Merge pull request #98496 from bruvzg/icu761

Update ICU to 76.1

modules/text_server_adv/SCsub

@@ -477,7 +477,7 @@ if env["builtin_icu4c"]:
     ]
     thirdparty_sources = [thirdparty_dir + file for file in thirdparty_sources]
 
-    icu_data_name = "icudt75l.dat"
+    icu_data_name = "icudt76l.dat"
 
     if env.editor_build:
         env_icu.Depends("#thirdparty/icu4c/icudata.gen.h", "#thirdparty/icu4c/" + icu_data_name)

modules/text_server_adv/gdextension_build/SConstruct

@@ -717,7 +717,7 @@ thirdparty_icu_sources = [
 ]
 thirdparty_icu_sources = [thirdparty_icu_dir + file for file in thirdparty_icu_sources]
 
-icu_data_name = "icudt75l.dat"
+icu_data_name = "icudt76l.dat"
 
 if env["static_icu_data"]:
     env_icu.Depends("../../../thirdparty/icu4c/icudata.gen.h", "../../../thirdparty/icu4c/" + icu_data_name)

modules/text_server_adv/text_server_adv.h

@@ -96,6 +96,11 @@ using namespace godot;
 
 // Thirdparty headers.
 
+#if defined(__GNUC__) && !defined(__clang__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wshadow"
+#endif
+
 #include <unicode/ubidi.h>
 #include <unicode/ubrk.h>
 #include <unicode/uchar.h>
@@ -109,6 +114,10 @@ using namespace godot;
 #include <unicode/ustring.h>
 #include <unicode/utypes.h>
 
+#if defined(__GNUC__) && !defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
+
 #ifdef MODULE_FREETYPE_ENABLED
 #include <ft2build.h>
 #include FT_FREETYPE_H

thirdparty/README.md

@@ -403,7 +403,7 @@ Files extracted from upstream source:
 ## icu4c
 
 - Upstream: https://github.com/unicode-org/icu
-- Version: 75.1 (7750081bda4b3bc1768ae03849ec70f67ea10625, 2024)
+- Version: 76.1 (8eca245c7484ac6cc179e3e5f7c1ea7680810f39, 2024)
 - License: Unicode
 
 Files extracted from upstream source:
@@ -415,7 +415,7 @@ Files extracted from upstream source:
 
 Files generated from upstream source:
 
-- The `icudt75l.dat` built with the provided `godot_data.json` config file (see
+- The `icudt76l.dat` built with the provided `godot_data.json` config file (see
   https://github.com/unicode-org/icu/blob/master/docs/userguide/icu_data/buildtool.md
   for instructions).
 
@@ -425,7 +425,7 @@ Files generated from upstream source:
 3. Reconfigure ICU with custom data config:
    `ICU_DATA_FILTER_FILE={GODOT_SOURCE}/thirdparty/icu4c/godot_data.json ./runConfigureICU {PLATFORM} --with-data-packaging=common`
 4. Delete `data/out` folder and rebuild data: `cd data && rm -rf ./out && make`
-5. Copy `source/data/out/icudt75l.dat` to the `{GODOT_SOURCE}/thirdparty/icu4c/icudt75l.dat`
+5. Copy `source/data/out/icudt76l.dat` to the `{GODOT_SOURCE}/thirdparty/icu4c/icudt76l.dat`
 
 
 ## jpeg-compressor

thirdparty/icu4c/LICENSE

@@ -433,6 +433,34 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 ----------------------------------------------------------------------
 
+JSON parsing library (nlohmann/json)
+
+File: vendor/json/upstream/single_include/nlohmann/json.hpp (only for ICU4C)
+
+MIT License
+
+Copyright (c) 2013-2022 Niels Lohmann
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+----------------------------------------------------------------------
+
 File: aclocal.m4 (only for ICU4C)
 Section: pkg.m4 - Macros to locate and utilise pkg-config.
 
@@ -473,7 +501,7 @@ File: config.guess (only for ICU4C)
 
 This file is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 3 of the License, or
+the Free Software Foundation, either version 3 of the License, or
 (at your option) any later version.
 
 This program is distributed in the hope that it will be useful, but

thirdparty/icu4c/common/appendable.cpp

@@ -25,7 +25,7 @@ Appendable::~Appendable() {}
 UBool
 Appendable::appendCodePoint(UChar32 c) {
     if(c<=0xffff) {
-        return appendCodeUnit((char16_t)c);
+        return appendCodeUnit(static_cast<char16_t>(c));
     } else {
         return appendCodeUnit(U16_LEAD(c)) && appendCodeUnit(U16_TRAIL(c));
     }

thirdparty/icu4c/common/bmpset.cpp

@@ -75,7 +75,7 @@ static void set32x64Bits(uint32_t table[64], int32_t start, int32_t limit) {
     int32_t trail=start&0x3f;  // Named for UTF-8 2-byte trail byte with lower 6 bits.
 
     // Set one bit indicating an all-one block.
-    uint32_t bits=(uint32_t)1<<lead;
+    uint32_t bits = static_cast<uint32_t>(1) << lead;
     if((start+1)==limit) {  // Single-character shortcut.
         table[trail]|=bits;
         return;
@@ -100,9 +100,9 @@ static void set32x64Bits(uint32_t table[64], int32_t start, int32_t limit) {
             ++lead;
         }
         if(lead<limitLead) {
-            bits=~(((unsigned)1<<lead)-1);
+            bits = ~((static_cast<unsigned>(1) << lead) - 1);
             if(limitLead<0x20) {
-                bits&=((unsigned)1<<limitLead)-1;
+                bits &= (static_cast<unsigned>(1) << limitLead) - 1;
             }
             for(trail=0; trail<64; ++trail) {
                 table[trail]|=bits;
@@ -111,7 +111,7 @@ static void set32x64Bits(uint32_t table[64], int32_t start, int32_t limit) {
         // limit<=0x800. If limit==0x800 then limitLead=32 and limitTrail=0.
         // In that case, bits=1<<limitLead is undefined but the bits value
         // is not used because trail<limitTrail is already false.
-        bits=(uint32_t)1<<((limitLead == 0x20) ? (limitLead - 1) : limitLead);
+        bits = static_cast<uint32_t>(1) << ((limitLead == 0x20) ? (limitLead - 1) : limitLead);
         for(trail=0; trail<limitTrail; ++trail) {
             table[trail]|=bits;
         }
@@ -290,22 +290,22 @@ int32_t BMPSet::findCodePoint(UChar32 c, int32_t lo, int32_t hi) const {
 
 UBool
 BMPSet::contains(UChar32 c) const {
-    if((uint32_t)c<=0xff) {
-        return (UBool)latin1Contains[c];
-    } else if((uint32_t)c<=0x7ff) {
-        return (UBool)((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))!=0);
-    } else if((uint32_t)c<0xd800 || (c>=0xe000 && c<=0xffff)) {
+    if (static_cast<uint32_t>(c) <= 0xff) {
+        return latin1Contains[c];
+    } else if (static_cast<uint32_t>(c) <= 0x7ff) {
+        return (table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) != 0;
+    } else if (static_cast<uint32_t>(c) < 0xd800 || (c >= 0xe000 && c <= 0xffff)) {
         int lead=c>>12;
         uint32_t twoBits=(bmpBlockBits[(c>>6)&0x3f]>>lead)&0x10001;
         if(twoBits<=1) {
             // All 64 code points with the same bits 15..6
             // are either in the set or not.
-            return (UBool)twoBits;
+            return twoBits;
         } else {
             // Look up the code point in its 4k block of code points.
             return containsSlow(c, list4kStarts[lead], list4kStarts[lead+1]);
         }
-    } else if((uint32_t)c<=0x10ffff) {
+    } else if (static_cast<uint32_t>(c) <= 0x10ffff) {
         // surrogate or supplementary code point
         return containsSlow(c, list4kStarts[0xd], list4kStarts[0x11]);
     } else {
@@ -332,7 +332,7 @@ BMPSet::span(const char16_t *s, const char16_t *limit, USetSpanCondition spanCon
                     break;
                 }
             } else if(c<=0x7ff) {
-                if((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))==0) {
+                if ((table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) == 0) {
                     break;
                 }
             } else if(c<0xd800 || c>=0xe000) {
@@ -372,7 +372,7 @@ BMPSet::span(const char16_t *s, const char16_t *limit, USetSpanCondition spanCon
                     break;
                 }
             } else if(c<=0x7ff) {
-                if((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))!=0) {
+                if ((table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) != 0) {
                     break;
                 }
             } else if(c<0xd800 || c>=0xe000) {
@@ -421,7 +421,7 @@ BMPSet::spanBack(const char16_t *s, const char16_t *limit, USetSpanCondition spa
                     break;
                 }
             } else if(c<=0x7ff) {
-                if((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))==0) {
+                if ((table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) == 0) {
                     break;
                 }
             } else if(c<0xd800 || c>=0xe000) {
@@ -464,7 +464,7 @@ BMPSet::spanBack(const char16_t *s, const char16_t *limit, USetSpanCondition spa
                     break;
                 }
             } else if(c<=0x7ff) {
-                if((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))!=0) {
+                if ((table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) != 0) {
                     break;
                 }
             } else if(c<0xd800 || c>=0xe000) {
@@ -527,7 +527,7 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
                 b=*s;
             } while(U8_IS_SINGLE(b));
         }
-        length=(int32_t)(limit-s);
+        length = static_cast<int32_t>(limit - s);
     }
 
     if(spanCondition!=USET_SPAN_NOT_CONTAINED) {
@@ -547,7 +547,7 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
      * the truncated sequence.
      */
     b=*(limit-1);
-    if((int8_t)b<0) {
+    if (static_cast<int8_t>(b) < 0) {
         // b>=0x80: lead or trail byte
         if(b<0xc0) {
             // single trail byte, check for preceding 3- or 4-byte lead byte
@@ -602,15 +602,15 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
         if(b>=0xe0) {
             if(b<0xf0) {
                 if( /* handle U+0000..U+FFFF inline */
-                    (t1=(uint8_t)(s[0]-0x80)) <= 0x3f &&
-                    (t2=(uint8_t)(s[1]-0x80)) <= 0x3f
+                    (t1 = static_cast<uint8_t>(s[0] - 0x80)) <= 0x3f &&
+                    (t2 = static_cast<uint8_t>(s[1] - 0x80)) <= 0x3f
                 ) {
                     b&=0xf;
                     uint32_t twoBits=(bmpBlockBits[t1]>>b)&0x10001;
                     if(twoBits<=1) {
                         // All 64 code points with this lead byte and middle trail byte
                         // are either in the set or not.
-                        if(twoBits!=(uint32_t)spanCondition) {
+                        if (twoBits != static_cast<uint32_t>(spanCondition)) {
                             return s-1;
                         }
                     } else {
@@ -624,12 +624,12 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
                     continue;
                 }
             } else if( /* handle U+10000..U+10FFFF inline */
-                (t1=(uint8_t)(s[0]-0x80)) <= 0x3f &&
-                (t2=(uint8_t)(s[1]-0x80)) <= 0x3f &&
-                (t3=(uint8_t)(s[2]-0x80)) <= 0x3f
+                (t1 = static_cast<uint8_t>(s[0] - 0x80)) <= 0x3f &&
+                (t2 = static_cast<uint8_t>(s[1] - 0x80)) <= 0x3f &&
+                (t3 = static_cast<uint8_t>(s[2] - 0x80)) <= 0x3f
             ) {
                 // Give an illegal sequence the same value as the result of contains(FFFD).
-                UChar32 c=((UChar32)(b-0xf0)<<18)|((UChar32)t1<<12)|(t2<<6)|t3;
+                UChar32 c = (static_cast<UChar32>(b - 0xf0) << 18) | (static_cast<UChar32>(t1) << 12) | (t2 << 6) | t3;
                 if( (   (0x10000<=c && c<=0x10ffff) ?
                             containsSlow(c, list4kStarts[0x10], list4kStarts[0x11]) :
                             containsFFFD
@@ -643,9 +643,9 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
         } else {
             if( /* handle U+0000..U+07FF inline */
                 b>=0xc0 &&
-                (t1=(uint8_t)(*s-0x80)) <= 0x3f
+                (t1 = static_cast<uint8_t>(*s - 0x80)) <= 0x3f
             ) {
-                if((USetSpanCondition)((table7FF[t1]&((uint32_t)1<<(b&0x1f)))!=0) != spanCondition) {
+                if (static_cast<USetSpanCondition>((table7FF[t1] & (static_cast<uint32_t>(1) << (b & 0x1f))) != 0) != spanCondition) {
                     return s-1;
                 }
                 ++s;
@@ -711,7 +711,7 @@ BMPSet::spanBackUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCon
         c=utf8_prevCharSafeBody(s, 0, &length, b, -3);
         // c is a valid code point, not ASCII, not a surrogate
         if(c<=0x7ff) {
-            if((USetSpanCondition)((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))!=0) != spanCondition) {
+            if (static_cast<USetSpanCondition>((table7FF[c & 0x3f] & (static_cast<uint32_t>(1) << (c >> 6))) != 0) != spanCondition) {
                 return prev+1;
             }
         } else if(c<=0xffff) {
@@ -720,7 +720,7 @@ BMPSet::spanBackUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCon
             if(twoBits<=1) {
                 // All 64 code points with the same bits 15..6
                 // are either in the set or not.
-                if(twoBits!=(uint32_t)spanCondition) {
+                if (twoBits != static_cast<uint32_t>(spanCondition)) {
                     return prev+1;
                 }
             } else {

thirdparty/icu4c/common/bmpset.h

@@ -156,7 +156,7 @@ private:
 };
 
 inline UBool BMPSet::containsSlow(UChar32 c, int32_t lo, int32_t hi) const {
-    return (UBool)(findCodePoint(c, lo, hi) & 1);
+    return findCodePoint(c, lo, hi) & 1;
 }
 
 U_NAMESPACE_END

thirdparty/icu4c/common/brkeng.cpp

@@ -86,7 +86,7 @@ UnhandledEngine::findBreaks( UText *text,
     if (U_FAILURE(status)) return 0;
     utext_setNativeIndex(text, startPos);
     UChar32 c = utext_current32(text);
-    while((int32_t)utext_getNativeIndex(text) < endPos && fHandled->contains(c)) {
+    while (static_cast<int32_t>(utext_getNativeIndex(text)) < endPos && fHandled->contains(c)) {
         utext_next32(text);            // TODO:  recast loop to work with post-increment operations.
         c = utext_current32(text);
     }
@@ -146,7 +146,7 @@ ICULanguageBreakFactory::getEngineFor(UChar32 c, const char* locale) {
     Mutex m(&gBreakEngineMutex);
     int32_t i = fEngines->size();
     while (--i >= 0) {
-        lbe = (const LanguageBreakEngine *)(fEngines->elementAt(i));
+        lbe = static_cast<const LanguageBreakEngine*>(fEngines->elementAt(i));
         if (lbe != nullptr && lbe->handles(c, locale)) {
             return lbe;
         }
@@ -259,7 +259,7 @@ ICULanguageBreakFactory::loadDictionaryMatcherFor(UScriptCode script) {
     CharString ext;
     const char16_t *extStart = u_memrchr(dictfname, 0x002e, dictnlength);  // last dot
     if (extStart != nullptr) {
-        int32_t len = (int32_t)(extStart - dictfname);
+        int32_t len = static_cast<int32_t>(extStart - dictfname);
         ext.appendInvariantChars(UnicodeString(false, extStart + 1, dictnlength - len - 1), status);
         dictnlength = len;
     }
@@ -269,18 +269,18 @@ ICULanguageBreakFactory::loadDictionaryMatcherFor(UScriptCode script) {
     UDataMemory *file = udata_open(U_ICUDATA_BRKITR, ext.data(), dictnbuf.data(), &status);
     if (U_SUCCESS(status)) {
         // build trie
-        const uint8_t *data = (const uint8_t *)udata_getMemory(file);
-        const int32_t *indexes = (const int32_t *)data;
+        const uint8_t* data = static_cast<const uint8_t*>(udata_getMemory(file));
+        const int32_t* indexes = reinterpret_cast<const int32_t*>(data);
         const int32_t offset = indexes[DictionaryData::IX_STRING_TRIE_OFFSET];
         const int32_t trieType = indexes[DictionaryData::IX_TRIE_TYPE] & DictionaryData::TRIE_TYPE_MASK;
         DictionaryMatcher *m = nullptr;
         if (trieType == DictionaryData::TRIE_TYPE_BYTES) {
             const int32_t transform = indexes[DictionaryData::IX_TRANSFORM];
-            const char *characters = (const char *)(data + offset);
+            const char* characters = reinterpret_cast<const char*>(data + offset);
             m = new BytesDictionaryMatcher(characters, transform, file);
         }
         else if (trieType == DictionaryData::TRIE_TYPE_UCHARS) {
-            const char16_t *characters = (const char16_t *)(data + offset);
+            const char16_t* characters = reinterpret_cast<const char16_t*>(data + offset);
             m = new UCharsDictionaryMatcher(characters, file);
         }
         if (m == nullptr) {
@@ -337,12 +337,12 @@ int32_t BreakEngineWrapper::findBreaks(
     //   extends towards the start or end of the text, depending on 'reverse'.
 
     utext_setNativeIndex(text, startPos);
-    int32_t start = (int32_t)utext_getNativeIndex(text);
+    int32_t start = static_cast<int32_t>(utext_getNativeIndex(text));
     int32_t current;
     int32_t rangeStart;
     int32_t rangeEnd;
     UChar32 c = utext_current32(text);
-    while((current = (int32_t)utext_getNativeIndex(text)) < endPos && delegate->handles(c)) {
+    while ((current = static_cast<int32_t>(utext_getNativeIndex(text))) < endPos && delegate->handles(c)) {
         utext_next32(text);         // TODO:  recast loop for postincrement
         c = utext_current32(text);
     }

thirdparty/icu4c/common/brkiter.cpp

@@ -85,7 +85,7 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &st
         // Get the actual string
         brkfname = ures_getString(brkName, &size, &status);
         U_ASSERT((size_t)size<sizeof(fnbuff));
-        if ((size_t)size>=sizeof(fnbuff)) {
+        if (static_cast<size_t>(size) >= sizeof(fnbuff)) {
             size=0;
             if (U_SUCCESS(status)) {
                 status = U_BUFFER_OVERFLOW_ERROR;
@@ -99,7 +99,7 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &st
             char16_t* extStart=u_strchr(brkfname, 0x002e);
             int len = 0;
             if (extStart != nullptr){
-                len = (int)(extStart-brkfname);
+                len = static_cast<int>(extStart - brkfname);
                 u_UCharsToChars(extStart+1, ext, sizeof(ext)); // nul terminates the buff
                 u_UCharsToChars(brkfname, fnbuff, len);
             }

thirdparty/icu4c/common/bytesinkutil.cpp

@@ -64,7 +64,7 @@ ByteSinkUtil::appendChange(const uint8_t *s, const uint8_t *limit,
         errorCode = U_INDEX_OUTOFBOUNDS_ERROR;
         return false;
     }
-    return appendChange((int32_t)(limit - s), s16, s16Length, sink, edits, errorCode);
+    return appendChange(static_cast<int32_t>(limit - s), s16, s16Length, sink, edits, errorCode);
 }
 
 void
@@ -81,15 +81,15 @@ ByteSinkUtil::appendCodePoint(int32_t length, UChar32 c, ByteSink &sink, Edits *
 namespace {
 
 // See unicode/utf8.h U8_APPEND_UNSAFE().
-inline uint8_t getTwoByteLead(UChar32 c) { return (uint8_t)((c >> 6) | 0xc0); }
-inline uint8_t getTwoByteTrail(UChar32 c) { return (uint8_t)((c & 0x3f) | 0x80); }
+inline uint8_t getTwoByteLead(UChar32 c) { return static_cast<uint8_t>((c >> 6) | 0xc0); }
+inline uint8_t getTwoByteTrail(UChar32 c) { return static_cast<uint8_t>((c & 0x3f) | 0x80); }
 
 }  // namespace
 
 void
 ByteSinkUtil::appendTwoBytes(UChar32 c, ByteSink &sink) {
     U_ASSERT(0x80 <= c && c <= 0x7ff);  // 2-byte UTF-8
-    char s8[2] = { (char)getTwoByteLead(c), (char)getTwoByteTrail(c) };
+    char s8[2] = {static_cast<char>(getTwoByteLead(c)), static_cast<char>(getTwoByteTrail(c))};
     sink.Append(s8, 2);
 }
 
@@ -114,7 +114,7 @@ ByteSinkUtil::appendUnchanged(const uint8_t *s, const uint8_t *limit,
         errorCode = U_INDEX_OUTOFBOUNDS_ERROR;
         return false;
     }
-    int32_t length = (int32_t)(limit - s);
+    int32_t length = static_cast<int32_t>(limit - s);
     if (length > 0) {
         appendNonEmptyUnchanged(s, length, sink, options, edits);
     }

thirdparty/icu4c/common/bytesinkutil.h

@@ -73,7 +73,7 @@ public:
     /** The few bytes at [src, nextSrc[ were mapped/changed to valid code point c. */
     static inline void appendCodePoint(const uint8_t *src, const uint8_t *nextSrc, UChar32 c,
                                        ByteSink &sink, Edits *edits = nullptr) {
-        appendCodePoint((int32_t)(nextSrc - src), c, sink, edits);
+        appendCodePoint(static_cast<int32_t>(nextSrc - src), c, sink, edits);
     }
 
     /** Append the two-byte character (U+0080..U+07FF). */

thirdparty/icu4c/common/bytestrie.cpp

@@ -327,7 +327,7 @@ BytesTrie::findUniqueValueFromBranch(const uint8_t *pos, int32_t length,
         ++pos;  // ignore a comparison byte
         // handle its value
         int32_t node=*pos++;
-        UBool isFinal=(UBool)(node&kValueIsFinal);
+        UBool isFinal = static_cast<UBool>(node & kValueIsFinal);
         int32_t value=readValue(pos, node>>1);
         pos=skipValue(pos, node);
         if(isFinal) {
@@ -366,7 +366,7 @@ BytesTrie::findUniqueValue(const uint8_t *pos, UBool haveUniqueValue, int32_t &u
             // linear-match node
             pos+=node-kMinLinearMatch+1;  // Ignore the match bytes.
         } else {
-            UBool isFinal=(UBool)(node&kValueIsFinal);
+            UBool isFinal = static_cast<UBool>(node & kValueIsFinal);
             int32_t value=readValue(pos, node>>1);
             if(haveUniqueValue) {
                 if(value!=uniqueValue) {
@@ -434,7 +434,7 @@ BytesTrie::getNextBranchBytes(const uint8_t *pos, int32_t length, ByteSink &out)
 
 void
 BytesTrie::append(ByteSink &out, int c) {
-    char ch=(char)c;
+    char ch = static_cast<char>(c);
     out.Append(&ch, 1);
 }
 

thirdparty/icu4c/common/bytestriebuilder.cpp

@@ -43,10 +43,10 @@ public:
         int32_t offset=stringOffset;
         int32_t length;
         if(offset>=0) {
-            length=(uint8_t)strings[offset++];
+            length = static_cast<uint8_t>(strings[offset++]);
         } else {
             offset=~offset;
-            length=((int32_t)(uint8_t)strings[offset]<<8)|(uint8_t)strings[offset+1];
+            length = (static_cast<int32_t>(static_cast<uint8_t>(strings[offset])) << 8) | static_cast<uint8_t>(strings[offset + 1]);
             offset+=2;
         }
         return StringPiece(strings.data()+offset, length);
@@ -54,10 +54,10 @@ public:
     int32_t getStringLength(const CharString &strings) const {
         int32_t offset=stringOffset;
         if(offset>=0) {
-            return (uint8_t)strings[offset];
+            return static_cast<uint8_t>(strings[offset]);
         } else {
             offset=~offset;
-            return ((int32_t)(uint8_t)strings[offset]<<8)|(uint8_t)strings[offset+1];
+            return (static_cast<int32_t>(static_cast<uint8_t>(strings[offset])) << 8) | static_cast<uint8_t>(strings[offset + 1]);
         }
     }
 
@@ -102,9 +102,9 @@ BytesTrieElement::setTo(StringPiece s, int32_t val,
     int32_t offset=strings.length();
     if(length>0xff) {
         offset=~offset;
-        strings.append((char)(length>>8), errorCode);
+        strings.append(static_cast<char>(length >> 8), errorCode);
     }
-    strings.append((char)length, errorCode);
+    strings.append(static_cast<char>(length), errorCode);
     stringOffset=offset;
     value=val;
     strings.append(s, errorCode);
@@ -229,7 +229,7 @@ BytesTrieBuilder::buildBytes(UStringTrieBuildOption buildOption, UErrorCode &err
             errorCode=U_INDEX_OUTOFBOUNDS_ERROR;
             return;
         }
-        uprv_sortArray(elements, elementsLength, (int32_t)sizeof(BytesTrieElement),
+        uprv_sortArray(elements, elementsLength, static_cast<int32_t>(sizeof(BytesTrieElement)),
                       compareElementStrings, strings,
                       false,  // need not be a stable sort
                       &errorCode);
@@ -284,7 +284,7 @@ BytesTrieBuilder::getElementStringLength(int32_t i) const {
 
 char16_t
 BytesTrieBuilder::getElementUnit(int32_t i, int32_t byteIndex) const {
-    return (uint8_t)elements[i].charAt(byteIndex, *strings);
+    return static_cast<uint8_t>(elements[i].charAt(byteIndex, *strings));
 }
 
 int32_t
@@ -330,7 +330,7 @@ BytesTrieBuilder::skipElementsBySomeUnits(int32_t i, int32_t byteIndex, int32_t
 
 int32_t
 BytesTrieBuilder::indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, char16_t byte) const {
-    char b=(char)byte;
+    char b = static_cast<char>(byte);
     while(b==elements[i].charAt(byteIndex, *strings)) {
         ++i;
     }
@@ -404,7 +404,7 @@ BytesTrieBuilder::write(int32_t byte) {
     int32_t newLength=bytesLength+1;
     if(ensureCapacity(newLength)) {
         bytesLength=newLength;
-        bytes[bytesCapacity-bytesLength]=(char)byte;
+        bytes[bytesCapacity - bytesLength] = static_cast<char>(byte);
     }
     return bytesLength;
 }
@@ -432,30 +432,30 @@ BytesTrieBuilder::writeValueAndFinal(int32_t i, UBool isFinal) {
     char intBytes[5];
     int32_t length=1;
     if(i<0 || i>0xffffff) {
-        intBytes[0]=(char)BytesTrie::kFiveByteValueLead;
-        intBytes[1]=(char)((uint32_t)i>>24);
-        intBytes[2]=(char)((uint32_t)i>>16);
-        intBytes[3]=(char)((uint32_t)i>>8);
-        intBytes[4]=(char)i;
+        intBytes[0] = static_cast<char>(BytesTrie::kFiveByteValueLead);
+        intBytes[1] = static_cast<char>(static_cast<uint32_t>(i) >> 24);
+        intBytes[2] = static_cast<char>(static_cast<uint32_t>(i) >> 16);
+        intBytes[3] = static_cast<char>(static_cast<uint32_t>(i) >> 8);
+        intBytes[4] = static_cast<char>(i);
         length=5;
     // } else if(i<=BytesTrie::kMaxOneByteValue) {
     //     intBytes[0]=(char)(BytesTrie::kMinOneByteValueLead+i);
     } else {
         if(i<=BytesTrie::kMaxTwoByteValue) {
-            intBytes[0]=(char)(BytesTrie::kMinTwoByteValueLead+(i>>8));
+            intBytes[0] = static_cast<char>(BytesTrie::kMinTwoByteValueLead + (i >> 8));
         } else {
             if(i<=BytesTrie::kMaxThreeByteValue) {
-                intBytes[0]=(char)(BytesTrie::kMinThreeByteValueLead+(i>>16));
+                intBytes[0] = static_cast<char>(BytesTrie::kMinThreeByteValueLead + (i >> 16));
             } else {
-                intBytes[0]=(char)BytesTrie::kFourByteValueLead;
-                intBytes[1]=(char)(i>>16);
+                intBytes[0] = static_cast<char>(BytesTrie::kFourByteValueLead);
+                intBytes[1] = static_cast<char>(i >> 16);
                 length=2;
             }
-            intBytes[length++]=(char)(i>>8);
+            intBytes[length++] = static_cast<char>(i >> 8);
         }
-        intBytes[length++]=(char)i;
+        intBytes[length++] = static_cast<char>(i);
     }
-    intBytes[0]=(char)((intBytes[0]<<1)|isFinal);
+    intBytes[0] = static_cast<char>((intBytes[0] << 1) | isFinal);
     return write(intBytes, length);
 }
 
@@ -484,28 +484,28 @@ int32_t
 BytesTrieBuilder::internalEncodeDelta(int32_t i, char intBytes[]) {
     U_ASSERT(i>=0);
     if(i<=BytesTrie::kMaxOneByteDelta) {
-        intBytes[0]=(char)i;
+        intBytes[0] = static_cast<char>(i);
         return 1;
     }
     int32_t length=1;
     if(i<=BytesTrie::kMaxTwoByteDelta) {
-        intBytes[0]=(char)(BytesTrie::kMinTwoByteDeltaLead+(i>>8));
+        intBytes[0] = static_cast<char>(BytesTrie::kMinTwoByteDeltaLead + (i >> 8));
     } else {
         if(i<=BytesTrie::kMaxThreeByteDelta) {
-            intBytes[0]=(char)(BytesTrie::kMinThreeByteDeltaLead+(i>>16));
+            intBytes[0] = static_cast<char>(BytesTrie::kMinThreeByteDeltaLead + (i >> 16));
         } else {
             if(i<=0xffffff) {
-                intBytes[0]=(char)BytesTrie::kFourByteDeltaLead;
+                intBytes[0] = static_cast<char>(BytesTrie::kFourByteDeltaLead);
             } else {
-                intBytes[0]=(char)BytesTrie::kFiveByteDeltaLead;
-                intBytes[1]=(char)(i>>24);
+                intBytes[0] = static_cast<char>(BytesTrie::kFiveByteDeltaLead);
+                intBytes[1] = static_cast<char>(i >> 24);
                 length=2;
             }
-            intBytes[length++]=(char)(i>>16);
+            intBytes[length++] = static_cast<char>(i >> 16);
         }
-        intBytes[length++]=(char)(i>>8);
+        intBytes[length++] = static_cast<char>(i >> 8);
     }
-    intBytes[length++]=(char)i;
+    intBytes[length++] = static_cast<char>(i);
     return length;
 }
 

thirdparty/icu4c/common/bytestrieiterator.cpp

@@ -115,14 +115,14 @@ BytesTrie::Iterator::next(UErrorCode &errorCode) {
         pos=bytes_+stack_->elementAti(stackSize-2);
         stack_->setSize(stackSize-2);
         str_->truncate(length&0xffff);
-        length=(int32_t)((uint32_t)length>>16);
+        length = static_cast<int32_t>(static_cast<uint32_t>(length) >> 16);
         if(length>1) {
             pos=branchNext(pos, length, errorCode);
             if(pos==nullptr) {
                 return true;  // Reached a final value.
             }
         } else {
-            str_->append((char)*pos++, errorCode);
+            str_->append(static_cast<char>(*pos++), errorCode);
         }
     }
     if(remainingMatchLength_>=0) {
@@ -134,7 +134,7 @@ BytesTrie::Iterator::next(UErrorCode &errorCode) {
         int32_t node=*pos++;
         if(node>=kMinValueLead) {
             // Deliver value for the byte sequence so far.
-            UBool isFinal=(UBool)(node&kValueIsFinal);
+            UBool isFinal = static_cast<UBool>(node & kValueIsFinal);
             value_=readValue(pos, node>>1);
             if(isFinal || (maxLength_>0 && str_->length()==maxLength_)) {
                 pos_=nullptr;
@@ -186,7 +186,7 @@ BytesTrie::Iterator::branchNext(const uint8_t *pos, int32_t length, UErrorCode &
     while(length>kMaxBranchLinearSubNodeLength) {
         ++pos;  // ignore the comparison byte
         // Push state for the greater-or-equal edge.
-        stack_->addElement((int32_t)(skipDelta(pos)-bytes_), errorCode);
+        stack_->addElement(static_cast<int32_t>(skipDelta(pos) - bytes_), errorCode);
         stack_->addElement(((length-(length>>1))<<16)|str_->length(), errorCode);
         // Follow the less-than edge.
         length>>=1;
@@ -196,12 +196,12 @@ BytesTrie::Iterator::branchNext(const uint8_t *pos, int32_t length, UErrorCode &
     // Read the first (key, value) pair.
     uint8_t trieByte=*pos++;
     int32_t node=*pos++;
-    UBool isFinal=(UBool)(node&kValueIsFinal);
+    UBool isFinal = static_cast<UBool>(node & kValueIsFinal);
     int32_t value=readValue(pos, node>>1);
     pos=skipValue(pos, node);
-    stack_->addElement((int32_t)(pos-bytes_), errorCode);
+    stack_->addElement(static_cast<int32_t>(pos - bytes_), errorCode);
     stack_->addElement(((length-1)<<16)|str_->length(), errorCode);
-    str_->append((char)trieByte, errorCode);
+    str_->append(static_cast<char>(trieByte), errorCode);
     if(isFinal) {
         pos_=nullptr;
         value_=value;

thirdparty/icu4c/common/caniter.cpp

@@ -183,10 +183,10 @@ void CanonicalIterator::setSource(const UnicodeString &newSource, UErrorCode &st
 
     // catch degenerate case
     if (newSource.length() == 0) {
-        pieces = (UnicodeString **)uprv_malloc(sizeof(UnicodeString *));
-        pieces_lengths = (int32_t*)uprv_malloc(1 * sizeof(int32_t));
+        pieces = static_cast<UnicodeString**>(uprv_malloc(sizeof(UnicodeString*)));
+        pieces_lengths = static_cast<int32_t*>(uprv_malloc(1 * sizeof(int32_t)));
         pieces_length = 1;
-        current = (int32_t*)uprv_malloc(1 * sizeof(int32_t));
+        current = static_cast<int32_t*>(uprv_malloc(1 * sizeof(int32_t)));
         current_length = 1;
         if (pieces == nullptr || pieces_lengths == nullptr || current == nullptr) {
             status = U_MEMORY_ALLOCATION_ERROR;
@@ -229,10 +229,10 @@ void CanonicalIterator::setSource(const UnicodeString &newSource, UErrorCode &st
 
 
     // allocate the arrays, and find the strings that are CE to each segment
-    pieces = (UnicodeString **)uprv_malloc(list_length * sizeof(UnicodeString *));
+    pieces = static_cast<UnicodeString**>(uprv_malloc(list_length * sizeof(UnicodeString*)));
     pieces_length = list_length;
-    pieces_lengths = (int32_t*)uprv_malloc(list_length * sizeof(int32_t));
-    current = (int32_t*)uprv_malloc(list_length * sizeof(int32_t));
+    pieces_lengths = static_cast<int32_t*>(uprv_malloc(list_length * sizeof(int32_t)));
+    current = static_cast<int32_t*>(uprv_malloc(list_length * sizeof(int32_t)));
     current_length = list_length;
     if (pieces == nullptr || pieces_lengths == nullptr || current == nullptr) {
         status = U_MEMORY_ALLOCATION_ERROR;
@@ -330,7 +330,7 @@ void U_EXPORT2 CanonicalIterator::permute(UnicodeString &source, UBool skipZeros
         // prefix this character to all of them
         ne = subpermute.nextElement(el);
         while (ne != nullptr) {
-            UnicodeString *permRes = (UnicodeString *)(ne->value.pointer);
+            UnicodeString* permRes = static_cast<UnicodeString*>(ne->value.pointer);
             UnicodeString *chStr = new UnicodeString(cp);
             //test for nullptr
             if (chStr == nullptr) {
@@ -363,6 +363,9 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
     char16_t USeg[256];
     int32_t segLen = segment.extract(USeg, 256, status);
     getEquivalents2(&basic, USeg, segLen, status);
+    if (U_FAILURE(status)) {
+        return nullptr;
+    }
 
     // now get all the permutations
     // add only the ones that are canonically equivalent
@@ -375,7 +378,7 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
     //while (it.hasNext())
     while (ne != nullptr) {
         //String item = (String) it.next();
-        UnicodeString item = *((UnicodeString *)(ne->value.pointer));
+        UnicodeString item = *static_cast<UnicodeString*>(ne->value.pointer);
 
         permutations.removeAll();
         permute(item, CANITER_SKIP_ZEROES, &permutations, status);
@@ -387,7 +390,7 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
         while (ne2 != nullptr) {
             //String possible = (String) it2.next();
             //UnicodeString *possible = new UnicodeString(*((UnicodeString *)(ne2->value.pointer)));
-            UnicodeString possible(*((UnicodeString *)(ne2->value.pointer)));
+            UnicodeString possible(*static_cast<UnicodeString*>(ne2->value.pointer));
             UnicodeString attempt;
             nfd->normalize(possible, attempt, status);
 
@@ -429,7 +432,7 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
     el = UHASH_FIRST;
     ne = result.nextElement(el);
     while(ne != nullptr) {
-        finalResult[result_len++] = *((UnicodeString *)(ne->value.pointer));
+        finalResult[result_len++] = *static_cast<UnicodeString*>(ne->value.pointer);
         ne = result.nextElement(el);
     }
 
@@ -466,6 +469,9 @@ Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const cha
             Hashtable remainder(status);
             remainder.setValueDeleter(uprv_deleteUObject);
             if (extract(&remainder, cp2, segment, segLen, i, status) == nullptr) {
+                if (U_FAILURE(status)) {
+                    return nullptr;
+                }
                 continue;
             }
 
@@ -476,7 +482,7 @@ Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const cha
             int32_t el = UHASH_FIRST;
             const UHashElement *ne = remainder.nextElement(el);
             while (ne != nullptr) {
-                UnicodeString item = *((UnicodeString *)(ne->value.pointer));
+                UnicodeString item = *static_cast<UnicodeString*>(ne->value.pointer);
                 UnicodeString *toAdd = new UnicodeString(prefix);
                 /* test for nullptr */
                 if (toAdd == nullptr) {
@@ -490,6 +496,13 @@ Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const cha
 
                 ne = remainder.nextElement(el);
             }
+            // ICU-22642 Guards against strings that have so many permutations
+            // that they would otherwise hang the function.
+            constexpr int32_t kResultLimit = 4096;
+            if (fillinResult->count() > kResultLimit) {
+                status = U_UNSUPPORTED_ERROR;
+                return nullptr;
+            }
         }
     }
 

thirdparty/icu4c/common/characterproperties.cpp

@@ -58,17 +58,17 @@ icu::UMutex cpMutex;
 // Does not use uset.h to reduce code dependencies
 void U_CALLCONV
 _set_add(USet *set, UChar32 c) {
-    ((UnicodeSet *)set)->add(c);
+    reinterpret_cast<UnicodeSet*>(set)->add(c);
 }
 
 void U_CALLCONV
 _set_addRange(USet *set, UChar32 start, UChar32 end) {
-    ((UnicodeSet *)set)->add(start, end);
+    reinterpret_cast<UnicodeSet*>(set)->add(start, end);
 }
 
 void U_CALLCONV
 _set_addString(USet *set, const char16_t *str, int32_t length) {
-    ((UnicodeSet *)set)->add(icu::UnicodeString((UBool)(length<0), str, length));
+    reinterpret_cast<UnicodeSet*>(set)->add(icu::UnicodeString(static_cast<UBool>(length < 0), str, length));
 }
 
 UBool U_CALLCONV characterproperties_cleanup() {
@@ -103,7 +103,7 @@ void U_CALLCONV initInclusion(UPropertySource src, UErrorCode &errorCode) {
         return;
     }
     USetAdder sa = {
-        (USet *)incl.getAlias(),
+        reinterpret_cast<USet*>(incl.getAlias()),
         _set_add,
         _set_addRange,
         _set_addString,
@@ -184,8 +184,12 @@ void U_CALLCONV initInclusion(UPropertySource src, UErrorCode &errorCode) {
         sa.add(sa.set, 0x2FFF + 1);
         break;
     case UPROPS_SRC_ID_COMPAT_MATH:
+    case UPROPS_SRC_MCM:
         uprops_addPropertyStarts(src, &sa, &errorCode);
         break;
+    case UPROPS_SRC_BLOCK:
+        ublock_addPropertyStarts(&sa, errorCode);
+        break;
     default:
         errorCode = U_INTERNAL_PROGRAM_ERROR;
         break;
@@ -289,7 +293,7 @@ UnicodeSet *makeSet(UProperty property, UErrorCode &errorCode) {
         const icu::EmojiProps *ep = icu::EmojiProps::getSingleton(errorCode);
         if (U_FAILURE(errorCode)) { return nullptr; }
         USetAdder sa = {
-            (USet *)set.getAlias(),
+            reinterpret_cast<USet*>(set.getAlias()),
             _set_add,
             _set_addRange,
             _set_addString,

thirdparty/icu4c/common/cstring.cpp

@@ -126,7 +126,7 @@ T_CString_toLowerCase(char* str)
 
     if (str) {
         do
-            *str = (char)uprv_tolower(*str);
+            *str = uprv_tolower(*str);
         while (*(str++));
     }
 
@@ -140,7 +140,7 @@ T_CString_toUpperCase(char* str)
 
     if (str) {
         do
-            *str = (char)uprv_toupper(*str);
+            *str = uprv_toupper(*str);
         while (*(str++));
     }
 

thirdparty/icu4c/common/dictbe.cpp

@@ -61,12 +61,12 @@ DictionaryBreakEngine::findBreaks( UText *text,
     //   extends towards the start or end of the text, depending on 'reverse'.
 
     utext_setNativeIndex(text, startPos);
-    int32_t start = (int32_t)utext_getNativeIndex(text);
+    int32_t start = static_cast<int32_t>(utext_getNativeIndex(text));
     int32_t current;
     int32_t rangeStart;
     int32_t rangeEnd;
     UChar32 c = utext_current32(text);
-    while((current = (int32_t)utext_getNativeIndex(text)) < endPos && fSet.contains(c)) {
+    while ((current = static_cast<int32_t>(utext_getNativeIndex(text))) < endPos && fSet.contains(c)) {
         utext_next32(text);         // TODO:  recast loop for postincrement
         c = utext_current32(text);
     }
@@ -137,7 +137,7 @@ public:
 
 int32_t PossibleWord::candidates( UText *text, DictionaryMatcher *dict, int32_t rangeEnd ) {
     // TODO: If getIndex is too slow, use offset < 0 and add discardAll()
-    int32_t start = (int32_t)utext_getNativeIndex(text);
+    int32_t start = static_cast<int32_t>(utext_getNativeIndex(text));
     if (start != offset) {
         offset = start;
         count = dict->matches(text, rangeEnd-start, UPRV_LENGTHOF(cuLengths), cuLengths, cpLengths, nullptr, &prefix);
@@ -253,7 +253,7 @@ ThaiBreakEngine::divideUpDictionaryRange( UText *text,
     
     utext_setNativeIndex(text, rangeStart);
     
-    while (U_SUCCESS(status) && (current = (int32_t)utext_getNativeIndex(text)) < rangeEnd) {
+    while (U_SUCCESS(status) && (current = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd) {
         cpWordLength = 0;
         cuWordLength = 0;
 
@@ -269,7 +269,7 @@ ThaiBreakEngine::divideUpDictionaryRange( UText *text,
         // If there was more than one, see which one can take us forward the most words
         else if (candidates > 1) {
             // If we're already at the end of the range, we're done
-            if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+            if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                 goto foundBest;
             }
             do {
@@ -278,7 +278,7 @@ ThaiBreakEngine::divideUpDictionaryRange( UText *text,
                     words[wordsFound%THAI_LOOKAHEAD].markCurrent();
                     
                     // If we're already at the end of the range, we're done
-                    if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+                    if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                         goto foundBest;
                     }
                     
@@ -308,7 +308,7 @@ foundBest:
         // The text iterator should now be positioned at the end of the word we found.
         
