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

[László Németh]

 i18npool/source/collator/data/hu_charset.txt |   14 ++++++++++++++
 1 file changed, 14 insertions(+)

New commits:
commit 7b1eb6313c0d2621c364df1724c69d28f8267841
Author: László Németh <nemeth at numbertext.org>
Date:   Tue Mar 27 22:42:18 2018 +0200

    tdf#116666 fix Hungarian sorting
    
    Apply the following extra requirements of Hungarian orthography
    for sorting words and sentences:
    
    – expand simplified double consonants;
    
    – ignore spaces and hyphens;
    
    – prefer lower case homonyms.
    
    Note: automatic sorting is better this way, but it's still not error-free.
    
    Important advantage, that now it's *possible* to fix all errors
    in a semi-automatic way, using soft hyphens. Inserting them in bad
    or ambiguous character positions will fix all automatic sortings later.
    
    Example with consonant "gy", simplified form of long "gygy" is the
    ambiguous "ggy" (it can be "g" and "gy", too, as in "meggyőz"):
    
    = Bad =   = Now =   = Good (corrected, "|" signs soft hyphen) =
    megbíz    megbíz    megbíz
    meggyíz   megzavar  meg|győz
    meggyőz   megye     megzavar
    megzavar  meggyíz   megye
    megye     meggyőz   meggyíz
    megyünk   megyünk   megyünk
    
    Change-Id: Ia84f264ad9ea4cdebe5f3ea22212a9594b4fe44d
    Reviewed-on: https://gerrit.libreoffice.org/51973
    Tested-by: Jenkins <ci at libreoffice.org>
    Reviewed-by: László Németh <nemeth at numbertext.org>

diff --git a/i18npool/source/collator/data/hu_charset.txt b/i18npool/source/collator/data/hu_charset.txt
index a63d4bab9c45..2b7288e7d8a6 100644
--- a/i18npool/source/collator/data/hu_charset.txt
+++ b/i18npool/source/collator/data/hu_charset.txt
@@ -19,6 +19,11 @@
 #
 # Collation of Hungarian letters
 #
+
+[caseLevel on]
+[caseFirst lower]
+[alternate shifted]
+
 & c < cs <<< Cs <<< CS
 & d < dz <<< DZ < dzs <<< Dzs <<< DZS
 & g < gy <<< Gy <<< GY
@@ -30,3 +35,12 @@
 & u < ü <<< Ü <<< ű <<< Ű
 & z < zs <<< Zs <<< ZS
 
+& cs <<< ccs / cs <<< Ccs / cs <<< CCs / cs <<< CCS / cs
+& dz <<< ddz / dz <<< Ddz / dz <<< DDz / dz <<< DDZ / dz
+& dzs <<< ddzs / dzs <<< Ddzs / dzs <<< DDzs / dzs <<< DDZs / dzs <<< DDZS / dzs
+& gy <<< ggy / gy <<< Ggy / gy <<< GGy / gy <<< GGY / gy
+& ly <<< lly / ly <<< Lly / ly <<< LLy / ly <<< LLY / ly
+& ny <<< nny / ny <<< Nny / ny <<< NNy / ny <<< NNY / ny
+& sz <<< ssz / sz <<< Ssz / sz <<< SSz / sz <<< SSZ / sz
+& ty <<< tty / ty <<< Tty / ty <<< TTy / ty <<< TTY / ty
+& zs <<< zzs / zs <<< Zzs / zs <<< ZZs / zs <<< ZZS / zs