|
|
@@ -1,5 +1,5 @@
|
|
|
# IdnaTest.txt
|
|
|
-# Date: 2017-05-22, 14:06:39 GMT
|
|
|
+# Date: 2017-06-02, 14:19:52 GMT
|
|
|
# © 2017 Unicode®, Inc.
|
|
|
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
|
|
|
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
|
|
@@ -21,16 +21,16 @@
|
|
|
# Leading and trailing spaces and tabs in each column are ignored.
|
|
|
# Comments are indicated with hash marks.
|
|
|
#
|
|
|
-# Column 1: type - T for transitional, N for nontransitional, B for both
|
|
|
-# Column 2: source - The source string to be tested
|
|
|
-# Column 3: toUnicode - The result of applying toUnicode to the source, using nontransitional.
|
|
|
-# A blank value means the same as the source value; a value in [...] is a set of status codes.
|
|
|
-# Column 4: toASCII - The result of applying toASCII to the source, using the specified type: T, N, or B.
|
|
|
-# A blank value means the same as the toUnicode value; a value in [...] is a set of status codes.
|
|
|
-# Column 5: idna2008Status - NV8 is only present if the status is valid but the character is excluded by IDNA2008
|
|
|
-# from all domain names for all versions of Unicode.
|
|
|
-# XV8 is present when the character is excluded by IDNA2008 for the current version of Unicode.
|
|
|
-# These are informative values only.
|
|
|
+# Column 1: type - T for transitional, N for nontransitional, B for both
|
|
|
+# Column 2: source - The source string to be tested
|
|
|
+# Column 3: toUnicode - The result of applying toUnicode to the source, using nontransitional.
|
|
|
+# A blank value means the same as the source value; a value in [...] is a set of error codes.
|
|
|
+# Column 4: toASCII - The result of applying toASCII to the source, using the specified type: T, N, or B.
|
|
|
+# A blank value means the same as the toUnicode value; a value in [...] is a set of error codes.
|
|
|
+# Column 5: idna2008 - NV8 is only present if the status is valid but the character is excluded by IDNA2008
|
|
|
+# from all domain names for all versions of Unicode.
|
|
|
+# XV8 is present when the character is excluded by IDNA2008 for the current version of Unicode.
|
|
|
+# These are informative values only.
|
|
|
#
|
|
|
# If the value of toUnicode is the same as source, the column will be blank.
|
|
|
# The line comments currently show visible characters that have been escaped
|
|
|
@@ -59,10 +59,10 @@
|
|
|
#
|
|
|
# CONFORMANCE:
|
|
|
#
|
|
|
-# To test for conformance to UTS46, an implementation must first perform the toASCII and to Unicode operations
|
|
|
-# on the source string, with the indicated type. Implementations may be more strict than UTS46;
|
|
|
-# thus they may have errors where the file indicates results. In particular, an implementation conformant to
|
|
|
-# IDNA2008 would disallow the input for lines marked with NV8.
|
|
|
+# To test for conformance to UTS46, an implementation must first perform the toUnicode operation
|
|
|
+# on the source string, then the toASCII operation (with the indicated type) on the source string.
|
|
|
+# Implementations may be more strict than UTS46; thus they may have errors where the file indicates results.
|
|
|
+# In particular, an implementation conformant to IDNA2008 would disallow the input for lines marked with NV8.
|
|
|
#
|
|
|
# Moreover, the error codes in the file are informative; implementations need only record that there is an error:
|
|
|
# they need not reproduce those codes. Thus to then verify conformance for the toASCII and toUnicode columns:
|
|
|
@@ -569,12 +569,16 @@ N; \u0644\u200C; [B3 C1]; [B3 C1] # ل
|
|
|
B; xn--ghb; \u0644; xn--ghb # ل
|
|
|
B; \u0644; ; xn--ghb # ل
|
|
|
B; xn--ghb413k; [B3 C1]; [B3 C1] # ل
|
|
|
+B; a。。b; [A4_2]; [A4_2]
|
|
|
+B; A。。B; [A4_2]; [A4_2]
|
|
|
+B; a..b; [A4_2]; [A4_2]
|
|
|
T; \u200D。。\u06B9\u200C; [B1 B3 C1 C2 A4_2]; [A4_2] # ..ڹ
|
|
|
N; \u200D。。\u06B9\u200C; [B1 B3 C1 C2 A4_2]; [B1 B3 C1 C2 A4_2] # ..ڹ
|
|
|
B; ..xn--skb; [A4_2]; [A4_2] # ..ڹ
|
|
|
B; xn--1ug..xn--skb080k; [B1 B3 C1 C2 A4_2]; [B1 B3 C1 C2 A4_2] # ..ڹ
|
|
|
B; \u05D00\u0660; [B4]; [B4] # א0٠
|
|
|
B; xn--0-zhc74b; [B4]; [B4] # א0٠
|
|
|
+B; $; [P1 V6]; [P1 V6]
|
|
|
|
|
|
# RANDOMIZED TESTS
|
|
|
|
Behnam Esfahbod