ICU-8.11.tar.gz

[apple/icu.git] / icuSources / test / testdata / rbbitst.txt

diff --git a/icuSources/test/testdata/rbbitst.txt b/icuSources/test/testdata/rbbitst.txt
index bdb45db0c74cd7a393d455eee282d53f8b8a3619..d336c674e814f58474c0d359f7a4ab1b08ce9587 100644 (file)
--- a/icuSources/test/testdata/rbbitst.txt
+++ b/icuSources/test/testdata/rbbitst.txt
@@ -1,4 +1,4 @@
-# Copyright (c) 2001-2004 International Business Machines
+# Copyright (c) 2001-2006 International Business Machines
 # Corporation and others. All Rights Reserved.
 #
 # RBBI Test Data
@@ -12,6 +12,7 @@
 #   <sent>    any following data is for sentence break testing
 #   <line>    any following data is for line break testing
 #   <char>    any following data is for char break testing
+#   <locale local_name>  Switch to the named locale at the next occurence of <word>, <sent>, etc.
 #   <data> ... </data>   test data.  May span multiple lines.
 #      <>        Break position, status == 0
 #      •         Break position, status == 0   (Bullet, \u2022) 
@@ -22,7 +23,7 @@
 #
 
 
-#   Temp debugging tests
+#   Temp debugging tests 
 <line>
 #     to test for bug #4097920
 <data>•dog,cat,mouse •(one)•(two)\n<100></data>
@@ -87,6 +88,8 @@
 #     (Requires special casing in implementation, which is why it gets a test.)
 <data>•\uffff•\uffff• •a•</data>
 
+#  Treat Japanese Half Width voicing marks as combining
+<data>•A\uff9e•B\uff9f\uff9e\uff9f•C•</data>
 
 ########################################################################################
 #
@@ -156,7 +159,7 @@
 
 <data>•abc<200>\u4e01<400>\u4e02<400>\u3005<200>\u4e03<400>\u4e03<400>abc<200> •</data>
 
-<data>•\u06c9\uc799<200>\ufffa•</data>
+<data>•\u06c9\uc799\ufffa<200></data>
 
 #      
 #      Try some words from other scripts.
@@ -185,6 +188,11 @@
 #
 <data>•\u8527<400>\u02ba<200>\u0027\u0d42•\u00b7•\u09ea<100></data>
 
+#
+# Jitterbug 5276 - treat Japanese half width voicing marks as Grapheme Extend
+#
+<data>•A\uff9e\uff9fBC<200> •1\uff9e\uff9f23<100></data>
+
 ########################################################################################
 #
 #
@@ -217,19 +225,19 @@ doing? •This\n<100> costs $20,00,000. •</data>
 "This isn't it." •Hi! \
 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
 "This isn't it." •\
-Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!•! •Don't rock the boat.\u2029•Because I am the daddy, that is why. 
-•Not on my time (el timo.)•! •</data>
+Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mezzo del cammin di nostra vita, mi ritrovai in una selva oscura. •Che la dritta via aveo smarrita. •He said, that I said, that you said!! •Don't rock the boat.\u2029•Because I am the daddy, that is why. 
+•Not on my time (el timo.)! •</data>
 
-<data>•Hello.  •So what!•!\u2029•"But now," he said, \
+<data>•Hello.  •So what!!\u2029•"But now," he said, \
 "I know!" •\
-Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!)•. •One species, B. anthracis, is highly virulent.
+Harris thumbed down several, including "Away We Go" (which became the huge success Oklahoma!). •One species, B. anthracis, is highly virulent.
 •Wolf said about Sounder:\
 "Beautifully thought-out and directed." •\
 Have you ever said, "This is where\tI shall live"? •He answered, \
-"You may not!" •Another popular saying is: "How do you do?"•. \n•\
+"You may not!" •Another popular saying is: "How do you do?". \n•\
 Yet another popular saying is: \
 'I'm fine thanks.' •\
-What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12" tall!•!\
+What is the proper use of the abbreviation pp.? •Yes, I am definatelly 12" tall!!\
 •Now\r<100>is\n<100>the\r\n<100>time\n<100>\r<100>for\r<100>\r<100></data>
 
