C++ IsUTF8函数代码示例

/// get page from network
bool getPage(const char* url, int method, std::string& response)
{
	// Todo : add proxy and authentication support
	response.clear();
	string strurl = url;
	boost::regex regspace(" ");
	strurl = boost::regex_replace(strurl, regspace, "%20");
	HttpWrap *phttpwrap = new HttpWrap();
	response += phttpwrap->Get(strurl.c_str());
	delete phttpwrap;
    phttpwrap = NULL;
	if (response.length() < 200)
	{
		return false;
	} 
	else
	{
		boost::regex regRn("\\r\\n");
		response = boost::regex_replace(response, regRn, "\\n");
		boost::regex reg1("<meta(.*?)charset=(.*?)>",boost::regex::icase); 
		boost::smatch what;
		std::string::const_iterator start = response.begin();
		std::string::const_iterator end1 = response.end();
		if( boost::regex_search(start, end1, what, reg1) )
		{
			string strcharset(what[2].first,what[2].second);
			if((int)strcharset.length() == 0)
			{
				if(!IsUTF8(response.c_str(),response.length()))
				{
					string strtmp = "";
					iconv_string("gbk","utf-8", response.c_str(), response.length(),strtmp,1);
					response = strtmp;

				}
			}
			else 
			{
				if ((int)strcharset.find("UTF") >= 0 || (int)strcharset.find("utf") >= 0)
				{
					;
				} 
				else
				{
					string strtmp = "";
					iconv_string("gbk","utf-8", response.c_str(), response.length(),strtmp,1);
					response = strtmp;
				}
			}
		}
		else if(!IsUTF8(response.c_str(),response.length())/*pSpiderconf->m_config.ruleCollections[pSpiderconf->m_config.plans[m_plan_id].collectionRuleId].charset != "utf-8"*/)
		{
			string strtmp = "";
			iconv_string("gbk","utf-8", response.c_str(), response.length(),strtmp,1);
			response = strtmp;

		}
	}
	return true;
}

NS_IMETHODIMP  
nsUTF8ConverterService::ConvertStringToUTF8(const nsACString &aString, 
                                            const char *aCharset, 
                                            bool aSkipCheck, 
                                            bool aAllowSubstitution,
                                            uint8_t aOptionalArgc,
                                            nsACString &aUTF8String)
{
  bool allowSubstitution = (aOptionalArgc == 1) ? aAllowSubstitution : true;

  // return if ASCII only or valid UTF-8 providing that the ASCII/UTF-8
  // check is requested. It may not be asked for if a caller suspects
  // that the input is in non-ASCII 7bit charset (ISO-2022-xx, HZ) or 
  // it's in a charset other than UTF-8 that can be mistaken for UTF-8.
  if (!aSkipCheck && (IsASCII(aString) || IsUTF8(aString))) {
    aUTF8String = aString;
    return NS_OK;
  }

  aUTF8String.Truncate();

  nsresult rv = ToUTF8(aString, aCharset, allowSubstitution, aUTF8String);

  // additional protection for cases where check is skipped and  the input
  // is actually in UTF-8 as opposed to aCharset. (i.e. caller's hunch
  // was wrong.) We don't check ASCIIness assuming there's no charset
  // incompatible with ASCII (we don't support EBCDIC).
  if (aSkipCheck && NS_FAILED(rv) && IsUTF8(aString)) {
    aUTF8String = aString;
    return NS_OK;
  }

  return rv;
}

	void CWrapper_encoding_isutf8(char **characters, int *numres)
	{
		char* s = *characters;
		int l;
		l = strlen(s);
		*numres = IsUTF8(s,l);
	}

NS_IMETHODIMP  
nsUTF8ConverterService::ConvertURISpecToUTF8(const nsACString &aSpec, 
                                             const char *aCharset, 
                                             nsACString &aUTF8Spec)
{
  // assume UTF-8 if the spec contains unescaped non-ASCII characters.
  // No valid spec in Mozilla would break this assumption.
  if (!IsASCII(aSpec)) {
    aUTF8Spec = aSpec;
    return NS_OK;
  }

  aUTF8Spec.Truncate();

  nsAutoCString unescapedSpec; 
  // NS_UnescapeURL does not fill up unescapedSpec unless there's at least 
  // one character to unescape.
  bool written = NS_UnescapeURL(PromiseFlatCString(aSpec).get(), aSpec.Length(), 
                                  esc_OnlyNonASCII, unescapedSpec);

