diff options
Diffstat (limited to 'lib/xmerl/src')
-rw-r--r-- | lib/xmerl/src/xmerl_dtd.erl | 0 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_lib.erl | 9 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_sax_parser.erl | 7 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_sax_parser_base.erlsrc | 41 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_sax_parser_utf16be.erlsrc | 4 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_sax_parser_utf16le.erlsrc | 4 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_scan.erl | 73 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_ucs.erl | 37 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_uri.erl | 8 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_xpath.erl | 8 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_xsd.erl | 68 | ||||
-rw-r--r-- | lib/xmerl/src/xmerl_xsd_type.erl | 6 |
12 files changed, 174 insertions, 91 deletions
diff --git a/lib/xmerl/src/xmerl_dtd.erl b/lib/xmerl/src/xmerl_dtd.erl deleted file mode 100644 index e69de29bb2..0000000000 --- a/lib/xmerl/src/xmerl_dtd.erl +++ /dev/null diff --git a/lib/xmerl/src/xmerl_lib.erl b/lib/xmerl/src/xmerl_lib.erl index 7b76a76a33..6402f1cbeb 100644 --- a/lib/xmerl/src/xmerl_lib.erl +++ b/lib/xmerl/src/xmerl_lib.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2003-2009. All Rights Reserved. +%% Copyright Ericsson AB 2003-2011. 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 @@ -148,9 +148,10 @@ expand_element(Element) -> expand_element(Element, Pos, Parents) -> expand_element(Element, Pos, Parents, false). -expand_element(E = #xmlElement{}, Pos, Parents, Norm) -> - Content = expand_content(E#xmlElement.content, 1, Parents, Norm), - Attrs = expand_attributes(E#xmlElement.attributes, 1, []), +expand_element(E = #xmlElement{name = N}, Pos, Parents, Norm) -> + NewParents = [{N,Pos}|Parents], + Content = expand_content(E#xmlElement.content, 1, NewParents, Norm), + Attrs = expand_attributes(E#xmlElement.attributes, 1, NewParents), E#xmlElement{pos = Pos, parents = Parents, attributes = Attrs, diff --git a/lib/xmerl/src/xmerl_sax_parser.erl b/lib/xmerl/src/xmerl_sax_parser.erl index eb9f8deec6..45e2a928ac 100644 --- a/lib/xmerl/src/xmerl_sax_parser.erl +++ b/lib/xmerl/src/xmerl_sax_parser.erl @@ -1,7 +1,7 @@ %%-------------------------------------------------------------------- %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2008-2009. All Rights Reserved. +%% Copyright Ericsson AB 2008-2011. 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 @@ -263,11 +263,11 @@ detect_charset_1(<<16#3C, 16#3F, 16#78, 16#6D, 16#6C, Xml2/binary>> = Xml, State {Xml, State#xmerl_sax_parser_state{encoding=Enc}} end; _ -> - {Xml, State#xmerl_sax_parser_state{encoding=utf8}} + {Xml, State} end end; detect_charset_1(Xml, State) -> - {Xml, State#xmerl_sax_parser_state{encoding=utf8}}. + {Xml, State}. %%---------------------------------------------------------------------- %% Function: convert_encoding(Enc) @@ -278,6 +278,7 @@ detect_charset_1(Xml, State) -> convert_encoding(Enc) -> %% Just for 7,8 bit + utf8 case string:to_lower(Enc) of "utf-8" -> utf8; + "us-ascii" -> utf8; "iso-8859-1" -> latin1; % Handle all iso-8859 as latin1 "iso-8859-2" -> latin1; "iso-8859-3" -> latin1; diff --git a/lib/xmerl/src/xmerl_sax_parser_base.erlsrc b/lib/xmerl/src/xmerl_sax_parser_base.erlsrc index 9d184152d1..3b9eaa309c 100644 --- a/lib/xmerl/src/xmerl_sax_parser_base.erlsrc +++ b/lib/xmerl/src/xmerl_sax_parser_base.erlsrc @@ -1,7 +1,7 @@ %%-*-erlang-*- %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2008-2009. All Rights Reserved. +%% Copyright Ericsson AB 2008-2010. 