libreoffice/openoffice.org-3.1.1.ooo105784.vcl.sniffscriptforsubs.patch

diff -ru vcl.orig/unx/source/fontmanager/fontconfig.cxx vcl/unx/source/fontmanager/fontconfig.cxx
--- vcl.orig/unx/source/fontmanager/fontconfig.cxx	2009-10-08 13:25:00.000000000 +0100
+++ vcl/generic/fontmanager/fontconfig.cxx	2009-10-08 13:51:51.000000000 +0100
@@ -92,6 +92,9 @@
 
 #include "sal/alloca.h"
 
+#include <i18nutil/unicode.hxx>  //unicode::getUnicodeScriptType
+#include <com/sun/star/i18n/ScriptType.hdl> //ScriptType
+
 #include <utility>
 #include <algorithm>
 
@@ -1108,6 +1111,138 @@
     }
 }
 
+static const char* pick_sample_language(const sal_uInt32 cCode)
+{
+    using namespace ::com::sun::star::i18n;
+
+    static ScriptTypeList aScripts[] =
+    {
+        { UnicodeScript_kBasicLatin, UnicodeScript_kBasicLatin, UnicodeScript_kBasicLatin },
+        { UnicodeScript_kLatin1Supplement, UnicodeScript_kLatin1Supplement, UnicodeScript_kLatin1Supplement },
+        { UnicodeScript_kLatinExtendedA, UnicodeScript_kLatinExtendedA, UnicodeScript_kLatinExtendedA },
+        { UnicodeScript_kLatinExtendedB, UnicodeScript_kLatinExtendedB, UnicodeScript_kLatinExtendedB },
+        { UnicodeScript_kGreek, UnicodeScript_kGreek, UnicodeScript_kGreek },
+        { UnicodeScript_kCyrillic, UnicodeScript_kCyrillic, UnicodeScript_kCyrillic },
+        { UnicodeScript_kArmenian, UnicodeScript_kArmenian, UnicodeScript_kArmenian },
+        { UnicodeScript_kHebrew, UnicodeScript_kHebrew, UnicodeScript_kHebrew },
+        { UnicodeScript_kArabic, UnicodeScript_kArabic, UnicodeScript_kArabic },
+        { UnicodeScript_kSyriac, UnicodeScript_kSyriac, UnicodeScript_kSyriac },
+        { UnicodeScript_kThaana, UnicodeScript_kThaana, UnicodeScript_kThaana },
+        { UnicodeScript_kDevanagari, UnicodeScript_kDevanagari, UnicodeScript_kDevanagari },
+        { UnicodeScript_kBengali, UnicodeScript_kBengali, UnicodeScript_kBengali },
+        { UnicodeScript_kGurmukhi, UnicodeScript_kGurmukhi, UnicodeScript_kGurmukhi },
+        { UnicodeScript_kGujarati, UnicodeScript_kGujarati, UnicodeScript_kGujarati },
+        { UnicodeScript_kOriya, UnicodeScript_kOriya, UnicodeScript_kOriya },
+        { UnicodeScript_kTamil, UnicodeScript_kTamil, UnicodeScript_kTamil },
+        { UnicodeScript_kTelugu, UnicodeScript_kTelugu, UnicodeScript_kTelugu },
+        { UnicodeScript_kKannada, UnicodeScript_kKannada, UnicodeScript_kKannada },
+        { UnicodeScript_kMalayalam, UnicodeScript_kMalayalam, UnicodeScript_kMalayalam },
+        { UnicodeScript_kSinhala, UnicodeScript_kSinhala, UnicodeScript_kSinhala },
+        { UnicodeScript_kThai, UnicodeScript_kThai, UnicodeScript_kThai },
+        { UnicodeScript_kLao, UnicodeScript_kLao, UnicodeScript_kLao },
+        { UnicodeScript_kTibetan, UnicodeScript_kTibetan, UnicodeScript_kTibetan },
+        { UnicodeScript_kMyanmar, UnicodeScript_kMyanmar, UnicodeScript_kMyanmar },
+        { UnicodeScript_kGeorgian, UnicodeScript_kGeorgian, UnicodeScript_kGeorgian },
+        { UnicodeScript_kHangulJamo, UnicodeScript_kHangulJamo, UnicodeScript_kHangulJamo },
+        { UnicodeScript_kEthiopic, UnicodeScript_kEthiopic, UnicodeScript_kEthiopic },
+        { UnicodeScript_kCherokee, UnicodeScript_kCherokee, UnicodeScript_kCherokee },
+        { UnicodeScript_kUnifiedCanadianAboriginalSyllabics, 
+            UnicodeScript_kUnifiedCanadianAboriginalSyllabics, 
+            UnicodeScript_kUnifiedCanadianAboriginalSyllabics },
+        { UnicodeScript_kKhmer, UnicodeScript_kKhmer, UnicodeScript_kKhmer },
+        { UnicodeScript_kMongolian, UnicodeScript_kMongolian, UnicodeScript_kMongolian },
+        { UnicodeScript_kLatinExtendedAdditional, UnicodeScript_kLatinExtendedAdditional,
+          UnicodeScript_kLatinExtendedAdditional },
+        { UnicodeScript_kGreekExtended, UnicodeScript_kGreekExtended, UnicodeScript_kGreekExtended },
+        { UnicodeScript_kHiragana, UnicodeScript_kHiragana, UnicodeScript_kHiragana },
+        { UnicodeScript_kKatakana, UnicodeScript_kKatakana, UnicodeScript_kKatakana },
+        { UnicodeScript_kHangulCompatibilityJamo, UnicodeScript_kHangulCompatibilityJamo, 
+          UnicodeScript_kHangulCompatibilityJamo },
+        { UnicodeScript_kHangulSyllable, UnicodeScript_kHangulSyllable,
+          UnicodeScript_kHangulSyllable },
+        { UnicodeScript_kArabicPresentationB, UnicodeScript_kArabicPresentationB,
+          UnicodeScript_kArabicPresentationB },
+        { UnicodeScript_kScriptCount, UnicodeScript_kScriptCount, UnicodeScript_kScriptCount }
+    };
+
+    switch (unicode::getUnicodeScriptType(cCode, aScripts, UnicodeScript_kScriptCount))
+    {
+        case UnicodeScript_kBasicLatin:
+        case UnicodeScript_kLatin1Supplement:
+        case UnicodeScript_kLatinExtendedA:
+        case UnicodeScript_kLatinExtendedB:
+        case UnicodeScript_kLatinExtendedAdditional:
+            return "en";
+        case UnicodeScript_kGreek:
+        case UnicodeScript_kGreekExtended:
+            return "el";
+        case UnicodeScript_kCyrillic:
+            return "ru";
+        case UnicodeScript_kArmenian:
+            return "hy";
+        case UnicodeScript_kHebrew:
+            return "he";
+        case UnicodeScript_kArabic:
+        case UnicodeScript_kArabicPresentationB:
+            return "ar";
+        case UnicodeScript_kSyriac:
+            return "syr";
+        case UnicodeScript_kThaana:
+            return "dv";
+        case UnicodeScript_kDevanagari:
+            return "hi";
+        case UnicodeScript_kBengali:
+            return "bn";
+        case UnicodeScript_kGurmukhi:
+            return "pa";
+        case UnicodeScript_kGujarati:
+            return "gu";
+        case UnicodeScript_kOriya:
+            return "or";
+        case UnicodeScript_kTamil:
+            return "ta";
+        case UnicodeScript_kTelugu:
+            return "te";
+        case UnicodeScript_kKannada:
+            return "ka";
+        case UnicodeScript_kMalayalam:
+            return "ml";
+        case UnicodeScript_kSinhala:
+            return "si";
+        case UnicodeScript_kThai:
+            return "th";
+        case UnicodeScript_kLao:
+            return "lo";
+        case UnicodeScript_kTibetan:
+            return "bo";
+        case UnicodeScript_kMyanmar:
+            return "my";
+        case UnicodeScript_kGeorgian:
+            return "ka";
+        case UnicodeScript_kHangulJamo:
+        case UnicodeScript_kHangulCompatibilityJamo:
+        case UnicodeScript_kHangulSyllable:
+            return "ko";
+        case UnicodeScript_kEthiopic:
+            return "am";
+        case UnicodeScript_kCherokee:
+            return "chr";
+        case UnicodeScript_kUnifiedCanadianAboriginalSyllabics:
+            return "ui";
+        case UnicodeScript_kKhmer:
+            return "km";
+        case UnicodeScript_kMongolian:
+            return "mn";
+        case UnicodeScript_kHiragana:
+        case UnicodeScript_kKatakana:
+            return "ja";
+        default:
+            break;
+    }
+
+    return NULL;
+}
+
 rtl::OUString PrintFontManager::Substitute(const rtl::OUString& rFontName,
     rtl::OUString& rMissingCodes, const rtl::OString &rLangAttrib,
     italic::type &rItalic, weight::type &rWeight,
@@ -1128,14 +1263,13 @@
     const FcChar8* pTargetNameUtf8 = (FcChar8*)aTargetName.getStr();
     rWrapper.FcPatternAddString( pPattern, FC_FAMILY, pTargetNameUtf8 );
 
