External/pugixml
8
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix interaction between parse_merge_pcdata and append_buffer

Browse Source 
strconcat in the parsing loop only works if we know the source string
comes from the same buffer that we're parsing. This is somewhat
cumbersome to establish during parsing and it requires extra tracking
data, so we just disable this combination as it's unlikely to be
actually useful - usually append_buffer would be called on a possibly
empty collection of elements, not on something with PCDATA.
This commit is contained in:
Arseny Kapoulkine 2023-08-25 19:29:35 -07:00
parent f31ad2c1ab
commit 6749789ec4
2 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/pugixml.cpp
View File

@ -6307,6 +6307,9 @@ namespace pugi
// append_buffer is only valid for elements/documents
if (!impl::allow_insert_child(type(), node_element)) return impl::make_parse_result(status_append_invalid_root);
// append buffer can not merge PCDATA into existing PCDATA nodes
if ((options & parse_merge_pcdata) != 0 && last_child().type() == node_pcdata) return impl::make_parse_result(status_append_invalid_root);
// get document node
impl::xml_document_struct* doc = &impl::get_document(_root);

16
tests/test_parse.cpp
View File

@ -1334,6 +1334,22 @@ TEST(parse_merge_pcdata_whitespace)
}
}
TEST(parse_merge_pcdata_append)
{
xml_document doc;
doc.append_child(STR("node")).append_child(node_pcdata);
xml_parse_result res = doc.child(STR("node")).append_buffer("hello <!--comment-->world", 25, parse_merge_pcdata | parse_fragment);
CHECK(res.status == status_append_invalid_root);
CHECK_STRING(doc.child(STR("node")).first_child().value(), STR(""));
doc.child(STR("node")).remove_children();
res = doc.child(STR("node")).append_buffer("hello <!--comment-->world", 25, parse_merge_pcdata | parse_fragment);
CHECK(res.status == status_ok);
CHECK_STRING(doc.child(STR("node")).first_child().value(), STR("hello world"));
}
TEST(parse_encoding_detect)
{
char test[] = "<?xml version='1.0' encoding='utf-8'?><n/>";