You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by sa...@apache.org on 2011/01/06 15:54:49 UTC

svn commit: r1055904 [1/3] - in /lucene/dev/branches/branch_3x: ./ lucene/ lucene/contrib/icu/ lucene/contrib/icu/src/tools/java/org/apache/lucene/analysis/icu/ lucene/src/java/org/apache/lucene/analysis/standard/ lucene/src/test/org/apache/lucene/anal...

Author: sarowe
Date: Thu Jan  6 14:54:48 2011
New Revision: 1055904

URL: http://svn.apache.org/viewvc?rev=1055904&view=rev
Log:
LUCENE-2847: Support all of unicode, including supplementary code points above the basic multilingual plane, in StandardTokenizer and UAX29URLEmailTokenizer.

Added:
    lucene/dev/branches/branch_3x/lucene/contrib/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateJFlexSupplementaryMacros.java
      - copied unchanged from r1055877, lucene/dev/trunk/modules/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateJFlexSupplementaryMacros.java
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro
      - copied, changed from r1055877, lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro
Modified:
    lucene/dev/branches/branch_3x/   (props changed)
    lucene/dev/branches/branch_3x/lucene/   (props changed)
    lucene/dev/branches/branch_3x/lucene/CHANGES.txt
    lucene/dev/branches/branch_3x/lucene/build.xml
    lucene/dev/branches/branch_3x/lucene/contrib/icu/build.xml
    lucene/dev/branches/branch_3x/lucene/contrib/icu/src/tools/java/org/apache/lucene/analysis/icu/   (props changed)
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/   (props changed)
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/ASCIITLD.jflex-macro
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java
    lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.jflex
    lucene/dev/branches/branch_3x/lucene/src/test/org/apache/lucene/analysis/   (props changed)
    lucene/dev/branches/branch_3x/lucene/src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java
    lucene/dev/branches/branch_3x/lucene/src/test/org/apache/lucene/analysis/TestUAX29URLEmailTokenizer.java
    lucene/dev/branches/branch_3x/solr/   (props changed)

Modified: lucene/dev/branches/branch_3x/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/CHANGES.txt?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/branch_3x/lucene/CHANGES.txt Thu Jan  6 14:54:48 2011
@@ -228,12 +228,14 @@ API Changes
   opens internally when apply deletions or creating a near-real-time
   reader.  (Earwin Burrfoot via Mike McCandless)
 
-* LUCENE-2167,LUCENE-2699,LUCENE-2763: StandardTokenizer/Analyzer now 
-  implement the Word Break rules from the Unicode 6.0.0 Text Segmentation 
-  algorithm (UAX#29).  
+* LUCENE-2167,LUCENE-2699,LUCENE-2763,LUCENE-2847: StandardTokenizer/Analyzer
+  in common/standard/ now implement the Word Break rules from the Unicode 6.0.0
+  Text Segmentation algorithm (UAX#29), covering the full range of Unicode code
+  points, including values from U+FFFF to U+10FFFF
    
-  ClassicTokenizer/Analyzer retains the old StandardTokenizer/Analyzer
-  implementation and behavior.
+  ClassicTokenizer/Analyzer retains the old (pre-Lucene 3.1) StandardTokenizer/
+  Analyzer implementation and behavior.  Only the Unicode Basic Multilingual
+  Plane (code points from U+0000 to U+FFFF) is covered.
 
   UAX29URLEmailTokenizer tokenizes URLs and E-mail addresses according to the
   relevant RFCs, in addition to implementing the UAX#29 Word Break rules.

Modified: lucene/dev/branches/branch_3x/lucene/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/build.xml?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/build.xml (original)
+++ lucene/dev/branches/branch_3x/lucene/build.xml Thu Jan  6 14:54:48 2011
@@ -519,7 +519,14 @@
   <!-- Build the JFlex files into the source tree                         -->
   <!-- ================================================================== -->
 
-  <target name="jflex" depends="jflex-check,clean-jflex,jflex-StandardAnalyzer,jflex-UAX29URLEmailTokenizer" />
+  <target name="jflex" depends="jflex-check,clean-jflex,gen-uax29-supp-macros,
+                                jflex-StandardAnalyzer,jflex-UAX29URLEmailTokenizer"/>
+
+  <target name="gen-uax29-supp-macros">
+    <subant target="gen-uax29-supp-macros">
+       <fileset dir="contrib/icu" includes="build.xml"/>
+    </subant>
+  </target>
 
   <target name="jflex-StandardAnalyzer" depends="init,jflex-check,gen-tlds" if="jflex.present">
     <taskdef classname="jflex.anttask.JFlexTask" name="jflex">

Modified: lucene/dev/branches/branch_3x/lucene/contrib/icu/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/icu/build.xml?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/icu/build.xml (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/icu/build.xml Thu Jan  6 14:54:48 2011
@@ -80,7 +80,24 @@ are part of the ICU4C package. See http:
       <arg value="${rbbi.dst.dir}"/>
     </java>
   </target>
-			
+
+  <property name="uax29.supp.macros.output.file" 
+            location="../../src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro"/>
+
+  <target name="gen-uax29-supp-macros" depends="compile-tools">
+    <java
+      classname="org.apache.lucene.analysis.icu.GenerateJFlexSupplementaryMacros"
+      dir="."
+      fork="true"
+      failonerror="true"
+      output="${uax29.supp.macros.output.file}">
+      <classpath>
+      	<path refid="additional.dependencies"/>
+      	<pathelement location="${build.dir}/classes/tools"/>
+      </classpath>
+    </java>
+  </target>
+  
   <target name="compile-tools">
     <compile
       srcdir="src/tools/java"

Modified: lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/ASCIITLD.jflex-macro
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/ASCIITLD.jflex-macro?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/ASCIITLD.jflex-macro (original)
+++ lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/ASCIITLD.jflex-macro Thu Jan  6 14:54:48 2011
@@ -15,8 +15,8 @@
  */
 
 // Generated from IANA Root Zone Database <http://www.internic.net/zones/root.zone>
-// file version from Tuesday, December 7, 2010 12:34:02 PM UTC
-// generated on Tuesday, December 7, 2010 4:53:37 PM UTC
+// file version from Thursday, January 6, 2011 12:34:09 PM UTC
+// generated on Thursday, January 6, 2011 2:34:39 PM UTC
 // by org.apache.lucene.analysis.standard.GenerateJflexTLDMacros
 
 ASCIITLD = "." (
@@ -306,6 +306,7 @@ ASCIITLD = "." (
 	| [xX][nN]--[pP]1[aA][iI]
 	| [xX][nN]--[pP][gG][bB][sS]0[dD][hH]
 	| [xX][nN]--[wW][gG][bB][hH]1[cC]
+	| [xX][nN]--[wW][gG][bB][lL]6[aA]
 	| [xX][nN]--[xX][kK][cC]2[aA][lL]3[hH][yY][eE]2[aA]
 	| [xX][nN]--[yY][gG][bB][iI]2[aA][mM][mM][xX]
 	| [xX][nN]--[zZ][cC][kK][zZ][aA][hH]