         UChar32 uc = 0;
-        if ((int32_t)utext_getNativeIndex(text) < rangeEnd &&  cpWordLength < THAI_ROOT_COMBINE_THRESHOLD) {
+        if (static_cast<int32_t>(utext_getNativeIndex(text)) < rangeEnd && cpWordLength < THAI_ROOT_COMBINE_THRESHOLD) {
             // if it is a dictionary word, do nothing. If it isn't, then if there is
             // no preceding word, or the non-word shares less than the minimum threshold
             // of characters with a dictionary word, then scan to resynchronize
@@ -320,9 +320,9 @@ foundBest:
                 UChar32 pc;
                 int32_t chars = 0;
                 for (;;) {
-                    int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
+                    int32_t pcIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                     pc = utext_next32(text);
-                    int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
+                    int32_t pcSize = static_cast<int32_t>(utext_getNativeIndex(text)) - pcIndex;
                     chars += pcSize;
                     remaining -= pcSize;
                     if (remaining <= 0) {
@@ -356,28 +356,28 @@ foundBest:
                 utext_setNativeIndex(text, current+cuWordLength);
             }
         }
-        
+
         // Never stop before a combining mark.
         int32_t currPos;
-        while ((currPos = (int32_t)utext_getNativeIndex(text)) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
+        while ((currPos = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
             utext_next32(text);
-            cuWordLength += (int32_t)utext_getNativeIndex(text) - currPos;
+            cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - currPos;
         }
-        
+
         // Look ahead for possible suffixes if a dictionary word does not follow.
         // We do this in code rather than using a rule so that the heuristic
         // resynch continues to function. For example, one of the suffix characters
         // could be a typo in the middle of a word.
-        if ((int32_t)utext_getNativeIndex(text) < rangeEnd && cuWordLength > 0) {
+        if (static_cast<int32_t>(utext_getNativeIndex(text)) < rangeEnd && cuWordLength > 0) {
             if (words[wordsFound%THAI_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) <= 0
                 && fSuffixSet.contains(uc = utext_current32(text))) {
                 if (uc == THAI_PAIYANNOI) {
                     if (!fSuffixSet.contains(utext_previous32(text))) {
                         // Skip over previous end and PAIYANNOI
                         utext_next32(text);
-                        int32_t paiyannoiIndex = (int32_t)utext_getNativeIndex(text);
+                        int32_t paiyannoiIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                         utext_next32(text);
-                        cuWordLength += (int32_t)utext_getNativeIndex(text) - paiyannoiIndex;    // Add PAIYANNOI to word
+                        cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - paiyannoiIndex; // Add PAIYANNOI to word
                         uc = utext_current32(text);     // Fetch next character
                     }
                     else {
@@ -389,9 +389,9 @@ foundBest:
                     if (utext_previous32(text) != THAI_MAIYAMOK) {
                         // Skip over previous end and MAIYAMOK
                         utext_next32(text);
-                        int32_t maiyamokIndex = (int32_t)utext_getNativeIndex(text);
+                        int32_t maiyamokIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                         utext_next32(text);
-                        cuWordLength += (int32_t)utext_getNativeIndex(text) - maiyamokIndex;    // Add MAIYAMOK to word
+                        cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - maiyamokIndex; // Add MAIYAMOK to word
                     }
                     else {
                         // Restore prior position
@@ -489,7 +489,7 @@ LaoBreakEngine::divideUpDictionaryRange( UText *text,
 
     utext_setNativeIndex(text, rangeStart);
 
-    while (U_SUCCESS(status) && (current = (int32_t)utext_getNativeIndex(text)) < rangeEnd) {
+    while (U_SUCCESS(status) && (current = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd) {
         cuWordLength = 0;
         cpWordLength = 0;
 
@@ -514,7 +514,7 @@ LaoBreakEngine::divideUpDictionaryRange( UText *text,
                     words[wordsFound%LAO_LOOKAHEAD].markCurrent();
                     
                     // If we're already at the end of the range, we're done
-                    if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+                    if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                         goto foundBest;
                     }
                     
@@ -541,7 +541,7 @@ foundBest:
         // just found (if there is one), but only if the preceding word does not exceed
         // the threshold.
         // The text iterator should now be positioned at the end of the word we found.
-        if ((int32_t)utext_getNativeIndex(text) < rangeEnd && cpWordLength < LAO_ROOT_COMBINE_THRESHOLD) {
+        if (static_cast<int32_t>(utext_getNativeIndex(text)) < rangeEnd && cpWordLength < LAO_ROOT_COMBINE_THRESHOLD) {
             // if it is a dictionary word, do nothing. If it isn't, then if there is
             // no preceding word, or the non-word shares less than the minimum threshold
             // of characters with a dictionary word, then scan to resynchronize
@@ -554,9 +554,9 @@ foundBest:
                 UChar32 uc;
                 int32_t chars = 0;
                 for (;;) {
-                    int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
+                    int32_t pcIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                     pc = utext_next32(text);
-                    int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
+                    int32_t pcSize = static_cast<int32_t>(utext_getNativeIndex(text)) - pcIndex;
                     chars += pcSize;
                     remaining -= pcSize;
                     if (remaining <= 0) {
@@ -590,9 +590,9 @@ foundBest:
         
         // Never stop before a combining mark.
         int32_t currPos;
-        while ((currPos = (int32_t)utext_getNativeIndex(text)) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
+        while ((currPos = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
             utext_next32(text);
-            cuWordLength += (int32_t)utext_getNativeIndex(text) - currPos;
+            cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - currPos;
         }
         
         // Look ahead for possible suffixes if a dictionary word does not follow.
@@ -682,7 +682,7 @@ BurmeseBreakEngine::divideUpDictionaryRange( UText *text,
 
     utext_setNativeIndex(text, rangeStart);
 
-    while (U_SUCCESS(status) && (current = (int32_t)utext_getNativeIndex(text)) < rangeEnd) {
+    while (U_SUCCESS(status) && (current = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd) {
         cuWordLength = 0;
         cpWordLength = 0;
 
@@ -707,7 +707,7 @@ BurmeseBreakEngine::divideUpDictionaryRange( UText *text,
                     words[wordsFound%BURMESE_LOOKAHEAD].markCurrent();
                     
                     // If we're already at the end of the range, we're done
-                    if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+                    if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                         goto foundBest;
                     }
                     
@@ -734,7 +734,7 @@ foundBest:
         // just found (if there is one), but only if the preceding word does not exceed
         // the threshold.
         // The text iterator should now be positioned at the end of the word we found.
-        if ((int32_t)utext_getNativeIndex(text) < rangeEnd && cpWordLength < BURMESE_ROOT_COMBINE_THRESHOLD) {
+        if (static_cast<int32_t>(utext_getNativeIndex(text)) < rangeEnd && cpWordLength < BURMESE_ROOT_COMBINE_THRESHOLD) {
             // if it is a dictionary word, do nothing. If it isn't, then if there is
             // no preceding word, or the non-word shares less than the minimum threshold
             // of characters with a dictionary word, then scan to resynchronize
@@ -747,9 +747,9 @@ foundBest:
                 UChar32 uc;
                 int32_t chars = 0;
                 for (;;) {
-                    int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
+                    int32_t pcIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                     pc = utext_next32(text);
-                    int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
+                    int32_t pcSize = static_cast<int32_t>(utext_getNativeIndex(text)) - pcIndex;
                     chars += pcSize;
                     remaining -= pcSize;
                     if (remaining <= 0) {
@@ -783,9 +783,9 @@ foundBest:
         
         // Never stop before a combining mark.
         int32_t currPos;
-        while ((currPos = (int32_t)utext_getNativeIndex(text)) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
+        while ((currPos = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
             utext_next32(text);
-            cuWordLength += (int32_t)utext_getNativeIndex(text) - currPos;
+            cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - currPos;
         }
         
         // Look ahead for possible suffixes if a dictionary word does not follow.
@@ -888,7 +888,7 @@ KhmerBreakEngine::divideUpDictionaryRange( UText *text,
 
     utext_setNativeIndex(text, rangeStart);
 
-    while (U_SUCCESS(status) && (current = (int32_t)utext_getNativeIndex(text)) < rangeEnd) {
+    while (U_SUCCESS(status) && (current = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd) {
         cuWordLength = 0;
         cpWordLength = 0;
 
@@ -905,7 +905,7 @@ KhmerBreakEngine::divideUpDictionaryRange( UText *text,
         // If there was more than one, see which one can take us forward the most words
         else if (candidates > 1) {
             // If we're already at the end of the range, we're done
-            if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+            if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                 goto foundBest;
             }
             do {
@@ -914,7 +914,7 @@ KhmerBreakEngine::divideUpDictionaryRange( UText *text,
                     words[wordsFound % KHMER_LOOKAHEAD].markCurrent();
 
                     // If we're already at the end of the range, we're done
-                    if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {
+                    if (static_cast<int32_t>(utext_getNativeIndex(text)) >= rangeEnd) {
                         goto foundBest;
                     }
 
@@ -941,7 +941,7 @@ foundBest:
         // just found (if there is one), but only if the preceding word does not exceed
         // the threshold.
         // The text iterator should now be positioned at the end of the word we found.
-        if ((int32_t)utext_getNativeIndex(text) < rangeEnd && cpWordLength < KHMER_ROOT_COMBINE_THRESHOLD) {
+        if (static_cast<int32_t>(utext_getNativeIndex(text)) < rangeEnd && cpWordLength < KHMER_ROOT_COMBINE_THRESHOLD) {
             // if it is a dictionary word, do nothing. If it isn't, then if there is
             // no preceding word, or the non-word shares less than the minimum threshold
             // of characters with a dictionary word, then scan to resynchronize
@@ -954,9 +954,9 @@ foundBest:
                 UChar32 uc;
                 int32_t chars = 0;
                 for (;;) {
-                    int32_t pcIndex = (int32_t)utext_getNativeIndex(text);
+                    int32_t pcIndex = static_cast<int32_t>(utext_getNativeIndex(text));
                     pc = utext_next32(text);
-                    int32_t pcSize = (int32_t)utext_getNativeIndex(text) - pcIndex;
+                    int32_t pcSize = static_cast<int32_t>(utext_getNativeIndex(text)) - pcIndex;
                     chars += pcSize;
                     remaining -= pcSize;
                     if (remaining <= 0) {
@@ -989,9 +989,9 @@ foundBest:
 
         // Never stop before a combining mark.
         int32_t currPos;
-        while ((currPos = (int32_t)utext_getNativeIndex(text)) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
+        while ((currPos = static_cast<int32_t>(utext_getNativeIndex(text))) < rangeEnd && fMarkSet.contains(utext_current32(text))) {
             utext_next32(text);
-            cuWordLength += (int32_t)utext_getNativeIndex(text) - currPos;
+            cuWordLength += static_cast<int32_t>(utext_getNativeIndex(text)) - currPos;
         }
 
         // Look ahead for possible suffixes if a dictionary word does not follow.
@@ -1120,7 +1120,7 @@ static inline bool isKatakana(UChar32 value) {
 //   Replicates an internal UText function.
 
 static inline int32_t utext_i32_flag(int32_t bitIndex) {
-    return (int32_t)1 << bitIndex;
+    return static_cast<int32_t>(1) << bitIndex;
 }
        
 /*
@@ -1167,14 +1167,14 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
         int32_t limit = rangeEnd;
         U_ASSERT(limit <= utext_nativeLength(inText));
         if (limit > utext_nativeLength(inText)) {
-            limit = (int32_t)utext_nativeLength(inText);
+            limit = static_cast<int32_t>(utext_nativeLength(inText));
         }
         inputMap.adoptInsteadAndCheckErrorCode(new UVector32(status), status);
         if (U_FAILURE(status)) {
             return 0;
         }
         while (utext_getNativeIndex(inText) < limit) {
-            int32_t nativePosition = (int32_t)utext_getNativeIndex(inText);
+            int32_t nativePosition = static_cast<int32_t>(utext_getNativeIndex(inText));
             UChar32 c = utext_next32(inText);
             U_ASSERT(c != U_SENTINEL);
             inString.append(c);
@@ -1304,7 +1304,7 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
     int32_t ix = 0;
     bool is_prev_katakana = false;
     for (int32_t i = 0;  i < numCodePts;  ++i, ix = inString.moveIndex32(ix, 1)) {
-        if ((uint32_t)bestSnlp.elementAti(i) == kuint32max) {
+        if (static_cast<uint32_t>(bestSnlp.elementAti(i)) == kuint32max) {
             continue;
         }
 
@@ -1327,9 +1327,9 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
         }
 
         for (int32_t j = 0; j < count; j++) {
-            uint32_t newSnlp = (uint32_t)bestSnlp.elementAti(i) + (uint32_t)values.elementAti(j);
+            uint32_t newSnlp = static_cast<uint32_t>(bestSnlp.elementAti(i)) + static_cast<uint32_t>(values.elementAti(j));
             int32_t ln_j_i = lengths.elementAti(j) + i;
-            if (newSnlp < (uint32_t)bestSnlp.elementAti(ln_j_i)) {
+            if (newSnlp < static_cast<uint32_t>(bestSnlp.elementAti(ln_j_i))) {
                 bestSnlp.setElementAt(newSnlp, ln_j_i);
                 prev.setElementAt(i, ln_j_i);
             }
@@ -1353,7 +1353,7 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
             }
             if (katakanaRunLength < kMaxKatakanaGroupLength) {
                 uint32_t newSnlp = bestSnlp.elementAti(i) + getKatakanaCost(katakanaRunLength);
-                if (newSnlp < (uint32_t)bestSnlp.elementAti(i+katakanaRunLength)) {
+                if (newSnlp < static_cast<uint32_t>(bestSnlp.elementAti(i + katakanaRunLength))) {
                     bestSnlp.setElementAt(newSnlp, i+katakanaRunLength);
                     prev.setElementAt(i, i+katakanaRunLength);  // prev[j] = i;
                 }
@@ -1371,7 +1371,7 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
 
     int32_t numBreaks = 0;
     // No segmentation found, set boundary to end of range
-    if ((uint32_t)bestSnlp.elementAti(numCodePts) == kuint32max) {
+    if (static_cast<uint32_t>(bestSnlp.elementAti(numCodePts)) == kuint32max) {
         t_boundary.addElement(numCodePts, status);
         numBreaks++;
     } else if (isPhraseBreaking) {

thirdparty/icu4c/common/dictionarydata.cpp

@@ -47,13 +47,13 @@ int32_t UCharsDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t
                             int32_t *prefix) const {
 
     UCharsTrie uct(characters);
-    int32_t startingTextIndex = (int32_t)utext_getNativeIndex(text);
+    int32_t startingTextIndex = static_cast<int32_t>(utext_getNativeIndex(text));
     int32_t wordCount = 0;
     int32_t codePointsMatched = 0;
 
     for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
         UStringTrieResult result = (codePointsMatched == 0) ? uct.first(c) : uct.next(c);
-        int32_t lengthMatched = (int32_t)utext_getNativeIndex(text) - startingTextIndex;
+        int32_t lengthMatched = static_cast<int32_t>(utext_getNativeIndex(text)) - startingTextIndex;
         codePointsMatched += 1;
         if (USTRINGTRIE_HAS_VALUE(result)) {
             if (wordCount < limit) {
@@ -101,7 +101,7 @@ UChar32 BytesDictionaryMatcher::transform(UChar32 c) const {
         if (delta < 0 || 0xFD < delta) {
             return U_SENTINEL;
         }
-        return (UChar32)delta;
+        return static_cast<UChar32>(delta);
     }
     return c;
 }
@@ -114,13 +114,13 @@ int32_t BytesDictionaryMatcher::matches(UText *text, int32_t maxLength, int32_t
                             int32_t *lengths, int32_t *cpLengths, int32_t *values,
                             int32_t *prefix) const {
     BytesTrie bt(characters);
-    int32_t startingTextIndex = (int32_t)utext_getNativeIndex(text);
+    int32_t startingTextIndex = static_cast<int32_t>(utext_getNativeIndex(text));
     int32_t wordCount = 0;
     int32_t codePointsMatched = 0;
 
     for (UChar32 c = utext_next32(text); c >= 0; c=utext_next32(text)) {
         UStringTrieResult result = (codePointsMatched == 0) ? bt.first(transform(c)) : bt.next(transform(c));
-        int32_t lengthMatched = (int32_t)utext_getNativeIndex(text) - startingTextIndex;
+        int32_t lengthMatched = static_cast<int32_t>(utext_getNativeIndex(text)) - startingTextIndex;
         codePointsMatched += 1;
         if (USTRINGTRIE_HAS_VALUE(result)) {
             if (wordCount < limit) {

thirdparty/icu4c/common/edits.cpp

@@ -47,7 +47,7 @@ Edits &Edits::copyArray(const Edits &other) {
         return *this;
     }
     if (length > capacity) {
-        uint16_t *newArray = (uint16_t *)uprv_malloc((size_t)length * 2);
+        uint16_t* newArray = static_cast<uint16_t*>(uprv_malloc(static_cast<size_t>(length) * 2));
         if (newArray == nullptr) {
             length = delta = numChanges = 0;
             errorCode_ = U_MEMORY_ALLOCATION_ERROR;
@@ -186,30 +186,30 @@ void Edits::addReplace(int32_t oldLength, int32_t newLength) {
             head |= oldLength << 6;
         } else if(oldLength <= 0x7fff) {
             head |= LENGTH_IN_1TRAIL << 6;
-            array[limit++] = (uint16_t)(0x8000 | oldLength);
+            array[limit++] = static_cast<uint16_t>(0x8000 | oldLength);
         } else {
             head |= (LENGTH_IN_2TRAIL + (oldLength >> 30)) << 6;
-            array[limit++] = (uint16_t)(0x8000 | (oldLength >> 15));
-            array[limit++] = (uint16_t)(0x8000 | oldLength);
+            array[limit++] = static_cast<uint16_t>(0x8000 | (oldLength >> 15));
+            array[limit++] = static_cast<uint16_t>(0x8000 | oldLength);
         }
         if(newLength < LENGTH_IN_1TRAIL) {
             head |= newLength;
         } else if(newLength <= 0x7fff) {
             head |= LENGTH_IN_1TRAIL;
-            array[limit++] = (uint16_t)(0x8000 | newLength);
+            array[limit++] = static_cast<uint16_t>(0x8000 | newLength);
         } else {
             head |= LENGTH_IN_2TRAIL + (newLength >> 30);
-            array[limit++] = (uint16_t)(0x8000 | (newLength >> 15));
-            array[limit++] = (uint16_t)(0x8000 | newLength);
+            array[limit++] = static_cast<uint16_t>(0x8000 | (newLength >> 15));
+            array[limit++] = static_cast<uint16_t>(0x8000 | newLength);
         }
-        array[length] = (uint16_t)head;
+        array[length] = static_cast<uint16_t>(head);
         length = limit;
     }
 }
 
 void Edits::append(int32_t r) {
     if(length < capacity || growArray()) {
-        array[length++] = (uint16_t)r;
+        array[length++] = static_cast<uint16_t>(r);
     }
 }
 
@@ -232,7 +232,7 @@ UBool Edits::growArray() {
         errorCode_ = U_INDEX_OUTOFBOUNDS_ERROR;
         return false;
     }
-    uint16_t *newArray = (uint16_t *)uprv_malloc((size_t)newCapacity * 2);
+    uint16_t* newArray = static_cast<uint16_t*>(uprv_malloc(static_cast<size_t>(newCapacity) * 2));
     if (newArray == nullptr) {
         errorCode_ = U_MEMORY_ALLOCATION_ERROR;
         return false;
@@ -415,7 +415,7 @@ int32_t Edits::Iterator::readLength(int32_t head) {
         U_ASSERT(array[index] >= 0x8000);
         U_ASSERT(array[index + 1] >= 0x8000);
         int32_t len = ((head & 1) << 30) |
-                ((int32_t)(array[index] & 0x7fff) << 15) |
+                (static_cast<int32_t>(array[index] & 0x7fff) << 15) |
                 (array[index + 1] & 0x7fff);
         index += 2;
         return len;

thirdparty/icu4c/common/emojiprops.cpp

@@ -83,8 +83,8 @@ void
 EmojiProps::load(UErrorCode &errorCode) {
     memory = udata_openChoice(nullptr, "icu", "uemoji", isAcceptable, this, &errorCode);
     if (U_FAILURE(errorCode)) { return; }
-    const uint8_t *inBytes = (const uint8_t *)udata_getMemory(memory);
-    const int32_t *inIndexes = (const int32_t *)inBytes;
+    const uint8_t* inBytes = static_cast<const uint8_t*>(udata_getMemory(memory));
+    const int32_t* inIndexes = reinterpret_cast<const int32_t*>(inBytes);
     int32_t indexesLength = inIndexes[IX_CPTRIE_OFFSET] / 4;
     if (indexesLength <= IX_RGI_EMOJI_ZWJ_SEQUENCE_TRIE_OFFSET) {
         errorCode = U_INVALID_FORMAT_ERROR;  // Not enough indexes.
@@ -104,7 +104,7 @@ EmojiProps::load(UErrorCode &errorCode) {
         offset = inIndexes[i];
         nextOffset = inIndexes[i + 1];
         // Set/leave nullptr if there is no UCharsTrie.
-        const char16_t *p = nextOffset > offset ? (const char16_t *)(inBytes + offset) : nullptr;
+        const char16_t* p = nextOffset > offset ? reinterpret_cast<const char16_t*>(inBytes + offset) : nullptr;
         stringTries[getStringTrieIndex(i)] = p;
     }
 }

thirdparty/icu4c/common/filteredbrk.cpp

@@ -50,8 +50,8 @@ static void _fb_trace(const char *m, const UnicodeString *s, UBool b, int32_t d,
  * Used with sortedInsert()
  */
 static int32_t U_CALLCONV compareUnicodeString(UElement t1, UElement t2) {
-    const UnicodeString &a = *(const UnicodeString*)t1.pointer;
-    const UnicodeString &b = *(const UnicodeString*)t2.pointer;
+    const UnicodeString& a = *static_cast<const UnicodeString*>(t1.pointer);
+    const UnicodeString& b = *static_cast<const UnicodeString*>(t2.pointer);
     return a.compare(b);
 }
 
@@ -76,7 +76,7 @@ class UStringSet : public UVector {
    * Return the ith UnicodeString alias
    */
   inline const UnicodeString* getStringAt(int32_t i) const {
-    return (const UnicodeString*)elementAt(i);
+    return static_cast<const UnicodeString*>(elementAt(i));
   }
   /**
    * Adopt the UnicodeString if not already contained.

thirdparty/icu4c/common/icuplug.cpp

@@ -747,7 +747,7 @@ uplug_init(UErrorCode *status) {
     FILE *f;
         
     CharString pluginFile;
-#ifdef OS390BATCH
+#ifdef ICU_PLUGINS_DD
 /* There are potentially a lot of ways to implement a plugin directory on OS390/zOS  */
 /* Keeping in mind that unauthorized file access is logged, monitored, and enforced  */
 /* I've chosen to open a DDNAME if BATCH and leave it alone for (presumably) UNIX    */

thirdparty/icu4c/common/loadednormalizer2impl.cpp

@@ -63,7 +63,7 @@ LoadedNormalizer2Impl::isAcceptable(void * /*context*/,
         pInfo->dataFormat[1]==0x72 &&
         pInfo->dataFormat[2]==0x6d &&
         pInfo->dataFormat[3]==0x32 &&
-        pInfo->formatVersion[0]==4
+        pInfo->formatVersion[0]==5
     ) {
         // Normalizer2Impl *me=(Normalizer2Impl *)context;
         // uprv_memcpy(me->dataVersion, pInfo->dataVersion, 4);
@@ -82,8 +82,8 @@ LoadedNormalizer2Impl::load(const char *packageName, const char *name, UErrorCod
     if(U_FAILURE(errorCode)) {
         return;
     }
-    const uint8_t *inBytes=(const uint8_t *)udata_getMemory(memory);
-    const int32_t *inIndexes=(const int32_t *)inBytes;
+    const uint8_t* inBytes = static_cast<const uint8_t*>(udata_getMemory(memory));
+    const int32_t* inIndexes = reinterpret_cast<const int32_t*>(inBytes);
     int32_t indexesLength=inIndexes[IX_NORM_TRIE_OFFSET]/4;
     if(indexesLength<=IX_MIN_LCCC_CP) {
         errorCode=U_INVALID_FORMAT_ERROR;  // Not enough indexes.
@@ -101,7 +101,7 @@ LoadedNormalizer2Impl::load(const char *packageName, const char *name, UErrorCod
 
     offset=nextOffset;
     nextOffset=inIndexes[IX_SMALL_FCD_OFFSET];
-    const uint16_t *inExtraData=(const uint16_t *)(inBytes+offset);
+    const uint16_t* inExtraData = reinterpret_cast<const uint16_t*>(inBytes + offset);
 
     // smallFCD: new in formatVersion 2
     offset=nextOffset;
@@ -311,7 +311,7 @@ Normalizer2::getInstance(const char *packageName,
         {
             Mutex lock;
             if(cache!=nullptr) {
-                allModes=(Norm2AllModes *)uhash_get(cache, name);
+                allModes = static_cast<Norm2AllModes*>(uhash_get(cache, name));
             }
         }
         if(allModes==nullptr) {
@@ -331,7 +331,7 @@ Normalizer2::getInstance(const char *packageName,
                 void *temp=uhash_get(cache, name);
                 if(temp==nullptr) {
                     int32_t keyLength= static_cast<int32_t>(uprv_strlen(name)+1);
-                    char *nameCopy=(char *)uprv_malloc(keyLength);
+                    char* nameCopy = static_cast<char*>(uprv_malloc(keyLength));
                     if(nameCopy==nullptr) {
                         errorCode=U_MEMORY_ALLOCATION_ERROR;
                         return nullptr;
@@ -341,7 +341,7 @@ Normalizer2::getInstance(const char *packageName,
                     uhash_put(cache, nameCopy, localAllModes.orphan(), &errorCode);
                 } else {
                     // race condition
-                    allModes=(Norm2AllModes *)temp;
+                    allModes = static_cast<Norm2AllModes*>(temp);
                 }
             }
         }

thirdparty/icu4c/common/localebuilder.cpp

@@ -1,6 +1,8 @@
 // © 2019 and later: Unicode, Inc. and others.
 // License & terms of use: http://www.unicode.org/copyright.html
 
+#include <optional>
+#include <string_view>
 #include <utility>
 
 #include "bytesinkutil.h"  // StringByteSink<CharString>
@@ -162,12 +164,15 @@ _isKeywordValue(const char* key, const char* value, int32_t value_len)
     // otherwise: unicode extension value
     // We need to convert from legacy key/value to unicode
     // key/value
-    const char* unicode_locale_key = uloc_toUnicodeLocaleKey(key);
-    const char* unicode_locale_type = uloc_toUnicodeLocaleType(key, value);
-
-    return unicode_locale_key && unicode_locale_type &&
-           ultag_isUnicodeLocaleKey(unicode_locale_key, -1) &&
-           ultag_isUnicodeLocaleType(unicode_locale_type, -1);
+    std::optional<std::string_view> unicode_locale_key = ulocimp_toBcpKeyWithFallback(key);
+    std::optional<std::string_view> unicode_locale_type = ulocimp_toBcpTypeWithFallback(key, value);
+
+    return unicode_locale_key.has_value() &&
+           unicode_locale_type.has_value() &&
+           ultag_isUnicodeLocaleKey(unicode_locale_key->data(),
+                                    static_cast<int32_t>(unicode_locale_key->size())) &&
+           ultag_isUnicodeLocaleType(unicode_locale_type->data(),
+                                     static_cast<int32_t>(unicode_locale_type->size()));
 }
 
 void

thirdparty/icu4c/common/localematcher.cpp

@@ -780,7 +780,7 @@ int32_t acceptLanguage(UEnumeration &supportedLocales, Locale::Iterator &desired
                 ULOC_ACCEPT_VALID : ULOC_ACCEPT_FALLBACK;
         }
         const char *bestStr = result.getSupportedLocale()->getName();
-        int32_t bestLength = (int32_t)uprv_strlen(bestStr);
+        int32_t bestLength = static_cast<int32_t>(uprv_strlen(bestStr));
         if (bestLength <= capacity) {
             uprv_memcpy(dest, bestStr, bestLength);
         }

thirdparty/icu4c/common/locbased.h

@@ -99,7 +99,7 @@ inline LocaleBased::LocaleBased(char* validAlias, char* actualAlias) :
 inline LocaleBased::LocaleBased(const char* validAlias,
                                 const char* actualAlias) :
     // ugh: cast away const
-    valid((char*)validAlias), actual((char*)actualAlias) {
+    valid(const_cast<char*>(validAlias)), actual(const_cast<char*>(actualAlias)) {
 }
 
 U_NAMESPACE_END

thirdparty/icu4c/common/locdispnames.cpp

@@ -245,7 +245,7 @@ Locale::getDisplayName(const Locale &displayLocale,
     return result;
 }
 
-#if ! UCONFIG_NO_BREAK_ITERATION
+#if !UCONFIG_NO_BREAK_ITERATION
 
 // -------------------------------------
 // Gets the objectLocale display name in the default locale language.
@@ -351,7 +351,7 @@ _getStringOrCopyKey(const char *path, const char *locale,
         }
     } else {
         /* no string from a resource bundle: convert the substitute */
-        length=(int32_t)uprv_strlen(substitute);
+        length = static_cast<int32_t>(uprv_strlen(substitute));
         u_charsToUChars(substitute, dest, uprv_min(length, destCapacity));
         errorCode = U_USING_DEFAULT_WARNING;
     }
@@ -835,7 +835,10 @@ uloc_getDisplayKeywordValue(   const char* locale,
     }
 
     /* get the keyword value */
-    CharString keywordValue = ulocimp_getKeywordValue(locale, keyword, *status);
+    CharString keywordValue;
+    if (keyword != nullptr && *keyword != '\0') {
+        keywordValue = ulocimp_getKeywordValue(locale, keyword, *status);
+    }
 
     /* 
      * if the keyword is equal to currency .. then to get the display name 

thirdparty/icu4c/common/locdspnm.cpp

@@ -336,10 +336,11 @@ LocaleDisplayNamesImpl::LocaleDisplayNamesImpl(const Locale& locale,
 {
     while (length-- > 0) {
         UDisplayContext value = *contexts++;
-        UDisplayContextType selector = (UDisplayContextType)((uint32_t)value >> 8);
+        UDisplayContextType selector =
+            static_cast<UDisplayContextType>(static_cast<uint32_t>(value) >> 8);
         switch (selector) {
             case UDISPCTX_TYPE_DIALECT_HANDLING:
-                dialectHandling = (UDialectHandling)value;
+                dialectHandling = static_cast<UDialectHandling>(value);
                 break;
             case UDISPCTX_TYPE_CAPITALIZATION:
                 capitalizationContext = value;
@@ -407,7 +408,7 @@ LocaleDisplayNamesImpl::CapitalizationContextSink::~CapitalizationContextSink()
 
 void
 LocaleDisplayNamesImpl::initialize() {
-    LocaleDisplayNamesImpl *nonConstThis = (LocaleDisplayNamesImpl *)this;
+    LocaleDisplayNamesImpl* nonConstThis = this;
     nonConstThis->locale = langData.getLocale() == Locale::getRoot()
         ? regionData.getLocale()
         : langData.getLocale();
@@ -426,16 +427,16 @@ LocaleDisplayNamesImpl::initialize() {
         pattern = UnicodeString("{0} ({1})", -1, US_INV);
     }
     format.applyPatternMinMaxArguments(pattern, 2, 2, status);
-    if (pattern.indexOf((char16_t)0xFF08) >= 0) {
-        formatOpenParen.setTo((char16_t)0xFF08);         // fullwidth (
-        formatReplaceOpenParen.setTo((char16_t)0xFF3B);  // fullwidth [
-        formatCloseParen.setTo((char16_t)0xFF09);        // fullwidth )
-        formatReplaceCloseParen.setTo((char16_t)0xFF3D); // fullwidth ]
+    if (pattern.indexOf(static_cast<char16_t>(0xFF08)) >= 0) {
+        formatOpenParen.setTo(static_cast<char16_t>(0xFF08));         // fullwidth (
+        formatReplaceOpenParen.setTo(static_cast<char16_t>(0xFF3B));  // fullwidth [
+        formatCloseParen.setTo(static_cast<char16_t>(0xFF09));        // fullwidth )
+        formatReplaceCloseParen.setTo(static_cast<char16_t>(0xFF3D)); // fullwidth ]
     } else {
-        formatOpenParen.setTo((char16_t)0x0028);         // (
-        formatReplaceOpenParen.setTo((char16_t)0x005B);  // [
-        formatCloseParen.setTo((char16_t)0x0029);        // )
-        formatReplaceCloseParen.setTo((char16_t)0x005D); // ]
+        formatOpenParen.setTo(static_cast<char16_t>(0x0028));         // (
+        formatReplaceOpenParen.setTo(static_cast<char16_t>(0x005B));  // [
+        formatCloseParen.setTo(static_cast<char16_t>(0x0029));        // )
+        formatReplaceCloseParen.setTo(static_cast<char16_t>(0x005D)); // ]
     }
 
     UnicodeString ktPattern;
@@ -495,7 +496,7 @@ UDisplayContext
 LocaleDisplayNamesImpl::getContext(UDisplayContextType type) const {
     switch (type) {
         case UDISPCTX_TYPE_DIALECT_HANDLING:
-            return (UDisplayContext)dialectHandling;
+            return static_cast<UDisplayContext>(dialectHandling);
         case UDISPCTX_TYPE_CAPITALIZATION:
             return capitalizationContext;
         case UDISPCTX_TYPE_DISPLAY_LENGTH:
@@ -505,7 +506,7 @@ LocaleDisplayNamesImpl::getContext(UDisplayContextType type) const {
         default:
             break;
     }
-    return (UDisplayContext)0;
+    return static_cast<UDisplayContext>(0);
 }
 
 UnicodeString&
@@ -652,7 +653,7 @@ LocaleDisplayNamesImpl::localeDisplayName(const Locale& loc,
         appendWithSep(resultRemainder, temp3);
       } else {
         appendWithSep(resultRemainder, temp)
-          .append((char16_t)0x3d /* = */)
+          .append(static_cast<char16_t>(0x3d) /* = */)
           .append(temp2);
       }
     }

thirdparty/icu4c/common/locid.cpp

@@ -31,6 +31,8 @@
 ******************************************************************************
 */
 
+#include <optional>
+#include <string_view>
 #include <utility>
 
 #include "unicode/bytestream.h"
@@ -109,7 +111,7 @@ namespace {
 //
 void U_CALLCONV
 deleteLocale(void *obj) {
-    delete (icu::Locale *) obj;
+    delete static_cast<icu::Locale*>(obj);
 }
 
 UBool U_CALLCONV locale_cleanup()
@@ -132,7 +134,7 @@ void U_CALLCONV locale_init(UErrorCode &status) {
     U_NAMESPACE_USE
 
     U_ASSERT(gLocaleCache == nullptr);
-    gLocaleCache = new Locale[(int)eMAX_LOCALES];
+    gLocaleCache = new Locale[static_cast<int>(eMAX_LOCALES)];
     if (gLocaleCache == nullptr) {
         status = U_MEMORY_ALLOCATION_ERROR;
         return;
@@ -194,7 +196,7 @@ Locale *locale_set_default_internal(const char *id, UErrorCode& status) {
         ucln_common_registerCleanup(UCLN_COMMON_LOCALE, locale_cleanup);
     }
 
-    Locale *newDefault = (Locale *)uhash_get(gDefaultLocalesHashT, localeNameBuf.data());
+    Locale* newDefault = static_cast<Locale*>(uhash_get(gDefaultLocalesHashT, localeNameBuf.data()));
     if (newDefault == nullptr) {
         newDefault = new Locale(Locale::eBOGUS);
         if (newDefault == nullptr) {
@@ -202,7 +204,7 @@ Locale *locale_set_default_internal(const char *id, UErrorCode& status) {
             return gDefaultLocale;
         }
         newDefault->init(localeNameBuf.data(), false);
-        uhash_put(gDefaultLocalesHashT, (char*) newDefault->getName(), newDefault, &status);
+        uhash_put(gDefaultLocalesHashT, const_cast<char*>(newDefault->getName()), newDefault, &status);
         if (U_FAILURE(status)) {
             return gDefaultLocale;
         }
@@ -296,7 +298,7 @@ Locale::Locale( const   char * newLanguage,
         // Language
         if ( newLanguage != nullptr )
         {
-            lsize = (int32_t)uprv_strlen(newLanguage);
+            lsize = static_cast<int32_t>(uprv_strlen(newLanguage));
             if ( lsize < 0 || lsize > ULOC_STRING_LIMIT ) { // int32 wrap
                 setToBogus();
                 return;
@@ -308,7 +310,7 @@ Locale::Locale( const   char * newLanguage,
         // _Country
         if ( newCountry != nullptr )
         {
-            csize = (int32_t)uprv_strlen(newCountry);
+            csize = static_cast<int32_t>(uprv_strlen(newCountry));
             if ( csize < 0 || csize > ULOC_STRING_LIMIT ) { // int32 wrap
                 setToBogus();
                 return;
@@ -325,7 +327,7 @@ Locale::Locale( const   char * newLanguage,
             }
 
             // remove trailing _'s
-            vsize = (int32_t)uprv_strlen(newVariant);
+            vsize = static_cast<int32_t>(uprv_strlen(newVariant));
             if ( vsize < 0 || vsize > ULOC_STRING_LIMIT ) { // int32 wrap
                 setToBogus();
                 return;
@@ -338,7 +340,7 @@ Locale::Locale( const   char * newLanguage,
 
         if ( newKeywords != nullptr)
         {
-            ksize = (int32_t)uprv_strlen(newKeywords);
+            ksize = static_cast<int32_t>(uprv_strlen(newKeywords));
             if ( ksize < 0 || ksize > ULOC_STRING_LIMIT ) {
               setToBogus();
               return;
@@ -1200,8 +1202,8 @@ AliasReplacer::parseLanguageReplacement(
         return;
     }
     // We have multiple field so we have to allocate and parse
-    CharString* str = new CharString(
-        replacement, (int32_t)uprv_strlen(replacement), status);
+    CharString* str =
+        new CharString(replacement, static_cast<int32_t>(uprv_strlen(replacement)), status);
     LocalPointer<CharString> lpStr(str, status);
     toBeFreed.adoptElement(lpStr.orphan(), status);
     if (U_FAILURE(status)) {
@@ -1213,7 +1215,7 @@ AliasReplacer::parseLanguageReplacement(
     *endOfField = '\0'; // null terminiate it.
     endOfField++;
     const char* start = endOfField;
-    endOfField = (char*) uprv_strchr(start, '_');
+    endOfField = const_cast<char*>(uprv_strchr(start, '_'));
     size_t len = 0;
     if (endOfField == nullptr) {
         len = uprv_strlen(start);
@@ -1228,7 +1230,7 @@ AliasReplacer::parseLanguageReplacement(
             return;
         }
         start = endOfField++;
-        endOfField = (char*)uprv_strchr(start, '_');
+        endOfField = const_cast<char*>(uprv_strchr(start, '_'));
         if (endOfField == nullptr) {
             len = uprv_strlen(start);
         } else {
@@ -1243,7 +1245,7 @@ AliasReplacer::parseLanguageReplacement(
             return;
         }
         start = endOfField++;
-        endOfField = (char*)uprv_strchr(start, '_');
+        endOfField = const_cast<char*>(uprv_strchr(start, '_'));
         if (endOfField == nullptr) {
             len = uprv_strlen(start);
         } else {
@@ -1285,7 +1287,7 @@ AliasReplacer::replaceLanguage(
             variant_index++) {
         if (checkVariants) {
             U_ASSERT(variant_index < variant_size);
-            searchVariant = (const char*)(variants.elementAt(variant_index));
+            searchVariant = static_cast<const char*>(variants.elementAt(variant_index));
         }
 
         if (searchVariant != nullptr && uprv_strlen(searchVariant) < 4) {
@@ -1406,13 +1408,13 @@ AliasReplacer::replaceTerritory(UVector& toBeFreed, UErrorCode& status)
                 U_ASSERT(foundInReplacement[len] == ' ' ||
                          foundInReplacement[len] == '\0');
                 item.adoptInsteadAndCheckErrorCode(
-                    new CharString(foundInReplacement, (int32_t)len, status), status);
+                    new CharString(foundInReplacement, static_cast<int32_t>(len), status), status);
             }
         }
         if (item.isNull() && U_SUCCESS(status)) {
             item.adoptInsteadAndCheckErrorCode(
                 new CharString(replacement,
-                               (int32_t)(firstSpace - replacement), status), status);
+                               static_cast<int32_t>(firstSpace - replacement), status), status);
         }
         if (U_FAILURE(status)) { return false; }
         replacedRegion = item->data();
@@ -1454,7 +1456,7 @@ AliasReplacer::replaceVariant(UErrorCode& status)
     }
     // Since we may have more than one variant, we need to loop through them.
     for (int32_t i = 0; i < variants.size(); i++) {
-        const char *variant = (const char*)(variants.elementAt(i));
+        const char* variant = static_cast<const char*>(variants.elementAt(i));
         const char *replacement = data->variantMap().get(variant);
         if (replacement == nullptr) {
             // Found no replacement data for this variant.
@@ -1496,7 +1498,7 @@ AliasReplacer::replaceSubdivision(
         size_t len = (firstSpace != nullptr) ?
             (firstSpace - replacement) : uprv_strlen(replacement);
         if (2 <= len && len <= 8) {
-            output.append(replacement, (int32_t)len, status);
+            output.append(replacement, static_cast<int32_t>(len), status);
             if (2 == len) {
                 // Add 'zzzz' based on changes to UTS #35 for CLDR-14312.
                 output.append("zzzz", 4, status);
@@ -1546,7 +1548,7 @@ AliasReplacer::replaceTransformedExtensions(
             }
             const char* nextTKey = ultag_getTKeyStart(tvalue);
             if (nextTKey != nullptr) {
-                *((char*)(nextTKey-1)) = '\0';  // NUL terminate tvalue
+                *const_cast<char*>(nextTKey - 1) = '\0'; // NUL terminate tvalue
             }
             tfields.insertElementAt((void*)tkey, tfields.size(), status);
             if (U_FAILURE(status)) {
@@ -1561,17 +1563,17 @@ AliasReplacer::replaceTransformedExtensions(
              if (output.length() > 0) {
                  output.append('-', status);
              }
-             const char* tfield = (const char*) tfields.elementAt(i);
+             const char* tfield = static_cast<const char*>(tfields.elementAt(i));
              const char* tvalue = uprv_strchr(tfield, '-');
              if (tvalue == nullptr) {
                  status = U_ILLEGAL_ARGUMENT_ERROR;
                  return false;
              }
              // Split the "tkey-tvalue" pair string so that we can canonicalize the tvalue.
-             *((char*)tvalue++) = '\0'; // NUL terminate tkey
+             *const_cast<char*>(tvalue++) = '\0'; // NUL terminate tkey
              output.append(tfield, status).append('-', status);
-             const char* bcpTValue = ulocimp_toBcpType(tfield, tvalue, nullptr, nullptr);
-             output.append((bcpTValue == nullptr) ? tvalue : bcpTValue, status);
+             std::optional<std::string_view> bcpTValue = ulocimp_toBcpType(tfield, tvalue);
+             output.append(bcpTValue.has_value() ? *bcpTValue : tvalue, status);
         }
     }
     if (U_FAILURE(status)) {
@@ -1604,7 +1606,7 @@ AliasReplacer::outputToString(
         int32_t variantsStart = out.length();
         for (int32_t i = 0; i < variants.size(); i++) {
              out.append(SEP_CHAR, status)
-                 .append((const char*)(variants.elementAt(i)),
+                 .append(static_cast<const char*>(variants.elementAt(i)),
                          status);
         }
         T_CString_toUpperCase(out.data() + variantsStart);
@@ -1673,7 +1675,7 @@ AliasReplacer::replace(const Locale& locale, CharString& out, UErrorCode& status
     int changed = 0;
     // A UVector to to hold CharString allocated by the replace* method
     // and freed when out of scope from his function.
-    UVector stringsToBeFreed([](void *obj){ delete ((CharString*) obj); },
+    UVector stringsToBeFreed([](void *obj) { delete static_cast<CharString*>(obj); },
                              nullptr, 10, status);
     while (U_SUCCESS(status)) {
         // Something wrong with the data cause looping here more than 10 times
@@ -1866,14 +1868,14 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
             uloc_canonicalize(localeID, fullName, sizeof(fullNameBuffer), &err) :
             uloc_getName(localeID, fullName, sizeof(fullNameBuffer), &err);
 
-        if(err == U_BUFFER_OVERFLOW_ERROR || length >= (int32_t)sizeof(fullNameBuffer)) {
+        if (err == U_BUFFER_OVERFLOW_ERROR || length >= static_cast<int32_t>(sizeof(fullNameBuffer))) {
             U_ASSERT(baseName == nullptr);
             /*Go to heap for the fullName if necessary*/
-            fullName = (char *)uprv_malloc(sizeof(char)*(length + 1));
-            if (fullName == nullptr) {
-                fullName = fullNameBuffer;
+            char* newFullName = static_cast<char*>(uprv_malloc(sizeof(char) * (length + 1)));
+            if (newFullName == nullptr) {
                 break; // error: out of memory
             }
+            fullName = newFullName;
             err = U_ZERO_ERROR;
             length = canonicalize ?
                 uloc_canonicalize(localeID, fullName, length+1, &err) :
@@ -1895,7 +1897,7 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
                fieldIdx < UPRV_LENGTHOF(field)-1 &&
                (at == nullptr || separator < at)) {
             field[fieldIdx] = separator + 1;
-            fieldLen[fieldIdx-1] = (int32_t)(separator - field[fieldIdx-1]);
+            fieldLen[fieldIdx - 1] = static_cast<int32_t>(separator - field[fieldIdx - 1]);
             fieldIdx++;
         }
         // variant may contain @foo or .foo POSIX cruft; remove it
@@ -1905,12 +1907,12 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
             if (separator==nullptr || (sep2!=nullptr && separator > sep2)) {
                 separator = sep2;
             }
-            fieldLen[fieldIdx-1] = (int32_t)(separator - field[fieldIdx-1]);
+            fieldLen[fieldIdx - 1] = static_cast<int32_t>(separator - field[fieldIdx - 1]);
         } else {
-            fieldLen[fieldIdx-1] = length - (int32_t)(field[fieldIdx-1] - fullName);
+            fieldLen[fieldIdx - 1] = length - static_cast<int32_t>(field[fieldIdx - 1] - fullName);
         }
 
-        if (fieldLen[0] >= (int32_t)(sizeof(language)))
+        if (fieldLen[0] >= static_cast<int32_t>(sizeof(language)))
         {
             break; // error: the language field is too long
         }
@@ -1941,7 +1943,7 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
 
         if (fieldLen[variantField] > 0) {
             /* We have a variant */
-            variantBegin = (int32_t)(field[variantField] - fullName);
+            variantBegin = static_cast<int32_t>(field[variantField] - fullName);
         }
 
         err = U_ZERO_ERROR;
@@ -1991,12 +1993,13 @@ Locale::initBaseName(UErrorCode &status) {
     const char *eqPtr = uprv_strchr(fullName, '=');
     if (atPtr && eqPtr && atPtr < eqPtr) {
         // Key words exist.
-        int32_t baseNameLength = (int32_t)(atPtr - fullName);
-        baseName = (char *)uprv_malloc(baseNameLength + 1);
-        if (baseName == nullptr) {
+        int32_t baseNameLength = static_cast<int32_t>(atPtr - fullName);
+        char* newBaseName = static_cast<char*>(uprv_malloc(baseNameLength + 1));
+        if (newBaseName == nullptr) {
             status = U_MEMORY_ALLOCATION_ERROR;
             return;
         }
+        baseName = newBaseName;
         uprv_strncpy(baseName, fullName, baseNameLength);
         baseName[baseNameLength] = 0;
 
@@ -2434,7 +2437,7 @@ public:
         UErrorCode status = U_ZERO_ERROR;
         return new KeywordEnumeration(
                 keywords.data(), keywords.length(),
-                (int32_t)(current - keywords.data()), status);
+                static_cast<int32_t>(current - keywords.data()), status);
     }
 
     virtual int32_t count(UErrorCode& status) const override {
@@ -2453,7 +2456,7 @@ public:
         int32_t len;
         if(U_SUCCESS(status) && *current != 0) {
             result = current;
-            len = (int32_t)uprv_strlen(current);
+            len = static_cast<int32_t>(uprv_strlen(current));
             current += len+1;
             if(resultLength != nullptr) {
                 *resultLength = len;
@@ -2596,13 +2599,7 @@ Locale::getKeywordValue(StringPiece keywordName, ByteSink& sink, UErrorCode& sta
         return;
     }
 
-    // TODO: Remove the need for a const char* to a NUL terminated buffer.
-    const CharString keywordName_nul(keywordName, status);
-    if (U_FAILURE(status)) {
-        return;
-    }
-
-    ulocimp_getKeywordValue(fullName, keywordName_nul.data(), sink, status);
+    ulocimp_getKeywordValue(fullName, keywordName, sink, status);
 }
 
 void
@@ -2613,88 +2610,89 @@ Locale::getUnicodeKeywordValue(StringPiece keywordName,
         return;
     }
 
-    // TODO: Remove the need for a const char* to a NUL terminated buffer.
-    const CharString keywordName_nul(keywordName, status);
-    if (U_FAILURE(status)) {
-        return;
-    }
-
-    const char* legacy_key = uloc_toLegacyKey(keywordName_nul.data());
-    if (legacy_key == nullptr) {
+    std::optional<std::string_view> legacy_key = ulocimp_toLegacyKeyWithFallback(keywordName);
+    if (!legacy_key.has_value()) {
         status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
     }
 
