/// <summary>
/// Search for the longest among the following suffixes, and perform the action indicated.
/// eed eedly+
/// replace by ee if in R1
/// ed edly+ ing ingly+
/// delete if the preceding word part contains a vowel, and then
/// if the word ends at, bl or iz add e (so luxuriat -> luxuriate), or
/// if the word ends with a double remove the last letter (so hopp -> hop), or
/// if the word is short, add e (so hop -> hope)
/// </summary>
internal void StripSuffixStep1b()
{
// eed eedly+ - replace by ee if in R1
if (Stem.EndsWith("eed") ||
Stem.EndsWith("eedly"))
{
if (EndsWithAndInR1("eed") ||
EndsWithAndInR1("eedly"))
{
if (_r1.Contains(Stem.Length))
{
Stem = Stem.Substring(0, Stem.LastIndexOf("eed")) + "ee";
}
}
return;
}
// ed edly+ ing ingly+ - delete if the preceding word part contains a vowel, and then
if ((Stem.EndsWith("ed") && Stem.IndexOfAny(Vowels, 0, Stem.Length - 2) != -1) ||
(Stem.EndsWith("edly") && Stem.IndexOfAny(Vowels, 0, Stem.Length - 4) != -1) ||
(Stem.EndsWith("ing") && Stem.IndexOfAny(Vowels, 0, Stem.Length - 3) != -1) ||
(Stem.EndsWith("ingly") && Stem.IndexOfAny(Vowels, 0, Stem.Length - 5) != -1))
{
StripEnding(new string[4] {
"ed", "edly", "ing", "ingly"
});
// if the word ends at, bl or iz add e (so luxuriat -> luxuriate), or
if (Stem.EndsWith("at") ||
Stem.EndsWith("bl") ||
Stem.EndsWith("iz"))
{
Stem += "e";
return;
}
// if the word ends with a double remove the last letter (so hopp -> hop), or
string end2chars;
if (Stem.Length >= 2)
{
end2chars = Stem.Substring(Stem.Length - 2, 2);
}
else
{
return;
}
var doubleEndings = new List <string>(DoubleChars);
if (doubleEndings.Contains(end2chars))
{
Stem = Stem.Remove(Stem.Length - 1);
return;
}
// if the word is short, add e (so hop -> hope)
if (IsShortWord())
{
Stem += "e";
return;
}
}
}
private bool IsValidLIEnding()
{
if (Stem.Length > 2)
{
string preLi = Stem.Substring(Stem.Length - 3, 1);
return(ValidLIEnding.Contains(preLi));
}
return(false);
}
/// <summary>
/// replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say)
/// </summary>
internal void ReplaceSuffixStep1c()
{
//replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say)
if (Stem.EndsWith("y", StringComparison.OrdinalIgnoreCase) &&
(Stem.Length > 2) &&
(Stem.IndexOfAny(Vowels, Stem.Length - 2) != Stem.Length - 2))
{
Stem = Stem.Substring(0, Stem.Length - 1) + "i";
}
}
/// <summary>
/// Handle the three forms of closing apostrophe
/// </summary>
internal void StripTrailingApostrophe()
{
if (Stem.EndsWith("'s'"))
{
Stem = Stem.Substring(0, Stem.Length - 3);
return;
}
if (Stem.EndsWith("'s"))
{
Stem = Stem.Substring(0, Stem.Length - 2);
return;
}
if (Stem.EndsWith("'"))
{
Stem = Stem.Substring(0, Stem.Length - 1);
return;
}
}
/// <summary>
/// Search for the longest among the following suffixes, and perform the action indicated.
