summaryrefslogtreecommitdiff
path: root/app/wlib/mswlib/utf8conv.c
diff options
context:
space:
mode:
Diffstat (limited to 'app/wlib/mswlib/utf8conv.c')
-rw-r--r--app/wlib/mswlib/utf8conv.c277
1 files changed, 138 insertions, 139 deletions
diff --git a/app/wlib/mswlib/utf8conv.c b/app/wlib/mswlib/utf8conv.c
index 62ada76..2363df9 100644
--- a/app/wlib/mswlib/utf8conv.c
+++ b/app/wlib/mswlib/utf8conv.c
@@ -19,10 +19,9 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
-#include <malloc.h>
#include <stdbool.h>
#include <string.h>
@@ -43,29 +42,29 @@
bool
wSystemToUTF8(const char *inString, char *outString, unsigned outStringLength)
{
- unsigned int cnt = 2 * (strlen(inString) + 1);
- char *tempBuffer = malloc(cnt);
-
- // convert to wide character (UTF16)
- MultiByteToWideChar(CP_ACP,
- 0,
- inString,
- -1,
- (LPWSTR)tempBuffer,
- cnt);
-
- // convert from wide char to UTF-8
- WideCharToMultiByte(CP_UTF8,
- 0,
- (LPCWCH)tempBuffer,
- -1,
- (LPSTR)outString,
- outStringLength,
- NULL,
- NULL);
-
- free(tempBuffer);
- return true;
+ unsigned int cnt = 2 * (unsigned int)(strlen(inString) + 1);
+ char *tempBuffer = malloc(cnt);
+
+ // convert to wide character (UTF16)
+ MultiByteToWideChar(CP_ACP,
+ 0,
+ inString,
+ -1,
+ (LPWSTR)tempBuffer,
+ cnt);
+
+ // convert from wide char to UTF-8
+ WideCharToMultiByte(CP_UTF8,
+ 0,
+ (LPCWCH)tempBuffer,
+ -1,
+ (LPSTR)outString,
+ outStringLength,
+ NULL,
+ NULL);
+
+ free(tempBuffer);
+ return true;
}
/**
@@ -81,43 +80,43 @@ wSystemToUTF8(const char *inString, char *outString, unsigned outStringLength)
bool
wUTF8ToSystem(const char *inString, char *outString, unsigned outStringLength)
{
- unsigned int cnt = 2 * (strlen(inString) + 1);
- char *tempBuffer = malloc(cnt);
-
- // convert to wide character (UTF16)
- MultiByteToWideChar(CP_UTF8,
- 0,
- inString,
- -1,
- (LPWSTR)tempBuffer,
- cnt);
-
-
- cnt = WideCharToMultiByte(CP_ACP,
- 0,
- (LPCWCH)tempBuffer,
- -1,
- (LPSTR)outString,
- 0L,
- NULL,
- NULL);
-
- if (outStringLength <= cnt) {
- return (false);
- }
-
- // convert from wide char to system codepage
- WideCharToMultiByte(CP_ACP,
- 0,
- (LPCWCH)tempBuffer,
- -1,
- (LPSTR)outString,
- outStringLength,
- NULL,
- NULL);
-
- free(tempBuffer);
- return true;
+ unsigned int cnt = 2 * (int)(strlen(inString) + 1);
+ char *tempBuffer = malloc(cnt);
+
+ // convert to wide character (UTF16)
+ MultiByteToWideChar(CP_UTF8,
+ 0,
+ inString,
+ -1,
+ (LPWSTR)tempBuffer,
+ cnt);
+
+
+ cnt = WideCharToMultiByte(CP_ACP,
+ 0,
+ (LPCWCH)tempBuffer,
+ -1,
+ (LPSTR)outString,
+ 0L,
+ NULL,
+ NULL);
+
+ if (outStringLength <= cnt) {
+ return (false);
+ }
+
+ // convert from wide char to system codepage
+ WideCharToMultiByte(CP_ACP,
+ 0,
+ (LPCWCH)tempBuffer,
+ -1,
+ (LPSTR)outString,
+ outStringLength,
+ NULL,
+ NULL);
+
+ free(tempBuffer);
+ return true;
}
/**
@@ -131,80 +130,80 @@ wUTF8ToSystem(const char *inString, char *outString, unsigned outStringLength)
bool wIsUTF8(const char * string)
{
- if (!string) {
- return 0;
- }
-
- const unsigned char * bytes = (const unsigned char *)string;
- while (*bytes) {
- if ((// ASCII
- // use bytes[0] <= 0x7F to allow ASCII control characters