-    auto legacy_value = getKeywordValue<CharString>(legacy_key, status);
+    auto legacy_value = getKeywordValue<CharString>(*legacy_key, status);
 
     if (U_FAILURE(status)) {
         return;
     }
 
-    const char* unicode_value = uloc_toUnicodeLocaleType(
-            keywordName_nul.data(), legacy_value.data());
-
-    if (unicode_value == nullptr) {
+    std::optional<std::string_view> unicode_value =
+        ulocimp_toBcpTypeWithFallback(keywordName, legacy_value.toStringPiece());
+    if (!unicode_value.has_value()) {
         status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
     }
 
-    sink.Append(unicode_value, static_cast<int32_t>(uprv_strlen(unicode_value)));
+    sink.Append(unicode_value->data(), static_cast<int32_t>(unicode_value->size()));
 }
 
 void
-Locale::setKeywordValue(const char* keywordName, const char* keywordValue, UErrorCode &status)
-{
-    if (U_FAILURE(status)) {
+Locale::setKeywordValue(StringPiece keywordName,
+                        StringPiece keywordValue,
+                        UErrorCode& status) {
+    if (U_FAILURE(status)) { return; }
+    if (keywordName.empty()) {
+        status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
     }
     if (status == U_STRING_NOT_TERMINATED_WARNING) {
         status = U_ZERO_ERROR;
     }
-    int32_t bufferLength = uprv_max((int32_t)(uprv_strlen(fullName) + 1), ULOC_FULLNAME_CAPACITY);
-    int32_t newLength = uloc_setKeywordValue(keywordName, keywordValue, fullName,
-                                             bufferLength, &status) + 1;
-    U_ASSERT(status != U_STRING_NOT_TERMINATED_WARNING);
-    /* Handle the case the current buffer is not enough to hold the new id */
-    if (status == U_BUFFER_OVERFLOW_ERROR) {
-        U_ASSERT(newLength > bufferLength);
-        char* newFullName = (char *)uprv_malloc(newLength);
-        if (newFullName == nullptr) {
-            status = U_MEMORY_ALLOCATION_ERROR;
-            return;
-        }
-        uprv_strcpy(newFullName, fullName);
-        if (fullName != fullNameBuffer) {
-            // if full Name is already on the heap, need to free it.
-            uprv_free(fullName);
-            if (baseName == fullName) {
-                baseName = newFullName; // baseName should not point to freed memory.
+
+    int32_t length = static_cast<int32_t>(uprv_strlen(fullName));
+    int32_t capacity = fullName == fullNameBuffer ? ULOC_FULLNAME_CAPACITY : length + 1;
+
+    const char* start = locale_getKeywordsStart(fullName);
+    int32_t offset = start == nullptr ? length : start - fullName;
+
+    for (;;) {
+        // Remove -1 from the capacity so that this function can guarantee NUL termination.
+        CheckedArrayByteSink sink(fullName + offset, capacity - offset - 1);
+
+        int32_t reslen = ulocimp_setKeywordValue(
+            {fullName + offset, static_cast<std::string_view::size_type>(length - offset)},
+            keywordName,
+            keywordValue,
+            sink,
+            status);
+
+        if (status == U_BUFFER_OVERFLOW_ERROR) {
+            capacity = reslen + offset + 1;
+            char* newFullName = static_cast<char*>(uprv_malloc(capacity));
+            if (newFullName == nullptr) {
+                status = U_MEMORY_ALLOCATION_ERROR;
+                return;
+            }
+            uprv_memcpy(newFullName, fullName, length + 1);
+            if (fullName != fullNameBuffer) {
+                if (baseName == fullName) {
+                    baseName = newFullName; // baseName should not point to freed memory.
+                }
+                // if fullName is already on the heap, need to free it.
+                uprv_free(fullName);
             }
+            fullName = newFullName;
+            status = U_ZERO_ERROR;
+            continue;
         }
-        fullName = newFullName;
-        status = U_ZERO_ERROR;
-        uloc_setKeywordValue(keywordName, keywordValue, fullName, newLength, &status);
-        U_ASSERT(status != U_STRING_NOT_TERMINATED_WARNING);
-    } else {
-        U_ASSERT(newLength <= bufferLength);
+
+        if (U_FAILURE(status)) { return; }
+        u_terminateChars(fullName, capacity, reslen + offset, &status);
+        break;
     }
-    if (U_SUCCESS(status) && baseName == fullName) {
+
+    if (baseName == fullName) {
         // May have added the first keyword, meaning that the fullName is no longer also the baseName.
         initBaseName(status);
     }
 }
 
-void
-Locale::setKeywordValue(StringPiece keywordName,
-                        StringPiece keywordValue,
-                        UErrorCode& status) {
-    if (U_FAILURE(status)) { return; }
-    // TODO: Remove the need for a const char* to a NUL terminated buffer.
-    const CharString keywordName_nul(keywordName, status);
-    const CharString keywordValue_nul(keywordValue, status);
-    setKeywordValue(keywordName_nul.data(), keywordValue_nul.data(), status);
-}
-
 void
 Locale::setUnicodeKeywordValue(StringPiece keywordName,
                                StringPiece keywordValue,
@@ -2703,32 +2701,25 @@ Locale::setUnicodeKeywordValue(StringPiece keywordName,
         return;
     }
 
-    // TODO: Remove the need for a const char* to a NUL terminated buffer.
-    const CharString keywordName_nul(keywordName, status);
-    const CharString keywordValue_nul(keywordValue, status);
-    if (U_FAILURE(status)) {
-        return;
-    }
-
-    const char* legacy_key = uloc_toLegacyKey(keywordName_nul.data());
-    if (legacy_key == nullptr) {
+    std::optional<std::string_view> legacy_key = ulocimp_toLegacyKeyWithFallback(keywordName);
+    if (!legacy_key.has_value()) {
         status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
     }
 
-    const char* legacy_value = nullptr;
-
-    if (!keywordValue_nul.isEmpty()) {
-        legacy_value =
-            uloc_toLegacyType(keywordName_nul.data(), keywordValue_nul.data());
+    std::string_view value;
 
-        if (legacy_value == nullptr) {
+    if (!keywordValue.empty()) {
+        std::optional<std::string_view> legacy_value =
+            ulocimp_toLegacyTypeWithFallback(keywordName, keywordValue);
+        if (!legacy_value.has_value()) {
             status = U_ILLEGAL_ARGUMENT_ERROR;
             return;
         }
+        value = *legacy_value;
     }
 
-    setKeywordValue(legacy_key, legacy_value, status);
+    setKeywordValue(*legacy_key, value, status);
 }
 
 const char *

thirdparty/icu4c/common/loclikely.cpp

@@ -19,6 +19,7 @@
 *   that then do not depend on resource bundle code and likely-subtags data.
 */
 
+#include <string_view>
 #include <utility>
 
 #include "unicode/bytestream.h"
@@ -170,7 +171,7 @@ _uloc_addLikelySubtags(const char* localeID,
         return;
     }
 
-    int32_t trailingLength = (int32_t)uprv_strlen(trailing);
+    int32_t trailingLength = static_cast<int32_t>(uprv_strlen(trailing));
 
     const icu::LikelySubtags* likelySubtags = icu::LikelySubtags::getSingleton(err);
     if (U_FAILURE(err)) {
@@ -193,11 +194,11 @@ _uloc_addLikelySubtags(const char* localeID,
     }
     createTagStringWithAlternates(
         language,
-        (int32_t)uprv_strlen(language),
+        static_cast<int32_t>(uprv_strlen(language)),
         lsr.script,
-        (int32_t)uprv_strlen(lsr.script),
+        static_cast<int32_t>(uprv_strlen(lsr.script)),
         lsr.region,
-        (int32_t)uprv_strlen(lsr.region),
+        static_cast<int32_t>(uprv_strlen(lsr.region)),
         variant.data(),
         variant.length(),
         trailing,
@@ -235,7 +236,7 @@ _uloc_minimizeSubtags(const char* localeID,
         return;
     }
 
-    int32_t trailingLength = (int32_t)uprv_strlen(trailing);
+    int32_t trailingLength = static_cast<int32_t>(uprv_strlen(trailing));
 
     const icu::LikelySubtags* likelySubtags = icu::LikelySubtags::getSingleton(err);
     if (U_FAILURE(err)) {
@@ -256,11 +257,11 @@ _uloc_minimizeSubtags(const char* localeID,
     }
     createTagStringWithAlternates(
         language,
-        (int32_t)uprv_strlen(language),
+        static_cast<int32_t>(uprv_strlen(language)),
         lsr.script,
-        (int32_t)uprv_strlen(lsr.script),
+        static_cast<int32_t>(uprv_strlen(lsr.script)),
         lsr.region,
-        (int32_t)uprv_strlen(lsr.region),
+        static_cast<int32_t>(uprv_strlen(lsr.region)),
         variant.data(),
         variant.length(),
         trailing,
@@ -388,21 +389,32 @@ U_NAMESPACE_END
 
 namespace {
 icu::CharString
-GetRegionFromKey(const char* localeID, const char* key, UErrorCode& status) {
+GetRegionFromKey(const char* localeID, std::string_view key, UErrorCode& status) {
     icu::CharString result;
-
     // First check for keyword value
     icu::CharString kw = ulocimp_getKeywordValue(localeID, key, status);
     int32_t len = kw.length();
-    if (U_SUCCESS(status) && len >= 3 && len <= 7) {
-        // chop off the subdivision code (which will generally be "zzzz" anyway)
-        const char* const data = kw.data();
-        if (uprv_isASCIILetter(data[0])) {
-            result.append(uprv_toupper(data[0]), status);
-            result.append(uprv_toupper(data[1]), status);
-        } else {
-            // assume three-digit region code
-            result.append(data, 3, status);
+    // In UTS35
+    //   type = alphanum{3,8} (sep alphanum{3,8})* ;
+    // so we know the subdivision must fit the type already.
+    //
+    //   unicode_subdivision_id = unicode_region_subtag unicode_subdivision_suffix ;
+    //   unicode_region_subtag = (alpha{2} | digit{3}) ;
+    //   unicode_subdivision_suffix = alphanum{1,4} ;
+    // But we also know there are no id in start with digit{3} in
+    // https://github.com/unicode-org/cldr/blob/main/common/validity/subdivision.xml
+    // Therefore we can simplify as
+    // unicode_subdivision_id = alpha{2} alphanum{1,4}
+    //
+    // and only need to accept/reject the code based on the alpha{2} and the length.
+    if (U_SUCCESS(status) && len >= 3 && len <= 6 &&
+        uprv_isASCIILetter(kw[0]) && uprv_isASCIILetter(kw[1])) {
+        // Additional Check
+        static icu::RegionValidateMap valid;
+        const char region[] = {kw[0], kw[1], '\0'};
+        if (valid.isSet(region)) {
+            result.append(uprv_toupper(kw[0]), status);
+            result.append(uprv_toupper(kw[1]), status);
         }
     }
     return result;
@@ -435,3 +447,55 @@ ulocimp_getRegionForSupplementalData(const char *localeID, bool inferRegion,
 
     return rgBuf;
 }
+
+namespace {
+
+// The following data is generated by unit test code inside
+// test/intltest/regiontst.cpp from the resource data while
+// the test failed.
+const uint32_t gValidRegionMap[] = {
+    0xeedf597c, 0xdeddbdef, 0x15943f3f, 0x0e00d580, 
+    0xb0095c00, 0x0015fb9f, 0x781c068d, 0x0340400f, 
+    0xf42b1d00, 0xfd4f8141, 0x25d7fffc, 0x0100084b, 
+    0x538f3c40, 0x40000001, 0xfdf15100, 0x9fbb7ae7, 
+    0x0410419a, 0x00408557, 0x00004002, 0x00100001, 
+    0x00400408, 0x00000001, 
+};
+
+}  // namespace
+   //
+U_NAMESPACE_BEGIN
+RegionValidateMap::RegionValidateMap() {
+    uprv_memcpy(map, gValidRegionMap, sizeof(map));
+}
+
+RegionValidateMap::~RegionValidateMap() {
+}
+
+bool RegionValidateMap::isSet(const char* region) const {
+    int32_t index = value(region);
+    if (index < 0) {
+        return false;
+    }
+    return 0 != (map[index / 32] & (1L << (index % 32)));
+}
+
+bool RegionValidateMap::equals(const RegionValidateMap& that) const {
+    return uprv_memcmp(map, that.map, sizeof(map)) == 0;
+}
+
+// The code transform two letter a-z to a integer valued between -1, 26x26.
+// -1 indicate the region is outside the range of two letter a-z
+// the rest of value is between 0 and 676 (= 26x26) and used as an index
+// the the bigmap in map. The map is an array of 22 int32_t.
+// since 32x21 < 676/32 < 32x22 we store this 676 bits bitmap into 22 int32_t.
+int32_t RegionValidateMap::value(const char* region) const {
+    if (uprv_isASCIILetter(region[0]) && uprv_isASCIILetter(region[1]) &&
+        region[2] == '\0') {
+        return (uprv_toupper(region[0])-'A') * 26 +
+               (uprv_toupper(region[1])-'A');
+    }
+    return -1;
+}
+
+U_NAMESPACE_END

thirdparty/icu4c/common/loclikelysubtags.cpp

@@ -564,47 +564,40 @@ LSR LikelySubtags::makeMaximizedLsr(const char *language, const char *script, co
     // Handle pseudolocales like en-XA, ar-XB, fr-PSCRACK.
     // They should match only themselves,
     // not other locales with what looks like the same language and script subtags.
-    char c1;
-    if (region[0] == 'X' && (c1 = region[1]) != 0 && region[2] == 0) {
-        switch (c1) {
-        case 'A':
-            if (returnInputIfUnmatch) {
-                return LSR(language, script, region, LSR::EXPLICIT_LSR);
-            }
-            return LSR(PSEUDO_ACCENTS_PREFIX, language, script, region,
-                       LSR::EXPLICIT_LSR, errorCode);
-        case 'B':
-            if (returnInputIfUnmatch) {
-                return LSR(language, script, region, LSR::EXPLICIT_LSR);
-            }
-            return LSR(PSEUDO_BIDI_PREFIX, language, script, region,
-                       LSR::EXPLICIT_LSR, errorCode);
-        case 'C':
-            if (returnInputIfUnmatch) {
-                return LSR(language, script, region, LSR::EXPLICIT_LSR);
+    if (!returnInputIfUnmatch) {
+        char c1;
+        if (region[0] == 'X' && (c1 = region[1]) != 0 && region[2] == 0) {
+            switch (c1) {
+            case 'A':
+                return LSR(PSEUDO_ACCENTS_PREFIX, language, script, region,
+                           LSR::EXPLICIT_LSR, errorCode);
+            case 'B':
+                return LSR(PSEUDO_BIDI_PREFIX, language, script, region,
+                           LSR::EXPLICIT_LSR, errorCode);
+            case 'C':
+                return LSR(PSEUDO_CRACKED_PREFIX, language, script, region,
+                           LSR::EXPLICIT_LSR, errorCode);
+            default:  // normal locale
+                break;
             }
-            return LSR(PSEUDO_CRACKED_PREFIX, language, script, region,
-                       LSR::EXPLICIT_LSR, errorCode);
-        default:  // normal locale
-            break;
         }
-    }
 
-    if (variant[0] == 'P' && variant[1] == 'S') {
-        int32_t lsrFlags = *region == 0 ?
-            LSR::EXPLICIT_LANGUAGE | LSR::EXPLICIT_SCRIPT : LSR::EXPLICIT_LSR;
-        if (uprv_strcmp(variant, "PSACCENT") == 0) {
-            return LSR(PSEUDO_ACCENTS_PREFIX, language, script,
-                       *region == 0 ? "XA" : region, lsrFlags, errorCode);
-        } else if (uprv_strcmp(variant, "PSBIDI") == 0) {
-            return LSR(PSEUDO_BIDI_PREFIX, language, script,
-                       *region == 0 ? "XB" : region, lsrFlags, errorCode);
-        } else if (uprv_strcmp(variant, "PSCRACK") == 0) {
-            return LSR(PSEUDO_CRACKED_PREFIX, language, script,
-                       *region == 0 ? "XC" : region, lsrFlags, errorCode);
+        if (variant[0] == 'P' && variant[1] == 'S') {
+            int32_t lsrFlags = *region == 0 ?
+                LSR::EXPLICIT_LANGUAGE | LSR::EXPLICIT_SCRIPT : LSR::EXPLICIT_LSR;
+            if (uprv_strcmp(variant, "PSACCENT") == 0) {
+                return LSR(PSEUDO_ACCENTS_PREFIX, language, script,
+                           *region == 0 ? "XA" : region, lsrFlags, errorCode);
+            } else if (uprv_strcmp(variant, "PSBIDI") == 0) {
+                return LSR(PSEUDO_BIDI_PREFIX, language, script,
+                           *region == 0 ? "XB" : region, lsrFlags, errorCode);
+            } else if (uprv_strcmp(variant, "PSCRACK") == 0) {
+                return LSR(PSEUDO_CRACKED_PREFIX, language, script,
+                           *region == 0 ? "XC" : region, lsrFlags, errorCode);
+            }
+            // else normal locale
         }
-        // else normal locale
-    }
+    } // end of if (!returnInputIfUnmatch)
 
     language = getCanonical(languageAliases, language);
     // (We have no script mappings.)
@@ -616,9 +609,9 @@ LSR LikelySubtags::maximize(const char *language, const char *script, const char
                              bool returnInputIfUnmatch,
                              UErrorCode &errorCode) const {
     if (U_FAILURE(errorCode)) { return {}; }
-    return maximize({language, (int32_t)uprv_strlen(language)},
-                    {script, (int32_t)uprv_strlen(script)},
-                    {region, (int32_t)uprv_strlen(region)},
+    return maximize({language, static_cast<int32_t>(uprv_strlen(language))},
+                    {script, static_cast<int32_t>(uprv_strlen(script))},
+                    {region, static_cast<int32_t>(uprv_strlen(region))},
                     returnInputIfUnmatch,
                     errorCode);
 }

thirdparty/icu4c/common/locmap.cpp

@@ -979,7 +979,7 @@ getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode& status)
     if (U_FAILURE(status)) { return locmap_root->hostID; }
     int32_t bestIdx = 0;
     int32_t bestIdxDiff = 0;
-    int32_t posixIDlen = (int32_t)uprv_strlen(posixID);
+    int32_t posixIDlen = static_cast<int32_t>(uprv_strlen(posixID));
     uint32_t idx;
 
     for (idx = 0; idx < this_0->numRegions; idx++ ) {

thirdparty/icu4c/common/locutil.cpp

@@ -171,7 +171,7 @@ LocaleUtility::initLocaleFromName(const UnicodeString& id, Locale& result)
         prev = 0;
         UErrorCode status = U_ZERO_ERROR;
         do {
-            i = id.indexOf((char16_t)0x40, prev);
+            i = id.indexOf(static_cast<char16_t>(0x40), prev);
             if(i < 0) {
                 // no @ between prev and the rest of the string
                 buffer.appendInvariantChars(id.tempSubString(prev), status);
@@ -224,7 +224,7 @@ LocaleUtility::getAvailableLocaleNames(const UnicodeString& bundleID)
 
     Hashtable* htp;
     umtx_lock(nullptr);
-    htp = (Hashtable*) cache->get(bundleID);
+    htp = static_cast<Hashtable*>(cache->get(bundleID));
     umtx_unlock(nullptr);
 
     if (htp == nullptr) {

thirdparty/icu4c/common/lstmbe.cpp

@@ -164,7 +164,7 @@ public:
     Array1D() : memory_(nullptr), data_(nullptr), d1_(0) {}
     Array1D(int32_t d1, UErrorCode &status)
         : memory_(uprv_malloc(d1 * sizeof(float))),
-          data_((float*)memory_), d1_(d1) {
+          data_(static_cast<float*>(memory_)), d1_(d1) {
         if (U_SUCCESS(status)) {
             if (memory_ == nullptr) {
                 status = U_MEMORY_ALLOCATION_ERROR;
@@ -301,7 +301,7 @@ public:
     Array2D() : memory_(nullptr), data_(nullptr), d1_(0), d2_(0) {}
     Array2D(int32_t d1, int32_t d2, UErrorCode &status)
         : memory_(uprv_malloc(d1 * d2 * sizeof(float))),
-          data_((float*)memory_), d1_(d1), d2_(d2) {
+          data_(static_cast<float*>(memory_)), d1_(d1), d2_(d2) {
         if (U_SUCCESS(status)) {
             if (memory_ == nullptr) {
                 status = U_MEMORY_ALLOCATION_ERROR;
@@ -526,11 +526,11 @@ void CodePointsVectorizer::vectorize(
         int32_t current;
         char16_t str[2] = {0, 0};
         while (U_SUCCESS(status) &&
-               (current = (int32_t)utext_getNativeIndex(text)) < endPos) {
+               (current = static_cast<int32_t>(utext_getNativeIndex(text))) < endPos) {
             // Since the LSTMBreakEngine is currently only accept chars in BMP,
             // we can ignore the possibility of hitting supplementary code
             // point.
-            str[0] = (char16_t) utext_next32(text);
+            str[0] = static_cast<char16_t>(utext_next32(text));
             U_ASSERT(!U_IS_SURROGATE(str[0]));
             offsets.addElement(current, status);
             indices.addElement(stringToIndex(str), status);
@@ -733,7 +733,7 @@ LSTMBreakEngine::divideUpDictionaryRange( UText *text,
 #endif  // LSTM_DEBUG
 
         // current = argmax(logp)
-        LSTMClass current = (LSTMClass)logp.maxIndex();
+        LSTMClass current = static_cast<LSTMClass>(logp.maxIndex());
         // BIES logic.
         if (current == BEGIN || current == SINGLE) {
             if (i != 0) {

thirdparty/icu4c/common/messagepattern.cpp

@@ -351,7 +351,7 @@ MessagePattern::autoQuoteApostropheDeep() const {
     for(int32_t i=count; i>0;) {
         const Part &part=getPart(--i);
         if(part.getType()==UMSGPAT_PART_TYPE_INSERT_CHAR) {
-           modified.insert(part.index, (char16_t)part.value);
+           modified.insert(part.index, static_cast<char16_t>(part.value));
         }
     }
     return modified;
@@ -437,7 +437,7 @@ MessagePattern::parseMessage(int32_t index, int32_t msgStartLength,
     if(U_FAILURE(errorCode)) {
         return 0;
     }
-    if(nestingLevel>Part::MAX_VALUE) {
+    if(nestingLevel>Part::MAX_NESTED_LEVELS) {
         errorCode=U_INDEX_OUTOFBOUNDS_ERROR;
         return 0;
     }
@@ -628,7 +628,7 @@ MessagePattern::parseArg(int32_t index, int32_t argStartLength, int32_t nestingL
             }
         }
         // change the ARG_START type from NONE to argType
-        partsList->a[argStart].value=(int16_t)argType;
+        partsList->a[argStart].value = static_cast<int16_t>(argType);
         if(argType==UMSGPAT_ARG_TYPE_SIMPLE) {
             addPart(UMSGPAT_PART_TYPE_ARG_TYPE, typeIndex, length, 0, errorCode);
         }
@@ -980,13 +980,13 @@ MessagePattern::parseDouble(int32_t start, int32_t limit, UBool allowInfinity,
         }
         // Let Double.parseDouble() throw a NumberFormatException.
         char numberChars[128];
-        int32_t capacity=(int32_t)sizeof(numberChars);
+        int32_t capacity = static_cast<int32_t>(sizeof(numberChars));
         int32_t length=limit-start;
         if(length>=capacity) {
             break;  // number too long
         }
         msg.extract(start, length, numberChars, capacity, US_INV);
-        if((int32_t)uprv_strlen(numberChars)<length) {
+        if (static_cast<int32_t>(uprv_strlen(numberChars)) < length) {
             break;  // contains non-invariant character that was turned into NUL
         }
         char *end;
@@ -1006,7 +1006,7 @@ MessagePattern::skipWhiteSpace(int32_t index) {
     const char16_t *s=msg.getBuffer();
     int32_t msgLength=msg.length();
     const char16_t *t=PatternProps::skipWhiteSpace(s+index, msgLength-index);
-    return (int32_t)(t-s);
+    return static_cast<int32_t>(t - s);
 }
 
 int32_t
@@ -1014,7 +1014,7 @@ MessagePattern::skipIdentifier(int32_t index) {
     const char16_t *s=msg.getBuffer();
     int32_t msgLength=msg.length();
     const char16_t *t=PatternProps::skipIdentifier(s+index, msgLength-index);
-    return (int32_t)(t-s);
+    return static_cast<int32_t>(t - s);
 }
 
 int32_t
@@ -1105,8 +1105,8 @@ MessagePattern::addPart(UMessagePatternPartType type, int32_t index, int32_t len
         Part &part=partsList->a[partsLength++];
         part.type=type;
         part.index=index;
-        part.length=(uint16_t)length;
-        part.value=(int16_t)value;
+        part.length = static_cast<uint16_t>(length);
+        part.value = static_cast<int16_t>(value);
         part.limitPartIndex=0;
     }
 }

thirdparty/icu4c/common/mlbe.cpp

@@ -57,12 +57,12 @@ int32_t MlBreakEngine::divideUpRange(UText *inText, int32_t rangeStart, int32_t
     // moving forward, finally the last six values in the indexList are
     // [length-4, length-3, length-2, length-1, -1, -1]. The "+4" here means four extra "-1".
     int32_t indexSize = codePointLength + 4;
-    int32_t *indexList = (int32_t *)uprv_malloc(indexSize * sizeof(int32_t));
-    if (indexList == nullptr) {
+    LocalMemory<int32_t> indexList(static_cast<int32_t*>(uprv_malloc(indexSize * sizeof(int32_t))));
+    if (indexList.isNull()) {
         status = U_MEMORY_ALLOCATION_ERROR;
         return 0;
     }
-    int32_t numCodeUnits = initIndexList(inString, indexList, status);
+    int32_t numCodeUnits = initIndexList(inString, indexList.getAlias(), status);
 
     // Add a break for the start.
     boundary.addElement(0, status);
@@ -71,13 +71,12 @@ int32_t MlBreakEngine::divideUpRange(UText *inText, int32_t rangeStart, int32_t
 
     for (int32_t idx = 0; idx + 1 < codePointLength && U_SUCCESS(status); idx++) {
         numBreaks =
-            evaluateBreakpoint(inString, indexList, idx, numCodeUnits, numBreaks, boundary, status);
+            evaluateBreakpoint(inString, indexList.getAlias(), idx, numCodeUnits, numBreaks, boundary, status);
         if (idx + 4 < codePointLength) {
             indexList[idx + 6] = numCodeUnits;
             numCodeUnits += U16_LENGTH(inString.char32At(indexList[idx + 6]));
         }
     }
-    uprv_free(indexList);
 
     if (U_FAILURE(status)) return 0;
 

thirdparty/icu4c/common/norm2allmodes.h

@@ -174,7 +174,7 @@ public:
             errorCode=U_ILLEGAL_ARGUMENT_ERROR;
             return 0;
         }
-        return (int32_t)(spanQuickCheckYes(sArray, sArray+s.length(), errorCode)-sArray);
+        return static_cast<int32_t>(spanQuickCheckYes(sArray, sArray + s.length(), errorCode) - sArray);
     }
     virtual const char16_t *
     spanQuickCheckYes(const char16_t *src, const char16_t *limit, UErrorCode &errorCode) const = 0;

thirdparty/icu4c/common/normalizer2.cpp

@@ -380,8 +380,8 @@ normalizeSecondAndAppend(const UNormalizer2 *norm2,
     firstLength=firstString.length();  // In case it was -1.
     // secondLength==0: Nothing to do, and n2wi->normalizeAndAppend(nullptr, nullptr, buffer, ...) would crash.
     if(secondLength!=0) {
-        const Normalizer2 *n2=(const Normalizer2 *)norm2;
-        const Normalizer2WithImpl *n2wi=dynamic_cast<const Normalizer2WithImpl *>(n2);
+        const Normalizer2* n2 = reinterpret_cast<const Normalizer2*>(norm2);
+        const Normalizer2WithImpl* n2wi = dynamic_cast<const Normalizer2WithImpl*>(n2);
         if(n2wi!=nullptr) {
             // Avoid duplicate argument checking and support NUL-terminated src.
             UnicodeString safeMiddle;

thirdparty/icu4c/common/normalizer2impl.cpp

@@ -53,9 +53,9 @@ namespace {
  */
 inline uint8_t leadByteForCP(UChar32 c) {
     if (c <= 0x7f) {
-        return (uint8_t)c;
+        return static_cast<uint8_t>(c);
     } else if (c <= 0x7ff) {
-        return (uint8_t)(0xc0+(c>>6));
+        return static_cast<uint8_t>(0xc0 + (c >> 6));
     } else {
         // Should not occur because ccc(U+0300)!=0.
         return 0xe0;
@@ -82,7 +82,7 @@ UChar32 codePointFromValidUTF8(const uint8_t *cpStart, const uint8_t *cpLimit) {
         return ((c&0x1f)<<6) | (cpStart[1]&0x3f);
     case 3:
         // no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (char16_t)
-        return (char16_t)((c<<12) | ((cpStart[1]&0x3f)<<6) | (cpStart[2]&0x3f));
+        return static_cast<char16_t>((c << 12) | ((cpStart[1] & 0x3f) << 6) | (cpStart[2] & 0x3f));
     case 4:
         return ((c&7)<<18) | ((cpStart[1]&0x3f)<<12) | ((cpStart[2]&0x3f)<<6) | (cpStart[3]&0x3f);
     default:
@@ -100,8 +100,8 @@ UChar32 previousHangulOrJamo(const uint8_t *start, const uint8_t *p) {
         uint8_t l = *p;
         uint8_t t1, t2;
         if (0xe1 <= l && l <= 0xed &&
-                (t1 = (uint8_t)(p[1] - 0x80)) <= 0x3f &&
-                (t2 = (uint8_t)(p[2] - 0x80)) <= 0x3f &&
+                (t1 = static_cast<uint8_t>(p[1] - 0x80)) <= 0x3f &&
+                (t2 = static_cast<uint8_t>(p[2] - 0x80)) <= 0x3f &&
                 (l < 0xed || t1 <= 0x1f)) {
             return ((l & 0xf) << 12) | (t1 << 6) | t2;
         }
@@ -125,7 +125,7 @@ int32_t getJamoTMinusBase(const uint8_t *src, const uint8_t *limit) {
             }
         } else if (src[1] == 0x87) {
             uint8_t t = src[2];
-            if ((int8_t)t <= (int8_t)0x82u) {
+            if (static_cast<int8_t>(t) <= static_cast<int8_t>(0x82u)) {
                 return t - (0xa7 - 0x40);
             }
         }
@@ -138,10 +138,10 @@ appendCodePointDelta(const uint8_t *cpStart, const uint8_t *cpLimit, int32_t del
                      ByteSink &sink, Edits *edits) {
     char buffer[U8_MAX_LENGTH];
     int32_t length;
-    int32_t cpLength = (int32_t)(cpLimit - cpStart);
+    int32_t cpLength = static_cast<int32_t>(cpLimit - cpStart);
     if (cpLength == 1) {
         // The builder makes ASCII map to ASCII.
-        buffer[0] = (uint8_t)(*cpStart + delta);
+        buffer[0] = static_cast<uint8_t>(*cpStart + delta);
         length = 1;
     } else {
         int32_t trail = *(cpLimit-1) + delta;
@@ -150,7 +150,7 @@ appendCodePointDelta(const uint8_t *cpStart, const uint8_t *cpLimit, int32_t del
             --cpLimit;
             length = 0;
             do { buffer[length++] = *cpStart++; } while (cpStart < cpLimit);
-            buffer[length++] = (uint8_t)trail;
+            buffer[length++] = static_cast<uint8_t>(trail);
         } else {
             // Decode the code point, add the delta, re-encode.
             UChar32 c = codePointFromValidUTF8(cpStart, cpLimit) + delta;
@@ -205,16 +205,16 @@ UBool ReorderingBuffer::init(int32_t destCapacity, UErrorCode &errorCode) {
 }
 
 UBool ReorderingBuffer::equals(const char16_t *otherStart, const char16_t *otherLimit) const {
-    int32_t length=(int32_t)(limit-start);
+    int32_t length = static_cast<int32_t>(limit - start);
     return
-        length==(int32_t)(otherLimit-otherStart) &&
+        length == static_cast<int32_t>(otherLimit - otherStart) &&
         0==u_memcmp(start, otherStart, length);
 }
 
 UBool ReorderingBuffer::equals(const uint8_t *otherStart, const uint8_t *otherLimit) const {
     U_ASSERT((otherLimit - otherStart) <= INT32_MAX);  // ensured by caller
-    int32_t length = (int32_t)(limit - start);
-    int32_t otherLength = (int32_t)(otherLimit - otherStart);
+    int32_t length = static_cast<int32_t>(limit - start);
+    int32_t otherLength = static_cast<int32_t>(otherLimit - otherStart);
     // For equal strings, UTF-8 is at least as long as UTF-16, and at most three times as long.
     if (otherLength < length || (otherLength / 3) > length) {
         return false;
@@ -284,7 +284,7 @@ UBool ReorderingBuffer::append(const char16_t *s, int32_t length, UBool isNFD,
             U16_NEXT(s, i, length, c);
             if(i<length) {
                 if (isNFD) {
-                    leadCC = Normalizer2Impl::getCCFromYesOrMaybe(impl.getRawNorm16(c));
+                    leadCC = Normalizer2Impl::getCCFromYesOrMaybeYes(impl.getRawNorm16(c));
                 } else {
                     leadCC = impl.getCC(impl.getNorm16(c));
                 }
@@ -304,7 +304,7 @@ UBool ReorderingBuffer::appendZeroCC(UChar32 c, UErrorCode &errorCode) {
     }
     remainingCapacity-=cpLength;
     if(cpLength==1) {
-        *limit++=(char16_t)c;
+        *limit++ = static_cast<char16_t>(c);
     } else {
         limit[0]=U16_LEAD(c);
         limit[1]=U16_TRAIL(c);
@@ -319,7 +319,7 @@ UBool ReorderingBuffer::appendZeroCC(const char16_t *s, const char16_t *sLimit,
     if(s==sLimit) {
         return true;
     }
-    int32_t length=(int32_t)(sLimit-s);
+    int32_t length = static_cast<int32_t>(sLimit - s);
     if(remainingCapacity<length && !resize(length, errorCode)) {
         return false;
     }
@@ -350,8 +350,8 @@ void ReorderingBuffer::removeSuffix(int32_t suffixLength) {
 }
 
 UBool ReorderingBuffer::resize(int32_t appendLength, UErrorCode &errorCode) {
-    int32_t reorderStartIndex=(int32_t)(reorderStart-start);
-    int32_t length=(int32_t)(limit-start);
+    int32_t reorderStartIndex = static_cast<int32_t>(reorderStart - start);
+    int32_t length = static_cast<int32_t>(limit - start);
     str.releaseBuffer(length);
     int32_t newCapacity=length+appendLength;
     int32_t doubleCapacity=2*str.getCapacity();
@@ -392,7 +392,7 @@ uint8_t ReorderingBuffer::previousCC() {
         --codePointStart;
         c=U16_GET_SUPPLEMENTARY(c2, c);
     }
-    return impl.getCCFromYesOrMaybeCP(c);
+    return impl.getCCFromYesOrMaybeYesCP(c);
 }
 
 // Inserts c somewhere before the last character.
@@ -440,15 +440,14 @@ Normalizer2Impl::init(const int32_t *inIndexes, const UCPTrie *inTrie,
     minNoNoCompNoMaybeCC = static_cast<uint16_t>(inIndexes[IX_MIN_NO_NO_COMP_NO_MAYBE_CC]);
     minNoNoEmpty = static_cast<uint16_t>(inIndexes[IX_MIN_NO_NO_EMPTY]);
     limitNoNo = static_cast<uint16_t>(inIndexes[IX_LIMIT_NO_NO]);
+    minMaybeNo = static_cast<uint16_t>(inIndexes[IX_MIN_MAYBE_NO]);
+    minMaybeNoCombinesFwd = static_cast<uint16_t>(inIndexes[IX_MIN_MAYBE_NO_COMBINES_FWD]);
     minMaybeYes = static_cast<uint16_t>(inIndexes[IX_MIN_MAYBE_YES]);
-    U_ASSERT((minMaybeYes & 7) == 0);  // 8-aligned for noNoDelta bit fields
-    centerNoNoDelta = (minMaybeYes >> DELTA_SHIFT) - MAX_DELTA - 1;
+    U_ASSERT((minMaybeNo & 7) == 0);  // 8-aligned for noNoDelta bit fields
+    centerNoNoDelta = (minMaybeNo >> DELTA_SHIFT) - MAX_DELTA - 1;
 
     normTrie=inTrie;
-
-    maybeYesCompositions=inExtraData;
-    extraData=maybeYesCompositions+((MIN_NORMAL_MAYBE_YES-minMaybeYes)>>OFFSET_SHIFT);
-
+    extraData=inExtraData;
     smallFCD=inSmallFCD;
 }
 
@@ -486,7 +485,7 @@ Normalizer2Impl::addPropertyStarts(const USetAdder *sa, UErrorCode & /*errorCode
     while ((end = ucptrie_getRange(normTrie, start, UCPMAP_RANGE_FIXED_LEAD_SURROGATES, INERT,
                                    nullptr, nullptr, &value)) >= 0) {
         sa->add(sa->set, start);
-        if (start != end && isAlgorithmicNoNo((uint16_t)value) &&
+        if (start != end && isAlgorithmicNoNo(static_cast<uint16_t>(value)) &&
                 (value & Normalizer2Impl::DELTA_TCCC_MASK) > Normalizer2Impl::DELTA_TCCC_1) {
             // Range of code points with same-norm16-value algorithmic decompositions.
             // They might have different non-zero FCD16 values.
@@ -570,7 +569,7 @@ Normalizer2Impl::decompose(const char16_t *src, const char16_t *limit,
                            int32_t destLengthEstimate,
                            UErrorCode &errorCode) const {
     if(destLengthEstimate<0 && limit!=nullptr) {
-        destLengthEstimate=(int32_t)(limit-src);
+        destLengthEstimate = static_cast<int32_t>(limit - src);
     }
     dest.remove();
     ReorderingBuffer buffer(*this, dest);
@@ -650,7 +649,7 @@ Normalizer2Impl::decompose(const char16_t *src, const char16_t *limit,
             }
         } else {
             if(isDecompYes(norm16)) {
-                uint8_t cc=getCCFromYesOrMaybe(norm16);
+                uint8_t cc=getCCFromYesOrMaybeYes(norm16);
                 if(prevCC<=cc || cc==0) {
                     prevCC=cc;
                     if(cc<=1) {
@@ -702,12 +701,13 @@ UBool Normalizer2Impl::decompose(UChar32 c, uint16_t norm16,
                                  UErrorCode &errorCode) const {
     // get the decomposition and the lead and trail cc's
     if (norm16 >= limitNoNo) {
-        if (isMaybeOrNonZeroCC(norm16)) {
-            return buffer.append(c, getCCFromYesOrMaybe(norm16), errorCode);
+        if (isMaybeYesOrNonZeroCC(norm16)) {
+            return buffer.append(c, getCCFromYesOrMaybeYes(norm16), errorCode);
+        } else if (norm16 < minMaybeNo) {
+            // Maps to an isCompYesAndZeroCC.
+            c=mapAlgorithmic(c, norm16);
+            norm16=getRawNorm16(c);
         }
-        // Maps to an isCompYesAndZeroCC.
-        c=mapAlgorithmic(c, norm16);
-        norm16=getRawNorm16(c);
     }
     if (norm16 < minYesNo) {
         // c does not decompose
@@ -718,17 +718,17 @@ UBool Normalizer2Impl::decompose(UChar32 c, uint16_t norm16,
         return buffer.appendZeroCC(jamos, jamos+Hangul::decompose(c, jamos), errorCode);
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getData(norm16);
     uint16_t firstUnit=*mapping;
     int32_t length=firstUnit&MAPPING_LENGTH_MASK;
     uint8_t leadCC, trailCC;
-    trailCC=(uint8_t)(firstUnit>>8);
+    trailCC = static_cast<uint8_t>(firstUnit >> 8);
     if(firstUnit&MAPPING_HAS_CCC_LCCC_WORD) {
-        leadCC=(uint8_t)(*(mapping-1)>>8);
+        leadCC = static_cast<uint8_t>(*(mapping - 1) >> 8);
     } else {
         leadCC=0;
     }
-    return buffer.append((const char16_t *)mapping+1, length, true, leadCC, trailCC, errorCode);
+    return buffer.append(reinterpret_cast<const char16_t*>(mapping) + 1, length, true, leadCC, trailCC, errorCode);
 }
 
 // Dual functionality:
@@ -787,9 +787,9 @@ Normalizer2Impl::decomposeUTF8(uint32_t options,
         }
 
         // Medium-fast path: Quick check.
-        if (isMaybeOrNonZeroCC(norm16)) {
+        if (isMaybeYesOrNonZeroCC(norm16)) {
             // Does not decompose.
-            uint8_t cc = getCCFromYesOrMaybe(norm16);
+            uint8_t cc = getCCFromYesOrMaybeYes(norm16);
             if (prevCC <= cc || cc == 0) {
                 prevCC = cc;
                 if (cc <= 1) {
@@ -836,7 +836,7 @@ Normalizer2Impl::decomposeUTF8(uint32_t options,
         }
         // We already know there was a change if the original character decomposed;
         // otherwise compare.
-        if (isMaybeOrNonZeroCC(norm16) && buffer.equals(prevBoundary, src)) {
+        if (isMaybeYesOrNonZeroCC(norm16) && buffer.equals(prevBoundary, src)) {
             if (!ByteSinkUtil::appendUnchanged(prevBoundary, src,
                                                *sink, options, edits, errorCode)) {
                 break;
@@ -867,9 +867,9 @@ Normalizer2Impl::decomposeShort(const uint8_t *src, const uint8_t *limit,
         // Get the decomposition and the lead and trail cc's.
         UChar32 c = U_SENTINEL;
         if (norm16 >= limitNoNo) {
-            if (isMaybeOrNonZeroCC(norm16)) {
+            if (isMaybeYesOrNonZeroCC(norm16)) {
                 // No comp boundaries around this character.
-                uint8_t cc = getCCFromYesOrMaybe(norm16);
+                uint8_t cc = getCCFromYesOrMaybeYes(norm16);
                 if (cc == 0 && stopAt == STOP_AT_DECOMP_BOUNDARY) {
                     return prevSrc;
                 }
@@ -881,14 +881,15 @@ Normalizer2Impl::decomposeShort(const uint8_t *src, const uint8_t *limit,
                     return src;
                 }
                 continue;
+            } else if (norm16 < minMaybeNo) {
+                // Maps to an isCompYesAndZeroCC.
+                if (stopAt != STOP_AT_LIMIT) {
+                    return prevSrc;
+                }
+                c = codePointFromValidUTF8(prevSrc, src);
+                c = mapAlgorithmic(c, norm16);
+                norm16 = getRawNorm16(c);
             }
-            // Maps to an isCompYesAndZeroCC.
-            if (stopAt != STOP_AT_LIMIT) {
-                return prevSrc;
-            }
-            c = codePointFromValidUTF8(prevSrc, src);
-            c = mapAlgorithmic(c, norm16);
-            norm16 = getRawNorm16(c);
         } else if (stopAt != STOP_AT_LIMIT && norm16 < minNoNoCompNoMaybeCC) {
             return prevSrc;
         }
@@ -918,20 +919,20 @@ Normalizer2Impl::decomposeShort(const uint8_t *src, const uint8_t *limit,
             }
         } else {
             // The character decomposes, get everything from the variable-length extra data.
-            const uint16_t *mapping = getMapping(norm16);
+            const uint16_t *mapping = getData(norm16);
             uint16_t firstUnit = *mapping;
             int32_t length = firstUnit & MAPPING_LENGTH_MASK;
-            uint8_t trailCC = (uint8_t)(firstUnit >> 8);
+            uint8_t trailCC = static_cast<uint8_t>(firstUnit >> 8);
             uint8_t leadCC;
             if (firstUnit & MAPPING_HAS_CCC_LCCC_WORD) {
-                leadCC = (uint8_t)(*(mapping-1) >> 8);
+                leadCC = static_cast<uint8_t>(*(mapping - 1) >> 8);
             } else {
                 leadCC = 0;
             }
             if (leadCC == 0 && stopAt == STOP_AT_DECOMP_BOUNDARY) {
                 return prevSrc;
             }
-            if (!buffer.append((const char16_t *)mapping+1, length, true, leadCC, trailCC, errorCode)) {
+            if (!buffer.append(reinterpret_cast<const char16_t*>(mapping) + 1, length, true, leadCC, trailCC, errorCode)) {
                 return nullptr;
             }
         }
@@ -946,7 +947,7 @@ Normalizer2Impl::decomposeShort(const uint8_t *src, const uint8_t *limit,
 const char16_t *
 Normalizer2Impl::getDecomposition(UChar32 c, char16_t buffer[4], int32_t &length) const {
     uint16_t norm16;
-    if(c<minDecompNoCP || isMaybeOrNonZeroCC(norm16=getNorm16(c))) {
+    if(c<minDecompNoCP || isMaybeYesOrNonZeroCC(norm16=getNorm16(c))) {
         // c does not decompose
         return nullptr;
     }
@@ -968,9 +969,9 @@ Normalizer2Impl::getDecomposition(UChar32 c, char16_t buffer[4], int32_t &length
         return buffer;
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getData(norm16);
     length=*mapping&MAPPING_LENGTH_MASK;
-    return (const char16_t *)mapping+1;
+    return reinterpret_cast<const char16_t*>(mapping) + 1;
 }
 
 // The capacity of the buffer must be 30=MAPPING_LENGTH_MASK-1
@@ -995,7 +996,7 @@ Normalizer2Impl::getRawDecomposition(UChar32 c, char16_t buffer[30], int32_t &le
         return buffer;
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getData(norm16);
     uint16_t firstUnit=*mapping;
     int32_t mLength=firstUnit&MAPPING_LENGTH_MASK;  // length of normal mapping
     if(firstUnit&MAPPING_HAS_RAW_MAPPING) {
@@ -1005,17 +1006,17 @@ Normalizer2Impl::getRawDecomposition(UChar32 c, char16_t buffer[30], int32_t &le
         uint16_t rm0=*rawMapping;
         if(rm0<=MAPPING_LENGTH_MASK) {
             length=rm0;
-            return (const char16_t *)rawMapping-rm0;
+            return reinterpret_cast<const char16_t*>(rawMapping) - rm0;
         } else {
             // Copy the normal mapping and replace its first two code units with rm0.
-            buffer[0]=(char16_t)rm0;
-            u_memcpy(buffer+1, (const char16_t *)mapping+1+2, mLength-2);
+            buffer[0] = static_cast<char16_t>(rm0);
+            u_memcpy(buffer + 1, reinterpret_cast<const char16_t*>(mapping) + 1 + 2, mLength - 2);
             length=mLength-1;
             return buffer;
         }
     } else {
         length=mLength;
-        return (const char16_t *)mapping+1;
+        return reinterpret_cast<const char16_t*>(mapping) + 1;
     }
 }
 
@@ -1052,7 +1053,7 @@ void Normalizer2Impl::decomposeAndAppend(const char16_t *src, const char16_t *li
         limit=u_strchr(p, 0);
     }
 