+    const FcChar8* pLangAttribUtf8 = NULL;
     if( rLangAttrib.getLength() )
     {
-        const FcChar8* pLangAttribUtf8;
         if (rLangAttrib.equalsIgnoreAsciiCase(OString(RTL_CONSTASCII_STRINGPARAM("pa-in"))))
             pLangAttribUtf8 = (FcChar8*)"pa";
         else
             pLangAttribUtf8 = (FcChar8*)rLangAttrib.getStr();
-        rWrapper.FcPatternAddString( pPattern, FC_LANG, pLangAttribUtf8 );
     }
 
     // Add required Unicode characters, if any
@@ -1147,11 +1281,16 @@
            // also handle unicode surrogates
            const sal_uInt32 nCode = rMissingCodes.iterateCodePoints( &nStrIndex );
            rWrapper.FcCharSetAddChar( unicodes, nCode );
+           if (!pLangAttribUtf8)
+               pLangAttribUtf8 = (const FcChar8*)pick_sample_language(nCode);
        }
        rWrapper.FcPatternAddCharSet( pPattern, FC_CHARSET, unicodes);
        rWrapper.FcCharSetDestroy( unicodes );
     }
 
+    if( pLangAttribUtf8 )
+        rWrapper.FcPatternAddString( pPattern, FC_LANG, pLangAttribUtf8 );
+
     addtopattern(rWrapper, pPattern, rItalic, rWeight, rWidth, rPitch);
 
     // query fontconfig for a substitute