JavaScriptCore-7600.1.4.13.1.tar.gz

[apple/javascriptcore.git] / icu / unicode / uscript.h

diff --git a/icu/unicode/uscript.h b/icu/unicode/uscript.h
index 16375447d08343b22c08d59f80933f8b79e8aef8..ee21c740d16a6e64e94424a2ea7d69064cf18e47 100644 (file)
--- a/icu/unicode/uscript.h
+++ b/icu/unicode/uscript.h
@@ -1,17 +1,18 @@
 /*
 /*

-**********************************************************************
-*   Copyright (C) 1997-2006, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
-*
-* File USCRIPT.H
-*
-* Modification History:
-*
-*   Date        Name        Description
-*   07/06/2001    Ram         Creation.
-******************************************************************************
-*/
+ **********************************************************************
+ *   Copyright (C) 1997-2010, 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"
 #ifndef USCRIPT_H
 #define USCRIPT_H
 #include "unicode/utypes.h"


@@ -44,8 +45,8 @@
  */
 typedef enum UScriptCode {
       USCRIPT_INVALID_CODE = -1,
  */
 typedef enum UScriptCode {
       USCRIPT_INVALID_CODE = -1,

-      USCRIPT_COMMON       =  0 , /* Zyyy */
-      USCRIPT_INHERITED    =  1,  /* Qaai */
+      USCRIPT_COMMON       =  0,  /* Zyyy */
+      USCRIPT_INHERITED    =  1,  /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */

       USCRIPT_ARABIC       =  2,  /* Arab */
       USCRIPT_ARMENIAN     =  3,  /* Armn */
       USCRIPT_BENGALI      =  4,  /* Beng */
       USCRIPT_ARABIC       =  2,  /* Arab */
       USCRIPT_ARMENIAN     =  3,  /* Armn */
       USCRIPT_BENGALI      =  4,  /* Beng */


@@ -106,9 +107,8 @@ typedef enum UScriptCode {
 
       /** New script code in Unicode 4.0.1 @stable ICU 3.0 */
       USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
 
       /** New script code in Unicode 4.0.1 @stable ICU 3.0 */
       USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */

-      
-#ifndef U_HIDE_DRAFT_API
-      /* New scripts in Unicode 4.1 @draft ICU 3.4 */
+
+      /* New scripts in Unicode 4.1 @stable ICU 3.4 */

       USCRIPT_BUGINESE      = 55, /* Bugi */
       USCRIPT_GLAGOLITIC    = 56, /* Glag */
       USCRIPT_KHAROSHTHI    = 57, /* Khar */
       USCRIPT_BUGINESE      = 55, /* Bugi */
       USCRIPT_GLAGOLITIC    = 56, /* Glag */
       USCRIPT_KHAROSHTHI    = 57, /* Khar */


@@ -117,7 +117,7 @@ typedef enum UScriptCode {
       USCRIPT_TIFINAGH      = 60, /* Tfng */
       USCRIPT_OLD_PERSIAN   = 61, /* Xpeo */
 
       USCRIPT_TIFINAGH      = 60, /* Tfng */
       USCRIPT_OLD_PERSIAN   = 61, /* Xpeo */
 

-      /* New script codes from ISO 15924 @draft ICU 3.6 */
+      /* New script codes from ISO 15924 @stable ICU 3.6 */

       USCRIPT_BALINESE                      = 62, /* Bali */
       USCRIPT_BATAK                         = 63, /* Batk */
       USCRIPT_BLISSYMBOLS                   = 64, /* Blis */
       USCRIPT_BALINESE                      = 62, /* Bali */
       USCRIPT_BATAK                         = 63, /* Batk */
       USCRIPT_BLISSYMBOLS                   = 64, /* Blis */


@@ -140,9 +140,15 @@ typedef enum UScriptCode {
       USCRIPT_LATIN_GAELIC                  = 81, /* Latg */
       USCRIPT_LEPCHA                        = 82, /* Lepc */
       USCRIPT_LINEAR_A                      = 83, /* Lina */
       USCRIPT_LATIN_GAELIC                  = 81, /* Latg */
       USCRIPT_LEPCHA                        = 82, /* Lepc */
       USCRIPT_LINEAR_A                      = 83, /* Lina */