/// sses
/// replace by ss
///
/// ied+ ies*
/// replace by i if preceded by more than one letter, otherwise by ie (so ties -> tie, cries -> cri)
///
/// s
/// delete if the preceding word part contains a vowel not immediately before the s (so gas and this retain the s, gaps and kiwis lose it)
///
/// us+ ss
/// do nothing
/// </summary>
internal void StripSuffixStep1a()
{
//sses - replace by ss
if (Stem.EndsWith("sses"))
{
Stem = Stem.Substring(0, Stem.Length - 2); //4 to remove sses -2 to re-introduce ss
return;
}
//ied+ ies* - replace by i if preceded by more than one letter, otherwise by ie (so ties -> tie, cries -> cri)
if (Stem.EndsWith("ies") ||
Stem.EndsWith("ied"))
{
if (Stem.Length > 4)
{
Stem = Stem.Substring(0, Stem.Length - 2);
}
else
{
Stem = Stem.Substring(0, Stem.Length - 1);
}
return;
}
//us+ ss - do nothing
if (Stem.EndsWith("us") ||
Stem.EndsWith("ss"))
{
return;
}
//s - delete if the preceding word part contains a vowel not immediately
// before the s (so gas and this retain the s, gaps and kiwis lose it)
if (Stem.EndsWith("s") &&
Stem.Length > 2 &&
Stem.Substring(0, Stem.Length - 2).IndexOfAny(Vowels) > -1)
{
Stem = Stem.Substring(0, Stem.Length - 1);
return;
}
}
/// <summary>
/// Step 2:
///Search for the longest among the following suffixes, and, if found and in R1, perform the action indicated.
///
///tional: replace by tion
///enci: replace by ence
///anci: replace by ance
///abli: replace by able
///entli: replace by ent
///izer ization: replace by ize
///ational ation ator: replace by ate
///alism aliti alli: replace by al
///fulness: replace by ful
///ousli ousness: replace by ous
///iveness iviti: replace by ive
///biliti bli+: replace by ble
///ogi+: replace by og if preceded by l
///fulli+: replace by ful
///lessli+: replace by less
///li+: delete if preceded by a valid li-ending
/// </summary>
internal void ReplaceEndingStep2()
{
//Step 2:
//Search for the longest among the following suffixes, and, if found and in R1, perform the action indicated.
if (EndsWithAndInR1("ational"))
{
//7 ational ation ator: replace by ate
Stem = Stem.Substring(0, Stem.Length - 7) + "ate";
return;
}
;
if (EndsWithAndInR1("fulness"))
{
//7 fulness: replace by ful
Stem = Stem.Substring(0, Stem.Length - 7) + "ful";
return;
}
;
if (EndsWithAndInR1("iveness"))
{
//7 iveness iviti: replace by ive
Stem = Stem.Substring(0, Stem.Length - 7) + "ive";
return;
}
;
if (EndsWithAndInR1("ization"))
{
//7 izer ization: replace by ize
Stem = Stem.Substring(0, Stem.Length - 7) + "ize";
return;
}
;
if (EndsWithAndInR1("ousness"))
{
//7 ousli ousness: replace by ous
Stem = Stem.Substring(0, Stem.Length - 7) + "ous";
return;
}
;
if (EndsWithAndInR1("biliti"))
{
//6 biliti bli+: replace by ble
Stem = Stem.Substring(0, Stem.Length - 6) + "ble";
return;
}
;
if (EndsWithAndInR1("lessli"))
{
//6 lessli+: replace by less
Stem = Stem.Substring(0, Stem.Length - 6) + "less";
return;
}
;
if (EndsWithAndInR1("tional"))
{
//6 tional: replace by tion
Stem = Stem.Substring(0, Stem.Length - 6) + "tion";
return;
}
;
if (EndsWithAndInR1("alism"))
{
//5 alism aliti alli: replace by al
Stem = Stem.Substring(0, Stem.Length - 5) + "al";
return;
}
;
if (EndsWithAndInR1("aliti"))
