ICU-13630 WSegSpace, use word property value in rules definitions.

X-SVN-Rev: 41205

diff --git a/icu4c/source/data/brkitr/rules/word.txt b/icu4c/source/data/brkitr/rules/word.txt
index 1bbbbca5737f6c3dc5bb89d367c79c82b938a4e2..8a4ef9775195996b7fb9aff7abe4031407bc575a 100644 (file)
--- a/icu4c/source/data/brkitr/rules/word.txt
+++ b/icu4c/source/data/brkitr/rules/word.txt
@@ -46,7 +46,7 @@ $MidLetter          = [\p{Word_Break = MidLetter}];
 $MidNum             = [\p{Word_Break = MidNum}];
 $Numeric            = [\p{Word_Break = Numeric}];
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-$WSegSpace          = [[\p{Zs}]-[\p{Line_Break = Glue}]];
+$WSegSpace          = [\p{Word_Break = WSegSpace}];
 $Extended_Pict      = [:ExtPict:];
 
 $Han                = [:Han:];

diff --git a/icu4c/source/data/brkitr/rules/word_POSIX.txt b/icu4c/source/data/brkitr/rules/word_POSIX.txt
index ee7127892421b146f9b0a1fab52a4d94732711d4..4cc8cad2c2b1c120351cc021ebdb55d1b6bd4fa0 100644 (file)
--- a/icu4c/source/data/brkitr/rules/word_POSIX.txt
+++ b/icu4c/source/data/brkitr/rules/word_POSIX.txt
@@ -46,7 +46,7 @@ $MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
 $MidNum             = [\p{Word_Break = MidNum} [.]];
 $Numeric            = [\p{Word_Break = Numeric}];
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-$WSegSpace          = [[\p{Zs}]-[\p{Line_Break = Glue}]];
+$WSegSpace          = [\p{Word_Break = WSegSpace}];
 $Extended_Pict      = [:ExtPict:];
 
 $Han                = [:Han:];

diff --git a/icu4c/source/test/intltest/rbbitst.cpp b/icu4c/source/test/intltest/rbbitst.cpp
index 864a5a4fce7c0b362973e8a2feb737909e0ee68c..6c8cff8602c57152e8d2705abf6cf7bb8ff75422 100644 (file)
--- a/icu4c/source/test/intltest/rbbitst.cpp
+++ b/icu4c/source/test/intltest/rbbitst.cpp
@@ -1868,7 +1868,7 @@ RBBIWordMonkey::RBBIWordMonkey()
     fFormatSet        = new UnicodeSet(u"[\\p{Word_Break = Format}]",       status);
     fExtendNumLetSet  = new UnicodeSet(u"[\\p{Word_Break = ExtendNumLet}]", status);
     fExtendSet        = new UnicodeSet(u"[\\p{Word_Break = Extend}]",       status);
-    fWSegSpaceSet     = new UnicodeSet(u"[[\\p{Zs}]-[\\p{Line_Break = GL}]]",   status);
+    fWSegSpaceSet     = new UnicodeSet(u"[\\p{Word_Break = WSegSpace}]",    status);
 
     fZWJSet           = new UnicodeSet(u"[\\p{Word_Break = ZWJ}]",          status);
     fExtendedPictSet  = new UnicodeSet(u"[:Extended_Pictographic:]", status);

diff --git a/icu4c/source/test/testdata/break_rules/word.txt b/icu4c/source/test/testdata/break_rules/word.txt
index 541367404a34d1a0dc05a5a5764f05d346f89e36..fc7bc9b188655f04fbc0d96f0c8655c440ef3642 100644 (file)
--- a/icu4c/source/test/testdata/break_rules/word.txt
+++ b/icu4c/source/test/testdata/break_rules/word.txt
@@ -32,7 +32,7 @@ MidLetter          = [\p{Word_Break = MidLetter}];
 MidNum             = [\p{Word_Break = MidNum}];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-WSegSpace          = [[\p{Zs}]-[\p{Line_Break=Glue}]];
+WSegSpace          = [\p{Word_Break = WSegSpace}];
 Extended_Pict      = [:ExtPict:];
 
 #define dictionary, with the effect being that those characters don't appear in test data.

diff --git a/icu4c/source/test/testdata/break_rules/word_POSIX.txt b/icu4c/source/test/testdata/break_rules/word_POSIX.txt
index d43f6c56a6b300c6d124d5693f16722b2b7e405e..10efc32d2103d445d690ec201a36eb22cb3d2cf7 100644 (file)
--- a/icu4c/source/test/testdata/break_rules/word_POSIX.txt
+++ b/icu4c/source/test/testdata/break_rules/word_POSIX.txt
@@ -31,7 +31,7 @@ MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
 MidNum             = [\p{Word_Break = MidNum} [.]];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-WSegSpace          = [[\p{Zs}]-[\p{Line_Break=Glue}]];
+WSegSpace          = [\p{Word_Break = WSegSpace}];
 Extended_Pict      = [:ExtPict:];
 
 #define dictionary, with the effect being that those characters don't appear in test data.

diff --git a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java
index 41788ef54ba1487dddbc17e5241022cb3fd99185..c986f04df9e915fa279f59ebdd0764a4757a8d72 100644 (file)
--- a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java
+++ b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/RBBITestMonkey.java
@@ -334,7 +334,7 @@ public class RBBITestMonkey extends TestFmwk {
             fFormatSet       = new UnicodeSet("[\\p{Word_Break = Format}]");
             fExtendNumLetSet = new UnicodeSet("[\\p{Word_Break = ExtendNumLet}]");
             fExtendSet       = new UnicodeSet("[\\p{Word_Break = Extend}]");
-            fWSegSpaceSet    = new UnicodeSet("[[\\p{Zs}]-[\\p{Line_Break = GL}]]");
+            fWSegSpaceSet    = new UnicodeSet("[\\p{Word_Break = WSegSpace}]");
             fZWJSet          = new UnicodeSet("[\\p{Word_Break = ZWJ}]");
             fExtendedPictSet = new UnicodeSet("[:Extended_Pictographic:]");
 

diff --git a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word.txt b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word.txt
index 541367404a34d1a0dc05a5a5764f05d346f89e36..fc7bc9b188655f04fbc0d96f0c8655c440ef3642 100644 (file)
--- a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word.txt
+++ b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word.txt
@@ -32,7 +32,7 @@ MidLetter          = [\p{Word_Break = MidLetter}];
 MidNum             = [\p{Word_Break = MidNum}];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-WSegSpace          = [[\p{Zs}]-[\p{Line_Break=Glue}]];
+WSegSpace          = [\p{Word_Break = WSegSpace}];
 Extended_Pict      = [:ExtPict:];
 
 #define dictionary, with the effect being that those characters don't appear in test data.

diff --git a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word_POSIX.txt b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word_POSIX.txt
index d43f6c56a6b300c6d124d5693f16722b2b7e405e..10efc32d2103d445d690ec201a36eb22cb3d2cf7 100644 (file)
--- a/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word_POSIX.txt
+++ b/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/break_rules/word_POSIX.txt
@@ -31,7 +31,7 @@ MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
 MidNum             = [\p{Word_Break = MidNum} [.]];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
-WSegSpace          = [[\p{Zs}]-[\p{Line_Break=Glue}]];
+WSegSpace          = [\p{Word_Break = WSegSpace}];
 Extended_Pict      = [:ExtPict:];
 
 #define dictionary, with the effect being that those characters don't appear in test data.