deps: update icu to 79.1

deps/icu-small/LICENSE

@@ -2,7 +2,7 @@ UNICODE LICENSE V3
 
 COPYRIGHT AND PERMISSION NOTICE
 
-Copyright © 2016-2025 Unicode, Inc.
+Copyright © 1991-2026 Unicode, Inc.
 
 NOTICE TO USER: Carefully read the following legal agreement. BY
 DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR

deps/icu-small/README-FULL-ICU.txt

@@ -1,8 +1,8 @@
 ICU sources - auto generated by shrink-icu-src.py
 
 This directory contains the ICU subset used by --with-intl=full-icu
-It is a strict subset of ICU 78 source files with the following exception(s):
-* deps/icu-small/source/data/in/icudt78l.dat.bz2 : compressed data file
+It is a strict subset of ICU 79 source files with the following exception(s):
+* deps/icu-small/source/data/in/icudt79l.dat.bz2 : compressed data file
 
 
 To rebuild this directory, see ../../tools/icu/README.md

deps/icu-small/source/.clang-format

@@ -5,7 +5,7 @@
 Language: Cpp
 BasedOnStyle: LLVM
 IndentWidth: 4
-ColumnLimit: 105
+ColumnLimit: 100
 AllowShortBlocksOnASingleLine: false 
 AllowShortIfStatementsOnASingleLine: true 
 ...

deps/icu-small/source/common/BUILD.bazel

@@ -36,6 +36,9 @@ cc_library(
     # Bazel workspace:
     # https://stackoverflow.com/a/65635893/2077918
     includes = ["."],
+    defines = [
+        "U_DEBUG", # enable U_ASSERT()
+    ],
     local_defines = [
         "U_COMMON_IMPLEMENTATION",
     ],

deps/icu-small/source/common/appendable.cpp

@@ -56,11 +56,12 @@ Appendable::reserveAppendCapacity(int32_t /*appendCapacity*/) {
     return true;
 }
 
-char16_t *
+char16_t*
 Appendable::getAppendBuffer(int32_t minCapacity,
                             int32_t /*desiredCapacityHint*/,
-                            char16_t *scratch, int32_t scratchCapacity,
-                            int32_t *resultCapacity) {
+                            char16_t* scratch U_LIFETIME_BOUND,
+                            int32_t scratchCapacity,
+                            int32_t* resultCapacity) U_LIFETIME_BOUND {
     if(minCapacity<1 || scratchCapacity<minCapacity) {
         *resultCapacity=0;
         return nullptr;

deps/icu-small/source/common/brkiter.cpp

@@ -213,7 +213,7 @@ BreakIterator::BreakIterator(const BreakIterator &other)
       requestLocale(other.requestLocale) {
 }
 
-BreakIterator &BreakIterator::operator =(const BreakIterator &other) {
+BreakIterator& BreakIterator::operator=(const BreakIterator& other) U_LIFETIME_BOUND {
     if (this != &other) {
         actualLocale = other.actualLocale;
         validLocale = other.validLocale;
@@ -504,8 +504,8 @@ BreakIterator::getLocale(ULocDataLocaleType type, UErrorCode& status) const {
     return LocaleBased::getLocale(validLocale, actualLocale, type, status);
 }
 
-const char *
-BreakIterator::getLocaleID(ULocDataLocaleType type, UErrorCode& status) const {
+const char*
+BreakIterator::getLocaleID(ULocDataLocaleType type, UErrorCode& status) const U_LIFETIME_BOUND {
     if (U_FAILURE(status)) {
         return nullptr;
     }

deps/icu-small/source/common/bytesinkutil.cpp

@@ -136,9 +136,9 @@ CharStringByteSink::Append(const char* bytes, int32_t n) {
 char*
 CharStringByteSink::GetAppendBuffer(int32_t min_capacity,
                                     int32_t desired_capacity_hint,
-                                    char* scratch,
+                                    char* scratch U_LIFETIME_BOUND,
                                     int32_t scratch_capacity,
-                                    int32_t* result_capacity) {
+                                    int32_t* result_capacity) U_LIFETIME_BOUND {
     if (min_capacity < 1 || scratch_capacity < min_capacity) {
         *result_capacity = 0;
         return nullptr;

deps/icu-small/source/common/bytesinkutil.h

@@ -35,9 +35,9 @@ class U_COMMON_API CharStringByteSink : public ByteSink {
 
     char* GetAppendBuffer(int32_t min_capacity,
                           int32_t desired_capacity_hint,
-                          char* scratch,
+                          char* scratch U_LIFETIME_BOUND,
                           int32_t scratch_capacity,
-                          int32_t* result_capacity) override;
+                          int32_t* result_capacity) U_LIFETIME_BOUND override;
 
 private:
     CharString& dest_;

