docstring sgml::cleanID(Buffer const & buf, OutputParams const & runparams,
docstring const & orig)
{
// The standard DocBook SGML declaration only allows letters,
// digits, '-' and '.' in a name.
// Since users might change that declaration one has to cater
// for additional allowed characters.
// This routine replaces illegal characters by '-' or '.'
// and adds a number for uniqueness.
// If you know what you are doing, you can set allowed==""
// to disable this mangling.
DocumentClass const & tclass = buf.params().documentClass();
docstring const allowed = from_ascii(
runparams.flavor == OutputParams::XML ? ".-_:" : tclass.options());
if (allowed.empty())
return orig;
docstring::const_iterator it = orig.begin();
docstring::const_iterator end = orig.end();
docstring content;
// FIXME THREAD
typedef map<docstring, docstring> MangledMap;
static MangledMap mangledNames;
static int mangleID = 1;
MangledMap::const_iterator const known = mangledNames.find(orig);
if (known != mangledNames.end())
return known->second;
// make sure it starts with a letter
if (!isAlphaASCII(*it) && allowed.find(*it) >= allowed.size())
content += "x";
bool mangle = false;
for (; it != end; ++it) {
char_type c = *it;
if (isAlphaASCII(c) || isDigitASCII(c) || c == '-' || c == '.'
|| allowed.find(c) < allowed.size())
content += c;
else if (c == '_' || c == ' ') {
mangle = true;
content += "-";
}
else if (c == ':' || c == ',' || c == ';' || c == '!') {
mangle = true;
content += ".";
}
else {
mangle = true;
}
}
if (mangle)
content += "-" + convert<docstring>(mangleID++);
else if (isDigitASCII(content[content.size() - 1]))
content += ".";
mangledNames[orig] = content;
return content;
}
bool Token::isAlnumASCII() const
{
return cat_ == catLetter ||
(cat_ == catOther && cs_.length() == 1 && isDigitASCII(cs_[0]));
}