  if (!written) {
    aUTF8Spec = aSpec;
    return NS_OK;
  }
  // return if ASCII only or escaped UTF-8
  if (IsASCII(unescapedSpec) || IsUTF8(unescapedSpec)) {
    aUTF8Spec = unescapedSpec;
    return NS_OK;
  }

  return ToUTF8(unescapedSpec, aCharset, true, aUTF8Spec);
}

BOOL StrictUTF8(char *s)
{
	char	*invalid_point = NULL;
	if (!IsUTF8(s, NULL, &invalid_point) && invalid_point) {
		*invalid_point = 0;
		return	TRUE;
	}
	return	FALSE;
}

static inline void MaybeFromLocaleRep (char **str)
{
    char *const orig_str = *str;

    if ((orig_str != NULL) && !IsUTF8 (orig_str))
    {
        *str = FromLocaleDup (orig_str);
        free (orig_str);
    }
}

static bool IsSDPString (const char *str)
{
    if (strchr (str, '\r') != NULL)
        return false;
    if (strchr (str, '\n') != NULL)
        return false;
    if (!IsUTF8 (str))
        return false;
    return true;
}

// XXX : aTryLocaleCharset is not yet effective.
nsresult 
nsMIMEHeaderParamImpl::DoGetParameter(const nsACString& aHeaderVal, 
                                      const char *aParamName,
                                      ParamDecoding aDecoding,
                                      const nsACString& aFallbackCharset, 
                                      bool aTryLocaleCharset, 
                                      char **aLang, nsAString& aResult)
{
    aResult.Truncate();
    nsresult rv;

    // get parameter (decode RFC 2231/5987 when applicable, as specified by
    // aDecoding (5987 being a subset of 2231) and return charset.)
    nsXPIDLCString med;
    nsXPIDLCString charset;
    rv = DoParameterInternal(PromiseFlatCString(aHeaderVal).get(), aParamName, 
                             aDecoding, getter_Copies(charset), aLang, 
                             getter_Copies(med));
    if (NS_FAILED(rv))
        return rv; 

    // convert to UTF-8 after charset conversion and RFC 2047 decoding 
    // if necessary.
    
    nsCAutoString str1;
    rv = DecodeParameter(med, charset.get(), nullptr, false, str1);
    NS_ENSURE_SUCCESS(rv, rv);

    if (!aFallbackCharset.IsEmpty())
    {
        nsCAutoString str2;
        nsCOMPtr<nsIUTF8ConverterService> 
          cvtUTF8(do_GetService(NS_UTF8CONVERTERSERVICE_CONTRACTID));
        if (cvtUTF8 &&
            NS_SUCCEEDED(cvtUTF8->ConvertStringToUTF8(str1, 
                PromiseFlatCString(aFallbackCharset).get(), false, true,
                                   1, str2))) {
          CopyUTF8toUTF16(str2, aResult);
          return NS_OK;
        }
    }

    if (IsUTF8(str1)) {
      CopyUTF8toUTF16(str1, aResult);
      return NS_OK;
    }

    if (aTryLocaleCharset && !NS_IsNativeUTF8()) 
      return NS_CopyNativeToUnicode(str1, aResult);

    CopyASCIItoUTF16(str1, aResult);
    return NS_OK;
}

nsresult nsTextToSubURI::convertURItoUnicode(const nsAFlatCString &aCharset,
                                             const nsAFlatCString &aURI, 
                                             bool aIRI, 
                                             nsAString &_retval)
{
  nsresult rv = NS_OK;

  // check for 7bit encoding the data may not be ASCII after we decode
  bool isStatefulCharset = statefulCharset(aCharset.get());

  if (!isStatefulCharset && IsASCII(aURI)) {
    CopyASCIItoUTF16(aURI, _retval);
    return rv;
  }

  if (!isStatefulCharset && aIRI) {
    if (IsUTF8(aURI)) {
      CopyUTF8toUTF16(aURI, _retval);
      return rv;
    }
  }

