Singularity-Viewer/SingularityViewer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix xml parser.

Browse Source 
This fixes quoted strings, like <tag>"Hello \"World\""</tag>,
which otherwise might not be processed correctly because
the XML_CharacterDataHandler isn't guaranteed to be called
exactly once per element. It certainly isn't when a string
contains entities, ie: <tag>"&apos;Hello \"World\"&apos;"</tag>
certainly fails to be unescaped with the old code.
Moreover, the old unescape code things that a singly quote
is actually a quoted string (not noting that begin and end
quote are the same) and destructs all &quot; entities; also
fixed with this commit.
This commit is contained in:
Aleric Inglewood
2013-11-05 02:12:04 +01:00
parent 78673e4a94
commit d549e549d8
1 changed files with 40 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
indra/llxml/llxmlnode.cpp
View File

@@ -555,6 +555,36 @@ void XMLCALL EndXMLNode(void *userData,
node->setValue(value);
}
}
// Singu note: moved here from XMLData.
if (LLXMLNode::sStripEscapedStrings)
{
std::string value = node->getValue();
int len = value.length();
if (len > 1 && value[0] == '"' && value[len - 1] == '"')
{
// Special-case: Escaped string.
std::string unescaped_string;
for (S32 pos = 1; pos < len - 1; ++pos)
{
if (value[pos] == '\\' && value[pos + 1] == '\\')
{
unescaped_string += '\\';
++pos;
}
else if (value[pos] == '\\' && value[pos + 1] == '"')
{
unescaped_string += '"';
++pos;
}
else
{
unescaped_string += value[pos];
}
}
value += unescaped_string;
node->setValue(value);
}
}
}
void XMLCALL XMLData(void *userData,
@@ -563,6 +593,15 @@ void XMLCALL XMLData(void *userData,
{
LLXMLNode* current_node = (LLXMLNode *)userData;
std::string value = current_node->getValue();
#if 0
// Apparently also Lindens who write XML parsers can't read documentation.
// "A single block of contiguous text free of markup may still result in a sequence
// of calls to this handler. In other words, if you're searching for a pattern in
// the text, it may be split across calls to this handler."
// (http://sepp.oetiker.ch/expat-1.95.6-rs.SEPP/expat-1.95.6/doc/reference.html#XML_SetCharacterDataHandler)
//
// In other words, this is not guaranteed to work at all -- Aleric.
if (LLXMLNode::sStripEscapedStrings)
{
if (s[0] == '\"' && s[len-1] == '\"')
@@ -591,6 +630,7 @@ void XMLCALL XMLData(void *userData,
return;
}
}
#endif
value.append(std::string(s, len));
current_node->setValue(value);
}