-      USCRIPT_MANDAEAN                      = 84, /* Mand */
+      /** @stable ICU 4.6 */
+      USCRIPT_MANDAIC                       = 84, /* Mand */
+      /** @stable ICU 3.6 */
+      USCRIPT_MANDAEAN                      = USCRIPT_MANDAIC,

       USCRIPT_MAYAN_HIEROGLYPHS             = 85, /* Maya */
       USCRIPT_MAYAN_HIEROGLYPHS             = 85, /* Maya */

-      USCRIPT_MEROITIC                      = 86, /* Mero */
+      /** @stable ICU 4.6 */
+      USCRIPT_MEROITIC_HIEROGLYPHS          = 86, /* Mero */
+      /** @stable ICU 3.6 */
+      USCRIPT_MEROITIC                      = USCRIPT_MEROITIC_HIEROGLYPHS,

       USCRIPT_NKO                           = 87, /* Nkoo */
       USCRIPT_ORKHON                        = 88, /* Orkh */
       USCRIPT_OLD_PERMIC                    = 89, /* Perm */
       USCRIPT_NKO                           = 87, /* Nkoo */
       USCRIPT_ORKHON                        = 88, /* Orkh */
       USCRIPT_OLD_PERMIC                    = 89, /* Perm */


@@ -156,13 +162,64 @@ typedef enum UScriptCode {
       USCRIPT_EASTERN_SYRIAC                = 97, /* Syrn */
       USCRIPT_TENGWAR                       = 98, /* Teng */
       USCRIPT_VAI                           = 99, /* Vaii */
       USCRIPT_EASTERN_SYRIAC                = 97, /* Syrn */
       USCRIPT_TENGWAR                       = 98, /* Teng */
       USCRIPT_VAI                           = 99, /* Vaii */

-      USCRIPT_VISIBLE_SPEECH                = 100, /* Visp */
+      USCRIPT_VISIBLE_SPEECH                = 100,/* Visp */

       USCRIPT_CUNEIFORM                     = 101,/* Xsux */
       USCRIPT_UNWRITTEN_LANGUAGES           = 102,/* Zxxx */
       USCRIPT_UNKNOWN                       = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
       USCRIPT_CUNEIFORM                     = 101,/* Xsux */
       USCRIPT_UNWRITTEN_LANGUAGES           = 102,/* Zxxx */
       USCRIPT_UNKNOWN                       = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */

