deps: update ICU to 69.1

Refs: https://github.com/unicode-org/icu/releases/tag/release-69-1

PR-URL: #38178
Reviewed-By: Colin Ihrig <cjihrig@gmail.com>
Reviewed-By: Richard Lau <rlau@redhat.com>
Reviewed-By: Jiawen Geng <technicalcute@gmail.com>
Reviewed-By: James M Snell <jasnell@gmail.com>

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 68 source files with the following exception(s):
-* deps/icu-small/source/data/in/icudt68l.dat.bz2 : compressed data file
+It is a strict subset of ICU 69 source files with the following exception(s):
+* deps/icu-small/source/data/in/icudt69l.dat.bz2 : compressed data file
 
 
 To rebuild this directory, see ../../tools/icu/README.md

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

@@ -474,31 +474,39 @@ BytesTrieBuilder::writeDeltaTo(int32_t jumpTarget) {
     U_ASSERT(i>=0);
     if(i<=BytesTrie::kMaxOneByteDelta) {
         return write(i);
+    } else {
+        char intBytes[5];
+        return write(intBytes, internalEncodeDelta(i, intBytes));
     }
-    char intBytes[5];
-    int32_t length;
+}
+
+int32_t
+BytesTrieBuilder::internalEncodeDelta(int32_t i, char intBytes[]) {
+    U_ASSERT(i>=0);
+    if(i<=BytesTrie::kMaxOneByteDelta) {
+        intBytes[0]=(char)i;
+        return 1;
+    }
+    int32_t length=1;
     if(i<=BytesTrie::kMaxTwoByteDelta) {
         intBytes[0]=(char)(BytesTrie::kMinTwoByteDeltaLead+(i>>8));
-        length=1;
     } else {
         if(i<=BytesTrie::kMaxThreeByteDelta) {
             intBytes[0]=(char)(BytesTrie::kMinThreeByteDeltaLead+(i>>16));
-            length=2;
         } else {
             if(i<=0xffffff) {
                 intBytes[0]=(char)BytesTrie::kFourByteDeltaLead;
-                length=3;
             } else {
                 intBytes[0]=(char)BytesTrie::kFiveByteDeltaLead;
                 intBytes[1]=(char)(i>>24);
-                length=4;
+                length=2;
             }
-            intBytes[1]=(char)(i>>16);
+            intBytes[length++]=(char)(i>>16);
         }
-        intBytes[1]=(char)(i>>8);
+        intBytes[length++]=(char)(i>>8);
     }
     intBytes[length++]=(char)i;
-    return write(intBytes, length);
+    return length;
 }
 
 U_NAMESPACE_END

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

@@ -14,6 +14,8 @@
 *   created by: Markus W. Scherer
 */
 
+#include <cstdlib>
+
 #include "unicode/utypes.h"
 #include "unicode/putil.h"
 #include "charstr.h"
@@ -141,6 +143,38 @@ CharString &CharString::append(const char *s, int32_t sLength, UErrorCode &error
     return *this;
 }
 
+CharString &CharString::appendNumber(int32_t number, UErrorCode &status) {
+    if (number < 0) {
+        this->append('-', status);
+        if (U_FAILURE(status)) {
+            return *this;
+        }
+    }
+
+    if (number == 0) {
+        this->append('0', status);
+        return *this;
+    }
+
+    int32_t numLen = 0;
+    while (number != 0) {
+        int32_t residue = number % 10;
+        number /= 10;
+        this->append(std::abs(residue) + '0', status);
+        numLen++;
+        if (U_FAILURE(status)) {
+            return *this;
+        }
+    }
+
+    int32_t start = this->length() - numLen, end = this->length() - 1;
+    while(start < end) {
+        std::swap(this->data()[start++], this->data()[end--]);
+    }
+
+    return *this;
+}
+
 char *CharString::getAppendBuffer(int32_t minCapacity,
                                   int32_t desiredCapacityHint,
                                   int32_t &resultCapacity,

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

@@ -127,6 +127,9 @@ class U_COMMON_API CharString : public UMemory {
         return append(s.data(), s.length(), errorCode);
     }
     CharString &append(const char *s, int32_t sLength, UErrorCode &status);
+
+    CharString &appendNumber(int32_t number, UErrorCode &status);
+
     /**
      * Returns a writable buffer for appending and writes the buffer's capacity to
      * resultCapacity. Guarantees resultCapacity>=minCapacity if U_SUCCESS().

