From 84adefa331c4159d432d22840663c38f155cd4c1 Mon Sep 17 00:00:00 2001 From: Erlang/OTP Date: Fri, 20 Nov 2009 14:54:40 +0000 Subject: The R13B03 release. --- lib/compiler/test/bs_utf_SUITE.erl | 396 +++++++++++++++++++++++++++++++++++++ 1 file changed, 396 insertions(+) create mode 100644 lib/compiler/test/bs_utf_SUITE.erl (limited to 'lib/compiler/test/bs_utf_SUITE.erl') diff --git a/lib/compiler/test/bs_utf_SUITE.erl b/lib/compiler/test/bs_utf_SUITE.erl new file mode 100644 index 0000000000..d93bdef73d --- /dev/null +++ b/lib/compiler/test/bs_utf_SUITE.erl @@ -0,0 +1,396 @@ +%% +%% %CopyrightBegin% +%% +%% Copyright Ericsson AB 2008-2009. All Rights Reserved. +%% +%% The contents of this file are subject to the Erlang Public License, +%% Version 1.1, (the "License"); you may not use this file except in +%% compliance with the License. You should have received a copy of the +%% Erlang Public License along with this software. If not, it can be +%% retrieved online at http://www.erlang.org/. +%% +%% Software distributed under the License is distributed on an "AS IS" +%% basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See +%% the License for the specific language governing rights and limitations +%% under the License. +%% +%% %CopyrightEnd% +%% + +-module(bs_utf_SUITE). + +-export([all/1, + utf8_roundtrip/1,unused_utf_char/1,utf16_roundtrip/1, + utf32_roundtrip/1,guard/1,extreme_tripping/1, + literals/1,coverage/1]). + +-include("test_server.hrl"). + +all(suite) -> + test_lib:recompile(?MODULE), + [utf8_roundtrip,unused_utf_char,utf16_roundtrip, + utf32_roundtrip,guard,extreme_tripping, + literals,coverage]. + +utf8_roundtrip(Config) when is_list(Config) -> + ?line [utf8_roundtrip_1(P) || P <- utf_data()], + ok. + +utf8_roundtrip_1({Str,Bin,Bin}) -> + ?line Str = utf8_to_list(Bin), + ?line Bin = list_to_utf8(Str), + ?line [ok = utf8_guard(C, <<42,C/utf8>>) || C <- Str], + ?line [error = utf8_guard(C, <>) || C <- Str], + ok. + +utf8_guard(C, Bin) when <<42,C/utf8>> =:= Bin -> ok; +utf8_guard(_, _) -> error. + +utf8_to_list(<>) -> + [C|utf8_to_list(T)]; +utf8_to_list(<<>>) -> []. + +list_to_utf8(L) -> + list_to_utf8(L, <<>>). + +list_to_utf8([H|T], Bin) -> + list_to_utf8(T, <>); +list_to_utf8([], Bin) -> Bin. + +unused_utf_char(Config) when is_list(Config) -> + [true = utf8_len(Utf8) =:= length(Str) || + {Str,Utf8} <- utf_data()], + ok. + +utf8_len(B) -> + utf8_len(B, 0). + +utf8_len(<<_/utf8,T/binary>>, N) -> + utf8_len(T, N+1); +utf8_len(<<>>, N) -> N. + +utf16_roundtrip(Config) when is_list(Config) -> + ?line {Str,Big,Big,Little,Little} = utf16_data(), + ?line 4 = utf16_big_len(Big), + ?line 4 = utf16_little_len(Little), + ?line Str = big_utf16_to_list(Big), + ?line Str = little_utf16_to_list(Little), + + ?line Big = list_to_big_utf16(Str), + ?line Little = list_to_little_utf16(Str), + + ok. + +utf16_big_len(B) -> + utf16_big_len(B, 0). + +utf16_big_len(<<_/utf16,T/binary>>, N) -> + utf16_big_len(T, N+1); +utf16_big_len(<<>>, N) -> N. + +utf16_little_len(B) -> + utf16_little_len(B, 