  // empty charset could indicate UTF-8, but aURI turns out not to be UTF-8.
  NS_ENSURE_FALSE(aCharset.IsEmpty(), NS_ERROR_INVALID_ARG);

  nsCOMPtr<nsICharsetConverterManager> charsetConverterManager;

  charsetConverterManager = do_GetService(NS_CHARSETCONVERTERMANAGER_CONTRACTID, &rv);
  NS_ENSURE_SUCCESS(rv, rv);

  nsCOMPtr<nsIUnicodeDecoder> unicodeDecoder;
  rv = charsetConverterManager->GetUnicodeDecoder(aCharset.get(), 
                                                  getter_AddRefs(unicodeDecoder));
  NS_ENSURE_SUCCESS(rv, rv);
  unicodeDecoder->SetInputErrorBehavior(nsIUnicodeDecoder::kOnError_Signal);

  int32_t srcLen = aURI.Length();
  int32_t dstLen;
  rv = unicodeDecoder->GetMaxLength(aURI.get(), srcLen, &dstLen);
  NS_ENSURE_SUCCESS(rv, rv);

  char16_t *ustr = (char16_t *) NS_Alloc(dstLen * sizeof(char16_t));
  NS_ENSURE_TRUE(ustr, NS_ERROR_OUT_OF_MEMORY);

  rv = unicodeDecoder->Convert(aURI.get(), &srcLen, ustr, &dstLen);

  if (NS_SUCCEEDED(rv))
    _retval.Assign(ustr, dstLen);
  
  NS_Free(ustr);

  return rv;
}

nsresult
net_GetFileFromURLSpec(const nsACString &aURL, nsIFile **result)
{
    // NOTE: See also the implementation in nsURLHelperOSX.cpp,
    // which is based on this.

    nsresult rv;

    nsCOMPtr<nsILocalFile> localFile;
    rv = NS_NewNativeLocalFile(EmptyCString(), PR_TRUE, getter_AddRefs(localFile));
    if (NS_FAILED(rv))
      return rv;
    
    nsCAutoString directory, fileBaseName, fileExtension, path;

    rv = net_ParseFileURL(aURL, directory, fileBaseName, fileExtension);
    if (NS_FAILED(rv)) return rv;

    if (!directory.IsEmpty())
        NS_EscapeURL(directory, esc_Directory|esc_AlwaysCopy, path);
    if (!fileBaseName.IsEmpty())
        NS_EscapeURL(fileBaseName, esc_FileBaseName|esc_AlwaysCopy, path);
    if (!fileExtension.IsEmpty()) {
        path += '.';
        NS_EscapeURL(fileExtension, esc_FileExtension|esc_AlwaysCopy, path);
    }
    
    NS_UnescapeURL(path);
    if (path.Length() != strlen(path.get()))
        return NS_ERROR_FILE_INVALID_PATH;

    if (IsUTF8(path)) {
        // speed up the start-up where UTF-8 is the native charset
        // (e.g. on recent Linux distributions)
        if (NS_IsNativeUTF8())
            rv = localFile->InitWithNativePath(path);
        else
            rv = localFile->InitWithPath(NS_ConvertUTF8toUTF16(path));
            // XXX In rare cases, a valid UTF-8 string can be valid as a native 
            // encoding (e.g. 0xC5 0x83 is valid both as UTF-8 and Windows-125x).
            // However, the chance is very low that a meaningful word in a legacy
            // encoding is valid as UTF-8.
    }
    else 
        // if path is not in UTF-8, assume it is encoded in the native charset
        rv = localFile->InitWithNativePath(path);

    if (NS_FAILED(rv)) return rv;

    NS_ADDREF(*result = localFile);
    return NS_OK;
}

// XXX : aTryLocaleCharset is not yet effective.
NS_IMETHODIMP 
nsMIMEHeaderParamImpl::GetParameter(const nsACString& aHeaderVal, 
                                    const char *aParamName,
                                    const nsACString& aFallbackCharset, 
                                    PRBool aTryLocaleCharset, 
                                    char **aLang, nsAString& aResult)
{
    aResult.Truncate();
    nsresult rv;

    // get parameter (decode RFC 2231 if it's RFC 2231-encoded and 
    // return charset.)
    nsXPIDLCString med;
    nsXPIDLCString charset;
    rv = GetParameterInternal(PromiseFlatCString(aHeaderVal).get(), aParamName, 
                              getter_Copies(charset), aLang, getter_Copies(med));
    if (NS_FAILED(rv))
        return rv; 

    // convert to UTF-8 after charset conversion and RFC 2047 decoding 
    // if necessary.
    
