ICU-64260.0.1.tar.gz

[apple/icu.git] / icuSources / common / static_unicode_sets.h

diff --git a/icuSources/common/static_unicode_sets.h b/icuSources/common/static_unicode_sets.h
index 5f18b3217eae2bb5909165bdb31443db14cebc42..5d90ce5908de9817be4069ed717ff56f04d6fa0d 100644 (file)
--- a/icuSources/common/static_unicode_sets.h
+++ b/icuSources/common/static_unicode_sets.h
@@ -1,7 +1,17 @@
 // © 2018 and later: Unicode, Inc. and others.
 // License & terms of use: http://www.unicode.org/copyright.html
 
 // © 2018 and later: Unicode, Inc. and others.
 // License & terms of use: http://www.unicode.org/copyright.html
 

+// This file contains utilities to deal with static-allocated UnicodeSets.
+//
+// Common use case: you write a "private static final" UnicodeSet in Java, and
+// want something similarly easy in C++.  Originally written for number
+// parsing, but this header can be used for other applications.
+//
+// Main entrypoint: `unisets::get(unisets::MY_SET_ID_HERE)`
+//

 // This file is in common instead of i18n because it is needed by ucurr.cpp.
 // This file is in common instead of i18n because it is needed by ucurr.cpp.

+//
+// Author: sffc

 
 #include "unicode/utypes.h"
 
 
 #include "unicode/utypes.h"
 


@@ -35,6 +45,7 @@ enum Key {
     PERIOD,
     STRICT_COMMA,
     STRICT_PERIOD,
     PERIOD,
     STRICT_COMMA,
     STRICT_PERIOD,

+    APOSTROPHE_SIGN,

     OTHER_GROUPING_SEPARATORS,
     ALL_SEPARATORS,
     STRICT_ALL_SEPARATORS,
     OTHER_GROUPING_SEPARATORS,
     ALL_SEPARATORS,
     STRICT_ALL_SEPARATORS,


@@ -44,13 +55,14 @@ enum Key {
     PLUS_SIGN,
     PERCENT_SIGN,
     PERMILLE_SIGN,
     PLUS_SIGN,
     PERCENT_SIGN,
     PERMILLE_SIGN,

-    INFINITY_KEY, // INFINITY is defined in cmath
+    INFINITY_SIGN,

 
     // Currency Symbols
     DOLLAR_SIGN,
     POUND_SIGN,
     RUPEE_SIGN,
 
     // Currency Symbols
     DOLLAR_SIGN,
     POUND_SIGN,
     RUPEE_SIGN,

-    YEN_SIGN, // not in CLDR data, but Currency.java wants it
+    YEN_SIGN,
+    WON_SIGN,

 
     // Other
     DIGITS,
 
     // Other
     DIGITS,


@@ -60,7 +72,7 @@ enum Key {
     DIGITS_OR_STRICT_ALL_SEPARATORS,
 
     // The number of elements in the enum.
     DIGITS_OR_STRICT_ALL_SEPARATORS,
 
     // The number of elements in the enum.

-    COUNT
+    UNISETS_KEY_COUNT

 };
 
 /**
 };
 
 /**


@@ -69,6 +81,13 @@ enum Key {
  *
  * Exported as U_COMMON_API for ucurr.cpp
  *
  *
  * Exported as U_COMMON_API for ucurr.cpp
  *

+ * This method is always safe and OK to chain: in the case of a memory or other
+ * error, it returns an empty set from static memory.
+ * 
+ * Example:
+ * 
+ *     UBool hasIgnorables = unisets::get(unisets::DEFAULT_IGNORABLES)->contains(...);
+ *

  * @param key The desired UnicodeSet according to the enum in this file.
  * @return The requested UnicodeSet. Guaranteed to be frozen and non-null, but
  *         may be empty if an error occurred during data loading.
  * @param key The desired UnicodeSet according to the enum in this file.
  * @return The requested UnicodeSet. Guaranteed to be frozen and non-null, but
  *         may be empty if an error occurred during data loading.


@@ -99,6 +118,7 @@ U_COMMON_API Key chooseFrom(UnicodeString str, Key key1);
  */
 U_COMMON_API Key chooseFrom(UnicodeString str, Key key1, Key key2);
 
  */
 U_COMMON_API Key chooseFrom(UnicodeString str, Key key1, Key key2);
 

+// TODO: Load these from data: ICU-20108

 // Unused in C++:
 // Key chooseCurrency(UnicodeString str);
 // Used instead:
 // Unused in C++:
 // Key chooseCurrency(UnicodeString str);
 // Used instead:


@@ -108,8 +128,9 @@ static const struct {
 } kCurrencyEntries[] = {
     {DOLLAR_SIGN, u'$'},
     {POUND_SIGN, u'£'},
 } kCurrencyEntries[] = {
     {DOLLAR_SIGN, u'$'},
     {POUND_SIGN, u'£'},

-    {RUPEE_SIGN, u'â\82¨'},
+    {RUPEE_SIGN, u'â\82¹'},

     {YEN_SIGN, u'¥'},
     {YEN_SIGN, u'¥'},

+    {WON_SIGN, u'₩'},

 };
 
 } // namespace unisets
 };
 
 } // namespace unisets