ICU 56 update step 1

source/test/testdata/regextst.txt

Index: source/test/testdata/regextst.txt
diff --git a/source/test/testdata/regextst.txt b/source/test/testdata/regextst.txt
index d642e8b9c8b3d33eff50902f46fd97b0af25f955..15d13bf156ea48750832fad9fe20a82e383c78e3 100644
--- a/source/test/testdata/regextst.txt
+++ b/source/test/testdata/regextst.txt
@@ -1,4 +1,4 @@
-# Copyright (c) 2001-2014 International Business Machines
+# Copyright (c) 2001-2015 International Business Machines
 # Corporation and others. All Rights Reserved.
 #
 #  file:
@@ -513,6 +513,15 @@
 "ab(?:(c)|(d))\1"            i "abde"
 "ab(?:(c)|(d))\1"            i "<0>ab<1>c</1>c</0>e"
 
+# Named back references
+"(?<one>abcd)\k<one>"          "<0><1>abcd</1>abcd</0>"
+"(no)?(?<one>abcd)\k<one>"     "<0><2>abcd</2>abcd</0>"
+
+"(?<a_1>...)"               E  "  "   # backref names are ascii letters & numbers only"
+"(?<1a>...)"                E  "  "   # backref names must begin with a letter"
+"(?<a>.)(?<a>.)"            E  "  "   # Repeated names are illegal.
+
+
 # Case Insensitive
 "aBc"                    i      "<0>ABC</0>"
 "a[^bc]d"                i      "ABD"
@@ -685,6 +694,78 @@
 "abc[ \j]kl"                      "<0>abcjkl</0>"
 
 #
+# \R  all newline sequences.
+#
+"abc\Rxyz"                        "<0>abc\u000axyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u000bxyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u000cxyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u000dxyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u0085xyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u2028xyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u2029xyz</0>gh"
+"abc\Rxyz"                        "<0>abc\u000d\u000axyz</0>gh"
+
+"abc\R\nxyz"                      "abc\u000d\u000axyzgh"          # \R cannot match only the CR from a CR/LF sequence.
+"abc\r\nxyz"                      "<0>abc\u000d\u000axyz</0>gh"
+
+"abc\Rxyz"                        "abc\u0009xyz"                  # Assorted non-matches.
+"abc\Rxyz"                        "abc\u000exyz"
+"abc\Rxyz"                        "abc\u202axyz"
+
+# \v \V single character new line sequences.
+
+"abc\vxyz"                        "<0>abc\u000axyz</0>gh"
+"abc\vxyz"                        "<0>abc\u000bxyz</0>gh"
+"abc\vxyz"                        "<0>abc\u000cxyz</0>gh"
+"abc\vxyz"                        "<0>abc\u000dxyz</0>gh"
+"abc\vxyz"                        "<0>abc\u0085xyz</0>gh"
+"abc\vxyz"                        "<0>abc\u2028xyz</0>gh"
+"abc\vxyz"                        "<0>abc\u2029xyz</0>gh"
+"abc\vxyz"                        "abc\u000d\u000axyzgh"
+"abc\vxyz"                        "abc?xyzgh"
+
+"abc[\v]xyz"                      "<0>abc\u000axyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u000bxyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u000cxyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u000dxyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u0085xyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u2028xyz</0>gh"
+"abc[\v]xyz"                      "<0>abc\u2029xyz</0>gh"
+"abc[\v]xyz"                      "abc\u000d\u000axyzgh"
+"abc[\v]xyz"                      "abc?xyzgh"
+
+"abc\Vxyz"                        "abc\u000axyzgh"
+"abc\Vxyz"                        "abc\u000bxyzgh"
+"abc\Vxyz"                        "abc\u000cxyzgh"
+"abc\Vxyz"                        "abc\u000dxyzgh"
+"abc\Vxyz"                        "abc\u0085xyzgh"
+"abc\Vxyz"                        "abc\u2028xyzgh"
+"abc\Vxyz"                        "abc\u2029xyzgh"
+"abc\Vxyz"                        "abc\u000d\u000axyzgh"
+"abc\Vxyz"                        "<0>abc?xyz</0>gh"
+
+# \h \H horizontal white space. Defined as gc=space_separator plus ascii tab
+
+"abc\hxyz"                        "<0>abc xyz</0>gh"
+"abc\Hxyz"                        "abc xyzgh"
+"abc\hxyz"                        "<0>abc\u2003xyz</0>gh"
+"abc\Hxyz"                        "abc\u2003xyzgh"
+"abc\hxyz"                        "<0>abc\u0009xyz</0>gh"
+"abc\Hxyz"                        "abc\u0009xyzgh"
+"abc\hxyz"                        "abc?xyzgh"
+"abc\Hxyz"                        "<0>abc?xyz</0>gh"
+
+"abc[\h]xyz"                      "<0>abc xyz</0>gh"
+"abc[\H]xyz"                      "abc xyzgh"
+"abc[\h]xyz"                      "<0>abc\u2003xyz</0>gh"
+"abc[\H]xyz"                      "abc\u2003xyzgh"
+"abc[\h]xyz"                      "<0>abc\u0009xyz</0>gh"
+"abc[\H]xyz"                      "abc\u0009xyzgh"
+"abc[\h]xyz"                      "abc?xyzgh"
+"abc[\H]xyz"                      "<0>abc?xyz</0>gh"
+
+
+#
 # Bug xxxx
 #
 "(?:\-|(\-?\d+\d\d\d))?(?:\-|\-(\d\d))?(?:\-|\-(\d\d))?(T)?(?:(\d\d):(\d\d):(\d\d)(\.\d+)?)?(?:(?:((?:\+|\-)\d\d):(\d\d))|(Z))?"   MG  "<0>-1234-21-31T41:51:61.789+71:81</0>"
@@ -1218,6 +1299,21 @@
 "(?<!(0123456789a){10000000})x"         E  "no match"
 "(?<!\\ubeaf(\\ubeaf{11000}){11000})"   E  "no match"
 
+# Bug 11374 Bad integer overflow check in number conversion.
+#           4294967300 converts to 4 with 32 bit overflow.
+
+"x{4294967300}"                         E  "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+"x{0,4294967300}"                       E  "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+
+# Bug 11373
+#
+#    Overflow checking in max match length computation for loops.
+#    Value here is 10 * 100000 * 3000 = 3E9, overflowing a 32 bit signed value.
+#    Before fixing, this case gave an assertion failure.
+
+"(?<=((0123456789){100000}){3000})abc"  E  "abc"
+
+
 
 #  Random debugging, Temporary
 #