Copied: lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro (from r1055877, lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro)
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro?p2=lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro&p1=lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro&r1=1055877&r2=1055904&rev=1055904&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro (original)
+++ lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro Thu Jan  6 14:54:48 2011
@@ -1,15 +1,15 @@
 ALetterSupp = (
-	  ([\ud80d][\uDC00-\uDC2E])
+	  ([\ud804][\uDC03-\uDC37\uDC83-\uDCAF])
 	| ([\ud80c][\uDC00-\uDFFF])
-	| ([\ud809][\uDC00-\uDC62])
-	| ([\ud808][\uDC00-\uDF6E])
-	| ([\ud81a][\uDC00-\uDE38])
-	| ([\ud804][\uDC03-\uDC37\uDC83-\uDCAF])
-	| ([\ud835][\uDC00-\uDC54\uDC56-\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDEA5\uDEA8-\uDEC0\uDEC2-\uDEDA\uDEDC-\uDEFA\uDEFC-\uDF14\uDF16-\uDF34\uDF36-\uDF4E\uDF50-\uDF6E\uDF70-\uDF88\uDF8A-\uDFA8\uDFAA-\uDFC2\uDFC4-\uDFCB])
 	| ([\ud801][\uDC00-\uDC9D])
 	| ([\ud800][\uDC00-\uDC0B\uDC0D-\uDC26\uDC28-\uDC3A\uDC3C\uDC3D\uDC3F-\uDC4D\uDC50-\uDC5D\uDC80-\uDCFA\uDD40-\uDD74\uDE80-\uDE9C\uDEA0-\uDED0\uDF00-\uDF1E\uDF30-\uDF4A\uDF80-\uDF9D\uDFA0-\uDFC3\uDFC8-\uDFCF\uDFD1-\uDFD5])
+	| ([\ud81a][\uDC00-\uDE38])
+	| ([\ud809][\uDC00-\uDC62])
+	| ([\ud835][\uDC00-\uDC54\uDC56-\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDEA5\uDEA8-\uDEC0\uDEC2-\uDEDA\uDEDC-\uDEFA\uDEFC-\uDF14\uDF16-\uDF34\uDF36-\uDF4E\uDF50-\uDF6E\uDF70-\uDF88\uDF8A-\uDFA8\uDFAA-\uDFC2\uDFC4-\uDFCB])
 	| ([\ud803][\uDC00-\uDC48])
+	| ([\ud808][\uDC00-\uDF6E])
 	| ([\ud802][\uDC00-\uDC05\uDC08\uDC0A-\uDC35\uDC37\uDC38\uDC3C\uDC3F-\uDC55\uDD00-\uDD15\uDD20-\uDD39\uDE00\uDE10-\uDE13\uDE15-\uDE17\uDE19-\uDE33\uDE60-\uDE7C\uDF00-\uDF35\uDF40-\uDF55\uDF60-\uDF72])
+	| ([\ud80d][\uDC00-\uDC2E])
 )
 FormatSupp = (
 	  ([\ud804][\uDCBD])
@@ -25,8 +25,8 @@ ExtendSupp = (
 )
 NumericSupp = (
 	  ([\ud804][\uDC66-\uDC6F])
-	| ([\ud835][\uDFCE-\uDFFF])
 	| ([\ud801][\uDCA0-\uDCA9])
+	| ([\ud835][\uDFCE-\uDFFF])
 )
 KatakanaSupp = (
 	  ([\ud82c][\uDC00])
@@ -50,56 +50,56 @@ ComplexContextSupp = (
 	  []
 )
 HanSupp = (
-	  ([\ud87e][\uDC00-\uDE1D])
-	| ([\ud86b][\uDC00-\uDFFF])
-	| ([\ud86a][\uDC00-\uDFFF])
-	| ([\ud869][\uDC00-\uDED6\uDF00-\uDFFF])
-	| ([\ud868][\uDC00-\uDFFF])
-	| ([\ud86e][\uDC00-\uDC1D])
-	| ([\ud86d][\uDC00-\uDF34\uDF40-\uDFFF])
-	| ([\ud86c][\uDC00-\uDFFF])
-	| ([\ud863][\uDC00-\uDFFF])
-	| ([\ud862][\uDC00-\uDFFF])
-	| ([\ud861][\uDC00-\uDFFF])
-	| ([\ud860][\uDC00-\uDFFF])
-	| ([\ud867][\uDC00-\uDFFF])
-	| ([\ud866][\uDC00-\uDFFF])
+	  ([\ud858][\uDC00-\uDFFF])
 	| ([\ud865][\uDC00-\uDFFF])
-	| ([\ud864][\uDC00-\uDFFF])
-	| ([\ud858][\uDC00-\uDFFF])
-	| ([\ud859][\uDC00-\uDFFF])
-	| ([\ud85a][\uDC00-\uDFFF])
-	| ([\ud85b][\uDC00-\uDFFF])
-	| ([\ud85c][\uDC00-\uDFFF])
-	| ([\ud85d][\uDC00-\uDFFF])
-	| ([\ud85e][\uDC00-\uDFFF])
+	| ([\ud87e][\uDC00-\uDE1D])
 	| ([\ud85f][\uDC00-\uDFFF])
-	| ([\ud850][\uDC00-\uDFFF])
-	| ([\ud851][\uDC00-\uDFFF])
-	| ([\ud852][\uDC00-\uDFFF])
-	| ([\ud853][\uDC00-\uDFFF])
-	| ([\ud854][\uDC00-\uDFFF])
-	| ([\ud855][\uDC00-\uDFFF])
-	| ([\ud856][\uDC00-\uDFFF])
-	| ([\ud857][\uDC00-\uDFFF])
-	| ([\ud849][\uDC00-\uDFFF])
-	| ([\ud848][\uDC00-\uDFFF])
-	| ([\ud84b][\uDC00-\uDFFF])
-	| ([\ud84a][\uDC00-\uDFFF])
-	| ([\ud84d][\uDC00-\uDFFF])
+	| ([\ud86c][\uDC00-\uDFFF])
 	| ([\ud84c][\uDC00-\uDFFF])
-	| ([\ud84f][\uDC00-\uDFFF])
-	| ([\ud84e][\uDC00-\uDFFF])
+	| ([\ud857][\uDC00-\uDFFF])
 	| ([\ud841][\uDC00-\uDFFF])
+	| ([\ud860][\uDC00-\uDFFF])
+	| ([\ud849][\uDC00-\uDFFF])
 	| ([\ud840][\uDC00-\uDFFF])
+	| ([\ud853][\uDC00-\uDFFF])
+	| ([\ud859][\uDC00-\uDFFF])
+	| ([\ud844][\uDC00-\uDFFF])
+	| ([\ud856][\uDC00-\uDFFF])
+	| ([\ud84a][\uDC00-\uDFFF])
+	| ([\ud863][\uDC00-\uDFFF])
 	| ([\ud843][\uDC00-\uDFFF])
+	| ([\ud86e][\uDC00-\uDC1D])
+	| ([\ud866][\uDC00-\uDFFF])
+	| ([\ud86b][\uDC00-\uDFFF])
+	| ([\ud84b][\uDC00-\uDFFF])
+	| ([\ud85e][\uDC00-\uDFFF])
+	| ([\ud851][\uDC00-\uDFFF])
 	| ([\ud842][\uDC00-\uDFFF])
+	| ([\ud862][\uDC00-\uDFFF])
+	| ([\ud86d][\uDC00-\uDF34\uDF40-\uDFFF])
 	| ([\ud845][\uDC00-\uDFFF])
-	| ([\ud844][\uDC00-\uDFFF])
+	| ([\ud85b][\uDC00-\uDFFF])
+	| ([\ud861][\uDC00-\uDFFF])
+	| ([\ud84e][\uDC00-\uDFFF])
+	| ([\ud868][\uDC00-\uDFFF])
+	| ([\ud848][\uDC00-\uDFFF])
+	| ([\ud854][\uDC00-\uDFFF])
+	| ([\ud869][\uDC00-\uDED6\uDF00-\uDFFF])
+	| ([\ud84f][\uDC00-\uDFFF])
+	| ([\ud85c][\uDC00-\uDFFF])
+	| ([\ud867][\uDC00-\uDFFF])
 	| ([\ud847][\uDC00-\uDFFF])
+	| ([\ud864][\uDC00-\uDFFF])
+	| ([\ud850][\uDC00-\uDFFF])
+	| ([\ud86a][\uDC00-\uDFFF])
+	| ([\ud85d][\uDC00-\uDFFF])
+	| ([\ud852][\uDC00-\uDFFF])
+	| ([\ud855][\uDC00-\uDFFF])
 	| ([\ud846][\uDC00-\uDFFF])
+	| ([\ud85a][\uDC00-\uDFFF])
+	| ([\ud84d][\uDC00-\uDFFF])
 )
 HiraganaSupp = (
-	  ([\ud83c][\uDE00])
-	| ([\ud82c][\uDC01])
+	  ([\ud82c][\uDC01])
+	| ([\ud83c][\uDE00])
 )

Modified: lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java (original)
+++ lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java Thu Jan  6 14:54:48 2011
@@ -1,4 +1,4 @@
-/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 12/7/10 11:53 AM */
+/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 1/6/11 9:34 AM */
 
 package org.apache.lucene.analysis.standard;
 
@@ -35,14 +35,6 @@ import org.apache.lucene.analysis.tokena
  *   <li>&lt;IDEOGRAPHIC&gt;: A single CJKV ideographic character</li>
  *   <li>&lt;HIRAGANA&gt;: A single hiragana character</li>
  * </ul>
- * <b>WARNING</b>: Because JFlex does not support Unicode supplementary 
- * characters (characters above the Basic Multilingual Plane, which contains
- * those up to and including U+FFFF), this scanner will not recognize them
- * properly.  If you need to be able to process text containing supplementary 
- * characters, consider using the ICU4J-backed implementation in modules/analysis/icu  
- * (org.apache.lucene.analysis.icu.segmentation.ICUTokenizer)
- * instead of this class, since the ICU4J-backed implementation does not have
- * this limitation.
  */
 
