lib: unichar: Add uni_utf8_data_truncate().

Returns the size of the data when truncated to be less than or equal to
a specified size, making sure UTF-8 character boundaries are respected.

diff --git a/src/lib/unichar.c b/src/lib/unichar.c
index 0b6756afd685ee58bd1d29d6d4ce653c9e0b7491..29489a20142405b94c72de545f4b09bf612691be 100644 (file)
--- a/src/lib/unichar.c
+++ b/src/lib/unichar.c
@@ -428,3 +428,20 @@ bool uni_utf8_data_is_valid(const unsigned char *data, size_t size)
 
        return uni_utf8_find_invalid_pos(data, size, &i) == 0;
 }
+
+size_t uni_utf8_data_truncate(const unsigned char *data, size_t old_size,
+                             size_t max_new_size)
+{
+       if (max_new_size >= old_size)
+               return old_size;
+       if (max_new_size == 0)
+               return 0;
+
+       if ((data[max_new_size] & 0x80) == 0)
+               return max_new_size;
+       while (max_new_size > 0 && (data[max_new_size-1] & 0xc0) == 0x80)
+               max_new_size--;
+       if (max_new_size > 0 && (data[max_new_size-1] & 0xc0) == 0xc0)
+               max_new_size--;
+       return max_new_size;
+}

diff --git a/src/lib/unichar.h b/src/lib/unichar.h
index bdeaeffa0de60777dfe383945f9b4ed8207285cc..08df8e56f315fe4c7f3847c825fffbd47d07be0b 100644 (file)
--- a/src/lib/unichar.h
+++ b/src/lib/unichar.h
@@ -114,6 +114,11 @@ bool uni_utf8_get_valid_data(const unsigned char *input, size_t size,
 bool uni_utf8_str_is_valid(const char *str);
 /* Returns TRUE if data contains only valid UTF-8 input. */
 bool uni_utf8_data_is_valid(const unsigned char *data, size_t size);
+/* Returns the size of the data when truncated to be less than or equal to
+   max_new_size, making sure UTF-8 character boundaries are respected. This only
+   looks at the last character at the new boundary. */
+size_t uni_utf8_data_truncate(const unsigned char *data, size_t old_size,
+                             size_t max_new_size);
 
 /* surrogate handling */
 static inline unichar_t uni_join_surrogate(unichar_t high, unichar_t low)