2007-11-30 Zoltan Varga <vargaz@gmail.com>

[mono.git] / mcs / class / corlib / Mono.Globalization.Unicode / CollationDataStructures.txt

diff --git a/mcs/class/corlib/Mono.Globalization.Unicode/CollationDataStructures.txt b/mcs/class/corlib/Mono.Globalization.Unicode/CollationDataStructures.txt
index e6fb368f6a281cbddb9079362a26958a9a1047d6..0598a278a0c72b74d9dcb700a6457f3eaf7e4e99 100644 (file)
--- a/mcs/class/corlib/Mono.Globalization.Unicode/CollationDataStructures.txt
+++ b/mcs/class/corlib/Mono.Globalization.Unicode/CollationDataStructures.txt
@@ -1,24 +1,11 @@
 * Collation Data structure and code
 
+** This document is not up to date
 
-** General
-
-       I will create a code generator named "collation-builder" (currently
-       create-mscompat-collation-table.cs), which creates collation support
-       source files:
-
-       - collation-tables.h : C header that holds raw constant arrays
-       - CollationTable.cs : C# source that declares raw constant arrays
-
-       The latter one is totally optional. It is created just for ease of
-       debugging in pure managed world.
-
-       CollationSource class is used to represent a culture-specific collation
-       resource set.
-
-       Note that there are many characters whose sortkey cannot be acquired
-       only via those tables. For example, Korean Jamo ((U+1113 - U+115F) has
-       primary keys which is more than 2 bytes.
+       Currently the table generator generates all three kind of files
+       (C header, C# source and binary resources) but only binary resources
+       are used in fact. C# source is useful for debugging. C header is
+       historical.
 
 
 ** Manual tasks required to maintain the source.
@@ -27,15 +14,17 @@
        that is likely not be in sync with the constant arrays.
 
 
-
 ** collation-tables.h
 
+       Note: the structures are similar in MSCompatUnicodeTable.cs but now
+       it is managed code.
+
        typedef struct {
                ushort lcid;
                ushort tailoringIndex;
                ushort tailoringCount;
                short reverseAccentOrder; /* 1:French sort. 0:Normal */
-       } CollationSource;
+       } TailoringInfo;
 
        Those [*] characters will be compressed using CodePointIndexer
        whose max value is char.MaxValue+1.
@@ -76,10 +65,7 @@
        static CodePointIndexer Ignorable;
        static CodePointIndexer WidthCompat;
        static CodePointIndexer CjkCHS;
-       static CodePointIndexer CjkCHT;
-       static CodePointIndexer CjkJA;
-       static CodePointIndexer CjkKO;
-       static CodePointIndexer CjkKOLevel1;
+       static CodePointIndexer Cjk;
 
 ** CollatorSource.cs
 
@@ -96,20 +82,11 @@
        static ushort [] cjkKO;
        static byte [] cjkKOlv2;
 
-       class CollationSource // instantiated for each CultureInfo
+       class TailoringInfo // instantiated for each CultureInfo
        {
                // Primary constants
                int tailoringIndex;
                int tailoringCount;
-               bool reverseAccentOrder;
-
-               // This array is set according to CJK type, and CJK type
-               // will be hardcoded, being identified from LCID.
-               ushort [] cjk;
-
-               // For Korean, level2 table is specially treated.
-
-               // Computed values for optimization in use.
-               byte [*] hasTailoringHead;
-               byte [*] hasTailoringTail;
+               bool frenchSort;
        }
+