MdeModulePkg RegularExpressionDxe: Update Oniguruma from v6.9.0 to v6.9.3

[mirror_edk2.git] / MdeModulePkg / Universal / RegularExpressionDxe / Oniguruma / utf16_le.c

diff --git a/MdeModulePkg/Universal/RegularExpressionDxe/Oniguruma/utf16_le.c b/MdeModulePkg/Universal/RegularExpressionDxe/Oniguruma/utf16_le.c
index b139f83ff012ab7a739c1e226c35b6f6d301470f..535713852f7d3a72a1c278b8118d3c7e9b4a9158 100644 (file)
--- a/MdeModulePkg/Universal/RegularExpressionDxe/Oniguruma/utf16_le.c
+++ b/MdeModulePkg/Universal/RegularExpressionDxe/Oniguruma/utf16_le.c
@@ -2,7 +2,7 @@
   utf16_le.c -  Oniguruma (regular expression library)\r
 **********************************************************************/\r
 /*-\r
- * Copyright (c) 2002-2018  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>\r
+ * Copyright (c) 2002-2019  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>\r
  * All rights reserved.\r
  *\r
  * Redistribution and use in source and binary forms, with or without\r
@@ -95,7 +95,15 @@ static const int EncLen_UTF16[] = {
 static int\r
 utf16le_code_to_mbclen(OnigCodePoint code)\r
 {\r
-  return (code > 0xffff ? 4 : 2);\r
+  if (code > 0xffff) {\r
+    if (code > 0x10ffff)\r
+      return ONIGERR_INVALID_CODE_POINT_VALUE;\r
+    else\r
+      return 4;\r
+  }\r
+  else {\r
+    return 2;\r
+  }\r
 }\r
 \r
 static int\r
@@ -110,7 +118,16 @@ is_valid_mbc_string(const UChar* p, const UChar* end)
   const UChar* end1 = end - 1;\r
 \r
   while (p < end1) {\r
-    p += utf16le_mbc_enc_len(p);\r
+    int len = utf16le_mbc_enc_len(p);\r
+    if (len == 4) {\r
+      if (p + 3 < end && ! UTF16_IS_SURROGATE_SECOND(*(p + 3)))\r
+        return FALSE;\r
+    }\r
+    else\r
+      if (UTF16_IS_SURROGATE_SECOND(*(p + 1)))\r
+        return FALSE;\r
+\r
+    p += len;\r
   }\r
 \r
   if (p != end)\r
@@ -184,7 +201,7 @@ utf16le_code_to_mbc(OnigCodePoint code, UChar *buf)
 \r
 static int\r
 utf16le_mbc_case_fold(OnigCaseFoldType flag,\r
-                     const UChar** pp, const UChar* end, UChar* fold)\r
+                      const UChar** pp, const UChar* end, UChar* fold)\r
 {\r
   const UChar* p = *pp;\r
 \r
@@ -207,13 +224,13 @@ utf16le_mbc_case_fold(OnigCaseFoldType flag,
   }\r
   else\r
     return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_LE, flag, pp, end,\r
-                                        fold);\r
+                                         fold);\r
 }\r
 \r
 #if 0\r
 static int\r
 utf16le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp,\r
-                        const UChar* end)\r
+                         const UChar* end)\r
 {\r
   const UChar* p = *pp;\r
 \r
@@ -252,7 +269,8 @@ utf16le_left_adjust_char_head(const UChar* start, const UChar* s)
     s--;\r
   }\r
 \r
-  if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)\r
+  if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1 &&\r
+      UTF16_IS_SURROGATE_FIRST(*(s-1)))\r
     s -= 2;\r
 \r
   return (UChar* )s;\r
@@ -263,7 +281,7 @@ utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])\r
 {\r
   return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF16_LE,\r
-                                                   flag, p, end, items);\r
+                                                    flag, p, end, items);\r
 }\r
 \r
 OnigEncodingType OnigEncodingUTF16_LE = {\r
@@ -286,6 +304,6 @@ OnigEncodingType OnigEncodingUTF16_LE = {
   init,\r
   0, /* is_initialized */\r
   is_valid_mbc_string,\r
-  ENC_FLAG_UNICODE,\r
+  ENC_FLAG_UNICODE|ENC_FLAG_SKIP_OFFSET_1,\r
   0, 0\r
 };\r