-    if (buffer.append(src, (int32_t)(p - src), false, firstCC, prevCC, errorCode)) {
+    if (buffer.append(src, static_cast<int32_t>(p - src), false, firstCC, prevCC, errorCode)) {
         buffer.appendZeroCC(p, limit, errorCode);
     }
 }
@@ -1070,7 +1071,7 @@ UBool Normalizer2Impl::norm16HasDecompBoundaryBefore(uint16_t norm16) const {
         return norm16 <= MIN_NORMAL_MAYBE_YES || norm16 == JAMO_VT;
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getDataForYesOrNo(norm16);
     uint16_t firstUnit=*mapping;
     // true if leadCC==0 (hasFCDBoundaryBefore())
     return (firstUnit&MAPPING_HAS_CCC_LCCC_WORD)==0 || (*(mapping-1)&0xff00)==0;
@@ -1091,14 +1092,15 @@ UBool Normalizer2Impl::norm16HasDecompBoundaryAfter(uint16_t norm16) const {
         return true;
     }
     if (norm16 >= limitNoNo) {
-        if (isMaybeOrNonZeroCC(norm16)) {
+        if (isMaybeYesOrNonZeroCC(norm16)) {
             return norm16 <= MIN_NORMAL_MAYBE_YES || norm16 == JAMO_VT;
+        } else if (norm16 < minMaybeNo) {
+            // Maps to an isCompYesAndZeroCC.
+            return (norm16 & DELTA_TCCC_MASK) <= DELTA_TCCC_1;
         }
-        // Maps to an isCompYesAndZeroCC.
-        return (norm16 & DELTA_TCCC_MASK) <= DELTA_TCCC_1;
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getData(norm16);
     uint16_t firstUnit=*mapping;
     // decomp after-boundary: same as hasFCDBoundaryAfter(),
     // fcd16<=1 || trailCC==0
@@ -1140,13 +1142,13 @@ int32_t Normalizer2Impl::combine(const uint16_t *list, UChar32 trail) {
     if(trail<COMP_1_TRAIL_LIMIT) {
         // trail character is 0..33FF
         // result entry may have 2 or 3 units
-        key1=(uint16_t)(trail<<1);
+        key1 = static_cast<uint16_t>(trail << 1);
         while(key1>(firstUnit=*list)) {
             list+=2+(firstUnit&COMP_1_TRIPLE);
         }
         if(key1==(firstUnit&COMP_1_TRAIL_MASK)) {
             if(firstUnit&COMP_1_TRIPLE) {
-                return ((int32_t)list[1]<<16)|list[2];
+                return (static_cast<int32_t>(list[1]) << 16) | list[2];
             } else {
                 return list[1];
             }
@@ -1154,10 +1156,10 @@ int32_t Normalizer2Impl::combine(const uint16_t *list, UChar32 trail) {
     } else {
         // trail character is 3400..10FFFF
         // result entry has 3 units
-        key1=(uint16_t)(COMP_1_TRAIL_LIMIT+
+        key1 = static_cast<uint16_t>(COMP_1_TRAIL_LIMIT +
                         (((trail>>COMP_1_TRAIL_SHIFT))&
                           ~COMP_1_TRIPLE));
-        uint16_t key2=(uint16_t)(trail<<COMP_2_TRAIL_SHIFT);
+        uint16_t key2 = static_cast<uint16_t>(trail << COMP_2_TRAIL_SHIFT);
         uint16_t secondUnit;
         for(;;) {
             if(key1>(firstUnit=*list)) {
@@ -1170,7 +1172,7 @@ int32_t Normalizer2Impl::combine(const uint16_t *list, UChar32 trail) {
                         list+=3;
                     }
                 } else if(key2==(secondUnit&COMP_2_TRAIL_MASK)) {
-                    return ((int32_t)(secondUnit&~COMP_2_TRAIL_MASK)<<16)|list[2];
+                    return (static_cast<int32_t>(secondUnit & ~COMP_2_TRAIL_MASK) << 16) | list[2];
                 } else {
                     break;
                 }
@@ -1195,7 +1197,7 @@ void Normalizer2Impl::addComposites(const uint16_t *list, UnicodeSet &set) const
             compositeAndFwd=list[1];
             list+=2;
         } else {
-            compositeAndFwd=(((int32_t)list[1]&~COMP_2_TRAIL_MASK)<<16)|list[2];
+            compositeAndFwd = ((static_cast<int32_t>(list[1]) & ~COMP_2_TRAIL_MASK) << 16) | list[2];
             list+=3;
         }
         UChar32 composite=compositeAndFwd>>1;
@@ -1240,7 +1242,7 @@ void Normalizer2Impl::recompose(ReorderingBuffer &buffer, int32_t recomposeStart
 
     for(;;) {
         UCPTRIE_FAST_U16_NEXT(normTrie, UCPTRIE_16, p, limit, c, norm16);
-        cc=getCCFromYesOrMaybe(norm16);
+        cc=getCCFromYesOrMaybeYes(norm16);
         if( // this character combines backward and
             isMaybe(norm16) &&
             // we have seen a starter that combines forward and
@@ -1252,15 +1254,15 @@ void Normalizer2Impl::recompose(ReorderingBuffer &buffer, int32_t recomposeStart
                 // c is a Jamo V/T, see if we can compose it with the previous character.
                 if(c<Hangul::JAMO_T_BASE) {
                     // c is a Jamo Vowel, compose with previous Jamo L and following Jamo T.
-                    char16_t prev=(char16_t)(*starter-Hangul::JAMO_L_BASE);
+                    char16_t prev = static_cast<char16_t>(*starter - Hangul::JAMO_L_BASE);
                     if(prev<Hangul::JAMO_L_COUNT) {
                         pRemove=p-1;
-                        char16_t syllable=(char16_t)
-                            (Hangul::HANGUL_BASE+
+                        char16_t syllable = static_cast<char16_t>(
+                            Hangul::HANGUL_BASE +
                              (prev*Hangul::JAMO_V_COUNT+(c-Hangul::JAMO_V_BASE))*
                              Hangul::JAMO_T_COUNT);
                         char16_t t;
-                        if(p!=limit && (t=(char16_t)(*p-Hangul::JAMO_T_BASE))<Hangul::JAMO_T_COUNT) {
+                        if (p != limit && (t = static_cast<char16_t>(*p - Hangul::JAMO_T_BASE)) < Hangul::JAMO_T_COUNT) {
                             ++p;
                             syllable+=t;  // The next character was a Jamo T.
                         }
@@ -1298,7 +1300,7 @@ void Normalizer2Impl::recompose(ReorderingBuffer &buffer, int32_t recomposeStart
                         starter[0]=U16_LEAD(composite);
                         starter[1]=U16_TRAIL(composite);
                     } else {
-                        *starter=(char16_t)composite;
+                        *starter = static_cast<char16_t>(composite);
                         // The composite is shorter than the starter,
                         // move the intermediate characters forward one.
                         starterIsSupplementary=false;
@@ -1323,7 +1325,7 @@ void Normalizer2Impl::recompose(ReorderingBuffer &buffer, int32_t recomposeStart
                     *--starter=U16_LEAD(composite);  // undo the temporary increment
                 } else {
                     // both are on the BMP
-                    *starter=(char16_t)composite;
+                    *starter = static_cast<char16_t>(composite);
                 }
 
                 /* remove the combining mark by moving the following text over it */
@@ -1414,17 +1416,22 @@ Normalizer2Impl::composePair(UChar32 a, UChar32 b) const {
             }
         } else {
             // 'a' has a compositions list in extraData
-            list=getMapping(norm16);
+            list=getDataForYesOrNo(norm16);
             if(norm16>minYesNo) {  // composite 'a' has both mapping & compositions list
                 list+=  // mapping pointer
                     1+  // +1 to skip the first unit with the mapping length
                     (*list&MAPPING_LENGTH_MASK);  // + mapping length
             }
         }
-    } else if(norm16<minMaybeYes || MIN_NORMAL_MAYBE_YES<=norm16) {
+    } else if(norm16<minMaybeNoCombinesFwd || MIN_NORMAL_MAYBE_YES<=norm16) {
         return U_SENTINEL;
     } else {
-        list=getCompositionsListForMaybe(norm16);
+        list=getDataForMaybe(norm16);
+        if(norm16<minMaybeYes) {  // composite 'a' has both mapping & compositions list
+            list+=  // mapping pointer
+                1+  // +1 to skip the first unit with the mapping length
+                (*list&MAPPING_LENGTH_MASK);  // + mapping length
+        }
     }
     if(b<0 || 0x10ffff<b) {  // combine(list, b) requires a valid code point b
         return U_SENTINEL;
@@ -1502,12 +1509,12 @@ Normalizer2Impl::compose(const char16_t *src, const char16_t *limit,
         }
         // isCompYesAndZeroCC(norm16) is false, that is, norm16>=minNoNo.
         // The current character is either a "noNo" (has a mapping)
-        // or a "maybeYes" (combines backward)
+        // or a "maybeYes" / "maybeNo" (combines backward)
         // or a "yesYes" with ccc!=0.
         // It is not a Hangul syllable or Jamo L because those have "yes" properties.
 
         // Medium-fast path: Handle cases that do not require full decomposition and recomposition.
-        if (!isMaybeOrNonZeroCC(norm16)) {  // minNoNo <= norm16 < minMaybeYes
+        if (norm16 < minMaybeNo) {  // minNoNo <= norm16 < minMaybeNo
             if (!doCompose) {
                 return false;
             }
@@ -1534,7 +1541,7 @@ Normalizer2Impl::compose(const char16_t *src, const char16_t *limit,
                     if (prevBoundary != prevSrc && !buffer.appendZeroCC(prevBoundary, prevSrc, errorCode)) {
                         break;
                     }
-                    const char16_t *mapping = reinterpret_cast<const char16_t *>(getMapping(norm16));
+                    const char16_t *mapping = reinterpret_cast<const char16_t *>(getDataForYesOrNo(norm16));
                     int32_t length = *mapping++ & MAPPING_LENGTH_MASK;
                     if(!buffer.appendZeroCC(mapping, mapping + length, errorCode)) {
                         break;
@@ -1562,14 +1569,14 @@ Normalizer2Impl::compose(const char16_t *src, const char16_t *limit,
             if(c<Hangul::JAMO_T_BASE) {
                 // The current character is a Jamo Vowel,
                 // compose with previous Jamo L and following Jamo T.
-                char16_t l = (char16_t)(prev-Hangul::JAMO_L_BASE);
+                char16_t l = static_cast<char16_t>(prev - Hangul::JAMO_L_BASE);
                 if(l<Hangul::JAMO_L_COUNT) {
                     if (!doCompose) {
                         return false;
                     }
                     int32_t t;
                     if (src != limit &&
-                            0 < (t = ((int32_t)*src - Hangul::JAMO_T_BASE)) &&
+                            0 < (t = (static_cast<int32_t>(*src) - Hangul::JAMO_T_BASE)) &&
                             t < Hangul::JAMO_T_COUNT) {
                         // The next character is a Jamo T.
                         ++src;
@@ -1587,7 +1594,7 @@ Normalizer2Impl::compose(const char16_t *src, const char16_t *limit,
                         if (prevBoundary != prevSrc && !buffer.appendZeroCC(prevBoundary, prevSrc, errorCode)) {
                             break;
                         }
-                        if(!buffer.appendBMP((char16_t)syllable, 0, errorCode)) {
+                        if (!buffer.appendBMP(static_cast<char16_t>(syllable), 0, errorCode)) {
                             break;
                         }
                         prevBoundary = src;
@@ -1612,7 +1619,7 @@ Normalizer2Impl::compose(const char16_t *src, const char16_t *limit,
                 if (prevBoundary != prevSrc && !buffer.appendZeroCC(prevBoundary, prevSrc, errorCode)) {
                     break;
                 }
-                if(!buffer.appendBMP((char16_t)syllable, 0, errorCode)) {
+                if (!buffer.appendBMP(static_cast<char16_t>(syllable), 0, errorCode)) {
                     break;
                 }
                 prevBoundary = src;
@@ -1763,7 +1770,7 @@ Normalizer2Impl::composeQuickCheck(const char16_t *src, const char16_t *limit,
         }
         // isCompYesAndZeroCC(norm16) is false, that is, norm16>=minNoNo.
         // The current character is either a "noNo" (has a mapping)
-        // or a "maybeYes" (combines backward)
+        // or a "maybeYes" / "maybeNo" (combines backward)
         // or a "yesYes" with ccc!=0.
         // It is not a Hangul syllable or Jamo L because those have "yes" properties.
 
@@ -1784,8 +1791,9 @@ Normalizer2Impl::composeQuickCheck(const char16_t *src, const char16_t *limit,
             }
         }
 
-        if(isMaybeOrNonZeroCC(norm16)) {
-            uint8_t cc=getCCFromYesOrMaybe(norm16);
+        if (norm16 >= minMaybeNo) {
+            uint16_t fcd16 = getFCD16FromMaybeOrNonZeroCC(norm16);
+            uint8_t cc = fcd16 >> 8;
             if (onlyContiguous /* FCC */ && cc != 0 &&
                     getTrailCCFromCompYesAndZeroCC(prevNorm16) > cc) {
                 // The [prevBoundary..prevSrc[ character
@@ -1806,11 +1814,12 @@ Normalizer2Impl::composeQuickCheck(const char16_t *src, const char16_t *limit,
                     if (src == limit) {
                         return src;
                     }
-                    uint8_t prevCC = cc;
+                    uint8_t prevCC = fcd16;
                     nextSrc = src;
                     UCPTRIE_FAST_U16_NEXT(normTrie, UCPTRIE_16, nextSrc, limit, c, norm16);
-                    if (isMaybeOrNonZeroCC(norm16)) {
-                        cc = getCCFromYesOrMaybe(norm16);
+                    if (norm16 >= minMaybeNo) {
+                        fcd16 = getFCD16FromMaybeOrNonZeroCC(norm16);
+                        cc = fcd16 >> 8;
                         if (!(prevCC <= cc || cc == 0)) {
                             break;
                         }
@@ -1845,11 +1854,11 @@ void Normalizer2Impl::composeAndAppend(const char16_t *src, const char16_t *limi
         if(src!=firstStarterInSrc) {
             const char16_t *lastStarterInDest=findPreviousCompBoundary(buffer.getStart(),
                                                                     buffer.getLimit(), onlyContiguous);
-            int32_t destSuffixLength=(int32_t)(buffer.getLimit()-lastStarterInDest);
+            int32_t destSuffixLength = static_cast<int32_t>(buffer.getLimit() - lastStarterInDest);
             UnicodeString middle(lastStarterInDest, destSuffixLength);
             buffer.removeSuffix(destSuffixLength);
             safeMiddle=middle;
-            middle.append(src, (int32_t)(firstStarterInSrc-src));
+            middle.append(src, static_cast<int32_t>(firstStarterInSrc - src));
             const char16_t *middleStart=middle.getBuffer();
             compose(middleStart, middleStart+middle.length(), onlyContiguous,
                     true, buffer, errorCode);
@@ -1903,12 +1912,12 @@ Normalizer2Impl::composeUTF8(uint32_t options, UBool onlyContiguous,
         }
         // isCompYesAndZeroCC(norm16) is false, that is, norm16>=minNoNo.
         // The current character is either a "noNo" (has a mapping)
-        // or a "maybeYes" (combines backward)
+        // or a "maybeYes" / "maybeNo" (combines backward)
         // or a "yesYes" with ccc!=0.
         // It is not a Hangul syllable or Jamo L because those have "yes" properties.
 
         // Medium-fast path: Handle cases that do not require full decomposition and recomposition.
-        if (!isMaybeOrNonZeroCC(norm16)) {  // minNoNo <= norm16 < minMaybeYes
+        if (norm16 < minMaybeNo) {  // minNoNo <= norm16 < minMaybeNo
             if (sink == nullptr) {
                 return false;
             }
@@ -1937,9 +1946,9 @@ Normalizer2Impl::composeUTF8(uint32_t options, UBool onlyContiguous,
                                                            *sink, options, edits, errorCode)) {
                         break;
                     }
-                    const uint16_t *mapping = getMapping(norm16);
+                    const uint16_t *mapping = getDataForYesOrNo(norm16);
                     int32_t length = *mapping++ & MAPPING_LENGTH_MASK;
-                    if (!ByteSinkUtil::appendChange(prevSrc, src, (const char16_t *)mapping, length,
+                    if (!ByteSinkUtil::appendChange(prevSrc, src, reinterpret_cast<const char16_t*>(mapping), length,
                                                     *sink, edits, errorCode)) {
                         break;
                     }
@@ -1958,7 +1967,7 @@ Normalizer2Impl::composeUTF8(uint32_t options, UBool onlyContiguous,
                         break;
                     }
                     if (edits != nullptr) {
-                        edits->addReplace((int32_t)(src - prevSrc), 0);
+                        edits->addReplace(static_cast<int32_t>(src - prevSrc), 0);
                     }
                     prevBoundary = src;
                     continue;
@@ -1976,7 +1985,7 @@ Normalizer2Impl::composeUTF8(uint32_t options, UBool onlyContiguous,
                 // The current character is a Jamo Vowel,
                 // compose with previous Jamo L and following Jamo T.
                 UChar32 l = prev - Hangul::JAMO_L_BASE;
-                if ((uint32_t)l < Hangul::JAMO_L_COUNT) {
+                if (static_cast<uint32_t>(l) < Hangul::JAMO_L_COUNT) {
                     if (sink == nullptr) {
                         return false;
                     }
@@ -2204,20 +2213,20 @@ uint8_t Normalizer2Impl::getPreviousTrailCC(const char16_t *start, const char16_
     if (start == p) {
         return 0;
     }
-    int32_t i = (int32_t)(p - start);
+    int32_t i = static_cast<int32_t>(p - start);
     UChar32 c;
     U16_PREV(start, 0, i, c);
-    return (uint8_t)getFCD16(c);
+    return static_cast<uint8_t>(getFCD16(c));
 }
 
 uint8_t Normalizer2Impl::getPreviousTrailCC(const uint8_t *start, const uint8_t *p) const {
     if (start == p) {
         return 0;
     }
-    int32_t i = (int32_t)(p - start);
+    int32_t i = static_cast<int32_t>(p - start);
     UChar32 c;
     U8_PREV(start, 0, i, c);
-    return (uint8_t)getFCD16(c);
+    return static_cast<uint8_t>(getFCD16(c));
 }
 
 // Note: normalizer2impl.cpp r30982 (2011-nov-27)
@@ -2245,7 +2254,7 @@ uint16_t Normalizer2Impl::getFCD16FromNormData(UChar32 c) const {
             return norm16|(norm16<<8);
         } else if(norm16>=minMaybeYes) {
             return 0;
-        } else {  // isDecompNoAlgorithmic(norm16)
+        } else if(norm16<minMaybeNo) {  // isDecompNoAlgorithmic(norm16)
             uint16_t deltaTrailCC = norm16 & DELTA_TCCC_MASK;
             if (deltaTrailCC <= DELTA_TCCC_1) {
                 return deltaTrailCC >> OFFSET_SHIFT;
@@ -2260,7 +2269,7 @@ uint16_t Normalizer2Impl::getFCD16FromNormData(UChar32 c) const {
         return 0;
     }
     // c decomposes, get everything from the variable-length extra data
-    const uint16_t *mapping=getMapping(norm16);
+    const uint16_t *mapping=getData(norm16);
     uint16_t firstUnit=*mapping;
     norm16=firstUnit>>8;  // tccc
     if(firstUnit&MAPPING_HAS_CCC_LCCC_WORD) {
@@ -2272,6 +2281,23 @@ uint16_t Normalizer2Impl::getFCD16FromNormData(UChar32 c) const {
 #pragma optimize( "", on )
 #endif
 
+uint16_t Normalizer2Impl::getFCD16FromMaybeOrNonZeroCC(uint16_t norm16) const {
+    U_ASSERT(norm16 >= minMaybeNo);
+    if (norm16 >= MIN_NORMAL_MAYBE_YES) {
+        // combining mark
+        norm16 = getCCFromNormalYesOrMaybe(norm16);
+        return norm16 | (norm16<<8);
+    } else if (norm16 >= minMaybeYes) {
+        return 0;
+    }
+    // c decomposes, get everything from the variable-length extra data
+    const uint16_t *mapping = getDataForMaybe(norm16);
+    uint16_t firstUnit = *mapping;
+    // maybeNo has lccc = 0
+    U_ASSERT((firstUnit & MAPPING_HAS_CCC_LCCC_WORD) == 0 || (*(mapping - 1) & 0xff00) == 0);
+    return firstUnit >> 8;  // tccc
+}
+
 // Dual functionality:
 // buffer!=nullptr: normalize
 // buffer==nullptr: isNormalized/quickCheck/spanQuickCheckYes
@@ -2395,7 +2421,7 @@ Normalizer2Impl::makeFCD(const char16_t *src, const char16_t *limit,
              * already but is now going to be decomposed.
              * prevSrc is set to after what was copied/appended.
              */
-            buffer->removeSuffix((int32_t)(prevSrc-prevBoundary));
+            buffer->removeSuffix(static_cast<int32_t>(prevSrc - prevBoundary));
             /*
              * Find the part of the source that needs to be decomposed,
              * up to the next safe boundary.
@@ -2426,11 +2452,11 @@ void Normalizer2Impl::makeFCDAndAppend(const char16_t *src, const char16_t *limi
         if(src!=firstBoundaryInSrc) {
             const char16_t *lastBoundaryInDest=findPreviousFCDBoundary(buffer.getStart(),
                                                                     buffer.getLimit());
-            int32_t destSuffixLength=(int32_t)(buffer.getLimit()-lastBoundaryInDest);
+            int32_t destSuffixLength = static_cast<int32_t>(buffer.getLimit() - lastBoundaryInDest);
             UnicodeString middle(lastBoundaryInDest, destSuffixLength);
             buffer.removeSuffix(destSuffixLength);
             safeMiddle=middle;
-            middle.append(src, (int32_t)(firstBoundaryInSrc-src));
+            middle.append(src, static_cast<int32_t>(firstBoundaryInSrc - src));
             const char16_t *middleStart=middle.getBuffer();
             makeFCD(middleStart, middleStart+middle.length(), &buffer, errorCode);
             if(U_FAILURE(errorCode)) {
@@ -2507,8 +2533,8 @@ void CanonIterData::addToStartSet(UChar32 origin, UChar32 decompLead, UErrorCode
             if(U_FAILURE(errorCode)) {
                 return;
             }
-            UChar32 firstOrigin=(UChar32)(canonValue&CANON_VALUE_MASK);
-            canonValue=(canonValue&~CANON_VALUE_MASK)|CANON_HAS_SET|(uint32_t)canonStartSets.size();
+            UChar32 firstOrigin = static_cast<UChar32>(canonValue & CANON_VALUE_MASK);
+            canonValue = (canonValue & ~CANON_VALUE_MASK) | CANON_HAS_SET | static_cast<uint32_t>(canonStartSets.size());
             umutablecptrie_set(mutableTrie, decompLead, canonValue, &errorCode);
             canonStartSets.adoptElement(lpSet.orphan(), errorCode);
             if (U_FAILURE(errorCode)) {
@@ -2518,7 +2544,7 @@ void CanonIterData::addToStartSet(UChar32 origin, UChar32 decompLead, UErrorCode
                 set->add(firstOrigin);
             }
         } else {
-            set=(UnicodeSet *)canonStartSets[(int32_t)(canonValue&CANON_VALUE_MASK)];
+            set = static_cast<UnicodeSet*>(canonStartSets[static_cast<int32_t>(canonValue & CANON_VALUE_MASK)]);
         }
         set->add(origin);
     }
@@ -2575,9 +2601,11 @@ void InitCanonIterData::doInit(Normalizer2Impl *impl, UErrorCode &errorCode) {
 void Normalizer2Impl::makeCanonIterDataFromNorm16(UChar32 start, UChar32 end, const uint16_t norm16,
                                                   CanonIterData &newData,
                                                   UErrorCode &errorCode) const {
-    if(isInert(norm16) || (minYesNo<=norm16 && norm16<minNoNo)) {
+    if(isInert(norm16) ||
+            (minYesNo<=norm16 && norm16<minNoNo) ||
+            (minMaybeNo<=norm16 && norm16<minMaybeYes)) {
         // Inert, or 2-way mapping (including Hangul syllable).
-        // We do not write a canonStartSet for any yesNo character.
+        // We do not write a canonStartSet for any yesNo/maybeNo character.
         // Composites from 2-way mappings are added at runtime from the
         // starter's compositions list, and the other characters in
         // 2-way mappings get CANON_NOT_SEGMENT_STARTER set because they are
@@ -2587,7 +2615,7 @@ void Normalizer2Impl::makeCanonIterDataFromNorm16(UChar32 start, UChar32 end, co
     for(UChar32 c=start; c<=end; ++c) {
         uint32_t oldValue = umutablecptrie_get(newData.mutableTrie, c);
         uint32_t newValue=oldValue;
-        if(isMaybeOrNonZeroCC(norm16)) {
+        if(isMaybeYesOrNonZeroCC(norm16)) {
             // not a segment starter if it occurs in a decomposition or has cc!=0
             newValue|=CANON_NOT_SEGMENT_STARTER;
             if(norm16<MIN_NORMAL_MAYBE_YES) {
@@ -2609,7 +2637,7 @@ void Normalizer2Impl::makeCanonIterDataFromNorm16(UChar32 start, UChar32 end, co
             }
             if (norm16_2 > minYesNo) {
                 // c decomposes, get everything from the variable-length extra data
-                const uint16_t *mapping=getMapping(norm16_2);
+                const uint16_t *mapping=getDataForYesOrNo(norm16_2);
                 uint16_t firstUnit=*mapping;
                 int32_t length=firstUnit&MAPPING_LENGTH_MASK;
                 if((firstUnit&MAPPING_HAS_CCC_LCCC_WORD)!=0) {
@@ -2657,11 +2685,11 @@ UBool Normalizer2Impl::ensureCanonIterData(UErrorCode &errorCode) const {
 }
 
 int32_t Normalizer2Impl::getCanonValue(UChar32 c) const {
-    return (int32_t)ucptrie_get(fCanonIterData->trie, c);
+    return static_cast<int32_t>(ucptrie_get(fCanonIterData->trie, c));
 }
 
 const UnicodeSet &Normalizer2Impl::getCanonStartSet(int32_t n) const {
-    return *(const UnicodeSet *)fCanonIterData->canonStartSets[n];
+    return *static_cast<const UnicodeSet*>(fCanonIterData->canonStartSets[n]);
 }
 
 UBool Normalizer2Impl::isCanonSegmentStarter(UChar32 c) const {
@@ -2684,7 +2712,7 @@ UBool Normalizer2Impl::getCanonStartSet(UChar32 c, UnicodeSet &set) const {
         uint16_t norm16=getRawNorm16(c);
         if(norm16==JAMO_L) {
             UChar32 syllable=
-                (UChar32)(Hangul::HANGUL_BASE+(c-Hangul::JAMO_L_BASE)*Hangul::JAMO_VT_COUNT);
+                static_cast<UChar32>(Hangul::HANGUL_BASE + (c - Hangul::JAMO_L_BASE) * Hangul::JAMO_VT_COUNT);
             set.add(syllable, syllable+Hangul::JAMO_VT_COUNT-1);
         } else {
             addComposites(getCompositionsList(norm16), set);
@@ -2728,7 +2756,7 @@ unorm2_swap(const UDataSwapper *ds,
         pInfo->dataFormat[1]==0x72 &&
         pInfo->dataFormat[2]==0x6d &&
         pInfo->dataFormat[3]==0x32 &&
-        (1<=formatVersion0 && formatVersion0<=4)
+        (1<=formatVersion0 && formatVersion0<=5)
     )) {
         udata_printError(ds, "unorm2_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as Normalizer2 data\n",
                          pInfo->dataFormat[0], pInfo->dataFormat[1],
@@ -2747,8 +2775,10 @@ unorm2_swap(const UDataSwapper *ds,
         minIndexesLength=Normalizer2Impl::IX_MIN_MAYBE_YES+1;
     } else if(formatVersion0==2) {
         minIndexesLength=Normalizer2Impl::IX_MIN_YES_NO_MAPPINGS_ONLY+1;
-    } else {
+    } else if(formatVersion0<=4) {
         minIndexesLength=Normalizer2Impl::IX_MIN_LCCC_CP+1;
+    } else {
+        minIndexesLength=Normalizer2Impl::IX_MIN_MAYBE_NO_COMBINES_FWD+1;
     }
 
     if(length>=0) {

thirdparty/icu4c/common/normalizer2impl.h

@@ -81,10 +81,10 @@ public:
         return 0<=c && c<HANGUL_COUNT && c%JAMO_T_COUNT==0;
     }
     static inline UBool isJamoL(UChar32 c) {
-        return (uint32_t)(c-JAMO_L_BASE)<JAMO_L_COUNT;
+        return static_cast<uint32_t>(c - JAMO_L_BASE) < JAMO_L_COUNT;
     }
     static inline UBool isJamoV(UChar32 c) {
-        return (uint32_t)(c-JAMO_V_BASE)<JAMO_V_COUNT;
+        return static_cast<uint32_t>(c - JAMO_V_BASE) < JAMO_V_COUNT;
     }
     static inline UBool isJamoT(UChar32 c) {
         int32_t t=c-JAMO_T_BASE;
@@ -103,12 +103,12 @@ public:
         c-=HANGUL_BASE;
         UChar32 c2=c%JAMO_T_COUNT;
         c/=JAMO_T_COUNT;
-        buffer[0]=(char16_t)(JAMO_L_BASE+c/JAMO_V_COUNT);
-        buffer[1]=(char16_t)(JAMO_V_BASE+c%JAMO_V_COUNT);
+        buffer[0] = static_cast<char16_t>(JAMO_L_BASE + c / JAMO_V_COUNT);
+        buffer[1] = static_cast<char16_t>(JAMO_V_BASE + c % JAMO_V_COUNT);
         if(c2==0) {
             return 2;
         } else {
-            buffer[2]=(char16_t)(JAMO_T_BASE+c2);
+            buffer[2] = static_cast<char16_t>(JAMO_T_BASE + c2);
             return 3;
         }
     }
@@ -123,11 +123,11 @@ public:
         UChar32 c2=c%JAMO_T_COUNT;
         if(c2==0) {
             c/=JAMO_T_COUNT;
-            buffer[0]=(char16_t)(JAMO_L_BASE+c/JAMO_V_COUNT);
-            buffer[1]=(char16_t)(JAMO_V_BASE+c%JAMO_V_COUNT);
+            buffer[0] = static_cast<char16_t>(JAMO_L_BASE + c / JAMO_V_COUNT);
+            buffer[1] = static_cast<char16_t>(JAMO_V_BASE + c % JAMO_V_COUNT);
         } else {
-            buffer[0]=(char16_t)(orig-c2);  // LV syllable
-            buffer[1]=(char16_t)(JAMO_T_BASE+c2);
+            buffer[0] = static_cast<char16_t>(orig - c2); // LV syllable
+            buffer[1] = static_cast<char16_t>(JAMO_T_BASE + c2);
         }
     }
 private:
@@ -147,13 +147,13 @@ public:
     ReorderingBuffer(const Normalizer2Impl &ni, UnicodeString &dest, UErrorCode &errorCode);
     ~ReorderingBuffer() {
         if (start != nullptr) {
-            str.releaseBuffer((int32_t)(limit-start));
+            str.releaseBuffer(static_cast<int32_t>(limit - start));
         }
     }
     UBool init(int32_t destCapacity, UErrorCode &errorCode);
 
     UBool isEmpty() const { return start==limit; }
-    int32_t length() const { return (int32_t)(limit-start); }
+    int32_t length() const { return static_cast<int32_t>(limit - start); }
     char16_t *getStart() { return start; }
     char16_t *getLimit() { return limit; }
     uint8_t getLastCC() const { return lastCC; }
@@ -163,7 +163,7 @@ public:
 
     UBool append(UChar32 c, uint8_t cc, UErrorCode &errorCode) {
         return (c<=0xffff) ?
-            appendBMP((char16_t)c, cc, errorCode) :
+            appendBMP(static_cast<char16_t>(c), cc, errorCode) :
             appendSupplementary(c, cc, errorCode);
     }
     UBool append(const char16_t *s, int32_t length, UBool isNFD,
@@ -190,12 +190,12 @@ public:
     void remove();
     void removeSuffix(int32_t suffixLength);
     void setReorderingLimit(char16_t *newLimit) {
-        remainingCapacity+=(int32_t)(limit-newLimit);
+        remainingCapacity += static_cast<int32_t>(limit - newLimit);
         reorderStart=limit=newLimit;
         lastCC=0;
     }
     void copyReorderableSuffixTo(UnicodeString &s) const {
-        s.setTo(ConstChar16Ptr(reorderStart), (int32_t)(limit-reorderStart));
+        s.setTo(ConstChar16Ptr(reorderStart), static_cast<int32_t>(limit - reorderStart));
     }
 private:
     /*
@@ -215,7 +215,7 @@ private:
     void insert(UChar32 c, uint8_t cc);
     static void writeCodePoint(char16_t *p, UChar32 c) {
         if(c<=0xffff) {
-            *p=(char16_t)c;
+            *p = static_cast<char16_t>(c);
         } else {
             p[0]=U16_LEAD(c);
             p[1]=U16_TRAIL(c);
@@ -241,7 +241,7 @@ private:
  * Low-level implementation of the Unicode Normalization Algorithm.
  * For the data structure and details see the documentation at the end of
  * this normalizer2impl.h and in the design doc at
- * https://icu.unicode.org/design/normalization/custom
+ * https://unicode-org.github.io/icu/design/normalization/custom.html
  */
 class U_COMMON_API Normalizer2Impl : public UObject {
 public:
@@ -271,14 +271,14 @@ public:
     UNormalizationCheckResult getCompQuickCheck(uint16_t norm16) const {
         if(norm16<minNoNo || MIN_YES_YES_WITH_CC<=norm16) {
             return UNORM_YES;
-        } else if(minMaybeYes<=norm16) {
+        } else if(minMaybeNo<=norm16) {
             return UNORM_MAYBE;
         } else {
             return UNORM_NO;
         }
     }
-    UBool isAlgorithmicNoNo(uint16_t norm16) const { return limitNoNo<=norm16 && norm16<minMaybeYes; }
-    UBool isCompNo(uint16_t norm16) const { return minNoNo<=norm16 && norm16<minMaybeYes; }
+    UBool isAlgorithmicNoNo(uint16_t norm16) const { return limitNoNo<=norm16 && norm16<minMaybeNo; }
+    UBool isCompNo(uint16_t norm16) const { return minNoNo<=norm16 && norm16<minMaybeNo; }
     UBool isDecompYes(uint16_t norm16) const { return norm16<minYesNo || minMaybeYes<=norm16; }
 
     uint8_t getCC(uint16_t norm16) const {
@@ -291,14 +291,14 @@ public:
         return getCCFromNoNo(norm16);
     }
     static uint8_t getCCFromNormalYesOrMaybe(uint16_t norm16) {
-        return (uint8_t)(norm16 >> OFFSET_SHIFT);
+        return static_cast<uint8_t>(norm16 >> OFFSET_SHIFT);
     }
-    static uint8_t getCCFromYesOrMaybe(uint16_t norm16) {
+    static uint8_t getCCFromYesOrMaybeYes(uint16_t norm16) {
         return norm16>=MIN_NORMAL_MAYBE_YES ? getCCFromNormalYesOrMaybe(norm16) : 0;
     }
-    uint8_t getCCFromYesOrMaybeCP(UChar32 c) const {
+    uint8_t getCCFromYesOrMaybeYesCP(UChar32 c) const {
         if (c < minCompNoMaybeCP) { return 0; }
-        return getCCFromYesOrMaybe(getNorm16(c));
+        return getCCFromYesOrMaybeYes(getNorm16(c));
     }
 
     /**
@@ -364,11 +364,13 @@ public:
         // 0<=lead<=0xffff
         uint8_t bits=smallFCD[lead>>8];
         if(bits==0) { return false; }
-        return (UBool)((bits>>((lead>>5)&7))&1);
+        return (bits >> ((lead >> 5) & 7)) & 1;
     }
     /** Returns the FCD value from the regular normalization data. */
     uint16_t getFCD16FromNormData(UChar32 c) const;
 
+    uint16_t getFCD16FromMaybeOrNonZeroCC(uint16_t norm16) const;
+
     /**
      * Gets the decomposition for one code point.
      * @param c code point
@@ -450,7 +452,13 @@ public:
 
         IX_MIN_LCCC_CP,
         IX_RESERVED19,
-        IX_COUNT
+
+        /** Two-way mappings; each starts with a character that combines backward. */
+        IX_MIN_MAYBE_NO,  // 20
+        /** Two-way mappings & compositions. */
+        IX_MIN_MAYBE_NO_COMBINES_FWD,
+
+        IX_COUNT  // 22
     };
 
     enum {
@@ -541,7 +549,8 @@ public:
         uint16_t norm16=getNorm16(c);
         return isCompYesAndZeroCC(norm16) &&
             (norm16 & HAS_COMP_BOUNDARY_AFTER) != 0 &&
-            (!onlyContiguous || isInert(norm16) || *getMapping(norm16) <= 0x1ff);
+            (!onlyContiguous || isInert(norm16) || *getDataForYesOrNo(norm16) <= 0x1ff);
+            // The last check fetches the mapping's first unit and checks tccc<=1.
     }
 
     UBool hasFCDBoundaryBefore(UChar32 c) const { return hasDecompBoundaryBefore(c); }
@@ -551,8 +560,8 @@ private:
     friend class InitCanonIterData;
     friend class LcccContext;
 
-    UBool isMaybe(uint16_t norm16) const { return minMaybeYes<=norm16 && norm16<=JAMO_VT; }
-    UBool isMaybeOrNonZeroCC(uint16_t norm16) const { return norm16>=minMaybeYes; }
+    UBool isMaybe(uint16_t norm16) const { return minMaybeNo<=norm16 && norm16<=JAMO_VT; }
+    UBool isMaybeYesOrNonZeroCC(uint16_t norm16) const { return norm16>=minMaybeYes; }
     static UBool isInert(uint16_t norm16) { return norm16==INERT; }
     static UBool isJamoL(uint16_t norm16) { return norm16==JAMO_L; }
     static UBool isJamoVT(uint16_t norm16) { return norm16==JAMO_VT; }
@@ -566,7 +575,7 @@ private:
     //     return norm16>=MIN_YES_YES_WITH_CC || norm16<minNoNo;
     // }
     // UBool isCompYesOrMaybe(uint16_t norm16) const {
-    //     return norm16<minNoNo || minMaybeYes<=norm16;
+    //     return norm16<minNoNo || minMaybeNo<=norm16;
     // }
     // UBool hasZeroCCFromDecompYes(uint16_t norm16) const {
     //     return norm16<=MIN_NORMAL_MAYBE_YES || norm16==JAMO_VT;
@@ -579,12 +588,12 @@ private:
     /**
      * A little faster and simpler than isDecompYesAndZeroCC() but does not include
      * the MaybeYes which combine-forward and have ccc=0.
-     * (Standard Unicode 10 normalization does not have such characters.)
      */
     UBool isMostDecompYesAndZeroCC(uint16_t norm16) const {
         return norm16<minYesNo || norm16==MIN_NORMAL_MAYBE_YES || norm16==JAMO_VT;
     }
-    UBool isDecompNoAlgorithmic(uint16_t norm16) const { return norm16>=limitNoNo; }
+    /** Since formatVersion 5: same as isAlgorithmicNoNo() */
+    UBool isDecompNoAlgorithmic(uint16_t norm16) const { return limitNoNo<=norm16 && norm16<minMaybeNo; }
 
     // For use with isCompYes().
     // Perhaps the compiler can combine the two tests for MIN_YES_YES_WITH_CC.
@@ -592,9 +601,9 @@ private:
     //     return norm16>=MIN_YES_YES_WITH_CC ? getCCFromNormalYesOrMaybe(norm16) : 0;
     // }
     uint8_t getCCFromNoNo(uint16_t norm16) const {
-        const uint16_t *mapping=getMapping(norm16);
+        const uint16_t *mapping=getDataForYesOrNo(norm16);
         if(*mapping&MAPPING_HAS_CCC_LCCC_WORD) {
-            return (uint8_t)*(mapping-1);
+            return static_cast<uint8_t>(*(mapping - 1));
         } else {
             return 0;
         }
@@ -605,7 +614,7 @@ private:
             return 0;  // yesYes and Hangul LV have ccc=tccc=0
         } else {
             // For Hangul LVT we harmlessly fetch a firstUnit with tccc=0 here.
-            return (uint8_t)(*getMapping(norm16)>>8);  // tccc from yesNo
+            return static_cast<uint8_t>(*getDataForYesOrNo(norm16) >> 8); // tccc from yesNo
         }
     }
     uint8_t getPreviousTrailCC(const char16_t *start, const char16_t *p) const;
@@ -619,28 +628,33 @@ private:
         return (norm16>>DELTA_SHIFT)-centerNoNoDelta;
     }
 
-    // Requires minYesNo<norm16<limitNoNo.
-    const uint16_t *getMapping(uint16_t norm16) const { return extraData+(norm16>>OFFSET_SHIFT); }
+    const uint16_t *getDataForYesOrNo(uint16_t norm16) const {
+        return extraData+(norm16>>OFFSET_SHIFT);
+    }
+    const uint16_t *getDataForMaybe(uint16_t norm16) const {
+        return extraData+((norm16-minMaybeNo+limitNoNo)>>OFFSET_SHIFT);
+    }
+    const uint16_t *getData(uint16_t norm16) const {
+        if(norm16>=minMaybeNo) {
+            norm16=norm16-minMaybeNo+limitNoNo;
+        }
+        return extraData+(norm16>>OFFSET_SHIFT);
+    }
     const uint16_t *getCompositionsListForDecompYes(uint16_t norm16) const {
         if(norm16<JAMO_L || MIN_NORMAL_MAYBE_YES<=norm16) {
             return nullptr;
-        } else if(norm16<minMaybeYes) {
-            return getMapping(norm16);  // for yesYes; if Jamo L: harmless empty list
         } else {
-            return maybeYesCompositions+norm16-minMaybeYes;
+            // if yesYes: if Jamo L: harmless empty list
+            return getData(norm16);
         }
     }
     const uint16_t *getCompositionsListForComposite(uint16_t norm16) const {
         // A composite has both mapping & compositions list.
-        const uint16_t *list=getMapping(norm16);
+        const uint16_t *list=getData(norm16);
         return list+  // mapping pointer
             1+  // +1 to skip the first unit with the mapping length
             (*list&MAPPING_LENGTH_MASK);  // + mapping length
     }
-    const uint16_t *getCompositionsListForMaybe(uint16_t norm16) const {
-        // minMaybeYes<=norm16<MIN_NORMAL_MAYBE_YES
-        return maybeYesCompositions+((norm16-minMaybeYes)>>OFFSET_SHIFT);
-    }
     /**
      * @param c code point must have compositions
      * @return compositions list pointer
@@ -692,11 +706,13 @@ private:
     /** For FCC: Given norm16 HAS_COMP_BOUNDARY_AFTER, does it have tccc<=1? */
     UBool isTrailCC01ForCompBoundaryAfter(uint16_t norm16) const {
         return isInert(norm16) || (isDecompNoAlgorithmic(norm16) ?
-            (norm16 & DELTA_TCCC_MASK) <= DELTA_TCCC_1 : *getMapping(norm16) <= 0x1ff);
+            (norm16 & DELTA_TCCC_MASK) <= DELTA_TCCC_1 : *getDataForYesOrNo(norm16) <= 0x1ff);
     }
 
-    const char16_t *findPreviousCompBoundary(const char16_t *start, const char16_t *p, UBool onlyContiguous) const;
-    const char16_t *findNextCompBoundary(const char16_t *p, const char16_t *limit, UBool onlyContiguous) const;
+    const char16_t *findPreviousCompBoundary(const char16_t *start, const char16_t *p,
+                                             UBool onlyContiguous) const;
+    const char16_t *findNextCompBoundary(const char16_t *p, const char16_t *limit,
+                                         UBool onlyContiguous) const;
 
     const char16_t *findPreviousFCDBoundary(const char16_t *start, const char16_t *p) const;
     const char16_t *findNextFCDBoundary(const char16_t *p, const char16_t *limit) const;
@@ -723,11 +739,12 @@ private:
     uint16_t minNoNoEmpty;
     uint16_t limitNoNo;
     uint16_t centerNoNoDelta;
+    uint16_t minMaybeNo;
+    uint16_t minMaybeNoCombinesFwd;
     uint16_t minMaybeYes;
 
     const UCPTrie *normTrie;
-    const uint16_t *maybeYesCompositions;
-    const uint16_t *extraData;  // mappings and/or compositions for yesYes, yesNo & noNo characters
+    const uint16_t *extraData;  // mappings and/or compositions
     const uint8_t *smallFCD;  // [0x100] one bit per 32 BMP code points, set if any FCD!=0
 
     UInitOnce       fCanonIterDataInitOnce {};
@@ -785,7 +802,7 @@ unorm_getFCD16(UChar32 c);
 