 <data>•No breaks when . is surrounded by UPPER.Case letters.  •</data>
@@ -245,13 +253,13 @@ What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12"
 #      Treat fullwidth variants of .!? the same as their
 #      normal counterparts
 #
-<data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>"
+<data>•I know I'm right\uff0e •Right\uff1f •Right\uff01 •</data>
 
 
 #
 #       Don't break sentences at boundary between CJK and digits
 #
-<data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e48888\u821c\u8165\u7fc8\u51ce\u306d\ue30b\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46\u97e5\u7751\u3002•Bye, now<100></data>"
+<data>•\u5487\u67ff\ue591\u5017\u61b3\u60a1\u9510\u8165\u9de8\u97e48888\u821c\u8165\u7fc8\u51ce\u306d\ue30b\u2494\u56d8\u4ec0\u60b1\u8560\u51ba\u611d\u57b6\u2510\u5d46\u97e5\u7751\u3002•Bye, now<100></data>
 
 #
 #      Breaks around '(' following a sentence TERM.  (Rule 9)
@@ -310,7 +318,7 @@ What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12"
 #         Regression test for bug #1984, Sentence break in Arabic text.
   
 <data>\
-•\u0623\u0633\u0627\u0633\u064b\u0627\u060c\u0020\u062a\u062a\u0639\u0627"\u0645\u0644\u0020\u0627\u0644\u062d\u0648\u0627\u0633\u064a\u0628\u0020"\u0641\u0642\u0637\u0020\u0645\u0639\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u060c\u0648\u062a\u0642\u0648\u0645\u0020\u0628\u062a\u062e\u0632\u064a\u0646\u0020\u0627\u0644\u0623\u062d\u0631\u0641\u0020\u0648\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0623\u062e\u0631\u0649\u0020\u0628\u0639\u062f\u0020\u0623\u0646\u062a\u064f\u0639\u0637\u064a\u0020\u0631\u0642\u0645\u0627\u0020\u0645\u0639\u064a\u0646\u0627\u0020\u0644\u0643\u0644\u0020\u0648\u0627\u062d\u062f\u0020\u0645\u0646\u0647\u0627\u002e\u0020•\u0648\u0642\u0628\u0644\u0020\u0627\u062e\u062a\u0631\u0627\u0639\u0022\u064a\u0648\u0646\u0650\u0643\u0648\u062f\u0022\u060c\u0020\u0643\u0627\u0646\u0020\u0647\u0646\u0627\u0643\u0020\u0645\u0626\u0627\u062a\u0020\u0627\u0644\u0623\u0646\u0638\u0645\u0629\u0020\u0644\u0644\u062a\u0634\u0641\u064a\u0631\u0648\u062a\u062e\u0635\u064a\u0635\u0020\u0647\u0630\u0647\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u0020\u0644\u0644\u0645\u062d\u0627\u0631\u0641\u060c\u0020\u0648\u0644\u0645\u0020\u064a\u0648\u062c\u062f\u0020\u0646\u0638\u0627\u0645\u062a\u0634\u0641\u064a\u0020\u0639\u0644\u0649\u0020\u062c\u0645\u064a\u0639\u0020\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0636\u0631\u0648\u0631\u064a\u0629.  •</data>"
+•\u0623\u0633\u0627\u0633\u064b\u0627\u060c\u0020\u062a\u062a\u0639\u0627"\u0645\u0644\u0020\u0627\u0644\u062d\u0648\u0627\u0633\u064a\u0628\u0020"\u0641\u0642\u0637\u0020\u0645\u0639\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u060c\u0648\u062a\u0642\u0648\u0645\u0020\u0628\u062a\u062e\u0632\u064a\u0646\u0020\u0627\u0644\u0623\u062d\u0631\u0641\u0020\u0648\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0623\u062e\u0631\u0649\u0020\u0628\u0639\u062f\u0020\u0623\u0646\u062a\u064f\u0639\u0637\u064a\u0020\u0631\u0642\u0645\u0627\u0020\u0645\u0639\u064a\u0646\u0627\u0020\u0644\u0643\u0644\u0020\u0648\u0627\u062d\u062f\u0020\u0645\u0646\u0647\u0627\u002e\u0020•\u0648\u0642\u0628\u0644\u0020\u0627\u062e\u062a\u0631\u0627\u0639\u0022\u064a\u0648\u0646\u0650\u0643\u0648\u062f\u0022\u060c\u0020\u0643\u0627\u0646\u0020\u0647\u0646\u0627\u0643\u0020\u0645\u0626\u0627\u062a\u0020\u0627\u0644\u0623\u0646\u0638\u0645\u0629\u0020\u0644\u0644\u062a\u0634\u0641\u064a\u0631\u0648\u062a\u062e\u0635\u064a\u0635\u0020\u0647\u0630\u0647\u0020\u0627\u0644\u0623\u0631\u0642\u0627\u0645\u0020\u0644\u0644\u0645\u062d\u0627\u0631\u0641\u060c\u0020\u0648\u0644\u0645\u0020\u064a\u0648\u062c\u062f\u0020\u0646\u0638\u0627\u0645\u062a\u0634\u0641\u064a\u0020\u0639\u0644\u0649\u0020\u062c\u0645\u064a\u0639\u0020\u0627\u0644\u0645\u062d\u0627\u0631\u0641\u0020\u0627\u0644\u0636\u0631\u0648\u0631\u064a\u0629.  •</data>
 