    nsCAutoString str1;
    rv = DecodeParameter(med, charset.get(), nsnull, PR_FALSE, str1);
    NS_ENSURE_SUCCESS(rv, rv);

    if (!aFallbackCharset.IsEmpty())
    {
        nsCAutoString str2;
        nsCOMPtr<nsIUTF8ConverterService> 
          cvtUTF8(do_GetService(NS_UTF8CONVERTERSERVICE_CONTRACTID));
        if (cvtUTF8 &&
            NS_SUCCEEDED(cvtUTF8->ConvertStringToUTF8(str1, 
                PromiseFlatCString(aFallbackCharset).get(), PR_FALSE, str2))) {
          CopyUTF8toUTF16(str2, aResult);
          return NS_OK;
        }
    }

    if (IsUTF8(str1)) {
      CopyUTF8toUTF16(str1, aResult);
      return NS_OK;
    }

    if (aTryLocaleCharset && !NS_IsNativeUTF8()) 
      return NS_CopyNativeToUnicode(str1, aResult);

    CopyASCIItoUTF16(str1, aResult);
    return NS_OK;
}

static void test (const char *in, const char *out)
{
    bool isutf8 = !strcmp (in, out);
    char *str = strdup (in);
    if (str == NULL)
        abort ();

    if (isutf8)
        printf ("\"%s\" should be accepted...\n", in);
    else
        printf ("\"%s\" should be rewritten as \"%s\"...\n", in, out);

    if ((IsUTF8 (in) != NULL) != isutf8)
    {
        printf (" ERROR: IsUTF8 (%s) failed\n", in);
        exit (1);
    }

    if ((EnsureUTF8 (str) != NULL) != isutf8)
    {
        printf (" ERROR: EnsureUTF8 (%s) failed\n", in);
        exit (2);
    }

    if (strcmp (str, out))
    {
        printf (" ERROR: got \"%s\"\n", str);
        exit (3);
    }

    if ((EnsureUTF8 (str) == NULL) || IsUTF8 (str) == NULL)
    {
        printf (" ERROR: EnsureUTF8 (%s) is not UTF-8\n", in);
        exit (4);
    }
    free (str);
}

/* ACString ConvertUTF8toACE (in AUTF8String input); */
NS_IMETHODIMP nsIDNService::ConvertUTF8toACE(const nsACString & input, nsACString & ace)
{
  // protect against bogus input
  NS_ENSURE_TRUE(IsUTF8(input), NS_ERROR_UNEXPECTED);

  nsresult rv;
  NS_ConvertUTF8toUCS2 ustr(input);

  // map ideographic period to ASCII period etc.
  normalizeFullStops(ustr);


  PRUint32 len, offset;
  len = 0;
  offset = 0;
  nsCAutoString encodedBuf;

  nsAString::const_iterator start, end;
  ustr.BeginReading(start); 
  ustr.EndReading(end); 
  ace.Truncate();

  // encode nodes if non ASCII
  while (start != end) {
    len++;
    if (*start++ == (PRUnichar)'.') {
      rv = stringPrepAndACE(Substring(ustr, offset, len - 1), encodedBuf);
      NS_ENSURE_SUCCESS(rv, rv);

      ace.Append(encodedBuf);
      ace.Append('.');
      offset += len;
      len = 0;
    }
  }

  // add extra node for multilingual test bed
  if (mMultilingualTestBed)
    ace.AppendLiteral("mltbd.");
  // encode the last node if non ASCII
  if (len) {
    rv = stringPrepAndACE(Substring(ustr, offset, len), encodedBuf);
    NS_ENSURE_SUCCESS(rv, rv);

    ace.Append(encodedBuf);
  }

  return NS_OK;
}

BOOL Cfg::IniStrToW(char *str, WCHAR *wstr)
{
	int		len = (int)strlen(str) + 1;

	if (needIniConvert && *str == '|') { // old style
		hexstr2bin(str + 1, (BYTE *)wstr, len, &len);
	}
	else {
		if (needIniConvert && !IsUTF8(str)) {
			AtoW(str, wstr, len);
		} else {
			U8toW(str, wstr, len);
		}
	}

	return	TRUE;
}

bool CMainWindow::LoadFile(HANDLE hFile)
{
    InitEditor();
    char data[4096] = { 0 };
    DWORD dwRead = 0;

    BOOL bRet = ReadFile(hFile, data, sizeof(data), &dwRead, NULL);
    bool bUTF8 = IsUTF8(data, dwRead);
    while ((dwRead > 0) && (bRet))
    {
        SendEditor(SCI_ADDTEXT, dwRead,
            reinterpret_cast<LPARAM>(static_cast<char *>(data)));
        bRet = ReadFile(hFile, data, sizeof(data), &dwRead, NULL);
    }
    SetupWindow(bUTF8);
    return true;
}