0). + +utf16_little_len(<<_/little-utf16,T/binary>>, N) -> + utf16_little_len(T, N+1); +utf16_little_len(<<>>, N) -> N. + +list_to_big_utf16(List) -> + list_to_big_utf16(List, <<>>). + +list_to_big_utf16([H|T], Bin) -> + list_to_big_utf16(T, <>); +list_to_big_utf16([], Bin) -> Bin. + +list_to_little_utf16(List) -> + list_to_little_utf16(List, <<>>). + +list_to_little_utf16([H|T], Bin) -> + list_to_little_utf16(T, <>); +list_to_little_utf16([], Bin) -> Bin. + +big_utf16_to_list(<>) -> + [H|big_utf16_to_list(T)]; +big_utf16_to_list(<<>>) -> []. + +little_utf16_to_list(<>) -> + [H|little_utf16_to_list(T)]; +little_utf16_to_list(<<>>) -> []. + +utf32_roundtrip(Config) when is_list(Config) -> + ?line {Str,Big,Big,Little,Little} = utf32_data(), + ?line 4 = utf32_big_len(Big), + ?line 4 = utf32_little_len(Little), + ?line Str = big_utf32_to_list(Big), + ?line Str = little_utf32_to_list(Little), + + ?line Big = list_to_big_utf32(Str), + ?line Little = list_to_little_utf32(Str), + + ok. + +utf32_big_len(B) -> + utf32_big_len(B, 0). + +utf32_big_len(<<_/utf32,T/binary>>, N) -> + utf32_big_len(T, N+1); +utf32_big_len(<<>>, N) -> N. + +utf32_little_len(B) -> + utf32_little_len(B, 0). + +utf32_little_len(<<_/little-utf32,T/binary>>, N) -> + utf32_little_len(T, N+1); +utf32_little_len(<<>>, N) -> N. + +list_to_big_utf32(List) -> + list_to_big_utf32(List, <<>>). + +list_to_big_utf32([H|T], Bin) -> + list_to_big_utf32(T, <>); +list_to_big_utf32([], Bin) -> Bin. + +list_to_little_utf32(List) -> + list_to_little_utf32(List, <<>>). + +list_to_little_utf32([H|T], Bin) -> + list_to_little_utf32(T, <>); +list_to_little_utf32([], Bin) -> Bin. + +big_utf32_to_list(<>) -> + [H|big_utf32_to_list(T)]; +big_utf32_to_list(<<>>) -> []. + +little_utf32_to_list(<>) -> + [H|little_utf32_to_list(T)]; +little_utf32_to_list(<<>>) -> []. + + +guard(Config) when is_list(Config) -> + ?line error = do_guard(16#D800), + ok. + +do_guard(C) when byte_size(<>) =/= 42 -> ok; +do_guard(C) when byte_size(<>) =/= 42 -> ok; +do_guard(C) when byte_size(<>) =/= 42 -> ok; +do_guard(_) -> error. + +%% The purpose of this test is to make sure that +%% the delayed creation of sub-binaries works. + +extreme_tripping(Config) when is_list(Config) -> + ?line Unicode = lists:seq(0, 1024), + ?line Utf8 = unicode_to_utf8(Unicode, <<>>), + ?line Utf16 = utf8_to_utf16(Utf8, <<>>), + ?line Utf32 = utf8_to_utf32(Utf8, <<>>), + ?line Utf32 = utf16_to_utf32(Utf16, <<>>), + ?line Utf8 = utf32_to_utf8(Utf32, <<>>), + ?line Unicode = utf32_to_unicode(Utf32), + ok. + +unicode_to_utf8([C|T], Bin) -> + unicode_to_utf8(T, <>); +unicode_to_utf8([], Bin) -> Bin. + +utf8_to_utf16(<>, Bin) -> + utf8_to_utf16(T, <>); +utf8_to_utf16(<<>>, Bin) -> Bin. + +utf16_to_utf32(<>, Bin) -> + utf16_to_utf32(T, <>); +utf16_to_utf32(<<>>, Bin) -> Bin. + +utf8_to_utf32(<>, Bin) -> + utf8_to_utf32(T, <>); +utf8_to_utf32(<<>>, Bin) -> Bin. + +utf32_to_utf8(<>, Bin) -> + utf32_to_utf8(T, <>); +utf32_to_utf8(<<>>, Bin) -> Bin. + +utf32_to_unicode(<>) -> + [C|utf32_to_unicode(T)]; +utf32_to_unicode(<<>>) -> []. + +literals(Config) when is_list(Config) -> + ?line abc_utf8 = match_literal(<<"abc"/utf8>>), + ?line abc_utf8 = match_literal(<<$a,$b,$c>>), + + ?line abc_utf16be = match_literal(<<"abc"/utf16>>), + ?line abc_utf16be = match_literal(<<$a:16,$b:16,$c:16>>), + ?line abc_utf16le = match_literal(<<"abc"/little-utf16>>), + ?line abc_utf16le = match_literal(<<$a:16/little,$b:16/little,$c:16/little>>), + + ?line abc_utf32be = match_literal(<<"abc"/utf32>>), + ?line abc_utf32be = match_literal(<<$a:32,$b:32,$c:32>>), + ?line abc_utf32le = match_literal(<<"abc"/little-utf32>>), + ?line abc_utf32le = match_literal(<<$a:32/little,$b:32/little,$c:32/little>>), + + ?line bjorn_utf8 = match_literal(<<"bj\366rn"/utf8>>), + ?line bjorn_utf8 = match_literal(<<$b,$j,195,182,$r,$n>>), + + ?line bjorn_utf16be = match_literal(<<"bj\366rn"/utf16>>), + ?line bjorn_utf16be = match_literal(<<$b:16,$j:16,246:16,$r:16,$n:16>>), + ?line bjorn_utf16le = match_literal(<<"bj\366rn"/little-utf16>>), + ?line bjorn_utf16le = match_literal(<<$b:16/little,$j:16/little, + 246:16/little,$r:16/little, + $n:16/little>>), + ?line <<244,143,191,191>> = <<16#10ffff/utf8>>, + + %% Invalid literals. + I = 0, + ?line {'EXIT',{badarg,_}} = (catch <<(-1)/utf8,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<(-1)/utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<(-1)/little-utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<(-1)/utf32,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<(-1)/little-utf32,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf8,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf8,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/utf8,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#D800/little-utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/little-utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/little-utf16,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#D800/utf32,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#D800/little-utf32,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFE/utf32,I/utf8>>), + ?line {'EXIT',{badarg,_}} = (catch <<16#FFFF/little-utf32,I/utf8>>), + + B = 16#10FFFF+1, + ?line {'EXIT',{badarg,_}} = (catch <>), + ?line {'EXIT',{badarg,_}} = (catch <>), + ?line {'EXIT',{badarg,_}} = (catch <>), + ?line {'EXIT',{badarg,_}} = (catch <>), + ?line {'EXIT',{badarg,_}} = (catch <>), + + %% Matching of bad literals. + ?line error = bad_literal_match(<<237,160,128>>), %16#D800 in UTF-8 + ?line error = bad_literal_match(<<239,191,190>>), %16#FFFE in UTF-8 + ?line error = bad_literal_match(<<239,191,191>>), %16#FFFF in UTF-8 + ?line error = bad_literal_match(<<244,144,128,128>>), %16#110000 in UTF-8 + + ?line error = bad_literal_match(<<255,254>>), %16#FFFE in UTF-16 + ?line error = bad_literal_match(<<255,255>>), %16#FFFF in UTF-16 + + ?line error = bad_literal_match(<<16#D800:32>>), + ?line error = bad_literal_match(<<16#FFFE:32>>), + ?line error = bad_literal_match(<<16#FFFF:32>>), + ?line error = bad_literal_match(<<16#110000:32>>), + ?line error = bad_literal_match(<<16#D800:32/little>>), + ?line error = bad_literal_match(<<16#FFFE:32/little>>), + ?line error = bad_literal_match(<<16#FFFF:32/little>>), + ?line error = bad_literal_match(<<16#110000:32/little>>), + + ok. + +match_literal(<<"abc"/utf8>>) -> abc_utf8; +match_literal(<<"abc"/big-utf16>>) -> abc_utf16be; +match_literal(<<"abc"/little-utf16>>) -> abc_utf16le; +match_literal(<<"abc"/big-utf32>>) -> abc_utf32be; +match_literal(<<"abc"/little-utf32>>) -> abc_utf32le; +match_literal(<<"bj\366rn"/utf8>>) -> bjorn_utf8; +match_literal(<<"bj\366rn"/big-utf16>>) -> bjorn_utf16be; +match_literal(<<"bj\366rn"/little-utf16>>) -> bjorn_utf16le. + +bad_literal_match(<<16#D800/utf8>>) -> ok; +bad_literal_match(<<16#FFFE/utf8>>) -> ok; +bad_literal_match(<<16#FFFF/utf8>>) -> ok; +bad_literal_match(<<16#110000/utf8>>) -> ok; +bad_literal_match(<<16#FFFE/utf16>>) -> ok; +bad_literal_match(<<16#FFFF/utf16>>) -> ok; +bad_literal_match(<<16#D800/utf32>>) -> ok; +bad_literal_match(<<16#110000/utf32>>) -> ok; +bad_literal_match(<<16#D800/little-utf32>>) -> ok; +bad_literal_match(<<16#110000/little-utf32>>) -> ok; +bad_literal_match(_) -> error. + +coverage(Config) when is_list(Config) -> + %% Cover bit syntax matching optimizations in v3_kernel. + ?line 0 = coverage_1(<<4096/utf8,65536/utf8,0>>), + ?line 1 = coverage_1(<<4096/utf8,65536/utf8,1>>), + + ?line 0 = coverage_2(<<4096/utf8,65536/utf8,0>>), + ?line 1 = coverage_2(<<1024/utf8,1025/utf8,1>>), + + ?line {'EXIT',{function_clause,_}} = (catch coverage_3(1)), + + %% Cover beam_flatten (combining the heap allocation in + %% a subsequent test_heap instruction into the bs_init2 + %% instruction). + {ok,<<533/utf8>>} = cover_test_heap_utf8(533), + {ok,<<1024/utf16>>} = cover_test_heap_utf16(1024), + {ok,<<7966/utf32>>} = cover_test_heap_utf32(7966), + + ok. + +coverage_1(<<4096/utf8,65536/utf8,0>>) -> 0; +coverage_1(<<4096/utf8,65536/utf8,1>>) -> 1. + +coverage_2(<<4096/utf8,65536/utf8,0>>) -> 0; +coverage_2(<<1024/utf8,1025/utf8,1>>) -> 1. + +coverage_3(<<16#7fffffff/utf8,65536/utf8,0>>) -> 0. + +cover_test_heap_utf8(C) -> {ok,<>}. +cover_test_heap_utf16(C) -> {ok,<>}. +cover_test_heap_utf32(C) -> {ok,<>}. + +utf_data() -> +%% From RFC-3629. + + %% Give the compiler a chance to do some constant propagation. + NotIdentical = 16#2262, + + [ + %% "A." + {[16#0041,NotIdentical,16#0391,16#002E], + <<16#0041/utf8,NotIdentical/utf8,16#0391/utf8,16#002E/utf8>>, + <<16#41,16#E2,16#89,16#A2,16#CE,16#91,16#2E>>}, + + %% Korean "hangugeo" (meaning "the Korean language") + {[16#D55C,16#AD6D,16#C5B4], + <<16#D55C/utf8,16#AD6D/utf8,16#C5B4/utf8>>, + <<16#ED,16#95,16#9C,16#EA,16#B5,16#AD,16#EC,16#96,16#B4>>}, + + %% Japanese "nihongo" (meaning "the Japanese language"). + {[16#65E5,16#672C,16#8A9E], + <<16#65E5/utf8,16#672C/utf8,16#8A9E/utf8>>, + <<16#E6,16#97,16#A5,16#E6,16#9C,16#AC,16#E8,16#AA,16#9E>>} + ]. + +utf16_data() -> + %% Example from RFC-2781. "*=Ra", where "*" represents a + %% hypothetical Ra hieroglyph (code point 16#12345). + + %% Give the compiler a chance to do some constant propagation. + RaHieroglyph = 16#12345, + + %% First as a list of Unicode characters. + {[RaHieroglyph,16#3D,16#52,16#61], + + %% Big endian (the two binaries should be equal). + <>, + <<16#D8,16#08,16#DF,16#45,16#00,16#3D,16#00,16#52,16#00,16#61>>, + + %% Little endian (the two binaries should be equal). + <>, + <<16#08,16#D8,16#45,16#DF,16#3D,16#00,16#52,16#00,16#61,16#00>>}. + +utf32_data() -> + %% "A." + NotIdentical = 16#2262, + {[16#0041,NotIdentical,16#0391,16#002E], + + %% Big endian. + <<16#0041/utf32,NotIdentical/utf32,16#0391/utf32,16#002E/utf32>>, + <<16#41:32,NotIdentical:32,16#0391:32,16#2E:32>>, + + %% Little endian. + <<16#0041/little-utf32,NotIdentical/little-utf32, + 16#0391/little-utf32,16#002E/little-utf32>>, + <<16#41:32/little,NotIdentical:32/little, + 16#0391:32/little,16#2E:32/little>>}. + -- cgit v1.2.3