deps/icu-small/source/common/bytestream.cpp

@@ -16,8 +16,9 @@ ByteSink::~ByteSink() {}
 
 char* ByteSink::GetAppendBuffer(int32_t min_capacity,
                                 int32_t /*desired_capacity_hint*/,
-                                char* scratch, int32_t scratch_capacity,
-                                int32_t* result_capacity) {
+                                char* scratch U_LIFETIME_BOUND,
+                                int32_t scratch_capacity,
+                                int32_t* result_capacity) U_LIFETIME_BOUND {
   if (min_capacity < 1 || scratch_capacity < min_capacity) {
     *result_capacity = 0;
     return nullptr;
@@ -35,7 +36,7 @@ CheckedArrayByteSink::CheckedArrayByteSink(char* outbuf, int32_t capacity)
 
 CheckedArrayByteSink::~CheckedArrayByteSink() {}
 
-CheckedArrayByteSink& CheckedArrayByteSink::Reset() {
+CheckedArrayByteSink& CheckedArrayByteSink::Reset() U_LIFETIME_BOUND {
   size_ = appended_ = 0;
   overflowed_ = false;
   return *this;
@@ -65,9 +66,9 @@ void CheckedArrayByteSink::Append(const char* bytes, int32_t n) {
 
 char* CheckedArrayByteSink::GetAppendBuffer(int32_t min_capacity,
                                             int32_t /*desired_capacity_hint*/,
-                                            char* scratch,
+                                            char* scratch U_LIFETIME_BOUND,
                                             int32_t scratch_capacity,
-                                            int32_t* result_capacity) {
+                                            int32_t* result_capacity) U_LIFETIME_BOUND {
   if (min_capacity < 1 || scratch_capacity < min_capacity) {
     *result_capacity = 0;
     return nullptr;

deps/icu-small/source/common/bytestrie.cpp

@@ -45,8 +45,8 @@ BytesTrie::readValue(const uint8_t *pos, int32_t leadByte) {
     return value;
 }
 
-const uint8_t *
-BytesTrie::jumpByDelta(const uint8_t *pos) {
+const uint8_t*
+BytesTrie::jumpByDelta(const uint8_t* pos U_LIFETIME_BOUND) {
     int32_t delta=*pos++;
     if(delta<kMinTwoByteDeltaLead) {
         // nothing to do
@@ -312,9 +312,11 @@ BytesTrie::next(const char *s, int32_t sLength) {
     }
 }
 
-const uint8_t *
-BytesTrie::findUniqueValueFromBranch(const uint8_t *pos, int32_t length,
-                                     UBool haveUniqueValue, int32_t &uniqueValue) {
+const uint8_t*
+BytesTrie::findUniqueValueFromBranch(const uint8_t* pos U_LIFETIME_BOUND,
+                                     int32_t length,
+                                     UBool haveUniqueValue,
+                                     int32_t& uniqueValue) {
     while(length>kMaxBranchLinearSubNodeLength) {
         ++pos;  // ignore the comparison byte
         if(nullptr==findUniqueValueFromBranch(jumpByDelta(pos), length>>1, haveUniqueValue, uniqueValue)) {

deps/icu-small/source/common/bytestriebuilder.cpp

@@ -39,7 +39,7 @@ class BytesTrieElement : public UMemory {
 
     void setTo(StringPiece s, int32_t val, CharString &strings, UErrorCode &errorCode);
 
-    StringPiece getString(const CharString &strings) const {
+    StringPiece getString(const CharString& strings U_LIFETIME_BOUND) const {
         int32_t offset=stringOffset;
         int32_t length;
         if(offset>=0) {
@@ -68,7 +68,7 @@ class BytesTrieElement : public UMemory {
     int32_t compareStringTo(const BytesTrieElement &o, const CharString &strings) const;
 
 private:
-    const char *data(const CharString &strings) const {
+    const char* data(const CharString& strings U_LIFETIME_BOUND) const {
         int32_t offset=stringOffset;
         if(offset>=0) {
             ++offset;
@@ -144,8 +144,8 @@ BytesTrieBuilder::~BytesTrieBuilder() {
     uprv_free(bytes);
 }
 
-BytesTrieBuilder &
-BytesTrieBuilder::add(StringPiece s, int32_t value, UErrorCode &errorCode) {
+BytesTrieBuilder&
+BytesTrieBuilder::add(StringPiece s, int32_t value, UErrorCode& errorCode) U_LIFETIME_BOUND {
     if(U_FAILURE(errorCode)) {
         return *this;
     }
@@ -206,7 +206,8 @@ BytesTrieBuilder::build(UStringTrieBuildOption buildOption, UErrorCode &errorCod
 }
 