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 @@ -934,6 +934,13 @@ parse_att_value(?STRING_REST("&", Rest), State, Stop, Acc) -> parse_att_value(Rest1, State2, Stop, ParsedValue ++ Acc); {external_general, Name, _} -> ?fatal_error(State1, "External parsed entity reference in attribute value: " ++ Name); + {not_found, Name} -> + case State#xmerl_sax_parser_state.skip_external_dtd of + false -> + ?fatal_error(State1, "Entity not declared: " ++ Name); %%VC: Entity Declared + true -> + parse_att_value(Rest1, State1, Stop, ";" ++ lists:reverse(Name) ++ "&" ++ Acc) + end; {unparsed, Name, _} -> ?fatal_error(State1, "Unparsed entity reference in attribute value: " ++ Name) end; @@ -1098,6 +1105,13 @@ parse_content(?STRING_REST("&", Rest), State, Acc, _IgnorableWS) -> {external_general, _, {PubId, SysId}} -> State2 = parse_external_entity(State1, PubId, SysId), parse_content(Rest1, State2, Acc, false); + {not_found, Name} -> + case State#xmerl_sax_parser_state.skip_external_dtd of + false -> + ?fatal_error(State1, "Entity not declared: " ++ Name); %%VC: Entity Declared + true -> + parse_content(Rest1, State1, ";" ++ lists:reverse(Name) ++ "&" ++ Acc, false) + end; {unparsed, Name, _} -> ?fatal_error(State1, "Unparsed entity reference in content: " ++ Name) end; @@ -1357,7 +1371,7 @@ look_up_reference(Name, HaveToExist, State) -> yes -> ?fatal_error(State, "Entity not declared: " ++ Name); %%WFC: Entity Declared no -> - ?fatal_error(State, "Entity not declared: " ++ Name) %%VC: Entity Declared + {not_found, Name} %%VC: Entity Declared end; false -> {not_found, Name} @@ -1869,7 +1883,14 @@ parse_doctype_decl(?STRING_REST("%", Rest), State) -> parse_doctype_decl(?APPEND_STRING(IValue, Rest1), State1); {external_parameter, _, {PubId, SysId}} -> State2 = parse_external_entity(State1#xmerl_sax_parser_state{file_type = entity}, PubId, SysId), - parse_doctype_decl(Rest1, State2) + parse_doctype_decl(Rest1, State2); + {not_found, Name} -> + case State#xmerl_sax_parser_state.skip_external_dtd of + false -> + ?fatal_error(State1, "Entity not declared: " ++ Name); %%WFC: Entity Declared + true -> + parse_doctype_decl(Rest1, State1) + end end; parse_doctype_decl(?STRING_REST("<!", Rest1), State) -> parse_doctype_decl_1(Rest1, State); @@ -2443,7 +2464,7 @@ parse_ndata(Bytes, State) -> %% Acc = string() %% Result : {Value, Rest, State} %% Value = string() -%% Description: Parse an attribute value +%% Description: Parse an entity value %%---------------------------------------------------------------------- parse_entity_value(?STRING_EMPTY, State, undefined, Acc) -> {Acc, [], State}; %% stop clause when parsing references @@ -2473,7 +2494,7 @@ parse_entity_value(?STRING_REST("&", Rest), State, Stop, Acc) -> {external_general, Name, _} -> parse_entity_value(Rest1, State1, Stop, ";" ++ lists:reverse(Name) ++ "&" ++ Acc); {not_found, Name} -> - parse_entity_value(Rest1, State1, Stop, ";" ++ lists:reverse(Name) ++ "&" ++ Acc); + parse_entity_value(Rest1, State1, Stop, ";" ++ lists:reverse(Name) ++ "&" ++ Acc); {unparsed, Name, _} -> ?fatal_error(State1, "Unparsed entity reference in entity value: " ++ Name) end; @@ -2490,7 +2511,15 @@ parse_entity_value(?STRING_REST("%", Rest), #xmerl_sax_parser_state{file_type=Ty IValue = ?TO_INPUT_FORMAT(" " ++ RefValue ++ " "), parse_entity_value(?APPEND_STRING(IValue, Rest1), State1, Stop, Acc); {external_parameter, _, {_PubId, _SysId}} -> - ?fatal_error(State1, "Parameter references in entity value not supported yet.") + ?fatal_error(State1, "Parameter references in entity value not supported yet."); + {not_found, Name} -> + case State#xmerl_sax_parser_state.skip_external_dtd of + false -> + ?fatal_error(State1, "Entity not declared: " ++ Name); %%VC: Entity Declared + true -> + parse_entity_value(Rest1, State1, Stop, ";" ++ lists:reverse(Name) ++ "&" ++ Acc) + end + end end; parse_entity_value(?STRING_UNBOUND_REST(Stop, Rest), State, Stop, Acc) -> diff --git a/lib/xmerl/src/xmerl_sax_parser_utf16be.erlsrc b/lib/xmerl/src/xmerl_sax_parser_utf16be.erlsrc index fae5346e6a..5c995a5a9c 100644 --- a/lib/xmerl/src/xmerl_sax_parser_utf16be.erlsrc +++ b/lib/xmerl/src/xmerl_sax_parser_utf16be.erlsrc @@ -2,7 +2,7 @@ %%-------------------------------------------------------------------- %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2008-2009. All Rights Reserved. +%% Copyright Ericsson AB 2008-2011. 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 @@ -35,6 +35,6 @@ %% STRING_REST and STRING_UNBOUND_REST is only different in the list case -define(STRING_UNBOUND_REST(MatchChar, Rest), <<MatchChar/big-utf16, Rest/binary>>). --define(BYTE_ORDER_MARK_1, undefined). +-define(BYTE_ORDER_MARK_1, undefined_bom1). -define(BYTE_ORDER_MARK_2, <<16#FE>>). -define(BYTE_ORDER_MARK_REST(Rest), <<16#FE, 16#FF, Rest/binary>>). diff --git a/lib/xmerl/src/xmerl_sax_parser_utf16le.erlsrc b/lib/xmerl/src/xmerl_sax_parser_utf16le.erlsrc index 5e1f0a217c..5c6ca0caba 100644 --- a/lib/xmerl/src/xmerl_sax_parser_utf16le.erlsrc +++ b/lib/xmerl/src/xmerl_sax_parser_utf16le.erlsrc @@ -2,7 +2,7 @@ %%-------------------------------------------------------------------- %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2008-2009. All Rights Reserved. +%% Copyright Ericsson AB 2008-2011. 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 @@ -35,6 +35,6 @@ %% STRING_REST and STRING_UNBOUND_REST is only different in the list case -define(STRING_UNBOUND_REST(MatchChar, Rest), <<MatchChar/little-utf16, Rest/binary>>). --define(BYTE_ORDER_MARK_1, undefined). +-define(BYTE_ORDER_MARK_1, undefined_bom1). -define(BYTE_ORDER_MARK_2, <<16#FF>>). -define(BYTE_ORDER_MARK_REST(Rest), <<16#FF, 16#FE, Rest/binary>>). diff --git a/lib/xmerl/src/xmerl_scan.erl b/lib/xmerl/src/xmerl_scan.erl index 4e5cc59d8f..25c6547497 100644 --- a/lib/xmerl/src/xmerl_scan.erl +++ b/lib/xmerl/src/xmerl_scan.erl @@ -1,19 +1,19 @@ %% %% %CopyrightBegin% -%% -%% Copyright Ericsson AB 2003-2009. All Rights Reserved. -%% +%% +%% Copyright Ericsson AB 2003-2011. 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% %% @@ -34,7 +34,9 @@ %% See also <a href="xmerl_examples.html">tutorial</a> on customization %% functions. %% </p> +%% <p> %% Possible options are: +%% </p> %% <dl> %% <dt><code>{acc_fun, Fun}</code></dt> %% <dd>Call back function to accumulate contents of entity.