 public final class StandardTokenizerImpl implements StandardTokenizerInterface {
@@ -70,115 +62,138 @@ public final class StandardTokenizerImpl
    * Translates characters to character classes
    */
   private static final String ZZ_CMAP_PACKED = 
-    "\47\0\1\7\4\0\1\6\1\0\1\7\1\0\12\3\1\5\1\6"+
-    "\5\0\32\1\4\0\1\10\1\0\32\1\57\0\1\1\2\0\1\2"+
-    "\7\0\1\1\1\0\1\5\2\0\1\1\5\0\27\1\1\0\37\1"+
-    "\1\0\u01ca\1\4\0\14\1\16\0\5\1\7\0\1\1\1\0\1\1"+
-    "\21\0\160\2\5\1\1\0\2\1\2\0\4\1\1\6\7\0\1\1"+
-    "\1\5\3\1\1\0\1\1\1\0\24\1\1\0\123\1\1\0\213\1"+
-    "\1\0\7\2\236\1\11\0\46\1\2\0\1\1\7\0\47\1\1\0"+
-    "\1\6\7\0\55\2\1\0\1\2\1\0\2\2\1\0\2\2\1\0"+
-    "\1\2\10\0\33\1\5\0\4\1\1\5\13\0\4\2\10\0\2\6"+
-    "\2\0\13\2\5\0\53\1\25\2\12\3\1\0\1\3\1\6\1\0"+
-    "\2\1\1\2\143\1\1\0\1\1\10\2\1\0\6\2\2\1\2\2"+
-    "\1\0\4\2\2\1\12\3\3\1\2\0\1\1\17\0\1\2\1\1"+
-    "\1\2\36\1\33\2\2\0\131\1\13\2\1\1\16\0\12\3\41\1"+
-    "\11\2\2\1\2\0\1\6\1\0\1\1\5\0\26\1\4\2\1\1"+
-    "\11\2\1\1\3\2\1\1\5\2\22\0\31\1\3\2\244\0\4\2"+
-    "\66\1\3\2\1\1\22\2\1\1\7\2\12\1\2\2\2\0\12\3"+
-    "\1\0\7\1\1\0\7\1\1\0\3\2\1\0\10\1\2\0\2\1"+
-    "\2\0\26\1\1\0\7\1\1\0\1\1\3\0\4\1\2\0\1\2"+
-    "\1\1\7\2\2\0\2\2\2\0\3\2\1\1\10\0\1\2\4\0"+
-    "\2\1\1\0\3\1\2\2\2\0\12\3\2\1\17\0\3\2\1\0"+
-    "\6\1\4\0\2\1\2\0\26\1\1\0\7\1\1\0\2\1\1\0"+
-    "\2\1\1\0\2\1\2\0\1\2\1\0\5\2\4\0\2\2\2\0"+
-    "\3\2\3\0\1\2\7\0\4\1\1\0\1\1\7\0\12\3\2\2"+
-    "\3\1\1\2\13\0\3\2\1\0\11\1\1\0\3\1\1\0\26\1"+
-    "\1\0\7\1\1\0\2\1\1\0\5\1\2\0\1\2\1\1\10\2"+
-    "\1\0\3\2\1\0\3\2\2\0\1\1\17\0\2\1\2\2\2\0"+
-    "\12\3\21\0\3\2\1\0\10\1\2\0\2\1\2\0\26\1\1\0"+
-    "\7\1\1\0\2\1\1\0\5\1\2\0\1\2\1\1\7\2\2\0"+
-    "\2\2\2\0\3\2\10\0\2\2\4\0\2\1\1\0\3\1\2\2"+
-    "\2\0\12\3\1\0\1\1\20\0\1\2\1\1\1\0\6\1\3\0"+
-    "\3\1\1\0\4\1\3\0\2\1\1\0\1\1\1\0\2\1\3\0"+
-    "\2\1\3\0\3\1\3\0\14\1\4\0\5\2\3\0\3\2\1\0"+
-    "\4\2\2\0\1\1\6\0\1\2\16\0\12\3\21\0\3\2\1\0"+
-    "\10\1\1\0\3\1\1\0\27\1\1\0\12\1\1\0\5\1\3\0"+
-    "\1\1\7\2\1\0\3\2\1\0\4\2\7\0\2\2\1\0\2\1"+
-    "\6\0\2\1\2\2\2\0\12\3\22\0\2\2\1\0\10\1\1\0"+
-    "\3\1\1\0\27\1\1\0\12\1\1\0\5\1\2\0\1\2\1\1"+
-    "\7\2\1\0\3\2\1\0\4\2\7\0\2\2\7\0\1\1\1\0"+
-    "\2\1\2\2\2\0\12\3\1\0\2\1\17\0\2\2\1\0\10\1"+
-    "\1\0\3\1\1\0\51\1\2\0\1\1\7\2\1\0\3\2\1\0"+
-    "\4\2\1\1\10\0\1\2\10\0\2\1\2\2\2\0\12\3\12\0"+
-    "\6\1\2\0\2\2\1\0\22\1\3\0\30\1\1\0\11\1\1\0"+
-    "\1\1\2\0\7\1\3\0\1\2\4\0\6\2\1\0\1\2\1\0"+
-    "\10\2\22\0\2\2\15\0\60\11\1\12\2\11\7\12\5\0\7\11"+
-    "\10\12\1\0\12\3\47\0\2\11\1\0\1\11\2\0\2\11\1\0"+
-    "\1\11\2\0\1\11\6\0\4\11\1\0\7\11\1\0\3\11\1\0"+
-    "\1\11\1\0\1\11\2\0\2\11\1\0\4\11\1\12\2\11\6\12"+
-    "\1\0\2\12\1\11\2\0\5\11\1\0\1\11\1\0\6\12\2\0"+
-    "\12\3\2\0\2\11\42\0\1\1\27\0\2\2\6\0\12\3\13\0"+
-    "\1\2\1\0\1\2\1\0\1\2\4\0\2\2\10\1\1\0\44\1"+
-    "\4\0\24\2\1\0\2\2\5\1\13\2\1\0\44\2\11\0\1\2"+
-    "\71\0\53\11\24\12\1\11\12\3\6\0\6\11\4\12\4\11\3\12"+
-    "\1\11\3\12\2\11\7\12\3\11\4\12\15\11\14\12\1\11\1\12"+
-    "\12\3\4\12\2\11\46\1\12\0\53\1\1\0\1\1\3\0\u0149\1"+
-    "\1\0\4\1\2\0\7\1\1\0\1\1\1\0\4\1\2\0\51\1"+
-    "\1\0\4\1\2\0\41\1\1\0\4\1\2\0\7\1\1\0\1\1"+
-    "\1\0\4\1\2\0\17\1\1\0\71\1\1\0\4\1\2\0\103\1"+
-    "\2\0\3\2\40\0\20\1\20\0\125\1\14\0\u026c\1\2\0\21\1"+
-    "\1\0\32\1\5\0\113\1\3\0\3\1\17\0\15\1\1\0\4\1"+
-    "\3\2\13\0\22\1\3\2\13\0\22\1\2\2\14\0\15\1\1\0"+
-    "\3\1\1\0\2\2\14\0\64\11\40\12\3\0\1\11\4\0\1\11"+
-    "\1\12\2\0\12\3\41\0\3\2\2\0\12\3\6\0\130\1\10\0"+
-    "\51\1\1\2\1\1\5\0\106\1\12\0\35\1\3\0\14\2\4\0"+
-    "\14\2\12\0\12\3\36\11\2\0\5\11\13\0\54\11\4\0\21\12"+
-    "\7\11\2\12\6\0\12\3\1\11\3\0\2\11\40\0\27\1\5\2"+
-    "\4\0\65\11\12\12\1\0\35\12\2\0\1\2\12\3\6\0\12\3"+
-    "\6\0\16\11\122\0\5\2\57\1\21\2\7\1\4\0\12\3\21\0"+
-    "\11\2\14\0\3\2\36\1\12\2\3\0\2\1\12\3\6\0\46\1"+
-    "\16\2\14\0\44\1\24\2\10\0\12\3\3\0\3\1\12\3\44\1"+
-    "\122\0\3\2\1\0\25\2\4\1\1\2\4\1\1\2\15\0\300\1"+
-    "\47\2\25\0\4\2\u0116\1\2\0\6\1\2\0\46\1\2\0\6\1"+
-    "\2\0\10\1\1\0\1\1\1\0\1\1\1\0\1\1\1\0\37\1"+
-    "\2\0\65\1\1\0\7\1\1\0\1\1\3\0\3\1\1\0\7\1"+
-    "\3\0\4\1\2\0\6\1\4\0\15\1\5\0\3\1\1\0\7\1"+
-    "\17\0\4\2\10\0\2\7\12\0\1\7\2\0\1\5\2\0\5\2"+
-    "\20\0\2\10\3\0\1\6\17\0\1\10\13\0\5\2\5\0\6\2"+
-    "\1\0\1\1\15\0\1\1\20\0\15\1\63\0\41\2\21\0\1\1"+
-    "\4\0\1\1\2\0\12\1\1\0\1\1\3\0\5\1\6\0\1\1"+
-    "\1\0\1\1\1\0\1\1\1\0\4\1\1\0\13\1\2\0\4\1"+
-    "\5\0\5\1\4\0\1\1\21\0\51\1\u032d\0\64\1\u0716\0\57\1"+
-    "\1\0\57\1\1\0\205\1\6\0\4\1\3\2\16\0\46\1\12\0"+
-    "\66\1\11\0\1\1\17\0\1\2\27\1\11\0\7\1\1\0\7\1"+
-    "\1\0\7\1\1\0\7\1\1\0\7\1\1\0\7\1\1\0\7\1"+
-    "\1\0\7\1\1\0\40\2\57\0\1\1\120\0\32\13\1\0\131\13"+
-    "\14\0\326\13\57\0\1\1\1\0\1\13\31\0\11\13\6\2\1\0"+
-    "\5\4\2\0\3\13\1\1\1\1\4\0\126\14\2\0\2\2\2\4"+
-    "\3\14\133\4\1\0\4\4\5\0\51\1\3\0\136\1\21\0\33\1"+
-    "\65\0\20\4\320\0\57\4\1\0\130\4\250\0\u19b6\13\112\0\u51cc\13"+
-    "\64\0\u048d\1\103\0\56\1\2\0\u010d\1\3\0\20\1\12\3\2\1"+
-    "\24\0\57\1\4\2\11\0\2\2\1\0\31\1\10\0\120\1\2\2"+
-    "\45\0\11\1\2\0\147\1\2\0\4\1\1\0\2\1\16\0\12\1"+
-    "\120\0\10\1\1\2\3\1\1\2\4\1\1\2\27\1\5\2\30\0"+
-    "\64\1\14\0\2\2\62\1\21\2\13\0\12\3\6\0\22\2\6\1"+
-    "\3\0\1\1\4\0\12\3\34\1\10\2\2\0\27\1\15\2\14\0"+
-    "\35\1\3\0\4\2\57\1\16\2\16\0\1\1\12\3\46\0\51\1"+
-    "\16\2\11\0\3\1\1\2\10\1\2\2\2\0\12\3\6\0\33\11"+
-    "\1\12\4\0\60\11\1\12\1\11\3\12\2\11\2\12\5\11\2\12"+
-    "\1\11\1\12\1\11\30\0\5\11\41\0\6\1\2\0\6\1\2\0"+
-    "\6\1\11\0\7\1\1\0\7\1\221\0\43\1\10\2\1\0\2\2"+
-    "\2\0\12\3\6\0\u2ba4\1\14\0\27\1\4\0\61\1\u2104\0\u012e\13"+
-    "\2\0\76\13\2\0\152\13\46\0\7\1\14\0\5\1\5\0\1\1"+
-    "\1\2\12\1\1\0\15\1\1\0\5\1\1\0\1\1\1\0\2\1"+
-    "\1\0\2\1\1\0\154\1\41\0\u016b\1\22\0\100\1\2\0\66\1"+
-    "\50\0\14\1\4\0\20\2\1\6\2\0\1\5\1\6\13\0\7\2"+
-    "\14\0\2\10\30\0\3\10\1\6\1\0\1\7\1\0\1\6\1\5"+
-    "\32\0\5\1\1\0\207\1\2\0\1\2\7\0\1\7\4\0\1\6"+
-    "\1\0\1\7\1\0\12\3\1\5\1\6\5\0\32\1\4\0\1\10"+
-    "\1\0\32\1\13\0\70\4\2\2\37\1\3\0\6\1\2\0\6\1"+
-    "\2\0\6\1\2\0\3\1\34\0\3\2\4\0";
+    "\47\0\1\140\4\0\1\137\1\0\1\140\1\0\12\134\1\136\1\137"+
+    "\5\0\32\132\4\0\1\141\1\0\32\132\57\0\1\132\2\0\1\133"+
+    "\7\0\1\132\1\0\1\136\2\0\1\132\5\0\27\132\1\0\37\132"+
+    "\1\0\u01ca\132\4\0\14\132\16\0\5\132\7\0\1\132\1\0\1\132"+
+    "\21\0\160\133\5\132\1\0\2\132\2\0\4\132\1\137\7\0\1\132"+
+    "\1\136\3\132\1\0\1\132\1\0\24\132\1\0\123\132\1\0\213\132"+
+    "\1\0\7\133\236\132\11\0\46\132\2\0\1\132\7\0\47\132\1\0"+
+    "\1\137\7\0\55\133\1\0\1\133\1\0\2\133\1\0\2\133\1\0"+
+    "\1\133\10\0\33\132\5\0\4\132\1\136\13\0\4\133\10\0\2\137"+
+    "\2\0\13\133\5\0\53\132\25\133\12\134\1\0\1\134\1\137\1\0"+
+    "\2\132\1\133\143\132\1\0\1\132\7\133\1\133\1\0\6\133\2\132"+
+    "\2\133\1\0\4\133\2\132\12\134\3\132\2\0\1\132\17\0\1\133"+
+    "\1\132\1\133\36\132\33\133\2\0\131\132\13\133\1\132\16\0\12\134"+
+    "\41\132\11\133\2\132\2\0\1\137\1\0\1\132\5\0\26\132\4\133"+
+    "\1\132\11\133\1\132\3\133\1\132\5\133\22\0\31\132\3\133\244\0"+
+    "\4\133\66\132\3\133\1\132\22\133\1\132\7\133\12\132\2\133\2\0"+
+    "\12\134\1\0\7\132\1\0\7\132\1\0\3\133\1\0\10\132\2\0"+
+    "\2\132\2\0\26\132\1\0\7\132\1\0\1\132\3\0\4\132\2\0"+
+    "\1\133\1\132\7\133\2\0\2\133\2\0\3\133\1\132\10\0\1\133"+
