[FFmpeg-devel] [PATCH] lavu/avstring: add av_get_utf8() function

[Stefano Sabatini]

TODO: minor bump, APIchanges entry
---
 libavutil/avstring.c | 25 +++++++++++++++++++++++++
 libavutil/avstring.h | 10 ++++++++++
 2 files changed, 35 insertions(+)

diff --git a/libavutil/avstring.c b/libavutil/avstring.c
index eed58fa..4be88e7 100644
--- a/libavutil/avstring.c
+++ b/libavutil/avstring.c
@@ -307,6 +307,31 @@ int av_isxdigit(int c)
     return av_isdigit(c) || (c >= 'a' && c <= 'f');
 }
 
+int av_get_utf8(int32_t *code, const uint8_t **buf, int flags)
+{
+    const uint8_t *p = *buf;
+    uint32_t top;
+
+    *code = *p++;
+
+    top = (*code & 128) >> 1;
+    if ((*code & 0xc0) == 0x80 || *code >= 0xFE)
+        return AVERROR(EINVAL);
+    *buf = p;
+
+    while (*code & top) {
+        int tmp = *p++ - 128;
+        if (tmp>>6)
+            return AVERROR(EINVAL);
+        *code = (*code<<6) + tmp;
+        top <<= 5;
+    }
+    *code &= (top << 1) - 1;
+
+    *buf = p;
+    return 0;
+}
+
 #ifdef TEST
 
 int main(void)
diff --git a/libavutil/avstring.h b/libavutil/avstring.h
index 438ef79..bd1f722 100644
--- a/libavutil/avstring.h
+++ b/libavutil/avstring.h
@@ -22,6 +22,7 @@
 #define AVUTIL_AVSTRING_H
 
 #include <stddef.h>
+#include <stdint.h>
 #include "attributes.h"
 
 /**
@@ -226,6 +227,15 @@ static inline int av_tolower(int c)
 int av_isxdigit(int c);
 
 /**
+ * Read an UTF-8 character from buffer in *buf, and update *buf to point to the
+ * next sequence after the found character.
+ *
+ * @return >= 0 in case a sequence was successfully read, a negative
+ * value in case of invalid sequence
+ */
+int av_get_utf8(int32_t *code, const uint8_t **buf, int flags);
+
+/**
  * Locale-independent case-insensitive compare.
  * @note This means only ASCII-range characters are case-insensitive
  */
-- 
1.8.1.2