</dd> @@ -100,6 +102,7 @@ %% declaration. </dd> %% </dl> + -module(xmerl_scan). -vsn('0.20'). -date('03-09-16'). @@ -2071,10 +2074,10 @@ scan_element(T, S, Pos, Name, StartL, StartC, Attrs, Lang, Parents, {AttName, NamespaceInfo, T1, S1} = scan_name(T, S), {T2, S2} = scan_eq(T1, S1), {AttType,_DefaultDecl} = get_att_type(S2,AttName,Name), - {AttValue, T3, S3,IsNorm} = scan_att_value(T2, S2, AttType), + {AttValue, T3a, S3a,IsNorm} = scan_att_value(T2, S2, AttType), %% check_default_value(S3,DefaultDecl,AttValue), NewNS = check_namespace(AttName, NamespaceInfo, AttValue, NS), - wfc_whitespace_betw_attrs(hd(T3),S3), + {T3,S3} = wfc_whitespace_betw_attrs(T3a,S3a), ?strip4, AttrPos = case Attrs of [] -> @@ -2273,7 +2276,7 @@ scan_att_chars([H|T], S0, H, Acc, TmpAcc,AttType,IsNorm) -> % End quote true -> normalize(Acc,S,IsNorm) end, - {lists:reverse(Acc2), T, S2,IsNorm2}; + {lists:flatten(lists:reverse(Acc2)), T, S2,IsNorm2}; scan_att_chars("&" ++ T, S0, Delim, Acc, TmpAcc,AT,IsNorm) -> % Reference ?bump_col(1), {ExpRef, T1, S1} = scan_reference(T, S), @@ -2281,8 +2284,16 @@ scan_att_chars("&" ++ T, S0, Delim, Acc, TmpAcc,AT,IsNorm) -> % Reference true -> scan_att_chars(T1,S1,Delim,[ExpRef|Acc],[ExpRef|TmpAcc],AT,IsNorm); _ -> - scan_att_chars(string_to_char_set(S#xmerl_scanner.encoding,ExpRef) - ++ T1, S1, Delim, Acc,TmpAcc, AT,IsNorm) + Ch = string_to_char_set(S#xmerl_scanner.encoding, ExpRef), + case T of + "#" ++ _ -> + %% normalization rules (sec 3.3.3) require that for + %% character references, the referenced character be + %% added directly to the normalized value + scan_att_chars(T1, S1, Delim, Ch ++ Acc,TmpAcc, AT,IsNorm); + _ -> + scan_att_chars(Ch ++ T1, S1, Delim, Acc,TmpAcc, AT,IsNorm) + end end; scan_att_chars("<" ++ _T, S0, _Delim, _Acc,_, _,_) -> % Tags not allowed here ?fatal(unexpected_char, S0); @@ -2602,8 +2613,7 @@ scan_reference("#x" ++ T, S0) -> %% [66] CharRef ?bump_col(1), if hd(T) /= $; -> - {[Ch], T2, S2} = scan_char_ref_hex(T, S, 0), - {to_char_set(S2#xmerl_scanner.encoding,Ch),T2,S2}; + scan_char_ref_hex(T, S, 0); true -> ?fatal(invalid_char_ref, S) end; @@ -3274,12 +3284,17 @@ wfc_legal_char(Ch,S) -> end. -wfc_whitespace_betw_attrs(WS,_S) when ?whitespace(WS) -> - ok; -wfc_whitespace_betw_attrs($/,_S) -> - ok; -wfc_whitespace_betw_attrs($>,_S) -> - ok; +wfc_whitespace_betw_attrs([WS |_]=L,S) when ?whitespace(WS) -> + {L,S}; +wfc_whitespace_betw_attrs([$/ |_]=L,S) -> + {L,S}; +wfc_whitespace_betw_attrs([$> |_]=L,S) -> + {L,S}; +wfc_whitespace_betw_attrs([],S=#xmerl_scanner{continuation_fun = F}) -> + ?dbg("cont()...~n", []), + F(fun(MoreBytes, S1) -> wfc_whitespace_betw_attrs(MoreBytes, S1) end, + fun(S1) -> ?fatal(unexpected_end, S1) end, + S); wfc_whitespace_betw_attrs(_,S) -> ?fatal({whitespace_required_between_attributes},S). @@ -3452,14 +3467,14 @@ scan_entity_value("%" ++ T, S0, Delim, Acc, PEName,Namespace,PENesting) -> %% {system,URI} or {public,URI} %% Included in literal. {ExpRef,Sx}=fetch_not_parse(Tuple,S1), - {EntV,_,_S2} = - scan_entity_value(ExpRef, Sx, no_delim,[], + {EntV, _, S5} = + scan_entity_value(ExpRef, Sx, no_delim,[], PERefName,parameter,[]), %% should do an update