-      /* Private use codes from Qaaa - Qabx are not supported*/
-#endif /* U_HIDE_DRAFT_API */
-      USCRIPT_CODE_LIMIT    = 104
+
+      /* New script codes from ISO 15924 @stable ICU 3.8 */
+      USCRIPT_CARIAN                        = 104,/* Cari */
+      USCRIPT_JAPANESE                      = 105,/* Jpan */
+      USCRIPT_LANNA                         = 106,/* Lana */
+      USCRIPT_LYCIAN                        = 107,/* Lyci */
+      USCRIPT_LYDIAN                        = 108,/* Lydi */
+      USCRIPT_OL_CHIKI                      = 109,/* Olck */
+      USCRIPT_REJANG                        = 110,/* Rjng */
+      USCRIPT_SAURASHTRA                    = 111,/* Saur */
+      USCRIPT_SIGN_WRITING                  = 112,/* Sgnw */
+      USCRIPT_SUNDANESE                     = 113,/* Sund */
+      USCRIPT_MOON                          = 114,/* Moon */
+      USCRIPT_MEITEI_MAYEK                  = 115,/* Mtei */
+
+      /* New script codes from ISO 15924 @stable ICU 4.0 */
+      USCRIPT_IMPERIAL_ARAMAIC              = 116,/* Armi */
+      USCRIPT_AVESTAN                       = 117,/* Avst */
+      USCRIPT_CHAKMA                        = 118,/* Cakm */
+      USCRIPT_KOREAN                        = 119,/* Kore */
+      USCRIPT_KAITHI                        = 120,/* Kthi */
+      USCRIPT_MANICHAEAN                    = 121,/* Mani */
+      USCRIPT_INSCRIPTIONAL_PAHLAVI         = 122,/* Phli */
+      USCRIPT_PSALTER_PAHLAVI               = 123,/* Phlp */
+      USCRIPT_BOOK_PAHLAVI                  = 124,/* Phlv */
+      USCRIPT_INSCRIPTIONAL_PARTHIAN        = 125,/* Prti */
+      USCRIPT_SAMARITAN                     = 126,/* Samr */
+      USCRIPT_TAI_VIET                      = 127,/* Tavt */
+      USCRIPT_MATHEMATICAL_NOTATION         = 128,/* Zmth */
+      USCRIPT_SYMBOLS                       = 129,/* Zsym */
+
+      /* New script codes from ISO 15924 @stable ICU 4.4 */
+      USCRIPT_BAMUM                         = 130,/* Bamu */
+      USCRIPT_LISU                          = 131,/* Lisu */
+      USCRIPT_NAKHI_GEBA                    = 132,/* Nkgb */
+      USCRIPT_OLD_SOUTH_ARABIAN             = 133,/* Sarb */
+
+      /* New script codes from ISO 15924 @stable ICU 4.6 */
+      USCRIPT_BASSA_VAH                     = 134,/* Bass */
+      USCRIPT_DUPLOYAN_SHORTAND             = 135,/* Dupl */
+      USCRIPT_ELBASAN                       = 136,/* Elba */
+      USCRIPT_GRANTHA                       = 137,/* Gran */
+      USCRIPT_KPELLE                        = 138,/* Kpel */
+      USCRIPT_LOMA                          = 139,/* Loma */
+      USCRIPT_MENDE                         = 140,/* Mend */
+      USCRIPT_MEROITIC_CURSIVE              = 141,/* Merc */
+      USCRIPT_OLD_NORTH_ARABIAN             = 142,/* Narb */
+      USCRIPT_NABATAEAN                     = 143,/* Nbat */
+      USCRIPT_PALMYRENE                     = 144,/* Palm */
+      USCRIPT_SINDHI                        = 145,/* Sind */
+      USCRIPT_WARANG_CITI                   = 146,/* Wara */
+
+      /* Private use codes from Qaaa - Qabx are not supported */
+      USCRIPT_CODE_LIMIT    = 147

 } UScriptCode;
 
 /**
 } UScriptCode;
 
 /**


@@ -208,7 +265,7 @@ uscript_getName(UScriptCode scriptCode);
 U_STABLE const char*  U_EXPORT2 
 uscript_getShortName(UScriptCode scriptCode);
 
 U_STABLE 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
  * Gets the script code associated with the given codepoint.
  * Returns USCRIPT_MALAYALAM given 0x0D02 
  * @param codepoint UChar32 codepoint


@@ -219,4 +276,51 @@ uscript_getShortName(UScriptCode scriptCode);
 U_STABLE UScriptCode  U_EXPORT2 
 uscript_getScript(UChar32 codepoint, UErrorCode *err);
 
 U_STABLE UScriptCode  U_EXPORT2 
 uscript_getScript(UChar32 codepoint, UErrorCode *err);
 

+/**
+ * Is code point c used in script sc?
+ * That is, does code point c have the Script property value sc,
+ * or do code point c's Script_Extensions include script code sc?
+ *
+ * Some characters are commonly used in multiple scripts.
+ * For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
+ *
+ * The Script_Extensions property is provisional. It may be modified or removed
+ * in future versions of the Unicode Standard, and thus in ICU.
+ * @param c code point
+ * @param sc script code
+ * @return TRUE if Script(c)==sc or sc is in Script_Extensions(c)
+ * @draft ICU 4.6
+ */
+U_DRAFT 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.
+ *
+ * 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.)
+ *
+ * The Script_Extensions property is provisional. It may be modified or removed
+ * in future versions of the Unicode Standard, and thus in ICU.
+ * @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,
+ *         written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity
+ * @draft ICU 4.6
+ */
+U_DRAFT int32_t U_EXPORT2
+uscript_getScriptExtensions(UChar32 c,
+                            UScriptCode *scripts, int32_t capacity,
+                            UErrorCode *pErrorCode);
+

 #endif
 #endif