deps: update ICU to 64.2

Update the version of the bundled ICU (deps/icu-small) to ICU version
64.2 (Unicode 12, CLDR 35)

Fixes: #26388

PR-URL: #27361
Reviewed-By: Richard Lau <[email protected]>
Reviewed-By: Steven R Loomis <[email protected]>
Reviewed-By: Michael Dawson <[email protected]>

Author: ryzokuken

deps/icu-small/LICENSE

@@ -1,7 +1,7 @@
 COPYRIGHT AND PERMISSION NOTICE (ICU 58 and later)
 
-Copyright © 1991-2018 Unicode, Inc. All rights reserved.
-Distributed under the Terms of Use in http://www.unicode.org/copyright.html.
+Copyright © 1991-2019 Unicode, Inc. All rights reserved.
+Distributed under the Terms of Use in https://www.unicode.org/copyright.html.
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of the Unicode data files and any associated documentation

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

@@ -1,8 +1,8 @@
 Small ICU sources - auto generated by shrink-icu-src.py
 
 This directory contains the ICU subset used by --with-intl=small-icu (the default)
-It is a strict subset of ICU 63 source files with the following exception(s):
-* deps/icu-small/source/data/in/icudt63l.dat : Reduced-size data file
+It is a strict subset of ICU 64 source files with the following exception(s):
+* deps/icu-small/source/data/in/icudt64l.dat : Reduced-size data file
 
 
 To rebuild this directory, see ../../tools/icu/README.md

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

@@ -124,13 +124,12 @@ static void U_CALLCONV _deleteEngine(void *obj) {
 U_CDECL_END
 U_NAMESPACE_BEGIN
 
-static UMutex gBreakEngineMutex = U_MUTEX_INITIALIZER;
-
 const LanguageBreakEngine *
 ICULanguageBreakFactory::getEngineFor(UChar32 c) {
     const LanguageBreakEngine *lbe = NULL;
     UErrorCode  status = U_ZERO_ERROR;
 
+    static UMutex gBreakEngineMutex = U_MUTEX_INITIALIZER;
     Mutex m(&gBreakEngineMutex);
 
     if (fEngines == NULL) {

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

@@ -0,0 +1,97 @@
+// © 2018 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+
+#ifndef __CAPI_HELPER_H__
+#define __CAPI_HELPER_H__
+
+#include "unicode/utypes.h"
+
+U_NAMESPACE_BEGIN
+
+/**
+ * An internal helper class to help convert between C and C++ APIs.
+ */
+template<typename CType, typename CPPType, int32_t kMagic>
+class IcuCApiHelper {
+  public:
+    /**
+     * Convert from the C type to the C++ type (const version).
+     */
+    static const CPPType* validate(const CType* input, UErrorCode& status);
+
+    /**
+     * Convert from the C type to the C++ type (non-const version).
+     */
+    static CPPType* validate(CType* input, UErrorCode& status);
+
+    /**
+     * Convert from the C++ type to the C type (const version).
+     */
+    const CType* exportConstForC() const;
+
+    /**
+     * Convert from the C++ type to the C type (non-const version).
+     */
+    CType* exportForC();
+
+    /**
+     * Invalidates the object.
+     */
+    ~IcuCApiHelper();
+
+  private:
+    /**
+     * While the object is valid, fMagic equals kMagic.
+     */
+    int32_t fMagic = kMagic;
+};
+
+
+template<typename CType, typename CPPType, int32_t kMagic>
+const CPPType*
+IcuCApiHelper<CType, CPPType, kMagic>::validate(const CType* input, UErrorCode& status) {
+    if (U_FAILURE(status)) {
+        return nullptr;
+    }
+    if (input == nullptr) {
+        status = U_ILLEGAL_ARGUMENT_ERROR;
+        return nullptr;
+    }
+    auto* impl = reinterpret_cast<const CPPType*>(input);
+    if (static_cast<const IcuCApiHelper<CType, CPPType, kMagic>*>(impl)->fMagic != kMagic) {
+        status = U_INVALID_FORMAT_ERROR;
+        return nullptr;
+    }
+    return impl;
+}
+
+template<typename CType, typename CPPType, int32_t kMagic>
+CPPType*
+IcuCApiHelper<CType, CPPType, kMagic>::validate(CType* input, UErrorCode& status) {
+    auto* constInput = static_cast<const CType*>(input);
+    auto* validated = validate(constInput, status);
+    return const_cast<CPPType*>(validated);
+}
+
+template<typename CType, typename CPPType, int32_t kMagic>
+const CType*
+IcuCApiHelper<CType, CPPType, kMagic>::exportConstForC() const {
+    return reinterpret_cast<const CType*>(static_cast<const CPPType*>(this));
+}
+
+template<typename CType, typename CPPType, int32_t kMagic>
+CType*
+IcuCApiHelper<CType, CPPType, kMagic>::exportForC() {
+    return reinterpret_cast<CType*>(static_cast<CPPType*>(this));
+}
+
+template<typename CType, typename CPPType, int32_t kMagic>
+IcuCApiHelper<CType, CPPType, kMagic>::~IcuCApiHelper() {
+    // head off application errors by preventing use of of deleted objects.
+    fMagic = 0;
+}
+
+
+U_NAMESPACE_END
+
+#endif // __CAPI_HELPER_H__

