example, Hani and Thai. * * @param script script code * @return true if the script allows line breaks between letters * @stable ICU 51 */ U_CAPI UBool U_EXPORT2 uscript_breaksBetweenLetters(UScriptCode script); /** * Returns true if in modern (or most recent) usage of the script case distinctions are customary. * For example, Latn and Cyrl. * * @param script script code * @return true if the script is cased * @stable ICU 51 */ U_CAPI UBool U_EXPORT2 uscript_isCased(UScriptCode script); #endif
Codebase Browser
godot