upgrade to ICU 58

Change-Id: I4a992447df65b337721a2a2627d974172a14cba5
Reviewed-on: https://gerrit.libreoffice.org/30487Reviewed-by: Eike Rathke <erack@redhat.com>
Tested-by: Eike Rathke <erack@redhat.com>

configure.ac

@@ -9136,7 +9136,7 @@ SYSTEM_GENBRK=
 SYSTEM_GENCCODE=
 SYSTEM_GENCMN=
 
-ICU_MAJOR=57
+ICU_MAJOR=58
 ICU_MINOR=1
 ICU_RECLASSIFIED_PREPEND_SET_EMPTY="TRUE"
 ICU_RECLASSIFIED_CONDITIONAL_JAPANESE_STARTER="TRUE"

download.lst

@@ -62,7 +62,7 @@ export HARFBUZZ_TARBALL := harfbuzz-1.3.2.tar.bz2
 export HSQLDB_TARBALL := 17410483b5b5f267aa18b7e00b65e6e0-hsqldb_1_8_0.zip
 export HUNSPELL_TARBALL := 33d370f7fe5a030985e445a5672b2067-hunspell-1.4.1.tar.gz
 export HYPHEN_TARBALL := 5ade6ae2a99bc1e9e57031ca88d36dad-hyphen-2.8.8.tar.gz
-export ICU_TARBALL := 976734806026a4ef8bdd17937c8898b9-icu4c-57_1-src.tgz
+export ICU_TARBALL := 1901302aaff1c1633ef81862663d2917-icu4c-58_1-src.tgz
 export JFREEREPORT_FLOW_ENGINE_TARBALL := ba2930200c9f019c2d93a8c88c651a0f-flow-engine-0.9.4.zip
 export JFREEREPORT_FLUTE_TARBALL := d8bd5eed178db6e2b18eeed243f85aa8-flute-1.1.6.zip
 export JFREEREPORT_LIBBASE_TARBALL := eeb2c7ddf0d302fba4bfc6e97eac9624-libbase-1.1.6.zip

external/icu/icu-ubsan.patch.0

@@ -151,14 +151,3 @@
                    length(len), next(subNode) {}
          virtual UBool operator==(const Node &other) const;
          virtual int32_t markRightEdgesFirst(int32_t edgeNumber);
---- source/common/unifiedcache.h
-+++ source/common/unifiedcache.h
-@@ -139,7 +139,7 @@
-            : CacheKey<T>(other), fLoc(other.fLoc) { }
-    virtual ~LocaleCacheKey() { }
-    virtual int32_t hashCode() const {
--       return 37 *CacheKey<T>::hashCode() + fLoc.hashCode();
-+       return 37U *CacheKey<T>::hashCode() + fLoc.hashCode();
-    }
-    virtual UBool operator == (const CacheKeyBase &other) const {
-        // reflexive

external/icu/icu4c-warnings.patch

@@ -8,15 +8,3 @@
      } \
  }
  
---- misc/icu/source/common/unicode/utypes.h
-+++ misc/build/icu/source/common/unicode/utypes.h
-@@ -399,7 +399,7 @@
-  * some Linux/Unix compilers have problems with defining global new/delete.
-  * On Windows, it is _MSC_VER>=1200 for MSVC 6.0 and higher.
-  */
--#if defined(__cplusplus) && U_DEBUG && U_OVERRIDE_CXX_ALLOCATION && (_MSC_VER>=1200) && !defined(U_STATIC_IMPLEMENTATION) && (defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUT_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION))
-+#if defined(__cplusplus) && U_DEBUG && U_OVERRIDE_CXX_ALLOCATION && defined (_MSC_VER) && (_MSC_VER>=1200) && !defined(U_STATIC_IMPLEMENTATION) && (defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUT_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION))
- 
- #ifndef U_HIDE_INTERNAL_API
- /**
-

