/// <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;
}
}
}
/// <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";
}
}
private bool StripEnding(string[] endings)
{
foreach (string ending in endings)
{
if (Stem.EndsWith(ending))
{
Stem = Stem.Remove(Stem.Length - ending.Length);
return(true);
}
}
return(false);
}
/// <summary>
/// Step 4: Search for the longest among the following suffixes, and, if found and in R2, perform the action indicated.
/// al ance ence er ic able ible ant ement ment ent ism ate iti ous ive ize delete
/// ion delete if preceded by s or t
/// </summary>
internal void StripSuffixStep4()
{
if (EndsWithAndInR2("ement"))
{
Stem = Stem.Remove(Stem.Length - 5);
return;
}
if (EndsWithAndInR2("ance") ||
EndsWithAndInR2("ence") ||
EndsWithAndInR2("able") ||
EndsWithAndInR2("ible") ||
EndsWithAndInR2("ment"))
{
Stem = Stem.Remove(Stem.Length - 4);
return;
}
if (EndsWithAndInR2("ion") &&
(Stem.EndsWith("tion") || Stem.EndsWith("sion")))
{
Stem = Stem.Remove(Stem.Length - 3);
return;
}
if (Stem.EndsWith("ment"))
{
return; //breaking change, but makes the voc.txt parse correctly
}
if (EndsWithAndInR2("ant") ||
EndsWithAndInR2("ent") ||
EndsWithAndInR2("ism") ||
EndsWithAndInR2("ate") ||
EndsWithAndInR2("iti") ||
EndsWithAndInR2("ous") ||
EndsWithAndInR2("ize") ||
EndsWithAndInR2("ive"))
{
Stem = Stem.Remove(Stem.Length - 3);
return;
}
if (EndsWithAndInR2("al") ||
EndsWithAndInR2("er") ||
EndsWithAndInR2("ic")
)
{
Stem = Stem.Remove(Stem.Length - 2);
return;
}
}
/// <summary>
/// Step 5: * Search for the the following suffixes, and, if found, perform the action indicated.
///e delete if in R2, or in R1 and not preceded by a short syllable
/// l delete if in R2 and preceded by l
/// </summary>
internal void StripSuffixStep5()
{
if (EndsWithAndInR2("e") ||
(EndsWithAndInR1("e") && IsShortSyllable(Stem.Length - 3) == false))
{
Stem = Stem.Remove(Stem.Length - 1);
return;
}
if (EndsWithAndInR2("l") &&
Stem.EndsWith("ll"))
{
Stem = Stem.Remove(Stem.Length - 1);
return;
}
}
/// <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;
}
}
private bool EndsWithAndInR2(string suffix)
{
return(Stem.EndsWith(suffix) &&
GetR2().Contains(suffix));
}