protected virtual string CleanString(string text, CleanStringType stringType, CultureInfo culture, char?separator)
{
// be safe
if (text == null)
{
throw new ArgumentNullException("text");
}
if (culture == null)
{
throw new ArgumentNullException("culture");
}
// get config
var config = GetConfig(stringType, culture);
stringType = config.StringTypeExtend(stringType);
// apply defaults
if ((stringType & CleanStringType.CaseMask) == CleanStringType.None)
{
stringType |= CleanStringType.CamelCase;
}
if ((stringType & CleanStringType.CodeMask) == CleanStringType.None)
{
stringType |= CleanStringType.Ascii;
}
// use configured unless specified
separator = separator ?? config.Separator;
// apply pre-filter
if (config.PreFilter != null)
{
text = config.PreFilter(text);
}
// apply replacements
//if (config.Replacements != null)
// text = ReplaceMany(text, config.Replacements);
// recode
var codeType = stringType & CleanStringType.CodeMask;
text = codeType == CleanStringType.Ascii
? Utf8ToAsciiConverter.ToAsciiString(text)
: RemoveSurrogatePairs(text);
// clean
text = CleanCodeString(text, stringType, separator.Value, culture, config);
// apply post-filter
if (config.PostFilter != null)
{
text = config.PostFilter(text);
}
return(text);
}
/// <summary>
/// Returns a new string containing only characters within the specified code type.
/// </summary>
/// <param name="text">The string to filter.</param>
/// <param name="stringType">The string type.</param>
/// <returns>The filtered string.</returns>
/// <remarks>If <paramref name="stringType"/> is not <c>Unicode</c> then non-utf8 characters are
/// removed. If it is <c>Ascii</c> we try to do some intelligent replacement of accents, etc.</remarks>
public virtual string Recode(string text, CleanStringType stringType)
{
// be safe
if (text == null)
{
throw new ArgumentNullException("text");
}
var codeType = stringType & CleanStringType.CodeMask;
// unicode to utf8 or ascii: just remove the unicode chars
// utf8 to ascii: try to be clever and replace some chars
// what's the point?
if (codeType == CleanStringType.Unicode)
{
return(text);
}
return(codeType == CleanStringType.Utf8
? RemoveNonUtf8(text)
: Utf8ToAsciiConverter.ToAsciiString(text));
}
protected virtual string CleanString(string text, CleanStringType stringType, string culture, char?separator)
{
// be safe
if (text == null)
{
throw new ArgumentNullException(nameof(text));
}
culture = culture ?? "";
// get config
var config = _config.For(stringType, culture);
stringType = config.StringTypeExtend(stringType);
// apply defaults
if ((stringType & CleanStringType.CaseMask) == CleanStringType.None)
{
stringType |= CleanStringType.CamelCase;
}
if ((stringType & CleanStringType.CodeMask) == CleanStringType.None)
{
stringType |= CleanStringType.Ascii;
}
// use configured unless specified
separator = separator ?? config.Separator;
// apply pre-filter
if (config.PreFilter != null)
{
text = config.PreFilter(text);
}
// apply replacements
//if (config.Replacements != null)
// text = ReplaceMany(text, config.Replacements);
// recode
var codeType = stringType & CleanStringType.CodeMask;
switch (codeType)
{
case CleanStringType.Ascii:
text = Utf8ToAsciiConverter.ToAsciiString(text);
break;
case CleanStringType.TryAscii:
const char ESC = (char)27;
var ctext = Utf8ToAsciiConverter.ToAsciiString(text, ESC);
if (ctext.Contains(ESC) == false)
{
text = ctext;
}
break;
default:
text = RemoveSurrogatePairs(text);
break;
}
// clean
text = CleanCodeString(text, stringType, separator.Value, culture, config);
// apply post-filter
if (config.PostFilter != null)
{
text = config.PostFilter(text);
}
return(text);
}