Write(parameter_entity) %% so next expand_pe_reference is faster - {EntV,_S2}; + {string_to_char_set(S5#xmerl_scanner.encoding, EntV), S5}; ExpRef -> - {ExpRef,S1} + {string_to_char_set(S1#xmerl_scanner.encoding, ExpRef) ,S1} end, %% single or duoble qoutes are not treated as delimeters %% in passages "included in literal" @@ -3908,7 +3923,7 @@ schemaLocations(#xmlElement{attributes=Atts,xmlbase=_Base}) -> case lists:dropwhile(Pred,Atts) of [#xmlAttribute{value=Paths}|_] -> - case string:tokens(Paths," ") of + case string:tokens(Paths," \n\t\r") of L when length(L) > 0 -> case length(L) rem 2 of 0 -> @@ -4020,12 +4035,12 @@ utf8_2_ucs([A|Rest]) when A < 16#80 -> utf8_2_ucs([A|Rest]) -> {{error,{bad_character,A}},Rest}. -to_char_set("iso-10646-utf-1",Ch) -> - [Ch]; -to_char_set(UTF8,Ch) when UTF8 =:= "utf-8"; UTF8 =:= undefined -> - ucs_2_utf8(Ch); -to_char_set(_,Ch) -> - [Ch]. +%% to_char_set("iso-10646-utf-1",Ch) -> +%% [Ch]; +%% to_char_set(UTF8,Ch) when UTF8 =:= "utf-8"; UTF8 =:= undefined -> +%% ucs_2_utf8(Ch); +%% to_char_set(_,Ch) -> +%% [Ch]. ucs_2_utf8(Ch) when Ch < 128 -> %% 0vvvvvvv diff --git a/lib/xmerl/src/xmerl_ucs.erl b/lib/xmerl/src/xmerl_ucs.erl index 7c45c838ab..6550a9d954 100644 --- a/lib/xmerl/src/xmerl_ucs.erl +++ b/lib/xmerl/src/xmerl_ucs.erl @@ -1,19 +1,19 @@ %% %% %CopyrightBegin% -%% -%% Copyright Ericsson AB 2005-2009. All Rights Reserved. -%% +%% +%% Copyright Ericsson AB 2005-2011. 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% %% @@ -43,6 +43,7 @@ -export([to_utf16be/1, from_utf16be/1, from_utf16be/2]). -export([to_utf16le/1, from_utf16le/1, from_utf16le/2]). -export([to_utf8/1, from_utf8/1]). +-export([from_latin9/1]). %%% NB: Non-canonical UTF-8 encodings and incorrectly used %%% surrogate-pair codes are disallowed by this code. There are @@ -177,13 +178,27 @@ to_utf8(List) when is_list(List) -> lists:flatmap(fun to_utf8/1, List); to_utf8(Ch) -> char_to_utf8(Ch). from_utf8(Bin) when is_binary(Bin) -> from_utf8(binary_to_list(Bin)); -from_utf8(List) -> +from_utf8(List) -> case expand_utf8(List) of {Result,0} -> Result; {_Res,_NumBadChar} -> exit({ucs,{bad_utf8_character_code}}) end. +%%% Latin9 support +from_latin9(Bin) when is_binary(Bin) -> from_latin9(binary_to_list(Bin)); +from_latin9(List) -> + [ latin9_to_ucs4(Char) || Char <- List]. + +latin9_to_ucs4(16#A4) -> 16#20AC; +latin9_to_ucs4(16#A6) -> 16#160; +latin9_to_ucs4(16#A8) -> 16#161; +latin9_to_ucs4(16#B4) -> 16#17D; +latin9_to_ucs4(16#B8) -> 16#17E; +latin9_to_ucs4(16#BC) -> 16#152; +latin9_to_ucs4(16#BD) -> 16#153; +latin9_to_ucs4(16#BE) -> 16#178; +latin9_to_ucs4(Other) -> Other. @@ -238,7 +253,7 @@ from_ucs4le(Bin,Acc,Tail) -> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% UCS-2 support -%%% FIXME! Don't know how to encode UCS-2!! +%%% FIXME! Don't know how to encode UCS-2!! %%% Currently I just encode as UCS-4, but strips the 16 higher bits. char_to_ucs2be(Ch) -> true = is_iso10646(Ch), @@ -259,15 +274,15 @@ from_ucs2be(Bin,Acc,Tail) -> char_to_ucs2le(Ch) -> true = is_iso10646(Ch), - [(Ch bsr 16) band 16#FF, - (Ch bsr 24)]. + [Ch band 16#FF, + (Ch bsr 8) band 16#FF]. from_ucs2le(<<Ch:16/little-signed-integer, Rest/binary>>,Acc,Tail) -> if Ch < 0; Ch >= 16#D800, Ch < 16#E000; Ch =:= 16#FFFE; Ch =:= 16#FFFF -> exit({bad_character_code,Ch}); true -> - from_ucs4le(Rest,[Ch|Acc],Tail) + from_ucs2le(Rest,[Ch|Acc],Tail) end; from_ucs2le(<<>>,Acc,Tail) -> lists:reverse(Acc,Tail); @@ -476,6 +491,8 @@ to_unicode(Input,Cs) when Cs=='iso_8859-1:1987';Cs=='iso-ir-100'; Cs=='l1';Cs=='ibm819'; Cs=='cp819';Cs=='csisolatin1' -> Input; +to_unicode(Input,Cs) when Cs=='iso_8859-15';Cs=='iso-8859-15';Cs=='latin9' -> + from_latin9(Input); % to_unicode(Input,Cs) when Cs=='mnemonic';Cs=='"mnemonic+ascii+38'; % Cs=='mnem';Cs=='"mnemonic+ascii+8200' -> % from_mnemonic(Input); diff --git a/lib/xmerl/src/xmerl_uri.erl b/lib/xmerl/src/xmerl_uri.erl index d8edb2e6e1..a0c6f1c2a7 100644 --- a/lib/xmerl/src/xmerl_uri.erl +++ b/lib/xmerl/src/xmerl_uri.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2005-2009. All Rights Reserved. +%% Copyright Ericsson AB 2005-2011. 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 @@ -359,9 +359,9 @@ scan_host(C0) -> %% Hex4=<?HEX -> %% {C1,lists:reverse(lists:append(IPv6address))}; {C1,Hostname,[A|_HostF]} -> - {C1,lists:reverse(lists:append(Hostname))}; - _ -> - {error,no_host} + {C1,lists:reverse(lists:append(Hostname))} +%% _ -> +%% {error,no_host} end. scan_host2([H|C0],Acc,CurF,Host,HostF) when $0=<H,H=<$9 -> diff --git a/lib/xmerl/src/xmerl_xpath.erl b/lib/xmerl/src/xmerl_xpath.erl index 182a186d2c..db3d3ac2d6 100644 --- a/lib/xmerl/src/xmerl_xpath.erl +++ b/lib/xmerl/src/xmerl_xpath.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2003-2009. All Rights Reserved. +%% Copyright Ericsson AB 2003-2011. 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 @@ -19,8 +19,8 @@ %% Description : Implements a search engine based on XPath -%% @doc The xmerl_xpath module handles the entire XPath 1.0 spec -%% XPath expressions typically occurs in XML attributes and are used to addres +%% @doc The xmerl_xpath module handles the entire XPath 1.0 spec. +%% XPath expressions typically occur in XML attributes and are used to address %% parts of an XML document. % The grammar is defined in <code>xmerl_xpath_parse.yrl</code>. % The core functions are defined in <code>xmerl_xpath_pred.erl</code>. @@ -57,7 +57,9 @@ %% @type option_list(). <p>Options allows to customize the behaviour of the %% XPath scanner. %% </p> +%% <p> %% Possible options are: +%% </p> %% <dl> %% <dt><code>{namespace, #xmlNamespace}</code></dt> %% <dd>Set namespace nodes, from XmlNamspace, in xmlContext</dd> diff --git a/lib/xmerl/src/xmerl_xsd.erl b/lib/xmerl/src/xmerl_xsd.erl index 1aedc9e270..dfdc6138ef 100644 --- a/lib/xmerl/src/xmerl_xsd.erl +++ b/lib/xmerl/src/xmerl_xsd.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2006-2010. All Rights Reserved. +%% Copyright Ericsson AB 2006-2011. 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 @@ -29,7 +29,9 @@ %% @type option_list(). <p>Options allow to customize the behaviour of the %% validation. %% </p> +%% <p> %% Possible options are : +%% </p> %% <dl> %% <dt><code>{tab2file,boolean()}</code></dt> %% <dd>Enables saving of abstract structure on file for debugging @@ -46,6 +48,7 @@ %% <dd>It is possible by this option to provide a state with process %% information from an earlier validation.