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

@@ -31,14 +31,63 @@
 #include <stddef.h>
 #include <string.h>
 #include "unicode/localpointer.h"
+#include "uassert.h"
 
 #if U_DEBUG && defined(UPRV_MALLOC_COUNT)
 #include <stdio.h>
 #endif
 
-
-#define uprv_memcpy(dst, src, size) U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size)
-#define uprv_memmove(dst, src, size) U_STANDARD_CPP_NAMESPACE memmove(dst, src, size)
+// uprv_memcpy and uprv_memmove
+#if defined(__clang__)
+#define uprv_memcpy(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    /* Suppress warnings about addresses that will never be NULL */ \
+    _Pragma("clang diagnostic push") \
+    _Pragma("clang diagnostic ignored \"-Waddress\"") \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    _Pragma("clang diagnostic pop") \
+    U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#define uprv_memmove(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    /* Suppress warnings about addresses that will never be NULL */ \
+    _Pragma("clang diagnostic push") \
+    _Pragma("clang diagnostic ignored \"-Waddress\"") \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    _Pragma("clang diagnostic pop") \
+    U_STANDARD_CPP_NAMESPACE memmove(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#elif defined(__GNUC__)
+#define uprv_memcpy(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    /* Suppress warnings about addresses that will never be NULL */ \
+    _Pragma("GCC diagnostic push") \
+    _Pragma("GCC diagnostic ignored \"-Waddress\"") \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    _Pragma("GCC diagnostic pop") \
+    U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#define uprv_memmove(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    /* Suppress warnings about addresses that will never be NULL */ \
+    _Pragma("GCC diagnostic push") \
+    _Pragma("GCC diagnostic ignored \"-Waddress\"") \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    _Pragma("GCC diagnostic pop") \
+    U_STANDARD_CPP_NAMESPACE memmove(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#else
+#define uprv_memcpy(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#define uprv_memmove(dst, src, size) UPRV_BLOCK_MACRO_BEGIN { \
+    U_ASSERT(dst != NULL); \
+    U_ASSERT(src != NULL); \
+    U_STANDARD_CPP_NAMESPACE memmove(dst, src, size); \
+} UPRV_BLOCK_MACRO_END
+#endif
 
 /**
  * \def UPRV_LENGTHOF

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

@@ -265,13 +265,9 @@ ThaiBreakEngine::divideUpDictionaryRange( UText *text,
                 goto foundBest;
             }
             do {
-                int32_t wordsMatched = 1;
                 if (words[(wordsFound + 1) % THAI_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) {
-                    if (wordsMatched < 2) {
-                        // Followed by another dictionary word; mark first word as a good candidate
-                        words[wordsFound%THAI_LOOKAHEAD].markCurrent();
-                        wordsMatched = 2;
-                    }
+                    // Followed by another dictionary word; mark first word as a good candidate
+                    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) {
@@ -503,13 +499,9 @@ LaoBreakEngine::divideUpDictionaryRange( UText *text,
                 goto foundBest;
             }
             do {
-                int32_t wordsMatched = 1;
                 if (words[(wordsFound + 1) % LAO_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) {
-                    if (wordsMatched < 2) {
-                        // Followed by another dictionary word; mark first word as a good candidate
-                        words[wordsFound%LAO_LOOKAHEAD].markCurrent();
-                        wordsMatched = 2;
-                    }
+                    // Followed by another dictionary word; mark first word as a good candidate
+                    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) {
@@ -699,13 +691,9 @@ BurmeseBreakEngine::divideUpDictionaryRange( UText *text,
                 goto foundBest;
             }
             do {
-                int32_t wordsMatched = 1;
                 if (words[(wordsFound + 1) % BURMESE_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) {
-                    if (wordsMatched < 2) {
-                        // Followed by another dictionary word; mark first word as a good candidate
-                        words[wordsFound%BURMESE_LOOKAHEAD].markCurrent();
-                        wordsMatched = 2;
-                    }
+                    // Followed by another dictionary word; mark first word as a good candidate
+                    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) {
@@ -908,13 +896,9 @@ KhmerBreakEngine::divideUpDictionaryRange( UText *text,
                 goto foundBest;
             }
             do {
-                int32_t wordsMatched = 1;
                 if (words[(wordsFound + 1) % KHMER_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) {
-                    if (wordsMatched < 2) {
-                        // Followed by another dictionary word; mark first word as a good candidate
-                        words[wordsFound % KHMER_LOOKAHEAD].markCurrent();
-                        wordsMatched = 2;
-                    }
+                    // Followed by another dictionary word; mark first word as a good candidate
+                    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) {

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

@@ -86,6 +86,7 @@ Edits &Edits::moveArray(Edits &src) U_NOEXCEPT {
 }
 
 Edits &Edits::operator=(const Edits &other) {
+    if (this == &other) { return *this; }  // self-assignment: no-op
     length = other.length;
     delta = other.delta;
     numChanges = other.numChanges;