Fix icu version checks.

commit 30c303 "Make charmap.cxx compile with icu >= 4.4." was incomplete
and had wrong version checks. After ICU 4.8 (4.8.1.1) the next version
of ICU was 49 (49.1) so U_ICU_VERSION_MAJOR_NUM contains two digets (49),
earlier that it was just one digit (4). The correct header to include to
do version checks is unicode/uversion.h. USCRIPT_MANDAEAN is the old
alias of USCRIPT_MANDAIC (same numeric value). U_JG_FARSI_YEH is only
available since ICU 4.4. Note that on older icu versions (4.2.1) the
200B (ZWSP) Zero Width Space breakiterator testcase fails (others
succeed).

Change-Id: If73c1402239a28546077437e9382f0bd38642bad
Reviewed-on: https://gerrit.libreoffice.org/4139
Reviewed-by: Luboš Luňák <l.lunak@suse.cz>
Tested-by: Luboš Luňák <l.lunak@suse.cz>

4 files changed, 13 insertions, 6 deletions

diff --git a/i18npool/qa/cppunit/test_breakiterator.cxx b/i18npool/qa/cppunit/test_breakiterator.cxx
index b3ec68fa969a..4ba6a79013a5 100644
--- a/i18npool/qa/cppunit/test_breakiterator.cxx
+++ b/i18npool/qa/cppunit/test_breakiterator.cxx
@@ -19,7 +19,7 @@
 #include <com/sun/star/i18n/WordType.hpp>
 #include <unotest/bootstrapfixturebase.hxx>
 
-#include <unicode/uvernum.h>
+#include <unicode/uversion.h>
 
 #include <rtl/strbuf.hxx>
 #include <rtl/ustrbuf.hxx>
@@ -236,6 +236,8 @@ void TestBreakIterator::testWordBoundaries()
     }
 
     //See https://bugs.freedesktop.org/show_bug.cgi?id=49629
+    //Note that the breakiterator test will fail on older icu versions
+    //(4.2.1) for the 200B (ZWSP) Zero Width Space testcase.
     sal_Unicode aBreakTests[] = { ' ', 1, 2, 3, 4, 5, 6, 7, 0x91, 0x92, 0x200B, 0xE8FF, 0xF8FF };
     for (int mode = i18n::WordType::ANY_WORD; mode <= i18n::WordType::WORD_COUNT; ++mode)
     {
diff --git a/i18nutil/source/utility/unicode.cxx b/i18nutil/source/utility/unicode.cxx
index 2c2dd421ca4e..b46a7f61b2c0 100644
--- a/i18nutil/source/utility/unicode.cxx
+++ b/i18nutil/source/utility/unicode.cxx
@@ -826,6 +826,9 @@ OString SAL_CALL unicode::getExemplerLanguageForUScriptCode(UScriptCode eScript)
         case USCRIPT_TAI_VIET:
             sRet = "blt";
             break;
+        case USCRIPT_MANDAEAN: /* Aliased to USCRIPT_MANDAIC in icu 4.6. */
+            sRet = "mic";
+            break;
 #if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 4)
         case USCRIPT_NABATAEAN: //no language with an assigned code yet
             sRet = "mis";
@@ -833,9 +836,6 @@ OString SAL_CALL unicode::getExemplerLanguageForUScriptCode(UScriptCode eScript)
         case USCRIPT_PALMYRENE: //no language with an assigned code yet
             sRet = "mis";
             break;
-        case USCRIPT_MANDAIC:
-            sRet = "mic";
-            break;
         case USCRIPT_BAMUM:
             sRet = "bax";
             break;
diff --git a/svx/source/dialog/charmap.cxx b/svx/source/dialog/charmap.cxx
index bc6c83e137cc..907d9f80b083 100644
--- a/svx/source/dialog/charmap.cxx
+++ b/svx/source/dialog/charmap.cxx
@@ -1302,7 +1302,7 @@ void SubsetMap::InitList()
                 case UBLOCK_DOMINO_TILES:
                     aAllSubsets.push_back( Subset( 0x1F030, 0x1F09F, RID_SUBSETSTR_DOMINO_TILES ) );
                     break;
-#if U_ICU_VERSION_MAJOR_NUM >= 44
+#if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 4)
                 case UBLOCK_SAMARITAN:
                     aAllSubsets.push_back( Subset( 0x0800, 0x083F, RID_SUBSETSTR_SAMARITAN ) );
                     break;
@@ -1382,7 +1382,7 @@ void SubsetMap::InitList()
                     aAllSubsets.push_back( Subset( 0x2A700, 0x2B73F, RID_SUBSETSTR_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C ) );
                     break;
 #endif
-#if U_ICU_VERSION_MAJOR_NUM >= 46
+#if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 6)
                 case UBLOCK_MANDAIC:
                     aAllSubsets.push_back( Subset( 0x0840, 0x085F, RID_SUBSETSTR_MANDAIC ) );
                     break;
@@ -1420,6 +1420,7 @@ void SubsetMap::InitList()
                     aAllSubsets.push_back( Subset( 0x2B740, 0x2B81F, RID_SUBSETSTR_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D ) );
                     break;
 #endif
+// Note ICU version 49 (NOT 4.9), so the MAJOR_NUM is two digits.
 #if U_ICU_VERSION_MAJOR_NUM >= 49
                 case UBLOCK_ARABIC_EXTENDED_A:
                     aAllSubsets.push_back( Subset( 0x08A0, 0x08FF, RID_SUBSETSTR_ARABIC_EXTENDED_A ) );
diff --git a/sw/source/core/text/porlay.cxx b/sw/source/core/text/porlay.cxx
index b820b8bbb3eb..edc8458689e5 100644
--- a/sw/source/core/text/porlay.cxx
+++ b/sw/source/core/text/porlay.cxx
@@ -72,7 +72,11 @@ using namespace i18n::ScriptType;
 #define isRehChar(c)        IS_JOINING_GROUP((c), REH)
 #define isTehMarbutaChar(c) IS_JOINING_GROUP((c), TEH_MARBUTA)
 #define isWawChar(c)        IS_JOINING_GROUP((c), WAW)
+#if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 4)
 #define isYehChar(c)        (IS_JOINING_GROUP((c), YEH) || IS_JOINING_GROUP((c), FARSI_YEH))
+#else
+#define isYehChar(c)        IS_JOINING_GROUP((c), YEH)
+#endif
 #define isSeenOrSadChar(c)  (IS_JOINING_GROUP((c), SAD) || IS_JOINING_GROUP((c), SEEN))
 
 bool isTransparentChar ( sal_Unicode cCh )