</dd> %% </dl> +%% @end %%%------------------------------------------------------------------- -module(xmerl_xsd). @@ -284,10 +287,19 @@ process_schema(Schema) -> %% error reason. The error reason may be a list of several errors %% or a single error encountered during the processing. process_schema(Schema,Options) when is_list(Options) -> - S = initiate_state(Options,Schema), - process_schema2(xmerl_scan:file(filename:join(S#xsd_state.xsd_base, Schema)),S,Schema); -process_schema(Schema,State) when is_record(State,xsd_state) -> - process_schema2(xmerl_scan:file(filename:join(State#xsd_state.xsd_base, Schema)),State,Schema). + State = initiate_state(Options,Schema), + process_schema(Schema, State); +process_schema(Schema, State=#xsd_state{fetch_fun=Fetch})-> + case Fetch(Schema, State) of + {ok,{file,File},_} -> + process_schema2(xmerl_scan:file(File), State, Schema); + {ok,{string,Str},_} -> + process_schema2(xmerl_scan:string(Str), State, Schema); + {ok,[],_} -> + {error,enoent}; + Err -> + Err + end. process_schema2(Err={error,_},_,_) -> Err; @@ -316,12 +328,9 @@ process_schemas(Schemas) -> %% error reason. The error reason may be a list of several errors %% or a single error encountered during the processing. process_schemas(Schemas=[{_,Schema}|_],Options) when is_list(Options) -> - process_schemas(Schemas,initiate_state(Options,Schema)); + State = initiate_state(Options,Schema), + process_schemas(Schemas, State); process_schemas([{_NS,Schema}|Rest],State=#xsd_state{fetch_fun=Fetch}) -> -%% case process_external_schema_once(Schema,if_list_to_atom(NS),State) of -%% S when is_record(S,xsd_state) -> -%% case process_schema(filename:join([State#xsd_state.xsd_base,Schema]),State) of -%% {ok,S} -> Res= case Fetch(Schema,State) of {ok,{file,File},_} -> @@ -342,20 +351,20 @@ process_schemas([{_NS,Schema}|Rest],State=#xsd_state{fetch_fun=Fetch}) -> process_schemas([],S) when is_record(S,xsd_state) -> {ok,S}. - initiate_state(Opts,Schema) -> XSDBase = filename:dirname(Schema), {{state,S},RestOpts}=new_state(Opts), S2 = create_tables(S), - initiate_state2(S2#xsd_state{schema_name = Schema, - xsd_base = XSDBase, - fetch_fun = fun fetch/2},RestOpts). + initiate_state2(S2#xsd_state{schema_name = Schema, xsd_base=XSDBase, + fetch_fun = fun fetch/2}, + RestOpts). + initiate_state2(S,[]) -> S; initiate_state2(S,[{tab2file,Bool}|T]) -> initiate_state2(S#xsd_state{tab2file=Bool},T); -initiate_state2(S,[{xsdbase,XSDBase}|T]) -> - initiate_state2(S#xsd_state{xsd_base=XSDBase},T); +initiate_state2(S,[{xsdbase, XSDBase}|T]) -> + initiate_state2(S#xsd_state{xsd_base=XSDBase, external_xsd_base=true},T); initiate_state2(S,[{fetch_fun,FetchFun}|T]) -> initiate_state2(S#xsd_state{fetch_fun=FetchFun},T); initiate_state2(S,[{fetch_path,FetchPath}|T]) -> @@ -733,7 +742,7 @@ element_content({IDC,S},El,Env) {{IDC,IDConstr},S3}; Err -> S3 = acc_errs(S2,{error_path(El,El#xmlElement.name),?MODULE, - {erronous_content_in_identity_constraint,IDC,Err}}), + {erroneous_content_in_identity_constraint,IDC,Err}}), {{IDC,[]},S3} end; element_content({selector,S},Sel,_Env) -> @@ -2417,8 +2426,8 @@ validate_xml(XMLEl=#xmlElement{},SEl=#schema_element{},S) -> %% 2 often check_element_type(XML=[XMLTxt=#xmlText{}|Rest],CM=[CMEl|CMRest],Env, Block,S,Checked) -> - %% XMLTxt ��r det f��rsta av content i element, - %% CMEl ��r den till��tna typen enligt schemat + %% XMLTxt is the first part of the elements content, + %% CMEl