diff options
Diffstat (limited to 'src/mir_core')
| -rw-r--r-- | src/mir_core/mir_core.def | 1 | ||||
| -rw-r--r-- | src/mir_core/utf.cpp | 45 |
2 files changed, 46 insertions, 0 deletions
diff --git a/src/mir_core/mir_core.def b/src/mir_core/mir_core.def index 41585d0845..66324ec1ed 100644 --- a/src/mir_core/mir_core.def +++ b/src/mir_core/mir_core.def @@ -129,3 +129,4 @@ replaceStrW @126 db_setCurrent @127
CmdLine_GetOption @128
CmdLine_Parse @129
+Utf8CheckString @130
diff --git a/src/mir_core/utf.cpp b/src/mir_core/utf.cpp index ddf2d1ca9f..a9e7145973 100644 --- a/src/mir_core/utf.cpp +++ b/src/mir_core/utf.cpp @@ -404,3 +404,48 @@ MIR_CORE_DLL(char*) Utf8EncodeW(const wchar_t* src) return result;
}
+
+/////////////////////////////////////////////////////////////////////////////////////////
+// Utf8Encode - converts UCS2 string to the UTF8-encoded format
+
+MIR_CORE_DLL(BOOL) Utf8CheckString(const char* str)
+{
+ int expect_bytes = 0, utf_found = 0;
+
+ if (!str) return 0;
+
+ while (*str) {
+ if ((*str & 0x80) == 0) {
+ /* Looks like an ASCII character */
+ if (expect_bytes)
+ /* byte of UTF-8 character expected */
+ return 0;
+ }
+ else {
+ /* Looks like byte of an UTF-8 character */
+ if (expect_bytes) {
+ /* expect_bytes already set: first byte of UTF-8 char already seen */
+ if ((*str & 0xC0) != 0x80) {
+ /* again first byte ?!?! */
+ return 0;
+ }
+ }
+ else {
+ /* First byte of the UTF-8 character */
+ /* count initial one bits and set expect_bytes to 1 less */
+ char ch = *str;
+ while (ch & 0x80) {
+ expect_bytes++;
+ ch = (ch & 0x7f) << 1;
+ }
+ }
+ /* OK, next byte of UTF-8 character */
+ /* Decrement number of expected bytes */
+ if (--expect_bytes == 0)
+ utf_found = 1;
+ }
+ str++;
+ }
+
+ return (utf_found && expect_bytes == 0);
+}
|