 StringPiece
-BytesTrieBuilder::buildStringPiece(UStringTrieBuildOption buildOption, UErrorCode &errorCode) {
+BytesTrieBuilder::buildStringPiece(UStringTrieBuildOption buildOption,
+                                   UErrorCode& errorCode) U_LIFETIME_BOUND {
     buildBytes(buildOption, errorCode);
     StringPiece result;
     if(U_SUCCESS(errorCode)) {
@@ -269,8 +270,8 @@ BytesTrieBuilder::buildBytes(UStringTrieBuildOption buildOption, UErrorCode &err
     }
 }
 
-BytesTrieBuilder &
-BytesTrieBuilder::clear() {
+BytesTrieBuilder&
+BytesTrieBuilder::clear() U_LIFETIME_BOUND {
     strings->clear();
     elementsLength=0;
     bytesLength=0;

deps/icu-small/source/common/bytestrieiterator.cpp

@@ -22,8 +22,9 @@
 
 U_NAMESPACE_BEGIN
 
-BytesTrie::Iterator::Iterator(const void *trieBytes, int32_t maxStringLength,
-                              UErrorCode &errorCode)
+BytesTrie::Iterator::Iterator(const void* trieBytes U_LIFETIME_BOUND,
+                              int32_t maxStringLength,
+                              UErrorCode& errorCode)
         : bytes_(static_cast<const uint8_t *>(trieBytes)),
           pos_(bytes_), initialPos_(bytes_),
           remainingMatchLength_(-1), initialRemainingMatchLength_(-1),
@@ -80,8 +81,8 @@ BytesTrie::Iterator::~Iterator() {
     delete stack_;
 }
 
-BytesTrie::Iterator &
-BytesTrie::Iterator::reset() {
+BytesTrie::Iterator&
+BytesTrie::Iterator::reset() U_LIFETIME_BOUND {
     pos_=initialPos_;
     remainingMatchLength_=initialRemainingMatchLength_;
     int32_t length=remainingMatchLength_+1;  // Remaining match length.
@@ -169,7 +170,7 @@ BytesTrie::Iterator::next(UErrorCode &errorCode) {
 }
 
 StringPiece
-BytesTrie::Iterator::getString() const {
+BytesTrie::Iterator::getString() const U_LIFETIME_BOUND {
     return str_ == nullptr ? StringPiece() : str_->toStringPiece();
 }
 
@@ -181,8 +182,10 @@ BytesTrie::Iterator::truncateAndStop() {
 }
 
 // Branch node, needs to take the first outbound edge and push state for the rest.
-const uint8_t *
-BytesTrie::Iterator::branchNext(const uint8_t *pos, int32_t length, UErrorCode &errorCode) {
+const uint8_t*
+BytesTrie::Iterator::branchNext(const uint8_t* pos U_LIFETIME_BOUND,
+                                int32_t length,
+                                UErrorCode& errorCode) {
     while(length>kMaxBranchLinearSubNodeLength) {
         ++pos;  // ignore the comparison byte
         // Push state for the greater-or-equal edge.

deps/icu-small/source/common/caniter.cpp

@@ -440,8 +440,10 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
     return finalResult;
 }
 
-Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const char16_t *segment, int32_t segLen, UErrorCode &status) {
-
+Hashtable* CanonicalIterator::getEquivalents2(Hashtable* fillinResult U_LIFETIME_BOUND,
+                                              const char16_t* segment,
+                                              int32_t segLen,
+                                              UErrorCode& status) {
     if (U_FAILURE(status)) {
         return nullptr;
     }
@@ -518,7 +520,12 @@ Hashtable *CanonicalIterator::getEquivalents2(Hashtable *fillinResult, const cha
  * (with canonical rearrangement!)
  * If so, take the remainder, and return the equivalents 
  */
-Hashtable *CanonicalIterator::extract(Hashtable *fillinResult, UChar32 comp, const char16_t *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status) {
+Hashtable* CanonicalIterator::extract(Hashtable* fillinResult U_LIFETIME_BOUND,
+                                      UChar32 comp,
+                                      const char16_t* segment,
+                                      int32_t segLen,
+                                      int32_t segmentPos,
+                                      UErrorCode& status) {
 //Hashtable *CanonicalIterator::extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status) {
     //if (PROGRESS) printf(" extract: %s, ", UToS(Tr(UnicodeString(comp))));
     //if (PROGRESS) printf("%s, %i\n", UToS(Tr(segment)), segmentPos);

deps/icu-small/source/common/chariter.cpp

@@ -73,8 +73,8 @@ textLength(that.textLength), pos(that.pos), begin(that.begin), end(that.end)
 {
 }
 
-CharacterIterator &
-CharacterIterator::operator=(const CharacterIterator &that) {
+CharacterIterator&
+CharacterIterator::operator=(const CharacterIterator& that) U_LIFETIME_BOUND {
     ForwardCharacterIterator::operator=(that);
     textLength = that.textLength;
     pos = that.pos;