This adds the strtoutf8 function that truncate a string before the
first non UTF-8 character.
This truncation is done in place.
---
src/shared/util.c | 42 ++++++++++++++++++++++++++++++++++++++++++
src/shared/util.h | 1 +
2 files changed, 43 insertions(+)
diff --git a/src/shared/util.c b/src/shared/util.c
index 5d3a14d96..5262458cb 100644
--- a/src/shared/util.c
+++ b/src/shared/util.c
@@ -1959,3 +1959,45 @@ bool argsisutf8(int argc, char *argv[])
return true;
}
+
+char *strtoutf8(char *str, size_t len)
+{
+ size_t i = 0;
+
+ while (i < len) {
+ unsigned char c = str[i];
+ size_t size = 0;
+
+ /* Check the first byte to determine the number of bytes in the
+ * UTF-8 character.
+ */
+ if ((c & 0x80) == 0x00)
+ size = 1;
+ else if ((c & 0xE0) == 0xC0)
+ size = 2;
+ else if ((c & 0xF0) == 0xE0)
+ size = 3;
+ else if ((c & 0xF8) == 0xF0)
+ size = 4;
+ else
+ /* Invalid UTF-8 sequence */
+ goto done;
+
+ /* Check the following bytes to ensure they have the correct
+ * format.
+ */
+ for (size_t j = 1; j < size; ++j) {
+ if (i + j > len || (str[i + j] & 0xC0) != 0x80)
+ /* Invalid UTF-8 sequence */
+ goto done;
+ }
+
+ /* Move to the next character */
+ i += size;
+ }
+
+done:
+ /* Truncate to the longest valid UTF-8 string */
+ memset(str + i, 0, len - i);
+ return str;
+}
diff --git a/src/shared/util.h b/src/shared/util.h
index dd357fb93..6fc02a9dc 100644
--- a/src/shared/util.h
+++ b/src/shared/util.h
@@ -92,6 +92,7 @@ int strsuffix(const char *str, const char *suffix);
char *strstrip(char *str);
bool strisutf8(const char *str, size_t length);
bool argsisutf8(int argc, char *argv[]);
+char *strtoutf8(char *str, size_t len);
void *util_malloc(size_t size);
void *util_memdup(const void *src, size_t size);
--
2.43.0