is the allowed type according to the schema case is_whitespace(XMLTxt) of true -> %% Ignore XMLEl check_element_type(Rest,CM,Env,Block,S,[XMLTxt|Checked]); @@ -2450,7 +2459,7 @@ check_element_type(XML=[#xmlElement{}|_],[{choice,{CM,Occ}}|_CMRest], check_element_type(XML=[#xmlElement{}|_],[{all,{CM,Occ}}|_CMRest], Env,_Block,S,Checked) -> ?debug("calling choice/6~n",[]), - check_all(XML,CM,Occ,Env,S,Checked,XML); + check_all(XML,CM,Occ,Env,set_num_el(S,0),Checked,XML); %%LTH %% 3 often. CMEL may be ((simpleType | complexType)?, (unique | key | keyref)*)) check_element_type(XML=[XMLEl=#xmlElement{}|_],[CMEl|CMRest],Env, Block,S,Checked) -> @@ -2918,7 +2927,7 @@ schemaLocations(El=#xmlElement{attributes=Atts},S) -> [] -> S; [#xmlAttribute{value=Paths}|_] -> - case string:tokens(Paths," ") of + case string:tokens(Paths," \n\t\r") of L when length(L) > 0 -> case length(L) rem 2 of 0 -> @@ -3390,8 +3399,12 @@ qualified_node_set(Paths,[QN|QNs],El,S,Acc) -> end end, {KeySequence,S2} = mapfoldl(Fun,S,Paths), - qualified_node_set(Paths,QNs,El,S2,[flatten(KeySequence)|Acc]). - + case flatten(KeySequence) of + [] -> + qualified_node_set(Paths,QNs,El,S2,Acc); + KS -> + qualified_node_set(Paths,QNs,El,S2,[KS|Acc]) + end. apply_field(F,El,S) -> %% xmerl_xpath:string returns a list @@ -5225,7 +5238,12 @@ fetch(URI,S) -> [] -> %% empty systemliteral []; _ -> - filename:join(S#xsd_state.xsd_base, URI) + case S#xsd_state.external_xsd_base of + true -> + filename:join(S#xsd_state.xsd_base, URI); + false -> + filename:join(S#xsd_state.xsd_base, filename:basename(URI)) + end end, Path = path_locate(S#xsd_state.fetch_path, Filename, Fullname), ?dbg("fetch(~p) -> {file, ~p}.~n", [URI, Path]), @@ -5553,7 +5571,7 @@ format_error({incomplete_file,_FileName,_Other}) -> "Schema: The file containing a schema state must be produced by xmerl_xsd:state2file/[1,2]."; format_error({unexpected_content_in_any,A}) -> io_lib:format("Schema: The any type is considered to have no content besides annotation. ~p was found.",[A]); -format_error({erronous_content_in_identity_constraint,IDC,Err}) -> +format_error({erroneous_content_in_identity_constraint,IDC,Err}) -> io_lib:format("Schema: An ~p identity constraint must have one selector and one or more field in content. This case ~p",[IDC,Err]); format_error({missing_xpath_attribute,IDCContent}) -> io_lib:format("Schema: A ~p in a identity constraint must have a xpath attribute.",[IDCContent]); diff --git a/lib/xmerl/src/xmerl_xsd_type.erl b/lib/xmerl/src/xmerl_xsd_type.erl index 19951f030f..0f46b1f9aa 100644 --- a/lib/xmerl/src/xmerl_xsd_type.erl +++ b/lib/xmerl/src/xmerl_xsd_type.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2006-2009. All Rights Reserved. +%% Copyright Ericsson AB 2006-2011. 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 @@ -612,7 +612,7 @@ check_NMTOKEN2([H|T]) -> check_NMTOKEN2(T). check_NMTOKENS(Value) -> - TokList = string:tokens(Value," "), + TokList = string:tokens(Value," \n\t\r"), lists:foreach(fun check_NMTOKEN/1,TokList), {ok,Value}. @@ -645,7 +645,7 @@ check_ENTITIES(Value) -> check_list_type(Value,fun check_ENTITY/1). check_list_type(Value,BaseTypeFun) -> - Tokens = string:tokens(Value," "), + Tokens = string:tokens(Value," \n\t\r"), lists:foreach(BaseTypeFun,Tokens), {ok,Value}. |