From 11a642476470712fee8d6f78424d56b8b6da92d7 Mon Sep 17 00:00:00 2001 From: Hans Bolinder Date: Wed, 13 Feb 2013 12:33:31 +0100 Subject: Extend ~ts to handle binaries with characters coded in ISO-latin-1 Make sure io_lib:fwrite() with a format string including "~ts" does not crash when given binaries that cannot be interpreted as UTF-8-encoded strings. We want to avoid crashes caused by excessive use of the 't' modifier. --- lib/stdlib/src/io_lib_format.erl | 22 ++++++++++++++++++++-- lib/stdlib/test/io_SUITE.erl | 11 +++++++++-- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/lib/stdlib/src/io_lib_format.erl b/lib/stdlib/src/io_lib_format.erl index 6a06d9448b..64d19ccf48 100644 --- a/lib/stdlib/src/io_lib_format.erl +++ b/lib/stdlib/src/io_lib_format.erl @@ -185,8 +185,7 @@ control($s, [L0], F, Adj, P, Pad, latin1, _I) -> L = iolist_to_chars(L0), string(L, F, Adj, P, Pad); control($s, [L0], F, Adj, P, Pad, unicode, _I) -> - L = unicode:characters_to_list(L0), - true = is_list(L), + L = cdata_to_chars(L0), uniconv(string(L, F, Adj, P, Pad)); control($e, [A], F, Adj, P, Pad, _Enc, _I) when is_float(A) -> fwrite_e(A, F, Adj, P, Pad); @@ -558,6 +557,25 @@ iolist_to_chars([]) -> iolist_to_chars(B) when is_binary(B) -> binary_to_list(B). +%% cdata() :: clist() | cbinary() +%% clist() :: maybe_improper_list(char() | cbinary() | clist(), +%% cbinary() | nil()) +%% cbinary() :: unicode:unicode_binary() | unicode:latin1_binary() + +%% cdata_to_chars(cdata()) -> io_lib:deep_char_list() + +cdata_to_chars([C|Cs]) when is_integer(C), C >= $\000 -> + [C | cdata_to_chars(Cs)]; +cdata_to_chars([I|Cs]) -> + [cdata_to_chars(I) | cdata_to_chars(Cs)]; +cdata_to_chars([]) -> + []; +cdata_to_chars(B) when is_binary(B) -> + case catch unicode:characters_to_list(B) of + L when is_list(L) -> L; + _ -> binary_to_list(B) + end. + %% string(String, Field, Adjust, Precision, PadChar) string(S, none, _Adj, none, _Pad) -> S; diff --git a/lib/stdlib/test/io_SUITE.erl b/lib/stdlib/test/io_SUITE.erl index 05009fa570..65a112c966 100644 --- a/lib/stdlib/test/io_SUITE.erl +++ b/lib/stdlib/test/io_SUITE.erl @@ -29,7 +29,7 @@ manpage/1, otp_6708/1, otp_7084/1, otp_7421/1, io_lib_collect_line_3_wb/1, cr_whitespace_in_string/1, io_fread_newlines/1, otp_8989/1, io_lib_fread_literal/1, - io_lib_print_binary_depth_one/1, otp_10302/1]). + io_lib_print_binary_depth_one/1, otp_10302/1, otp_10836/1]). %-define(debug, true). @@ -65,7 +65,7 @@ all() -> manpage, otp_6708, otp_7084, otp_7421, io_lib_collect_line_3_wb, cr_whitespace_in_string, io_fread_newlines, otp_8989, io_lib_fread_literal, - io_lib_print_binary_depth_one, otp_10302]. + io_lib_print_binary_depth_one, otp_10302, otp_10836]. groups() -> []. @@ -2078,3 +2078,10 @@ pretty(Term, Opts) when is_list(Opts) -> is_latin1(S) -> S >= 0 andalso S =< 255. + +otp_10836(doc) -> + "OTP-10836. ~ts extended to latin1"; +otp_10836(Suite) when is_list(Suite) -> + S = io_lib:format("~ts", [[<<"äpple"/utf8>>, <<"äpple">>]]), + "äppleäpple" = lists:flatten(S), + ok. -- cgit v1.2.3