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

@@ -23,24 +23,34 @@
 #include "umutex.h"
 #include "uprops.h"
 
+using icu::LocalPointer;
+#if !UCONFIG_NO_NORMALIZATION
+using icu::Normalizer2Factory;
+using icu::Normalizer2Impl;
+#endif
 using icu::UInitOnce;
 using icu::UnicodeSet;
 
 namespace {
 
 UBool U_CALLCONV characterproperties_cleanup();
 
+constexpr int32_t NUM_INCLUSIONS = UPROPS_SRC_COUNT + UCHAR_INT_LIMIT - UCHAR_INT_START;
+
 struct Inclusion {
     UnicodeSet  *fSet;
     UInitOnce    fInitOnce;
 };
-Inclusion gInclusions[UPROPS_SRC_COUNT]; // cached getInclusions()
+Inclusion gInclusions[NUM_INCLUSIONS]; // cached getInclusions()
 
 UnicodeSet *sets[UCHAR_BINARY_LIMIT] = {};
 
 UCPMap *maps[UCHAR_INT_LIMIT - UCHAR_INT_START] = {};
 
-UMutex cpMutex = U_MUTEX_INITIALIZER;
+icu::UMutex *cpMutex() {
+    static icu::UMutex m = U_MUTEX_INITIALIZER;
+    return &m;
+}
 
 //----------------------------------------------------------------
 // Inclusions list
@@ -80,43 +90,29 @@ UBool U_CALLCONV characterproperties_cleanup() {
     return TRUE;
 }
 
-}  // namespace
-
-U_NAMESPACE_BEGIN
-
-/*
-Reduce excessive reallocation, and make it easier to detect initialization problems.
-Usually you don't see smaller sets than this for Unicode 5.0.
-*/
-constexpr int32_t DEFAULT_INCLUSION_CAPACITY = 3072;
-
-void U_CALLCONV CharacterProperties::initInclusion(UPropertySource src, UErrorCode &errorCode) {
+void U_CALLCONV initInclusion(UPropertySource src, UErrorCode &errorCode) {
     // This function is invoked only via umtx_initOnce().
-    // This function is a friend of class UnicodeSet.
-
     U_ASSERT(0 <= src && src < UPROPS_SRC_COUNT);
     if (src == UPROPS_SRC_NONE) {
         errorCode = U_INTERNAL_PROGRAM_ERROR;
         return;
     }
-    UnicodeSet * &incl = gInclusions[src].fSet;
-    U_ASSERT(incl == nullptr);
+    U_ASSERT(gInclusions[src].fSet == nullptr);
 
-    incl = new UnicodeSet();
-    if (incl == nullptr) {
+    LocalPointer<UnicodeSet> incl(new UnicodeSet());
+    if (incl.isNull()) {
         errorCode = U_MEMORY_ALLOCATION_ERROR;
         return;
     }
     USetAdder sa = {
-        (USet *)incl,
+        (USet *)incl.getAlias(),
         _set_add,
         _set_addRange,
         _set_addString,
         nullptr, // don't need remove()
         nullptr // don't need removeRange()
     };
 
-    incl->ensureCapacity(DEFAULT_INCLUSION_CAPACITY, errorCode);
     switch(src) {
     case UPROPS_SRC_CHAR:
         uchar_addPropertyStarts(&sa, &errorCode);
@@ -183,12 +179,15 @@ void U_CALLCONV CharacterProperties::initInclusion(UPropertySource src, UErrorCo
     }
 
     if (U_FAILURE(errorCode)) {
-        delete incl;
-        incl = nullptr;
         return;
     }
-    // Compact for caching
+    if (incl->isBogus()) {
+        errorCode = U_MEMORY_ALLOCATION_ERROR;
+        return;
+    }
+    // Compact for caching.
     incl->compact();
+    gInclusions[src].fSet = incl.orphan();
     ucln_common_registerCleanup(UCLN_COMMON_CHARACTERPROPERTIES, characterproperties_cleanup);
 }
 