 /**
  * Format of Normalizer2 .nrm data files.
- * Format version 4.0.
+ * Format version 5.0.
  *
  * Normalizer2 .nrm data files provide data for the Unicode Normalization algorithms.
  * ICU ships with data files for standard Unicode Normalization Forms
@@ -807,7 +824,7 @@ unorm_getFCD16(UChar32 c);
  * Constants are defined as enum values of the Normalizer2Impl class.
  *
  * Many details of the data structures are described in the design doc
- * which is at https://icu.unicode.org/design/normalization/custom
+ * which is at https://unicode-org.github.io/icu/design/normalization/custom.html
  *
  * int32_t indexes[indexesLength]; -- indexesLength=indexes[IX_NORM_TRIE_OFFSET]/4;
  *
@@ -829,7 +846,9 @@ unorm_getFCD16(UChar32 c);
  *
  *      The next eight indexes are thresholds of 16-bit trie values for ranges of
  *      values indicating multiple normalization properties.
- *      They are listed here in threshold order, not in the order they are stored in the indexes.
+ *      Format version 5 adds the two minMaybeNo* threshold indexes.
+ *      The thresholds are listed here in threshold order,
+ *      not in the order they are stored in the indexes.
  *          minYesNo=indexes[IX_MIN_YES_NO];
  *          minYesNoMappingsOnly=indexes[IX_MIN_YES_NO_MAPPINGS_ONLY];
  *          minNoNo=indexes[IX_MIN_NO_NO];
@@ -837,6 +856,8 @@ unorm_getFCD16(UChar32 c);
  *          minNoNoCompNoMaybeCC=indexes[IX_MIN_NO_NO_COMP_NO_MAYBE_CC];
  *          minNoNoEmpty=indexes[IX_MIN_NO_NO_EMPTY];
  *          limitNoNo=indexes[IX_LIMIT_NO_NO];
+ *          minMaybeNo=indexes[IX_MIN_MAYBE_NO];
+ *          minMaybeNoCombinesFwd=indexes[IX_MIN_MAYBE_NO_COMBINES_FWD];
  *          minMaybeYes=indexes[IX_MIN_MAYBE_YES];
  *      See the normTrie description below and the design doc for details.
  *
@@ -845,13 +866,14 @@ unorm_getFCD16(UChar32 c);
  *      The trie holds the main normalization data. Each code point is mapped to a 16-bit value.
  *      Rather than using independent bits in the value (which would require more than 16 bits),
  *      information is extracted primarily via range checks.
- *      Except, format version 3 uses bit 0 for hasCompBoundaryAfter().
+ *      Except, format version 3+ uses bit 0 for hasCompBoundaryAfter().
  *      For example, a 16-bit value norm16 in the range minYesNo<=norm16<minNoNo
  *      means that the character has NF*C_QC=Yes and NF*D_QC=No properties,
  *      which means it has a two-way (round-trip) decomposition mapping.
- *      Values in the range 2<=norm16<limitNoNo are also directly indexes into the extraData
+ *      Values in the ranges 2<=norm16<limitNoNo and minMaybeNo<=norm16<minMaybeYes
+ *      are also directly indexes into the extraData
  *      pointing to mappings, compositions lists, or both.
- *      Value norm16==INERT (0 in versions 1 & 2, 1 in version 3)
+ *      Value norm16==INERT (0 in versions 1 & 2, 1 in version 3+)
  *      means that the character is normalization-inert, that is,
  *      it does not have a mapping, does not participate in composition, has a zero
  *      canonical combining class, and forms a boundary where text before it and after it
@@ -870,33 +892,38 @@ unorm_getFCD16(UChar32 c);
  *      When the lead surrogate unit's value exceeds the quick check minimum during processing,
  *      the properties for the full supplementary code point need to be looked up.
  *
- * uint16_t maybeYesCompositions[MIN_NORMAL_MAYBE_YES-minMaybeYes];
  * uint16_t extraData[];
  *
- *      There is only one byte offset for the end of these two arrays.
- *      The split between them is given by the constant and variable mentioned above.
- *      In version 3, the difference must be shifted right by OFFSET_SHIFT.
- *
- *      The maybeYesCompositions array contains compositions lists for characters that
- *      combine both forward (as starters in composition pairs)
- *      and backward (as trailing characters in composition pairs).
- *      Such characters do not occur in Unicode 5.2 but are allowed by
- *      the Unicode Normalization algorithms.
- *      If there are no such characters, then minMaybeYes==MIN_NORMAL_MAYBE_YES
- *      and the maybeYesCompositions array is empty.
- *      If there are such characters, then minMaybeYes is subtracted from their norm16 values
- *      to get the index into this array.
- *
- *      The extraData array contains compositions lists for "YesYes" characters,
- *      followed by mappings and optional compositions lists for "YesNo" characters,
- *      followed by only mappings for "NoNo" characters.
- *      (Referring to pairs of NFC/NFD quick check values.)
- *      The norm16 values of those characters are directly indexes into the extraData array.
- *      In version 3, the norm16 values must be shifted right by OFFSET_SHIFT
+ *      The extraData array contains many per-character data sections.
+ *      Each section contains mappings and/or composition lists.
+ *      The norm16 value of each character that has such data is directly an index to
+ *      a section of the extraData array.
+ *
+ *      In version 3+, the norm16 values must be shifted right by OFFSET_SHIFT
  *      for accessing extraData.
  *
  *      The data structures for compositions lists and mappings are described in the design doc.
  *
+ *      In version 4 and below, the composition lists for MaybeYes characters were stored before
+ *      the data for other characters.
+ *      This sub-array had a length of MIN_NORMAL_MAYBE_YES-minMaybeYes.
+ *      In version 3 & 4, the difference must be shifted right by OFFSET_SHIFT.
+ *
+ *      In version 5, the data for MaybeNo and MaybeYes characters is stored after
+ *      the data for other characters.
+ *
+ *      If there are no MaybeNo and no MaybeYes characters,
+ *      then minMaybeYes==minMaybeNo==MIN_NORMAL_MAYBE_YES.
+ *      If there are such characters, then minMaybeNo is subtracted from their norm16 values
+ *      to get the index into the extraData.
+ *      In version 4 and below, the data index for Yes* and No* characters needs to be
+ *      offset by the length of the MaybeYes data.
+ *      In version 5, the data index for Maybe* characters needs to be offset by limitNoNo.
+ *
+ *      Version 5 is the first to support MaybeNo characters, and
+ *      adds the minMaybeNo and minMaybeNoCombinesFwd thresholds and
+ *      the corresponding sections of the extraData.
+ *
  * uint8_t smallFCD[0x100]; -- new in format version 2
  *
  *      This is a bit set to help speed up FCD value lookups in the absence of a full
@@ -936,7 +963,7 @@ unorm_getFCD16(UChar32 c);
  *   to make room for two bits (three values) indicating whether the tccc is 0, 1, or greater.
  *   See DELTA_TCCC_MASK etc.
  *   This helps with fetching tccc/FCD values and FCC hasCompBoundaryAfter().
- *   minMaybeYes is 8-aligned so that the DELTA_TCCC_MASK bits can be tested directly.
+ *   minMaybeNo is 8-aligned so that the DELTA_TCCC_MASK bits can be tested directly.
  *
  * - Algorithmic mappings are only used for mapping to "comp yes and ccc=0" characters,
  *   and ASCII characters are mapped algorithmically only to other ASCII characters.
@@ -982,6 +1009,23 @@ unorm_getFCD16(UChar32 c);
  * gennorm2 now has to reject mappings for surrogate code points.
  * UTS #46 maps unpaired surrogates to U+FFFD in code rather than via its
  * custom normalization data file.
+ *
+ * Changes from format version 4 to format version 5 (ICU 76) ------------------
+ *
+ * Unicode 16 adds the first MaybeYes characters which combine both backward and forward,
+ * taking this formerly theoretical data structure into reality.
+ *
+ * Unicode 16 also adds the first characters that have two-way mappings whose first characters
+ * combine backward. In order for normalization and the quick check to work properly,
+ * these composite characters also must be marked as NFC_QC=Maybe,
+ * corresponding to "combines back", although the composites themselves do not combine backward.
+ * Format version 5 adds two new ranges between "algorithmic NoNo" and MaybeYes,
+ * with thresholds minMaybeNo and minMaybeNoCombinesFwd,
+ * and indexes[IX_MIN_MAYBE_NO] and indexes[IX_MIN_MAYBE_NO_COMBINES_FWD],
+ * and corresponding mappings and composition lists in the extraData.
+ *
+ * Format version 5 moves the data for Maybe* characters from the start of the extraData array
+ * to its end.
  */
 
 #endif  /* !UCONFIG_NO_NORMALIZATION */

thirdparty/icu4c/common/patternprops.cpp

@@ -120,12 +120,12 @@ PatternProps::isSyntax(UChar32 c) {
     if(c<0) {
         return false;
     } else if(c<=0xff) {
-        return (UBool)(latin1[c]>>1)&1;
+        return (latin1[c] >> 1) & 1;
     } else if(c<0x2010) {
         return false;
     } else if(c<=0x3030) {
         uint32_t bits=syntax2000[index2000[(c-0x2000)>>5]];
-        return (UBool)((bits>>(c&0x1f))&1);
+        return (bits >> (c & 0x1f)) & 1;
     } else if(0xfd3e<=c && c<=0xfe46) {
         return c<=0xfd3f || 0xfe45<=c;
     } else {
@@ -138,12 +138,12 @@ PatternProps::isSyntaxOrWhiteSpace(UChar32 c) {
     if(c<0) {
         return false;
     } else if(c<=0xff) {
-        return (UBool)(latin1[c]&1);
+        return latin1[c] & 1;
     } else if(c<0x200e) {
         return false;
     } else if(c<=0x3030) {
         uint32_t bits=syntaxOrWhiteSpace2000[index2000[(c-0x2000)>>5]];
-        return (UBool)((bits>>(c&0x1f))&1);
+        return (bits >> (c & 0x1f)) & 1;
     } else if(0xfd3e<=c && c<=0xfe46) {
         return c<=0xfd3f || 0xfe45<=c;
     } else {
@@ -156,7 +156,7 @@ PatternProps::isWhiteSpace(UChar32 c) {
     if(c<0) {
         return false;
     } else if(c<=0xff) {
-        return (UBool)(latin1[c]>>2)&1;
+        return (latin1[c] >> 2) & 1;
     } else if(0x200e<=c && c<=0x2029) {
         return c<=0x200f || 0x2028<=c;
     } else {

thirdparty/icu4c/common/propname.cpp

@@ -43,7 +43,7 @@ getASCIIPropertyNameChar(const char *name) {
     ) {}
 
     if(c!=0) {
-        return (i<<8)|(uint8_t)uprv_asciitolower((char)c);
+        return (i << 8) | static_cast<uint8_t>(uprv_asciitolower(c));
     } else {
         return i<<8;
     }
@@ -66,7 +66,7 @@ getEBCDICPropertyNameChar(const char *name) {
     ) {}
 
     if(c!=0) {
-        return (i<<8)|(uint8_t)uprv_ebcdictolower((char)c);
+        return (i << 8) | static_cast<uint8_t>(uprv_ebcdictolower(c));
     } else {
         return i<<8;
     }
@@ -231,7 +231,7 @@ UBool PropNameData::containsName(BytesTrie &trie, const char *name) {
         if(!USTRINGTRIE_HAS_NEXT(result)) {
             return false;
         }
-        result=trie.next((uint8_t)c);
+        result = trie.next(static_cast<uint8_t>(c));
     }
     return USTRINGTRIE_HAS_VALUE(result);
 }

thirdparty/icu4c/common/propsvec.cpp

@@ -102,29 +102,29 @@ _findRow(UPropsVectors *pv, UChar32 rangeStart) {
 
     /* check the vicinity of the last-seen row (start searching with an unrolled loop) */
     row=pv->v+prevRow*columns;
-    if(rangeStart>=(UChar32)row[0]) {
-        if(rangeStart<(UChar32)row[1]) {
+    if (rangeStart >= static_cast<UChar32>(row[0])) {
+        if (rangeStart < static_cast<UChar32>(row[1])) {
             /* same row as last seen */
             return row;
-        } else if(rangeStart<(UChar32)(row+=columns)[1]) {
+        } else if (rangeStart < static_cast<UChar32>((row += columns)[1])) {
             /* next row after the last one */
             pv->prevRow=prevRow+1;
             return row;
-        } else if(rangeStart<(UChar32)(row+=columns)[1]) {
+        } else if (rangeStart < static_cast<UChar32>((row += columns)[1])) {
             /* second row after the last one */
             pv->prevRow=prevRow+2;
             return row;
-        } else if((rangeStart-(UChar32)row[1])<10) {
+        } else if ((rangeStart - static_cast<UChar32>(row[1])) < 10) {
             /* we are close, continue looping */
             prevRow+=2;
             do {
                 ++prevRow;
                 row+=columns;
-            } while(rangeStart>=(UChar32)row[1]);
+            } while (rangeStart >= static_cast<UChar32>(row[1]));
             pv->prevRow=prevRow;
             return row;
         }
-    } else if(rangeStart<(UChar32)pv->v[1]) {
+    } else if (rangeStart < static_cast<UChar32>(pv->v[1])) {
         /* the very first row */
         pv->prevRow=0;
         return pv->v;
@@ -135,9 +135,9 @@ _findRow(UPropsVectors *pv, UChar32 rangeStart) {
     while(start<limit-1) {
         i=(start+limit)/2;
         row=pv->v+i*columns;
-        if(rangeStart<(UChar32)row[0]) {
+        if (rangeStart < static_cast<UChar32>(row[0])) {
             limit=i;
-        } else if(rangeStart<(UChar32)row[1]) {
+        } else if (rangeStart < static_cast<UChar32>(row[1])) {
             pv->prevRow=i;
             return row;
         } else {
@@ -194,8 +194,8 @@ upvec_setValue(UPropsVectors *pv,
      * input range (only possible for the first and last rows)
      * and if their value differs from the input value.
      */
-    splitFirstRow= (UBool)(start!=(UChar32)firstRow[0] && value!=(firstRow[column]&mask));
-    splitLastRow= (UBool)(limit!=(UChar32)lastRow[1] && value!=(lastRow[column]&mask));
+    splitFirstRow = start != static_cast<UChar32>(firstRow[0]) && value != (firstRow[column] & mask);
+    splitLastRow = limit != static_cast<UChar32>(lastRow[1]) && value != (lastRow[column] & mask);
 
     /* split first/last rows if necessary */
     if(splitFirstRow || splitLastRow) {
@@ -312,8 +312,8 @@ upvec_getRow(const UPropsVectors *pv, int32_t rowIndex,
 
 static int32_t U_CALLCONV
 upvec_compareRows(const void *context, const void *l, const void *r) {
-    const uint32_t *left=(const uint32_t *)l, *right=(const uint32_t *)r;
-    const UPropsVectors *pv=(const UPropsVectors *)context;
+    const uint32_t* left = static_cast<const uint32_t*>(l), *right = static_cast<const uint32_t*>(r);
+    const UPropsVectors* pv = static_cast<const UPropsVectors*>(context);
     int32_t i, count, columns;
 
     count=columns=pv->columns; /* includes start/limit columns */

thirdparty/icu4c/common/punycode.cpp

@@ -97,12 +97,12 @@ digitToBasic(int32_t digit, UBool uppercase) {
     /* 26..35 map to ASCII 0..9         */
     if(digit<26) {
         if(uppercase) {
-            return (char)(_CAPITAL_A+digit);
+            return static_cast<char>(_CAPITAL_A + digit);
         } else {
-            return (char)(_SMALL_A+digit);
+            return static_cast<char>(_SMALL_A + digit);
         }
     } else {
-        return (char)((_ZERO_-26)+digit);
+        return static_cast<char>((_ZERO_ - 26) + digit);
     }
 }
 
@@ -353,10 +353,10 @@ u_strToPunycode(const char16_t *src, int32_t srcLength,
                 }
 
                 if(destLength<destCapacity) {
-                    dest[destLength]=digitToBasic(q, (UBool)(cpBuffer[j]<0));
+                    dest[destLength] = digitToBasic(q, cpBuffer[j] < 0);
                 }
                 ++destLength;
-                bias=adaptBias(delta, handledCPCount+1, (UBool)(handledCPCount==basicLength));
+                bias = adaptBias(delta, handledCPCount + 1, handledCPCount == basicLength);
                 delta=0;
                 ++handledCPCount;
             }
@@ -421,7 +421,7 @@ u_strFromPunycode(const char16_t *src, int32_t srcLength,
         }
 
         if(j<destCapacity) {
-            dest[j]=(char16_t)b;
+            dest[j] = b;
 
             if(caseFlags!=nullptr) {
                 caseFlags[j]=IS_BASIC_UPPERCASE(b);
@@ -500,7 +500,7 @@ u_strFromPunycode(const char16_t *src, int32_t srcLength,
          * where needed instead of in for() loop tail.
          */
         ++destCPCount;
-        bias=adaptBias(i-oldi, destCPCount, (UBool)(oldi==0));
+        bias = adaptBias(i - oldi, destCPCount, oldi == 0);
 
         /*
          * i was supposed to wrap around from (incremented) destCPCount to 0,

thirdparty/icu4c/common/putil.cpp

@@ -46,11 +46,6 @@
 // First, the platform type. Need this for U_PLATFORM.
 #include "unicode/platform.h"
 
-#if U_PLATFORM == U_PF_MINGW && defined __STRICT_ANSI__
-/* tzset isn't defined in strict ANSI on MinGW. */
-#undef __STRICT_ANSI__
-#endif
-
 /*
  * Cygwin with GCC requires inclusion of time.h after the above disabling strict asci mode statement.
  */
@@ -180,8 +175,8 @@ typedef union {
     int64_t i64; /* This must be defined first in order to allow the initialization to work. This is a C89 feature. */
     double d64;
 } BitPatternConversion;
-static const BitPatternConversion gNan = { (int64_t) INT64_C(0x7FF8000000000000) };
-static const BitPatternConversion gInf = { (int64_t) INT64_C(0x7FF0000000000000) };
+static const BitPatternConversion gNan = {static_cast<int64_t>(INT64_C(0x7FF8000000000000))};
+static const BitPatternConversion gInf = {static_cast<int64_t>(INT64_C(0x7FF0000000000000))};
 
 /*---------------------------------------------------------------------------
   Platform utilities
@@ -230,7 +225,7 @@ u_signBit(double d) {
 #if U_IS_BIG_ENDIAN
     hiByte = *(uint8_t *)&d;
 #else
-    hiByte = *(((uint8_t *)&d) + sizeof(double) - 1);
+    hiByte = *(reinterpret_cast<uint8_t*>(&d) + sizeof(double) - 1);
 #endif
     return (hiByte & 0x80) != 0;
 }
@@ -347,7 +342,7 @@ uprv_isNaN(double number)
     BitPatternConversion convertedNumber;
     convertedNumber.d64 = number;
     /* Infinity is 0x7FF0000000000000U. Anything greater than that is a NaN */
-    return (UBool)((convertedNumber.i64 & U_INT64_MAX) > gInf.i64);
+    return (convertedNumber.i64 & U_INT64_MAX) > gInf.i64;
 
 #elif U_PLATFORM == U_PF_OS390
     uint32_t highBits = *(uint32_t*)u_topNBytesOfDouble(&number,
@@ -373,7 +368,7 @@ uprv_isInfinite(double number)
     BitPatternConversion convertedNumber;
     convertedNumber.d64 = number;
     /* Infinity is exactly 0x7FF0000000000000U. */
-    return (UBool)((convertedNumber.i64 & U_INT64_MAX) == gInf.i64);
+    return (convertedNumber.i64 & U_INT64_MAX) == gInf.i64;
 #elif U_PLATFORM == U_PF_OS390
     uint32_t highBits = *(uint32_t*)u_topNBytesOfDouble(&number,
                         sizeof(uint32_t));
@@ -394,7 +389,7 @@ U_CAPI UBool U_EXPORT2
 uprv_isPositiveInfinity(double number)
 {
 #if IEEE_754 || U_PLATFORM == U_PF_OS390
-    return (UBool)(number > 0 && uprv_isInfinite(number));
+    return number > 0 && uprv_isInfinite(number);
 #else
     return uprv_isInfinite(number);
 #endif
@@ -404,7 +399,7 @@ U_CAPI UBool U_EXPORT2
 uprv_isNegativeInfinity(double number)
 {
 #if IEEE_754 || U_PLATFORM == U_PF_OS390
-    return (UBool)(number < 0 && uprv_isInfinite(number));
+    return number < 0 && uprv_isInfinite(number);
 
 #else
     uint32_t highBits = *(uint32_t*)u_topNBytesOfDouble(&number,
@@ -749,11 +744,11 @@ static UBool isValidOlsonID(const char *id) {
     The timezone is sometimes set to "CST-7CDT", "CST6CDT5,J129,J131/19:30",
     "GRNLNDST3GRNLNDDT" or similar, so we cannot use it.
     The rest of the time it could be an Olson ID. George */
-    return (UBool)(id[idx] == 0
+    return id[idx] == 0
         || uprv_strcmp(id, "PST8PDT") == 0
         || uprv_strcmp(id, "MST7MDT") == 0
         || uprv_strcmp(id, "CST6CDT") == 0
-        || uprv_strcmp(id, "EST5EDT") == 0);
+        || uprv_strcmp(id, "EST5EDT") == 0;
 }
 
 /* On some Unix-like OS, 'posix' subdirectory in
@@ -932,7 +927,7 @@ static UBool compareBinaryFiles(const char* defaultTZFileName, const char* TZFil
              */
             if (tzInfo->defaultTZBuffer == nullptr) {
                 rewind(tzInfo->defaultTZFilePtr);
-                tzInfo->defaultTZBuffer = (char*)uprv_malloc(sizeof(char) * tzInfo->defaultTZFileSize);
+                tzInfo->defaultTZBuffer = static_cast<char*>(uprv_malloc(sizeof(char) * tzInfo->defaultTZFileSize));
                 sizeFileRead = fread(tzInfo->defaultTZBuffer, 1, tzInfo->defaultTZFileSize, tzInfo->defaultTZFilePtr);
             }
             rewind(file);

thirdparty/icu4c/common/putilimp.h

@@ -90,6 +90,8 @@ typedef size_t uintptr_t;
 #   define U_NL_LANGINFO_CODESET -1
 #elif U_PLATFORM == U_PF_OS400
    /* not defined */
+#elif U_PLATFORM == U_PF_HAIKU
+   /* not defined */
 #else
 #   define U_NL_LANGINFO_CODESET CODESET
 #endif
@@ -103,6 +105,8 @@ typedef size_t uintptr_t;
 #endif
 #elif U_PLATFORM == U_PF_OS400
    /* not defined */
+#elif U_PLATFORM == U_PF_HAIKU
+   /* not defined */
 #else
 #   define U_TZSET tzset
 #endif
@@ -141,6 +145,8 @@ typedef size_t uintptr_t;
 #endif
 #elif U_PLATFORM == U_PF_OS400
    /* not defined */
+#elif U_PLATFORM == U_PF_HAIKU
+    /* not defined, (well it is but a loop back to icu) */
 #else
 #   define U_TZNAME tzname
 #endif
@@ -553,7 +559,7 @@ inline int32_t pinCapacity(T *dest, int32_t capacity) {
     if (maxInt < destInt) {
         // Less than 2GB to the end of the address space.
         // Pin to that to prevent address overflow.
-        maxInt = (uintptr_t)-1;
+        maxInt = static_cast<uintptr_t>(-1);
     }
 #  endif
 

thirdparty/icu4c/common/rbbi.cpp

@@ -110,7 +110,7 @@ RuleBasedBreakIterator::RuleBasedBreakIterator(const uint8_t *compiledRules,
         status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
     }
-    const RBBIDataHeader *data = (const RBBIDataHeader *)compiledRules;
+    const RBBIDataHeader* data = reinterpret_cast<const RBBIDataHeader*>(compiledRules);
     if (data->fLength > ruleLength) {
         status = U_ILLEGAL_ARGUMENT_ERROR;
         return;
@@ -553,7 +553,7 @@ int32_t RuleBasedBreakIterator::first() {
  * @return The text's past-the-end offset.
  */
 int32_t RuleBasedBreakIterator::last() {
-    int32_t endPos = (int32_t)utext_nativeLength(&fText);
+    int32_t endPos = static_cast<int32_t>(utext_nativeLength(&fText));
     UBool endShouldBeBoundary = isBoundary(endPos);      // Has side effect of setting iterator position.
     (void)endShouldBeBoundary;
     U_ASSERT(endShouldBeBoundary);
@@ -625,7 +625,7 @@ int32_t RuleBasedBreakIterator::following(int32_t startPos) {
     // Move requested offset to a code point start. It might be on a trail surrogate,
     // or on a trail byte if the input is UTF-8. Or it may be beyond the end of the text.
     utext_setNativeIndex(&fText, startPos);
-    startPos = (int32_t)utext_getNativeIndex(&fText);
+    startPos = static_cast<int32_t>(utext_getNativeIndex(&fText));
 
     UErrorCode status = U_ZERO_ERROR;
     fBreakCache->following(startPos, status);
@@ -881,7 +881,7 @@ int32_t RuleBasedBreakIterator::handleNext() {
         if (accepting == ACCEPTING_UNCONDITIONAL) {
             // Match found, common case.
             if (mode != RBBI_START) {
-                result = (int32_t)UTEXT_GETNATIVEINDEX(&fText);
+                result = static_cast<int32_t>(UTEXT_GETNATIVEINDEX(&fText));
             }
             fRuleStatusIndex = row->fTagsIdx;   // Remember the break status (tag) values.
         } else if (accepting > ACCEPTING_UNCONDITIONAL) {
@@ -905,7 +905,7 @@ int32_t RuleBasedBreakIterator::handleNext() {
         U_ASSERT(rule == 0 || rule > ACCEPTING_UNCONDITIONAL);
         U_ASSERT(rule == 0 || rule < fData->fForwardTable->fLookAheadResultsSize);
         if (rule > ACCEPTING_UNCONDITIONAL) {
-            int32_t  pos = (int32_t)UTEXT_GETNATIVEINDEX(&fText);
+            int32_t pos = static_cast<int32_t>(UTEXT_GETNATIVEINDEX(&fText));
             fLookAheadMatches[rule] = pos;
         }
 
@@ -937,7 +937,7 @@ int32_t RuleBasedBreakIterator::handleNext() {
     if (result == initialPosition) {
         utext_setNativeIndex(&fText, initialPosition);
         utext_next32(&fText);
-        result = (int32_t)utext_getNativeIndex(&fText);
+        result = static_cast<int32_t>(utext_getNativeIndex(&fText));
         fRuleStatusIndex = 0;
     }
 
@@ -1027,7 +1027,7 @@ int32_t RuleBasedBreakIterator::handleSafePrevious(int32_t fromPosition) {
     }
 
     // The state machine is done.  Check whether it found a match...
-    result = (int32_t)UTEXT_GETNATIVEINDEX(&fText);
+    result = static_cast<int32_t>(UTEXT_GETNATIVEINDEX(&fText));
     #ifdef RBBI_DEBUG
         if (gTrace) {
             RBBIDebugPrintf("result = %d\n\n", result);
@@ -1091,7 +1091,7 @@ const uint8_t  *RuleBasedBreakIterator::getBinaryRules(uint32_t &length) {
     length = 0;
 
     if (fData != nullptr) {
-        retPtr = (const uint8_t *)fData->fHeader;
+        retPtr = reinterpret_cast<const uint8_t*>(fData->fHeader);
         length = fData->fHeader->fLength;
     }
     return retPtr;
@@ -1187,7 +1187,7 @@ getLanguageBreakEngineFromFactory(UChar32 c, const char* locale)
     int32_t i = gLanguageBreakFactories->size();
     const LanguageBreakEngine *lbe = nullptr;
     while (--i >= 0) {
-        LanguageBreakFactory *factory = (LanguageBreakFactory *)(gLanguageBreakFactories->elementAt(i));
+        LanguageBreakFactory* factory = static_cast<LanguageBreakFactory*>(gLanguageBreakFactories->elementAt(i));
         lbe = factory->getEngineFor(c, locale);
         if (lbe != nullptr) {
             break;
@@ -1219,7 +1219,7 @@ RuleBasedBreakIterator::getLanguageBreakEngine(UChar32 c, const char* locale) {
 
     int32_t i = fLanguageBreakEngines->size();
     while (--i >= 0) {
-        lbe = (const LanguageBreakEngine *)(fLanguageBreakEngines->elementAt(i));
+        lbe = static_cast<const LanguageBreakEngine*>(fLanguageBreakEngines->elementAt(i));
         if (lbe->handles(c, locale)) {
             return lbe;
         }

thirdparty/icu4c/common/rbbi_cache.cpp

@@ -146,7 +146,7 @@ void RuleBasedBreakIterator::DictionaryCache::populateDictionary(int32_t startPo
     uint32_t dictStart = fBI->fData->fForwardTable->fDictCategoriesStart;
 
     while(U_SUCCESS(status)) {
-        while((current = (int32_t)UTEXT_GETNATIVEINDEX(text)) < rangeEnd
+        while ((current = static_cast<int32_t>(UTEXT_GETNATIVEINDEX(text))) < rangeEnd
                 && (category < dictStart)) {
             utext_next32(text);           // TODO: cleaner loop structure.
             c = utext_current32(text);
@@ -221,7 +221,7 @@ void RuleBasedBreakIterator::BreakCache::reset(int32_t pos, int32_t ruleStatus)
     fTextIdx = pos;
     fBufIdx = 0;
     fBoundaries[0] = pos;
-    fStatuses[0] = (uint16_t)ruleStatus;
+    fStatuses[0] = static_cast<uint16_t>(ruleStatus);
 }
 
 

thirdparty/icu4c/common/rbbidata.cpp

@@ -104,10 +104,10 @@ void RBBIDataWrapper::init(const RBBIDataHeader *data, UErrorCode &status) {
 
     fDontFreeData = false;
     if (data->fFTableLen != 0) {
-        fForwardTable = (RBBIStateTable *)((char *)data + fHeader->fFTable);
+        fForwardTable = reinterpret_cast<const RBBIStateTable*>(reinterpret_cast<const char*>(data) + fHeader->fFTable);
     }
     if (data->fRTableLen != 0) {
-        fReverseTable = (RBBIStateTable *)((char *)data + fHeader->fRTable);
+        fReverseTable = reinterpret_cast<const RBBIStateTable*>(reinterpret_cast<const char*>(data) + fHeader->fRTable);
     }
 
     fTrie = ucptrie_openFromBinary(UCPTRIE_TYPE_FAST,
@@ -130,7 +130,7 @@ void RBBIDataWrapper::init(const RBBIDataHeader *data, UErrorCode &status) {
     fRuleString = UnicodeString::fromUTF8(StringPiece(fRuleSource, fHeader->fRuleSourceLen));
     U_ASSERT(data->fRuleSourceLen > 0);
 
-    fRuleStatusTable = (int32_t *)((char *)data + fHeader->fStatusTable);
+    fRuleStatusTable = reinterpret_cast<const int32_t*>(reinterpret_cast<const char*>(data) + fHeader->fStatusTable);
     fStatusMaxIdx    = data->fStatusTableLen / sizeof(int32_t);
 
     fRefCount = 1;

thirdparty/icu4c/common/rbbirb.cpp

@@ -103,7 +103,7 @@ RBBIRuleBuilder::~RBBIRuleBuilder() {
 
     int        i;
     for (i=0; ; i++) {
-        RBBINode *n = (RBBINode *)fUSetNodes->elementAt(i);
+        RBBINode* n = static_cast<RBBINode*>(fUSetNodes->elementAt(i));
         if (n==nullptr) {
             break;
         }
@@ -182,12 +182,12 @@ RBBIDataHeader *RBBIRuleBuilder::flattenData() {
     }
 #endif
 
-    RBBIDataHeader  *data     = (RBBIDataHeader *)uprv_malloc(totalSize);
-    if (data == nullptr) {
+    LocalMemory<RBBIDataHeader> data(static_cast<RBBIDataHeader*>(uprv_malloc(totalSize)));
+    if (data.isNull()) {
         *fStatus = U_MEMORY_ALLOCATION_ERROR;
         return nullptr;
     }
-    uprv_memset(data, 0, totalSize);
+    uprv_memset(data.getAlias(), 0, totalSize);
 
 
     data->fMagic            = 0xb1a0;
@@ -213,23 +213,23 @@ RBBIDataHeader *RBBIRuleBuilder::flattenData() {
 
     uprv_memset(data->fReserved, 0, sizeof(data->fReserved));
 
-    fForwardTable->exportTable((uint8_t *)data + data->fFTable);
-    fForwardTable->exportSafeTable((uint8_t *)data + data->fRTable);
-    fSetBuilder->serializeTrie ((uint8_t *)data + data->fTrie);
+    fForwardTable->exportTable(reinterpret_cast<uint8_t*>(data.getAlias()) + data->fFTable);
+    fForwardTable->exportSafeTable(reinterpret_cast<uint8_t*>(data.getAlias()) + data->fRTable);
+    fSetBuilder->serializeTrie(reinterpret_cast<uint8_t*>(data.getAlias()) + data->fTrie);
 
-    int32_t *ruleStatusTable = (int32_t *)((uint8_t *)data + data->fStatusTable);
+    int32_t* ruleStatusTable = reinterpret_cast<int32_t*>(reinterpret_cast<uint8_t*>(data.getAlias()) + data->fStatusTable);
     for (i=0; i<fRuleStatusVals->size(); i++) {
         ruleStatusTable[i] = fRuleStatusVals->elementAti(i);
     }
 
-    u_strToUTF8WithSub((char *)data+data->fRuleSource, rulesSize, &rulesLengthInUTF8,
+    u_strToUTF8WithSub(reinterpret_cast<char*>(data.getAlias()) + data->fRuleSource, rulesSize, &rulesLengthInUTF8,
                        fStrippedRules.getBuffer(), fStrippedRules.length(),
                        0xfffd, nullptr, fStatus);
     if (U_FAILURE(*fStatus)) {
         return nullptr;
     }
 
-    return data;
+    return data.orphan();
 }
 
 

thirdparty/icu4c/common/rbbiscan.cpp

@@ -748,7 +748,7 @@ void RBBIRuleScanner::findSetFor(const UnicodeString &s, RBBINode *node, Unicode
     // First check whether we've already cached a set for this string.
     // If so, just use the cached set in the new node.
     //   delete any set provided by the caller, since we own it.
-    el = (RBBISetTableEl *)uhash_get(fSetTable, &s);
+    el = static_cast<RBBISetTableEl*>(uhash_get(fSetTable, &s));
     if (el != nullptr) {
         delete setToAdopt;
         node->fLeftChild = el->val;
@@ -794,7 +794,7 @@ void RBBIRuleScanner::findSetFor(const UnicodeString &s, RBBINode *node, Unicode
     //
     // Add the new set to the set hash table.
     //
-    el      = (RBBISetTableEl *)uprv_malloc(sizeof(RBBISetTableEl));
+    el = static_cast<RBBISetTableEl*>(uprv_malloc(sizeof(RBBISetTableEl)));
     UnicodeString *tkey = new UnicodeString(s);
     if (tkey == nullptr || el == nullptr || setToAdopt == nullptr) {
         // Delete to avoid memory leak
@@ -864,7 +864,7 @@ UChar32  RBBIRuleScanner::nextCharLL() {
     UChar32  ch;
 
     if (fNextIndex >= fRB->fRules.length()) {
-        return (UChar32)-1;
+        return static_cast<UChar32>(-1);
     }
     ch         = fRB->fRules.char32At(fNextIndex);
     if (U_IS_SURROGATE(ch)) {
@@ -939,7 +939,7 @@ void RBBIRuleScanner::nextChar(RBBIRuleChar &c) {
         }
     }
 
-    if (c.fChar == (UChar32)-1) {
+    if (c.fChar == static_cast<UChar32>(-1)) {
         return;
     }
     if (fQuoteMode) {
@@ -958,7 +958,7 @@ void RBBIRuleScanner::nextChar(RBBIRuleChar &c) {
             int32_t commentStart = fScanIndex;
             for (;;) {
                 c.fChar = nextCharLL();
-                if (c.fChar == (UChar32)-1 ||  // EOF
+                if (c.fChar == static_cast<UChar32>(-1) || // EOF
                     c.fChar == chCR     ||
                     c.fChar == chLF     ||
                     c.fChar == chNEL    ||
@@ -968,7 +968,7 @@ void RBBIRuleScanner::nextChar(RBBIRuleChar &c) {
                 fRB->fStrippedRules.setCharAt(i, u' ');
             }
         }
-        if (c.fChar == (UChar32)-1) {
+        if (c.fChar == static_cast<UChar32>(-1)) {
             return;
         }
 
@@ -1065,14 +1065,14 @@ void RBBIRuleScanner::parse() {
                 // Table row specified "escaped P" and the char is either 'p' or 'P'.
                 break;
             }
-            if (tableEl->fCharClass == 252 && fC.fChar == (UChar32)-1)  {
+            if (tableEl->fCharClass == 252 && fC.fChar == static_cast<UChar32>(-1)) {
                 // Table row specified eof and we hit eof on the input.
                 break;
             }
 
             if (tableEl->fCharClass >= 128 && tableEl->fCharClass < 240 &&   // Table specs a char class &&
                 fC.fEscaped == false &&                                      //   char is not escaped &&
-                fC.fChar != (UChar32)-1) {                                   //   char is not EOF
+                fC.fChar != static_cast<UChar32>(-1)) {                      //   char is not EOF
                 U_ASSERT((tableEl->fCharClass-128) < UPRV_LENGTHOF(fRuleSets));
                 if (fRuleSets[tableEl->fCharClass-128].contains(fC.fChar)) {
                     // Table row specified a character class, or set of characters,
@@ -1090,7 +1090,7 @@ void RBBIRuleScanner::parse() {
         // We've found the row of the state table that matches the current input
         //   character from the rules string.
         // Perform any action specified  by this row in the state table.
-        if (doParseActions((int32_t)tableEl->fAction) == false) {
+        if (doParseActions(static_cast<int32_t>(tableEl->fAction)) == false) {
             // Break out of the state machine loop if the
             //   the action signalled some kind of error, or
             //   the action was to exit, occurs on normal end-of-rules-input.

thirdparty/icu4c/common/rbbisetb.cpp

@@ -120,7 +120,7 @@ void RBBISetBuilder::buildRanges() {
     //
     int  ni;
     for (ni=0; ; ni++) {        // Loop over each of the UnicodeSets encountered in the input rules
-        usetNode = (RBBINode *)this->fRB->fUSetNodes->elementAt(ni);
+        usetNode = static_cast<RBBINode*>(this->fRB->fUSetNodes->elementAt(ni));
         if (usetNode==nullptr) {
             break;
         }
@@ -251,7 +251,7 @@ void RBBISetBuilder::buildRanges() {
     UnicodeString eofString(u"eof");
     UnicodeString bofString(u"bof");
     for (ni=0; ; ni++) {        // Loop over each of the UnicodeSets encountered in the input rules
-        usetNode = (RBBINode *)this->fRB->fUSetNodes->elementAt(ni);
+        usetNode = static_cast<RBBINode*>(this->fRB->fUSetNodes->elementAt(ni));
         if (usetNode==nullptr) {
             break;
         }
@@ -369,7 +369,7 @@ void  RBBISetBuilder::addValToSets(UVector *sets, uint32_t val) {
     int32_t       ix;
 
     for (ix=0; ix<sets->size(); ix++) {
-        RBBINode *usetNode = (RBBINode *)sets->elementAt(ix);
+        RBBINode* usetNode = static_cast<RBBINode*>(sets->elementAt(ix));
         addValToSet(usetNode, val);
     }
 }
@@ -380,7 +380,7 @@ void  RBBISetBuilder::addValToSet(RBBINode *usetNode, uint32_t val) {
         *fStatus = U_MEMORY_ALLOCATION_ERROR;
         return;
     }
-    leafNode->fVal = (unsigned short)val;
+    leafNode->fVal = static_cast<unsigned short>(val);
     if (usetNode->fLeftChild == nullptr) {
         usetNode->fLeftChild = leafNode;
         leafNode->fParent    = usetNode;
@@ -441,7 +441,7 @@ UBool  RBBISetBuilder::sawBOF() const {
 //------------------------------------------------------------------------
 UChar32  RBBISetBuilder::getFirstChar(int32_t category) const {
     RangeDescriptor   *rlRange;
-    UChar32            retVal = (UChar32)-1;
+    UChar32 retVal = static_cast<UChar32>(-1);
     for (rlRange = fRangeList; rlRange!=nullptr; rlRange=rlRange->fNext) {
         if (rlRange->fNum == category) {
             retVal = rlRange->fStartChar;
@@ -674,7 +674,7 @@ void RangeDescriptor::split(UChar32 where, UErrorCode &status) {
 bool RangeDescriptor::isDictionaryRange() {
     static const char16_t *dictionary = u"dictionary";
     for (int32_t i=0; i<fIncludesSets->size(); i++) {
-        RBBINode *usetNode  = (RBBINode *)fIncludesSets->elementAt(i);
+        RBBINode* usetNode = static_cast<RBBINode*>(fIncludesSets->elementAt(i));
         RBBINode *setRef = usetNode->fParent;
         if (setRef != nullptr) {
             RBBINode *varRef = setRef->fParent;

thirdparty/icu4c/common/rbbistbl.cpp

@@ -41,7 +41,7 @@ U_CDECL_END
 U_NAMESPACE_BEGIN
 
 RBBISymbolTable::RBBISymbolTable(RBBIRuleScanner *rs, const UnicodeString &rules, UErrorCode &status)
-    :fRules(rules), fRuleScanner(rs), ffffString(char16_t(0xffff))
+    : fRules(rules), fRuleScanner(rs), ffffString(static_cast<char16_t>(0xffff))
 {
     fHashTable       = nullptr;
     fCachedSetLookup = nullptr;
@@ -76,9 +76,9 @@ const UnicodeString  *RBBISymbolTable::lookup(const UnicodeString& s) const
     RBBINode              *exprNode;
     RBBINode              *usetNode;
     const UnicodeString   *retString;
-    RBBISymbolTable       *This = (RBBISymbolTable *)this;   // cast off const
+    RBBISymbolTable       *This = const_cast<RBBISymbolTable*>(this); // cast off const
 
-    el = (RBBISymbolTableEntry *)uhash_get(fHashTable, &s);
+    el = static_cast<RBBISymbolTableEntry*>(uhash_get(fHashTable, &s));
     if (el == nullptr) {
         return nullptr;
     }
@@ -119,7 +119,7 @@ const UnicodeString  *RBBISymbolTable::lookup(const UnicodeString& s) const
 const UnicodeFunctor *RBBISymbolTable::lookupMatcher(UChar32 ch) const
 {
     UnicodeSet *retVal = nullptr;
-    RBBISymbolTable *This = (RBBISymbolTable *)this;   // cast off const
+    RBBISymbolTable *This = const_cast<RBBISymbolTable*>(this); // cast off const
     if (ch == 0xffff) {
         retVal = fCachedSetLookup;
         This->fCachedSetLookup = nullptr;
@@ -170,7 +170,7 @@ RBBINode       *RBBISymbolTable::lookupNode(const UnicodeString &key) const{
     RBBINode             *retNode = nullptr;
     RBBISymbolTableEntry *el;
 
-    el = (RBBISymbolTableEntry *)uhash_get(fHashTable, &key);
+    el = static_cast<RBBISymbolTableEntry*>(uhash_get(fHashTable, &key));
     if (el != nullptr) {
         retNode = el->val;
     }
@@ -190,7 +190,7 @@ void            RBBISymbolTable::addEntry  (const UnicodeString &key, RBBINode *
     if (U_FAILURE(err)) {
         return;
     }
-    e = (RBBISymbolTableEntry *)uhash_get(fHashTable, &key);
+    e = static_cast<RBBISymbolTableEntry*>(uhash_get(fHashTable, &key));
     if (e != nullptr) {
         err = U_BRK_VARIABLE_REDFINITION;
         return;

thirdparty/icu4c/common/rbbitblb.cpp

@@ -51,7 +51,7 @@ RBBITableBuilder::RBBITableBuilder(RBBIRuleBuilder *rb, RBBINode **rootNode, UEr
 RBBITableBuilder::~RBBITableBuilder() {
     int i;
     for (i=0; i<fDStates->size(); i++) {
-        delete (RBBIStateDescriptor *)fDStates->elementAt(i);
+        delete static_cast<RBBIStateDescriptor*>(fDStates->elementAt(i));
     }
     delete fDStates;
     delete fSafeTable;
@@ -361,8 +361,8 @@ void RBBITableBuilder::calcFollowPos(RBBINode *n) {
 
         UVector *LastPosOfLeftChild = n->fLeftChild->fLastPosSet;
 
-        for (ix=0; ix<(uint32_t)LastPosOfLeftChild->size(); ix++) {
-            i = (RBBINode *)LastPosOfLeftChild->elementAt(ix);
+        for (ix = 0; ix < static_cast<uint32_t>(LastPosOfLeftChild->size()); ix++) {
+            i = static_cast<RBBINode*>(LastPosOfLeftChild->elementAt(ix));
             setAdd(i->fFollowPos, n->fRightChild->fFirstPosSet);
         }
     }
@@ -373,8 +373,8 @@ void RBBITableBuilder::calcFollowPos(RBBINode *n) {
         RBBINode   *i;  // again, n and i are the names from Aho's description.
         uint32_t    ix;
 
-        for (ix=0; ix<(uint32_t)n->fLastPosSet->size(); ix++) {
-            i = (RBBINode *)n->fLastPosSet->elementAt(ix);
+        for (ix = 0; ix < static_cast<uint32_t>(n->fLastPosSet->size()); ix++) {
+            i = static_cast<RBBINode*>(n->fLastPosSet->elementAt(ix));
             setAdd(i->fFollowPos, n->fFirstPosSet);
         }
     }
@@ -445,7 +445,7 @@ void RBBITableBuilder::calcChainedFollowPos(RBBINode *tree, RBBINode *endMarkNod
     int32_t  startNodeIx;
 
     for (endNodeIx=0; endNodeIx<leafNodes.size(); endNodeIx++) {
-        RBBINode *endNode   = (RBBINode *)leafNodes.elementAt(endNodeIx);
+        RBBINode* endNode = static_cast<RBBINode*>(leafNodes.elementAt(endNodeIx));
 
         // Identify leaf nodes that correspond to overall rule match positions.
         // These include the endMarkNode in their followPos sets.
@@ -465,7 +465,7 @@ void RBBITableBuilder::calcChainedFollowPos(RBBINode *tree, RBBINode *endMarkNod
         //   with the same char class as our ending node.
         RBBINode *startNode;
         for (startNodeIx = 0; startNodeIx<matchStartNodes.size(); startNodeIx++) {
-            startNode = (RBBINode *)matchStartNodes.elementAt(startNodeIx);
+            startNode = static_cast<RBBINode*>(matchStartNodes.elementAt(startNodeIx));
             if (startNode->fType != RBBINode::leafChar) {
                 continue;
             }
@@ -525,7 +525,7 @@ void RBBITableBuilder::bofFixup() {
     RBBINode *startNode;
     int       startNodeIx;
     for (startNodeIx = 0; startNodeIx<matchStartNodes->size(); startNodeIx++) {
-        startNode = (RBBINode *)matchStartNodes->elementAt(startNodeIx);
+        startNode = static_cast<RBBINode*>(matchStartNodes->elementAt(startNodeIx));
         if (startNode->fType != RBBINode::leafChar) {
             continue;
         }
@@ -605,7 +605,7 @@ void RBBITableBuilder::buildStateTable() {
         int32_t              tx;
         for (tx=1; tx<fDStates->size(); tx++) {
             RBBIStateDescriptor *temp;
-            temp = (RBBIStateDescriptor *)fDStates->elementAt(tx);
+            temp = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(tx));
             if (temp->fMarked == false) {
                 T = temp;
                 break;
@@ -628,7 +628,7 @@ void RBBITableBuilder::buildStateTable() {
             RBBINode   *p;
             int32_t     px;
             for (px=0; px<T->fPositions->size(); px++) {
-                p = (RBBINode *)T->fPositions->elementAt(px);
+                p = static_cast<RBBINode*>(T->fPositions->elementAt(px));
                 if ((p->fType == RBBINode::leafChar) &&  (p->fVal == a)) {
                     if (U == nullptr) {
                         U = new UVector(*fStatus);
@@ -649,7 +649,7 @@ void RBBITableBuilder::buildStateTable() {
                 int  ix;
                 for (ix=0; ix<fDStates->size(); ix++) {
                     RBBIStateDescriptor *temp2;
-                    temp2 = (RBBIStateDescriptor *)fDStates->elementAt(ix);
+                    temp2 = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(ix));
                     if (setEquals(U, temp2->fPositions)) {
                         delete U;
                         U  = temp2->fPositions;
@@ -705,7 +705,7 @@ void RBBITableBuilder::mapLookAheadRules() {
     fLookAheadRuleMap->setSize(fRB->fScanner->numRules() + 1);
 
     for (int32_t n=0; n<fDStates->size(); n++) {
-        RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(n);
+        RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(n));
         int32_t laSlotForState = 0;
 