{
//5 alism aliti alli: replace by al
Stem = Stem.Substring(0, Stem.Length - 5) + "al";
return;
}
;
if (EndsWithAndInR1("ation"))
{
//5 ational ation ator: replace by ate
Stem = Stem.Substring(0, Stem.Length - 5) + "ate";
return;
}
;
if (EndsWithAndInR1("entli"))
{
//5 entli: replace by ent
Stem = Stem.Substring(0, Stem.Length - 5) + "ent";
return;
}
;
if (EndsWithAndInR1("fulli"))
{
//5 fulli+: replace by ful
Stem = Stem.Substring(0, Stem.Length - 5) + "ful";
return;
}
;
if (EndsWithAndInR1("iviti"))
{
//5 iveness iviti: replace by ive
Stem = Stem.Substring(0, Stem.Length - 5) + "ive";
return;
}
;
if (EndsWithAndInR1("ousli"))
{
//5 ousli ousness: replace by ous
Stem = Stem.Substring(0, Stem.Length - 5) + "ous";
return;
}
;
if (EndsWithAndInR1("abli"))
{
//4 abli: replace by able
Stem = Stem.Substring(0, Stem.Length - 4) + "able";
return;
}
;
if (EndsWithAndInR1("alli"))
{
//4 alism aliti alli: replace by al
Stem = Stem.Substring(0, Stem.Length - 4) + "al";
return;
}
;
if (EndsWithAndInR1("anci"))
{
//4 anci: replace by ance
Stem = Stem.Substring(0, Stem.Length - 4) + "ance";
return;
}
;
if (EndsWithAndInR1("ator"))
{
//5 ational ation ator: replace by ate
Stem = Stem.Substring(0, Stem.Length - 4) + "ate";
return;
}
;
if (EndsWithAndInR1("enci"))
{
//4 enci: replace by ence
Stem = Stem.Substring(0, Stem.Length - 4) + "ence";
return;
}
;
if (EndsWithAndInR1("izer"))
{
//4 izer ization: replace by ize
Stem = Stem.Substring(0, Stem.Length - 4) + "ize";
return;
}
;
if (EndsWithAndInR1("bli"))
{
//3 biliti bli+: replace by ble
Stem = Stem.Substring(0, Stem.Length - 3) + "ble";
return;
}
;
if (EndsWithAndInR1("ogi"))
{
//3 ogi+: replace by og if preceded by l
Stem = Stem.Substring(0, Stem.Length - 3) + "og";
return;
}
;
if (EndsWithAndInR1("li") &&
IsValidLIEnding())
{
//2 li+: delete if preceded by a valid li-ending
Stem = Stem.Substring(0, Stem.Length - 2);
return;
}
;
}
/// <summary>
/// Step 3:
///Search for the longest among the following suffixes, and, if found and in R1, perform the action indicated.
///
///tional+: replace by tion
///ational+: replace by ate
///alize: replace by al
///icate iciti ical: replace by ic
///ful ness: delete
///ative*: delete if in R2
/// </summary>
internal void ReplaceEndingStep3()
{
//ational+: replace by ate
if (EndsWithAndInR1("ational"))
{
Stem = Stem.Substring(0, Stem.Length - 5) + "e";
return;
}
;
//tional+: replace by tion
if (EndsWithAndInR1("tional"))
{
Stem = Stem.Substring(0, Stem.Length - 2);
return;
}
;
//alize: replace by al
if (EndsWithAndInR1("alize"))
{
Stem = Stem.Substring(0, Stem.Length - 3);
return;
}
;
//ative*: delete if in R2
if (EndsWithAndInR2("ative"))
{
Stem = Stem.Substring(0, Stem.Length - 5);
return;
}
;
//icate : replace by ic
//iciti : replace by ic
if (EndsWithAndInR1("icate") || EndsWithAndInR1("iciti"))
{
Stem = Stem.Substring(0, Stem.Length - 3);
return;
}
;
//ical: replace by ic
if (EndsWithAndInR1("ical"))
{
Stem = Stem.Substring(0, Stem.Length - 2);
return;
}
;
// ness: delete
if (EndsWithAndInR1("ness"))
{
Stem = Stem.Substring(0, Stem.Length - 4);
return;
}
;
//ful : delete
if (EndsWithAndInR1("ful"))
{
Stem = Stem.Substring(0, Stem.Length - 3);
return;
}
;
}