[Libreoffice-commits] core.git: i18npool/source

[Caolán McNamara]

 i18npool/source/characterclassification/cclass_unicode_parser.cxx |   13 ++++++++++
 1 file changed, 13 insertions(+)

New commits:
commit b6807fd38373c98adc276697c24dcfcdf9471ac0
Author: Caolán McNamara <caolanm at redhat.com>
Date:   Thu Sep 12 14:21:32 2013 +0100

    Resolves: fdo#61754 allow midletters in field name tokens
    
    Change-Id: I77cea3c1d2210435109ca0b6f762b6aea478e91b

diff --git a/i18npool/source/characterclassification/cclass_unicode_parser.cxx b/i18npool/source/characterclassification/cclass_unicode_parser.cxx
index 3f3de5b..488b62e 100644
--- a/i18npool/source/characterclassification/cclass_unicode_parser.cxx
+++ b/i18npool/source/characterclassification/cclass_unicode_parser.cxx
@@ -666,6 +666,19 @@ UPT_FLAG_TYPE cclass_Unicode::getFlagsExtended( const sal_Unicode* aStr, sal_Int
         case U_SPACE_SEPARATOR :
             return ((nTypes & KParseTokens::IGNORE_LEADING_WS) ?
                 TOKEN_CHAR_DONTCARE : (bStart ? TOKEN_CHAR_WORD : (TOKEN_CHAR_DONTCARE | TOKEN_WORD_SEP | TOKEN_VALUE_SEP) ));
+        case U_OTHER_PUNCTUATION:
+            // fdo#61754 Lets see (if we not at the start) if this is midletter
+            // punctuation and allow it in a word if it is similarly to
+            // U_NON_SPACING_MARK
+            if (bStart || U_WB_MIDLETTER != u_getIntPropertyValue(c, UCHAR_WORD_BREAK))
+                return TOKEN_ILLEGAL;
+            else
+            {
+                //allowing it to continue the word
+                return (nTypes & KParseTokens::UNI_OTHER_LETTER) ?
+                    TOKEN_WORD : TOKEN_ILLEGAL;
+            }
+            break;
     }
 
     return TOKEN_ILLEGAL;