         // Establish the look-ahead slot for this state, if the state covers
@@ -789,9 +789,9 @@ void     RBBITableBuilder::flagAcceptingStates() {
     }
 
     for (i=0; i<endMarkerNodes.size(); i++) {
-        endMarker = (RBBINode *)endMarkerNodes.elementAt(i);
+        endMarker = static_cast<RBBINode*>(endMarkerNodes.elementAt(i));
         for (n=0; n<fDStates->size(); n++) {
-            RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(n);
+            RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(n));
             if (sd->fPositions->indexOf(endMarker) >= 0) {
                 // Any non-zero value for fAccepting means this is an accepting node.
                 // The value is what will be returned to the user as the break status.
@@ -837,11 +837,11 @@ void     RBBITableBuilder::flagLookAheadStates() {
         return;
     }
     for (i=0; i<lookAheadNodes.size(); i++) {
-        lookAheadNode = (RBBINode *)lookAheadNodes.elementAt(i);
+        lookAheadNode = static_cast<RBBINode*>(lookAheadNodes.elementAt(i));
         U_ASSERT(lookAheadNode->fType == RBBINode::NodeType::lookAhead);
 
         for (n=0; n<fDStates->size(); n++) {
-            RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(n);
+            RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(n));
             int32_t positionsIdx = sd->fPositions->indexOf(lookAheadNode);
             if (positionsIdx >= 0) {
                 U_ASSERT(lookAheadNode == sd->fPositions->elementAt(positionsIdx));
@@ -882,10 +882,10 @@ void     RBBITableBuilder::flagTaggedStates() {
         return;
     }
     for (i=0; i<tagNodes.size(); i++) {                   // For each tag node t (all of 'em)
-        tagNode = (RBBINode *)tagNodes.elementAt(i);
+        tagNode = static_cast<RBBINode*>(tagNodes.elementAt(i));
 
         for (n=0; n<fDStates->size(); n++) {              //    For each state  s (row in the state table)
-            RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(n);
+            RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(n));
             if (sd->fPositions->indexOf(tagNode) >= 0) {  //       if  s include the tag node t
                 sortedAdd(&sd->fTagVals, tagNode->fVal);
             }
@@ -923,12 +923,12 @@ void  RBBITableBuilder::mergeRuleStatusVals() {
     //   We will need this as a default, for rule sets with no explicit tagging.
     if (fRB->fRuleStatusVals->size() == 0) {
         fRB->fRuleStatusVals->addElement(1, *fStatus);  // Num of statuses in group
-        fRB->fRuleStatusVals->addElement((int32_t)0, *fStatus);  //   and our single status of zero
+        fRB->fRuleStatusVals->addElement(static_cast<int32_t>(0), *fStatus); // and our single status of zero
     }
 
     //    For each state
     for (n=0; n<fDStates->size(); n++) {
-        RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(n);
+        RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(n));
         UVector *thisStatesTagValues = sd->fTagVals;
         if (thisStatesTagValues == nullptr) {
             // No tag values are explicitly associated with this state.
@@ -1154,9 +1154,9 @@ bool RBBITableBuilder::findDuplCharClassFrom(IntPair *categories) {
             uint16_t table_base = 0;
             uint16_t table_dupl = 1;
             for (int32_t state=0; state<numStates; state++) {
-                RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(state);
-                table_base = (uint16_t)sd->fDtran->elementAti(categories->first);
-                table_dupl = (uint16_t)sd->fDtran->elementAti(categories->second);
+                RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(state));
+                table_base = static_cast<uint16_t>(sd->fDtran->elementAti(categories->first));
+                table_dupl = static_cast<uint16_t>(sd->fDtran->elementAti(categories->second));
                 if (table_base != table_dupl) {
                     break;
                 }
@@ -1176,7 +1176,7 @@ bool RBBITableBuilder::findDuplCharClassFrom(IntPair *categories) {
 void RBBITableBuilder::removeColumn(int32_t column) {
     int32_t numStates = fDStates->size();
     for (int32_t state=0; state<numStates; state++) {
-        RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(state);
+        RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(state));
         U_ASSERT(column < sd->fDtran->size());
         sd->fDtran->removeElementAt(column);
     }
@@ -1190,9 +1190,9 @@ bool RBBITableBuilder::findDuplicateState(IntPair *states) {
     int32_t numCols = fRB->fSetBuilder->getNumCharCategories();
 
     for (; states->first<numStates-1; states->first++) {
-        RBBIStateDescriptor *firstSD = (RBBIStateDescriptor *)fDStates->elementAt(states->first);
+        RBBIStateDescriptor* firstSD = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(states->first));
         for (states->second=states->first+1; states->second<numStates; states->second++) {
-            RBBIStateDescriptor *duplSD = (RBBIStateDescriptor *)fDStates->elementAt(states->second);
+            RBBIStateDescriptor* duplSD = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(states->second));
             if (firstSD->fAccepting != duplSD->fAccepting ||
                 firstSD->fLookAhead != duplSD->fLookAhead ||
                 firstSD->fTagsIdx   != duplSD->fTagsIdx) {
@@ -1252,14 +1252,14 @@ void RBBITableBuilder::removeState(IntPair duplStates) {
     U_ASSERT(keepState < duplState);
     U_ASSERT(duplState < fDStates->size());
 
-    RBBIStateDescriptor *duplSD = (RBBIStateDescriptor *)fDStates->elementAt(duplState);
+    RBBIStateDescriptor* duplSD = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(duplState));
     fDStates->removeElementAt(duplState);
     delete duplSD;
 
     int32_t numStates = fDStates->size();
     int32_t numCols = fRB->fSetBuilder->getNumCharCategories();
     for (int32_t state=0; state<numStates; ++state) {
-        RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(state);
+        RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(state));
         for (int32_t col=0; col<numCols; col++) {
             int32_t existingVal = sd->fDtran->elementAti(col);
             int32_t newVal = existingVal;
@@ -1283,7 +1283,7 @@ void RBBITableBuilder::removeSafeState(IntPair duplStates) {
                                               // and will auto-delete the removed element.
     int32_t numStates = fSafeTable->size();
     for (int32_t state=0; state<numStates; ++state) {
-        UnicodeString *sd = (UnicodeString *)fSafeTable->elementAt(state);
+        UnicodeString* sd = static_cast<UnicodeString*>(fSafeTable->elementAt(state));
         int32_t numCols = sd->length();
         for (int32_t col=0; col<numCols; col++) {
             int32_t existingVal = sd->charAt(col);
@@ -1357,7 +1357,7 @@ bool RBBITableBuilder::use8BitsForTable() const {
 //
 //-----------------------------------------------------------------------------
 void RBBITableBuilder::exportTable(void *where) {
-    RBBIStateTable    *table = (RBBIStateTable *)where;
+    RBBIStateTable* table = static_cast<RBBIStateTable*>(where);
     uint32_t           state;
     int                col;
 
@@ -1390,13 +1390,13 @@ void RBBITableBuilder::exportTable(void *where) {
     }
 
     for (state=0; state<table->fNumStates; state++) {
-        RBBIStateDescriptor *sd = (RBBIStateDescriptor *)fDStates->elementAt(state);
-        RBBIStateTableRow   *row = (RBBIStateTableRow *)(table->fTableData + state*table->fRowLen);
+        RBBIStateDescriptor* sd = static_cast<RBBIStateDescriptor*>(fDStates->elementAt(state));
+        RBBIStateTableRow* row = reinterpret_cast<RBBIStateTableRow*>(table->fTableData + state * table->fRowLen);
         if (use8BitsForTable()) {
             U_ASSERT (sd->fAccepting <= 255);
             U_ASSERT (sd->fLookAhead <= 255);
             U_ASSERT (0 <= sd->fTagsIdx && sd->fTagsIdx <= 255);
-            RBBIStateTableRow8 *r8 = (RBBIStateTableRow8*)row;
+            RBBIStateTableRow8* r8 = reinterpret_cast<RBBIStateTableRow8*>(row);
             r8->fAccepting = sd->fAccepting;
             r8->fLookAhead = sd->fLookAhead;
             r8->fTagsIdx   = sd->fTagsIdx;
@@ -1472,8 +1472,8 @@ void RBBITableBuilder::buildSafeReverseTable(UErrorCode &status) {
                 }
             }
             if (wantedEndState == endState) {
-                safePairs.append((char16_t)c1);
-                safePairs.append((char16_t)c2);
+                safePairs.append(static_cast<char16_t>(c1));
+                safePairs.append(static_cast<char16_t>(c2));
                 // printf("(%d, %d) ", c1, c2);
             }
         }
@@ -1579,7 +1579,7 @@ bool RBBITableBuilder::use8BitsForSafeTable() const {
 //
 //-----------------------------------------------------------------------------
 void RBBITableBuilder::exportSafeTable(void *where) {
-    RBBIStateTable    *table = (RBBIStateTable *)where;
+    RBBIStateTable* table = static_cast<RBBIStateTable*>(where);
     uint32_t           state;
     int                col;
 
@@ -1604,10 +1604,10 @@ void RBBITableBuilder::exportSafeTable(void *where) {
     }
 
     for (state=0; state<table->fNumStates; state++) {
-        UnicodeString *rowString = (UnicodeString *)fSafeTable->elementAt(state);
-        RBBIStateTableRow   *row = (RBBIStateTableRow *)(table->fTableData + state*table->fRowLen);
+        UnicodeString* rowString = static_cast<UnicodeString*>(fSafeTable->elementAt(state));
+        RBBIStateTableRow* row = reinterpret_cast<RBBIStateTableRow*>(table->fTableData + state * table->fRowLen);
         if (use8BitsForSafeTable()) {
-            RBBIStateTableRow8 *r8 = (RBBIStateTableRow8*)row;
+            RBBIStateTableRow8* r8 = reinterpret_cast<RBBIStateTableRow8*>(row);
             r8->fAccepting = 0;
             r8->fLookAhead = 0;
             r8->fTagsIdx    = 0;

thirdparty/icu4c/common/resbund_cnv.cpp

@@ -49,7 +49,7 @@ ResourceBundle::constructForLocale(const UnicodeString& path,
     }
     else {
         UnicodeString nullTerminatedPath(path);
-        nullTerminatedPath.append((char16_t)0);
+        nullTerminatedPath.append(static_cast<char16_t>(0));
         fResource = ures_openU(nullTerminatedPath.getBuffer(), locale.getName(), &error);
     }
 }

thirdparty/icu4c/common/ruleiter.cpp

@@ -139,7 +139,7 @@ UChar32 RuleCharacterIterator::_current() const {
         return buf->char32At(bufPos);
     } else {
         int i = pos.getIndex();
-        return (i < text.length()) ? text.char32At(i) : (UChar32)DONE;
+        return (i < text.length()) ? text.char32At(i) : static_cast<UChar32>(DONE);
     }
 }
 

thirdparty/icu4c/common/serv.cpp

@@ -424,7 +424,7 @@ ICUService::getKey(ICUServiceKey& key, UnicodeString* actualReturn, const ICUSer
         return handleDefault(key, actualReturn, status);
     }
 
-    ICUService* ncthis = (ICUService*)this; // cast away semantic const
+    ICUService* ncthis = const_cast<ICUService*>(this); // cast away semantic const
 
     CacheEntry* result = nullptr;
     {
@@ -462,7 +462,7 @@ ICUService::getKey(ICUServiceKey& key, UnicodeString* actualReturn, const ICUSer
 
         if (factory != nullptr) {
             for (int32_t i = 0; i < limit; ++i) {
-                if (factory == (const ICUServiceFactory*)factories->elementAt(i)) {
+                if (factory == static_cast<const ICUServiceFactory*>(factories->elementAt(i))) {
                     startIndex = i + 1;
                     break;
                 }
@@ -478,7 +478,7 @@ ICUService::getKey(ICUServiceKey& key, UnicodeString* actualReturn, const ICUSer
         do {
             currentDescriptor.remove();
             key.currentDescriptor(currentDescriptor);
-            result = (CacheEntry*)serviceCache->get(currentDescriptor);
+            result = static_cast<CacheEntry*>(serviceCache->get(currentDescriptor));
             if (result != nullptr) {
                 break;
             }
@@ -490,7 +490,7 @@ ICUService::getKey(ICUServiceKey& key, UnicodeString* actualReturn, const ICUSer
 
             int32_t index = startIndex;
             while (index < limit) {
-                ICUServiceFactory* f = (ICUServiceFactory*)factories->elementAt(index++);
+                ICUServiceFactory* f = static_cast<ICUServiceFactory*>(factories->elementAt(index++));
                 LocalPointer<UObject> service(f->create(key, this, status));
                 if (U_FAILURE(status)) {
                     return nullptr;
@@ -543,7 +543,7 @@ outerEnd:
 
                 if (cacheDescriptorList.isValid()) {
                     for (int32_t i = cacheDescriptorList->size(); --i >= 0;) {
-                        UnicodeString* desc = (UnicodeString*)cacheDescriptorList->elementAt(i);
+                        UnicodeString* desc = static_cast<UnicodeString*>(cacheDescriptorList->elementAt(i));
 
                         serviceCache->put(*desc, result, status);
                         if (U_FAILURE(status)) {
@@ -558,7 +558,7 @@ outerEnd:
 
             if (actualReturn != nullptr) {
                 // strip null prefix
-                if (result->actualDescriptor.indexOf((char16_t)0x2f) == 0) { // U+002f=slash (/)
+                if (result->actualDescriptor.indexOf(static_cast<char16_t>(0x2f)) == 0) { // U+002f=slash (/)
                     actualReturn->remove();
                     actualReturn->append(result->actualDescriptor, 
                         1, 
@@ -618,7 +618,7 @@ ICUService::getVisibleIDs(UVector& result, const UnicodeString* matchID, UErrorC
                     break;
                 }
 
-                const UnicodeString* id = (const UnicodeString*)e->key.pointer;
+                const UnicodeString* id = static_cast<const UnicodeString*>(e->key.pointer);
                 if (fallbackKey != nullptr) {
                     if (!fallbackKey->isFallbackOf(*id)) {
                         continue;
@@ -644,14 +644,14 @@ ICUService::getVisibleIDMap(UErrorCode& status) const {
 
     // must only be called when lock is already held
 
-    ICUService* ncthis = (ICUService*)this; // cast away semantic const
+    ICUService* ncthis = const_cast<ICUService*>(this); // cast away semantic const
     if (idCache == nullptr) {
         ncthis->idCache = new Hashtable(status);
         if (idCache == nullptr) {
             status = U_MEMORY_ALLOCATION_ERROR;
         } else if (factories != nullptr) {
             for (int32_t pos = factories->size(); --pos >= 0;) {
-                ICUServiceFactory* f = (ICUServiceFactory*)factories->elementAt(pos);
+                ICUServiceFactory* f = static_cast<ICUServiceFactory*>(factories->elementAt(pos));
                 f->updateVisibleIDs(*idCache, status);
             }
             if (U_FAILURE(status)) {
@@ -679,7 +679,7 @@ ICUService::getDisplayName(const UnicodeString& id, UnicodeString& result, const
         Mutex mutex(&lock);
         const Hashtable* map = getVisibleIDMap(status);
         if (map != nullptr) {
-            ICUServiceFactory* f = (ICUServiceFactory*)map->get(id);
+            ICUServiceFactory* f = static_cast<ICUServiceFactory*>(map->get(id));
             if (f != nullptr) {
                 f->getDisplayName(id, locale, result);
                 return result;
@@ -691,7 +691,7 @@ ICUService::getDisplayName(const UnicodeString& id, UnicodeString& result, const
             while (fallbackKey != nullptr && fallbackKey->fallback()) {
                 UnicodeString us;
                 fallbackKey->currentID(us);
-                f = (ICUServiceFactory*)map->get(us);
+                f = static_cast<ICUServiceFactory*>(map->get(us));
                 if (f != nullptr) {
                     f->getDisplayName(id, locale, result);
                     delete fallbackKey;
@@ -727,7 +727,7 @@ ICUService::getDisplayNames(UVector& result,
     result.removeAllElements();
     result.setDeleter(userv_deleteStringPair);
     if (U_SUCCESS(status)) {
-        ICUService* ncthis = (ICUService*)this; // cast away semantic const
+        ICUService* ncthis = const_cast<ICUService*>(this); // cast away semantic const
         Mutex mutex(&lock);
 
         if (dnCache != nullptr && dnCache->locale != locale) {
@@ -749,8 +749,8 @@ ICUService::getDisplayNames(UVector& result,
             int32_t pos = UHASH_FIRST;
             const UHashElement* entry = nullptr;
             while ((entry = m->nextElement(pos)) != nullptr) {
-                const UnicodeString* id = (const UnicodeString*)entry->key.pointer;
-                ICUServiceFactory* f = (ICUServiceFactory*)entry->value.pointer;
+                const UnicodeString* id = static_cast<const UnicodeString*>(entry->key.pointer);
+                ICUServiceFactory* f = static_cast<ICUServiceFactory*>(entry->value.pointer);
                 UnicodeString dname;
                 f->getDisplayName(*id, locale, dname);
                 if (dname.isBogus()) {
@@ -776,11 +776,11 @@ ICUService::getDisplayNames(UVector& result,
     int32_t pos = UHASH_FIRST; 
     const UHashElement *entry = nullptr;
     while ((entry = dnCache->cache.nextElement(pos)) != nullptr) {
-        const UnicodeString* id = (const UnicodeString*)entry->value.pointer;
+        const UnicodeString* id = static_cast<const UnicodeString*>(entry->value.pointer);
         if (matchKey != nullptr && !matchKey->isFallbackOf(*id)) {
             continue;
         }
-        const UnicodeString* dn = (const UnicodeString*)entry->key.pointer;
+        const UnicodeString* dn = static_cast<const UnicodeString*>(entry->key.pointer);
         StringPair* sp = StringPair::create(*id, *dn, status);
         result.adoptElement(sp, status);
         if (U_FAILURE(status)) {

thirdparty/icu4c/common/servlkf.cpp

@@ -76,7 +76,7 @@ LocaleKeyFactory::updateVisibleIDs(Hashtable& result, UErrorCode& status) const
         const UHashElement* elem = nullptr;
         int32_t pos = UHASH_FIRST;
         while ((elem = supported->nextElement(pos)) != nullptr) {
-            const UnicodeString& id = *((const UnicodeString*)elem->key.pointer);
+            const UnicodeString& id = *static_cast<const UnicodeString*>(elem->key.pointer);
             if (!visible) {
                 result.remove(id);
             } else {

thirdparty/icu4c/common/servls.cpp

@@ -179,7 +179,7 @@ private:
 
             length = other._ids.size();
             for(i = 0; i < length; ++i) {
-                LocalPointer<UnicodeString> clonedId(((UnicodeString *)other._ids.elementAt(i))->clone(), status);
+                LocalPointer<UnicodeString> clonedId(static_cast<UnicodeString*>(other._ids.elementAt(i))->clone(), status);
                 _ids.adoptElement(clonedId.orphan(), status);
             }
 
@@ -228,7 +228,7 @@ public:
 
     virtual const UnicodeString* snext(UErrorCode& status) override {
         if (upToDate(status) && (_pos < _ids.size())) {
-            return (const UnicodeString*)_ids[_pos++];
+            return static_cast<const UnicodeString*>(_ids[_pos++]);
         }
         return nullptr;
     }
@@ -263,7 +263,7 @@ const UnicodeString&
 ICULocaleService::validateFallbackLocale() const
 {
     const Locale&     loc    = Locale::getDefault();
-    ICULocaleService* ncThis = (ICULocaleService*)this;
+    ICULocaleService* ncThis = const_cast<ICULocaleService*>(this);
     static UMutex llock;
     {
         Mutex mutex(&llock);

thirdparty/icu4c/common/servnotf.cpp

@@ -56,7 +56,7 @@ ICUNotifier::addListener(const EventListener* l, UErrorCode& status)
                 listeners = lpListeners.orphan();
             } else {
                 for (int i = 0, e = listeners->size(); i < e; ++i) {
-                    const EventListener* el = (const EventListener*)(listeners->elementAt(i));
+                    const EventListener* el = static_cast<const EventListener*>(listeners->elementAt(i));
                     if (l == el) {
                         return;
                     }
@@ -88,7 +88,7 @@ ICUNotifier::removeListener(const EventListener *l, UErrorCode& status)
             if (listeners != nullptr) {
                 // identity equality check
                 for (int i = 0, e = listeners->size(); i < e; ++i) {
-                    const EventListener* el = (const EventListener*)listeners->elementAt(i);
+                    const EventListener* el = static_cast<const EventListener*>(listeners->elementAt(i));
                     if (l == el) {
                         listeners->removeElementAt(i);
                         if (listeners->size() == 0) {
@@ -109,7 +109,7 @@ ICUNotifier::notifyChanged()
     Mutex lmx(&notifyLock);
     if (listeners != nullptr) {
         for (int i = 0, e = listeners->size(); i < e; ++i) {
-            EventListener* el = (EventListener*)listeners->elementAt(i);
+            EventListener* el = static_cast<EventListener*>(listeners->elementAt(i));
             notifyListener(*el);
         }
     }

thirdparty/icu4c/common/servrbf.cpp

@@ -61,8 +61,8 @@ ICUResourceBundleFactory::handleCreate(const Locale& loc, int32_t /* kind */, co
                 // who made this change? -- dlf
         char pkg[20];
         int32_t length;
-        length=_bundleName.extract(0, INT32_MAX, pkg, (int32_t)sizeof(pkg), US_INV);
-        if(length>=(int32_t)sizeof(pkg)) {
+        length = _bundleName.extract(0, INT32_MAX, pkg, static_cast<int32_t>(sizeof(pkg)), US_INV);
+        if (length >= static_cast<int32_t>(sizeof(pkg))) {
             return nullptr;
         }
         return new ResourceBundle(pkg, loc, status);

thirdparty/icu4c/common/simpleformatter.cpp

@@ -73,7 +73,7 @@ UBool SimpleFormatter::applyPatternMinMaxArguments(
     const char16_t *patternBuffer = pattern.getBuffer();
     int32_t patternLength = pattern.length();
     // Reserve the first char for the number of arguments.
-    compiledPattern.setTo((char16_t)0);
+    compiledPattern.setTo(static_cast<char16_t>(0));
     int32_t textLength = 0;
     int32_t maxArg = -1;
     UBool inQuote = false;
@@ -98,7 +98,7 @@ UBool SimpleFormatter::applyPatternMinMaxArguments(
         } else if (!inQuote && c == OPEN_BRACE) {
             if (textLength > 0) {
                 compiledPattern.setCharAt(compiledPattern.length() - textLength - 1,
-                                          (char16_t)(ARG_NUM_LIMIT + textLength));
+                                          static_cast<char16_t>(ARG_NUM_LIMIT + textLength));
                 textLength = 0;
             }
             int32_t argNumber;
@@ -129,7 +129,7 @@ UBool SimpleFormatter::applyPatternMinMaxArguments(
             if (argNumber > maxArg) {
                 maxArg = argNumber;
             }
-            compiledPattern.append((char16_t)argNumber);
+            compiledPattern.append(static_cast<char16_t>(argNumber));
             continue;
         }  // else: c is part of literal text
         // Append c and track the literal-text segment length.
@@ -144,14 +144,14 @@ UBool SimpleFormatter::applyPatternMinMaxArguments(
     }
     if (textLength > 0) {
         compiledPattern.setCharAt(compiledPattern.length() - textLength - 1,
-                                  (char16_t)(ARG_NUM_LIMIT + textLength));
+                                  static_cast<char16_t>(ARG_NUM_LIMIT + textLength));
     }
     int32_t argCount = maxArg + 1;
     if (argCount < min || max < argCount) {
         errorCode = U_ILLEGAL_ARGUMENT_ERROR;
         return false;
     }
-    compiledPattern.setCharAt(0, (char16_t)argCount);
+    compiledPattern.setCharAt(0, static_cast<char16_t>(argCount));
     return true;
 }
 

thirdparty/icu4c/common/stringtriebuilder.cpp

@@ -328,7 +328,7 @@ StringTrieBuilder::registerNode(Node *newNode, UErrorCode &errorCode) {
     const UHashElement *old=uhash_find(nodes, newNode);
     if(old!=nullptr) {
         delete newNode;
-        return (Node *)old->key.pointer;
+        return static_cast<Node*>(old->key.pointer);
     }
     // If uhash_puti() returns a non-zero value from an equivalent, previously
     // registered node, then uhash_find() failed to find that and we will leak newNode.
@@ -352,7 +352,7 @@ StringTrieBuilder::registerFinalValue(int32_t value, UErrorCode &errorCode) {
     FinalValueNode key(value);
     const UHashElement *old=uhash_find(nodes, &key);
     if(old!=nullptr) {
-        return (Node *)old->key.pointer;
+        return static_cast<Node*>(old->key.pointer);
     }
     Node *newNode=new FinalValueNode(value);
     if(newNode==nullptr) {
@@ -375,12 +375,12 @@ StringTrieBuilder::registerFinalValue(int32_t value, UErrorCode &errorCode) {
 
 int32_t
 StringTrieBuilder::hashNode(const void *node) {
-    return ((const Node *)node)->hashCode();
+    return static_cast<const Node*>(node)->hashCode();
 }
 
 UBool
 StringTrieBuilder::equalNodes(const void *left, const void *right) {
-    return *(const Node *)left==*(const Node *)right;
+    return *static_cast<const Node*>(left) == *static_cast<const Node*>(right);
 }
 
 bool

thirdparty/icu4c/common/ubidi.cpp

@@ -304,7 +304,7 @@ ubidi_setReorderingMode(UBiDi *pBiDi, UBiDiReorderingMode reorderingMode) UPRV_N
     if ((pBiDi!=nullptr) && (reorderingMode >= UBIDI_REORDER_DEFAULT)
                         && (reorderingMode < UBIDI_REORDER_COUNT)) {
         pBiDi->reorderingMode = reorderingMode;
-        pBiDi->isInverse = (UBool)(reorderingMode == UBIDI_REORDER_INVERSE_NUMBERS_AS_L);
+        pBiDi->isInverse = reorderingMode == UBIDI_REORDER_INVERSE_NUMBERS_AS_L;
     }
 }
 
@@ -381,7 +381,7 @@ firstL_R_AL(UBiDi *pBiDi) {
     for(i=0; i<length; ) {
         /* i is incremented by U16_NEXT */
         U16_NEXT(text, i, length, uchar);
-        dirProp=(DirProp)ubidi_getCustomizedClass(pBiDi, uchar);
+        dirProp = static_cast<DirProp>(ubidi_getCustomizedClass(pBiDi, uchar));
         if(result==ON) {
             if(dirProp==L || dirProp==R || dirProp==AL) {
                 result=dirProp;
@@ -436,13 +436,13 @@ getDirProps(UBiDi *pBiDi) {
     UBool isDefaultLevel=IS_DEFAULT_LEVEL(pBiDi->paraLevel);
     /* for inverse BiDi, the default para level is set to RTL if there is a
        strong R or AL character at either end of the text                            */
-    UBool isDefaultLevelInverse=isDefaultLevel && (UBool)
-            (pBiDi->reorderingMode==UBIDI_REORDER_INVERSE_LIKE_DIRECT ||
-             pBiDi->reorderingMode==UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL);
+    UBool isDefaultLevelInverse = isDefaultLevel && static_cast<UBool>(
+            pBiDi->reorderingMode == UBIDI_REORDER_INVERSE_LIKE_DIRECT ||
+            pBiDi->reorderingMode == UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL);
     int32_t lastArabicPos=-1;
     int32_t controlCount=0;
-    UBool removeBiDiControls = (UBool)(pBiDi->reorderingOptions &
-                                       UBIDI_OPTION_REMOVE_CONTROLS);
+    UBool removeBiDiControls =
+        static_cast<UBool>(pBiDi->reorderingOptions & UBIDI_OPTION_REMOVE_CONTROLS);
 
     enum State {
          NOT_SEEKING_STRONG,            /* 0: not contextual paraLevel, not after FSI */
@@ -676,7 +676,7 @@ bracketInit(UBiDi *pBiDi, BracketData *bd) {
     bd->isoRuns[0].level=GET_PARALEVEL(pBiDi, 0);
     UBiDiLevel t = GET_PARALEVEL(pBiDi, 0) & 1;
     bd->isoRuns[0].lastStrong = bd->isoRuns[0].lastBase = t;
-    bd->isoRuns[0].contextDir = (UBiDiDirection)t;
+    bd->isoRuns[0].contextDir = static_cast<UBiDiDirection>(t);
     bd->isoRuns[0].contextPos=0;
     if(pBiDi->openingsMemory) {
         bd->openings=pBiDi->openingsMemory;
@@ -696,7 +696,7 @@ bracketProcessB(BracketData *bd, UBiDiLevel level) {
     bd->isoRuns[0].limit=0;
     bd->isoRuns[0].level=level;
     bd->isoRuns[0].lastStrong=bd->isoRuns[0].lastBase=level&1;
-    bd->isoRuns[0].contextDir=(UBiDiDirection)(level&1);
+    bd->isoRuns[0].contextDir = static_cast<UBiDiDirection>(level & 1);
     bd->isoRuns[0].contextPos=0;
 }
 
@@ -713,8 +713,8 @@ bracketProcessBoundary(BracketData *bd, int32_t lastCcPos,
     pLastIsoRun->limit=pLastIsoRun->start;
     pLastIsoRun->level=embeddingLevel;
     pLastIsoRun->lastStrong=pLastIsoRun->lastBase=contextLevel&1;
-    pLastIsoRun->contextDir=(UBiDiDirection)(contextLevel&1);
-    pLastIsoRun->contextPos=(UBiDiDirection)lastCcPos;
+    pLastIsoRun->contextDir = static_cast<UBiDiDirection>(contextLevel & 1);
+    pLastIsoRun->contextPos = static_cast<UBiDiDirection>(lastCcPos);
 }
 
 /* LRI or RLI */
@@ -729,7 +729,7 @@ bracketProcessLRI_RLI(BracketData *bd, UBiDiLevel level) {
     pLastIsoRun->start=pLastIsoRun->limit=lastLimit;
     pLastIsoRun->level=level;
     pLastIsoRun->lastStrong=pLastIsoRun->lastBase=level&1;
-    pLastIsoRun->contextDir=(UBiDiDirection)(level&1);
+    pLastIsoRun->contextDir = static_cast<UBiDiDirection>(level & 1);
     pLastIsoRun->contextPos=0;
 }
 
@@ -803,7 +803,7 @@ bracketProcessClosing(BracketData *bd, int32_t openIdx, int32_t position) {
     UBool stable;
     DirProp newProp;
     pOpening=&bd->openings[openIdx];
-    direction=(UBiDiDirection)(pLastIsoRun->level&1);
+    direction = static_cast<UBiDiDirection>(pLastIsoRun->level & 1);
     stable=true;            /* assume stable until proved otherwise */
 
     /* The stable flag is set when brackets are paired and their
@@ -896,7 +896,7 @@ bracketProcessChar(BracketData *bd, int32_t position) {
                 break;
             }
             pLastIsoRun->lastBase=ON;
-            pLastIsoRun->contextDir=(UBiDiDirection)newProp;
+            pLastIsoRun->contextDir = static_cast<UBiDiDirection>(newProp);
             pLastIsoRun->contextPos=position;
             level=bd->pBiDi->levels[position];
             if(level&UBIDI_LEVEL_OVERRIDE) {    /* X4, X5 */
@@ -944,14 +944,14 @@ bracketProcessChar(BracketData *bd, int32_t position) {
             dirProps[position]=newProp;
         pLastIsoRun->lastBase=newProp;
         pLastIsoRun->lastStrong=newProp;
-        pLastIsoRun->contextDir=(UBiDiDirection)newProp;
+        pLastIsoRun->contextDir = static_cast<UBiDiDirection>(newProp);
         pLastIsoRun->contextPos=position;
     }
     else if(dirProp<=R || dirProp==AL) {
         newProp= static_cast<DirProp>(DIR_FROM_STRONG(dirProp));
         pLastIsoRun->lastBase=dirProp;
         pLastIsoRun->lastStrong=dirProp;
-        pLastIsoRun->contextDir=(UBiDiDirection)newProp;
+        pLastIsoRun->contextDir = static_cast<UBiDiDirection>(newProp);
         pLastIsoRun->contextPos=position;
     }
     else if(dirProp==EN) {
@@ -960,7 +960,7 @@ bracketProcessChar(BracketData *bd, int32_t position) {
             newProp=L;                  /* W7 */
             if(!bd->isNumbersSpecial)
                 dirProps[position]=ENL;
-            pLastIsoRun->contextDir=(UBiDiDirection)L;
+            pLastIsoRun->contextDir = static_cast<UBiDiDirection>(L);
             pLastIsoRun->contextPos=position;
         }
         else {
@@ -969,14 +969,14 @@ bracketProcessChar(BracketData *bd, int32_t position) {
                 dirProps[position]=AN;  /* W2 */
             else
                 dirProps[position]=ENR;
-            pLastIsoRun->contextDir=(UBiDiDirection)R;
+            pLastIsoRun->contextDir = static_cast<UBiDiDirection>(R);
             pLastIsoRun->contextPos=position;
         }
     }
     else if(dirProp==AN) {
         newProp=R;                      /* N0 */
         pLastIsoRun->lastBase=AN;
-        pLastIsoRun->contextDir=(UBiDiDirection)R;
+        pLastIsoRun->contextDir = static_cast<UBiDiDirection>(R);
         pLastIsoRun->contextPos=position;
     }
     else if(dirProp==NSM) {
@@ -1177,10 +1177,10 @@ resolveExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 levels[i]=previousLevel;
                 if (dirProp==LRE || dirProp==LRO)
                     /* least greater even level */
-                    newLevel=(UBiDiLevel)((embeddingLevel+2)&~(UBIDI_LEVEL_OVERRIDE|1));
+                    newLevel = static_cast<UBiDiLevel>((embeddingLevel + 2) & ~(UBIDI_LEVEL_OVERRIDE | 1));
                 else
                     /* least greater odd level */
-                    newLevel=(UBiDiLevel)((NO_OVERRIDE(embeddingLevel)+1)|1);
+                    newLevel = static_cast<UBiDiLevel>((NO_OVERRIDE(embeddingLevel) + 1) | 1);
                 if(newLevel<=UBIDI_MAX_EXPLICIT_LEVEL && overflowIsolateCount==0 &&
                                                          overflowEmbeddingCount==0) {
                     lastCcPos=i;
@@ -1213,7 +1213,7 @@ resolveExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 if(stackLast>0 && stack[stackLast]<ISOLATE) {   /* not an isolate entry */
                     lastCcPos=i;
                     stackLast--;
-                    embeddingLevel=(UBiDiLevel)stack[stackLast];
+                    embeddingLevel = static_cast<UBiDiLevel>(stack[stackLast]);
                 }
                 break;
             case LRI:
@@ -1229,10 +1229,10 @@ resolveExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 /* (X5a, X5b) */
                 if(dirProp==LRI)
                     /* least greater even level */
-                    newLevel=(UBiDiLevel)((embeddingLevel+2)&~(UBIDI_LEVEL_OVERRIDE|1));
+                    newLevel = static_cast<UBiDiLevel>((embeddingLevel + 2) & ~(UBIDI_LEVEL_OVERRIDE | 1));
                 else
                     /* least greater odd level */
-                    newLevel=(UBiDiLevel)((NO_OVERRIDE(embeddingLevel)+1)|1);
+                    newLevel = static_cast<UBiDiLevel>((NO_OVERRIDE(embeddingLevel) + 1) | 1);
                 if(newLevel<=UBIDI_MAX_EXPLICIT_LEVEL && overflowIsolateCount==0 &&
                                                          overflowEmbeddingCount==0) {
                     flags|=DIRPROP_FLAG(dirProp);
@@ -1276,7 +1276,7 @@ resolveExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 } else
                     /* make it WS so that it is handled by adjustWSLevels() */
                     dirProps[i]=WS;
-                embeddingLevel=(UBiDiLevel)stack[stackLast]&~ISOLATE;
+                embeddingLevel = static_cast<UBiDiLevel>(stack[stackLast]) & ~ISOLATE;
                 flags|=(DIRPROP_FLAG(ON)|DIRPROP_FLAG_LR(embeddingLevel));
                 previousLevel=embeddingLevel;
                 levels[i]=NO_OVERRIDE(embeddingLevel);
@@ -1315,7 +1315,7 @@ resolveExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 previousLevel=embeddingLevel;
                 levels[i]=embeddingLevel;
                 if(!bracketProcessChar(&bracketData, i))
-                    return (UBiDiDirection)-1;
+                    return static_cast<UBiDiDirection>(-1);
                 /* the dirProp may have been changed in bracketProcessChar() */
                 flags|=DIRPROP_FLAG(dirProps[i]);
                 break;
@@ -1386,7 +1386,7 @@ checkExplicitLevels(UBiDi *pBiDi, UErrorCode *pErrorCode) {
                 } else {
                     // Treat explicit level 0 as a wildcard for the paragraph level.
                     // Avoid making the caller guess what the paragraph level would be.
-                    level = (UBiDiLevel)currentParaLevel;
+                    level = static_cast<UBiDiLevel>(currentParaLevel);
                     levels[i] = level | overrideFlag;
                 }
             } else {
@@ -1868,7 +1868,7 @@ processPropertySeq(UBiDi *pBiDi, LevState *pLevState, uint8_t _prop,
     int32_t start0, k;
 
     start0=start;                           /* save original start position */
-    oldStateSeq=(uint8_t)pLevState->state;
+    oldStateSeq = static_cast<uint8_t>(pLevState->state);
     cell=(*pImpTab)[oldStateSeq][_prop];
     pLevState->state=GET_STATE(cell);       /* isolate the new state */
     actionSeq=(*pImpAct)[GET_ACTION(cell)]; /* isolate the action */
@@ -2076,7 +2076,7 @@ lastL_R_AL(UBiDi *pBiDi) {
     for(i=length; i>0; ) {
         /* i is decremented by U16_PREV */
         U16_PREV(text, 0, i, uchar);
-        dirProp=(DirProp)ubidi_getCustomizedClass(pBiDi, uchar);
+        dirProp = static_cast<DirProp>(ubidi_getCustomizedClass(pBiDi, uchar));
         if(dirProp==L) {
             return DirProp_L;
         }
@@ -2104,7 +2104,7 @@ firstL_R_AL_EN_AN(UBiDi *pBiDi) {
     for(i=0; i<length; ) {
         /* i is incremented by U16_NEXT */
         U16_NEXT(text, i, length, uchar);
-        dirProp=(DirProp)ubidi_getCustomizedClass(pBiDi, uchar);
+        dirProp = static_cast<DirProp>(ubidi_getCustomizedClass(pBiDi, uchar));
         if(dirProp==L) {
             return DirProp_L;
         }
@@ -2142,18 +2142,18 @@ resolveImplicitLevels(UBiDi *pBiDi,
      * actions) and different levels state tables (maybe very similar to the
      * LTR corresponding ones.
      */
-    inverseRTL=(UBool)
-        ((start<pBiDi->lastArabicPos) && (GET_PARALEVEL(pBiDi, start) & 1) &&
-         (pBiDi->reorderingMode==UBIDI_REORDER_INVERSE_LIKE_DIRECT  ||
-          pBiDi->reorderingMode==UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL));
+    inverseRTL =
+        static_cast<UBool>((start < pBiDi->lastArabicPos) && (GET_PARALEVEL(pBiDi, start) & 1) &&
+                           (pBiDi->reorderingMode == UBIDI_REORDER_INVERSE_LIKE_DIRECT ||
+                            pBiDi->reorderingMode == UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL));
 
     /* initialize for property and levels state tables */
     levState.startL2EN=-1;              /* used for INVERSE_LIKE_DIRECT_WITH_MARKS */
     levState.lastStrongRTL=-1;          /* used for INVERSE_LIKE_DIRECT_WITH_MARKS */
     levState.runStart=start;
     levState.runLevel=pBiDi->levels[start];
-    levState.pImpTab=(const ImpTab*)((pBiDi->pImpTabPair)->pImpTab)[levState.runLevel&1];
-    levState.pImpAct=(const ImpAct*)((pBiDi->pImpTabPair)->pImpAct)[levState.runLevel&1];
+    levState.pImpTab = static_cast<const ImpTab*>(((pBiDi->pImpTabPair)->pImpTab)[levState.runLevel & 1]);
+    levState.pImpAct = static_cast<const ImpAct*>(((pBiDi->pImpTabPair)->pImpAct)[levState.runLevel & 1]);
     if(start==0 && pBiDi->proLength>0) {
         DirProp lastStrong=lastL_R_AL(pBiDi);
         if(lastStrong!=DirProp_ON) {
@@ -2391,8 +2391,8 @@ setParaRunsOnly(UBiDi *pBiDi, const char16_t *text, int32_t length,
         goto cleanup3;
     }
     visualMap=runsOnlyMemory;
-    visualText=(char16_t *)&visualMap[length];
-    saveLevels=(UBiDiLevel *)&visualText[length];
+    visualText = reinterpret_cast<char16_t*>(&visualMap[length]);
+    saveLevels = reinterpret_cast<UBiDiLevel*>(&visualText[length]);
     saveOptions=pBiDi->reorderingOptions;
     if(saveOptions & UBIDI_OPTION_INSERT_MARKS) {
         pBiDi->reorderingOptions&=~UBIDI_OPTION_INSERT_MARKS;

thirdparty/icu4c/common/ubidi_props.cpp

@@ -51,7 +51,7 @@ _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32
     (void)end;
     (void)value;
     /* add the start code point to the USet */
-    const USetAdder *sa=(const USetAdder *)context;
+    const USetAdder* sa = static_cast<const USetAdder*>(context);
     sa->add(sa->set, start);
     return true;
 }
@@ -139,7 +139,7 @@ ubidi_getClass(UChar32 c) {
 U_CFUNC UBool
 ubidi_isMirrored(UChar32 c) {
     uint16_t props=UTRIE2_GET16(&ubidi_props_singleton.trie, c);
-    return (UBool)UBIDI_GET_FLAG(props, UBIDI_IS_MIRRORED_SHIFT);
+    return UBIDI_GET_FLAG(props, UBIDI_IS_MIRRORED_SHIFT);
 }
 
 static UChar32
@@ -183,13 +183,13 @@ ubidi_getMirror(UChar32 c) {
 U_CFUNC UBool
 ubidi_isBidiControl(UChar32 c) {
     uint16_t props=UTRIE2_GET16(&ubidi_props_singleton.trie, c);
-    return (UBool)UBIDI_GET_FLAG(props, UBIDI_BIDI_CONTROL_SHIFT);
+    return UBIDI_GET_FLAG(props, UBIDI_BIDI_CONTROL_SHIFT);
 }
 
 U_CFUNC UBool
 ubidi_isJoinControl(UChar32 c) {
     uint16_t props=UTRIE2_GET16(&ubidi_props_singleton.trie, c);
-    return (UBool)UBIDI_GET_FLAG(props, UBIDI_JOIN_CONTROL_SHIFT);
+    return UBIDI_GET_FLAG(props, UBIDI_JOIN_CONTROL_SHIFT);
 }
 
 U_CFUNC UJoiningType

thirdparty/icu4c/common/ubiditransform.cpp

@@ -233,7 +233,7 @@ updateSrc(UBiDiTransform *pTransform, const char16_t *newSrc, uint32_t newLength
             uprv_free(pTransform->src);
             pTransform->src = nullptr;
         }
-        pTransform->src = (char16_t *)uprv_malloc(newSize * sizeof(char16_t));
+        pTransform->src = static_cast<char16_t*>(uprv_malloc(newSize * sizeof(char16_t)));
         if (pTransform->src == nullptr) {
             *pErrorCode = U_MEMORY_ALLOCATION_ERROR;
             //pTransform->srcLength = pTransform->srcSize = 0;
@@ -499,7 +499,7 @@ ubiditransform_transform(UBiDiTransform *pBiDiTransform,
     /* Checking for U_SUCCESS() within the loop to bail out on first failure. */
     for (action = pBiDiTransform->pActiveScheme->actions; *action && U_SUCCESS(*pErrorCode); action++) {
         if ((*action)(pBiDiTransform, pErrorCode)) {
-            if (action + 1) {
+            if (action[1] != nullptr) {
                 updateSrc(pBiDiTransform, pBiDiTransform->dest, *pBiDiTransform->pDestLength,
                         *pBiDiTransform->pDestLength, pErrorCode);
             }

thirdparty/icu4c/common/ubidiwrt.cpp

@@ -501,7 +501,10 @@ ubidi_writeReordered(UBiDi *pBiDi,
                     destSize-=runLength;
 
                     if((pBiDi->isInverse) &&
-                       (/*run<runCount-1 &&*/ dirProps[logicalStart+runLength-1]!=L)) {
+                           (/*run<runCount-1 &&*/
+                            runLength > 0 && // doWriteForward may return 0 if src
+                                             // only include bidi control chars
+                            dirProps[logicalStart+runLength-1]!=L)) {
                         markFlag |= LRM_AFTER;
                     }
                     if (markFlag & LRM_AFTER) {
@@ -632,7 +635,10 @@ ubidi_writeReordered(UBiDi *pBiDi,
                     }
                     destSize-=runLength;
 
-                    if(/*run>0 &&*/ !(MASK_R_AL&DIRPROP_FLAG(dirProps[logicalStart+runLength-1]))) {
+                    if(/*run>0 &&*/
+                            runLength > 0 && // doWriteForward may return 0 if src
+                                             // only include bidi control chars
+                            !(MASK_R_AL&DIRPROP_FLAG(dirProps[logicalStart+runLength-1]))) {
                         if(destSize>0) {
                             *dest++=RLM_CHAR;
                         }

thirdparty/icu4c/common/ucase.cpp

@@ -38,7 +38,7 @@
 static UBool U_CALLCONV
 _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 /*end*/, uint32_t /*value*/) {
     /* add the start code point to the USet */
-    const USetAdder *sa=(const USetAdder *)context;
+    const USetAdder* sa = static_cast<const USetAdder*>(context);
     sa->add(sa->set, start);
     return true;
 }
@@ -696,17 +696,17 @@ getDotType(UChar32 c) {
 
 U_CAPI UBool U_EXPORT2
 ucase_isSoftDotted(UChar32 c) {
-    return (UBool)(getDotType(c)==UCASE_SOFT_DOTTED);
+    return getDotType(c)==UCASE_SOFT_DOTTED;
 }
 
 U_CAPI UBool U_EXPORT2
 ucase_isCaseSensitive(UChar32 c) {
     uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
     if(!UCASE_HAS_EXCEPTION(props)) {
-        return (UBool)((props&UCASE_SENSITIVE)!=0);
+        return (props&UCASE_SENSITIVE)!=0;
     } else {
         const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
-        return (UBool)((*pe&UCASE_EXC_SENSITIVE)!=0);
+        return (*pe&UCASE_EXC_SENSITIVE)!=0;
     }
 }
 
