Update Lexbor (#16288)

Sync up to lexbor/lexbor@72236d31da.
Reason: pulling in mainly
lexbor/lexbor@cbf1263e78 for the WHATWG
encoding update.

ext/dom/lexbor/lexbor/core/swar.h

@@ -59,6 +59,35 @@ lexbor_swar_seek4(const lxb_char_t *data, const lxb_char_t *end,
     return data;
 }
 
+lxb_inline const lxb_char_t *
+lexbor_swar_seek3(const lxb_char_t *data, const lxb_char_t *end,
+                  lxb_char_t c1, lxb_char_t c2, lxb_char_t c3)
+{
+    size_t bytes, matches, t1, t2, t3;
+
+    if (LEXBOR_SWAR_IS_LITTLE_ENDIAN) {
+        while (data + sizeof(size_t) <= end) {
+            memcpy(&bytes, data, sizeof(size_t));
+
+            t1 = bytes ^ LEXBOR_SWAR_REPEAT(c1);
+            t2 = bytes ^ LEXBOR_SWAR_REPEAT(c2);
+            t3 = bytes ^ LEXBOR_SWAR_REPEAT(c3);
+            matches =   LEXBOR_SWAR_HAS_ZERO(t1) | LEXBOR_SWAR_HAS_ZERO(t2)
+                       | LEXBOR_SWAR_HAS_ZERO(t3);
+
+            if (matches) {
+                data += ((((matches - 1) & LEXBOR_SWAR_ONES) * LEXBOR_SWAR_ONES)
+                         >> (sizeof(size_t) * 8 - 8)) - 1;
+                break;
+            } else {
+                data += sizeof(size_t);
+            }
+        }
+    }
+
+    return data;
+}
+
 
 #ifdef __cplusplus
 } /* extern "C" */

ext/dom/lexbor/lexbor/encoding/big5.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019 Alexander Borisov
+ * Copyright (C) 2024 Alexander Borisov
  *
  * Author: Alexander Borisov <borisov@lexbor.com>
  */

ext/dom/lexbor/lexbor/encoding/decode.c

@@ -2955,6 +2955,77 @@ lxb_encoding_decode_valid_utf_8_single(const lxb_char_t **data,
     return cp;
 }
 
+lxb_codepoint_t
+lxb_encoding_decode_valid_utf_8_single_reverse(const lxb_char_t **end,
+                                               const lxb_char_t *begin)
+{
+    lxb_codepoint_t cp;
+    const lxb_char_t *p = *end;
+
+    while (p > begin) {
+        p -= 1;
+
+        if (*p < 0x80){
+            cp = (lxb_codepoint_t) *p;
+
+            (*end) = p;
+            return cp;
+        }
+        else if ((*p & 0xe0) == 0xc0) {
+            /* 110xxxxx 10xxxxxx */
+
+            if (*end - p < 2) {
+                *end = p;
+                return LXB_ENCODING_DECODE_ERROR;
+            }
+
+            cp  = (p[0] ^ (0xC0 & p[0])) << 6;
+            cp |= (p[1] ^ (0x80 & p[1]));
+
+            (*end) = p;
+            return cp;
+        }
+        else if ((*p & 0xf0) == 0xe0) {
+            /* 1110xxxx 10xxxxxx 10xxxxxx */
+
+            if (*end - p < 3) {
+                *end = p;
+                return LXB_ENCODING_DECODE_ERROR;
+            }
+
+            cp  = (p[0] ^ (0xE0 & p[0])) << 12;
+            cp |= (p[1] ^ (0x80 & p[1])) << 6;
+            cp |= (p[2] ^ (0x80 & p[2]));
+
+            (*end) = p;
+            return cp;
+        }
+        else if ((*p & 0xf8) == 0xf0) {
+            /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
+
+            if (*end - p < 4) {
+                *end = p;
+                return LXB_ENCODING_DECODE_ERROR;
+            }
+
+            cp  = (p[0] ^ (0xF0 & p[0])) << 18;
+            cp |= (p[1] ^ (0x80 & p[1])) << 12;
+            cp |= (p[2] ^ (0x80 & p[2])) << 6;
+            cp |= (p[3] ^ (0x80 & p[3]));
+
+            (*end) = p;
+            return cp;
+        }
+        else if (*end - p >= 4) {
+            break;
+        }
+    }
+
+    *end = p;
+
+    return LXB_ENCODING_DECODE_ERROR;
+}
+
 uint8_t
 lxb_encoding_decode_utf_8_length(lxb_char_t data)
 {

ext/dom/lexbor/lexbor/encoding/decode.h

@@ -306,6 +306,10 @@ LXB_API lxb_codepoint_t
 lxb_encoding_decode_valid_utf_8_single(const lxb_char_t **data,
                                        const lxb_char_t *end);
 
+LXB_API lxb_codepoint_t
+lxb_encoding_decode_valid_utf_8_single_reverse(const lxb_char_t **end,
+                                               const lxb_char_t *begin);
+
 LXB_API uint8_t
 lxb_encoding_decode_utf_8_length(lxb_char_t data);
 

ext/dom/lexbor/lexbor/encoding/euc_kr.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019 Alexander Borisov
+ * Copyright (C) 2024 Alexander Borisov
  *
  * Author: Alexander Borisov <borisov@lexbor.com>
  */

ext/dom/lexbor/lexbor/encoding/iso_2022_jp_katakana.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019 Alexander Borisov
+ * Copyright (C) 2024 Alexander Borisov
  *
  * Author: Alexander Borisov <borisov@lexbor.com>
  */

ext/dom/lexbor/lexbor/encoding/jis0208.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019 Alexander Borisov
+ * Copyright (C) 2024 Alexander Borisov
  *
  * Author: Alexander Borisov <borisov@lexbor.com>
  */

ext/dom/lexbor/lexbor/encoding/jis0212.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019 Alexander Borisov
+ * Copyright (C) 2024 Alexander Borisov
  *
  * Author: Alexander Borisov <borisov@lexbor.com>
  */