UefiCpuPkg PiSmmCpuDxeSmm: Update SmiEntry function run the same position

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

/**********************************************************************\r
  utf16_le.c -  Oniguruma (regular expression library)\r
**********************************************************************/\r
/*-\r
 * Copyright (c) 2002-2008  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
 * modification, are permitted provided that the following conditions\r
 * are met:\r
 * 1. Redistributions of source code must retain the above copyright\r
 *    notice, this list of conditions and the following disclaimer.\r
 * 2. Redistributions in binary form must reproduce the above copyright\r
 *    notice, this list of conditions and the following disclaimer in the\r
 *    documentation and/or other materials provided with the distribution.\r
 *\r
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND\r
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\r
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE\r
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE\r
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL\r
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS\r
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)\r
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT\r
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY\r
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF\r
 * SUCH DAMAGE.\r
 */\r
\r
#include "regenc.h"\r
\r
static const int EncLen_UTF16[] = {\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\r
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2\r
};\r
\r
static int\r
utf16le_code_to_mbclen(OnigCodePoint code)\r
{\r
  return (code > 0xffff ? 4 : 2);\r
}\r
\r
static int\r
utf16le_mbc_enc_len(const UChar* p)\r
{\r
  return EncLen_UTF16[*(p+1)];\r
}\r
\r
static int\r
utf16le_is_mbc_newline(const UChar* p, const UChar* end)\r
{\r
  if (p + 1 < end) {\r
    if (*p == 0x0a && *(p+1) == 0x00)\r
      return 1;\r
#ifdef USE_UNICODE_ALL_LINE_TERMINATORS\r
    if ((\r
#ifndef USE_CRNL_AS_LINE_TERMINATOR\r
	 *p == 0x0d ||\r
#endif\r
	 *p == 0x85) && *(p+1) == 0x00)\r
      return 1;\r
    if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28))\r
      return 1;\r
#endif\r
  }\r
  return 0;\r
}\r
\r
static OnigCodePoint\r
utf16le_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)\r
{\r
  OnigCodePoint code;\r
  UChar c0 = *p;\r
  UChar c1 = *(p+1);\r
\r
  if (UTF16_IS_SURROGATE_FIRST(c1)) {\r
    code = ((((c1 - 0xd8) << 2) + ((c0  & 0xc0) >> 6) + 1) << 16)\r
         + ((((c0 & 0x3f) << 2) + (p[3] - 0xdc)) << 8)\r
         + p[2];\r
  }\r
  else {\r
    code = c1 * 256 + p[0];\r
  }\r
  return code;\r
}\r
\r
static int\r
utf16le_code_to_mbc(OnigCodePoint code, UChar *buf)\r
{\r
  UChar* p = buf;\r
\r
  if (code > 0xffff) {\r
    unsigned int plane, high;\r
\r
    plane = (code >> 16) - 1;\r
    high = (code & 0xff00) >> 8;\r
\r
    *p++ = (UChar)(((plane & 0x03) << 6) + (high >> 2));\r
    *p++ = (UChar)((plane >> 2) + 0xd8);\r
    *p++ = (UChar )(code & 0xff);\r
    *p   = (high & 0x03) + 0xdc;\r
    return 4;\r
  }\r
  else {\r
    *p++ = (UChar )(code & 0xff);\r
    *p++ = (UChar )((code & 0xff00) >> 8);\r
    return 2;\r
  }\r
}\r
\r
static int\r
utf16le_mbc_case_fold(OnigCaseFoldType flag,\r
		      const UChar** pp, const UChar* end, UChar* fold)\r
{\r
  const UChar* p = *pp;\r
\r
  if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0) {\r
#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI\r
    if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {\r
      if (*p == 0x49) {\r
	*fold++ = 0x31;\r
	*fold   = 0x01;\r
	(*pp) += 2;\r
	return 2;\r
      }\r
    }\r
#endif\r
\r
    *fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);\r
    *fold   = 0;\r
    *pp += 2;\r
    return 2;\r
  }\r
  else\r
    return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_LE, flag, pp, end,\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
{\r
  const UChar* p = *pp;\r
\r
  (*pp) += EncLen_UTF16[*(p+1)];\r
\r
  if (*(p+1) == 0) {\r
    int c, v;\r
\r
    if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {\r
      return TRUE;\r
    }\r
\r
    c = *p;\r
    v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,\r
                       (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));\r
    if ((v | BIT_CTYPE_LOWER) != 0) {\r
      /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */\r
      if (c >= 0xaa && c <= 0xba)\r
	return FALSE;\r
      else\r
	return TRUE;\r
    }\r
    return (v != 0 ? TRUE : FALSE);\r
  }\r
\r
  return FALSE;\r
}\r
#endif\r
\r
static UChar*\r
utf16le_left_adjust_char_head(const UChar* start, const UChar* s)\r
{\r
  if (s <= start) return (UChar* )s;\r
\r
  if ((s - start) % 2 == 1) {\r
    s--;\r
  }\r
\r
  if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)\r
    s -= 2;\r
\r
  return (UChar* )s;\r
}\r
\r
static int\r
utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,\r
    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
}\r
\r
OnigEncodingType OnigEncodingUTF16_LE = {\r
  utf16le_mbc_enc_len,\r
  "UTF-16LE",   /* name */\r
  4,            /* max byte length */\r
  2,            /* min byte length */\r
  utf16le_is_mbc_newline,\r
  utf16le_mbc_to_code,\r
  utf16le_code_to_mbclen,\r
  utf16le_code_to_mbc,\r
  utf16le_mbc_case_fold,\r
  onigenc_unicode_apply_all_case_fold,\r
  utf16le_get_case_fold_codes_by_str,\r
  onigenc_unicode_property_name_to_ctype,\r
  onigenc_unicode_is_code_ctype,\r
  onigenc_utf16_32_get_ctype_code_range,\r
  utf16le_left_adjust_char_head,\r
  onigenc_always_false_is_allowed_reverse_match\r
};\r