@@ -1623,12 +1623,12 @@ ucase_toFullFolding(UChar32 c,
 
 U_CAPI UBool U_EXPORT2
 u_isULowercase(UChar32 c) {
-    return (UBool)(UCASE_LOWER==ucase_getType(c));
+    return UCASE_LOWER==ucase_getType(c);
 }
 
 U_CAPI UBool U_EXPORT2
 u_isUUppercase(UChar32 c) {
-    return (UBool)(UCASE_UPPER==ucase_getType(c));
+    return UCASE_UPPER==ucase_getType(c);
 }
 
 /* Transforms the Unicode character to its lower case equivalent.*/

thirdparty/icu4c/common/ucasemap.cpp

@@ -160,12 +160,12 @@ appendResult(int32_t cpLength, int32_t result, const char16_t *s,
 }
 
 // See unicode/utf8.h U8_APPEND_UNSAFE().
-inline uint8_t getTwoByteLead(UChar32 c) { return (uint8_t)((c >> 6) | 0xc0); }
-inline uint8_t getTwoByteTrail(UChar32 c) { return (uint8_t)((c & 0x3f) | 0x80); }
+inline uint8_t getTwoByteLead(UChar32 c) { return static_cast<uint8_t>((c >> 6) | 0xc0); }
+inline uint8_t getTwoByteTrail(UChar32 c) { return static_cast<uint8_t>((c & 0x3f) | 0x80); }
 
 UChar32 U_CALLCONV
 utf8_caseContextIterator(void *context, int8_t dir) {
-    UCaseContext *csc=(UCaseContext *)context;
+    UCaseContext* csc = static_cast<UCaseContext*>(context);
     UChar32 c;
 
     if(dir<0) {
@@ -234,7 +234,7 @@ void toLower(int32_t caseLocale, uint32_t options,
                 if (d == 0) { continue; }
                 ByteSinkUtil::appendUnchanged(src + prev, srcIndex - 1 - prev,
                                               sink, options, edits, errorCode);
-                char ascii = (char)(lead + d);
+                char ascii = static_cast<char>(lead + d);
                 sink.Append(&ascii, 1);
                 if (edits != nullptr) {
                     edits->addReplace(1, 1);
@@ -342,7 +342,7 @@ void toUpper(int32_t caseLocale, uint32_t options,
                 if (d == 0) { continue; }
                 ByteSinkUtil::appendUnchanged(src + prev, srcIndex - 1 - prev,
                                               sink, options, edits, errorCode);
-                char ascii = (char)(lead + d);
+                char ascii = static_cast<char>(lead + d);
                 sink.Append(&ascii, 1);
                 if (edits != nullptr) {
                     edits->addReplace(1, 1);
@@ -747,14 +747,14 @@ void toUpper(uint32_t options,
                 int32_t i2 = i + 2;
                 if ((data & HAS_EITHER_DIALYTIKA) != 0) {
                     change |= (i2 + 2) > nextIndex ||
-                            src[i2] != (uint8_t)u8"\u0308"[0] ||
-                            src[i2 + 1] != (uint8_t)u8"\u0308"[1];
+                            src[i2] != static_cast<uint8_t>(u8"\u0308"[0]) ||
+                            src[i2 + 1] != static_cast<uint8_t>(u8"\u0308"[1]);
                     i2 += 2;
                 }
                 if (addTonos) {
                     change |= (i2 + 2) > nextIndex ||
-                            src[i2] != (uint8_t)u8"\u0301"[0] ||
-                            src[i2 + 1] != (uint8_t)u8"\u0301"[1];
+                            src[i2] != static_cast<uint8_t>(u8"\u0301"[0]) ||
+                            src[i2 + 1] != static_cast<uint8_t>(u8"\u0301"[1]);
                     i2 += 2;
                 }
                 int32_t oldLength = nextIndex - i;
@@ -867,14 +867,14 @@ ucasemap_mapUTF8(int32_t caseLocale, uint32_t options, UCASEMAP_BREAK_ITERATOR_P
 
     // Get the string length.
     if (srcLength == -1) {
-        srcLength = (int32_t)uprv_strlen((const char *)src);
+        srcLength = static_cast<int32_t>(uprv_strlen(src));
     }
 
     if (edits != nullptr && (options & U_EDITS_NO_RESET) == 0) {
         edits->reset();
     }
     stringCaseMapper(caseLocale, options, UCASEMAP_BREAK_ITERATOR
-                     (const uint8_t *)src, srcLength, sink, edits, errorCode);
+                     reinterpret_cast<const uint8_t*>(src), srcLength, sink, edits, errorCode);
     sink.Flush();
     if (U_SUCCESS(errorCode)) {
         if (edits != nullptr) {
@@ -904,7 +904,7 @@ ucasemap_mapUTF8(int32_t caseLocale, uint32_t options, UCASEMAP_BREAK_ITERATOR_P
 
     /* get the string length */
     if(srcLength==-1) {
-        srcLength=(int32_t)uprv_strlen((const char *)src);
+        srcLength = static_cast<int32_t>(uprv_strlen(src));
     }
 
     /* check for overlapping source and destination */
@@ -923,7 +923,7 @@ ucasemap_mapUTF8(int32_t caseLocale, uint32_t options, UCASEMAP_BREAK_ITERATOR_P
         dest, destCapacity,
         [&](ByteSink& sink, UErrorCode& status) {
             stringCaseMapper(caseLocale, options, UCASEMAP_BREAK_ITERATOR
-                             (const uint8_t *)src, srcLength, sink, edits, status);
+                             reinterpret_cast<const uint8_t*>(src), srcLength, sink, edits, status);
         },
         errorCode);
     if (U_SUCCESS(errorCode) && edits != nullptr) {

thirdparty/icu4c/common/ucasemap_titlecase_brkiter.cpp

@@ -107,7 +107,7 @@ ucasemap_utf8ToTitle(UCaseMap *csm,
         return 0;
     }
     UText utext=UTEXT_INITIALIZER;
-    utext_openUTF8(&utext, (const char *)src, srcLength, pErrorCode);
+    utext_openUTF8(&utext, src, srcLength, pErrorCode);
     if (U_FAILURE(*pErrorCode)) {
         return 0;
     }

thirdparty/icu4c/common/uchar.cpp

@@ -23,6 +23,7 @@
 
 #include "unicode/utypes.h"
 #include "unicode/uchar.h"
+#include "unicode/ucptrie.h"
 #include "unicode/uscript.h"
 #include "unicode/udata.h"
 #include "uassert.h"
@@ -67,9 +68,9 @@ _enumTypeValue(const void *context, uint32_t value) {
 static UBool U_CALLCONV
 _enumTypeRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
     /* just cast the value to UCharCategory */
-    return ((struct _EnumTypeCallback *)context)->
-        enumRange(((struct _EnumTypeCallback *)context)->context,
-                  start, end+1, (UCharCategory)value);
+    return static_cast<const _EnumTypeCallback*>(context)->
+        enumRange(static_cast<const _EnumTypeCallback*>(context)->context,
+                  start, end + 1, static_cast<UCharCategory>(value));
 }
 
 U_CAPI void U_EXPORT2
@@ -90,7 +91,7 @@ U_CAPI UBool U_EXPORT2
 u_islower(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)==U_LOWERCASE_LETTER);
+    return GET_CATEGORY(props)==U_LOWERCASE_LETTER;
 }
 
 /* Checks if ch is an upper case letter.*/
@@ -98,7 +99,7 @@ U_CAPI UBool U_EXPORT2
 u_isupper(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)==U_UPPERCASE_LETTER);
+    return GET_CATEGORY(props)==U_UPPERCASE_LETTER;
 }
 
 /* Checks if ch is a title case letter; usually upper case letters.*/
@@ -106,7 +107,7 @@ U_CAPI UBool U_EXPORT2
 u_istitle(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)==U_TITLECASE_LETTER);
+    return GET_CATEGORY(props)==U_TITLECASE_LETTER;
 }
 
 /* Checks if ch is a decimal digit. */
@@ -114,7 +115,7 @@ U_CAPI UBool U_EXPORT2
 u_isdigit(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
+    return GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER;
 }
 
 U_CAPI UBool U_EXPORT2
@@ -130,7 +131,7 @@ u_isxdigit(UChar32 c) {
     }
 
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER);
+    return GET_CATEGORY(props)==U_DECIMAL_DIGIT_NUMBER;
 }
 
 /* Checks if the Unicode character is a letter.*/
@@ -138,7 +139,7 @@ U_CAPI UBool U_EXPORT2
 u_isalpha(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&U_GC_L_MASK)!=0);
+    return (CAT_MASK(props)&U_GC_L_MASK)!=0;
 }
 
 U_CAPI UBool U_EXPORT2
@@ -151,7 +152,7 @@ U_CAPI UBool U_EXPORT2
 u_isalnum(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0);
+    return (CAT_MASK(props)&(U_GC_L_MASK|U_GC_ND_MASK))!=0;
 }
 
 /**
@@ -160,7 +161,7 @@ u_isalnum(UChar32 c) {
  */
 U_CFUNC UBool
 u_isalnumPOSIX(UChar32 c) {
-    return (UBool)(u_isUAlphabetic(c) || u_isdigit(c));
+    return u_isUAlphabetic(c) || u_isdigit(c);
 }
 
 /* Checks if ch is a unicode character with assigned character type.*/
@@ -168,7 +169,7 @@ U_CAPI UBool U_EXPORT2
 u_isdefined(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(GET_CATEGORY(props)!=0);
+    return GET_CATEGORY(props)!=0;
 }
 
 /* Checks if the Unicode character is a base form character that can take a diacritic.*/
@@ -176,7 +177,7 @@ U_CAPI UBool U_EXPORT2
 u_isbase(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0);
+    return (CAT_MASK(props)&(U_GC_L_MASK|U_GC_N_MASK|U_GC_MC_MASK|U_GC_ME_MASK))!=0;
 }
 
 /* Checks if the Unicode character is a control character.*/
@@ -184,7 +185,7 @@ U_CAPI UBool U_EXPORT2
 u_iscntrl(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0);
+    return (CAT_MASK(props)&(U_GC_CC_MASK|U_GC_CF_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK))!=0;
 }
 
 U_CAPI UBool U_EXPORT2
@@ -205,14 +206,14 @@ U_CAPI UBool U_EXPORT2
 u_isspace(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c));
+    return (CAT_MASK(props)&U_GC_Z_MASK)!=0 || IS_THAT_CONTROL_SPACE(c);
 }
 
 U_CAPI UBool U_EXPORT2
 u_isJavaSpaceChar(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&U_GC_Z_MASK)!=0);
+    return (CAT_MASK(props)&U_GC_Z_MASK)!=0;
 }
 
 /* Checks if the Unicode character is a whitespace character.*/
@@ -220,11 +221,9 @@ U_CAPI UBool U_EXPORT2
 u_isWhitespace(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(
-                ((CAT_MASK(props)&U_GC_Z_MASK)!=0 &&
-                    c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */
-                IS_THAT_ASCII_CONTROL_SPACE(c)
-           );
+    return ((CAT_MASK(props)&U_GC_Z_MASK)!=0 &&
+               c!=NBSP && c!=FIGURESP && c!=NNBSP) || /* exclude no-break spaces */
+           IS_THAT_ASCII_CONTROL_SPACE(c);
 }
 
 U_CAPI UBool U_EXPORT2
@@ -235,7 +234,7 @@ u_isblank(UChar32 c) {
         /* Zs */
         uint32_t props;
         GET_PROPS(c, props);
-        return (UBool)(GET_CATEGORY(props)==U_SPACE_SEPARATOR);
+        return GET_CATEGORY(props)==U_SPACE_SEPARATOR;
     }
 }
 
@@ -250,7 +249,7 @@ u_isprint(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
     /* comparing ==0 returns false for the categories mentioned */
-    return (UBool)((CAT_MASK(props)&U_GC_C_MASK)==0);
+    return (CAT_MASK(props)&U_GC_C_MASK)==0;
 }
 
 /**
@@ -266,7 +265,7 @@ u_isprintPOSIX(UChar32 c) {
      * The only cntrl character in graph+blank is TAB (in blank).
      * Here we implement (blank-TAB)=Zs instead of calling u_isblank().
      */
-    return (UBool)((GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c));
+    return (GET_CATEGORY(props)==U_SPACE_SEPARATOR) || u_isgraphPOSIX(c);
 }
 
 U_CAPI UBool U_EXPORT2
@@ -274,9 +273,9 @@ u_isgraph(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
     /* comparing ==0 returns false for the categories mentioned */
-    return (UBool)((CAT_MASK(props)&
-                    (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
-                   ==0);
+    return (CAT_MASK(props)&
+            (U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
+           ==0;
 }
 
 /**
@@ -292,16 +291,16 @@ u_isgraphPOSIX(UChar32 c) {
     GET_PROPS(c, props);
     /* \p{space}\p{gc=Control} == \p{gc=Z}\p{Control} */
     /* comparing ==0 returns false for the categories mentioned */
-    return (UBool)((CAT_MASK(props)&
-                    (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
-                   ==0);
+    return (CAT_MASK(props)&
+            (U_GC_CC_MASK|U_GC_CS_MASK|U_GC_CN_MASK|U_GC_Z_MASK))
+           ==0;
 }
 
 U_CAPI UBool U_EXPORT2
 u_ispunct(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&U_GC_P_MASK)!=0);
+    return (CAT_MASK(props)&U_GC_P_MASK)!=0;
 }
 
 /*Checks if the Unicode character can be ignorable in a Java or Unicode identifier.*/
@@ -312,7 +311,7 @@ u_isIDIgnorable(UChar32 c) {
     } else {
         uint32_t props;
         GET_PROPS(c, props);
-        return (UBool)(GET_CATEGORY(props)==U_FORMAT_CHAR);
+        return GET_CATEGORY(props)==U_FORMAT_CHAR;
     }
 }
 
@@ -321,7 +320,7 @@ U_CAPI UBool U_EXPORT2
 u_isJavaIDStart(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)((CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0);
+    return (CAT_MASK(props)&(U_GC_L_MASK|U_GC_SC_MASK|U_GC_PC_MASK))!=0;
 }
 
 /*Checks if the Unicode character can be a Java identifier part other than starting the
@@ -331,14 +330,13 @@ U_CAPI UBool U_EXPORT2
 u_isJavaIDPart(UChar32 c) {
     uint32_t props;
     GET_PROPS(c, props);
-    return (UBool)(
-           (CAT_MASK(props)&
+    return (CAT_MASK(props)&
             (U_GC_ND_MASK|U_GC_NL_MASK|
              U_GC_L_MASK|
              U_GC_SC_MASK|U_GC_PC_MASK|
              U_GC_MC_MASK|U_GC_MN_MASK)
            )!=0 ||
-           u_isIDIgnorable(c));
+           u_isIDIgnorable(c);
 }
 
 U_CAPI int32_t U_EXPORT2
@@ -515,6 +513,8 @@ uprv_getMaxValues(int32_t column) {
         return indexes[UPROPS_MAX_VALUES_INDEX];
     case 2:
         return indexes[UPROPS_MAX_VALUES_2_INDEX];
+    case UPROPS_MAX_VALUES_OTHER_INDEX:
+        return indexes[column];
     default:
         return 0;
     }
@@ -524,8 +524,8 @@ U_CAPI void U_EXPORT2
 u_charAge(UChar32 c, UVersionInfo versionArray) {
     if(versionArray!=nullptr) {
         uint32_t version=u_getUnicodeProperties(c, 0)>>UPROPS_AGE_SHIFT;
-        versionArray[0]=(uint8_t)(version>>4);
-        versionArray[1]=(uint8_t)(version&0xf);
+        versionArray[0]=(uint8_t)(version>>2);
+        versionArray[1]=(uint8_t)(version&3);
         versionArray[2]=versionArray[3]=0;
     }
 }
@@ -540,7 +540,7 @@ uscript_getScript(UChar32 c, UErrorCode *pErrorCode) {
         return USCRIPT_INVALID_CODE;
     }
     uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
-    uint32_t codeOrIndex=uprops_mergeScriptCodeOrIndex(scriptX);
+    uint32_t codeOrIndex=scriptX&UPROPS_MAX_SCRIPT;
     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
         return (UScriptCode)codeOrIndex;
     } else if(scriptX<UPROPS_SCRIPT_X_WITH_INHERITED) {
@@ -555,7 +555,7 @@ uscript_getScript(UChar32 c, UErrorCode *pErrorCode) {
 U_CAPI UBool U_EXPORT2
 uscript_hasScript(UChar32 c, UScriptCode sc) UPRV_NO_SANITIZE_UNDEFINED {
     uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
-    uint32_t codeOrIndex=uprops_mergeScriptCodeOrIndex(scriptX);
+    uint32_t codeOrIndex=scriptX&UPROPS_MAX_SCRIPT;
     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
         return sc==(UScriptCode)codeOrIndex;
     }
@@ -587,7 +587,7 @@ uscript_getScriptExtensions(UChar32 c,
         return 0;
     }
     uint32_t scriptX=u_getUnicodeProperties(c, 0)&UPROPS_SCRIPT_X_MASK;
-    uint32_t codeOrIndex=uprops_mergeScriptCodeOrIndex(scriptX);
+    uint32_t codeOrIndex=scriptX&UPROPS_MAX_SCRIPT;
     if(scriptX<UPROPS_SCRIPT_X_WITH_COMMON) {
         if(capacity==0) {
             *pErrorCode=U_BUFFER_OVERFLOW_ERROR;
@@ -618,7 +618,15 @@ uscript_getScriptExtensions(UChar32 c,
 
 U_CAPI UBlockCode U_EXPORT2
 ublock_getCode(UChar32 c) {
-    return (UBlockCode)((u_getUnicodeProperties(c, 0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT);
+    // We store Block values indexed by the code point shifted right 4 bits
+    // and use a "small" UCPTrie=CodePointTrie for minimal data size.
+    // This works because blocks have xxx0..xxxF ranges.
+    uint32_t c4 = c;  // unsigned so that shifting right does not worry the compiler
+    // Shift unless out of range, in which case we fetch the trie's error value.
+    if (c4 <= 0x10ffff) {
+        c4 >>= 4;
+    }
+    return (UBlockCode)ucptrie_get(&block_trie, c4);
 }
 
 /* property starts for UnicodeSet ------------------------------------------- */
@@ -626,7 +634,7 @@ ublock_getCode(UChar32 c) {
 static UBool U_CALLCONV
 _enumPropertyStartsRange(const void *context, UChar32 start, UChar32 end, uint32_t value) {
     /* add the start code point to the USet */
-    const USetAdder *sa=(const USetAdder *)context;
+    const USetAdder* sa = static_cast<const USetAdder*>(context);
     sa->add(sa->set, start);
     (void)end;
     (void)value;
@@ -706,3 +714,18 @@ upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
     /* add the start code point of each same-value range of the properties vectors trie */
     utrie2_enum(&propsVectorsTrie, nullptr, _enumPropertyStartsRange, sa);
 }
+
+U_CFUNC void U_EXPORT2
+ublock_addPropertyStarts(const USetAdder *sa, UErrorCode & /*errorCode*/) {
+    // Add the start code point of each same-value range of the trie.
+    // We store Block values indexed by the code point shifted right 4 bits;
+    // see ublock_getCode().
+    UChar32 start = 0, end;
+    uint32_t value;
+    while (start < 0x11000 &&  // limit: (max code point + 1) >> 4
+            (end = ucptrie_getRange(&block_trie, start, UCPMAP_RANGE_NORMAL, 0,
+                                    nullptr, nullptr, &value)) >= 0) {
+        sa->add(sa->set, start << 4);
+        start = end + 1;
+    }
+}

thirdparty/icu4c/common/ucharstrie.cpp

@@ -297,7 +297,7 @@ UCharsTrie::findUniqueValueFromBranch(const char16_t *pos, int32_t length,
         ++pos;  // ignore a comparison unit
         // handle its value
         int32_t node=*pos++;
-        UBool isFinal=(UBool)(node>>15);
+        UBool isFinal = static_cast<UBool>(node >> 15);
         node&=0x7fff;
         int32_t value=readValue(pos, node);
         pos=skipValue(pos, node);
@@ -339,7 +339,7 @@ UCharsTrie::findUniqueValue(const char16_t *pos, UBool haveUniqueValue, int32_t
             pos+=node-kMinLinearMatch+1;  // Ignore the match units.
             node=*pos++;
         } else {
-            UBool isFinal=(UBool)(node>>15);
+            UBool isFinal = static_cast<UBool>(node >> 15);
             int32_t value;
             if(isFinal) {
                 value=readValue(pos, node&0x7fff);

thirdparty/icu4c/common/ucharstriebuilder.cpp

@@ -75,7 +75,7 @@ UCharsTrieElement::setTo(const UnicodeString &s, int32_t val,
         return;
     }
     stringOffset=strings.length();
-    strings.append((char16_t)length);
+    strings.append(static_cast<char16_t>(length));
     value=val;
     strings.append(s);
 }
@@ -186,7 +186,7 @@ UCharsTrieBuilder::buildUChars(UStringTrieBuildOption buildOption, UErrorCode &e
             errorCode=U_MEMORY_ALLOCATION_ERROR;
             return;
         }
-        uprv_sortArray(elements, elementsLength, (int32_t)sizeof(UCharsTrieElement),
+        uprv_sortArray(elements, elementsLength, static_cast<int32_t>(sizeof(UCharsTrieElement)),
                       compareElementStrings, &strings,
                       false,  // need not be a stable sort
                       &errorCode);
@@ -351,7 +351,7 @@ UCharsTrieBuilder::write(int32_t unit) {
     int32_t newLength=ucharsLength+1;
     if(ensureCapacity(newLength)) {
         ucharsLength=newLength;
-        uchars[ucharsCapacity-ucharsLength]=(char16_t)unit;
+        uchars[ucharsCapacity - ucharsLength] = static_cast<char16_t>(unit);
     }
     return ucharsLength;
 }
@@ -379,19 +379,19 @@ UCharsTrieBuilder::writeValueAndFinal(int32_t i, UBool isFinal) {
     char16_t intUnits[3];
     int32_t length;
     if(i<0 || i>UCharsTrie::kMaxTwoUnitValue) {
-        intUnits[0]=(char16_t)(UCharsTrie::kThreeUnitValueLead);
-        intUnits[1]=(char16_t)((uint32_t)i>>16);
-        intUnits[2]=(char16_t)i;
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kThreeUnitValueLead);
+        intUnits[1] = static_cast<char16_t>(static_cast<uint32_t>(i) >> 16);
+        intUnits[2] = static_cast<char16_t>(i);
         length=3;
     // } else if(i<=UCharsTrie::kMaxOneUnitValue) {
     //     intUnits[0]=(char16_t)(i);
     //     length=1;
     } else {
-        intUnits[0]=(char16_t)(UCharsTrie::kMinTwoUnitValueLead+(i>>16));
-        intUnits[1]=(char16_t)i;
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kMinTwoUnitValueLead + (i >> 16));
+        intUnits[1] = static_cast<char16_t>(i);
         length=2;
     }
-    intUnits[0]=(char16_t)(intUnits[0]|(isFinal<<15));
+    intUnits[0] = static_cast<char16_t>(intUnits[0] | (isFinal << 15));
     return write(intUnits, length);
 }
 
@@ -403,19 +403,19 @@ UCharsTrieBuilder::writeValueAndType(UBool hasValue, int32_t value, int32_t node
     char16_t intUnits[3];
     int32_t length;
     if(value<0 || value>UCharsTrie::kMaxTwoUnitNodeValue) {
-        intUnits[0]=(char16_t)(UCharsTrie::kThreeUnitNodeValueLead);
-        intUnits[1]=(char16_t)((uint32_t)value>>16);
-        intUnits[2]=(char16_t)value;
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kThreeUnitNodeValueLead);
+        intUnits[1] = static_cast<char16_t>(static_cast<uint32_t>(value) >> 16);
+        intUnits[2] = static_cast<char16_t>(value);
         length=3;
     } else if(value<=UCharsTrie::kMaxOneUnitNodeValue) {
-        intUnits[0]=(char16_t)((value+1)<<6);
+        intUnits[0] = static_cast<char16_t>((value + 1) << 6);
         length=1;
     } else {
-        intUnits[0]=(char16_t)(UCharsTrie::kMinTwoUnitNodeValueLead+((value>>10)&0x7fc0));
-        intUnits[1]=(char16_t)value;
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kMinTwoUnitNodeValueLead + ((value >> 10) & 0x7fc0));
+        intUnits[1] = static_cast<char16_t>(value);
         length=2;
     }
-    intUnits[0]|=(char16_t)node;
+    intUnits[0] |= static_cast<char16_t>(node);
     return write(intUnits, length);
 }
 
@@ -429,14 +429,14 @@ UCharsTrieBuilder::writeDeltaTo(int32_t jumpTarget) {
     char16_t intUnits[3];
     int32_t length;
     if(i<=UCharsTrie::kMaxTwoUnitDelta) {
-        intUnits[0]=(char16_t)(UCharsTrie::kMinTwoUnitDeltaLead+(i>>16));
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kMinTwoUnitDeltaLead + (i >> 16));
         length=1;
     } else {
-        intUnits[0]=(char16_t)(UCharsTrie::kThreeUnitDeltaLead);
-        intUnits[1]=(char16_t)(i>>16);
+        intUnits[0] = static_cast<char16_t>(UCharsTrie::kThreeUnitDeltaLead);
+        intUnits[1] = static_cast<char16_t>(i >> 16);
         length=2;
     }
-    intUnits[length++]=(char16_t)i;
+    intUnits[length++] = static_cast<char16_t>(i);
     return write(intUnits, length);
 }
 

thirdparty/icu4c/common/ucharstrieiterator.cpp

@@ -114,7 +114,7 @@ UCharsTrie::Iterator::next(UErrorCode &errorCode) {
         pos=uchars_+stack_->elementAti(stackSize-2);
         stack_->setSize(stackSize-2);
         str_.truncate(length&0xffff);
-        length=(int32_t)((uint32_t)length>>16);
+        length = static_cast<int32_t>(static_cast<uint32_t>(length) >> 16);
         if(length>1) {
             pos=branchNext(pos, length, errorCode);
             if(pos==nullptr) {
@@ -138,7 +138,7 @@ UCharsTrie::Iterator::next(UErrorCode &errorCode) {
                 skipValue_=false;
             } else {
                 // Deliver value for the string so far.
-                UBool isFinal=(UBool)(node>>15);
+                UBool isFinal = static_cast<UBool>(node >> 15);
                 if(isFinal) {
                     value_=readValue(pos, node&0x7fff);
                 } else {
@@ -187,7 +187,7 @@ UCharsTrie::Iterator::branchNext(const char16_t *pos, int32_t length, UErrorCode
     while(length>kMaxBranchLinearSubNodeLength) {
         ++pos;  // ignore the comparison unit
         // Push state for the greater-or-equal edge.
-        stack_->addElement((int32_t)(skipDelta(pos)-uchars_), errorCode);
+        stack_->addElement(static_cast<int32_t>(skipDelta(pos) - uchars_), errorCode);
         stack_->addElement(((length-(length>>1))<<16)|str_.length(), errorCode);
         // Follow the less-than edge.
         length>>=1;
@@ -197,10 +197,10 @@ UCharsTrie::Iterator::branchNext(const char16_t *pos, int32_t length, UErrorCode
     // Read the first (key, value) pair.
     char16_t trieUnit=*pos++;
     int32_t node=*pos++;
-    UBool isFinal=(UBool)(node>>15);
+    UBool isFinal = static_cast<UBool>(node >> 15);
     int32_t value=readValue(pos, node&=0x7fff);
     pos=skipValue(pos, node);
-    stack_->addElement((int32_t)(pos-uchars_), errorCode);
+    stack_->addElement(static_cast<int32_t>(pos - uchars_), errorCode);
     stack_->addElement(((length-1)<<16)|str_.length(), errorCode);
     str_.append(trieUnit);
     if(isFinal) {

thirdparty/icu4c/common/uchriter.cpp

@@ -172,7 +172,7 @@ UCharCharacterIterator::nextPostInc() {
 
 UBool
 UCharCharacterIterator::hasNext() {
-    return (UBool)(pos < end ? true : false);
+    return pos < end;
 }
 
 char16_t
@@ -186,7 +186,7 @@ UCharCharacterIterator::previous() {
 
 UBool
 UCharCharacterIterator::hasPrevious() {
-    return (UBool)(pos > begin ? true : false);
+    return pos > begin;
 }
 
 UChar32

thirdparty/icu4c/common/ucmndata.cpp

@@ -108,8 +108,8 @@ strcmpAfterPrefix(const char *s1, const char *s2, int32_t *pPrefixLength) {
     s1+=pl;
     s2+=pl;
     for(;;) {
-        int32_t c1=(uint8_t)*s1++;
-        int32_t c2=(uint8_t)*s2++;
+        int32_t c1 = static_cast<uint8_t>(*s1++);
+        int32_t c2 = static_cast<uint8_t>(*s2++);
         cmp=c1-c2;
         if(cmp!=0 || c1==0) {  /* different or done */
             break;
@@ -271,7 +271,7 @@ offsetTOCLookupFn(const UDataMemory *pData,
 
 static uint32_t U_CALLCONV pointerTOCEntryCount(const UDataMemory *pData) {
     const PointerTOC *toc = (PointerTOC *)pData->toc;
-    return (uint32_t)((toc != nullptr) ? (toc->count) : 0);
+    return toc != nullptr ? toc->count : 0;
 }
 
 static const DataHeader * U_CALLCONV pointerTOCLookupFn(const UDataMemory *pData,

thirdparty/icu4c/common/ucnv.cpp

@@ -916,7 +916,7 @@ _fromUnicodeWithCallback(UConverterFromUnicodeArgs *pArgs, UErrorCode *err) {
              * s<sourceLimit before converterSawEndOfInput is checked
              */
             converterSawEndOfInput=
-                (UBool)(U_SUCCESS(*err) &&
+                static_cast<UBool>(U_SUCCESS(*err) &&
                         pArgs->flush && pArgs->source==pArgs->sourceLimit &&
                         cnv->fromUChar32==0);
         } else {
@@ -941,7 +941,7 @@ _fromUnicodeWithCallback(UConverterFromUnicodeArgs *pArgs, UErrorCode *err) {
         for(;;) {
             /* update offsets if we write any */
             if(offsets!=nullptr) {
-                int32_t length=(int32_t)(pArgs->target-t);
+                int32_t length = static_cast<int32_t>(pArgs->target - t);
                 if(length>0) {
                     _updateOffsets(offsets, length, sourceIndex, errorInputLength);
 
@@ -956,7 +956,7 @@ _fromUnicodeWithCallback(UConverterFromUnicodeArgs *pArgs, UErrorCode *err) {
                 }
 
                 if(sourceIndex>=0) {
-                    sourceIndex+=(int32_t)(pArgs->source-s);
+                    sourceIndex += static_cast<int32_t>(pArgs->source - s);
                 }
             }
 
@@ -1066,10 +1066,10 @@ _fromUnicodeWithCallback(UConverterFromUnicodeArgs *pArgs, UErrorCode *err) {
 
                         U_ASSERT(cnv->preFromULength==0);
 
-                        length=(int32_t)(pArgs->sourceLimit-pArgs->source);
+                        length = static_cast<int32_t>(pArgs->sourceLimit - pArgs->source);
                         if(length>0) {
                             u_memcpy(cnv->preFromU, pArgs->source, length);
-                            cnv->preFromULength=(int8_t)-length;
+                            cnv->preFromULength = static_cast<int8_t>(-length);
                         }
 
                         pArgs->source=realSource;
@@ -1089,7 +1089,7 @@ _fromUnicodeWithCallback(UConverterFromUnicodeArgs *pArgs, UErrorCode *err) {
                 codePoint=cnv->fromUChar32;
                 errorInputLength=0;
                 U16_APPEND_UNSAFE(cnv->invalidUCharBuffer, errorInputLength, codePoint);
-                cnv->invalidUCharLength=(int8_t)errorInputLength;
+                cnv->invalidUCharLength = static_cast<int8_t>(errorInputLength);
 
                 /* set the converter state to deal with the next character */
                 cnv->fromUChar32=0;
@@ -1134,7 +1134,7 @@ ucnv_outputOverflowFromUnicode(UConverter *cnv,
         offsets=nullptr;
     }
 
-    overflow=(char *)cnv->charErrorBuffer;
+    overflow = reinterpret_cast<char*>(cnv->charErrorBuffer);
     length=cnv->charErrorBufferLength;
     i=0;
     while(i<length) {
@@ -1146,7 +1146,7 @@ ucnv_outputOverflowFromUnicode(UConverter *cnv,
                 overflow[j++]=overflow[i++];
             } while(i<length);
 
-            cnv->charErrorBufferLength=(int8_t)j;
+            cnv->charErrorBufferLength = static_cast<int8_t>(j);
             *target=t;
             if(offsets!=nullptr) {
                 *pOffsets=offsets;
@@ -1361,7 +1361,7 @@ _toUnicodeWithCallback(UConverterToUnicodeArgs *pArgs, UErrorCode *err) {
              * s<sourceLimit before converterSawEndOfInput is checked
              */
             converterSawEndOfInput=
-                (UBool)(U_SUCCESS(*err) &&
+                static_cast<UBool>(U_SUCCESS(*err) &&
                         pArgs->flush && pArgs->source==pArgs->sourceLimit &&
                         cnv->toULength==0);
         } else {
@@ -1386,7 +1386,7 @@ _toUnicodeWithCallback(UConverterToUnicodeArgs *pArgs, UErrorCode *err) {
         for(;;) {
             /* update offsets if we write any */
             if(offsets!=nullptr) {
-                int32_t length=(int32_t)(pArgs->target-t);
+                int32_t length = static_cast<int32_t>(pArgs->target - t);
                 if(length>0) {
                     _updateOffsets(offsets, length, sourceIndex, errorInputLength);
 
@@ -1401,7 +1401,7 @@ _toUnicodeWithCallback(UConverterToUnicodeArgs *pArgs, UErrorCode *err) {
                 }
 
                 if(sourceIndex>=0) {
-                    sourceIndex+=(int32_t)(pArgs->source-s);
+                    sourceIndex += static_cast<int32_t>(pArgs->source - s);
                 }
             }
 
@@ -1513,10 +1513,10 @@ _toUnicodeWithCallback(UConverterToUnicodeArgs *pArgs, UErrorCode *err) {
 
                         U_ASSERT(cnv->preToULength==0);
 
-                        length=(int32_t)(pArgs->sourceLimit-pArgs->source);
+                        length = static_cast<int32_t>(pArgs->sourceLimit - pArgs->source);
                         if(length>0) {
                             uprv_memcpy(cnv->preToU, pArgs->source, length);
-                            cnv->preToULength=(int8_t)-length;
+                            cnv->preToULength = static_cast<int8_t>(-length);
                         }
 
                         pArgs->source=realSource;
@@ -1592,7 +1592,7 @@ ucnv_outputOverflowToUnicode(UConverter *cnv,
                 overflow[j++]=overflow[i++];
             } while(i<length);
 
-            cnv->UCharErrorBufferLength=(int8_t)j;
+            cnv->UCharErrorBufferLength = static_cast<int8_t>(j);
             *target=t;
             if(offsets!=nullptr) {
                 *pOffsets=offsets;
@@ -2437,7 +2437,7 @@ ucnv_internalConvert(UConverter *outConverter, UConverter *inConverter,
                        false,
                        true,
                        pErrorCode);
-        targetLength=(int32_t)(myTarget-target);
+        targetLength = static_cast<int32_t>(myTarget - target);
     }
 
     /*
@@ -2460,7 +2460,7 @@ ucnv_internalConvert(UConverter *outConverter, UConverter *inConverter,
                            false,
                            true,
                            pErrorCode);
-            targetLength+=(int32_t)(myTarget-targetBuffer);
+            targetLength += static_cast<int32_t>(myTarget - targetBuffer);
         } while(*pErrorCode==U_BUFFER_OVERFLOW_ERROR);
 
         /* done with preflighting, set warnings and errors as appropriate */
@@ -2684,7 +2684,7 @@ ucnv_fixFileSeparator(const UConverter *cnv,
 
 U_CAPI UBool  U_EXPORT2
 ucnv_isAmbiguous(const UConverter *cnv) {
-    return (UBool)(ucnv_getAmbiguous(cnv)!=nullptr);
+    return ucnv_getAmbiguous(cnv)!=nullptr;
 }
 
 U_CAPI void  U_EXPORT2

thirdparty/icu4c/common/ucnv_bld.cpp

@@ -231,7 +231,7 @@ static void
 ucnv_flushAvailableConverterCache() {
     gAvailableConverterCount = 0;
     if (gAvailableConverters) {
-        uprv_free((char **)gAvailableConverters);
+        uprv_free(const_cast<char**>(gAvailableConverters));
         gAvailableConverters = nullptr;
     }
     gAvailableConvertersInitOnce.reset();
@@ -270,7 +270,7 @@ static UBool U_CALLCONV
 isCnvAcceptable(void * /*context*/,
                 const char * /*type*/, const char * /*name*/,
                 const UDataInfo *pInfo) {
-    return (UBool)(
+    return
         pInfo->size>=20 &&
         pInfo->isBigEndian==U_IS_BIG_ENDIAN &&
         pInfo->charsetFamily==U_CHARSET_FAMILY &&
@@ -279,7 +279,7 @@ isCnvAcceptable(void * /*context*/,
         pInfo->dataFormat[1]==0x6e &&
         pInfo->dataFormat[2]==0x76 &&
         pInfo->dataFormat[3]==0x74 &&
-        pInfo->formatVersion[0]==6);  /* Everything will be version 6 */
+        pInfo->formatVersion[0]==6;  /* Everything will be version 6 */
 }
 
 /**
@@ -289,15 +289,15 @@ static UConverterSharedData*
 ucnv_data_unFlattenClone(UConverterLoadArgs *pArgs, UDataMemory *pData, UErrorCode *status)
 {
     /* UDataInfo info; -- necessary only if some converters have different formatVersion */
-    const uint8_t *raw = (const uint8_t *)udata_getMemory(pData);
-    const UConverterStaticData *source = (const UConverterStaticData *) raw;
+    const uint8_t* raw = static_cast<const uint8_t*>(udata_getMemory(pData));
+    const UConverterStaticData* source = reinterpret_cast<const UConverterStaticData*>(raw);
     UConverterSharedData *data;
-    UConverterType type = (UConverterType)source->conversionType;
+    UConverterType type = static_cast<UConverterType>(source->conversionType);
 
     if(U_FAILURE(*status))
         return nullptr;
 
-    if( (uint16_t)type >= UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES ||
+    if (static_cast<uint16_t>(type) >= UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES ||
         converterData[type] == nullptr ||
         !converterData[type]->isReferenceCounted ||
         converterData[type]->referenceCounter != 1 ||
@@ -307,7 +307,7 @@ ucnv_data_unFlattenClone(UConverterLoadArgs *pArgs, UDataMemory *pData, UErrorCo
         return nullptr;
     }
 
-    data = (UConverterSharedData *)uprv_malloc(sizeof(UConverterSharedData));
+    data = static_cast<UConverterSharedData*>(uprv_malloc(sizeof(UConverterSharedData)));
     if(data == nullptr) {
         *status = U_MEMORY_ALLOCATION_ERROR;
         return nullptr;
@@ -397,7 +397,7 @@ getAlgorithmicTypeFromName(const char *realName)
     lastMid = UINT32_MAX;
 
     for (;;) {
-        mid = (uint32_t)((start + limit) / 2);
+        mid = (start + limit) / 2;
         if (lastMid == mid) {   /* Have we moved? */
             break;  /* We haven't moved, and it wasn't found. */
         }
@@ -491,7 +491,7 @@ ucnv_getSharedConverterData(const char *name)
     {
         UConverterSharedData *rc;
 
-        rc = (UConverterSharedData*)uhash_get(SHARED_DATA_HASHTABLE, name);
+        rc = static_cast<UConverterSharedData*>(uhash_get(SHARED_DATA_HASHTABLE, name));
         UCNV_DEBUG_LOG("get",name,rc);
         return rc;
     }
@@ -682,8 +682,8 @@ parseConverterOptions(const char *inName,
             if(c==0) {
                 pArgs->options=(pPieces->options&=~UCNV_OPTION_VERSION);
                 return;
-            } else if((uint8_t)(c-'0')<10) {
-                pArgs->options=pPieces->options=(pPieces->options&~UCNV_OPTION_VERSION)|(uint32_t)(c-'0');
+            } else if (static_cast<uint8_t>(c - '0') < 10) {
+                pArgs->options = pPieces->options = (pPieces->options & ~UCNV_OPTION_VERSION) | static_cast<uint32_t>(c - '0');
                 ++inName;
             }
         } else if(uprv_strncmp(inName, "swaplfnl", 8)==0) {
@@ -909,7 +909,7 @@ ucnv_createAlgorithmicConverter(UConverter *myUConverter,
     stackArgs.options = options;
     stackArgs.locale=locale;
     cnv = ucnv_createConverterFromSharedData(
-            myUConverter, (UConverterSharedData *)sharedData,
+            myUConverter, const_cast<UConverterSharedData*>(sharedData),
             &stackArgs, err);
 
     UTRACE_EXIT_PTR_STATUS(cnv, *err);
@@ -1112,7 +1112,7 @@ static void U_CALLCONV initAvailableConvertersList(UErrorCode &errCode) {
     }
 
     /* We can't have more than "*converterTable" converters to open */
-    gAvailableConverters = (const char **) uprv_malloc(allConverterCount * sizeof(char*));
+    gAvailableConverters = static_cast<const char**>(uprv_malloc(allConverterCount * sizeof(char*)));
     if (!gAvailableConverters) {
         errCode = U_MEMORY_ALLOCATION_ERROR;
         return;
@@ -1440,7 +1440,7 @@ ucnv_swap(const UDataSwapper *ds,
                    MBCS_OPT_UNKNOWN_INCOMPATIBLE_MASK)==0
         ) {
             mbcsHeaderLength=mbcsHeader.options&MBCS_OPT_LENGTH_MASK;
-            noFromU=(UBool)((mbcsHeader.options&MBCS_OPT_NO_FROM_U)!=0);
+            noFromU = (mbcsHeader.options & MBCS_OPT_NO_FROM_U) != 0;
         } else {
             udata_printError(ds, "ucnv_swap(): unsupported _MBCSHeader.version %d.%d\n",
                              inMBCSHeader->version[0], inMBCSHeader->version[1]);

thirdparty/icu4c/common/ucnv_ct.cpp

@@ -368,7 +368,7 @@ getTrail:
                     /*look ahead to find the trail surrogate*/
                     if(source < sourceLimit) {
                         /* test the following code unit */
-                        char16_t trail=(char16_t) *source;
+                        char16_t trail = *source;
                         if(U16_IS_TRAIL(trail)) {
                             source++;
                             sourceChar=U16_GET_SUPPLEMENTARY(sourceChar, trail);

thirdparty/icu4c/common/ucnv_ext.cpp

@@ -41,8 +41,8 @@ ucnv_extFindToU(const uint32_t *toUSection, int32_t length, uint8_t byte) {
     int32_t i, start, limit;
 
     /* check the input byte against the lowest and highest section bytes */
-    start=(int32_t)UCNV_EXT_TO_U_GET_BYTE(toUSection[0]);
-    limit=(int32_t)UCNV_EXT_TO_U_GET_BYTE(toUSection[length-1]);
+    start = static_cast<int32_t>(UCNV_EXT_TO_U_GET_BYTE(toUSection[0]));
+    limit = static_cast<int32_t>(UCNV_EXT_TO_U_GET_BYTE(toUSection[length - 1]));
     if(byte<start || limit<byte) {
         return 0; /* the byte is out of range */
     }
@@ -180,9 +180,9 @@ ucnv_extMatchToU(const int32_t *cx, int8_t sisoState,
 
         /* match pre[] then src[] */
         if(i<preLength) {
-            b=(uint8_t)pre[i++];
+            b = static_cast<uint8_t>(pre[i++]);
         } else if(j<srcLength) {
-            b=(uint8_t)src[j++];
+            b = static_cast<uint8_t>(src[j++]);
         } else {
             /* all input consumed, partial match */
             if(flush || (length=(i+j))>UCNV_EXT_MAX_BYTES) {
@@ -206,7 +206,7 @@ ucnv_extMatchToU(const int32_t *cx, int8_t sisoState,
         } else {
             if(UCNV_EXT_TO_U_IS_PARTIAL(value)) {
                 /* partial match, continue */
-                idx=(int32_t)UCNV_EXT_TO_U_GET_PARTIAL_INDEX(value);
+                idx = static_cast<int32_t>(UCNV_EXT_TO_U_GET_PARTIAL_INDEX(value));
             } else {
                 if( (UCNV_EXT_TO_U_IS_ROUNDTRIP(value) ||
                      TO_U_USE_FALLBACK(useFallback)) &&
@@ -572,7 +572,7 @@ ucnv_extMatchFromU(const int32_t *cx,
 
     if(UCNV_EXT_TO_U_IS_PARTIAL(value)) {
         /* partial match, enter the loop below */
-        idx=(int32_t)UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value);
+        idx = static_cast<int32_t>(UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value));
 
         /* initialize */
         fromUTableUChars=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_UCHARS_INDEX, char16_t);
@@ -627,7 +627,7 @@ ucnv_extMatchFromU(const int32_t *cx,
                 value=fromUSectionValues[idx];
                 if(UCNV_EXT_FROM_U_IS_PARTIAL(value)) {
                     /* partial match, continue */
-                    idx=(int32_t)UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value);
+                    idx = static_cast<int32_t>(UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value));
                 } else {
                     if(extFromUUseMapping(useFallback, value, firstCP)) {
                         /* full match, stop with result */
@@ -679,7 +679,7 @@ ucnv_extWriteFromU(UConverter *cnv, const int32_t *cx,
     int32_t length, prevLength;
 
     length=UCNV_EXT_FROM_U_GET_LENGTH(value);
-    value=(uint32_t)UCNV_EXT_FROM_U_GET_DATA(value);
+    value = UCNV_EXT_FROM_U_GET_DATA(value);
 
     /* output the result */
     if(length<=UCNV_EXT_FROM_U_MAX_DIRECT_LENGTH) {
@@ -692,13 +692,13 @@ ucnv_extWriteFromU(UConverter *cnv, const int32_t *cx,
         uint8_t *p=buffer+1; /* reserve buffer[0] for shiftByte below */
         switch(length) {
         case 3:
-            *p++=(uint8_t)(value>>16);
+            *p++ = static_cast<uint8_t>(value >> 16);
             U_FALLTHROUGH;
         case 2:
-            *p++=(uint8_t)(value>>8);
+            *p++ = static_cast<uint8_t>(value >> 8);
             U_FALLTHROUGH;
         case 1:
-            *p++=(uint8_t)value;
+            *p++ = static_cast<uint8_t>(value);
             U_FALLTHROUGH;
         default:
             break; /* will never occur */
@@ -716,11 +716,11 @@ ucnv_extWriteFromU(UConverter *cnv, const int32_t *cx,
 
         if(prevLength>1 && length==1) {
             /* change from double-byte mode to single-byte */
-            shiftByte=(uint8_t)UCNV_SI;
+            shiftByte = static_cast<uint8_t>(UCNV_SI);
             cnv->fromUnicodeStatus=1;
         } else if(prevLength==1 && length>1) {
             /* change from single-byte mode to double-byte */
-            shiftByte=(uint8_t)UCNV_SO;
+            shiftByte = static_cast<uint8_t>(UCNV_SO);
             cnv->fromUnicodeStatus=2;
         } else {
             shiftByte=0;
@@ -737,7 +737,7 @@ ucnv_extWriteFromU(UConverter *cnv, const int32_t *cx,
         }
     }
 