+    "\4\0\2\132\1\0\3\132\2\133\2\0\12\134\2\132\17\0\3\133"+
+    "\1\0\6\132\4\0\2\132\2\0\26\132\1\0\7\132\1\0\2\132"+
+    "\1\0\2\132\1\0\2\132\2\0\1\133\1\0\5\133\4\0\2\133"+
+    "\2\0\3\133\3\0\1\133\7\0\4\132\1\0\1\132\7\0\12\134"+
+    "\2\133\3\132\1\133\13\0\3\133\1\0\11\132\1\0\3\132\1\0"+
+    "\26\132\1\0\7\132\1\0\2\132\1\0\5\132\2\0\1\133\1\132"+
+    "\10\133\1\0\3\133\1\0\3\133\2\0\1\132\17\0\2\132\2\133"+
+    "\2\0\12\134\21\0\3\133\1\0\10\132\2\0\2\132\2\0\26\132"+
+    "\1\0\7\132\1\0\2\132\1\0\5\132\2\0\1\133\1\132\7\133"+
+    "\2\0\2\133\2\0\3\133\10\0\2\133\4\0\2\132\1\0\3\132"+
+    "\2\133\2\0\12\134\1\0\1\132\20\0\1\133\1\132\1\0\6\132"+
+    "\3\0\3\132\1\0\4\132\3\0\2\132\1\0\1\132\1\0\2\132"+
+    "\3\0\2\132\3\0\3\132\3\0\14\132\4\0\5\133\3\0\3\133"+
+    "\1\0\4\133\2\0\1\132\6\0\1\133\16\0\12\134\21\0\3\133"+
+    "\1\0\10\132\1\0\3\132\1\0\27\132\1\0\12\132\1\0\5\132"+
+    "\3\0\1\132\7\133\1\0\3\133\1\0\4\133\7\0\2\133\1\0"+
+    "\2\132\6\0\2\132\2\133\2\0\12\134\22\0\2\133\1\0\10\132"+
+    "\1\0\3\132\1\0\27\132\1\0\12\132\1\0\5\132\2\0\1\133"+
+    "\1\132\7\133\1\0\3\133\1\0\4\133\7\0\2\133\7\0\1\132"+
+    "\1\0\2\132\2\133\2\0\12\134\1\0\2\132\17\0\2\133\1\0"+
+    "\10\132\1\0\3\132\1\0\51\132\2\0\1\132\7\133\1\0\3\133"+
+    "\1\0\4\133\1\132\10\0\1\133\10\0\2\132\2\133\2\0\12\134"+
+    "\12\0\6\132\2\0\2\133\1\0\22\132\3\0\30\132\1\0\11\132"+
+    "\1\0\1\132\2\0\7\132\3\0\1\133\4\0\6\133\1\0\1\133"+
+    "\1\0\10\133\22\0\2\133\15\0\60\142\1\143\2\142\7\143\5\0"+
+    "\7\142\10\143\1\0\12\134\47\0\2\142\1\0\1\142\2\0\2\142"+
+    "\1\0\1\142\2\0\1\142\6\0\4\142\1\0\7\142\1\0\3\142"+
+    "\1\0\1\142\1\0\1\142\2\0\2\142\1\0\4\142\1\143\2\142"+
+    "\6\143\1\0\2\143\1\142\2\0\5\142\1\0\1\142\1\0\6\143"+
+    "\2\0\12\134\2\0\2\142\42\0\1\132\27\0\2\133\6\0\12\134"+
+    "\13\0\1\133\1\0\1\133\1\0\1\133\4\0\2\133\10\132\1\0"+
+    "\44\132\4\0\24\133\1\0\2\133\5\132\13\133\1\0\44\133\11\0"+
+    "\1\133\71\0\53\142\24\143\1\142\12\134\6\0\6\142\4\143\4\142"+
+    "\3\143\1\142\3\143\2\142\7\143\3\142\4\143\15\142\14\143\1\142"+
+    "\1\143\12\134\4\143\2\142\46\132\12\0\53\132\1\0\1\132\3\0"+
+    "\u0149\132\1\0\4\132\2\0\7\132\1\0\1\132\1\0\4\132\2\0"+
+    "\51\132\1\0\4\132\2\0\41\132\1\0\4\132\2\0\7\132\1\0"+
+    "\1\132\1\0\4\132\2\0\17\132\1\0\71\132\1\0\4\132\2\0"+
+    "\103\132\2\0\3\133\40\0\20\132\20\0\125\132\14\0\u026c\132\2\0"+
+    "\21\132\1\0\32\132\5\0\113\132\3\0\3\132\17\0\15\132\1\0"+
+    "\4\132\3\133\13\0\22\132\3\133\13\0\22\132\2\133\14\0\15\132"+
+    "\1\0\3\132\1\0\2\133\14\0\64\142\2\143\36\143\3\0\1\142"+
+    "\4\0\1\142\1\143\2\0\12\134\41\0\3\133\2\0\12\134\6\0"+
+    "\130\132\10\0\51\132\1\133\1\132\5\0\106\132\12\0\35\132\3\0"+
+    "\14\133\4\0\14\133\12\0\12\134\36\142\2\0\5\142\13\0\54\142"+
+    "\4\0\21\143\7\142\2\143\6\0\12\134\1\142\3\0\2\142\40\0"+
+    "\27\132\5\133\4\0\65\142\12\143\1\0\35\143\2\0\1\133\12\134"+
+    "\6\0\12\134\6\0\16\142\122\0\5\133\57\132\21\133\7\132\4\0"+
+    "\12\134\21\0\11\133\14\0\3\133\36\132\12\133\3\0\2\132\12\134"+
+    "\6\0\46\132\16\133\14\0\44\132\24\133\10\0\12\134\3\0\3\132"+
+    "\12\134\44\132\122\0\3\133\1\0\25\133\4\132\1\133\4\132\1\133"+
+    "\15\0\300\132\47\133\25\0\4\133\u0116\132\2\0\6\132\2\0\46\132"+
+    "\2\0\6\132\2\0\10\132\1\0\1\132\1\0\1\132\1\0\1\132"+
+    "\1\0\37\132\2\0\65\132\1\0\7\132\1\0\1\132\3\0\3\132"+
+    "\1\0\7\132\3\0\4\132\2\0\6\132\4\0\15\132\5\0\3\132"+
+    "\1\0\7\132\17\0\2\133\2\133\10\0\2\140\12\0\1\140\2\0"+
+    "\1\136\2\0\5\133\20\0\2\141\3\0\1\137\17\0\1\141\13\0"+
+    "\5\133\5\0\6\133\1\0\1\132\15\0\1\132\20\0\15\132\63\0"+
+    "\41\133\21\0\1\132\4\0\1\132\2\0\12\132\1\0\1\132\3\0"+
+    "\5\132\6\0\1\132\1\0\1\132\1\0\1\132\1\0\4\132\1\0"+
+    "\13\132\2\0\4\132\5\0\5\132\4\0\1\132\21\0\51\132\u032d\0"+
+    "\64\132\u0716\0\57\132\1\0\57\132\1\0\205\132\6\0\4\132\3\133"+
+    "\16\0\46\132\12\0\66\132\11\0\1\132\17\0\1\133\27\132\11\0"+
+    "\7\132\1\0\7\132\1\0\7\132\1\0\7\132\1\0\7\132\1\0"+
+    "\7\132\1\0\7\132\1\0\7\132\1\0\40\133\57\0\1\132\120\0"+
+    "\32\144\1\0\131\144\14\0\326\144\57\0\1\132\1\0\1\144\31\0"+
+    "\11\144\6\133\1\0\5\135\2\0\3\144\1\132\1\132\4\0\126\145"+
+    "\2\0\2\133\2\135\3\145\133\135\1\0\4\135\5\0\51\132\3\0"+
+    "\136\132\21\0\33\132\65\0\20\135\320\0\57\135\1\0\130\135\250\0"+
+    "\u19b6\144\112\0\u51cc\144\64\0\u048d\132\103\0\56\132\2\0\u010d\132\3\0"+
+    "\20\132\12\134\2\132\24\0\57\132\4\133\11\0\2\133\1\0\31\132"+
+    "\10\0\120\132\2\133\45\0\11\132\2\0\147\132\2\0\4\132\1\0"+
+    "\2\132\16\0\12\132\120\0\10\132\1\133\3\132\1\133\4\132\1\133"+
+    "\27\132\5\133\30\0\64\132\14\0\2\133\62\132\21\133\13\0\12\134"+
+    "\6\0\22\133\6\132\3\0\1\132\4\0\12\134\34\132\10\133\2\0"+
+    "\27\132\15\133\14\0\35\132\3\0\4\133\57\132\16\133\16\0\1\132"+
+    "\12\134\46\0\51\132\16\133\11\0\3\132\1\133\10\132\2\133\2\0"+
+    "\12\134\6\0\33\142\1\143\4\0\60\142\1\143\1\142\3\143\2\142"+
+    "\2\143\5\142\2\143\1\142\1\143\1\142\30\0\5\142\41\0\6\132"+
+    "\2\0\6\132\2\0\6\132\11\0\7\132\1\0\7\132\221\0\43\132"+
+    "\10\133\1\0\2\133\2\0\12\134\6\0\u2ba4\132\14\0\27\132\4\0"+
+    "\61\132\4\0\1\10\1\5\1\43\1\33\1\1\3\0\1\36\1\17"+
+    "\2\0\1\3\1\60\14\0\1\14\21\0\1\112\7\0\1\65\1\23"+
+    "\6\0\1\130\3\0\1\114\1\114\1\114\1\114\1\114\1\114\1\114"+
+    "\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114"+
+    "\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114"+
+    "\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114\1\114"+
+    "\1\114\1\114\1\114\1\114\1\126\1\114\1\114\1\114\1\123\1\121"+
+    "\17\0\1\115\u02c1\0\1\70\277\0\1\113\1\73\1\63\3\122\2\61"+
+    "\1\122\1\61\2\122\1\6\21\122\2\62\7\72\1\71\7\72\7\47"+
+    "\1\21\1\47\1\75\2\35\1\34\1\75\1\35\1\34\10\75\2\53"+
+    "\5\52\2\46\5\52\1\22\10\32\5\20\3\7\12\106\20\7\3\13"+
+    "\32\27\1\12\2\24\2\107\1\110\2\107\2\110\2\107\1\110\3\24"+
+    "\1\2\2\24\12\64\1\74\1\31\1\16\1\64\6\31\1\16\66\31"+
+    "\5\116\6\103\1\45\4\103\2\45\10\103\1\45\7\101\1\15\2\101"+
+    "\32\103\1\15\4\101\1\15\5\102\1\100\1\102\3\100\7\102\1\100"+
+    "\23\102\5\67\3\102\6\67\2\67\6\66\10\66\2\101\7\66\36\101"+
+    "\4\66\102\101\15\116\1\77\2\116\1\131\3\120\1\116\2\120\5\116"+
+    "\4\120\4\117\1\116\3\117\1\116\5\117\26\51\4\30\1\104\2\105"+
+    "\4\127\1\105\2\127\3\76\33\127\35\56\3\127\35\124\3\127\6\124"+
+    "\2\40\31\124\1\40\17\124\6\127\4\41\1\37\37\41\1\37\4\41"+
+    "\25\57\1\125\11\57\21\56\5\57\1\55\12\42\13\57\4\56\1\54"+
+    "\6\56\12\127\17\56\1\44\3\50\15\25\11\26\1\11\24\26\2\25"+
+    "\11\26\1\11\31\26\1\11\4\25\4\26\2\11\2\111\1\4\5\111"+
+    "\52\4\u1900\0\u012e\144\2\0\76\144\2\0\152\144\46\0\7\132\14\0"+
+    "\5\132\5\0\1\132\1\133\12\132\1\0\15\132\1\0\5\132\1\0"+
+    "\1\132\1\0\2\132\1\0\2\132\1\0\154\132\41\0\u016b\132\22\0"+
+    "\100\132\2\0\66\132\50\0\14\132\4\0\20\133\1\137\2\0\1\136"+
+    "\1\137\13\0\7\133\14\0\2\141\30\0\3\141\1\137\1\0\1\140"+
+    "\1\0\1\137\1\136\32\0\5\132\1\0\207\132\2\0\1\133\7\0"+
+    "\1\140\4\0\1\137\1\0\1\140\1\0\12\134\1\136\1\137\5\0"+
+    "\32\132\4\0\1\141\1\0\32\132\13\0\70\135\2\133\37\132\3\0"+
+    "\6\132\2\0\6\132\2\0\6\132\2\0\3\132\34\0\3\133\4\0";
 
