summaryrefslogtreecommitdiff
path: root/include/term/unicode/utf8.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/term/unicode/utf8.h')
-rw-r--r--include/term/unicode/utf8.h243
1 files changed, 243 insertions, 0 deletions
diff --git a/include/term/unicode/utf8.h b/include/term/unicode/utf8.h
new file mode 100644
index 0000000..1c3cc3f
--- /dev/null
+++ b/include/term/unicode/utf8.h
@@ -0,0 +1,243 @@
+#ifndef UTF_8_H
+#define UTF_8_H
+
+#include <stdint.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+
+#define UTF8_ACCEPT 0
+#define UTF8_REJECT 1
+
+#define UTF8_3BYTE_MIN 0x800u
+#define UTF8_SURROGATE_LO 0xd800u
+#define UTF8_SURROGATE_HI 0xdfffu
+
+static const uint8_t utf8d[] = {
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
+ 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+ 8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+ 0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3,
+ 0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,
+ 0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1,
+ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1,
+ 1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,
+ 1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1,
+ 1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+};
+
+static inline uint32_t utf8_decode(uint32_t *state, uint32_t *codep, uint32_t byte) {
+ byte &= 0xff;
+ uint32_t type = utf8d[byte];
+
+ *codep = (*state != UTF8_ACCEPT) ?
+ (byte & 0x3fu) | (*codep << 6) :
+ (0xff >> type) & (byte);
+
+ *state = utf8d[256 + *state*16 + type];
+ return *state;
+}
+
+static const uint8_t utf8_acc_state[256] = {
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 5, 3, 3,
+6, 7, 7, 7, 8, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+};
+static const uint8_t utf8_acc_codep[256] = {
+0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
+32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
+48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
+80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
+96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111,
+112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127,
+0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1,
+0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1,
+0, 0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
+0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+0, 1, 2, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+};
+
+/*
+ * Decode one code point at the start of buf and return the bytes it used.
+ * Each maximal invalid subpart gives U+FFFD (Unicode 3.9); the byte that
+ * ends a subpart stays unused, so the caller reads it again. A C0 control
+ * ends an unfinished sequence the same way. An unfinished sequence at the
+ * end of buf gives *cp = 0 and keeps the state.
+ */
+static inline int utf8_decode_ground(uint32_t *state, uint32_t *codep,
+ const char *buf, size_t len, uint32_t *cp) {
+ uint32_t st = *state;
+ uint32_t cpv = *codep;
+ int n = 0;
+ *cp = 0;
+ if (len == 0)
+ return 0;
+ do {
+ unsigned char c = (unsigned char)buf[n];
+ if (c < 0x20) {
