summaryrefslogtreecommitdiff
path: root/tests/test-wcwidth.c
diff options
context:
space:
mode:
authorJörg Frings-Fürst <debian@jff.email>2022-02-07 06:57:44 +0100
committerJörg Frings-Fürst <debian@jff.email>2022-02-07 06:57:44 +0100
commit6ffaa52cf732a84c0f8259dbc9b8183960ec5c33 (patch)
treed3136c22e3e805cfc0efe78412cce905a17e0c8d /tests/test-wcwidth.c
parent591cbf5878b7d4105b275585b9db1324c9dfce56 (diff)
parentaf151c593704a40e10efb28d1e3dd59a23a661f3 (diff)
Merge branch 'release/debian/1.0-1'debian/1.0-1
Diffstat (limited to 'tests/test-wcwidth.c')
-rw-r--r--tests/test-wcwidth.c28
1 files changed, 25 insertions, 3 deletions
diff --git a/tests/test-wcwidth.c b/tests/test-wcwidth.c
index f0eb7ab4..c2be2f32 100644
--- a/tests/test-wcwidth.c
+++ b/tests/test-wcwidth.c
@@ -1,5 +1,5 @@
/* Test of wcwidth() function.
- Copyright (C) 2007-2018 Free Software Foundation, Inc.
+ Copyright (C) 2007-2022 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -35,10 +35,12 @@ main ()
{
wchar_t wc;
-#ifdef C_CTYPE_ASCII
+#if !GNULIB_WCHAR_SINGLE_LOCALE
+# ifdef C_CTYPE_ASCII
/* Test width of ASCII characters. */
for (wc = 0x20; wc < 0x7F; wc++)
ASSERT (wcwidth (wc) == 1);
+# endif
#endif
/* Switch to an UTF-8 locale. */
@@ -67,9 +69,29 @@ main ()
#endif
/* Test width of some zero width characters. */
- ASSERT (wcwidth (0x200B) == 0);
+ /* While it is desirable that U+200B, U+200C, U+200D have width 0,
+ because this makes wcswidth work better on strings that contain these
+ characters, it is acceptable if an implementation treats these
+ characters like control characters. */
+ ASSERT (wcwidth (0x200B) <= 0);
ASSERT (wcwidth (0xFEFF) <= 0);
+ /* Test width of some math symbols.
+ U+2202 is marked as having ambiguous width (A) in EastAsianWidth.txt
+ (see <https://www.unicode.org/Public/12.0.0/ucd/EastAsianWidth.txt>).
+ The Unicode Standard Annex 11
+ <https://www.unicode.org/reports/tr11/tr11-36.html>
+ says
+ "Ambiguous characters behave like wide or narrow characters
+ depending on the context (language tag, script identification,
+ associated font, source of data, or explicit markup; all can
+ provide the context). If the context cannot be established
+ reliably, they should be treated as narrow characters by default."
+ For wcwidth(), the only available context information is the locale.
+ "fr_FR.UTF-8" is a Western locale, not an East Asian locale, therefore
+ U+2202 should be treated like a narrow character. */
+ ASSERT (wcwidth (0x2202) == 1);
+
/* Test width of some CJK characters. */
ASSERT (wcwidth (0x3000) == 2);
ASSERT (wcwidth (0xB250) == 2);