From: Andy Heninger <andy.heninger@gmail.com>
Date: Fri, 6 Apr 2018 17:31:18 +0000 (+0000)
Subject: ICU-13630 WSegSpace, use word property value in rules definitions.
X-Git-Tag: release-62-rc~206^2
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=b58e06a604a6d279809716ec192630d8cbca3aa1;p=icu
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 1bbbbca5737..8a4ef977519 100644
--- 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 ee712789242..4cc8cad2c2b 100644
--- 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 864a5a4fce7..6c8cff8602c 100644
--- 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 541367404a3..fc7bc9b1886 100644
--- 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 d43f6c56a6b..10efc32d210 100644
--- 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 41788ef54ba..c986f04df9e 100644
--- 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 541367404a3..fc7bc9b1886 100644
--- 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 d43f6c56a6b..10efc32d210 100644
--- 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.