From ef0dbc4f2a43d629d086c3e2b9a762bbc00d034b Mon Sep 17 00:00:00 2001
From: Hans Bolinder <hasse@erlang.org>
Date: Wed, 19 Apr 2017 16:10:15 +0200
Subject: stdlib: Add Unicode modifier t to control sequences w and W

As of the introduction of Unicode characters in atoms, the control
sequences 'w' and 'W' can return non-Latin-1 characters, unless some
measure is taken.

This commit makes sure that '~w' and '~W' always return Latin-1
characters, or bytes, which can be output to ports or written to raw
files.

The Unicode translation modifier 't' is needed to return non-Latin-1
characters.
---
 lib/stdlib/test/io_SUITE.erl | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'lib/stdlib/test/io_SUITE.erl')

diff --git a/lib/stdlib/test/io_SUITE.erl b/lib/stdlib/test/io_SUITE.erl
index b2754e47ba..fb62e3aa3c 100644
--- a/lib/stdlib/test/io_SUITE.erl
+++ b/lib/stdlib/test/io_SUITE.erl
@@ -2348,4 +2348,19 @@ otp_14285(_Config) ->
     L1 = [S || C <- Chars, S <- io_lib:write_atom(list_to_atom([C])),
                not is_latin1(S)],
     L1 = lists:seq(256, 512),
+
+    latin1_fmt("~w", ['кирилли́ческий атом']),
+    latin1_fmt("~w", ['\x{10FFFF}']),
+    "'кирилли́ческий атом'" = fmt("~tw", ['кирилли́ческий атом']),
+    [$',16#10FFFF,$'] = fmt("~tw", ['\x{10FFFF}']),
+
+    latin1_fmt("~W", ['кирилли́ческий атом', 13]),
+    latin1_fmt("~W", ['\x{10FFFF}', 13]),
+    "'кирилли́ческий атом'" = fmt("~tW", ['кирилли́ческий атом', 13]),
+    [$',16#10FFFF,$'] = fmt("~tW", ['\x{10FFFF}', 13]),
+
     ok.
+
+latin1_fmt(Fmt, Args) ->
+    L = fmt(Fmt, Args),
+    true = lists:all(fun is_latin1/1, L).
-- 
cgit v1.2.3