   /** 
    * Translates characters to character classes
@@ -191,11 +206,11 @@ public final class StandardTokenizerImpl
   private static final int [] ZZ_ACTION = zzUnpackAction();
 
   private static final String ZZ_ACTION_PACKED_0 =
-    "\1\0\1\1\1\2\1\3\1\2\1\1\1\4\1\5"+
-    "\1\6\1\2\1\0\1\2\1\0\1\3\2\0";
+    "\1\0\23\1\1\2\1\3\1\2\1\1\1\4\1\5"+
+    "\1\6\15\0\1\2\1\0\1\2\10\0\1\3\61\0";
 
   private static int [] zzUnpackAction() {
-    int [] result = new int[16];
+    int [] result = new int[101];
     int offset = 0;
     offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result);
     return result;
@@ -220,11 +235,22 @@ public final class StandardTokenizerImpl
   private static final int [] ZZ_ROWMAP = zzUnpackRowMap();
 
   private static final String ZZ_ROWMAP_PACKED_0 =
-    "\0\0\0\15\0\32\0\47\0\64\0\101\0\116\0\15"+
-    "\0\15\0\133\0\150\0\165\0\202\0\217\0\101\0\234";
+    "\0\0\0\146\0\314\0\u0132\0\u0198\0\u01fe\0\u0264\0\u02ca"+
+    "\0\u0330\0\u0396\0\u03fc\0\u0462\0\u04c8\0\u052e\0\u0594\0\u05fa"+
+    "\0\u0660\0\u06c6\0\u072c\0\u0792\0\u07f8\0\u085e\0\u08c4\0\u092a"+
+    "\0\u0990\0\146\0\146\0\u09f6\0\u0132\0\u0a5c\0\u0ac2\0\u0264"+
+    "\0\u02ca\0\u0b28\0\u0396\0\u03fc\0\u0b8e\0\u04c8\0\u0bf4\0\u0c5a"+
+    "\0\u0cc0\0\u0d26\0\u0d8c\0\u0df2\0\u0198\0\u0e58\0\u0330\0\u0ebe"+
+    "\0\u0f24\0\u0f8a\0\u0ff0\0\u1056\0\u10bc\0\u1122\0\u1188\0\u11ee"+
+    "\0\u1254\0\u12ba\0\u1320\0\u1386\0\u13ec\0\u1452\0\u14b8\0\u092a"+
+    "\0\u151e\0\u1584\0\u15ea\0\u1650\0\u16b6\0\u171c\0\u1782\0\u17e8"+
+    "\0\u184e\0\u18b4\0\u191a\0\u1980\0\u19e6\0\u1a4c\0\u1ab2\0\u1b18"+
+    "\0\u1b7e\0\u1be4\0\u1c4a\0\u1cb0\0\u1d16\0\u1d7c\0\u1de2\0\u1e48"+
+    "\0\u1eae\0\u1f14\0\u1f7a\0\u1fe0\0\u2046\0\u20ac\0\u2112\0\u2178"+
+    "\0\u21de\0\u2244\0\u22aa\0\u2310\0\u2376";
 
   private static int [] zzUnpackRowMap() {
-    int [] result = new int[16];
+    int [] result = new int[101];
     int offset = 0;
     offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result);
     return result;
@@ -247,21 +273,267 @@ public final class StandardTokenizerImpl
   private static final int [] ZZ_TRANS = zzUnpackTrans();
 