i18npool/source/breakiterator/breakiterator_unicode.cxx

@@ -63,10 +63,13 @@ BreakIterator_Unicode::~BreakIterator_Unicode()
 class OOoRuleBasedBreakIterator : public RuleBasedBreakIterator
 {
     public:
+#if (U_ICU_VERSION_MAJOR_NUM < 58)
+    // RuleBasedBreakIterator::setBreakType() is private as of ICU 58.
     inline void publicSetBreakType(int32_t type)
         {
             setBreakType(type);
         };
+#endif
     OOoRuleBasedBreakIterator(UDataMemory* image,
                               UErrorCode &status)
         : RuleBasedBreakIterator(image, status)
@@ -142,12 +145,21 @@ void SAL_CALL BreakIterator_Unicode::loadICUBreakIterator(const css::lang::Local
                 }
             }
             if (rbi) {
+#if (U_ICU_VERSION_MAJOR_NUM < 58)
+                // ICU 58 made RuleBasedBreakIterator::setBreakType() private
+                // instead of protected, so the old workaround of
+                // https://ssl.icu-project.org/trac/ticket/5498
+                // doesn't work anymore. However, they also claim to have fixed
+                // the cause that an initial fBreakType==-1 would lead to an
+                // endless loop under some circumstances.
+                // Let's see ...
                 switch (rBreakType) {
                     case LOAD_CHARACTER_BREAKITERATOR: rbi->publicSetBreakType(UBRK_CHARACTER); break;
                     case LOAD_WORD_BREAKITERATOR: rbi->publicSetBreakType(UBRK_WORD); break;
                     case LOAD_SENTENCE_BREAKITERATOR: rbi->publicSetBreakType(UBRK_SENTENCE); break;
                     case LOAD_LINE_BREAKITERATOR: rbi->publicSetBreakType(UBRK_LINE); break;
                 }
+#endif
                 icuBI->aBreakIterator = rbi;
             }
         }

i18nutil/source/utility/unicode.cxx

@@ -956,6 +956,32 @@ OString SAL_CALL unicode::getExemplarLanguageForUScriptCode(UScriptCode eScript)
         case USCRIPT_SIDDHAM:
             sRet = "sa-Sidd";
             break;
+#endif
+#if (U_ICU_VERSION_MAJOR_NUM >= 58)
+        case USCRIPT_ADLAM:
+            sRet = "mis";   // Adlm - Adlam for Fulani, no language code
+            break;
+        case USCRIPT_BHAIKSUKI:
+            sRet = "mis";   // Bhks - Bhaiksuki for some Buddhist texts, no language code
+            break;
+        case USCRIPT_MARCHEN:
+            sRet = "bo-Marc";
+            break;
+        case USCRIPT_NEWA:
+            sRet = "new-Newa";
+            break;
+        case USCRIPT_OSAGE:
+            sRet = "osa-Osge";
+            break;
+        case USCRIPT_HAN_WITH_BOPOMOFO:
+            sRet = "mis";   // Hanb - Han with Bopomofo, zh-Hanb ?
+            break;
+        case USCRIPT_JAMO:
+            sRet = "mis";   // Jamo - Jamo subset of Hangul, ko-Jamo ?
+            break;
+        case USCRIPT_SYMBOLS_EMOJI:
+            sRet = "mis";   // Zsye - Emoji variant
+            break;
 #endif
     }
     return sRet;

include/svx/ucsubset.hrc

@@ -291,6 +291,17 @@
 #define RID_SUBSETSTR_OLD_HUNGARIAN             (RID_SUBSET_START + 263)
 #define RID_SUBSETSTR_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS  (RID_SUBSET_START + 264)
 #define RID_SUBSETSTR_SUTTON_SIGNWRITING        (RID_SUBSET_START + 265)
+#define RID_SUBSETSTR_ADLAM                     (RID_SUBSET_START + 266)
+#define RID_SUBSETSTR_BHAIKSUKI                 (RID_SUBSET_START + 267)
+#define RID_SUBSETSTR_CYRILLIC_EXTENDED_C       (RID_SUBSET_START + 268)
+#define RID_SUBSETSTR_GLAGOLITIC_SUPPLEMENT     (RID_SUBSET_START + 269)
+#define RID_SUBSETSTR_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION   (RID_SUBSET_START + 270)
+#define RID_SUBSETSTR_MARCHEN                   (RID_SUBSET_START + 271)
+#define RID_SUBSETSTR_MONGOLIAN_SUPPLEMENT      (RID_SUBSET_START + 272)
+#define RID_SUBSETSTR_NEWA                      (RID_SUBSET_START + 273)
+#define RID_SUBSETSTR_OSAGE                     (RID_SUBSET_START + 274)
+#define RID_SUBSETSTR_TANGUT                    (RID_SUBSET_START + 275)
+#define RID_SUBSETSTR_TANGUT_COMPONENTS         (RID_SUBSET_START + 276)
 