@@ -199,15 +198,66 @@ const UnicodeSet *getInclusionsForSource(UPropertySource src, UErrorCode &errorC
         return nullptr;
     }
     Inclusion &i = gInclusions[src];
-    umtx_initOnce(i.fInitOnce, &CharacterProperties::initInclusion, src, errorCode);
+    umtx_initOnce(i.fInitOnce, &initInclusion, src, errorCode);
     return i.fSet;
 }
 
+void U_CALLCONV initIntPropInclusion(UProperty prop, UErrorCode &errorCode) {
+    // This function is invoked only via umtx_initOnce().
+    U_ASSERT(UCHAR_INT_START <= prop && prop < UCHAR_INT_LIMIT);
+    int32_t inclIndex = UPROPS_SRC_COUNT + prop - UCHAR_INT_START;
+    U_ASSERT(gInclusions[inclIndex].fSet == nullptr);
+    UPropertySource src = uprops_getSource(prop);
+    const UnicodeSet *incl = getInclusionsForSource(src, errorCode);
+    if (U_FAILURE(errorCode)) {
+        return;
+    }
+
+    LocalPointer<UnicodeSet> intPropIncl(new UnicodeSet(0, 0));
+    if (intPropIncl.isNull()) {
+        errorCode = U_MEMORY_ALLOCATION_ERROR;
+        return;
+    }
+    int32_t numRanges = incl->getRangeCount();
+    int32_t prevValue = 0;
+    for (int32_t i = 0; i < numRanges; ++i) {
+        UChar32 rangeEnd = incl->getRangeEnd(i);
+        for (UChar32 c = incl->getRangeStart(i); c <= rangeEnd; ++c) {
+            // TODO: Get a UCharacterProperty.IntProperty to avoid the property dispatch.
+            int32_t value = u_getIntPropertyValue(c, prop);
+            if (value != prevValue) {
+                intPropIncl->add(c);
+                prevValue = value;
+            }
+        }
+    }
+
+    if (intPropIncl->isBogus()) {
+        errorCode = U_MEMORY_ALLOCATION_ERROR;
+        return;
+    }
+    // Compact for caching.
+    intPropIncl->compact();
+    gInclusions[inclIndex].fSet = intPropIncl.orphan();
+    ucln_common_registerCleanup(UCLN_COMMON_CHARACTERPROPERTIES, characterproperties_cleanup);
+}
+
+}  // namespace
+
+U_NAMESPACE_BEGIN
+
 const UnicodeSet *CharacterProperties::getInclusionsForProperty(
         UProperty prop, UErrorCode &errorCode) {
     if (U_FAILURE(errorCode)) { return nullptr; }
-    UPropertySource src = uprops_getSource(prop);
-    return getInclusionsForSource(src, errorCode);
+    if (UCHAR_INT_START <= prop && prop < UCHAR_INT_LIMIT) {
+        int32_t inclIndex = UPROPS_SRC_COUNT + prop - UCHAR_INT_START;
+        Inclusion &i = gInclusions[inclIndex];
+        umtx_initOnce(i.fInitOnce, &initIntPropInclusion, prop, errorCode);
+        return i.fSet;
+    } else {
+        UPropertySource src = uprops_getSource(prop);
+        return getInclusionsForSource(src, errorCode);
+    }
 }
 
 U_NAMESPACE_END
@@ -216,7 +266,7 @@ namespace {
 
 UnicodeSet *makeSet(UProperty property, UErrorCode &errorCode) {
     if (U_FAILURE(errorCode)) { return nullptr; }
-    icu::LocalPointer<UnicodeSet> set(new UnicodeSet());
+    LocalPointer<UnicodeSet> set(new UnicodeSet());
     if (set.isNull()) {
         errorCode = U_MEMORY_ALLOCATION_ERROR;
         return nullptr;
@@ -311,7 +361,7 @@ u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode) {
         *pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
         return nullptr;
     }
-    Mutex m(&cpMutex);
+    Mutex m(cpMutex());
     UnicodeSet *set = sets[property];
     if (set == nullptr) {
         sets[property] = set = makeSet(property, *pErrorCode);
@@ -327,7 +377,7 @@ u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode) {
         *pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
         return nullptr;
     }
-    Mutex m(&cpMutex);
+    Mutex m(cpMutex());
     UCPMap *map = maps[property - UCHAR_INT_START];
     if (map == nullptr) {
         maps[property - UCHAR_INT_START] = map = makeMap(property, *pErrorCode);