   private static final String ZZ_TRANS_PACKED_0 =
-    "\1\2\1\3\1\2\1\4\1\5\3\2\1\6\2\7"+
-    "\1\10\1\11\16\0\2\3\1\12\1\0\1\13\1\0"+
-    "\1\13\1\14\1\0\1\3\3\0\1\3\2\4\2\0"+
-    "\2\15\1\16\1\0\1\4\4\0\1\5\1\0\1\5"+
-    "\3\0\1\14\1\0\1\5\3\0\1\3\1\17\1\4"+
-    "\1\5\3\0\1\17\1\0\1\17\13\0\2\7\3\0"+
-    "\1\3\2\12\2\0\2\20\1\14\1\0\1\12\3\0"+
-    "\1\3\1\13\7\0\1\13\3\0\1\3\1\14\1\12"+
-    "\1\5\3\0\1\14\1\0\1\14\4\0\1\15\1\4"+
-    "\6\0\1\15\3\0\1\3\1\16\1\4\1\5\3\0"+
-    "\1\16\1\0\1\16\4\0\1\20\1\12\6\0\1\20"+
-    "\2\0";
+    "\1\2\1\3\1\2\1\4\1\2\1\5\2\2\1\6"+
+    "\3\2\1\7\2\2\1\10\3\2\1\11\7\2\1\12"+
+    "\2\2\1\13\4\2\1\14\14\2\1\15\31\2\1\16"+
+    "\1\2\1\17\1\20\3\2\1\21\1\2\1\22\2\2"+
+    "\1\23\1\2\1\24\1\2\1\25\1\2\1\26\1\27"+
+    "\3\2\1\30\2\31\1\32\1\33\150\0\1\25\3\0"+
+    "\1\25\3\0\1\25\6\0\1\25\2\0\1\25\2\0"+
+    "\1\25\17\0\1\25\11\0\2\25\6\0\2\25\13\0"+
+    "\1\26\2\25\11\0\1\25\25\0\1\25\1\0\1\25"+
+    "\1\0\2\25\1\0\3\25\1\0\2\25\1\0\3\25"+
+    "\1\0\7\25\1\0\2\25\1\0\4\25\1\0\14\25"+
+    "\1\0\4\25\1\0\2\25\1\0\21\25\1\0\1\25"+
+    "\2\0\3\25\1\0\1\25\1\0\2\25\1\0\1\25"+
+    "\1\0\1\25\22\0\2\25\2\0\2\25\4\0\3\25"+
+    "\4\0\1\25\2\0\1\25\1\0\2\25\10\0\2\25"+
+    "\2\0\2\25\5\0\3\25\5\0\3\25\1\0\1\25"+
+    "\10\0\1\25\2\26\2\0\1\25\6\0\1\25\25\0"+
+    "\1\25\6\0\3\25\2\0\1\25\2\0\2\25\1\0"+
+    "\1\25\1\0\2\25\1\0\2\25\2\0\1\25\2\0"+
+    "\1\25\1\0\1\25\4\0\1\25\2\0\2\25\1\0"+
+    "\1\25\1\0\1\25\1\0\4\25\2\0\1\25\2\0"+
+    "\4\25\2\0\1\25\1\0\1\25\4\0\3\25\1\0"+
+    "\1\25\6\0\1\25\1\0\2\25\22\0\1\25\3\0"+
+    "\2\25\2\0\2\25\1\0\2\25\1\0\3\25\1\0"+
+    "\1\25\2\0\4\25\1\0\2\25\7\0\3\25\1\0"+
+    "\3\25\5\0\4\25\1\0\2\25\1\0\5\25\1\0"+
+    "\6\25\1\0\3\25\2\0\1\25\2\0\3\25\1\0"+
+    "\1\25\6\0\1\25\22\0\1\25\11\0\3\25\7\0"+
+    "\1\25\1\0\2\25\10\0\2\25\2\0\2\25\5\0"+
+    "\3\25\5\0\3\25\1\0\1\25\15\0\1\25\6\0"+
+    "\1\25\27\0\1\26\1\0\2\25\3\0\1\25\4\0"+
+    "\2\25\2\0\7\25\1\0\2\25\3\0\2\25\3\0"+
+    "\6\25\2\0\2\25\1\0\4\25\1\0\2\25\1\0"+
+    "\3\25\1\0\3\25\1\0\6\25\1\0\1\25\1\26"+
+    "\1\0\1\25\2\0\3\25\1\0\1\25\1\0\1\25"+
+    "\2\0\1\25\1\0\1\25\22\0\1\25\12\0\1\25"+
+    "\12\0\2\25\11\0\1\25\3\0\1\25\5\0\3\25"+
+    "\5\0\3\25\1\0\1\25\15\0\1\25\6\0\1\25"+
+    "\25\0\1\25\3\0\2\25\2\0\2\25\1\0\2\25"+
+    "\1\0\3\25\1\0\1\25\2\0\4\25\1\0\2\25"+
+    "\1\0\4\25\2\0\3\25\1\0\7\25\1\0\4\25"+
+    "\1\0\2\25\1\0\20\25\2\0\1\25\2\0\3\25"+
+    "\1\0\1\25\1\0\2\25\1\0\1\25\1\0\1\25"+
+    "\22\0\1\25\13\0\1\25\21\0\14\25\2\0\2\25"+
+    "\5\0\3\25\1\0\1\25\5\0\1\25\7\0\1\25"+
+    "\3\0\1\25\2\0\1\25\2\0\1\25\3\0\1\25"+
+    "\22\0\1\25\52\0\3\25\5\0\3\25\17\0\1\25"+
+    "\6\0\1\25\116\0\1\33\17\0\1\27\34\0\1\32"+
+    "\1\0\1\32\1\0\2\32\1\0\3\32\1\0\2\32"+
+    "\1\0\3\32\1\0\7\32\1\0\2\32\1\0\4\32"+
+    "\1\0\14\32\1\0\4\32\1\0\2\32\1\0\21\32"+
+    "\1\0\1\32\2\0\3\32\1\0\1\32\1\0\2\32"+
+    "\1\0\1\32\1\0\1\32\16\0\1\32\3\0\2\32"+
+    "\2\0\2\32\1\0\2\32\1\0\3\32\1\0\1\32"+
+    "\2\0\1\32\1\0\2\32\1\0\2\32\7\0\3\32"+
+    "\2\0\2\32\5\0\4\32\1\0\2\32\1\0\5\32"+
+    "\1\0\5\32\2\0\3\32\2\0\1\32\2\0\3\32"+
+    "\1\0\1\32\6\0\1\32\22\0\1\32\52\0\1\32"+
+    "\1\0\1\32\7\0\1\32\17\0\1\32\6\0\1\32"+
+    "\25\0\1\32\1\0\1\32\1\0\2\32\1\0\3\32"+
+    "\1\0\2\32\1\0\3\32\1\0\7\32\1\0\2\32"+
+    "\1\0\3\32\2\0\11\32\1\0\2\32\1\0\4\32"+
+    "\1\0\2\32\1\0\21\32\1\0\1\32\2\0\3\32"+
+    "\1\0\1\32\1\0\2\32\1\0\1\32\1\0\1\32"+
+    "\16\0\1\32\1\0\1\32\1\0\2\32\1\0\3\32"+
+    "\1\0\2\32\1\0\3\32\1\0\7\32\1\0\2\32"+
+    "\2\0\1\32\1\0\1\32\1\0\14\32\1\0\4\32"+
+    "\1\0\2\32\1\0\21\32\1\0\1\32\2\0\3\32"+
+    "\1\0\1\32\1\0\2\32\1\0\1\32\1\0\1\32"+
+    "\145\0\1\33\15\0\1\34\1\0\1\35\1\0\1\36"+
+    "\2\0\1\37\3\0\1\40\2\0\1\41\3\0\1\42"+
+    "\7\0\1\43\2\0\1\44\4\0\1\45\14\0\1\46"+
+    "\4\0\1\47\2\0\1\50\41\0\2\25\1\51\1\0"+
+    "\1\52\1\0\1\52\1\53\1\0\1\25\3\0\1\54"+
+    "\1\0\1\35\1\0\1\55\2\0\1\56\3\0\1\40"+
+    "\2\0\1\41\3\0\1\57\7\0\1\43\2\0\1\44"+
+    "\4\0\1\60\14\0\1\46\4\0\1\61\2\0\1\62"+
+    "\41\0\1\25\2\26\2\0\2\63\1\64\1\0\1\26"+
+    "\3\0\1\65\6\0\1\66\32\0\1\67\21\0\1\70"+
+    "\2\0\1\71\21\0\1\72\20\0\1\27\1\0\1\27"+
+    "\3\0\1\53\1\0\1\27\3\0\1\73\1\0\1\35"+
+    "\1\0\1\55\2\0\1\74\3\0\1\40\2\0\1\41"+
+    "\3\0\1\57\7\0\1\43\2\0\1\44\4\0\1\75"+
+    "\14\0\1\46\4\0\1\76\2\0\1\77\21\0\1\72"+
+    "\17\0\1\25\1\100\1\26\1\27\3\0\1\100\1\0"+
+    "\1\100\144\0\2\31\4\0\1\25\3\0\1\25\3\0"+
+    "\2\25\5\0\1\25\2\0\1\25\2\0\1\25\4\0"+
+    "\2\25\11\0\1\25\11\0\4\25\4\0\5\25\10\0"+
+    "\1\51\2\25\2\0\1\25\6\0\1\25\31\0\2\25"+
+    "\2\0\2\25\4\0\3\25\4\0\1\25\2\0\1\25"+
+    "\1\0\2\25\10\0\2\25\2\0\2\25\5\0\3\25"+
+    "\5\0\3\25\1\0\1\25\10\0\1\25\2\51\2\0"+
+    "\1\25\6\0\1\25\25\0\1\25\6\0\3\25\2\0"+
+    "\1\25\2\0\2\25\1\0\1\25\1\0\2\25\1\0"+
+    "\2\25\2\0\1\25\2\0\1\25\1\0\1\25\4\0"+
+    "\1\25\2\0\2\25\1\0\1\25\1\0\1\25\1\0"+
+    "\4\25\2\0\1\25\2\0\4\25\1\0\2\25\1\0"+
+    "\1\25\4\0\3\25\1\0\1\25\6\0\1\25\1\0"+
+    "\2\25\24\0\1\51\1\0\2\25\3\0\1\25\4\0"+
+    "\2\25\2\0\7\25\1\0\2\25\3\0\2\25\3\0"+
+    "\6\25\2\0\2\25\1\0\4\25\1\0\2\25\1\0"+
+    "\3\25\1\0\3\25\1\0\6\25\1\0\1\25\1\51"+
+    "\1\0\1\25\2\0\3\25\1\0\1\25\1\0\1\25"+
+    "\2\0\1\25\1\0\1\25\22\0\1\25\13\0\1\25"+
+    "\21\0\14\25\2\0\2\25\5\0\3\25\1\0\1\25"+
+    "\5\0\3\25\5\0\1\25\3\0\2\25\1\0\1\25"+
+    "\2\0\1\25\3\0\1\25\102\0\2\25\6\0\1\25"+
+    "\56\0\1\25\5\0\1\25\2\0\3\25\7\0\1\25"+
+    "\1\0\2\25\7\0\3\25\2\0\2\25\12\0\2\25"+
+    "\1\0\3\25\1\0\1\25\2\0\4\25\2\0\1\25"+
+    "\40\0\1\101\1\0\1\35\1\0\1\36\2\0\1\102"+
+    "\3\0\1\40\2\0\1\41\3\0\1\42\7\0\1\43"+
+    "\2\0\1\44\4\0\1\103\14\0\1\46\4\0\1\104"+
+    "\2\0\1\105\41\0\1\25\2\51\2\0\2\106\1\53"+
+    "\1\0\1\51\3\0\1\107\1\0\1\35\1\0\1\110"+
+    "\2\0\1\111\3\0\1\40\2\0\1\41\3\0\1\112"+
+    "\7\0\1\43\2\0\1\44\4\0\1\113\14\0\1\46"+
+    "\4\0\1\114\2\0\1\115\41\0\1\25\1\52\7\0"+
+    "\1\52\3\0\1\116\1\0\1\35\1\0\1\36\2\0"+
+    "\1\117\3\0\1\40\2\0\1\41\3\0\1\42\7\0"+
+    "\1\43\2\0\1\44\4\0\1\120\14\0\1\46\4\0"+
+    "\1\121\2\0\1\122\21\0\1\72\17\0\1\25\1\53"+
+    "\1\51\1\27\3\0\1\53\1\0\1\53\4\0\1\25"+
+    "\3\0\1\25\3\0\1\25\1\26\5\0\1\25\2\0"+