 //      RID_SUBSET_END                          (RID_SUBSET_START + 299)
 

svx/source/dialog/charmap.cxx

@@ -1594,6 +1594,41 @@ void SubsetMap::InitList()
                     aAllSubsets.push_back( Subset( 0x1D800, 0x1DAAF, RID_SUBSETSTR_SUTTON_SIGNWRITING ) );
                     break;
 #endif
+#if (U_ICU_VERSION_MAJOR_NUM >= 58)
+                case UBLOCK_ADLAM:
+                    aAllSubsets.push_back( Subset( 0x1E900, 0x1E95F, RID_SUBSETSTR_ADLAM ) );
+                    break;
+                case UBLOCK_BHAIKSUKI:
+                    aAllSubsets.push_back( Subset( 0x11C00, 0x11C6F, RID_SUBSETSTR_BHAIKSUKI ) );
+                    break;
+                case UBLOCK_CYRILLIC_EXTENDED_C:
+                    aAllSubsets.push_back( Subset( 0x1C80, 0x1C8F, RID_SUBSETSTR_CYRILLIC_EXTENDED_C ) );
+                    break;
+                case UBLOCK_GLAGOLITIC_SUPPLEMENT:
+                    aAllSubsets.push_back( Subset( 0x1E000, 0x1E02F, RID_SUBSETSTR_GLAGOLITIC_SUPPLEMENT ) );
+                    break;
+                case UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION:
+                    aAllSubsets.push_back( Subset( 0x16FE0, 0x16FFF, RID_SUBSETSTR_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION ) );
+                    break;
+                case UBLOCK_MARCHEN:
+                    aAllSubsets.push_back( Subset( 0x11C70, 0x11CBF, RID_SUBSETSTR_MARCHEN ) );
+                    break;
+                case UBLOCK_MONGOLIAN_SUPPLEMENT:
+                    aAllSubsets.push_back( Subset( 0x11660, 0x1167F, RID_SUBSETSTR_MONGOLIAN_SUPPLEMENT ) );
+                    break;
+                case UBLOCK_NEWA:
+                    aAllSubsets.push_back( Subset( 0x11400, 0x1147F, RID_SUBSETSTR_NEWA ) );
+                    break;
+                case UBLOCK_OSAGE:
+                    aAllSubsets.push_back( Subset( 0x104B0, 0x104FF, RID_SUBSETSTR_OSAGE ) );
+                    break;
+                case UBLOCK_TANGUT:
+                    aAllSubsets.push_back( Subset( 0x17000, 0x187FF, RID_SUBSETSTR_TANGUT ) );
+                    break;
+                case UBLOCK_TANGUT_COMPONENTS:
+                    aAllSubsets.push_back( Subset( 0x18800, 0x18AFF, RID_SUBSETSTR_TANGUT_COMPONENTS ) );
+                    break;
+#endif
 
             }
 

svx/source/dialog/ucsubset.src

@@ -1079,6 +1079,50 @@ Resource RID_SUBSETMAP
     {
         Text [ en-US ] = "Sutton Signwriting";
     };
+    String RID_SUBSETSTR_ADLAM
+    {
+        Text [ en-US ] = "Adlam";
+    };
+    String RID_SUBSETSTR_BHAIKSUKI
+    {
+        Text [ en-US ] = "Bhaiksuki";
+    };
+    String RID_SUBSETSTR_CYRILLIC_EXTENDED_C
+    {
+        Text [ en-US ] = "Cyrillic Extended-C";
+    };
+    String RID_SUBSETSTR_GLAGOLITIC_SUPPLEMENT
+    {
+        Text [ en-US ] = "Glagolitic Supplement";
+    };
+    String RID_SUBSETSTR_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION
+    {
+        Text [ en-US ] = "Ideographic Symbols and Punctuation";
+    };
+    String RID_SUBSETSTR_MARCHEN
+    {
+        Text [ en-US ] = "Marchen";
+    };
+    String RID_SUBSETSTR_MONGOLIAN_SUPPLEMENT
+    {
+        Text [ en-US ] = "Mongolian Supplement";
+    };
+    String RID_SUBSETSTR_NEWA
+    {
+        Text [ en-US ] = "Newa";
+    };
+    String RID_SUBSETSTR_OSAGE
+    {
+        Text [ en-US ] = "Osage";
+    };
+    String RID_SUBSETSTR_TANGUT
+    {
+        Text [ en-US ] = "Tangut";
+    };
+    String RID_SUBSETSTR_TANGUT_COMPONENTS
+    {
+        Text [ en-US ] = "Tangut Components";
+    };
 };
 
 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */