diff options
Diffstat (limited to 'src/utils/encoding.hpp')
| -rw-r--r-- | src/utils/encoding.hpp | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/src/utils/encoding.hpp b/src/utils/encoding.hpp index 362f1df..a3bccfc 100644 --- a/src/utils/encoding.hpp +++ b/src/utils/encoding.hpp @@ -12,6 +12,14 @@ namespace utils */ bool is_valid_utf8(const char* s); /** + * Remove all invalid codepoints from the given utf-8-encoded string. + * The value returned is a copy of the string, without the removed chars. + * + * See http://www.w3.org/TR/xml/#charsets for the list of valid characters + * in XML. + */ + std::string remove_invalid_xml_chars(const std::string& original); + /** * Convert the given string (encoded is "encoding") into valid utf-8. * If some decoding fails, insert an utf-8 placeholder character instead. */ |