/// <summary>
/// Converts input to as close to sentence\ correct case as possible
/// </summary>
/// <param name="input">
/// Free text for case correction
/// </param>
/// <returns>
/// Free text converted to sentence\ correct case
/// </returns>
public string SentenceCase(string input)
{
//Break out if there is not work to do
if (string.IsNullOrEmpty(input))
{
return "";
}
//Array of characters that signal the next character should be capitalised
List<char> lineTerminators = new List<char>(new char[] { '.', ':', '\n', '\r', '!', '?' });
//Indicates if previous character was a lineTerminators
Boolean start = true;
//Indicates that currently parsing personal pronoun contraction (e.g. I'll, 'I'd, I'm etc.)
Boolean personalProNoun = false;
//outputed string
char[] output = new char[input.Length];
//Character previous to current character
char cPrev = new char();
//Character following current character
char cNext;
//Current character
char c;
//Loop through input chars
for (int i = 0; i < input.Length; i++)
{
c = input[i];
cNext = i < (input.Length - 1) ? input[i + 1] : '.';
//current character is always lower case if part of personal pronoun contraction
if (personalProNoun)
{
output[i] = Char.ToLower(c);
start = false;
//Set personalProNoun to false if the next character is not a letter
personalProNoun = Char.IsLetter(cNext);
}
//any non-letter characters are added to output
else if (!Char.IsLetter(c))
{
output[i] = c;
//Line terminators set start boolean to true
if (lineTerminators.Contains(c))
{
start = true;
}
//Numbers count as starting a new sentence, other characters do not
else if (Char.IsNumber(c) && start)
{
start = false;
}
}
//"I" or "i" with no letters either side are assumed to be personal pronoun "I"
else if ((c.Equals('I') || c.Equals('i')) && !Char.IsLetter(cPrev) && !Char.IsLetter(cNext))
{
//Append "I" in upper case
output[i] = Char.ToUpper(c);
start = false;
//If the following character is apostrophe we are starting a personal pronoun contraction
if (cNext.Equals('\''))
{
personalProNoun = true;
}
}
//If the last character was a line terminator then current letter is upper case
else if (start)
{
start = false;
output[i] = Char.ToUpper(c);
}
//Lower case letters are unchanged
else if (Char.IsLower(c))
{
output[i] = c;
start = false;
}
//Only upper case letters remain now
else
{
start = false;
//If this is the start of a se4ntence, add the letter as it is
if (start)
{
output[i] = c;
}
//if there are uppercase letters either side of this letter, convert to lower case
//This allows us to retain the odd upper case character when the freee text is not
//solely made up fo upper case letters
else if (Char.IsUpper(cPrev) || Char.IsUpper(cNext))
{
output[i] = Char.ToLower(c);
}
else
{
output[i] = c;
}
}
cPrev = c;
}
return new string(output);
}
|