+    "\1\25\2\0\1\25\4\0\2\26\11\0\1\25\11\0"+
+    "\2\25\2\26\4\0\2\25\3\26\10\0\1\26\2\25"+
+    "\2\0\1\26\6\0\1\25\25\0\1\25\6\0\3\25"+
+    "\2\0\1\25\2\0\2\25\1\0\1\25\1\0\2\25"+
+    "\1\0\2\25\2\0\1\25\2\0\1\25\1\0\1\25"+
+    "\4\0\1\25\2\0\2\25\1\0\1\25\1\0\1\25"+
+    "\1\0\4\25\2\0\1\25\2\0\4\25\1\0\1\26"+
+    "\1\25\1\0\1\25\4\0\3\25\1\0\1\25\6\0"+
+    "\1\25\1\0\2\25\26\0\1\25\13\0\1\25\21\0"+
+    "\14\25\2\0\2\25\5\0\3\25\1\0\1\25\5\0"+
+    "\1\25\2\26\5\0\1\25\3\0\1\25\1\26\1\0"+
+    "\1\25\2\0\1\25\3\0\1\25\102\0\2\26\6\0"+
+    "\1\26\56\0\1\26\5\0\1\26\2\0\3\26\7\0"+
+    "\1\26\1\0\2\26\7\0\3\26\2\0\2\26\12\0"+
+    "\2\26\1\0\3\26\1\0\1\26\2\0\4\26\2\0"+
+    "\1\26\40\0\1\123\3\0\1\124\2\0\1\125\12\0"+
+    "\1\126\17\0\1\127\21\0\1\130\2\0\1\131\42\0"+
+    "\1\63\1\26\6\0\1\63\3\0\1\132\1\0\1\35"+
+    "\1\0\1\55\2\0\1\133\3\0\1\40\2\0\1\41"+
+    "\3\0\1\57\7\0\1\43\2\0\1\44\4\0\1\134"+
+    "\14\0\1\46\4\0\1\135\2\0\1\136\21\0\1\72"+
+    "\17\0\1\25\1\64\1\26\1\27\3\0\1\64\1\0"+
+    "\1\64\15\0\1\27\20\0\2\27\25\0\2\27\6\0"+
+    "\3\27\15\0\1\27\131\0\1\27\152\0\2\27\12\0"+
+    "\1\27\113\0\2\27\6\0\1\27\56\0\1\27\5\0"+
+    "\1\27\2\0\3\27\7\0\1\27\1\0\2\27\7\0"+
+    "\3\27\2\0\2\27\12\0\2\27\1\0\3\27\1\0"+
+    "\1\27\2\0\4\27\2\0\1\27\152\0\1\27\34\0"+
+    "\1\25\3\0\1\25\3\0\1\25\1\100\5\0\1\25"+
+    "\2\0\1\25\2\0\1\25\4\0\2\100\11\0\1\25"+
+    "\11\0\2\25\2\100\4\0\2\25\3\100\10\0\1\26"+
+    "\2\25\2\0\1\100\6\0\1\25\25\0\1\25\6\0"+
+    "\3\25\2\0\1\25\2\0\2\25\1\0\1\25\1\0"+
+    "\2\25\1\0\2\25\2\0\1\25\2\0\1\25\1\0"+
+    "\1\25\4\0\1\25\2\0\2\25\1\0\1\25\1\0"+
+    "\1\25\1\0\4\25\2\0\1\25\2\0\4\25\1\0"+
+    "\1\100\1\25\1\0\1\25\4\0\3\25\1\0\1\25"+
+    "\6\0\1\25\1\0\2\25\26\0\1\25\13\0\1\25"+
+    "\21\0\14\25\2\0\2\25\5\0\3\25\1\0\1\25"+
+    "\5\0\1\25\2\100\5\0\1\25\3\0\1\25\1\100"+
+    "\1\0\1\25\2\0\1\25\3\0\1\25\102\0\2\100"+
+    "\6\0\1\100\56\0\1\100\5\0\1\100\2\0\3\100"+
+    "\7\0\1\100\1\0\2\100\7\0\3\100\2\0\2\100"+
+    "\12\0\2\100\1\0\3\100\1\0\1\100\2\0\4\100"+
+    "\2\0\1\100\41\0\1\25\3\0\1\25\3\0\1\25"+
+    "\1\51\5\0\1\25\2\0\1\25\2\0\1\25\4\0"+
+    "\2\51\11\0\1\25\11\0\2\25\2\51\4\0\2\25"+
+    "\3\51\10\0\1\51\2\25\2\0\1\51\6\0\1\25"+
+    "\25\0\1\25\6\0\3\25\2\0\1\25\2\0\2\25"+
+    "\1\0\1\25\1\0\2\25\1\0\2\25\2\0\1\25"+
+    "\2\0\1\25\1\0\1\25\4\0\1\25\2\0\2\25"+
+    "\1\0\1\25\1\0\1\25\1\0\4\25\2\0\1\25"+
+    "\2\0\4\25\1\0\1\51\1\25\1\0\1\25\4\0"+
+    "\3\25\1\0\1\25\6\0\1\25\1\0\2\25\26\0"+
+    "\1\25\13\0\1\25\21\0\14\25\2\0\2\25\5\0"+
+    "\3\25\1\0\1\25\5\0\1\25\2\51\5\0\1\25"+
+    "\3\0\1\25\1\51\1\0\1\25\2\0\1\25\3\0"+
+    "\1\25\102\0\2\51\6\0\1\51\56\0\1\51\5\0"+
+    "\1\51\2\0\3\51\7\0\1\51\1\0\2\51\7\0"+
+    "\3\51\2\0\2\51\12\0\2\51\1\0\3\51\1\0"+
+    "\1\51\2\0\4\51\2\0\1\51\40\0\1\137\3\0"+
+    "\1\140\2\0\1\141\12\0\1\142\17\0\1\143\21\0"+
+    "\1\144\2\0\1\145\42\0\1\106\1\51\6\0\1\106"+
+    "\4\0\1\25\3\0\1\25\3\0\1\25\1\52\5\0"+
+    "\1\25\2\0\1\25\2\0\1\25\4\0\2\52\11\0"+
+    "\1\25\11\0\2\25\2\52\4\0\2\25\3\52\11\0"+
+    "\2\25\2\0\1\52\6\0\1\25\31\0\2\25\2\0"+
+    "\2\25\4\0\3\25\4\0\1\25\2\0\1\25\1\0"+
+    "\2\25\10\0\2\25\2\0\2\25\5\0\3\25\5\0"+
+    "\3\25\1\0\1\25\10\0\1\25\4\0\1\25\6\0"+
+    "\1\25\25\0\1\25\6\0\3\25\2\0\1\25\2\0"+
+    "\2\25\1\0\1\25\1\0\2\25\1\0\2\25\2\0"+
+    "\1\25\2\0\1\25\1\0\1\25\4\0\1\25\2\0"+
+    "\2\25\1\0\1\25\1\0\1\25\1\0\4\25\2\0"+
+    "\1\25\2\0\4\25\1\0\1\52\1\25\1\0\1\25"+
+    "\4\0\3\25\1\0\1\25\6\0\1\25\1\0\2\25"+
+    "\26\0\2\25\3\0\1\25\4\0\2\25\2\0\7\25"+
+    "\1\0\2\25\3\0\2\25\3\0\6\25\2\0\2\25"+
+    "\1\0\4\25\1\0\2\25\1\0\3\25\1\0\3\25"+
+    "\1\0\6\25\1\0\1\25\2\0\1\25\2\0\3\25"+
+    "\1\0\1\25\1\0\1\25\2\0\1\25\1\0\1\25"+
+    "\22\0\1\25\13\0\1\25\21\0\14\25\2\0\2\25"+
+    "\5\0\3\25\1\0\1\25\5\0\1\25\2\52\5\0"+
+    "\1\25\3\0\1\25\1\52\1\0\1\25\2\0\1\25"+
+    "\3\0\1\25\102\0\2\52\6\0\1\52\56\0\1\52"+
+    "\5\0\1\52\2\0\3\52\7\0\1\52\1\0\2\52"+
+    "\7\0\3\52\2\0\2\52\12\0\2\52\1\0\3\52"+
+    "\1\0\1\52\2\0\4\52\2\0\1\52\41\0\1\25"+
+    "\3\0\1\25\3\0\1\25\1\53\5\0\1\25\2\0"+
+    "\1\25\2\0\1\25\4\0\2\53\11\0\1\25\11\0"+
+    "\2\25\2\53\4\0\2\25\3\53\10\0\1\51\2\25"+
+    "\2\0\1\53\6\0\1\25\25\0\1\25\6\0\3\25"+
+    "\2\0\1\25\2\0\2\25\1\0\1\25\1\0\2\25"+
+    "\1\0\2\25\2\0\1\25\2\0\1\25\1\0\1\25"+
+    "\4\0\1\25\2\0\2\25\1\0\1\25\1\0\1\25"+
+    "\1\0\4\25\2\0\1\25\2\0\4\25\1\0\1\53"+
+    "\1\25\1\0\1\25\4\0\3\25\1\0\1\25\6\0"+
+    "\1\25\1\0\2\25\26\0\1\25\13\0\1\25\21\0"+
+    "\14\25\2\0\2\25\5\0\3\25\1\0\1\25\5\0"+
+    "\1\25\2\53\5\0\1\25\3\0\1\25\1\53\1\0"+
+    "\1\25\2\0\1\25\3\0\1\25\102\0\2\53\6\0"+
+    "\1\53\56\0\1\53\5\0\1\53\2\0\3\53\7\0"+
+    "\1\53\1\0\2\53\7\0\3\53\2\0\2\53\12\0"+
+    "\2\53\1\0\3\53\1\0\1\53\2\0\4\53\2\0"+
+    "\1\53\52\0\1\63\20\0\2\63\25\0\2\63\6\0"+
+    "\3\63\10\0\1\26\4\0\1\63\141\0\2\26\134\0"+
+    "\1\63\52\0\1\26\104\0\1\26\140\0\2\63\12\0"+
+    "\1\63\113\0\2\63\6\0\1\63\56\0\1\63\5\0"+
+    "\1\63\2\0\3\63\7\0\1\63\1\0\2\63\7\0"+
+    "\3\63\2\0\2\63\12\0\2\63\1\0\3\63\1\0"+
+    "\1\63\2\0\4\63\2\0\1\63\41\0\1\25\3\0"+
+    "\1\25\3\0\1\25\1\64\5\0\1\25\2\0\1\25"+
+    "\2\0\1\25\4\0\2\64\11\0\1\25\11\0\2\25"+
+    "\2\64\4\0\2\25\3\64\10\0\1\26\2\25\2\0"+
+    "\1\64\6\0\1\25\25\0\1\25\6\0\3\25\2\0"+
+    "\1\25\2\0\2\25\1\0\1\25\1\0\2\25\1\0"+
+    "\2\25\2\0\1\25\2\0\1\25\1\0\1\25\4\0"+
+    "\1\25\2\0\2\25\1\0\1\25\1\0\1\25\1\0"+
+    "\4\25\2\0\1\25\2\0\4\25\1\0\1\64\1\25"+
+    "\1\0\1\25\4\0\3\25\1\0\1\25\6\0\1\25"+
+    "\1\0\2\25\26\0\1\25\13\0\1\25\21\0\14\25"+
+    "\2\0\2\25\5\0\3\25\1\0\1\25\5\0\1\25"+
+    "\2\64\5\0\1\25\3\0\1\25\1\64\1\0\1\25"+
+    "\2\0\1\25\3\0\1\25\102\0\2\64\6\0\1\64"+
+    "\56\0\1\64\5\0\1\64\2\0\3\64\7\0\1\64"+
+    "\1\0\2\64\7\0\3\64\2\0\2\64\12\0\2\64"+
+    "\1\0\3\64\1\0\1\64\2\0\4\64\2\0\1\64"+
+    "\52\0\1\106\20\0\2\106\25\0\2\106\6\0\3\106"+
+    "\10\0\1\51\4\0\1\106\141\0\2\51\134\0\1\106"+
+    "\52\0\1\51\104\0\1\51\140\0\2\106\12\0\1\106"+
+    "\113\0\2\106\6\0\1\106\56\0\1\106\5\0\1\106"+
+    "\2\0\3\106\7\0\1\106\1\0\2\106\7\0\3\106"+
+    "\2\0\2\106\12\0\2\106\1\0\3\106\1\0\1\106"+
+    "\2\0\4\106\2\0\1\106\37\0";
 
