Added utf8_peek()

2 files changed, 12 insertions, 1 deletions

diff --git a/include/stc/utf8.h b/include/stc/utf8.h
index 53d6cf40..b7edd2cb 100644
--- a/include/stc/utf8.h
+++ b/include/stc/utf8.h
@@ -41,6 +41,7 @@ bool        utf8_valid_n(const char* s, size_t n);
 int         utf8_icmp_n(size_t u8max, const char* s1, size_t n1,
                                       const char* s2, size_t n2);
 unsigned    utf8_encode(char *out, uint32_t c);
+uint32_t    utf8_peek(const char *s, int pos);
 
 /* decode next utf8 codepoint. https://bjoern.hoehrmann.de/utf-8/decoder/dfa */
 typedef struct { uint32_t state, codep; } utf8_decode_t;
@@ -90,7 +91,7 @@ STC_INLINE const char* utf8_at(const char *s, size_t index) {
     return s;
 }
 
-STC_INLINE size_t utf8_pos(const char*   s, size_t index)
+STC_INLINE size_t utf8_pos(const char* s, size_t index)
     { return utf8_at(s, index) - s; }
 
 #endif
diff --git a/src/utf8code.c b/src/utf8code.c
index 9613ba95..1c1e4336 100644
--- a/src/utf8code.c
+++ b/src/utf8code.c
@@ -45,6 +45,16 @@ unsigned utf8_encode(char *out, uint32_t c)
     return 0;
 }
 
+uint32_t utf8_peek(const char* s, int pos) {
+    int inc = 1;
+    if (pos < 0) pos = -pos, inc = -1;
+    while (pos)
+        pos -= (*(s += inc) & 0xC0) != 0x80;
+    utf8_decode_t d = {.state=0};
+    do { utf8_decode(&d, (uint8_t)*s++); } while (d.state);
+    return d.codep;
+}
+
 bool utf8_valid(const char* s) {
     utf8_decode_t d = {.state=0};
     while (*s)