aboutsummaryrefslogtreecommitdiffstats
path: root/lib/xmerl
diff options
context:
space:
mode:
Diffstat (limited to 'lib/xmerl')
-rw-r--r--lib/xmerl/src/xmerl_scan.erl21
-rw-r--r--lib/xmerl/src/xmerl_ucs.erl35
-rw-r--r--lib/xmerl/src/xmerl_xsd.erl10
-rw-r--r--lib/xmerl/test/xmerl_SUITE.erl23
4 files changed, 65 insertions, 24 deletions
diff --git a/lib/xmerl/src/xmerl_scan.erl b/lib/xmerl/src/xmerl_scan.erl
index e598c5f56d..25c6547497 100644
--- a/lib/xmerl/src/xmerl_scan.erl
+++ b/lib/xmerl/src/xmerl_scan.erl
@@ -2074,10 +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
[] ->
@@ -3284,12 +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).
diff --git a/lib/xmerl/src/xmerl_ucs.erl b/lib/xmerl/src/xmerl_ucs.erl
index 7c45c838ab..feb16070a0 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.
-%%
+%%
%% 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_xsd.erl b/lib/xmerl/src/xmerl_xsd.erl
index f003cc74ba..dfdc6138ef 100644
--- a/lib/xmerl/src/xmerl_xsd.erl
+++ b/lib/xmerl/src/xmerl_xsd.erl
@@ -355,9 +355,9 @@ initiate_state(Opts,Schema) ->
XSDBase = filename:dirname(Schema),
{{state,S},RestOpts}=new_state(Opts),
S2 = create_tables(S),
- S3 = 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;
@@ -742,7 +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) ->
@@ -5571,7 +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/test/xmerl_SUITE.erl b/lib/xmerl/test/xmerl_SUITE.erl
index 0c809dbcb6..94c38d4d48 100644
--- a/lib/xmerl/test/xmerl_SUITE.erl
+++ b/lib/xmerl/test/xmerl_SUITE.erl
@@ -58,7 +58,7 @@ groups() ->
{ticket_tests, [],
[ticket_5998, ticket_7211, ticket_7214, ticket_7430,
ticket_6873, ticket_7496, ticket_8156, ticket_8697,
- ticket_9411]},
+ ticket_9411, ticket_9457]},
{app_test, [], [{xmerl_app_test, all}]},
{appup_test, [], [{xmerl_appup_test, all}]}].
@@ -588,7 +588,26 @@ ticket_9411(Config) ->
?line {E, _} = xmerl_scan:string(Xml),
?line {E, _} = xmerl_xsd:validate(E, Schema).
-
+ticket_9457(suite) -> [];
+ticket_9457(doc) ->
+ ["Test that xmerl_scan handles continuation correct when current input runs out at the end of an attribute value"];
+ticket_9457(Config) ->
+ Opts = [{continuation_fun, fun ticket_9457_cont/3, start}, {space, normalize}],
+ ?line {E, _} = xmerl_scan:string([], Opts).
+
+ticket_9457_cont(Continue, Exception, GlobalState) ->
+ case xmerl_scan:cont_state(GlobalState) of
+ start ->
+ G1 = xmerl_scan:cont_state(next, GlobalState),
+ Bytes = "<?xml version=\"1.0\" ?>\r\n<item a=\"b\"",
+ Continue(Bytes, G1);
+ next ->
+ G1 = xmerl_scan:cont_state(last, GlobalState),
+ Bytes = ">blah</item>\r\n",
+ Continue(Bytes, G1);
+ _ ->
+ Exception(GlobalState)
+ end.
%%======================================================================
%% Support Functions
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-01 13:41:59 +0000