+ if (st != UTF8_ACCEPT) *cp = 0xFFFD;
+ st = UTF8_ACCEPT;
+ break;
+ }
+ uint32_t before = st;
+ n++;
+ if (st == UTF8_ACCEPT) {
+ cpv = utf8_acc_codep[c];
+ st = utf8_acc_state[c];
+ } else {
+ uint32_t type = utf8d[c];
+ cpv = (c & 0x3fu) | (cpv << 6);
+ st = utf8d[256 + st*16 + type];
+ }
+ if (st == UTF8_ACCEPT) { *cp = cpv; break; }
+ if (st == UTF8_REJECT) {
+ st = UTF8_ACCEPT;
+ *cp = 0xFFFD;
+ if (before != UTF8_ACCEPT) n--;
+ break;
+ }
+ } while ((size_t)n < len);
+ *state = st;
+ *codep = cpv;
+ return n;
+}
+
+static inline int
+utf8_decode_one(const char *buf, size_t len, uint32_t *codep)
+{
+ const unsigned char *s = (const unsigned char *)buf;
+ unsigned c0, c1, c2, c3;
+ uint32_t cp;
+
+ if (len == 0)
+ return 0;
+ c0 = s[0];
+ if (c0 < 0x80) {
+ *codep = c0;
+ return 1;
+ }
+ if (c0 < 0xc2 || c0 > 0xf4)
+ return 0;
+
+ if (c0 <= 0xdf) {
+ if (len < 2)
+ return 0;
+ c1 = s[1];
+ if ((c1 & 0xc0) != 0x80)
+ return 0;
+ *codep = ((c0 & 0x1f) << 6) | (c1 & 0x3f);
+ return 2;
+ }
+
+ if (c0 <= 0xef) {
+ if (len < 3)
+ return 0;
+ c1 = s[1];
+ c2 = s[2];
+ if ((c1 & 0xc0) != 0x80 || (c2 & 0xc0) != 0x80)
+ return 0;
+ cp = ((c0 & 0x0f) << 12) | ((c1 & 0x3f) << 6) | (c2 & 0x3f);
+ if (cp < UTF8_3BYTE_MIN ||
+ (cp >= UTF8_SURROGATE_LO && cp <= UTF8_SURROGATE_HI))
+ return 0;
+ *codep = cp;
+ return 3;
+ }
+
+ if (len < 4)
+ return 0;
+ c1 = s[1];
+ c2 = s[2];
+ c3 = s[3];
+ if ((c1 & 0xc0) != 0x80 || (c2 & 0xc0) != 0x80 ||
+ (c3 & 0xc0) != 0x80)
+ return 0;
+ cp = ((c0 & 0x07) << 18) | ((c1 & 0x3f) << 12) |
+ ((c2 & 0x3f) << 6) | (c3 & 0x3f);
+ if (cp < 0x10000 || cp > 0x10ffff)
+ return 0;
+ *codep = cp;
+ return 4;
+}
+
+static inline void
+utf8_sanitize(char *dst, size_t cap, const char *src)
+{
+ if (!cap)
+ return;
+ size_t i = 0, len = strlen(src), off = 0;
+ while (off < len && i + 1 < cap) {
+ uint32_t cp;
+ int n = utf8_decode_one(src + off, len - off, &cp);
+ if (n <= 0 || i + (size_t)n >= cap) {
+ off++;
+ continue;
+ }
+ memcpy(dst + i, src + off, (size_t)n);
+ i += (size_t)n;
+ off += (size_t)n;
+ }
+ dst[i] = '\0';
+}
+
+/* A sanitized copy of src. Sanitizing only drops bytes, so the copy is
+ * never longer than src. */
+static inline char *utf8_sanitize_dup(const char *src)
+{
+ size_t cap = strlen(src) + 1;
+ char *dst = malloc(cap);
+ if (dst)
+ utf8_sanitize(dst, cap, src);
+ return dst;
+}
+
+#define UTF8_MAX_BYTES 4
+static inline int utf8_encode(uint32_t cp, char *out)
+{
+ if (cp > 0x10ffff || (cp >= 0xd800 && cp <= 0xdfff))
+ cp = 0xfffd;
+ if (cp < 0x80) {
+ out[0] = (char)cp;
+ return 1;
+ }
+ if (cp < 0x800) {
+ out[0] = (char)(0xc0 | (cp >> 6));
+ out[1] = (char)(0x80 | (cp & 0x3f));
+ return 2;
+ }
+ if (cp < 0x10000) {
+ out[0] = (char)(0xe0 | (cp >> 12));
+ out[1] = (char)(0x80 | ((cp >> 6) & 0x3f));
+ out[2] = (char)(0x80 | (cp & 0x3f));
+ return 3;
+ }
+ out[0] = (char)(0xf0 | (cp >> 18));
+ out[1] = (char)(0x80 | ((cp >> 12) & 0x3f));
+ out[2] = (char)(0x80 | ((cp >> 6) & 0x3f));
+ out[3] = (char)(0x80 | (cp & 0x3f));
+ return 4;
+}
+
+#endif
generated by cgit v1.2.3 (git 2.39.1) at 2026-10-25 02:20:36 +0000