- bytes[0] == 0x09 ||
- bytes[0] == 0x0A ||
- bytes[0] == 0x0D ||
- (0x20 <= bytes[0] && bytes[0] <= 0x7E)
- )
- ) {
- bytes += 1;
- continue;
- }
-
- if ((// non-overlong 2-byte
- (0xC2 <= bytes[0] && bytes[0] <= 0xDF) &&
- (0x80 <= bytes[1] && bytes[1] <= 0xBF)
- )
- ) {
- bytes += 2;
- continue;
- }
-
- if ((// excluding overlongs
- bytes[0] == 0xE0 &&
- (0xA0 <= bytes[1] && bytes[1] <= 0xBF) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF)
- ) ||
- (// straight 3-byte
- ((0xE1 <= bytes[0] && bytes[0] <= 0xEC) ||
- bytes[0] == 0xEE ||
- bytes[0] == 0xEF) &&
- (0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF)
- ) ||
- (// excluding surrogates
- bytes[0] == 0xED &&
- (0x80 <= bytes[1] && bytes[1] <= 0x9F) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF)
- )
- ) {
- bytes += 3;
- continue;
- }
-
- if ((// planes 1-3
- bytes[0] == 0xF0 &&
- (0x90 <= bytes[1] && bytes[1] <= 0xBF) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
- (0x80 <= bytes[3] && bytes[3] <= 0xBF)
- ) ||
- (// planes 4-15
- (0xF1 <= bytes[0] && bytes[0] <= 0xF3) &&
- (0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
- (0x80 <= bytes[3] && bytes[3] <= 0xBF)
- ) ||
- (// plane 16
- bytes[0] == 0xF4 &&
- (0x80 <= bytes[1] && bytes[1] <= 0x8F) &&
- (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
- (0x80 <= bytes[3] && bytes[3] <= 0xBF)
- )
- ) {
- bytes += 4;
- continue;
- }
-
- return false;
- }
-
- return true;
-} \ No newline at end of file
+ if (!string) {
+ return 0;
+ }
+
+ const unsigned char * bytes = (const unsigned char *)string;
+ while (*bytes) {
+ if ((// ASCII
+ // use bytes[0] <= 0x7F to allow ASCII control characters
+ bytes[0] == 0x09 ||
+ bytes[0] == 0x0A ||
+ bytes[0] == 0x0D ||
+ (0x20 <= bytes[0] && bytes[0] <= 0x7E)
+ )
+ ) {
+ bytes += 1;
+ continue;
+ }
+
+ if ((// non-overlong 2-byte
+ (0xC2 <= bytes[0] && bytes[0] <= 0xDF) &&
+ (0x80 <= bytes[1] && bytes[1] <= 0xBF)
+ )
+ ) {
+ bytes += 2;
+ continue;
+ }
+
+ if ((// excluding overlongs
+ bytes[0] == 0xE0 &&
+ (0xA0 <= bytes[1] && bytes[1] <= 0xBF) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF)
+ ) ||
+ (// straight 3-byte
+ ((0xE1 <= bytes[0] && bytes[0] <= 0xEC) ||
+ bytes[0] == 0xEE ||
+ bytes[0] == 0xEF) &&
+ (0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF)
+ ) ||
+ (// excluding surrogates
+ bytes[0] == 0xED &&
+ (0x80 <= bytes[1] && bytes[1] <= 0x9F) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF)
+ )
+ ) {
+ bytes += 3;
+ continue;
+ }
+
+ if ((// planes 1-3
+ bytes[0] == 0xF0 &&
+ (0x90 <= bytes[1] && bytes[1] <= 0xBF) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
+ (0x80 <= bytes[3] && bytes[3] <= 0xBF)
+ ) ||
+ (// planes 4-15
+ (0xF1 <= bytes[0] && bytes[0] <= 0xF3) &&
+ (0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
+ (0x80 <= bytes[3] && bytes[3] <= 0xBF)
+ ) ||
+ (// plane 16
+ bytes[0] == 0xF4 &&
+ (0x80 <= bytes[1] && bytes[1] <= 0x8F) &&
+ (0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
+ (0x80 <= bytes[3] && bytes[3] <= 0xBF)
+ )
+ ) {
+ bytes += 4;
+ continue;
+ }
+
+ return false;
+ }
+
+ return true;
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-15 15:26:07 +0000