-    ucnv_fromUWriteBytes(cnv, (const char *)result, length,
+    ucnv_fromUWriteBytes(cnv, reinterpret_cast<const char*>(result), length,
                          target, targetLimit,
                          offsets, srcIndex,
                          pErrorCode);
@@ -830,7 +830,7 @@ ucnv_extSimpleMatchFromU(const int32_t *cx,
 
         isRoundtrip=UCNV_EXT_FROM_U_IS_ROUNDTRIP(value);
         length=UCNV_EXT_FROM_U_GET_LENGTH(value);
-        value=(uint32_t)UCNV_EXT_FROM_U_GET_DATA(value);
+        value = UCNV_EXT_FROM_U_GET_DATA(value);
 
         if(length<=UCNV_EXT_FROM_U_MAX_DIRECT_LENGTH) {
             *pValue=value;
@@ -1018,7 +1018,7 @@ ucnv_extGetUnicodeSetString(const UConverterSharedData *sharedData,
             ucnv_extGetUnicodeSetString(
                 sharedData, cx, sa, which, minLength,
                 firstCP, s, length+1,
-                (int32_t)UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value),
+                static_cast<int32_t>(UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value)),
                 pErrorCode);
         } else if(extSetUseMapping(which, minLength, value)) {
             sa->addString(sa->set, s, length+1);

thirdparty/icu4c/common/ucnv_io.cpp

@@ -205,7 +205,7 @@ static UBool U_CALLCONV
 isAcceptable(void * /*context*/,
              const char * /*type*/, const char * /*name*/,
              const UDataInfo *pInfo) {
-    return (UBool)(
+    return
         pInfo->size>=20 &&
         pInfo->isBigEndian==U_IS_BIG_ENDIAN &&
         pInfo->charsetFamily==U_CHARSET_FAMILY &&
@@ -213,7 +213,7 @@ isAcceptable(void * /*context*/,
         pInfo->dataFormat[1]==0x76 &&
         pInfo->dataFormat[2]==0x41 &&
         pInfo->dataFormat[3]==0x6c &&
-        pInfo->formatVersion[0]==3);
+        pInfo->formatVersion[0]==3;
 }
 
 static UBool U_CALLCONV ucnv_io_cleanup()
@@ -244,8 +244,8 @@ static void U_CALLCONV initAliasData(UErrorCode &errCode) {
         return;
     }
 
-    sectionSizes = (const uint32_t *)udata_getMemory(data);
-    table = (const uint16_t *)sectionSizes;
+    sectionSizes = static_cast<const uint32_t*>(udata_getMemory(data));
+    table = reinterpret_cast<const uint16_t*>(sectionSizes);
 
     tableStart      = sectionSizes[0];
     if (tableStart < minTocLength) {
@@ -289,10 +289,10 @@ static void U_CALLCONV initAliasData(UErrorCode &errCode) {
 
     currOffset += gMainTable.taggedAliasListsSize;
     if (gMainTable.optionTableSize > 0
-        && ((const UConverterAliasOptions *)(table + currOffset))->stringNormalizationType < UCNV_IO_NORM_TYPE_COUNT)
+        && reinterpret_cast<const UConverterAliasOptions*>(table + currOffset)->stringNormalizationType < UCNV_IO_NORM_TYPE_COUNT)
     {
         /* Faster table */
-        gMainTable.optionTable = (const UConverterAliasOptions *)(table + currOffset);
+        gMainTable.optionTable = reinterpret_cast<const UConverterAliasOptions*>(table + currOffset);
     }
     else {
         /* Smaller table, or I can't handle this normalization mode!
@@ -321,7 +321,7 @@ isAlias(const char *alias, UErrorCode *pErrorCode) {
         *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
         return false;
     }
-    return (UBool)(*alias!=0);
+    return *alias != 0;
 }
 
 static uint32_t getTagNumber(const char *tagname) {
@@ -574,7 +574,7 @@ findConverter(const char *alias, UBool *containsOption, UErrorCode *pErrorCode)
     lastMid = UINT32_MAX;
 
     for (;;) {
-        mid = (uint32_t)((start + limit) / 2);
+        mid = (start + limit) / 2;
         if (lastMid == mid) {   /* Have we moved? */
             break;  /* We haven't moved, and it wasn't found. */
         }
@@ -601,8 +601,8 @@ findConverter(const char *alias, UBool *containsOption, UErrorCode *pErrorCode)
             /* State whether the canonical converter name contains an option.
             This information is contained in this list in order to maintain backward & forward compatibility. */
             if (containsOption) {
-                UBool containsCnvOptionInfo = (UBool)gMainTable.optionTable->containsCnvOptionInfo;
-                *containsOption = (UBool)((containsCnvOptionInfo
+                UBool containsCnvOptionInfo = static_cast<UBool>(gMainTable.optionTable->containsCnvOptionInfo);
+                *containsOption = static_cast<UBool>((containsCnvOptionInfo
                     && ((gMainTable.untaggedConvArray[mid] & UCNV_CONTAINS_OPTION_BIT) != 0))
                     || !containsCnvOptionInfo);
             }
@@ -939,7 +939,7 @@ static uint16_t
 ucnv_io_countStandards(UErrorCode *pErrorCode) {
     if (haveAliasData(pErrorCode)) {
         /* Don't include the empty list */
-        return (uint16_t)(gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS);
+        return static_cast<uint16_t>(gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS);
     }
 
     return 0;
@@ -1130,8 +1130,9 @@ io_compareRows(const void *context, const void *left, const void *right) {
     TempAliasTable *tempTable=(TempAliasTable *)context;
     const char *chars=tempTable->chars;
 
-    return (int32_t)uprv_strcmp(tempTable->stripForCompare(strippedLeft, chars+2*((const TempRow *)left)->strIndex),
-                                tempTable->stripForCompare(strippedRight, chars+2*((const TempRow *)right)->strIndex));
+    return static_cast<int32_t>(uprv_strcmp(
+        tempTable->stripForCompare(strippedLeft, chars + 2 * static_cast<const TempRow*>(left)->strIndex),
+        tempTable->stripForCompare(strippedRight, chars + 2 * static_cast<const TempRow*>(right)->strIndex)));
 }
 
 U_CAPI int32_t U_EXPORT2

thirdparty/icu4c/common/ucnv_lmb.cpp

@@ -633,7 +633,7 @@ _LMBCSOpenWorker(UConverter*  _this,
                  UErrorCode*  err,
                  ulmbcs_byte_t OptGroup)
 {
-    UConverterDataLMBCS * extraInfo = (UConverterDataLMBCS*)uprv_malloc (sizeof (UConverterDataLMBCS));
+    UConverterDataLMBCS* extraInfo = static_cast<UConverterDataLMBCS*>(uprv_malloc(sizeof(UConverterDataLMBCS)));
     _this->extraInfo = extraInfo;
     if(extraInfo != nullptr)
     {

thirdparty/icu4c/common/ucnv_u16.cpp

@@ -236,10 +236,10 @@ _UTF16BEFromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
         /* output length bytes with overflow (length>targetCapacity>0) */
         ucnv_fromUWriteBytes(cnv,
                              overflow, length,
-                             (char **)&target, pArgs->targetLimit,
+                             &target, pArgs->targetLimit,
                              &offsets, sourceIndex,
                              pErrorCode);
-        targetCapacity=(uint32_t)(pArgs->targetLimit-(char *)target);
+        targetCapacity = static_cast<uint32_t>(pArgs->targetLimit - target);
     }
 
     if(U_SUCCESS(*pErrorCode) && source<pArgs->sourceLimit && targetCapacity==0) {
@@ -248,7 +248,7 @@ _UTF16BEFromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
 
     /* write back the updated pointers */
     pArgs->source=source;
-    pArgs->target=(char *)target;
+    pArgs->target = target;
     pArgs->offsets=offsets;
 }
 
@@ -840,7 +840,7 @@ _UTF16LEFromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
                              &target, pArgs->targetLimit,
                              &offsets, sourceIndex,
                              pErrorCode);
-        targetCapacity=(uint32_t)(pArgs->targetLimit-(char *)target);
+        targetCapacity = static_cast<uint32_t>(pArgs->targetLimit - target);
     }
 
     if(U_SUCCESS(*pErrorCode) && source<pArgs->sourceLimit && targetCapacity==0) {

thirdparty/icu4c/common/ucnv_u8.cpp

@@ -49,8 +49,8 @@ U_CFUNC void ucnv_fromUnicode_UTF8_OFFSETS_LOGIC(UConverterFromUnicodeArgs *args
 #define MAXIMUM_UCS2            0x0000FFFF
 
 static const uint32_t offsetsFromUTF8[5] = {0,
-  (uint32_t) 0x00000000, (uint32_t) 0x00003080, (uint32_t) 0x000E2080,
-  (uint32_t) 0x03C82080
+  static_cast<uint32_t>(0x00000000), static_cast<uint32_t>(0x00003080),
+  static_cast<uint32_t>(0x000E2080), static_cast<uint32_t>(0x03C82080)
 };
 
 static UBool hasCESU8Data(const UConverter *cnv)
@@ -58,7 +58,7 @@ static UBool hasCESU8Data(const UConverter *cnv)
 #if UCONFIG_ONLY_HTML_CONVERSION
     return false;
 #else
-    return (UBool)(cnv->sharedData == &_CESU8Data);
+    return cnv->sharedData == &_CESU8Data;
 #endif
 }
 U_CDECL_BEGIN
@@ -571,7 +571,7 @@ static UChar32 U_CALLCONV ucnv_getNextUChar_UTF8(UConverterToUnicodeArgs *args,
         return 0xffff;
     }
 
-    myByte = (uint8_t)*(source++);
+    myByte = *(source++);
     if (U8_IS_SINGLE(myByte))
     {
         args->source = (const char *)source;

thirdparty/icu4c/common/ucnvbocu.cpp

@@ -338,7 +338,7 @@ packDiff(int32_t diff) {
              */
             result|=BOCU1_TRAIL_TO_BYTE(diff)<<16;
 
-            result|=((uint32_t)BOCU1_START_POS_4)<<24;
+            result |= static_cast<uint32_t>(BOCU1_START_POS_4) << 24;
         }
     } else {
         /* two- to four-byte negative differences */
@@ -405,13 +405,13 @@ _Bocu1FromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
     cnv=pArgs->converter;
     source=pArgs->source;
     sourceLimit=pArgs->sourceLimit;
-    target=(uint8_t *)pArgs->target;
-    targetCapacity=(int32_t)(pArgs->targetLimit-pArgs->target);
+    target = reinterpret_cast<uint8_t*>(pArgs->target);
+    targetCapacity = static_cast<int32_t>(pArgs->targetLimit - pArgs->target);
     offsets=pArgs->offsets;
 
     /* get the converter state from UConverter */
     c=cnv->fromUChar32;
-    prev=(int32_t)cnv->fromUnicodeStatus;
+    prev = static_cast<int32_t>(cnv->fromUnicodeStatus);
     if(prev==0) {
         prev=BOCU1_ASCII_PREV;
     }
@@ -428,7 +428,7 @@ _Bocu1FromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
 fastSingle:
     /* fast loop for single-byte differences */
     /* use only one loop counter variable, targetCapacity, not also source */
-    diff=(int32_t)(sourceLimit-source);
+    diff = static_cast<int32_t>(sourceLimit - source);
     if(targetCapacity>diff) {
         targetCapacity=diff;
     }
@@ -437,7 +437,7 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(uint8_t)c;
+            *target++ = static_cast<uint8_t>(c);
             *offsets++=nextSourceIndex++;
             ++source;
             --targetCapacity;
@@ -445,7 +445,7 @@ fastSingle:
             diff=c-prev;
             if(DIFF_IS_SINGLE(diff)) {
                 prev=BOCU1_SIMPLE_PREV(c);
-                *target++=(uint8_t)PACK_SINGLE_DIFF(diff);
+                *target++ = static_cast<uint8_t>(PACK_SINGLE_DIFF(diff));
                 *offsets++=nextSourceIndex++;
                 ++source;
                 --targetCapacity;
@@ -455,7 +455,7 @@ fastSingle:
         }
     }
     /* restore real values */
-    targetCapacity=(int32_t)((const uint8_t *)pArgs->targetLimit-target);
+    targetCapacity = static_cast<int32_t>(reinterpret_cast<const uint8_t*>(pArgs->targetLimit) - target);
     sourceIndex=nextSourceIndex; /* wrong if offsets==nullptr but does not matter */
 
     /* regular loop for all cases */
@@ -473,7 +473,7 @@ fastSingle:
                 if(c!=0x20) {
                     prev=BOCU1_ASCII_PREV;
                 }
-                *target++=(uint8_t)c;
+                *target++ = static_cast<uint8_t>(c);
                 *offsets++=sourceIndex;
                 --targetCapacity;
 
@@ -510,7 +510,7 @@ getTrail:
             diff=c-prev;
             prev=BOCU1_PREV(c);
             if(DIFF_IS_SINGLE(diff)) {
-                *target++=(uint8_t)PACK_SINGLE_DIFF(diff);
+                *target++ = static_cast<uint8_t>(PACK_SINGLE_DIFF(diff));
                 *offsets++=sourceIndex;
                 --targetCapacity;
                 sourceIndex=nextSourceIndex;
@@ -531,8 +531,8 @@ getTrail:
                     NEGDIVMOD(diff, BOCU1_TRAIL_COUNT, m);
                     diff+=BOCU1_START_NEG_2;
                 }
-                *target++=(uint8_t)diff;
-                *target++=(uint8_t)BOCU1_TRAIL_TO_BYTE(m);
+                *target++ = static_cast<uint8_t>(diff);
+                *target++ = static_cast<uint8_t>(BOCU1_TRAIL_TO_BYTE(m));
                 *offsets++=sourceIndex;
                 *offsets++=sourceIndex;
                 targetCapacity-=2;
@@ -549,18 +549,18 @@ getTrail:
                     switch(length) {
                         /* each branch falls through to the next one */
                     case 4:
-                        *target++=(uint8_t)(diff>>24);
+                        *target++ = static_cast<uint8_t>(diff >> 24);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     case 3:
-                        *target++=(uint8_t)(diff>>16);
+                        *target++ = static_cast<uint8_t>(diff >> 16);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     case 2:
-                        *target++=(uint8_t)(diff>>8);
+                        *target++ = static_cast<uint8_t>(diff >> 8);
                         *offsets++=sourceIndex;
                     /* case 1: handled above */
-                        *target++=(uint8_t)diff;
+                        *target++ = static_cast<uint8_t>(diff);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     default:
@@ -584,34 +584,34 @@ getTrail:
                     switch(length) {
                         /* each branch falls through to the next one */
                     case 3:
-                        *charErrorBuffer++=(uint8_t)(diff>>16);
+                        *charErrorBuffer++ = static_cast<uint8_t>(diff >> 16);
                         U_FALLTHROUGH;
                     case 2:
-                        *charErrorBuffer++=(uint8_t)(diff>>8);
+                        *charErrorBuffer++ = static_cast<uint8_t>(diff >> 8);
                         U_FALLTHROUGH;
                     case 1:
-                        *charErrorBuffer=(uint8_t)diff;
+                        *charErrorBuffer = static_cast<uint8_t>(diff);
                         U_FALLTHROUGH;
                     default:
                         /* will never occur */
                         break;
                     }
-                    cnv->charErrorBufferLength=(int8_t)length;
+                    cnv->charErrorBufferLength = static_cast<int8_t>(length);
 
                     /* now output what fits into the regular target */
                     diff>>=8*length; /* length was reduced by targetCapacity */
                     switch(targetCapacity) {
                         /* each branch falls through to the next one */
                     case 3:
-                        *target++=(uint8_t)(diff>>16);
+                        *target++ = static_cast<uint8_t>(diff >> 16);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     case 2:
-                        *target++=(uint8_t)(diff>>8);
+                        *target++ = static_cast<uint8_t>(diff >> 8);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     case 1:
-                        *target++=(uint8_t)diff;
+                        *target++ = static_cast<uint8_t>(diff);
                         *offsets++=sourceIndex;
                         U_FALLTHROUGH;
                     default:
@@ -634,11 +634,11 @@ getTrail:
 
     /* set the converter state back into UConverter */
     cnv->fromUChar32= c<0 ? -c : 0;
-    cnv->fromUnicodeStatus=(uint32_t)prev;
+    cnv->fromUnicodeStatus = static_cast<uint32_t>(prev);
 
     /* write back the updated pointers */
     pArgs->source=source;
-    pArgs->target=(char *)target;
+    pArgs->target = reinterpret_cast<char*>(target);
     pArgs->offsets=offsets;
 }
 
@@ -663,12 +663,12 @@ _Bocu1FromUnicode(UConverterFromUnicodeArgs *pArgs,
     cnv=pArgs->converter;
     source=pArgs->source;
     sourceLimit=pArgs->sourceLimit;
-    target=(uint8_t *)pArgs->target;
-    targetCapacity=(int32_t)(pArgs->targetLimit-pArgs->target);
+    target = reinterpret_cast<uint8_t*>(pArgs->target);
+    targetCapacity = static_cast<int32_t>(pArgs->targetLimit - pArgs->target);
 
     /* get the converter state from UConverter */
     c=cnv->fromUChar32;
-    prev=(int32_t)cnv->fromUnicodeStatus;
+    prev = static_cast<int32_t>(cnv->fromUnicodeStatus);
     if(prev==0) {
         prev=BOCU1_ASCII_PREV;
     }
@@ -681,7 +681,7 @@ _Bocu1FromUnicode(UConverterFromUnicodeArgs *pArgs,
 fastSingle:
     /* fast loop for single-byte differences */
     /* use only one loop counter variable, targetCapacity, not also source */
-    diff=(int32_t)(sourceLimit-source);
+    diff = static_cast<int32_t>(sourceLimit - source);
     if(targetCapacity>diff) {
         targetCapacity=diff;
     }
@@ -690,12 +690,12 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(uint8_t)c;
+            *target++ = static_cast<uint8_t>(c);
         } else {
             diff=c-prev;
             if(DIFF_IS_SINGLE(diff)) {
                 prev=BOCU1_SIMPLE_PREV(c);
-                *target++=(uint8_t)PACK_SINGLE_DIFF(diff);
+                *target++ = static_cast<uint8_t>(PACK_SINGLE_DIFF(diff));
             } else {
                 break;
             }
@@ -704,7 +704,7 @@ fastSingle:
         --targetCapacity;
     }
     /* restore real values */
-    targetCapacity=(int32_t)((const uint8_t *)pArgs->targetLimit-target);
+    targetCapacity = static_cast<int32_t>(reinterpret_cast<const uint8_t*>(pArgs->targetLimit) - target);
 
     /* regular loop for all cases */
     while(source<sourceLimit) {
@@ -720,7 +720,7 @@ fastSingle:
                 if(c!=0x20) {
                     prev=BOCU1_ASCII_PREV;
                 }
-                *target++=(uint8_t)c;
+                *target++ = static_cast<uint8_t>(c);
                 --targetCapacity;
                 continue;
             }
@@ -753,7 +753,7 @@ getTrail:
             diff=c-prev;
             prev=BOCU1_PREV(c);
             if(DIFF_IS_SINGLE(diff)) {
-                *target++=(uint8_t)PACK_SINGLE_DIFF(diff);
+                *target++ = static_cast<uint8_t>(PACK_SINGLE_DIFF(diff));
                 --targetCapacity;
                 if(c<0x3000) {
                     goto fastSingle;
@@ -772,8 +772,8 @@ getTrail:
                     NEGDIVMOD(diff, BOCU1_TRAIL_COUNT, m);
                     diff+=BOCU1_START_NEG_2;
                 }
-                *target++=(uint8_t)diff;
-                *target++=(uint8_t)BOCU1_TRAIL_TO_BYTE(m);
+                *target++ = static_cast<uint8_t>(diff);
+                *target++ = static_cast<uint8_t>(BOCU1_TRAIL_TO_BYTE(m));
                 targetCapacity-=2;
             } else {
                 int32_t length; /* will be 2..4 */
@@ -787,14 +787,14 @@ getTrail:
                     switch(length) {
                         /* each branch falls through to the next one */
                     case 4:
-                        *target++=(uint8_t)(diff>>24);
+                        *target++ = static_cast<uint8_t>(diff >> 24);
                         U_FALLTHROUGH;
                     case 3:
-                        *target++=(uint8_t)(diff>>16);
+                        *target++ = static_cast<uint8_t>(diff >> 16);
                     /* case 2: handled above */
-                        *target++=(uint8_t)(diff>>8);
+                        *target++ = static_cast<uint8_t>(diff >> 8);
                     /* case 1: handled above */
-                        *target++=(uint8_t)diff;
+                        *target++ = static_cast<uint8_t>(diff);
                         U_FALLTHROUGH;
                     default:
                         /* will never occur */
@@ -816,32 +816,32 @@ getTrail:
                     switch(length) {
                         /* each branch falls through to the next one */
                     case 3:
-                        *charErrorBuffer++=(uint8_t)(diff>>16);
+                        *charErrorBuffer++ = static_cast<uint8_t>(diff >> 16);
                         U_FALLTHROUGH;
                     case 2:
-                        *charErrorBuffer++=(uint8_t)(diff>>8);
+                        *charErrorBuffer++ = static_cast<uint8_t>(diff >> 8);
                         U_FALLTHROUGH;
                     case 1:
-                        *charErrorBuffer=(uint8_t)diff;
+                        *charErrorBuffer = static_cast<uint8_t>(diff);
                         U_FALLTHROUGH;
                     default:
                         /* will never occur */
                         break;
                     }
-                    cnv->charErrorBufferLength=(int8_t)length;
+                    cnv->charErrorBufferLength = static_cast<int8_t>(length);
 
                     /* now output what fits into the regular target */
                     diff>>=8*length; /* length was reduced by targetCapacity */
                     switch(targetCapacity) {
                         /* each branch falls through to the next one */
                     case 3:
-                        *target++=(uint8_t)(diff>>16);
+                        *target++ = static_cast<uint8_t>(diff >> 16);
                         U_FALLTHROUGH;
                     case 2:
-                        *target++=(uint8_t)(diff>>8);
+                        *target++ = static_cast<uint8_t>(diff >> 8);
                         U_FALLTHROUGH;
                     case 1:
-                        *target++=(uint8_t)diff;
+                        *target++ = static_cast<uint8_t>(diff);
                         U_FALLTHROUGH;
                     default:
                         /* will never occur */
@@ -863,11 +863,11 @@ getTrail:
 
     /* set the converter state back into UConverter */
     cnv->fromUChar32= c<0 ? -c : 0;
-    cnv->fromUnicodeStatus=(uint32_t)prev;
+    cnv->fromUnicodeStatus = static_cast<uint32_t>(prev);
 
     /* write back the updated pointers */
     pArgs->source=source;
-    pArgs->target=(char *)target;
+    pArgs->target = reinterpret_cast<char*>(target);
 }
 
 /* BOCU-1-to-Unicode conversion functions ----------------------------------- */
@@ -887,11 +887,11 @@ decodeBocu1LeadByte(int32_t b) {
         /* positive difference */
         if(b<BOCU1_START_POS_3) {
             /* two bytes */
-            diff=((int32_t)b-BOCU1_START_POS_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_POS_1+1;
+            diff = (b - BOCU1_START_POS_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_POS_1 + 1;
             count=1;
         } else if(b<BOCU1_START_POS_4) {
             /* three bytes */
-            diff=((int32_t)b-BOCU1_START_POS_3)*BOCU1_TRAIL_COUNT*BOCU1_TRAIL_COUNT+BOCU1_REACH_POS_2+1;
+            diff = (b - BOCU1_START_POS_3) * BOCU1_TRAIL_COUNT * BOCU1_TRAIL_COUNT + BOCU1_REACH_POS_2 + 1;
             count=2;
         } else {
             /* four bytes */
@@ -902,11 +902,11 @@ decodeBocu1LeadByte(int32_t b) {
         /* negative difference */
         if(b>=BOCU1_START_NEG_3) {
             /* two bytes */
-            diff=((int32_t)b-BOCU1_START_NEG_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_NEG_1;
+            diff = (b - BOCU1_START_NEG_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_NEG_1;
             count=1;
         } else if(b>BOCU1_MIN) {
             /* three bytes */
-            diff=((int32_t)b-BOCU1_START_NEG_3)*BOCU1_TRAIL_COUNT*BOCU1_TRAIL_COUNT+BOCU1_REACH_NEG_2;
+            diff = (b - BOCU1_START_NEG_3) * BOCU1_TRAIL_COUNT * BOCU1_TRAIL_COUNT + BOCU1_REACH_NEG_2;
             count=2;
         } else {
             /* four bytes */
@@ -916,7 +916,7 @@ decodeBocu1LeadByte(int32_t b) {
     }
 
     /* return the state for decoding the trail byte(s) */
-    return ((uint32_t)diff<<2)|count;
+    return (static_cast<uint32_t>(diff) << 2) | count;
 }
 
 /**
@@ -970,14 +970,14 @@ _Bocu1ToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
 
     /* set up the local pointers */
     cnv=pArgs->converter;
-    source=(const uint8_t *)pArgs->source;
-    sourceLimit=(const uint8_t *)pArgs->sourceLimit;
+    source = reinterpret_cast<const uint8_t*>(pArgs->source);
+    sourceLimit = reinterpret_cast<const uint8_t*>(pArgs->sourceLimit);
     target=pArgs->target;
     targetLimit=pArgs->targetLimit;
     offsets=pArgs->offsets;
 
     /* get the converter state from UConverter */
-    prev=(int32_t)cnv->toUnicodeStatus;
+    prev = static_cast<int32_t>(cnv->toUnicodeStatus);
     if(prev==0) {
         prev=BOCU1_ASCII_PREV;
     }
@@ -1000,8 +1000,8 @@ _Bocu1ToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
 fastSingle:
     /* fast loop for single-byte differences */
     /* use count as the only loop counter variable */
-    diff=(int32_t)(sourceLimit-source);
-    count=(int32_t)(pArgs->targetLimit-target);
+    diff = static_cast<int32_t>(sourceLimit - source);
+    count = static_cast<int32_t>(pArgs->targetLimit - target);
     if(count>diff) {
         count=diff;
     }
@@ -1009,7 +1009,7 @@ fastSingle:
         if(BOCU1_START_NEG_2<=(c=*source) && c<BOCU1_START_POS_2) {
             c=prev+(c-BOCU1_MIDDLE);
             if(c<0x3000) {
-                *target++=(char16_t)c;
+                *target++ = static_cast<char16_t>(c);
                 *offsets++=nextSourceIndex++;
                 prev=BOCU1_SIMPLE_PREV(c);
             } else {
@@ -1019,7 +1019,7 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
             *offsets++=nextSourceIndex++;
         } else {
             break;
@@ -1043,7 +1043,7 @@ fastSingle:
             /* Write a code point directly from a single-byte difference. */
             c=prev+(c-BOCU1_MIDDLE);
             if(c<0x3000) {
-                *target++=(char16_t)c;
+                *target++ = static_cast<char16_t>(c);
                 *offsets++=sourceIndex;
                 prev=BOCU1_SIMPLE_PREV(c);
                 sourceIndex=nextSourceIndex;
@@ -1057,22 +1057,22 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
             *offsets++=sourceIndex;
             sourceIndex=nextSourceIndex;
             continue;
         } else if(BOCU1_START_NEG_3<=c && c<BOCU1_START_POS_3 && source<sourceLimit) {
             /* Optimize two-byte case. */
             if(c>=BOCU1_MIDDLE) {
-                diff=((int32_t)c-BOCU1_START_POS_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_POS_1+1;
+                diff = (c - BOCU1_START_POS_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_POS_1 + 1;
             } else {
-                diff=((int32_t)c-BOCU1_START_NEG_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_NEG_1;
+                diff = (c - BOCU1_START_NEG_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_NEG_1;
             }
 
             /* trail byte */
             ++nextSourceIndex;
             c=decodeBocu1TrailByte(1, *source++);
-            if(c<0 || (uint32_t)(c=prev+diff+c)>0x10ffff) {
+            if (c < 0 || static_cast<uint32_t>(c = prev + diff + c) > 0x10ffff) {
                 bytes[0]=source[-2];
                 bytes[1]=source[-1];
                 byteIndex=2;
@@ -1090,7 +1090,7 @@ fastSingle:
              * with the partial difference value from the lead byte and
              * with the number of trail bytes.
              */
-            bytes[0]=(uint8_t)c;
+            bytes[0] = static_cast<uint8_t>(c);
             byteIndex=1;
 
             diff=decodeBocu1LeadByte(c);
@@ -1116,7 +1116,7 @@ getTrail:
                     /* final trail byte, deliver a code point */
                     byteIndex=0;
                     c=prev+diff;
-                    if((uint32_t)c>0x10ffff) {
+                    if (static_cast<uint32_t>(c) > 0x10ffff) {
                         *pErrorCode=U_ILLEGAL_CHAR_FOUND;
                         goto endloop;
                     }
@@ -1128,7 +1128,7 @@ getTrail:
         /* calculate the next prev and output c */
         prev=BOCU1_PREV(c);
         if(c<=0xffff) {
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
             *offsets++=sourceIndex;
         } else {
             /* output surrogate pair */
@@ -1156,13 +1156,13 @@ endloop:
         cnv->mode=0;
     } else {
         /* set the converter state back into UConverter */
-        cnv->toUnicodeStatus=(uint32_t)prev;
-        cnv->mode=(int32_t)((uint32_t)diff<<2)|count;
+        cnv->toUnicodeStatus = static_cast<uint32_t>(prev);
+        cnv->mode = static_cast<int32_t>(static_cast<uint32_t>(diff) << 2) | count;
     }
     cnv->toULength=byteIndex;
 
     /* write back the updated pointers */
-    pArgs->source=(const char *)source;
+    pArgs->source = reinterpret_cast<const char*>(source);
     pArgs->target=target;
     pArgs->offsets=offsets;
 }
@@ -1189,13 +1189,13 @@ _Bocu1ToUnicode(UConverterToUnicodeArgs *pArgs,
 
     /* set up the local pointers */
     cnv=pArgs->converter;
-    source=(const uint8_t *)pArgs->source;
-    sourceLimit=(const uint8_t *)pArgs->sourceLimit;
+    source = reinterpret_cast<const uint8_t*>(pArgs->source);
+    sourceLimit = reinterpret_cast<const uint8_t*>(pArgs->sourceLimit);
     target=pArgs->target;
     targetLimit=pArgs->targetLimit;
 
     /* get the converter state from UConverter */
-    prev=(int32_t)cnv->toUnicodeStatus;
+    prev = static_cast<int32_t>(cnv->toUnicodeStatus);
     if(prev==0) {
         prev=BOCU1_ASCII_PREV;
     }
@@ -1214,8 +1214,8 @@ _Bocu1ToUnicode(UConverterToUnicodeArgs *pArgs,
 fastSingle:
     /* fast loop for single-byte differences */
     /* use count as the only loop counter variable */
-    diff=(int32_t)(sourceLimit-source);
-    count=(int32_t)(pArgs->targetLimit-target);
+    diff = static_cast<int32_t>(sourceLimit - source);
+    count = static_cast<int32_t>(pArgs->targetLimit - target);
     if(count>diff) {
         count=diff;
     }
@@ -1223,7 +1223,7 @@ fastSingle:
         if(BOCU1_START_NEG_2<=(c=*source) && c<BOCU1_START_POS_2) {
             c=prev+(c-BOCU1_MIDDLE);
             if(c<0x3000) {
-                *target++=(char16_t)c;
+                *target++ = static_cast<char16_t>(c);
                 prev=BOCU1_SIMPLE_PREV(c);
             } else {
                 break;
@@ -1232,7 +1232,7 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
         } else {
             break;
         }
@@ -1253,7 +1253,7 @@ fastSingle:
             /* Write a code point directly from a single-byte difference. */
             c=prev+(c-BOCU1_MIDDLE);
             if(c<0x3000) {
-                *target++=(char16_t)c;
+                *target++ = static_cast<char16_t>(c);
                 prev=BOCU1_SIMPLE_PREV(c);
                 goto fastSingle;
             }
@@ -1265,19 +1265,19 @@ fastSingle:
             if(c!=0x20) {
                 prev=BOCU1_ASCII_PREV;
             }
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
             continue;
         } else if(BOCU1_START_NEG_3<=c && c<BOCU1_START_POS_3 && source<sourceLimit) {
             /* Optimize two-byte case. */
             if(c>=BOCU1_MIDDLE) {
-                diff=((int32_t)c-BOCU1_START_POS_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_POS_1+1;
+                diff = (c - BOCU1_START_POS_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_POS_1 + 1;
             } else {
-                diff=((int32_t)c-BOCU1_START_NEG_2)*BOCU1_TRAIL_COUNT+BOCU1_REACH_NEG_1;
+                diff = (c - BOCU1_START_NEG_2) * BOCU1_TRAIL_COUNT + BOCU1_REACH_NEG_1;
             }
 
             /* trail byte */
             c=decodeBocu1TrailByte(1, *source++);
-            if(c<0 || (uint32_t)(c=prev+diff+c)>0x10ffff) {
+            if (c < 0 || static_cast<uint32_t>(c = prev + diff + c) > 0x10ffff) {
                 bytes[0]=source[-2];
                 bytes[1]=source[-1];
                 byteIndex=2;
@@ -1294,7 +1294,7 @@ fastSingle:
              * with the partial difference value from the lead byte and
              * with the number of trail bytes.
              */
-            bytes[0]=(uint8_t)c;
+            bytes[0] = static_cast<uint8_t>(c);
             byteIndex=1;
 
             diff=decodeBocu1LeadByte(c);
@@ -1319,7 +1319,7 @@ getTrail:
                     /* final trail byte, deliver a code point */
                     byteIndex=0;
                     c=prev+diff;
-                    if((uint32_t)c>0x10ffff) {
+                    if (static_cast<uint32_t>(c) > 0x10ffff) {
                         *pErrorCode=U_ILLEGAL_CHAR_FOUND;
                         goto endloop;
                     }
@@ -1331,7 +1331,7 @@ getTrail:
         /* calculate the next prev and output c */
         prev=BOCU1_PREV(c);
         if(c<=0xffff) {
-            *target++=(char16_t)c;
+            *target++ = static_cast<char16_t>(c);
         } else {
             /* output surrogate pair */
             *target++=U16_LEAD(c);
@@ -1354,13 +1354,13 @@ endloop:
         cnv->mode=0;
     } else {
         /* set the converter state back into UConverter */
-        cnv->toUnicodeStatus=(uint32_t)prev;
-        cnv->mode=((uint32_t)diff<<2)|count;
+        cnv->toUnicodeStatus = static_cast<uint32_t>(prev);
+        cnv->mode = (static_cast<uint32_t>(diff) << 2) | count;
     }
     cnv->toULength=byteIndex;
 
     /* write back the updated pointers */
-    pArgs->source=(const char *)source;
+    pArgs->source = reinterpret_cast<const char*>(source);
     pArgs->target=target;
 }
 

thirdparty/icu4c/common/ucnvhz.cpp

@@ -345,7 +345,7 @@ UConverter_fromUnicode_HZ_OFFSETS_LOGIC (UConverterFromUnicodeArgs * args,
     uint32_t targetUniChar = 0x0000;
     UChar32 mySourceChar = 0x0000;
     UConverterDataHZ *myConverterData=(UConverterDataHZ*)args->converter->extraInfo;
-    UBool isTargetUCharDBCS = (UBool) myConverterData->isTargetUCharDBCS;
+    UBool isTargetUCharDBCS = myConverterData->isTargetUCharDBCS;
     UBool oldIsTargetUCharDBCS;
     int len =0;
     const char* escSeq=nullptr;
@@ -363,7 +363,7 @@ UConverter_fromUnicode_HZ_OFFSETS_LOGIC (UConverterFromUnicodeArgs * args,
         targetUniChar = missingCharMarker;
         if (myTargetIndex < targetLength){
             
-            mySourceChar = (char16_t) mySource[mySourceIndex++];
+            mySourceChar = mySource[mySourceIndex++];
             
 
             oldIsTargetUCharDBCS = isTargetUCharDBCS;
@@ -389,7 +389,7 @@ UConverter_fromUnicode_HZ_OFFSETS_LOGIC (UConverterFromUnicodeArgs * args,
                 }
             }
             if (targetUniChar != missingCharMarker){
-               myConverterData->isTargetUCharDBCS = isTargetUCharDBCS = (UBool)(targetUniChar>0x00FF);     
+               myConverterData->isTargetUCharDBCS = isTargetUCharDBCS = targetUniChar > 0x00FF;
                  if(oldIsTargetUCharDBCS != isTargetUCharDBCS || !myConverterData->isEscapeAppended ){
                     /*Shifting from a double byte to single byte mode*/
                     if(!isTargetUCharDBCS){

thirdparty/icu4c/common/ucnvisci.cpp

@@ -174,7 +174,7 @@ isPNJConsonant(UChar32 c) {
     if (c < 0xa00 || 0xa50 <= c) {
         return false;
     } else {
-        return (UBool)(pnjMap[c - 0xa00] & 1);
+        return pnjMap[c - 0xa00] & 1;
     }
 }
 
@@ -183,7 +183,7 @@ isPNJBindiTippi(UChar32 c) {
     if (c < 0xa00 || 0xa50 <= c) {
         return false;
     } else {
-        return (UBool)(pnjMap[c - 0xa00] >> 1);
+        return pnjMap[c - 0xa00] >> 1;
     }
 }
 U_CDECL_BEGIN
@@ -1484,7 +1484,7 @@ UConverter_toUnicode_ISCII_OFFSETS_LOGIC(UConverterToUnicodeArgs *args, UErrorCo
                  */
                 *err = U_INVALID_CHAR_FOUND;
 CALLBACK:
-                args->converter->toUBytes[0] = (uint8_t) sourceChar;
+                args->converter->toUBytes[0] = sourceChar;
                 args->converter->toULength = 1;
                 break;
             }

thirdparty/icu4c/common/ucnvlat1.cpp

@@ -381,7 +381,7 @@ ucnv_Latin1FromUTF8(UConverterFromUnicodeArgs *pFromUArgs,
             b=*source++;
             if(U8_IS_SINGLE(b)) {
                 /* convert ASCII */
-                *target++=(uint8_t)b;
+                *target++ = b;
                 --targetCapacity;
             } else if( /* handle U+0080..U+00FF inline */
                        b>=0xc2 && b<=0xc3 &&

thirdparty/icu4c/common/ucnvscsu.cpp

@@ -883,8 +883,8 @@ static int8_t
 getWindow(const uint32_t offsets[8], uint32_t c) {
     int i;
     for(i=0; i<8; ++i) {
-        if((uint32_t)(c-offsets[i])<=0x7f) {
-            return (int8_t)(i);
+        if (c - offsets[i] <= 0x7f) {
+            return static_cast<int8_t>(i);
         }
     }
     return -1;
@@ -893,9 +893,9 @@ getWindow(const uint32_t offsets[8], uint32_t c) {
 /* is the character in the dynamic window starting at the offset, or in the direct-encoded range? */
 static UBool
 isInOffsetWindowOrDirect(uint32_t offset, uint32_t c) {
-    return (UBool)(c<=offset+0x7f &&
+    return c<=offset+0x7f &&
           (c>=offset || (c<=0x7f &&
-                        (c>=0x20 || (1UL<<c)&0x2601))));
+                        (c>=0x20 || (1UL<<c)&0x2601)));
                                 /* binary 0010 0110 0000 0001,
                                    check for b==0xd || b==0xa || b==9 || b==0 */
 }
@@ -963,7 +963,7 @@ getDynamicOffset(uint32_t c, uint32_t *pOffset) {
     int i;
 
     for(i=0; i<7; ++i) {
-        if((uint32_t)(c-fixedOffsets[i])<=0x7f) {
+        if (c - fixedOffsets[i] <= 0x7f) {
             *pOffset=fixedOffsets[i];
             return 0xf9+i;
         }
@@ -973,16 +973,16 @@ getDynamicOffset(uint32_t c, uint32_t *pOffset) {
         /* No dynamic window for US-ASCII. */
         return -1;
     } else if(c<0x3400 ||
-              (uint32_t)(c-0x10000)<(0x14000-0x10000) ||
-              (uint32_t)(c-0x1d000)<=(0x1ffff-0x1d000)
+              c - 0x10000 < 0x14000 - 0x10000 ||
+              c - 0x1d000 <= 0x1ffff - 0x1d000
     ) {
         /* This character is in a code range for a "small", i.e., reasonably windowable, script. */
         *pOffset=c&0x7fffff80;
-        return (int)(c>>7);
+        return static_cast<int>(c >> 7);
     } else if(0xe000<=c && c!=0xfeff && c<0xfff0) {
         /* For these characters we need to take the gapOffset into account. */
         *pOffset=c&0x7fffff80;
-        return (int)((c-gapOffset)>>7);
+        return static_cast<int>((c - gapOffset) >> 7);
     } else {
         return -1;
     }
@@ -1208,8 +1208,8 @@ getTrailSingle:
                     c=((uint32_t)(SD0+dynamicWindow)<<16)|((uint32_t)code<<8)|(c-currentOffset)|0x80;
                     length=3;
                     goto outputBytes;
-                } else if((uint32_t)(c-0x3400)<(0xd800-0x3400) &&
-                          (source>=sourceLimit || (uint32_t)(*source-0x3400)<(0xd800-0x3400))
+                } else if ((c - 0x3400) < (0xd800 - 0x3400) &&
+                           (source >= sourceLimit || (uint32_t)(*source - 0x3400) < (0xd800 - 0x3400))
                 ) {
                     /*
                      * this character is not compressible (a BMP ideograph or similar);
@@ -1248,7 +1248,7 @@ getTrailSingle:
             c=*source++;
             ++nextSourceIndex;
 
-            if((uint32_t)(c-0x3400)<(0xd800-0x3400)) {
+            if ((c - 0x3400) < (0xd800 - 0x3400)) {
                 /* not compressible, write character directly */
                 if(targetCapacity>=2) {
                     *target++=(uint8_t)(c>>8);
@@ -1262,10 +1262,10 @@ getTrailSingle:
                     length=2;
                     goto outputBytes;
                 }
-            } else if((uint32_t)(c-0x3400)>=(0xf300-0x3400) /* c<0x3400 || c>=0xf300 */) {
+            } else if (c - 0x3400 >= 0xf300 - 0x3400 /* c<0x3400 || c>=0xf300 */) {
                 /* compress BMP character if the following one is not an uncompressible ideograph */
                 if(!(source<sourceLimit && (uint32_t)(*source-0x3400)<(0xd800-0x3400))) {
-                    if(((uint32_t)(c-0x30)<10 || (uint32_t)(c-0x61)<26 || (uint32_t)(c-0x41)<26)) {
+                    if (c - 0x30 < 10 || c - 0x61 < 26 || c - 0x41 < 26) {
                         /* ASCII digit or letter */
                         isSingleByteMode=true;
                         c|=((uint32_t)(UC0+dynamicWindow)<<8)|c;
@@ -1691,8 +1691,8 @@ getTrailSingle:
                     c=((uint32_t)(SD0+dynamicWindow)<<16)|((uint32_t)code<<8)|(c-currentOffset)|0x80;
                     length=3;
                     goto outputBytes;
-                } else if((uint32_t)(c-0x3400)<(0xd800-0x3400) &&
-                          (source>=sourceLimit || (uint32_t)(*source-0x3400)<(0xd800-0x3400))
+                } else if (c - 0x3400 < 0xd800 - 0x3400 &&
+                           (source >= sourceLimit || static_cast<uint32_t>(*source - 0x3400) < 0xd800 - 0x3400)
                 ) {
                     /*
                      * this character is not compressible (a BMP ideograph or similar);
@@ -1729,7 +1729,7 @@ getTrailSingle:
             }
             c=*source++;
 
-            if((uint32_t)(c-0x3400)<(0xd800-0x3400)) {
+            if (c - 0x3400 < 0xd800 - 0x3400) {
                 /* not compressible, write character directly */
                 if(targetCapacity>=2) {
                     *target++=(uint8_t)(c>>8);
@@ -1739,10 +1739,10 @@ getTrailSingle:
                     length=2;
                     goto outputBytes;
                 }
-            } else if((uint32_t)(c-0x3400)>=(0xf300-0x3400) /* c<0x3400 || c>=0xf300 */) {
+            } else if (c - 0x3400 >= 0xf300 - 0x3400 /* c<0x3400 || c>=0xf300 */) {
                 /* compress BMP character if the following one is not an uncompressible ideograph */
                 if(!(source<sourceLimit && (uint32_t)(*source-0x3400)<(0xd800-0x3400))) {
-                    if(((uint32_t)(c-0x30)<10 || (uint32_t)(c-0x61)<26 || (uint32_t)(c-0x41)<26)) {
+                    if (c - 0x30 < 10 || c - 0x61 < 26 || c - 0x41 < 26) {
                         /* ASCII digit or letter */
                         isSingleByteMode=true;
                         c|=((uint32_t)(UC0+dynamicWindow)<<8)|c;

thirdparty/icu4c/common/ucnvsel.cpp

@@ -377,7 +377,7 @@ ucnvsel_swap(const UDataSwapper *ds,
   }
 
   /* check data format and format version */
-  const UDataInfo *pInfo = (const UDataInfo *)((const char *)inData + 4);
+  const UDataInfo* pInfo = reinterpret_cast<const UDataInfo*>(static_cast<const char*>(inData) + 4);
   if(!(
     pInfo->dataFormat[0] == 0x43 &&  /* dataFormat="CSel" */
     pInfo->dataFormat[1] == 0x53 &&
@@ -407,11 +407,11 @@ ucnvsel_swap(const UDataSwapper *ds,
     }
   }
 
-  const uint8_t *inBytes = (const uint8_t *)inData + headerSize;
-  uint8_t *outBytes = (uint8_t *)outData + headerSize;
+  const uint8_t* inBytes = static_cast<const uint8_t*>(inData) + headerSize;
+  uint8_t* outBytes = static_cast<uint8_t*>(outData) + headerSize;
 
   /* read the indexes */
-  const int32_t *inIndexes = (const int32_t *)inBytes;
+  const int32_t* inIndexes = reinterpret_cast<const int32_t*>(inBytes);
   int32_t indexes[16];
   int32_t i;
   for(i = 0; i < 16; ++i) {