From 6444fd39fe22239e8c23c008158704b06f0e40e9 Mon Sep 17 00:00:00 2001
From: Lars Thorsen <lars@erlang.org>
Date: Mon, 31 Oct 2011 15:58:12 +0100
Subject: Fix character check of non-characters due to change in unicode module
---
lib/xmerl/src/xmerl_sax_parser_base.erlsrc | 38 +++++++++++++++++++-----------
1 file changed, 24 insertions(+), 14 deletions(-)
(limited to 'lib')
diff --git a/lib/xmerl/src/xmerl_sax_parser_base.erlsrc b/lib/xmerl/src/xmerl_sax_parser_base.erlsrc
index 3b9eaa309c..ec9178ea25 100644
--- a/lib/xmerl/src/xmerl_sax_parser_base.erlsrc
+++ b/lib/xmerl/src/xmerl_sax_parser_base.erlsrc
@@ -944,14 +944,19 @@ parse_att_value(?STRING_REST("&", Rest), State, Stop, Acc) ->
{unparsed, Name, _} ->
?fatal_error(State1, "Unparsed entity reference in attribute value: " ++ Name)
end;
-parse_att_value(?STRING_UNBOUND_REST(Stop, Rest), State, Stop, Acc) ->
+parse_att_value(?STRING_UNBOUND_REST(Stop, Rest), State, Stop, Acc) ->
{lists:reverse(Acc), Rest, State};
-parse_att_value(?STRING_UNBOUND_REST($<, _Rest), State, _Stop, _Acc) ->
+parse_att_value(?STRING_UNBOUND_REST($<, _Rest), State, _Stop, _Acc) ->
?fatal_error(State, "< not allowed in attribute value");
-parse_att_value(?STRING_UNBOUND_REST(C, Rest), State, Stop, Acc) ->
- parse_att_value(Rest, State, Stop, [C|Acc]);
-parse_att_value(Bytes, State, Stop, Acc) ->
- unicode_incomplete_check([Bytes, State, Stop, Acc, fun parse_att_value/4],
+parse_att_value(?STRING_UNBOUND_REST(C, Rest), State, Stop, Acc) ->
+ if
+ ?is_char(C) ->
+ parse_att_value(Rest, State, Stop, [C|Acc]);
+ true ->
+ ?fatal_error(State, lists:flatten(io_lib:format("Bad character in attribute value: ~p", [C])))
+ end;
+parse_att_value(Bytes, State, Stop, Acc) ->
+ unicode_incomplete_check([Bytes, State, Stop, Acc, fun parse_att_value/4],
undefined).
@@ -1120,10 +1125,10 @@ parse_content(?STRING_UNBOUND_REST(C, Rest), State, Acc, _IgnorableWS) ->
?is_char(C) ->
parse_content(Rest, State, [C|Acc], false);
true ->
- ?fatal_error(State, "Bad character in content: " ++ C)
- end;
-parse_content(Bytes, State, Acc, IgnorableWS) ->
- unicode_incomplete_check([Bytes, State, Acc, IgnorableWS, fun parse_content/4],
+ ?fatal_error(State, lists:flatten(io_lib:format("Bad character in content: ~p", [C])))
+ end;
+parse_content(Bytes, State, Acc, IgnorableWS) ->
+ unicode_incomplete_check([Bytes, State, Acc, IgnorableWS, fun parse_content/4],
undefined).
@@ -2522,11 +2527,16 @@ parse_entity_value(?STRING_REST("%", Rest), #xmerl_sax_parser_state{file_type=Ty
end
end;
-parse_entity_value(?STRING_UNBOUND_REST(Stop, Rest), State, Stop, Acc) ->
+parse_entity_value(?STRING_UNBOUND_REST(Stop, Rest), State, Stop, Acc) ->
{lists:reverse(Acc), Rest, State};
-parse_entity_value(?STRING_UNBOUND_REST(C, Rest), State, Stop, Acc) ->
- parse_entity_value(Rest, State, Stop, [C|Acc]);
-parse_entity_value(Bytes, State, Stop, Acc) ->
+parse_entity_value(?STRING_UNBOUND_REST(C, Rest), State, Stop, Acc) ->
+ if
+ ?is_char(C) ->
+ parse_entity_value(Rest, State, Stop, [C|Acc]);
+ true ->
+ ?fatal_error(State, lists:flatten(io_lib:format("Bad character in entity value: ~p", [C])))
+ end;
+parse_entity_value(Bytes, State, Stop, Acc) ->
unicode_incomplete_check([Bytes, State, Stop, Acc, fun parse_entity_value/4],
undefined).
--
cgit v1.2.3