ICU-0 latest changes for Unicode generation

X-SVN-Rev: 16954

tools/unicodetools/com/ibm/text/UCD/GenerateData.java

@@ -5,8 +5,8 @@
 *******************************************************************************
 *
 * $Source: /xsrl/Nsvn/icu/unicodetools/com/ibm/text/UCD/GenerateData.java,v $
-* $Date: 2004/03/11 19:03:17 $
-* $Revision: 1.35 $
+* $Date: 2004/12/15 02:39:25 $
+* $Revision: 1.36 $
 *
 *******************************************************************************
 */
@@ -793,7 +793,7 @@ public class GenerateData implements UCD_Types {
         log.println("@Part1 # Character by character test");
         log.println("# All characters not explicitly occurring in c1 of Part 1 have identical NFC, D, KC, KD forms.");
         log.println("#");
-
+        
         for (int ch = 0; ch < 0x10FFFF; ++ch) {
             Utility.dot(ch);
             if (!Default.ucd().isAssigned(ch)) continue;
@@ -846,6 +846,42 @@ public class GenerateData implements UCD_Types {
             writeLine("a" + sample + UTF32.valueOf32(ch) + "b", log, false);
             writeLine("a" + UTF32.valueOf32(ch) + sample + "b", log, false);
         }
+        
+        System.out.println("Writing Part 3");
+        log.println("#");
+        log.println("@Part3 # PRI #29 Test");
+        log.println("#");
+        
+        Set prilist = new TreeSet();
+        
+        for (int ch = 0; ch < 0x10FFFF; ++ch) {
+            Utility.dot(ch);
+            if (!Default.ucd().isAssigned(ch)) continue;
+            if (Default.ucd().isPUA(ch)) continue;
+            if (0xAC00 <= ch && ch <= 0xD7FF) { // skip most
+            	if (((ch - 0xAC00) % 91) != 0) continue;
+            }
+           // also gather data for pri29 test
+            if (ch == 0x09CB) {
+            	System.out.println("debug");
+            }
+            if (Default.ucd().getDecompositionType(ch) != CANONICAL) continue;
+            //if (!Default.nfc().isNormalized(ch)) continue;
+            String s = Default.ucd().getDecompositionMapping(ch);
+            if (UTF16.hasMoreCodePointsThan(s, 2)) continue;
+            if (!UTF16.hasMoreCodePointsThan(s, 1)) continue;
+            int c1 = UTF16.charAt(s, 0);
+            int c2 = UTF16.charAt(s, UTF16.getCharCount(c1));
+            if (Default.ucd().getCombiningClass(c1) != 0) continue;
+            if (Default.ucd().getCombiningClass(c2) != 0) continue;
+            prilist.add(UTF16.valueOf(c1) + '\u0334' + UTF16.valueOf(c2));
+        }
+        Utility.fixDot();
+        
+        for (Iterator it = prilist.iterator(); it.hasNext();) {
+            writeLine((String)it.next(),log, false);
+        }
+
         Utility.fixDot();
         log.println("#");
         log.println("# END OF FILE");

tools/unicodetools/com/ibm/text/UCD/MakeUnicodeFiles.txt

@@ -1,5 +1,5 @@
-Generate: 
-DeltaVersion: 8
+Generate: Derived.*
+DeltaVersion: 9
 CopyrightYear: 2005
 
 File: uax29/GraphemeBreakProperty

tools/unicodetools/com/ibm/text/UCD/SpecialCasingHeader.txt

@@ -32,8 +32,55 @@
 # <ISO_3166_code> := 2-letter ISO country code,
 # <ISO_639_code> :=  2-letter ISO language code
 #
-# A context is one of the following, as defined in the Unicode Standard:
-#   Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot, Not_Before_Dot, After_I
+# A context for a character C is one of the following. This overrides Table
+# 3-13. Context Specification for Casing on p. 89 of The Unicode Standard,
+# Version 4.0.
+#
+# Definitions
+# - The property "cased" is defined in D47 on that same page (p. 89)
+# - A character C is defined to be "case-ignorable" if it meets either of the
+# following criteria:
+#  A. The general category of C is Nonspacing Mark (Mn), or Enclosing Mark
+#     (Me), or Format Control (Cf), or Letter Modifier (Lm), or 
+#     Symbol Modifier (Sk)
+#  B. C is a MidLetter as defined in UAX #29
+# - A "case-ignorable sequence" is a sequence of zero or more case-ignorable
+# characters.
+#
+# A description of each context is followed by the equivalent regular
+# expression(s) describing the context before C and/or the context after C.
+# The regular expression uses the syntax of UTS #18,  with one addition: 
+# "!" means that the expression does not match. All regular expressions
+# below are case-sensitive.
+#
+# Context: Final_Sigma
+# Description: C is preceded by a sequence consisting of a cased letter and
+# a case-ignorable sequence, and C is not followed by a sequence consisting 
+# of an ignorable sequence
+# and then a cased letter.
+# Before C: \p{cased} (\p{case-ignorable})*
+# After C: !( (\p{case-ignorable})* \p{cased} )
+#
+# Context: After_Soft_Dotted
+# Description: The last preceding character with combining class of zero before C was
+# Soft_Dotted,  and there is no intervening combining character class 230 (ABOVE).
+# Before C: [\p{Soft_Dotted}] ([^{cc=230} {cc=0}])*
+#
+# Context: More_Above
+# Description: C is followed by one or more characters of combining class
+# 230 (ABOVE) in the combining character sequence.
+# After C: [^\p{cc=0}]* [\p{cc=230}]
+#
+# Context: Before_Dot
+# Description: C is followed by combining dot above (U+0307). Any sequence
+# of characters with a combining class that is neither 0 nor 230 may intervene
+# between the current character and the combining dot above.
+# After C: ([^\p{cc=230} \p{cc=0}])* [\u0307]
+#
+# Context: After_I
+# Description: The last preceding base character was an uppercase I, and
+# there is no intervening combining character class 230 (ABOVE).
+# Before C: [I] ([^\p{cc=230} \p{cc=0}])
 #
 # Parsers of this file must be prepared to deal with future additions to this format:
 #  * Additional contexts

tools/unicodetools/com/ibm/text/UCD/UnicodeInvariants.txt

@@ -65,6 +65,7 @@ $Alphabetic ⊃ [$Uppercase $Lowercase]
 
 $ID_Start ⊇ $×ID_Start
 $ID_Continue ⊇ $×ID_Continue
+[$Decomposition_Type:Canonical - $Full_Composition_Exclusion] = [$×Decomposition_Type:Canonical - $×Full_Composition_Exclusion]
 
 #$age:4.0.1 = $age4.0.0