 #         Try a few more of the less common sentence endings.
 <data>•Hello, world\u3002 •Hello, world\u1803 •Hello, world\u2048 •Hello, world\u203c •Let's end here. •</data>
@@ -473,7 +481,7 @@ What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12"
 <data>•\u4e01•\ud840\udc01•\u4e02•abc •\ue000 •\udb80\udc01•</data>
 
 #      Regression for bug 836
-<data>•AAA•(AAA •</data> 
+<data>•AAA(AAA •</data> 
 
 #       Try some words from other scripts.
 #          Greek, Cyrillic, Hebrew, Arabic, Arabic, Georgian, Latin
@@ -499,3 +507,34 @@ What is the proper use of the abbreviation pp.•? •Yes, I am definatelly 12"
 
 <data>•'•start •with •a •case-•ignorable •cha'r'a'cter•</data>
 
+
+##########################################################################################
+#
+#   Thai Tests
+#
+##########################################################################################
+<locale th>
+<word>
+#
+# Test data originally from the test code source file
+#      // @suwit -- Thai sample data from GVT Guideline
+#
+<data>•\u0E2B\u0E19\u0E36\u0E48\u0E07<200>\u0E04\u0E33<200>\u0E44\u0E17\u0E22<200>\
+\u0E2A\u0E32\u0E21\u0E32\u0E23\u0E16<200>\u0E1B\u0E23\u0E30\u0E01\u0E2D\u0E1A<200>\
+\u0E14\u0E49\u0E27\u0E22<200>\u0e2b\u0e25\u0e32\u0e22<200>\
+\u0e1e\u0e22\u0e32\u0e07\u0e04\u0e4c<200></data>
+
+#
+#  Jitterbug 3671 Test Case
+#
+<data>•สวัสดี<200>ครับ<200>สบาย<200>ดี<200>ไหม<200> •ครับ<200></data>
+
+#
+#  Trac ticket 5595 Test Case
+<data>•บท<200>ที่๑พายุ<200>ไซโคลน<200>โด<200>โรธี<200>อาศัย<200>อยู่<200>ท่ามกลาง<200>\
+ทุ่งใหญ่<200>ใน<200>แคนซัส<200>กับ<200>ลุง<200>เฮ<200>นรี<200>ชาวไร่<200>และ<200>ป้า<200>เอ็ม<200>\
+ภรรยา<200>ชาวไร่<200>บ้าน<200>ของ<200>พวก<200>เขา<200>หลัง<200>เล็ก<200>เพราะ<200>ไม้<200>\
+สร้าง<200>บ้าน<200>ต้อง<200>ขน<200>มา<200>ด้วย<200>เกวียน<200>เป็น<200>ระยะ<200>ทาง<200>หลาย<200>\
+ไมล์<200></data>
+
+