   private static int [] zzUnpackTrans() {
-    int [] result = new int[169];
+    int [] result = new int[9180];
     int offset = 0;
     offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result);
     return result;
@@ -299,11 +571,11 @@ public final class StandardTokenizerImpl
   private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
 
   private static final String ZZ_ATTRIBUTE_PACKED_0 =
-    "\1\0\1\11\5\1\2\11\1\1\1\0\1\1\1\0"+
-    "\1\1\2\0";
+    "\1\0\1\11\27\1\2\11\15\0\1\1\1\0\1\1"+
+    "\10\0\1\1\61\0";
 
   private static int [] zzUnpackAttribute() {
-    int [] result = new int[16];
+    int [] result = new int[101];
     int offset = 0;
     offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result);
     return result;
@@ -434,7 +706,7 @@ public final class StandardTokenizerImpl
     char [] map = new char[0x10000];
     int i = 0;  /* index in packed string  */
     int j = 0;  /* index in unpacked array */
-    while (i < 2174) {
+    while (i < 2640) {
       int  count = packed.charAt(i++);
       char value = packed.charAt(i++);
       do map[j++] = value; while (--count > 0);

Modified: lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex?rev=1055904&r1=1055903&r2=1055904&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex (original)
+++ lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex Thu Jan  6 14:54:48 2011
@@ -33,14 +33,6 @@ import org.apache.lucene.analysis.tokena
  *   <li>&lt;IDEOGRAPHIC&gt;: A single CJKV ideographic character</li>
  *   <li>&lt;HIRAGANA&gt;: A single hiragana character</li>
  * </ul>
- * <b>WARNING</b>: Because JFlex does not support Unicode supplementary 
- * characters (characters above the Basic Multilingual Plane, which contains
- * those up to and including U+FFFF), this scanner will not recognize them
- * properly.  If you need to be able to process text containing supplementary 
- * characters, consider using the ICU4J-backed implementation in modules/analysis/icu  
- * (org.apache.lucene.analysis.icu.segmentation.ICUTokenizer)
- * instead of this class, since the ICU4J-backed implementation does not have
- * this limitation.
  */
 %%
 
@@ -53,15 +45,29 @@ import org.apache.lucene.analysis.tokena
 %function getNextToken
 %char
 
+%include src/java/org/apache/lucene/analysis/standard/SUPPLEMENTARY.jflex-macro
+ALetter = ([\p{WB:ALetter}] | {ALetterSupp})
+Format =  ([\p{WB:Format}] | {FormatSupp})
+Numeric = ([\p{WB:Numeric}] | {NumericSupp})
+Extend =  ([\p{WB:Extend}] | {ExtendSupp})
+Katakana = ([\p{WB:Katakana}] | {KatakanaSupp})
+MidLetter = ([\p{WB:MidLetter}] | {MidLetterSupp})
+MidNum = ([\p{WB:MidNum}] | {MidNumSupp})
+MidNumLet = ([\p{WB:MidNumLet}] | {MidNumLetSupp})
+ExtendNumLet = ([\p{WB:ExtendNumLet}] | {ExtendNumLetSupp})
+ComplexContext = ([\p{LB:Complex_Context}] | {ComplexContextSupp})
+Han = ([\p{Script:Han}] | {HanSupp})
+Hiragana = ([\p{Script:Hiragana}] | {HiraganaSupp})
+
 // UAX#29 WB4. X (Extend | Format)* --> X
 //
-ALetterEx      = \p{WB:ALetter}                     [\p{WB:Format}\p{WB:Extend}]*
+ALetterEx      = {ALetter}                     ({Format} | {Extend})*
 // TODO: Convert hard-coded full-width numeric range to property intersection (something like [\p{Full-Width}&&\p{Numeric}]) once JFlex supports it
-NumericEx      = [\p{WB:Numeric}\uFF10-\uFF19]      [\p{WB:Format}\p{WB:Extend}]*
-KatakanaEx     = \p{WB:Katakana}                    [\p{WB:Format}\p{WB:Extend}]* 
-MidLetterEx    = [\p{WB:MidLetter}\p{WB:MidNumLet}] [\p{WB:Format}\p{WB:Extend}]* 
-MidNumericEx   = [\p{WB:MidNum}\p{WB:MidNumLet}]    [\p{WB:Format}\p{WB:Extend}]*
-ExtendNumLetEx = \p{WB:ExtendNumLet}                [\p{WB:Format}\p{WB:Extend}]*
+NumericEx      = ({Numeric} | [\uFF10-\uFF19]) ({Format} | {Extend})*
+KatakanaEx     = {Katakana}                    ({Format} | {Extend})* 
+MidLetterEx    = ({MidLetter} | {MidNumLet})   ({Format} | {Extend})* 
+MidNumericEx   = ({MidNum} | {MidNumLet})      ({Format} | {Extend})*
+ExtendNumLetEx = {ExtendNumLet}                ({Format} | {Extend})*
 
 
 %{
@@ -156,12 +162,12 @@ ExtendNumLetEx = \p{WB:ExtendNumLet}    
 //
 //    http://www.unicode.org/reports/tr14/#SA
 //
-\p{LB:Complex_Context}+ { return SOUTH_EAST_ASIAN_TYPE; }
+{ComplexContext}+ { return SOUTH_EAST_ASIAN_TYPE; }
 
 // UAX#29 WB14.  Any ÷ Any
 //
-\p{Script:Han} { return IDEOGRAPHIC_TYPE; }
-\p{Script:Hiragana} { return HIRAGANA_TYPE; }
+{Han} { return IDEOGRAPHIC_TYPE; }
+{Hiragana} { return HIRAGANA_TYPE; }
 
 
 // UAX#29 WB3.   CR × LF